wait for successful connection before setting up db

* Specify macro_namespace of global_project dispatch macros

* Dispatch get_custom_alias, too

* Add integration tests

* Add changelog entry

.bumpversion.cfg

@@ -1,23 +1,27 @@
 [bumpversion]
-current_version = 0.19.0
+current_version = 0.21.0b1
 parse = (?P<major>\d+)
 	\.(?P<minor>\d+)
 	\.(?P<patch>\d+)
-	((?P<prerelease>[a-z]+)(?P<num>\d+))?
-serialize =
-	{major}.{minor}.{patch}{prerelease}{num}
+	((?P<prekind>a|b|rc)
+	(?P<pre>\d+)  # pre-release version num
+	)?
+serialize = 
+	{major}.{minor}.{patch}{prekind}{pre}
 	{major}.{minor}.{patch}
 commit = False
 tag = False
 
-[bumpversion:part:prerelease]
+[bumpversion:part:prekind]
 first_value = a
-values =
+optional_value = final
+values = 
 	a
 	b
 	rc
+	final
 
-[bumpversion:part:num]
+[bumpversion:part:pre]
 first_value = 1
 
 [bumpversion:file:setup.py]
@@ -26,6 +30,8 @@ first_value = 1
 
 [bumpversion:file:core/dbt/version.py]
 
+[bumpversion:file:core/scripts/create_adapter_plugins.py]
+
 [bumpversion:file:plugins/postgres/setup.py]
 
 [bumpversion:file:plugins/redshift/setup.py]
@@ -41,3 +47,4 @@ first_value = 1
 [bumpversion:file:plugins/snowflake/dbt/adapters/snowflake/__version__.py]
 
 [bumpversion:file:plugins/bigquery/dbt/adapters/bigquery/__version__.py]
+

.circleci/config.yml

@@ -1,218 +0,0 @@
-version: 2.1
-jobs:
-  unit:
-    docker: &test_only
-      - image: fishtownanalytics/test-container:9
-        environment:
-          DBT_INVOCATION_ENV: circle
-    steps:
-      - checkout
-      - run: tox -e flake8,mypy,unit-py36,unit-py38
-  build-wheels:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Build wheels
-          command: |
-            python3.8 -m venv "${PYTHON_ENV}"
-            export PYTHON_BIN="${PYTHON_ENV}/bin/python"
-            $PYTHON_BIN -m pip install -U pip setuptools
-            $PYTHON_BIN -m pip install -r requirements.txt
-            $PYTHON_BIN -m pip install -r dev_requirements.txt
-            /bin/bash ./scripts/build-wheels.sh
-            $PYTHON_BIN ./scripts/collect-dbt-contexts.py > ./dist/context_metadata.json
-            $PYTHON_BIN ./scripts/collect-artifact-schema.py > ./dist/artifact_schemas.json
-          environment:
-            PYTHON_ENV: /home/tox/build_venv/
-      - store_artifacts:
-          path: ./dist
-          destination: dist
-  integration-postgres-py36:
-    docker: &test_and_postgres
-      - image: fishtownanalytics/test-container:9
-        environment:
-          DBT_INVOCATION_ENV: circle
-      - image: postgres
-        name: database
-        environment: &pgenv
-          POSTGRES_USER: "root"
-          POSTGRES_PASSWORD: "password"
-          POSTGRES_DB: "dbt"
-    steps:
-      - checkout
-      - run: &setupdb
-          name: Setup postgres
-          command: bash test/setup_db.sh
-          environment:
-            PGHOST: database
-            PGUSER: root
-            PGPASSWORD: password
-            PGDATABASE: postgres
-      - run:
-          name: Run tests
-          command: tox -e integration-postgres-py36
-      - store_artifacts:
-          path: ./logs
-  integration-snowflake-py36:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-snowflake-py36
-          no_output_timeout: 1h
-      - store_artifacts:
-          path: ./logs
-  integration-redshift-py36:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-redshift-py36
-      - store_artifacts:
-          path: ./logs
-  integration-bigquery-py36:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-bigquery-py36
-      - store_artifacts:
-          path: ./logs
-  integration-postgres-py38:
-    docker: *test_and_postgres
-    steps:
-      - checkout
-      - run: *setupdb
-      - run:
-          name: Run tests
-          command: tox -e integration-postgres-py38
-      - store_artifacts:
-          path: ./logs
-  integration-snowflake-py38:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-snowflake-py38
-          no_output_timeout: 1h
-      - store_artifacts:
-          path: ./logs
-  integration-redshift-py38:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-redshift-py38
-      - store_artifacts:
-          path: ./logs
-  integration-bigquery-py38:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-bigquery-py38
-      - store_artifacts:
-          path: ./logs
-
-  integration-postgres-py39:
-    docker: *test_and_postgres
-    steps:
-      - checkout
-      - run: *setupdb
-      - run:
-          name: Run tests
-          command: tox -e integration-postgres-py39
-      - store_artifacts:
-          path: ./logs
-  integration-snowflake-py39:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-snowflake-py39
-          no_output_timeout: 1h
-      - store_artifacts:
-          path: ./logs
-  integration-redshift-py39:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-redshift-py39
-      - store_artifacts:
-          path: ./logs
-  integration-bigquery-py39:
-    docker: *test_only
-    steps:
-      - checkout
-      - run:
-          name: Run tests
-          command: tox -e integration-bigquery-py39
-      - store_artifacts:
-          path: ./logs
-
-workflows:
-  version: 2
-  test-everything:
-    jobs:
-      - unit
-      - integration-postgres-py36:
-          requires:
-            - unit
-      - integration-redshift-py36:
-          requires:
-            - integration-postgres-py36
-      - integration-bigquery-py36:
-          requires:
-            - integration-postgres-py36
-      - integration-snowflake-py36:
-          requires:
-            - integration-postgres-py36
-      - integration-postgres-py38:
-          requires:
-            - unit
-      - integration-redshift-py38:
-          requires:
-            - integration-postgres-py38
-      - integration-bigquery-py38:
-          requires:
-            - integration-postgres-py38
-      - integration-snowflake-py38:
-          requires:
-            - integration-postgres-py38
-      - integration-postgres-py39:
-          requires:
-            - unit
-      - integration-redshift-py39:
-          requires:
-            - integration-postgres-py39
-      - integration-bigquery-py39:
-          requires:
-            - integration-postgres-py39
-      # - integration-snowflake-py39:
-      #     requires:
-      #       - integration-postgres-py39
-      - build-wheels:
-          requires:
-            - unit
-            - integration-postgres-py36
-            - integration-redshift-py36
-            - integration-bigquery-py36
-            - integration-snowflake-py36
-            - integration-postgres-py38
-            - integration-redshift-py38
-            - integration-bigquery-py38
-            - integration-snowflake-py38
-            - integration-postgres-py39
-            - integration-redshift-py39
-            - integration-bigquery-py39
-            # - integration-snowflake-py39

.github/ISSUE_TEMPLATE/beta-minor-version-release.md

@@ -0,0 +1,27 @@
+---
+name: Beta minor version release
+about: Creates a tracking checklist of items for a Beta minor version release
+title: "[Tracking] v#.##.#B# release "
+labels: 'release'
+assignees: ''
+
+---
+
+### Release Core
+- [ ] [Engineering] Follow [dbt-release workflow](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#03ff37da697d4d8ba63d24fae1bfa817) 
+- [ ] [Engineering] Verify new release branch is created in the repo
+- [ ] [Product] Finalize migration guide (next.docs.getdbt.com)
+
+### Release Cloud
+- [ ] [Engineering] Create a platform issue to update dbt Cloud and verify it is completed. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
+- [ ] [Engineering] Determine if schemas have changed. If so, generate new schemas and push to schemas.getdbt.com
+
+### Announce
+- [ ] [Product] Announce in dbt Slack
+
+### Post-release
+- [ ] [Engineering] [Bump plugin versions](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#f01854e8da3641179fbcbe505bdf515c) (dbt-spark + dbt-presto), add compatibility as needed
+   - [ ]  [Spark](https://github.com/dbt-labs/dbt-spark) 
+   - [ ]  [Presto](https://github.com/dbt-labs/dbt-presto)
+- [ ] [Engineering] Create a platform issue to update dbt-spark versions to dbt Cloud. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
+- [ ] [Engineering] Create an epic for the RC release

.github/ISSUE_TEMPLATE/final-minor-version-release.md

@@ -0,0 +1,28 @@
+---
+name: Final minor version release
+about: Creates a tracking checklist of items for a final minor version release
+title: "[Tracking] v#.##.# final release "
+labels: 'release'
+assignees: ''
+
+---
+
+### Release Core
+- [ ] [Engineering] Verify all necessary changes exist on the release branch
+- [ ] [Engineering] Follow [dbt-release workflow](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#03ff37da697d4d8ba63d24fae1bfa817) 
+- [ ] [Product] Merge `next` into `current` for docs.getdbt.com
+
+### Release Cloud
+- [ ] [Engineering] Create a platform issue to update dbt Cloud and verify it is completed. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
+- [ ] [Engineering] Determine if schemas have changed. If so, generate new schemas and push to schemas.getdbt.com
+
+### Announce
+- [ ] [Product] Update discourse
+- [ ] [Product] Announce in dbt Slack
+
+### Post-release
+- [ ] [Engineering] [Bump plugin versions](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#f01854e8da3641179fbcbe505bdf515c) (dbt-spark + dbt-presto), add compatibility as needed
+   - [ ]  [Spark](https://github.com/dbt-labs/dbt-spark) 
+   - [ ]  [Presto](https://github.com/dbt-labs/dbt-presto)
+- [ ] [Engineering] Create a platform issue to update dbt-spark versions to dbt Cloud. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
+- [ ] [Product] Release new version of dbt-utils with new dbt version compatibility. If there are breaking changes requiring a minor version, plan upgrades of other packages that depend on dbt-utils.

.github/ISSUE_TEMPLATE/rc-minor-version-release copy.md

@@ -0,0 +1,29 @@
+---
+name: RC minor version release
+about: Creates a tracking checklist of items for a RC minor version release
+title: "[Tracking] v#.##.#RC# release "
+labels: 'release'
+assignees: ''
+
+---
+
+### Release Core
+- [ ] [Engineering] Verify all necessary changes exist on the release branch
+- [ ] [Engineering] Follow [dbt-release workflow](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#03ff37da697d4d8ba63d24fae1bfa817) 
+- [ ] [Product] Update migration guide (next.docs.getdbt.com)
+
+### Release Cloud
+- [ ] [Engineering] Create a platform issue to update dbt Cloud and verify it is completed. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
+- [ ] [Engineering] Determine if schemas have changed. If so, generate new schemas and push to schemas.getdbt.com
+
+### Announce
+- [ ] [Product] Publish discourse
+- [ ] [Product] Announce in dbt Slack
+
+### Post-release
+- [ ] [Engineering] [Bump plugin versions](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#f01854e8da3641179fbcbe505bdf515c) (dbt-spark + dbt-presto), add compatibility as needed
+   - [ ]  [Spark](https://github.com/dbt-labs/dbt-spark) 
+   - [ ]  [Presto](https://github.com/dbt-labs/dbt-presto)
+- [ ] [Engineering] Create a platform issue to update dbt-spark versions to dbt Cloud. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
+- [ ] [Product] Release new version of dbt-utils with new dbt version compatibility. If there are breaking changes requiring a minor version, plan upgrades of other packages that depend on dbt-utils.
+- [ ] [Engineering] Create an epic for the final release

.github/actions/setup-postgres-linux/action.yml

@@ -0,0 +1,10 @@
+name: "Set up postgres (linux)"
+description: "Set up postgres service on linux vm for dbt integration tests"
+runs:
+  using: "composite"
+  steps:
+    - shell: bash
+      run: |
+        sudo systemctl start postgresql.service
+        pg_isready
+        sudo -u postgres bash ${{ github.action_path }}/setup_db.sh

.github/actions/setup-postgres-linux/setup_db.sh

@@ -0,0 +1 @@
+../../../test/setup_db.sh

.github/actions/setup-postgres-macos/action.yml

@@ -0,0 +1,24 @@
+name: "Set up postgres (macos)"
+description: "Set up postgres service on macos vm for dbt integration tests"
+runs:
+  using: "composite"
+  steps:
+    - shell: bash
+      run: |
+        brew services start postgresql
+        echo "Check PostgreSQL service is running"
+        i=10
+        COMMAND='pg_isready'
+        while [ $i -gt -1 ]; do
+            if [ $i == 0 ]; then
+                echo "PostgreSQL service not ready, all attempts exhausted"
+                exit 1
+            fi
+            echo "Check PostgreSQL service status"
+            eval $COMMAND && break
+            echo "PostgreSQL service not ready, wait 10 more sec, attempts left: $i"
+            sleep 10
+            ((i--))
+        done
+        createuser -s postgres
+        bash ${{ github.action_path }}/setup_db.sh

.github/actions/setup-postgres-macos/setup_db.sh

@@ -0,0 +1 @@
+../../../test/setup_db.sh

.github/actions/setup-postgres-windows/action.yml

@@ -0,0 +1,12 @@
+name: "Set up postgres (windows)"
+description: "Set up postgres service on windows vm for dbt integration tests"
+runs:
+  using: "composite"
+  steps:
+    - shell: pwsh
+      run: |
+        $pgService = Get-Service -Name postgresql*
+        Set-Service -InputObject $pgService -Status running -StartupType automatic
+        Start-Process -FilePath "$env:PGBIN\pg_isready" -Wait -PassThru
+        $env:Path += ";$env:PGBIN"
+        bash ${{ github.action_path }}/setup_db.sh

.github/actions/setup-postgres-windows/setup_db.sh

@@ -0,0 +1 @@
+../../../test/setup_db.sh

.github/pull_request_template.md

@@ -9,14 +9,13 @@ resolves #
     resolves #1234
 -->
 
-
 ### Description
 
 <!--- Describe the Pull Request here -->
 
-
 ### Checklist
- - [ ] I have signed the [CLA](https://docs.getdbt.com/docs/contributor-license-agreements)
- - [ ] I have run this code in development and it appears to resolve the stated issue
- - [ ] This PR includes tests, or tests are not required/relevant for this PR
- - [ ] I have updated the `CHANGELOG.md` and added information about my change to the "dbt next" section.
+
+- [ ] I have signed the [CLA](https://docs.getdbt.com/docs/contributor-license-agreements)
+- [ ] I have run this code in development and it appears to resolve the stated issue
+- [ ] This PR includes tests, or tests are not required/relevant for this PR
+- [ ] I have updated the `CHANGELOG.md` and added information about my change to the "dbt next" section.

.github/scripts/integration-test-matrix.js

@@ -0,0 +1,95 @@
+module.exports = ({ context }) => {
+  const defaultPythonVersion = "3.8";
+  const supportedPythonVersions = ["3.6", "3.7", "3.8", "3.9"];
+  const supportedAdapters = ["snowflake", "postgres", "bigquery", "redshift"];
+
+  // if PR, generate matrix based on files changed and PR labels
+  if (context.eventName.includes("pull_request")) {
+    // `changes` is a list of adapter names that have related
+    // file changes in the PR
+    // ex: ['postgres', 'snowflake']
+    const changes = JSON.parse(process.env.CHANGES);
+    const labels = context.payload.pull_request.labels.map(({ name }) => name);
+    console.log("labels", labels);
+    console.log("changes", changes);
+    const testAllLabel = labels.includes("test all");
+    const include = [];
+
+    for (const adapter of supportedAdapters) {
+      if (
+        changes.includes(adapter) ||
+        testAllLabel ||
+        labels.includes(`test ${adapter}`)
+      ) {
+        for (const pythonVersion of supportedPythonVersions) {
+          if (
+            pythonVersion === defaultPythonVersion ||
+            labels.includes(`test python${pythonVersion}`) ||
+            testAllLabel
+          ) {
+            // always run tests on ubuntu by default
+            include.push({
+              os: "ubuntu-latest",
+              adapter,
+              "python-version": pythonVersion,
+            });
+
+            if (labels.includes("test windows") || testAllLabel) {
+              include.push({
+                os: "windows-latest",
+                adapter,
+                "python-version": pythonVersion,
+              });
+            }
+
+            if (labels.includes("test macos") || testAllLabel) {
+              include.push({
+                os: "macos-latest",
+                adapter,
+                "python-version": pythonVersion,
+              });
+            }
+          }
+        }
+      }
+    }
+
+    console.log("matrix", { include });
+
+    return {
+      include,
+    };
+  }
+  // if not PR, generate matrix of python version, adapter, and operating
+  // system to run integration tests on
+
+  const include = [];
+  // run for all adapters and python versions on ubuntu
+  for (const adapter of supportedAdapters) {
+    for (const pythonVersion of supportedPythonVersions) {
+      include.push({
+        os: 'ubuntu-latest',
+        adapter: adapter,
+        "python-version": pythonVersion,
+      });
+    }
+  }
+
+  // additionally include runs for all adapters, on macos and windows,
+  // but only for the default python version
+  for (const adapter of supportedAdapters) {
+    for (const operatingSystem of ["windows-latest", "macos-latest"]) {
+      include.push({
+        os: operatingSystem,
+        adapter: adapter,
+        "python-version": defaultPythonVersion,
+      });
+    }
+  }
+
+  console.log("matrix", { include });
+
+  return {
+    include,
+  };
+};

.github/workflows/integration.yml

@@ -0,0 +1,266 @@
+# **what?**
+# This workflow runs all integration tests for supported OS
+# and python versions and core adapters. If triggered by PR,
+# the workflow will only run tests for adapters related
+# to code changes. Use the `test all` and `test ${adapter}`
+# label to run all or additional tests. Use `ok to test`
+# label to mark PRs from forked repositories that are safe
+# to run integration tests for. Requires secrets to run
+# against different warehouses.
+
+# **why?**
+# This checks the functionality of dbt from a user's perspective
+# and attempts to catch functional regressions.
+
+# **when?**
+# This workflow will run on every push to a protected branch
+# and when manually triggered. It will also run for all PRs, including
+# PRs from forks. The workflow will be skipped until there is a label
+# to mark the PR as safe to run.
+
+name: Adapter Integration Tests
+
+on:
+  # pushes to release branches
+  push:
+    branches:
+      - "main"
+      - "develop"
+      - "*.latest"
+      - "releases/*"
+  # all PRs, important to note that `pull_request_target` workflows
+  # will run in the context of the target branch of a PR
+  pull_request_target:
+  # manual tigger
+  workflow_dispatch:
+
+# explicitly turn off permissions for `GITHUB_TOKEN`
+permissions: read-all
+
+# will cancel previous workflows triggered by the same event and for the same ref for PRs or same SHA otherwise
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event_name }}-${{ contains(github.event_name, 'pull_request') && github.event.pull_request.head.ref || github.sha }}
+  cancel-in-progress: true
+
+# sets default shell to bash, for all operating systems
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  # generate test metadata about what files changed and the testing matrix to use
+  test-metadata:
+    # run if not a PR from a forked repository or has a label to mark as safe to test
+    if: >-
+      github.event_name != 'pull_request_target' ||
+      github.event.pull_request.head.repo.full_name == github.repository ||
+      contains(github.event.pull_request.labels.*.name, 'ok to test')
+
+    runs-on: ubuntu-latest
+
+    outputs:
+      matrix: ${{ steps.generate-matrix.outputs.result }}
+
+    steps:
+      - name: Check out the repository (non-PR)
+        if: github.event_name != 'pull_request_target'
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+
+      - name: Check out the repository (PR)
+        if: github.event_name == 'pull_request_target'
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Check if relevant files changed
+        # https://github.com/marketplace/actions/paths-changes-filter
+        # For each filter, it sets output variable named by the filter to the text:
+        #  'true' - if any of changed files matches any of filter rules
+        #  'false' - if none of changed files matches any of filter rules
+        # also, returns:
+        #  `changes` - JSON array with names of all filters matching any of the changed files
+        uses: dorny/paths-filter@v2
+        id: get-changes
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          filters: |
+            postgres:
+              - 'core/**'
+              - 'plugins/postgres/**'
+              - 'dev-requirements.txt'
+            snowflake:
+              - 'core/**'
+              - 'plugins/snowflake/**'
+            bigquery:
+              - 'core/**'
+              - 'plugins/bigquery/**'
+            redshift:
+              - 'core/**'
+              - 'plugins/redshift/**'
+              - 'plugins/postgres/**'
+
+      - name: Generate integration test matrix
+        id: generate-matrix
+        uses: actions/github-script@v4
+        env:
+          CHANGES: ${{ steps.get-changes.outputs.changes }}
+        with:
+          script: |
+            const script = require('./.github/scripts/integration-test-matrix.js')
+            const matrix = script({ context })
+            console.log(matrix)
+            return matrix
+
+  test:
+    name: ${{ matrix.adapter }} / python ${{ matrix.python-version }} / ${{ matrix.os }}
+
+    # run if not a PR from a forked repository or has a label to mark as safe to test
+    # also checks that the matrix generated is not empty
+    if: >-
+      needs.test-metadata.outputs.matrix &&
+      fromJSON( needs.test-metadata.outputs.matrix ).include[0] &&
+      (
+        github.event_name != 'pull_request_target' ||
+        github.event.pull_request.head.repo.full_name == github.repository ||
+        contains(github.event.pull_request.labels.*.name, 'ok to test')
+      )
+
+    runs-on: ${{ matrix.os }}
+
+    needs: test-metadata
+
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.test-metadata.outputs.matrix) }}
+
+    env:
+      TOXENV: integration-${{ matrix.adapter }}
+      PYTEST_ADDOPTS: "-v --color=yes -n4 --csv integration_results.csv"
+      DBT_INVOCATION_ENV: github-actions
+
+    steps:
+      - name: Check out the repository
+        if: github.event_name != 'pull_request_target'
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+
+      # explicity checkout the branch for the PR,
+      # this is necessary for the `pull_request_target` event
+      - name: Check out the repository (PR)
+        if: github.event_name == 'pull_request_target'
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Set up postgres (linux)
+        if: |
+          matrix.adapter == 'postgres' &&
+          runner.os == 'Linux'
+        uses: ./.github/actions/setup-postgres-linux
+
+      - name: Set up postgres (macos)
+        if: |
+          matrix.adapter == 'postgres' &&
+          runner.os == 'macOS'
+        uses: ./.github/actions/setup-postgres-macos
+
+      - name: Set up postgres (windows)
+        if: |
+          matrix.adapter == 'postgres' &&
+          runner.os == 'Windows'
+        uses: ./.github/actions/setup-postgres-windows
+
+      - name: Install python dependencies
+        run: |
+          pip install --upgrade pip
+          pip install tox
+          pip --version
+          tox --version
+
+      - name: Run tox (postgres)
+        if: matrix.adapter == 'postgres'
+        run: tox
+
+      - name: Run tox (redshift)
+        if: matrix.adapter == 'redshift'
+        env:
+          REDSHIFT_TEST_DBNAME: ${{ secrets.REDSHIFT_TEST_DBNAME }}
+          REDSHIFT_TEST_PASS: ${{ secrets.REDSHIFT_TEST_PASS }}
+          REDSHIFT_TEST_USER: ${{ secrets.REDSHIFT_TEST_USER }}
+          REDSHIFT_TEST_PORT: ${{ secrets.REDSHIFT_TEST_PORT }}
+          REDSHIFT_TEST_HOST: ${{ secrets.REDSHIFT_TEST_HOST }}
+        run: tox
+
+      - name: Run tox (snowflake)
+        if: matrix.adapter == 'snowflake'
+        env:
+          SNOWFLAKE_TEST_ACCOUNT: ${{ secrets.SNOWFLAKE_TEST_ACCOUNT }}
+          SNOWFLAKE_TEST_PASSWORD: ${{ secrets.SNOWFLAKE_TEST_PASSWORD }}
+          SNOWFLAKE_TEST_USER: ${{ secrets.SNOWFLAKE_TEST_USER }}
+          SNOWFLAKE_TEST_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_WAREHOUSE }}
+          SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN: ${{ secrets.SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN }}
+          SNOWFLAKE_TEST_OAUTH_CLIENT_ID: ${{ secrets.SNOWFLAKE_TEST_OAUTH_CLIENT_ID }}
+          SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET: ${{ secrets.SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET }}
+          SNOWFLAKE_TEST_ALT_DATABASE: ${{ secrets.SNOWFLAKE_TEST_ALT_DATABASE }}
+          SNOWFLAKE_TEST_ALT_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_ALT_WAREHOUSE }}
+          SNOWFLAKE_TEST_DATABASE: ${{ secrets.SNOWFLAKE_TEST_DATABASE }}
+          SNOWFLAKE_TEST_QUOTED_DATABASE: ${{ secrets.SNOWFLAKE_TEST_QUOTED_DATABASE }}
+          SNOWFLAKE_TEST_ROLE: ${{ secrets.SNOWFLAKE_TEST_ROLE }}
+        run: tox
+
+      - name: Run tox (bigquery)
+        if: matrix.adapter == 'bigquery'
+        env:
+          BIGQUERY_TEST_SERVICE_ACCOUNT_JSON: ${{ secrets.BIGQUERY_TEST_SERVICE_ACCOUNT_JSON }}
+          BIGQUERY_TEST_ALT_DATABASE: ${{ secrets.BIGQUERY_TEST_ALT_DATABASE }}
+        run: tox
+
+      - uses: actions/upload-artifact@v2
+        if: always()
+        with:
+          name: logs
+          path: ./logs
+
+      - name: Get current date
+        if: always()
+        id: date
+        run: echo "::set-output name=date::$(date +'%Y-%m-%dT%H_%M_%S')" #no colons allowed for artifacts
+
+      - uses: actions/upload-artifact@v2
+        if: always()
+        with:
+          name: integration_results_${{ matrix.python-version }}_${{ matrix.os }}_${{ matrix.adapter }}-${{ steps.date.outputs.date }}.csv
+          path: integration_results.csv
+
+  require-label-comment:
+    runs-on: ubuntu-latest
+
+    needs: test
+
+    permissions:
+      pull-requests: write
+
+    steps:
+      - name: Needs permission PR comment
+        if: >-
+          needs.test.result == 'skipped' &&
+          github.event_name == 'pull_request_target' &&
+          github.event.pull_request.head.repo.full_name != github.repository
+        uses: unsplash/comment-on-pr@master
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          msg: |
+            "You do not have permissions to run integration tests, @dbt-labs/core "\
+            "needs to label this PR with `ok to test` in order to run integration tests!"
+          check_for_duplicate_msg: true

.github/workflows/main.yml

@@ -0,0 +1,206 @@
+# **what?**
+# Runs code quality checks, unit tests, and verifies python build on
+# all code commited to the repository. This workflow should not
+# require any secrets since it runs for PRs from forked repos.
+# By default, secrets are not passed to workflows running from
+# a forked repo.
+
+# **why?**
+# Ensure code for dbt meets a certain quality standard.
+
+# **when?**
+# This will run for all PRs, when code is pushed to a release
+# branch, and when manually triggered.
+
+name: Tests and Code Checks
+
+on:
+  push:
+    branches:
+      - "main"
+      - "develop"
+      - "*.latest"
+      - "releases/*"
+  pull_request:
+  workflow_dispatch:
+
+permissions: read-all
+
+# will cancel previous workflows triggered by the same event and for the same ref for PRs or same SHA otherwise
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event_name }}-${{ contains(github.event_name, 'pull_request') && github.event.pull_request.head.ref || github.sha }}
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  code-quality:
+    name: ${{ matrix.toxenv }}
+
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        toxenv: [flake8, mypy]
+
+    env:
+      TOXENV: ${{ matrix.toxenv }}
+      PYTEST_ADDOPTS: "-v --color=yes"
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+
+      - name: Install python dependencies
+        run: |
+          pip install --upgrade pip
+          pip install tox
+          pip --version
+          tox --version
+
+      - name: Run tox
+        run: tox
+
+  unit:
+    name: unit test / python ${{ matrix.python-version }}
+
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [3.6, 3.7, 3.8] # TODO: support unit testing for python 3.9 (https://github.com/dbt-labs/dbt/issues/3689)
+
+    env:
+      TOXENV: "unit"
+      PYTEST_ADDOPTS: "-v --color=yes --csv unit_results.csv"
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install python dependencies
+        run: |
+          pip install --upgrade pip
+          pip install tox
+          pip --version
+          tox --version
+
+      - name: Run tox
+        run: tox
+
+      - name: Get current date
+        if: always()
+        id: date
+        run: echo "::set-output name=date::$(date +'%Y-%m-%dT%H_%M_%S')" #no colons allowed for artifacts
+
+      - uses: actions/upload-artifact@v2
+        if: always()
+        with:
+          name: unit_results_${{ matrix.python-version }}-${{ steps.date.outputs.date }}.csv
+          path: unit_results.csv
+
+  build:
+    name: build packages
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+
+      - name: Install python dependencies
+        run: |
+          pip install --upgrade pip
+          pip install --upgrade setuptools wheel twine check-wheel-contents
+          pip --version
+
+      - name: Build distributions
+        run: ./scripts/build-dist.sh
+
+      - name: Show distributions
+        run: ls -lh dist/
+
+      - name: Check distribution descriptions
+        run: |
+          twine check dist/*
+
+      - name: Check wheel contents
+        run: |
+          check-wheel-contents dist/*.whl --ignore W007,W008
+
+      - uses: actions/upload-artifact@v2
+        with:
+          name: dist
+          path: dist/
+
+  test-build:
+    name: verify packages / python ${{ matrix.python-version }} / ${{ matrix.os }}
+
+    needs: build
+
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: [3.6, 3.7, 3.8, 3.9]
+
+    steps:
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install python dependencies
+        run: |
+          pip install --upgrade pip
+          pip install --upgrade wheel
+          pip --version
+
+      - uses: actions/download-artifact@v2
+        with:
+          name: dist
+          path: dist/
+
+      - name: Show distributions
+        run: ls -lh dist/
+
+      - name: Install wheel distributions
+        run: |
+          find ./dist/*.whl -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
+
+      - name: Check wheel distributions
+        run: |
+          dbt --version
+
+      - name: Install source distributions
+        run: |
+          find ./dist/*.gz -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
+
+      - name: Check source distributions
+        run: |
+          dbt --version

.github/workflows/performance.yml

@@ -0,0 +1,174 @@
+name: Performance Regression Tests
+# Schedule triggers
+on:
+  # runs twice a day at 10:05am and 10:05pm
+  schedule:
+    - cron: "5 10,22 * * *"
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  # checks fmt of runner code
+  # purposefully not a dependency of any other job
+  # will block merging, but not prevent developing
+  fmt:
+    name: Cargo fmt
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+      - run: rustup component add rustfmt
+      - uses: actions-rs/cargo@v1
+        with:
+          command: fmt
+          args: --manifest-path performance/runner/Cargo.toml --all -- --check
+
+  # runs any tests associated with the runner
+  # these tests make sure the runner logic is correct
+  test-runner:
+    name: Test Runner
+    runs-on: ubuntu-latest
+    env:
+      # turns errors into warnings
+      RUSTFLAGS: "-D warnings"
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+      - uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --manifest-path performance/runner/Cargo.toml
+
+  # build an optimized binary to be used as the runner in later steps
+  build-runner:
+    needs: [test-runner]
+    name: Build Runner
+    runs-on: ubuntu-latest
+    env:
+      RUSTFLAGS: "-D warnings"
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+      - uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --release --manifest-path performance/runner/Cargo.toml
+      - uses: actions/upload-artifact@v2
+        with:
+          name: runner
+          path: performance/runner/target/release/runner
+
+  # run the performance measurements on the current or default branch
+  measure-dev:
+    needs: [build-runner]
+    name: Measure Dev Branch
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout dev
+        uses: actions/checkout@v2
+      - name: Setup Python
+        uses: actions/setup-python@v2.2.2
+        with:
+          python-version: "3.8"
+      - name: install dbt
+        run: pip install -r dev-requirements.txt -r editable-requirements.txt
+      - name: install hyperfine
+        run: wget https://github.com/sharkdp/hyperfine/releases/download/v1.11.0/hyperfine_1.11.0_amd64.deb && sudo dpkg -i hyperfine_1.11.0_amd64.deb
+      - uses: actions/download-artifact@v2
+        with:
+          name: runner
+      - name: change permissions
+        run: chmod +x ./runner
+      - name: run
+        run: ./runner measure -b dev -p ${{ github.workspace }}/performance/projects/
+      - uses: actions/upload-artifact@v2
+        with:
+          name: dev-results
+          path: performance/results/
+
+  # run the performance measurements on the release branch which we use
+  # as a performance baseline. This part takes by far the longest, so
+  # we do everything we can first so the job fails fast.
+  # -----
+  # we need to checkout dbt twice in this job: once for the baseline dbt
+  # version, and once to get the latest regression testing projects,
+  # metrics, and runner code from the develop or current branch so that
+  # the calculations match for both versions of dbt we are comparing.
+  measure-baseline:
+    needs: [build-runner]
+    name: Measure Baseline Branch
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout latest
+        uses: actions/checkout@v2
+        with:
+          ref: "0.20.latest"
+      - name: Setup Python
+        uses: actions/setup-python@v2.2.2
+        with:
+          python-version: "3.8"
+      - name: move repo up a level
+        run: mkdir ${{ github.workspace }}/../baseline/ && cp -r ${{ github.workspace }} ${{ github.workspace }}/../baseline
+      - name: "[debug] ls new dbt location"
+        run: ls ${{ github.workspace }}/../baseline/dbt/
+      # installation creates egg-links so we have to preserve source
+      - name: install dbt from new location
+        run: cd ${{ github.workspace }}/../baseline/dbt/ && pip install -r dev-requirements.txt -r editable-requirements.txt
+      # checkout the current branch to get all the target projects
+      # this deletes the old checked out code which is why we had to copy before
+      - name: checkout dev
+        uses: actions/checkout@v2
+      - name: install hyperfine
+        run: wget https://github.com/sharkdp/hyperfine/releases/download/v1.11.0/hyperfine_1.11.0_amd64.deb && sudo dpkg -i hyperfine_1.11.0_amd64.deb
+      - uses: actions/download-artifact@v2
+        with:
+          name: runner
+      - name: change permissions
+        run: chmod +x ./runner
+      - name: run runner
+        run: ./runner measure -b baseline -p ${{ github.workspace }}/performance/projects/
+      - uses: actions/upload-artifact@v2
+        with:
+          name: baseline-results
+          path: performance/results/
+
+  # detect regressions on the output generated from measuring
+  # the two branches. Exits with non-zero code if a regression is detected.
+  calculate-regressions:
+    needs: [measure-dev, measure-baseline]
+    name: Compare Results
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/download-artifact@v2
+        with:
+          name: dev-results
+      - uses: actions/download-artifact@v2
+        with:
+          name: baseline-results
+      - name: "[debug] ls result files"
+        run: ls
+      - uses: actions/download-artifact@v2
+        with:
+          name: runner
+      - name: change permissions
+        run: chmod +x ./runner
+      - name: run calculation
+        run: ./runner calculate -r ./
+        # always attempt to upload the results even if there were regressions found
+      - uses: actions/upload-artifact@v2
+        if: ${{ always() }}
+        with:
+          name: final-calculations
+          path: ./final_calculations.json

.gitignore

@@ -85,6 +85,7 @@ target/
 
 # pycharm
 .idea/
+venv/
 
 # AWS credentials
 .aws/

.pre-commit-config.yaml

@@ -1,20 +0,0 @@
-repos:
--   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.3.0
-    hooks:
-    -   id: check-yaml
-    -   id: end-of-file-fixer
-    -   id: trailing-whitespace
--   repo: https://github.com/psf/black
-    rev: 20.8b1
-    hooks:
-    -   id: black
--   repo: https://gitlab.com/PyCQA/flake8
-    rev: 3.9.0
-    hooks:
-    -   id: flake8
--   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.812
-    hooks:
-    -   id: mypy
-        files: ^core/dbt/

ARCHITECTURE.md

@@ -1,4 +1,4 @@
-The core function of dbt is SQL compilation and execution. Users create projects of dbt resources (models, tests, seeds, snapshots, ...), defined in SQL and YAML files, and they invoke dbt to create, update, or query associated views and tables. Today, dbt makes heavy use of Jinja2 to enable the templating of SQL, and to construct a DAG (Directed Acyclic Graph) from all of the resources in a project. Users can also extend their projects by installing resources (including Jinja macros) from other projects, called "packages."
+The core function of dbt is SQL compilation and execution. Users create projects of dbt resources (models, tests, seeds, snapshots, ...), defined in SQL and YAML files, and they invoke dbt to create, update, or query associated views and tables. Today, dbt makes heavy use of Jinja2 to enable the templating of SQL, and to construct a DAG (Directed Acyclic Graph) from all of the resources in a project. Users can also extend their projects by installing resources (including Jinja macros) from other projects, called "packages." 
 
 ## dbt-core
 
@@ -26,9 +26,9 @@ This is the docs website code. It comes from the dbt-docs repository, and is gen
 
 ## Adapters
 
-dbt uses an adapter-plugin pattern to extend support to different databases, warehouses, query engines, etc. The four core adapters that are in the main repository, contained within the [`plugins`](plugins) subdirectory, are: Postgres Redshift, Snowflake and BigQuery. Other warehouses use adapter plugins defined in separate repositories (e.g. [dbt-spark](https://github.com/fishtown-analytics/dbt-spark), [dbt-presto](https://github.com/fishtown-analytics/dbt-presto)).
+dbt uses an adapter-plugin pattern to extend support to different databases, warehouses, query engines, etc. The four core adapters that are in the main repository, contained within the [`plugins`](plugins) subdirectory, are: Postgres Redshift, Snowflake and BigQuery. Other warehouses use adapter plugins defined in separate repositories (e.g. [dbt-spark](https://github.com/dbt-labs/dbt-spark), [dbt-presto](https://github.com/dbt-labs/dbt-presto)).
 
-Each adapter is a mix of python, Jinja2, and SQL. The adapter code also makes heavy use of Jinja2 to wrap modular chunks of SQL functionality, define default implementations, and allow plugins to override it.
+Each adapter is a mix of python, Jinja2, and SQL. The adapter code also makes heavy use of Jinja2 to wrap modular chunks of SQL functionality, define default implementations, and allow plugins to override it. 
 
 Each adapter plugin is a standalone python package that includes:
 

CONTRIBUTING.md

@@ -1,118 +1,117 @@
-# Contributing to dbt
+# Contributing to `dbt`
 
 1. [About this document](#about-this-document)
 2. [Proposing a change](#proposing-a-change)
 3. [Getting the code](#getting-the-code)
 4. [Setting up an environment](#setting-up-an-environment)
-5. [Running dbt in development](#running-dbt-in-development)
+5. [Running `dbt` in development](#running-dbt-in-development)
 6. [Testing](#testing)
 7. [Submitting a Pull Request](#submitting-a-pull-request)
 
 ## About this document
 
-This document is a guide intended for folks interested in contributing to dbt. Below, we document the process by which members of the community should create issues and submit pull requests (PRs) in this repository. It is not intended as a guide for using dbt, and it assumes a certain level of familiarity with Python concepts such as virtualenvs, `pip`, python modules, filesystems, and so on. This guide assumes you are using macOS or Linux and are comfortable with the command line.
+This document is a guide intended for folks interested in contributing to `dbt`. Below, we document the process by which members of the community should create issues and submit pull requests (PRs) in this repository. It is not intended as a guide for using `dbt`, and it assumes a certain level of familiarity with Python concepts such as virtualenvs, `pip`, python modules, filesystems, and so on. This guide assumes you are using macOS or Linux and are comfortable with the command line.
 
-If you're new to python development or contributing to open-source software, we encourage you to read this document from start to finish. If you get stuck, drop us a line in the #development channel on [slack](community.getdbt.com).
+If you're new to python development or contributing to open-source software, we encourage you to read this document from start to finish. If you get stuck, drop us a line in the `#dbt-core-development` channel on [slack](https://community.getdbt.com).
 
 ### Signing the CLA
 
-Please note that all contributors to dbt must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements) to have their Pull Request merged into the dbt codebase. If you are unable to sign the CLA, then the dbt maintainers will unfortunately be unable to merge your Pull Request. You are, however, welcome to open issues and comment on existing ones.
+Please note that all contributors to `dbt` must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements) to have their Pull Request merged into the `dbt` codebase. If you are unable to sign the CLA, then the `dbt` maintainers will unfortunately be unable to merge your Pull Request. You are, however, welcome to open issues and comment on existing ones.
 
 ## Proposing a change
 
-dbt is Apache 2.0-licensed open source software. dbt is what it is today because community members like you have opened issues, provided feedback, and contributed to the knowledge loop for the entire communtiy. Whether you are a seasoned open source contributor or a first-time committer, we welcome and encourage you to contribute code, documentation, ideas, or problem statements to this project.
+`dbt` is Apache 2.0-licensed open source software. `dbt` is what it is today because community members like you have opened issues, provided feedback, and contributed to the knowledge loop for the entire communtiy. Whether you are a seasoned open source contributor or a first-time committer, we welcome and encourage you to contribute code, documentation, ideas, or problem statements to this project.
 
 ### Defining the problem
 
-If you have an idea for a new feature or if you've discovered a bug in dbt, the first step is to open an issue. Please check the list of [open issues](https://github.com/fishtown-analytics/dbt/issues) before creating a new one. If you find a relevant issue, please add a comment to the open issue instead of creating a new one. There are hundreds of open issues in this repository and it can be hard to know where to look for a relevant open issue. **The dbt maintainers are always happy to point contributors in the right direction**, so please err on the side of documenting your idea in a new issue if you are unsure where a problem statement belongs.
+If you have an idea for a new feature or if you've discovered a bug in `dbt`, the first step is to open an issue. Please check the list of [open issues](https://github.com/dbt-labs/dbt/issues) before creating a new one. If you find a relevant issue, please add a comment to the open issue instead of creating a new one. There are hundreds of open issues in this repository and it can be hard to know where to look for a relevant open issue. **The `dbt` maintainers are always happy to point contributors in the right direction**, so please err on the side of documenting your idea in a new issue if you are unsure where a problem statement belongs.
 
-**Note:** All community-contributed Pull Requests _must_ be associated with an open issue. If you submit a Pull Request that does not pertain to an open issue, you will be asked to create an issue describing the problem before the Pull Request can be reviewed.
+> **Note:** All community-contributed Pull Requests _must_ be associated with an open issue. If you submit a Pull Request that does not pertain to an open issue, you will be asked to create an issue describing the problem before the Pull Request can be reviewed.
 
 ### Discussing the idea
 
-After you open an issue, a dbt maintainer will follow up by commenting on your issue (usually within 1-3 days) to explore your idea further and advise on how to implement the suggested changes. In many cases, community members will chime in with their own thoughts on the problem statement. If you as the issue creator are interested in submitting a Pull Request to address the issue, you should indicate this in the body of the issue. The dbt maintainers are _always_ happy to help contributors with the implementation of fixes and features, so please also indicate if there's anything you're unsure about or could use guidance around in the issue.
+After you open an issue, a `dbt` maintainer will follow up by commenting on your issue (usually within 1-3 days) to explore your idea further and advise on how to implement the suggested changes. In many cases, community members will chime in with their own thoughts on the problem statement. If you as the issue creator are interested in submitting a Pull Request to address the issue, you should indicate this in the body of the issue. The `dbt` maintainers are _always_ happy to help contributors with the implementation of fixes and features, so please also indicate if there's anything you're unsure about or could use guidance around in the issue.
 
 ### Submitting a change
 
-If an issue is appropriately well scoped and describes a beneficial change to the dbt codebase, then anyone may submit a Pull Request to implement the functionality described in the issue. See the sections below on how to do this.
+If an issue is appropriately well scoped and describes a beneficial change to the `dbt` codebase, then anyone may submit a Pull Request to implement the functionality described in the issue. See the sections below on how to do this.
 
-The dbt maintainers will add a `good first issue` label if an issue is suitable for a first-time contributor. This label often means that the required code change is small, limited to one database adapter, or a net-new addition that does not impact existing functionality. You can see the list of currently open issues on the [Contribute](https://github.com/fishtown-analytics/dbt/contribute) page.
+The `dbt` maintainers will add a `good first issue` label if an issue is suitable for a first-time contributor. This label often means that the required code change is small, limited to one database adapter, or a net-new addition that does not impact existing functionality. You can see the list of currently open issues on the [Contribute](https://github.com/dbt-labs/dbt/contribute) page.
 
 Here's a good workflow:
 - Comment on the open issue, expressing your interest in contributing the required code change
 - Outline your planned implementation. If you want help getting started, ask!
-- Follow the steps outlined below to develop locally. Once you have opened a PR, one of the dbt maintainers will work with you to review your code.
-- Add a test! Tests are crucial for both fixes and new features alike. We want to make sure that code works as intended, and that it avoids any bugs  previously encountered. Currently, the best resource for understanding dbt's [unit](test/unit) and [integration](test/integration) tests is the tests themselves. One of the maintainers can help by pointing out relevant examples.
+- Follow the steps outlined below to develop locally. Once you have opened a PR, one of the `dbt` maintainers will work with you to review your code.
+- Add a test! Tests are crucial for both fixes and new features alike. We want to make sure that code works as intended, and that it avoids any bugs  previously encountered. Currently, the best resource for understanding `dbt`'s [unit](test/unit) and [integration](test/integration) tests is the tests themselves. One of the maintainers can help by pointing out relevant examples.
 
-In some cases, the right resolution to an open issue might be tangential to the dbt codebase. The right path forward might be a documentation update or a change that can be made in user-space. In other cases, the issue might describe functionality that the dbt maintainers are unwilling or unable to incorporate into the dbt codebase. When it is determined that an open issue describes functionality that will not translate to a code change in the dbt repository, the issue will be tagged with the `wontfix` label (see below) and closed.
+In some cases, the right resolution to an open issue might be tangential to the `dbt` codebase. The right path forward might be a documentation update or a change that can be made in user-space. In other cases, the issue might describe functionality that the `dbt` maintainers are unwilling or unable to incorporate into the `dbt` codebase. When it is determined that an open issue describes functionality that will not translate to a code change in the `dbt` repository, the issue will be tagged with the `wontfix` label (see below) and closed.
 
 ### Using issue labels
 
-The dbt maintainers use labels to categorize open issues. Some labels indicate the databases impacted by the issue, while others describe the domain in the dbt codebase germane to the discussion. While most of these labels are self-explanatory (eg. `snowflake` or `bigquery`), there are others that are worth describing.
+The `dbt` maintainers use labels to categorize open issues. Some labels indicate the databases impacted by the issue, while others describe the domain in the `dbt` codebase germane to the discussion. While most of these labels are self-explanatory (eg. `snowflake` or `bigquery`), there are others that are worth describing.
 
 | tag | description |
 | --- | ----------- |
-| [triage](https://github.com/fishtown-analytics/dbt/labels/triage) | This is a new issue which has not yet been reviewed by a dbt maintainer. This label is removed when a maintainer reviews and responds to the issue. |
-| [bug](https://github.com/fishtown-analytics/dbt/labels/bug) | This issue represents a defect or regression in dbt |
-| [enhancement](https://github.com/fishtown-analytics/dbt/labels/enhancement) | This issue represents net-new functionality in dbt |
-| [good first issue](https://github.com/fishtown-analytics/dbt/labels/good%20first%20issue) | This issue does not require deep knowledge of the dbt codebase to implement. This issue is appropriate for a first-time contributor. |
-| [help wanted](https://github.com/fishtown-analytics/dbt/labels/help%20wanted) / [discussion](https://github.com/fishtown-analytics/dbt/labels/discussion) | Conversation around this issue in ongoing, and there isn't yet a clear path forward. Input from community members is most welcome. |
-| [duplicate](https://github.com/fishtown-analytics/dbt/issues/duplicate) | This issue is functionally identical to another open issue. The dbt maintainers will close this issue and encourage community members to focus conversation on the other one. |
-| [snoozed](https://github.com/fishtown-analytics/dbt/labels/snoozed) | This issue describes a good idea, but one which will probably not be addressed in a six-month time horizon. The dbt maintainers will revist these issues periodically and re-prioritize them accordingly. |
-| [stale](https://github.com/fishtown-analytics/dbt/labels/stale) | This is an old issue which has not recently been updated. Stale issues will periodically be closed by dbt maintainers, but they can be re-opened if the discussion is restarted. |
-| [wontfix](https://github.com/fishtown-analytics/dbt/labels/wontfix) | This issue does not require a code change in the dbt repository, or the maintainers are unwilling/unable to merge a Pull Request which implements the behavior described in the issue. |
+| [triage](https://github.com/dbt-labs/dbt/labels/triage) | This is a new issue which has not yet been reviewed by a `dbt` maintainer. This label is removed when a maintainer reviews and responds to the issue. |
+| [bug](https://github.com/dbt-labs/dbt/labels/bug) | This issue represents a defect or regression in `dbt` |
+| [enhancement](https://github.com/dbt-labs/dbt/labels/enhancement) | This issue represents net-new functionality in `dbt` |
+| [good first issue](https://github.com/dbt-labs/dbt/labels/good%20first%20issue) | This issue does not require deep knowledge of the `dbt` codebase to implement. This issue is appropriate for a first-time contributor. |
+| [help wanted](https://github.com/dbt-labs/dbt/labels/help%20wanted) / [discussion](https://github.com/dbt-labs/dbt/labels/discussion) | Conversation around this issue in ongoing, and there isn't yet a clear path forward. Input from community members is most welcome. |
+| [duplicate](https://github.com/dbt-labs/dbt/issues/duplicate) | This issue is functionally identical to another open issue. The `dbt` maintainers will close this issue and encourage community members to focus conversation on the other one. |
+| [snoozed](https://github.com/dbt-labs/dbt/labels/snoozed) | This issue describes a good idea, but one which will probably not be addressed in a six-month time horizon. The `dbt` maintainers will revist these issues periodically and re-prioritize them accordingly. |
+| [stale](https://github.com/dbt-labs/dbt/labels/stale) | This is an old issue which has not recently been updated. Stale issues will periodically be closed by `dbt` maintainers, but they can be re-opened if the discussion is restarted. |
+| [wontfix](https://github.com/dbt-labs/dbt/labels/wontfix) | This issue does not require a code change in the `dbt` repository, or the maintainers are unwilling/unable to merge a Pull Request which implements the behavior described in the issue. |
 
 #### Branching Strategy
 
-dbt has three types of branches:
+`dbt` has three types of branches:
 
 - **Trunks** are where active development of the next release takes place. There is one trunk named `develop` at the time of writing this, and will be the default branch of the repository.
-- **Release Branches** track a specific, not yet complete release of dbt. Each minor version release has a corresponding release branch. For example, the `0.11.x` series of releases has a branch called `0.11.latest`. This allows us to release new patch versions under `0.11` without necessarily needing to pull them into the latest version of dbt.
+- **Release Branches** track a specific, not yet complete release of `dbt`. Each minor version release has a corresponding release branch. For example, the `0.11.x` series of releases has a branch called `0.11.latest`. This allows us to release new patch versions under `0.11` without necessarily needing to pull them into the latest version of `dbt`.
 - **Feature Branches** track individual features and fixes. On completion they should be merged into the trunk brnach or a specific release branch.
 
 ## Getting the code
 
 ### Installing git
 
-You will need `git` in order to download and modify the dbt source code. On macOS, the best way to download git is to just install [Xcode](https://developer.apple.com/support/xcode/).
+You will need `git` in order to download and modify the `dbt` source code. On macOS, the best way to download git is to just install [Xcode](https://developer.apple.com/support/xcode/).
 
 ### External contributors
 
-If you are not a member of the `fishtown-analytics` GitHub organization, you can contribute to dbt by forking the dbt repository. For a detailed overview on forking, check out the [GitHub docs on forking](https://help.github.com/en/articles/fork-a-repo). In short, you will need to:
+If you are not a member of the `dbt-labs` GitHub organization, you can contribute to `dbt` by forking the `dbt` repository. For a detailed overview on forking, check out the [GitHub docs on forking](https://help.github.com/en/articles/fork-a-repo). In short, you will need to:
 
-1. fork the dbt repository
+1. fork the `dbt` repository
 2. clone your fork locally
 3. check out a new branch for your proposed changes
 4. push changes to your fork
-5. open a pull request against `fishtown-analytics/dbt` from your forked repository
+5. open a pull request against `dbt-labs/dbt` from your forked repository
 
 ### Core contributors
 
-If you are a member of the `fishtown-analytics` GitHub organization, you will have push access to the dbt repo. Rather than
-forking dbt to make your changes, just clone the repository, check out a new branch, and push directly to that branch.
+If you are a member of the `dbt-labs` GitHub organization, you will have push access to the `dbt` repo. Rather than forking `dbt` to make your changes, just clone the repository, check out a new branch, and push directly to that branch.
 
 ## Setting up an environment
 
-There are some tools that will be helpful to you in developing locally. While this is the list relevant for dbt development, many of these tools are used commonly across open-source python projects.
+There are some tools that will be helpful to you in developing locally. While this is the list relevant for `dbt` development, many of these tools are used commonly across open-source python projects.
 
 ### Tools
 
-A short list of tools used in dbt testing that will be helpful to your understanding:
+A short list of tools used in `dbt` testing that will be helpful to your understanding:
 
-- [virtualenv](https://virtualenv.pypa.io/en/stable/) to manage dependencies
-- [tox](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions
-- [pytest](https://docs.pytest.org/en/latest/) to discover/run tests
-- [make](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) - but don't worry too much, nobody _really_ understands how make works and our Makefile is super simple
-- [flake8](https://gitlab.com/pycqa/flake8) for code linting
+- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.6, Python 3.7, Python 3.8, and Python 3.9
+- [`pytest`](https://docs.pytest.org/en/latest/) to discover/run tests
+- [`make`](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) - but don't worry too much, nobody _really_ understands how make works and our Makefile is super simple
+- [`flake8`](https://flake8.pycqa.org/en/latest/) for code linting
+- [`mypy`](https://mypy.readthedocs.io/en/stable/) for static type checking
 - [CircleCI](https://circleci.com/product/) and [Azure Pipelines](https://azure.microsoft.com/en-us/services/devops/pipelines/)
 
-A deep understanding of these tools in not required to effectively contribute to dbt, but we recommend checking out the attached documentation if you're interested in learning more about them.
+A deep understanding of these tools in not required to effectively contribute to `dbt`, but we recommend checking out the attached documentation if you're interested in learning more about them.
 
 #### virtual environments
 
-We strongly recommend using virtual environments when developing code in dbt. We recommend creating this virtualenv
-in the root of the dbt repository. To create a new virtualenv, run:
-```
+We strongly recommend using virtual environments when developing code in `dbt`. We recommend creating this virtualenv
+in the root of the `dbt` repository. To create a new virtualenv, run:
+```sh
 python3 -m venv env
 source env/bin/activate
 ```
@@ -128,23 +127,25 @@ Docker and docker-compose are both used in testing. Specific instructions for yo
 
 For testing, and later in the examples in this document, you may want to have `psql` available so you can poke around in the database and see what happened. We recommend that you use [homebrew](https://brew.sh/) for that on macOS, and your package manager on Linux. You can install any version of the postgres client that you'd like. On macOS, with homebrew setup, you can run:
 
-```
+```sh
 brew install postgresql
 ```
 
-## Running dbt in development
+## Running `dbt` in development
 
 ### Installation
 
-First make sure that you set up your `virtualenv` as described in section _Setting up an environment_. Next, install dbt (and its dependencies) with:
+First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment). Next, install `dbt` (and its dependencies) with:
 
-```
-pip install -r requirements-editable.txt
+```sh
+make dev
+# or
+pip install -r dev-requirements.txt -r editable-requirements.txt
 ```
 
-When dbt is installed from source in this way, any changes you make to the dbt source code will be reflected immediately in your next `dbt` run.
+When `dbt` is installed this way, any changes you make to the `dbt` source code will be reflected immediately in your next `dbt` run.
 
-### Running dbt
+### Running `dbt`
 
 With your virtualenv activated, the `dbt` script should point back to the source code you've cloned on your machine. You can verify this by running `which dbt`. This command should show you a path to an executable in your virtualenv.
 
@@ -152,76 +153,79 @@ Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as
 
 ## Testing
 
-Getting the dbt integration tests set up in your local environment will be very helpful as you start to make changes to your local version of dbt. The section that follows outlines some helpful tips for setting up the test environment.
+Getting the `dbt` integration tests set up in your local environment will be very helpful as you start to make changes to your local version of `dbt`. The section that follows outlines some helpful tips for setting up the test environment.
 
-### Running tests via Docker
+Since `dbt` works with a number of different databases, you will need to supply credentials for one or more of these databases in your test environment. Most organizations don't have access to each of a BigQuery, Redshift, Snowflake, and Postgres database, so it's likely that you will be unable to run every integration test locally. Fortunately, dbt Labs provides a CI environment with access to sandboxed Redshift, Snowflake, BigQuery, and Postgres databases. See the section on [_Submitting a Pull Request_](#submitting-a-pull-request) below for more information on this CI setup.
 
-dbt's unit and integration tests run in Docker. Because dbt works with a number of different databases, you will need to supply credentials for one or more of these databases in your test environment. Most organizations don't have access to each of a BigQuery, Redshift, Snowflake, and Postgres database, so it's likely that you will be unable to run every integration test locally. Fortunately, Fishtown Analytics provides a CI environment with access to sandboxed Redshift, Snowflake, BigQuery, and Postgres databases. See the section on [_Submitting a Pull Request_](#submitting-a-pull-request) below for more information on this CI setup.
+### Initial setup
 
+We recommend starting with `dbt`'s Postgres tests. These tests cover most of the functionality in `dbt`, are the fastest to run, and are the easiest to set up. To run the Postgres integration tests, you'll have to do one extra step of setting up the test database:
 
-### Specifying your test credentials
-
-dbt uses test credentials specified in a `test.env` file in the root of the repository. This `test.env` file is git-ignored, but please be _extra_ careful to never check in credentials or other sensitive information when developing against dbt. To create your `test.env` file, copy the provided sample file, then supply your relevant credentials:
-
-```
-cp test.env.sample test.env
-```
-
-We recommend starting with dbt's Postgres tests. These tests cover most of the functionality in dbt, are the fastest to run, and are the easiest to set up. dbt's test suite runs Postgres in a Docker container, so no setup should be required to run these tests.
-
-If you additionally want to test Snowflake, Bigquery, or Redshift, locally you'll need to get credentials and add them to the `test.env` file. In general, it's most important to have successful unit and Postgres tests. Once you open a PR, dbt will automatically run integration tests for the other three core database adapters. Of course, if you are a BigQuery user, contributing a BigQuery-only feature, it's important to run BigQuery tests as well.
-
-### Test commands
-
-dbt's unit tests and Python linter can be run with:
-
-```
-make test-unit
-```
-
-To run the Postgres + Python 3.6 integration tests, you'll have to do one extra step of setting up the test database:
-
+```sh
+make setup-db
 ```
+or, alternatively:
+```sh
 docker-compose up -d database
 PGHOST=localhost PGUSER=root PGPASSWORD=password PGDATABASE=postgres bash test/setup_db.sh
 ```
 
-To run a quick test for Python3 integration tests on Postgres, you can run:
+`dbt` uses test credentials specified in a `test.env` file in the root of the repository for non-Postgres databases. This `test.env` file is git-ignored, but please be _extra_ careful to never check in credentials or other sensitive information when developing against `dbt`. To create your `test.env` file, copy the provided sample file, then supply your relevant credentials. This step is only required to use non-Postgres databases.
 
 ```
-make test-quick
+cp test.env.sample test.env
+$EDITOR test.env
 ```
 
-To run tests for a specific database, invoke `tox` directly with the required flags:
-```
-# Run Postgres py36 tests
-docker-compose run test tox -e integration-postgres-py36 -- -x
+> In general, it's most important to have successful unit and Postgres tests. Once you open a PR, `dbt` will automatically run integration tests for the other three core database adapters. Of course, if you are a BigQuery user, contributing a BigQuery-only feature, it's important to run BigQuery tests as well.
 
-# Run Snowflake py36 tests
-docker-compose run test tox -e integration-snowflake-py36 -- -x
+### Test commands
 
-# Run BigQuery py36 tests
-docker-compose run test tox -e integration-bigquery-py36 -- -x
+There are a few methods for running tests locally.
 
-# Run Redshift py36 tests
-docker-compose run test tox -e integration-redshift-py36 -- -x
-```
+#### Makefile
 
-To run a specific test by itself:
-```
-docker-compose run test tox -e explicit-py36 -- -s -x -m profile_{adapter} {path_to_test_file_or_folder}
-```
-E.g.
-```
-docker-compose run test tox -e explicit-py36 -- -s -x -m profile_snowflake test/integration/001_simple_copy_test
-```
+There are multiple targets in the Makefile to run common test suites and code
+checks, most notably:
 
-See the `Makefile` contents for more some other examples of ways to run `tox`.
+```sh
+# Runs unit tests with py38 and code checks in parallel.
+make test
+# Runs postgres integration tests with py38 in "fail fast" mode.
+make integration
+```
+> These make targets assume you have a recent version of [`tox`](https://tox.readthedocs.io/en/latest/) installed locally,
+> unless you use choose a Docker container to run tests. Run `make help` for more info.
 
+Check out the other targets in the Makefile to see other commonly used test
+suites.
+
+#### `tox`
+
+[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run
+tests. You can also run tests in parallel, for example, you can run unit tests
+for Python 3.6, Python 3.7, Python 3.8, `flake8` checks, and `mypy` checks in
+parallel with `tox -p`. Also, you can run unit tests for specific python versions
+with `tox -e py36`. The configuration for these tests in located in `tox.ini`.
+
+#### `pytest`
+
+Finally, you can also run a specific test or group of tests using [`pytest`](https://docs.pytest.org/en/latest/) directly. With a virtualenv
+active and dev dependencies installed you can do things like:
+```sh
+# run specific postgres integration tests
+python -m pytest -m profile_postgres test/integration/001_simple_copy_test
+# run all unit tests in a file
+python -m pytest test/unit/test_graph.py
+# run a specific unit test
+python -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
+```
+> [Here](https://docs.pytest.org/en/reorganize-docs/new-docs/user/commandlineuseful.html)
+> is a list of useful command-line options for `pytest` to use while developing.
 ## Submitting a Pull Request
 
-Fishtown Analytics provides a sandboxed Redshift, Snowflake, and BigQuery database for use in a CI environment. When pull requests are submitted to the `fishtown-analytics/dbt` repo, GitHub will trigger automated tests in CircleCI and Azure Pipelines.
+dbt Labs provides a sandboxed Redshift, Snowflake, and BigQuery database for use in a CI environment. When pull requests are submitted to the `dbt-labs/dbt` repo, GitHub will trigger automated tests in CircleCI and Azure Pipelines.
 
-A dbt maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
+A `dbt` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
 
-Once all tests are passing and your PR has been approved, a dbt maintainer will merge your changes into the active development branch. And that's it! Happy developing :tada:
+Once all tests are passing and your PR has been approved, a `dbt` maintainer will merge your changes into the active development branch. And that's it! Happy developing :tada:

Dockerfile.test

@@ -1,8 +1,11 @@
-FROM ubuntu:18.04
+FROM ubuntu:20.04
 
 ENV DEBIAN_FRONTEND noninteractive
 
 RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+    software-properties-common \
+    && add-apt-repository ppa:git-core/ppa -y \
     && apt-get dist-upgrade -y \
     && apt-get install -y --no-install-recommends \
     netcat \
@@ -46,9 +49,7 @@ RUN curl -LO https://github.com/jwilder/dockerize/releases/download/$DOCKERIZE_V
     && tar -C /usr/local/bin -xzvf dockerize-linux-amd64-$DOCKERIZE_VERSION.tar.gz \
     && rm dockerize-linux-amd64-$DOCKERIZE_VERSION.tar.gz
 
-RUN pip3 install -U "tox==3.14.4" wheel "six>=1.14.0,<1.15.0" "virtualenv==20.0.3" setuptools
-# tox fails if the 'python' interpreter (python2) doesn't have `tox` installed
-RUN pip install -U "tox==3.14.4" "six>=1.14.0,<1.15.0" "virtualenv==20.0.3" setuptools
+RUN pip3 install -U tox wheel six setuptools
 
 # These args are passed in via docker-compose, which reads then from the .env file.
 # On Linux, run `make .env` to create the .env file for the current user.

License.md

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright {yyyy} {name of copyright owner}
+   Copyright 2021 dbt Labs, Inc.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

Makefile

@@ -1,24 +1,81 @@
-.PHONY: install test test-unit test-integration
+.DEFAULT_GOAL:=help
 
-test: .env
-	@echo "Full test run starting..."
-	@time docker-compose run --rm test tox
+# Optional flag to run target in a docker container.
+# (example `make test USE_DOCKER=true`)
+ifeq ($(USE_DOCKER),true)
+	DOCKER_CMD := docker-compose run --rm test
+endif
 
-test-unit: .env
-	@echo "Unit test run starting..."
-	@time docker-compose run --rm test tox -e unit-py36,flake8
+.PHONY: dev
+dev: ## Installs dbt-* packages in develop mode along with development dependencies.
+	pip install -r dev-requirements.txt -r editable-requirements.txt
 
-test-integration: .env
-	@echo "Integration test run starting..."
-	@time docker-compose run --rm test tox -e integration-postgres-py36,integration-redshift-py36,integration-snowflake-py36,integration-bigquery-py36
+.PHONY: mypy
+mypy: .env ## Runs mypy for static type checking.
+	$(DOCKER_CMD) tox -e mypy
 
-test-quick: .env
-	@echo "Integration test run starting, will exit on first failure..."
-	@time docker-compose run --rm test tox -e integration-postgres-py36 -- -x
+.PHONY: flake8
+flake8: .env ## Runs flake8 to enforce style guide.
+	$(DOCKER_CMD) tox -e flake8
+
+.PHONY: lint
+lint: .env ## Runs all code checks in parallel.
+	$(DOCKER_CMD) tox -p -e flake8,mypy
+
+.PHONY: unit
+unit: .env ## Runs unit tests with py38.
+	$(DOCKER_CMD) tox -e py38
+
+.PHONY: test
+test: .env ## Runs unit tests with py38 and code checks in parallel.
+	$(DOCKER_CMD) tox -p -e py38,flake8,mypy
+
+.PHONY: integration
+integration: .env integration-postgres ## Alias for integration-postgres.
+
+.PHONY: integration-fail-fast
+integration-fail-fast: .env integration-postgres-fail-fast ## Alias for integration-postgres-fail-fast.
+
+.PHONY: integration-postgres
+integration-postgres: .env ## Runs postgres integration tests with py38.
+	$(DOCKER_CMD) tox -e py38-postgres -- -nauto
+
+.PHONY: integration-postgres-fail-fast
+integration-postgres-fail-fast: .env ## Runs postgres integration tests with py38 in "fail fast" mode.
+	$(DOCKER_CMD) tox -e py38-postgres -- -x -nauto
+
+.PHONY: integration-redshift
+integration-redshift: .env ## Runs redshift integration tests with py38.
+	$(DOCKER_CMD) tox -e py38-redshift -- -nauto
+
+.PHONY: integration-redshift-fail-fast
+integration-redshift-fail-fast: .env ## Runs redshift integration tests with py38 in "fail fast" mode.
+	$(DOCKER_CMD) tox -e py38-redshift -- -x -nauto
+
+.PHONY: integration-snowflake
+integration-snowflake: .env ## Runs snowflake integration tests with py38.
+	$(DOCKER_CMD) tox -e py38-snowflake -- -nauto
+
+.PHONY: integration-snowflake-fail-fast
+integration-snowflake-fail-fast: .env ## Runs snowflake integration tests with py38 in "fail fast" mode.
+	$(DOCKER_CMD) tox -e py38-snowflake -- -x -nauto
+
+.PHONY: integration-bigquery
+integration-bigquery: .env ## Runs bigquery integration tests with py38.
+	$(DOCKER_CMD) tox -e py38-bigquery -- -nauto
+
+.PHONY: integration-bigquery-fail-fast
+integration-bigquery-fail-fast: .env ## Runs bigquery integration tests with py38 in "fail fast" mode.
+	$(DOCKER_CMD) tox -e py38-bigquery -- -x -nauto
+
+.PHONY: setup-db
+setup-db: ## Setup Postgres database with docker-compose for system testing.
+	docker-compose up -d database
+	PGHOST=localhost PGUSER=root PGPASSWORD=password PGDATABASE=postgres bash test/setup_db.sh
 
 # This rule creates a file named .env that is used by docker-compose for passing
 # the USER_ID and GROUP_ID arguments to the Docker image.
-.env:
+.env: ## Setup step for using using docker-compose with make target.
 	@touch .env
 ifneq ($(OS),Windows_NT)
 ifneq ($(shell uname -s), Darwin)
@@ -26,9 +83,9 @@ ifneq ($(shell uname -s), Darwin)
 	@echo GROUP_ID=$(shell id -g) >> .env
 endif
 endif
-	@time docker-compose build
 
-clean:
+.PHONY: clean
+clean: ## Resets development environment.
 	rm -f .coverage
 	rm -rf .eggs/
 	rm -f .env
@@ -42,3 +99,14 @@ clean:
 	rm -rf target/
 	find . -type f -name '*.pyc' -delete
 	find . -type d -name '__pycache__' -depth -delete
+
+.PHONY: help
+help: ## Show this help message.
+	@echo 'usage: make [target] [USE_DOCKER=true]'
+	@echo
+	@echo 'targets:'
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
+	@echo
+	@echo 'options:'
+	@echo 'use USE_DOCKER=true to run target in a docker container'
+

README.md

@@ -1,28 +1,18 @@
 <p align="center">
-  <img src="https://raw.githubusercontent.com/fishtown-analytics/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-logo-full.svg" alt="dbt logo" width="500"/>
+  <img src="https://raw.githubusercontent.com/dbt-labs/dbt/ec7dee39f793aa4f7dd3dae37282cc87664813e4/etc/dbt-logo-full.svg" alt="dbt logo" width="500"/>
 </p>
 <p align="center">
-  <a href="https://codeclimate.com/github/fishtown-analytics/dbt">
-    <img src="https://codeclimate.com/github/fishtown-analytics/dbt/badges/gpa.svg" alt="Code Climate"/>
+  <a href="https://github.com/dbt-labs/dbt/actions/workflows/main.yml">
+    <img src="https://github.com/dbt-labs/dbt/actions/workflows/main.yml/badge.svg?event=push" alt="Unit Tests Badge"/>
   </a>
-  <a href="https://circleci.com/gh/fishtown-analytics/dbt/tree/master">
-    <img src="https://circleci.com/gh/fishtown-analytics/dbt/tree/master.svg?style=svg"  alt="CircleCI" />
-  </a>
-  <a href="https://ci.appveyor.com/project/DrewBanin/dbt/branch/development">
-    <img src="https://ci.appveyor.com/api/projects/status/v01rwd3q91jnwp9m/branch/development?svg=true" alt="AppVeyor" />
-  </a>
-  <a href="https://community.getdbt.com">
-    <img src="https://community.getdbt.com/badge.svg" alt="Slack" />
+  <a href="https://github.com/dbt-labs/dbt/actions/workflows/integration.yml">
+    <img src="https://github.com/dbt-labs/dbt/actions/workflows/integration.yml/badge.svg?event=push" alt="Integration Tests Badge"/>
   </a>
 </p>
 
-**[dbt](https://www.getdbt.com/)** (data build tool) enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.
+**[dbt](https://www.getdbt.com/)** enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.
 
-dbt is the T in ELT. Organize, cleanse, denormalize, filter, rename, and pre-aggregate the raw data in your warehouse so that it's ready for analysis.
-
-![dbt architecture](https://raw.githubusercontent.com/fishtown-analytics/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-arch.png)
-
-dbt can be used to [aggregate pageviews into sessions](https://github.com/fishtown-analytics/snowplow), calculate [ad spend ROI](https://github.com/fishtown-analytics/facebook-ads), or report on [email campaign performance](https://github.com/fishtown-analytics/mailchimp).
+![architecture](https://raw.githubusercontent.com/dbt-labs/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-arch.png)
 
 ## Understanding dbt
 
@@ -30,28 +20,22 @@ Analysts using dbt can transform their data by simply writing select statements,
 
 These select statements, or "models", form a dbt project. Models frequently build on top of one another – dbt makes it easy to [manage relationships](https://docs.getdbt.com/docs/ref) between models, and [visualize these relationships](https://docs.getdbt.com/docs/documentation), as well as assure the quality of your transformations through [testing](https://docs.getdbt.com/docs/testing).
 
-![dbt dag](https://raw.githubusercontent.com/fishtown-analytics/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-dag.png)
+![dbt dag](https://raw.githubusercontent.com/dbt-labs/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-dag.png)
 
 ## Getting started
 
--   [Install dbt](https://docs.getdbt.com/docs/installation)
--   Read the [documentation](https://docs.getdbt.com/).
--   Productionize your dbt project with [dbt Cloud](https://www.getdbt.com)
+- [Install dbt](https://docs.getdbt.com/docs/installation)
+- Read the [introduction](https://docs.getdbt.com/docs/introduction/) and [viewpoint](https://docs.getdbt.com/docs/about/viewpoint/)
 
-## Find out more
+## Join the dbt Community
 
--   Check out the [Introduction to dbt](https://docs.getdbt.com/docs/introduction/).
--   Read the [dbt Viewpoint](https://docs.getdbt.com/docs/about/viewpoint/).
-
-## Join thousands of analysts in the dbt community
-
--   Join the [chat](http://community.getdbt.com/) on Slack.
--   Find community posts on [dbt Discourse](https://discourse.getdbt.com).
+- Be part of the conversation in the [dbt Community Slack](http://community.getdbt.com/)
+- Read more on the [dbt Community Discourse](https://discourse.getdbt.com)
 
 ## Reporting bugs and contributing code
 
--   Want to report a bug or request a feature? Let us know on [Slack](http://community.getdbt.com/), or open [an issue](https://github.com/fishtown-analytics/dbt/issues/new).
--   Want to help us build dbt? Check out the [Contributing Getting Started Guide](https://github.com/fishtown-analytics/dbt/blob/HEAD/CONTRIBUTING.md)
+- Want to report a bug or request a feature? Let us know on [Slack](http://community.getdbt.com/), or open [an issue](https://github.com/dbt-labs/dbt/issues/new)
+- Want to help us build dbt? Check out the [Contributing Guide](https://github.com/dbt-labs/dbt/blob/HEAD/CONTRIBUTING.md)
 
 ## Code of Conduct
 

azure-pipelines.yml

@@ -1,154 +0,0 @@
-# Python package
-# Create and test a Python package on multiple Python versions.
-# Add steps that analyze code, save the dist with the build record, publish to a PyPI-compatible index, and more:
-# https://docs.microsoft.com/azure/devops/pipelines/languages/python
-
-trigger:
-  branches:
-    include:
-    - master
-    - dev/*
-    - pr/*
-
-jobs:
-- job: UnitTest
-  pool:
-    vmImage: 'vs2017-win2016'
-  steps:
-  - task: UsePythonVersion@0
-    inputs:
-      versionSpec: '3.7'
-      architecture: 'x64'
-
-  - script: python -m pip install --upgrade pip && pip install tox
-    displayName: 'Install dependencies'
-
-  - script: python -m tox -e pywin-unit
-    displayName: Run unit tests
-
-- job: PostgresIntegrationTest
-  pool:
-    vmImage: 'vs2017-win2016'
-  dependsOn: UnitTest
-
-  steps:
-  - pwsh: |
-      $serviceName = Get-Service -Name postgresql*
-      Set-Service -InputObject $serviceName -StartupType Automatic
-      Start-Service -InputObject $serviceName
-
-      & $env:PGBIN\createdb.exe -U postgres dbt
-      & $env:PGBIN\psql.exe  -U postgres -c "CREATE ROLE root WITH PASSWORD 'password';"
-      & $env:PGBIN\psql.exe  -U postgres -c "ALTER ROLE root WITH LOGIN;"
-      & $env:PGBIN\psql.exe  -U postgres -c "GRANT CREATE, CONNECT ON DATABASE dbt TO root WITH GRANT OPTION;"
-      & $env:PGBIN\psql.exe  -U postgres -c "CREATE ROLE noaccess WITH PASSWORD 'password' NOSUPERUSER;"
-      & $env:PGBIN\psql.exe  -U postgres -c "ALTER ROLE noaccess WITH LOGIN;"
-      & $env:PGBIN\psql.exe  -U postgres -c "GRANT CONNECT ON DATABASE dbt TO noaccess;"
-    displayName: Install postgresql and set up database
-
-  - task: UsePythonVersion@0
-    inputs:
-      versionSpec: '3.7'
-      architecture: 'x64'
-
-  - script: python -m pip install --upgrade pip && pip install tox
-    displayName: 'Install dependencies'
-
-  - script: python -m tox -e pywin-postgres
-    displayName: Run integration tests
-
-# These three are all similar except secure environment variables, which MUST be passed along to their tasks,
-# but there's probably a better way to do this!
-- job: SnowflakeIntegrationTest
-  pool:
-    vmImage: 'vs2017-win2016'
-  dependsOn: PostgresIntegrationTest
-  condition: succeeded()
-  steps:
-  - task: UsePythonVersion@0
-    inputs:
-      versionSpec: '3.7'
-      architecture: 'x64'
-
-  - script: python -m pip install --upgrade pip && pip install tox
-    displayName: 'Install dependencies'
-
-  - script: python -m tox -e pywin-snowflake
-    env:
-      SNOWFLAKE_TEST_ACCOUNT: $(SNOWFLAKE_TEST_ACCOUNT)
-      SNOWFLAKE_TEST_PASSWORD: $(SNOWFLAKE_TEST_PASSWORD)
-      SNOWFLAKE_TEST_USER: $(SNOWFLAKE_TEST_USER)
-      SNOWFLAKE_TEST_WAREHOUSE: $(SNOWFLAKE_TEST_WAREHOUSE)
-      SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN: $(SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN)
-      SNOWFLAKE_TEST_OAUTH_CLIENT_ID: $(SNOWFLAKE_TEST_OAUTH_CLIENT_ID)
-      SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET: $(SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET)
-    displayName: Run integration tests
-
-- job: BigQueryIntegrationTest
-  pool:
-    vmImage: 'vs2017-win2016'
-  dependsOn: PostgresIntegrationTest
-  condition: succeeded()
-  steps:
-  - task: UsePythonVersion@0
-    inputs:
-      versionSpec: '3.7'
-      architecture: 'x64'
-  - script: python -m pip install --upgrade pip && pip install tox
-    displayName: 'Install dependencies'
-  - script: python -m tox -e pywin-bigquery
-    env:
-      BIGQUERY_SERVICE_ACCOUNT_JSON: $(BIGQUERY_SERVICE_ACCOUNT_JSON)
-    displayName: Run integration tests
-
-- job: RedshiftIntegrationTest
-  pool:
-    vmImage: 'vs2017-win2016'
-  dependsOn: PostgresIntegrationTest
-  condition: succeeded()
-  steps:
-  - task: UsePythonVersion@0
-    inputs:
-      versionSpec: '3.7'
-      architecture: 'x64'
-
-  - script: python -m pip install --upgrade pip && pip install tox
-    displayName: 'Install dependencies'
-
-  - script: python -m tox -e pywin-redshift
-    env:
-      REDSHIFT_TEST_DBNAME: $(REDSHIFT_TEST_DBNAME)
-      REDSHIFT_TEST_PASS: $(REDSHIFT_TEST_PASS)
-      REDSHIFT_TEST_USER: $(REDSHIFT_TEST_USER)
-      REDSHIFT_TEST_PORT: $(REDSHIFT_TEST_PORT)
-      REDSHIFT_TEST_HOST: $(REDSHIFT_TEST_HOST)
-    displayName: Run integration tests
-
-- job: BuildWheel
-  pool:
-    vmImage: 'vs2017-win2016'
-  dependsOn:
-    - UnitTest
-    - PostgresIntegrationTest
-    - RedshiftIntegrationTest
-    - SnowflakeIntegrationTest
-    - BigQueryIntegrationTest
-  condition: succeeded()
-  steps:
-    - task: UsePythonVersion@0
-      inputs:
-        versionSpec: '3.7'
-        architecture: 'x64'
-    - script: python -m pip install --upgrade pip setuptools && python -m pip install -r requirements.txt && python -m pip install -r requirements-dev.txt
-      displayName: Install dependencies
-    - task: ShellScript@2
-      inputs:
-        scriptPath: scripts/build-wheels.sh
-    - task: CopyFiles@2
-      inputs:
-        contents: 'dist\?(*.whl|*.tar.gz)'
-        TargetFolder: '$(Build.ArtifactStagingDirectory)'
-    - task: PublishBuildArtifacts@1
-      inputs:
-        pathtoPublish: '$(Build.ArtifactStagingDirectory)'
-        artifactName: dists

converter.py

@@ -1,75 +0,0 @@
-#!/usr/bin/env python
-import json
-import yaml
-import sys
-import argparse
-from datetime import datetime, timezone
-import dbt.clients.registry as registry
-
-
-def yaml_type(fname):
-    with open(fname) as f:
-        return yaml.load(f)
-
-
-def parse_args():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--project", type=yaml_type, default="dbt_project.yml")
-    parser.add_argument("--namespace", required=True)
-    return parser.parse_args()
-
-
-def get_full_name(args):
-    return "{}/{}".format(args.namespace, args.project["name"])
-
-
-def init_project_in_packages(args, packages):
-    full_name = get_full_name(args)
-    if full_name not in packages:
-        packages[full_name] = {
-            "name": args.project["name"],
-            "namespace": args.namespace,
-            "latest": args.project["version"],
-            "assets": {},
-            "versions": {},
-        }
-    return packages[full_name]
-
-
-def add_version_to_package(args, project_json):
-    project_json["versions"][args.project["version"]] = {
-        "id": "{}/{}".format(get_full_name(args), args.project["version"]),
-        "name": args.project["name"],
-        "version": args.project["version"],
-        "description": "",
-        "published_at": datetime.now(timezone.utc).astimezone().isoformat(),
-        "packages": args.project.get("packages") or [],
-        "works_with": [],
-        "_source": {
-            "type": "github",
-            "url": "",
-            "readme": "",
-        },
-        "downloads": {
-            "tarball": "",
-            "format": "tgz",
-            "sha1": "",
-        },
-    }
-
-
-def main():
-    args = parse_args()
-    packages = registry.packages()
-    project_json = init_project_in_packages(args, packages)
-    if args.project["version"] in project_json["versions"]:
-        raise Exception(
-            "Version {} already in packages JSON".format(args.project["version"]),
-            file=sys.stderr,
-        )
-    add_version_to_package(args, project_json)
-    print(json.dumps(packages, indent=2))
-
-
-if __name__ == "__main__":
-    main()

core/MANIFEST.in

@@ -1 +1 @@
-recursive-include dbt/include *.py *.sql *.yml *.html *.md
+recursive-include dbt/include *.py *.sql *.yml *.html *.md .gitkeep .gitignore

core/dbt/adapters/base/column.py

@@ -8,10 +8,10 @@ from dbt.exceptions import RuntimeException
 @dataclass
 class Column:
     TYPE_LABELS: ClassVar[Dict[str, str]] = {
-        "STRING": "TEXT",
-        "TIMESTAMP": "TIMESTAMP",
-        "FLOAT": "FLOAT",
-        "INTEGER": "INT",
+        'STRING': 'TEXT',
+        'TIMESTAMP': 'TIMESTAMP',
+        'FLOAT': 'FLOAT',
+        'INTEGER': 'INT'
     }
     column: str
     dtype: str
@@ -24,7 +24,7 @@ class Column:
         return cls.TYPE_LABELS.get(dtype.upper(), dtype)
 
     @classmethod
-    def create(cls, name, label_or_dtype: str) -> "Column":
+    def create(cls, name, label_or_dtype: str) -> 'Column':
         column_type = cls.translate_type(label_or_dtype)
         return cls(name, column_type)
 
@@ -41,19 +41,14 @@ class Column:
         if self.is_string():
             return Column.string_type(self.string_size())
         elif self.is_numeric():
-            return Column.numeric_type(
-                self.dtype, self.numeric_precision, self.numeric_scale
-            )
+            return Column.numeric_type(self.dtype, self.numeric_precision,
+                                       self.numeric_scale)
         else:
             return self.dtype
 
     def is_string(self) -> bool:
-        return self.dtype.lower() in [
-            "text",
-            "character varying",
-            "character",
-            "varchar",
-        ]
+        return self.dtype.lower() in ['text', 'character varying', 'character',
+                                      'varchar']
 
     def is_number(self):
         return any([self.is_integer(), self.is_numeric(), self.is_float()])
@@ -61,45 +56,33 @@ class Column:
     def is_float(self):
         return self.dtype.lower() in [
             # floats
-            "real",
-            "float4",
-            "float",
-            "double precision",
-            "float8",
+            'real', 'float4', 'float', 'double precision', 'float8'
         ]
 
     def is_integer(self) -> bool:
         return self.dtype.lower() in [
             # real types
-            "smallint",
-            "integer",
-            "bigint",
-            "smallserial",
-            "serial",
-            "bigserial",
+            'smallint', 'integer', 'bigint',
+            'smallserial', 'serial', 'bigserial',
             # aliases
-            "int2",
-            "int4",
-            "int8",
-            "serial2",
-            "serial4",
-            "serial8",
+            'int2', 'int4', 'int8',
+            'serial2', 'serial4', 'serial8',
         ]
 
     def is_numeric(self) -> bool:
-        return self.dtype.lower() in ["numeric", "decimal"]
+        return self.dtype.lower() in ['numeric', 'decimal']
 
     def string_size(self) -> int:
         if not self.is_string():
             raise RuntimeException("Called string_size() on non-string field!")
 
-        if self.dtype == "text" or self.char_size is None:
+        if self.dtype == 'text' or self.char_size is None:
             # char_size should never be None. Handle it reasonably just in case
             return 256
         else:
             return int(self.char_size)
 
-    def can_expand_to(self, other_column: "Column") -> bool:
+    def can_expand_to(self, other_column: 'Column') -> bool:
         """returns True if this column can be expanded to the size of the
         other column"""
         if not self.is_string() or not other_column.is_string():
@@ -127,10 +110,12 @@ class Column:
         return "<Column {} ({})>".format(self.name, self.data_type)
 
     @classmethod
-    def from_description(cls, name: str, raw_data_type: str) -> "Column":
-        match = re.match(r"([^(]+)(\([^)]+\))?", raw_data_type)
+    def from_description(cls, name: str, raw_data_type: str) -> 'Column':
+        match = re.match(r'([^(]+)(\([^)]+\))?', raw_data_type)
         if match is None:
-            raise RuntimeException(f'Could not interpret data type "{raw_data_type}"')
+            raise RuntimeException(
+                f'Could not interpret data type "{raw_data_type}"'
+            )
         data_type, size_info = match.groups()
         char_size = None
         numeric_precision = None
@@ -138,7 +123,7 @@ class Column:
         if size_info is not None:
             # strip out the parentheses
             size_info = size_info[1:-1]
-            parts = size_info.split(",")
+            parts = size_info.split(',')
             if len(parts) == 1:
                 try:
                     char_size = int(parts[0])
@@ -163,4 +148,6 @@ class Column:
                         f'could not convert "{parts[1]}" to an integer'
                     )
 
-        return cls(name, data_type, char_size, numeric_precision, numeric_scale)
+        return cls(
+            name, data_type, char_size, numeric_precision, numeric_scale
+        )

core/dbt/adapters/base/connections.py

@@ -1,21 +1,18 @@
 import abc
 import os
-
 # multiprocessing.RLock is a function returning this type
 from multiprocessing.synchronize import RLock
 from threading import get_ident
-from typing import Dict, Tuple, Hashable, Optional, ContextManager, List, Union
+from typing import (
+    Dict, Tuple, Hashable, Optional, ContextManager, List, Union
+)
 
 import agate
 
 import dbt.exceptions
 from dbt.contracts.connection import (
-    Connection,
-    Identifier,
-    ConnectionState,
-    AdapterRequiredConfig,
-    LazyHandle,
-    AdapterResponse,
+    Connection, Identifier, ConnectionState,
+    AdapterRequiredConfig, LazyHandle, AdapterResponse
 )
 from dbt.contracts.graph.manifest import Manifest
 from dbt.adapters.base.query_headers import (
@@ -38,7 +35,6 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     You must also set the 'TYPE' class attribute with a class-unique constant
     string.
     """
-
     TYPE: str = NotImplemented
 
     def __init__(self, profile: AdapterRequiredConfig):
@@ -69,7 +65,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         key = self.get_thread_identifier()
         if key in self.thread_connections:
             raise dbt.exceptions.InternalException(
-                "In set_thread_connection, existing connection exists for {}"
+                'In set_thread_connection, existing connection exists for {}'
             )
         self.thread_connections[key] = conn
 
@@ -109,19 +105,18 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             underlying database.
         """
         raise dbt.exceptions.NotImplementedException(
-            "`exception_handler` is not implemented for this adapter!"
-        )
+            '`exception_handler` is not implemented for this adapter!')
 
     def set_connection_name(self, name: Optional[str] = None) -> Connection:
         conn_name: str
         if name is None:
             # if a name isn't specified, we'll re-use a single handle
             # named 'master'
-            conn_name = "master"
+            conn_name = 'master'
         else:
             if not isinstance(name, str):
                 raise dbt.exceptions.CompilerException(
-                    f"For connection name, got {name} - not a string!"
+                    f'For connection name, got {name} - not a string!'
                 )
             assert isinstance(name, str)
             conn_name = name
@@ -134,20 +129,20 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
                 state=ConnectionState.INIT,
                 transaction_open=False,
                 handle=None,
-                credentials=self.profile.credentials,
+                credentials=self.profile.credentials
             )
             self.set_thread_connection(conn)
 
-        if conn.name == conn_name and conn.state == "open":
+        if conn.name == conn_name and conn.state == 'open':
             return conn
 
-        logger.debug('Acquiring new {} connection "{}".'.format(self.TYPE, conn_name))
+        logger.debug(
+            'Acquiring new {} connection "{}".'.format(self.TYPE, conn_name))
 
-        if conn.state == "open":
+        if conn.state == 'open':
             logger.debug(
-                "Re-using an available connection from the pool (formerly {}).".format(
-                    conn.name
-                )
+                'Re-using an available connection from the pool (formerly {}).'
+                .format(conn.name)
             )
         else:
             conn.handle = LazyHandle(self.open)
@@ -159,7 +154,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     def cancel_open(self) -> Optional[List[str]]:
         """Cancel all open connections on the adapter. (passable)"""
         raise dbt.exceptions.NotImplementedException(
-            "`cancel_open` is not implemented for this adapter!"
+            '`cancel_open` is not implemented for this adapter!'
         )
 
     @abc.abstractclassmethod
@@ -173,7 +168,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         connection should not be in either in_use or available.
         """
         raise dbt.exceptions.NotImplementedException(
-            "`open` is not implemented for this adapter!"
+            '`open` is not implemented for this adapter!'
         )
 
     def release(self) -> None:
@@ -194,14 +189,12 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     def cleanup_all(self) -> None:
         with self.lock:
             for connection in self.thread_connections.values():
-                if connection.state not in {"closed", "init"}:
-                    logger.debug(
-                        "Connection '{}' was left open.".format(connection.name)
-                    )
+                if connection.state not in {'closed', 'init'}:
+                    logger.debug("Connection '{}' was left open."
+                                 .format(connection.name))
                 else:
-                    logger.debug(
-                        "Connection '{}' was properly closed.".format(connection.name)
-                    )
+                    logger.debug("Connection '{}' was properly closed."
+                                 .format(connection.name))
                 self.close(connection)
 
             # garbage collect these connections
@@ -211,14 +204,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     def begin(self) -> None:
         """Begin a transaction. (passable)"""
         raise dbt.exceptions.NotImplementedException(
-            "`begin` is not implemented for this adapter!"
+            '`begin` is not implemented for this adapter!'
         )
 
     @abc.abstractmethod
     def commit(self) -> None:
         """Commit a transaction. (passable)"""
         raise dbt.exceptions.NotImplementedException(
-            "`commit` is not implemented for this adapter!"
+            '`commit` is not implemented for this adapter!'
         )
 
     @classmethod
@@ -227,17 +220,20 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         try:
             connection.handle.rollback()
         except Exception:
-            logger.debug("Failed to rollback {}".format(connection.name), exc_info=True)
+            logger.debug(
+                'Failed to rollback {}'.format(connection.name),
+                exc_info=True
+            )
 
     @classmethod
     def _close_handle(cls, connection: Connection) -> None:
         """Perform the actual close operation."""
         # On windows, sometimes connection handles don't have a close() attr.
-        if hasattr(connection.handle, "close"):
-            logger.debug(f"On {connection.name}: Close")
+        if hasattr(connection.handle, 'close'):
+            logger.debug(f'On {connection.name}: Close')
             connection.handle.close()
         else:
-            logger.debug(f"On {connection.name}: No close available on handle")
+            logger.debug(f'On {connection.name}: No close available on handle')
 
     @classmethod
     def _rollback(cls, connection: Connection) -> None:
@@ -245,16 +241,16 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         if flags.STRICT_MODE:
             if not isinstance(connection, Connection):
                 raise dbt.exceptions.CompilerException(
-                    f"In _rollback, got {connection} - not a Connection!"
+                    f'In _rollback, got {connection} - not a Connection!'
                 )
 
         if connection.transaction_open is False:
             raise dbt.exceptions.InternalException(
-                f"Tried to rollback transaction on connection "
+                f'Tried to rollback transaction on connection '
                 f'"{connection.name}", but it does not have one open!'
             )
 
-        logger.debug(f"On {connection.name}: ROLLBACK")
+        logger.debug(f'On {connection.name}: ROLLBACK')
         cls._rollback_handle(connection)
 
         connection.transaction_open = False
@@ -264,7 +260,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         if flags.STRICT_MODE:
             if not isinstance(connection, Connection):
                 raise dbt.exceptions.CompilerException(
-                    f"In close, got {connection} - not a Connection!"
+                    f'In close, got {connection} - not a Connection!'
                 )
 
         # if the connection is in closed or init, there's nothing to do
@@ -272,7 +268,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             return connection
 
         if connection.transaction_open and connection.handle:
-            logger.debug("On {}: ROLLBACK".format(connection.name))
+            logger.debug('On {}: ROLLBACK'.format(connection.name))
             cls._rollback_handle(connection)
         connection.transaction_open = False
 
@@ -306,5 +302,5 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :rtype: Tuple[Union[str, AdapterResponse], agate.Table]
         """
         raise dbt.exceptions.NotImplementedException(
-            "`execute` is not implemented for this adapter!"
+            '`execute` is not implemented for this adapter!'
         )

core/dbt/adapters/base/impl.py

@@ -4,31 +4,17 @@ from contextlib import contextmanager
 from datetime import datetime
 from itertools import chain
 from typing import (
-    Optional,
-    Tuple,
-    Callable,
-    Iterable,
-    Type,
-    Dict,
-    Any,
-    List,
-    Mapping,
-    Iterator,
-    Union,
-    Set,
+    Optional, Tuple, Callable, Iterable, Type, Dict, Any, List, Mapping,
+    Iterator, Union, Set
 )
 
 import agate
 import pytz
 
 from dbt.exceptions import (
-    raise_database_error,
-    raise_compiler_error,
-    invalid_type_error,
+    raise_database_error, raise_compiler_error, invalid_type_error,
     get_relation_returned_multiple_results,
-    InternalException,
-    NotImplementedException,
-    RuntimeException,
+    InternalException, NotImplementedException, RuntimeException,
 )
 from dbt import flags
 
@@ -39,21 +25,19 @@ from dbt.adapters.protocol import (
 )
 from dbt.clients.agate_helper import empty_table, merge_tables, table_from_rows
 from dbt.clients.jinja import MacroGenerator
-from dbt.contracts.graph.compiled import CompileResultNode, CompiledSeedNode
+from dbt.contracts.graph.compiled import (
+    CompileResultNode, CompiledSeedNode
+)
 from dbt.contracts.graph.manifest import Manifest, MacroManifest
 from dbt.contracts.graph.parsed import ParsedSeedNode
 from dbt.exceptions import warn_or_error
-from dbt.node_types import NodeType
 from dbt.logger import GLOBAL_LOGGER as logger
 from dbt.utils import filter_null_values, executor
 
 from dbt.adapters.base.connections import Connection, AdapterResponse
 from dbt.adapters.base.meta import AdapterMeta, available
 from dbt.adapters.base.relation import (
-    ComponentName,
-    BaseRelation,
-    InformationSchema,
-    SchemaSearchMap,
+    ComponentName, BaseRelation, InformationSchema, SchemaSearchMap
 )
 from dbt.adapters.base import Column as BaseColumn
 from dbt.adapters.cache import RelationsCache
@@ -62,14 +46,15 @@ from dbt.adapters.cache import RelationsCache
 SeedModel = Union[ParsedSeedNode, CompiledSeedNode]
 
 
-GET_CATALOG_MACRO_NAME = "get_catalog"
-FRESHNESS_MACRO_NAME = "collect_freshness"
+GET_CATALOG_MACRO_NAME = 'get_catalog'
+FRESHNESS_MACRO_NAME = 'collect_freshness'
 
 
 def _expect_row_value(key: str, row: agate.Row):
     if key not in row.keys():
         raise InternalException(
-            'Got a row without "{}" column, columns: {}'.format(key, row.keys())
+            'Got a row without "{}" column, columns: {}'
+            .format(key, row.keys())
         )
     return row[key]
 
@@ -78,37 +63,40 @@ def _catalog_filter_schemas(manifest: Manifest) -> Callable[[agate.Row], bool]:
     """Return a function that takes a row and decides if the row should be
     included in the catalog output.
     """
-    schemas = frozenset((d.lower(), s.lower()) for d, s in manifest.get_used_schemas())
+    schemas = frozenset((d.lower(), s.lower())
+                        for d, s in manifest.get_used_schemas())
 
     def test(row: agate.Row) -> bool:
-        table_database = _expect_row_value("table_database", row)
-        table_schema = _expect_row_value("table_schema", row)
+        table_database = _expect_row_value('table_database', row)
+        table_schema = _expect_row_value('table_schema', row)
         # the schema may be present but None, which is not an error and should
         # be filtered out
         if table_schema is None:
             return False
         return (table_database.lower(), table_schema.lower()) in schemas
-
     return test
 
 
-def _utc(dt: Optional[datetime], source: BaseRelation, field_name: str) -> datetime:
+def _utc(
+    dt: Optional[datetime], source: BaseRelation, field_name: str
+) -> datetime:
     """If dt has a timezone, return a new datetime that's in UTC. Otherwise,
     assume the datetime is already for UTC and add the timezone.
     """
     if dt is None:
         raise raise_database_error(
             "Expected a non-null value when querying field '{}' of table "
-            " {} but received value 'null' instead".format(field_name, source)
-        )
+            " {} but received value 'null' instead".format(
+                field_name,
+                source))
 
-    elif not hasattr(dt, "tzinfo"):
+    elif not hasattr(dt, 'tzinfo'):
         raise raise_database_error(
             "Expected a timestamp value when querying field '{}' of table "
             "{} but received value of type '{}' instead".format(
-                field_name, source, type(dt).__name__
-            )
-        )
+                field_name,
+                source,
+                type(dt).__name__))
 
     elif dt.tzinfo:
         return dt.astimezone(pytz.UTC)
@@ -118,7 +106,7 @@ def _utc(dt: Optional[datetime], source: BaseRelation, field_name: str) -> datet
 
 def _relation_name(rel: Optional[BaseRelation]) -> str:
     if rel is None:
-        return "null relation"
+        return 'null relation'
     else:
         return str(rel)
 
@@ -159,7 +147,6 @@ class BaseAdapter(metaclass=AdapterMeta):
     Macros:
         - get_catalog
     """
-
     Relation: Type[BaseRelation] = BaseRelation
     Column: Type[BaseColumn] = BaseColumn
     ConnectionManager: Type[ConnectionManagerProtocol]
@@ -193,12 +180,12 @@ class BaseAdapter(metaclass=AdapterMeta):
         self.connections.commit_if_has_connection()
 
     def debug_query(self) -> None:
-        self.execute("select 1 as id")
+        self.execute('select 1 as id')
 
     def nice_connection_name(self) -> str:
         conn = self.connections.get_if_exists()
         if conn is None or conn.name is None:
-            return "<None>"
+            return '<None>'
         return conn.name
 
     @contextmanager
@@ -216,11 +203,13 @@ class BaseAdapter(metaclass=AdapterMeta):
                 self.connections.query_header.reset()
 
     @contextmanager
-    def connection_for(self, node: CompileResultNode) -> Iterator[None]:
+    def connection_for(
+        self, node: CompileResultNode
+    ) -> Iterator[None]:
         with self.connection_named(node.unique_id, node):
             yield
 
-    @available.parse(lambda *a, **k: ("", empty_table()))
+    @available.parse(lambda *a, **k: ('', empty_table()))
     def execute(
         self, sql: str, auto_begin: bool = False, fetch: bool = False
     ) -> Tuple[Union[str, AdapterResponse], agate.Table]:
@@ -234,10 +223,16 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: A tuple of the status and the results (empty if fetch=False).
         :rtype: Tuple[Union[str, AdapterResponse], agate.Table]
         """
-        return self.connections.execute(sql=sql, auto_begin=auto_begin, fetch=fetch)
+        return self.connections.execute(
+            sql=sql,
+            auto_begin=auto_begin,
+            fetch=fetch
+        )
 
-    @available.parse(lambda *a, **k: ("", empty_table()))
-    def get_partitions_metadata(self, table: str) -> Tuple[agate.Table]:
+    @available.parse(lambda *a, **k: ('', empty_table()))
+    def get_partitions_metadata(
+        self, table: str
+    ) -> Tuple[agate.Table]:
         """Obtain partitions metadata for a BigQuery partitioned table.
 
         :param str table_id: a partitioned table id, in standard SQL format.
@@ -245,7 +240,9 @@ class BaseAdapter(metaclass=AdapterMeta):
             https://cloud.google.com/bigquery/docs/creating-partitioned-tables#getting_partition_metadata_using_meta_tables.
         :rtype: agate.Table
         """
-        return self.connections.get_partitions_metadata(table=table)
+        return self.connections.get_partitions_metadata(
+            table=table
+        )
 
     ###
     # Methods that should never be overridden
@@ -275,9 +272,8 @@ class BaseAdapter(metaclass=AdapterMeta):
     def load_macro_manifest(self) -> MacroManifest:
         if self._macro_manifest_lazy is None:
             # avoid a circular import
-            from dbt.parser.manifest import load_macro_manifest
-
-            manifest = load_macro_manifest(
+            from dbt.parser.manifest import ManifestLoader
+            manifest = ManifestLoader.load_macros(
                 self.config, self.connections.set_query_header
             )
             self._macro_manifest_lazy = manifest
@@ -297,9 +293,8 @@ class BaseAdapter(metaclass=AdapterMeta):
             return False
         elif (database, schema) not in self.cache:
             logger.debug(
-                'On "{}": cache miss for schema "{}.{}", this is inefficient'.format(
-                    self.nice_connection_name(), database, schema
-                )
+                'On "{}": cache miss for schema "{}.{}", this is inefficient'
+                .format(self.nice_connection_name(), database, schema)
             )
             return False
         else:
@@ -314,8 +309,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             self.Relation.create_from(self.config, node).without_identifier()
             for node in manifest.nodes.values()
             if (
-                node.resource_type in NodeType.executable()
-                and not node.is_ephemeral_model
+                node.is_relational and not node.is_ephemeral_model
             )
         }
 
@@ -355,9 +349,9 @@ class BaseAdapter(metaclass=AdapterMeta):
             for cache_schema in cache_schemas:
                 fut = tpe.submit_connected(
                     self,
-                    f"list_{cache_schema.database}_{cache_schema.schema}",
+                    f'list_{cache_schema.database}_{cache_schema.schema}',
                     self.list_relations_without_caching,
-                    cache_schema,
+                    cache_schema
                 )
                 futures.append(fut)
 
@@ -375,7 +369,9 @@ class BaseAdapter(metaclass=AdapterMeta):
             cache_update.add((relation.database, relation.schema))
         self.cache.update_schemas(cache_update)
 
-    def set_relations_cache(self, manifest: Manifest, clear: bool = False) -> None:
+    def set_relations_cache(
+        self, manifest: Manifest, clear: bool = False
+    ) -> None:
         """Run a query that gets a populated cache of the relations in the
         database and set the cache on this adapter.
         """
@@ -393,12 +389,12 @@ class BaseAdapter(metaclass=AdapterMeta):
         if relation is None:
             name = self.nice_connection_name()
             raise_compiler_error(
-                "Attempted to cache a null relation for {}".format(name)
+                'Attempted to cache a null relation for {}'.format(name)
             )
         if flags.USE_CACHE:
             self.cache.add(relation)
         # so jinja doesn't render things
-        return ""
+        return ''
 
     @available
     def cache_dropped(self, relation: Optional[BaseRelation]) -> str:
@@ -408,11 +404,11 @@ class BaseAdapter(metaclass=AdapterMeta):
         if relation is None:
             name = self.nice_connection_name()
             raise_compiler_error(
-                "Attempted to drop a null relation for {}".format(name)
+                'Attempted to drop a null relation for {}'.format(name)
             )
         if flags.USE_CACHE:
             self.cache.drop(relation)
-        return ""
+        return ''
 
     @available
     def cache_renamed(
@@ -428,12 +424,13 @@ class BaseAdapter(metaclass=AdapterMeta):
             src_name = _relation_name(from_relation)
             dst_name = _relation_name(to_relation)
             raise_compiler_error(
-                "Attempted to rename {} to {} for {}".format(src_name, dst_name, name)
+                'Attempted to rename {} to {} for {}'
+                .format(src_name, dst_name, name)
             )
 
         if flags.USE_CACHE:
             self.cache.rename(from_relation, to_relation)
-        return ""
+        return ''
 
     ###
     # Abstract methods for database-specific values, attributes, and types
@@ -442,13 +439,12 @@ class BaseAdapter(metaclass=AdapterMeta):
     def date_function(cls) -> str:
         """Get the date function used by this adapter's database."""
         raise NotImplementedException(
-            "`date_function` is not implemented for this adapter!"
-        )
+            '`date_function` is not implemented for this adapter!')
 
     @abc.abstractclassmethod
     def is_cancelable(cls) -> bool:
         raise NotImplementedException(
-            "`is_cancelable` is not implemented for this adapter!"
+            '`is_cancelable` is not implemented for this adapter!'
         )
 
     ###
@@ -458,7 +454,7 @@ class BaseAdapter(metaclass=AdapterMeta):
     def list_schemas(self, database: str) -> List[str]:
         """Get a list of existing schemas in database"""
         raise NotImplementedException(
-            "`list_schemas` is not implemented for this adapter!"
+            '`list_schemas` is not implemented for this adapter!'
         )
 
     @available.parse(lambda *a, **k: False)
@@ -469,7 +465,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         and adapters should implement it if there is an optimized path (and
         there probably is)
         """
-        search = (s.lower() for s in self.list_schemas(database=database))
+        search = (
+            s.lower() for s in
+            self.list_schemas(database=database)
+        )
         return schema.lower() in search
 
     ###
@@ -483,7 +482,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         *Implementors must call self.cache.drop() to preserve cache state!*
         """
         raise NotImplementedException(
-            "`drop_relation` is not implemented for this adapter!"
+            '`drop_relation` is not implemented for this adapter!'
         )
 
     @abc.abstractmethod
@@ -491,7 +490,7 @@ class BaseAdapter(metaclass=AdapterMeta):
     def truncate_relation(self, relation: BaseRelation) -> None:
         """Truncate the given relation."""
         raise NotImplementedException(
-            "`truncate_relation` is not implemented for this adapter!"
+            '`truncate_relation` is not implemented for this adapter!'
         )
 
     @abc.abstractmethod
@@ -504,30 +503,36 @@ class BaseAdapter(metaclass=AdapterMeta):
         Implementors must call self.cache.rename() to preserve cache state.
         """
         raise NotImplementedException(
-            "`rename_relation` is not implemented for this adapter!"
+            '`rename_relation` is not implemented for this adapter!'
         )
 
     @abc.abstractmethod
     @available.parse_list
-    def get_columns_in_relation(self, relation: BaseRelation) -> List[BaseColumn]:
-        """Get a list of the columns in the given Relation."""
+    def get_columns_in_relation(
+        self, relation: BaseRelation
+    ) -> List[BaseColumn]:
+        """Get a list of the columns in the given Relation. """
         raise NotImplementedException(
-            "`get_columns_in_relation` is not implemented for this adapter!"
+            '`get_columns_in_relation` is not implemented for this adapter!'
         )
 
-    @available.deprecated("get_columns_in_relation", lambda *a, **k: [])
-    def get_columns_in_table(self, schema: str, identifier: str) -> List[BaseColumn]:
+    @available.deprecated('get_columns_in_relation', lambda *a, **k: [])
+    def get_columns_in_table(
+        self, schema: str, identifier: str
+    ) -> List[BaseColumn]:
         """DEPRECATED: Get a list of the columns in the given table."""
         relation = self.Relation.create(
             database=self.config.credentials.database,
             schema=schema,
             identifier=identifier,
-            quote_policy=self.config.quoting,
+            quote_policy=self.config.quoting
         )
         return self.get_columns_in_relation(relation)
 
     @abc.abstractmethod
-    def expand_column_types(self, goal: BaseRelation, current: BaseRelation) -> None:
+    def expand_column_types(
+        self, goal: BaseRelation, current: BaseRelation
+    ) -> None:
         """Expand the current table's types to match the goal table. (passable)
 
         :param self.Relation goal: A relation that currently exists in the
@@ -536,7 +541,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             database with columns of unspecified types.
         """
         raise NotImplementedException(
-            "`expand_target_column_types` is not implemented for this adapter!"
+            '`expand_target_column_types` is not implemented for this adapter!'
         )
 
     @abc.abstractmethod
@@ -553,7 +558,8 @@ class BaseAdapter(metaclass=AdapterMeta):
         :rtype: List[self.Relation]
         """
         raise NotImplementedException(
-            "`list_relations_without_caching` is not implemented for this " "adapter!"
+            '`list_relations_without_caching` is not implemented for this '
+            'adapter!'
         )
 
     ###
@@ -568,33 +574,32 @@ class BaseAdapter(metaclass=AdapterMeta):
         """
         if not isinstance(from_relation, self.Relation):
             invalid_type_error(
-                method_name="get_missing_columns",
-                arg_name="from_relation",
+                method_name='get_missing_columns',
+                arg_name='from_relation',
                 got_value=from_relation,
-                expected_type=self.Relation,
-            )
+                expected_type=self.Relation)
 
         if not isinstance(to_relation, self.Relation):
             invalid_type_error(
-                method_name="get_missing_columns",
-                arg_name="to_relation",
+                method_name='get_missing_columns',
+                arg_name='to_relation',
                 got_value=to_relation,
-                expected_type=self.Relation,
-            )
+                expected_type=self.Relation)
 
         from_columns = {
-            col.name: col for col in self.get_columns_in_relation(from_relation)
+            col.name: col for col in
+            self.get_columns_in_relation(from_relation)
         }
 
         to_columns = {
-            col.name: col for col in self.get_columns_in_relation(to_relation)
+            col.name: col for col in
+            self.get_columns_in_relation(to_relation)
         }
 
         missing_columns = set(from_columns.keys()) - set(to_columns.keys())
 
         return [
-            col
-            for (col_name, col) in from_columns.items()
+            col for (col_name, col) in from_columns.items()
             if col_name in missing_columns
         ]
 
@@ -609,19 +614,18 @@ class BaseAdapter(metaclass=AdapterMeta):
         """
         if not isinstance(relation, self.Relation):
             invalid_type_error(
-                method_name="valid_snapshot_target",
-                arg_name="relation",
+                method_name='valid_snapshot_target',
+                arg_name='relation',
                 got_value=relation,
-                expected_type=self.Relation,
-            )
+                expected_type=self.Relation)
 
         columns = self.get_columns_in_relation(relation)
         names = set(c.name.lower() for c in columns)
-        expanded_keys = ("scd_id", "valid_from", "valid_to")
+        expanded_keys = ('scd_id', 'valid_from', 'valid_to')
         extra = []
         missing = []
         for legacy in expanded_keys:
-            desired = "dbt_" + legacy
+            desired = 'dbt_' + legacy
             if desired not in names:
                 missing.append(desired)
                 if legacy in names:
@@ -631,13 +635,13 @@ class BaseAdapter(metaclass=AdapterMeta):
             if extra:
                 msg = (
                     'Snapshot target has ("{}") but not ("{}") - is it an '
-                    "unmigrated previous version archive?".format(
-                        '", "'.join(extra), '", "'.join(missing)
-                    )
+                    'unmigrated previous version archive?'
+                    .format('", "'.join(extra), '", "'.join(missing))
                 )
             else:
-                msg = 'Snapshot target is not a snapshot table (missing "{}")'.format(
-                    '", "'.join(missing)
+                msg = (
+                    'Snapshot target is not a snapshot table (missing "{}")'
+                    .format('", "'.join(missing))
                 )
             raise_compiler_error(msg)
 
@@ -647,19 +651,17 @@ class BaseAdapter(metaclass=AdapterMeta):
     ) -> None:
         if not isinstance(from_relation, self.Relation):
             invalid_type_error(
-                method_name="expand_target_column_types",
-                arg_name="from_relation",
+                method_name='expand_target_column_types',
+                arg_name='from_relation',
                 got_value=from_relation,
-                expected_type=self.Relation,
-            )
+                expected_type=self.Relation)
 
         if not isinstance(to_relation, self.Relation):
             invalid_type_error(
-                method_name="expand_target_column_types",
-                arg_name="to_relation",
+                method_name='expand_target_column_types',
+                arg_name='to_relation',
                 got_value=to_relation,
-                expected_type=self.Relation,
-            )
+                expected_type=self.Relation)
 
         self.expand_column_types(from_relation, to_relation)
 
@@ -672,41 +674,38 @@ class BaseAdapter(metaclass=AdapterMeta):
         schema_relation = self.Relation.create(
             database=database,
             schema=schema,
-            identifier="",
-            quote_policy=self.config.quoting,
+            identifier='',
+            quote_policy=self.config.quoting
         ).without_identifier()
 
         # we can't build the relations cache because we don't have a
         # manifest so we can't run any operations.
-        relations = self.list_relations_without_caching(schema_relation)
-
-        logger.debug(
-            "with database={}, schema={}, relations={}".format(
-                database, schema, relations
-            )
+        relations = self.list_relations_without_caching(
+            schema_relation
         )
+
+        logger.debug('with database={}, schema={}, relations={}'
+                     .format(database, schema, relations))
         return relations
 
     def _make_match_kwargs(
         self, database: str, schema: str, identifier: str
     ) -> Dict[str, str]:
         quoting = self.config.quoting
-        if identifier is not None and quoting["identifier"] is False:
+        if identifier is not None and quoting['identifier'] is False:
             identifier = identifier.lower()
 
-        if schema is not None and quoting["schema"] is False:
+        if schema is not None and quoting['schema'] is False:
             schema = schema.lower()
 
-        if database is not None and quoting["database"] is False:
+        if database is not None and quoting['database'] is False:
             database = database.lower()
 
-        return filter_null_values(
-            {
-                "database": database,
-                "identifier": identifier,
-                "schema": schema,
-            }
-        )
+        return filter_null_values({
+            'database': database,
+            'identifier': identifier,
+            'schema': schema,
+        })
 
     def _make_match(
         self,
@@ -732,22 +731,25 @@ class BaseAdapter(metaclass=AdapterMeta):
     ) -> Optional[BaseRelation]:
         relations_list = self.list_relations(database, schema)
 
-        matches = self._make_match(relations_list, database, schema, identifier)
+        matches = self._make_match(relations_list, database, schema,
+                                   identifier)
 
         if len(matches) > 1:
             kwargs = {
-                "identifier": identifier,
-                "schema": schema,
-                "database": database,
+                'identifier': identifier,
+                'schema': schema,
+                'database': database,
             }
-            get_relation_returned_multiple_results(kwargs, matches)
+            get_relation_returned_multiple_results(
+                kwargs, matches
+            )
 
         elif matches:
             return matches[0]
 
         return None
 
-    @available.deprecated("get_relation", lambda *a, **k: False)
+    @available.deprecated('get_relation', lambda *a, **k: False)
     def already_exists(self, schema: str, name: str) -> bool:
         """DEPRECATED: Return if a model already exists in the database"""
         database = self.config.credentials.database
@@ -763,7 +765,7 @@ class BaseAdapter(metaclass=AdapterMeta):
     def create_schema(self, relation: BaseRelation):
         """Create the given schema if it does not exist."""
         raise NotImplementedException(
-            "`create_schema` is not implemented for this adapter!"
+            '`create_schema` is not implemented for this adapter!'
         )
 
     @abc.abstractmethod
@@ -771,14 +773,16 @@ class BaseAdapter(metaclass=AdapterMeta):
     def drop_schema(self, relation: BaseRelation):
         """Drop the given schema (and everything in it) if it exists."""
         raise NotImplementedException(
-            "`drop_schema` is not implemented for this adapter!"
+            '`drop_schema` is not implemented for this adapter!'
         )
 
     @available
     @abc.abstractclassmethod
     def quote(cls, identifier: str) -> str:
         """Quote the given identifier, as appropriate for the database."""
-        raise NotImplementedException("`quote` is not implemented for this adapter!")
+        raise NotImplementedException(
+            '`quote` is not implemented for this adapter!'
+        )
 
     @available
     def quote_as_configured(self, identifier: str, quote_key: str) -> str:
@@ -800,17 +804,19 @@ class BaseAdapter(metaclass=AdapterMeta):
             return identifier
 
     @available
-    def quote_seed_column(self, column: str, quote_config: Optional[bool]) -> str:
+    def quote_seed_column(
+        self, column: str, quote_config: Optional[bool]
+    ) -> str:
         # this is the default for now
         quote_columns: bool = False
         if isinstance(quote_config, bool):
             quote_columns = quote_config
         elif quote_config is None:
-            deprecations.warn("column-quoting-unset")
+            deprecations.warn('column-quoting-unset')
         else:
             raise_compiler_error(
                 f'The seed configuration value of "quote_columns" has an '
-                f"invalid type {type(quote_config)}"
+                f'invalid type {type(quote_config)}'
             )
 
         if quote_columns:
@@ -823,7 +829,9 @@ class BaseAdapter(metaclass=AdapterMeta):
     # converting agate types into their sql equivalents.
     ###
     @abc.abstractclassmethod
-    def convert_text_type(cls, agate_table: agate.Table, col_idx: int) -> str:
+    def convert_text_type(
+        cls, agate_table: agate.Table, col_idx: int
+    ) -> str:
         """Return the type in the database that best maps to the agate.Text
         type for the given agate table and column index.
 
@@ -832,11 +840,12 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The name of the type in the database
         """
         raise NotImplementedException(
-            "`convert_text_type` is not implemented for this adapter!"
-        )
+            '`convert_text_type` is not implemented for this adapter!')
 
     @abc.abstractclassmethod
-    def convert_number_type(cls, agate_table: agate.Table, col_idx: int) -> str:
+    def convert_number_type(
+        cls, agate_table: agate.Table, col_idx: int
+    ) -> str:
         """Return the type in the database that best maps to the agate.Number
         type for the given agate table and column index.
 
@@ -845,11 +854,12 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The name of the type in the database
         """
         raise NotImplementedException(
-            "`convert_number_type` is not implemented for this adapter!"
-        )
+            '`convert_number_type` is not implemented for this adapter!')
 
     @abc.abstractclassmethod
-    def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str:
+    def convert_boolean_type(
+        cls, agate_table: agate.Table, col_idx: int
+    ) -> str:
         """Return the type in the database that best maps to the agate.Boolean
         type for the given agate table and column index.
 
@@ -858,11 +868,12 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The name of the type in the database
         """
         raise NotImplementedException(
-            "`convert_boolean_type` is not implemented for this adapter!"
-        )
+            '`convert_boolean_type` is not implemented for this adapter!')
 
     @abc.abstractclassmethod
-    def convert_datetime_type(cls, agate_table: agate.Table, col_idx: int) -> str:
+    def convert_datetime_type(
+        cls, agate_table: agate.Table, col_idx: int
+    ) -> str:
         """Return the type in the database that best maps to the agate.DateTime
         type for the given agate table and column index.
 
@@ -871,8 +882,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The name of the type in the database
         """
         raise NotImplementedException(
-            "`convert_datetime_type` is not implemented for this adapter!"
-        )
+            '`convert_datetime_type` is not implemented for this adapter!')
 
     @abc.abstractclassmethod
     def convert_date_type(cls, agate_table: agate.Table, col_idx: int) -> str:
@@ -884,8 +894,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The name of the type in the database
         """
         raise NotImplementedException(
-            "`convert_date_type` is not implemented for this adapter!"
-        )
+            '`convert_date_type` is not implemented for this adapter!')
 
     @abc.abstractclassmethod
     def convert_time_type(cls, agate_table: agate.Table, col_idx: int) -> str:
@@ -897,12 +906,13 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The name of the type in the database
         """
         raise NotImplementedException(
-            "`convert_time_type` is not implemented for this adapter!"
-        )
+            '`convert_time_type` is not implemented for this adapter!')
 
     @available
     @classmethod
-    def convert_type(cls, agate_table: agate.Table, col_idx: int) -> Optional[str]:
+    def convert_type(
+        cls, agate_table: agate.Table, col_idx: int
+    ) -> Optional[str]:
         return cls.convert_agate_type(agate_table, col_idx)
 
     @classmethod
@@ -951,7 +961,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param release: Ignored.
         """
         if release is not False:
-            deprecations.warn("execute-macro-release")
+            deprecations.warn('execute-macro-release')
         if kwargs is None:
             kwargs = {}
         if context_override is None:
@@ -965,27 +975,28 @@ class BaseAdapter(metaclass=AdapterMeta):
         )
         if macro is None:
             if project is None:
-                package_name = "any package"
+                package_name = 'any package'
             else:
                 package_name = 'the "{}" package'.format(project)
 
             raise RuntimeException(
-                'dbt could not find a macro with the name "{}" in {}'.format(
-                    macro_name, package_name
-                )
+                'dbt could not find a macro with the name "{}" in {}'
+                .format(macro_name, package_name)
             )
         # This causes a reference cycle, as generate_runtime_macro()
         # ends up calling get_adapter, so the import has to be here.
         from dbt.context.providers import generate_runtime_macro
-
         macro_context = generate_runtime_macro(
-            macro=macro, config=self.config, manifest=manifest, package_name=project
+            macro=macro,
+            config=self.config,
+            manifest=manifest,
+            package_name=project
         )
         macro_context.update(context_override)
 
         macro_function = MacroGenerator(macro, macro_context)
 
-        with self.connections.exception_handler(f"macro {macro_name}"):
+        with self.connections.exception_handler(f'macro {macro_name}'):
             result = macro_function(**kwargs)
         return result
 
@@ -1000,7 +1011,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         table = table_from_rows(
             table.rows,
             table.column_names,
-            text_only_columns=["table_database", "table_schema", "table_name"],
+            text_only_columns=['table_database', 'table_schema', 'table_name']
         )
         return table.where(_catalog_filter_schemas(manifest))
 
@@ -1011,7 +1022,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         manifest: Manifest,
     ) -> agate.Table:
 
-        kwargs = {"information_schema": information_schema, "schemas": schemas}
+        kwargs = {
+            'information_schema': information_schema,
+            'schemas': schemas
+        }
         table = self.execute_macro(
             GET_CATALOG_MACRO_NAME,
             kwargs=kwargs,
@@ -1023,7 +1037,9 @@ class BaseAdapter(metaclass=AdapterMeta):
         results = self._catalog_filter_table(table, manifest)
         return results
 
-    def get_catalog(self, manifest: Manifest) -> Tuple[agate.Table, List[Exception]]:
+    def get_catalog(
+        self, manifest: Manifest
+    ) -> Tuple[agate.Table, List[Exception]]:
         schema_map = self._get_catalog_schemas(manifest)
 
         with executor(self.config) as tpe:
@@ -1031,10 +1047,14 @@ class BaseAdapter(metaclass=AdapterMeta):
             for info, schemas in schema_map.items():
                 if len(schemas) == 0:
                     continue
-                name = ".".join([str(info.database), "information_schema"])
+                name = '.'.join([
+                    str(info.database),
+                    'information_schema'
+                ])
 
                 fut = tpe.submit_connected(
-                    self, name, self._get_one_catalog, info, schemas, manifest
+                    self, name,
+                    self._get_one_catalog, info, schemas, manifest
                 )
                 futures.append(fut)
 
@@ -1051,18 +1071,20 @@ class BaseAdapter(metaclass=AdapterMeta):
         source: BaseRelation,
         loaded_at_field: str,
         filter: Optional[str],
-        manifest: Optional[Manifest] = None,
+        manifest: Optional[Manifest] = None
     ) -> Dict[str, Any]:
         """Calculate the freshness of sources in dbt, and return it"""
         kwargs: Dict[str, Any] = {
-            "source": source,
-            "loaded_at_field": loaded_at_field,
-            "filter": filter,
+            'source': source,
+            'loaded_at_field': loaded_at_field,
+            'filter': filter,
         }
 
         # run the macro
         table = self.execute_macro(
-            FRESHNESS_MACRO_NAME, kwargs=kwargs, manifest=manifest
+            FRESHNESS_MACRO_NAME,
+            kwargs=kwargs,
+            manifest=manifest
         )
         # now we have a 1-row table of the maximum `loaded_at_field` value and
         # the current time according to the db.
@@ -1082,9 +1104,9 @@ class BaseAdapter(metaclass=AdapterMeta):
         snapshotted_at = _utc(table[0][1], source, loaded_at_field)
         age = (snapshotted_at - max_loaded_at).total_seconds()
         return {
-            "max_loaded_at": max_loaded_at,
-            "snapshotted_at": snapshotted_at,
-            "age": age,
+            'max_loaded_at': max_loaded_at,
+            'snapshotted_at': snapshotted_at,
+            'age': age,
         }
 
     def pre_model_hook(self, config: Mapping[str, Any]) -> Any:
@@ -1114,7 +1136,6 @@ class BaseAdapter(metaclass=AdapterMeta):
 
     def get_compiler(self):
         from dbt.compilation import Compiler
-
         return Compiler(self.config)
 
     # Methods used in adapter tests
@@ -1125,13 +1146,13 @@ class BaseAdapter(metaclass=AdapterMeta):
         clause: str,
         where_clause: Optional[str] = None,
     ) -> str:
-        clause = f"update {dst_name} set {dst_column} = {clause}"
+        clause = f'update {dst_name} set {dst_column} = {clause}'
         if where_clause is not None:
-            clause += f" where {where_clause}"
+            clause += f' where {where_clause}'
         return clause
 
     def timestamp_add_sql(
-        self, add_to: str, number: int = 1, interval: str = "hour"
+        self, add_to: str, number: int = 1, interval: str = 'hour'
     ) -> str:
         # for backwards compatibility, we're compelled to set some sort of
         # default. A lot of searching has lead me to believe that the
@@ -1140,24 +1161,23 @@ class BaseAdapter(metaclass=AdapterMeta):
         return f"{add_to} + interval '{number} {interval}'"
 
     def string_add_sql(
-        self,
-        add_to: str,
-        value: str,
-        location="append",
+        self, add_to: str, value: str, location='append',
     ) -> str:
-        if location == "append":
+        if location == 'append':
             return f"{add_to} || '{value}'"
-        elif location == "prepend":
+        elif location == 'prepend':
             return f"'{value}' || {add_to}"
         else:
-            raise RuntimeException(f'Got an unexpected location value of "{location}"')
+            raise RuntimeException(
+                f'Got an unexpected location value of "{location}"'
+            )
 
     def get_rows_different_sql(
         self,
         relation_a: BaseRelation,
         relation_b: BaseRelation,
         column_names: Optional[List[str]] = None,
-        except_operator: str = "EXCEPT",
+        except_operator: str = 'EXCEPT',
     ) -> str:
         """Generate SQL for a query that returns a single row with a two
         columns: the number of rows that are different between the two
@@ -1170,7 +1190,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             names = sorted((self.quote(c.name) for c in columns))
         else:
             names = sorted((self.quote(n) for n in column_names))
-        columns_csv = ", ".join(names)
+        columns_csv = ', '.join(names)
 
         sql = COLUMNS_EQUAL_SQL.format(
             columns=columns_csv,
@@ -1182,7 +1202,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         return sql
 
 
-COLUMNS_EQUAL_SQL = """
+COLUMNS_EQUAL_SQL = '''
 with diff_count as (
     SELECT
         1 as id,
@@ -1208,11 +1228,11 @@ select
     diff_count.num_missing as num_mismatched
 from row_count_diff
 join diff_count using (id)
-""".strip()
+'''.strip()
 
 
 def catch_as_completed(
-    futures,  # typing: List[Future[agate.Table]]
+    futures  # typing: List[Future[agate.Table]]
 ) -> Tuple[agate.Table, List[Exception]]:
 
     # catalogs: agate.Table = agate.Table(rows=[])
@@ -1225,10 +1245,15 @@ def catch_as_completed(
         if exc is None:
             catalog = future.result()
             tables.append(catalog)
-        elif isinstance(exc, KeyboardInterrupt) or not isinstance(exc, Exception):
+        elif (
+            isinstance(exc, KeyboardInterrupt) or
+            not isinstance(exc, Exception)
+        ):
             raise exc
         else:
-            warn_or_error(f"Encountered an error while generating catalog: {str(exc)}")
+            warn_or_error(
+                f'Encountered an error while generating catalog: {str(exc)}'
+            )
             # exc is not None, derives from Exception, and isn't ctrl+c
             exceptions.append(exc)
     return merge_tables(tables), exceptions

core/dbt/adapters/base/meta.py

@@ -30,11 +30,9 @@ class _Available:
             x.update(big_expensive_db_query())
             return x
         """
-
         def inner(func):
             func._parse_replacement_ = parse_replacement
             return self(func)
-
         return inner
 
     def deprecated(
@@ -59,14 +57,13 @@ class _Available:
         The optional parse_replacement, if provided, will provide a parse-time
         replacement for the actual method (see `available.parse`).
         """
-
         def wrapper(func):
             func_name = func.__name__
             renamed_method(func_name, supported_name)
 
             @wraps(func)
             def inner(*args, **kwargs):
-                warn("adapter:{}".format(func_name))
+                warn('adapter:{}'.format(func_name))
                 return func(*args, **kwargs)
 
             if parse_replacement:
@@ -74,7 +71,6 @@ class _Available:
             else:
                 available_function = self
             return available_function(inner)
-
         return wrapper
 
     def parse_none(self, func: Callable) -> Callable:
@@ -113,14 +109,14 @@ class AdapterMeta(abc.ABCMeta):
 
         # collect base class data first
         for base in bases:
-            available.update(getattr(base, "_available_", set()))
-            replacements.update(getattr(base, "_parse_replacements_", set()))
+            available.update(getattr(base, '_available_', set()))
+            replacements.update(getattr(base, '_parse_replacements_', set()))
 
         # override with local data if it exists
         for name, value in namespace.items():
-            if getattr(value, "_is_available_", False):
+            if getattr(value, '_is_available_', False):
                 available.add(name)
-            parse_replacement = getattr(value, "_parse_replacement_", None)
+            parse_replacement = getattr(value, '_parse_replacement_', None)
             if parse_replacement is not None:
                 replacements[name] = parse_replacement
 

core/dbt/adapters/base/plugin.py

@@ -8,10 +8,11 @@ from dbt.adapters.protocol import AdapterProtocol
 def project_name_from_path(include_path: str) -> str:
     # avoid an import cycle
     from dbt.config.project import Project
-
     partial = Project.partial_load(include_path)
     if partial.project_name is None:
-        raise CompilationException(f"Invalid project at {include_path}: name not set!")
+        raise CompilationException(
+            f'Invalid project at {include_path}: name not set!'
+        )
     return partial.project_name
 
 
@@ -22,13 +23,12 @@ class AdapterPlugin:
     :param dependencies: A list of adapter names that this adapter depends
         upon.
     """
-
     def __init__(
         self,
         adapter: Type[AdapterProtocol],
         credentials: Type[Credentials],
         include_path: str,
-        dependencies: Optional[List[str]] = None,
+        dependencies: Optional[List[str]] = None
     ):
 
         self.adapter: Type[AdapterProtocol] = adapter

core/dbt/adapters/base/query_headers.py

@@ -15,7 +15,7 @@ class NodeWrapper:
         self._inner_node = node
 
     def __getattr__(self, name):
-        return getattr(self._inner_node, name, "")
+        return getattr(self._inner_node, name, '')
 
 
 class _QueryComment(local):
@@ -24,7 +24,6 @@ class _QueryComment(local):
         - the current thread's query comment.
         - a source_name indicating what set the current thread's query comment
     """
-
     def __init__(self, initial):
         self.query_comment: Optional[str] = initial
         self.append = False
@@ -36,16 +35,16 @@ class _QueryComment(local):
         if self.append:
             # replace last ';' with '<comment>;'
             sql = sql.rstrip()
-            if sql[-1] == ";":
+            if sql[-1] == ';':
                 sql = sql[:-1]
-                return "{}\n/* {} */;".format(sql, self.query_comment.strip())
+                return '{}\n/* {} */;'.format(sql, self.query_comment.strip())
 
-            return "{}\n/* {} */".format(sql, self.query_comment.strip())
+            return '{}\n/* {} */'.format(sql, self.query_comment.strip())
 
-        return "/* {} */\n{}".format(self.query_comment.strip(), sql)
+        return '/* {} */\n{}'.format(self.query_comment.strip(), sql)
 
     def set(self, comment: Optional[str], append: bool):
-        if isinstance(comment, str) and "*/" in comment:
+        if isinstance(comment, str) and '*/' in comment:
             # tell the user "no" so they don't hurt themselves by writing
             # garbage
             raise RuntimeException(
@@ -64,17 +63,15 @@ class MacroQueryStringSetter:
         self.config = config
 
         comment_macro = self._get_comment_macro()
-        self.generator: QueryStringFunc = lambda name, model: ""
+        self.generator: QueryStringFunc = lambda name, model: ''
         # if the comment value was None or the empty string, just skip it
         if comment_macro:
             assert isinstance(comment_macro, str)
-            macro = "\n".join(
-                (
-                    "{%- macro query_comment_macro(connection_name, node) -%}",
-                    comment_macro,
-                    "{% endmacro %}",
-                )
-            )
+            macro = '\n'.join((
+                '{%- macro query_comment_macro(connection_name, node) -%}',
+                comment_macro,
+                '{% endmacro %}'
+            ))
             ctx = self._get_context()
             self.generator = QueryStringGenerator(macro, ctx)
         self.comment = _QueryComment(None)
@@ -90,7 +87,7 @@ class MacroQueryStringSetter:
         return self.comment.add(sql)
 
     def reset(self):
-        self.set("master", None)
+        self.set('master', None)
 
     def set(self, name: str, node: Optional[CompileResultNode]):
         wrapped: Optional[NodeWrapper] = None

core/dbt/adapters/base/relation.py

@@ -1,16 +1,13 @@
 from collections.abc import Hashable
 from dataclasses import dataclass
-from typing import Optional, TypeVar, Any, Type, Dict, Union, Iterator, Tuple, Set
+from typing import (
+    Optional, TypeVar, Any, Type, Dict, Union, Iterator, Tuple, Set
+)
 
 from dbt.contracts.graph.compiled import CompiledNode
 from dbt.contracts.graph.parsed import ParsedSourceDefinition, ParsedNode
 from dbt.contracts.relation import (
-    RelationType,
-    ComponentName,
-    HasQuoting,
-    FakeAPIObject,
-    Policy,
-    Path,
+    RelationType, ComponentName, HasQuoting, FakeAPIObject, Policy, Path
 )
 from dbt.exceptions import InternalException
 from dbt.node_types import NodeType
@@ -19,7 +16,7 @@ from dbt.utils import filter_null_values, deep_merge, classproperty
 import dbt.exceptions
 
 
-Self = TypeVar("Self", bound="BaseRelation")
+Self = TypeVar('Self', bound='BaseRelation')
 
 
 @dataclass(frozen=True, eq=False, repr=False)
@@ -43,7 +40,7 @@ class BaseRelation(FakeAPIObject, Hashable):
             if field.name == field_name:
                 return field
         # this should be unreachable
-        raise ValueError(f"BaseRelation has no {field_name} field!")
+        raise ValueError(f'BaseRelation has no {field_name} field!')
 
     def __eq__(self, other):
         if not isinstance(other, self.__class__):
@@ -52,18 +49,20 @@ class BaseRelation(FakeAPIObject, Hashable):
 
     @classmethod
     def get_default_quote_policy(cls) -> Policy:
-        return cls._get_field_named("quote_policy").default
+        return cls._get_field_named('quote_policy').default
 
     @classmethod
     def get_default_include_policy(cls) -> Policy:
-        return cls._get_field_named("include_policy").default
+        return cls._get_field_named('include_policy').default
 
     def get(self, key, default=None):
         """Override `.get` to return a metadata object so we don't break
         dbt_utils.
         """
-        if key == "metadata":
-            return {"type": self.__class__.__name__}
+        if key == 'metadata':
+            return {
+                'type': self.__class__.__name__
+            }
         return super().get(key, default)
 
     def matches(
@@ -72,19 +71,16 @@ class BaseRelation(FakeAPIObject, Hashable):
         schema: Optional[str] = None,
         identifier: Optional[str] = None,
     ) -> bool:
-        search = filter_null_values(
-            {
-                ComponentName.Database: database,
-                ComponentName.Schema: schema,
-                ComponentName.Identifier: identifier,
-            }
-        )
+        search = filter_null_values({
+            ComponentName.Database: database,
+            ComponentName.Schema: schema,
+            ComponentName.Identifier: identifier
+        })
 
         if not search:
             # nothing was passed in
             raise dbt.exceptions.RuntimeException(
-                "Tried to match relation, but no search path was passed!"
-            )
+                "Tried to match relation, but no search path was passed!")
 
         exact_match = True
         approximate_match = True
@@ -113,13 +109,11 @@ class BaseRelation(FakeAPIObject, Hashable):
         schema: Optional[bool] = None,
         identifier: Optional[bool] = None,
     ) -> Self:
-        policy = filter_null_values(
-            {
-                ComponentName.Database: database,
-                ComponentName.Schema: schema,
-                ComponentName.Identifier: identifier,
-            }
-        )
+        policy = filter_null_values({
+            ComponentName.Database: database,
+            ComponentName.Schema: schema,
+            ComponentName.Identifier: identifier
+        })
 
         new_quote_policy = self.quote_policy.replace_dict(policy)
         return self.replace(quote_policy=new_quote_policy)
@@ -130,18 +124,16 @@ class BaseRelation(FakeAPIObject, Hashable):
         schema: Optional[bool] = None,
         identifier: Optional[bool] = None,
     ) -> Self:
-        policy = filter_null_values(
-            {
-                ComponentName.Database: database,
-                ComponentName.Schema: schema,
-                ComponentName.Identifier: identifier,
-            }
-        )
+        policy = filter_null_values({
+            ComponentName.Database: database,
+            ComponentName.Schema: schema,
+            ComponentName.Identifier: identifier
+        })
 
         new_include_policy = self.include_policy.replace_dict(policy)
         return self.replace(include_policy=new_include_policy)
 
-    def information_schema(self, view_name=None) -> "InformationSchema":
+    def information_schema(self, view_name=None) -> 'InformationSchema':
         # some of our data comes from jinja, where things can be `Undefined`.
         if not isinstance(view_name, str):
             view_name = None
@@ -151,10 +143,10 @@ class BaseRelation(FakeAPIObject, Hashable):
         info_schema = InformationSchema.from_relation(self, view_name)
         return info_schema.incorporate(path={"schema": None})
 
-    def information_schema_only(self) -> "InformationSchema":
+    def information_schema_only(self) -> 'InformationSchema':
         return self.information_schema()
 
-    def without_identifier(self) -> "BaseRelation":
+    def without_identifier(self) -> 'BaseRelation':
         """Return a form of this relation that only has the database and schema
         set to included. To get the appropriately-quoted form the schema out of
         the result (for use as part of a query), use `.render()`. To get the
@@ -165,7 +157,7 @@ class BaseRelation(FakeAPIObject, Hashable):
         return self.include(identifier=False).replace_path(identifier=None)
 
     def _render_iterator(
-        self,
+        self
     ) -> Iterator[Tuple[Optional[ComponentName], Optional[str]]]:
 
         for key in ComponentName:
@@ -178,10 +170,13 @@ class BaseRelation(FakeAPIObject, Hashable):
 
     def render(self) -> str:
         # if there is nothing set, this will return the empty string.
-        return ".".join(part for _, part in self._render_iterator() if part is not None)
+        return '.'.join(
+            part for _, part in self._render_iterator()
+            if part is not None
+        )
 
     def quoted(self, identifier):
-        return "{quote_char}{identifier}{quote_char}".format(
+        return '{quote_char}{identifier}{quote_char}'.format(
             quote_char=self.quote_character,
             identifier=identifier,
         )
@@ -191,11 +186,11 @@ class BaseRelation(FakeAPIObject, Hashable):
         cls: Type[Self], source: ParsedSourceDefinition, **kwargs: Any
     ) -> Self:
         source_quoting = source.quoting.to_dict(omit_none=True)
-        source_quoting.pop("column", None)
+        source_quoting.pop('column', None)
         quote_policy = deep_merge(
             cls.get_default_quote_policy().to_dict(omit_none=True),
             source_quoting,
-            kwargs.get("quote_policy", {}),
+            kwargs.get('quote_policy', {}),
         )
 
         return cls.create(
@@ -203,12 +198,12 @@ class BaseRelation(FakeAPIObject, Hashable):
             schema=source.schema,
             identifier=source.identifier,
             quote_policy=quote_policy,
-            **kwargs,
+            **kwargs
         )
 
     @staticmethod
     def add_ephemeral_prefix(name: str):
-        return f"__dbt__cte__{name}"
+        return f'__dbt__cte__{name}'
 
     @classmethod
     def create_ephemeral_from_node(
@@ -241,8 +236,7 @@ class BaseRelation(FakeAPIObject, Hashable):
             schema=node.schema,
             identifier=node.alias,
             quote_policy=quote_policy,
-            **kwargs,
-        )
+            **kwargs)
 
     @classmethod
     def create_from(
@@ -254,16 +248,15 @@ class BaseRelation(FakeAPIObject, Hashable):
         if node.resource_type == NodeType.Source:
             if not isinstance(node, ParsedSourceDefinition):
                 raise InternalException(
-                    "type mismatch, expected ParsedSourceDefinition but got {}".format(
-                        type(node)
-                    )
+                    'type mismatch, expected ParsedSourceDefinition but got {}'
+                    .format(type(node))
                 )
             return cls.create_from_source(node, **kwargs)
         else:
             if not isinstance(node, (ParsedNode, CompiledNode)):
                 raise InternalException(
-                    "type mismatch, expected ParsedNode or CompiledNode but "
-                    "got {}".format(type(node))
+                    'type mismatch, expected ParsedNode or CompiledNode but '
+                    'got {}'.format(type(node))
                 )
             return cls.create_from_node(config, node, **kwargs)
 
@@ -276,16 +269,14 @@ class BaseRelation(FakeAPIObject, Hashable):
         type: Optional[RelationType] = None,
         **kwargs,
     ) -> Self:
-        kwargs.update(
-            {
-                "path": {
-                    "database": database,
-                    "schema": schema,
-                    "identifier": identifier,
-                },
-                "type": type,
-            }
-        )
+        kwargs.update({
+            'path': {
+                'database': database,
+                'schema': schema,
+                'identifier': identifier,
+            },
+            'type': type,
+        })
         return cls.from_dict(kwargs)
 
     def __repr__(self) -> str:
@@ -351,7 +342,7 @@ class BaseRelation(FakeAPIObject, Hashable):
         return RelationType
 
 
-Info = TypeVar("Info", bound="InformationSchema")
+Info = TypeVar('Info', bound='InformationSchema')
 
 
 @dataclass(frozen=True, eq=False, repr=False)
@@ -361,7 +352,7 @@ class InformationSchema(BaseRelation):
     def __post_init__(self):
         if not isinstance(self.information_schema_view, (type(None), str)):
             raise dbt.exceptions.CompilationException(
-                "Got an invalid name: {}".format(self.information_schema_view)
+                'Got an invalid name: {}'.format(self.information_schema_view)
             )
 
     @classmethod
@@ -371,7 +362,7 @@ class InformationSchema(BaseRelation):
         return Path(
             database=relation.database,
             schema=relation.schema,
-            identifier="INFORMATION_SCHEMA",
+            identifier='INFORMATION_SCHEMA',
         )
 
     @classmethod
@@ -402,7 +393,9 @@ class InformationSchema(BaseRelation):
         relation: BaseRelation,
         information_schema_view: Optional[str],
     ) -> Info:
-        include_policy = cls.get_include_policy(relation, information_schema_view)
+        include_policy = cls.get_include_policy(
+            relation, information_schema_view
+        )
         quote_policy = cls.get_quote_policy(relation, information_schema_view)
         path = cls.get_path(relation, information_schema_view)
         return cls(
@@ -424,7 +417,6 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
     search for what schemas. The schema values are all lowercased to avoid
     duplication.
     """
-
     def add(self, relation: BaseRelation):
         key = relation.information_schema_only()
         if key not in self:
@@ -434,27 +426,31 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
             schema = relation.schema.lower()
         self[key].add(schema)
 
-    def search(self) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
+    def search(
+        self
+    ) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
         for information_schema_name, schemas in self.items():
             for schema in schemas:
                 yield information_schema_name, schema
 
-    def flatten(self):
+    def flatten(self, allow_multiple_databases: bool = False):
         new = self.__class__()
 
-        # make sure we don't have duplicates
-        seen = {r.database.lower() for r in self if r.database}
-        if len(seen) > 1:
-            dbt.exceptions.raise_compiler_error(str(seen))
+        # make sure we don't have multiple databases if allow_multiple_databases is set to False
+        if not allow_multiple_databases:
+            seen = {r.database.lower() for r in self if r.database}
+            if len(seen) > 1:
+                dbt.exceptions.raise_compiler_error(str(seen))
 
         for information_schema_name, schema in self.search():
-            path = {"database": information_schema_name.database, "schema": schema}
-            new.add(
-                information_schema_name.incorporate(
-                    path=path,
-                    quote_policy={"database": False},
-                    include_policy={"database": False},
-                )
-            )
+            path = {
+                'database': information_schema_name.database,
+                'schema': schema
+            }
+            new.add(information_schema_name.incorporate(
+                path=path,
+                quote_policy={'database': False},
+                include_policy={'database': False},
+            ))
 
         return new

core/dbt/adapters/cache.py

@@ -7,7 +7,7 @@ from dbt.logger import CACHE_LOGGER as logger
 from dbt.utils import lowercase
 import dbt.exceptions
 
-_ReferenceKey = namedtuple("_ReferenceKey", "database schema identifier")
+_ReferenceKey = namedtuple('_ReferenceKey', 'database schema identifier')
 
 
 def _make_key(relation) -> _ReferenceKey:
@@ -15,11 +15,9 @@ def _make_key(relation) -> _ReferenceKey:
     to keep track of quoting
     """
     # databases and schemas can both be None
-    return _ReferenceKey(
-        lowercase(relation.database),
-        lowercase(relation.schema),
-        lowercase(relation.identifier),
-    )
+    return _ReferenceKey(lowercase(relation.database),
+                         lowercase(relation.schema),
+                         lowercase(relation.identifier))
 
 
 def dot_separated(key: _ReferenceKey) -> str:
@@ -27,7 +25,7 @@ def dot_separated(key: _ReferenceKey) -> str:
 
     :param _ReferenceKey key: The key to stringify.
     """
-    return ".".join(map(str, key))
+    return '.'.join(map(str, key))
 
 
 class _CachedRelation:
@@ -39,14 +37,13 @@ class _CachedRelation:
         that refer to this relation.
     :attr BaseRelation inner: The underlying dbt relation.
     """
-
     def __init__(self, inner):
         self.referenced_by = {}
         self.inner = inner
 
     def __str__(self) -> str:
         return (
-            "_CachedRelation(database={}, schema={}, identifier={}, inner={})"
+            '_CachedRelation(database={}, schema={}, identifier={}, inner={})'
         ).format(self.database, self.schema, self.identifier, self.inner)
 
     @property
@@ -81,7 +78,7 @@ class _CachedRelation:
         """
         return _make_key(self)
 
-    def add_reference(self, referrer: "_CachedRelation"):
+    def add_reference(self, referrer: '_CachedRelation'):
         """Add a reference from referrer to self, indicating that if this node
         were drop...cascaded, the referrer would be dropped as well.
 
@@ -125,9 +122,9 @@ class _CachedRelation:
         # table_name is ever anything but the identifier (via .create())
         self.inner = self.inner.incorporate(
             path={
-                "database": new_relation.inner.database,
-                "schema": new_relation.inner.schema,
-                "identifier": new_relation.inner.identifier,
+                'database': new_relation.inner.database,
+                'schema': new_relation.inner.schema,
+                'identifier': new_relation.inner.identifier
             },
         )
 
@@ -143,9 +140,8 @@ class _CachedRelation:
         """
         if new_key in self.referenced_by:
             dbt.exceptions.raise_cache_inconsistent(
-                'in rename of "{}" -> "{}", new name is in the cache already'.format(
-                    old_key, new_key
-                )
+                'in rename of "{}" -> "{}", new name is in the cache already'
+                .format(old_key, new_key)
             )
 
         if old_key not in self.referenced_by:
@@ -176,16 +172,13 @@ class RelationsCache:
         The adapters also hold this lock while filling the cache.
     :attr Set[str] schemas: The set of known/cached schemas, all lowercased.
     """
-
     def __init__(self) -> None:
         self.relations: Dict[_ReferenceKey, _CachedRelation] = {}
         self.lock = threading.RLock()
         self.schemas: Set[Tuple[Optional[str], Optional[str]]] = set()
 
     def add_schema(
-        self,
-        database: Optional[str],
-        schema: Optional[str],
+        self, database: Optional[str], schema: Optional[str],
     ) -> None:
         """Add a schema to the set of known schemas (case-insensitive)
 
@@ -195,9 +188,7 @@ class RelationsCache:
         self.schemas.add((lowercase(database), lowercase(schema)))
 
     def drop_schema(
-        self,
-        database: Optional[str],
-        schema: Optional[str],
+        self, database: Optional[str], schema: Optional[str],
     ) -> None:
         """Drop the given schema and remove it from the set of known schemas.
 
@@ -272,15 +263,15 @@ class RelationsCache:
             return
         if referenced is None:
             dbt.exceptions.raise_cache_inconsistent(
-                "in add_link, referenced link key {} not in cache!".format(
-                    referenced_key
-                )
+                'in add_link, referenced link key {} not in cache!'
+                .format(referenced_key)
             )
 
         dependent = self.relations.get(dependent_key)
         if dependent is None:
             dbt.exceptions.raise_cache_inconsistent(
-                "in add_link, dependent link key {} not in cache!".format(dependent_key)
+                'in add_link, dependent link key {} not in cache!'
+                .format(dependent_key)
             )
 
         assert dependent is not None  # we just raised!
@@ -307,23 +298,28 @@ class RelationsCache:
             # referring to a table outside our control. There's no need to make
             # a link - we will never drop the referenced relation during a run.
             logger.debug(
-                "{dep!s} references {ref!s} but {ref.database}.{ref.schema} "
-                "is not in the cache, skipping assumed external relation".format(
-                    dep=dependent, ref=ref_key
-                )
+                '{dep!s} references {ref!s} but {ref.database}.{ref.schema} '
+                'is not in the cache, skipping assumed external relation'
+                .format(dep=dependent, ref=ref_key)
             )
             return
         if ref_key not in self.relations:
             # Insert a dummy "external" relation.
-            referenced = referenced.replace(type=referenced.External)
+            referenced = referenced.replace(
+                type=referenced.External
+            )
             self.add(referenced)
 
         dep_key = _make_key(dependent)
         if dep_key not in self.relations:
             # Insert a dummy "external" relation.
-            dependent = dependent.replace(type=referenced.External)
+            dependent = dependent.replace(
+                type=referenced.External
+            )
             self.add(dependent)
-        logger.debug("adding link, {!s} references {!s}".format(dep_key, ref_key))
+        logger.debug(
+            'adding link, {!s} references {!s}'.format(dep_key, ref_key)
+        )
         with self.lock:
             self._add_link(ref_key, dep_key)
 
@@ -334,14 +330,14 @@ class RelationsCache:
         :param BaseRelation relation: The underlying relation.
         """
         cached = _CachedRelation(relation)
-        logger.debug("Adding relation: {!s}".format(cached))
+        logger.debug('Adding relation: {!s}'.format(cached))
 
-        lazy_log("before adding: {!s}", self.dump_graph)
+        lazy_log('before adding: {!s}', self.dump_graph)
 
         with self.lock:
             self._setdefault(cached)
 
-        lazy_log("after adding: {!s}", self.dump_graph)
+        lazy_log('after adding: {!s}', self.dump_graph)
 
     def _remove_refs(self, keys):
         """Removes all references to all entries in keys. This does not
@@ -363,10 +359,13 @@ class RelationsCache:
         :param _CachedRelation dropped: An existing _CachedRelation to drop.
         """
         if dropped not in self.relations:
-            logger.debug("dropped a nonexistent relationship: {!s}".format(dropped))
+            logger.debug('dropped a nonexistent relationship: {!s}'
+                         .format(dropped))
             return
         consequences = self.relations[dropped].collect_consequences()
-        logger.debug("drop {} is cascading to {}".format(dropped, consequences))
+        logger.debug(
+            'drop {} is cascading to {}'.format(dropped, consequences)
+        )
         self._remove_refs(consequences)
 
     def drop(self, relation):
@@ -381,7 +380,7 @@ class RelationsCache:
         :param str identifier: The identifier of the relation to drop.
         """
         dropped = _make_key(relation)
-        logger.debug("Dropping relation: {!s}".format(dropped))
+        logger.debug('Dropping relation: {!s}'.format(dropped))
         with self.lock:
             self._drop_cascade_relation(dropped)
 
@@ -405,9 +404,8 @@ class RelationsCache:
         for cached in self.relations.values():
             if cached.is_referenced_by(old_key):
                 logger.debug(
-                    "updated reference from {0} -> {2} to {1} -> {2}".format(
-                        old_key, new_key, cached.key()
-                    )
+                    'updated reference from {0} -> {2} to {1} -> {2}'
+                    .format(old_key, new_key, cached.key())
                 )
                 cached.rename_key(old_key, new_key)
 
@@ -432,16 +430,14 @@ class RelationsCache:
         """
         if new_key in self.relations:
             dbt.exceptions.raise_cache_inconsistent(
-                "in rename, new key {} already in cache: {}".format(
-                    new_key, list(self.relations.keys())
-                )
+                'in rename, new key {} already in cache: {}'
+                .format(new_key, list(self.relations.keys()))
             )
 
         if old_key not in self.relations:
             logger.debug(
-                "old key {} not found in self.relations, assuming temporary".format(
-                    old_key
-                )
+                'old key {} not found in self.relations, assuming temporary'
+                .format(old_key)
             )
             return False
         return True
@@ -460,9 +456,11 @@ class RelationsCache:
         """
         old_key = _make_key(old)
         new_key = _make_key(new)
-        logger.debug("Renaming relation {!s} to {!s}".format(old_key, new_key))
+        logger.debug('Renaming relation {!s} to {!s}'.format(
+            old_key, new_key
+        ))
 
-        lazy_log("before rename: {!s}", self.dump_graph)
+        lazy_log('before rename: {!s}', self.dump_graph)
 
         with self.lock:
             if self._check_rename_constraints(old_key, new_key):
@@ -470,7 +468,7 @@ class RelationsCache:
             else:
                 self._setdefault(_CachedRelation(new))
 
-        lazy_log("after rename: {!s}", self.dump_graph)
+        lazy_log('after rename: {!s}', self.dump_graph)
 
     def get_relations(
         self, database: Optional[str], schema: Optional[str]
@@ -485,14 +483,14 @@ class RelationsCache:
         schema = lowercase(schema)
         with self.lock:
             results = [
-                r.inner
-                for r in self.relations.values()
-                if (lowercase(r.schema) == schema and lowercase(r.database) == database)
+                r.inner for r in self.relations.values()
+                if (lowercase(r.schema) == schema and
+                    lowercase(r.database) == database)
             ]
 
         if None in results:
             dbt.exceptions.raise_cache_inconsistent(
-                "in get_relations, a None relation was found in the cache!"
+                'in get_relations, a None relation was found in the cache!'
             )
         return results
 

core/dbt/adapters/factory.py

@@ -50,7 +50,9 @@ class AdapterContainer:
         adapter = self.get_adapter_class_by_name(name)
         return adapter.Relation
 
-    def get_config_class_by_name(self, name: str) -> Type[AdapterConfig]:
+    def get_config_class_by_name(
+        self, name: str
+    ) -> Type[AdapterConfig]:
         adapter = self.get_adapter_class_by_name(name)
         return adapter.AdapterSpecificConfigs
 
@@ -60,24 +62,24 @@ class AdapterContainer:
         # singletons
         try:
             # mypy doesn't think modules have any attributes.
-            mod: Any = import_module("." + name, "dbt.adapters")
+            mod: Any = import_module('.' + name, 'dbt.adapters')
         except ModuleNotFoundError as exc:
             # if we failed to import the target module in particular, inform
             # the user about it via a runtime error
-            if exc.name == "dbt.adapters." + name:
-                raise RuntimeException(f"Could not find adapter type {name}!")
-            logger.info(f"Error importing adapter: {exc}")
+            if exc.name == 'dbt.adapters.' + name:
+                raise RuntimeException(f'Could not find adapter type {name}!')
+            logger.info(f'Error importing adapter: {exc}')
             # otherwise, the error had to have come from some underlying
             # library. Log the stack trace.
-            logger.debug("", exc_info=True)
+            logger.debug('', exc_info=True)
             raise
         plugin: AdapterPlugin = mod.Plugin
         plugin_type = plugin.adapter.type()
 
         if plugin_type != name:
             raise RuntimeException(
-                f"Expected to find adapter with type named {name}, got "
-                f"adapter with type {plugin_type}"
+                f'Expected to find adapter with type named {name}, got '
+                f'adapter with type {plugin_type}'
             )
 
         with self.lock:
@@ -107,7 +109,8 @@ class AdapterContainer:
         return self.adapters[adapter_name]
 
     def reset_adapters(self):
-        """Clear the adapters. This is useful for tests, which change configs."""
+        """Clear the adapters. This is useful for tests, which change configs.
+        """
         with self.lock:
             for adapter in self.adapters.values():
                 adapter.cleanup_connections()
@@ -137,7 +140,9 @@ class AdapterContainer:
             try:
                 plugin = self.plugins[plugin_name]
             except KeyError:
-                raise InternalException(f"No plugin found for {plugin_name}") from None
+                raise InternalException(
+                    f'No plugin found for {plugin_name}'
+                ) from None
             plugins.append(plugin)
             seen.add(plugin_name)
             if plugin.dependencies is None:
@@ -161,7 +166,7 @@ class AdapterContainer:
                 path = self.packages[package_name]
             except KeyError:
                 raise InternalException(
-                    f"No internal package listing found for {package_name}"
+                    f'No internal package listing found for {package_name}'
                 )
             paths.append(path)
         return paths
@@ -182,7 +187,8 @@ def get_adapter(config: AdapterRequiredConfig):
 
 
 def reset_adapters():
-    """Clear the adapters. This is useful for tests, which change configs."""
+    """Clear the adapters. This is useful for tests, which change configs.
+    """
     FACTORY.reset_adapters()
 
 

core/dbt/adapters/protocol.py

@@ -1,27 +1,17 @@
 from dataclasses import dataclass
 from typing import (
-    Type,
-    Hashable,
-    Optional,
-    ContextManager,
-    List,
-    Generic,
-    TypeVar,
-    ClassVar,
-    Tuple,
-    Union,
-    Dict,
-    Any,
+    Type, Hashable, Optional, ContextManager, List, Generic, TypeVar, ClassVar,
+    Tuple, Union, Dict, Any
 )
 from typing_extensions import Protocol
 
 import agate
 
-from dbt.contracts.connection import Connection, AdapterRequiredConfig, AdapterResponse
+from dbt.contracts.connection import (
+    Connection, AdapterRequiredConfig, AdapterResponse
+)
 from dbt.contracts.graph.compiled import (
-    CompiledNode,
-    ManifestNode,
-    NonSourceCompiledNode,
+    CompiledNode, ManifestNode, NonSourceCompiledNode
 )
 from dbt.contracts.graph.parsed import ParsedNode, ParsedSourceDefinition
 from dbt.contracts.graph.model_config import BaseConfig
@@ -44,7 +34,7 @@ class ColumnProtocol(Protocol):
     pass
 
 
-Self = TypeVar("Self", bound="RelationProtocol")
+Self = TypeVar('Self', bound='RelationProtocol')
 
 
 class RelationProtocol(Protocol):
@@ -74,11 +64,19 @@ class CompilerProtocol(Protocol):
         ...
 
 
-AdapterConfig_T = TypeVar("AdapterConfig_T", bound=AdapterConfig)
-ConnectionManager_T = TypeVar("ConnectionManager_T", bound=ConnectionManagerProtocol)
-Relation_T = TypeVar("Relation_T", bound=RelationProtocol)
-Column_T = TypeVar("Column_T", bound=ColumnProtocol)
-Compiler_T = TypeVar("Compiler_T", bound=CompilerProtocol)
+AdapterConfig_T = TypeVar(
+    'AdapterConfig_T', bound=AdapterConfig
+)
+ConnectionManager_T = TypeVar(
+    'ConnectionManager_T', bound=ConnectionManagerProtocol
+)
+Relation_T = TypeVar(
+    'Relation_T', bound=RelationProtocol
+)
+Column_T = TypeVar(
+    'Column_T', bound=ColumnProtocol
+)
+Compiler_T = TypeVar('Compiler_T', bound=CompilerProtocol)
 
 
 class AdapterProtocol(
@@ -89,7 +87,7 @@ class AdapterProtocol(
         Relation_T,
         Column_T,
         Compiler_T,
-    ],
+    ]
 ):
     AdapterSpecificConfigs: ClassVar[Type[AdapterConfig_T]]
     Column: ClassVar[Type[Column_T]]

core/dbt/adapters/sql/connections.py

@@ -7,7 +7,9 @@ import agate
 import dbt.clients.agate_helper
 import dbt.exceptions
 from dbt.adapters.base import BaseConnectionManager
-from dbt.contracts.connection import Connection, ConnectionState, AdapterResponse
+from dbt.contracts.connection import (
+    Connection, ConnectionState, AdapterResponse
+)
 from dbt.logger import GLOBAL_LOGGER as logger
 from dbt import flags
 
@@ -21,12 +23,11 @@ class SQLConnectionManager(BaseConnectionManager):
         - get_response
         - open
     """
-
     @abc.abstractmethod
     def cancel(self, connection: Connection):
         """Cancel the given connection."""
         raise dbt.exceptions.NotImplementedException(
-            "`cancel` is not implemented for this adapter!"
+            '`cancel` is not implemented for this adapter!'
         )
 
     def cancel_open(self) -> List[str]:
@@ -40,8 +41,8 @@ class SQLConnectionManager(BaseConnectionManager):
                 # if the connection failed, the handle will be None so we have
                 # nothing to cancel.
                 if (
-                    connection.handle is not None
-                    and connection.state == ConnectionState.OPEN
+                    connection.handle is not None and
+                    connection.state == ConnectionState.OPEN
                 ):
                     self.cancel(connection)
                 if connection.name is not None:
@@ -53,22 +54,23 @@ class SQLConnectionManager(BaseConnectionManager):
         sql: str,
         auto_begin: bool = True,
         bindings: Optional[Any] = None,
-        abridge_sql_log: bool = False,
+        abridge_sql_log: bool = False
     ) -> Tuple[Connection, Any]:
         connection = self.get_thread_connection()
         if auto_begin and connection.transaction_open is False:
             self.begin()
 
-        logger.debug('Using {} connection "{}".'.format(self.TYPE, connection.name))
+        logger.debug('Using {} connection "{}".'
+                     .format(self.TYPE, connection.name))
 
         with self.exception_handler(sql):
             if abridge_sql_log:
-                log_sql = "{}...".format(sql[:512])
+                log_sql = '{}...'.format(sql[:512])
             else:
                 log_sql = sql
 
             logger.debug(
-                "On {connection_name}: {sql}",
+                'On {connection_name}: {sql}',
                 connection_name=connection.name,
                 sql=log_sql,
             )
@@ -79,7 +81,7 @@ class SQLConnectionManager(BaseConnectionManager):
             logger.debug(
                 "SQL status: {status} in {elapsed:0.2f} seconds",
                 status=self.get_response(cursor),
-                elapsed=(time.time() - pre),
+                elapsed=(time.time() - pre)
             )
 
             return connection, cursor
@@ -88,14 +90,23 @@ class SQLConnectionManager(BaseConnectionManager):
     def get_response(cls, cursor: Any) -> Union[AdapterResponse, str]:
         """Get the status of the cursor."""
         raise dbt.exceptions.NotImplementedException(
-            "`get_response` is not implemented for this adapter!"
+            '`get_response` is not implemented for this adapter!'
         )
 
     @classmethod
     def process_results(
-        cls, column_names: Iterable[str], rows: Iterable[Any]
+        cls,
+        column_names: Iterable[str],
+        rows: Iterable[Any]
     ) -> List[Dict[str, Any]]:
-
+        unique_col_names = dict()
+        for idx in range(len(column_names)):
+            col_name = column_names[idx]
+            if col_name in unique_col_names:
+                unique_col_names[col_name] += 1
+                column_names[idx] = f'{col_name}_{unique_col_names[col_name]}'
+            else:
+                unique_col_names[column_names[idx]] = 1
         return [dict(zip(column_names, row)) for row in rows]
 
     @classmethod
@@ -108,7 +119,10 @@ class SQLConnectionManager(BaseConnectionManager):
             rows = cursor.fetchall()
             data = cls.process_results(column_names, rows)
 
-        return dbt.clients.agate_helper.table_from_data_flat(data, column_names)
+        return dbt.clients.agate_helper.table_from_data_flat(
+            data,
+            column_names
+        )
 
     def execute(
         self, sql: str, auto_begin: bool = False, fetch: bool = False
@@ -123,10 +137,10 @@ class SQLConnectionManager(BaseConnectionManager):
         return response, table
 
     def add_begin_query(self):
-        return self.add_query("BEGIN", auto_begin=False)
+        return self.add_query('BEGIN', auto_begin=False)
 
     def add_commit_query(self):
-        return self.add_query("COMMIT", auto_begin=False)
+        return self.add_query('COMMIT', auto_begin=False)
 
     def begin(self):
         connection = self.get_thread_connection()
@@ -134,14 +148,13 @@ class SQLConnectionManager(BaseConnectionManager):
         if flags.STRICT_MODE:
             if not isinstance(connection, Connection):
                 raise dbt.exceptions.CompilerException(
-                    f"In begin, got {connection} - not a Connection!"
+                    f'In begin, got {connection} - not a Connection!'
                 )
 
         if connection.transaction_open is True:
             raise dbt.exceptions.InternalException(
                 'Tried to begin a new transaction on connection "{}", but '
-                "it already had one open!".format(connection.name)
-            )
+                'it already had one open!'.format(connection.name))
 
         self.add_begin_query()
 
@@ -153,16 +166,15 @@ class SQLConnectionManager(BaseConnectionManager):
         if flags.STRICT_MODE:
             if not isinstance(connection, Connection):
                 raise dbt.exceptions.CompilerException(
-                    f"In commit, got {connection} - not a Connection!"
+                    f'In commit, got {connection} - not a Connection!'
                 )
 
         if connection.transaction_open is False:
             raise dbt.exceptions.InternalException(
                 'Tried to commit transaction on connection "{}", but '
-                "it does not have one open!".format(connection.name)
-            )
+                'it does not have one open!'.format(connection.name))
 
-        logger.debug("On {}: COMMIT".format(connection.name))
+        logger.debug('On {}: COMMIT'.format(connection.name))
         self.add_commit_query()
 
         connection.transaction_open = False

core/dbt/adapters/sql/impl.py

@@ -10,16 +10,16 @@ from dbt.logger import GLOBAL_LOGGER as logger
 
 from dbt.adapters.base.relation import BaseRelation
 
-LIST_RELATIONS_MACRO_NAME = "list_relations_without_caching"
-GET_COLUMNS_IN_RELATION_MACRO_NAME = "get_columns_in_relation"
-LIST_SCHEMAS_MACRO_NAME = "list_schemas"
-CHECK_SCHEMA_EXISTS_MACRO_NAME = "check_schema_exists"
-CREATE_SCHEMA_MACRO_NAME = "create_schema"
-DROP_SCHEMA_MACRO_NAME = "drop_schema"
-RENAME_RELATION_MACRO_NAME = "rename_relation"
-TRUNCATE_RELATION_MACRO_NAME = "truncate_relation"
-DROP_RELATION_MACRO_NAME = "drop_relation"
-ALTER_COLUMN_TYPE_MACRO_NAME = "alter_column_type"
+LIST_RELATIONS_MACRO_NAME = 'list_relations_without_caching'
+GET_COLUMNS_IN_RELATION_MACRO_NAME = 'get_columns_in_relation'
+LIST_SCHEMAS_MACRO_NAME = 'list_schemas'
+CHECK_SCHEMA_EXISTS_MACRO_NAME = 'check_schema_exists'
+CREATE_SCHEMA_MACRO_NAME = 'create_schema'
+DROP_SCHEMA_MACRO_NAME = 'drop_schema'
+RENAME_RELATION_MACRO_NAME = 'rename_relation'
+TRUNCATE_RELATION_MACRO_NAME = 'truncate_relation'
+DROP_RELATION_MACRO_NAME = 'drop_relation'
+ALTER_COLUMN_TYPE_MACRO_NAME = 'alter_column_type'
 
 
 class SQLAdapter(BaseAdapter):
@@ -60,23 +60,30 @@ class SQLAdapter(BaseAdapter):
         :param abridge_sql_log: If set, limit the raw sql logged to 512
             characters
         """
-        return self.connections.add_query(sql, auto_begin, bindings, abridge_sql_log)
+        return self.connections.add_query(sql, auto_begin, bindings,
+                                          abridge_sql_log)
 
     @classmethod
     def convert_text_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         return "text"
 
     @classmethod
-    def convert_number_type(cls, agate_table: agate.Table, col_idx: int) -> str:
-        decimals = agate_table.aggregate(agate.MaxPrecision(col_idx))  # type: ignore
+    def convert_number_type(
+        cls, agate_table: agate.Table, col_idx: int
+    ) -> str:
+        decimals = agate_table.aggregate(agate.MaxPrecision(col_idx))
         return "float8" if decimals else "integer"
 
     @classmethod
-    def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str:
+    def convert_boolean_type(
+            cls, agate_table: agate.Table, col_idx: int
+    ) -> str:
         return "boolean"
 
     @classmethod
-    def convert_datetime_type(cls, agate_table: agate.Table, col_idx: int) -> str:
+    def convert_datetime_type(
+            cls, agate_table: agate.Table, col_idx: int
+    ) -> str:
         return "timestamp without time zone"
 
     @classmethod
@@ -92,28 +99,31 @@ class SQLAdapter(BaseAdapter):
         return True
 
     def expand_column_types(self, goal, current):
-        reference_columns = {c.name: c for c in self.get_columns_in_relation(goal)}
+        reference_columns = {
+            c.name: c for c in
+            self.get_columns_in_relation(goal)
+        }
 
-        target_columns = {c.name: c for c in self.get_columns_in_relation(current)}
+        target_columns = {
+            c.name: c for c
+            in self.get_columns_in_relation(current)
+        }
 
         for column_name, reference_column in reference_columns.items():
             target_column = target_columns.get(column_name)
 
-            if target_column is not None and target_column.can_expand_to(
-                reference_column
-            ):
+            if target_column is not None and \
+               target_column.can_expand_to(reference_column):
                 col_string_size = reference_column.string_size()
                 new_type = self.Column.string_type(col_string_size)
-                logger.debug(
-                    "Changing col type from {} to {} in table {}",
-                    target_column.data_type,
-                    new_type,
-                    current,
-                )
+                logger.debug("Changing col type from {} to {} in table {}",
+                             target_column.data_type, new_type, current)
 
                 self.alter_column_type(current, column_name, new_type)
 
-    def alter_column_type(self, relation, column_name, new_column_type) -> None:
+    def alter_column_type(
+            self, relation, column_name, new_column_type
+    ) -> None:
         """
         1. Create a new column (w/ temp name and correct type)
         2. Copy data over to it
@@ -121,40 +131,53 @@ class SQLAdapter(BaseAdapter):
         4. Rename the new column to existing column
         """
         kwargs = {
-            "relation": relation,
-            "column_name": column_name,
-            "new_column_type": new_column_type,
+            'relation': relation,
+            'column_name': column_name,
+            'new_column_type': new_column_type,
         }
-        self.execute_macro(ALTER_COLUMN_TYPE_MACRO_NAME, kwargs=kwargs)
+        self.execute_macro(
+            ALTER_COLUMN_TYPE_MACRO_NAME,
+            kwargs=kwargs
+        )
 
     def drop_relation(self, relation):
         if relation.type is None:
             dbt.exceptions.raise_compiler_error(
-                "Tried to drop relation {}, but its type is null.".format(relation)
-            )
+                'Tried to drop relation {}, but its type is null.'
+                .format(relation))
 
         self.cache_dropped(relation)
-        self.execute_macro(DROP_RELATION_MACRO_NAME, kwargs={"relation": relation})
+        self.execute_macro(
+            DROP_RELATION_MACRO_NAME,
+            kwargs={'relation': relation}
+        )
 
     def truncate_relation(self, relation):
-        self.execute_macro(TRUNCATE_RELATION_MACRO_NAME, kwargs={"relation": relation})
+        self.execute_macro(
+            TRUNCATE_RELATION_MACRO_NAME,
+            kwargs={'relation': relation}
+        )
 
     def rename_relation(self, from_relation, to_relation):
         self.cache_renamed(from_relation, to_relation)
 
-        kwargs = {"from_relation": from_relation, "to_relation": to_relation}
-        self.execute_macro(RENAME_RELATION_MACRO_NAME, kwargs=kwargs)
+        kwargs = {'from_relation': from_relation, 'to_relation': to_relation}
+        self.execute_macro(
+            RENAME_RELATION_MACRO_NAME,
+            kwargs=kwargs
+        )
 
     def get_columns_in_relation(self, relation):
         return self.execute_macro(
-            GET_COLUMNS_IN_RELATION_MACRO_NAME, kwargs={"relation": relation}
+            GET_COLUMNS_IN_RELATION_MACRO_NAME,
+            kwargs={'relation': relation}
         )
 
     def create_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
         logger.debug('Creating schema "{}"', relation)
         kwargs = {
-            "relation": relation,
+            'relation': relation,
         }
         self.execute_macro(CREATE_SCHEMA_MACRO_NAME, kwargs=kwargs)
         self.commit_if_has_connection()
@@ -165,35 +188,39 @@ class SQLAdapter(BaseAdapter):
         relation = relation.without_identifier()
         logger.debug('Dropping schema "{}".', relation)
         kwargs = {
-            "relation": relation,
+            'relation': relation,
         }
         self.execute_macro(DROP_SCHEMA_MACRO_NAME, kwargs=kwargs)
         # we can update the cache here
         self.cache.drop_schema(relation.database, relation.schema)
 
     def list_relations_without_caching(
-        self,
-        schema_relation: BaseRelation,
+        self, schema_relation: BaseRelation,
     ) -> List[BaseRelation]:
-        kwargs = {"schema_relation": schema_relation}
-        results = self.execute_macro(LIST_RELATIONS_MACRO_NAME, kwargs=kwargs)
+        kwargs = {'schema_relation': schema_relation}
+        results = self.execute_macro(
+            LIST_RELATIONS_MACRO_NAME,
+            kwargs=kwargs
+        )
 
         relations = []
-        quote_policy = {"database": True, "schema": True, "identifier": True}
+        quote_policy = {
+            'database': True,
+            'schema': True,
+            'identifier': True
+        }
         for _database, name, _schema, _type in results:
             try:
                 _type = self.Relation.get_relation_type(_type)
             except ValueError:
                 _type = self.Relation.External
-            relations.append(
-                self.Relation.create(
-                    database=_database,
-                    schema=_schema,
-                    identifier=name,
-                    quote_policy=quote_policy,
-                    type=_type,
-                )
-            )
+            relations.append(self.Relation.create(
+                database=_database,
+                schema=_schema,
+                identifier=name,
+                quote_policy=quote_policy,
+                type=_type
+            ))
         return relations
 
     def quote(self, identifier):
@@ -201,7 +228,8 @@ class SQLAdapter(BaseAdapter):
 
     def list_schemas(self, database: str) -> List[str]:
         results = self.execute_macro(
-            LIST_SCHEMAS_MACRO_NAME, kwargs={"database": database}
+            LIST_SCHEMAS_MACRO_NAME,
+            kwargs={'database': database}
         )
 
         return [row[0] for row in results]
@@ -210,10 +238,13 @@ class SQLAdapter(BaseAdapter):
         information_schema = self.Relation.create(
             database=database,
             schema=schema,
-            identifier="INFORMATION_SCHEMA",
-            quote_policy=self.config.quoting,
+            identifier='INFORMATION_SCHEMA',
+            quote_policy=self.config.quoting
         ).information_schema()
 
-        kwargs = {"information_schema": information_schema, "schema": schema}
-        results = self.execute_macro(CHECK_SCHEMA_EXISTS_MACRO_NAME, kwargs=kwargs)
+        kwargs = {'information_schema': information_schema, 'schema': schema}
+        results = self.execute_macro(
+            CHECK_SCHEMA_EXISTS_MACRO_NAME,
+            kwargs=kwargs
+        )
         return results[0][0] > 0

core/dbt/clients/_jinja_blocks.py

@@ -10,89 +10,79 @@ def regex(pat):
 
 class BlockData:
     """raw plaintext data from the top level of the file."""
-
     def __init__(self, contents):
-        self.block_type_name = "__dbt__data"
+        self.block_type_name = '__dbt__data'
         self.contents = contents
         self.full_block = contents
 
 
 class BlockTag:
-    def __init__(
-        self, block_type_name, block_name, contents=None, full_block=None, **kw
-    ):
+    def __init__(self, block_type_name, block_name, contents=None,
+                 full_block=None, **kw):
         self.block_type_name = block_type_name
         self.block_name = block_name
         self.contents = contents
         self.full_block = full_block
 
     def __str__(self):
-        return "BlockTag({!r}, {!r})".format(self.block_type_name, self.block_name)
+        return 'BlockTag({!r}, {!r})'.format(self.block_type_name,
+                                             self.block_name)
 
     def __repr__(self):
         return str(self)
 
     @property
     def end_block_type_name(self):
-        return "end{}".format(self.block_type_name)
+        return 'end{}'.format(self.block_type_name)
 
     def end_pat(self):
         # we don't want to use string formatting here because jinja uses most
         # of the string formatting operators in its syntax...
-        pattern = "".join(
-            (
-                r"(?P<endblock>((?:\s*\{\%\-|\{\%)\s*",
-                self.end_block_type_name,
-                r"\s*(?:\-\%\}\s*|\%\})))",
-            )
-        )
+        pattern = ''.join((
+            r'(?P<endblock>((?:\s*\{\%\-|\{\%)\s*',
+            self.end_block_type_name,
+            r'\s*(?:\-\%\}\s*|\%\})))',
+        ))
         return regex(pattern)
 
 
-Tag = namedtuple("Tag", "block_type_name block_name start end")
+Tag = namedtuple('Tag', 'block_type_name block_name start end')
 
 
-_NAME_PATTERN = r"[A-Za-z_][A-Za-z_0-9]*"
+_NAME_PATTERN = r'[A-Za-z_][A-Za-z_0-9]*'
 
-COMMENT_START_PATTERN = regex(r"(?:(?P<comment_start>(\s*\{\#)))")
-COMMENT_END_PATTERN = regex(r"(.*?)(\s*\#\})")
+COMMENT_START_PATTERN = regex(r'(?:(?P<comment_start>(\s*\{\#)))')
+COMMENT_END_PATTERN = regex(r'(.*?)(\s*\#\})')
 RAW_START_PATTERN = regex(
-    r"(?:\s*\{\%\-|\{\%)\s*(?P<raw_start>(raw))\s*(?:\-\%\}\s*|\%\})"
+    r'(?:\s*\{\%\-|\{\%)\s*(?P<raw_start>(raw))\s*(?:\-\%\}\s*|\%\})'
 )
-EXPR_START_PATTERN = regex(r"(?P<expr_start>(\{\{\s*))")
-EXPR_END_PATTERN = regex(r"(?P<expr_end>(\s*\}\}))")
+EXPR_START_PATTERN = regex(r'(?P<expr_start>(\{\{\s*))')
+EXPR_END_PATTERN = regex(r'(?P<expr_end>(\s*\}\}))')
 
-BLOCK_START_PATTERN = regex(
-    "".join(
-        (
-            r"(?:\s*\{\%\-|\{\%)\s*",
-            r"(?P<block_type_name>({}))".format(_NAME_PATTERN),
-            # some blocks have a 'block name'.
-            r"(?:\s+(?P<block_name>({})))?".format(_NAME_PATTERN),
-        )
-    )
-)
+BLOCK_START_PATTERN = regex(''.join((
+    r'(?:\s*\{\%\-|\{\%)\s*',
+    r'(?P<block_type_name>({}))'.format(_NAME_PATTERN),
+    # some blocks have a 'block name'.
+    r'(?:\s+(?P<block_name>({})))?'.format(_NAME_PATTERN),
+)))
 
 
-RAW_BLOCK_PATTERN = regex(
-    "".join(
-        (
-            r"(?:\s*\{\%\-|\{\%)\s*raw\s*(?:\-\%\}\s*|\%\})",
-            r"(?:.*?)",
-            r"(?:\s*\{\%\-|\{\%)\s*endraw\s*(?:\-\%\}\s*|\%\})",
-        )
-    )
-)
+RAW_BLOCK_PATTERN = regex(''.join((
+    r'(?:\s*\{\%\-|\{\%)\s*raw\s*(?:\-\%\}\s*|\%\})',
+    r'(?:.*?)',
+    r'(?:\s*\{\%\-|\{\%)\s*endraw\s*(?:\-\%\}\s*|\%\})',
+)))
 
-TAG_CLOSE_PATTERN = regex(r"(?:(?P<tag_close>(\-\%\}\s*|\%\})))")
+TAG_CLOSE_PATTERN = regex(r'(?:(?P<tag_close>(\-\%\}\s*|\%\})))')
 
 # stolen from jinja's lexer. Note that we've consumed all prefix whitespace by
 # the time we want to use this.
 STRING_PATTERN = regex(
-    r"(?P<string>('([^'\\]*(?:\\.[^'\\]*)*)'|" r'"([^"\\]*(?:\\.[^"\\]*)*)"))'
+    r"(?P<string>('([^'\\]*(?:\\.[^'\\]*)*)'|"
+    r'"([^"\\]*(?:\\.[^"\\]*)*)"))'
 )
 
-QUOTE_START_PATTERN = regex(r"""(?P<quote>(['"]))""")
+QUOTE_START_PATTERN = regex(r'''(?P<quote>(['"]))''')
 
 
 class TagIterator:
@@ -109,10 +99,10 @@ class TagIterator:
         end_val: int = self.pos if end is None else end
         data = self.data[:end_val]
         # if not found, rfind returns -1, and -1+1=0, which is perfect!
-        last_line_start = data.rfind("\n") + 1
+        last_line_start = data.rfind('\n') + 1
         # it's easy to forget this, but line numbers are 1-indexed
-        line_number = data.count("\n") + 1
-        return f"{line_number}:{end_val - last_line_start}"
+        line_number = data.count('\n') + 1
+        return f'{line_number}:{end_val - last_line_start}'
 
     def advance(self, new_position):
         self.pos = new_position
@@ -130,7 +120,7 @@ class TagIterator:
         matches = []
         for pattern in patterns:
             # default to 'search', but sometimes we want to 'match'.
-            if kwargs.get("method", "search") == "search":
+            if kwargs.get('method', 'search') == 'search':
                 match = self._search(pattern)
             else:
                 match = self._match(pattern)
@@ -146,7 +136,7 @@ class TagIterator:
         match = self._first_match(*patterns, **kwargs)
         if match is None:
             msg = 'unexpected EOF, expected {}, got "{}"'.format(
-                expected_name, self.data[self.pos :]
+                expected_name, self.data[self.pos:]
             )
             dbt.exceptions.raise_compiler_error(msg)
         return match
@@ -166,20 +156,22 @@ class TagIterator:
         """
         self.advance(match.end())
         while True:
-            match = self._expect_match("}}", EXPR_END_PATTERN, QUOTE_START_PATTERN)
-            if match.groupdict().get("expr_end") is not None:
+            match = self._expect_match('}}',
+                                       EXPR_END_PATTERN,
+                                       QUOTE_START_PATTERN)
+            if match.groupdict().get('expr_end') is not None:
                 break
             else:
                 # it's a quote. we haven't advanced for this match yet, so
                 # just slurp up the whole string, no need to rewind.
-                match = self._expect_match("string", STRING_PATTERN)
+                match = self._expect_match('string', STRING_PATTERN)
                 self.advance(match.end())
 
         self.advance(match.end())
 
     def handle_comment(self, match):
         self.advance(match.end())
-        match = self._expect_match("#}", COMMENT_END_PATTERN)
+        match = self._expect_match('#}', COMMENT_END_PATTERN)
         self.advance(match.end())
 
     def _expect_block_close(self):
@@ -196,19 +188,22 @@ class TagIterator:
         """
         while True:
             end_match = self._expect_match(
-                'tag close ("%}")', QUOTE_START_PATTERN, TAG_CLOSE_PATTERN
+                'tag close ("%}")',
+                QUOTE_START_PATTERN,
+                TAG_CLOSE_PATTERN
             )
             self.advance(end_match.end())
-            if end_match.groupdict().get("tag_close") is not None:
+            if end_match.groupdict().get('tag_close') is not None:
                 return
             # must be a string. Rewind to its start and advance past it.
             self.rewind()
-            string_match = self._expect_match("string", STRING_PATTERN)
+            string_match = self._expect_match('string', STRING_PATTERN)
             self.advance(string_match.end())
 
     def handle_raw(self):
         # raw blocks are super special, they are a single complete regex
-        match = self._expect_match("{% raw %}...{% endraw %}", RAW_BLOCK_PATTERN)
+        match = self._expect_match('{% raw %}...{% endraw %}',
+                                   RAW_BLOCK_PATTERN)
         self.advance(match.end())
         return match.end()
 
@@ -225,12 +220,13 @@ class TagIterator:
         """
         groups = match.groupdict()
         # always a value
-        block_type_name = groups["block_type_name"]
+        block_type_name = groups['block_type_name']
         # might be None
-        block_name = groups.get("block_name")
+        block_name = groups.get('block_name')
         start_pos = self.pos
-        if block_type_name == "raw":
-            match = self._expect_match("{% raw %}...{% endraw %}", RAW_BLOCK_PATTERN)
+        if block_type_name == 'raw':
+            match = self._expect_match('{% raw %}...{% endraw %}',
+                                       RAW_BLOCK_PATTERN)
             self.advance(match.end())
         else:
             self.advance(match.end())
@@ -239,13 +235,15 @@ class TagIterator:
             block_type_name=block_type_name,
             block_name=block_name,
             start=start_pos,
-            end=self.pos,
+            end=self.pos
         )
 
     def find_tags(self):
         while True:
             match = self._first_match(
-                BLOCK_START_PATTERN, COMMENT_START_PATTERN, EXPR_START_PATTERN
+                BLOCK_START_PATTERN,
+                COMMENT_START_PATTERN,
+                EXPR_START_PATTERN
             )
             if match is None:
                 break
@@ -254,9 +252,9 @@ class TagIterator:
             # start = self.pos
 
             groups = match.groupdict()
-            comment_start = groups.get("comment_start")
-            expr_start = groups.get("expr_start")
-            block_type_name = groups.get("block_type_name")
+            comment_start = groups.get('comment_start')
+            expr_start = groups.get('expr_start')
+            block_type_name = groups.get('block_type_name')
 
             if comment_start is not None:
                 self.handle_comment(match)
@@ -266,8 +264,8 @@ class TagIterator:
                 yield self.handle_tag(match)
             else:
                 raise dbt.exceptions.InternalException(
-                    "Invalid regex match in next_block, expected block start, "
-                    "expr start, or comment start"
+                    'Invalid regex match in next_block, expected block start, '
+                    'expr start, or comment start'
                 )
 
     def __iter__(self):
@@ -275,18 +273,21 @@ class TagIterator:
 
 
 duplicate_tags = (
-    "Got nested tags: {outer.block_type_name} (started at {outer.start}) did "
-    "not have a matching {{% end{outer.block_type_name} %}} before a "
-    "subsequent {inner.block_type_name} was found (started at {inner.start})"
+    'Got nested tags: {outer.block_type_name} (started at {outer.start}) did '
+    'not have a matching {{% end{outer.block_type_name} %}} before a '
+    'subsequent {inner.block_type_name} was found (started at {inner.start})'
 )
 
 
 _CONTROL_FLOW_TAGS = {
-    "if": "endif",
-    "for": "endfor",
+    'if': 'endif',
+    'for': 'endfor',
 }
 
-_CONTROL_FLOW_END_TAGS = {v: k for k, v in _CONTROL_FLOW_TAGS.items()}
+_CONTROL_FLOW_END_TAGS = {
+    v: k
+    for k, v in _CONTROL_FLOW_TAGS.items()
+}
 
 
 class BlockIterator:
@@ -309,15 +310,15 @@ class BlockIterator:
 
     def is_current_end(self, tag):
         return (
-            tag.block_type_name.startswith("end")
-            and self.current is not None
-            and tag.block_type_name[3:] == self.current.block_type_name
+            tag.block_type_name.startswith('end') and
+            self.current is not None and
+            tag.block_type_name[3:] == self.current.block_type_name
         )
 
     def find_blocks(self, allowed_blocks=None, collect_raw_data=True):
         """Find all top-level blocks in the data."""
         if allowed_blocks is None:
-            allowed_blocks = {"snapshot", "macro", "materialization", "docs"}
+            allowed_blocks = {'snapshot', 'macro', 'materialization', 'docs'}
 
         for tag in self.tag_parser.find_tags():
             if tag.block_type_name in _CONTROL_FLOW_TAGS:
@@ -328,43 +329,37 @@ class BlockIterator:
                     found = self.stack.pop()
                 else:
                     expected = _CONTROL_FLOW_END_TAGS[tag.block_type_name]
-                    dbt.exceptions.raise_compiler_error(
-                        (
-                            "Got an unexpected control flow end tag, got {} but "
-                            "never saw a preceeding {} (@ {})"
-                        ).format(
-                            tag.block_type_name,
-                            expected,
-                            self.tag_parser.linepos(tag.start),
-                        )
-                    )
+                    dbt.exceptions.raise_compiler_error((
+                        'Got an unexpected control flow end tag, got {} but '
+                        'never saw a preceeding {} (@ {})'
+                    ).format(
+                        tag.block_type_name,
+                        expected,
+                        self.tag_parser.linepos(tag.start)
+                    ))
                 expected = _CONTROL_FLOW_TAGS[found]
                 if expected != tag.block_type_name:
-                    dbt.exceptions.raise_compiler_error(
-                        (
-                            "Got an unexpected control flow end tag, got {} but "
-                            "expected {} next (@ {})"
-                        ).format(
-                            tag.block_type_name,
-                            expected,
-                            self.tag_parser.linepos(tag.start),
-                        )
-                    )
+                    dbt.exceptions.raise_compiler_error((
+                        'Got an unexpected control flow end tag, got {} but '
+                        'expected {} next (@ {})'
+                    ).format(
+                        tag.block_type_name,
+                        expected,
+                        self.tag_parser.linepos(tag.start)
+                    ))
 
             if tag.block_type_name in allowed_blocks:
                 if self.stack:
-                    dbt.exceptions.raise_compiler_error(
-                        (
-                            "Got a block definition inside control flow at {}. "
-                            "All dbt block definitions must be at the top level"
-                        ).format(self.tag_parser.linepos(tag.start))
-                    )
+                    dbt.exceptions.raise_compiler_error((
+                        'Got a block definition inside control flow at {}. '
+                        'All dbt block definitions must be at the top level'
+                    ).format(self.tag_parser.linepos(tag.start)))
                 if self.current is not None:
                     dbt.exceptions.raise_compiler_error(
                         duplicate_tags.format(outer=self.current, inner=tag)
                     )
                 if collect_raw_data:
-                    raw_data = self.data[self.last_position : tag.start]
+                    raw_data = self.data[self.last_position:tag.start]
                     self.last_position = tag.start
                     if raw_data:
                         yield BlockData(raw_data)
@@ -376,28 +371,23 @@ class BlockIterator:
                 yield BlockTag(
                     block_type_name=self.current.block_type_name,
                     block_name=self.current.block_name,
-                    contents=self.data[self.current.end : tag.start],
-                    full_block=self.data[self.current.start : tag.end],
+                    contents=self.data[self.current.end:tag.start],
+                    full_block=self.data[self.current.start:tag.end]
                 )
                 self.current = None
 
         if self.current:
-            linecount = self.data[: self.current.end].count("\n") + 1
-            dbt.exceptions.raise_compiler_error(
-                (
-                    "Reached EOF without finding a close tag for "
-                    "{} (searched from line {})"
-                ).format(self.current.block_type_name, linecount)
-            )
+            linecount = self.data[:self.current.end].count('\n') + 1
+            dbt.exceptions.raise_compiler_error((
+                'Reached EOF without finding a close tag for '
+                '{} (searched from line {})'
+            ).format(self.current.block_type_name, linecount))
 
         if collect_raw_data:
-            raw_data = self.data[self.last_position :]
+            raw_data = self.data[self.last_position:]
             if raw_data:
                 yield BlockData(raw_data)
 
     def lex_for_blocks(self, allowed_blocks=None, collect_raw_data=True):
-        return list(
-            self.find_blocks(
-                allowed_blocks=allowed_blocks, collect_raw_data=collect_raw_data
-            )
-        )
+        return list(self.find_blocks(allowed_blocks=allowed_blocks,
+                                     collect_raw_data=collect_raw_data))

core/dbt/clients/agate_helper.py

@@ -10,7 +10,7 @@ from typing import Iterable, List, Dict, Union, Optional, Any
 from dbt.exceptions import RuntimeException
 
 
-BOM = BOM_UTF8.decode("utf-8")  # '\ufeff'
+BOM = BOM_UTF8.decode('utf-8')  # '\ufeff'
 
 
 class ISODateTime(agate.data_types.DateTime):
@@ -30,23 +30,32 @@ class ISODateTime(agate.data_types.DateTime):
         except:  # noqa
             pass
 
-        raise agate.exceptions.CastError('Can not parse value "%s" as datetime.' % d)
+        raise agate.exceptions.CastError(
+            'Can not parse value "%s" as datetime.' % d
+        )
 
 
-def build_type_tester(text_columns: Iterable[str]) -> agate.TypeTester:
+def build_type_tester(
+    text_columns: Iterable[str],
+    string_null_values: Optional[Iterable[str]] = ('null', '')
+) -> agate.TypeTester:
+
     types = [
-        agate.data_types.Number(null_values=("null", "")),
-        agate.data_types.Date(null_values=("null", ""), date_format="%Y-%m-%d"),
-        agate.data_types.DateTime(
-            null_values=("null", ""), datetime_format="%Y-%m-%d %H:%M:%S"
-        ),
-        ISODateTime(null_values=("null", "")),
-        agate.data_types.Boolean(
-            true_values=("true",), false_values=("false",), null_values=("null", "")
-        ),
-        agate.data_types.Text(null_values=("null", "")),
+        agate.data_types.Number(null_values=('null', '')),
+        agate.data_types.Date(null_values=('null', ''),
+                              date_format='%Y-%m-%d'),
+        agate.data_types.DateTime(null_values=('null', ''),
+                                  datetime_format='%Y-%m-%d %H:%M:%S'),
+        ISODateTime(null_values=('null', '')),
+        agate.data_types.Boolean(true_values=('true',),
+                                 false_values=('false',),
+                                 null_values=('null', '')),
+        agate.data_types.Text(null_values=string_null_values)
     ]
-    force = {k: agate.data_types.Text(null_values=("null", "")) for k in text_columns}
+    force = {
+        k: agate.data_types.Text(null_values=string_null_values)
+        for k in text_columns
+    }
     return agate.TypeTester(force=force, types=types)
 
 
@@ -61,7 +70,13 @@ def table_from_rows(
     if text_only_columns is None:
         column_types = DEFAULT_TYPE_TESTER
     else:
-        column_types = build_type_tester(text_only_columns)
+        # If text_only_columns are present, prevent coercing empty string or
+        # literal 'null' strings to a None representation.
+        column_types = build_type_tester(
+            text_only_columns,
+            string_null_values=()
+        )
+
     return agate.Table(rows, column_names, column_types=column_types)
 
 
@@ -81,19 +96,34 @@ def table_from_data(data, column_names: Iterable[str]) -> agate.Table:
 
 
 def table_from_data_flat(data, column_names: Iterable[str]) -> agate.Table:
-    "Convert list of dictionaries into an Agate table"
+    """
+    Convert a list of dictionaries into an Agate table. This method does not
+    coerce string values into more specific types (eg. '005' will not be
+    coerced to '5'). Additionally, this method does not coerce values to
+    None (eg. '' or 'null' will retain their string literal representations).
+    """
 
     rows = []
+    text_only_columns = set()
     for _row in data:
         row = []
-        for value in list(_row.values()):
+        for col_name in column_names:
+            value = _row[col_name]
             if isinstance(value, (dict, list, tuple)):
-                row.append(json.dumps(value, cls=dbt.utils.JSONEncoder))
-            else:
-                row.append(value)
+                # Represent container types as json strings
+                value = json.dumps(value, cls=dbt.utils.JSONEncoder)
+                text_only_columns.add(col_name)
+            elif isinstance(value, str):
+                text_only_columns.add(col_name)
+            row.append(value)
+
         rows.append(row)
 
-    return table_from_rows(rows=rows, column_names=column_names)
+    return table_from_rows(
+        rows=rows,
+        column_names=column_names,
+        text_only_columns=text_only_columns
+    )
 
 
 def empty_table():
@@ -110,7 +140,7 @@ def as_matrix(table):
 
 def from_csv(abspath, text_columns):
     type_tester = build_type_tester(text_columns=text_columns)
-    with open(abspath, encoding="utf-8") as fp:
+    with open(abspath, encoding='utf-8') as fp:
         if fp.read(1) != BOM:
             fp.seek(0)
         return agate.Table.from_csv(fp, column_types=type_tester)
@@ -142,8 +172,8 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
         elif not isinstance(value, type(existing_type)):
             # actual type mismatch!
             raise RuntimeException(
-                f"Tables contain columns with the same names ({key}), "
-                f"but different types ({value} vs {existing_type})"
+                f'Tables contain columns with the same names ({key}), '
+                f'but different types ({value} vs {existing_type})'
             )
 
     def finalize(self) -> Dict[str, agate.data_types.DataType]:
@@ -158,7 +188,7 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
 
 
 def _merged_column_types(
-    tables: List[agate.Table],
+    tables: List[agate.Table]
 ) -> Dict[str, agate.data_types.DataType]:
     # this is a lot like agate.Table.merge, but with handling for all-null
     # rows being "any type".
@@ -185,7 +215,10 @@ def merge_tables(tables: List[agate.Table]) -> agate.Table:
 
     rows: List[agate.Row] = []
     for table in tables:
-        if table.column_names == column_names and table.column_types == column_types:
+        if (
+            table.column_names == column_names and
+            table.column_types == column_types
+        ):
             rows.extend(table.rows)
         else:
             for row in table.rows:

core/dbt/clients/gcloud.py

@@ -12,7 +12,7 @@ https://cloud.google.com/sdk/
 
 def gcloud_installed():
     try:
-        run_cmd(".", ["gcloud", "--version"])
+        run_cmd('.', ['gcloud', '--version'])
         return True
     except OSError as e:
         logger.debug(e)
@@ -21,6 +21,6 @@ def gcloud_installed():
 
 def setup_default_credentials():
     if gcloud_installed():
-        run_cmd(".", ["gcloud", "auth", "application-default", "login"])
+        run_cmd('.', ["gcloud", "auth", "application-default", "login"])
     else:
         raise dbt.exceptions.RuntimeException(NOT_INSTALLED_MSG)

core/dbt/clients/git.py

@@ -4,77 +4,112 @@ import os.path
 from dbt.clients.system import run_cmd, rmdir
 from dbt.logger import GLOBAL_LOGGER as logger
 import dbt.exceptions
+from packaging import version
 
 
-def clone(repo, cwd, dirname=None, remove_git_dir=False, branch=None):
-    clone_cmd = ["git", "clone", "--depth", "1"]
+def _is_commit(revision: str) -> bool:
+    # match SHA-1 git commit
+    return bool(re.match(r"\b[0-9a-f]{40}\b", revision))
 
-    if branch is not None:
-        clone_cmd.extend(["--branch", branch])
+
+def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirectory=None):
+    has_revision = revision is not None
+    is_commit = _is_commit(revision or "")
+
+    clone_cmd = ['git', 'clone', '--depth', '1']
+    if subdirectory:
+        logger.debug('  Subdirectory specified: {}, using sparse checkout.'.format(subdirectory))
+        out, _ = run_cmd(cwd, ['git', '--version'], env={'LC_ALL': 'C'})
+        git_version = version.parse(re.search(r"\d+\.\d+\.\d+", out.decode("utf-8")).group(0))
+        if not git_version >= version.parse("2.25.0"):
+            # 2.25.0 introduces --sparse
+            raise RuntimeError(
+                "Please update your git version to pull a dbt package "
+                "from a subdirectory: your version is {}, >= 2.25.0 needed".format(git_version)
+            )
+        clone_cmd.extend(['--filter=blob:none', '--sparse'])
+
+    if has_revision and not is_commit:
+        clone_cmd.extend(['--branch', revision])
 
     clone_cmd.append(repo)
 
     if dirname is not None:
         clone_cmd.append(dirname)
+    result = run_cmd(cwd, clone_cmd, env={'LC_ALL': 'C'})
 
-    result = run_cmd(cwd, clone_cmd, env={"LC_ALL": "C"})
+    if subdirectory:
+        run_cmd(os.path.join(cwd, dirname or ''), ['git', 'sparse-checkout', 'set', subdirectory])
 
     if remove_git_dir:
-        rmdir(os.path.join(dirname, ".git"))
+        rmdir(os.path.join(dirname, '.git'))
 
     return result
 
 
 def list_tags(cwd):
-    out, err = run_cmd(cwd, ["git", "tag", "--list"], env={"LC_ALL": "C"})
-    tags = out.decode("utf-8").strip().split("\n")
+    out, err = run_cmd(cwd, ['git', 'tag', '--list'], env={'LC_ALL': 'C'})
+    tags = out.decode('utf-8').strip().split("\n")
     return tags
 
 
-def _checkout(cwd, repo, branch):
-    logger.debug("  Checking out branch {}.".format(branch))
+def _checkout(cwd, repo, revision):
+    logger.debug('  Checking out revision {}.'.format(revision))
 
-    run_cmd(cwd, ["git", "remote", "set-branches", "origin", branch])
-    run_cmd(cwd, ["git", "fetch", "--tags", "--depth", "1", "origin", branch])
+    fetch_cmd = ["git", "fetch", "origin", "--depth", "1"]
 
-    tags = list_tags(cwd)
-
-    # Prefer tags to branches if one exists
-    if branch in tags:
-        spec = "tags/{}".format(branch)
+    if _is_commit(revision):
+        run_cmd(cwd, fetch_cmd + [revision])
     else:
-        spec = "origin/{}".format(branch)
+        run_cmd(cwd, ['git', 'remote', 'set-branches', 'origin', revision])
+        run_cmd(cwd, fetch_cmd + ["--tags", revision])
 
-    out, err = run_cmd(cwd, ["git", "reset", "--hard", spec], env={"LC_ALL": "C"})
+    if _is_commit(revision):
+        spec = revision
+    # Prefer tags to branches if one exists
+    elif revision in list_tags(cwd):
+        spec = 'tags/{}'.format(revision)
+    else:
+        spec = 'origin/{}'.format(revision)
+
+    out, err = run_cmd(cwd, ['git', 'reset', '--hard', spec],
+                       env={'LC_ALL': 'C'})
     return out, err
 
 
-def checkout(cwd, repo, branch=None):
-    if branch is None:
-        branch = "HEAD"
+def checkout(cwd, repo, revision=None):
+    if revision is None:
+        revision = 'HEAD'
     try:
-        return _checkout(cwd, repo, branch)
+        return _checkout(cwd, repo, revision)
     except dbt.exceptions.CommandResultError as exc:
-        stderr = exc.stderr.decode("utf-8").strip()
-    dbt.exceptions.bad_package_spec(repo, branch, stderr)
+        stderr = exc.stderr.decode('utf-8').strip()
+    dbt.exceptions.bad_package_spec(repo, revision, stderr)
 
 
 def get_current_sha(cwd):
-    out, err = run_cmd(cwd, ["git", "rev-parse", "HEAD"], env={"LC_ALL": "C"})
+    out, err = run_cmd(cwd, ['git', 'rev-parse', 'HEAD'], env={'LC_ALL': 'C'})
 
-    return out.decode("utf-8")
+    return out.decode('utf-8')
 
 
 def remove_remote(cwd):
-    return run_cmd(cwd, ["git", "remote", "rm", "origin"], env={"LC_ALL": "C"})
+    return run_cmd(cwd, ['git', 'remote', 'rm', 'origin'], env={'LC_ALL': 'C'})
 
 
-def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False, branch=None):
+def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
+                       revision=None, subdirectory=None):
     exists = None
     try:
-        _, err = clone(repo, cwd, dirname=dirname, remove_git_dir=remove_git_dir)
+        _, err = clone(
+            repo,
+            cwd,
+            dirname=dirname,
+            remove_git_dir=remove_git_dir,
+            subdirectory=subdirectory,
+        )
     except dbt.exceptions.CommandResultError as exc:
-        err = exc.stderr.decode("utf-8")
+        err = exc.stderr.decode('utf-8')
         exists = re.match("fatal: destination path '(.+)' already exists", err)
         if not exists:  # something else is wrong, raise it
             raise
@@ -83,26 +118,25 @@ def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False, branch=Non
     start_sha = None
     if exists:
         directory = exists.group(1)
-        logger.debug("Updating existing dependency {}.", directory)
+        logger.debug('Updating existing dependency {}.', directory)
     else:
-        matches = re.match("Cloning into '(.+)'", err.decode("utf-8"))
+        matches = re.match("Cloning into '(.+)'", err.decode('utf-8'))
         if matches is None:
             raise dbt.exceptions.RuntimeException(
                 f'Error cloning {repo} - never saw "Cloning into ..." from git'
             )
         directory = matches.group(1)
-        logger.debug("Pulling new dependency {}.", directory)
+        logger.debug('Pulling new dependency {}.', directory)
     full_path = os.path.join(cwd, directory)
     start_sha = get_current_sha(full_path)
-    checkout(full_path, repo, branch)
+    checkout(full_path, repo, revision)
     end_sha = get_current_sha(full_path)
     if exists:
         if start_sha == end_sha:
-            logger.debug("  Already at {}, nothing to do.", start_sha[:7])
+            logger.debug('  Already at {}, nothing to do.', start_sha[:7])
         else:
-            logger.debug(
-                "  Updated checkout from {} to {}.", start_sha[:7], end_sha[:7]
-            )
+            logger.debug('  Updated checkout from {} to {}.',
+                         start_sha[:7], end_sha[:7])
     else:
-        logger.debug("  Checked out at {}.", end_sha[:7])
-    return directory
+        logger.debug('  Checked out at {}.', end_sha[:7])
+    return os.path.join(directory, subdirectory or '')

core/dbt/clients/jinja.py

@@ -8,17 +8,8 @@ from ast import literal_eval
 from contextlib import contextmanager
 from itertools import chain, islice
 from typing import (
-    List,
-    Union,
-    Set,
-    Optional,
-    Dict,
-    Any,
-    Iterator,
-    Type,
-    NoReturn,
-    Tuple,
-    Callable,
+    List, Union, Set, Optional, Dict, Any, Iterator, Type, NoReturn, Tuple,
+    Callable
 )
 
 import jinja2
@@ -29,22 +20,17 @@ import jinja2.parser
 import jinja2.sandbox
 
 from dbt.utils import (
-    get_dbt_macro_name,
-    get_docs_macro_name,
-    get_materialization_macro_name,
-    deep_map,
+    get_dbt_macro_name, get_docs_macro_name, get_materialization_macro_name,
+    get_test_macro_name, deep_map
 )
 
 from dbt.clients._jinja_blocks import BlockIterator, BlockData, BlockTag
 from dbt.contracts.graph.compiled import CompiledSchemaTestNode
 from dbt.contracts.graph.parsed import ParsedSchemaTestNode
 from dbt.exceptions import (
-    InternalException,
-    raise_compiler_error,
-    CompilationException,
-    invalid_materialization_argument,
-    MacroReturn,
-    JinjaRenderingException,
+    InternalException, raise_compiler_error, CompilationException,
+    invalid_materialization_argument, MacroReturn, JinjaRenderingException,
+    UndefinedMacroException
 )
 from dbt import flags
 from dbt.logger import GLOBAL_LOGGER as logger  # noqa
@@ -55,26 +41,26 @@ def _linecache_inject(source, write):
         # this is the only reliable way to accomplish this. Obviously, it's
         # really darn noisy and will fill your temporary directory
         tmp_file = tempfile.NamedTemporaryFile(
-            prefix="dbt-macro-compiled-",
-            suffix=".py",
+            prefix='dbt-macro-compiled-',
+            suffix='.py',
             delete=False,
-            mode="w+",
-            encoding="utf-8",
+            mode='w+',
+            encoding='utf-8',
         )
         tmp_file.write(source)
         filename = tmp_file.name
     else:
         # `codecs.encode` actually takes a `bytes` as the first argument if
         # the second argument is 'hex' - mypy does not know this.
-        rnd = codecs.encode(os.urandom(12), "hex")  # type: ignore
-        filename = rnd.decode("ascii")
+        rnd = codecs.encode(os.urandom(12), 'hex')  # type: ignore
+        filename = rnd.decode('ascii')
 
     # put ourselves in the cache
     cache_entry = (
         len(source),
         None,
-        [line + "\n" for line in source.splitlines()],
-        filename,
+        [line + '\n' for line in source.splitlines()],
+        filename
     )
     # linecache does in fact have an attribute `cache`, thanks
     linecache.cache[filename] = cache_entry  # type: ignore
@@ -88,10 +74,12 @@ class MacroFuzzParser(jinja2.parser.Parser):
         # modified to fuzz macros defined in the same file. this way
         # dbt can understand the stack of macros being called.
         #  - @cmcarthur
-        node.name = get_dbt_macro_name(self.parse_assign_target(name_only=True).name)
+        node.name = get_dbt_macro_name(
+            self.parse_assign_target(name_only=True).name)
 
         self.parse_signature(node)
-        node.body = self.parse_statements(("name:endmacro",), drop_needle=True)
+        node.body = self.parse_statements(('name:endmacro',),
+                                          drop_needle=True)
         return node
 
 
@@ -107,8 +95,8 @@ class MacroFuzzEnvironment(jinja2.sandbox.SandboxedEnvironment):
         If the value is 'write', also write the files to disk.
         WARNING: This can write a ton of data if you aren't careful.
         """
-        if filename == "<template>" and flags.MACRO_DEBUGGING:
-            write = flags.MACRO_DEBUGGING == "write"
+        if filename == '<template>' and flags.MACRO_DEBUGGING:
+            write = flags.MACRO_DEBUGGING == 'write'
             filename = _linecache_inject(source, write)
 
         return super()._compile(source, filename)  # type: ignore
@@ -151,7 +139,7 @@ def quoted_native_concat(nodes):
     head = list(islice(nodes, 2))
 
     if not head:
-        return ""
+        return ''
 
     if len(head) == 1:
         raw = head[0]
@@ -193,7 +181,9 @@ class NativeSandboxTemplate(jinja2.nativetypes.NativeTemplate):  # mypy: ignore
         vars = dict(*args, **kwargs)
 
         try:
-            return quoted_native_concat(self.root_render_func(self.new_context(vars)))
+            return quoted_native_concat(
+                self.root_render_func(self.new_context(vars))
+            )
         except Exception:
             return self.environment.handle_exception()
 
@@ -232,10 +222,10 @@ class BaseMacroGenerator:
         self.context: Optional[Dict[str, Any]] = context
 
     def get_template(self):
-        raise NotImplementedError("get_template not implemented!")
+        raise NotImplementedError('get_template not implemented!')
 
     def get_name(self) -> str:
-        raise NotImplementedError("get_name not implemented!")
+        raise NotImplementedError('get_name not implemented!')
 
     def get_macro(self):
         name = self.get_name()
@@ -258,7 +248,9 @@ class BaseMacroGenerator:
     def call_macro(self, *args, **kwargs):
         # called from __call__ methods
         if self.context is None:
-            raise InternalException("Context is still None in call_macro!")
+            raise InternalException(
+                'Context is still None in call_macro!'
+            )
         assert self.context is not None
 
         macro = self.get_macro()
@@ -285,7 +277,7 @@ class MacroStack(threading.local):
     def pop(self, name):
         got = self.call_stack.pop()
         if got != name:
-            raise InternalException(f"popped {got}, expected {name}")
+            raise InternalException(f'popped {got}, expected {name}')
 
 
 class MacroGenerator(BaseMacroGenerator):
@@ -294,7 +286,7 @@ class MacroGenerator(BaseMacroGenerator):
         macro,
         context: Optional[Dict[str, Any]] = None,
         node: Optional[Any] = None,
-        stack: Optional[MacroStack] = None,
+        stack: Optional[MacroStack] = None
     ) -> None:
         super().__init__(context)
         self.macro = macro
@@ -342,7 +334,9 @@ class MacroGenerator(BaseMacroGenerator):
 
 
 class QueryStringGenerator(BaseMacroGenerator):
-    def __init__(self, template_str: str, context: Dict[str, Any]) -> None:
+    def __init__(
+        self, template_str: str, context: Dict[str, Any]
+    ) -> None:
         super().__init__(context)
         self.template_str: str = template_str
         env = get_environment()
@@ -352,7 +346,7 @@ class QueryStringGenerator(BaseMacroGenerator):
         )
 
     def get_name(self) -> str:
-        return "query_comment_macro"
+        return 'query_comment_macro'
 
     def get_template(self):
         """Don't use the template cache, we don't have a node"""
@@ -363,41 +357,45 @@ class QueryStringGenerator(BaseMacroGenerator):
 
 
 class MaterializationExtension(jinja2.ext.Extension):
-    tags = ["materialization"]
+    tags = ['materialization']
 
     def parse(self, parser):
         node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
-        materialization_name = parser.parse_assign_target(name_only=True).name
+        materialization_name = \
+            parser.parse_assign_target(name_only=True).name
 
-        adapter_name = "default"
+        adapter_name = 'default'
         node.args = []
         node.defaults = []
 
-        while parser.stream.skip_if("comma"):
+        while parser.stream.skip_if('comma'):
             target = parser.parse_assign_target(name_only=True)
 
-            if target.name == "default":
+            if target.name == 'default':
                 pass
 
-            elif target.name == "adapter":
-                parser.stream.expect("assign")
+            elif target.name == 'adapter':
+                parser.stream.expect('assign')
                 value = parser.parse_expression()
                 adapter_name = value.value
 
             else:
-                invalid_materialization_argument(materialization_name, target.name)
+                invalid_materialization_argument(
+                    materialization_name, target.name
+                )
 
-        node.name = get_materialization_macro_name(materialization_name, adapter_name)
-
-        node.body = parser.parse_statements(
-            ("name:endmaterialization",), drop_needle=True
+        node.name = get_materialization_macro_name(
+            materialization_name, adapter_name
         )
 
+        node.body = parser.parse_statements(('name:endmaterialization',),
+                                            drop_needle=True)
+
         return node
 
 
 class DocumentationExtension(jinja2.ext.Extension):
-    tags = ["docs"]
+    tags = ['docs']
 
     def parse(self, parser):
         node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
@@ -406,12 +404,27 @@ class DocumentationExtension(jinja2.ext.Extension):
         node.args = []
         node.defaults = []
         node.name = get_docs_macro_name(docs_name)
-        node.body = parser.parse_statements(("name:enddocs",), drop_needle=True)
+        node.body = parser.parse_statements(('name:enddocs',),
+                                            drop_needle=True)
+        return node
+
+
+class TestExtension(jinja2.ext.Extension):
+    tags = ['test']
+
+    def parse(self, parser):
+        node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
+        test_name = parser.parse_assign_target(name_only=True).name
+
+        parser.parse_signature(node)
+        node.name = get_test_macro_name(test_name)
+        node.body = parser.parse_statements(('name:endtest',),
+                                            drop_needle=True)
         return node
 
 
 def _is_dunder_name(name):
-    return name.startswith("__") and name.endswith("__")
+    return name.startswith('__') and name.endswith('__')
 
 
 def create_undefined(node=None):
@@ -432,11 +445,10 @@ def create_undefined(node=None):
             return self
 
         def __getattr__(self, name):
-            if name == "name" or _is_dunder_name(name):
+            if name == 'name' or _is_dunder_name(name):
                 raise AttributeError(
-                    "'{}' object has no attribute '{}'".format(
-                        type(self).__name__, name
-                    )
+                    "'{}' object has no attribute '{}'"
+                    .format(type(self).__name__, name)
                 )
 
             self.name = name
@@ -447,24 +459,24 @@ def create_undefined(node=None):
             return self
 
         def __reduce__(self):
-            raise_compiler_error(f"{self.name} is undefined", node=node)
+            raise_compiler_error(f'{self.name} is undefined', node=node)
 
     return Undefined
 
 
 NATIVE_FILTERS: Dict[str, Callable[[Any], Any]] = {
-    "as_text": TextMarker,
-    "as_bool": BoolMarker,
-    "as_native": NativeMarker,
-    "as_number": NumberMarker,
+    'as_text': TextMarker,
+    'as_bool': BoolMarker,
+    'as_native': NativeMarker,
+    'as_number': NumberMarker,
 }
 
 
 TEXT_FILTERS: Dict[str, Callable[[Any], Any]] = {
-    "as_text": lambda x: x,
-    "as_bool": lambda x: x,
-    "as_native": lambda x: x,
-    "as_number": lambda x: x,
+    'as_text': lambda x: x,
+    'as_bool': lambda x: x,
+    'as_native': lambda x: x,
+    'as_number': lambda x: x,
 }
 
 
@@ -474,14 +486,15 @@ def get_environment(
     native: bool = False,
 ) -> jinja2.Environment:
     args: Dict[str, List[Union[str, Type[jinja2.ext.Extension]]]] = {
-        "extensions": ["jinja2.ext.do"]
+        'extensions': ['jinja2.ext.do']
     }
 
     if capture_macros:
-        args["undefined"] = create_undefined(node)
+        args['undefined'] = create_undefined(node)
 
-    args["extensions"].append(MaterializationExtension)
-    args["extensions"].append(DocumentationExtension)
+    args['extensions'].append(MaterializationExtension)
+    args['extensions'].append(DocumentationExtension)
+    args['extensions'].append(TestExtension)
 
     env_cls: Type[jinja2.Environment]
     text_filter: Type
@@ -506,7 +519,7 @@ def catch_jinja(node=None) -> Iterator[None]:
         e.translated = False
         raise CompilationException(str(e), node) from e
     except jinja2.exceptions.UndefinedError as e:
-        raise CompilationException(str(e), node) from e
+        raise UndefinedMacroException(str(e), node) from e
     except CompilationException as exc:
         exc.add_node(node)
         raise
@@ -544,8 +557,8 @@ def _requote_result(raw_value: str, rendered: str) -> str:
     elif single_quoted:
         quote_char = "'"
     else:
-        quote_char = ""
-    return f"{quote_char}{rendered}{quote_char}"
+        quote_char = ''
+    return f'{quote_char}{rendered}{quote_char}'
 
 
 # performance note: Local benmcharking (so take it with a big grain of salt!)
@@ -553,7 +566,7 @@ def _requote_result(raw_value: str, rendered: str) -> str:
 # checking two separate patterns, but the standard deviation is smaller with
 # one pattern. The time difference between the two was ~2 std deviations, which
 # is small enough that I've just chosen the more readable option.
-_HAS_RENDER_CHARS_PAT = re.compile(r"({[{%#]|[#}%]})")
+_HAS_RENDER_CHARS_PAT = re.compile(r'({[{%#]|[#}%]})')
 
 
 def get_rendered(
@@ -570,9 +583,9 @@ def get_rendered(
     # native=True case by passing the input string to ast.literal_eval, like
     # the native renderer does.
     if (
-        not native
-        and isinstance(string, str)
-        and _HAS_RENDER_CHARS_PAT.search(string) is None
+        not native and
+        isinstance(string, str) and
+        _HAS_RENDER_CHARS_PAT.search(string) is None
     ):
         return string
     template = get_template(
@@ -609,11 +622,12 @@ def extract_toplevel_blocks(
         `collect_raw_data` is `True`) `BlockData` objects.
     """
     return BlockIterator(data).lex_for_blocks(
-        allowed_blocks=allowed_blocks, collect_raw_data=collect_raw_data
+        allowed_blocks=allowed_blocks,
+        collect_raw_data=collect_raw_data
     )
 
 
-SCHEMA_TEST_KWARGS_NAME = "_dbt_schema_test_kwargs"
+SCHEMA_TEST_KWARGS_NAME = '_dbt_schema_test_kwargs'
 
 
 def add_rendered_test_kwargs(
@@ -625,21 +639,24 @@ def add_rendered_test_kwargs(
     renderer, then insert that value into the given context as the special test
     keyword arguments member.
     """
-    looks_like_func = r"^\s*(env_var|ref|var|source|doc)\s*\(.+\)\s*$"
+    looks_like_func = r'^\s*(env_var|ref|var|source|doc)\s*\(.+\)\s*$'
 
-    def _convert_function(value: Any, keypath: Tuple[Union[str, int], ...]) -> Any:
+    def _convert_function(
+        value: Any, keypath: Tuple[Union[str, int], ...]
+    ) -> Any:
         if isinstance(value, str):
-            if keypath == ("column_name",):
+            if keypath == ('column_name',):
                 # special case: Don't render column names as native, make them
                 # be strings
                 return value
 
             if re.match(looks_like_func, value) is not None:
                 # curly braces to make rendering happy
-                value = f"{{{{ {value} }}}}"
+                value = f'{{{{ {value} }}}}'
 
             value = get_rendered(
-                value, context, node, capture_macros=capture_macros, native=True
+                value, context, node, capture_macros=capture_macros,
+                native=True
             )
 
         return value

core/dbt/clients/jinja_static.py

@@ -0,0 +1,225 @@
+import jinja2
+from dbt.clients.jinja import get_environment
+from dbt.exceptions import raise_compiler_error
+
+
+def statically_extract_macro_calls(string, ctx, db_wrapper=None):
+    # set 'capture_macros' to capture undefined
+    env = get_environment(None, capture_macros=True)
+    parsed = env.parse(string)
+
+    standard_calls = ['source', 'ref', 'config']
+    possible_macro_calls = []
+    for func_call in parsed.find_all(jinja2.nodes.Call):
+        func_name = None
+        if hasattr(func_call, 'node') and hasattr(func_call.node, 'name'):
+            func_name = func_call.node.name
+        else:
+            # func_call for dbt_utils.current_timestamp macro
+            # Call(
+            #   node=Getattr(
+            #     node=Name(
+            #       name='dbt_utils',
+            #       ctx='load'
+            #     ),
+            #     attr='current_timestamp',
+            #     ctx='load
+            #   ),
+            #   args=[],
+            #   kwargs=[],
+            #   dyn_args=None,
+            #   dyn_kwargs=None
+            # )
+            if (hasattr(func_call, 'node') and
+                    hasattr(func_call.node, 'node') and
+                    type(func_call.node.node).__name__ == 'Name' and
+                    hasattr(func_call.node, 'attr')):
+                package_name = func_call.node.node.name
+                macro_name = func_call.node.attr
+                if package_name == 'adapter':
+                    if macro_name == 'dispatch':
+                        ad_macro_calls = statically_parse_adapter_dispatch(
+                            func_call, ctx, db_wrapper)
+                        possible_macro_calls.extend(ad_macro_calls)
+                    else:
+                        # This skips calls such as adapter.parse_index
+                        continue
+                else:
+                    func_name = f'{package_name}.{macro_name}'
+            else:
+                continue
+        if not func_name:
+            continue
+        if func_name in standard_calls:
+            continue
+        elif ctx.get(func_name):
+            continue
+        else:
+            if func_name not in possible_macro_calls:
+                possible_macro_calls.append(func_name)
+
+    return possible_macro_calls
+
+
+# Call(
+#   node=Getattr(
+#     node=Name(
+#       name='adapter',
+#       ctx='load'
+#     ),
+#     attr='dispatch',
+#     ctx='load'
+#   ),
+#   args=[
+#     Const(value='test_pkg_and_dispatch')
+#   ],
+#   kwargs=[
+#     Keyword(
+#       key='packages',
+#       value=Call(node=Getattr(node=Name(name='local_utils', ctx='load'),
+#          attr='_get_utils_namespaces', ctx='load'), args=[], kwargs=[],
+#          dyn_args=None, dyn_kwargs=None)
+#     )
+#   ],
+#   dyn_args=None,
+#   dyn_kwargs=None
+# )
+def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
+    possible_macro_calls = []
+    # This captures an adapter.dispatch('<macro_name>') call.
+
+    func_name = None
+    # macro_name positional argument
+    if len(func_call.args) > 0:
+        func_name = func_call.args[0].value
+    if func_name:
+        possible_macro_calls.append(func_name)
+
+    # packages positional argument
+    packages = None
+    macro_namespace = None
+    packages_arg = None
+    packages_arg_type = None
+
+    if len(func_call.args) > 1:
+        packages_arg = func_call.args[1]
+        # This can be a List or a Call
+        packages_arg_type = type(func_call.args[1]).__name__
+
+    # keyword arguments
+    if func_call.kwargs:
+        for kwarg in func_call.kwargs:
+            if kwarg.key == 'packages':
+                # The packages keyword will be deprecated and
+                # eventually removed
+                packages_arg = kwarg.value
+                # This can be a List or a Call
+                packages_arg_type = type(kwarg.value).__name__
+            elif kwarg.key == 'macro_name':
+                # This will remain to enable static resolution
+                if type(kwarg.value).__name__ == 'Const':
+                    func_name = kwarg.value.value
+                    possible_macro_calls.append(func_name)
+                else:
+                    raise_compiler_error(f"The macro_name parameter ({kwarg.value.value}) "
+                                         "to adapter.dispatch was not a string")
+            elif kwarg.key == 'macro_namespace':
+                # This will remain to enable static resolution
+                kwarg_type = type(kwarg.value).__name__
+                if kwarg_type == 'Const':
+                    macro_namespace = kwarg.value.value
+                else:
+                    raise_compiler_error("The macro_namespace parameter to adapter.dispatch "
+                                         f"is a {kwarg_type}, not a string")
+
+    # positional arguments
+    if packages_arg:
+        if packages_arg_type == 'List':
+            # This will remain to enable static resolution
+            packages = []
+            for item in packages_arg.items:
+                packages.append(item.value)
+        elif packages_arg_type == 'Const':
+            # This will remain to enable static resolution
+            macro_namespace = packages_arg.value
+        elif packages_arg_type == 'Call':
+            # This is deprecated and should be removed eventually.
+            # It is here to support (hackily) common ways of providing
+            # a packages list to adapter.dispatch
+            if (hasattr(packages_arg, 'node') and
+                    hasattr(packages_arg.node, 'node') and
+                    hasattr(packages_arg.node.node, 'name') and
+                    hasattr(packages_arg.node, 'attr')):
+                package_name = packages_arg.node.node.name
+                macro_name = packages_arg.node.attr
+                if (macro_name.startswith('_get') and 'namespaces' in macro_name):
+                    # noqa: https://github.com/dbt-labs/dbt-utils/blob/9e9407b/macros/cross_db_utils/_get_utils_namespaces.sql
+                    var_name = f'{package_name}_dispatch_list'
+                    # hard code compatibility for fivetran_utils, just a teensy bit different
+                    # noqa: https://github.com/fivetran/dbt_fivetran_utils/blob/0978ba2/macros/_get_utils_namespaces.sql
+                    if package_name == 'fivetran_utils':
+                        default_packages = ['dbt_utils', 'fivetran_utils']
+                    else:
+                        default_packages = [package_name]
+
+                    namespace_names = get_dispatch_list(ctx, var_name, default_packages)
+                    packages = []
+                    if namespace_names:
+                        packages.extend(namespace_names)
+                else:
+                    msg = (
+                        f"As of v0.19.2, custom macros, such as '{macro_name}', are no longer "
+                        "supported in the 'packages' argument of 'adapter.dispatch()'.\n"
+                        f"See https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch "
+                        "for details."
+                    ).strip()
+                    raise_compiler_error(msg)
+        elif packages_arg_type == 'Add':
+            # This logic is for when there is a variable and an addition of a list,
+            # like: packages = (var('local_utils_dispatch_list', []) + ['local_utils2'])
+            # This is deprecated and should be removed eventually.
+            namespace_var = None
+            default_namespaces = []
+            # This might be a single call or it might be the 'left' piece in an addition
+            for var_call in packages_arg.find_all(jinja2.nodes.Call):
+                if (hasattr(var_call, 'node') and
+                        var_call.node.name == 'var' and
+                        hasattr(var_call, 'args')):
+                    namespace_var = var_call.args[0].value
+            if hasattr(packages_arg, 'right'):  # we have a default list of namespaces
+                for item in packages_arg.right.items:
+                    default_namespaces.append(item.value)
+            if namespace_var:
+                namespace_names = get_dispatch_list(ctx, namespace_var, default_namespaces)
+                packages = []
+                if namespace_names:
+                    packages.extend(namespace_names)
+
+    if db_wrapper:
+        macro = db_wrapper.dispatch(
+            func_name,
+            packages=packages,
+            macro_namespace=macro_namespace
+        ).macro
+        func_name = f'{macro.package_name}.{macro.name}'
+        possible_macro_calls.append(func_name)
+    else:  # this is only for test/unit/test_macro_calls.py
+        if macro_namespace:
+            packages = [macro_namespace]
+        if packages is None:
+            packages = []
+        for package_name in packages:
+            possible_macro_calls.append(f'{package_name}.{func_name}')
+
+    return possible_macro_calls
+
+
+def get_dispatch_list(ctx, var_name, default_packages):
+    namespace_list = None
+    try:
+        # match the logic currently used in package _get_namespaces() macro
+        namespace_list = ctx['var'](var_name) + default_packages
+    except Exception:
+        pass
+    namespace_list = namespace_list if namespace_list else default_packages
+    return namespace_list

core/dbt/clients/registry.py

@@ -1,72 +1,79 @@
-from functools import wraps
+import functools
 import requests
-from dbt.exceptions import RegistryException
-from dbt.utils import memoized
+from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
 from dbt.logger import GLOBAL_LOGGER as logger
+from dbt import deprecations
 import os
-import time
 
-if os.getenv("DBT_PACKAGE_HUB_URL"):
-    DEFAULT_REGISTRY_BASE_URL = os.getenv("DBT_PACKAGE_HUB_URL")
+if os.getenv('DBT_PACKAGE_HUB_URL'):
+    DEFAULT_REGISTRY_BASE_URL = os.getenv('DBT_PACKAGE_HUB_URL')
 else:
-    DEFAULT_REGISTRY_BASE_URL = "https://hub.getdbt.com/"
+    DEFAULT_REGISTRY_BASE_URL = 'https://hub.getdbt.com/'
 
 
 def _get_url(url, registry_base_url=None):
     if registry_base_url is None:
         registry_base_url = DEFAULT_REGISTRY_BASE_URL
 
-    return "{}{}".format(registry_base_url, url)
+    return '{}{}'.format(registry_base_url, url)
 
 
-def _wrap_exceptions(fn):
-    @wraps(fn)
-    def wrapper(*args, **kwargs):
-        max_attempts = 5
-        attempt = 0
-        while True:
-            attempt += 1
-            try:
-                return fn(*args, **kwargs)
-            except requests.exceptions.ConnectionError as exc:
-                if attempt < max_attempts:
-                    time.sleep(1)
-                    continue
-
-                raise RegistryException("Unable to connect to registry hub") from exc
-
-    return wrapper
+def _get_with_retries(path, registry_base_url=None):
+    get_fn = functools.partial(_get, path, registry_base_url)
+    return connection_exception_retry(get_fn, 5)
 
 
-@_wrap_exceptions
 def _get(path, registry_base_url=None):
     url = _get_url(path, registry_base_url)
-    logger.debug("Making package registry request: GET {}".format(url))
-    resp = requests.get(url)
-    logger.debug("Response from registry: GET {} {}".format(url, resp.status_code))
+    logger.debug('Making package registry request: GET {}'.format(url))
+    resp = requests.get(url, timeout=30)
+    logger.debug('Response from registry: GET {} {}'.format(url,
+                                                            resp.status_code))
     resp.raise_for_status()
     return resp.json()
 
 
 def index(registry_base_url=None):
-    return _get("api/v1/index.json", registry_base_url)
+    return _get_with_retries('api/v1/index.json', registry_base_url)
 
 
 index_cached = memoized(index)
 
 
 def packages(registry_base_url=None):
-    return _get("api/v1/packages.json", registry_base_url)
+    return _get_with_retries('api/v1/packages.json', registry_base_url)
 
 
 def package(name, registry_base_url=None):
-    return _get("api/v1/{}.json".format(name), registry_base_url)
+    response = _get_with_retries('api/v1/{}.json'.format(name), registry_base_url)
+
+    # Either redirectnamespace or redirectname in the JSON response indicate a redirect
+    # redirectnamespace redirects based on package ownership
+    # redirectname redirects based on package name
+    # Both can be present at the same time, or neither. Fails gracefully to old name
+
+    if ('redirectnamespace' in response) or ('redirectname' in response):
+
+        if ('redirectnamespace' in response) and response['redirectnamespace'] is not None:
+            use_namespace = response['redirectnamespace']
+        else:
+            use_namespace = response['namespace']
+
+        if ('redirectname' in response) and response['redirectname'] is not None:
+            use_name = response['redirectname']
+        else:
+            use_name = response['name']
+
+        new_nwo = use_namespace + "/" + use_name
+        deprecations.warn('package-redirect', old_name=name, new_name=new_nwo)
+
+    return response
 
 
 def package_version(name, version, registry_base_url=None):
-    return _get("api/v1/{}/{}.json".format(name, version), registry_base_url)
+    return _get_with_retries('api/v1/{}/{}.json'.format(name, version), registry_base_url)
 
 
 def get_available_versions(name):
     response = package(name)
-    return list(response["versions"])
+    return list(response['versions'])

core/dbt/clients/system.py

@@ -1,4 +1,5 @@
 import errno
+import functools
 import fnmatch
 import json
 import os
@@ -10,14 +11,15 @@ import sys
 import tarfile
 import requests
 import stat
-from typing import Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
+from typing import (
+    Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
+)
 
 import dbt.exceptions
-import dbt.utils
-
 from dbt.logger import GLOBAL_LOGGER as logger
+from dbt.utils import _connection_exception_retry as connection_exception_retry
 
-if sys.platform == "win32":
+if sys.platform == 'win32':
     from ctypes import WinDLL, c_bool
 else:
     WinDLL = None
@@ -49,29 +51,30 @@ def find_matching(
     reobj = re.compile(regex, re.IGNORECASE)
 
     for relative_path_to_search in relative_paths_to_search:
-        absolute_path_to_search = os.path.join(root_path, relative_path_to_search)
+        absolute_path_to_search = os.path.join(
+            root_path, relative_path_to_search)
         walk_results = os.walk(absolute_path_to_search)
 
         for current_path, subdirectories, local_files in walk_results:
             for local_file in local_files:
                 absolute_path = os.path.join(current_path, local_file)
-                relative_path = os.path.relpath(absolute_path, absolute_path_to_search)
+                relative_path = os.path.relpath(
+                    absolute_path, absolute_path_to_search
+                )
                 if reobj.match(local_file):
-                    matching.append(
-                        {
-                            "searched_path": relative_path_to_search,
-                            "absolute_path": absolute_path,
-                            "relative_path": relative_path,
-                        }
-                    )
+                    matching.append({
+                        'searched_path': relative_path_to_search,
+                        'absolute_path': absolute_path,
+                        'relative_path': relative_path,
+                    })
 
     return matching
 
 
 def load_file_contents(path: str, strip: bool = True) -> str:
     path = convert_path(path)
-    with open(path, "rb") as handle:
-        to_return = handle.read().decode("utf-8")
+    with open(path, 'rb') as handle:
+        to_return = handle.read().decode('utf-8')
 
     if strip:
         to_return = to_return.strip()
@@ -98,14 +101,14 @@ def make_directory(path: str) -> None:
                 raise e
 
 
-def make_file(path: str, contents: str = "", overwrite: bool = False) -> bool:
+def make_file(path: str, contents: str = '', overwrite: bool = False) -> bool:
     """
     Make a file at `path` assuming that the directory it resides in already
     exists. The file is saved with contents `contents`
     """
     if overwrite or not os.path.exists(path):
         path = convert_path(path)
-        with open(path, "w") as fh:
+        with open(path, 'w') as fh:
             fh.write(contents)
         return True
 
@@ -117,7 +120,7 @@ def make_symlink(source: str, link_path: str) -> None:
     Create a symlink at `link_path` referring to `source`.
     """
     if not supports_symlinks():
-        dbt.exceptions.system_error("create a symbolic link")
+        dbt.exceptions.system_error('create a symbolic link')
 
     os.symlink(source, link_path)
 
@@ -126,11 +129,11 @@ def supports_symlinks() -> bool:
     return getattr(os, "symlink", None) is not None
 
 
-def write_file(path: str, contents: str = "") -> bool:
+def write_file(path: str, contents: str = '') -> bool:
     path = convert_path(path)
     try:
         make_directory(os.path.dirname(path))
-        with open(path, "w", encoding="utf-8") as f:
+        with open(path, 'w', encoding='utf-8') as f:
             f.write(str(contents))
     except Exception as exc:
         # note that you can't just catch FileNotFound, because sometimes
@@ -139,20 +142,20 @@ def write_file(path: str, contents: str = "") -> bool:
         # sometimes windows fails to write paths that are less than the length
         # limit. So on windows, suppress all errors that happen from writing
         # to disk.
-        if os.name == "nt":
+        if os.name == 'nt':
             # sometimes we get a winerror of 3 which means the path was
             # definitely too long, but other times we don't and it means the
             # path was just probably too long. This is probably based on the
             # windows/python version.
-            if getattr(exc, "winerror", 0) == 3:
-                reason = "Path was too long"
+            if getattr(exc, 'winerror', 0) == 3:
+                reason = 'Path was too long'
             else:
-                reason = "Path was possibly too long"
+                reason = 'Path was possibly too long'
             # all our hard work and the path was still too long. Log and
             # continue.
             logger.debug(
-                f"Could not write to path {path}({len(path)} characters): "
-                f"{reason}\nexception: {exc}"
+                f'Could not write to path {path}({len(path)} characters): '
+                f'{reason}\nexception: {exc}'
             )
         else:
             raise
@@ -186,7 +189,10 @@ def resolve_path_from_base(path_to_resolve: str, base_path: str) -> str:
     If path_to_resolve is an absolute path or a user path (~), just
     resolve it to an absolute path and return.
     """
-    return os.path.abspath(os.path.join(base_path, os.path.expanduser(path_to_resolve)))
+    return os.path.abspath(
+        os.path.join(
+            base_path,
+            os.path.expanduser(path_to_resolve)))
 
 
 def rmdir(path: str) -> None:
@@ -196,7 +202,7 @@ def rmdir(path: str) -> None:
     cloned via git) can cause rmtree to throw a PermissionError exception
     """
     path = convert_path(path)
-    if sys.platform == "win32":
+    if sys.platform == 'win32':
         onerror = _windows_rmdir_readonly
     else:
         onerror = None
@@ -215,7 +221,7 @@ def _win_prepare_path(path: str) -> str:
     # letter back in.
     # Unless it starts with '\\'. In that case, the path is a UNC mount point
     # and splitdrive will be fine.
-    if not path.startswith("\\\\") and path.startswith("\\"):
+    if not path.startswith('\\\\') and path.startswith('\\'):
         curdrive = os.path.splitdrive(os.getcwd())[0]
         path = curdrive + path
 
@@ -230,7 +236,7 @@ def _win_prepare_path(path: str) -> str:
 
 
 def _supports_long_paths() -> bool:
-    if sys.platform != "win32":
+    if sys.platform != 'win32':
         return True
     # Eryk Sun says to use `WinDLL('ntdll')` instead of `windll.ntdll` because
     # of pointer caching in a comment here:
@@ -238,11 +244,11 @@ def _supports_long_paths() -> bool:
     # I don't know exaclty what he means, but I am inclined to believe him as
     # he's pretty active on Python windows bugs!
     try:
-        dll = WinDLL("ntdll")
+        dll = WinDLL('ntdll')
     except OSError:  # I don't think this happens? you need ntdll to run python
         return False
     # not all windows versions have it at all
-    if not hasattr(dll, "RtlAreLongPathsEnabled"):
+    if not hasattr(dll, 'RtlAreLongPathsEnabled'):
         return False
     # tell windows we want to get back a single unsigned byte (a bool).
     dll.RtlAreLongPathsEnabled.restype = c_bool
@@ -262,7 +268,7 @@ def convert_path(path: str) -> str:
     if _supports_long_paths():
         return path
 
-    prefix = "\\\\?\\"
+    prefix = '\\\\?\\'
     # Nothing to do
     if path.startswith(prefix):
         return path
@@ -293,35 +299,39 @@ def path_is_symlink(path: str) -> bool:
 
 def open_dir_cmd() -> str:
     # https://docs.python.org/2/library/sys.html#sys.platform
-    if sys.platform == "win32":
-        return "start"
+    if sys.platform == 'win32':
+        return 'start'
 
-    elif sys.platform == "darwin":
-        return "open"
+    elif sys.platform == 'darwin':
+        return 'open'
 
     else:
-        return "xdg-open"
+        return 'xdg-open'
 
 
-def _handle_posix_cwd_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
+def _handle_posix_cwd_error(
+    exc: OSError, cwd: str, cmd: List[str]
+) -> NoReturn:
     if exc.errno == errno.ENOENT:
-        message = "Directory does not exist"
+        message = 'Directory does not exist'
     elif exc.errno == errno.EACCES:
-        message = "Current user cannot access directory, check permissions"
+        message = 'Current user cannot access directory, check permissions'
     elif exc.errno == errno.ENOTDIR:
-        message = "Not a directory"
+        message = 'Not a directory'
     else:
-        message = "Unknown OSError: {} - cwd".format(str(exc))
+        message = 'Unknown OSError: {} - cwd'.format(str(exc))
     raise dbt.exceptions.WorkingDirectoryError(cwd, cmd, message)
 
 
-def _handle_posix_cmd_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
+def _handle_posix_cmd_error(
+    exc: OSError, cwd: str, cmd: List[str]
+) -> NoReturn:
     if exc.errno == errno.ENOENT:
         message = "Could not find command, ensure it is in the user's PATH"
     elif exc.errno == errno.EACCES:
-        message = "User does not have permissions for this command"
+        message = 'User does not have permissions for this command'
     else:
-        message = "Unknown OSError: {} - cmd".format(str(exc))
+        message = 'Unknown OSError: {} - cmd'.format(str(exc))
     raise dbt.exceptions.ExecutableError(cwd, cmd, message)
 
 
@@ -346,7 +356,7 @@ def _handle_posix_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
             - exc.errno == EACCES
             - exc.filename == None(?)
     """
-    if getattr(exc, "filename", None) == cwd:
+    if getattr(exc, 'filename', None) == cwd:
         _handle_posix_cwd_error(exc, cwd, cmd)
     else:
         _handle_posix_cmd_error(exc, cwd, cmd)
@@ -355,48 +365,46 @@ def _handle_posix_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
 def _handle_windows_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
     cls: Type[dbt.exceptions.Exception] = dbt.exceptions.CommandError
     if exc.errno == errno.ENOENT:
-        message = (
-            "Could not find command, ensure it is in the user's PATH "
-            "and that the user has permissions to run it"
-        )
+        message = ("Could not find command, ensure it is in the user's PATH "
+                   "and that the user has permissions to run it")
         cls = dbt.exceptions.ExecutableError
     elif exc.errno == errno.ENOEXEC:
-        message = "Command was not executable, ensure it is valid"
+        message = ('Command was not executable, ensure it is valid')
         cls = dbt.exceptions.ExecutableError
     elif exc.errno == errno.ENOTDIR:
-        message = (
-            "Unable to cd: path does not exist, user does not have"
-            " permissions, or not a directory"
-        )
+        message = ('Unable to cd: path does not exist, user does not have'
+                   ' permissions, or not a directory')
         cls = dbt.exceptions.WorkingDirectoryError
     else:
         message = 'Unknown error: {} (errno={}: "{}")'.format(
-            str(exc), exc.errno, errno.errorcode.get(exc.errno, "<Unknown!>")
+            str(exc), exc.errno, errno.errorcode.get(exc.errno, '<Unknown!>')
         )
     raise cls(cwd, cmd, message)
 
 
 def _interpret_oserror(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
-    """Interpret an OSError exc and raise the appropriate dbt exception."""
+    """Interpret an OSError exc and raise the appropriate dbt exception.
+
+    """
     if len(cmd) == 0:
         raise dbt.exceptions.CommandError(cwd, cmd)
 
     # all of these functions raise unconditionally
-    if os.name == "nt":
+    if os.name == 'nt':
         _handle_windows_error(exc, cwd, cmd)
     else:
         _handle_posix_error(exc, cwd, cmd)
 
     # this should not be reachable, raise _something_ at least!
     raise dbt.exceptions.InternalException(
-        "Unhandled exception in _interpret_oserror: {}".format(exc)
+        'Unhandled exception in _interpret_oserror: {}'.format(exc)
     )
 
 
 def run_cmd(
     cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None
 ) -> Tuple[bytes, bytes]:
-    logger.debug('Executing "{}"'.format(" ".join(cmd)))
+    logger.debug('Executing "{}"'.format(' '.join(cmd)))
     if len(cmd) == 0:
         raise dbt.exceptions.CommandError(cwd, cmd)
 
@@ -408,9 +416,15 @@ def run_cmd(
         full_env.update(env)
 
     try:
+        exe_pth = shutil.which(cmd[0])
+        if exe_pth:
+            cmd = [os.path.abspath(exe_pth)] + list(cmd[1:])
         proc = subprocess.Popen(
-            cmd, cwd=cwd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=full_env
-        )
+            cmd,
+            cwd=cwd,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            env=full_env)
 
         out, err = proc.communicate()
     except OSError as exc:
@@ -420,19 +434,27 @@ def run_cmd(
     logger.debug('STDERR: "{!s}"'.format(err))
 
     if proc.returncode != 0:
-        logger.debug("command return code={}".format(proc.returncode))
-        raise dbt.exceptions.CommandResultError(cwd, cmd, proc.returncode, out, err)
+        logger.debug('command return code={}'.format(proc.returncode))
+        raise dbt.exceptions.CommandResultError(cwd, cmd, proc.returncode,
+                                                out, err)
 
     return out, err
 
 
+def download_with_retries(
+    url: str, path: str, timeout: Optional[Union[float, tuple]] = None
+) -> None:
+    download_fn = functools.partial(download, url, path, timeout)
+    connection_exception_retry(download_fn, 5)
+
+
 def download(
     url: str, path: str, timeout: Optional[Union[float, tuple]] = None
 ) -> None:
     path = convert_path(path)
-    connection_timeout = timeout or float(os.getenv("DBT_HTTP_TIMEOUT", 10))
+    connection_timeout = timeout or float(os.getenv('DBT_HTTP_TIMEOUT', 10))
     response = requests.get(url, timeout=connection_timeout)
-    with open(path, "wb") as handle:
+    with open(path, 'wb') as handle:
         for block in response.iter_content(1024 * 64):
             handle.write(block)
 
@@ -456,7 +478,7 @@ def untar_package(
 ) -> None:
     tar_path = convert_path(tar_path)
     tar_dir_name = None
-    with tarfile.open(tar_path, "r") as tarball:
+    with tarfile.open(tar_path, 'r') as tarball:
         tarball.extractall(dest_dir)
         tar_dir_name = os.path.commonprefix(tarball.getnames())
     if rename_to:
@@ -472,7 +494,7 @@ def chmod_and_retry(func, path, exc_info):
     We want to retry most operations here, but listdir is one that we know will
     be useless.
     """
-    if func is os.listdir or os.name != "nt":
+    if func is os.listdir or os.name != 'nt':
         raise
     os.chmod(path, stat.S_IREAD | stat.S_IWRITE)
     # on error,this will raise.
@@ -493,7 +515,7 @@ def move(src, dst):
     """
     src = convert_path(src)
     dst = convert_path(dst)
-    if os.name != "nt":
+    if os.name != 'nt':
         return shutil.move(src, dst)
 
     if os.path.isdir(dst):
@@ -501,7 +523,7 @@ def move(src, dst):
             os.rename(src, dst)
             return
 
-        dst = os.path.join(dst, os.path.basename(src.rstrip("/\\")))
+        dst = os.path.join(dst, os.path.basename(src.rstrip('/\\')))
         if os.path.exists(dst):
             raise EnvironmentError("Path '{}' already exists".format(dst))
 
@@ -510,10 +532,11 @@ def move(src, dst):
     except OSError:
         # probably different drives
         if os.path.isdir(src):
-            if _absnorm(dst + "\\").startswith(_absnorm(src + "\\")):
+            if _absnorm(dst + '\\').startswith(_absnorm(src + '\\')):
                 # dst is inside src
                 raise EnvironmentError(
-                    "Cannot move a directory '{}' into itself '{}'".format(src, dst)
+                    "Cannot move a directory '{}' into itself '{}'"
+                    .format(src, dst)
                 )
             shutil.copytree(src, dst, symlinks=True)
             rmtree(src)

core/dbt/clients/yaml_helper.py

@@ -1,13 +1,19 @@
 import dbt.exceptions
-
+from typing import Any, Dict, Optional
 import yaml
 import yaml.scanner
 
 # the C version is faster, but it doesn't always exist
 try:
-    from yaml import CLoader as Loader, CSafeLoader as SafeLoader, CDumper as Dumper
+    from yaml import (
+        CLoader as Loader,
+        CSafeLoader as SafeLoader,
+        CDumper as Dumper
+    )
 except ImportError:
-    from yaml import Loader, SafeLoader, Dumper  # type: ignore  # noqa: F401
+    from yaml import (  # type: ignore  # noqa: F401
+        Loader, SafeLoader, Dumper
+    )
 
 
 YAML_ERROR_MESSAGE = """
@@ -27,14 +33,14 @@ def line_no(i, line, width=3):
 
 
 def prefix_with_line_numbers(string, no_start, no_end):
-    line_list = string.split("\n")
+    line_list = string.split('\n')
 
     numbers = range(no_start, no_end)
     relevant_lines = line_list[no_start:no_end]
 
-    return "\n".join(
-        [line_no(i + 1, line) for (i, line) in zip(numbers, relevant_lines)]
-    )
+    return "\n".join([
+        line_no(i + 1, line) for (i, line) in zip(numbers, relevant_lines)
+    ])
 
 
 def contextualized_yaml_error(raw_contents, error):
@@ -45,12 +51,12 @@ def contextualized_yaml_error(raw_contents, error):
 
     nice_error = prefix_with_line_numbers(raw_contents, min_line, max_line)
 
-    return YAML_ERROR_MESSAGE.format(
-        line_number=mark.line + 1, nice_error=nice_error, raw_error=error
-    )
+    return YAML_ERROR_MESSAGE.format(line_number=mark.line + 1,
+                                     nice_error=nice_error,
+                                     raw_error=error)
 
 
-def safe_load(contents):
+def safe_load(contents) -> Optional[Dict[str, Any]]:
     return yaml.load(contents, Loader=SafeLoader)
 
 
@@ -58,7 +64,7 @@ def load_yaml_text(contents):
     try:
         return safe_load(contents)
     except (yaml.scanner.ScannerError, yaml.YAMLError) as e:
-        if hasattr(e, "problem_mark"):
+        if hasattr(e, 'problem_mark'):
             error = contextualized_yaml_error(contents, e)
         else:
             error = str(e)

core/dbt/compilation.py

@@ -12,9 +12,8 @@ from dbt.clients.system import make_directory
 from dbt.context.providers import generate_runtime_model
 from dbt.contracts.graph.manifest import Manifest
 from dbt.contracts.graph.compiled import (
-    CompiledDataTestNode,
-    CompiledSchemaTestNode,
     COMPILED_TYPES,
+    CompiledSchemaTestNode,
     GraphMemberNode,
     InjectedCTE,
     ManifestNode,
@@ -32,28 +31,28 @@ from dbt.node_types import NodeType
 from dbt.utils import pluralize
 import dbt.tracking
 
-graph_file_name = "graph.gpickle"
+graph_file_name = 'graph.gpickle'
 
 
 def _compiled_type_for(model: ParsedNode):
     if type(model) not in COMPILED_TYPES:
         raise InternalException(
-            f"Asked to compile {type(model)} node, but it has no compiled form"
+            f'Asked to compile {type(model)} node, but it has no compiled form'
         )
     return COMPILED_TYPES[type(model)]
 
 
 def print_compile_stats(stats):
     names = {
-        NodeType.Model: "model",
-        NodeType.Test: "test",
-        NodeType.Snapshot: "snapshot",
-        NodeType.Analysis: "analysis",
-        NodeType.Macro: "macro",
-        NodeType.Operation: "operation",
-        NodeType.Seed: "seed file",
-        NodeType.Source: "source",
-        NodeType.Exposure: "exposure",
+        NodeType.Model: 'model',
+        NodeType.Test: 'test',
+        NodeType.Snapshot: 'snapshot',
+        NodeType.Analysis: 'analysis',
+        NodeType.Macro: 'macro',
+        NodeType.Operation: 'operation',
+        NodeType.Seed: 'seed file',
+        NodeType.Source: 'source',
+        NodeType.Exposure: 'exposure',
     }
 
     results = {k: 0 for k in names.keys()}
@@ -64,9 +63,10 @@ def print_compile_stats(stats):
         resource_counts = {k.pluralize(): v for k, v in results.items()}
         dbt.tracking.track_resource_counts(resource_counts)
 
-    stat_line = ", ".join(
-        [pluralize(ct, names.get(t)) for t, ct in results.items() if t in names]
-    )
+    stat_line = ", ".join([
+        pluralize(ct, names.get(t)) for t, ct in results.items()
+        if t in names
+    ])
 
     logger.info("Found {}".format(stat_line))
 
@@ -165,7 +165,9 @@ class Compiler:
         extra_context: Dict[str, Any],
     ) -> Dict[str, Any]:
 
-        context = generate_runtime_model(node, self.config, manifest)
+        context = generate_runtime_model(
+            node, self.config, manifest
+        )
         context.update(extra_context)
         if isinstance(node, CompiledSchemaTestNode):
             # for test nodes, add a special keyword args value to the context
@@ -180,7 +182,7 @@ class Compiler:
 
     def _get_relation_name(self, node: ParsedNode):
         relation_name = None
-        if node.resource_type in NodeType.refable() and not node.is_ephemeral_model:
+        if node.is_relational and not node.is_ephemeral_model:
             adapter = get_adapter(self.config)
             relation_cls = adapter.Relation
             relation_name = str(relation_cls.create_from(self.config, node))
@@ -223,45 +225,47 @@ class Compiler:
 
         with_stmt = None
         for token in parsed.tokens:
-            if token.is_keyword and token.normalized == "WITH":
+            if token.is_keyword and token.normalized == 'WITH':
                 with_stmt = token
                 break
 
         if with_stmt is None:
             # no with stmt, add one, and inject CTEs right at the beginning
             first_token = parsed.token_first()
-            with_stmt = sqlparse.sql.Token(sqlparse.tokens.Keyword, "with")
+            with_stmt = sqlparse.sql.Token(sqlparse.tokens.Keyword, 'with')
             parsed.insert_before(first_token, with_stmt)
         else:
             # stmt exists, add a comma (which will come after injected CTEs)
-            trailing_comma = sqlparse.sql.Token(sqlparse.tokens.Punctuation, ",")
+            trailing_comma = sqlparse.sql.Token(
+                sqlparse.tokens.Punctuation, ','
+            )
             parsed.insert_after(with_stmt, trailing_comma)
 
         token = sqlparse.sql.Token(
-            sqlparse.tokens.Keyword, ", ".join(c.sql for c in ctes)
+            sqlparse.tokens.Keyword,
+            ", ".join(c.sql for c in ctes)
         )
         parsed.insert_after(with_stmt, token)
 
         return str(parsed)
 
-    def _get_dbt_test_name(self) -> str:
-        return "dbt__cte__internal_test"
-
-    # This method is called by the 'compile_node' method. Starting
-    # from the node that it is passed in, it will recursively call
-    # itself using the 'extra_ctes'.  The 'ephemeral' models do
-    # not produce SQL that is executed directly, instead they
-    # are rolled up into the models that refer to them by
-    # inserting CTEs into the SQL.
     def _recursively_prepend_ctes(
         self,
         model: NonSourceCompiledNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]],
     ) -> Tuple[NonSourceCompiledNode, List[InjectedCTE]]:
-
+        """This method is called by the 'compile_node' method. Starting
+        from the node that it is passed in, it will recursively call
+        itself using the 'extra_ctes'.  The 'ephemeral' models do
+        not produce SQL that is executed directly, instead they
+        are rolled up into the models that refer to them by
+        inserting CTEs into the SQL.
+        """
         if model.compiled_sql is None:
-            raise RuntimeException("Cannot inject ctes into an unparsed node", model)
+            raise RuntimeException(
+                'Cannot inject ctes into an unparsed node', model
+            )
         if model.extra_ctes_injected:
             return (model, model.extra_ctes)
 
@@ -275,62 +279,59 @@ class Compiler:
         # gathered and then "injected" into the model.
         prepended_ctes: List[InjectedCTE] = []
 
-        dbt_test_name = self._get_dbt_test_name()
-
         # extra_ctes are added to the model by
         # RuntimeRefResolver.create_relation, which adds an
         # extra_cte for every model relation which is an
         # ephemeral model.
         for cte in model.extra_ctes:
-            if cte.id == dbt_test_name:
-                sql = cte.sql
+            if cte.id not in manifest.nodes:
+                raise InternalException(
+                    f'During compilation, found a cte reference that '
+                    f'could not be resolved: {cte.id}'
+                )
+            cte_model = manifest.nodes[cte.id]
+
+            if not cte_model.is_ephemeral_model:
+                raise InternalException(f'{cte.id} is not ephemeral')
+
+            # This model has already been compiled, so it's been
+            # through here before
+            if getattr(cte_model, 'compiled', False):
+                assert isinstance(cte_model, tuple(COMPILED_TYPES.values()))
+                cte_model = cast(NonSourceCompiledNode, cte_model)
+                new_prepended_ctes = cte_model.extra_ctes
+
+            # if the cte_model isn't compiled, i.e. first time here
             else:
-                if cte.id not in manifest.nodes:
-                    raise InternalException(
-                        f"During compilation, found a cte reference that "
-                        f"could not be resolved: {cte.id}"
-                    )
-                cte_model = manifest.nodes[cte.id]
-
-                if not cte_model.is_ephemeral_model:
-                    raise InternalException(f"{cte.id} is not ephemeral")
-
-                # This model has already been compiled, so it's been
-                # through here before
-                if getattr(cte_model, "compiled", False):
-                    assert isinstance(cte_model, tuple(COMPILED_TYPES.values()))
-                    cte_model = cast(NonSourceCompiledNode, cte_model)
-                    new_prepended_ctes = cte_model.extra_ctes
-
-                # if the cte_model isn't compiled, i.e. first time here
-                else:
-                    # This is an ephemeral parsed model that we can compile.
-                    # Compile and update the node
-                    cte_model = self._compile_node(cte_model, manifest, extra_context)
-                    # recursively call this method
-                    cte_model, new_prepended_ctes = self._recursively_prepend_ctes(
+                # This is an ephemeral parsed model that we can compile.
+                # Compile and update the node
+                cte_model = self._compile_node(
+                    cte_model, manifest, extra_context)
+                # recursively call this method
+                cte_model, new_prepended_ctes = \
+                    self._recursively_prepend_ctes(
                         cte_model, manifest, extra_context
                     )
-                    # Save compiled SQL file and sync manifest
-                    self._write_node(cte_model)
-                    manifest.sync_update_node(cte_model)
+                # Save compiled SQL file and sync manifest
+                self._write_node(cte_model)
+                manifest.sync_update_node(cte_model)
 
-                _extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
+            _extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
 
-                new_cte_name = self.add_ephemeral_prefix(cte_model.name)
-                sql = f" {new_cte_name} as (\n{cte_model.compiled_sql}\n)"
+            new_cte_name = self.add_ephemeral_prefix(cte_model.name)
+            rendered_sql = (
+                cte_model._pre_injected_sql or cte_model.compiled_sql
+            )
+            sql = f' {new_cte_name} as (\n{rendered_sql}\n)'
 
             _add_prepended_cte(prepended_ctes, InjectedCTE(id=cte.id, sql=sql))
 
-        # We don't save injected_sql into compiled sql for ephemeral models
-        # because it will cause problems with processing of subsequent models.
-        # Ephemeral models do not produce executable SQL of their own.
-        if not model.is_ephemeral_model:
-            injected_sql = self._inject_ctes_into_sql(
-                model.compiled_sql,
-                prepended_ctes,
-            )
-            model.compiled_sql = injected_sql
+        injected_sql = self._inject_ctes_into_sql(
+            model.compiled_sql,
+            prepended_ctes,
+        )
+        model._pre_injected_sql = model.compiled_sql
+        model.compiled_sql = injected_sql
         model.extra_ctes_injected = True
         model.extra_ctes = prepended_ctes
         model.validate(model.to_dict(omit_none=True))
@@ -339,33 +340,6 @@ class Compiler:
 
         return model, prepended_ctes
 
-    def _add_ctes(
-        self,
-        compiled_node: NonSourceCompiledNode,
-        manifest: Manifest,
-        extra_context: Dict[str, Any],
-    ) -> NonSourceCompiledNode:
-        """Wrap the data test SQL in a CTE."""
-
-        # for data tests, we need to insert a special CTE at the end of the
-        # list containing the test query, and then have the "real" query be a
-        # select count(*) from that model.
-        # the benefit of doing it this way is that _add_ctes() can be
-        # rewritten for different adapters to handle databases that don't
-        # support CTEs, or at least don't have full support.
-        if isinstance(compiled_node, CompiledDataTestNode):
-            # the last prepend (so last in order) should be the data test body.
-            # then we can add our select count(*) from _that_ cte as the "real"
-            # compiled_sql, and do the regular prepend logic from CTEs.
-            name = self._get_dbt_test_name()
-            cte = InjectedCTE(
-                id=name, sql=f" {name} as (\n{compiled_node.compiled_sql}\n)"
-            )
-            compiled_node.extra_ctes.append(cte)
-            compiled_node.compiled_sql = f"\nselect count(*) from {name}"
-
-        return compiled_node
-
     # creates a compiled_node from the ManifestNode passed in,
     # creates a "context" dictionary for jinja rendering,
     # and then renders the "compiled_sql" using the node, the
@@ -382,17 +356,17 @@ class Compiler:
         logger.debug("Compiling {}".format(node.unique_id))
 
         data = node.to_dict(omit_none=True)
-        data.update(
-            {
-                "compiled": False,
-                "compiled_sql": None,
-                "extra_ctes_injected": False,
-                "extra_ctes": [],
-            }
-        )
+        data.update({
+            'compiled': False,
+            'compiled_sql': None,
+            'extra_ctes_injected': False,
+            'extra_ctes': [],
+        })
         compiled_node = _compiled_type_for(node).from_dict(data)
 
-        context = self._create_node_context(compiled_node, manifest, extra_context)
+        context = self._create_node_context(
+            compiled_node, manifest, extra_context
+        )
 
         compiled_node.compiled_sql = jinja.get_rendered(
             node.raw_sql,
@@ -404,10 +378,6 @@ class Compiler:
 
         compiled_node.compiled = True
 
-        # add ctes for specific test nodes, and also for
-        # possible future use in adapters
-        compiled_node = self._add_ctes(compiled_node, manifest, extra_context)
-
         return compiled_node
 
     def write_graph_file(self, linker: Linker, manifest: Manifest):
@@ -416,17 +386,21 @@ class Compiler:
         if flags.WRITE_JSON:
             linker.write_graph(graph_path, manifest)
 
-    def link_node(self, linker: Linker, node: GraphMemberNode, manifest: Manifest):
+    def link_node(
+        self, linker: Linker, node: GraphMemberNode, manifest: Manifest
+    ):
         linker.add_node(node.unique_id)
 
         for dependency in node.depends_on_nodes:
             if dependency in manifest.nodes:
                 linker.dependency(
-                    node.unique_id, (manifest.nodes[dependency].unique_id)
+                    node.unique_id,
+                    (manifest.nodes[dependency].unique_id)
                 )
             elif dependency in manifest.sources:
                 linker.dependency(
-                    node.unique_id, (manifest.sources[dependency].unique_id)
+                    node.unique_id,
+                    (manifest.sources[dependency].unique_id)
                 )
             else:
                 dependency_not_found(node, dependency)
@@ -461,21 +435,19 @@ class Compiler:
 
     # writes the "compiled_sql" into the target/compiled directory
     def _write_node(self, node: NonSourceCompiledNode) -> ManifestNode:
-        if not node.extra_ctes_injected or node.resource_type == NodeType.Snapshot:
+        if (not node.extra_ctes_injected or
+                node.resource_type == NodeType.Snapshot):
             return node
         logger.debug(f'Writing injected SQL for node "{node.unique_id}"')
 
         if node.compiled_sql:
-            node.build_path = node.write_node(
-                self.config.target_path, "compiled", node.compiled_sql
+            node.compiled_path = node.write_node(
+                self.config.target_path,
+                'compiled',
+                node.compiled_sql
             )
         return node
 
-    # This is the main entry point into this code. It's called by
-    # CompileRunner.compile, GenericRPCRunner.compile, and
-    # RunTask.get_hook_sql. It calls '_compile_node' to convert
-    # the node into a compiled node, and then calls the
-    # recursive method to "prepend" the ctes.
     def compile_node(
         self,
         node: ManifestNode,
@@ -483,9 +455,17 @@ class Compiler:
         extra_context: Optional[Dict[str, Any]] = None,
         write: bool = True,
     ) -> NonSourceCompiledNode:
+        """This is the main entry point into this code. It's called by
+        CompileRunner.compile, GenericRPCRunner.compile, and
+        RunTask.get_hook_sql. It calls '_compile_node' to convert
+        the node into a compiled node, and then calls the
+        recursive method to "prepend" the ctes.
+        """
         node = self._compile_node(node, manifest, extra_context)
 
-        node, _ = self._recursively_prepend_ctes(node, manifest, extra_context)
+        node, _ = self._recursively_prepend_ctes(
+            node, manifest, extra_context
+        )
         if write:
             self._write_node(node)
         return node

core/dbt/config/profile.py

@@ -20,8 +20,10 @@ from dbt.utils import coerce_dict_str
 from .renderer import ProfileRenderer
 
 DEFAULT_THREADS = 1
-DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser("~"), ".dbt")
-PROFILES_DIR = os.path.expanduser(os.getenv("DBT_PROFILES_DIR", DEFAULT_PROFILES_DIR))
+DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser('~'), '.dbt')
+PROFILES_DIR = os.path.expanduser(
+    os.getenv('DBT_PROFILES_DIR', DEFAULT_PROFILES_DIR)
+)
 
 INVALID_PROFILE_MESSAGE = """
 dbt encountered an error while trying to read your profiles.yml file.
@@ -41,13 +43,11 @@ Here, [profile name] should be replaced with a profile name
 defined in your profiles.yml file. You can find profiles.yml here:
 
 {profiles_file}/profiles.yml
-""".format(
-    profiles_file=PROFILES_DIR
-)
+""".format(profiles_file=PROFILES_DIR)
 
 
 def read_profile(profiles_dir: str) -> Dict[str, Any]:
-    path = os.path.join(profiles_dir, "profiles.yml")
+    path = os.path.join(profiles_dir, 'profiles.yml')
 
     contents = None
     if os.path.isfile(path):
@@ -55,8 +55,12 @@ def read_profile(profiles_dir: str) -> Dict[str, Any]:
             contents = load_file_contents(path, strip=False)
             yaml_content = load_yaml_text(contents)
             if not yaml_content:
-                msg = f"The profiles.yml file at {path} is empty"
-                raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
+                msg = f'The profiles.yml file at {path} is empty'
+                raise DbtProfileError(
+                    INVALID_PROFILE_MESSAGE.format(
+                        error_string=msg
+                    )
+                )
             return yaml_content
         except ValidationException as e:
             msg = INVALID_PROFILE_MESSAGE.format(error_string=e)
@@ -69,7 +73,7 @@ def read_user_config(directory: str) -> UserConfig:
     try:
         profile = read_profile(directory)
         if profile:
-            user_cfg = coerce_dict_str(profile.get("config", {}))
+            user_cfg = coerce_dict_str(profile.get('config', {}))
             if user_cfg is not None:
                 UserConfig.validate(user_cfg)
                 return UserConfig.from_dict(user_cfg)
@@ -80,7 +84,8 @@ def read_user_config(directory: str) -> UserConfig:
 
 # The Profile class is included in RuntimeConfig, so any attribute
 # additions must also be set where the RuntimeConfig class is created
-@dataclass
+# `init=False` is a workaround for https://bugs.python.org/issue45081
+@dataclass(init=False)
 class Profile(HasCredentials):
     profile_name: str
     target_name: str
@@ -88,7 +93,26 @@ class Profile(HasCredentials):
     threads: int
     credentials: Credentials
 
-    def to_profile_info(self, serialize_credentials: bool = False) -> Dict[str, Any]:
+    def __init__(
+        self,
+        profile_name: str,
+        target_name: str,
+        config: UserConfig,
+        threads: int,
+        credentials: Credentials
+    ):
+        """Explicitly defining `__init__` to work around bug in Python 3.9.7
+        https://bugs.python.org/issue45081
+        """
+        self.profile_name = profile_name
+        self.target_name = target_name
+        self.config = config
+        self.threads = threads
+        self.credentials = credentials
+
+    def to_profile_info(
+        self, serialize_credentials: bool = False
+    ) -> Dict[str, Any]:
         """Unlike to_project_config, this dict is not a mirror of any existing
         on-disk data structure. It's used when creating a new profile from an
         existing one.
@@ -98,35 +122,34 @@ class Profile(HasCredentials):
         :returns dict: The serialized profile.
         """
         result = {
-            "profile_name": self.profile_name,
-            "target_name": self.target_name,
-            "config": self.config,
-            "threads": self.threads,
-            "credentials": self.credentials,
+            'profile_name': self.profile_name,
+            'target_name': self.target_name,
+            'config': self.config,
+            'threads': self.threads,
+            'credentials': self.credentials,
         }
         if serialize_credentials:
-            result["config"] = self.config.to_dict(omit_none=True)
-            result["credentials"] = self.credentials.to_dict(omit_none=True)
+            result['config'] = self.config.to_dict(omit_none=True)
+            result['credentials'] = self.credentials.to_dict(omit_none=True)
         return result
 
     def to_target_dict(self) -> Dict[str, Any]:
-        target = dict(self.credentials.connection_info(with_aliases=True))
-        target.update(
-            {
-                "type": self.credentials.type,
-                "threads": self.threads,
-                "name": self.target_name,
-                "target_name": self.target_name,
-                "profile_name": self.profile_name,
-                "config": self.config.to_dict(omit_none=True),
-            }
+        target = dict(
+            self.credentials.connection_info(with_aliases=True)
         )
+        target.update({
+            'type': self.credentials.type,
+            'threads': self.threads,
+            'name': self.target_name,
+            'target_name': self.target_name,
+            'profile_name': self.profile_name,
+            'config': self.config.to_dict(omit_none=True),
+        })
         return target
 
     def __eq__(self, other: object) -> bool:
-        if not (
-            isinstance(other, self.__class__) and isinstance(self, other.__class__)
-        ):
+        if not (isinstance(other, self.__class__) and
+                isinstance(self, other.__class__)):
             return NotImplemented
         return self.to_profile_info() == other.to_profile_info()
 
@@ -146,17 +169,14 @@ class Profile(HasCredentials):
     ) -> Credentials:
         # avoid an import cycle
         from dbt.adapters.factory import load_plugin
-
         # credentials carry their 'type' in their actual type, not their
         # attributes. We do want this in order to pick our Credentials class.
-        if "type" not in profile:
+        if 'type' not in profile:
             raise DbtProfileError(
-                'required field "type" not found in profile {} and target {}'.format(
-                    profile_name, target_name
-                )
-            )
+                'required field "type" not found in profile {} and target {}'
+                .format(profile_name, target_name))
 
-        typename = profile.pop("type")
+        typename = profile.pop('type')
         try:
             cls = load_plugin(typename)
             data = cls.translate_aliases(profile)
@@ -165,9 +185,8 @@ class Profile(HasCredentials):
         except (RuntimeException, ValidationError) as e:
             msg = str(e) if isinstance(e, RuntimeException) else e.message
             raise DbtProfileError(
-                'Credentials in profile "{}", target "{}" invalid: {}'.format(
-                    profile_name, target_name, msg
-                )
+                'Credentials in profile "{}", target "{}" invalid: {}'
+                .format(profile_name, target_name, msg)
             ) from e
 
         return credentials
@@ -188,21 +207,19 @@ class Profile(HasCredentials):
     def _get_profile_data(
         profile: Dict[str, Any], profile_name: str, target_name: str
     ) -> Dict[str, Any]:
-        if "outputs" not in profile:
+        if 'outputs' not in profile:
             raise DbtProfileError(
                 "outputs not specified in profile '{}'".format(profile_name)
             )
-        outputs = profile["outputs"]
+        outputs = profile['outputs']
 
         if target_name not in outputs:
-            outputs = "\n".join(" - {}".format(output) for output in outputs)
-            msg = (
-                "The profile '{}' does not have a target named '{}'. The "
-                "valid target names for this profile are:\n{}".format(
-                    profile_name, target_name, outputs
-                )
-            )
-            raise DbtProfileError(msg, result_type="invalid_target")
+            outputs = '\n'.join(' - {}'.format(output)
+                                for output in outputs)
+            msg = ("The profile '{}' does not have a target named '{}'. The "
+                   "valid target names for this profile are:\n{}"
+                   .format(profile_name, target_name, outputs))
+            raise DbtProfileError(msg, result_type='invalid_target')
         profile_data = outputs[target_name]
 
         if not isinstance(profile_data, dict):
@@ -210,7 +227,7 @@ class Profile(HasCredentials):
                 f"output '{target_name}' of profile '{profile_name}' is "
                 f"misconfigured in profiles.yml"
             )
-            raise DbtProfileError(msg, result_type="invalid_target")
+            raise DbtProfileError(msg, result_type='invalid_target')
 
         return profile_data
 
@@ -221,8 +238,8 @@ class Profile(HasCredentials):
         threads: int,
         profile_name: str,
         target_name: str,
-        user_cfg: Optional[Dict[str, Any]] = None,
-    ) -> "Profile":
+        user_cfg: Optional[Dict[str, Any]] = None
+    ) -> 'Profile':
         """Create a profile from an existing set of Credentials and the
         remaining information.
 
@@ -245,7 +262,7 @@ class Profile(HasCredentials):
             target_name=target_name,
             config=config,
             threads=threads,
-            credentials=credentials,
+            credentials=credentials
         )
         profile.validate()
         return profile
@@ -270,18 +287,19 @@ class Profile(HasCredentials):
         # name to extract a profile that we can render.
         if target_override is not None:
             target_name = target_override
-        elif "target" in raw_profile:
+        elif 'target' in raw_profile:
             # render the target if it was parsed from yaml
-            target_name = renderer.render_value(raw_profile["target"])
+            target_name = renderer.render_value(raw_profile['target'])
         else:
-            target_name = "default"
+            target_name = 'default'
             logger.debug(
-                "target not specified in profile '{}', using '{}'".format(
-                    profile_name, target_name
-                )
+                "target not specified in profile '{}', using '{}'"
+                .format(profile_name, target_name)
             )
 
-        raw_profile_data = cls._get_profile_data(raw_profile, profile_name, target_name)
+        raw_profile_data = cls._get_profile_data(
+            raw_profile, profile_name, target_name
+        )
 
         try:
             profile_data = renderer.render_data(raw_profile_data)
@@ -298,7 +316,7 @@ class Profile(HasCredentials):
         user_cfg: Optional[Dict[str, Any]] = None,
         target_override: Optional[str] = None,
         threads_override: Optional[int] = None,
-    ) -> "Profile":
+    ) -> 'Profile':
         """Create a profile from its raw profile information.
 
          (this is an intermediate step, mostly useful for unit testing)
@@ -319,7 +337,7 @@ class Profile(HasCredentials):
         """
         # user_cfg is not rendered.
         if user_cfg is None:
-            user_cfg = raw_profile.get("config")
+            user_cfg = raw_profile.get('config')
         # TODO: should it be, and the values coerced to bool?
         target_name, profile_data = cls.render_profile(
             raw_profile, profile_name, target_override, renderer
@@ -327,7 +345,7 @@ class Profile(HasCredentials):
 
         # valid connections never include the number of threads, but it's
         # stored on a per-connection level in the raw configs
-        threads = profile_data.pop("threads", DEFAULT_THREADS)
+        threads = profile_data.pop('threads', DEFAULT_THREADS)
         if threads_override is not None:
             threads = threads_override
 
@@ -340,7 +358,7 @@ class Profile(HasCredentials):
             profile_name=profile_name,
             target_name=target_name,
             threads=threads,
-            user_cfg=user_cfg,
+            user_cfg=user_cfg
         )
 
     @classmethod
@@ -351,7 +369,7 @@ class Profile(HasCredentials):
         renderer: ProfileRenderer,
         target_override: Optional[str] = None,
         threads_override: Optional[int] = None,
-    ) -> "Profile":
+    ) -> 'Profile':
         """
         :param raw_profiles: The profile data, from disk as yaml.
         :param profile_name: The profile name to use.
@@ -375,9 +393,15 @@ class Profile(HasCredentials):
         # don't render keys, so we can pluck that out
         raw_profile = raw_profiles[profile_name]
         if not raw_profile:
-            msg = f"Profile {profile_name} in profiles.yml is empty"
-            raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
-        user_cfg = raw_profiles.get("config")
+            msg = (
+                f'Profile {profile_name} in profiles.yml is empty'
+            )
+            raise DbtProfileError(
+                INVALID_PROFILE_MESSAGE.format(
+                    error_string=msg
+                )
+            )
+        user_cfg = raw_profiles.get('config')
 
         return cls.from_raw_profile_info(
             raw_profile=raw_profile,
@@ -394,7 +418,7 @@ class Profile(HasCredentials):
         args: Any,
         renderer: ProfileRenderer,
         project_profile_name: Optional[str],
-    ) -> "Profile":
+    ) -> 'Profile':
         """Given the raw profiles as read from disk and the name of the desired
         profile if specified, return the profile component of the runtime
         config.
@@ -409,16 +433,15 @@ class Profile(HasCredentials):
             target could not be found.
         :returns Profile: The new Profile object.
         """
-        threads_override = getattr(args, "threads", None)
-        target_override = getattr(args, "target", None)
+        threads_override = getattr(args, 'threads', None)
+        target_override = getattr(args, 'target', None)
         raw_profiles = read_profile(args.profiles_dir)
-        profile_name = cls.pick_profile_name(
-            getattr(args, "profile", None), project_profile_name
-        )
+        profile_name = cls.pick_profile_name(getattr(args, 'profile', None),
+                                             project_profile_name)
         return cls.from_raw_profiles(
             raw_profiles=raw_profiles,
             profile_name=profile_name,
             renderer=renderer,
             target_override=target_override,
-            threads_override=threads_override,
+            threads_override=threads_override
         )

core/dbt/config/project.py

@@ -2,13 +2,7 @@ from copy import deepcopy
 from dataclasses import dataclass, field
 from itertools import chain
 from typing import (
-    List,
-    Dict,
-    Any,
-    Optional,
-    TypeVar,
-    Union,
-    Mapping,
+    List, Dict, Any, Optional, TypeVar, Union, Mapping,
 )
 from typing_extensions import Protocol, runtime_checkable
 
@@ -88,7 +82,9 @@ def _load_yaml(path):
 
 
 def package_data_from_root(project_root):
-    package_filepath = resolve_path_from_base("packages.yml", project_root)
+    package_filepath = resolve_path_from_base(
+        'packages.yml', project_root
+    )
 
     if path_exists(package_filepath):
         packages_dict = _load_yaml(package_filepath)
@@ -99,7 +95,7 @@ def package_data_from_root(project_root):
 
 def package_config_from_data(packages_data: Dict[str, Any]):
     if not packages_data:
-        packages_data = {"packages": []}
+        packages_data = {'packages': []}
 
     try:
         PackageConfig.validate(packages_data)
@@ -122,7 +118,7 @@ def _parse_versions(versions: Union[List[str], str]) -> List[VersionSpecifier]:
     Regardless, this will return a list of VersionSpecifiers
     """
     if isinstance(versions, str):
-        versions = versions.split(",")
+        versions = versions.split(',')
     return [VersionSpecifier.from_version_string(v) for v in versions]
 
 
@@ -133,12 +129,11 @@ def _all_source_paths(
     analysis_paths: List[str],
     macro_paths: List[str],
 ) -> List[str]:
-    return list(
-        chain(source_paths, data_paths, snapshot_paths, analysis_paths, macro_paths)
-    )
+    return list(chain(source_paths, data_paths, snapshot_paths, analysis_paths,
+                      macro_paths))
 
 
-T = TypeVar("T")
+T = TypeVar('T')
 
 
 def value_or(value: Optional[T], default: T) -> T:
@@ -151,27 +146,30 @@ def value_or(value: Optional[T], default: T) -> T:
 def _raw_project_from(project_root: str) -> Dict[str, Any]:
 
     project_root = os.path.normpath(project_root)
-    project_yaml_filepath = os.path.join(project_root, "dbt_project.yml")
+    project_yaml_filepath = os.path.join(project_root, 'dbt_project.yml')
 
     # get the project.yml contents
     if not path_exists(project_yaml_filepath):
         raise DbtProjectError(
-            "no dbt_project.yml found at expected path {}".format(project_yaml_filepath)
+            'no dbt_project.yml found at expected path {}'
+            .format(project_yaml_filepath)
         )
 
     project_dict = _load_yaml(project_yaml_filepath)
 
     if not isinstance(project_dict, dict):
-        raise DbtProjectError("dbt_project.yml does not parse to a dictionary")
+        raise DbtProjectError(
+            'dbt_project.yml does not parse to a dictionary'
+        )
 
     return project_dict
 
 
 def _query_comment_from_cfg(
-    cfg_query_comment: Union[QueryComment, NoValue, str, None]
+        cfg_query_comment: Union[QueryComment, NoValue, str, None]
 ) -> QueryComment:
     if not cfg_query_comment:
-        return QueryComment(comment="")
+        return QueryComment(comment='')
 
     if isinstance(cfg_query_comment, str):
         return QueryComment(comment=cfg_query_comment)
@@ -188,7 +186,9 @@ def validate_version(dbt_version: List[VersionSpecifier], project_name: str):
     if not versions_compatible(*dbt_version):
         msg = IMPOSSIBLE_VERSION_ERROR.format(
             package=project_name,
-            version_spec=[x.to_version_string() for x in dbt_version],
+            version_spec=[
+                x.to_version_string() for x in dbt_version
+            ]
         )
         raise DbtProjectError(msg)
 
@@ -196,7 +196,9 @@ def validate_version(dbt_version: List[VersionSpecifier], project_name: str):
         msg = INVALID_VERSION_ERROR.format(
             package=project_name,
             installed=installed.to_version_string(),
-            version_spec=[x.to_version_string() for x in dbt_version],
+            version_spec=[
+                x.to_version_string() for x in dbt_version
+            ]
         )
         raise DbtProjectError(msg)
 
@@ -205,8 +207,8 @@ def _get_required_version(
     project_dict: Dict[str, Any],
     verify_version: bool,
 ) -> List[VersionSpecifier]:
-    dbt_raw_version: Union[List[str], str] = ">=0.0.0"
-    required = project_dict.get("require-dbt-version")
+    dbt_raw_version: Union[List[str], str] = '>=0.0.0'
+    required = project_dict.get('require-dbt-version')
     if required is not None:
         dbt_raw_version = required
 
@@ -217,11 +219,11 @@ def _get_required_version(
 
     if verify_version:
         # no name is also an error that we want to raise
-        if "name" not in project_dict:
+        if 'name' not in project_dict:
             raise DbtProjectError(
                 'Required "name" field not present in project',
             )
-        validate_version(dbt_version, project_dict["name"])
+        validate_version(dbt_version, project_dict['name'])
 
     return dbt_version
 
@@ -229,36 +231,34 @@ def _get_required_version(
 @dataclass
 class RenderComponents:
     project_dict: Dict[str, Any] = field(
-        metadata=dict(description="The project dictionary")
+        metadata=dict(description='The project dictionary')
     )
     packages_dict: Dict[str, Any] = field(
-        metadata=dict(description="The packages dictionary")
+        metadata=dict(description='The packages dictionary')
     )
     selectors_dict: Dict[str, Any] = field(
-        metadata=dict(description="The selectors dictionary")
+        metadata=dict(description='The selectors dictionary')
     )
 
 
 @dataclass
 class PartialProject(RenderComponents):
-    profile_name: Optional[str] = field(
-        metadata=dict(description="The unrendered profile name in the project, if set")
-    )
-    project_name: Optional[str] = field(
-        metadata=dict(
-            description=(
-                "The name of the project. This should always be set and will not "
-                "be rendered"
-            )
+    profile_name: Optional[str] = field(metadata=dict(
+        description='The unrendered profile name in the project, if set'
+    ))
+    project_name: Optional[str] = field(metadata=dict(
+        description=(
+            'The name of the project. This should always be set and will not '
+            'be rendered'
         )
-    )
+    ))
     project_root: str = field(
-        metadata=dict(description="The root directory of the project"),
+        metadata=dict(description='The root directory of the project'),
     )
     verify_version: bool = field(
-        metadata=dict(
-            description=("If True, verify the dbt version matches the required version")
-        )
+        metadata=dict(description=(
+            'If True, verify the dbt version matches the required version'
+        ))
     )
 
     def render_profile_name(self, renderer) -> Optional[str]:
@@ -271,7 +271,9 @@ class PartialProject(RenderComponents):
         renderer: DbtProjectYamlRenderer,
     ) -> RenderComponents:
 
-        rendered_project = renderer.render_project(self.project_dict, self.project_root)
+        rendered_project = renderer.render_project(
+            self.project_dict, self.project_root
+        )
         rendered_packages = renderer.render_packages(self.packages_dict)
         rendered_selectors = renderer.render_selectors(self.selectors_dict)
 
@@ -281,16 +283,16 @@ class PartialProject(RenderComponents):
             selectors_dict=rendered_selectors,
         )
 
-    def render(self, renderer: DbtProjectYamlRenderer) -> "Project":
+    def render(self, renderer: DbtProjectYamlRenderer) -> 'Project':
         try:
             rendered = self.get_rendered(renderer)
             return self.create_project(rendered)
         except DbtProjectError as exc:
             if exc.path is None:
-                exc.path = os.path.join(self.project_root, "dbt_project.yml")
+                exc.path = os.path.join(self.project_root, 'dbt_project.yml')
             raise
 
-    def create_project(self, rendered: RenderComponents) -> "Project":
+    def create_project(self, rendered: RenderComponents) -> 'Project':
         unrendered = RenderComponents(
             project_dict=self.project_dict,
             packages_dict=self.packages_dict,
@@ -303,7 +305,9 @@ class PartialProject(RenderComponents):
 
         try:
             ProjectContract.validate(rendered.project_dict)
-            cfg = ProjectContract.from_dict(rendered.project_dict)
+            cfg = ProjectContract.from_dict(
+                rendered.project_dict
+            )
         except ValidationError as e:
             raise DbtProjectError(validator_error_message(e)) from e
         # name/version are required in the Project definition, so we can assume
@@ -313,30 +317,31 @@ class PartialProject(RenderComponents):
         # this is added at project_dict parse time and should always be here
         # once we see it.
         if cfg.project_root is None:
-            raise DbtProjectError("cfg must have a project root!")
+            raise DbtProjectError('cfg must have a project root!')
         else:
             project_root = cfg.project_root
         # this is only optional in the sense that if it's not present, it needs
         # to have been a cli argument.
         profile_name = cfg.profile
         # these are all the defaults
-        source_paths: List[str] = value_or(cfg.source_paths, ["models"])
-        macro_paths: List[str] = value_or(cfg.macro_paths, ["macros"])
-        data_paths: List[str] = value_or(cfg.data_paths, ["data"])
-        test_paths: List[str] = value_or(cfg.test_paths, ["test"])
+        source_paths: List[str] = value_or(cfg.source_paths, ['models'])
+        macro_paths: List[str] = value_or(cfg.macro_paths, ['macros'])
+        data_paths: List[str] = value_or(cfg.data_paths, ['data'])
+        test_paths: List[str] = value_or(cfg.test_paths, ['test'])
         analysis_paths: List[str] = value_or(cfg.analysis_paths, [])
-        snapshot_paths: List[str] = value_or(cfg.snapshot_paths, ["snapshots"])
+        snapshot_paths: List[str] = value_or(cfg.snapshot_paths, ['snapshots'])
 
         all_source_paths: List[str] = _all_source_paths(
-            source_paths, data_paths, snapshot_paths, analysis_paths, macro_paths
+            source_paths, data_paths, snapshot_paths, analysis_paths,
+            macro_paths
         )
 
         docs_paths: List[str] = value_or(cfg.docs_paths, all_source_paths)
         asset_paths: List[str] = value_or(cfg.asset_paths, [])
-        target_path: str = value_or(cfg.target_path, "target")
+        target_path: str = value_or(cfg.target_path, 'target')
         clean_targets: List[str] = value_or(cfg.clean_targets, [target_path])
-        log_path: str = value_or(cfg.log_path, "logs")
-        modules_path: str = value_or(cfg.modules_path, "dbt_modules")
+        log_path: str = value_or(cfg.log_path, 'logs')
+        modules_path: str = value_or(cfg.modules_path, 'dbt_modules')
         # in the default case we'll populate this once we know the adapter type
         # It would be nice to just pass along a Quoting here, but that would
         # break many things
@@ -344,16 +349,20 @@ class PartialProject(RenderComponents):
         if cfg.quoting is not None:
             quoting = cfg.quoting.to_dict(omit_none=True)
 
+        dispatch: List[Dict[str, Any]]
         models: Dict[str, Any]
         seeds: Dict[str, Any]
         snapshots: Dict[str, Any]
         sources: Dict[str, Any]
+        tests: Dict[str, Any]
         vars_value: VarProvider
 
+        dispatch = cfg.dispatch
         models = cfg.models
         seeds = cfg.seeds
         snapshots = cfg.snapshots
         sources = cfg.sources
+        tests = cfg.tests
         if cfg.vars is None:
             vars_dict: Dict[str, Any] = {}
         else:
@@ -368,12 +377,11 @@ class PartialProject(RenderComponents):
         packages = package_config_from_data(rendered.packages_dict)
         selectors = selector_config_from_data(rendered.selectors_dict)
         manifest_selectors: Dict[str, Any] = {}
-        if rendered.selectors_dict and rendered.selectors_dict["selectors"]:
+        if rendered.selectors_dict and rendered.selectors_dict['selectors']:
             # this is a dict with a single key 'selectors' pointing to a list
             # of dicts.
             manifest_selectors = SelectorDict.parse_from_selectors_list(
-                rendered.selectors_dict["selectors"]
-            )
+                rendered.selectors_dict['selectors'])
 
         project = Project(
             project_name=name,
@@ -396,6 +404,7 @@ class PartialProject(RenderComponents):
             models=models,
             on_run_start=on_run_start,
             on_run_end=on_run_end,
+            dispatch=dispatch,
             seeds=seeds,
             snapshots=snapshots,
             dbt_version=dbt_version,
@@ -404,6 +413,7 @@ class PartialProject(RenderComponents):
             selectors=selectors,
             query_comment=query_comment,
             sources=sources,
+            tests=tests,
             vars=vars_value,
             config_version=cfg.config_version,
             unrendered=unrendered,
@@ -422,9 +432,10 @@ class PartialProject(RenderComponents):
         *,
         verify_version: bool = False,
     ):
-        """Construct a partial project from its constituent dicts."""
-        project_name = project_dict.get("name")
-        profile_name = project_dict.get("profile")
+        """Construct a partial project from its constituent dicts.
+        """
+        project_name = project_dict.get('name')
+        profile_name = project_dict.get('profile')
 
         return cls(
             profile_name=profile_name,
@@ -439,14 +450,14 @@ class PartialProject(RenderComponents):
     @classmethod
     def from_project_root(
         cls, project_root: str, *, verify_version: bool = False
-    ) -> "PartialProject":
+    ) -> 'PartialProject':
         project_root = os.path.normpath(project_root)
         project_dict = _raw_project_from(project_root)
-        config_version = project_dict.get("config-version", 1)
+        config_version = project_dict.get('config-version', 1)
         if config_version != 2:
             raise DbtProjectError(
-                f"Invalid config version: {config_version}, expected 2",
-                path=os.path.join(project_root, "dbt_project.yml"),
+                f'Invalid config version: {config_version}, expected 2',
+                path=os.path.join(project_root, 'dbt_project.yml')
             )
 
         packages_dict = package_data_from_root(project_root)
@@ -463,10 +474,15 @@ class PartialProject(RenderComponents):
 class VarProvider:
     """Var providers are tied to a particular Project."""
 
-    def __init__(self, vars: Dict[str, Dict[str, Any]]) -> None:
+    def __init__(
+        self,
+        vars: Dict[str, Dict[str, Any]]
+    ) -> None:
         self.vars = vars
 
-    def vars_for(self, node: IsFQNResource, adapter_type: str) -> Mapping[str, Any]:
+    def vars_for(
+        self, node: IsFQNResource, adapter_type: str
+    ) -> Mapping[str, Any]:
         # in v2, vars are only either project or globally scoped
         merged = MultiDict([self.vars])
         merged.add(self.vars.get(node.package_name, {}))
@@ -500,9 +516,11 @@ class Project:
     models: Dict[str, Any]
     on_run_start: List[str]
     on_run_end: List[str]
+    dispatch: List[Dict[str, Any]]
     seeds: Dict[str, Any]
     snapshots: Dict[str, Any]
     sources: Dict[str, Any]
+    tests: Dict[str, Any]
     vars: VarProvider
     dbt_version: List[VersionSpecifier]
     packages: Dict[str, Any]
@@ -515,11 +533,8 @@ class Project:
     @property
     def all_source_paths(self) -> List[str]:
         return _all_source_paths(
-            self.source_paths,
-            self.data_paths,
-            self.snapshot_paths,
-            self.analysis_paths,
-            self.macro_paths,
+            self.source_paths, self.data_paths, self.snapshot_paths,
+            self.analysis_paths, self.macro_paths
         )
 
     def __str__(self):
@@ -527,13 +542,11 @@ class Project:
         return str(cfg)
 
     def __eq__(self, other):
-        if not (
-            isinstance(other, self.__class__) and isinstance(self, other.__class__)
-        ):
+        if not (isinstance(other, self.__class__) and
+                isinstance(self, other.__class__)):
             return False
-        return self.to_project_config(with_packages=True) == other.to_project_config(
-            with_packages=True
-        )
+        return self.to_project_config(with_packages=True) == \
+            other.to_project_config(with_packages=True)
 
     def to_project_config(self, with_packages=False):
         """Return a dict representation of the config that could be written to
@@ -543,39 +556,40 @@ class Project:
             file in the root.
         :returns dict: The serialized profile.
         """
-        result = deepcopy(
-            {
-                "name": self.project_name,
-                "version": self.version,
-                "project-root": self.project_root,
-                "profile": self.profile_name,
-                "source-paths": self.source_paths,
-                "macro-paths": self.macro_paths,
-                "data-paths": self.data_paths,
-                "test-paths": self.test_paths,
-                "analysis-paths": self.analysis_paths,
-                "docs-paths": self.docs_paths,
-                "asset-paths": self.asset_paths,
-                "target-path": self.target_path,
-                "snapshot-paths": self.snapshot_paths,
-                "clean-targets": self.clean_targets,
-                "log-path": self.log_path,
-                "quoting": self.quoting,
-                "models": self.models,
-                "on-run-start": self.on_run_start,
-                "on-run-end": self.on_run_end,
-                "seeds": self.seeds,
-                "snapshots": self.snapshots,
-                "sources": self.sources,
-                "vars": self.vars.to_dict(),
-                "require-dbt-version": [
-                    v.to_version_string() for v in self.dbt_version
-                ],
-                "config-version": self.config_version,
-            }
-        )
+        result = deepcopy({
+            'name': self.project_name,
+            'version': self.version,
+            'project-root': self.project_root,
+            'profile': self.profile_name,
+            'source-paths': self.source_paths,
+            'macro-paths': self.macro_paths,
+            'data-paths': self.data_paths,
+            'test-paths': self.test_paths,
+            'analysis-paths': self.analysis_paths,
+            'docs-paths': self.docs_paths,
+            'asset-paths': self.asset_paths,
+            'target-path': self.target_path,
+            'snapshot-paths': self.snapshot_paths,
+            'clean-targets': self.clean_targets,
+            'log-path': self.log_path,
+            'quoting': self.quoting,
+            'models': self.models,
+            'on-run-start': self.on_run_start,
+            'on-run-end': self.on_run_end,
+            'dispatch': self.dispatch,
+            'seeds': self.seeds,
+            'snapshots': self.snapshots,
+            'sources': self.sources,
+            'tests': self.tests,
+            'vars': self.vars.to_dict(),
+            'require-dbt-version': [
+                v.to_version_string() for v in self.dbt_version
+            ],
+            'config-version': self.config_version,
+        })
         if self.query_comment:
-            result["query-comment"] = self.query_comment.to_dict(omit_none=True)
+            result['query-comment'] = \
+                self.query_comment.to_dict(omit_none=True)
 
         if with_packages:
             result.update(self.packages.to_dict(omit_none=True))
@@ -606,8 +620,8 @@ class Project:
         selectors_dict: Dict[str, Any],
         renderer: DbtProjectYamlRenderer,
         *,
-        verify_version: bool = False,
-    ) -> "Project":
+        verify_version: bool = False
+    ) -> 'Project':
         partial = PartialProject.from_dicts(
             project_root=project_root,
             project_dict=project_dict,
@@ -624,17 +638,23 @@ class Project:
         renderer: DbtProjectYamlRenderer,
         *,
         verify_version: bool = False,
-    ) -> "Project":
+    ) -> 'Project':
         partial = cls.partial_load(project_root, verify_version=verify_version)
         return partial.render(renderer)
 
     def hashed_name(self):
-        return hashlib.md5(self.project_name.encode("utf-8")).hexdigest()
+        return hashlib.md5(self.project_name.encode('utf-8')).hexdigest()
 
     def get_selector(self, name: str) -> SelectionSpec:
         if name not in self.selectors:
             raise RuntimeException(
-                f"Could not find selector named {name}, expected one of "
-                f"{list(self.selectors)}"
+                f'Could not find selector named {name}, expected one of '
+                f'{list(self.selectors)}'
             )
         return self.selectors[name]
+
+    def get_macro_search_order(self, macro_namespace: str):
+        for dispatch_entry in self.dispatch:
+            if dispatch_entry['macro_namespace'] == macro_namespace:
+                return dispatch_entry['search_order']
+        return None

core/dbt/config/renderer.py

@@ -2,7 +2,9 @@ from typing import Dict, Any, Tuple, Optional, Union, Callable
 
 from dbt.clients.jinja import get_rendered, catch_jinja
 
-from dbt.exceptions import DbtProjectError, CompilationException, RecursionException
+from dbt.exceptions import (
+    DbtProjectError, CompilationException, RecursionException
+)
 from dbt.node_types import NodeType
 from dbt.utils import deep_map
 
@@ -16,7 +18,7 @@ class BaseRenderer:
 
     @property
     def name(self):
-        return "Rendering"
+        return 'Rendering'
 
     def should_render_keypath(self, keypath: Keypath) -> bool:
         return True
@@ -27,7 +29,9 @@ class BaseRenderer:
 
         return self.render_value(value, keypath)
 
-    def render_value(self, value: Any, keypath: Optional[Keypath] = None) -> Any:
+    def render_value(
+        self, value: Any, keypath: Optional[Keypath] = None
+    ) -> Any:
         # keypath is ignored.
         # if it wasn't read as a string, ignore it
         if not isinstance(value, str):
@@ -36,16 +40,18 @@ class BaseRenderer:
             with catch_jinja():
                 return get_rendered(value, self.context, native=True)
         except CompilationException as exc:
-            msg = f"Could not render {value}: {exc.msg}"
+            msg = f'Could not render {value}: {exc.msg}'
             raise CompilationException(msg) from exc
 
-    def render_data(self, data: Dict[str, Any]) -> Dict[str, Any]:
+    def render_data(
+        self, data: Dict[str, Any]
+    ) -> Dict[str, Any]:
         try:
             return deep_map(self.render_entry, data)
         except RecursionException:
             raise DbtProjectError(
-                f"Cycle detected: {self.name} input has a reference to itself",
-                project=data,
+                f'Cycle detected: {self.name} input has a reference to itself',
+                project=data
             )
 
 
@@ -72,15 +78,15 @@ class ProjectPostprocessor(Dict[Keypath, Callable[[Any], Any]]):
     def __init__(self):
         super().__init__()
 
-        self[("on-run-start",)] = _list_if_none_or_string
-        self[("on-run-end",)] = _list_if_none_or_string
+        self[('on-run-start',)] = _list_if_none_or_string
+        self[('on-run-end',)] = _list_if_none_or_string
 
-        for k in ("models", "seeds", "snapshots"):
+        for k in ('models', 'seeds', 'snapshots'):
             self[(k,)] = _dict_if_none
-            self[(k, "vars")] = _dict_if_none
-            self[(k, "pre-hook")] = _list_if_none_or_string
-            self[(k, "post-hook")] = _list_if_none_or_string
-        self[("seeds", "column_types")] = _dict_if_none
+            self[(k, 'vars')] = _dict_if_none
+            self[(k, 'pre-hook')] = _list_if_none_or_string
+            self[(k, 'post-hook')] = _list_if_none_or_string
+        self[('seeds', 'column_types')] = _dict_if_none
 
     def postprocess(self, value: Any, key: Keypath) -> Any:
         if key in self:
@@ -95,7 +101,7 @@ class DbtProjectYamlRenderer(BaseRenderer):
 
     @property
     def name(self):
-        "Project config"
+        'Project config'
 
     def get_package_renderer(self) -> BaseRenderer:
         return PackageRenderer(self.context)
@@ -110,7 +116,7 @@ class DbtProjectYamlRenderer(BaseRenderer):
     ) -> Dict[str, Any]:
         """Render the project and insert the project root after rendering."""
         rendered_project = self.render_data(project)
-        rendered_project["project-root"] = project_root
+        rendered_project['project-root'] = project_root
         return rendered_project
 
     def render_packages(self, packages: Dict[str, Any]):
@@ -132,19 +138,20 @@ class DbtProjectYamlRenderer(BaseRenderer):
 
         first = keypath[0]
         # run hooks are not rendered
-        if first in {"on-run-start", "on-run-end", "query-comment"}:
+        if first in {'on-run-start', 'on-run-end', 'query-comment'}:
             return False
 
         # don't render vars blocks until runtime
-        if first == "vars":
+        if first == 'vars':
             return False
 
-        if first in {"seeds", "models", "snapshots", "seeds"}:
+        if first in {'seeds', 'models', 'snapshots', 'tests'}:
             keypath_parts = {
-                (k.lstrip("+") if isinstance(k, str) else k) for k in keypath
+                (k.lstrip('+ ') if isinstance(k, str) else k)
+                for k in keypath
             }
             # model-level hooks
-            if "pre-hook" in keypath_parts or "post-hook" in keypath_parts:
+            if 'pre-hook' in keypath_parts or 'post-hook' in keypath_parts:
                 return False
 
         return True
@@ -153,15 +160,17 @@ class DbtProjectYamlRenderer(BaseRenderer):
 class ProfileRenderer(BaseRenderer):
     @property
     def name(self):
-        "Profile"
+        'Profile'
 
 
 class SchemaYamlRenderer(BaseRenderer):
-    DOCUMENTABLE_NODES = frozenset(n.pluralize() for n in NodeType.documentable())
+    DOCUMENTABLE_NODES = frozenset(
+        n.pluralize() for n in NodeType.documentable()
+    )
 
     @property
     def name(self):
-        return "Rendering yaml"
+        return 'Rendering yaml'
 
     def _is_norender_key(self, keypath: Keypath) -> bool:
         """
@@ -176,13 +185,13 @@ class SchemaYamlRenderer(BaseRenderer):
 
         Return True if it's tests or description - those aren't rendered
         """
-        if len(keypath) >= 2 and keypath[1] in ("tests", "description"):
+        if len(keypath) >= 2 and keypath[1] in ('tests', 'description'):
             return True
 
         if (
-            len(keypath) >= 4
-            and keypath[1] == "columns"
-            and keypath[3] in ("tests", "description")
+            len(keypath) >= 4 and
+            keypath[1] == 'columns' and
+            keypath[3] in ('tests', 'description')
         ):
             return True
 
@@ -200,13 +209,13 @@ class SchemaYamlRenderer(BaseRenderer):
             return True
 
         if keypath[0] == NodeType.Source.pluralize():
-            if keypath[2] == "description":
+            if keypath[2] == 'description':
                 return False
-            if keypath[2] == "tables":
+            if keypath[2] == 'tables':
                 if self._is_norender_key(keypath[3:]):
                     return False
         elif keypath[0] == NodeType.Macro.pluralize():
-            if keypath[2] == "arguments":
+            if keypath[2] == 'arguments':
                 if self._is_norender_key(keypath[3:]):
                     return False
             elif self._is_norender_key(keypath[1:]):
@@ -220,10 +229,10 @@ class SchemaYamlRenderer(BaseRenderer):
 class PackageRenderer(BaseRenderer):
     @property
     def name(self):
-        return "Packages config"
+        return 'Packages config'
 
 
 class SelectorRenderer(BaseRenderer):
     @property
     def name(self):
-        return "Selector config"
+        return 'Selector config'

core/dbt/config/runtime.py

@@ -4,16 +4,8 @@ from copy import deepcopy
 from dataclasses import dataclass, fields
 from pathlib import Path
 from typing import (
-    Dict,
-    Any,
-    Optional,
-    Mapping,
-    Iterator,
-    Iterable,
-    Tuple,
-    List,
-    MutableSet,
-    Type,
+    Dict, Any, Optional, Mapping, Iterator, Iterable, Tuple, List, MutableSet,
+    Type
 )
 
 from .profile import Profile
@@ -23,7 +15,7 @@ from .utils import parse_cli_vars
 from dbt import tracking
 from dbt.adapters.factory import get_relation_class_by_name, get_include_paths
 from dbt.helper_types import FQNPath, PathSet
-from dbt.context import generate_base_context
+from dbt.context.base import generate_base_context
 from dbt.context.target import generate_target_context
 from dbt.contracts.connection import AdapterRequiredConfig, Credentials
 from dbt.contracts.graph.manifest import ManifestMetadata
@@ -38,13 +30,15 @@ from dbt.exceptions import (
     DbtProjectError,
     validator_error_message,
     warn_or_error,
-    raise_compiler_error,
+    raise_compiler_error
 )
 
 from dbt.dataclass_schema import ValidationError
 
 
-def _project_quoting_dict(proj: Project, profile: Profile) -> Dict[ComponentName, bool]:
+def _project_quoting_dict(
+    proj: Project, profile: Profile
+) -> Dict[ComponentName, bool]:
     src: Dict[str, Any] = profile.credentials.translate_aliases(proj.quoting)
     result: Dict[ComponentName, bool] = {}
     for key in ComponentName:
@@ -60,7 +54,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
     args: Any
     profile_name: str
     cli_vars: Dict[str, Any]
-    dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None
+    dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None
 
     def __post_init__(self):
         self.validate()
@@ -71,8 +65,8 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         project: Project,
         profile: Profile,
         args: Any,
-        dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None,
-    ) -> "RuntimeConfig":
+        dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None,
+    ) -> 'RuntimeConfig':
         """Instantiate a RuntimeConfig from its components.
 
         :param profile: A parsed dbt Profile.
@@ -86,7 +80,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             .replace_dict(_project_quoting_dict(project, profile))
         ).to_dict(omit_none=True)
 
-        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
 
         return cls(
             project_name=project.project_name,
@@ -108,6 +102,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             models=project.models,
             on_run_start=project.on_run_start,
             on_run_end=project.on_run_end,
+            dispatch=project.dispatch,
             seeds=project.seeds,
             snapshots=project.snapshots,
             dbt_version=project.dbt_version,
@@ -116,6 +111,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             selectors=project.selectors,
             query_comment=project.query_comment,
             sources=project.sources,
+            tests=project.tests,
             vars=project.vars,
             config_version=project.config_version,
             unrendered=project.unrendered,
@@ -129,7 +125,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             dependencies=dependencies,
         )
 
-    def new_project(self, project_root: str) -> "RuntimeConfig":
+    def new_project(self, project_root: str) -> 'RuntimeConfig':
         """Given a new project root, read in its project dictionary, supply the
         existing project's profile info, and create a new project file.
 
@@ -148,7 +144,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         project = Project.from_project_root(
             project_root,
             renderer,
-            verify_version=getattr(self.args, "version_check", False),
+            verify_version=getattr(self.args, 'version_check', False),
         )
 
         cfg = self.from_parts(
@@ -171,7 +167,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         """
         result = self.to_project_config(with_packages=True)
         result.update(self.to_profile_info(serialize_credentials=True))
-        result["cli_vars"] = deepcopy(self.cli_vars)
+        result['cli_vars'] = deepcopy(self.cli_vars)
         return result
 
     def validate(self):
@@ -191,21 +187,30 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         profile_renderer: ProfileRenderer,
         profile_name: Optional[str],
     ) -> Profile:
-        return Profile.render_from_args(args, profile_renderer, profile_name)
+        return Profile.render_from_args(
+            args, profile_renderer, profile_name
+        )
 
     @classmethod
-    def collect_parts(cls: Type["RuntimeConfig"], args: Any) -> Tuple[Project, Profile]:
+    def collect_parts(
+        cls: Type['RuntimeConfig'], args: Any
+    ) -> Tuple[Project, Profile]:
         # profile_name from the project
         project_root = args.project_dir if args.project_dir else os.getcwd()
-        version_check = getattr(args, "version_check", False)
-        partial = Project.partial_load(project_root, verify_version=version_check)
+        version_check = getattr(args, 'version_check', False)
+        partial = Project.partial_load(
+            project_root,
+            verify_version=version_check
+        )
 
         # build the profile using the base renderer and the one fact we know
-        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
         profile_renderer = ProfileRenderer(generate_base_context(cli_vars))
         profile_name = partial.render_profile_name(profile_renderer)
 
-        profile = cls._get_rendered_profile(args, profile_renderer, profile_name)
+        profile = cls._get_rendered_profile(
+            args, profile_renderer, profile_name
+        )
 
         # get a new renderer using our target information and render the
         # project
@@ -215,7 +220,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         return (project, profile)
 
     @classmethod
-    def from_args(cls, args: Any) -> "RuntimeConfig":
+    def from_args(cls, args: Any) -> 'RuntimeConfig':
         """Given arguments, read in dbt_project.yml from the current directory,
         read in packages.yml if it exists, and use them to find the profile to
         load.
@@ -235,7 +240,8 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
     def get_metadata(self) -> ManifestMetadata:
         return ManifestMetadata(
-            project_id=self.hashed_name(), adapter_type=self.credentials.type
+            project_id=self.hashed_name(),
+            adapter_type=self.credentials.type
         )
 
     def _get_v2_config_paths(
@@ -245,7 +251,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         paths: MutableSet[FQNPath],
     ) -> PathSet:
         for key, value in config.items():
-            if isinstance(value, dict) and not key.startswith("+"):
+            if isinstance(value, dict) and not key.startswith('+'):
                 self._get_v2_config_paths(value, path + (key,), paths)
             else:
                 paths.add(path)
@@ -261,22 +267,23 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             paths = set()
 
         for key, value in config.items():
-            if isinstance(value, dict) and not key.startswith("+"):
+            if isinstance(value, dict) and not key.startswith('+'):
                 self._get_v2_config_paths(value, path + (key,), paths)
             else:
                 paths.add(path)
         return frozenset(paths)
 
     def get_resource_config_paths(self) -> Dict[str, PathSet]:
-        """Return a dictionary with 'seeds' and 'models' keys whose values are
+        """Return a dictionary with resource type keys whose values are
         lists of lists of strings, where each inner list of strings represents
         a configured path in the resource.
         """
         return {
-            "models": self._get_config_paths(self.models),
-            "seeds": self._get_config_paths(self.seeds),
-            "snapshots": self._get_config_paths(self.snapshots),
-            "sources": self._get_config_paths(self.sources),
+            'models': self._get_config_paths(self.models),
+            'seeds': self._get_config_paths(self.seeds),
+            'snapshots': self._get_config_paths(self.snapshots),
+            'sources': self._get_config_paths(self.sources),
+            'tests': self._get_config_paths(self.tests),
         }
 
     def get_unused_resource_config_paths(
@@ -297,7 +304,9 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
             for config_path in config_paths:
                 if not _is_config_used(config_path, fqns):
-                    unused_resource_config_paths.append((resource_type,) + config_path)
+                    unused_resource_config_paths.append(
+                        (resource_type,) + config_path
+                    )
         return unused_resource_config_paths
 
     def warn_for_unused_resource_config_paths(
@@ -310,25 +319,38 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             return
 
         msg = UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE.format(
-            len(unused), "\n".join("- {}".format(".".join(u)) for u in unused)
+            len(unused),
+            '\n'.join('- {}'.format('.'.join(u)) for u in unused)
         )
 
-        warn_or_error(msg, log_fmt=warning_tag("{}"))
+        warn_or_error(msg, log_fmt=warning_tag('{}'))
 
-    def load_dependencies(self) -> Mapping[str, "RuntimeConfig"]:
+    def load_dependencies(self) -> Mapping[str, 'RuntimeConfig']:
         if self.dependencies is None:
             all_projects = {self.project_name: self}
             internal_packages = get_include_paths(self.credentials.type)
+            # raise exception if fewer installed packages than in packages.yml
+            count_packages_specified = len(self.packages.packages)  # type: ignore
+            count_packages_installed = len(tuple(self._get_project_directories()))
+            if count_packages_specified > count_packages_installed:
+                raise_compiler_error(
+                    f'dbt found {count_packages_specified} package(s) '
+                    f'specified in packages.yml, but only '
+                    f'{count_packages_installed} package(s) installed '
+                    f'in {self.modules_path}. Run "dbt deps" to '
+                    f'install package dependencies.'
+                )
             project_paths = itertools.chain(
-                internal_packages, self._get_project_directories()
+                internal_packages,
+                self._get_project_directories()
             )
             for project_name, project in self.load_projects(project_paths):
                 if project_name in all_projects:
                     raise_compiler_error(
-                        f"dbt found more than one package with the name "
+                        f'dbt found more than one package with the name '
                         f'"{project_name}" included in this project. Package '
-                        f"names must be unique in a project. Please rename "
-                        f"one of these packages."
+                        f'names must be unique in a project. Please rename '
+                        f'one of these packages.'
                     )
                 all_projects[project_name] = project
             self.dependencies = all_projects
@@ -339,14 +361,14 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
     def load_projects(
         self, paths: Iterable[Path]
-    ) -> Iterator[Tuple[str, "RuntimeConfig"]]:
+    ) -> Iterator[Tuple[str, 'RuntimeConfig']]:
         for path in paths:
             try:
                 project = self.new_project(str(path))
             except DbtProjectError as e:
                 raise DbtProjectError(
-                    f"Failed to read package: {e}",
-                    result_type="invalid_project",
+                    f'Failed to read package: {e}',
+                    result_type='invalid_project',
                     path=path,
                 ) from e
             else:
@@ -357,18 +379,22 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
         if root.exists():
             for path in root.iterdir():
-                if path.is_dir() and not path.name.startswith("__"):
+                if path.is_dir() and not path.name.startswith('__'):
                     yield path
 
 
 class UnsetCredentials(Credentials):
     def __init__(self):
-        super().__init__("", "")
+        super().__init__('', '')
 
     @property
     def type(self):
         return None
 
+    @property
+    def unique_field(self):
+        return None
+
     def connection_info(self, *args, **kwargs):
         return {}
 
@@ -379,7 +405,9 @@ class UnsetCredentials(Credentials):
 class UnsetConfig(UserConfig):
     def __getattribute__(self, name):
         if name in {f.name for f in fields(UserConfig)}:
-            raise AttributeError(f"'UnsetConfig' object has no attribute {name}")
+            raise AttributeError(
+                f"'UnsetConfig' object has no attribute {name}"
+            )
 
     def __post_serialize__(self, dct):
         return {}
@@ -389,15 +417,15 @@ class UnsetProfile(Profile):
     def __init__(self):
         self.credentials = UnsetCredentials()
         self.config = UnsetConfig()
-        self.profile_name = ""
-        self.target_name = ""
+        self.profile_name = ''
+        self.target_name = ''
         self.threads = -1
 
     def to_target_dict(self):
         return {}
 
     def __getattribute__(self, name):
-        if name in {"profile_name", "target_name", "threads"}:
+        if name in {'profile_name', 'target_name', 'threads'}:
             raise RuntimeException(
                 f'Error: disallowed attribute "{name}" - no profile!'
             )
@@ -421,7 +449,7 @@ class UnsetProfileConfig(RuntimeConfig):
 
     def __getattribute__(self, name):
         # Override __getattribute__ to check that the attribute isn't 'banned'.
-        if name in {"profile_name", "target_name"}:
+        if name in {'profile_name', 'target_name'}:
             raise RuntimeException(
                 f'Error: disallowed attribute "{name}" - no profile!'
             )
@@ -439,8 +467,8 @@ class UnsetProfileConfig(RuntimeConfig):
         project: Project,
         profile: Profile,
         args: Any,
-        dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None,
-    ) -> "RuntimeConfig":
+        dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None,
+    ) -> 'RuntimeConfig':
         """Instantiate a RuntimeConfig from its components.
 
         :param profile: Ignored.
@@ -448,7 +476,7 @@ class UnsetProfileConfig(RuntimeConfig):
         :param args: The parsed command-line arguments.
         :returns RuntimeConfig: The new configuration.
         """
-        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
 
         return cls(
             project_name=project.project_name,
@@ -470,6 +498,7 @@ class UnsetProfileConfig(RuntimeConfig):
             models=project.models,
             on_run_start=project.on_run_start,
             on_run_end=project.on_run_end,
+            dispatch=project.dispatch,
             seeds=project.seeds,
             snapshots=project.snapshots,
             dbt_version=project.dbt_version,
@@ -478,13 +507,14 @@ class UnsetProfileConfig(RuntimeConfig):
             selectors=project.selectors,
             query_comment=project.query_comment,
             sources=project.sources,
+            tests=project.tests,
             vars=project.vars,
             config_version=project.config_version,
             unrendered=project.unrendered,
-            profile_name="",
-            target_name="",
+            profile_name='',
+            target_name='',
             config=UnsetConfig(),
-            threads=getattr(args, "threads", 1),
+            threads=getattr(args, 'threads', 1),
             credentials=UnsetCredentials(),
             args=args,
             cli_vars=cli_vars,
@@ -499,11 +529,16 @@ class UnsetProfileConfig(RuntimeConfig):
         profile_name: Optional[str],
     ) -> Profile:
         try:
-            profile = Profile.render_from_args(args, profile_renderer, profile_name)
+            profile = Profile.render_from_args(
+                args, profile_renderer, profile_name
+            )
         except (DbtProjectError, DbtProfileError) as exc:
-            logger.debug("Profile not loaded due to error: {}", exc, exc_info=True)
+            logger.debug(
+                'Profile not loaded due to error: {}', exc, exc_info=True
+            )
             logger.info(
-                'No profile "{}" found, continuing with no target', profile_name
+                'No profile "{}" found, continuing with no target',
+                profile_name
             )
             # return the poisoned form
             profile = UnsetProfile()
@@ -512,7 +547,7 @@ class UnsetProfileConfig(RuntimeConfig):
         return profile
 
     @classmethod
-    def from_args(cls: Type[RuntimeConfig], args: Any) -> "RuntimeConfig":
+    def from_args(cls: Type[RuntimeConfig], args: Any) -> 'RuntimeConfig':
         """Given arguments, read in dbt_project.yml from the current directory,
         read in packages.yml if it exists, and use them to find the profile to
         load.
@@ -527,7 +562,11 @@ class UnsetProfileConfig(RuntimeConfig):
             # if it's a real profile, return a real config
             cls = RuntimeConfig
 
-        return cls.from_parts(project=project, profile=profile, args=args)
+        return cls.from_parts(
+            project=project,
+            profile=profile,
+            args=args
+        )
 
 
 UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE = """\
@@ -541,6 +580,6 @@ There are {} unused configuration paths:
 def _is_config_used(path, fqns):
     if fqns:
         for fqn in fqns:
-            if len(path) <= len(fqn) and fqn[: len(path)] == path:
+            if len(path) <= len(fqn) and fqn[:len(path)] == path:
                 return True
     return False

core/dbt/config/selectors.py

@@ -1,6 +1,8 @@
 from pathlib import Path
 from typing import Dict, Any
-from dbt.clients.yaml_helper import yaml, Loader, Dumper, load_yaml_text  # noqa: F401
+from dbt.clients.yaml_helper import (  # noqa: F401
+    yaml, Loader, Dumper, load_yaml_text
+)
 from dbt.dataclass_schema import ValidationError
 
 from .renderer import SelectorRenderer
@@ -28,8 +30,9 @@ Validator Error:
 
 
 class SelectorConfig(Dict[str, SelectionSpec]):
+
     @classmethod
-    def selectors_from_dict(cls, data: Dict[str, Any]) -> "SelectorConfig":
+    def selectors_from_dict(cls, data: Dict[str, Any]) -> 'SelectorConfig':
         try:
             SelectorFile.validate(data)
             selector_file = SelectorFile.from_dict(data)
@@ -42,12 +45,12 @@ class SelectorConfig(Dict[str, SelectionSpec]):
                 f"union, intersection, string, dictionary. No lists. "
                 f"\nhttps://docs.getdbt.com/reference/node-selection/"
                 f"yaml-selectors",
-                result_type="invalid_selector",
+                result_type='invalid_selector'
             ) from exc
         except RuntimeException as exc:
             raise DbtSelectorsError(
-                f"Could not read selector file data: {exc}",
-                result_type="invalid_selector",
+                f'Could not read selector file data: {exc}',
+                result_type='invalid_selector',
             ) from exc
 
         return cls(selectors)
@@ -57,28 +60,26 @@ class SelectorConfig(Dict[str, SelectionSpec]):
         cls,
         data: Dict[str, Any],
         renderer: SelectorRenderer,
-    ) -> "SelectorConfig":
+    ) -> 'SelectorConfig':
         try:
             rendered = renderer.render_data(data)
         except (ValidationError, RuntimeException) as exc:
             raise DbtSelectorsError(
-                f"Could not render selector data: {exc}",
-                result_type="invalid_selector",
+                f'Could not render selector data: {exc}',
+                result_type='invalid_selector',
             ) from exc
         return cls.selectors_from_dict(rendered)
 
     @classmethod
     def from_path(
-        cls,
-        path: Path,
-        renderer: SelectorRenderer,
-    ) -> "SelectorConfig":
+        cls, path: Path, renderer: SelectorRenderer,
+    ) -> 'SelectorConfig':
         try:
             data = load_yaml_text(load_file_contents(str(path)))
         except (ValidationError, RuntimeException) as exc:
             raise DbtSelectorsError(
-                f"Could not read selector file: {exc}",
-                result_type="invalid_selector",
+                f'Could not read selector file: {exc}',
+                result_type='invalid_selector',
                 path=path,
             ) from exc
 
@@ -90,7 +91,9 @@ class SelectorConfig(Dict[str, SelectionSpec]):
 
 
 def selector_data_from_root(project_root: str) -> Dict[str, Any]:
-    selector_filepath = resolve_path_from_base("selectors.yml", project_root)
+    selector_filepath = resolve_path_from_base(
+        'selectors.yml', project_root
+    )
 
     if path_exists(selector_filepath):
         selectors_dict = load_yaml_text(load_file_contents(selector_filepath))
@@ -99,16 +102,18 @@ def selector_data_from_root(project_root: str) -> Dict[str, Any]:
     return selectors_dict
 
 
-def selector_config_from_data(selectors_data: Dict[str, Any]) -> SelectorConfig:
+def selector_config_from_data(
+    selectors_data: Dict[str, Any]
+) -> SelectorConfig:
     if not selectors_data:
-        selectors_data = {"selectors": []}
+        selectors_data = {'selectors': []}
 
     try:
         selectors = SelectorConfig.selectors_from_dict(selectors_data)
     except ValidationError as e:
         raise DbtSelectorsError(
             MALFORMED_SELECTOR_ERROR.format(error=str(e.message)),
-            result_type="invalid_selector",
+            result_type='invalid_selector',
         ) from e
     return selectors
 
@@ -120,6 +125,7 @@ def selector_config_from_data(selectors_data: Dict[str, Any]) -> SelectorConfig:
 # be necessary to make changes here. Ideally it would be
 # good to combine the two flows into one at some point.
 class SelectorDict:
+
     @classmethod
     def parse_dict_definition(cls, definition):
         key = list(definition)[0]
@@ -130,10 +136,10 @@ class SelectorDict:
                 new_value = cls.parse_from_definition(sel_def)
                 new_values.append(new_value)
             value = new_values
-        if key == "exclude":
+        if key == 'exclude':
             definition = {key: value}
         elif len(definition) == 1:
-            definition = {"method": key, "value": value}
+            definition = {'method': key, 'value': value}
         return definition
 
     @classmethod
@@ -155,10 +161,10 @@ class SelectorDict:
     def parse_from_definition(cls, definition):
         if isinstance(definition, str):
             definition = SelectionCriteria.dict_from_single_spec(definition)
-        elif "union" in definition:
-            definition = cls.parse_a_definition("union", definition)
-        elif "intersection" in definition:
-            definition = cls.parse_a_definition("intersection", definition)
+        elif 'union' in definition:
+            definition = cls.parse_a_definition('union', definition)
+        elif 'intersection' in definition:
+            definition = cls.parse_a_definition('intersection', definition)
         elif isinstance(definition, dict):
             definition = cls.parse_dict_definition(definition)
         return definition
@@ -169,8 +175,8 @@ class SelectorDict:
     def parse_from_selectors_list(cls, selectors):
         selector_dict = {}
         for selector in selectors:
-            sel_name = selector["name"]
+            sel_name = selector['name']
             selector_dict[sel_name] = selector
-            definition = cls.parse_from_definition(selector["definition"])
-            selector_dict[sel_name]["definition"] = definition
+            definition = cls.parse_from_definition(selector['definition'])
+            selector_dict[sel_name]['definition'] = definition
         return selector_dict

core/dbt/config/utils.py

@@ -15,8 +15,9 @@ def parse_cli_vars(var_string: str) -> Dict[str, Any]:
             type_name = var_type.__name__
             raise_compiler_error(
                 "The --vars argument must be a YAML dictionary, but was "
-                "of type '{}'".format(type_name)
-            )
+                "of type '{}'".format(type_name))
     except ValidationException:
-        logger.error("The YAML provided in the --vars argument is not valid.\n")
+        logger.error(
+            "The YAML provided in the --vars argument is not valid.\n"
+        )
         raise

core/dbt/context/base.py

@@ -1,16 +1,14 @@
 import json
 import os
-from typing import Any, Dict, NoReturn, Optional, Mapping
+from typing import (
+    Any, Dict, NoReturn, Optional, Mapping
+)
 
 from dbt import flags
 from dbt import tracking
 from dbt.clients.jinja import undefined_error, get_rendered
 from dbt.clients.yaml_helper import (  # noqa: F401
-    yaml,
-    safe_load,
-    SafeLoader,
-    Loader,
-    Dumper,
+    yaml, safe_load, SafeLoader, Loader, Dumper
 )
 from dbt.contracts.graph.compiled import CompiledResource
 from dbt.exceptions import raise_compiler_error, MacroReturn
@@ -27,26 +25,38 @@ import re
 def get_pytz_module_context() -> Dict[str, Any]:
     context_exports = pytz.__all__  # type: ignore
 
-    return {name: getattr(pytz, name) for name in context_exports}
+    return {
+        name: getattr(pytz, name) for name in context_exports
+    }
 
 
 def get_datetime_module_context() -> Dict[str, Any]:
-    context_exports = ["date", "datetime", "time", "timedelta", "tzinfo"]
+    context_exports = [
+        'date',
+        'datetime',
+        'time',
+        'timedelta',
+        'tzinfo'
+    ]
 
-    return {name: getattr(datetime, name) for name in context_exports}
+    return {
+        name: getattr(datetime, name) for name in context_exports
+    }
 
 
 def get_re_module_context() -> Dict[str, Any]:
     context_exports = re.__all__
 
-    return {name: getattr(re, name) for name in context_exports}
+    return {
+        name: getattr(re, name) for name in context_exports
+    }
 
 
 def get_context_modules() -> Dict[str, Dict[str, Any]]:
     return {
-        "pytz": get_pytz_module_context(),
-        "datetime": get_datetime_module_context(),
-        "re": get_re_module_context(),
+        'pytz': get_pytz_module_context(),
+        'datetime': get_datetime_module_context(),
+        're': get_re_module_context(),
     }
 
 
@@ -80,8 +90,8 @@ class ContextMeta(type):
         new_dct = {}
 
         for base in bases:
-            context_members.update(getattr(base, "_context_members_", {}))
-            context_attrs.update(getattr(base, "_context_attrs_", {}))
+            context_members.update(getattr(base, '_context_members_', {}))
+            context_attrs.update(getattr(base, '_context_attrs_', {}))
 
         for key, value in dct.items():
             if isinstance(value, ContextMember):
@@ -90,22 +100,21 @@ class ContextMeta(type):
                 context_attrs[context_key] = key
                 value = value.inner
             new_dct[key] = value
-        new_dct["_context_members_"] = context_members
-        new_dct["_context_attrs_"] = context_attrs
+        new_dct['_context_members_'] = context_members
+        new_dct['_context_attrs_'] = context_attrs
         return type.__new__(mcls, name, bases, new_dct)
 
 
 class Var:
-    UndefinedVarError = (
-        "Required var '{}' not found in config:\nVars " "supplied to {} = {}"
-    )
+    UndefinedVarError = "Required var '{}' not found in config:\nVars "\
+                        "supplied to {} = {}"
     _VAR_NOTSET = object()
 
     def __init__(
         self,
         context: Mapping[str, Any],
         cli_vars: Mapping[str, Any],
-        node: Optional[CompiledResource] = None,
+        node: Optional[CompiledResource] = None
     ) -> None:
         self._context: Mapping[str, Any] = context
         self._cli_vars: Mapping[str, Any] = cli_vars
@@ -120,12 +129,14 @@ class Var:
         if self._node is not None:
             return self._node.name
         else:
-            return "<Configuration>"
+            return '<Configuration>'
 
     def get_missing_var(self, var_name):
         dct = {k: self._merged[k] for k in self._merged}
         pretty_vars = json.dumps(dct, sort_keys=True, indent=4)
-        msg = self.UndefinedVarError.format(var_name, self.node_name, pretty_vars)
+        msg = self.UndefinedVarError.format(
+            var_name, self.node_name, pretty_vars
+        )
         raise_compiler_error(msg, self._node)
 
     def has_var(self, var_name: str):
@@ -156,7 +167,7 @@ class BaseContext(metaclass=ContextMeta):
     def generate_builtins(self):
         builtins: Dict[str, Any] = {}
         for key, value in self._context_members_.items():
-            if hasattr(value, "__get__"):
+            if hasattr(value, '__get__'):
                 # handle properties, bound methods, etc
                 value = value.__get__(self)
             builtins[key] = value
@@ -164,9 +175,9 @@ class BaseContext(metaclass=ContextMeta):
 
     # no dbtClassMixin so this is not an actual override
     def to_dict(self):
-        self._ctx["context"] = self._ctx
+        self._ctx['context'] = self._ctx
         builtins = self.generate_builtins()
-        self._ctx["builtins"] = builtins
+        self._ctx['builtins'] = builtins
         self._ctx.update(builtins)
         return self._ctx
 
@@ -275,20 +286,18 @@ class BaseContext(metaclass=ContextMeta):
             msg = f"Env var required but not provided: '{var}'"
             undefined_error(msg)
 
-    if os.environ.get("DBT_MACRO_DEBUGGING"):
-
+    if os.environ.get('DBT_MACRO_DEBUGGING'):
         @contextmember
         @staticmethod
         def debug():
             """Enter a debugger at this line in the compiled jinja code."""
             import sys
             import ipdb  # type: ignore
-
             frame = sys._getframe(3)
             ipdb.set_trace(frame)
-            return ""
+            return ''
 
-    @contextmember("return")
+    @contextmember('return')
     @staticmethod
     def _return(data: Any) -> NoReturn:
         """The `return` function can be used in macros to return data to the
@@ -339,7 +348,9 @@ class BaseContext(metaclass=ContextMeta):
 
     @contextmember
     @staticmethod
-    def tojson(value: Any, default: Any = None, sort_keys: bool = False) -> Any:
+    def tojson(
+        value: Any, default: Any = None, sort_keys: bool = False
+    ) -> Any:
         """The `tojson` context method can be used to serialize a Python
         object primitive, eg. a `dict` or `list` to a json string.
 
@@ -435,7 +446,7 @@ class BaseContext(metaclass=ContextMeta):
             logger.info(msg)
         else:
             logger.debug(msg)
-        return ""
+        return ''
 
     @contextproperty
     def run_started_at(self) -> Optional[datetime.datetime]:

core/dbt/context/configured.py

@@ -4,14 +4,16 @@ from dbt.contracts.connection import AdapterRequiredConfig
 from dbt.node_types import NodeType
 from dbt.utils import MultiDict
 
-from dbt.context import contextproperty, Var
+from dbt.context.base import contextproperty, Var
 from dbt.context.target import TargetContext
 
 
 class ConfiguredContext(TargetContext):
     config: AdapterRequiredConfig
 
-    def __init__(self, config: AdapterRequiredConfig) -> None:
+    def __init__(
+        self, config: AdapterRequiredConfig
+    ) -> None:
         super().__init__(config, config.cli_vars)
 
     @contextproperty
@@ -68,7 +70,20 @@ class SchemaYamlContext(ConfiguredContext):
 
     @contextproperty
     def var(self) -> ConfiguredVar:
-        return ConfiguredVar(self._ctx, self.config, self._project_name)
+        return ConfiguredVar(
+            self._ctx, self.config, self._project_name
+        )
+
+
+class MacroResolvingContext(ConfiguredContext):
+    def __init__(self, config):
+        super().__init__(config)
+
+    @contextproperty
+    def var(self) -> ConfiguredVar:
+        return ConfiguredVar(
+            self._ctx, self.config, self.config.project_name
+        )
 
 
 def generate_schema_yml(
@@ -76,3 +91,10 @@ def generate_schema_yml(
 ) -> Dict[str, Any]:
     ctx = SchemaYamlContext(config, project_name)
     return ctx.to_dict()
+
+
+def generate_macro_context(
+    config: AdapterRequiredConfig,
+) -> Dict[str, Any]:
+    ctx = MacroResolvingContext(config)
+    return ctx.to_dict()

core/dbt/context/context_config.py

@@ -17,8 +17,8 @@ class ModelParts(IsFQNResource):
     package_name: str
 
 
-T = TypeVar("T")  # any old type
-C = TypeVar("C", bound=BaseConfig)
+T = TypeVar('T')  # any old type
+C = TypeVar('C', bound=BaseConfig)
 
 
 class ConfigSource:
@@ -36,13 +36,15 @@ class UnrenderedConfig(ConfigSource):
     def get_config_dict(self, resource_type: NodeType) -> Dict[str, Any]:
         unrendered = self.project.unrendered.project_dict
         if resource_type == NodeType.Seed:
-            model_configs = unrendered.get("seeds")
+            model_configs = unrendered.get('seeds')
         elif resource_type == NodeType.Snapshot:
-            model_configs = unrendered.get("snapshots")
+            model_configs = unrendered.get('snapshots')
         elif resource_type == NodeType.Source:
-            model_configs = unrendered.get("sources")
+            model_configs = unrendered.get('sources')
+        elif resource_type == NodeType.Test:
+            model_configs = unrendered.get('tests')
         else:
-            model_configs = unrendered.get("models")
+            model_configs = unrendered.get('models')
 
         if model_configs is None:
             return {}
@@ -61,6 +63,8 @@ class RenderedConfig(ConfigSource):
             model_configs = self.project.snapshots
         elif resource_type == NodeType.Source:
             model_configs = self.project.sources
+        elif resource_type == NodeType.Test:
+            model_configs = self.project.tests
         else:
             model_configs = self.project.models
         return model_configs
@@ -79,8 +83,8 @@ class BaseContextConfigGenerator(Generic[T]):
         dependencies = self._active_project.load_dependencies()
         if project_name not in dependencies:
             raise InternalException(
-                f"Project name {project_name} not found in dependencies "
-                f"(found {list(dependencies)})"
+                f'Project name {project_name} not found in dependencies '
+                f'(found {list(dependencies)})'
             )
         return dependencies[project_name]
 
@@ -92,8 +96,8 @@ class BaseContextConfigGenerator(Generic[T]):
         for level_config in fqn_search(model_configs, fqn):
             result = {}
             for key, value in level_config.items():
-                if key.startswith("+"):
-                    result[key[1:]] = deepcopy(value)
+                if key.startswith('+'):
+                    result[key[1:].strip()] = deepcopy(value)
                 elif not isinstance(value, dict):
                     result[key] = deepcopy(value)
 
@@ -116,11 +120,12 @@ class BaseContextConfigGenerator(Generic[T]):
 
     def calculate_node_config(
         self,
-        config_calls: List[Dict[str, Any]],
+        config_call_dict: Dict[str, Any],
         fqn: List[str],
         resource_type: NodeType,
         project_name: str,
         base: bool,
+        patch_config_dict: Dict[str, Any] = None
     ) -> BaseConfig:
         own_config = self.get_node_project(project_name)
 
@@ -130,8 +135,15 @@ class BaseContextConfigGenerator(Generic[T]):
         for fqn_config in project_configs:
             result = self._update_from_config(result, fqn_config)
 
-        for config_call in config_calls:
-            result = self._update_from_config(result, config_call)
+        # When schema files patch config, it has lower precedence than
+        # config in the models (config_call_dict), so we add the patch_config_dict
+        # before the config_call_dict
+        if patch_config_dict:
+            result = self._update_from_config(result, patch_config_dict)
+
+        # config_calls are created in the 'experimental' model parser and
+        # the ParseConfigObject (via add_config_call)
+        result = self._update_from_config(result, config_call_dict)
 
         if own_config.project_name != self._active_project.project_name:
             for fqn_config in self._active_project_configs(fqn, resource_type):
@@ -143,11 +155,12 @@ class BaseContextConfigGenerator(Generic[T]):
     @abstractmethod
     def calculate_node_config_dict(
         self,
-        config_calls: List[Dict[str, Any]],
+        config_call_dict: Dict[str, Any],
         fqn: List[str],
         resource_type: NodeType,
         project_name: str,
         base: bool,
+        patch_config_dict: Dict[str, Any],
     ) -> Dict[str, Any]:
         ...
 
@@ -171,25 +184,31 @@ class ContextConfigGenerator(BaseContextConfigGenerator[C]):
     def _update_from_config(
         self, result: C, partial: Dict[str, Any], validate: bool = False
     ) -> C:
-        translated = self._active_project.credentials.translate_aliases(partial)
+        translated = self._active_project.credentials.translate_aliases(
+            partial
+        )
         return result.update_from(
-            translated, self._active_project.credentials.type, validate=validate
+            translated,
+            self._active_project.credentials.type,
+            validate=validate
         )
 
     def calculate_node_config_dict(
         self,
-        config_calls: List[Dict[str, Any]],
+        config_call_dict: Dict[str, Any],
         fqn: List[str],
         resource_type: NodeType,
         project_name: str,
         base: bool,
+        patch_config_dict: dict = None
     ) -> Dict[str, Any]:
         config = self.calculate_node_config(
-            config_calls=config_calls,
+            config_call_dict=config_call_dict,
             fqn=fqn,
             resource_type=resource_type,
             project_name=project_name,
             base=base,
+            patch_config_dict=patch_config_dict
         )
         finalized = config.finalize_and_validate()
         return finalized.to_dict(omit_none=True)
@@ -201,21 +220,27 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
 
     def calculate_node_config_dict(
         self,
-        config_calls: List[Dict[str, Any]],
+        config_call_dict: Dict[str, Any],
         fqn: List[str],
         resource_type: NodeType,
         project_name: str,
         base: bool,
+        patch_config_dict: dict = None
     ) -> Dict[str, Any]:
         return self.calculate_node_config(
-            config_calls=config_calls,
+            config_call_dict=config_call_dict,
             fqn=fqn,
             resource_type=resource_type,
             project_name=project_name,
             base=base,
+            patch_config_dict=patch_config_dict
         )
 
-    def initial_result(self, resource_type: NodeType, base: bool) -> Dict[str, Any]:
+    def initial_result(
+        self,
+        resource_type: NodeType,
+        base: bool
+    ) -> Dict[str, Any]:
         return {}
 
     def _update_from_config(
@@ -224,7 +249,9 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
         partial: Dict[str, Any],
         validate: bool = False,
     ) -> Dict[str, Any]:
-        translated = self._active_project.credentials.translate_aliases(partial)
+        translated = self._active_project.credentials.translate_aliases(
+            partial
+        )
         result.update(translated)
         return result
 
@@ -237,20 +264,39 @@ class ContextConfig:
         resource_type: NodeType,
         project_name: str,
     ) -> None:
-        self._config_calls: List[Dict[str, Any]] = []
+        self._config_call_dict: Dict[str, Any] = {}
         self._active_project = active_project
         self._fqn = fqn
         self._resource_type = resource_type
         self._project_name = project_name
 
-    def update_in_model_config(self, opts: Dict[str, Any]) -> None:
-        self._config_calls.append(opts)
+    def add_config_call(self, opts: Dict[str, Any]) -> None:
+        dct = self._config_call_dict
+        self._add_config_call(dct, opts)
+
+    @classmethod
+    def _add_config_call(cls, config_call_dict, opts: Dict[str, Any]) -> None:
+        for k, v in opts.items():
+            # MergeBehavior for post-hook and pre-hook is to collect all
+            # values, instead of overwriting
+            if k in BaseConfig.mergebehavior['append']:
+                if not isinstance(v, list):
+                    v = [v]
+            if k in BaseConfig.mergebehavior['update'] and not isinstance(v, dict):
+                raise InternalException(f'expected dict, got {v}')
+            if k in config_call_dict and isinstance(config_call_dict[k], list):
+                config_call_dict[k].extend(v)
+            elif k in config_call_dict and isinstance(config_call_dict[k], dict):
+                config_call_dict[k].update(v)
+            else:
+                config_call_dict[k] = v
 
     def build_config_dict(
         self,
         base: bool = False,
         *,
         rendered: bool = True,
+        patch_config_dict: dict = None
     ) -> Dict[str, Any]:
         if rendered:
             src = ContextConfigGenerator(self._active_project)
@@ -258,9 +304,10 @@ class ContextConfig:
             src = UnrenderedConfigGenerator(self._active_project)
 
         return src.calculate_node_config_dict(
-            config_calls=self._config_calls,
+            config_call_dict=self._config_call_dict,
             fqn=self._fqn,
             resource_type=self._resource_type,
             project_name=self._project_name,
             base=base,
+            patch_config_dict=patch_config_dict
         )

core/dbt/context/docs.py

@@ -1,4 +1,6 @@
-from typing import Any, Dict, Union
+from typing import (
+    Any, Dict, Union
+)
 
 from dbt.exceptions import (
     doc_invalid_args,
@@ -9,7 +11,7 @@ from dbt.contracts.graph.compiled import CompileResultNode
 from dbt.contracts.graph.manifest import Manifest
 from dbt.contracts.graph.parsed import ParsedMacro
 
-from dbt.context import contextmember
+from dbt.context.base import contextmember
 from dbt.context.configured import SchemaYamlContext
 
 
@@ -55,14 +57,19 @@ class DocsRuntimeContext(SchemaYamlContext):
         else:
             doc_invalid_args(self.node, args)
 
+        # ParsedDocumentation
         target_doc = self.manifest.resolve_doc(
             doc_name,
             doc_package_name,
             self._project_name,
             self.node.package_name,
         )
-
-        if target_doc is None:
+        if target_doc:
+            file_id = target_doc.file_id
+            if file_id in self.manifest.files:
+                source_file = self.manifest.files[file_id]
+                source_file.add_node(self.node.unique_id)
+        else:
             doc_target_not_found(self.node, doc_name, doc_package_name)
 
         return target_doc.block_contents

core/dbt/context/macro_resolver.py

@@ -1,4 +1,6 @@
-from typing import Dict, MutableMapping, Optional
+from typing import (
+    Dict, MutableMapping, Optional
+)
 from dbt.contracts.graph.parsed import ParsedMacro
 from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
@@ -12,8 +14,12 @@ MacroNamespace = Dict[str, ParsedMacro]
 # so that higher precedence macros are found first.
 # This functionality is also provided by the MacroNamespace,
 # but the intention is to eventually replace that class.
-# This enables us to get the macor unique_id without
+# This enables us to get the macro unique_id without
 # processing every macro in the project.
+# Note: the root project macros override everything in the
+# dbt internal projects. External projects (dependencies) will
+# use their own macros first, then pull from the root project
+# followed by dbt internal projects.
 class MacroResolver:
     def __init__(
         self,
@@ -43,20 +49,32 @@ class MacroResolver:
         for pkg in reversed(self.internal_package_names):
             if pkg in self.internal_packages:
                 # Turn the internal packages into a flat namespace
-                self.internal_packages_namespace.update(self.internal_packages[pkg])
+                self.internal_packages_namespace.update(
+                    self.internal_packages[pkg])
 
+    # search order:
+    # local_namespace (package of particular node), not including
+    #    the internal packages or the root package
+    #    This means that within an extra package, it uses its own macros
+    # root package namespace
+    # non-internal packages (that aren't local or root)
+    # dbt internal packages
     def _build_macros_by_name(self):
         macros_by_name = {}
-        # search root package macros
-        for macro in self.root_package_macros.values():
+
+        # all internal packages (already in the right order)
+        for macro in self.internal_packages_namespace.values():
             macros_by_name[macro.name] = macro
-        # search miscellaneous non-internal packages
+
+        # non-internal packages
         for fnamespace in self.packages.values():
             for macro in fnamespace.values():
                 macros_by_name[macro.name] = macro
-        # search all internal packages
-        for macro in self.internal_packages_namespace.values():
+
+        # root package macros
+        for macro in self.root_package_macros.values():
             macros_by_name[macro.name] = macro
+
         self.macros_by_name = macros_by_name
 
     def _add_macro_to(
@@ -71,7 +89,9 @@ class MacroResolver:
             package_namespaces[macro.package_name] = namespace
 
         if macro.name in namespace:
-            raise_duplicate_macro_name(macro, macro, macro.package_name)
+            raise_duplicate_macro_name(
+                macro, macro, macro.package_name
+            )
         package_namespaces[macro.package_name][macro.name] = macro
 
     def add_macro(self, macro: ParsedMacro):
@@ -92,20 +112,26 @@ class MacroResolver:
         for macro in self.macros.values():
             self.add_macro(macro)
 
-    def get_macro_id(self, local_package, macro_name):
+    def get_macro(self, local_package, macro_name):
         local_package_macros = {}
-        if (
-            local_package not in self.internal_package_names
-            and local_package in self.packages
-        ):
+        if (local_package not in self.internal_package_names and
+                local_package in self.packages):
             local_package_macros = self.packages[local_package]
         # First: search the local packages for this macro
         if macro_name in local_package_macros:
-            return local_package_macros[macro_name].unique_id
+            return local_package_macros[macro_name]
+        # Now look up in the standard search order
         if macro_name in self.macros_by_name:
-            return self.macros_by_name[macro_name].unique_id
+            return self.macros_by_name[macro_name]
         return None
 
+    def get_macro_id(self, local_package, macro_name):
+        macro = self.get_macro(local_package, macro_name)
+        if macro is None:
+            return None
+        else:
+            return macro.unique_id
+
 
 # Currently this is just used by test processing in the schema
 # parser (in connection with the MacroResolver). Future work
@@ -114,22 +140,42 @@ class MacroResolver:
 # is that you can limit the number of macros provided to the
 # context dictionary in the 'to_dict' manifest method.
 class TestMacroNamespace:
-    def __init__(self, macro_resolver, ctx, node, thread_ctx, depends_on_macros):
+    def __init__(
+        self, macro_resolver, ctx, node, thread_ctx, depends_on_macros
+    ):
         self.macro_resolver = macro_resolver
         self.ctx = ctx
-        self.node = node
+        self.node = node  # can be none
         self.thread_ctx = thread_ctx
-        local_namespace = {}
+        self.local_namespace = {}
+        self.project_namespace = {}
         if depends_on_macros:
-            for macro_unique_id in depends_on_macros:
-                macro = self.manifest.macros[macro_unique_id]
-                local_namespace[macro.name] = MacroGenerator(
-                    macro,
-                    self.ctx,
-                    self.node,
-                    self.thread_ctx,
-                )
-        self.local_namespace = local_namespace
+            dep_macros = []
+            self.recursively_get_depends_on_macros(depends_on_macros, dep_macros)
+            for macro_unique_id in dep_macros:
+                if macro_unique_id in self.macro_resolver.macros:
+                    # Split up the macro unique_id to get the project_name
+                    (_, project_name, macro_name) = macro_unique_id.split('.')
+                    # Save the plain macro_name in the local_namespace
+                    macro = self.macro_resolver.macros[macro_unique_id]
+                    macro_gen = MacroGenerator(
+                        macro, self.ctx, self.node, self.thread_ctx,
+                    )
+                    self.local_namespace[macro_name] = macro_gen
+                    # We also need the two part macro name
+                    if project_name not in self.project_namespace:
+                        self.project_namespace[project_name] = {}
+                    self.project_namespace[project_name][macro_name] = macro_gen
+
+    def recursively_get_depends_on_macros(self, depends_on_macros, dep_macros):
+        for macro_unique_id in depends_on_macros:
+            if macro_unique_id in dep_macros:
+                continue
+            dep_macros.append(macro_unique_id)
+            if macro_unique_id in self.macro_resolver.macros:
+                macro = self.macro_resolver.macros[macro_unique_id]
+                if macro.depends_on.macros:
+                    self.recursively_get_depends_on_macros(macro.depends_on.macros, dep_macros)
 
     def get_from_package(
         self, package_name: Optional[str], name: str
@@ -139,9 +185,15 @@ class TestMacroNamespace:
             macro = self.macro_resolver.macros_by_name.get(name)
         elif package_name == GLOBAL_PROJECT_NAME:
             macro = self.macro_resolver.internal_packages_namespace.get(name)
-        elif package_name in self.resolver.packages:
+        elif package_name in self.macro_resolver.packages:
             macro = self.macro_resolver.packages[package_name].get(name)
         else:
-            raise_compiler_error(f"Could not find package '{package_name}'")
-        macro_func = MacroGenerator(macro, self.ctx, self.node, self.thread_ctx)
+            raise_compiler_error(
+                f"Could not find package '{package_name}'"
+            )
+        if not macro:
+            return None
+        macro_func = MacroGenerator(
+            macro, self.ctx, self.node, self.thread_ctx
+        )
         return macro_func

core/dbt/context/macros.py

@@ -1,9 +1,13 @@
-from typing import Any, Dict, Iterable, Union, Optional, List, Iterator, Mapping, Set
+from typing import (
+    Any, Dict, Iterable, Union, Optional, List, Iterator, Mapping, Set
+)
 
 from dbt.clients.jinja import MacroGenerator, MacroStack
 from dbt.contracts.graph.parsed import ParsedMacro
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
-from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
+from dbt.exceptions import (
+    raise_duplicate_macro_name, raise_compiler_error
+)
 
 
 FlatNamespace = Dict[str, MacroGenerator]
@@ -15,13 +19,17 @@ FullNamespace = Dict[str, NamespaceMember]
 # and provide the ability to flatten them into the ManifestContexts
 # that are created for jinja, so that macro calls can be resolved.
 # Creates special iterators and _keys methods to flatten the lists.
+# When this class is created it has a static 'local_namespace' which
+# depends on the package of the node, so it only works for one
+# particular local package at a time for "flattening" into a context.
+# 'get_by_package' should work for any macro.
 class MacroNamespace(Mapping):
     def __init__(
         self,
-        global_namespace: FlatNamespace,
-        local_namespace: FlatNamespace,
-        global_project_namespace: FlatNamespace,
-        packages: Dict[str, FlatNamespace],
+        global_namespace: FlatNamespace,  # root package macros
+        local_namespace: FlatNamespace,   # packages for *this* node
+        global_project_namespace: FlatNamespace,  # internal packages
+        packages: Dict[str, FlatNamespace],  # non-internal packages
     ):
         self.global_namespace: FlatNamespace = global_namespace
         self.local_namespace: FlatNamespace = local_namespace
@@ -29,13 +37,13 @@ class MacroNamespace(Mapping):
         self.global_project_namespace: FlatNamespace = global_project_namespace
 
     def _search_order(self) -> Iterable[Union[FullNamespace, FlatNamespace]]:
-        yield self.local_namespace
-        yield self.global_namespace
-        yield self.packages
+        yield self.local_namespace   # local package
+        yield self.global_namespace  # root package
+        yield self.packages          # non-internal packages
         yield {
-            GLOBAL_PROJECT_NAME: self.global_project_namespace,
+            GLOBAL_PROJECT_NAME: self.global_project_namespace,  # dbt
         }
-        yield self.global_project_namespace
+        yield self.global_project_namespace  # other internal project besides dbt
 
     # provides special keys method for MacroNamespace iterator
     # returns keys from local_namespace, global_namespace, packages,
@@ -71,7 +79,9 @@ class MacroNamespace(Mapping):
         elif package_name in self.packages:
             return self.packages[package_name].get(name)
         else:
-            raise_compiler_error(f"Could not find package '{package_name}'")
+            raise_compiler_error(
+                f"Could not find package '{package_name}'"
+            )
 
 
 # This class builds the MacroNamespace by adding macros to
@@ -92,7 +102,9 @@ class MacroNamespaceBuilder:
         # internal packages comes from get_adapter_package_names
         self.internal_package_names = set(internal_packages)
         self.internal_package_names_order = internal_packages
-        # macro_func is added here if in root package
+        # macro_func is added here if in root package, since
+        # the root package acts as a "global" namespace, overriding
+        # everything else except local external package macro calls
         self.globals: FlatNamespace = {}
         # macro_func is added here if it's the package for this node
         self.locals: FlatNamespace = {}
@@ -116,7 +128,9 @@ class MacroNamespaceBuilder:
             hierarchy[macro.package_name] = namespace
 
         if macro.name in namespace:
-            raise_duplicate_macro_name(macro_func.macro, macro, macro.package_name)
+            raise_duplicate_macro_name(
+                macro_func.macro, macro, macro.package_name
+            )
         hierarchy[macro.package_name][macro.name] = macro_func
 
     def add_macro(self, macro: ParsedMacro, ctx: Dict[str, Any]):
@@ -161,8 +175,8 @@ class MacroNamespaceBuilder:
                 global_project_namespace.update(self.internal_packages[pkg])
 
         return MacroNamespace(
-            global_namespace=self.globals,
-            local_namespace=self.locals,
-            global_project_namespace=global_project_namespace,
-            packages=self.packages,
+            global_namespace=self.globals,  # root package macros
+            local_namespace=self.locals,  # packages for *this* node
+            global_project_namespace=global_project_namespace,  # internal packages
+            packages=self.packages,  # non internal_packages
         )

core/dbt/context/manifest.py

@@ -2,7 +2,7 @@ from typing import List
 
 from dbt.clients.jinja import MacroStack
 from dbt.contracts.connection import AdapterRequiredConfig
-from dbt.contracts.graph.manifest import Manifest, AnyManifest
+from dbt.contracts.graph.manifest import Manifest
 from dbt.context.macro_resolver import TestMacroNamespace
 
 
@@ -17,11 +17,10 @@ class ManifestContext(ConfiguredContext):
     The given macros can override any previous context values, which will be
     available as if they were accessed relative to the package name.
     """
-
     def __init__(
         self,
         config: AdapterRequiredConfig,
-        manifest: AnyManifest,
+        manifest: Manifest,
         search_package: str,
     ) -> None:
         super().__init__(config)
@@ -38,12 +37,13 @@ class ManifestContext(ConfiguredContext):
         # this takes all the macros in the manifest and adds them
         # to the MacroNamespaceBuilder stored in self.namespace
         builder = self._get_namespace_builder()
-        return builder.build_namespace(self.manifest.macros.values(), self._ctx)
+        return builder.build_namespace(
+            self.manifest.macros.values(), self._ctx
+        )
 
     def _get_namespace_builder(self) -> MacroNamespaceBuilder:
         # avoid an import loop
         from dbt.adapters.factory import get_adapter_package_names
-
         internal_packages: List[str] = get_adapter_package_names(
             self.config.credentials.type
         )
@@ -62,16 +62,21 @@ class ManifestContext(ConfiguredContext):
         # keys in the manifest dictionary
         if isinstance(self.namespace, TestMacroNamespace):
             dct.update(self.namespace.local_namespace)
+            dct.update(self.namespace.project_namespace)
         else:
             dct.update(self.namespace)
         return dct
 
 
 class QueryHeaderContext(ManifestContext):
-    def __init__(self, config: AdapterRequiredConfig, manifest: Manifest) -> None:
+    def __init__(
+        self, config: AdapterRequiredConfig, manifest: Manifest
+    ) -> None:
         super().__init__(config, manifest, config.project_name)
 
 
-def generate_query_header_context(config: AdapterRequiredConfig, manifest: Manifest):
+def generate_query_header_context(
+    config: AdapterRequiredConfig, manifest: Manifest
+):
     ctx = QueryHeaderContext(config, manifest)
     return ctx.to_dict()

core/dbt/context/providers.py

@@ -1,33 +1,29 @@
 import abc
 import os
 from typing import (
-    Callable,
-    Any,
-    Dict,
-    Optional,
-    Union,
-    List,
-    TypeVar,
-    Type,
-    Iterable,
+    Callable, Any, Dict, Optional, Union, List, TypeVar, Type, Iterable,
     Mapping,
 )
 from typing_extensions import Protocol
 
 from dbt import deprecations
 from dbt.adapters.base.column import Column
-from dbt.adapters.factory import get_adapter, get_adapter_package_names
+from dbt.adapters.factory import (
+    get_adapter, get_adapter_package_names, get_adapter_type_names
+)
 from dbt.clients import agate_helper
 from dbt.clients.jinja import get_rendered, MacroGenerator, MacroStack
 from dbt.config import RuntimeConfig, Project
-from dbt.context import contextmember, contextproperty, Var
+from .base import contextmember, contextproperty, Var
 from .configured import FQNLookup
 from .context_config import ContextConfig
 from dbt.context.macro_resolver import MacroResolver, TestMacroNamespace
 from .macros import MacroNamespaceBuilder, MacroNamespace
 from .manifest import ManifestContext
 from dbt.contracts.connection import AdapterResponse
-from dbt.contracts.graph.manifest import Manifest, AnyManifest, Disabled, MacroManifest
+from dbt.contracts.graph.manifest import (
+    Manifest, Disabled
+)
 from dbt.contracts.graph.compiled import (
     CompiledResource,
     CompiledSeedNode,
@@ -56,7 +52,9 @@ from dbt.config import IsFQNResource
 from dbt.logger import GLOBAL_LOGGER as logger  # noqa
 from dbt.node_types import NodeType
 
-from dbt.utils import merge, AttrDict, MultiDict
+from dbt.utils import (
+    merge, AttrDict, MultiDict
+)
 
 import agate
 
@@ -79,8 +77,9 @@ class RelationProxy:
         return self._relation_type.create_from_source(*args, **kwargs)
 
     def create(self, *args, **kwargs):
-        kwargs["quote_policy"] = merge(
-            self._quoting_config, kwargs.pop("quote_policy", {})
+        kwargs['quote_policy'] = merge(
+            self._quoting_config,
+            kwargs.pop('quote_policy', {})
         )
         return self._relation_type.create(*args, **kwargs)
 
@@ -97,7 +96,7 @@ class BaseDatabaseWrapper:
         self._namespace = namespace
 
     def __getattr__(self, name):
-        raise NotImplementedError("subclasses need to implement this")
+        raise NotImplementedError('subclasses need to implement this')
 
     @property
     def config(self):
@@ -110,19 +109,23 @@ class BaseDatabaseWrapper:
         return self._adapter.commit_if_has_connection()
 
     def _get_adapter_macro_prefixes(self) -> List[str]:
-        # a future version of this could have plugins automatically call fall
-        # back to their dependencies' dependencies by using
-        # `get_adapter_type_names` instead of `[self.config.credentials.type]`
-        search_prefixes = [self._adapter.type(), "default"]
+        # order matters for dispatch:
+        #  1. current adapter
+        #  2. any parent adapters (dependencies)
+        #  3. 'default'
+        search_prefixes = get_adapter_type_names(self._adapter.type()) + ['default']
         return search_prefixes
 
     def dispatch(
-        self, macro_name: str, packages: Optional[List[str]] = None
+        self,
+        macro_name: str,
+        macro_namespace: Optional[str] = None,
+        packages: Optional[List[str]] = None,
     ) -> MacroGenerator:
         search_packages: List[Optional[str]]
 
-        if "." in macro_name:
-            suggest_package, suggest_macro_name = macro_name.split(".", 1)
+        if '.' in macro_name:
+            suggest_package, suggest_macro_name = macro_name.split('.', 1)
             msg = (
                 f'In adapter.dispatch, got a macro name of "{macro_name}", '
                 f'but "." is not a valid macro name component. Did you mean '
@@ -131,38 +134,50 @@ class BaseDatabaseWrapper:
             )
             raise CompilationException(msg)
 
-        if packages is None:
+        if packages is not None:
+            deprecations.warn('dispatch-packages', macro_name=macro_name)
+
+        namespace = packages if packages else macro_namespace
+
+        if namespace is None:
             search_packages = [None]
-        elif isinstance(packages, str):
-            raise CompilationException(
-                f"In adapter.dispatch, got a string packages argument "
-                f'("{packages}"), but packages should be None or a list.'
-            )
+        elif isinstance(namespace, str):
+            search_packages = self._adapter.config.get_macro_search_order(namespace)
+            if not search_packages and namespace in self._adapter.config.dependencies:
+                search_packages = [namespace]
+            if not search_packages:
+                raise CompilationException(
+                    f'In adapter.dispatch, got a string packages argument '
+                    f'("{packages}"), but packages should be None or a list.'
+                )
         else:
-            search_packages = packages
+            # Not a string and not None so must be a list
+            search_packages = namespace
 
         attempts = []
 
         for package_name in search_packages:
             for prefix in self._get_adapter_macro_prefixes():
-                search_name = f"{prefix}__{macro_name}"
+                search_name = f'{prefix}__{macro_name}'
                 try:
                     # this uses the namespace from the context
-                    macro = self._namespace.get_from_package(package_name, search_name)
+                    macro = self._namespace.get_from_package(
+                        package_name, search_name
+                    )
                 except CompilationException as exc:
                     raise CompilationException(
-                        f"In dispatch: {exc.msg}",
+                        f'In dispatch: {exc.msg}',
                     ) from exc
 
                 if package_name is None:
                     attempts.append(search_name)
                 else:
-                    attempts.append(f"{package_name}.{search_name}")
+                    attempts.append(f'{package_name}.{search_name}')
 
                 if macro is not None:
                     return macro
 
-        searched = ", ".join(repr(a) for a in attempts)
+        searched = ', '.join(repr(a) for a in attempts)
         msg = (
             f"In dispatch: No macro named '{macro_name}' found\n"
             f"    Searched for: {searched}"
@@ -192,10 +207,14 @@ class BaseResolver(metaclass=abc.ABCMeta):
 
 class BaseRefResolver(BaseResolver):
     @abc.abstractmethod
-    def resolve(self, name: str, package: Optional[str] = None) -> RelationProxy:
+    def resolve(
+        self, name: str, package: Optional[str] = None
+    ) -> RelationProxy:
         ...
 
-    def _repack_args(self, name: str, package: Optional[str]) -> List[str]:
+    def _repack_args(
+        self, name: str, package: Optional[str]
+    ) -> List[str]:
         if package is None:
             return [name]
         else:
@@ -204,13 +223,14 @@ class BaseRefResolver(BaseResolver):
     def validate_args(self, name: str, package: Optional[str]):
         if not isinstance(name, str):
             raise CompilationException(
-                f"The name argument to ref() must be a string, got " f"{type(name)}"
+                f'The name argument to ref() must be a string, got '
+                f'{type(name)}'
             )
 
         if package is not None and not isinstance(package, str):
             raise CompilationException(
-                f"The package argument to ref() must be a string or None, got "
-                f"{type(package)}"
+                f'The package argument to ref() must be a string or None, got '
+                f'{type(package)}'
             )
 
     def __call__(self, *args: str) -> RelationProxy:
@@ -235,19 +255,20 @@ class BaseSourceResolver(BaseResolver):
     def validate_args(self, source_name: str, table_name: str):
         if not isinstance(source_name, str):
             raise CompilationException(
-                f"The source name (first) argument to source() must be a "
-                f"string, got {type(source_name)}"
+                f'The source name (first) argument to source() must be a '
+                f'string, got {type(source_name)}'
             )
         if not isinstance(table_name, str):
             raise CompilationException(
-                f"The table name (second) argument to source() must be a "
-                f"string, got {type(table_name)}"
+                f'The table name (second) argument to source() must be a '
+                f'string, got {type(table_name)}'
             )
 
     def __call__(self, *args: str) -> RelationProxy:
         if len(args) != 2:
             raise_compiler_error(
-                f"source() takes exactly two arguments ({len(args)} given)", self.model
+                f"source() takes exactly two arguments ({len(args)} given)",
+                self.model
             )
         self.validate_args(args[0], args[1])
         return self.resolve(args[0], args[1])
@@ -258,22 +279,21 @@ class Config(Protocol):
         ...
 
 
-# `config` implementations
+# Implementation of "config(..)" calls in models
 class ParseConfigObject(Config):
     def __init__(self, model, context_config: Optional[ContextConfig]):
         self.model = model
         self.context_config = context_config
 
     def _transform_config(self, config):
-        for oldkey in ("pre_hook", "post_hook"):
+        for oldkey in ('pre_hook', 'post_hook'):
             if oldkey in config:
-                newkey = oldkey.replace("_", "-")
+                newkey = oldkey.replace('_', '-')
                 if newkey in config:
                     raise_compiler_error(
-                        'Invalid config, has conflicting keys "{}" and "{}"'.format(
-                            oldkey, newkey
-                        ),
-                        self.model,
+                        'Invalid config, has conflicting keys "{}" and "{}"'
+                        .format(oldkey, newkey),
+                        self.model
                     )
                 config[newkey] = config.pop(oldkey)
         return config
@@ -284,25 +304,29 @@ class ParseConfigObject(Config):
         elif len(args) == 0 and len(kwargs) > 0:
             opts = kwargs
         else:
-            raise_compiler_error("Invalid inline model config", self.model)
+            raise_compiler_error(
+                "Invalid inline model config",
+                self.model)
 
         opts = self._transform_config(opts)
 
         # it's ok to have a parse context with no context config, but you must
         # not call it!
         if self.context_config is None:
-            raise RuntimeException("At parse time, did not receive a context config")
-        self.context_config.update_in_model_config(opts)
-        return ""
+            raise RuntimeException(
+                'At parse time, did not receive a context config'
+            )
+        self.context_config.add_config_call(opts)
+        return ''
 
     def set(self, name, value):
         return self.__call__({name: value})
 
     def require(self, name, validator=None):
-        return ""
+        return ''
 
     def get(self, name, validator=None, default=None):
-        return ""
+        return ''
 
     def persist_relation_docs(self) -> bool:
         return False
@@ -312,12 +336,14 @@ class ParseConfigObject(Config):
 
 
 class RuntimeConfigObject(Config):
-    def __init__(self, model, context_config: Optional[ContextConfig] = None):
+    def __init__(
+        self, model, context_config: Optional[ContextConfig] = None
+    ):
         self.model = model
         # we never use or get a config, only the parser cares
 
     def __call__(self, *args, **kwargs):
-        return ""
+        return ''
 
     def set(self, name, value):
         return self.__call__({name: value})
@@ -327,7 +353,7 @@ class RuntimeConfigObject(Config):
 
     def _lookup(self, name, default=_MISSING):
         # if this is a macro, there might be no `model.config`.
-        if not hasattr(self.model, "config"):
+        if not hasattr(self.model, 'config'):
             result = default
         else:
             result = self.model.config.get(name, default)
@@ -352,24 +378,22 @@ class RuntimeConfigObject(Config):
         return to_return
 
     def persist_relation_docs(self) -> bool:
-        persist_docs = self.get("persist_docs", default={})
+        persist_docs = self.get('persist_docs', default={})
         if not isinstance(persist_docs, dict):
             raise_compiler_error(
                 f"Invalid value provided for 'persist_docs'. Expected dict "
-                f"but received {type(persist_docs)}"
-            )
+                f"but received {type(persist_docs)}")
 
-        return persist_docs.get("relation", False)
+        return persist_docs.get('relation', False)
 
     def persist_column_docs(self) -> bool:
-        persist_docs = self.get("persist_docs", default={})
+        persist_docs = self.get('persist_docs', default={})
         if not isinstance(persist_docs, dict):
             raise_compiler_error(
                 f"Invalid value provided for 'persist_docs'. Expected dict "
-                f"but received {type(persist_docs)}"
-            )
+                f"but received {type(persist_docs)}")
 
-        return persist_docs.get("columns", False)
+        return persist_docs.get('columns', False)
 
 
 # `adapter` implementations
@@ -379,10 +403,8 @@ class ParseDatabaseWrapper(BaseDatabaseWrapper):
     """
 
     def __getattr__(self, name):
-        override = (
-            name in self._adapter._available_
-            and name in self._adapter._parse_replacements_
-        )
+        override = (name in self._adapter._available_ and
+                    name in self._adapter._parse_replacements_)
 
         if override:
             return self._adapter._parse_replacements_[name]
@@ -414,7 +436,9 @@ class RuntimeDatabaseWrapper(BaseDatabaseWrapper):
 
 # `ref` implementations
 class ParseRefResolver(BaseRefResolver):
-    def resolve(self, name: str, package: Optional[str] = None) -> RelationProxy:
+    def resolve(
+        self, name: str, package: Optional[str] = None
+    ) -> RelationProxy:
         self.model.refs.append(self._repack_args(name, package))
 
         return self.Relation.create_from(self.config, self.model)
@@ -444,15 +468,22 @@ class RuntimeRefResolver(BaseRefResolver):
         self.validate(target_model, target_name, target_package)
         return self.create_relation(target_model, target_name)
 
-    def create_relation(self, target_model: ManifestNode, name: str) -> RelationProxy:
+    def create_relation(
+        self, target_model: ManifestNode, name: str
+    ) -> RelationProxy:
         if target_model.is_ephemeral_model:
             self.model.set_cte(target_model.unique_id, None)
-            return self.Relation.create_ephemeral_from_node(self.config, target_model)
+            return self.Relation.create_ephemeral_from_node(
+                self.config, target_model
+            )
         else:
             return self.Relation.create_from(self.config, target_model)
 
     def validate(
-        self, resolved: ManifestNode, target_name: str, target_package: Optional[str]
+        self,
+        resolved: ManifestNode,
+        target_name: str,
+        target_package: Optional[str]
     ) -> None:
         if resolved.unique_id not in self.model.depends_on.nodes:
             args = self._repack_args(target_name, target_package)
@@ -468,15 +499,16 @@ class OperationRefResolver(RuntimeRefResolver):
     ) -> None:
         pass
 
-    def create_relation(self, target_model: ManifestNode, name: str) -> RelationProxy:
+    def create_relation(
+        self, target_model: ManifestNode, name: str
+    ) -> RelationProxy:
         if target_model.is_ephemeral_model:
             # In operations, we can't ref() ephemeral nodes, because
             # ParsedMacros do not support set_cte
             raise_compiler_error(
-                "Operations can not ref() ephemeral nodes, but {} is ephemeral".format(
-                    target_model.name
-                ),
-                self.model,
+                'Operations can not ref() ephemeral nodes, but {} is ephemeral'
+                .format(target_model.name),
+                self.model
             )
         else:
             return super().create_relation(target_model, name)
@@ -528,7 +560,8 @@ class ModelConfiguredVar(Var):
             if package_name not in dependencies:
                 # I don't think this is actually reachable
                 raise_compiler_error(
-                    f"Node package named {package_name} not found!", self._node
+                    f'Node package named {package_name} not found!',
+                    self._node
                 )
             yield dependencies[package_name]
         yield self._config
@@ -600,7 +633,7 @@ class OperationProvider(RuntimeProvider):
     ref = OperationRefResolver
 
 
-T = TypeVar("T")
+T = TypeVar('T')
 
 
 # Base context collection, used for parsing configs.
@@ -614,7 +647,9 @@ class ProviderContext(ManifestContext):
         context_config: Optional[ContextConfig],
     ) -> None:
         if provider is None:
-            raise InternalException(f"Invalid provider given to context: {provider}")
+            raise InternalException(
+                f"Invalid provider given to context: {provider}"
+            )
         # mypy appeasement - we know it'll be a RuntimeConfig
         self.config: RuntimeConfig
         self.model: Union[ParsedMacro, ManifestNode] = model
@@ -624,12 +659,16 @@ class ProviderContext(ManifestContext):
         self.provider: Provider = provider
         self.adapter = get_adapter(self.config)
         # The macro namespace is used in creating the DatabaseWrapper
-        self.db_wrapper = self.provider.DatabaseWrapper(self.adapter, self.namespace)
+        self.db_wrapper = self.provider.DatabaseWrapper(
+            self.adapter, self.namespace
+        )
 
     # This overrides the method in ManifestContext, and provides
     # a model, which the ManifestContext builder does not
     def _get_namespace_builder(self):
-        internal_packages = get_adapter_package_names(self.config.credentials.type)
+        internal_packages = get_adapter_package_names(
+            self.config.credentials.type
+        )
         return MacroNamespaceBuilder(
             self.config.project_name,
             self.search_package,
@@ -648,19 +687,19 @@ class ProviderContext(ManifestContext):
 
     @contextmember
     def store_result(
-        self, name: str, response: Any, agate_table: Optional[agate.Table] = None
+        self, name: str,
+        response: Any,
+        agate_table: Optional[agate.Table] = None
     ) -> str:
         if agate_table is None:
             agate_table = agate_helper.empty_table()
 
-        self.sql_results[name] = AttrDict(
-            {
-                "response": response,
-                "data": agate_helper.as_matrix(agate_table),
-                "table": agate_table,
-            }
-        )
-        return ""
+        self.sql_results[name] = AttrDict({
+            'response': response,
+            'data': agate_helper.as_matrix(agate_table),
+            'table': agate_table
+        })
+        return ''
 
     @contextmember
     def store_raw_result(
@@ -669,11 +708,10 @@ class ProviderContext(ManifestContext):
         message=Optional[str],
         code=Optional[str],
         rows_affected=Optional[str],
-        agate_table: Optional[agate.Table] = None,
+        agate_table: Optional[agate.Table] = None
     ) -> str:
         response = AdapterResponse(
-            _message=message, code=code, rows_affected=rows_affected
-        )
+            _message=message, code=code, rows_affected=rows_affected)
         return self.store_result(name, response, agate_table)
 
     @contextproperty
@@ -686,28 +724,25 @@ class ProviderContext(ManifestContext):
                     elif value == arg:
                         return
                 raise ValidationException(
-                    'Expected value "{}" to be one of {}'.format(
-                        value, ",".join(map(str, args))
-                    )
-                )
-
+                    'Expected value "{}" to be one of {}'
+                    .format(value, ','.join(map(str, args))))
             return inner
 
-        return AttrDict(
-            {
-                "any": validate_any,
-            }
-        )
+        return AttrDict({
+            'any': validate_any,
+        })
 
     @contextmember
     def write(self, payload: str) -> str:
         # macros/source defs aren't 'writeable'.
         if isinstance(self.model, (ParsedMacro, ParsedSourceDefinition)):
-            raise_compiler_error('cannot "write" macros or sources')
+            raise_compiler_error(
+                'cannot "write" macros or sources'
+            )
         self.model.build_path = self.model.write_node(
-            self.config.target_path, "run", payload
+            self.config.target_path, 'run', payload
         )
-        return ""
+        return ''
 
     @contextmember
     def render(self, string: str) -> str:
@@ -720,17 +755,20 @@ class ProviderContext(ManifestContext):
         try:
             return func(*args, **kwargs)
         except Exception:
-            raise_compiler_error(message_if_exception, self.model)
+            raise_compiler_error(
+                message_if_exception, self.model
+            )
 
     @contextmember
     def load_agate_table(self) -> agate.Table:
         if not isinstance(self.model, (ParsedSeedNode, CompiledSeedNode)):
             raise_compiler_error(
-                "can only load_agate_table for seeds (got a {})".format(
-                    self.model.resource_type
-                )
+                'can only load_agate_table for seeds (got a {})'
+                .format(self.model.resource_type)
             )
-        path = os.path.join(self.model.root_path, self.model.original_file_path)
+        path = os.path.join(
+            self.model.root_path, self.model.original_file_path
+        )
         column_types = self.model.config.column_types
         try:
             table = agate_helper.from_csv(path, text_columns=column_types)
@@ -788,7 +826,7 @@ class ProviderContext(ManifestContext):
             self.db_wrapper, self.model, self.config, self.manifest
         )
 
-    @contextproperty("config")
+    @contextproperty('config')
     def ctx_config(self) -> Config:
         """The `config` variable exists to handle end-user configuration for
         custom materializations. Configs like `unique_key` can be implemented
@@ -960,7 +998,7 @@ class ProviderContext(ManifestContext):
             node=self.model,
         )
 
-    @contextproperty("adapter")
+    @contextproperty('adapter')
     def ctx_adapter(self) -> BaseDatabaseWrapper:
         """`adapter` is a wrapper around the internal database adapter used by
         dbt. It allows users to make calls to the database in their dbt models.
@@ -972,8 +1010,8 @@ class ProviderContext(ManifestContext):
     @contextproperty
     def api(self) -> Dict[str, Any]:
         return {
-            "Relation": self.db_wrapper.Relation,
-            "Column": self.adapter.Column,
+            'Relation': self.db_wrapper.Relation,
+            'Column': self.adapter.Column,
         }
 
     @contextproperty
@@ -1091,7 +1129,7 @@ class ProviderContext(ManifestContext):
         """  # noqa
         return self.manifest.flat_graph
 
-    @contextproperty("model")
+    @contextproperty('model')
     def ctx_model(self) -> Dict[str, Any]:
         return self.model.to_dict(omit_none=True)
 
@@ -1155,20 +1193,21 @@ class ProviderContext(ManifestContext):
                ...
             {%- endmacro %}
         """
-        deprecations.warn("adapter-macro", macro_name=name)
+        deprecations.warn('adapter-macro', macro_name=name)
         original_name = name
-        package_names: Optional[List[str]] = None
-        if "." in name:
-            package_name, name = name.split(".", 1)
-            package_names = [package_name]
+        package_name = None
+        if '.' in name:
+            package_name, name = name.split('.', 1)
 
         try:
-            macro = self.db_wrapper.dispatch(macro_name=name, packages=package_names)
+            macro = self.db_wrapper.dispatch(
+                macro_name=name, macro_namespace=package_name
+            )
         except CompilationException as exc:
             raise CompilationException(
-                f"In adapter_macro: {exc.msg}\n"
+                f'In adapter_macro: {exc.msg}\n'
                 f"    Original name: '{original_name}'",
-                node=self.model,
+                node=self.model
             ) from exc
         return macro(*args, **kwargs)
 
@@ -1176,17 +1215,17 @@ class ProviderContext(ManifestContext):
 class MacroContext(ProviderContext):
     """Internally, macros can be executed like nodes, with some restrictions:
 
-    - they don't have have all values available that nodes do:
-       - 'this', 'pre_hooks', 'post_hooks', and 'sql' are missing
-       - 'schema' does not use any 'model' information
-    - they can't be configured with config() directives
+     - they don't have have all values available that nodes do:
+        - 'this', 'pre_hooks', 'post_hooks', and 'sql' are missing
+        - 'schema' does not use any 'model' information
+     - they can't be configured with config() directives
     """
 
     def __init__(
         self,
         model: ParsedMacro,
         config: RuntimeConfig,
-        manifest: AnyManifest,
+        manifest: Manifest,
         provider: Provider,
         search_package: Optional[str],
     ) -> None:
@@ -1204,29 +1243,37 @@ class ModelContext(ProviderContext):
 
     @contextproperty
     def pre_hooks(self) -> List[Dict[str, Any]]:
-        if isinstance(self.model, ParsedSourceDefinition):
+        if self.model.resource_type in [NodeType.Source, NodeType.Test]:
             return []
-        return [h.to_dict(omit_none=True) for h in self.model.config.pre_hook]
+        return [
+            h.to_dict(omit_none=True) for h in self.model.config.pre_hook
+        ]
 
     @contextproperty
     def post_hooks(self) -> List[Dict[str, Any]]:
-        if isinstance(self.model, ParsedSourceDefinition):
+        if self.model.resource_type in [NodeType.Source, NodeType.Test]:
             return []
-        return [h.to_dict(omit_none=True) for h in self.model.config.post_hook]
+        return [
+            h.to_dict(omit_none=True) for h in self.model.config.post_hook
+        ]
 
     @contextproperty
     def sql(self) -> Optional[str]:
-        if getattr(self.model, "extra_ctes_injected", None):
+        if getattr(self.model, 'extra_ctes_injected', None):
             return self.model.compiled_sql
         return None
 
     @contextproperty
     def database(self) -> str:
-        return getattr(self.model, "database", self.config.credentials.database)
+        return getattr(
+            self.model, 'database', self.config.credentials.database
+        )
 
     @contextproperty
     def schema(self) -> str:
-        return getattr(self.model, "schema", self.config.credentials.schema)
+        return getattr(
+            self.model, 'schema', self.config.credentials.schema
+        )
 
     @contextproperty
     def this(self) -> Optional[RelationProxy]:
@@ -1268,13 +1315,15 @@ class ModelContext(ProviderContext):
 def generate_parser_model(
     model: ManifestNode,
     config: RuntimeConfig,
-    manifest: MacroManifest,
+    manifest: Manifest,
     context_config: ContextConfig,
 ) -> Dict[str, Any]:
     # The __init__ method of ModelContext also initializes
     # a ManifestContext object which creates a MacroNamespaceBuilder
     # which adds every macro in the Manifest.
-    ctx = ModelContext(model, config, manifest, ParseProvider(), context_config)
+    ctx = ModelContext(
+        model, config, manifest, ParseProvider(), context_config
+    )
     # The 'to_dict' method in ManifestContext moves all of the macro names
     # in the macro 'namespace' up to top level keys
     return ctx.to_dict()
@@ -1283,9 +1332,11 @@ def generate_parser_model(
 def generate_generate_component_name_macro(
     macro: ParsedMacro,
     config: RuntimeConfig,
-    manifest: MacroManifest,
+    manifest: Manifest,
 ) -> Dict[str, Any]:
-    ctx = MacroContext(macro, config, manifest, GenerateNameProvider(), None)
+    ctx = MacroContext(
+        macro, config, manifest, GenerateNameProvider(), None
+    )
     return ctx.to_dict()
 
 
@@ -1294,7 +1345,9 @@ def generate_runtime_model(
     config: RuntimeConfig,
     manifest: Manifest,
 ) -> Dict[str, Any]:
-    ctx = ModelContext(model, config, manifest, RuntimeProvider(), None)
+    ctx = ModelContext(
+        model, config, manifest, RuntimeProvider(), None
+    )
     return ctx.to_dict()
 
 
@@ -1304,7 +1357,9 @@ def generate_runtime_macro(
     manifest: Manifest,
     package_name: Optional[str],
 ) -> Dict[str, Any]:
-    ctx = MacroContext(macro, config, manifest, OperationProvider(), package_name)
+    ctx = MacroContext(
+        macro, config, manifest, OperationProvider(), package_name
+    )
     return ctx.to_dict()
 
 
@@ -1313,39 +1368,40 @@ class ExposureRefResolver(BaseResolver):
         if len(args) not in (1, 2):
             ref_invalid_args(self.model, args)
         self.model.refs.append(list(args))
-        return ""
+        return ''
 
 
 class ExposureSourceResolver(BaseResolver):
     def __call__(self, *args) -> str:
         if len(args) != 2:
             raise_compiler_error(
-                f"source() takes exactly two arguments ({len(args)} given)", self.model
+                f"source() takes exactly two arguments ({len(args)} given)",
+                self.model
             )
         self.model.sources.append(list(args))
-        return ""
+        return ''
 
 
 def generate_parse_exposure(
     exposure: ParsedExposure,
     config: RuntimeConfig,
-    manifest: MacroManifest,
+    manifest: Manifest,
     package_name: str,
 ) -> Dict[str, Any]:
     project = config.load_dependencies()[package_name]
     return {
-        "ref": ExposureRefResolver(
+        'ref': ExposureRefResolver(
             None,
             exposure,
             project,
             manifest,
         ),
-        "source": ExposureSourceResolver(
+        'source': ExposureSourceResolver(
             None,
             exposure,
             project,
             manifest,
-        ),
+        )
     }
 
 
@@ -1367,7 +1423,12 @@ class TestContext(ProviderContext):
         self.macro_resolver = macro_resolver
         self.thread_ctx = MacroStack()
         super().__init__(model, config, manifest, provider, context_config)
-        self._build_test_namespace
+        self._build_test_namespace()
+        # We need to rebuild this because it's already been built by
+        # the ProviderContext with the wrong namespace.
+        self.db_wrapper = self.provider.DatabaseWrapper(
+            self.adapter, self.namespace
+        )
 
     def _build_namespace(self):
         return {}
@@ -1380,10 +1441,17 @@ class TestContext(ProviderContext):
         depends_on_macros = []
         if self.model.depends_on and self.model.depends_on.macros:
             depends_on_macros = self.model.depends_on.macros
+        lookup_macros = depends_on_macros.copy()
+        for macro_unique_id in lookup_macros:
+            lookup_macro = self.macro_resolver.macros.get(macro_unique_id)
+            if lookup_macro:
+                depends_on_macros.extend(lookup_macro.depends_on.macros)
+
         macro_namespace = TestMacroNamespace(
-            self.macro_resolver, self.ctx, self.node, self.thread_ctx, depends_on_macros
+            self.macro_resolver, self._ctx, self.model, self.thread_ctx,
+            depends_on_macros
         )
-        self._namespace = macro_namespace
+        self.namespace = macro_namespace
 
 
 def generate_test_context(
@@ -1391,10 +1459,11 @@ def generate_test_context(
     config: RuntimeConfig,
     manifest: Manifest,
     context_config: ContextConfig,
-    macro_resolver: MacroResolver,
+    macro_resolver: MacroResolver
 ) -> Dict[str, Any]:
     ctx = TestContext(
-        model, config, manifest, ParseProvider(), context_config, macro_resolver
+        model, config, manifest, ParseProvider(), context_config,
+        macro_resolver
     )
     # The 'to_dict' method in ManifestContext moves all of the macro names
     # in the macro 'namespace' up to top level keys

core/dbt/context/target.py

@@ -2,7 +2,9 @@ from typing import Any, Dict
 
 from dbt.contracts.connection import HasCredentials
 
-from dbt.context import BaseContext, contextproperty
+from dbt.context.base import (
+    BaseContext, contextproperty
+)
 
 
 class TargetContext(BaseContext):

core/dbt/contracts/connection.py

@@ -1,36 +1,27 @@
 import abc
 import itertools
+import hashlib
 from dataclasses import dataclass, field
 from typing import (
-    Any,
-    ClassVar,
-    Dict,
-    Tuple,
-    Iterable,
-    Optional,
-    List,
-    Callable,
+    Any, ClassVar, Dict, Tuple, Iterable, Optional, List, Callable,
 )
 from dbt.exceptions import InternalException
 from dbt.utils import translate_aliases
 from dbt.logger import GLOBAL_LOGGER as logger
 from typing_extensions import Protocol
 from dbt.dataclass_schema import (
-    dbtClassMixin,
-    StrEnum,
-    ExtensibleDbtClassMixin,
-    ValidatedStringMixin,
-    register_pattern,
+    dbtClassMixin, StrEnum, ExtensibleDbtClassMixin, HyphenatedDbtClassMixin,
+    ValidatedStringMixin, register_pattern
 )
 from dbt.contracts.util import Replaceable
 
 
 class Identifier(ValidatedStringMixin):
-    ValidationRegex = r"^[A-Za-z_][A-Za-z0-9_]+$"
+    ValidationRegex = r'^[A-Za-z_][A-Za-z0-9_]+$'
 
 
 # we need register_pattern for jsonschema validation
-register_pattern(Identifier, r"^[A-Za-z_][A-Za-z0-9_]+$")
+register_pattern(Identifier, r'^[A-Za-z_][A-Za-z0-9_]+$')
 
 
 @dataclass
@@ -44,10 +35,10 @@ class AdapterResponse(dbtClassMixin):
 
 
 class ConnectionState(StrEnum):
-    INIT = "init"
-    OPEN = "open"
-    CLOSED = "closed"
-    FAIL = "fail"
+    INIT = 'init'
+    OPEN = 'open'
+    CLOSED = 'closed'
+    FAIL = 'fail'
 
 
 @dataclass(init=False)
@@ -91,7 +82,8 @@ class Connection(ExtensibleDbtClassMixin, Replaceable):
                 self._handle.resolve(self)
             except RecursionError as exc:
                 raise InternalException(
-                    "A connection's open() method attempted to read the " "handle value"
+                    "A connection's open() method attempted to read the "
+                    "handle value"
                 ) from exc
         return self._handle
 
@@ -110,7 +102,8 @@ class LazyHandle:
 
     def resolve(self, connection: Connection) -> Connection:
         logger.debug(
-            "Opening a new connection, currently in state {}".format(connection.state)
+            'Opening a new connection, currently in state {}'
+            .format(connection.state)
         )
         return self.opener(connection)
 
@@ -120,24 +113,42 @@ class LazyHandle:
 # for why we have type: ignore. Maybe someday dataclasses + abstract classes
 # will work.
 @dataclass  # type: ignore
-class Credentials(ExtensibleDbtClassMixin, Replaceable, metaclass=abc.ABCMeta):
+class Credentials(
+    ExtensibleDbtClassMixin,
+    Replaceable,
+    metaclass=abc.ABCMeta
+):
     database: str
     schema: str
     _ALIASES: ClassVar[Dict[str, str]] = field(default={}, init=False)
 
     @abc.abstractproperty
     def type(self) -> str:
-        raise NotImplementedError("type not implemented for base credentials class")
+        raise NotImplementedError(
+            'type not implemented for base credentials class'
+        )
+
+    @abc.abstractproperty
+    def unique_field(self) -> str:
+        raise NotImplementedError(
+            'type not implemented for base credentials class'
+        )
+
+    def hashed_unique_field(self) -> str:
+        return hashlib.md5(self.unique_field.encode('utf-8')).hexdigest()
 
     def connection_info(
         self, *, with_aliases: bool = False
     ) -> Iterable[Tuple[str, Any]]:
-        """Return an ordered iterator of key/value pairs for pretty-printing."""
+        """Return an ordered iterator of key/value pairs for pretty-printing.
+        """
         as_dict = self.to_dict(omit_none=False)
         connection_keys = set(self._connection_keys())
         aliases: List[str] = []
         if with_aliases:
-            aliases = [k for k, v in self._ALIASES.items() if v in connection_keys]
+            aliases = [
+                k for k, v in self._ALIASES.items() if v in connection_keys
+            ]
         for key in itertools.chain(self._connection_keys(), aliases):
             if key in as_dict:
                 yield key, as_dict[key]
@@ -161,13 +172,11 @@ class Credentials(ExtensibleDbtClassMixin, Replaceable, metaclass=abc.ABCMeta):
     def __post_serialize__(self, dct):
         # no super() -- do we need it?
         if self._ALIASES:
-            dct.update(
-                {
-                    new_name: dct[canonical_name]
-                    for new_name, canonical_name in self._ALIASES.items()
-                    if canonical_name in dct
-                }
-            )
+            dct.update({
+                new_name: dct[canonical_name]
+                for new_name, canonical_name in self._ALIASES.items()
+                if canonical_name in dct
+            })
         return dct
 
 
@@ -189,10 +198,10 @@ class HasCredentials(Protocol):
     threads: int
 
     def to_target_dict(self):
-        raise NotImplementedError("to_target_dict not implemented")
+        raise NotImplementedError('to_target_dict not implemented')
 
 
-DEFAULT_QUERY_COMMENT = """
+DEFAULT_QUERY_COMMENT = '''
 {%- set comment_dict = {} -%}
 {%- do comment_dict.update(
     app='dbt',
@@ -209,13 +218,14 @@ DEFAULT_QUERY_COMMENT = """
   {%- do comment_dict.update(connection_name=connection_name) -%}
 {%- endif -%}
 {{ return(tojson(comment_dict)) }}
-"""
+'''
 
 
 @dataclass
-class QueryComment(dbtClassMixin):
+class QueryComment(HyphenatedDbtClassMixin):
     comment: str = DEFAULT_QUERY_COMMENT
     append: bool = False
+    job_label: bool = False
 
 
 class AdapterRequiredConfig(HasCredentials, Protocol):

core/dbt/contracts/files.py

@@ -1,17 +1,41 @@
 import hashlib
 import os
 from dataclasses import dataclass, field
-from typing import List, Optional, Union
+from mashumaro.types import SerializableType
+from typing import List, Optional, Union, Dict, Any
 
-from dbt.dataclass_schema import dbtClassMixin
+from dbt.dataclass_schema import dbtClassMixin, StrEnum
 
-from dbt.exceptions import InternalException
-
-from .util import MacroKey, SourceKey
+from .util import SourceKey
 
 
 MAXIMUM_SEED_SIZE = 1 * 1024 * 1024
-MAXIMUM_SEED_SIZE_NAME = "1MB"
+MAXIMUM_SEED_SIZE_NAME = '1MB'
+
+
+class ParseFileType(StrEnum):
+    Macro = 'macro'
+    Model = 'model'
+    Snapshot = 'snapshot'
+    Analysis = 'analysis'
+    Test = 'test'
+    Seed = 'seed'
+    Documentation = 'docs'
+    Schema = 'schema'
+    Hook = 'hook'   # not a real filetype, from dbt_project.yml
+
+
+parse_file_type_to_parser = {
+    ParseFileType.Macro: 'MacroParser',
+    ParseFileType.Model: 'ModelParser',
+    ParseFileType.Snapshot: 'SnapshotParser',
+    ParseFileType.Analysis: 'AnalysisParser',
+    ParseFileType.Test: 'DataTestParser',
+    ParseFileType.Seed: 'SeedParser',
+    ParseFileType.Documentation: 'DocumentationParser',
+    ParseFileType.Schema: 'SchemaParser',
+    ParseFileType.Hook: 'HookParser',
+}
 
 
 @dataclass
@@ -28,7 +52,9 @@ class FilePath(dbtClassMixin):
     @property
     def full_path(self) -> str:
         # useful for symlink preservation
-        return os.path.join(self.project_root, self.searched_path, self.relative_path)
+        return os.path.join(
+            self.project_root, self.searched_path, self.relative_path
+        )
 
     @property
     def absolute_path(self) -> str:
@@ -38,10 +64,13 @@ class FilePath(dbtClassMixin):
     def original_file_path(self) -> str:
         # this is mostly used for reporting errors. It doesn't show the project
         # name, should it?
-        return os.path.join(self.searched_path, self.relative_path)
+        return os.path.join(
+            self.searched_path, self.relative_path
+        )
 
     def seed_too_large(self) -> bool:
-        """Return whether the file this represents is over the seed size limit"""
+        """Return whether the file this represents is over the seed size limit
+        """
         return os.stat(self.full_path).st_size > MAXIMUM_SEED_SIZE
 
 
@@ -52,35 +81,35 @@ class FileHash(dbtClassMixin):
 
     @classmethod
     def empty(cls):
-        return FileHash(name="none", checksum="")
+        return FileHash(name='none', checksum='')
 
     @classmethod
     def path(cls, path: str):
-        return FileHash(name="path", checksum=path)
+        return FileHash(name='path', checksum=path)
 
     def __eq__(self, other):
         if not isinstance(other, FileHash):
             return NotImplemented
 
-        if self.name == "none" or self.name != other.name:
+        if self.name == 'none' or self.name != other.name:
             return False
 
         return self.checksum == other.checksum
 
     def compare(self, contents: str) -> bool:
         """Compare the file contents with the given hash"""
-        if self.name == "none":
+        if self.name == 'none':
             return False
 
         return self.from_contents(contents, name=self.name) == self.checksum
 
     @classmethod
-    def from_contents(cls, contents: str, name="sha256") -> "FileHash":
+    def from_contents(cls, contents: str, name='sha256') -> 'FileHash':
         """Create a file hash from the given file contents. The hash is always
         the utf-8 encoding of the contents given, because dbt only reads files
         as utf-8.
         """
-        data = contents.encode("utf-8")
+        data = contents.encode('utf-8')
         checksum = hashlib.new(name, data).hexdigest()
         return cls(name=name, checksum=checksum)
 
@@ -89,75 +118,181 @@ class FileHash(dbtClassMixin):
 class RemoteFile(dbtClassMixin):
     @property
     def searched_path(self) -> str:
-        return "from remote system"
+        return 'from remote system'
 
     @property
     def relative_path(self) -> str:
-        return "from remote system"
+        return 'from remote system'
 
     @property
     def absolute_path(self) -> str:
-        return "from remote system"
+        return 'from remote system'
 
     @property
     def original_file_path(self):
-        return "from remote system"
+        return 'from remote system'
 
 
 @dataclass
-class SourceFile(dbtClassMixin):
+class BaseSourceFile(dbtClassMixin, SerializableType):
     """Define a source file in dbt"""
-
     path: Union[FilePath, RemoteFile]  # the path information
     checksum: FileHash
+    # Seems like knowing which project the file came from would be useful
+    project_name: Optional[str] = None
+    # Parse file type: i.e. which parser will process this file
+    parse_file_type: Optional[ParseFileType] = None
     # we don't want to serialize this
-    _contents: Optional[str] = None
+    contents: Optional[str] = None
     # the unique IDs contained in this file
+
+    @property
+    def file_id(self):
+        if isinstance(self.path, RemoteFile):
+            return None
+        if self.checksum.name == 'none':
+            return None
+        return f'{self.project_name}://{self.path.original_file_path}'
+
+    def _serialize(self):
+        dct = self.to_dict()
+        return dct
+
+    @classmethod
+    def _deserialize(cls, dct: Dict[str, int]):
+        if dct['parse_file_type'] == 'schema':
+            sf = SchemaSourceFile.from_dict(dct)
+        else:
+            sf = SourceFile.from_dict(dct)
+        return sf
+
+    def __post_serialize__(self, dct):
+        dct = super().__post_serialize__(dct)
+        # remove empty lists to save space
+        dct_keys = list(dct.keys())
+        for key in dct_keys:
+            if isinstance(dct[key], list) and not dct[key]:
+                del dct[key]
+        # remove contents. Schema files will still have 'dict_from_yaml'
+        # from the contents
+        if 'contents' in dct:
+            del dct['contents']
+        return dct
+
+
+@dataclass
+class SourceFile(BaseSourceFile):
     nodes: List[str] = field(default_factory=list)
     docs: List[str] = field(default_factory=list)
     macros: List[str] = field(default_factory=list)
-    sources: List[str] = field(default_factory=list)
-    exposures: List[str] = field(default_factory=list)
-    # any node patches in this file. The entries are names, not unique ids!
-    patches: List[str] = field(default_factory=list)
-    # any macro patches in this file. The entries are package, name pairs.
-    macro_patches: List[MacroKey] = field(default_factory=list)
-    # any source patches in this file. The entries are package, name pairs
-    source_patches: List[SourceKey] = field(default_factory=list)
-
-    @property
-    def search_key(self) -> Optional[str]:
-        if isinstance(self.path, RemoteFile):
-            return None
-        if self.checksum.name == "none":
-            return None
-        return self.path.search_key
-
-    @property
-    def contents(self) -> str:
-        if self._contents is None:
-            raise InternalException("SourceFile has no contents!")
-        return self._contents
-
-    @contents.setter
-    def contents(self, value):
-        self._contents = value
 
     @classmethod
-    def empty(cls, path: FilePath) -> "SourceFile":
-        self = cls(path=path, checksum=FileHash.empty())
-        self.contents = ""
-        return self
-
-    @classmethod
-    def big_seed(cls, path: FilePath) -> "SourceFile":
+    def big_seed(cls, path: FilePath) -> 'SourceFile':
         """Parse seeds over the size limit with just the path"""
         self = cls(path=path, checksum=FileHash.path(path.original_file_path))
-        self.contents = ""
+        self.contents = ''
         return self
 
+    def add_node(self, value):
+        if value not in self.nodes:
+            self.nodes.append(value)
+
+    # TODO: do this a different way. This remote file kludge isn't going
+    # to work long term
     @classmethod
-    def remote(cls, contents: str) -> "SourceFile":
-        self = cls(path=RemoteFile(), checksum=FileHash.empty())
-        self.contents = contents
+    def remote(cls, contents: str, project_name: str) -> 'SourceFile':
+        self = cls(
+            path=RemoteFile(),
+            checksum=FileHash.from_contents(contents),
+            project_name=project_name,
+            contents=contents,
+        )
         return self
+
+
+@dataclass
+class SchemaSourceFile(BaseSourceFile):
+    dfy: Dict[str, Any] = field(default_factory=dict)
+    # these are in the manifest.nodes dictionary
+    tests: Dict[str, Any] = field(default_factory=dict)
+    sources: List[str] = field(default_factory=list)
+    exposures: List[str] = field(default_factory=list)
+    # node patches contain models, seeds, snapshots, analyses
+    ndp: List[str] = field(default_factory=list)
+    # any macro patches in this file by macro unique_id.
+    mcp: Dict[str, str] = field(default_factory=dict)
+    # any source patches in this file. The entries are package, name pairs
+    # Patches are only against external sources. Sources can be
+    # created too, but those are in 'sources'
+    sop: List[SourceKey] = field(default_factory=list)
+    pp_dict: Optional[Dict[str, Any]] = None
+    pp_test_index: Optional[Dict[str, Any]] = None
+
+    @property
+    def dict_from_yaml(self):
+        return self.dfy
+
+    @property
+    def node_patches(self):
+        return self.ndp
+
+    @property
+    def macro_patches(self):
+        return self.mcp
+
+    @property
+    def source_patches(self):
+        return self.sop
+
+    def __post_serialize__(self, dct):
+        dct = super().__post_serialize__(dct)
+        # Remove partial parsing specific data
+        for key in ('pp_files', 'pp_test_index', 'pp_dict'):
+            if key in dct:
+                del dct[key]
+        return dct
+
+    def append_patch(self, yaml_key, unique_id):
+        self.node_patches.append(unique_id)
+
+    def add_test(self, node_unique_id, test_from):
+        name = test_from['name']
+        key = test_from['key']
+        if key not in self.tests:
+            self.tests[key] = {}
+        if name not in self.tests[key]:
+            self.tests[key][name] = []
+        self.tests[key][name].append(node_unique_id)
+
+    def remove_tests(self, yaml_key, name):
+        if yaml_key in self.tests:
+            if name in self.tests[yaml_key]:
+                del self.tests[yaml_key][name]
+
+    def get_tests(self, yaml_key, name):
+        if yaml_key in self.tests:
+            if name in self.tests[yaml_key]:
+                return self.tests[yaml_key][name]
+        return []
+
+    def get_key_and_name_for_test(self, test_unique_id):
+        yaml_key = None
+        block_name = None
+        for key in self.tests.keys():
+            for name in self.tests[key]:
+                for unique_id in self.tests[key][name]:
+                    if unique_id == test_unique_id:
+                        yaml_key = key
+                        block_name = name
+                        break
+        return (yaml_key, block_name)
+
+    def get_all_test_ids(self):
+        test_ids = []
+        for key in self.tests.keys():
+            for name in self.tests[key]:
+                test_ids.extend(self.tests[key][name])
+        return test_ids
+
+
+AnySourceFile = Union[SchemaSourceFile, SourceFile]

core/dbt/contracts/graph/compiled.py

@@ -43,6 +43,7 @@ class CompiledNode(ParsedNode, CompiledNodeMixin):
     extra_ctes_injected: bool = False
     extra_ctes: List[InjectedCTE] = field(default_factory=list)
     relation_name: Optional[str] = None
+    _pre_injected_sql: Optional[str] = None
 
     def set_cte(self, cte_id: str, sql: str):
         """This is the equivalent of what self.extra_ctes[cte_id] = sql would
@@ -55,32 +56,40 @@ class CompiledNode(ParsedNode, CompiledNodeMixin):
         else:
             self.extra_ctes.append(InjectedCTE(id=cte_id, sql=sql))
 
+    def __post_serialize__(self, dct):
+        dct = super().__post_serialize__(dct)
+        if '_pre_injected_sql' in dct:
+            del dct['_pre_injected_sql']
+        return dct
+
 
 @dataclass
 class CompiledAnalysisNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Analysis]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Analysis]})
 
 
 @dataclass
 class CompiledHookNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
+    resource_type: NodeType = field(
+        metadata={'restrict': [NodeType.Operation]}
+    )
     index: Optional[int] = None
 
 
 @dataclass
 class CompiledModelNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Model]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Model]})
 
 
 @dataclass
 class CompiledRPCNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.RPCCall]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.RPCCall]})
 
 
 @dataclass
 class CompiledSeedNode(CompiledNode):
     # keep this in sync with ParsedSeedNode!
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Seed]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Seed]})
     config: SeedConfig = field(default_factory=SeedConfig)
 
     @property
@@ -94,35 +103,35 @@ class CompiledSeedNode(CompiledNode):
 
 @dataclass
 class CompiledSnapshotNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
 
 
 @dataclass
 class CompiledDataTestNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
-    config: TestConfig = field(default_factory=TestConfig)
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
+    # Was not able to make mypy happy and keep the code working. We need to
+    # refactor the various configs.
+    config: TestConfig = field(default_factory=TestConfig)  # type:ignore
 
 
 @dataclass
 class CompiledSchemaTestNode(CompiledNode, HasTestMetadata):
     # keep this in sync with ParsedSchemaTestNode!
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
     column_name: Optional[str] = None
-    config: TestConfig = field(default_factory=TestConfig)
-
-    def same_config(self, other) -> bool:
-        return self.unrendered_config.get("severity") == other.unrendered_config.get(
-            "severity"
-        )
-
-    def same_column_name(self, other) -> bool:
-        return self.column_name == other.column_name
+    # Was not able to make mypy happy and keep the code working. We need to
+    # refactor the various configs.
+    config: TestConfig = field(default_factory=TestConfig)  # type:ignore
 
     def same_contents(self, other) -> bool:
         if other is None:
             return False
 
-        return self.same_config(other) and self.same_fqn(other) and True
+        return (
+            self.same_config(other) and
+            self.same_fqn(other) and
+            True
+        )
 
 
 CompiledTestNode = Union[CompiledDataTestNode, CompiledSchemaTestNode]
@@ -168,7 +177,8 @@ def parsed_instance_for(compiled: CompiledNode) -> ParsedResource:
     cls = PARSED_TYPES.get(type(compiled))
     if cls is None:
         # how???
-        raise ValueError("invalid resource_type: {}".format(compiled.resource_type))
+        raise ValueError('invalid resource_type: {}'
+                         .format(compiled.resource_type))
 
     return cls.from_dict(compiled.to_dict(omit_none=True))
 

core/dbt/contracts/graph/model_config.py

@@ -2,29 +2,19 @@ from dataclasses import field, Field, dataclass
 from enum import Enum
 from itertools import chain
 from typing import (
-    Any,
-    List,
-    Optional,
-    Dict,
-    MutableMapping,
-    Union,
-    Type,
-    TypeVar,
-    Callable,
+    Any, List, Optional, Dict, Union, Type, TypeVar, Callable
 )
 from dbt.dataclass_schema import (
-    dbtClassMixin,
-    ValidationError,
-    register_pattern,
+    dbtClassMixin, ValidationError, register_pattern,
 )
 from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed
-from dbt.exceptions import CompilationException, InternalException
+from dbt.exceptions import InternalException, CompilationException
 from dbt.contracts.util import Replaceable, list_str
 from dbt import hooks
 from dbt.node_types import NodeType
 
 
-M = TypeVar("M", bound="Metadata")
+M = TypeVar('M', bound='Metadata')
 
 
 def _get_meta_value(cls: Type[M], fld: Field, key: str, default: Any) -> M:
@@ -39,7 +29,9 @@ def _get_meta_value(cls: Type[M], fld: Field, key: str, default: Any) -> M:
     try:
         return cls(value)
     except ValueError as exc:
-        raise InternalException(f"Invalid {cls} value: {value}") from exc
+        raise InternalException(
+            f'Invalid {cls} value: {value}'
+        ) from exc
 
 
 def _set_meta_value(
@@ -61,17 +53,19 @@ class Metadata(Enum):
 
         return _get_meta_value(cls, fld, key, default)
 
-    def meta(self, existing: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
+    def meta(
+        self, existing: Optional[Dict[str, Any]] = None
+    ) -> Dict[str, Any]:
         key = self.metadata_key()
         return _set_meta_value(self, key, existing)
 
     @classmethod
-    def default_field(cls) -> "Metadata":
-        raise NotImplementedError("Not implemented")
+    def default_field(cls) -> 'Metadata':
+        raise NotImplementedError('Not implemented')
 
     @classmethod
     def metadata_key(cls) -> str:
-        raise NotImplementedError("Not implemented")
+        raise NotImplementedError('Not implemented')
 
 
 class MergeBehavior(Metadata):
@@ -80,12 +74,12 @@ class MergeBehavior(Metadata):
     Clobber = 3
 
     @classmethod
-    def default_field(cls) -> "MergeBehavior":
+    def default_field(cls) -> 'MergeBehavior':
         return cls.Clobber
 
     @classmethod
     def metadata_key(cls) -> str:
-        return "merge"
+        return 'merge'
 
 
 class ShowBehavior(Metadata):
@@ -93,12 +87,12 @@ class ShowBehavior(Metadata):
     Hide = 2
 
     @classmethod
-    def default_field(cls) -> "ShowBehavior":
+    def default_field(cls) -> 'ShowBehavior':
         return cls.Show
 
     @classmethod
     def metadata_key(cls) -> str:
-        return "show_hide"
+        return 'show_hide'
 
     @classmethod
     def should_show(cls, fld: Field) -> bool:
@@ -110,12 +104,12 @@ class CompareBehavior(Metadata):
     Exclude = 2
 
     @classmethod
-    def default_field(cls) -> "CompareBehavior":
+    def default_field(cls) -> 'CompareBehavior':
         return cls.Include
 
     @classmethod
     def metadata_key(cls) -> str:
-        return "compare"
+        return 'compare'
 
     @classmethod
     def should_include(cls, fld: Field) -> bool:
@@ -147,30 +141,32 @@ def _merge_field_value(
         return _listify(self_value) + _listify(other_value)
     elif merge_behavior == MergeBehavior.Update:
         if not isinstance(self_value, dict):
-            raise InternalException(f"expected dict, got {self_value}")
+            raise InternalException(f'expected dict, got {self_value}')
         if not isinstance(other_value, dict):
-            raise InternalException(f"expected dict, got {other_value}")
+            raise InternalException(f'expected dict, got {other_value}')
         value = self_value.copy()
         value.update(other_value)
         return value
     else:
-        raise InternalException(f"Got an invalid merge_behavior: {merge_behavior}")
+        raise InternalException(
+            f'Got an invalid merge_behavior: {merge_behavior}'
+        )
 
 
 def insensitive_patterns(*patterns: str):
     lowercased = []
     for pattern in patterns:
         lowercased.append(
-            "".join("[{}{}]".format(s.upper(), s.lower()) for s in pattern)
+            ''.join('[{}{}]'.format(s.upper(), s.lower()) for s in pattern)
         )
-    return "^({})$".format("|".join(lowercased))
+    return '^({})$'.format('|'.join(lowercased))
 
 
 class Severity(str):
     pass
 
 
-register_pattern(Severity, insensitive_patterns("warn", "error"))
+register_pattern(Severity, insensitive_patterns('warn', 'error'))
 
 
 @dataclass
@@ -180,22 +176,28 @@ class Hook(dbtClassMixin, Replaceable):
     index: Optional[int] = None
 
 
-T = TypeVar("T", bound="BaseConfig")
+T = TypeVar('T', bound='BaseConfig')
 
 
 @dataclass
-class BaseConfig(AdditionalPropertiesAllowed, Replaceable, MutableMapping[str, Any]):
-    # Implement MutableMapping so this config will behave as some macros expect
-    # during parsing (notably, syntax like `{{ node.config['schema'] }}`)
+class BaseConfig(
+    AdditionalPropertiesAllowed, Replaceable
+):
+
+    # enable syntax like: config['key']
     def __getitem__(self, key):
-        """Handle parse-time use of `config` as a dictionary, making the extra
-        values available during parsing.
-        """
+        return self.get(key)
+
+    # like doing 'get' on a dictionary
+    def get(self, key, default=None):
         if hasattr(self, key):
             return getattr(self, key)
-        else:
+        elif key in self._extra:
             return self._extra[key]
+        else:
+            return default
 
+    # enable syntax like: config['key'] = value
     def __setitem__(self, key, value):
         if hasattr(self, key):
             setattr(self, key, value)
@@ -205,7 +207,8 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable, MutableMapping[str, A
     def __delitem__(self, key):
         if hasattr(self, key):
             msg = (
-                'Error, tried to delete config key "{}": Cannot delete ' "built-in keys"
+                'Error, tried to delete config key "{}": Cannot delete '
+                'built-in keys'
             ).format(key)
             raise CompilationException(msg)
         else:
@@ -245,7 +248,9 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable, MutableMapping[str, A
             return unrendered[key] == other[key]
 
     @classmethod
-    def same_contents(cls, unrendered: Dict[str, Any], other: Dict[str, Any]) -> bool:
+    def same_contents(
+        cls, unrendered: Dict[str, Any], other: Dict[str, Any]
+    ) -> bool:
         """This is like __eq__, except it ignores some fields."""
         seen = set()
         for fld, target_name in cls._get_fields():
@@ -262,8 +267,17 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable, MutableMapping[str, A
                     return False
         return True
 
+    # This is used in 'add_config_call' to created the combined config_call_dict.
+    # 'meta' moved here from node
+    mergebehavior = {
+        "append": ['pre-hook', 'pre_hook', 'post-hook', 'post_hook', 'tags'],
+        "update": ['quoting', 'column_types', 'meta'],
+    }
+
     @classmethod
-    def _extract_dict(cls, src: Dict[str, Any], data: Dict[str, Any]) -> Dict[str, Any]:
+    def _merge_dicts(
+        cls, src: Dict[str, Any], data: Dict[str, Any]
+    ) -> Dict[str, Any]:
         """Find all the items in data that match a target_field on this class,
         and merge them with the data found in `src` for target_field, using the
         field's specified merge behavior. Matching items will be removed from
@@ -303,15 +317,14 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable, MutableMapping[str, A
         """
         # sadly, this is a circular import
         from dbt.adapters.factory import get_config_class_by_name
-
         dct = self.to_dict(omit_none=False)
 
         adapter_config_cls = get_config_class_by_name(adapter_type)
 
-        self_merged = self._extract_dict(dct, data)
+        self_merged = self._merge_dicts(dct, data)
         dct.update(self_merged)
 
-        adapter_merged = adapter_config_cls._extract_dict(dct, data)
+        adapter_merged = adapter_config_cls._merge_dicts(dct, data)
         dct.update(adapter_merged)
 
         # any remaining fields must be "clobber"
@@ -343,33 +356,8 @@ class SourceConfig(BaseConfig):
 
 
 @dataclass
-class NodeConfig(BaseConfig):
+class NodeAndTestConfig(BaseConfig):
     enabled: bool = True
-    materialized: str = "view"
-    persist_docs: Dict[str, Any] = field(default_factory=dict)
-    post_hook: List[Hook] = field(
-        default_factory=list,
-        metadata=MergeBehavior.Append.meta(),
-    )
-    pre_hook: List[Hook] = field(
-        default_factory=list,
-        metadata=MergeBehavior.Append.meta(),
-    )
-    # this only applies for config v1, so it doesn't participate in comparison
-    vars: Dict[str, Any] = field(
-        default_factory=dict,
-        metadata=metas(CompareBehavior.Exclude, MergeBehavior.Update),
-    )
-    quoting: Dict[str, Any] = field(
-        default_factory=dict,
-        metadata=MergeBehavior.Update.meta(),
-    )
-    # This is actually only used by seeds. Should it be available to others?
-    # That would be a breaking change!
-    column_types: Dict[str, Any] = field(
-        default_factory=dict,
-        metadata=MergeBehavior.Update.meta(),
-    )
     # these fields are included in serialized output, but are not part of
     # config comparison (they are part of database_representation)
     alias: Optional[str] = field(
@@ -386,16 +374,47 @@ class NodeConfig(BaseConfig):
     )
     tags: Union[List[str], str] = field(
         default_factory=list_str,
-        metadata=metas(
-            ShowBehavior.Hide, MergeBehavior.Append, CompareBehavior.Exclude
-        ),
+        metadata=metas(ShowBehavior.Hide,
+                       MergeBehavior.Append,
+                       CompareBehavior.Exclude),
+    )
+    meta: Dict[str, Any] = field(
+        default_factory=dict,
+        metadata=MergeBehavior.Update.meta(),
+    )
+
+
+@dataclass
+class NodeConfig(NodeAndTestConfig):
+    # Note: if any new fields are added with MergeBehavior, also update the
+    # 'mergebehavior' dictionary
+    materialized: str = 'view'
+    persist_docs: Dict[str, Any] = field(default_factory=dict)
+    post_hook: List[Hook] = field(
+        default_factory=list,
+        metadata=MergeBehavior.Append.meta(),
+    )
+    pre_hook: List[Hook] = field(
+        default_factory=list,
+        metadata=MergeBehavior.Append.meta(),
+    )
+    quoting: Dict[str, Any] = field(
+        default_factory=dict,
+        metadata=MergeBehavior.Update.meta(),
+    )
+    # This is actually only used by seeds. Should it be available to others?
+    # That would be a breaking change!
+    column_types: Dict[str, Any] = field(
+        default_factory=dict,
+        metadata=MergeBehavior.Update.meta(),
     )
     full_refresh: Optional[bool] = None
+    on_schema_change: Optional[str] = 'ignore'
 
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        field_map = {"post-hook": "post_hook", "pre-hook": "pre_hook"}
+        field_map = {'post-hook': 'post_hook', 'pre-hook': 'pre_hook'}
         # create a new dict because otherwise it gets overwritten in
         # tests
         new_dict = {}
@@ -413,7 +432,7 @@ class NodeConfig(BaseConfig):
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        field_map = {"post_hook": "post-hook", "pre_hook": "pre-hook"}
+        field_map = {'post_hook': 'post-hook', 'pre_hook': 'pre-hook'}
         for field_name in field_map:
             if field_name in dct:
                 dct[field_map[field_name]] = dct.pop(field_name)
@@ -422,24 +441,59 @@ class NodeConfig(BaseConfig):
     # this is still used by jsonschema validation
     @classmethod
     def field_mapping(cls):
-        return {"post_hook": "post-hook", "pre_hook": "pre-hook"}
+        return {'post_hook': 'post-hook', 'pre_hook': 'pre-hook'}
 
 
 @dataclass
 class SeedConfig(NodeConfig):
-    materialized: str = "seed"
+    materialized: str = 'seed'
     quote_columns: Optional[bool] = None
 
 
 @dataclass
-class TestConfig(NodeConfig):
-    materialized: str = "test"
-    severity: Severity = Severity("ERROR")
+class TestConfig(NodeAndTestConfig):
+    # this is repeated because of a different default
+    schema: Optional[str] = field(
+        default='dbt_test__audit',
+        metadata=CompareBehavior.Exclude.meta(),
+    )
+    materialized: str = 'test'
+    severity: Severity = Severity('ERROR')
+    store_failures: Optional[bool] = None
+    where: Optional[str] = None
+    limit: Optional[int] = None
+    fail_calc: str = 'count(*)'
+    warn_if: str = '!= 0'
+    error_if: str = '!= 0'
+
+    @classmethod
+    def same_contents(
+        cls, unrendered: Dict[str, Any], other: Dict[str, Any]
+    ) -> bool:
+        """This is like __eq__, except it explicitly checks certain fields."""
+        modifiers = [
+            'severity',
+            'where',
+            'limit',
+            'fail_calc',
+            'warn_if',
+            'error_if',
+            'store_failures'
+        ]
+
+        seen = set()
+        for _, target_name in cls._get_fields():
+            key = target_name
+            seen.add(key)
+            if key in modifiers:
+                if not cls.compare_key(unrendered, other, key):
+                    return False
+        return True
 
 
 @dataclass
 class EmptySnapshotConfig(NodeConfig):
-    materialized: str = "snapshot"
+    materialized: str = 'snapshot'
 
 
 @dataclass
@@ -454,28 +508,30 @@ class SnapshotConfig(EmptySnapshotConfig):
     @classmethod
     def validate(cls, data):
         super().validate(data)
-        if data.get("strategy") == "check":
-            if not data.get("check_cols"):
+        if not data.get('strategy') or not data.get('unique_key') or not \
+                data.get('target_schema'):
+            raise ValidationError(
+                "Snapshots must be configured with a 'strategy', 'unique_key', "
+                "and 'target_schema'.")
+        if data.get('strategy') == 'check':
+            if not data.get('check_cols'):
                 raise ValidationError(
                     "A snapshot configured with the check strategy must "
-                    "specify a check_cols configuration."
-                )
-            if isinstance(data["check_cols"], str) and data["check_cols"] != "all":
+                    "specify a check_cols configuration.")
+            if (isinstance(data['check_cols'], str) and
+                    data['check_cols'] != 'all'):
                 raise ValidationError(
                     f"Invalid value for 'check_cols': {data['check_cols']}. "
-                    "Expected 'all' or a list of strings."
-                )
+                    "Expected 'all' or a list of strings.")
 
-        elif data.get("strategy") == "timestamp":
-            if not data.get("updated_at"):
+        elif data.get('strategy') == 'timestamp':
+            if not data.get('updated_at'):
                 raise ValidationError(
                     "A snapshot configured with the timestamp strategy "
-                    "must specify an updated_at configuration."
-                )
-            if data.get("check_cols"):
+                    "must specify an updated_at configuration.")
+            if data.get('check_cols'):
                 raise ValidationError(
-                    "A 'timestamp' snapshot should not have 'check_cols'"
-                )
+                    "A 'timestamp' snapshot should not have 'check_cols'")
         # If the strategy is not 'check' or 'timestamp' it's a custom strategy,
         # formerly supported with GenericSnapshotConfig
 
@@ -497,7 +553,9 @@ RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = {
 # base resource types are like resource types, except nothing has mandatory
 # configs.
 BASE_RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = RESOURCE_TYPES.copy()
-BASE_RESOURCE_TYPES.update({NodeType.Snapshot: EmptySnapshotConfig})
+BASE_RESOURCE_TYPES.update({
+    NodeType.Snapshot: EmptySnapshotConfig
+})
 
 
 def get_config_for(resource_type: NodeType, base=False) -> Type[BaseConfig]:

core/dbt/contracts/graph/parsed.py

@@ -1,5 +1,7 @@
 import os
+import time
 from dataclasses import dataclass, field
+from mashumaro.types import SerializableType
 from pathlib import Path
 from typing import (
     Optional,
@@ -13,27 +15,18 @@ from typing import (
     TypeVar,
 )
 
-from dbt.dataclass_schema import dbtClassMixin, ExtensibleDbtClassMixin
+from dbt.dataclass_schema import (
+    dbtClassMixin, ExtensibleDbtClassMixin
+)
 
 from dbt.clients.system import write_file
 from dbt.contracts.files import FileHash, MAXIMUM_SEED_SIZE_NAME
 from dbt.contracts.graph.unparsed import (
-    UnparsedNode,
-    UnparsedDocumentation,
-    Quoting,
-    Docs,
-    UnparsedBaseNode,
-    FreshnessThreshold,
-    ExternalTable,
-    HasYamlMetadata,
-    MacroArgument,
-    UnparsedSourceDefinition,
-    UnparsedSourceTableDefinition,
-    UnparsedColumn,
-    TestDef,
-    ExposureOwner,
-    ExposureType,
-    MaturityType,
+    UnparsedNode, UnparsedDocumentation, Quoting, Docs,
+    UnparsedBaseNode, FreshnessThreshold, ExternalTable,
+    HasYamlMetadata, MacroArgument, UnparsedSourceDefinition,
+    UnparsedSourceTableDefinition, UnparsedColumn, TestDef,
+    ExposureOwner, ExposureType, MaturityType
 )
 from dbt.contracts.util import Replaceable, AdditionalPropertiesMixin
 from dbt.exceptions import warn_or_error
@@ -53,9 +46,13 @@ from .model_config import (
 
 
 @dataclass
-class ColumnInfo(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable):
+class ColumnInfo(
+    AdditionalPropertiesMixin,
+    ExtensibleDbtClassMixin,
+    Replaceable
+):
     name: str
-    description: str = ""
+    description: str = ''
     meta: Dict[str, Any] = field(default_factory=dict)
     data_type: Optional[str] = None
     quote: Optional[bool] = None
@@ -67,7 +64,7 @@ class ColumnInfo(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable
 class HasFqn(dbtClassMixin, Replaceable):
     fqn: List[str]
 
-    def same_fqn(self, other: "HasFqn") -> bool:
+    def same_fqn(self, other: 'HasFqn') -> bool:
         return self.fqn == other.fqn
 
 
@@ -106,8 +103,8 @@ class HasRelationMetadata(dbtClassMixin, Replaceable):
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        if "database" not in data:
-            data["database"] = None
+        if 'database' not in data:
+            data['database'] = None
         return data
 
 
@@ -120,9 +117,24 @@ class ParsedNodeMixins(dbtClassMixin):
     def is_refable(self):
         return self.resource_type in NodeType.refable()
 
+    @property
+    def should_store_failures(self):
+        return self.resource_type == NodeType.Test and (
+            self.config.store_failures if self.config.store_failures is not None
+            else flags.STORE_FAILURES
+        )
+
+    # will this node map to an object in the database?
+    @property
+    def is_relational(self):
+        return (
+            self.resource_type in NodeType.refable() or
+            self.should_store_failures
+        )
+
     @property
     def is_ephemeral(self):
-        return self.config.materialized == "ephemeral"
+        return self.config.materialized == 'ephemeral'
 
     @property
     def is_ephemeral_model(self):
@@ -132,11 +144,14 @@ class ParsedNodeMixins(dbtClassMixin):
     def depends_on_nodes(self):
         return self.depends_on.nodes
 
-    def patch(self, patch: "ParsedNodePatch"):
+    def patch(self, patch: 'ParsedNodePatch'):
         """Given a ParsedNodePatch, add the new information to the node."""
         # explicitly pick out the parts to update so we don't inadvertently
         # step on the model name or anything
-        self.patch_path: Optional[str] = patch.original_file_path
+        # Note: config should already be updated
+        self.patch_path: Optional[str] = patch.file_id
+        # update created_at so process_docs will run in partial parsing
+        self.created_at = int(time.time())
         self.description = patch.description
         self.columns = patch.columns
         self.meta = patch.meta
@@ -152,13 +167,14 @@ class ParsedNodeMixins(dbtClassMixin):
     def get_materialization(self):
         return self.config.materialized
 
-    def local_vars(self):
-        return self.config.vars
-
 
 @dataclass
 class ParsedNodeMandatory(
-    UnparsedNode, HasUniqueID, HasFqn, HasRelationMetadata, Replaceable
+    UnparsedNode,
+    HasUniqueID,
+    HasFqn,
+    HasRelationMetadata,
+    Replaceable
 ):
     alias: str
     checksum: FileHash
@@ -175,38 +191,87 @@ class ParsedNodeDefaults(ParsedNodeMandatory):
     refs: List[List[str]] = field(default_factory=list)
     sources: List[List[Any]] = field(default_factory=list)
     depends_on: DependsOn = field(default_factory=DependsOn)
-    description: str = field(default="")
+    description: str = field(default='')
     columns: Dict[str, ColumnInfo] = field(default_factory=dict)
     meta: Dict[str, Any] = field(default_factory=dict)
     docs: Docs = field(default_factory=Docs)
     patch_path: Optional[str] = None
+    compiled_path: Optional[str] = None
     build_path: Optional[str] = None
     deferred: bool = False
     unrendered_config: Dict[str, Any] = field(default_factory=dict)
+    created_at: int = field(default_factory=lambda: int(time.time()))
+    config_call_dict: Dict[str, Any] = field(default_factory=dict)
 
     def write_node(self, target_path: str, subdirectory: str, payload: str):
-        if os.path.basename(self.path) == os.path.basename(self.original_file_path):
+        if (os.path.basename(self.path) ==
+                os.path.basename(self.original_file_path)):
             # One-to-one relationship of nodes to files.
             path = self.original_file_path
         else:
             #  Many-to-one relationship of nodes to files.
             path = os.path.join(self.original_file_path, self.path)
-        full_path = os.path.join(target_path, subdirectory, self.package_name, path)
+        full_path = os.path.join(
+            target_path, subdirectory, self.package_name, path
+        )
 
         write_file(full_path, payload)
         return full_path
 
 
-T = TypeVar("T", bound="ParsedNode")
+T = TypeVar('T', bound='ParsedNode')
 
 
 @dataclass
-class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins):
+class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
+
+    def _serialize(self):
+        return self.to_dict()
+
+    def __post_serialize__(self, dct):
+        if 'config_call_dict' in dct:
+            del dct['config_call_dict']
+        return dct
+
+    @classmethod
+    def _deserialize(cls, dct: Dict[str, int]):
+        # The serialized ParsedNodes do not differ from each other
+        # in fields that would allow 'from_dict' to distinguis
+        # between them.
+        resource_type = dct['resource_type']
+        if resource_type == 'model':
+            return ParsedModelNode.from_dict(dct)
+        elif resource_type == 'analysis':
+            return ParsedAnalysisNode.from_dict(dct)
+        elif resource_type == 'seed':
+            return ParsedSeedNode.from_dict(dct)
+        elif resource_type == 'rpc':
+            return ParsedRPCNode.from_dict(dct)
+        elif resource_type == 'test':
+            if 'test_metadata' in dct:
+                return ParsedSchemaTestNode.from_dict(dct)
+            else:
+                return ParsedDataTestNode.from_dict(dct)
+        elif resource_type == 'operation':
+            return ParsedHookNode.from_dict(dct)
+        elif resource_type == 'seed':
+            return ParsedSeedNode.from_dict(dct)
+        elif resource_type == 'snapshot':
+            return ParsedSnapshotNode.from_dict(dct)
+        else:
+            return cls.from_dict(dct)
+
     def _persist_column_docs(self) -> bool:
-        return bool(self.config.persist_docs.get("columns"))
+        if hasattr(self.config, 'persist_docs'):
+            assert isinstance(self.config, NodeConfig)
+            return bool(self.config.persist_docs.get('columns'))
+        return False
 
     def _persist_relation_docs(self) -> bool:
-        return bool(self.config.persist_docs.get("relation"))
+        if hasattr(self.config, 'persist_docs'):
+            assert isinstance(self.config, NodeConfig)
+            return bool(self.config.persist_docs.get('relation'))
+        return False
 
     def same_body(self: T, other: T) -> bool:
         return self.raw_sql == other.raw_sql
@@ -221,7 +286,9 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins):
 
         if self._persist_column_docs():
             # assert other._persist_column_docs()
-            column_descriptions = {k: v.description for k, v in self.columns.items()}
+            column_descriptions = {
+                k: v.description for k, v in self.columns.items()
+            }
             other_column_descriptions = {
                 k: v.description for k, v in other.columns.items()
             }
@@ -235,7 +302,7 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins):
         # compares the configured value, rather than the ultimate value (so
         # generate_*_name and unset values derived from the target are
         # ignored)
-        keys = ("database", "schema", "alias")
+        keys = ('database', 'schema', 'alias')
         for key in keys:
             mine = self.unrendered_config.get(key)
             others = other.unrendered_config.get(key)
@@ -254,34 +321,36 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins):
             return False
 
         return (
-            self.same_body(old)
-            and self.same_config(old)
-            and self.same_persisted_description(old)
-            and self.same_fqn(old)
-            and self.same_database_representation(old)
-            and True
+            self.same_body(old) and
+            self.same_config(old) and
+            self.same_persisted_description(old) and
+            self.same_fqn(old) and
+            self.same_database_representation(old) and
+            True
         )
 
 
 @dataclass
 class ParsedAnalysisNode(ParsedNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Analysis]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Analysis]})
 
 
 @dataclass
 class ParsedHookNode(ParsedNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
+    resource_type: NodeType = field(
+        metadata={'restrict': [NodeType.Operation]}
+    )
     index: Optional[int] = None
 
 
 @dataclass
 class ParsedModelNode(ParsedNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Model]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Model]})
 
 
 @dataclass
 class ParsedRPCNode(ParsedNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.RPCCall]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.RPCCall]})
 
 
 def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
@@ -291,31 +360,31 @@ def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
     # if the current checksum is a path, we want to log a warning.
     result = first.checksum == second.checksum
 
-    if first.checksum.name == "path":
+    if first.checksum.name == 'path':
         msg: str
-        if second.checksum.name != "path":
+        if second.checksum.name != 'path':
             msg = (
-                f"Found a seed ({first.package_name}.{first.name}) "
-                f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was "
-                f"<={MAXIMUM_SEED_SIZE_NAME}, so it has changed"
+                f'Found a seed ({first.package_name}.{first.name}) '
+                f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was '
+                f'<={MAXIMUM_SEED_SIZE_NAME}, so it has changed'
             )
         elif result:
             msg = (
-                f"Found a seed ({first.package_name}.{first.name}) "
-                f">{MAXIMUM_SEED_SIZE_NAME} in size at the same path, dbt "
-                f"cannot tell if it has changed: assuming they are the same"
+                f'Found a seed ({first.package_name}.{first.name}) '
+                f'>{MAXIMUM_SEED_SIZE_NAME} in size at the same path, dbt '
+                f'cannot tell if it has changed: assuming they are the same'
             )
         elif not result:
             msg = (
-                f"Found a seed ({first.package_name}.{first.name}) "
-                f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was in "
-                f"a different location, assuming it has changed"
+                f'Found a seed ({first.package_name}.{first.name}) '
+                f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was in '
+                f'a different location, assuming it has changed'
             )
         else:
             msg = (
-                f"Found a seed ({first.package_name}.{first.name}) "
-                f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file had a "
-                f"checksum type of {second.checksum.name}, so it has changed"
+                f'Found a seed ({first.package_name}.{first.name}) '
+                f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file had a '
+                f'checksum type of {second.checksum.name}, so it has changed'
             )
         warn_or_error(msg, node=first)
 
@@ -325,7 +394,7 @@ def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
 @dataclass
 class ParsedSeedNode(ParsedNode):
     # keep this in sync with CompiledSeedNode!
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Seed]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Seed]})
     config: SeedConfig = field(default_factory=SeedConfig)
 
     @property
@@ -351,30 +420,30 @@ class HasTestMetadata(dbtClassMixin):
 
 @dataclass
 class ParsedDataTestNode(ParsedNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
-    config: TestConfig = field(default_factory=TestConfig)
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
+    # Was not able to make mypy happy and keep the code working. We need to
+    # refactor the various configs.
+    config: TestConfig = field(default_factory=TestConfig)  # type: ignore
 
 
 @dataclass
 class ParsedSchemaTestNode(ParsedNode, HasTestMetadata):
     # keep this in sync with CompiledSchemaTestNode!
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
     column_name: Optional[str] = None
-    config: TestConfig = field(default_factory=TestConfig)
-
-    def same_config(self, other) -> bool:
-        return self.unrendered_config.get("severity") == other.unrendered_config.get(
-            "severity"
-        )
-
-    def same_column_name(self, other) -> bool:
-        return self.column_name == other.column_name
+    # Was not able to make mypy happy and keep the code working. We need to
+    # refactor the various configs.
+    config: TestConfig = field(default_factory=TestConfig)  # type: ignore
 
     def same_contents(self, other) -> bool:
         if other is None:
             return False
 
-        return self.same_config(other) and self.same_fqn(other) and True
+        return (
+            self.same_config(other) and
+            self.same_fqn(other) and
+            True
+        )
 
 
 @dataclass
@@ -385,13 +454,13 @@ class IntermediateSnapshotNode(ParsedNode):
     # defined in config blocks. To fix that, we have an intermediate type that
     # uses a regular node config, which the snapshot parser will then convert
     # into a full ParsedSnapshotNode after rendering.
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
     config: EmptySnapshotConfig = field(default_factory=EmptySnapshotConfig)
 
 
 @dataclass
 class ParsedSnapshotNode(ParsedNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
     config: SnapshotConfig
 
 
@@ -401,6 +470,7 @@ class ParsedPatch(HasYamlMetadata, Replaceable):
     description: str
     meta: Dict[str, Any]
     docs: Docs
+    config: Dict[str, Any]
 
 
 # The parsed node update is only the 'patch', not the test. The test became a
@@ -420,23 +490,22 @@ class ParsedMacroPatch(ParsedPatch):
 class ParsedMacro(UnparsedBaseNode, HasUniqueID):
     name: str
     macro_sql: str
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Macro]})
     # TODO: can macros even have tags?
     tags: List[str] = field(default_factory=list)
     # TODO: is this ever populated?
     depends_on: MacroDependsOn = field(default_factory=MacroDependsOn)
-    description: str = ""
+    description: str = ''
     meta: Dict[str, Any] = field(default_factory=dict)
     docs: Docs = field(default_factory=Docs)
     patch_path: Optional[str] = None
     arguments: List[MacroArgument] = field(default_factory=list)
-
-    def local_vars(self):
-        return {}
+    created_at: int = field(default_factory=lambda: int(time.time()))
 
     def patch(self, patch: ParsedMacroPatch):
-        self.patch_path: Optional[str] = patch.original_file_path
+        self.patch_path: Optional[str] = patch.file_id
         self.description = patch.description
+        self.created_at = int(time.time())
         self.meta = patch.meta
         self.docs = patch.docs
         self.arguments = patch.arguments
@@ -446,7 +515,7 @@ class ParsedMacro(UnparsedBaseNode, HasUniqueID):
             dct = self.to_dict(omit_none=False)
             self.validate(dct)
 
-    def same_contents(self, other: Optional["ParsedMacro"]) -> bool:
+    def same_contents(self, other: Optional['ParsedMacro']) -> bool:
         if other is None:
             return False
         # the only thing that makes one macro different from another with the
@@ -463,7 +532,7 @@ class ParsedDocumentation(UnparsedDocumentation, HasUniqueID):
     def search_name(self):
         return self.name
 
-    def same_contents(self, other: Optional["ParsedDocumentation"]) -> bool:
+    def same_contents(self, other: Optional['ParsedDocumentation']) -> bool:
         if other is None:
             return False
         # the only thing that makes one doc different from another with the
@@ -482,11 +551,11 @@ def normalize_test(testdef: TestDef) -> Dict[str, Any]:
 class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
     source: UnparsedSourceDefinition
     table: UnparsedSourceTableDefinition
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Source]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Source]})
     patch_path: Optional[Path] = None
 
     def get_full_source_name(self):
-        return f"{self.source.name}_{self.table.name}"
+        return f'{self.source.name}_{self.table.name}'
 
     def get_source_representation(self):
         return f'source("{self.source.name}", "{self.table.name}")'
@@ -511,7 +580,9 @@ class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
         else:
             return self.table.columns
 
-    def get_tests(self) -> Iterator[Tuple[Dict[str, Any], Optional[UnparsedColumn]]]:
+    def get_tests(
+        self
+    ) -> Iterator[Tuple[Dict[str, Any], Optional[UnparsedColumn]]]:
         for test in self.tests:
             yield normalize_test(test), None
 
@@ -530,19 +601,23 @@ class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
 
 @dataclass
 class ParsedSourceDefinition(
-    UnparsedBaseNode, HasUniqueID, HasRelationMetadata, HasFqn
+    UnparsedBaseNode,
+    HasUniqueID,
+    HasRelationMetadata,
+    HasFqn,
+
 ):
     name: str
     source_name: str
     source_description: str
     loader: str
     identifier: str
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Source]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Source]})
     quoting: Quoting = field(default_factory=Quoting)
     loaded_at_field: Optional[str] = None
     freshness: Optional[FreshnessThreshold] = None
     external: Optional[ExternalTable] = None
-    description: str = ""
+    description: str = ''
     columns: Dict[str, ColumnInfo] = field(default_factory=dict)
     meta: Dict[str, Any] = field(default_factory=dict)
     source_meta: Dict[str, Any] = field(default_factory=dict)
@@ -551,35 +626,38 @@ class ParsedSourceDefinition(
     patch_path: Optional[Path] = None
     unrendered_config: Dict[str, Any] = field(default_factory=dict)
     relation_name: Optional[str] = None
+    created_at: int = field(default_factory=lambda: int(time.time()))
 
-    def same_database_representation(self, other: "ParsedSourceDefinition") -> bool:
+    def same_database_representation(
+        self, other: 'ParsedSourceDefinition'
+    ) -> bool:
         return (
-            self.database == other.database
-            and self.schema == other.schema
-            and self.identifier == other.identifier
-            and True
+            self.database == other.database and
+            self.schema == other.schema and
+            self.identifier == other.identifier and
+            True
         )
 
-    def same_quoting(self, other: "ParsedSourceDefinition") -> bool:
+    def same_quoting(self, other: 'ParsedSourceDefinition') -> bool:
         return self.quoting == other.quoting
 
-    def same_freshness(self, other: "ParsedSourceDefinition") -> bool:
+    def same_freshness(self, other: 'ParsedSourceDefinition') -> bool:
         return (
-            self.freshness == other.freshness
-            and self.loaded_at_field == other.loaded_at_field
-            and True
+            self.freshness == other.freshness and
+            self.loaded_at_field == other.loaded_at_field and
+            True
         )
 
-    def same_external(self, other: "ParsedSourceDefinition") -> bool:
+    def same_external(self, other: 'ParsedSourceDefinition') -> bool:
         return self.external == other.external
 
-    def same_config(self, old: "ParsedSourceDefinition") -> bool:
+    def same_config(self, old: 'ParsedSourceDefinition') -> bool:
         return self.config.same_contents(
             self.unrendered_config,
             old.unrendered_config,
         )
 
-    def same_contents(self, old: Optional["ParsedSourceDefinition"]) -> bool:
+    def same_contents(self, old: Optional['ParsedSourceDefinition']) -> bool:
         # existing when it didn't before is a change!
         if old is None:
             return True
@@ -593,17 +671,17 @@ class ParsedSourceDefinition(
         # metadata/tags changes are not "changes"
         # patching/description changes are not "changes"
         return (
-            self.same_database_representation(old)
-            and self.same_fqn(old)
-            and self.same_config(old)
-            and self.same_quoting(old)
-            and self.same_freshness(old)
-            and self.same_external(old)
-            and True
+            self.same_database_representation(old) and
+            self.same_fqn(old) and
+            self.same_config(old) and
+            self.same_quoting(old) and
+            self.same_freshness(old) and
+            self.same_external(old) and
+            True
         )
 
     def get_full_source_name(self):
-        return f"{self.source_name}_{self.name}"
+        return f'{self.source_name}_{self.name}'
 
     def get_source_representation(self):
         return f'source("{self.source.name}", "{self.table.name}")'
@@ -624,6 +702,10 @@ class ParsedSourceDefinition(
     def depends_on_nodes(self):
         return []
 
+    @property
+    def depends_on(self):
+        return DependsOn(macros=[], nodes=[])
+
     @property
     def refs(self):
         return []
@@ -638,7 +720,7 @@ class ParsedSourceDefinition(
 
     @property
     def search_name(self):
-        return f"{self.source_name}.{self.name}"
+        return f'{self.source_name}.{self.name}'
 
 
 @dataclass
@@ -647,12 +729,15 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
     type: ExposureType
     owner: ExposureOwner
     resource_type: NodeType = NodeType.Exposure
-    description: str = ""
+    description: str = ''
     maturity: Optional[MaturityType] = None
+    meta: Dict[str, Any] = field(default_factory=dict)
+    tags: List[str] = field(default_factory=list)
     url: Optional[str] = None
     depends_on: DependsOn = field(default_factory=DependsOn)
     refs: List[List[str]] = field(default_factory=list)
     sources: List[List[str]] = field(default_factory=list)
+    created_at: int = field(default_factory=lambda: int(time.time()))
 
     @property
     def depends_on_nodes(self):
@@ -662,46 +747,54 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
     def search_name(self):
         return self.name
 
-    # no tags for now, but we could definitely add them
-    @property
-    def tags(self):
-        return []
-
-    def same_depends_on(self, old: "ParsedExposure") -> bool:
+    def same_depends_on(self, old: 'ParsedExposure') -> bool:
         return set(self.depends_on.nodes) == set(old.depends_on.nodes)
 
-    def same_description(self, old: "ParsedExposure") -> bool:
+    def same_description(self, old: 'ParsedExposure') -> bool:
         return self.description == old.description
 
-    def same_maturity(self, old: "ParsedExposure") -> bool:
+    def same_maturity(self, old: 'ParsedExposure') -> bool:
         return self.maturity == old.maturity
 
-    def same_owner(self, old: "ParsedExposure") -> bool:
+    def same_owner(self, old: 'ParsedExposure') -> bool:
         return self.owner == old.owner
 
-    def same_exposure_type(self, old: "ParsedExposure") -> bool:
+    def same_exposure_type(self, old: 'ParsedExposure') -> bool:
         return self.type == old.type
 
-    def same_url(self, old: "ParsedExposure") -> bool:
+    def same_url(self, old: 'ParsedExposure') -> bool:
         return self.url == old.url
 
-    def same_contents(self, old: Optional["ParsedExposure"]) -> bool:
+    def same_contents(self, old: Optional['ParsedExposure']) -> bool:
         # existing when it didn't before is a change!
+        # metadata/tags changes are not "changes"
         if old is None:
             return True
 
         return (
-            self.same_fqn(old)
-            and self.same_exposure_type(old)
-            and self.same_owner(old)
-            and self.same_maturity(old)
-            and self.same_url(old)
-            and self.same_description(old)
-            and self.same_depends_on(old)
-            and True
+            self.same_fqn(old) and
+            self.same_exposure_type(old) and
+            self.same_owner(old) and
+            self.same_maturity(old) and
+            self.same_url(old) and
+            self.same_description(old) and
+            self.same_depends_on(old) and
+            True
         )
 
 
+ManifestNodes = Union[
+    ParsedAnalysisNode,
+    ParsedDataTestNode,
+    ParsedHookNode,
+    ParsedModelNode,
+    ParsedRPCNode,
+    ParsedSchemaTestNode,
+    ParsedSeedNode,
+    ParsedSnapshotNode,
+]
+
+
 ParsedResource = Union[
     ParsedDocumentation,
     ParsedMacro,

core/dbt/contracts/graph/unparsed.py

@@ -4,12 +4,13 @@ from dbt.contracts.util import (
     Mergeable,
     Replaceable,
 )
-
 # trigger the PathEncoder
 import dbt.helper_types  # noqa:F401
 from dbt.exceptions import CompilationException
 
-from dbt.dataclass_schema import dbtClassMixin, StrEnum, ExtensibleDbtClassMixin
+from dbt.dataclass_schema import (
+    dbtClassMixin, StrEnum, ExtensibleDbtClassMixin
+)
 
 from dataclasses import dataclass, field
 from datetime import timedelta
@@ -24,6 +25,10 @@ class UnparsedBaseNode(dbtClassMixin, Replaceable):
     path: str
     original_file_path: str
 
+    @property
+    def file_id(self):
+        return f'{self.package_name}://{self.original_file_path}'
+
 
 @dataclass
 class HasSQL:
@@ -36,25 +41,21 @@ class HasSQL:
 
 @dataclass
 class UnparsedMacro(UnparsedBaseNode, HasSQL):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
+    resource_type: NodeType = field(metadata={'restrict': [NodeType.Macro]})
 
 
 @dataclass
 class UnparsedNode(UnparsedBaseNode, HasSQL):
     name: str
-    resource_type: NodeType = field(
-        metadata={
-            "restrict": [
-                NodeType.Model,
-                NodeType.Analysis,
-                NodeType.Test,
-                NodeType.Snapshot,
-                NodeType.Operation,
-                NodeType.Seed,
-                NodeType.RPCCall,
-            ]
-        }
-    )
+    resource_type: NodeType = field(metadata={'restrict': [
+        NodeType.Model,
+        NodeType.Analysis,
+        NodeType.Test,
+        NodeType.Snapshot,
+        NodeType.Operation,
+        NodeType.Seed,
+        NodeType.RPCCall,
+    ]})
 
     @property
     def search_name(self):
@@ -63,7 +64,9 @@ class UnparsedNode(UnparsedBaseNode, HasSQL):
 
 @dataclass
 class UnparsedRunHook(UnparsedNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
+    resource_type: NodeType = field(
+        metadata={'restrict': [NodeType.Operation]}
+    )
     index: Optional[int] = None
 
 
@@ -73,9 +76,10 @@ class Docs(dbtClassMixin, Replaceable):
 
 
 @dataclass
-class HasDocs(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable):
+class HasDocs(AdditionalPropertiesMixin, ExtensibleDbtClassMixin,
+              Replaceable):
     name: str
-    description: str = ""
+    description: str = ''
     meta: Dict[str, Any] = field(default_factory=dict)
     data_type: Optional[str] = None
     docs: Docs = field(default_factory=Docs)
@@ -116,14 +120,23 @@ class HasYamlMetadata(dbtClassMixin):
     yaml_key: str
     package_name: str
 
+    @property
+    def file_id(self):
+        return f'{self.package_name}://{self.original_file_path}'
+
 
 @dataclass
-class UnparsedAnalysisUpdate(HasColumnDocs, HasDocs, HasYamlMetadata):
+class HasConfig():
+    config: Dict[str, Any] = field(default_factory=dict)
+
+
+@dataclass
+class UnparsedAnalysisUpdate(HasConfig, HasColumnDocs, HasDocs, HasYamlMetadata):
     pass
 
 
 @dataclass
-class UnparsedNodeUpdate(HasColumnTests, HasTests, HasYamlMetadata):
+class UnparsedNodeUpdate(HasConfig, HasColumnTests, HasTests, HasYamlMetadata):
     quote_columns: Optional[bool] = None
 
 
@@ -131,21 +144,21 @@ class UnparsedNodeUpdate(HasColumnTests, HasTests, HasYamlMetadata):
 class MacroArgument(dbtClassMixin):
     name: str
     type: Optional[str] = None
-    description: str = ""
+    description: str = ''
 
 
 @dataclass
-class UnparsedMacroUpdate(HasDocs, HasYamlMetadata):
+class UnparsedMacroUpdate(HasConfig, HasDocs, HasYamlMetadata):
     arguments: List[MacroArgument] = field(default_factory=list)
 
 
 class TimePeriod(StrEnum):
-    minute = "minute"
-    hour = "hour"
-    day = "day"
+    minute = 'minute'
+    hour = 'hour'
+    day = 'day'
 
     def plural(self) -> str:
-        return str(self) + "s"
+        return str(self) + 's'
 
 
 @dataclass
@@ -167,7 +180,6 @@ class FreshnessThreshold(dbtClassMixin, Mergeable):
 
     def status(self, age: float) -> "dbt.contracts.results.FreshnessStatus":
         from dbt.contracts.results import FreshnessStatus
-
         if self.error_after and self.error_after.exceeded(age):
             return FreshnessStatus.Error
         elif self.warn_after and self.warn_after.exceeded(age):
@@ -180,21 +192,24 @@ class FreshnessThreshold(dbtClassMixin, Mergeable):
 
 
 @dataclass
-class AdditionalPropertiesAllowed(AdditionalPropertiesMixin, ExtensibleDbtClassMixin):
+class AdditionalPropertiesAllowed(
+    AdditionalPropertiesMixin,
+    ExtensibleDbtClassMixin
+):
     _extra: Dict[str, Any] = field(default_factory=dict)
 
 
 @dataclass
 class ExternalPartition(AdditionalPropertiesAllowed, Replaceable):
-    name: str = ""
-    description: str = ""
-    data_type: str = ""
+    name: str = ''
+    description: str = ''
+    data_type: str = ''
     meta: Dict[str, Any] = field(default_factory=dict)
 
     def __post_init__(self):
-        if self.name == "" or self.data_type == "":
+        if self.name == '' or self.data_type == '':
             raise CompilationException(
-                "External partition columns must have names and data types"
+                'External partition columns must have names and data types'
             )
 
 
@@ -223,39 +238,44 @@ class UnparsedSourceTableDefinition(HasColumnTests, HasTests):
     loaded_at_field: Optional[str] = None
     identifier: Optional[str] = None
     quoting: Quoting = field(default_factory=Quoting)
-    freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
+    freshness: Optional[FreshnessThreshold] = field(
+        default_factory=FreshnessThreshold
+    )
     external: Optional[ExternalTable] = None
     tags: List[str] = field(default_factory=list)
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        if "freshness" not in dct and self.freshness is None:
-            dct["freshness"] = None
+        if 'freshness' not in dct and self.freshness is None:
+            dct['freshness'] = None
         return dct
 
 
 @dataclass
 class UnparsedSourceDefinition(dbtClassMixin, Replaceable):
     name: str
-    description: str = ""
+    description: str = ''
     meta: Dict[str, Any] = field(default_factory=dict)
     database: Optional[str] = None
     schema: Optional[str] = None
-    loader: str = ""
+    loader: str = ''
     quoting: Quoting = field(default_factory=Quoting)
-    freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
+    freshness: Optional[FreshnessThreshold] = field(
+        default_factory=FreshnessThreshold
+    )
     loaded_at_field: Optional[str] = None
     tables: List[UnparsedSourceTableDefinition] = field(default_factory=list)
     tags: List[str] = field(default_factory=list)
+    config: Dict[str, Any] = field(default_factory=dict)
 
     @property
-    def yaml_key(self) -> "str":
-        return "sources"
+    def yaml_key(self) -> 'str':
+        return 'sources'
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        if "freshnewss" not in dct and self.freshness is None:
-            dct["freshness"] = None
+        if 'freshnewss' not in dct and self.freshness is None:
+            dct['freshness'] = None
         return dct
 
 
@@ -269,7 +289,9 @@ class SourceTablePatch(dbtClassMixin):
     loaded_at_field: Optional[str] = None
     identifier: Optional[str] = None
     quoting: Quoting = field(default_factory=Quoting)
-    freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
+    freshness: Optional[FreshnessThreshold] = field(
+        default_factory=FreshnessThreshold
+    )
     external: Optional[ExternalTable] = None
     tags: Optional[List[str]] = None
     tests: Optional[List[TestDef]] = None
@@ -277,13 +299,13 @@ class SourceTablePatch(dbtClassMixin):
 
     def to_patch_dict(self) -> Dict[str, Any]:
         dct = self.to_dict(omit_none=True)
-        remove_keys = "name"
+        remove_keys = ('name')
         for key in remove_keys:
             if key in dct:
                 del dct[key]
 
         if self.freshness is None:
-            dct["freshness"] = None
+            dct['freshness'] = None
 
         return dct
 
@@ -291,13 +313,13 @@ class SourceTablePatch(dbtClassMixin):
 @dataclass
 class SourcePatch(dbtClassMixin, Replaceable):
     name: str = field(
-        metadata=dict(description="The name of the source to override"),
+        metadata=dict(description='The name of the source to override'),
     )
     overrides: str = field(
-        metadata=dict(description="The package of the source to override"),
+        metadata=dict(description='The package of the source to override'),
     )
     path: Path = field(
-        metadata=dict(description="The path to the patch-defining yml file"),
+        metadata=dict(description='The path to the patch-defining yml file'),
     )
     description: Optional[str] = None
     meta: Optional[Dict[str, Any]] = None
@@ -314,13 +336,13 @@ class SourcePatch(dbtClassMixin, Replaceable):
 
     def to_patch_dict(self) -> Dict[str, Any]:
         dct = self.to_dict(omit_none=True)
-        remove_keys = ("name", "overrides", "tables", "path")
+        remove_keys = ('name', 'overrides', 'tables', 'path')
         for key in remove_keys:
             if key in dct:
                 del dct[key]
 
         if self.freshness is None:
-            dct["freshness"] = None
+            dct['freshness'] = None
 
         return dct
 
@@ -339,6 +361,10 @@ class UnparsedDocumentation(dbtClassMixin, Replaceable):
     path: str
     original_file_path: str
 
+    @property
+    def file_id(self):
+        return f'{self.package_name}://{self.original_file_path}'
+
     @property
     def resource_type(self):
         return NodeType.Documentation
@@ -352,9 +378,9 @@ class UnparsedDocumentationFile(UnparsedDocumentation):
 # can't use total_ordering decorator here, as str provides an ordering already
 # and it's not the one we want.
 class Maturity(StrEnum):
-    low = "low"
-    medium = "medium"
-    high = "high"
+    low = 'low'
+    medium = 'medium'
+    high = 'high'
 
     def __lt__(self, other):
         if not isinstance(other, Maturity):
@@ -379,17 +405,17 @@ class Maturity(StrEnum):
 
 
 class ExposureType(StrEnum):
-    Dashboard = "dashboard"
-    Notebook = "notebook"
-    Analysis = "analysis"
-    ML = "ml"
-    Application = "application"
+    Dashboard = 'dashboard'
+    Notebook = 'notebook'
+    Analysis = 'analysis'
+    ML = 'ml'
+    Application = 'application'
 
 
 class MaturityType(StrEnum):
-    Low = "low"
-    Medium = "medium"
-    High = "high"
+    Low = 'low'
+    Medium = 'medium'
+    High = 'high'
 
 
 @dataclass
@@ -403,7 +429,9 @@ class UnparsedExposure(dbtClassMixin, Replaceable):
     name: str
     type: ExposureType
     owner: ExposureOwner
-    description: str = ""
+    description: str = ''
     maturity: Optional[MaturityType] = None
+    meta: Dict[str, Any] = field(default_factory=dict)
+    tags: List[str] = field(default_factory=list)
     url: Optional[str] = None
     depends_on: List[str] = field(default_factory=list)

core/dbt/contracts/project.py

@@ -5,26 +5,24 @@ from dbt.logger import GLOBAL_LOGGER as logger  # noqa
 from dbt import tracking
 from dbt import ui
 from dbt.dataclass_schema import (
-    dbtClassMixin,
-    ValidationError,
+    dbtClassMixin, ValidationError,
     HyphenatedDbtClassMixin,
     ExtensibleDbtClassMixin,
-    register_pattern,
-    ValidatedStringMixin,
+    register_pattern, ValidatedStringMixin
 )
 from dataclasses import dataclass, field
 from typing import Optional, List, Dict, Union, Any
 from mashumaro.types import SerializableType
 
-PIN_PACKAGE_URL = "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"  # noqa
+PIN_PACKAGE_URL = 'https://docs.getdbt.com/docs/package-management#section-specifying-package-versions'  # noqa
 DEFAULT_SEND_ANONYMOUS_USAGE_STATS = True
 
 
 class Name(ValidatedStringMixin):
-    ValidationRegex = r"^[^\d\W]\w*$"
+    ValidationRegex = r'^[^\d\W]\w*$'
 
 
-register_pattern(Name, r"^[^\d\W]\w*$")
+register_pattern(Name, r'^[^\d\W]\w*$')
 
 
 class SemverString(str, SerializableType):
@@ -32,7 +30,7 @@ class SemverString(str, SerializableType):
         return self
 
     @classmethod
-    def _deserialize(cls, value: str) -> "SemverString":
+    def _deserialize(cls, value: str) -> 'SemverString':
         return SemverString(value)
 
 
@@ -41,7 +39,7 @@ class SemverString(str, SerializableType):
 # 'semver lite'.
 register_pattern(
     SemverString,
-    r"^(?:0|[1-9]\d*)\.(?:0|[1-9]\d*)(\.(?:0|[1-9]\d*))?$",
+    r'^(?:0|[1-9]\d*)\.(?:0|[1-9]\d*)(\.(?:0|[1-9]\d*))?$',
 )
 
 
@@ -72,6 +70,7 @@ class GitPackage(Package):
     git: str
     revision: Optional[RawVersion] = None
     warn_unpinned: Optional[bool] = None
+    subdirectory: Optional[str] = None
 
     def get_revisions(self) -> List[str]:
         if self.revision is None:
@@ -84,6 +83,7 @@ class GitPackage(Package):
 class RegistryPackage(Package):
     package: str
     version: Union[RawVersion, List[RawVersion]]
+    install_prerelease: Optional[bool] = False
 
     def get_versions(self) -> List[str]:
         if isinstance(self.version, list):
@@ -107,7 +107,8 @@ class ProjectPackageMetadata:
 
     @classmethod
     def from_project(cls, project):
-        return cls(name=project.project_name, packages=project.packages.packages)
+        return cls(name=project.project_name,
+                   packages=project.packages.packages)
 
 
 @dataclass
@@ -125,46 +126,46 @@ class RegistryPackageMetadata(
 
 # A list of all the reserved words that packages may not have as names.
 BANNED_PROJECT_NAMES = {
-    "_sql_results",
-    "adapter",
-    "api",
-    "column",
-    "config",
-    "context",
-    "database",
-    "env",
-    "env_var",
-    "exceptions",
-    "execute",
-    "flags",
-    "fromjson",
-    "fromyaml",
-    "graph",
-    "invocation_id",
-    "load_agate_table",
-    "load_result",
-    "log",
-    "model",
-    "modules",
-    "post_hooks",
-    "pre_hooks",
-    "ref",
-    "render",
-    "return",
-    "run_started_at",
-    "schema",
-    "source",
-    "sql",
-    "sql_now",
-    "store_result",
-    "store_raw_result",
-    "target",
-    "this",
-    "tojson",
-    "toyaml",
-    "try_or_compiler_error",
-    "var",
-    "write",
+    '_sql_results',
+    'adapter',
+    'api',
+    'column',
+    'config',
+    'context',
+    'database',
+    'env',
+    'env_var',
+    'exceptions',
+    'execute',
+    'flags',
+    'fromjson',
+    'fromyaml',
+    'graph',
+    'invocation_id',
+    'load_agate_table',
+    'load_result',
+    'log',
+    'model',
+    'modules',
+    'post_hooks',
+    'pre_hooks',
+    'ref',
+    'render',
+    'return',
+    'run_started_at',
+    'schema',
+    'source',
+    'sql',
+    'sql_now',
+    'store_result',
+    'store_raw_result',
+    'target',
+    'this',
+    'tojson',
+    'toyaml',
+    'try_or_compiler_error',
+    'var',
+    'write',
 }
 
 
@@ -191,15 +192,17 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
     on_run_start: Optional[List[str]] = field(default_factory=list_str)
     on_run_end: Optional[List[str]] = field(default_factory=list_str)
     require_dbt_version: Optional[Union[List[str], str]] = None
+    dispatch: List[Dict[str, Any]] = field(default_factory=list)
     models: Dict[str, Any] = field(default_factory=dict)
     seeds: Dict[str, Any] = field(default_factory=dict)
     snapshots: Dict[str, Any] = field(default_factory=dict)
     analyses: Dict[str, Any] = field(default_factory=dict)
     sources: Dict[str, Any] = field(default_factory=dict)
+    tests: Dict[str, Any] = field(default_factory=dict)
     vars: Optional[Dict[str, Any]] = field(
         default=None,
         metadata=dict(
-            description="map project names to their vars override dicts",
+            description='map project names to their vars override dicts',
         ),
     )
     packages: List[PackageSpec] = field(default_factory=list)
@@ -208,10 +211,17 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
     @classmethod
     def validate(cls, data):
         super().validate(data)
-        if data["name"] in BANNED_PROJECT_NAMES:
+        if data['name'] in BANNED_PROJECT_NAMES:
             raise ValidationError(
                 f"Invalid project name: {data['name']} is a reserved word"
             )
+        # validate dispatch config
+        if 'dispatch' in data and data['dispatch']:
+            entries = data['dispatch']
+            for entry in entries:
+                if ('macro_namespace' not in entry or 'search_order' not in entry or
+                        not isinstance(entry['search_order'], list)):
+                    raise ValidationError(f"Invalid project dispatch config: {entry}")
 
 
 @dataclass
@@ -236,8 +246,8 @@ class UserConfig(ExtensibleDbtClassMixin, Replaceable, UserConfigContract):
 
 @dataclass
 class ProfileConfig(HyphenatedDbtClassMixin, Replaceable):
-    profile_name: str = field(metadata={"preserve_underscore": True})
-    target_name: str = field(metadata={"preserve_underscore": True})
+    profile_name: str = field(metadata={'preserve_underscore': True})
+    target_name: str = field(metadata={'preserve_underscore': True})
     config: UserConfig
     threads: int
     # TODO: make this a dynamic union of some kind?
@@ -256,7 +266,7 @@ class ConfiguredQuoting(Quoting, Replaceable):
 class Configuration(Project, ProfileConfig):
     cli_vars: Dict[str, Any] = field(
         default_factory=dict,
-        metadata={"preserve_underscore": True},
+        metadata={'preserve_underscore': True},
     )
     quoting: Optional[ConfiguredQuoting] = None
 

core/dbt/contracts/relation.py

@@ -1,8 +1,7 @@
 from collections.abc import Mapping
 from dataclasses import dataclass, fields
 from typing import (
-    Optional,
-    Dict,
+    Optional, Dict,
 )
 from typing_extensions import Protocol
 
@@ -15,17 +14,17 @@ from dbt.utils import deep_merge
 
 
 class RelationType(StrEnum):
-    Table = "table"
-    View = "view"
-    CTE = "cte"
-    MaterializedView = "materializedview"
-    External = "external"
+    Table = 'table'
+    View = 'view'
+    CTE = 'cte'
+    MaterializedView = 'materializedview'
+    External = 'external'
 
 
 class ComponentName(StrEnum):
-    Database = "database"
-    Schema = "schema"
-    Identifier = "identifier"
+    Database = 'database'
+    Schema = 'schema'
+    Identifier = 'identifier'
 
 
 class HasQuoting(Protocol):
@@ -44,12 +43,12 @@ class FakeAPIObject(dbtClassMixin, Replaceable, Mapping):
             raise KeyError(key) from None
 
     def __iter__(self):
-        deprecations.warn("not-a-dictionary", obj=self)
+        deprecations.warn('not-a-dictionary', obj=self)
         for _, name in self._get_fields():
             yield name
 
     def __len__(self):
-        deprecations.warn("not-a-dictionary", obj=self)
+        deprecations.warn('not-a-dictionary', obj=self)
         return len(fields(self.__class__))
 
     def incorporate(self, **kwargs):
@@ -73,7 +72,8 @@ class Policy(FakeAPIObject):
             return self.identifier
         else:
             raise ValueError(
-                "Got a key of {}, expected one of {}".format(key, list(ComponentName))
+                'Got a key of {}, expected one of {}'
+                .format(key, list(ComponentName))
             )
 
     def replace_dict(self, dct: Dict[ComponentName, bool]):
@@ -93,15 +93,15 @@ class Path(FakeAPIObject):
         # handle pesky jinja2.Undefined sneaking in here and messing up rende
         if not isinstance(self.database, (type(None), str)):
             raise CompilationException(
-                "Got an invalid path database: {}".format(self.database)
+                'Got an invalid path database: {}'.format(self.database)
             )
         if not isinstance(self.schema, (type(None), str)):
             raise CompilationException(
-                "Got an invalid path schema: {}".format(self.schema)
+                'Got an invalid path schema: {}'.format(self.schema)
             )
         if not isinstance(self.identifier, (type(None), str)):
             raise CompilationException(
-                "Got an invalid path identifier: {}".format(self.identifier)
+                'Got an invalid path identifier: {}'.format(self.identifier)
             )
 
     def get_lowered_part(self, key: ComponentName) -> Optional[str]:
@@ -119,7 +119,8 @@ class Path(FakeAPIObject):
             return self.identifier
         else:
             raise ValueError(
-                "Got a key of {}, expected one of {}".format(key, list(ComponentName))
+                'Got a key of {}, expected one of {}'
+                .format(key, list(ComponentName))
             )
 
     def replace_dict(self, dct: Dict[ComponentName, str]):

core/dbt/contracts/results.py

@@ -1,5 +1,7 @@
 from dbt.contracts.graph.manifest import CompileResultNode
-from dbt.contracts.graph.unparsed import FreshnessThreshold
+from dbt.contracts.graph.unparsed import (
+    FreshnessThreshold
+)
 from dbt.contracts.graph.parsed import ParsedSourceDefinition
 from dbt.contracts.util import (
     BaseArtifactMetadata,
@@ -22,13 +24,7 @@ import agate
 from dataclasses import dataclass, field
 from datetime import datetime
 from typing import (
-    Union,
-    Dict,
-    List,
-    Optional,
-    Any,
-    NamedTuple,
-    Sequence,
+    Union, Dict, List, Optional, Any, NamedTuple, Sequence,
 )
 
 from dbt.clients.system import write_json
@@ -58,7 +54,7 @@ class collect_timing_info:
     def __exit__(self, exc_type, exc_value, traceback):
         self.timing_info.end()
         with JsonOnly(), TimingProcessor(self.timing_info):
-            logger.debug("finished collecting timing info")
+            logger.debug('finished collecting timing info')
 
 
 class NodeStatus(StrEnum):
@@ -82,6 +78,7 @@ class TestStatus(StrEnum):
     Error = NodeStatus.Error
     Fail = NodeStatus.Fail
     Warn = NodeStatus.Warn
+    Skipped = NodeStatus.Skipped
 
 
 class FreshnessStatus(StrEnum):
@@ -98,13 +95,16 @@ class BaseResult(dbtClassMixin):
     thread_id: str
     execution_time: float
     adapter_response: Dict[str, Any]
-    message: Optional[Union[str, int]]
+    message: Optional[str]
+    failures: Optional[int]
 
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        if "message" not in data:
-            data["message"] = None
+        if 'message' not in data:
+            data['message'] = None
+        if 'failures' not in data:
+            data['failures'] = None
         return data
 
 
@@ -116,8 +116,9 @@ class NodeResult(BaseResult):
 @dataclass
 class RunResult(NodeResult):
     agate_table: Optional[agate.Table] = field(
-        default=None,
-        metadata={"serialize": lambda x: None, "deserialize": lambda x: None},
+        default=None, metadata={
+            'serialize': lambda x: None, 'deserialize': lambda x: None
+        }
     )
 
     @property
@@ -161,6 +162,7 @@ def process_run_result(result: RunResult) -> RunResultOutput:
         execution_time=result.execution_time,
         message=result.message,
         adapter_response=result.adapter_response,
+        failures=result.failures
     )
 
 
@@ -183,7 +185,7 @@ class RunExecutionResult(
 
 
 @dataclass
-@schema_version("run-results", 1)
+@schema_version('run-results', 2)
 class RunResultsArtifact(ExecutionResult, ArtifactMixin):
     results: Sequence[RunResultOutput]
     args: Dict[str, Any] = field(default_factory=dict)
@@ -205,7 +207,7 @@ class RunResultsArtifact(ExecutionResult, ArtifactMixin):
             metadata=meta,
             results=processed_results,
             elapsed_time=elapsed_time,
-            args=args,
+            args=args
         )
 
     def write(self, path: str):
@@ -219,14 +221,15 @@ class RunOperationResult(ExecutionResult):
 
 @dataclass
 class RunOperationResultMetadata(BaseArtifactMetadata):
-    dbt_schema_version: str = field(
-        default_factory=lambda: str(RunOperationResultsArtifact.dbt_schema_version)
-    )
+    dbt_schema_version: str = field(default_factory=lambda: str(
+        RunOperationResultsArtifact.dbt_schema_version
+    ))
 
 
 @dataclass
-@schema_version("run-operation-result", 1)
+@schema_version('run-operation-result', 1)
 class RunOperationResultsArtifact(RunOperationResult, ArtifactMixin):
+
     @classmethod
     def from_success(
         cls,
@@ -245,7 +248,6 @@ class RunOperationResultsArtifact(RunOperationResult, ArtifactMixin):
             success=success,
         )
 
-
 # due to issues with typing.Union collapsing subclasses, this can't subclass
 # PartialResult
 
@@ -264,7 +266,7 @@ class SourceFreshnessResult(NodeResult):
 
 
 class FreshnessErrorEnum(StrEnum):
-    runtime_error = "runtime error"
+    runtime_error = 'runtime error'
 
 
 @dataclass
@@ -294,11 +296,14 @@ class PartialSourceFreshnessResult(NodeResult):
         return False
 
 
-FreshnessNodeResult = Union[PartialSourceFreshnessResult, SourceFreshnessResult]
+FreshnessNodeResult = Union[PartialSourceFreshnessResult,
+                            SourceFreshnessResult]
 FreshnessNodeOutput = Union[SourceFreshnessRuntimeError, SourceFreshnessOutput]
 
 
-def process_freshness_result(result: FreshnessNodeResult) -> FreshnessNodeOutput:
+def process_freshness_result(
+    result: FreshnessNodeResult
+) -> FreshnessNodeOutput:
     unique_id = result.node.unique_id
     if result.status == FreshnessStatus.RuntimeErr:
         return SourceFreshnessRuntimeError(
@@ -310,15 +315,16 @@ def process_freshness_result(result: FreshnessNodeResult) -> FreshnessNodeOutput
     # we know that this must be a SourceFreshnessResult
     if not isinstance(result, SourceFreshnessResult):
         raise InternalException(
-            "Got {} instead of a SourceFreshnessResult for a "
-            "non-error result in freshness execution!".format(type(result))
+            'Got {} instead of a SourceFreshnessResult for a '
+            'non-error result in freshness execution!'
+            .format(type(result))
         )
     # if we're here, we must have a non-None freshness threshold
     criteria = result.node.freshness
     if criteria is None:
         raise InternalException(
-            "Somehow evaluated a freshness result for a source "
-            "that has no freshness criteria!"
+            'Somehow evaluated a freshness result for a source '
+            'that has no freshness criteria!'
         )
     return SourceFreshnessOutput(
         unique_id=unique_id,
@@ -327,14 +333,16 @@ def process_freshness_result(result: FreshnessNodeResult) -> FreshnessNodeOutput
         max_loaded_at_time_ago_in_s=result.age,
         status=result.status,
         criteria=criteria,
-        adapter_response=result.adapter_response,
+        adapter_response=result.adapter_response
     )
 
 
 @dataclass
 class FreshnessMetadata(BaseArtifactMetadata):
     dbt_schema_version: str = field(
-        default_factory=lambda: str(FreshnessExecutionResultArtifact.dbt_schema_version)
+        default_factory=lambda: str(
+            FreshnessExecutionResultArtifact.dbt_schema_version
+        )
     )
 
 
@@ -355,7 +363,7 @@ class FreshnessResult(ExecutionResult):
 
 
 @dataclass
-@schema_version("sources", 1)
+@schema_version('sources', 1)
 class FreshnessExecutionResultArtifact(
     ArtifactMixin,
     VersionedSchema,
@@ -375,9 +383,11 @@ class FreshnessExecutionResultArtifact(
 
 
 Primitive = Union[bool, str, float, None]
+PrimitiveDict = Dict[str, Primitive]
 
 CatalogKey = NamedTuple(
-    "CatalogKey", [("database", Optional[str]), ("schema", str), ("name", str)]
+    'CatalogKey',
+    [('database', Optional[str]), ('schema', str), ('name', str)]
 )
 
 
@@ -446,13 +456,13 @@ class CatalogResults(dbtClassMixin):
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        if "_compile_results" in dct:
-            del dct["_compile_results"]
+        if '_compile_results' in dct:
+            del dct['_compile_results']
         return dct
 
 
 @dataclass
-@schema_version("catalog", 1)
+@schema_version('catalog', 1)
 class CatalogArtifact(CatalogResults, ArtifactMixin):
     metadata: CatalogMetadata
 
@@ -463,8 +473,8 @@ class CatalogArtifact(CatalogResults, ArtifactMixin):
         nodes: Dict[str, CatalogTable],
         sources: Dict[str, CatalogTable],
         compile_results: Optional[Any],
-        errors: Optional[List[str]],
-    ) -> "CatalogArtifact":
+        errors: Optional[List[str]]
+    ) -> 'CatalogArtifact':
         meta = CatalogMetadata(generated_at=generated_at)
         return cls(
             metadata=meta,

core/dbt/contracts/rpc.py

@@ -10,9 +10,7 @@ from dbt.dataclass_schema import dbtClassMixin, StrEnum
 from dbt.contracts.graph.compiled import CompileResultNode
 from dbt.contracts.graph.manifest import WritableManifest
 from dbt.contracts.results import (
-    RunResult,
-    RunResultsArtifact,
-    TimingInfo,
+    RunResult, RunResultsArtifact, TimingInfo,
     CatalogArtifact,
     CatalogResults,
     ExecutionResult,
@@ -42,10 +40,10 @@ class RPCParameters(dbtClassMixin):
     @classmethod
     def __pre_deserialize__(cls, data, omit_none=True):
         data = super().__pre_deserialize__(data)
-        if "timeout" not in data:
-            data["timeout"] = None
-        if "task_tags" not in data:
-            data["task_tags"] = None
+        if 'timeout' not in data:
+            data['timeout'] = None
+        if 'task_tags' not in data:
+            data['task_tags'] = None
         return data
 
 
@@ -60,15 +58,28 @@ class RPCExecParameters(RPCParameters):
 class RPCCompileParameters(RPCParameters):
     threads: Optional[int] = None
     models: Union[None, str, List[str]] = None
+    select: Union[None, str, List[str]] = None
     exclude: Union[None, str, List[str]] = None
     selector: Optional[str] = None
     state: Optional[str] = None
 
 
+@dataclass
+class RPCListParameters(RPCParameters):
+    resource_types: Optional[List[str]] = None
+    models: Union[None, str, List[str]] = None
+    exclude: Union[None, str, List[str]] = None
+    select: Union[None, str, List[str]] = None
+    selector: Optional[str] = None
+    output: Optional[str] = 'json'
+    output_keys: Optional[List[str]] = None
+
+
 @dataclass
 class RPCRunParameters(RPCParameters):
     threads: Optional[int] = None
     models: Union[None, str, List[str]] = None
+    select: Union[None, str, List[str]] = None
     exclude: Union[None, str, List[str]] = None
     selector: Optional[str] = None
     state: Optional[str] = None
@@ -108,6 +119,17 @@ class RPCDocsGenerateParameters(RPCParameters):
     state: Optional[str] = None
 
 
+@dataclass
+class RPCBuildParameters(RPCParameters):
+    threads: Optional[int] = None
+    models: Union[None, str, List[str]] = None
+    select: Union[None, str, List[str]] = None
+    exclude: Union[None, str, List[str]] = None
+    selector: Optional[str] = None
+    state: Optional[str] = None
+    defer: Optional[bool] = None
+
+
 @dataclass
 class RPCCliParameters(RPCParameters):
     cli: str
@@ -163,7 +185,6 @@ class GCParameters(RPCParameters):
         will be applied to the task manager before GC starts. By default the
         existing gc settings remain.
     """
-
     task_ids: Optional[List[TaskID]] = None
     before: Optional[datetime] = None
     settings: Optional[GCSettings] = None
@@ -179,13 +200,14 @@ class RPCRunOperationParameters(RPCParameters):
 class RPCSourceFreshnessParameters(RPCParameters):
     threads: Optional[int] = None
     select: Union[None, str, List[str]] = None
+    exclude: Union[None, str, List[str]] = None
+    selector: Optional[str] = None
 
 
 @dataclass
 class GetManifestParameters(RPCParameters):
     pass
 
-
 # Outputs
 
 
@@ -195,13 +217,20 @@ class RemoteResult(VersionedSchema):
 
 
 @dataclass
-@schema_version("remote-deps-result", 1)
+@schema_version('remote-list-results', 1)
+class RemoteListResults(RemoteResult):
+    output: List[Any]
+    generated_at: datetime = field(default_factory=datetime.utcnow)
+
+
+@dataclass
+@schema_version('remote-deps-result', 1)
 class RemoteDepsResult(RemoteResult):
     generated_at: datetime = field(default_factory=datetime.utcnow)
 
 
 @dataclass
-@schema_version("remote-catalog-result", 1)
+@schema_version('remote-catalog-result', 1)
 class RemoteCatalogResults(CatalogResults, RemoteResult):
     generated_at: datetime = field(default_factory=datetime.utcnow)
 
@@ -225,7 +254,7 @@ class RemoteCompileResultMixin(RemoteResult):
 
 
 @dataclass
-@schema_version("remote-compile-result", 1)
+@schema_version('remote-compile-result', 1)
 class RemoteCompileResult(RemoteCompileResultMixin):
     generated_at: datetime = field(default_factory=datetime.utcnow)
 
@@ -235,7 +264,7 @@ class RemoteCompileResult(RemoteCompileResultMixin):
 
 
 @dataclass
-@schema_version("remote-execution-result", 1)
+@schema_version('remote-execution-result', 1)
 class RemoteExecutionResult(ExecutionResult, RemoteResult):
     results: Sequence[RunResult]
     args: Dict[str, Any] = field(default_factory=dict)
@@ -255,7 +284,7 @@ class RemoteExecutionResult(ExecutionResult, RemoteResult):
         cls,
         base: RunExecutionResult,
         logs: List[LogMessage],
-    ) -> "RemoteExecutionResult":
+    ) -> 'RemoteExecutionResult':
         return cls(
             generated_at=base.generated_at,
             results=base.results,
@@ -272,7 +301,7 @@ class ResultTable(dbtClassMixin):
 
 
 @dataclass
-@schema_version("remote-run-operation-result", 1)
+@schema_version('remote-run-operation-result', 1)
 class RemoteRunOperationResult(RunOperationResult, RemoteResult):
     generated_at: datetime = field(default_factory=datetime.utcnow)
 
@@ -281,7 +310,7 @@ class RemoteRunOperationResult(RunOperationResult, RemoteResult):
         cls,
         base: RunOperationResultsArtifact,
         logs: List[LogMessage],
-    ) -> "RemoteRunOperationResult":
+    ) -> 'RemoteRunOperationResult':
         return cls(
             generated_at=base.metadata.generated_at,
             results=base.results,
@@ -300,14 +329,15 @@ class RemoteRunOperationResult(RunOperationResult, RemoteResult):
 
 
 @dataclass
-@schema_version("remote-freshness-result", 1)
+@schema_version('remote-freshness-result', 1)
 class RemoteFreshnessResult(FreshnessResult, RemoteResult):
+
     @classmethod
     def from_local_result(
         cls,
         base: FreshnessResult,
         logs: List[LogMessage],
-    ) -> "RemoteFreshnessResult":
+    ) -> 'RemoteFreshnessResult':
         return cls(
             metadata=base.metadata,
             results=base.results,
@@ -321,7 +351,7 @@ class RemoteFreshnessResult(FreshnessResult, RemoteResult):
 
 
 @dataclass
-@schema_version("remote-run-result", 1)
+@schema_version('remote-run-result', 1)
 class RemoteRunResult(RemoteCompileResultMixin):
     table: ResultTable
     generated_at: datetime = field(default_factory=datetime.utcnow)
@@ -339,15 +369,14 @@ RPCResult = Union[
 
 # GC types
 
-
 class GCResultState(StrEnum):
-    Deleted = "deleted"  # successful GC
-    Missing = "missing"  # nothing to GC
-    Running = "running"  # can't GC
+    Deleted = 'deleted'  # successful GC
+    Missing = 'missing'  # nothing to GC
+    Running = 'running'  # can't GC
 
 
 @dataclass
-@schema_version("remote-gc-result", 1)
+@schema_version('remote-gc-result', 1)
 class GCResult(RemoteResult):
     logs: List[LogMessage] = field(default_factory=list)
     deleted: List[TaskID] = field(default_factory=list)
@@ -362,20 +391,21 @@ class GCResult(RemoteResult):
         elif state == GCResultState.Deleted:
             self.deleted.append(task_id)
         else:
-            raise InternalException(f"Got invalid state in add_result: {state}")
-
+            raise InternalException(
+                f'Got invalid state in add_result: {state}'
+            )
 
 # Task management types
 
 
 class TaskHandlerState(StrEnum):
-    NotStarted = "not started"
-    Initializing = "initializing"
-    Running = "running"
-    Success = "success"
-    Error = "error"
-    Killed = "killed"
-    Failed = "failed"
+    NotStarted = 'not started'
+    Initializing = 'initializing'
+    Running = 'running'
+    Success = 'success'
+    Error = 'error'
+    Killed = 'killed'
+    Failed = 'failed'
 
     def __lt__(self, other) -> bool:
         """A logical ordering for TaskHandlerState:
@@ -383,7 +413,7 @@ class TaskHandlerState(StrEnum):
         NotStarted < Initializing < Running < (Success, Error, Killed, Failed)
         """
         if not isinstance(other, TaskHandlerState):
-            raise TypeError("cannot compare to non-TaskHandlerState")
+            raise TypeError('cannot compare to non-TaskHandlerState')
         order = (self.NotStarted, self.Initializing, self.Running)
         smaller = set()
         for value in order:
@@ -395,11 +425,13 @@ class TaskHandlerState(StrEnum):
 
     def __le__(self, other) -> bool:
         # so that ((Success <= Error) is True)
-        return (self < other) or (self == other) or (self.finished and other.finished)
+        return ((self < other) or
+                (self == other) or
+                (self.finished and other.finished))
 
     def __gt__(self, other) -> bool:
         if not isinstance(other, TaskHandlerState):
-            raise TypeError("cannot compare to non-TaskHandlerState")
+            raise TypeError('cannot compare to non-TaskHandlerState')
         order = (self.NotStarted, self.Initializing, self.Running)
         smaller = set()
         for value in order:
@@ -410,7 +442,9 @@ class TaskHandlerState(StrEnum):
 
     def __ge__(self, other) -> bool:
         # so that ((Success <= Error) is True)
-        return (self > other) or (self == other) or (self.finished and other.finished)
+        return ((self > other) or
+                (self == other) or
+                (self.finished and other.finished))
 
     @property
     def finished(self) -> bool:
@@ -429,7 +463,7 @@ class TaskTiming(dbtClassMixin):
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        for field_name in ("start", "end", "elapsed"):
+        for field_name in ('start', 'end', 'elapsed'):
             if field_name not in data:
                 data[field_name] = None
         return data
@@ -446,27 +480,27 @@ class TaskRow(TaskTiming):
 
 
 @dataclass
-@schema_version("remote-ps-result", 1)
+@schema_version('remote-ps-result', 1)
 class PSResult(RemoteResult):
     rows: List[TaskRow]
 
 
 class KillResultStatus(StrEnum):
-    Missing = "missing"
-    NotStarted = "not_started"
-    Killed = "killed"
-    Finished = "finished"
+    Missing = 'missing'
+    NotStarted = 'not_started'
+    Killed = 'killed'
+    Finished = 'finished'
 
 
 @dataclass
-@schema_version("remote-kill-result", 1)
+@schema_version('remote-kill-result', 1)
 class KillResult(RemoteResult):
     state: KillResultStatus = KillResultStatus.Missing
     logs: List[LogMessage] = field(default_factory=list)
 
 
 @dataclass
-@schema_version("remote-manifest-result", 1)
+@schema_version('remote-manifest-result', 1)
 class GetManifestResult(RemoteResult):
     manifest: Optional[WritableManifest] = None
 
@@ -497,28 +531,29 @@ class PollResult(RemoteResult, TaskTiming):
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        for field_name in ("start", "end", "elapsed"):
+        for field_name in ('start', 'end', 'elapsed'):
             if field_name not in data:
                 data[field_name] = None
         return data
 
 
 @dataclass
-@schema_version("poll-remote-deps-result", 1)
+@schema_version('poll-remote-deps-result', 1)
 class PollRemoteEmptyCompleteResult(PollResult, RemoteResult):
     state: TaskHandlerState = field(
-        metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
+        metadata=restrict_to(TaskHandlerState.Success,
+                             TaskHandlerState.Failed),
     )
     generated_at: datetime = field(default_factory=datetime.utcnow)
 
     @classmethod
     def from_result(
-        cls: Type["PollRemoteEmptyCompleteResult"],
+        cls: Type['PollRemoteEmptyCompleteResult'],
         base: RemoteDepsResult,
         tags: TaskTags,
         timing: TaskTiming,
         logs: List[LogMessage],
-    ) -> "PollRemoteEmptyCompleteResult":
+    ) -> 'PollRemoteEmptyCompleteResult':
         return cls(
             logs=logs,
             tags=tags,
@@ -526,12 +561,12 @@ class PollRemoteEmptyCompleteResult(PollResult, RemoteResult):
             start=timing.start,
             end=timing.end,
             elapsed=timing.elapsed,
-            generated_at=base.generated_at,
+            generated_at=base.generated_at
         )
 
 
 @dataclass
-@schema_version("poll-remote-killed-result", 1)
+@schema_version('poll-remote-killed-result', 1)
 class PollKilledResult(PollResult):
     state: TaskHandlerState = field(
         metadata=restrict_to(TaskHandlerState.Killed),
@@ -539,23 +574,24 @@ class PollKilledResult(PollResult):
 
 
 @dataclass
-@schema_version("poll-remote-execution-result", 1)
+@schema_version('poll-remote-execution-result', 1)
 class PollExecuteCompleteResult(
     RemoteExecutionResult,
     PollResult,
 ):
     state: TaskHandlerState = field(
-        metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
+        metadata=restrict_to(TaskHandlerState.Success,
+                             TaskHandlerState.Failed),
     )
 
     @classmethod
     def from_result(
-        cls: Type["PollExecuteCompleteResult"],
+        cls: Type['PollExecuteCompleteResult'],
         base: RemoteExecutionResult,
         tags: TaskTags,
         timing: TaskTiming,
         logs: List[LogMessage],
-    ) -> "PollExecuteCompleteResult":
+    ) -> 'PollExecuteCompleteResult':
         return cls(
             results=base.results,
             elapsed_time=base.elapsed_time,
@@ -570,23 +606,24 @@ class PollExecuteCompleteResult(
 
 
 @dataclass
-@schema_version("poll-remote-compile-result", 1)
+@schema_version('poll-remote-compile-result', 1)
 class PollCompileCompleteResult(
     RemoteCompileResult,
     PollResult,
 ):
     state: TaskHandlerState = field(
-        metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
+        metadata=restrict_to(TaskHandlerState.Success,
+                             TaskHandlerState.Failed),
     )
 
     @classmethod
     def from_result(
-        cls: Type["PollCompileCompleteResult"],
+        cls: Type['PollCompileCompleteResult'],
         base: RemoteCompileResult,
         tags: TaskTags,
         timing: TaskTiming,
         logs: List[LogMessage],
-    ) -> "PollCompileCompleteResult":
+    ) -> 'PollCompileCompleteResult':
         return cls(
             raw_sql=base.raw_sql,
             compiled_sql=base.compiled_sql,
@@ -598,28 +635,29 @@ class PollCompileCompleteResult(
             start=timing.start,
             end=timing.end,
             elapsed=timing.elapsed,
-            generated_at=base.generated_at,
+            generated_at=base.generated_at
         )
 
 
 @dataclass
-@schema_version("poll-remote-run-result", 1)
+@schema_version('poll-remote-run-result', 1)
 class PollRunCompleteResult(
     RemoteRunResult,
     PollResult,
 ):
     state: TaskHandlerState = field(
-        metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
+        metadata=restrict_to(TaskHandlerState.Success,
+                             TaskHandlerState.Failed),
     )
 
     @classmethod
     def from_result(
-        cls: Type["PollRunCompleteResult"],
+        cls: Type['PollRunCompleteResult'],
         base: RemoteRunResult,
         tags: TaskTags,
         timing: TaskTiming,
         logs: List[LogMessage],
-    ) -> "PollRunCompleteResult":
+    ) -> 'PollRunCompleteResult':
         return cls(
             raw_sql=base.raw_sql,
             compiled_sql=base.compiled_sql,
@@ -632,28 +670,29 @@ class PollRunCompleteResult(
             start=timing.start,
             end=timing.end,
             elapsed=timing.elapsed,
-            generated_at=base.generated_at,
+            generated_at=base.generated_at
         )
 
 
 @dataclass
-@schema_version("poll-remote-run-operation-result", 1)
+@schema_version('poll-remote-run-operation-result', 1)
 class PollRunOperationCompleteResult(
     RemoteRunOperationResult,
     PollResult,
 ):
     state: TaskHandlerState = field(
-        metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
+        metadata=restrict_to(TaskHandlerState.Success,
+                             TaskHandlerState.Failed),
     )
 
     @classmethod
     def from_result(
-        cls: Type["PollRunOperationCompleteResult"],
+        cls: Type['PollRunOperationCompleteResult'],
         base: RemoteRunOperationResult,
         tags: TaskTags,
         timing: TaskTiming,
         logs: List[LogMessage],
-    ) -> "PollRunOperationCompleteResult":
+    ) -> 'PollRunOperationCompleteResult':
         return cls(
             success=base.success,
             results=base.results,
@@ -669,20 +708,21 @@ class PollRunOperationCompleteResult(
 
 
 @dataclass
-@schema_version("poll-remote-catalog-result", 1)
+@schema_version('poll-remote-catalog-result', 1)
 class PollCatalogCompleteResult(RemoteCatalogResults, PollResult):
     state: TaskHandlerState = field(
-        metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
+        metadata=restrict_to(TaskHandlerState.Success,
+                             TaskHandlerState.Failed),
     )
 
     @classmethod
     def from_result(
-        cls: Type["PollCatalogCompleteResult"],
+        cls: Type['PollCatalogCompleteResult'],
         base: RemoteCatalogResults,
         tags: TaskTags,
         timing: TaskTiming,
         logs: List[LogMessage],
-    ) -> "PollCatalogCompleteResult":
+    ) -> 'PollCatalogCompleteResult':
         return cls(
             nodes=base.nodes,
             sources=base.sources,
@@ -699,26 +739,27 @@ class PollCatalogCompleteResult(RemoteCatalogResults, PollResult):
 
 
 @dataclass
-@schema_version("poll-remote-in-progress-result", 1)
+@schema_version('poll-remote-in-progress-result', 1)
 class PollInProgressResult(PollResult):
     pass
 
 
 @dataclass
-@schema_version("poll-remote-get-manifest-result", 1)
+@schema_version('poll-remote-get-manifest-result', 1)
 class PollGetManifestResult(GetManifestResult, PollResult):
     state: TaskHandlerState = field(
-        metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
+        metadata=restrict_to(TaskHandlerState.Success,
+                             TaskHandlerState.Failed),
     )
 
     @classmethod
     def from_result(
-        cls: Type["PollGetManifestResult"],
+        cls: Type['PollGetManifestResult'],
         base: GetManifestResult,
         tags: TaskTags,
         timing: TaskTiming,
         logs: List[LogMessage],
-    ) -> "PollGetManifestResult":
+    ) -> 'PollGetManifestResult':
         return cls(
             manifest=base.manifest,
             logs=logs,
@@ -731,20 +772,21 @@ class PollGetManifestResult(GetManifestResult, PollResult):
 
 
 @dataclass
-@schema_version("poll-remote-freshness-result", 1)
+@schema_version('poll-remote-freshness-result', 1)
 class PollFreshnessResult(RemoteFreshnessResult, PollResult):
     state: TaskHandlerState = field(
-        metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
+        metadata=restrict_to(TaskHandlerState.Success,
+                             TaskHandlerState.Failed),
     )
 
     @classmethod
     def from_result(
-        cls: Type["PollFreshnessResult"],
+        cls: Type['PollFreshnessResult'],
         base: RemoteFreshnessResult,
         tags: TaskTags,
         timing: TaskTiming,
         logs: List[LogMessage],
-    ) -> "PollFreshnessResult":
+    ) -> 'PollFreshnessResult':
         return cls(
             logs=logs,
             tags=tags,
@@ -757,19 +799,18 @@ class PollFreshnessResult(RemoteFreshnessResult, PollResult):
             elapsed_time=base.elapsed_time,
         )
 
-
 # Manifest parsing types
 
 
 class ManifestStatus(StrEnum):
-    Init = "init"
-    Compiling = "compiling"
-    Ready = "ready"
-    Error = "error"
+    Init = 'init'
+    Compiling = 'compiling'
+    Ready = 'ready'
+    Error = 'error'
 
 
 @dataclass
-@schema_version("remote-status-result", 1)
+@schema_version('remote-status-result', 1)
 class LastParse(RemoteResult):
     state: ManifestStatus = ManifestStatus.Init
     logs: List[LogMessage] = field(default_factory=list)

core/dbt/contracts/selection.py

@@ -8,7 +8,7 @@ from typing import List, Dict, Any, Union
 class SelectorDefinition(dbtClassMixin):
     name: str
     definition: Union[str, Dict[str, Any]]
-    description: str = ""
+    description: str = ''
 
 
 @dataclass

core/dbt/contracts/state.py

@@ -9,7 +9,7 @@ class PreviousState:
         self.path: Path = path
         self.manifest: Optional[WritableManifest] = None
 
-        manifest_path = self.path / "manifest.json"
+        manifest_path = self.path / 'manifest.json'
         if manifest_path.exists() and manifest_path.is_file():
             try:
                 self.manifest = WritableManifest.read(str(manifest_path))

core/dbt/contracts/util.py

@@ -1,7 +1,9 @@
 import dataclasses
 import os
 from datetime import datetime
-from typing import List, Tuple, ClassVar, Type, TypeVar, Dict, Any, Optional
+from typing import (
+    List, Tuple, ClassVar, Type, TypeVar, Dict, Any, Optional
+)
 
 from dbt.clients.system import write_json, read_json
 from dbt.exceptions import (
@@ -12,7 +14,6 @@ from dbt.version import __version__
 from dbt.tracking import get_invocation_id
 from dbt.dataclass_schema import dbtClassMixin
 
-MacroKey = Tuple[str, str]
 SourceKey = Tuple[str, str]
 
 
@@ -55,7 +56,9 @@ class Mergeable(Replaceable):
 
 class Writable:
     def write(self, path: str):
-        write_json(path, self.to_dict(omit_none=False))  # type: ignore
+        write_json(
+            path, self.to_dict(omit_none=False)  # type: ignore
+        )
 
 
 class AdditionalPropertiesMixin:
@@ -64,7 +67,6 @@ class AdditionalPropertiesMixin:
     The underlying class definition must include a type definition for a field
     named '_extra' that is of type `Dict[str, Any]`.
     """
-
     ADDITIONAL_PROPERTIES = True
 
     # This takes attributes in the dictionary that are
@@ -83,10 +85,10 @@ class AdditionalPropertiesMixin:
         cls_keys = cls._get_field_names()
         new_dict = {}
         for key, value in data.items():
-            if key not in cls_keys and key != "_extra":
-                if "_extra" not in new_dict:
-                    new_dict["_extra"] = {}
-                new_dict["_extra"][key] = value
+            if key not in cls_keys and key != '_extra':
+                if '_extra' not in new_dict:
+                    new_dict['_extra'] = {}
+                new_dict['_extra'][key] = value
             else:
                 new_dict[key] = value
         data = new_dict
@@ -96,8 +98,8 @@ class AdditionalPropertiesMixin:
     def __post_serialize__(self, dct):
         data = super().__post_serialize__(dct)
         data.update(self.extra)
-        if "_extra" in data:
-            del data["_extra"]
+        if '_extra' in data:
+            del data['_extra']
         return data
 
     def replace(self, **kwargs):
@@ -123,8 +125,8 @@ class Readable:
         return cls.from_dict(data)  # type: ignore
 
 
-BASE_SCHEMAS_URL = "https://schemas.getdbt.com/"
-SCHEMA_PATH = "dbt/{name}/v{version}.json"
+BASE_SCHEMAS_URL = 'https://schemas.getdbt.com/'
+SCHEMA_PATH = 'dbt/{name}/v{version}.json'
 
 
 @dataclasses.dataclass
@@ -134,22 +136,24 @@ class SchemaVersion:
 
     @property
     def path(self) -> str:
-        return SCHEMA_PATH.format(name=self.name, version=self.version)
+        return SCHEMA_PATH.format(
+            name=self.name,
+            version=self.version
+        )
 
     def __str__(self) -> str:
         return BASE_SCHEMAS_URL + self.path
 
 
-SCHEMA_VERSION_KEY = "dbt_schema_version"
+SCHEMA_VERSION_KEY = 'dbt_schema_version'
 
 
-METADATA_ENV_PREFIX = "DBT_ENV_CUSTOM_ENV_"
+METADATA_ENV_PREFIX = 'DBT_ENV_CUSTOM_ENV_'
 
 
 def get_metadata_env() -> Dict[str, str]:
     return {
-        k[len(METADATA_ENV_PREFIX) :]: v
-        for k, v in os.environ.items()
+        k[len(METADATA_ENV_PREFIX):]: v for k, v in os.environ.items()
         if k.startswith(METADATA_ENV_PREFIX)
     }
 
@@ -158,8 +162,12 @@ def get_metadata_env() -> Dict[str, str]:
 class BaseArtifactMetadata(dbtClassMixin):
     dbt_schema_version: str
     dbt_version: str = __version__
-    generated_at: datetime = dataclasses.field(default_factory=datetime.utcnow)
-    invocation_id: Optional[str] = dataclasses.field(default_factory=get_invocation_id)
+    generated_at: datetime = dataclasses.field(
+        default_factory=datetime.utcnow
+    )
+    invocation_id: Optional[str] = dataclasses.field(
+        default_factory=get_invocation_id
+    )
     env: Dict[str, str] = dataclasses.field(default_factory=get_metadata_env)
 
 
@@ -170,7 +178,6 @@ def schema_version(name: str, version: int):
             version=version,
         )
         return cls
-
     return inner
 
 
@@ -182,11 +189,11 @@ class VersionedSchema(dbtClassMixin):
     def json_schema(cls, embeddable: bool = False) -> Dict[str, Any]:
         result = super().json_schema(embeddable=embeddable)
         if not embeddable:
-            result["$id"] = str(cls.dbt_schema_version)
+            result['$id'] = str(cls.dbt_schema_version)
         return result
 
 
-T = TypeVar("T", bound="ArtifactMixin")
+T = TypeVar('T', bound='ArtifactMixin')
 
 
 # metadata should really be a Generic[T_M] where T_M is a TypeVar bound to
@@ -200,4 +207,6 @@ class ArtifactMixin(VersionedSchema, Writable, Readable):
     def validate(cls, data):
         super().validate(data)
         if cls.dbt_schema_version is None:
-            raise InternalException("Cannot call from_dict with no schema version!")
+            raise InternalException(
+                'Cannot call from_dict with no schema version!'
+            )

core/dbt/dataclass_schema.py

@@ -1,7 +1,5 @@
 from typing import (
-    Type,
-    ClassVar,
-    cast,
+    Type, ClassVar, cast,
 )
 import re
 from dataclasses import fields
@@ -13,7 +11,9 @@ from hologram import JsonSchemaMixin, FieldEncoder, ValidationError
 
 # type: ignore
 from mashumaro import DataClassDictMixin
-from mashumaro.config import TO_DICT_ADD_OMIT_NONE_FLAG, BaseConfig as MashBaseConfig
+from mashumaro.config import (
+    TO_DICT_ADD_OMIT_NONE_FLAG, BaseConfig as MashBaseConfig
+)
 from mashumaro.types import SerializableType, SerializationStrategy
 
 
@@ -26,7 +26,9 @@ class DateTimeSerialization(SerializationStrategy):
         return out
 
     def deserialize(self, value):
-        return value if isinstance(value, datetime) else parse(cast(str, value))
+        return (
+            value if isinstance(value, datetime) else parse(cast(str, value))
+        )
 
 
 # This class pulls in both JsonSchemaMixin from Hologram and
@@ -36,8 +38,8 @@ class DateTimeSerialization(SerializationStrategy):
 # come from Hologram.
 class dbtClassMixin(DataClassDictMixin, JsonSchemaMixin):
     """Mixin which adds methods to generate a JSON schema and
-    convert to and from JSON encodable dicts with validation
-    against the schema
+       convert to and from JSON encodable dicts with validation
+       against the schema
     """
 
     class Config(MashBaseConfig):
@@ -58,8 +60,8 @@ class dbtClassMixin(DataClassDictMixin, JsonSchemaMixin):
         if self._hyphenated:
             new_dict = {}
             for key in dct:
-                if "_" in key:
-                    new_key = key.replace("_", "-")
+                if '_' in key:
+                    new_key = key.replace('_', '-')
                     new_dict[new_key] = dct[key]
                 else:
                     new_dict[key] = dct[key]
@@ -71,11 +73,13 @@ class dbtClassMixin(DataClassDictMixin, JsonSchemaMixin):
     # performing the conversion to a dict
     @classmethod
     def __pre_deserialize__(cls, data):
-        if cls._hyphenated:
+        # `data` might not be a dict, e.g. for `query_comment`, which accepts
+        # a dict or a string; only snake-case for dict values.
+        if cls._hyphenated and isinstance(data, dict):
             new_dict = {}
             for key in data:
-                if "-" in key:
-                    new_key = key.replace("-", "_")
+                if '-' in key:
+                    new_key = key.replace('-', '_')
                     new_dict[new_key] = data[key]
                 else:
                     new_dict[key] = data[key]
@@ -87,16 +91,16 @@ class dbtClassMixin(DataClassDictMixin, JsonSchemaMixin):
     # hologram and in mashumaro.
     def _local_to_dict(self, **kwargs):
         args = {}
-        if "omit_none" in kwargs:
-            args["omit_none"] = kwargs["omit_none"]
+        if 'omit_none' in kwargs:
+            args['omit_none'] = kwargs['omit_none']
         return self.to_dict(**args)
 
 
 class ValidatedStringMixin(str, SerializableType):
-    ValidationRegex = ""
+    ValidationRegex = ''
 
     @classmethod
-    def _deserialize(cls, value: str) -> "ValidatedStringMixin":
+    def _deserialize(cls, value: str) -> 'ValidatedStringMixin':
         cls.validate(value)
         return ValidatedStringMixin(value)
 

core/dbt/deprecations.py

@@ -14,31 +14,53 @@ class DBTDeprecation:
     def name(self) -> str:
         if self._name is not None:
             return self._name
-        raise NotImplementedError("name not implemented for {}".format(self))
+        raise NotImplementedError(
+            'name not implemented for {}'.format(self)
+        )
 
     def track_deprecation_warn(self) -> None:
         if dbt.tracking.active_user is not None:
-            dbt.tracking.track_deprecation_warn({"deprecation_name": self.name})
+            dbt.tracking.track_deprecation_warn({
+                "deprecation_name": self.name
+            })
 
     @property
     def description(self) -> str:
         if self._description is not None:
             return self._description
-        raise NotImplementedError("description not implemented for {}".format(self))
+        raise NotImplementedError(
+            'description not implemented for {}'.format(self)
+        )
 
     def show(self, *args, **kwargs) -> None:
         if self.name not in active_deprecations:
             desc = self.description.format(**kwargs)
-            msg = ui.line_wrap_message(desc, prefix="* Deprecation Warning: ")
+            msg = ui.line_wrap_message(
+                desc, prefix='* Deprecation Warning: '
+            )
             dbt.exceptions.warn_or_error(msg)
             self.track_deprecation_warn()
             active_deprecations.add(self.name)
 
 
-class MaterializationReturnDeprecation(DBTDeprecation):
-    _name = "materialization-return"
+class DispatchPackagesDeprecation(DBTDeprecation):
+    _name = 'dispatch-packages'
+    _description = '''\
+    The "packages" argument of adapter.dispatch() has been deprecated.
+    Use the "macro_namespace" argument instead.
 
-    _description = """\
+    Raised during dispatch for: {macro_name}
+
+    For more information, see:
+
+    https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch
+    '''
+
+
+class MaterializationReturnDeprecation(DBTDeprecation):
+    _name = 'materialization-return'
+
+    _description = '''\
     The materialization ("{materialization}") did not explicitly return a list
     of relations to add to the cache. By default the target relation will be
     added, but this behavior will be removed in a future version of dbt.
@@ -48,22 +70,22 @@ class MaterializationReturnDeprecation(DBTDeprecation):
     For more information, see:
 
     https://docs.getdbt.com/v0.15/docs/creating-new-materializations#section-6-returning-relations
-    """
+    '''
 
 
 class NotADictionaryDeprecation(DBTDeprecation):
-    _name = "not-a-dictionary"
+    _name = 'not-a-dictionary'
 
-    _description = """\
+    _description = '''\
     The object ("{obj}") was used as a dictionary. In a future version of dbt
     this capability will be removed from objects of this type.
-    """
+    '''
 
 
 class ColumnQuotingDeprecation(DBTDeprecation):
-    _name = "column-quoting-unset"
+    _name = 'column-quoting-unset'
 
-    _description = """\
+    _description = '''\
     The quote_columns parameter was not set for seeds, so the default value of
     False was chosen. The default will change to True in a future release.
 
@@ -72,13 +94,13 @@ class ColumnQuotingDeprecation(DBTDeprecation):
     For more information, see:
 
     https://docs.getdbt.com/v0.15/docs/seeds#section-specify-column-quoting
-    """
+    '''
 
 
 class ModelsKeyNonModelDeprecation(DBTDeprecation):
-    _name = "models-key-mismatch"
+    _name = 'models-key-mismatch'
 
-    _description = """\
+    _description = '''\
     "{node.name}" is a {node.resource_type} node, but it is specified in
     the {patch.yaml_key} section of {patch.original_file_path}.
 
@@ -88,25 +110,33 @@ class ModelsKeyNonModelDeprecation(DBTDeprecation):
     the {expected_key} key instead.
 
     This warning will become an error in a future release.
-    """
+    '''
 
 
 class ExecuteMacrosReleaseDeprecation(DBTDeprecation):
-    _name = "execute-macro-release"
-    _description = """\
+    _name = 'execute-macro-release'
+    _description = '''\
     The "release" argument to execute_macro is now ignored, and will be removed
     in a future relase of dbt. At that time, providing a `release` argument
     will result in an error.
-    """
+    '''
 
 
 class AdapterMacroDeprecation(DBTDeprecation):
-    _name = "adapter-macro"
-    _description = """\
+    _name = 'adapter-macro'
+    _description = '''\
     The "adapter_macro" macro has been deprecated. Instead, use the
     `adapter.dispatch` method to find a macro and call the result.
     adapter_macro was called for: {macro_name}
-    """
+    '''
+
+
+class PackageRedirectDeprecation(DBTDeprecation):
+    _name = 'package-redirect'
+    _description = '''\
+    The `{old_name}` package is deprecated in favor of `{new_name}`. Please update
+    your `packages.yml` configuration to use `{new_name}` instead.
+    '''
 
 
 _adapter_renamed_description = """\
@@ -120,11 +150,11 @@ Documentation for {new_name} can be found here:
 
 
 def renamed_method(old_name: str, new_name: str):
+
     class AdapterDeprecationWarning(DBTDeprecation):
-        _name = "adapter:{}".format(old_name)
-        _description = _adapter_renamed_description.format(
-            old_name=old_name, new_name=new_name
-        )
+        _name = 'adapter:{}'.format(old_name)
+        _description = _adapter_renamed_description.format(old_name=old_name,
+                                                           new_name=new_name)
 
     dep = AdapterDeprecationWarning()
     deprecations_list.append(dep)
@@ -134,7 +164,9 @@ def renamed_method(old_name: str, new_name: str):
 def warn(name, *args, **kwargs):
     if name not in deprecations:
         # this should (hopefully) never happen
-        raise RuntimeError("Error showing deprecation warning: {}".format(name))
+        raise RuntimeError(
+            "Error showing deprecation warning: {}".format(name)
+        )
 
     deprecations[name].show(*args, **kwargs)
 
@@ -145,15 +177,19 @@ def warn(name, *args, **kwargs):
 active_deprecations: Set[str] = set()
 
 deprecations_list: List[DBTDeprecation] = [
+    DispatchPackagesDeprecation(),
     MaterializationReturnDeprecation(),
     NotADictionaryDeprecation(),
     ColumnQuotingDeprecation(),
     ModelsKeyNonModelDeprecation(),
     ExecuteMacrosReleaseDeprecation(),
     AdapterMacroDeprecation(),
+    PackageRedirectDeprecation()
 ]
 
-deprecations: Dict[str, DBTDeprecation] = {d.name: d for d in deprecations_list}
+deprecations: Dict[str, DBTDeprecation] = {
+    d.name: d for d in deprecations_list
+}
 
 
 def reset_deprecations():

core/dbt/deps/base.py

@@ -22,12 +22,12 @@ def downloads_directory():
     # the user might have set an environment variable. Set it to that, and do
     # not remove it when finished.
     if DOWNLOADS_PATH is None:
-        DOWNLOADS_PATH = os.getenv("DBT_DOWNLOADS_DIR")
+        DOWNLOADS_PATH = os.getenv('DBT_DOWNLOADS_DIR')
         remove_downloads = False
     # if we are making a per-run temp directory, remove it at the end of
     # successful runs
     if DOWNLOADS_PATH is None:
-        DOWNLOADS_PATH = tempfile.mkdtemp(prefix="dbt-downloads-")
+        DOWNLOADS_PATH = tempfile.mkdtemp(prefix='dbt-downloads-')
         remove_downloads = True
 
     system.make_directory(DOWNLOADS_PATH)
@@ -62,7 +62,7 @@ class PinnedPackage(BasePackage):
         if not version:
             return self.name
 
-        return "{}@{}".format(self.name, version)
+        return '{}@{}'.format(self.name, version)
 
     @abc.abstractmethod
     def get_version(self) -> Optional[str]:
@@ -93,9 +93,12 @@ class PinnedPackage(BasePackage):
         dest_dirname = self.get_project_name(project, renderer)
         return os.path.join(project.modules_path, dest_dirname)
 
+    def get_subdirectory(self):
+        return None
 
-SomePinned = TypeVar("SomePinned", bound=PinnedPackage)
-SomeUnpinned = TypeVar("SomeUnpinned", bound="UnpinnedPackage")
+
+SomePinned = TypeVar('SomePinned', bound=PinnedPackage)
+SomeUnpinned = TypeVar('SomeUnpinned', bound='UnpinnedPackage')
 
 
 class UnpinnedPackage(Generic[SomePinned], BasePackage):

core/dbt/deps/git.py

@@ -1,6 +1,6 @@
 import os
 import hashlib
-from typing import List
+from typing import List, Optional
 
 from dbt.clients import git, system
 from dbt.config import Project
@@ -8,16 +8,18 @@ from dbt.contracts.project import (
     ProjectPackageMetadata,
     GitPackage,
 )
-from dbt.deps import PinnedPackage, UnpinnedPackage, get_downloads_path
-from dbt.exceptions import ExecutableError, warn_or_error, raise_dependency_error
+from dbt.deps.base import PinnedPackage, UnpinnedPackage, get_downloads_path
+from dbt.exceptions import (
+    ExecutableError, warn_or_error, raise_dependency_error
+)
 from dbt.logger import GLOBAL_LOGGER as logger
 from dbt import ui
 
-PIN_PACKAGE_URL = "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"  # noqa
+PIN_PACKAGE_URL = 'https://docs.getdbt.com/docs/package-management#section-specifying-package-versions' # noqa
 
 
 def md5sum(s: str):
-    return hashlib.md5(s.encode("latin-1")).hexdigest()
+    return hashlib.md5(s.encode('latin-1')).hexdigest()
 
 
 class GitPackageMixin:
@@ -30,29 +32,39 @@ class GitPackageMixin:
         return self.git
 
     def source_type(self) -> str:
-        return "git"
+        return 'git'
 
 
 class GitPinnedPackage(GitPackageMixin, PinnedPackage):
-    def __init__(self, git: str, revision: str, warn_unpinned: bool = True) -> None:
+    def __init__(
+        self,
+        git: str,
+        revision: str,
+        warn_unpinned: bool = True,
+        subdirectory: Optional[str] = None,
+    ) -> None:
         super().__init__(git)
         self.revision = revision
         self.warn_unpinned = warn_unpinned
+        self.subdirectory = subdirectory
         self._checkout_name = md5sum(self.git)
 
     def get_version(self):
         return self.revision
 
+    def get_subdirectory(self):
+        return self.subdirectory
+
     def nice_version_name(self):
-        if self.revision == "HEAD":
-            return "HEAD (default branch)"
+        if self.revision == 'HEAD':
+            return 'HEAD (default revision)'
         else:
-            return "revision {}".format(self.revision)
+            return 'revision {}'.format(self.revision)
 
     def unpinned_msg(self):
-        if self.revision == "HEAD":
-            return "not pinned, using HEAD (default branch)"
-        elif self.revision in ("main", "master"):
+        if self.revision == 'HEAD':
+            return 'not pinned, using HEAD (default branch)'
+        elif self.revision in ('main', 'master'):
             return f'pinned to the "{self.revision}" branch'
         else:
             return None
@@ -64,17 +76,15 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
         the path to the checked out directory."""
         try:
             dir_ = git.clone_and_checkout(
-                self.git,
-                get_downloads_path(),
-                branch=self.revision,
-                dirname=self._checkout_name,
+                self.git, get_downloads_path(), revision=self.revision,
+                dirname=self._checkout_name, subdirectory=self.subdirectory
             )
         except ExecutableError as exc:
-            if exc.cmd and exc.cmd[0] == "git":
+            if exc.cmd and exc.cmd[0] == 'git':
                 logger.error(
-                    "Make sure git is installed on your machine. More "
-                    "information: "
-                    "https://docs.getdbt.com/docs/package-management"
+                    'Make sure git is installed on your machine. More '
+                    'information: '
+                    'https://docs.getdbt.com/docs/package-management'
                 )
             raise
         return os.path.join(get_downloads_path(), dir_)
@@ -85,10 +95,9 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
         if self.unpinned_msg() and self.warn_unpinned:
             warn_or_error(
                 'The git package "{}" \n\tis {}.\n\tThis can introduce '
-                "breaking changes into your project without warning!\n\nSee {}".format(
-                    self.git, self.unpinned_msg(), PIN_PACKAGE_URL
-                ),
-                log_fmt=ui.yellow("WARNING: {}"),
+                'breaking changes into your project without warning!\n\nSee {}'
+                .format(self.git, self.unpinned_msg(), PIN_PACKAGE_URL),
+                log_fmt=ui.yellow('WARNING: {}')
             )
         loaded = Project.from_project_root(path, renderer)
         return ProjectPackageMetadata.from_project(loaded)
@@ -106,46 +115,57 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
 
 class GitUnpinnedPackage(GitPackageMixin, UnpinnedPackage[GitPinnedPackage]):
     def __init__(
-        self, git: str, revisions: List[str], warn_unpinned: bool = True
+        self,
+        git: str,
+        revisions: List[str],
+        warn_unpinned: bool = True,
+        subdirectory: Optional[str] = None,
     ) -> None:
         super().__init__(git)
         self.revisions = revisions
         self.warn_unpinned = warn_unpinned
+        self.subdirectory = subdirectory
 
     @classmethod
-    def from_contract(cls, contract: GitPackage) -> "GitUnpinnedPackage":
+    def from_contract(
+        cls, contract: GitPackage
+    ) -> 'GitUnpinnedPackage':
         revisions = contract.get_revisions()
 
         # we want to map None -> True
         warn_unpinned = contract.warn_unpinned is not False
-        return cls(git=contract.git, revisions=revisions, warn_unpinned=warn_unpinned)
+        return cls(git=contract.git, revisions=revisions,
+                   warn_unpinned=warn_unpinned, subdirectory=contract.subdirectory)
 
     def all_names(self) -> List[str]:
-        if self.git.endswith(".git"):
+        if self.git.endswith('.git'):
             other = self.git[:-4]
         else:
-            other = self.git + ".git"
+            other = self.git + '.git'
         return [self.git, other]
 
-    def incorporate(self, other: "GitUnpinnedPackage") -> "GitUnpinnedPackage":
+    def incorporate(
+        self, other: 'GitUnpinnedPackage'
+    ) -> 'GitUnpinnedPackage':
         warn_unpinned = self.warn_unpinned and other.warn_unpinned
 
         return GitUnpinnedPackage(
             git=self.git,
             revisions=self.revisions + other.revisions,
             warn_unpinned=warn_unpinned,
+            subdirectory=self.subdirectory,
         )
 
     def resolved(self) -> GitPinnedPackage:
         requested = set(self.revisions)
         if len(requested) == 0:
-            requested = {"HEAD"}
+            requested = {'HEAD'}
         elif len(requested) > 1:
             raise_dependency_error(
-                "git dependencies should contain exactly one version. "
-                "{} contains: {}".format(self.git, requested)
-            )
+                'git dependencies should contain exactly one version. '
+                '{} contains: {}'.format(self.git, requested))
 
         return GitPinnedPackage(
-            git=self.git, revision=requested.pop(), warn_unpinned=self.warn_unpinned
+            git=self.git, revision=requested.pop(),
+            warn_unpinned=self.warn_unpinned, subdirectory=self.subdirectory
         )

core/dbt/deps/local.py

@@ -1,7 +1,7 @@
 import shutil
 
 from dbt.clients import system
-from dbt.deps import PinnedPackage, UnpinnedPackage
+from dbt.deps.base import PinnedPackage, UnpinnedPackage
 from dbt.contracts.project import (
     ProjectPackageMetadata,
     LocalPackage,
@@ -19,7 +19,7 @@ class LocalPackageMixin:
         return self.local
 
     def source_type(self):
-        return "local"
+        return 'local'
 
 
 class LocalPinnedPackage(LocalPackageMixin, PinnedPackage):
@@ -30,7 +30,7 @@ class LocalPinnedPackage(LocalPackageMixin, PinnedPackage):
         return None
 
     def nice_version_name(self):
-        return "<local @ {}>".format(self.local)
+        return '<local @ {}>'.format(self.local)
 
     def resolve_path(self, project):
         return system.resolve_path_from_base(
@@ -39,7 +39,9 @@ class LocalPinnedPackage(LocalPackageMixin, PinnedPackage):
         )
 
     def _fetch_metadata(self, project, renderer):
-        loaded = project.from_project_root(self.resolve_path(project), renderer)
+        loaded = project.from_project_root(
+            self.resolve_path(project), renderer
+        )
         return ProjectPackageMetadata.from_project(loaded)
 
     def install(self, project, renderer):
@@ -55,22 +57,27 @@ class LocalPinnedPackage(LocalPackageMixin, PinnedPackage):
                 system.remove_file(dest_path)
 
         if can_create_symlink:
-            logger.debug("  Creating symlink to local dependency.")
+            logger.debug('  Creating symlink to local dependency.')
             system.make_symlink(src_path, dest_path)
 
         else:
-            logger.debug(
-                "  Symlinks are not available on this " "OS, copying dependency."
-            )
+            logger.debug('  Symlinks are not available on this '
+                         'OS, copying dependency.')
             shutil.copytree(src_path, dest_path)
 
 
-class LocalUnpinnedPackage(LocalPackageMixin, UnpinnedPackage[LocalPinnedPackage]):
+class LocalUnpinnedPackage(
+    LocalPackageMixin, UnpinnedPackage[LocalPinnedPackage]
+):
     @classmethod
-    def from_contract(cls, contract: LocalPackage) -> "LocalUnpinnedPackage":
+    def from_contract(
+        cls, contract: LocalPackage
+    ) -> 'LocalUnpinnedPackage':
         return cls(local=contract.local)
 
-    def incorporate(self, other: "LocalUnpinnedPackage") -> "LocalUnpinnedPackage":
+    def incorporate(
+        self, other: 'LocalUnpinnedPackage'
+    ) -> 'LocalUnpinnedPackage':
         return LocalUnpinnedPackage(local=self.local)
 
     def resolved(self) -> LocalPinnedPackage:

core/dbt/deps/registry.py

@@ -7,7 +7,7 @@ from dbt.contracts.project import (
     RegistryPackageMetadata,
     RegistryPackage,
 )
-from dbt.deps import PinnedPackage, UnpinnedPackage, get_downloads_path
+from dbt.deps.base import PinnedPackage, UnpinnedPackage, get_downloads_path
 from dbt.exceptions import (
     package_version_not_found,
     VersionsNotCompatibleException,
@@ -26,26 +26,33 @@ class RegistryPackageMixin:
         return self.package
 
     def source_type(self) -> str:
-        return "hub"
+        return 'hub'
 
 
 class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
-    def __init__(self, package: str, version: str) -> None:
+    def __init__(self,
+                 package: str,
+                 version: str,
+                 version_latest: str) -> None:
         super().__init__(package)
         self.version = version
+        self.version_latest = version_latest
 
     @property
     def name(self):
         return self.package
 
     def source_type(self):
-        return "hub"
+        return 'hub'
 
     def get_version(self):
         return self.version
 
+    def get_version_latest(self):
+        return self.version_latest
+
     def nice_version_name(self):
-        return "version {}".format(self.version)
+        return 'version {}'.format(self.version)
 
     def _fetch_metadata(self, project, renderer) -> RegistryPackageMetadata:
         dct = registry.package_version(self.package, self.version)
@@ -54,12 +61,14 @@ class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
     def install(self, project, renderer):
         metadata = self.fetch_metadata(project, renderer)
 
-        tar_name = "{}.{}.tar.gz".format(self.package, self.version)
-        tar_path = os.path.realpath(os.path.join(get_downloads_path(), tar_name))
+        tar_name = '{}.{}.tar.gz'.format(self.package, self.version)
+        tar_path = os.path.realpath(
+            os.path.join(get_downloads_path(), tar_name)
+        )
         system.make_directory(os.path.dirname(tar_path))
 
         download_url = metadata.downloads.tarball
-        system.download(download_url, tar_path)
+        system.download_with_retries(download_url, tar_path)
         deps_path = project.modules_path
         package_name = self.get_project_name(project, renderer)
         system.untar_package(tar_path, deps_path, package_name)
@@ -68,9 +77,15 @@ class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
 class RegistryUnpinnedPackage(
     RegistryPackageMixin, UnpinnedPackage[RegistryPinnedPackage]
 ):
-    def __init__(self, package: str, versions: List[semver.VersionSpecifier]) -> None:
+    def __init__(
+        self,
+        package: str,
+        versions: List[semver.VersionSpecifier],
+        install_prerelease: bool
+    ) -> None:
         super().__init__(package)
         self.versions = versions
+        self.install_prerelease = install_prerelease
 
     def _check_in_index(self):
         index = registry.index_cached()
@@ -78,17 +93,27 @@ class RegistryUnpinnedPackage(
             package_not_found(self.package)
 
     @classmethod
-    def from_contract(cls, contract: RegistryPackage) -> "RegistryUnpinnedPackage":
+    def from_contract(
+        cls, contract: RegistryPackage
+    ) -> 'RegistryUnpinnedPackage':
         raw_version = contract.get_versions()
 
-        versions = [semver.VersionSpecifier.from_version_string(v) for v in raw_version]
-        return cls(package=contract.package, versions=versions)
+        versions = [
+            semver.VersionSpecifier.from_version_string(v)
+            for v in raw_version
+        ]
+        return cls(
+            package=contract.package,
+            versions=versions,
+            install_prerelease=contract.install_prerelease
+        )
 
     def incorporate(
-        self, other: "RegistryUnpinnedPackage"
-    ) -> "RegistryUnpinnedPackage":
+        self, other: 'RegistryUnpinnedPackage'
+    ) -> 'RegistryUnpinnedPackage':
         return RegistryUnpinnedPackage(
             package=self.package,
+            install_prerelease=self.install_prerelease,
             versions=self.versions + other.versions,
         )
 
@@ -97,16 +122,23 @@ class RegistryUnpinnedPackage(
         try:
             range_ = semver.reduce_versions(*self.versions)
         except VersionsNotCompatibleException as e:
-            new_msg = "Version error for package {}: {}".format(self.name, e)
+            new_msg = ('Version error for package {}: {}'
+                       .format(self.name, e))
             raise DependencyException(new_msg) from e
 
         available = registry.get_available_versions(self.package)
+        installable = semver.filter_installable(
+            available,
+            self.install_prerelease
+        )
+        available_latest = installable[-1]
 
         # for now, pick a version and then recurse. later on,
         # we'll probably want to traverse multiple options
         # so we can match packages. not going to make a difference
         # right now.
-        target = semver.resolve_to_specific_version(range_, available)
+        target = semver.resolve_to_specific_version(range_, installable)
         if not target:
-            package_version_not_found(self.package, range_, available)
-        return RegistryPinnedPackage(package=self.package, version=target)
+            package_version_not_found(self.package, range_, installable)
+        return RegistryPinnedPackage(package=self.package, version=target,
+                                     version_latest=available_latest)

core/dbt/deps/resolver.py

@@ -6,7 +6,7 @@ from dbt.exceptions import raise_dependency_error, InternalException
 from dbt.context.target import generate_target_context
 from dbt.config import Project, RuntimeConfig
 from dbt.config.renderer import DbtProjectYamlRenderer
-from dbt.deps import BasePackage, PinnedPackage, UnpinnedPackage
+from dbt.deps.base import BasePackage, PinnedPackage, UnpinnedPackage
 from dbt.deps.local import LocalUnpinnedPackage
 from dbt.deps.git import GitUnpinnedPackage
 from dbt.deps.registry import RegistryUnpinnedPackage
@@ -49,10 +49,12 @@ class PackageListing:
         key_str: str = self._pick_key(key)
         self.packages[key_str] = value
 
-    def _mismatched_types(self, old: UnpinnedPackage, new: UnpinnedPackage) -> NoReturn:
+    def _mismatched_types(
+        self, old: UnpinnedPackage, new: UnpinnedPackage
+    ) -> NoReturn:
         raise_dependency_error(
-            f"Cannot incorporate {new} ({new.__class__.__name__}) in {old} "
-            f"({old.__class__.__name__}): mismatched types"
+            f'Cannot incorporate {new} ({new.__class__.__name__}) in {old} '
+            f'({old.__class__.__name__}): mismatched types'
         )
 
     def incorporate(self, package: UnpinnedPackage):
@@ -76,14 +78,14 @@ class PackageListing:
                 pkg = RegistryUnpinnedPackage.from_contract(contract)
             else:
                 raise InternalException(
-                    "Invalid package type {}".format(type(contract))
+                    'Invalid package type {}'.format(type(contract))
                 )
             self.incorporate(pkg)
 
     @classmethod
     def from_contracts(
-        cls: Type["PackageListing"], src: List[PackageContract]
-    ) -> "PackageListing":
+        cls: Type['PackageListing'], src: List[PackageContract]
+    ) -> 'PackageListing':
         self = cls({})
         self.update_from(src)
         return self
@@ -106,14 +108,14 @@ def _check_for_duplicate_project_names(
         if project_name in seen:
             raise_dependency_error(
                 f'Found duplicate project "{project_name}". This occurs when '
-                "a dependency has the same project name as some other "
-                "dependency."
+                'a dependency has the same project name as some other '
+                'dependency.'
             )
         elif project_name == config.project_name:
             raise_dependency_error(
-                "Found a dependency with the same name as the root project "
+                'Found a dependency with the same name as the root project '
                 f'"{project_name}". Package names must be unique in a project.'
-                " Please rename one of these packages."
+                ' Please rename one of these packages.'
             )
         seen.add(project_name)
 

core/dbt/flags.py

@@ -1,7 +1,6 @@
 import os
 import multiprocessing
-
-if os.name != "nt":
+if os.name != 'nt':
     # https://bugs.python.org/issue41567
     import multiprocessing.popen_spawn_posix  # type: ignore
 from pathlib import Path
@@ -14,9 +13,11 @@ FULL_REFRESH = None
 USE_CACHE = None
 WARN_ERROR = None
 TEST_NEW_PARSER = None
+USE_EXPERIMENTAL_PARSER = None
 WRITE_JSON = None
 PARTIAL_PARSE = None
 USE_COLORS = None
+STORE_FAILURES = None
 
 
 def env_set_truthy(key: str) -> Optional[str]:
@@ -24,7 +25,7 @@ def env_set_truthy(key: str) -> Optional[str]:
     otherwise.
     """
     value = os.getenv(key)
-    if not value or value.lower() in ("0", "false", "f"):
+    if not value or value.lower() in ('0', 'false', 'f'):
         return None
     return value
 
@@ -37,56 +38,68 @@ def env_set_path(key: str) -> Optional[Path]:
         return Path(value)
 
 
-SINGLE_THREADED_WEBSERVER = env_set_truthy("DBT_SINGLE_THREADED_WEBSERVER")
-SINGLE_THREADED_HANDLER = env_set_truthy("DBT_SINGLE_THREADED_HANDLER")
-MACRO_DEBUGGING = env_set_truthy("DBT_MACRO_DEBUGGING")
-DEFER_MODE = env_set_truthy("DBT_DEFER_TO_STATE")
-ARTIFACT_STATE_PATH = env_set_path("DBT_ARTIFACT_STATE_PATH")
+SINGLE_THREADED_WEBSERVER = env_set_truthy('DBT_SINGLE_THREADED_WEBSERVER')
+SINGLE_THREADED_HANDLER = env_set_truthy('DBT_SINGLE_THREADED_HANDLER')
+MACRO_DEBUGGING = env_set_truthy('DBT_MACRO_DEBUGGING')
+DEFER_MODE = env_set_truthy('DBT_DEFER_TO_STATE')
+ARTIFACT_STATE_PATH = env_set_path('DBT_ARTIFACT_STATE_PATH')
 
 
 def _get_context():
     # TODO: change this back to use fork() on linux when we have made that safe
-    return multiprocessing.get_context("spawn")
+    return multiprocessing.get_context('spawn')
 
 
 MP_CONTEXT = _get_context()
 
 
 def reset():
-    global STRICT_MODE, FULL_REFRESH, USE_CACHE, WARN_ERROR, TEST_NEW_PARSER, WRITE_JSON, PARTIAL_PARSE, MP_CONTEXT, USE_COLORS
+    global STRICT_MODE, FULL_REFRESH, USE_CACHE, WARN_ERROR, TEST_NEW_PARSER, \
+        USE_EXPERIMENTAL_PARSER, WRITE_JSON, PARTIAL_PARSE, MP_CONTEXT, USE_COLORS, \
+        STORE_FAILURES
 
     STRICT_MODE = False
     FULL_REFRESH = False
     USE_CACHE = True
     WARN_ERROR = False
     TEST_NEW_PARSER = False
+    USE_EXPERIMENTAL_PARSER = False
     WRITE_JSON = True
     PARTIAL_PARSE = False
     MP_CONTEXT = _get_context()
     USE_COLORS = True
+    STORE_FAILURES = False
 
 
 def set_from_args(args):
-    global STRICT_MODE, FULL_REFRESH, USE_CACHE, WARN_ERROR, TEST_NEW_PARSER, WRITE_JSON, PARTIAL_PARSE, MP_CONTEXT, USE_COLORS
+    global STRICT_MODE, FULL_REFRESH, USE_CACHE, WARN_ERROR, TEST_NEW_PARSER, \
+        USE_EXPERIMENTAL_PARSER, WRITE_JSON, PARTIAL_PARSE, MP_CONTEXT, USE_COLORS, \
+        STORE_FAILURES
 
-    USE_CACHE = getattr(args, "use_cache", USE_CACHE)
+    USE_CACHE = getattr(args, 'use_cache', USE_CACHE)
 
-    FULL_REFRESH = getattr(args, "full_refresh", FULL_REFRESH)
-    STRICT_MODE = getattr(args, "strict", STRICT_MODE)
-    WARN_ERROR = STRICT_MODE or getattr(args, "warn_error", STRICT_MODE or WARN_ERROR)
+    FULL_REFRESH = getattr(args, 'full_refresh', FULL_REFRESH)
+    STRICT_MODE = getattr(args, 'strict', STRICT_MODE)
+    WARN_ERROR = (
+        STRICT_MODE or
+        getattr(args, 'warn_error', STRICT_MODE or WARN_ERROR)
+    )
 
-    TEST_NEW_PARSER = getattr(args, "test_new_parser", TEST_NEW_PARSER)
-    WRITE_JSON = getattr(args, "write_json", WRITE_JSON)
-    PARTIAL_PARSE = getattr(args, "partial_parse", None)
+    TEST_NEW_PARSER = getattr(args, 'test_new_parser', TEST_NEW_PARSER)
+    USE_EXPERIMENTAL_PARSER = getattr(args, 'use_experimental_parser', USE_EXPERIMENTAL_PARSER)
+    WRITE_JSON = getattr(args, 'write_json', WRITE_JSON)
+    PARTIAL_PARSE = getattr(args, 'partial_parse', None)
     MP_CONTEXT = _get_context()
 
     # The use_colors attribute will always have a value because it is assigned
     # None by default from the add_mutually_exclusive_group function
-    use_colors_override = getattr(args, "use_colors")
+    use_colors_override = getattr(args, 'use_colors')
 
     if use_colors_override is not None:
         USE_COLORS = use_colors_override
 
+    STORE_FAILURES = getattr(args, 'store_failures', STORE_FAILURES)
+
 
 # initialize everything to the defaults on module load
 reset()

core/dbt/graph/cli.py

@@ -2,7 +2,9 @@
 import itertools
 from dbt.clients.yaml_helper import yaml, Loader, Dumper  # noqa: F401
 
-from typing import Dict, List, Optional, Tuple, Any, Union
+from typing import (
+    Dict, List, Optional, Tuple, Any, Union
+)
 
 from dbt.contracts.selection import SelectorDefinition, SelectorFile
 from dbt.exceptions import InternalException, ValidationException
@@ -15,33 +17,34 @@ from .selector_spec import (
     SelectionCriteria,
 )
 
-INTERSECTION_DELIMITER = ","
+INTERSECTION_DELIMITER = ','
 
-DEFAULT_INCLUDES: List[str] = ["fqn:*", "source:*", "exposure:*"]
+DEFAULT_INCLUDES: List[str] = ['fqn:*', 'source:*', 'exposure:*']
 DEFAULT_EXCLUDES: List[str] = []
-DATA_TEST_SELECTOR: str = "test_type:data"
-SCHEMA_TEST_SELECTOR: str = "test_type:schema"
+DATA_TEST_SELECTOR: str = 'test_type:data'
+SCHEMA_TEST_SELECTOR: str = 'test_type:schema'
 
 
-def parse_union(components: List[str], expect_exists: bool) -> SelectionUnion:
+def parse_union(
+    components: List[str], expect_exists: bool, greedy: bool = False
+) -> SelectionUnion:
     # turn ['a b', 'c'] -> ['a', 'b', 'c']
-    raw_specs = itertools.chain.from_iterable(r.split(" ") for r in components)
+    raw_specs = itertools.chain.from_iterable(
+        r.split(' ') for r in components
+    )
     union_components: List[SelectionSpec] = []
 
     # ['a', 'b', 'c,d'] -> union('a', 'b', intersection('c', 'd'))
     for raw_spec in raw_specs:
         intersection_components: List[SelectionSpec] = [
-            SelectionCriteria.from_single_spec(part)
+            SelectionCriteria.from_single_spec(part, greedy=greedy)
             for part in raw_spec.split(INTERSECTION_DELIMITER)
         ]
-        union_components.append(
-            SelectionIntersection(
-                components=intersection_components,
-                expect_exists=expect_exists,
-                raw=raw_spec,
-            )
-        )
-
+        union_components.append(SelectionIntersection(
+            components=intersection_components,
+            expect_exists=expect_exists,
+            raw=raw_spec,
+        ))
     return SelectionUnion(
         components=union_components,
         expect_exists=False,
@@ -50,21 +53,21 @@ def parse_union(components: List[str], expect_exists: bool) -> SelectionUnion:
 
 
 def parse_union_from_default(
-    raw: Optional[List[str]], default: List[str]
+    raw: Optional[List[str]], default: List[str], greedy: bool = False
 ) -> SelectionUnion:
     components: List[str]
     expect_exists: bool
     if raw is None:
-        return parse_union(components=default, expect_exists=False)
+        return parse_union(components=default, expect_exists=False, greedy=greedy)
     else:
-        return parse_union(components=raw, expect_exists=True)
+        return parse_union(components=raw, expect_exists=True, greedy=greedy)
 
 
 def parse_difference(
     include: Optional[List[str]], exclude: Optional[List[str]]
 ) -> SelectionDifference:
     included = parse_union_from_default(include, DEFAULT_INCLUDES)
-    excluded = parse_union_from_default(exclude, DEFAULT_EXCLUDES)
+    excluded = parse_union_from_default(exclude, DEFAULT_EXCLUDES, greedy=True)
     return SelectionDifference(components=[included, excluded])
 
 
@@ -74,7 +77,9 @@ def parse_test_selectors(
     union_components = []
 
     if data:
-        union_components.append(SelectionCriteria.from_single_spec(DATA_TEST_SELECTOR))
+        union_components.append(
+            SelectionCriteria.from_single_spec(DATA_TEST_SELECTOR)
+        )
     if schema:
         union_components.append(
             SelectionCriteria.from_single_spec(SCHEMA_TEST_SELECTOR)
@@ -92,21 +97,27 @@ def parse_test_selectors(
             raw=[DATA_TEST_SELECTOR, SCHEMA_TEST_SELECTOR],
         )
 
-    return SelectionIntersection(components=[base, intersect_with], expect_exists=True)
+    return SelectionIntersection(
+        components=[base, intersect_with], expect_exists=True
+    )
 
 
 RawDefinition = Union[str, Dict[str, Any]]
 
 
-def _get_list_dicts(dct: Dict[str, Any], key: str) -> List[RawDefinition]:
+def _get_list_dicts(
+    dct: Dict[str, Any], key: str
+) -> List[RawDefinition]:
     result: List[RawDefinition] = []
     if key not in dct:
         raise InternalException(
-            f"Expected to find key {key} in dict, only found {list(dct)}"
+            f'Expected to find key {key} in dict, only found {list(dct)}'
         )
     values = dct[key]
     if not isinstance(values, list):
-        raise ValidationException(f'Invalid value for key "{key}". Expected a list.')
+        raise ValidationException(
+            f'Invalid value for key "{key}". Expected a list.'
+        )
     for value in values:
         if isinstance(value, dict):
             for value_key in value:
@@ -121,31 +132,36 @@ def _get_list_dicts(dct: Dict[str, Any], key: str) -> List[RawDefinition]:
         else:
             raise ValidationException(
                 f'Invalid value type {type(value)} in key "{key}", expected '
-                f"dict or str (value: {value})."
+                f'dict or str (value: {value}).'
             )
 
     return result
 
 
 def _parse_exclusions(definition) -> Optional[SelectionSpec]:
-    exclusions = _get_list_dicts(definition, "exclude")
-    parsed_exclusions = [parse_from_definition(excl) for excl in exclusions]
+    exclusions = _get_list_dicts(definition, 'exclude')
+    parsed_exclusions = [
+        parse_from_definition(excl) for excl in exclusions
+    ]
     if len(parsed_exclusions) == 1:
         return parsed_exclusions[0]
     elif len(parsed_exclusions) > 1:
-        return SelectionUnion(components=parsed_exclusions, raw=exclusions)
+        return SelectionUnion(
+            components=parsed_exclusions,
+            raw=exclusions
+        )
     else:
         return None
 
 
 def _parse_include_exclude_subdefs(
-    definitions: List[RawDefinition],
+    definitions: List[RawDefinition]
 ) -> Tuple[List[SelectionSpec], Optional[SelectionSpec]]:
     include_parts: List[SelectionSpec] = []
     diff_arg: Optional[SelectionSpec] = None
 
     for definition in definitions:
-        if isinstance(definition, dict) and "exclude" in definition:
+        if isinstance(definition, dict) and 'exclude' in definition:
             # do not allow multiple exclude: defs at the same level
             if diff_arg is not None:
                 yaml_sel_cfg = yaml.dump(definition)
@@ -161,7 +177,7 @@ def _parse_include_exclude_subdefs(
 
 
 def parse_union_definition(definition: Dict[str, Any]) -> SelectionSpec:
-    union_def_parts = _get_list_dicts(definition, "union")
+    union_def_parts = _get_list_dicts(definition, 'union')
     include, exclude = _parse_include_exclude_subdefs(union_def_parts)
 
     union = SelectionUnion(components=include)
@@ -170,11 +186,16 @@ def parse_union_definition(definition: Dict[str, Any]) -> SelectionSpec:
         union.raw = definition
         return union
     else:
-        return SelectionDifference(components=[union, exclude], raw=definition)
+        return SelectionDifference(
+            components=[union, exclude],
+            raw=definition
+        )
 
 
-def parse_intersection_definition(definition: Dict[str, Any]) -> SelectionSpec:
-    intersection_def_parts = _get_list_dicts(definition, "intersection")
+def parse_intersection_definition(
+    definition: Dict[str, Any]
+) -> SelectionSpec:
+    intersection_def_parts = _get_list_dicts(definition, 'intersection')
     include, exclude = _parse_include_exclude_subdefs(intersection_def_parts)
     intersection = SelectionIntersection(components=include)
 
@@ -182,7 +203,10 @@ def parse_intersection_definition(definition: Dict[str, Any]) -> SelectionSpec:
         intersection.raw = definition
         return intersection
     else:
-        return SelectionDifference(components=[intersection, exclude], raw=definition)
+        return SelectionDifference(
+            components=[intersection, exclude],
+            raw=definition
+        )
 
 
 def parse_dict_definition(definition: Dict[str, Any]) -> SelectionSpec:
@@ -196,14 +220,14 @@ def parse_dict_definition(definition: Dict[str, Any]) -> SelectionSpec:
                 f'"{type(key)}" ({key})'
             )
         dct = {
-            "method": key,
-            "value": value,
+            'method': key,
+            'value': value,
         }
-    elif "method" in definition and "value" in definition:
+    elif 'method' in definition and 'value' in definition:
         dct = definition
-        if "exclude" in definition:
+        if 'exclude' in definition:
             diff_arg = _parse_exclusions(definition)
-            dct = {k: v for k, v in dct.items() if k != "exclude"}
+            dct = {k: v for k, v in dct.items() if k != 'exclude'}
     else:
         raise ValidationException(
             f'Expected either 1 key or else "method" '
@@ -218,14 +242,13 @@ def parse_dict_definition(definition: Dict[str, Any]) -> SelectionSpec:
         return SelectionDifference(components=[base, diff_arg])
 
 
-def parse_from_definition(definition: RawDefinition, rootlevel=False) -> SelectionSpec:
+def parse_from_definition(
+    definition: RawDefinition, rootlevel=False
+) -> SelectionSpec:
 
-    if (
-        isinstance(definition, dict)
-        and ("union" in definition or "intersection" in definition)
-        and rootlevel
-        and len(definition) > 1
-    ):
+    if (isinstance(definition, dict) and
+            ('union' in definition or 'intersection' in definition) and
+            rootlevel and len(definition) > 1):
         keys = ",".join(definition.keys())
         raise ValidationException(
             f"Only a single 'union' or 'intersection' key is allowed "
@@ -233,24 +256,25 @@ def parse_from_definition(definition: RawDefinition, rootlevel=False) -> Selecti
         )
     if isinstance(definition, str):
         return SelectionCriteria.from_single_spec(definition)
-    elif "union" in definition:
+    elif 'union' in definition:
         return parse_union_definition(definition)
-    elif "intersection" in definition:
+    elif 'intersection' in definition:
         return parse_intersection_definition(definition)
     elif isinstance(definition, dict):
         return parse_dict_definition(definition)
     else:
         raise ValidationException(
-            f"Expected to find union, intersection, str or dict, instead "
-            f"found {type(definition)}: {definition}"
+            f'Expected to find union, intersection, str or dict, instead '
+            f'found {type(definition)}: {definition}'
         )
 
 
-def parse_from_selectors_definition(source: SelectorFile) -> Dict[str, SelectionSpec]:
+def parse_from_selectors_definition(
+    source: SelectorFile
+) -> Dict[str, SelectionSpec]:
     result: Dict[str, SelectionSpec] = {}
     selector: SelectorDefinition
     for selector in source.selectors:
-        result[selector.name] = parse_from_definition(
-            selector.definition, rootlevel=True
-        )
+        result[selector.name] = parse_from_definition(selector.definition,
+                                                      rootlevel=True)
     return result

core/dbt/graph/graph.py

@@ -1,16 +1,17 @@
-from typing import Set, Iterable, Iterator, Optional, NewType
+from typing import (
+    Set, Iterable, Iterator, Optional, NewType
+)
 import networkx as nx  # type: ignore
 
 from dbt.exceptions import InternalException
 
-UniqueId = NewType("UniqueId", str)
+UniqueId = NewType('UniqueId', str)
 
 
 class Graph:
     """A wrapper around the networkx graph that understands SelectionCriteria
     and how they interact with the graph.
     """
-
     def __init__(self, graph):
         self.graph = graph
 
@@ -28,11 +29,12 @@ class Graph:
     ) -> Set[UniqueId]:
         """Returns all nodes having a path to `node` in `graph`"""
         if not self.graph.has_node(node):
-            raise InternalException(f"Node {node} not found in the graph!")
+            raise InternalException(f'Node {node} not found in the graph!')
         with nx.utils.reversed(self.graph):
-            anc = nx.single_source_shortest_path_length(
-                G=self.graph, source=node, cutoff=max_depth
-            ).keys()
+            anc = nx.single_source_shortest_path_length(G=self.graph,
+                                                        source=node,
+                                                        cutoff=max_depth)\
+                .keys()
         return anc - {node}
 
     def descendants(
@@ -40,13 +42,16 @@ class Graph:
     ) -> Set[UniqueId]:
         """Returns all nodes reachable from `node` in `graph`"""
         if not self.graph.has_node(node):
-            raise InternalException(f"Node {node} not found in the graph!")
-        des = nx.single_source_shortest_path_length(
-            G=self.graph, source=node, cutoff=max_depth
-        ).keys()
+            raise InternalException(f'Node {node} not found in the graph!')
+        des = nx.single_source_shortest_path_length(G=self.graph,
+                                                    source=node,
+                                                    cutoff=max_depth)\
+            .keys()
         return des - {node}
 
-    def select_childrens_parents(self, selected: Set[UniqueId]) -> Set[UniqueId]:
+    def select_childrens_parents(
+        self, selected: Set[UniqueId]
+    ) -> Set[UniqueId]:
         ancestors_for = self.select_children(selected) | selected
         return self.select_parents(ancestors_for) | ancestors_for
 
@@ -72,7 +77,7 @@ class Graph:
             successors.update(self.graph.successors(node))
         return successors
 
-    def get_subset_graph(self, selected: Iterable[UniqueId]) -> "Graph":
+    def get_subset_graph(self, selected: Iterable[UniqueId]) -> 'Graph':
         """Create and return a new graph that is a shallow copy of the graph,
         but with only the nodes in include_nodes. Transitive edges across
         removed nodes are preserved as explicit new edges.
@@ -93,7 +98,7 @@ class Graph:
                 )
         return Graph(new_graph)
 
-    def subgraph(self, nodes: Iterable[UniqueId]) -> "Graph":
+    def subgraph(self, nodes: Iterable[UniqueId]) -> 'Graph':
         return Graph(self.graph.subgraph(nodes))
 
     def get_dependent_nodes(self, node: UniqueId):

core/dbt/graph/queue.py

@@ -1,8 +1,8 @@
-import threading
-from queue import PriorityQueue
-from typing import Dict, Set, Optional
-
 import networkx as nx  # type: ignore
+import threading
+
+from queue import PriorityQueue
+from typing import Dict, Set, List, Generator, Optional
 
 from .graph import UniqueId
 from dbt.contracts.graph.parsed import ParsedSourceDefinition, ParsedExposure
@@ -34,7 +34,7 @@ class GraphQueue:
         # this lock controls most things
         self.lock = threading.Lock()
         # store the 'score' of each node as a number. Lower is higher priority.
-        self._scores = self._calculate_scores()
+        self._scores = self._get_scores(self.graph)
         # populate the initial queue
         self._find_new_additions()
         # awaits after task end
@@ -53,33 +53,59 @@ class GraphQueue:
             return False
         return True
 
-    def _calculate_scores(self) -> Dict[UniqueId, int]:
-        """Calculate the 'value' of each node in the graph based on how many
-        blocking descendants it has. We use this score for the internal
-        priority queue's ordering, so the quality of this metric is important.
+    @staticmethod
+    def _grouped_topological_sort(
+        graph: nx.DiGraph,
+    ) -> Generator[List[str], None, None]:
+        """Topological sort of given graph that groups ties.
 
-        The score is stored as a negative number because the internal
-        PriorityQueue picks lowest values first.
+        Adapted from `nx.topological_sort`, this function returns a topo sort of a graph however
+        instead of arbitrarily ordering ties in the sort order, ties are grouped together in
+        lists.
 
-        We could do this in one pass over the graph instead of len(self.graph)
-        passes but this is easy. For large graphs this may hurt performance.
+        Args:
+            graph: The graph to be sorted.
 
-        This operates on the graph, so it would require a lock if called from
-        outside __init__.
-
-        :return Dict[str, int]: The score dict, mapping unique IDs to integer
-            scores. Lower scores are higher priority.
+        Returns:
+            A generator that yields lists of nodes, one list per graph depth level.
         """
+        indegree_map = {v: d for v, d in graph.in_degree() if d > 0}
+        zero_indegree = [v for v, d in graph.in_degree() if d == 0]
+
+        while zero_indegree:
+            yield zero_indegree
+            new_zero_indegree = []
+            for v in zero_indegree:
+                for _, child in graph.edges(v):
+                    indegree_map[child] -= 1
+                    if not indegree_map[child]:
+                        new_zero_indegree.append(child)
+            zero_indegree = new_zero_indegree
+
+    def _get_scores(self, graph: nx.DiGraph) -> Dict[str, int]:
+        """Scoring nodes for processing order.
+
+        Scores are calculated by the graph depth level. Lowest score (0) should be processed first.
+
+        Args:
+            graph: The graph to be scored.
+
+        Returns:
+            A dictionary consisting of `node name`:`score` pairs.
+        """
+        # split graph by connected subgraphs
+        subgraphs = (
+            graph.subgraph(x) for x in nx.connected_components(nx.Graph(graph))
+        )
+
+        # score all nodes in all subgraphs
         scores = {}
-        for node in self.graph.nodes():
-            score = -1 * len(
-                [
-                    d
-                    for d in nx.descendants(self.graph, node)
-                    if self._include_in_cost(d)
-                ]
-            )
-            scores[node] = score
+        for subgraph in subgraphs:
+            grouped_nodes = self._grouped_topological_sort(subgraph)
+            for level, group in enumerate(grouped_nodes):
+                for node in group:
+                    scores[node] = level
+
         return scores
 
     def get(
@@ -133,8 +159,6 @@ class GraphQueue:
     def _find_new_additions(self) -> None:
         """Find any nodes in the graph that need to be added to the internal
         queue and add them.
-
-        Callers must hold the lock.
         """
         for node, in_degree in self.graph.in_degree():
             if not self._already_known(node) and in_degree == 0:

core/dbt/graph/selector.py

@@ -1,4 +1,5 @@
-from typing import Set, List, Optional
+
+from typing import Set, List, Optional, Tuple
 
 from .graph import Graph, UniqueId
 from .queue import GraphQueue
@@ -24,13 +25,26 @@ def get_package_names(nodes):
 def alert_non_existence(raw_spec, nodes):
     if len(nodes) == 0:
         warn_or_error(
-            f"The selection criterion '{str(raw_spec)}' does not match" f" any nodes"
+            f"The selection criterion '{str(raw_spec)}' does not match"
+            f" any nodes"
         )
 
 
-class NodeSelector(MethodManager):
-    """The node selector is aware of the graph and manifest,"""
+def can_select_indirectly(node):
+    """If a node is not selected itself, but its parent(s) are, it may qualify
+    for indirect selection.
+    Today, only Test nodes can be indirectly selected. In the future,
+    other node types or invocation flags might qualify.
+    """
+    if node.resource_type == NodeType.Test:
+        return True
+    else:
+        return False
 
+
+class NodeSelector(MethodManager):
+    """The node selector is aware of the graph and manifest,
+    """
     def __init__(
         self,
         graph: Graph,
@@ -43,16 +57,13 @@ class NodeSelector(MethodManager):
         # build a subgraph containing only non-empty, enabled nodes and enabled
         # sources.
         graph_members = {
-            unique_id
-            for unique_id in self.full_graph.nodes()
+            unique_id for unique_id in self.full_graph.nodes()
             if self._is_graph_member(unique_id)
         }
         self.graph = self.full_graph.subgraph(graph_members)
 
     def select_included(
-        self,
-        included_nodes: Set[UniqueId],
-        spec: SelectionCriteria,
+        self, included_nodes: Set[UniqueId], spec: SelectionCriteria,
     ) -> Set[UniqueId]:
         """Select the explicitly included nodes, using the given spec. Return
         the selected set of unique IDs.
@@ -62,8 +73,8 @@ class NodeSelector(MethodManager):
 
     def get_nodes_from_criteria(
         self,
-        spec: SelectionCriteria,
-    ) -> Set[UniqueId]:
+        spec: SelectionCriteria
+    ) -> Tuple[Set[UniqueId], Set[UniqueId]]:
         """Get all nodes specified by the single selection criteria.
 
         - collect the directly included nodes
@@ -80,11 +91,14 @@ class NodeSelector(MethodManager):
                 f"The '{spec.method}' selector specified in {spec.raw} is "
                 f"invalid. Must be one of [{valid_selectors}]"
             )
-            return set()
+            return set(), set()
 
-        extras = self.collect_specified_neighbors(spec, collected)
-        result = self.expand_selection(collected | extras)
-        return result
+        neighbors = self.collect_specified_neighbors(spec, collected)
+        direct_nodes, indirect_nodes = self.expand_selection(
+            selected=(collected | neighbors),
+            greedy=spec.greedy
+        )
+        return direct_nodes, indirect_nodes
 
     def collect_specified_neighbors(
         self, spec: SelectionCriteria, selected: Set[UniqueId]
@@ -107,21 +121,46 @@ class NodeSelector(MethodManager):
             additional.update(self.graph.select_children(selected, depth))
         return additional
 
-    def select_nodes(self, spec: SelectionSpec) -> Set[UniqueId]:
-        """Select the nodes in the graph according to the spec.
-
-        If the spec is a composite spec (a union, difference, or intersection),
+    def select_nodes_recursively(self, spec: SelectionSpec) -> Tuple[Set[UniqueId], Set[UniqueId]]:
+        """If the spec is a composite spec (a union, difference, or intersection),
         recurse into its selections and combine them. If the spec is a concrete
         selection criteria, resolve that using the given graph.
         """
         if isinstance(spec, SelectionCriteria):
-            result = self.get_nodes_from_criteria(spec)
+            direct_nodes, indirect_nodes = self.get_nodes_from_criteria(spec)
         else:
-            node_selections = [self.select_nodes(component) for component in spec]
-            result = spec.combined(node_selections)
+            bundles = [
+                self.select_nodes_recursively(component)
+                for component in spec
+            ]
+
+            direct_sets = []
+            indirect_sets = []
+
+            for direct, indirect in bundles:
+                direct_sets.append(direct)
+                indirect_sets.append(direct | indirect)
+
+            initial_direct = spec.combined(direct_sets)
+            indirect_nodes = spec.combined(indirect_sets)
+
+            direct_nodes = self.incorporate_indirect_nodes(initial_direct, indirect_nodes)
+
             if spec.expect_exists:
-                alert_non_existence(spec.raw, result)
-        return result
+                alert_non_existence(spec.raw, direct_nodes)
+
+        return direct_nodes, indirect_nodes
+
+    def select_nodes(self, spec: SelectionSpec) -> Set[UniqueId]:
+        """Select the nodes in the graph according to the spec.
+
+        This is the main point of entry for turning a spec into a set of nodes:
+        - Recurse through spec, select by criteria, combine by set operation
+        - Return final (unfiltered) selection set
+        """
+
+        direct_nodes, indirect_nodes = self.select_nodes_recursively(spec)
+        return direct_nodes
 
     def _is_graph_member(self, unique_id: UniqueId) -> bool:
         if unique_id in self.manifest.sources:
@@ -147,30 +186,77 @@ class NodeSelector(MethodManager):
         elif unique_id in self.manifest.exposures:
             node = self.manifest.exposures[unique_id]
         else:
-            raise InternalException(f"Node {unique_id} not found in the manifest!")
+            raise InternalException(
+                f'Node {unique_id} not found in the manifest!'
+            )
         return self.node_is_match(node)
 
     def filter_selection(self, selected: Set[UniqueId]) -> Set[UniqueId]:
         """Return the subset of selected nodes that is a match for this
         selector.
         """
-        return {unique_id for unique_id in selected if self._is_match(unique_id)}
+        return {
+            unique_id for unique_id in selected if self._is_match(unique_id)
+        }
+
+    def expand_selection(
+        self, selected: Set[UniqueId], greedy: bool = False
+    ) -> Tuple[Set[UniqueId], Set[UniqueId]]:
+        # Test selection can expand to include an implicitly/indirectly selected test.
+        # In this way, `dbt test -m model_a` also includes tests that directly depend on `model_a`.
+        # Expansion has two modes, GREEDY and NOT GREEDY.
+        #
+        # GREEDY mode: If ANY parent is selected, select the test. We use this for EXCLUSION.
+        #
+        # NOT GREEDY mode:
+        #  - If ALL parents are selected, select the test.
+        #  - If ANY parent is missing, return it separately. We'll keep it around
+        #    for later and see if its other parents show up.
+        # We use this for INCLUSION.
+
+        direct_nodes = set(selected)
+        indirect_nodes = set()
+
+        for unique_id in self.graph.select_successors(selected):
+            if unique_id in self.manifest.nodes:
+                node = self.manifest.nodes[unique_id]
+                if can_select_indirectly(node):
+                    # should we add it in directly?
+                    if greedy or set(node.depends_on.nodes) <= set(selected):
+                        direct_nodes.add(unique_id)
+                    # if not:
+                    else:
+                        indirect_nodes.add(unique_id)
+
+        return direct_nodes, indirect_nodes
+
+    def incorporate_indirect_nodes(
+        self, direct_nodes: Set[UniqueId], indirect_nodes: Set[UniqueId] = set()
+    ) -> Set[UniqueId]:
+        # Check tests previously selected indirectly to see if ALL their
+        # parents are now present.
+
+        selected = set(direct_nodes)
+
+        for unique_id in indirect_nodes:
+            if unique_id in self.manifest.nodes:
+                node = self.manifest.nodes[unique_id]
+                if set(node.depends_on.nodes) <= set(selected):
+                    selected.add(unique_id)
 
-    def expand_selection(self, selected: Set[UniqueId]) -> Set[UniqueId]:
-        """Perform selector-specific expansion."""
         return selected
 
     def get_selected(self, spec: SelectionSpec) -> Set[UniqueId]:
-        """get_selected runs trhough the node selection process:
+        """get_selected runs through the node selection process:
 
-        - node selection. Based on the include/exclude sets, the set
-            of matched unique IDs is returned
-            - expand the graph at each leaf node, before combination
-                - selectors might override this. for example, this is where
-                    tests are added
-        - filtering:
-            - selectors can filter the nodes after all of them have been
-              selected
+            - node selection. Based on the include/exclude sets, the set
+                of matched unique IDs is returned
+                - expand the graph at each leaf node, before combination
+                    - selectors might override this. for example, this is where
+                        tests are added
+            - filtering:
+                - selectors can filter the nodes after all of them have been
+                  selected
         """
         selected_nodes = self.select_nodes(spec)
         filtered_nodes = self.filter_selection(selected_nodes)

core/dbt/graph/selector_methods.py

@@ -22,52 +22,48 @@ from dbt.contracts.graph.parsed import (
     ParsedSourceDefinition,
 )
 from dbt.contracts.state import PreviousState
-from dbt.logger import GLOBAL_LOGGER as logger
 from dbt.exceptions import (
     InternalException,
     RuntimeException,
 )
 from dbt.node_types import NodeType
-from dbt.ui import warning_tag
 
 
-SELECTOR_GLOB = "*"
-SELECTOR_DELIMITER = ":"
+SELECTOR_GLOB = '*'
+SELECTOR_DELIMITER = ':'
 
 
 class MethodName(StrEnum):
-    FQN = "fqn"
-    Tag = "tag"
-    Source = "source"
-    Path = "path"
-    Package = "package"
-    Config = "config"
-    TestName = "test_name"
-    TestType = "test_type"
-    ResourceType = "resource_type"
-    State = "state"
-    Exposure = "exposure"
+    FQN = 'fqn'
+    Tag = 'tag'
+    Source = 'source'
+    Path = 'path'
+    Package = 'package'
+    Config = 'config'
+    TestName = 'test_name'
+    TestType = 'test_type'
+    ResourceType = 'resource_type'
+    State = 'state'
+    Exposure = 'exposure'
 
 
-def is_selected_node(real_node, node_selector):
-    for i, selector_part in enumerate(node_selector):
+def is_selected_node(fqn: List[str], node_selector: str):
 
-        is_last = i == len(node_selector) - 1
+    # If qualified_name exactly matches model name (fqn's leaf), return True
+    if fqn[-1] == node_selector:
+        return True
+    # Flatten node parts. Dots in model names act as namespace separators
+    flat_fqn = [item for segment in fqn for item in segment.split('.')]
+    # Selector components cannot be more than fqn's
+    if len(flat_fqn) < len(node_selector.split('.')):
+        return False
 
+    for i, selector_part in enumerate(node_selector.split('.')):
         # if we hit a GLOB, then this node is selected
         if selector_part == SELECTOR_GLOB:
             return True
-
-        # match package.node_name or package.dir.node_name
-        elif is_last and selector_part == real_node[-1]:
-            return True
-
-        elif len(real_node) <= i:
-            return False
-
-        elif real_node[i] == selector_part:
+        elif flat_fqn[i] == selector_part:
             continue
-
         else:
             return False
 
@@ -83,14 +79,15 @@ class SelectorMethod(metaclass=abc.ABCMeta):
         self,
         manifest: Manifest,
         previous_state: Optional[PreviousState],
-        arguments: List[str],
+        arguments: List[str]
     ):
         self.manifest: Manifest = manifest
         self.previous_state = previous_state
         self.arguments: List[str] = arguments
 
     def parsed_nodes(
-        self, included_nodes: Set[UniqueId]
+        self,
+        included_nodes: Set[UniqueId]
     ) -> Iterator[Tuple[UniqueId, ManifestNode]]:
 
         for key, node in self.manifest.nodes.items():
@@ -100,7 +97,8 @@ class SelectorMethod(metaclass=abc.ABCMeta):
             yield unique_id, node
 
     def source_nodes(
-        self, included_nodes: Set[UniqueId]
+        self,
+        included_nodes: Set[UniqueId]
     ) -> Iterator[Tuple[UniqueId, ParsedSourceDefinition]]:
 
         for key, source in self.manifest.sources.items():
@@ -110,7 +108,8 @@ class SelectorMethod(metaclass=abc.ABCMeta):
             yield unique_id, source
 
     def exposure_nodes(
-        self, included_nodes: Set[UniqueId]
+        self,
+        included_nodes: Set[UniqueId]
     ) -> Iterator[Tuple[UniqueId, ParsedExposure]]:
 
         for key, exposure in self.manifest.exposures.items():
@@ -120,28 +119,26 @@ class SelectorMethod(metaclass=abc.ABCMeta):
             yield unique_id, exposure
 
     def all_nodes(
-        self, included_nodes: Set[UniqueId]
+        self,
+        included_nodes: Set[UniqueId]
     ) -> Iterator[Tuple[UniqueId, SelectorTarget]]:
-        yield from chain(
-            self.parsed_nodes(included_nodes),
-            self.source_nodes(included_nodes),
-            self.exposure_nodes(included_nodes),
-        )
+        yield from chain(self.parsed_nodes(included_nodes),
+                         self.source_nodes(included_nodes),
+                         self.exposure_nodes(included_nodes))
 
     def configurable_nodes(
-        self, included_nodes: Set[UniqueId]
+        self,
+        included_nodes: Set[UniqueId]
     ) -> Iterator[Tuple[UniqueId, CompileResultNode]]:
-        yield from chain(
-            self.parsed_nodes(included_nodes), self.source_nodes(included_nodes)
-        )
+        yield from chain(self.parsed_nodes(included_nodes),
+                         self.source_nodes(included_nodes))
 
     def non_source_nodes(
         self,
         included_nodes: Set[UniqueId],
     ) -> Iterator[Tuple[UniqueId, Union[ParsedExposure, ManifestNode]]]:
-        yield from chain(
-            self.parsed_nodes(included_nodes), self.exposure_nodes(included_nodes)
-        )
+        yield from chain(self.parsed_nodes(included_nodes),
+                         self.exposure_nodes(included_nodes))
 
     @abc.abstractmethod
     def search(
@@ -149,35 +146,24 @@ class SelectorMethod(metaclass=abc.ABCMeta):
         included_nodes: Set[UniqueId],
         selector: str,
     ) -> Iterator[UniqueId]:
-        raise NotImplementedError("subclasses should implement this")
+        raise NotImplementedError('subclasses should implement this')
 
 
 class QualifiedNameSelectorMethod(SelectorMethod):
-    def node_is_match(
-        self,
-        qualified_name: List[str],
-        package_names: Set[str],
-        fqn: List[str],
-    ) -> bool:
-        """Determine if a qualfied name matches an fqn, given the set of package
+    def node_is_match(self, qualified_name: str, fqn: List[str]) -> bool:
+        """Determine if a qualified name matches an fqn for all package
         names in the graph.
 
-        :param List[str] qualified_name: The components of the selector or node
-            name, split on '.'.
-        :param Set[str] package_names: The set of pacakge names in the graph.
+        :param str qualified_name: The qualified name to match the nodes with
         :param List[str] fqn: The node's fully qualified name in the graph.
         """
-        if len(qualified_name) == 1 and fqn[-1] == qualified_name[0]:
+        unscoped_fqn = fqn[1:]
+
+        if is_selected_node(fqn, qualified_name):
+            return True
+        # Match nodes across different packages
+        elif is_selected_node(unscoped_fqn, qualified_name):
             return True
-
-        if qualified_name[0] in package_names:
-            if is_selected_node(fqn, qualified_name):
-                return True
-
-        for package_name in package_names:
-            local_qualified_node_name = [package_name] + qualified_name
-            if is_selected_node(fqn, local_qualified_node_name):
-                return True
 
         return False
 
@@ -188,15 +174,9 @@ class QualifiedNameSelectorMethod(SelectorMethod):
 
         :param str selector: The selector or node name
         """
-        qualified_name = selector.split(".")
         parsed_nodes = list(self.parsed_nodes(included_nodes))
-        package_names = {n.package_name for _, n in parsed_nodes}
         for node, real_node in parsed_nodes:
-            if self.node_is_match(
-                qualified_name,
-                package_names,
-                real_node.fqn,
-            ):
+            if self.node_is_match(selector, real_node.fqn):
                 yield node
 
 
@@ -215,7 +195,7 @@ class SourceSelectorMethod(SelectorMethod):
         self, included_nodes: Set[UniqueId], selector: str
     ) -> Iterator[UniqueId]:
         """yields nodes from included are the specified source."""
-        parts = selector.split(".")
+        parts = selector.split('.')
         target_package = SELECTOR_GLOB
         if len(parts) == 1:
             target_source, target_table = parts[0], None
@@ -226,9 +206,9 @@ class SourceSelectorMethod(SelectorMethod):
         else:  # len(parts) > 3 or len(parts) == 0
             msg = (
                 'Invalid source selector value "{}". Sources must be of the '
-                "form `${{source_name}}`, "
-                "`${{source_name}}.${{target_name}}`, or "
-                "`${{package_name}}.${{source_name}}.${{target_name}}"
+                'form `${{source_name}}`, '
+                '`${{source_name}}.${{target_name}}`, or '
+                '`${{package_name}}.${{source_name}}.${{target_name}}'
             ).format(selector)
             raise RuntimeException(msg)
 
@@ -247,7 +227,7 @@ class ExposureSelectorMethod(SelectorMethod):
     def search(
         self, included_nodes: Set[UniqueId], selector: str
     ) -> Iterator[UniqueId]:
-        parts = selector.split(".")
+        parts = selector.split('.')
         target_package = SELECTOR_GLOB
         if len(parts) == 1:
             target_name = parts[0]
@@ -256,8 +236,8 @@ class ExposureSelectorMethod(SelectorMethod):
         else:
             msg = (
                 'Invalid exposure selector value "{}". Exposures must be of '
-                "the form ${{exposure_name}} or "
-                "${{exposure_package.exposure_name}}"
+                'the form ${{exposure_name}} or '
+                '${{exposure_package.exposure_name}}'
             ).format(selector)
             raise RuntimeException(msg)
 
@@ -274,7 +254,9 @@ class PathSelectorMethod(SelectorMethod):
     def search(
         self, included_nodes: Set[UniqueId], selector: str
     ) -> Iterator[UniqueId]:
-        """Yields nodes from inclucded that match the given path."""
+        """Yields nodes from inclucded that match the given path.
+
+        """
         # use '.' and not 'root' for easy comparison
         root = Path.cwd()
         paths = set(p.relative_to(root) for p in root.glob(selector))
@@ -333,7 +315,7 @@ class ConfigSelectorMethod(SelectorMethod):
         parts = self.arguments
         # special case: if the user wanted to compare test severity,
         # make the comparison case-insensitive
-        if parts == ["severity"]:
+        if parts == ['severity']:
             selector = CaseInsensitive(selector)
 
         # search sources is kind of useless now source configs only have
@@ -379,13 +361,14 @@ class TestTypeSelectorMethod(SelectorMethod):
         self, included_nodes: Set[UniqueId], selector: str
     ) -> Iterator[UniqueId]:
         search_types: Tuple[Type, ...]
-        if selector == "schema":
+        if selector == 'schema':
             search_types = (ParsedSchemaTestNode, CompiledSchemaTestNode)
-        elif selector == "data":
+        elif selector == 'data':
             search_types = (ParsedDataTestNode, CompiledDataTestNode)
         else:
             raise RuntimeException(
-                f'Invalid test type selector {selector}: expected "data" or ' '"schema"'
+                f'Invalid test type selector {selector}: expected "data" or '
+                '"schema"'
             )
 
         for node, real_node in self.parsed_nodes(included_nodes):
@@ -396,57 +379,87 @@ class TestTypeSelectorMethod(SelectorMethod):
 class StateSelectorMethod(SelectorMethod):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
-        self.macros_were_modified: Optional[List[str]] = None
+        self.modified_macros: Optional[List[str]] = None
 
     def _macros_modified(self) -> List[str]:
         # we checked in the caller!
         if self.previous_state is None or self.previous_state.manifest is None:
-            raise InternalException("No comparison manifest in _macros_modified")
+            raise InternalException(
+                'No comparison manifest in _macros_modified'
+            )
         old_macros = self.previous_state.manifest.macros
         new_macros = self.manifest.macros
 
         modified = []
         for uid, macro in new_macros.items():
-            name = f"{macro.package_name}.{macro.name}"
             if uid in old_macros:
                 old_macro = old_macros[uid]
                 if macro.macro_sql != old_macro.macro_sql:
-                    modified.append(f"{name} changed")
+                    modified.append(uid)
             else:
-                modified.append(f"{name} added")
+                modified.append(uid)
 
         for uid, macro in old_macros.items():
             if uid not in new_macros:
-                modified.append(f"{macro.package_name}.{macro.name} removed")
+                modified.append(uid)
 
-        return modified[:3]
+        return modified
 
-    def check_modified(
-        self,
-        old: Optional[SelectorTarget],
-        new: SelectorTarget,
+    def recursively_check_macros_modified(self, node):
+        # check if there are any changes in macros the first time
+        if self.modified_macros is None:
+            self.modified_macros = self._macros_modified()
+
+        # loop through all macros that this node depends on
+        for macro_uid in node.depends_on.macros:
+            # is this macro one of the modified macros?
+            if macro_uid in self.modified_macros:
+                return True
+            # if not, and this macro depends on other macros, keep looping
+            macro = self.manifest.macros[macro_uid]
+            if len(macro.depends_on.macros) > 0:
+                return self.recursively_check_macros_modified(macro)
+            else:
+                return False
+        return False
+
+    def check_modified(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
+        different_contents = not new.same_contents(old)  # type: ignore
+        upstream_macro_change = self.recursively_check_macros_modified(new)
+        return different_contents or upstream_macro_change
+
+    def check_modified_body(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
+        if hasattr(new, "same_body"):
+            return not new.same_body(old)  # type: ignore
+        else:
+            return False
+
+    def check_modified_configs(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
+        if hasattr(new, "same_config"):
+            return not new.same_config(old)  # type: ignore
+        else:
+            return False
+
+    def check_modified_persisted_descriptions(
+        self, old: Optional[SelectorTarget], new: SelectorTarget
     ) -> bool:
-        # check if there are any changes in macros, if so, log a warning the
-        # first time
-        if self.macros_were_modified is None:
-            self.macros_were_modified = self._macros_modified()
-            if self.macros_were_modified:
-                log_str = ", ".join(self.macros_were_modified)
-                logger.warning(
-                    warning_tag(
-                        f"During a state comparison, dbt detected a change in "
-                        f"macros. This will not be marked as a modification. Some "
-                        f"macros: {log_str}"
-                    )
-                )
+        if hasattr(new, "same_persisted_description"):
+            return not new.same_persisted_description(old)  # type: ignore
+        else:
+            return False
 
-        return not new.same_contents(old)  # type: ignore
-
-    def check_new(
-        self,
-        old: Optional[SelectorTarget],
-        new: SelectorTarget,
+    def check_modified_relation(
+        self, old: Optional[SelectorTarget], new: SelectorTarget
     ) -> bool:
+        if hasattr(new, "same_database_representation"):
+            return not new.same_database_representation(old)  # type: ignore
+        else:
+            return False
+
+    def check_modified_macros(self, _, new: SelectorTarget) -> bool:
+        return self.recursively_check_macros_modified(new)
+
+    def check_new(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
         return old is None
 
     def search(
@@ -454,12 +467,19 @@ class StateSelectorMethod(SelectorMethod):
     ) -> Iterator[UniqueId]:
         if self.previous_state is None or self.previous_state.manifest is None:
             raise RuntimeException(
-                "Got a state selector method, but no comparison manifest"
+                'Got a state selector method, but no comparison manifest'
             )
 
         state_checks = {
-            "modified": self.check_modified,
-            "new": self.check_new,
+            # it's new if there is no old version
+            'new': lambda old, _: old is None,
+            # use methods defined above to compare properties of old + new
+            'modified': self.check_modified,
+            'modified.body': self.check_modified_body,
+            'modified.configs': self.check_modified_configs,
+            'modified.persisted_descriptions': self.check_modified_persisted_descriptions,
+            'modified.relation': self.check_modified_relation,
+            'modified.macros': self.check_modified_macros,
         }
         if selector in state_checks:
             checker = state_checks[selector]
@@ -513,7 +533,7 @@ class MethodManager:
         if method not in self.SELECTOR_METHODS:
             raise InternalException(
                 f'Method name "{method}" is a valid node selection '
-                f"method name, but it is not handled"
+                f'method name, but it is not handled'
             )
         cls: Type[SelectorMethod] = self.SELECTOR_METHODS[method]
         return cls(self.manifest, self.previous_state, method_arguments)

core/dbt/graph/selector_spec.py

@@ -3,21 +3,23 @@ import re
 from abc import ABCMeta, abstractmethod
 from dataclasses import dataclass
 
-from typing import Set, Iterator, List, Optional, Dict, Union, Any, Iterable, Tuple
+from typing import (
+    Set, Iterator, List, Optional, Dict, Union, Any, Iterable, Tuple
+)
 from .graph import UniqueId
 from .selector_methods import MethodName
 from dbt.exceptions import RuntimeException, InvalidSelectorException
 
 
 RAW_SELECTOR_PATTERN = re.compile(
-    r"\A"
-    r"(?P<childrens_parents>(\@))?"
-    r"(?P<parents>((?P<parents_depth>(\d*))\+))?"
-    r"((?P<method>([\w.]+)):)?(?P<value>(.*?))"
-    r"(?P<children>(\+(?P<children_depth>(\d*))))?"
-    r"\Z"
+    r'\A'
+    r'(?P<childrens_parents>(\@))?'
+    r'(?P<parents>((?P<parents_depth>(\d*))\+))?'
+    r'((?P<method>([\w.]+)):)?(?P<value>(.*?))'
+    r'(?P<children>(\+(?P<children_depth>(\d*))))?'
+    r'\Z'
 )
-SELECTOR_METHOD_SEPARATOR = "."
+SELECTOR_METHOD_SEPARATOR = '.'
 
 
 def _probably_path(value: str):
@@ -41,15 +43,15 @@ def _match_to_int(match: Dict[str, str], key: str) -> Optional[int]:
         return int(raw)
     except ValueError as exc:
         raise RuntimeException(
-            f"Invalid node spec - could not handle parent depth {raw}"
+            f'Invalid node spec - could not handle parent depth {raw}'
         ) from exc
 
 
 SelectionSpec = Union[
-    "SelectionCriteria",
-    "SelectionIntersection",
-    "SelectionDifference",
-    "SelectionUnion",
+    'SelectionCriteria',
+    'SelectionIntersection',
+    'SelectionDifference',
+    'SelectionUnion',
 ]
 
 
@@ -64,12 +66,13 @@ class SelectionCriteria:
     parents_depth: Optional[int]
     children: bool
     children_depth: Optional[int]
+    greedy: bool = False
 
     def __post_init__(self):
         if self.children and self.childrens_parents:
             raise RuntimeException(
                 f'Invalid node spec {self.raw} - "@" prefix and "+" suffix '
-                "are incompatible"
+                'are incompatible'
             )
 
     @classmethod
@@ -80,10 +83,12 @@ class SelectionCriteria:
             return MethodName.FQN
 
     @classmethod
-    def parse_method(cls, groupdict: Dict[str, Any]) -> Tuple[MethodName, List[str]]:
-        raw_method = groupdict.get("method")
+    def parse_method(
+        cls, groupdict: Dict[str, Any]
+    ) -> Tuple[MethodName, List[str]]:
+        raw_method = groupdict.get('method')
         if raw_method is None:
-            return cls.default_method(groupdict["value"]), []
+            return cls.default_method(groupdict['value']), []
 
         method_parts: List[str] = raw_method.split(SELECTOR_METHOD_SEPARATOR)
         try:
@@ -99,54 +104,57 @@ class SelectionCriteria:
 
     @classmethod
     def selection_criteria_from_dict(
-        cls, raw: Any, dct: Dict[str, Any]
-    ) -> "SelectionCriteria":
-        if "value" not in dct:
-            raise RuntimeException(f'Invalid node spec "{raw}" - no search value!')
+        cls, raw: Any, dct: Dict[str, Any], greedy: bool = False
+    ) -> 'SelectionCriteria':
+        if 'value' not in dct:
+            raise RuntimeException(
+                f'Invalid node spec "{raw}" - no search value!'
+            )
         method_name, method_arguments = cls.parse_method(dct)
 
-        parents_depth = _match_to_int(dct, "parents_depth")
-        children_depth = _match_to_int(dct, "children_depth")
+        parents_depth = _match_to_int(dct, 'parents_depth')
+        children_depth = _match_to_int(dct, 'children_depth')
         return cls(
             raw=raw,
             method=method_name,
             method_arguments=method_arguments,
-            value=dct["value"],
-            childrens_parents=bool(dct.get("childrens_parents")),
-            parents=bool(dct.get("parents")),
+            value=dct['value'],
+            childrens_parents=bool(dct.get('childrens_parents')),
+            parents=bool(dct.get('parents')),
             parents_depth=parents_depth,
-            children=bool(dct.get("children")),
+            children=bool(dct.get('children')),
             children_depth=children_depth,
+            greedy=greedy
         )
 
     @classmethod
-    def dict_from_single_spec(cls, raw: str):
+    def dict_from_single_spec(cls, raw: str, greedy: bool = False):
         result = RAW_SELECTOR_PATTERN.match(raw)
         if result is None:
-            return {"error": "Invalid selector spec"}
+            return {'error': 'Invalid selector spec'}
         dct: Dict[str, Any] = result.groupdict()
         method_name, method_arguments = cls.parse_method(dct)
         meth_name = str(method_name)
         if method_arguments:
-            meth_name = meth_name + "." + ".".join(method_arguments)
-        dct["method"] = meth_name
-        dct = {k: v for k, v in dct.items() if (v is not None and v != "")}
-        if "childrens_parents" in dct:
-            dct["childrens_parents"] = bool(dct.get("childrens_parents"))
-        if "parents" in dct:
-            dct["parents"] = bool(dct.get("parents"))
-        if "children" in dct:
-            dct["children"] = bool(dct.get("children"))
+            meth_name = meth_name + '.' + '.'.join(method_arguments)
+        dct['method'] = meth_name
+        dct = {k: v for k, v in dct.items() if (v is not None and v != '')}
+        if 'childrens_parents' in dct:
+            dct['childrens_parents'] = bool(dct.get('childrens_parents'))
+        if 'parents' in dct:
+            dct['parents'] = bool(dct.get('parents'))
+        if 'children' in dct:
+            dct['children'] = bool(dct.get('children'))
         return dct
 
     @classmethod
-    def from_single_spec(cls, raw: str) -> "SelectionCriteria":
+    def from_single_spec(cls, raw: str, greedy: bool = False) -> 'SelectionCriteria':
         result = RAW_SELECTOR_PATTERN.match(raw)
         if result is None:
             # bad spec!
             raise RuntimeException(f'Invalid selector spec "{raw}"')
 
-        return cls.selection_criteria_from_dict(raw, result.groupdict())
+        return cls.selection_criteria_from_dict(raw, result.groupdict(), greedy=greedy)
 
 
 class BaseSelectionGroup(Iterable[SelectionSpec], metaclass=ABCMeta):
@@ -169,7 +177,9 @@ class BaseSelectionGroup(Iterable[SelectionSpec], metaclass=ABCMeta):
         self,
         selections: List[Set[UniqueId]],
     ) -> Set[UniqueId]:
-        raise NotImplementedError("_combine_selections not implemented!")
+        raise NotImplementedError(
+            '_combine_selections not implemented!'
+        )
 
     def combined(self, selections: List[Set[UniqueId]]) -> Set[UniqueId]:
         if not selections:

core/dbt/helper_types.py

@@ -5,9 +5,7 @@ from pathlib import Path
 from typing import Tuple, AbstractSet, Union
 
 from dbt.dataclass_schema import (
-    dbtClassMixin,
-    ValidationError,
-    StrEnum,
+    dbtClassMixin, ValidationError, StrEnum,
 )
 from hologram import FieldEncoder, JsonDict
 from mashumaro.types import SerializableType
@@ -15,11 +13,11 @@ from mashumaro.types import SerializableType
 
 class Port(int, SerializableType):
     @classmethod
-    def _deserialize(cls, value: Union[int, str]) -> "Port":
+    def _deserialize(cls, value: Union[int, str]) -> 'Port':
         try:
             value = int(value)
         except ValueError:
-            raise ValidationError(f"Cannot encode {value} into port number")
+            raise ValidationError(f'Cannot encode {value} into port number')
 
         return Port(value)
 
@@ -30,7 +28,7 @@ class Port(int, SerializableType):
 class PortEncoder(FieldEncoder):
     @property
     def json_schema(self):
-        return {"type": "integer", "minimum": 0, "maximum": 65535}
+        return {'type': 'integer', 'minimum': 0, 'maximum': 65535}
 
 
 class TimeDeltaFieldEncoder(FieldEncoder[timedelta]):
@@ -46,12 +44,12 @@ class TimeDeltaFieldEncoder(FieldEncoder[timedelta]):
             return timedelta(seconds=value)
         except TypeError:
             raise ValidationError(
-                "cannot encode {} into timedelta".format(value)
+                'cannot encode {} into timedelta'.format(value)
             ) from None
 
     @property
     def json_schema(self) -> JsonDict:
-        return {"type": "number"}
+        return {'type': 'number'}
 
 
 class PathEncoder(FieldEncoder):
@@ -65,16 +63,16 @@ class PathEncoder(FieldEncoder):
             return Path(value)
         except TypeError:
             raise ValidationError(
-                "cannot encode {} into timedelta".format(value)
+                'cannot encode {} into timedelta'.format(value)
             ) from None
 
     @property
     def json_schema(self) -> JsonDict:
-        return {"type": "string"}
+        return {'type': 'string'}
 
 
 class NVEnum(StrEnum):
-    novalue = "novalue"
+    novalue = 'novalue'
 
     def __eq__(self, other):
         return isinstance(other, NVEnum)
@@ -83,17 +81,14 @@ class NVEnum(StrEnum):
 @dataclass
 class NoValue(dbtClassMixin):
     """Sometimes, you want a way to say none that isn't None"""
-
     novalue: NVEnum = NVEnum.novalue
 
 
-dbtClassMixin.register_field_encoders(
-    {
-        Port: PortEncoder(),
-        timedelta: TimeDeltaFieldEncoder(),
-        Path: PathEncoder(),
-    }
-)
+dbtClassMixin.register_field_encoders({
+    Port: PortEncoder(),
+    timedelta: TimeDeltaFieldEncoder(),
+    Path: PathEncoder(),
+})
 
 
 FQNPath = Tuple[str, ...]

core/dbt/hooks.py

@@ -5,8 +5,8 @@ from typing import Union, Dict, Any
 
 
 class ModelHookType(StrEnum):
-    PreHook = "pre-hook"
-    PostHook = "post-hook"
+    PreHook = 'pre-hook'
+    PostHook = 'post-hook'
 
 
 def get_hook_dict(source: Union[str, Dict[str, Any]]) -> Dict[str, Any]:
@@ -18,4 +18,4 @@ def get_hook_dict(source: Union[str, Dict[str, Any]]) -> Dict[str, Any]:
     try:
         return json.loads(source)
     except ValueError:
-        return {"sql": source}
+        return {'sql': source}

core/dbt/include/global_project/__init__.py

@@ -1,6 +1,7 @@
 import os
 
 PACKAGE_PATH = os.path.dirname(__file__)
-PROJECT_NAME = "dbt"
+PROJECT_NAME = 'dbt'
 
-DOCS_INDEX_FILE_PATH = os.path.normpath(os.path.join(PACKAGE_PATH, "..", "index.html"))
+DOCS_INDEX_FILE_PATH = os.path.normpath(
+    os.path.join(PACKAGE_PATH, '..', "index.html"))

core/dbt/include/global_project/macros/adapters/common.sql

@@ -1,5 +1,5 @@
 {% macro get_columns_in_query(select_sql) -%}
-  {{ return(adapter.dispatch('get_columns_in_query')(select_sql)) }}
+  {{ return(adapter.dispatch('get_columns_in_query', 'dbt')(select_sql)) }}
 {% endmacro %}
 
 {% macro default__get_columns_in_query(select_sql) %}
@@ -15,7 +15,7 @@
 {% endmacro %}
 
 {% macro create_schema(relation) -%}
-  {{ adapter.dispatch('create_schema')(relation) }}
+  {{ adapter.dispatch('create_schema', 'dbt')(relation) }}
 {% endmacro %}
 
 {% macro default__create_schema(relation) -%}
@@ -25,7 +25,7 @@
 {% endmacro %}
 
 {% macro drop_schema(relation) -%}
-  {{ adapter.dispatch('drop_schema')(relation) }}
+  {{ adapter.dispatch('drop_schema', 'dbt')(relation) }}
 {% endmacro %}
 
 {% macro default__drop_schema(relation) -%}
@@ -35,7 +35,7 @@
 {% endmacro %}
 
 {% macro create_table_as(temporary, relation, sql) -%}
-  {{ adapter.dispatch('create_table_as')(temporary, relation, sql) }}
+  {{ adapter.dispatch('create_table_as', 'dbt')(temporary, relation, sql) }}
 {%- endmacro %}
 
 {% macro default__create_table_as(temporary, relation, sql) -%}
@@ -51,8 +51,31 @@
 
 {% endmacro %}
 
+{% macro get_create_index_sql(relation, index_dict) -%}
+  {{ return(adapter.dispatch('get_create_index_sql', 'dbt')(relation, index_dict)) }}
+{% endmacro %}
+
+{% macro default__get_create_index_sql(relation, index_dict) -%}
+  {% do return(None) %}
+{% endmacro %}
+
+{% macro create_indexes(relation) -%}
+  {{ adapter.dispatch('create_indexes', 'dbt')(relation) }}
+{%- endmacro %}
+
+{% macro default__create_indexes(relation) -%}
+  {%- set _indexes = config.get('indexes', default=[]) -%}
+
+  {% for _index_dict in _indexes %}
+    {% set create_index_sql = get_create_index_sql(relation, _index_dict) %}
+    {% if create_index_sql %}
+      {% do run_query(create_index_sql) %}
+    {% endif %}
+  {% endfor %}
+{% endmacro %}
+
 {% macro create_view_as(relation, sql) -%}
-  {{ adapter.dispatch('create_view_as')(relation, sql) }}
+  {{ adapter.dispatch('create_view_as', 'dbt')(relation, sql) }}
 {%- endmacro %}
 
 {% macro default__create_view_as(relation, sql) -%}
@@ -66,7 +89,7 @@
 
 
 {% macro get_catalog(information_schema, schemas) -%}
-  {{ return(adapter.dispatch('get_catalog')(information_schema, schemas)) }}
+  {{ return(adapter.dispatch('get_catalog', 'dbt')(information_schema, schemas)) }}
 {%- endmacro %}
 
 {% macro default__get_catalog(information_schema, schemas) -%}
@@ -81,7 +104,7 @@
 
 
 {% macro get_columns_in_relation(relation) -%}
-  {{ return(adapter.dispatch('get_columns_in_relation')(relation)) }}
+  {{ return(adapter.dispatch('get_columns_in_relation', 'dbt')(relation)) }}
 {% endmacro %}
 
 {% macro sql_convert_columns_in_relation(table) -%}
@@ -98,13 +121,13 @@
 {% endmacro %}
 
 {% macro alter_column_type(relation, column_name, new_column_type) -%}
-  {{ return(adapter.dispatch('alter_column_type')(relation, column_name, new_column_type)) }}
+  {{ return(adapter.dispatch('alter_column_type', 'dbt')(relation, column_name, new_column_type)) }}
 {% endmacro %}
 
 
 
 {% macro alter_column_comment(relation, column_dict) -%}
-  {{ return(adapter.dispatch('alter_column_comment')(relation, column_dict)) }}
+  {{ return(adapter.dispatch('alter_column_comment', 'dbt')(relation, column_dict)) }}
 {% endmacro %}
 
 {% macro default__alter_column_comment(relation, column_dict) -%}
@@ -113,7 +136,7 @@
 {% endmacro %}
 
 {% macro alter_relation_comment(relation, relation_comment) -%}
-  {{ return(adapter.dispatch('alter_relation_comment')(relation, relation_comment)) }}
+  {{ return(adapter.dispatch('alter_relation_comment', 'dbt')(relation, relation_comment)) }}
 {% endmacro %}
 
 {% macro default__alter_relation_comment(relation, relation_comment) -%}
@@ -122,7 +145,7 @@
 {% endmacro %}
 
 {% macro persist_docs(relation, model, for_relation=true, for_columns=true) -%}
-  {{ return(adapter.dispatch('persist_docs')(relation, model, for_relation, for_columns)) }}
+  {{ return(adapter.dispatch('persist_docs', 'dbt')(relation, model, for_relation, for_columns)) }}
 {% endmacro %}
 
 {% macro default__persist_docs(relation, model, for_relation, for_columns) -%}
@@ -157,7 +180,7 @@
 
 
 {% macro drop_relation(relation) -%}
-  {{ return(adapter.dispatch('drop_relation')(relation)) }}
+  {{ return(adapter.dispatch('drop_relation', 'dbt')(relation)) }}
 {% endmacro %}
 
 
@@ -168,7 +191,7 @@
 {% endmacro %}
 
 {% macro truncate_relation(relation) -%}
-  {{ return(adapter.dispatch('truncate_relation')(relation)) }}
+  {{ return(adapter.dispatch('truncate_relation', 'dbt')(relation)) }}
 {% endmacro %}
 
 
@@ -179,7 +202,7 @@
 {% endmacro %}
 
 {% macro rename_relation(from_relation, to_relation) -%}
-  {{ return(adapter.dispatch('rename_relation')(from_relation, to_relation)) }}
+  {{ return(adapter.dispatch('rename_relation', 'dbt')(from_relation, to_relation)) }}
 {% endmacro %}
 
 {% macro default__rename_relation(from_relation, to_relation) -%}
@@ -191,7 +214,7 @@
 
 
 {% macro information_schema_name(database) %}
-  {{ return(adapter.dispatch('information_schema_name')(database)) }}
+  {{ return(adapter.dispatch('information_schema_name', 'dbt')(database)) }}
 {% endmacro %}
 
 {% macro default__information_schema_name(database) -%}
@@ -204,7 +227,7 @@
 
 
 {% macro list_schemas(database) -%}
-  {{ return(adapter.dispatch('list_schemas')(database)) }}
+  {{ return(adapter.dispatch('list_schemas', 'dbt')(database)) }}
 {% endmacro %}
 
 {% macro default__list_schemas(database) -%}
@@ -218,7 +241,7 @@
 
 
 {% macro check_schema_exists(information_schema, schema) -%}
-  {{ return(adapter.dispatch('check_schema_exists')(information_schema, schema)) }}
+  {{ return(adapter.dispatch('check_schema_exists', 'dbt')(information_schema, schema)) }}
 {% endmacro %}
 
 {% macro default__check_schema_exists(information_schema, schema) -%}
@@ -233,7 +256,7 @@
 
 
 {% macro list_relations_without_caching(schema_relation) %}
-  {{ return(adapter.dispatch('list_relations_without_caching')(schema_relation)) }}
+  {{ return(adapter.dispatch('list_relations_without_caching', 'dbt')(schema_relation)) }}
 {% endmacro %}
 
 
@@ -244,7 +267,7 @@
 
 
 {% macro current_timestamp() -%}
-  {{ adapter.dispatch('current_timestamp')() }}
+  {{ adapter.dispatch('current_timestamp', 'dbt')() }}
 {%- endmacro %}
 
 
@@ -255,7 +278,7 @@
 
 
 {% macro collect_freshness(source, loaded_at_field, filter) %}
-  {{ return(adapter.dispatch('collect_freshness')(source, loaded_at_field, filter))}}
+  {{ return(adapter.dispatch('collect_freshness', 'dbt')(source, loaded_at_field, filter))}}
 {% endmacro %}
 
 
@@ -273,7 +296,7 @@
 {% endmacro %}
 
 {% macro make_temp_relation(base_relation, suffix='__dbt_tmp') %}
-  {{ return(adapter.dispatch('make_temp_relation')(base_relation, suffix))}}
+  {{ return(adapter.dispatch('make_temp_relation', 'dbt')(base_relation, suffix))}}
 {% endmacro %}
 
 {% macro default__make_temp_relation(base_relation, suffix) %}
@@ -287,3 +310,35 @@
 {% macro set_sql_header(config) -%}
   {{ config.set('sql_header', caller()) }}
 {%- endmacro %}
+
+
+{% macro alter_relation_add_remove_columns(relation, add_columns = none, remove_columns = none) -%}
+  {{ return(adapter.dispatch('alter_relation_add_remove_columns', 'dbt')(relation, add_columns, remove_columns)) }}
+{% endmacro %}
+
+{% macro default__alter_relation_add_remove_columns(relation, add_columns, remove_columns) %}
+  
+  {% if add_columns is none %}
+    {% set add_columns = [] %}
+  {% endif %}
+  {% if remove_columns is none %}
+    {% set remove_columns = [] %}
+  {% endif %}
+  
+  {% set sql -%}
+     
+     alter {{ relation.type }} {{ relation }}
+       
+            {% for column in add_columns %}
+               add column {{ column.name }} {{ column.data_type }}{{ ',' if not loop.last }}
+            {% endfor %}{{ ',' if remove_columns | length > 0 }}
+            
+            {% for column in remove_columns %}
+                drop column {{ column.name }}{{ ',' if not loop.last }}
+            {% endfor %}
+  
+  {%- endset -%}
+
+  {% do run_query(sql) %}
+
+{% endmacro %}

core/dbt/include/global_project/macros/etc/get_custom_alias.sql

@@ -13,6 +13,10 @@
 
 #}
 {% macro generate_alias_name(custom_alias_name=none, node=none) -%}
+    {% do return(adapter.dispatch('generate_alias_name', 'dbt')(custom_alias_name, node)) %}
+{%- endmacro %}
+
+{% macro default__generate_alias_name(custom_alias_name=none, node=none) -%}
 
     {%- if custom_alias_name is none -%}
 

core/dbt/include/global_project/macros/etc/get_custom_database.sql

@@ -14,7 +14,7 @@
 
 #}
 {% macro generate_database_name(custom_database_name=none, node=none) -%}
-    {% do return(adapter.dispatch('generate_database_name')(custom_database_name, node)) %}
+    {% do return(adapter.dispatch('generate_database_name', 'dbt')(custom_database_name, node)) %}
 {%- endmacro %}
 
 {% macro default__generate_database_name(custom_database_name=none, node=none) -%}