Case-insensitive comparisons

* Cache plugin modules

* Add changelog entry

* Use lru_cache to keep Python 3.8 happy.

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.7.0a1
+current_version = 1.8.0a1
 parse = (?P<major>[\d]+) # major version number
 	\.(?P<minor>[\d]+) # minor version number
 	\.(?P<patch>[\d]+) # patch version number

.changes/0.0.0.md

@@ -3,6 +3,7 @@
 For information on prior major and minor releases, see their changelogs:
 
 
+* [1.7](https://github.com/dbt-labs/dbt-core/blob/1.7.latest/CHANGELOG.md)
 * [1.6](https://github.com/dbt-labs/dbt-core/blob/1.6.latest/CHANGELOG.md)
 * [1.5](https://github.com/dbt-labs/dbt-core/blob/1.5.latest/CHANGELOG.md)
 * [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)

.changes/unreleased/Dependencies-20231031-131954.yaml

@@ -0,0 +1,6 @@
+kind: Dependencies
+body: Begin using DSI 0.4.x
+time: 2023-10-31T13:19:54.750009-07:00
+custom:
+  Author: QMalcolm peterallenwebb
+  PR: "8892"

.changes/unreleased/Dependencies-20231106-130051.yaml

@@ -0,0 +1,6 @@
+kind: Dependencies
+body: Update typing-extensions version to >=4.4
+time: 2023-11-06T13:00:51.062386-08:00
+custom:
+  Author: tlento
+  PR: "9012"

.changes/unreleased/Docs-20230531-115419.yaml

@@ -1,6 +0,0 @@
-kind: Docs
-body: Fix for column tests not rendering on quoted columns
-time: 2023-05-31T11:54:19.687363-04:00
-custom:
-  Author: drewbanin
-  Issue: "201"

.changes/unreleased/Docs-20230718-192422.yaml

@@ -1,6 +0,0 @@
-kind: Docs
-body: Remove static SQL codeblock for metrics
-time: 2023-07-18T19:24:22.155323+02:00
-custom:
-  Author: marcodamore
-  Issue: "436"

.changes/unreleased/Docs-20231106-123157.yaml

@@ -0,0 +1,6 @@
+kind: Docs
+body: fix get_custom_database docstring
+time: 2023-11-06T12:31:57.525711Z
+custom:
+  Author: LeoTheGriff
+  Issue: "9003"

.changes/unreleased/Features-20230802-145011.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Initial implementation of unit testing
+time: 2023-08-02T14:50:11.391992-04:00
+custom:
+  Author: gshank
+  Issue: "8287"

.changes/unreleased/Features-20230828-101825.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Unit test manifest artifacts and selection
+time: 2023-08-28T10:18:25.958929-04:00
+custom:
+  Author: gshank
+  Issue: "8295"

.changes/unreleased/Features-20230906-234741.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Support config with tags & meta for unit tests
+time: 2023-09-06T23:47:41.059915-04:00
+custom:
+  Author: michelleark
+  Issue: "8294"

.changes/unreleased/Features-20230928-163205.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Enable inline csv fixtures in unit tests
+time: 2023-09-28T16:32:05.573776-04:00
+custom:
+  Author: gshank
+  Issue: "8626"

.changes/unreleased/Features-20231017-143620.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Add drop_schema_named macro
+time: 2023-10-17T14:36:20.612289-07:00
+custom:
+  Author: colin-rogers-dbt
+  Issue: "8025"

.changes/unreleased/Features-20231031-132022.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Add exports to SavedQuery spec
+time: 2023-10-31T13:20:22.448158-07:00
+custom:
+  Author: QMalcolm peterallenwebb
+  Issue: "8892"

.changes/unreleased/Features-20231101-101845.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Support unit testing incremental models
+time: 2023-11-01T10:18:45.341781-04:00
+custom:
+  Author: michelleark
+  Issue: "8422"

.changes/unreleased/Features-20231106-194752.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Add support of csv file fixtures to unit testing
+time: 2023-11-06T19:47:52.501495-06:00
+custom:
+  Author: emmyoop
+  Issue: "8290"

.changes/unreleased/Features-20231107-231006.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Unit tests support --defer and state:modified
+time: 2023-11-07T23:10:06.376588-05:00
+custom:
+  Author: jtcohen6
+  Issue: "8517"

.changes/unreleased/Features-20231110-154255.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Support setting export configs hierarchically via saved query and project configs
+time: 2023-11-10T15:42:55.042317-08:00
+custom:
+  Author: QMalcolm
+  Issue: "8956"

.changes/unreleased/Features-20231111-191150.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Support source inputs in unit tests
+time: 2023-11-11T19:11:50.870494-05:00
+custom:
+  Author: gshank
+  Issue: "8507"

.changes/unreleased/Features-20231114-101555.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Use daff to render diff displayed in stdout when unit test fails
+time: 2023-11-14T10:15:55.689307-05:00
+custom:
+  Author: michelleark
+  Issue: "8558"

.changes/unreleased/Fixes-20230718-125518.yaml

@@ -1,6 +0,0 @@
-kind: Fixes
-body: Enable converting deprecation warnings to errors
-time: 2023-07-18T12:55:18.03914-04:00
-custom:
-  Author: michelleark
-  Issue: "8130"

.changes/unreleased/Fixes-20231013-130943.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: For packages installed with tarball method, fetch metadata to resolve nested dependencies
+time: 2023-10-13T13:09:43.188308-04:00
+custom:
+  Author: adamlopez
+  Issue: "8621"

.changes/unreleased/Fixes-20231016-163953.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Fix partial parsing not working for semantic model change
+time: 2023-10-16T16:39:53.05058-07:00
+custom:
+  Author: ChenyuLInx
+  Issue: "8859"

.changes/unreleased/Fixes-20231024-110151.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Handle unknown `type_code` for model contracts
+time: 2023-10-24T11:01:51.980781-06:00
+custom:
+  Author: dbeatty10
+  Issue: 8877 8353

.changes/unreleased/Fixes-20231024-145504.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Add back contract enforcement for temporary tables on postgres
+time: 2023-10-24T14:55:04.051683-05:00
+custom:
+  Author: emmyoop
+  Issue: "8857"

.changes/unreleased/Fixes-20231024-155400.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Rework get_catalog implementation to retain previous adapter interface semantics
+time: 2023-10-24T15:54:00.628086-04:00
+custom:
+  Author: peterallenwebb
+  Issue: "8846"

.changes/unreleased/Fixes-20231026-002536.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Add version to fqn when version==0
+time: 2023-10-26T00:25:36.259356-05:00
+custom:
+  Author: aranke
+  Issue: "8836"

.changes/unreleased/Fixes-20231030-093734.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Fix cased comparison in catalog-retrieval function.
+time: 2023-10-30T09:37:34.258612-04:00
+custom:
+  Author: peterallenwebb
+  Issue: "8939"

.changes/unreleased/Fixes-20231031-005345.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Catalog queries now assign the correct type to materialized views
+time: 2023-10-31T00:53:45.486203-04:00
+custom:
+  Author: mikealfare
+  Issue: "8864"

.changes/unreleased/Fixes-20231031-144837.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Fix compilation exception running empty seed file and support new Integer agate data_type
+time: 2023-10-31T14:48:37.774871-04:00
+custom:
+  Author: gshank
+  Issue: "8895"

.changes/unreleased/Fixes-20231101-155824.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Make relation filtering None-tolerant for maximal flexibility across adapters.
+time: 2023-11-01T15:58:24.552054-04:00
+custom:
+  Author: peterallenwebb
+  Issue: "8974"

.changes/unreleased/Fixes-20231106-155933.yaml

@@ -0,0 +1,7 @@
+kind: Fixes
+body: Update run_results.json from previous versions of dbt to support deferral and
+  rerun from failure
+time: 2023-11-06T15:59:33.677915-05:00
+custom:
+  Author: jtcohen6 peterallenwebb
+  Issue: "9010"

.changes/unreleased/Fixes-20231107-092358.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Fix git repository with subdirectory for Deps
+time: 2023-11-07T09:23:58.214271-08:00
+custom:
+  Author: ChenyuLInx
+  Issue: "9000"

.changes/unreleased/Fixes-20231107-094130.yaml

@@ -0,0 +1,7 @@
+kind: Fixes
+body: Use MANIFEST.in to recursively include all jinja templates; fixes issue where
+  some templates were not included in the distribution
+time: 2023-11-07T09:41:30.121733-05:00
+custom:
+  Author: mikealfare
+  Issue: "9016"

.changes/unreleased/Fixes-20231113-114956.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Fix formatting of tarball information in packages-lock.yml
+time: 2023-11-13T11:49:56.437007-08:00
+custom:
+  Author: ChenyuLInx QMalcolm
+  Issue: "9062"

.changes/unreleased/Fixes-20231113-154535.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Use seed file from disk for unit testing if rows not specified in YAML config
+time: 2023-11-13T15:45:35.008565Z
+custom:
+  Author: aranke
+  Issue: "8652"

.changes/unreleased/Under the Hood-20230912-190506.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Add unit testing functional tests
+time: 2023-09-12T19:05:06.023126-04:00
+custom:
+  Author: gshank
+  Issue: "8512"

.changes/unreleased/Under the Hood-20231027-140048.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Add a no-op runner for Saved Qeury
+time: 2023-10-27T14:00:48.4755-07:00
+custom:
+  Author: ChenyuLInx
+  Issue: "8893"

.changes/unreleased/Under the Hood-20231103-195222.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Move CatalogRelationTypes test case to the shared test suite to be reused by
+  adapter maintainers
+time: 2023-11-03T19:52:22.694394-04:00
+custom:
+  Author: mikealfare
+  Issue: "8952"

.changes/unreleased/Under the Hood-20231106-080422.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Treat SystemExit as an interrupt if raised during node execution.
+time: 2023-11-06T08:04:22.022179-05:00
+custom:
+  Author: benmosher
+  Issue: n/a

.changes/unreleased/Under the Hood-20231106-105730.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Removing unused 'documentable'
+time: 2023-11-06T10:57:30.694056-08:00
+custom:
+  Author: QMalcolm
+  Issue: "8871"

.changes/unreleased/Under the Hood-20231107-191546.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Cache dbt plugin modules to improve integration test performance
+time: 2023-11-07T19:15:46.170151-05:00
+custom:
+  Author: peterallenwebb
+  Issue: "9029"

.github/CODEOWNERS

@@ -13,23 +13,6 @@
 # the core team as a whole will be assigned
 *       @dbt-labs/core-team
 
-### OSS Tooling Guild
-
-/.github/                       @dbt-labs/guild-oss-tooling
-.bumpversion.cfg                @dbt-labs/guild-oss-tooling
-
-.changie.yaml                   @dbt-labs/guild-oss-tooling
-
-pre-commit-config.yaml          @dbt-labs/guild-oss-tooling
-pytest.ini                      @dbt-labs/guild-oss-tooling
-tox.ini                         @dbt-labs/guild-oss-tooling
-
-pyproject.toml                  @dbt-labs/guild-oss-tooling
-requirements.txt                @dbt-labs/guild-oss-tooling
-dev_requirements.txt            @dbt-labs/guild-oss-tooling
-/core/setup.py                  @dbt-labs/guild-oss-tooling
-/core/MANIFEST.in               @dbt-labs/guild-oss-tooling
-
 ### ADAPTERS
 
 # Adapter interface ("base" + "sql" adapter defaults, cache)
@@ -40,7 +23,7 @@ dev_requirements.txt            @dbt-labs/guild-oss-tooling
 
 # Postgres plugin
 /plugins/                       @dbt-labs/core-adapters
-/plugins/postgres/setup.py      @dbt-labs/core-adapters @dbt-labs/guild-oss-tooling
+/plugins/postgres/setup.py      @dbt-labs/core-adapters
 
 # Functional tests for adapter plugins
 /tests/adapter                  @dbt-labs/core-adapters

.github/ISSUE_TEMPLATE/implementation-ticket.yml

@@ -0,0 +1,58 @@
+name: 🛠️ Implementation
+description: This is an implementation ticket intended for use by the maintainers of dbt-core
+title: "[<project>] <title>"
+labels: ["user docs"]
+body:
+  - type: markdown
+    attributes:
+      value: This is an implementation ticket intended for use by the maintainers of dbt-core
+  - type: checkboxes
+    attributes:
+      label: Housekeeping
+      description: >
+        A couple friendly reminders:
+          1. Remove the `user docs` label if the scope of this work does not require changes to https://docs.getdbt.com/docs: no end-user interface (e.g. yml spec, CLI, error messages, etc) or functional changes
+          2. Link any blocking issues in the "Blocked on" field under the "Core devs & maintainers" project.
+      options:
+        - label: I am a maintainer of dbt-core
+          required: true
+  - type: textarea
+    attributes:
+      label: Short description
+      description: |
+        Describe the scope of the ticket, a high-level implementation approach and any tradeoffs to consider
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Acceptance criteria
+      description: |
+        What is the definition of done for this ticket? Include any relevant edge cases and/or test cases
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Impact to Other Teams
+      description: |
+        Will this change impact other teams?  Include details of the kinds of changes required (new tests, code changes, related tickets) and _add the relevant `Impact:[team]` label_.
+      placeholder: |
+        Example: This change impacts `dbt-redshift` because the tests will need to be modified.  The `Impact:[Adapter]` label has been added.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Will backports be required?
+      description: |
+        Will this change need to be backported to previous versions?  Add details, possible blockers to backporting and _add the relevant backport labels `backport 1.x.latest`_
+      placeholder: |
+        Example: Backport to 1.6.latest, 1.5.latest and 1.4.latest.  Since 1.4 isn't using click, the backport may be complicated. The `backport 1.6.latest`, `backport 1.5.latest` and `backport 1.4.latest` labels have been added.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Context
+      description: |
+        Provide the "why", motivation, and alternative approaches considered -- linking to previous refinement issues, spikes, Notion docs as appropriate
+          validations:
+    validations:
+      required: false

.github/dependabot.yml

@@ -28,3 +28,10 @@ updates:
     schedule:
       interval: "weekly"
     rebase-strategy: "disabled"
+
+  # github dependencies
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    rebase-strategy: "disabled"

.github/pull_request_template.md

@@ -1,15 +1,12 @@
-resolves #  
-[docs](https://github.com/dbt-labs/docs.getdbt.com/issues/new/choose) dbt-labs/docs.getdbt.com/#  
+resolves #
 
 <!---
   Include the number of the issue addressed by this PR above if applicable.
   PRs for code changes without an associated issue *will not be merged*.
   See CONTRIBUTING.md for more information.
 
-  Include the number of the docs issue that was opened for this PR. If
-  this change has no user-facing implications, "N/A" suffices instead. New
-  docs tickets can be created by clicking the link above or by going to
-  https://github.com/dbt-labs/docs.getdbt.com/issues/new/choose.
+  Add the `user docs` label to this PR if it will need docs changes.  An 
+  issue will get opened in docs.getdbt.com upon successful merge of this PR.
 -->
 
 ### Problem
@@ -33,3 +30,4 @@ resolves #
 - [ ] 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
 - [ ] This PR has no interface changes (e.g. macros, cli, logs, json artifacts, config files, adapter interface, etc) or this PR has already received feedback and approval from Product or DX
+- [ ] This PR includes [type annotations](https://docs.python.org/3/library/typing.html) for new and modified functions

.github/workflows/changelog-existence.yml

@@ -2,10 +2,8 @@
 # Checks that a file has been committed under the /.changes directory
 # as a new CHANGELOG entry.  Cannot check for a specific filename as
 # it is dynamically generated by change type and timestamp.
-# 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.
+# This workflow runs on pull_request_target because it requires
+# secrets to post comments.
 
 # **why?**
 # Ensure code change gets reflected in the CHANGELOG.
@@ -19,7 +17,7 @@
 name: Check Changelog Entry
 
 on:
-  pull_request:
+  pull_request_target:
     types: [opened, reopened, labeled, unlabeled, synchronize]
   workflow_dispatch:
 

.github/workflows/docs-issue.yml

@@ -0,0 +1,43 @@
+# **what?**
+# Open an issue in docs.getdbt.com when a PR is labeled `user docs`
+
+# **why?**
+# To reduce barriers for keeping docs up to date
+
+# **when?**
+# When a PR is labeled `user docs` and is merged.  Runs on pull_request_target to run off the workflow already merged,
+# not the workflow that existed on the PR branch.  This allows old PRs to get comments.
+
+
+name: Open issues in docs.getdbt.com repo when a PR is labeled
+run-name: "Open an issue in docs.getdbt.com for PR #${{ github.event.pull_request.number }}"
+
+on:
+  pull_request_target:
+    types: [labeled, closed]
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+    issues: write # opens new issues
+    pull-requests: write # comments on PRs
+
+
+jobs:
+  open_issues:
+    # we only want to run this when the PR has been merged or the label in the labeled event is `user docs`.  Otherwise it runs the
+    # risk of duplicaton of issues being created due to merge and label both triggering this workflow to run and neither having
+    # generating the comment before the other runs.  This lives here instead of the shared workflow because this is where we
+    # decide if it should run or not.
+    if: |
+      (github.event.pull_request.merged == true) &&
+      ((github.event.action == 'closed' && contains( github.event.pull_request.labels.*.name, 'user docs')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'user docs'))
+    uses: dbt-labs/actions/.github/workflows/open-issue-in-repo.yml@main
+    with:
+        issue_repository: "dbt-labs/docs.getdbt.com"
+        issue_title: "Docs Changes Needed from ${{ github.event.repository.name }} PR #${{ github.event.pull_request.number }}"
+        issue_body: "At a minimum, update body to include a link to the page on docs.getdbt.com requiring updates and what part(s) of the page you would like to see updated."
+    secrets: inherit

.github/workflows/main.yml

@@ -33,6 +33,11 @@ defaults:
   run:
     shell: bash
 
+# top-level adjustments can be made here
+env:
+  # number of parallel processes to spawn for python integration testing
+  PYTHON_INTEGRATION_TEST_WORKERS: 5
+
 jobs:
   code-quality:
     name: code-quality
@@ -103,26 +108,59 @@ jobs:
       - name: Upload Unit Test Coverage to Codecov
         if: ${{ matrix.python-version == '3.11' }}
         uses: codecov/codecov-action@v3
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          flags: unit
+
+  integration-metadata:
+    name: integration test metadata generation
+    runs-on: ubuntu-latest
+    outputs:
+      split-groups: ${{ steps.generate-split-groups.outputs.split-groups }}
+      include: ${{ steps.generate-include.outputs.include }}
+
+    steps:
+      - name: generate split-groups
+        id: generate-split-groups
+        run: |
+          MATRIX_JSON="["
+          for B in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
+              MATRIX_JSON+=$(sed 's/^/"/;s/$/"/' <<< "${B}")
+          done
+          MATRIX_JSON="${MATRIX_JSON//\"\"/\", \"}"
+          MATRIX_JSON+="]"
+          echo "split-groups=${MATRIX_JSON}"
+          echo "split-groups=${MATRIX_JSON}" >> $GITHUB_OUTPUT
+
+      - name: generate include
+        id: generate-include
+        run: |
+          INCLUDE=('"python-version":"3.8","os":"windows-latest"' '"python-version":"3.8","os":"macos-latest"' )
+          INCLUDE_GROUPS="["
+          for include in ${INCLUDE[@]}; do
+              for group in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
+                  INCLUDE_GROUPS+=$(sed 's/$/, /' <<< "{\"split-group\":\"${group}\",${include}}")
+              done
+          done
+          INCLUDE_GROUPS=$(echo $INCLUDE_GROUPS | sed 's/,*$//g')
+          INCLUDE_GROUPS+="]"
+          echo "include=${INCLUDE_GROUPS}"
+          echo "include=${INCLUDE_GROUPS}" >> $GITHUB_OUTPUT
 
   integration:
-    name: integration test / python ${{ matrix.python-version }} / ${{ matrix.os }}
+    name: (${{ matrix.split-group }}) integration test / python ${{ matrix.python-version }} / ${{ matrix.os }}
 
     runs-on: ${{ matrix.os }}
-    timeout-minutes: 60
-
+    timeout-minutes: 30
+    needs:
+      - integration-metadata
     strategy:
       fail-fast: false
       matrix:
         python-version: ["3.8", "3.9", "3.10", "3.11"]
         os: [ubuntu-20.04]
-        include:
-          - python-version: 3.8
-            os: windows-latest
-          - python-version: 3.8
-            os: macos-latest
-
+        split-group: ${{ fromJson(needs.integration-metadata.outputs.split-groups) }}
+        include: ${{ fromJson(needs.integration-metadata.outputs.include) }}
     env:
       TOXENV: integration
       DBT_INVOCATION_ENV: github-actions
@@ -165,6 +203,8 @@ jobs:
 
       - name: Run tests
         run: tox -- --ddtrace
+        env:
+          PYTEST_ADDOPTS: ${{ format('--splits {0} --group {1}', env.PYTHON_INTEGRATION_TEST_WORKERS, matrix.split-group) }}
 
       - name: Get current date
         if: always()
@@ -182,8 +222,26 @@ jobs:
       - name: Upload Integration Test Coverage to Codecov
         if: ${{ matrix.python-version == '3.11' }}
         uses: codecov/codecov-action@v3
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          flags: integration
+
+  integration-report:
+    if: ${{ always() }}
+    name: Integration Test Suite
+    runs-on: ubuntu-latest
+    needs: integration
+    steps:
+      - name: "Integration Tests Failed"
+        if: ${{ contains(needs.integration.result, 'failure') || contains(needs.integration.result, 'cancelled') }}
+        # when this is true the next step won't execute
+        run: |
+          echo "::notice title='Integration test suite failed'"
+          exit 1
+
+      - name: "Integration Tests Passed"
+        run: |
+          echo "::notice title='Integration test suite passed'"
 
   build:
     name: build packages

.github/workflows/release-docker.yml

@@ -83,7 +83,7 @@ jobs:
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build and push MAJOR.MINOR.PATCH tag
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v5
         with:
           file: docker/Dockerfile
           push: True
@@ -94,7 +94,7 @@ jobs:
             ghcr.io/dbt-labs/${{ github.event.inputs.package }}:${{ github.event.inputs.version_number }}
 
       - name: Build and push MINOR.latest tag
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v5
         if: ${{ needs.get_version_meta.outputs.minor_latest == 'True' }}
         with:
           file: docker/Dockerfile
@@ -106,7 +106,7 @@ jobs:
             ghcr.io/dbt-labs/${{ github.event.inputs.package }}:${{ needs.get_version_meta.outputs.major }}.${{ needs.get_version_meta.outputs.minor }}.latest
 
       - name: Build and push latest tag
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v5
         if: ${{ needs.get_version_meta.outputs.latest == 'True' }}
         with:
           file: docker/Dockerfile

.github/workflows/repository-cleanup.yml

@@ -0,0 +1,30 @@
+# **what?**
+# Cleanup branches left over from automation and testing.  Also cleanup
+# draft releases from release testing.
+
+# **why?**
+# The automations are leaving behind branches and releases that clutter
+# the repository.  Sometimes we need them to debug processes so we don't
+# want them immediately deleted.  Running on Saturday to avoid running
+# at the same time as an actual release to prevent breaking a release
+# mid-release.
+
+# **when?**
+# Mainly on a schedule of 12:00 Saturday.
+# Manual trigger can also run on demand
+
+name: Repository Cleanup
+
+on:
+  schedule:
+    - cron: '0 12 * * SAT' # At 12:00 on Saturday - details in `why` above
+
+  workflow_dispatch: # for manual triggering
+
+permissions:
+  contents: write
+
+jobs:
+  cleanup-repo:
+    uses: dbt-labs/actions/.github/workflows/repository-cleanup.yml@main
+    secrets: inherit

.github/workflows/structured-logging-schema-check.yml

@@ -18,11 +18,41 @@ on:
 
 permissions: read-all
 
+# top-level adjustments can be made here
+env:
+  # number of parallel processes to spawn for python testing
+  PYTHON_INTEGRATION_TEST_WORKERS: 5
+
 jobs:
+  integration-metadata:
+    name: integration test metadata generation
+    runs-on: ubuntu-latest
+    outputs:
+      split-groups: ${{ steps.generate-split-groups.outputs.split-groups }}
+
+    steps:
+      - name: generate split-groups
+        id: generate-split-groups
+        run: |
+          MATRIX_JSON="["
+          for B in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
+              MATRIX_JSON+=$(sed 's/^/"/;s/$/"/' <<< "${B}")
+          done
+          MATRIX_JSON="${MATRIX_JSON//\"\"/\", \"}"
+          MATRIX_JSON+="]"
+          echo "split-groups=${MATRIX_JSON}" >> $GITHUB_OUTPUT
+
   # run the performance measurements on the current or default branch
   test-schema:
     name: Test Log Schema
     runs-on: ubuntu-20.04
+    timeout-minutes: 30
+    needs:
+      - integration-metadata
+    strategy:
+      fail-fast: false
+      matrix:
+        split-group: ${{ fromJson(needs.integration-metadata.outputs.split-groups) }}
     env:
       # turns warnings into errors
       RUSTFLAGS: "-D warnings"
@@ -65,3 +95,14 @@ jobs:
       # we actually care if these pass, because the normal test run doesn't usually include many json log outputs
       - name: Run integration tests
         run: tox -e integration -- -nauto
+        env:
+          PYTEST_ADDOPTS: ${{ format('--splits {0} --group {1}', env.PYTHON_INTEGRATION_TEST_WORKERS, matrix.split-group) }}
+
+  test-schema-report:
+    name: Log Schema Test Suite
+    runs-on: ubuntu-latest
+    needs: test-schema
+    steps:
+      - name: "[Notification] Log test suite passes"
+        run: |
+          echo "::notice title="Log test suite passes""

.pre-commit-config.yaml

@@ -37,7 +37,7 @@ repos:
     alias: flake8-check
     stages: [manual]
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v1.3.0
+  rev: v1.4.1
   hooks:
   - id: mypy
     # N.B.: Mypy is... a bit fragile.

CHANGELOG.md

@@ -10,6 +10,7 @@
 For information on prior major and minor releases, see their changelogs:
 
 
+* [1.7](https://github.com/dbt-labs/dbt-core/blob/1.7.latest/CHANGELOG.md)
 * [1.6](https://github.com/dbt-labs/dbt-core/blob/1.6.latest/CHANGELOG.md)
 * [1.5](https://github.com/dbt-labs/dbt-core/blob/1.5.latest/CHANGELOG.md)
 * [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)

codecov.yml

@@ -0,0 +1,13 @@
+ignore:
+  - ".github"
+  - ".changes"
+coverage:
+  status:
+    project:
+      default:
+        target: auto
+        threshold: 0.1% # Reduce noise by ignoring rounding errors in coverage drops
+    patch:
+      default:
+        target: auto
+        threshold: 80%

core/dbt/adapters/base/column.py

@@ -7,12 +7,12 @@ from dbt.exceptions import DbtRuntimeError
 
 @dataclass
 class Column:
+    # Note: This is automatically used by contract code
+    # No-op conversions (INTEGER => INT) have been removed.
+    # Any adapter that wants to take advantage of "translate_type"
+    # should create a ClassVar with the appropriate conversions.
     TYPE_LABELS: ClassVar[Dict[str, str]] = {
         "STRING": "TEXT",
-        "TIMESTAMP": "TIMESTAMP",
-        "FLOAT": "FLOAT",
-        "INTEGER": "INT",
-        "BOOLEAN": "BOOLEAN",
     }
     column: str
     dtype: str

core/dbt/adapters/base/connections.py

@@ -72,7 +72,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
 
     TYPE: str = NotImplemented
 
-    def __init__(self, profile: AdapterRequiredConfig):
+    def __init__(self, profile: AdapterRequiredConfig) -> None:
         self.profile = profile
         self.thread_connections: Dict[Hashable, Connection] = {}
         self.lock: RLock = flags.MP_CONTEXT.RLock()
@@ -400,7 +400,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
 
     @abc.abstractmethod
     def execute(
-        self, sql: str, auto_begin: bool = False, fetch: bool = False
+        self, sql: str, auto_begin: bool = False, fetch: bool = False, limit: Optional[int] = None
     ) -> Tuple[AdapterResponse, agate.Table]:
         """Execute the given SQL.
 
@@ -408,7 +408,28 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :param bool auto_begin: If set, and dbt is not currently inside a
             transaction, automatically begin one.
         :param bool fetch: If set, fetch results.
+        :param int limit: If set, limits the result set
         :return: A tuple of the query status and results (empty if fetch=False).
         :rtype: Tuple[AdapterResponse, agate.Table]
         """
         raise dbt.exceptions.NotImplementedError("`execute` is not implemented for this adapter!")
+
+    def add_select_query(self, sql: str) -> Tuple[Connection, Any]:
+        """
+        This was added here because base.impl.BaseAdapter.get_column_schema_from_query expects it to be here.
+        That method wouldn't work unless the adapter used sql.impl.SQLAdapter, sql.connections.SQLConnectionManager
+        or defined this method on <Adapter>ConnectionManager before passing it in to <Adapter>Adapter.
+
+        See https://github.com/dbt-labs/dbt-core/issues/8396 for more information.
+        """
+        raise dbt.exceptions.NotImplementedError(
+            "`add_select_query` is not implemented for this adapter!"
+        )
+
+    @classmethod
+    def data_type_code_to_name(cls, type_code: Union[int, str]) -> str:
+        """Get the string representation of the data type from the type_code."""
+        # https://peps.python.org/pep-0249/#type-objects
+        raise dbt.exceptions.NotImplementedError(
+            "`data_type_code_to_name` is not implemented for this adapter!"
+        )

core/dbt/adapters/base/impl.py

@@ -17,9 +17,11 @@ from typing import (
     Set,
     Tuple,
     Type,
+    TypedDict,
     Union,
 )
 
+from dbt.adapters.capability import Capability, CapabilityDict
 from dbt.contracts.graph.nodes import ColumnLevelConstraint, ConstraintType, ModelLevelConstraint
 
 import agate
@@ -43,8 +45,14 @@ from dbt.exceptions import (
     UnexpectedNullError,
 )
 
-from dbt.adapters.protocol import AdapterConfig, ConnectionManagerProtocol
-from dbt.clients.agate_helper import empty_table, merge_tables, table_from_rows
+from dbt.adapters.protocol import AdapterConfig
+from dbt.clients.agate_helper import (
+    empty_table,
+    get_column_value_uncased,
+    merge_tables,
+    table_from_rows,
+    Integer,
+)
 from dbt.clients.jinja import MacroGenerator
 from dbt.contracts.graph.manifest import Manifest, MacroManifest
 from dbt.contracts.graph.nodes import ResultNode
@@ -60,7 +68,7 @@ from dbt.events.types import (
 )
 from dbt.utils import filter_null_values, executor, cast_to_str, AttrDict
 
-from dbt.adapters.base.connections import Connection, AdapterResponse
+from dbt.adapters.base.connections import Connection, AdapterResponse, BaseConnectionManager
 from dbt.adapters.base.meta import AdapterMeta, available
 from dbt.adapters.base.relation import (
     ComponentName,
@@ -74,7 +82,9 @@ from dbt.adapters.cache import RelationsCache, _make_ref_key_dict
 from dbt import deprecations
 
 GET_CATALOG_MACRO_NAME = "get_catalog"
+GET_CATALOG_RELATIONS_MACRO_NAME = "get_catalog_relations"
 FRESHNESS_MACRO_NAME = "collect_freshness"
+GET_RELATION_LAST_MODIFIED_MACRO_NAME = "get_relation_last_modified"
 
 
 class ConstraintSupport(str, Enum):
@@ -109,7 +119,7 @@ def _catalog_filter_schemas(manifest: Manifest) -> Callable[[agate.Row], bool]:
     return test
 
 
-def _utc(dt: Optional[datetime], source: BaseRelation, field_name: str) -> datetime:
+def _utc(dt: Optional[datetime], source: Optional[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.
     """
@@ -161,6 +171,12 @@ class PythonJobHelper:
         raise NotImplementedError("PythonJobHelper submit function is not implemented yet")
 
 
+class FreshnessResponse(TypedDict):
+    max_loaded_at: datetime
+    snapshotted_at: datetime
+    age: float  # age in seconds
+
+
 class BaseAdapter(metaclass=AdapterMeta):
     """The BaseAdapter provides an abstract base class for adapters.
 
@@ -208,7 +224,7 @@ class BaseAdapter(metaclass=AdapterMeta):
 
     Relation: Type[BaseRelation] = BaseRelation
     Column: Type[BaseColumn] = BaseColumn
-    ConnectionManager: Type[ConnectionManagerProtocol]
+    ConnectionManager: Type[BaseConnectionManager]
 
     # A set of clobber config fields accepted by this adapter
     # for use in materializations
@@ -222,7 +238,11 @@ class BaseAdapter(metaclass=AdapterMeta):
         ConstraintType.foreign_key: ConstraintSupport.ENFORCED,
     }
 
-    def __init__(self, config):
+    # This static member variable can be overriden in concrete adapter
+    # implementations to indicate adapter support for optional capabilities.
+    _capabilities = CapabilityDict({})
+
+    def __init__(self, config) -> None:
         self.config = config
         self.cache = RelationsCache()
         self.connections = self.ConnectionManager(config)
@@ -315,14 +335,21 @@ class BaseAdapter(metaclass=AdapterMeta):
 
     @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.
+        """
+        TODO: Can we move this to dbt-bigquery?
+        Obtain partitions metadata for a BigQuery partitioned table.
 
-        :param str table_id: a partitioned table id, in standard SQL format.
+        :param str table: a partitioned table id, in standard SQL format.
         :return: a partition metadata tuple, as described in
             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)
+        if hasattr(self.connections, "get_partitions_metadata"):
+            return self.connections.get_partitions_metadata(table=table)
+        else:
+            raise NotImplementedError(
+                "`get_partitions_metadata` is not implemented for this adapter!"
+            )
 
     ###
     # Methods that should never be overridden
@@ -408,7 +435,30 @@ class BaseAdapter(metaclass=AdapterMeta):
         lowercase strings.
         """
         info_schema_name_map = SchemaSearchMap()
-        nodes: Iterator[ResultNode] = chain(
+        relations = self._get_catalog_relations(manifest)
+        for relation in relations:
+            info_schema_name_map.add(relation)
+        # result is a map whose keys are information_schema Relations without
+        # identifiers that have appropriate database prefixes, and whose values
+        # are sets of lowercase schema names that are valid members of those
+        # databases
+        return info_schema_name_map
+
+    def _get_catalog_relations_by_info_schema(
+        self, relations
+    ) -> Dict[InformationSchema, List[BaseRelation]]:
+        relations_by_info_schema: Dict[InformationSchema, List[BaseRelation]] = dict()
+        for relation in relations:
+            info_schema = relation.information_schema_only()
+            if info_schema not in relations_by_info_schema:
+                relations_by_info_schema[info_schema] = []
+            relations_by_info_schema[info_schema].append(relation)
+
+        return relations_by_info_schema
+
+    def _get_catalog_relations(self, manifest: Manifest) -> List[BaseRelation]:
+
+        nodes = chain(
             [
                 node
                 for node in manifest.nodes.values()
@@ -416,14 +466,9 @@ class BaseAdapter(metaclass=AdapterMeta):
             ],
             manifest.sources.values(),
         )
-        for node in nodes:
-            relation = self.Relation.create_from(self.config, node)
-            info_schema_name_map.add(relation)
-        # result is a map whose keys are information_schema Relations without
-        # identifiers that have appropriate database prefixes, and whose values
-        # are sets of lowercase schema names that are valid members of those
-        # databases
-        return info_schema_name_map
+
+        relations = [self.Relation.create_from(self.config, n) for n in nodes]
+        return relations
 
     def _relations_cache_for_schemas(
         self, manifest: Manifest, cache_schemas: Optional[Set[BaseRelation]] = None
@@ -453,9 +498,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         # it's possible that there were no relations in some schemas. We want
         # to insert the schemas we query into the cache's `.schemas` attribute
         # so we can check it later
-        cache_update: Set[Tuple[Optional[str], Optional[str]]] = set()
+        cache_update: Set[Tuple[Optional[str], str]] = set()
         for relation in cache_schemas:
-            cache_update.add((relation.database, relation.schema))
+            if relation.schema:
+                cache_update.add((relation.database, relation.schema))
         self.cache.update_schemas(cache_update)
 
     def set_relations_cache(
@@ -917,6 +963,17 @@ class BaseAdapter(metaclass=AdapterMeta):
         """
         raise NotImplementedError("`convert_number_type` is not implemented for this adapter!")
 
+    @classmethod
+    def convert_integer_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.
+
+        :param agate_table: The table
+        :param col_idx: The index into the agate table for the column.
+        :return: The name of the type in the database
+        """
+        return "integer"
+
     @classmethod
     @abc.abstractmethod
     def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str:
@@ -974,6 +1031,7 @@ class BaseAdapter(metaclass=AdapterMeta):
     def convert_agate_type(cls, agate_table: agate.Table, col_idx: int) -> Optional[str]:
         agate_type: Type = agate_table.column_types[col_idx]
         conversions: List[Tuple[Type, Callable[..., str]]] = [
+            (Integer, cls.convert_integer_type),
             (agate.Text, cls.convert_text_type),
             (agate.Number, cls.convert_number_type),
             (agate.Boolean, cls.convert_boolean_type),
@@ -1085,25 +1143,108 @@ class BaseAdapter(metaclass=AdapterMeta):
         results = self._catalog_filter_table(table, manifest)  # type: ignore[arg-type]
         return results
 
-    def get_catalog(self, manifest: Manifest) -> Tuple[agate.Table, List[Exception]]:
-        schema_map = self._get_catalog_schemas(manifest)
+    def _get_one_catalog_by_relations(
+        self,
+        information_schema: InformationSchema,
+        relations: List[BaseRelation],
+        manifest: Manifest,
+    ) -> agate.Table:
 
+        kwargs = {
+            "information_schema": information_schema,
+            "relations": relations,
+        }
+        table = self.execute_macro(
+            GET_CATALOG_RELATIONS_MACRO_NAME,
+            kwargs=kwargs,
+            # pass in the full manifest, so we get any local project
+            # overrides
+            manifest=manifest,
+        )
+
+        results = self._catalog_filter_table(table, manifest)  # type: ignore[arg-type]
+        return results
+
+    def get_filtered_catalog(
+        self, manifest: Manifest, relations: Optional[Set[BaseRelation]] = None
+    ):
+        catalogs: agate.Table
+        if (
+            relations is None
+            or len(relations) > 100
+            or not self.supports(Capability.SchemaMetadataByRelations)
+        ):
+            # Do it the traditional way. We get the full catalog.
+            catalogs, exceptions = self.get_catalog(manifest)
+        else:
+            # Do it the new way. We try to save time by selecting information
+            # only for the exact set of relations we are interested in.
+            catalogs, exceptions = self.get_catalog_by_relations(manifest, relations)
+
+        if relations and catalogs:
+            relation_map = {
+                (
+                    r.database.casefold() if r.database else None,
+                    r.schema.casefold() if r.schema else None,
+                    r.identifier.casefold() if r.identifier else None,
+                )
+                for r in relations
+            }
+
+            def in_map(row: agate.Row):
+                d = _expect_row_value("table_database", row)
+                s = _expect_row_value("table_schema", row)
+                i = _expect_row_value("table_name", row)
+                d = d.casefold() if d is not None else None
+                s = s.casefold() if s is not None else None
+                i = i.casefold() if i is not None else None
+                return (d, s, i) in relation_map
+
+            catalogs = catalogs.where(in_map)
+
+        return catalogs, exceptions
+
+    def row_matches_relation(self, row: agate.Row, relations: Set[BaseRelation]):
+        pass
+
+    def get_catalog(self, manifest: Manifest) -> Tuple[agate.Table, List[Exception]]:
         with executor(self.config) as tpe:
             futures: List[Future[agate.Table]] = []
+            schema_map: SchemaSearchMap = self._get_catalog_schemas(manifest)
             for info, schemas in schema_map.items():
                 if len(schemas) == 0:
                     continue
                 name = ".".join([str(info.database), "information_schema"])
-
                 fut = tpe.submit_connected(
                     self, name, self._get_one_catalog, info, schemas, manifest
                 )
                 futures.append(fut)
 
-            catalogs, exceptions = catch_as_completed(futures)
-
+        catalogs, exceptions = catch_as_completed(futures)
         return catalogs, exceptions
 
+    def get_catalog_by_relations(
+        self, manifest: Manifest, relations: Set[BaseRelation]
+    ) -> Tuple[agate.Table, List[Exception]]:
+        with executor(self.config) as tpe:
+            futures: List[Future[agate.Table]] = []
+            relations_by_schema = self._get_catalog_relations_by_info_schema(relations)
+            for info_schema in relations_by_schema:
+                name = ".".join([str(info_schema.database), "information_schema"])
+                relations = set(relations_by_schema[info_schema])
+                fut = tpe.submit_connected(
+                    self,
+                    name,
+                    self._get_one_catalog_by_relations,
+                    info_schema,
+                    relations,
+                    manifest,
+                )
+                futures.append(fut)
+
+            catalogs, exceptions = catch_as_completed(futures)
+            return catalogs, exceptions
+
     def cancel_open_connections(self):
         """Cancel all open connections."""
         return self.connections.cancel_open()
@@ -1114,7 +1255,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         loaded_at_field: str,
         filter: Optional[str],
         manifest: Optional[Manifest] = None,
-    ) -> Tuple[Optional[AdapterResponse], Dict[str, Any]]:
+    ) -> Tuple[Optional[AdapterResponse], FreshnessResponse]:
         """Calculate the freshness of sources in dbt, and return it"""
         kwargs: Dict[str, Any] = {
             "source": source,
@@ -1149,13 +1290,52 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         snapshotted_at = _utc(table[0][1], source, loaded_at_field)
         age = (snapshotted_at - max_loaded_at).total_seconds()
-        freshness = {
+        freshness: FreshnessResponse = {
             "max_loaded_at": max_loaded_at,
             "snapshotted_at": snapshotted_at,
             "age": age,
         }
         return adapter_response, freshness
 
+    def calculate_freshness_from_metadata(
+        self,
+        source: BaseRelation,
+        manifest: Optional[Manifest] = None,
+    ) -> Tuple[Optional[AdapterResponse], FreshnessResponse]:
+        kwargs: Dict[str, Any] = {
+            "information_schema": source.information_schema_only(),
+            "relations": [source],
+        }
+        result = self.execute_macro(
+            GET_RELATION_LAST_MODIFIED_MACRO_NAME, kwargs=kwargs, manifest=manifest
+        )
+        adapter_response, table = result.response, result.table  # type: ignore[attr-defined]
+
+        try:
+            row = table[0]
+            last_modified_val = get_column_value_uncased("last_modified", row)
+            snapshotted_at_val = get_column_value_uncased("snapshotted_at", row)
+        except Exception:
+            raise MacroResultError(GET_RELATION_LAST_MODIFIED_MACRO_NAME, table)
+
+        if last_modified_val is None:
+            # Interpret missing value as "infinitely long ago"
+            max_loaded_at = datetime(1, 1, 1, 0, 0, 0, tzinfo=pytz.UTC)
+        else:
+            max_loaded_at = _utc(last_modified_val, None, "last_modified")
+
+        snapshotted_at = _utc(snapshotted_at_val, None, "snapshotted_at")
+
+        age = (snapshotted_at - max_loaded_at).total_seconds()
+
+        freshness: FreshnessResponse = {
+            "max_loaded_at": max_loaded_at,
+            "snapshotted_at": snapshotted_at,
+            "age": age,
+        }
+
+        return adapter_response, freshness
+
     def pre_model_hook(self, config: Mapping[str, Any]) -> Any:
         """A hook for running some operation before the model materialization
         runs. The hook can assume it has a connection available.
@@ -1429,6 +1609,14 @@ class BaseAdapter(metaclass=AdapterMeta):
         else:
             return None
 
+    @classmethod
+    def capabilities(cls) -> CapabilityDict:
+        return cls._capabilities
+
+    @classmethod
+    def supports(cls, capability: Capability) -> bool:
+        return bool(cls.capabilities()[capability])
+
 
 COLUMNS_EQUAL_SQL = """
 with diff_count as (

core/dbt/adapters/base/meta.py

@@ -93,7 +93,7 @@ class AdapterMeta(abc.ABCMeta):
     _available_: FrozenSet[str]
     _parse_replacements_: Dict[str, Callable]
 
-    def __new__(mcls, name, bases, namespace, **kwargs):
+    def __new__(mcls, name, bases, namespace, **kwargs) -> "AdapterMeta":
         # mypy does not like the `**kwargs`. But `ABCMeta` itself takes
         # `**kwargs` in its argspec here (and passes them to `type.__new__`.
         # I'm not sure there is any benefit to it after poking around a bit,

core/dbt/adapters/base/plugin.py

@@ -29,7 +29,7 @@ class AdapterPlugin:
         credentials: Type[Credentials],
         include_path: str,
         dependencies: Optional[List[str]] = None,
-    ):
+    ) -> None:
 
         self.adapter: Type[AdapterProtocol] = adapter
         self.credentials: Type[Credentials] = credentials

core/dbt/adapters/base/query_headers.py

@@ -11,7 +11,7 @@ from dbt.exceptions import DbtRuntimeError
 
 
 class NodeWrapper:
-    def __init__(self, node):
+    def __init__(self, node) -> None:
         self._inner_node = node
 
     def __getattr__(self, name):
@@ -25,9 +25,9 @@ class _QueryComment(local):
         - a source_name indicating what set the current thread's query comment
     """
 
-    def __init__(self, initial):
+    def __init__(self, initial) -> None:
         self.query_comment: Optional[str] = initial
-        self.append = False
+        self.append: bool = False
 
     def add(self, sql: str) -> str:
         if not self.query_comment:
@@ -57,7 +57,7 @@ QueryStringFunc = Callable[[str, Optional[NodeWrapper]], str]
 
 
 class MacroQueryStringSetter:
-    def __init__(self, config: AdapterRequiredConfig, manifest: Manifest):
+    def __init__(self, config: AdapterRequiredConfig, manifest: Manifest) -> None:
         self.manifest = manifest
         self.config = config
 

core/dbt/adapters/base/relation.py

@@ -1,8 +1,14 @@
 from collections.abc import Hashable
 from dataclasses import dataclass, field
-from typing import Optional, TypeVar, Any, Type, Dict, Iterator, Tuple, Set
+from typing import Optional, TypeVar, Any, Type, Dict, Iterator, Tuple, Set, Union, FrozenSet
 
-from dbt.contracts.graph.nodes import SourceDefinition, ManifestNode, ResultNode, ParsedNode
+from dbt.contracts.graph.nodes import (
+    SourceDefinition,
+    ManifestNode,
+    ResultNode,
+    ParsedNode,
+    UnitTestSourceDefinition,
+)
 from dbt.contracts.relation import (
     RelationType,
     ComponentName,
@@ -23,6 +29,7 @@ import dbt.exceptions
 
 
 Self = TypeVar("Self", bound="BaseRelation")
+SerializableIterable = Union[Tuple, FrozenSet]
 
 
 @dataclass(frozen=True, eq=False, repr=False)
@@ -36,6 +43,18 @@ class BaseRelation(FakeAPIObject, Hashable):
     quote_policy: Policy = field(default_factory=lambda: Policy())
     dbt_created: bool = False
 
+    # register relation types that can be renamed for the purpose of replacing relations using stages and backups
+    # adding a relation type here also requires defining the associated rename macro
+    # e.g. adding RelationType.View in dbt-postgres requires that you define:
+    # include/postgres/macros/relations/view/rename.sql::postgres__get_rename_view_sql()
+    renameable_relations: SerializableIterable = ()
+
+    # register relation types that are atomically replaceable, e.g. they have "create or replace" syntax
+    # adding a relation type here also requires defining the associated replace macro
+    # e.g. adding RelationType.View in dbt-postgres requires that you define:
+    # include/postgres/macros/relations/view/replace.sql::postgres__get_replace_view_sql()
+    replaceable_relations: SerializableIterable = ()
+
     def _is_exactish_match(self, field: ComponentName, value: str) -> bool:
         if self.dbt_created and self.quote_policy.get_part(field) is False:
             return self.path.get_lowered_part(field) == value.lower()
@@ -169,7 +188,6 @@ class BaseRelation(FakeAPIObject, Hashable):
         return self.include(identifier=False).replace_path(identifier=None)
 
     def _render_iterator(self) -> Iterator[Tuple[Optional[ComponentName], Optional[str]]]:
-
         for key in ComponentName:
             path_part: Optional[str] = None
             if self.include_policy.get_part(key):
@@ -189,7 +207,9 @@ class BaseRelation(FakeAPIObject, Hashable):
         )
 
     @classmethod
-    def create_from_source(cls: Type[Self], source: SourceDefinition, **kwargs: Any) -> Self:
+    def create_from_source(
+        cls: Type[Self], source: Union[SourceDefinition, UnitTestSourceDefinition], **kwargs: Any
+    ) -> Self:
         source_quoting = source.quoting.to_dict(omit_none=True)
         source_quoting.pop("column", None)
         quote_policy = deep_merge(
@@ -251,8 +271,10 @@ class BaseRelation(FakeAPIObject, Hashable):
         node: ResultNode,
         **kwargs: Any,
     ) -> Self:
-        if node.resource_type == NodeType.Source:
-            if not isinstance(node, SourceDefinition):
+        if node.resource_type == NodeType.Source or isinstance(node, UnitTestSourceDefinition):
+            if not (
+                isinstance(node, SourceDefinition) or isinstance(node, UnitTestSourceDefinition)
+            ):
                 raise DbtInternalError(
                     "type mismatch, expected SourceDefinition but got {}".format(type(node))
                 )
@@ -286,6 +308,14 @@ class BaseRelation(FakeAPIObject, Hashable):
         )
         return cls.from_dict(kwargs)
 
+    @property
+    def can_be_renamed(self) -> bool:
+        return self.type in self.renameable_relations
+
+    @property
+    def can_be_replaced(self) -> bool:
+        return self.type in self.replaceable_relations
+
     def __repr__(self) -> str:
         return "<{} {}>".format(self.__class__.__name__, self.render())
 
@@ -439,11 +469,11 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
         self[key].add(schema)
 
     def search(self) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
-        for information_schema_name, schemas in self.items():
+        for information_schema, schemas in self.items():
             for schema in schemas:
-                yield information_schema_name, schema
+                yield information_schema, schema
 
-    def flatten(self, allow_multiple_databases: bool = False):
+    def flatten(self, allow_multiple_databases: bool = False) -> "SchemaSearchMap":
         new = self.__class__()
 
         # make sure we don't have multiple databases if allow_multiple_databases is set to False

core/dbt/adapters/cache.py

@@ -38,8 +38,8 @@ class _CachedRelation:
     :attr BaseRelation inner: The underlying dbt relation.
     """
 
-    def __init__(self, inner):
-        self.referenced_by = {}
+    def __init__(self, inner) -> None:
+        self.referenced_by: Dict[_ReferenceKey, _CachedRelation] = {}
         self.inner = inner
 
     def __str__(self) -> str:

core/dbt/adapters/capability.py

@@ -0,0 +1,52 @@
+from dataclasses import dataclass
+from enum import Enum
+from typing import Optional, DefaultDict, Mapping
+
+
+class Capability(str, Enum):
+    """Enumeration of optional adapter features which can be probed using BaseAdapter.capabilities()"""
+
+    SchemaMetadataByRelations = "SchemaMetadataByRelations"
+    """Indicates efficient support for retrieving schema metadata for a list of relations, rather than always retrieving
+    all the relations in a schema."""
+
+    TableLastModifiedMetadata = "TableLastModifiedMetadata"
+    """Indicates support for determining the time of the last table modification by querying database metadata."""
+
+
+class Support(str, Enum):
+    Unknown = "Unknown"
+    """The adapter has not declared whether this capability is a feature of the underlying DBMS."""
+
+    Unsupported = "Unsupported"
+    """This capability is not possible with the underlying DBMS, so the adapter does not implement related macros."""
+
+    NotImplemented = "NotImplemented"
+    """This capability is available in the underlying DBMS, but support has not yet been implemented in the adapter."""
+
+    Versioned = "Versioned"
+    """Some versions of the DBMS supported by the adapter support this capability and the adapter has implemented any
+    macros needed to use it."""
+
+    Full = "Full"
+    """All versions of the DBMS supported by the adapter support this capability and the adapter has implemented any
+    macros needed to use it."""
+
+
+@dataclass
+class CapabilitySupport:
+    support: Support
+    first_version: Optional[str] = None
+
+    def __bool__(self):
+        return self.support == Support.Versioned or self.support == Support.Full
+
+
+class CapabilityDict(DefaultDict[Capability, CapabilitySupport]):
+    def __init__(self, vals: Mapping[Capability, CapabilitySupport]):
+        super().__init__(self._default)
+        self.update(vals)
+
+    @staticmethod
+    def _default():
+        return CapabilitySupport(support=Support.Unknown)

core/dbt/adapters/factory.py

@@ -19,7 +19,7 @@ Adapter = AdapterProtocol
 
 
 class AdapterContainer:
-    def __init__(self):
+    def __init__(self) -> None:
         self.lock = threading.Lock()
         self.adapters: Dict[str, Adapter] = {}
         self.plugins: Dict[str, AdapterPlugin] = {}

core/dbt/adapters/protocol.py

@@ -90,7 +90,7 @@ class AdapterProtocol(  # type: ignore[misc]
     ConnectionManager: Type[ConnectionManager_T]
     connections: ConnectionManager_T
 
-    def __init__(self, config: AdapterRequiredConfig):
+    def __init__(self, config: AdapterRequiredConfig) -> None:
         ...
 
     @classmethod

core/dbt/adapters/relation_configs/config_change.py

@@ -12,7 +12,7 @@ class RelationConfigChangeAction(StrEnum):
     drop = "drop"
 
 
-@dataclass(frozen=True, eq=True, unsafe_hash=True)
+@dataclass(frozen=True, eq=True, unsafe_hash=True)  # type: ignore
 class RelationConfigChange(RelationConfigBase, ABC):
     action: RelationConfigChangeAction
     context: Hashable  # this is usually a RelationConfig, e.g. IndexConfig, but shouldn't be limited

core/dbt/adapters/sql/connections.py

@@ -1,6 +1,6 @@
 import abc
 import time
-from typing import List, Optional, Tuple, Any, Iterable, Dict, Union
+from typing import List, Optional, Tuple, Any, Iterable, Dict
 
 import agate
 
@@ -131,14 +131,6 @@ class SQLConnectionManager(BaseConnectionManager):
 
         return dbt.clients.agate_helper.table_from_data_flat(data, column_names)
 
-    @classmethod
-    def data_type_code_to_name(cls, type_code: Union[int, str]) -> str:
-        """Get the string representation of the data type from the type_code."""
-        # https://peps.python.org/pep-0249/#type-objects
-        raise dbt.exceptions.NotImplementedError(
-            "`data_type_code_to_name` is not implemented for this adapter!"
-        )
-
     def execute(
         self, sql: str, auto_begin: bool = False, fetch: bool = False, limit: Optional[int] = None
     ) -> Tuple[AdapterResponse, agate.Table]:

core/dbt/adapters/sql/impl.py

@@ -75,6 +75,10 @@ class SQLAdapter(BaseAdapter):
         decimals = agate_table.aggregate(agate.MaxPrecision(col_idx))  # type: ignore[attr-defined]
         return "float8" if decimals else "integer"
 
+    @classmethod
+    def convert_integer_type(cls, agate_table: agate.Table, col_idx: int) -> str:
+        return "integer"
+
     @classmethod
     def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         return "boolean"

core/dbt/cli/flags.py

@@ -57,11 +57,10 @@ def args_to_context(args: List[str]) -> Context:
     from dbt.cli.main import cli
 
     cli_ctx = cli.make_context(cli.name, args)
-    # Split args if they're a comma seperated string.
+    # Split args if they're a comma separated string.
     if len(args) == 1 and "," in args[0]:
         args = args[0].split(",")
     sub_command_name, sub_command, args = cli.resolve_command(cli_ctx, args)
-
     # Handle source and docs group.
     if isinstance(sub_command, Group):
         sub_command_name, sub_command, args = sub_command.resolve_command(cli_ctx, args)
@@ -319,7 +318,6 @@ def command_params(command: CliCommand, args_dict: Dict[str, Any]) -> CommandPar
 
     for k, v in args_dict.items():
         k = k.lower()
-
         # if a "which" value exists in the args dict, it should match the command provided
         if k == WHICH_KEY:
             if v != command.value:
@@ -342,9 +340,14 @@ def command_params(command: CliCommand, args_dict: Dict[str, Any]) -> CommandPar
 
         spinal_cased = k.replace("_", "-")
 
+        # MultiOption flags come back as lists, but we want to pass them as space separated strings
+        if isinstance(v, list):
+            v = " ".join(v)
+
         if k == "macro" and command == CliCommand.RUN_OPERATION:
             add_fn(v)
-        elif v in (None, False):
+        # None is a Singleton, False is a Flyweight, only one instance of each.
+        elif v is None or v is False:
             add_fn(f"--no-{spinal_cased}")
         elif v is True:
             add_fn(f"--{spinal_cased}")
@@ -393,6 +396,7 @@ def command_args(command: CliCommand) -> ArgsList:
         CliCommand.SOURCE_FRESHNESS: cli.freshness,
         CliCommand.TEST: cli.test,
         CliCommand.RETRY: cli.retry,
+        CliCommand.UNIT_TEST: cli.unit_test,
     }
     click_cmd: Optional[ClickCommand] = CMD_DICT.get(command, None)
     if click_cmd is None:

core/dbt/cli/main.py

@@ -1,3 +1,4 @@
+import functools
 from copy import copy
 from dataclasses import dataclass
 from typing import Callable, List, Optional, Union
@@ -39,6 +40,7 @@ from dbt.task.serve import ServeTask
 from dbt.task.show import ShowTask
 from dbt.task.snapshot import SnapshotTask
 from dbt.task.test import TestTask
+from dbt.task.unit_test import UnitTestTask
 
 
 @dataclass
@@ -64,7 +66,7 @@ class dbtRunner:
         self,
         manifest: Optional[Manifest] = None,
         callbacks: Optional[List[Callable[[EventMsg], None]]] = None,
-    ):
+    ) -> None:
         self.manifest = manifest
 
         if callbacks is None:
@@ -118,6 +120,44 @@ class dbtRunner:
             )
 
 
+# approach from https://github.com/pallets/click/issues/108#issuecomment-280489786
+def global_flags(func):
+    @p.cache_selected_only
+    @p.debug
+    @p.deprecated_print
+    @p.enable_legacy_logger
+    @p.fail_fast
+    @p.log_cache_events
+    @p.log_file_max_bytes
+    @p.log_format_file
+    @p.log_level
+    @p.log_level_file
+    @p.log_path
+    @p.macro_debugging
+    @p.partial_parse
+    @p.partial_parse_file_path
+    @p.partial_parse_file_diff
+    @p.populate_cache
+    @p.print
+    @p.printer_width
+    @p.quiet
+    @p.record_timing_info
+    @p.send_anonymous_usage_stats
+    @p.single_threaded
+    @p.static_parser
+    @p.use_colors
+    @p.use_colors_file
+    @p.use_experimental_parser
+    @p.version
+    @p.version_check
+    @p.write_json
+    @functools.wraps(func)
+    def wrapper(*args, **kwargs):
+        return func(*args, **kwargs)
+
+    return wrapper
+
+
 # dbt
 @click.group(
     context_settings={"help_option_names": ["-h", "--help"]},
@@ -126,36 +166,11 @@ class dbtRunner:
     epilog="Specify one of these sub-commands and you can find more help from there.",
 )
 @click.pass_context
-@p.cache_selected_only
-@p.debug
-@p.deprecated_print
-@p.enable_legacy_logger
-@p.fail_fast
-@p.log_cache_events
-@p.log_format
-@p.log_format_file
-@p.log_level
-@p.log_level_file
-@p.log_path
-@p.macro_debugging
-@p.partial_parse
-@p.partial_parse_file_path
-@p.populate_cache
-@p.print
-@p.printer_width
-@p.quiet
-@p.record_timing_info
-@p.send_anonymous_usage_stats
-@p.single_threaded
-@p.static_parser
-@p.use_colors
-@p.use_colors_file
-@p.use_experimental_parser
-@p.version
-@p.version_check
+@global_flags
 @p.warn_error
 @p.warn_error_options
-@p.write_json
+@p.log_format
+@p.show_resource_report
 def cli(ctx, **kwargs):
     """An ELT tool for managing your SQL transformations and data models.
     For more documentation on these commands, visit: docs.getdbt.com
@@ -165,13 +180,14 @@ def cli(ctx, **kwargs):
 # dbt build
 @cli.command("build")
 @click.pass_context
+@global_flags
 @p.defer
 @p.deprecated_defer
 @p.exclude
-@p.fail_fast
 @p.favor_state
 @p.deprecated_favor_state
 @p.full_refresh
+@p.include_saved_query
 @p.indirect_selection
 @p.profile
 @p.profiles_dir
@@ -188,7 +204,6 @@ def cli(ctx, **kwargs):
 @p.target_path
 @p.threads
 @p.vars
-@p.version_check
 @requires.postflight
 @requires.preflight
 @requires.profile
@@ -211,6 +226,8 @@ def build(ctx, **kwargs):
 # dbt clean
 @cli.command("clean")
 @click.pass_context
+@global_flags
+@p.clean_project_files_only
 @p.profile
 @p.profiles_dir
 @p.project_dir
@@ -233,6 +250,7 @@ def clean(ctx, **kwargs):
 # dbt docs
 @cli.group()
 @click.pass_context
+@global_flags
 def docs(ctx, **kwargs):
     """Generate or serve the documentation website for your project"""
 
@@ -240,6 +258,7 @@ def docs(ctx, **kwargs):
 # dbt docs generate
 @docs.command("generate")
 @click.pass_context
+@global_flags
 @p.compile_docs
 @p.defer
 @p.deprecated_defer
@@ -252,6 +271,7 @@ def docs(ctx, **kwargs):
 @p.select
 @p.selector
 @p.empty_catalog
+@p.static
 @p.state
 @p.defer_state
 @p.deprecated_state
@@ -259,7 +279,6 @@ def docs(ctx, **kwargs):
 @p.target_path
 @p.threads
 @p.vars
-@p.version_check
 @requires.postflight
 @requires.preflight
 @requires.profile
@@ -282,6 +301,7 @@ def docs_generate(ctx, **kwargs):
 # dbt docs serve
 @docs.command("serve")
 @click.pass_context
+@global_flags
 @p.browser
 @p.port
 @p.profile
@@ -310,6 +330,7 @@ def docs_serve(ctx, **kwargs):
 # dbt compile
 @cli.command("compile")
 @click.pass_context
+@global_flags
 @p.defer
 @p.deprecated_defer
 @p.exclude
@@ -328,11 +349,11 @@ def docs_serve(ctx, **kwargs):
 @p.state
 @p.defer_state
 @p.deprecated_state
+@p.compile_inject_ephemeral_ctes
 @p.target
 @p.target_path
 @p.threads
 @p.vars
-@p.version_check
 @requires.postflight
 @requires.preflight
 @requires.profile
@@ -356,6 +377,7 @@ def compile(ctx, **kwargs):
 # dbt show
 @cli.command("show")
 @click.pass_context
+@global_flags
 @p.defer
 @p.deprecated_defer
 @p.exclude
@@ -379,7 +401,6 @@ def compile(ctx, **kwargs):
 @p.target_path
 @p.threads
 @p.vars
-@p.version_check
 @requires.postflight
 @requires.preflight
 @requires.profile
@@ -403,6 +424,7 @@ def show(ctx, **kwargs):
 # dbt debug
 @cli.command("debug")
 @click.pass_context
+@global_flags
 @p.debug_connection
 @p.config_dir
 @p.profile
@@ -410,7 +432,6 @@ def show(ctx, **kwargs):
 @p.project_dir
 @p.target
 @p.vars
-@p.version_check
 @requires.postflight
 @requires.preflight
 def debug(ctx, **kwargs):
@@ -429,18 +450,46 @@ def debug(ctx, **kwargs):
 # dbt deps
 @cli.command("deps")
 @click.pass_context
+@global_flags
 @p.profile
 @p.profiles_dir_exists_false
 @p.project_dir
 @p.target
 @p.vars
+@p.source
+@p.dry_run
+@p.lock
+@p.upgrade
+@p.add_package
 @requires.postflight
 @requires.preflight
 @requires.unset_profile
 @requires.project
 def deps(ctx, **kwargs):
-    """Pull the most recent version of the dependencies listed in packages.yml"""
-    task = DepsTask(ctx.obj["flags"], ctx.obj["project"])
+    """Install dbt packages specified.
+    In the following case, a new `package-lock.yml` will be generated and the packages are installed:
+    - user updated the packages.yml
+    - user specify the flag --update, which means for packages that are specified as a
+      range, dbt-core will try to install the newer version
+    Otherwise, deps will use `package-lock.yml` as source of truth to install packages.
+
+    There is a way to add new packages by providing an `--add-package` flag to deps command
+    which will allow user to specify a package they want to add in the format of packagename@version.
+    """
+    flags = ctx.obj["flags"]
+    if flags.ADD_PACKAGE:
+        if not flags.ADD_PACKAGE["version"] and flags.SOURCE != "local":
+            raise BadOptionUsage(
+                message=f"Version is required in --add-package when a package when source is {flags.SOURCE}",
+                option_name="--add-package",
+            )
+    else:
+        if flags.DRY_RUN:
+            raise BadOptionUsage(
+                message="Invalid flag `--dry-run` when not using `--add-package`.",
+                option_name="--dry-run",
+            )
+    task = DepsTask(flags, ctx.obj["project"])
     results = task.run()
     success = task.interpret_results(results)
     return results, success
@@ -449,6 +498,7 @@ def deps(ctx, **kwargs):
 # dbt init
 @cli.command("init")
 @click.pass_context
+@global_flags
 # for backwards compatibility, accept 'project_name' as an optional positional argument
 @click.argument("project_name", required=False)
 @p.profile
@@ -471,6 +521,7 @@ def init(ctx, **kwargs):
 # dbt list
 @cli.command("list")
 @click.pass_context
+@global_flags
 @p.exclude
 @p.indirect_selection
 @p.models
@@ -516,6 +567,7 @@ cli.add_command(ls, "ls")
 # dbt parse
 @cli.command("parse")
 @click.pass_context
+@global_flags
 @p.profile
 @p.profiles_dir
 @p.project_dir
@@ -523,7 +575,6 @@ cli.add_command(ls, "ls")
 @p.target_path
 @p.threads
 @p.vars
-@p.version_check
 @requires.postflight
 @requires.preflight
 @requires.profile
@@ -533,19 +584,18 @@ cli.add_command(ls, "ls")
 def parse(ctx, **kwargs):
     """Parses the project and provides information on performance"""
     # manifest generation and writing happens in @requires.manifest
-
     return ctx.obj["manifest"], True
 
 
 # dbt run
 @cli.command("run")
 @click.pass_context
+@global_flags
 @p.defer
 @p.deprecated_defer
 @p.favor_state
 @p.deprecated_favor_state
 @p.exclude
-@p.fail_fast
 @p.full_refresh
 @p.profile
 @p.profiles_dir
@@ -559,7 +609,6 @@ def parse(ctx, **kwargs):
 @p.target_path
 @p.threads
 @p.vars
-@p.version_check
 @requires.postflight
 @requires.preflight
 @requires.profile
@@ -582,6 +631,7 @@ def run(ctx, **kwargs):
 # dbt retry
 @cli.command("retry")
 @click.pass_context
+@global_flags
 @p.project_dir
 @p.profiles_dir
 @p.vars
@@ -589,7 +639,6 @@ def run(ctx, **kwargs):
 @p.target
 @p.state
 @p.threads
-@p.fail_fast
 @requires.postflight
 @requires.preflight
 @requires.profile
@@ -612,6 +661,7 @@ def retry(ctx, **kwargs):
 # dbt clone
 @cli.command("clone")
 @click.pass_context
+@global_flags
 @p.defer_state
 @p.exclude
 @p.full_refresh
@@ -626,7 +676,6 @@ def retry(ctx, **kwargs):
 @p.target_path
 @p.threads
 @p.vars
-@p.version_check
 @requires.preflight
 @requires.profile
 @requires.project
@@ -649,6 +698,7 @@ def clone(ctx, **kwargs):
 # dbt run operation
 @cli.command("run-operation")
 @click.pass_context
+@global_flags
 @click.argument("macro")
 @p.args
 @p.profile
@@ -680,6 +730,7 @@ def run_operation(ctx, **kwargs):
 # dbt seed
 @cli.command("seed")
 @click.pass_context
+@global_flags
 @p.exclude
 @p.full_refresh
 @p.profile
@@ -695,7 +746,6 @@ def run_operation(ctx, **kwargs):
 @p.target_path
 @p.threads
 @p.vars
-@p.version_check
 @requires.postflight
 @requires.preflight
 @requires.profile
@@ -717,6 +767,7 @@ def seed(ctx, **kwargs):
 # dbt snapshot
 @cli.command("snapshot")
 @click.pass_context
+@global_flags
 @p.defer
 @p.deprecated_defer
 @p.exclude
@@ -756,6 +807,7 @@ def snapshot(ctx, **kwargs):
 # dbt source
 @cli.group()
 @click.pass_context
+@global_flags
 def source(ctx, **kwargs):
     """Manage your project's sources"""
 
@@ -763,6 +815,7 @@ def source(ctx, **kwargs):
 # dbt source freshness
 @source.command("freshness")
 @click.pass_context
+@global_flags
 @p.exclude
 @p.output_path  # TODO: Is this ok to re-use?  We have three different output params, how much can we consolidate?
 @p.profile
@@ -805,6 +858,48 @@ cli.commands["source"].add_command(snapshot_freshness, "snapshot-freshness")  #
 # dbt test
 @cli.command("test")
 @click.pass_context
+@global_flags
+@p.defer
+@p.deprecated_defer
+@p.exclude
+@p.favor_state
+@p.deprecated_favor_state
+@p.indirect_selection
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.state
+@p.defer_state
+@p.deprecated_state
+@p.store_failures
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def test(ctx, **kwargs):
+    """Runs tests on data in deployed models. Run this after `dbt run`"""
+    task = TestTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt unit-test
+@cli.command("unit-test")
+@click.pass_context
 @p.defer
 @p.deprecated_defer
 @p.exclude
@@ -812,6 +907,7 @@ cli.commands["source"].add_command(snapshot_freshness, "snapshot-freshness")  #
 @p.favor_state
 @p.deprecated_favor_state
 @p.indirect_selection
+@p.show_output_format
 @p.profile
 @p.profiles_dir
 @p.project_dir
@@ -832,9 +928,9 @@ cli.commands["source"].add_command(snapshot_freshness, "snapshot-freshness")  #
 @requires.project
 @requires.runtime_config
 @requires.manifest
-def test(ctx, **kwargs):
+def unit_test(ctx, **kwargs):
     """Runs tests on data in deployed models. Run this after `dbt run`"""
-    task = TestTask(
+    task = UnitTestTask(
         ctx.obj["flags"],
         ctx.obj["runtime_config"],
         ctx.obj["manifest"],

core/dbt/cli/option_types.py

@@ -22,6 +22,26 @@ class YAML(ParamType):
             self.fail(f"String '{value}' is not valid YAML", param, ctx)
 
 
+class Package(ParamType):
+    """The Click STRING type. Converts string into dict with package name and version.
+    Example package:
+        package-name@1.0.0
+        package-name
+    """
+
+    name = "NewPackage"
+
+    def convert(self, value, param, ctx):
+        # assume non-string values are a problem
+        if not isinstance(value, str):
+            self.fail(f"Cannot load Package from type {type(value)}", param, ctx)
+        try:
+            package_name, package_version = value.split("@")
+            return {"name": package_name, "version": package_version}
+        except ValueError:
+            return {"name": value, "version": None}
+
+
 class WarnErrorOptionsType(YAML):
     """The Click WarnErrorOptions type. Converts YAML strings into objects."""
 

core/dbt/cli/options.py

@@ -2,19 +2,21 @@ import click
 import inspect
 import typing as t
 from click import Context
+from click.parser import OptionParser, ParsingState
 from dbt.cli.option_types import ChoiceTuple
 
 
 # Implementation from: https://stackoverflow.com/a/48394004
 # Note MultiOption options must be specified with type=tuple or type=ChoiceTuple (https://github.com/pallets/click/issues/2012)
 class MultiOption(click.Option):
-    def __init__(self, *args, **kwargs):
+    def __init__(self, *args, **kwargs) -> None:
         self.save_other_options = kwargs.pop("save_other_options", True)
         nargs = kwargs.pop("nargs", -1)
         assert nargs == -1, "nargs, if set, must be -1 not {}".format(nargs)
         super(MultiOption, self).__init__(*args, **kwargs)
-        self._previous_parser_process = None
-        self._eat_all_parser = None
+        # this makes mypy happy, setting these to None causes mypy failures
+        self._previous_parser_process = lambda *args, **kwargs: None
+        self._eat_all_parser = lambda *args, **kwargs: None
 
         # validate that multiple=True
         multiple = kwargs.pop("multiple", None)
@@ -29,34 +31,35 @@ class MultiOption(click.Option):
         else:
             assert isinstance(option_type, ChoiceTuple), msg
 
-    def add_to_parser(self, parser, ctx):
-        def parser_process(value, state):
+    def add_to_parser(self, parser: OptionParser, ctx: Context):
+        def parser_process(value: str, state: ParsingState):
             # method to hook to the parser.process
             done = False
-            value = [value]
+            value_list = str.split(value, " ")
             if self.save_other_options:
                 # grab everything up to the next option
                 while state.rargs and not done:
-                    for prefix in self._eat_all_parser.prefixes:
+                    for prefix in self._eat_all_parser.prefixes:  # type: ignore[attr-defined]
                         if state.rargs[0].startswith(prefix):
                             done = True
                     if not done:
-                        value.append(state.rargs.pop(0))
+                        value_list.append(state.rargs.pop(0))
             else:
                 # grab everything remaining
-                value += state.rargs
+                value_list += state.rargs
                 state.rargs[:] = []
-            value = tuple(value)
+            value_tuple = tuple(value_list)
             # call the actual process
-            self._previous_parser_process(value, state)
+            self._previous_parser_process(value_tuple, state)
 
         retval = super(MultiOption, self).add_to_parser(parser, ctx)
         for name in self.opts:
             our_parser = parser._long_opt.get(name) or parser._short_opt.get(name)
             if our_parser:
-                self._eat_all_parser = our_parser
+                self._eat_all_parser = our_parser  # type: ignore[assignment]
                 self._previous_parser_process = our_parser.process
-                our_parser.process = parser_process
+                # mypy doesnt like assingment to a method see https://github.com/python/mypy/issues/708
+                our_parser.process = parser_process  # type: ignore[method-assign]
                 break
         return retval
 

core/dbt/cli/params.py

@@ -2,10 +2,16 @@ from pathlib import Path
 
 import click
 from dbt.cli.options import MultiOption
-from dbt.cli.option_types import YAML, ChoiceTuple, WarnErrorOptionsType
+from dbt.cli.option_types import YAML, ChoiceTuple, WarnErrorOptionsType, Package
 from dbt.cli.resolvers import default_project_dir, default_profiles_dir
 from dbt.version import get_version_information
 
+add_package = click.option(
+    "--add-package",
+    help="Add a package to current package spec, specify it as package-name@version. Change the source with --source flag.",
+    envvar=None,
+    type=Package(),
+)
 args = click.option(
     "--args",
     envvar=None,
@@ -40,6 +46,14 @@ compile_docs = click.option(
     default=True,
 )
 
+compile_inject_ephemeral_ctes = click.option(
+    "--inject-ephemeral-ctes/--no-inject-ephemeral-ctes",
+    envvar=None,
+    help="Internal flag controlling injection of referenced ephemeral models' CTEs during `compile`.",
+    hidden=True,
+    default=True,
+)
+
 config_dir = click.option(
     "--config-dir",
     envvar=None,
@@ -69,6 +83,14 @@ deprecated_defer = click.option(
     hidden=True,
 )
 
+dry_run = click.option(
+    "--dry-run",
+    envvar=None,
+    help="Option to run `dbt deps --add-package` without updating package-lock.yml file.",
+    is_flag=True,
+)
+
+
 enable_legacy_logger = click.option(
     "--enable-legacy-logger/--no-enable-legacy-logger",
     envvar="DBT_ENABLE_LEGACY_LOGGER",
@@ -119,6 +141,13 @@ indirect_selection = click.option(
     default="eager",
 )
 
+lock = click.option(
+    "--lock",
+    envvar=None,
+    help="Generate the package-lock.yml file without install the packages.",
+    is_flag=True,
+)
+
 log_cache_events = click.option(
     "--log-cache-events/--no-log-cache-events",
     help="Enable verbose logging for relational cache events to help when debugging.",
@@ -171,6 +200,15 @@ use_colors_file = click.option(
     default=True,
 )
 
+log_file_max_bytes = click.option(
+    "--log-file-max-bytes",
+    envvar="DBT_LOG_FILE_MAX_BYTES",
+    help="Configure the max file size in bytes for a single dbt.log file, before rolling over. 0 means no limit.",
+    default=10 * 1024 * 1024,  # 10mb
+    type=click.INT,
+    hidden=True,
+)
+
 log_path = click.option(
     "--log-path",
     envvar="DBT_LOG_PATH",
@@ -248,6 +286,14 @@ partial_parse_file_path = click.option(
     type=click.Path(exists=True, dir_okay=False, resolve_path=True),
 )
 
+partial_parse_file_diff = click.option(
+    "--partial-parse-file-diff/--no-partial-parse-file-diff",
+    envvar="DBT_PARTIAL_PARSE_FILE_DIFF",
+    help="Internal flag for whether to compute a file diff during partial parsing.",
+    hidden=True,
+    default=True,
+)
+
 populate_cache = click.option(
     "--populate-cache/--no-populate-cache",
     envvar="DBT_POPULATE_CACHE",
@@ -290,7 +336,7 @@ printer_width = click.option(
 profile = click.option(
     "--profile",
     envvar=None,
-    help="Which profile to load. Overrides setting in dbt_project.yml.",
+    help="Which existing profile to load. Overrides setting in dbt_project.yml.",
 )
 
 profiles_dir = click.option(
@@ -343,6 +389,7 @@ resource_type = click.option(
     type=ChoiceTuple(
         [
             "metric",
+            "semantic_model",
             "source",
             "analysis",
             "model",
@@ -360,6 +407,14 @@ resource_type = click.option(
     default=(),
 )
 
+include_saved_query = click.option(
+    "--include-saved-query/--no-include-saved-query",
+    envvar="DBT_INCLUDE_SAVED_QUERY",
+    help="Include saved queries in the list of resources to be selected for build command",
+    is_flag=True,
+    hidden=True,
+)
+
 model_decls = ("-m", "--models", "--model")
 select_decls = ("-s", "--select")
 select_attrs = {
@@ -380,9 +435,9 @@ inline = click.option(
 # Most CLI arguments should use the combined `select` option that aliases `--models` to `--select`.
 # However, if you need to split out these separators (like `dbt ls`), use the `models` and `raw_select` options instead.
 # See https://github.com/dbt-labs/dbt-core/pull/6774#issuecomment-1408476095 for more info.
-models = click.option(*model_decls, **select_attrs)
-raw_select = click.option(*select_decls, **select_attrs)
-select = click.option(*select_decls, *model_decls, **select_attrs)
+models = click.option(*model_decls, **select_attrs)  # type: ignore[arg-type]
+raw_select = click.option(*select_decls, **select_attrs)  # type: ignore[arg-type]
+select = click.option(*select_decls, *model_decls, **select_attrs)  # type: ignore[arg-type]
 
 selector = click.option(
     "--selector",
@@ -397,6 +452,13 @@ send_anonymous_usage_stats = click.option(
     default=True,
 )
 
+clean_project_files_only = click.option(
+    "--clean-project-files-only / --no-clean-project-files-only",
+    envvar="DBT_CLEAN_PROJECT_FILES_ONLY",
+    help="If disabled, dbt clean will delete all paths specified in clean-paths, even if they're outside the dbt project.",
+    default=True,
+)
+
 show = click.option(
     "--show",
     envvar=None,
@@ -432,6 +494,21 @@ empty_catalog = click.option(
     is_flag=True,
 )
 
+source = click.option(
+    "--source",
+    envvar=None,
+    help="Source to download page from, must be one of hub, git, or local. Defaults to hub.",
+    type=click.Choice(["hub", "git", "local"], case_sensitive=True),
+    default="hub",
+)
+
+static = click.option(
+    "--static",
+    help="Generate an additional static_index.html with manifest and catalog built-in.",
+    default=False,
+    is_flag=True,
+)
+
 state = click.option(
     "--state",
     envvar="DBT_STATE",
@@ -500,6 +577,13 @@ target_path = click.option(
     type=click.Path(),
 )
 
+upgrade = click.option(
+    "--upgrade",
+    envvar=None,
+    help="Upgrade packages to the latest version.",
+    is_flag=True,
+)
+
 debug_connection = click.option(
     "--connection",
     envvar=None,
@@ -581,3 +665,10 @@ write_json = click.option(
     help="Whether or not to write the manifest.json and run_results.json files to the target directory",
     default=True,
 )
+
+show_resource_report = click.option(
+    "--show-resource-report/--no-show-resource-report",
+    default=False,
+    envvar="DBT_SHOW_RESOURCE_REPORT",
+    hidden=True,
+)

core/dbt/cli/requires.py

@@ -9,12 +9,14 @@ from dbt.cli.exceptions import (
 from dbt.cli.flags import Flags
 from dbt.config import RuntimeConfig
 from dbt.config.runtime import load_project, load_profile, UnsetProfile
+from dbt.events.base_types import EventLevel
 from dbt.events.functions import fire_event, LOG_VERSION, set_invocation_id, setup_event_logger
 from dbt.events.types import (
     CommandCompleted,
     MainReportVersion,
     MainReportArgs,
     MainTrackingUserState,
+    ResourceReport,
 )
 from dbt.events.helpers import get_json_string_utcnow
 from dbt.events.types import MainEncounteredError, MainStackTrace
@@ -27,6 +29,7 @@ from dbt.plugins import set_up_plugin_manager, get_plugin_manager
 
 from click import Context
 from functools import update_wrapper
+import importlib.util
 import time
 import traceback
 
@@ -96,6 +99,28 @@ def postflight(func):
             fire_event(MainStackTrace(stack_trace=traceback.format_exc()))
             raise ExceptionExit(e)
         finally:
+            # Fire ResourceReport, but only on systems which support the resource
+            # module. (Skip it on Windows).
+            if importlib.util.find_spec("resource") is not None:
+                import resource
+
+                rusage = resource.getrusage(resource.RUSAGE_SELF)
+                fire_event(
+                    ResourceReport(
+                        command_name=ctx.command.name,
+                        command_success=success,
+                        command_wall_clock_time=time.perf_counter() - start_func,
+                        process_user_time=rusage.ru_utime,
+                        process_kernel_time=rusage.ru_stime,
+                        process_mem_max_rss=rusage.ru_maxrss,
+                        process_in_blocks=rusage.ru_inblock,
+                        process_out_blocks=rusage.ru_oublock,
+                    ),
+                    EventLevel.INFO
+                    if "flags" in ctx.obj and ctx.obj["flags"].SHOW_RESOURCE_REPORT
+                    else None,
+                )
+
             fire_event(
                 CommandCompleted(
                     command=ctx.command_path,

core/dbt/cli/types.py

@@ -24,6 +24,7 @@ class Command(Enum):
     SOURCE_FRESHNESS = "freshness"
     TEST = "test"
     RETRY = "retry"
+    UNIT_TEST = "unit-test"
 
     @classmethod
     def from_str(cls, s: str) -> "Command":

core/dbt/clients/agate_helper.py

@@ -3,16 +3,30 @@ from codecs import BOM_UTF8
 import agate
 import datetime
 import isodate
+import io
 import json
 import dbt.utils
 from typing import Iterable, List, Dict, Union, Optional, Any
 
 from dbt.exceptions import DbtRuntimeError
 
-
 BOM = BOM_UTF8.decode("utf-8")  # '\ufeff'
 
 
+class Integer(agate.data_types.DataType):
+    def cast(self, d):
+        # by default agate will cast none as a Number
+        # but we need to cast it as an Integer to preserve
+        # the type when merging and unioning tables
+        if type(d) == int or d is None:
+            return d
+        else:
+            raise agate.exceptions.CastError('Can not parse value "%s" as Integer.' % d)
+
+    def jsonify(self, d):
+        return d
+
+
 class Number(agate.data_types.Number):
     # undo the change in https://github.com/wireservice/agate/pull/733
     # i.e. do not cast True and False to numeric 1 and 0
@@ -48,6 +62,7 @@ def build_type_tester(
 ) -> agate.TypeTester:
 
     types = [
+        Integer(null_values=("null", "")),
         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"),
@@ -123,6 +138,23 @@ def table_from_data_flat(data, column_names: Iterable[str]) -> agate.Table:
     )
 
 
+def json_rows_from_table(table: agate.Table) -> List[Dict[str, Any]]:
+    "Convert a table to a list of row dict objects"
+    output = io.StringIO()
+    table.to_json(path=output)  # type: ignore
+
+    return json.loads(output.getvalue())
+
+
+def list_rows_from_table(table: agate.Table) -> List[Any]:
+    "Convert a table to a list of lists, where the first element represents the header"
+    rows = [[col.name for col in table.columns]]
+    for row in table.rows:
+        rows.append(list(row.values()))
+
+    return rows
+
+
 def empty_table():
     "Returns an empty Agate table. To be used in place of None"
 
@@ -135,12 +167,12 @@ def as_matrix(table):
     return [r.values() for r in table.rows.values()]
 
 
-def from_csv(abspath, text_columns):
+def from_csv(abspath, text_columns, delimiter=","):
     type_tester = build_type_tester(text_columns=text_columns)
     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)
+        return agate.Table.from_csv(fp, column_types=type_tester, delimiter=delimiter)
 
 
 class _NullMarker:
@@ -151,7 +183,7 @@ NullableAgateType = Union[agate.data_types.DataType, _NullMarker]
 
 
 class ColumnTypeBuilder(Dict[str, NullableAgateType]):
-    def __init__(self):
+    def __init__(self) -> None:
         super().__init__()
 
     def __setitem__(self, key, value):
@@ -166,6 +198,13 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
         elif isinstance(value, _NullMarker):
             # use the existing value
             return
+        # when one table column is Number while another is Integer, force the column to Number on merge
+        elif isinstance(value, Integer) and isinstance(existing_type, agate.data_types.Number):
+            # use the existing value
+            return
+        elif isinstance(existing_type, Integer) and isinstance(value, agate.data_types.Number):
+            # overwrite
+            super().__setitem__(key, value)
         elif not isinstance(value, type(existing_type)):
             # actual type mismatch!
             raise DbtRuntimeError(
@@ -177,8 +216,9 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
         result: Dict[str, agate.data_types.DataType] = {}
         for key, value in self.items():
             if isinstance(value, _NullMarker):
-                # this is what agate would do.
-                result[key] = agate.data_types.Number()
+                # agate would make it a Number but we'll make it Integer so that if this column
+                # gets merged with another Integer column, it won't get forced to a Number
+                result[key] = Integer()
             else:
                 result[key] = value
         return result
@@ -218,3 +258,12 @@ def merge_tables(tables: List[agate.Table]) -> agate.Table:
                 rows.append(agate.Row(data, column_names))
     # _is_fork to tell agate that we already made things into `Row`s.
     return agate.Table(rows, column_names, column_types, _is_fork=True)
+
+
+def get_column_value_uncased(column_name: str, row: agate.Row) -> Any:
+    """Get the value of a column in this row, ignoring the casing of the column name."""
+    for key, value in row.items():
+        if key.casefold() == column_name.casefold():
+            return value
+
+    raise KeyError

core/dbt/clients/jinja.py

@@ -191,7 +191,7 @@ NativeSandboxEnvironment.template_class = NativeSandboxTemplate  # type: ignore
 
 
 class TemplateCache:
-    def __init__(self):
+    def __init__(self) -> None:
         self.file_cache: Dict[str, jinja2.Template] = {}
 
     def get_node_template(self, node) -> jinja2.Template:
@@ -330,6 +330,26 @@ class MacroGenerator(BaseMacroGenerator):
             return self.call_macro(*args, **kwargs)
 
 
+class UnitTestMacroGenerator(MacroGenerator):
+    # this makes UnitTestMacroGenerator objects callable like functions
+    def __init__(
+        self,
+        macro_generator: MacroGenerator,
+        call_return_value: Any,
+    ) -> None:
+        super().__init__(
+            macro_generator.macro,
+            macro_generator.context,
+            macro_generator.node,
+            macro_generator.stack,
+        )
+        self.call_return_value = call_return_value
+
+    def __call__(self, *args, **kwargs):
+        with self.track_call():
+            return self.call_return_value
+
+
 class QueryStringGenerator(BaseMacroGenerator):
     def __init__(self, template_str: str, context: Dict[str, Any]) -> None:
         super().__init__(context)

core/dbt/compilation.py

@@ -4,7 +4,6 @@ import json
 import networkx as nx  # type: ignore
 import os
 import pickle
-import sqlparse
 
 from collections import defaultdict
 from typing import List, Dict, Any, Tuple, Optional
@@ -13,7 +12,10 @@ from dbt.flags import get_flags
 from dbt.adapters.factory import get_adapter
 from dbt.clients import jinja
 from dbt.clients.system import make_directory
-from dbt.context.providers import generate_runtime_model_context
+from dbt.context.providers import (
+    generate_runtime_model_context,
+    generate_runtime_unit_test_context,
+)
 from dbt.contracts.graph.manifest import Manifest, UniqueID
 from dbt.contracts.graph.nodes import (
     ManifestNode,
@@ -22,6 +24,7 @@ from dbt.contracts.graph.nodes import (
     GraphMemberNode,
     InjectedCTE,
     SeedNode,
+    UnitTestNode,
 )
 from dbt.exceptions import (
     GraphDependencyNotFoundError,
@@ -36,6 +39,7 @@ from dbt.node_types import NodeType, ModelLanguage
 from dbt.events.format import pluralize
 import dbt.tracking
 import dbt.task.list as list_task
+import sqlparse
 
 graph_file_name = "graph.gpickle"
 
@@ -44,6 +48,7 @@ def print_compile_stats(stats):
     names = {
         NodeType.Model: "model",
         NodeType.Test: "test",
+        NodeType.Unit: "unit test",
         NodeType.Snapshot: "snapshot",
         NodeType.Analysis: "analysis",
         NodeType.Macro: "macro",
@@ -91,6 +96,7 @@ def _generate_stats(manifest: Manifest):
     stats[NodeType.Macro] += len(manifest.macros)
     stats[NodeType.Group] += len(manifest.groups)
     stats[NodeType.SemanticModel] += len(manifest.semantic_models)
+    stats[NodeType.Unit] += len(manifest.unit_tests)
 
     # TODO: should we be counting dimensions + entities?
 
@@ -125,7 +131,7 @@ def _get_tests_for_node(manifest: Manifest, unique_id: UniqueID) -> List[UniqueI
 
 
 class Linker:
-    def __init__(self, data=None):
+    def __init__(self, data=None) -> None:
         if data is None:
             data = {}
         self.graph = nx.DiGraph(**data)
@@ -183,14 +189,18 @@ class Linker:
     def link_graph(self, manifest: Manifest):
         for source in manifest.sources.values():
             self.add_node(source.unique_id)
-        for semantic_model in manifest.semantic_models.values():
-            self.add_node(semantic_model.unique_id)
         for node in manifest.nodes.values():
             self.link_node(node, manifest)
+        for semantic_model in manifest.semantic_models.values():
+            self.link_node(semantic_model, manifest)
         for exposure in manifest.exposures.values():
             self.link_node(exposure, manifest)
         for metric in manifest.metrics.values():
             self.link_node(metric, manifest)
+        for unit_test in manifest.unit_tests.values():
+            self.link_node(unit_test, manifest)
+        for saved_query in manifest.saved_queries.values():
+            self.link_node(saved_query, manifest)
 
         cycle = self.find_cycles()
 
@@ -274,7 +284,7 @@ class Linker:
 
 
 class Compiler:
-    def __init__(self, config):
+    def __init__(self, config) -> None:
         self.config = config
 
     def initialize(self):
@@ -289,8 +299,10 @@ class Compiler:
         manifest: Manifest,
         extra_context: Dict[str, Any],
     ) -> Dict[str, Any]:
-
-        context = generate_runtime_model_context(node, self.config, manifest)
+        if isinstance(node, UnitTestNode):
+            context = generate_runtime_unit_test_context(node, self.config, manifest)
+        else:
+            context = generate_runtime_model_context(node, self.config, manifest)
         context.update(extra_context)
 
         if isinstance(node, GenericTestNode):
@@ -320,6 +332,10 @@ class Compiler:
         if model.compiled_code is None:
             raise DbtRuntimeError("Cannot inject ctes into an uncompiled node", model)
 
+        # tech debt: safe flag/arg access (#6259)
+        if not getattr(self.config.args, "inject_ephemeral_ctes", True):
+            return (model, [])
+
         # extra_ctes_injected flag says that we've already recursively injected the ctes
         if model.extra_ctes_injected:
             return (model, model.extra_ctes)
@@ -378,16 +394,16 @@ class Compiler:
 
             _add_prepended_cte(prepended_ctes, InjectedCTE(id=cte.id, sql=sql))
 
-        injected_sql = inject_ctes_into_sql(
-            model.compiled_code,
-            prepended_ctes,
-        )
         # Check again before updating for multi-threading
         if not model.extra_ctes_injected:
+            injected_sql = inject_ctes_into_sql(
+                model.compiled_code,
+                prepended_ctes,
+            )
+            model.extra_ctes_injected = True
             model._pre_injected_sql = model.compiled_code
             model.compiled_code = injected_sql
             model.extra_ctes = prepended_ctes
-            model.extra_ctes_injected = True
 
         # if model.extra_ctes is not set to prepended ctes, something went wrong
         return model, model.extra_ctes
@@ -523,6 +539,12 @@ class Compiler:
         the node's raw_code into compiled_code, and then calls the
         recursive method to "prepend" the ctes.
         """
+        # Make sure Lexer for sqlparse 0.4.4 is initialized
+        from sqlparse.lexer import Lexer  # type: ignore
+
+        if hasattr(Lexer, "get_default_instance"):
+            Lexer.get_default_instance()
+
         node = self._compile_code(node, manifest, extra_context)
 
         node, _ = self._recursively_prepend_ctes(node, manifest, extra_context)

core/dbt/config/profile.py

@@ -83,7 +83,7 @@ class Profile(HasCredentials):
         user_config: UserConfig,
         threads: int,
         credentials: Credentials,
-    ):
+    ) -> None:
         """Explicitly defining `__init__` to work around bug in Python 3.9.7
         https://bugs.python.org/issue45081
         """

core/dbt/config/project.py

@@ -16,8 +16,12 @@ import os
 
 from dbt.flags import get_flags
 from dbt import deprecations
-from dbt.constants import DEPENDENCIES_FILE_NAME, PACKAGES_FILE_NAME
-from dbt.clients.system import path_exists, resolve_path_from_base, load_file_contents
+from dbt.constants import (
+    DEPENDENCIES_FILE_NAME,
+    PACKAGES_FILE_NAME,
+    PACKAGE_LOCK_HASH_KEY,
+)
+from dbt.clients.system import path_exists, load_file_contents
 from dbt.clients.yaml_helper import load_yaml_text
 from dbt.contracts.connection import QueryComment
 from dbt.exceptions import (
@@ -94,16 +98,17 @@ def _load_yaml(path):
     return load_yaml_text(contents)
 
 
-def package_and_project_data_from_root(project_root):
-    package_filepath = resolve_path_from_base(PACKAGES_FILE_NAME, project_root)
-    dependencies_filepath = resolve_path_from_base(DEPENDENCIES_FILE_NAME, project_root)
+def load_yml_dict(file_path):
+    ret = {}
+    if path_exists(file_path):
+        ret = _load_yaml(file_path) or {}
+    return ret
 
-    packages_yml_dict = {}
-    dependencies_yml_dict = {}
-    if path_exists(package_filepath):
-        packages_yml_dict = _load_yaml(package_filepath) or {}
-    if path_exists(dependencies_filepath):
-        dependencies_yml_dict = _load_yaml(dependencies_filepath) or {}
+
+def package_and_project_data_from_root(project_root):
+
+    packages_yml_dict = load_yml_dict(f"{project_root}/{PACKAGES_FILE_NAME}")
+    dependencies_yml_dict = load_yml_dict(f"{project_root}/{DEPENDENCIES_FILE_NAME}")
 
     if "packages" in packages_yml_dict and "packages" in dependencies_yml_dict:
         msg = "The 'packages' key cannot be specified in both packages.yml and dependencies.yml"
@@ -127,6 +132,8 @@ def package_config_from_data(packages_data: Dict[str, Any]) -> PackageConfig:
     if not packages_data:
         packages_data = {"packages": []}
 
+    if PACKAGE_LOCK_HASH_KEY in packages_data:
+        packages_data.pop(PACKAGE_LOCK_HASH_KEY)
     try:
         PackageConfig.validate(packages_data)
         packages = PackageConfig.from_dict(packages_data)
@@ -425,9 +432,13 @@ class PartialProject(RenderComponents):
         snapshots: Dict[str, Any]
         sources: Dict[str, Any]
         tests: Dict[str, Any]
+        unit_tests: Dict[str, Any]
         metrics: Dict[str, Any]
+        semantic_models: Dict[str, Any]
+        saved_queries: Dict[str, Any]
         exposures: Dict[str, Any]
         vars_value: VarProvider
+        dbt_cloud: Dict[str, Any]
 
         dispatch = cfg.dispatch
         models = cfg.models
@@ -435,7 +446,10 @@ class PartialProject(RenderComponents):
         snapshots = cfg.snapshots
         sources = cfg.sources
         tests = cfg.tests
+        unit_tests = cfg.unit_tests
         metrics = cfg.metrics
+        semantic_models = cfg.semantic_models
+        saved_queries = cfg.saved_queries
         exposures = cfg.exposures
         if cfg.vars is None:
             vars_dict: Dict[str, Any] = {}
@@ -459,6 +473,8 @@ class PartialProject(RenderComponents):
             manifest_selectors = SelectorDict.parse_from_selectors_list(
                 rendered.selectors_dict["selectors"]
             )
+        dbt_cloud = cfg.dbt_cloud
+
         project = Project(
             project_name=name,
             version=version,
@@ -491,13 +507,17 @@ class PartialProject(RenderComponents):
             query_comment=query_comment,
             sources=sources,
             tests=tests,
+            unit_tests=unit_tests,
             metrics=metrics,
+            semantic_models=semantic_models,
+            saved_queries=saved_queries,
             exposures=exposures,
             vars=vars_value,
             config_version=cfg.config_version,
             unrendered=unrendered,
             project_env_vars=project_env_vars,
             restrict_access=cfg.restrict_access,
+            dbt_cloud=dbt_cloud,
         )
         # sanity check - this means an internal issue
         project.validate()
@@ -541,6 +561,7 @@ class PartialProject(RenderComponents):
             packages_specified_path,
         ) = package_and_project_data_from_root(project_root)
         selectors_dict = selector_data_from_root(project_root)
+
         return cls.from_dicts(
             project_root=project_root,
             project_dict=project_dict,
@@ -597,7 +618,10 @@ class Project:
     snapshots: Dict[str, Any]
     sources: Dict[str, Any]
     tests: Dict[str, Any]
+    unit_tests: Dict[str, Any]
     metrics: Dict[str, Any]
+    semantic_models: Dict[str, Any]
+    saved_queries: Dict[str, Any]
     exposures: Dict[str, Any]
     vars: VarProvider
     dbt_version: List[VersionSpecifier]
@@ -609,6 +633,7 @@ class Project:
     unrendered: RenderComponents
     project_env_vars: Dict[str, Any]
     restrict_access: bool
+    dbt_cloud: Dict[str, Any]
 
     @property
     def all_source_paths(self) -> List[str]:
@@ -627,6 +652,13 @@ class Project:
             generic_test_paths.append(os.path.join(test_path, "generic"))
         return generic_test_paths
 
+    @property
+    def fixture_paths(self):
+        fixture_paths = []
+        for test_path in self.test_paths:
+            fixture_paths.append(os.path.join(test_path, "fixtures"))
+        return fixture_paths
+
     def __str__(self):
         cfg = self.to_project_config(with_packages=True)
         return str(cfg)
@@ -672,12 +704,16 @@ class Project:
                 "snapshots": self.snapshots,
                 "sources": self.sources,
                 "tests": self.tests,
+                "unit-tests": self.unit_tests,
                 "metrics": self.metrics,
+                "semantic-models": self.semantic_models,
+                "saved-queries": self.saved_queries,
                 "exposures": self.exposures,
                 "vars": self.vars.to_dict(),
                 "require-dbt-version": [v.to_version_string() for v in self.dbt_version],
                 "config-version": self.config_version,
                 "restrict-access": self.restrict_access,
+                "dbt-cloud": self.dbt_cloud,
             }
         )
         if self.query_comment:

core/dbt/config/renderer.py

@@ -74,7 +74,7 @@ def _list_if_none_or_string(value):
 
 
 class ProjectPostprocessor(Dict[Keypath, Callable[[Any], Any]]):
-    def __init__(self):
+    def __init__(self) -> None:
         super().__init__()
 
         self[("on-run-start",)] = _list_if_none_or_string

core/dbt/config/runtime.py

@@ -166,7 +166,10 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             query_comment=project.query_comment,
             sources=project.sources,
             tests=project.tests,
+            unit_tests=project.unit_tests,
             metrics=project.metrics,
+            semantic_models=project.semantic_models,
+            saved_queries=project.saved_queries,
             exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
@@ -182,6 +185,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             args=args,
             cli_vars=cli_vars,
             dependencies=dependencies,
+            dbt_cloud=project.dbt_cloud,
         )
 
     # Called by 'load_projects' in this class
@@ -321,7 +325,10 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             "snapshots": self._get_config_paths(self.snapshots),
             "sources": self._get_config_paths(self.sources),
             "tests": self._get_config_paths(self.tests),
+            "unit_tests": self._get_config_paths(self.unit_tests),
             "metrics": self._get_config_paths(self.metrics),
+            "semantic_models": self._get_config_paths(self.semantic_models),
+            "saved_queries": self._get_config_paths(self.saved_queries),
             "exposures": self._get_config_paths(self.exposures),
         }
 
@@ -404,7 +411,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
 
 class UnsetCredentials(Credentials):
-    def __init__(self):
+    def __init__(self) -> None:
         super().__init__("", "")
 
     @property

core/dbt/constants.py

@@ -9,8 +9,12 @@ PIN_PACKAGE_URL = (
     "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"
 )
 
+DBT_PROJECT_FILE_NAME = "dbt_project.yml"
 PACKAGES_FILE_NAME = "packages.yml"
 DEPENDENCIES_FILE_NAME = "dependencies.yml"
+PACKAGE_LOCK_FILE_NAME = "package-lock.yml"
 MANIFEST_FILE_NAME = "manifest.json"
 SEMANTIC_MANIFEST_FILE_NAME = "semantic_manifest.json"
 PARTIAL_PARSE_FILE_NAME = "partial_parse.msgpack"
+UNIT_TEST_MANIFEST_FILE_NAME = "unit_test_manifest.json"
+PACKAGE_LOCK_HASH_KEY = "sha1_hash"

core/dbt/context/base.py

@@ -1,6 +1,8 @@
+from __future__ import annotations
+
 import json
 import os
-from typing import Any, Dict, NoReturn, Optional, Mapping, Iterable, Set, List
+from typing import Any, Callable, Dict, NoReturn, Optional, Mapping, Iterable, Set, List
 import threading
 
 from dbt.flags import get_flags
@@ -86,33 +88,29 @@ def get_context_modules() -> Dict[str, Dict[str, Any]]:
 
 
 class ContextMember:
-    def __init__(self, value, name=None):
+    def __init__(self, value: Any, name: Optional[str] = None) -> None:
         self.name = name
         self.inner = value
 
-    def key(self, default):
+    def key(self, default: str) -> str:
         if self.name is None:
             return default
         return self.name
 
 
-def contextmember(value):
-    if isinstance(value, str):
-        return lambda v: ContextMember(v, name=value)
-    return ContextMember(value)
+def contextmember(value: Optional[str] = None) -> Callable:
+    return lambda v: ContextMember(v, name=value)
 
 
-def contextproperty(value):
-    if isinstance(value, str):
-        return lambda v: ContextMember(property(v), name=value)
-    return ContextMember(property(value))
+def contextproperty(value: Optional[str] = None) -> Callable:
+    return lambda v: ContextMember(property(v), name=value)
 
 
 class ContextMeta(type):
-    def __new__(mcls, name, bases, dct):
-        context_members = {}
-        context_attrs = {}
-        new_dct = {}
+    def __new__(mcls, name, bases, dct: Dict[str, Any]) -> ContextMeta:
+        context_members: Dict[str, Any] = {}
+        context_attrs: Dict[str, Any] = {}
+        new_dct: Dict[str, Any] = {}
 
         for base in bases:
             context_members.update(getattr(base, "_context_members_", {}))
@@ -148,27 +146,28 @@ class Var:
         return self._cli_vars
 
     @property
-    def node_name(self):
+    def node_name(self) -> str:
         if self._node is not None:
             return self._node.name
         else:
             return "<Configuration>"
 
-    def get_missing_var(self, var_name):
-        raise RequiredVarNotFoundError(var_name, self._merged, self._node)
+    def get_missing_var(self, var_name: str) -> NoReturn:
+        # TODO function name implies a non exception resolution
+        raise RequiredVarNotFoundError(var_name, dict(self._merged), self._node)
 
-    def has_var(self, var_name: str):
+    def has_var(self, var_name: str) -> bool:
         return var_name in self._merged
 
-    def get_rendered_var(self, var_name):
+    def get_rendered_var(self, var_name: str) -> Any:
         raw = self._merged[var_name]
         # if bool/int/float/etc are passed in, don't compile anything
         if not isinstance(raw, str):
             return raw
 
-        return get_rendered(raw, self._context)
+        return get_rendered(raw, dict(self._context))
 
-    def __call__(self, var_name, default=_VAR_NOTSET):
+    def __call__(self, var_name: str, default: Any = _VAR_NOTSET) -> Any:
         if self.has_var(var_name):
             return self.get_rendered_var(var_name)
         elif default is not self._VAR_NOTSET:
@@ -178,13 +177,17 @@ class Var:
 
 
 class BaseContext(metaclass=ContextMeta):
-    # subclass is TargetContext
-    def __init__(self, cli_vars):
-        self._ctx = {}
-        self.cli_vars = cli_vars
-        self.env_vars = {}
+    # Set by ContextMeta
+    _context_members_: Dict[str, Any]
+    _context_attrs_: Dict[str, Any]
 
-    def generate_builtins(self):
+    # subclass is TargetContext
+    def __init__(self, cli_vars: Dict[str, Any]) -> None:
+        self._ctx: Dict[str, Any] = {}
+        self.cli_vars: Dict[str, Any] = cli_vars
+        self.env_vars: Dict[str, Any] = {}
+
+    def generate_builtins(self) -> Dict[str, Any]:
         builtins: Dict[str, Any] = {}
         for key, value in self._context_members_.items():
             if hasattr(value, "__get__"):
@@ -194,14 +197,14 @@ class BaseContext(metaclass=ContextMeta):
         return builtins
 
     # no dbtClassMixin so this is not an actual override
-    def to_dict(self):
+    def to_dict(self) -> Dict[str, Any]:
         self._ctx["context"] = self._ctx
         builtins = self.generate_builtins()
         self._ctx["builtins"] = builtins
         self._ctx.update(builtins)
         return self._ctx
 
-    @contextproperty
+    @contextproperty()
     def dbt_version(self) -> str:
         """The `dbt_version` variable returns the installed version of dbt that
         is currently running. It can be used for debugging or auditing
@@ -221,7 +224,7 @@ class BaseContext(metaclass=ContextMeta):
         """
         return dbt_version
 
-    @contextproperty
+    @contextproperty()
     def var(self) -> Var:
         """Variables can be passed from your `dbt_project.yml` file into models
         during compilation. These variables are useful for configuring packages
@@ -290,7 +293,7 @@ class BaseContext(metaclass=ContextMeta):
         """
         return Var(self._ctx, self.cli_vars)
 
-    @contextmember
+    @contextmember()
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         """The env_var() function. Return the environment variable named 'var'.
         If there is no such environment variable set, return the default.
@@ -318,7 +321,7 @@ class BaseContext(metaclass=ContextMeta):
 
     if os.environ.get("DBT_MACRO_DEBUGGING"):
 
-        @contextmember
+        @contextmember()
         @staticmethod
         def debug():
             """Enter a debugger at this line in the compiled jinja code."""
@@ -357,7 +360,7 @@ class BaseContext(metaclass=ContextMeta):
         """
         raise MacroReturn(data)
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def fromjson(string: str, default: Any = None) -> Any:
         """The `fromjson` context method can be used to deserialize a json
@@ -378,7 +381,7 @@ class BaseContext(metaclass=ContextMeta):
         except ValueError:
             return default
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def tojson(value: Any, default: Any = None, sort_keys: bool = False) -> Any:
         """The `tojson` context method can be used to serialize a Python
@@ -401,7 +404,7 @@ class BaseContext(metaclass=ContextMeta):
         except ValueError:
             return default
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def fromyaml(value: str, default: Any = None) -> Any:
         """The fromyaml context method can be used to deserialize a yaml string
@@ -432,7 +435,7 @@ class BaseContext(metaclass=ContextMeta):
 
     # safe_dump defaults to sort_keys=True, but we act like json.dumps (the
     # opposite)
-    @contextmember
+    @contextmember()
     @staticmethod
     def toyaml(
         value: Any, default: Optional[str] = None, sort_keys: bool = False
@@ -477,7 +480,7 @@ class BaseContext(metaclass=ContextMeta):
         except TypeError:
             return default
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def set_strict(value: Iterable[Any]) -> Set[Any]:
         """The `set_strict` context method can be used to convert any iterable
@@ -519,7 +522,7 @@ class BaseContext(metaclass=ContextMeta):
         except TypeError:
             return default
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def zip_strict(*args: Iterable[Any]) -> Iterable[Any]:
         """The `zip_strict` context method can be used to used to return
@@ -541,7 +544,7 @@ class BaseContext(metaclass=ContextMeta):
         except TypeError as e:
             raise ZipStrictWrongTypeError(e)
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def log(msg: str, info: bool = False) -> str:
         """Logs a line to either the log file or stdout.
@@ -562,7 +565,7 @@ class BaseContext(metaclass=ContextMeta):
             fire_event(JinjaLogDebug(msg=msg, node_info=get_node_info()))
         return ""
 
-    @contextproperty
+    @contextproperty()
     def run_started_at(self) -> Optional[datetime.datetime]:
         """`run_started_at` outputs the timestamp that this run started, e.g.
         `2017-04-21 01:23:45.678`. The `run_started_at` variable is a Python
@@ -590,19 +593,19 @@ class BaseContext(metaclass=ContextMeta):
         else:
             return None
 
-    @contextproperty
+    @contextproperty()
     def invocation_id(self) -> Optional[str]:
         """invocation_id outputs a UUID generated for this dbt run (useful for
         auditing)
         """
         return get_invocation_id()
 
-    @contextproperty
+    @contextproperty()
     def thread_id(self) -> str:
         """thread_id outputs an ID for the current thread (useful for auditing)"""
         return threading.current_thread().name
 
-    @contextproperty
+    @contextproperty()
     def modules(self) -> Dict[str, Any]:
         """The `modules` variable in the Jinja context contains useful Python
         modules for operating on data.
@@ -627,7 +630,7 @@ class BaseContext(metaclass=ContextMeta):
         """  # noqa
         return get_context_modules()
 
-    @contextproperty
+    @contextproperty()
     def flags(self) -> Any:
         """The `flags` variable contains true/false values for flags provided
         on the command line.
@@ -644,7 +647,7 @@ class BaseContext(metaclass=ContextMeta):
         """
         return flags_module.get_flag_obj()
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def print(msg: str) -> str:
         """Prints a line to stdout.
@@ -662,7 +665,7 @@ class BaseContext(metaclass=ContextMeta):
             print(msg)
         return ""
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def diff_of_two_dicts(
         dict_a: Dict[str, List[str]], dict_b: Dict[str, List[str]]
@@ -691,7 +694,7 @@ class BaseContext(metaclass=ContextMeta):
                 dict_diff.update({k: dict_a[k]})
         return dict_diff
 
-    @contextmember
+    @contextmember()
     @staticmethod
     def local_md5(value: str) -> str:
         """Calculates an MD5 hash of the given string.

core/dbt/context/configured.py

@@ -19,7 +19,7 @@ class ConfiguredContext(TargetContext):
         super().__init__(config.to_target_dict(), config.cli_vars)
         self.config = config
 
-    @contextproperty
+    @contextproperty()
     def project_name(self) -> str:
         return self.config.project_name
 
@@ -80,11 +80,11 @@ class SchemaYamlContext(ConfiguredContext):
         self._project_name = project_name
         self.schema_yaml_vars = schema_yaml_vars
 
-    @contextproperty
+    @contextproperty()
     def var(self) -> ConfiguredVar:
         return ConfiguredVar(self._ctx, self.config, self._project_name)
 
-    @contextmember
+    @contextmember()
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
@@ -113,7 +113,7 @@ class MacroResolvingContext(ConfiguredContext):
     def __init__(self, config):
         super().__init__(config)
 
-    @contextproperty
+    @contextproperty()
     def var(self) -> ConfiguredVar:
         return ConfiguredVar(self._ctx, self.config, self.config.project_name)
 

core/dbt/context/context_config.py

@@ -45,8 +45,14 @@ class UnrenderedConfig(ConfigSource):
             model_configs = unrendered.get("tests")
         elif resource_type == NodeType.Metric:
             model_configs = unrendered.get("metrics")
+        elif resource_type == NodeType.SemanticModel:
+            model_configs = unrendered.get("semantic_models")
+        elif resource_type == NodeType.SavedQuery:
+            model_configs = unrendered.get("saved_queries")
         elif resource_type == NodeType.Exposure:
             model_configs = unrendered.get("exposures")
+        elif resource_type == NodeType.Unit:
+            model_configs = unrendered.get("unit_tests")
         else:
             model_configs = unrendered.get("models")
         if model_configs is None:
@@ -70,8 +76,14 @@ class RenderedConfig(ConfigSource):
             model_configs = self.project.tests
         elif resource_type == NodeType.Metric:
             model_configs = self.project.metrics
+        elif resource_type == NodeType.SemanticModel:
+            model_configs = self.project.semantic_models
+        elif resource_type == NodeType.SavedQuery:
+            model_configs = self.project.saved_queries
         elif resource_type == NodeType.Exposure:
             model_configs = self.project.exposures
+        elif resource_type == NodeType.Unit:
+            model_configs = self.project.unit_tests
         else:
             model_configs = self.project.models
         return model_configs
@@ -189,9 +201,21 @@ 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)
-        return result.update_from(
+        translated = self.translate_hook_names(translated)
+        updated = result.update_from(
             translated, self._active_project.credentials.type, validate=validate
         )
+        return updated
+
+    def translate_hook_names(self, project_dict):
+        # This is a kind of kludge because the fix for #6411 specifically allowed misspelling
+        # the hook field names in dbt_project.yml, which only ever worked because we didn't
+        # run validate on the dbt_project configs.
+        if "pre_hook" in project_dict:
+            project_dict["pre-hook"] = project_dict.pop("pre_hook")
+        if "post_hook" in project_dict:
+            project_dict["post-hook"] = project_dict.pop("post_hook")
+        return project_dict
 
     def calculate_node_config_dict(
         self,

core/dbt/context/docs.py

@@ -24,7 +24,7 @@ class DocsRuntimeContext(SchemaYamlContext):
         self.node = node
         self.manifest = manifest
 
-    @contextmember
+    @contextmember()
     def doc(self, *args: str) -> str:
         """The `doc` function is used to reference docs blocks in schema.yml
         files. It is analogous to the `ref` function. For more information,

core/dbt/context/exceptions_jinja.py

@@ -2,7 +2,6 @@ import functools
 from typing import NoReturn
 
 from dbt.events.functions import warn_or_error
-from dbt.events.helpers import env_secrets, scrub_secrets
 from dbt.events.types import JinjaLogWarning
 
 from dbt.exceptions import (
@@ -26,6 +25,8 @@ from dbt.exceptions import (
     ContractError,
     ColumnTypeMissingError,
     FailFastError,
+    scrub_secrets,
+    env_secrets,
 )
 
 

core/dbt/context/macro_resolver.py

@@ -40,7 +40,7 @@ class MacroResolver:
         self._build_internal_packages_namespace()
         self._build_macros_by_name()
 
-    def _build_internal_packages_namespace(self):
+    def _build_internal_packages_namespace(self) -> None:
         # Iterate in reverse-order and overwrite: the packages that are first
         # in the list are the ones we want to "win".
         self.internal_packages_namespace: MacroNamespace = {}
@@ -56,7 +56,7 @@ class MacroResolver:
     # root package namespace
     # non-internal packages (that aren't local or root)
     # dbt internal packages
-    def _build_macros_by_name(self):
+    def _build_macros_by_name(self) -> None:
         macros_by_name = {}
 
         # all internal packages (already in the right order)
@@ -78,7 +78,7 @@ class MacroResolver:
         self,
         package_namespaces: Dict[str, MacroNamespace],
         macro: Macro,
-    ):
+    ) -> None:
         if macro.package_name in package_namespaces:
             namespace = package_namespaces[macro.package_name]
         else:
@@ -89,7 +89,7 @@ class MacroResolver:
             raise DuplicateMacroNameError(macro, macro, macro.package_name)
         package_namespaces[macro.package_name][macro.name] = macro
 
-    def add_macro(self, macro: Macro):
+    def add_macro(self, macro: Macro) -> None:
         macro_name: str = macro.name
 
         # internal macros (from plugins) will be processed separately from
@@ -103,11 +103,11 @@ class MacroResolver:
             if macro.package_name == self.root_project_name:
                 self.root_package_macros[macro_name] = macro
 
-    def add_macros(self):
+    def add_macros(self) -> None:
         for macro in self.macros.values():
             self.add_macro(macro)
 
-    def get_macro(self, local_package, macro_name):
+    def get_macro(self, local_package, macro_name) -> Optional[Macro]:
         local_package_macros = {}
         # If the macro is explicitly prefixed with an internal namespace
         # (e.g. 'dbt.some_macro'), look there first
@@ -125,7 +125,7 @@ class MacroResolver:
             return self.macros_by_name[macro_name]
         return None
 
-    def get_macro_id(self, local_package, macro_name):
+    def get_macro_id(self, local_package, macro_name) -> Optional[str]:
         macro = self.get_macro(local_package, macro_name)
         if macro is None:
             return None

core/dbt/context/manifest.py

@@ -67,7 +67,7 @@ class ManifestContext(ConfiguredContext):
             dct.update(self.namespace)
         return dct
 
-    @contextproperty
+    @contextproperty()
     def context_macro_stack(self):
         return self.macro_stack
 

core/dbt/context/providers.py

@@ -1,4 +1,5 @@
 import abc
+from copy import deepcopy
 import os
 from typing import (
     Callable,
@@ -17,7 +18,7 @@ from typing_extensions import Protocol
 from dbt.adapters.base.column import Column
 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.clients.jinja import get_rendered, MacroGenerator, MacroStack, UnitTestMacroGenerator
 from dbt.config import RuntimeConfig, Project
 from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
 from dbt.context.base import contextmember, contextproperty, Var
@@ -39,6 +40,7 @@ from dbt.contracts.graph.nodes import (
     RefArgs,
     AccessType,
     SemanticModel,
+    UnitTestNode,
 )
 from dbt.contracts.graph.metrics import MetricReference, ResolvedMetricReference
 from dbt.contracts.graph.unparsed import NodeVersion
@@ -566,6 +568,17 @@ class OperationRefResolver(RuntimeRefResolver):
             return super().create_relation(target_model)
 
 
+class RuntimeUnitTestRefResolver(RuntimeRefResolver):
+    def resolve(
+        self,
+        target_name: str,
+        target_package: Optional[str] = None,
+        target_version: Optional[NodeVersion] = None,
+    ) -> RelationProxy:
+        target_name = f"{self.model.name}__{target_name}"
+        return super().resolve(target_name, target_package, target_version)
+
+
 # `source` implementations
 class ParseSourceResolver(BaseSourceResolver):
     def resolve(self, source_name: str, table_name: str):
@@ -593,6 +606,29 @@ class RuntimeSourceResolver(BaseSourceResolver):
         return self.Relation.create_from_source(target_source)
 
 
+class RuntimeUnitTestSourceResolver(BaseSourceResolver):
+    def resolve(self, source_name: str, table_name: str):
+        target_source = self.manifest.resolve_source(
+            source_name,
+            table_name,
+            self.current_project,
+            self.model.package_name,
+        )
+        if target_source is None or isinstance(target_source, Disabled):
+            raise TargetNotFoundError(
+                node=self.model,
+                target_name=f"{source_name}.{table_name}",
+                target_kind="source",
+                disabled=(isinstance(target_source, Disabled)),
+            )
+        # For unit tests, this isn't a "real" source, it's a ModelNode taking
+        # the place of a source. We don't really need to return the relation here,
+        # we just need to set_cte, but skipping it confuses typing. We *do* need
+        # the relation in the "this" property.
+        self.model.set_cte(target_source.unique_id, None)
+        return self.Relation.create_ephemeral_from_node(self.config, target_source)
+
+
 # metric` implementations
 class ParseMetricResolver(BaseMetricResolver):
     def resolve(self, name: str, package: Optional[str] = None) -> MetricReference:
@@ -618,7 +654,7 @@ class RuntimeMetricResolver(BaseMetricResolver):
                 target_package=target_package,
             )
 
-        return ResolvedMetricReference(target_metric, self.manifest, self.Relation)
+        return ResolvedMetricReference(target_metric, self.manifest)
 
 
 # `var` implementations.
@@ -670,6 +706,22 @@ class RuntimeVar(ModelConfiguredVar):
     pass
 
 
+class UnitTestVar(RuntimeVar):
+    def __init__(
+        self,
+        context: Dict[str, Any],
+        config: RuntimeConfig,
+        node: Resource,
+    ) -> None:
+        config_copy = None
+        assert isinstance(node, UnitTestNode)
+        if node.overrides and node.overrides.vars:
+            config_copy = deepcopy(config)
+            config_copy.cli_vars.update(node.overrides.vars)
+
+        super().__init__(context, config_copy or config, node=node)
+
+
 # Providers
 class Provider(Protocol):
     execute: bool
@@ -711,6 +763,16 @@ class RuntimeProvider(Provider):
     metric = RuntimeMetricResolver
 
 
+class RuntimeUnitTestProvider(Provider):
+    execute = True
+    Config = RuntimeConfigObject
+    DatabaseWrapper = RuntimeDatabaseWrapper
+    Var = UnitTestVar
+    ref = RuntimeUnitTestRefResolver
+    source = RuntimeUnitTestSourceResolver
+    metric = RuntimeMetricResolver
+
+
 class OperationProvider(RuntimeProvider):
     ref = OperationRefResolver
 
@@ -754,19 +816,19 @@ class ProviderContext(ManifestContext):
             self.model,
         )
 
-    @contextproperty
+    @contextproperty()
     def dbt_metadata_envs(self) -> Dict[str, str]:
         return get_metadata_vars()
 
-    @contextproperty
+    @contextproperty()
     def invocation_args_dict(self):
         return args_to_dict(self.config.args)
 
-    @contextproperty
+    @contextproperty()
     def _sql_results(self) -> Dict[str, Optional[AttrDict]]:
         return self.sql_results
 
-    @contextmember
+    @contextmember()
     def load_result(self, name: str) -> Optional[AttrDict]:
         if name in self.sql_results:
             # handle the special case of "main" macro
@@ -787,7 +849,7 @@ class ProviderContext(ManifestContext):
             # Handle trying to load a result that was never stored
             return None
 
-    @contextmember
+    @contextmember()
     def store_result(
         self, name: str, response: Any, agate_table: Optional[agate.Table] = None
     ) -> str:
@@ -803,7 +865,7 @@ class ProviderContext(ManifestContext):
         )
         return ""
 
-    @contextmember
+    @contextmember()
     def store_raw_result(
         self,
         name: str,
@@ -815,7 +877,7 @@ class ProviderContext(ManifestContext):
         response = AdapterResponse(_message=message, code=code, rows_affected=rows_affected)
         return self.store_result(name, response, agate_table)
 
-    @contextproperty
+    @contextproperty()
     def validation(self):
         def validate_any(*args) -> Callable[[T], None]:
             def inner(value: T) -> None:
@@ -836,7 +898,7 @@ class ProviderContext(ManifestContext):
             }
         )
 
-    @contextmember
+    @contextmember()
     def write(self, payload: str) -> str:
         # macros/source defs aren't 'writeable'.
         if isinstance(self.model, (Macro, SourceDefinition)):
@@ -845,11 +907,11 @@ class ProviderContext(ManifestContext):
         self.model.write_node(self.config.project_root, self.model.build_path, payload)
         return ""
 
-    @contextmember
+    @contextmember()
     def render(self, string: str) -> str:
         return get_rendered(string, self._ctx, self.model)
 
-    @contextmember
+    @contextmember()
     def try_or_compiler_error(
         self, message_if_exception: str, func: Callable, *args, **kwargs
     ) -> Any:
@@ -858,21 +920,32 @@ class ProviderContext(ManifestContext):
         except Exception:
             raise CompilationError(message_if_exception, self.model)
 
-    @contextmember
+    @contextmember()
     def load_agate_table(self) -> agate.Table:
         if not isinstance(self.model, SeedNode):
             raise LoadAgateTableNotSeedError(self.model.resource_type, node=self.model)
-        assert self.model.root_path
-        path = os.path.join(self.model.root_path, self.model.original_file_path)
+
+        # include package_path for seeds defined in packages
+        package_path = (
+            os.path.join(self.config.packages_install_path, self.model.package_name)
+            if self.model.package_name != self.config.project_name
+            else "."
+        )
+        path = os.path.join(self.config.project_root, package_path, self.model.original_file_path)
+        if not os.path.exists(path):
+            assert self.model.root_path
+            path = os.path.join(self.model.root_path, self.model.original_file_path)
+
         column_types = self.model.config.column_types
+        delimiter = self.model.config.delimiter
         try:
-            table = agate_helper.from_csv(path, text_columns=column_types)
+            table = agate_helper.from_csv(path, text_columns=column_types, delimiter=delimiter)
         except ValueError as e:
             raise LoadAgateTableValueError(e, node=self.model)
         table.original_abspath = os.path.abspath(path)
         return table
 
-    @contextproperty
+    @contextproperty()
     def ref(self) -> Callable:
         """The most important function in dbt is `ref()`; it's impossible to
         build even moderately complex models without it. `ref()` is how you
@@ -913,11 +986,11 @@ class ProviderContext(ManifestContext):
         """
         return self.provider.ref(self.db_wrapper, self.model, self.config, self.manifest)
 
-    @contextproperty
+    @contextproperty()
     def source(self) -> Callable:
         return self.provider.source(self.db_wrapper, self.model, self.config, self.manifest)
 
-    @contextproperty
+    @contextproperty()
     def metric(self) -> Callable:
         return self.provider.metric(self.db_wrapper, self.model, self.config, self.manifest)
 
@@ -978,7 +1051,7 @@ class ProviderContext(ManifestContext):
         """  # noqa
         return self.provider.Config(self.model, self.context_config)
 
-    @contextproperty
+    @contextproperty()
     def execute(self) -> bool:
         """`execute` is a Jinja variable that returns True when dbt is in
         "execute" mode.
@@ -1039,7 +1112,7 @@ class ProviderContext(ManifestContext):
         """  # noqa
         return self.provider.execute
 
-    @contextproperty
+    @contextproperty()
     def exceptions(self) -> Dict[str, Any]:
         """The exceptions namespace can be used to raise warnings and errors in
         dbt userspace.
@@ -1077,15 +1150,15 @@ class ProviderContext(ManifestContext):
         """  # noqa
         return wrapped_exports(self.model)
 
-    @contextproperty
+    @contextproperty()
     def database(self) -> str:
         return self.config.credentials.database
 
-    @contextproperty
+    @contextproperty()
     def schema(self) -> str:
         return self.config.credentials.schema
 
-    @contextproperty
+    @contextproperty()
     def var(self) -> ModelConfiguredVar:
         return self.provider.Var(
             context=self._ctx,
@@ -1102,22 +1175,22 @@ class ProviderContext(ManifestContext):
         """
         return self.db_wrapper
 
-    @contextproperty
+    @contextproperty()
     def api(self) -> Dict[str, Any]:
         return {
             "Relation": self.db_wrapper.Relation,
             "Column": self.adapter.Column,
         }
 
-    @contextproperty
+    @contextproperty()
     def column(self) -> Type[Column]:
         return self.adapter.Column
 
-    @contextproperty
+    @contextproperty()
     def env(self) -> Dict[str, Any]:
         return self.target
 
-    @contextproperty
+    @contextproperty()
     def graph(self) -> Dict[str, Any]:
         """The `graph` context variable contains information about the nodes in
         your dbt project. Models, sources, tests, and snapshots are all
@@ -1226,30 +1299,42 @@ class ProviderContext(ManifestContext):
 
     @contextproperty("model")
     def ctx_model(self) -> Dict[str, Any]:
-        ret = self.model.to_dict(omit_none=True)
+        model_dct = self.model.to_dict(omit_none=True)
         # Maintain direct use of compiled_sql
         # TODO add depreciation logic[CT-934]
-        if "compiled_code" in ret:
-            ret["compiled_sql"] = ret["compiled_code"]
-        return ret
+        if "compiled_code" in model_dct:
+            model_dct["compiled_sql"] = model_dct["compiled_code"]
 
-    @contextproperty
+        if (
+            hasattr(self.model, "contract")
+            and self.model.contract.alias_types is True
+            and "columns" in model_dct
+        ):
+            for column in model_dct["columns"].values():
+                if "data_type" in column:
+                    orig_data_type = column["data_type"]
+                    # translate data_type to value in Column.TYPE_LABELS
+                    new_data_type = self.adapter.Column.translate_type(orig_data_type)
+                    column["data_type"] = new_data_type
+        return model_dct
+
+    @contextproperty()
     def pre_hooks(self) -> Optional[List[Dict[str, Any]]]:
         return None
 
-    @contextproperty
+    @contextproperty()
     def post_hooks(self) -> Optional[List[Dict[str, Any]]]:
         return None
 
-    @contextproperty
+    @contextproperty()
     def sql(self) -> Optional[str]:
         return None
 
-    @contextproperty
+    @contextproperty()
     def sql_now(self) -> str:
         return self.adapter.date_function()
 
-    @contextmember
+    @contextmember()
     def adapter_macro(self, name: str, *args, **kwargs):
         """This was deprecated in v0.18 in favor of adapter.dispatch"""
         msg = (
@@ -1261,7 +1346,7 @@ class ProviderContext(ManifestContext):
         )
         raise CompilationError(msg)
 
-    @contextmember
+    @contextmember()
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         """The env_var() function. Return the environment variable named 'var'.
         If there is no such environment variable set, return the default.
@@ -1305,7 +1390,7 @@ class ProviderContext(ManifestContext):
         else:
             raise EnvVarMissingError(var)
 
-    @contextproperty
+    @contextproperty()
     def selected_resources(self) -> List[str]:
         """The `selected_resources` variable contains a list of the resources
         selected based on the parameters provided to the dbt command.
@@ -1314,7 +1399,7 @@ class ProviderContext(ManifestContext):
         """
         return selected_resources.SELECTED_RESOURCES
 
-    @contextmember
+    @contextmember()
     def submit_python_job(self, parsed_model: Dict, compiled_code: str) -> AdapterResponse:
         # Check macro_stack and that the unique id is for a materialization macro
         if not (
@@ -1357,25 +1442,25 @@ class MacroContext(ProviderContext):
 class ModelContext(ProviderContext):
     model: ManifestNode
 
-    @contextproperty
+    @contextproperty()
     def pre_hooks(self) -> List[Dict[str, Any]]:
-        if self.model.resource_type in [NodeType.Source, NodeType.Test]:
+        if self.model.resource_type in [NodeType.Source, NodeType.Test, NodeType.Unit]:
             return []
         # TODO CT-211
         return [
             h.to_dict(omit_none=True) for h in self.model.config.pre_hook  # type: ignore[union-attr] # noqa
         ]
 
-    @contextproperty
+    @contextproperty()
     def post_hooks(self) -> List[Dict[str, Any]]:
-        if self.model.resource_type in [NodeType.Source, NodeType.Test]:
+        if self.model.resource_type in [NodeType.Source, NodeType.Test, NodeType.Unit]:
             return []
         # TODO CT-211
         return [
             h.to_dict(omit_none=True) for h in self.model.config.post_hook  # type: ignore[union-attr] # noqa
         ]
 
-    @contextproperty
+    @contextproperty()
     def sql(self) -> Optional[str]:
         # only doing this in sql model for backward compatible
         if self.model.language == ModelLanguage.sql:  # type: ignore[union-attr]
@@ -1392,7 +1477,7 @@ class ModelContext(ProviderContext):
         else:
             return None
 
-    @contextproperty
+    @contextproperty()
     def compiled_code(self) -> Optional[str]:
         if getattr(self.model, "defer_relation", None):
             # TODO https://github.com/dbt-labs/dbt-core/issues/7976
@@ -1403,15 +1488,15 @@ class ModelContext(ProviderContext):
         else:
             return None
 
-    @contextproperty
+    @contextproperty()
     def database(self) -> str:
         return getattr(self.model, "database", self.config.credentials.database)
 
-    @contextproperty
+    @contextproperty()
     def schema(self) -> str:
         return getattr(self.model, "schema", self.config.credentials.schema)
 
-    @contextproperty
+    @contextproperty()
     def this(self) -> Optional[RelationProxy]:
         """`this` makes available schema information about the currently
         executing model. It's is useful in any context in which you need to
@@ -1446,7 +1531,7 @@ class ModelContext(ProviderContext):
             return None
         return self.db_wrapper.Relation.create_from(self.config, self.model)
 
-    @contextproperty
+    @contextproperty()
     def defer_relation(self) -> Optional[RelationProxy]:
         """
         For commands which add information about this node's corresponding
@@ -1461,6 +1546,33 @@ class ModelContext(ProviderContext):
             return None
 
 
+class UnitTestContext(ModelContext):
+    model: UnitTestNode
+
+    @contextmember()
+    def env_var(self, var: str, default: Optional[str] = None) -> str:
+        """The env_var() function. Return the overriden unit test environment variable named 'var'.
+
+        If there is no unit test override, return the environment variable named 'var'.
+
+        If there is no such environment variable set, return the default.
+
+        If the default is None, raise an exception for an undefined variable.
+        """
+        if self.model.overrides and var in self.model.overrides.env_vars:
+            return self.model.overrides.env_vars[var]
+        else:
+            return super().env_var(var, default)
+
+    @contextproperty()
+    def this(self) -> Optional[str]:
+        if self.model.this_input_node_unique_id:
+            this_node = self.manifest.expect(self.model.this_input_node_unique_id)
+            self.model.set_cte(this_node.unique_id, None)  # type: ignore
+            return self.adapter.Relation.add_ephemeral_prefix(this_node.name)
+        return None
+
+
 # This is called by '_context_for', used in 'render_with_context'
 def generate_parser_model_context(
     model: ManifestNode,
@@ -1505,6 +1617,24 @@ def generate_runtime_macro_context(
     return ctx.to_dict()
 
 
+def generate_runtime_unit_test_context(
+    unit_test: UnitTestNode,
+    config: RuntimeConfig,
+    manifest: Manifest,
+) -> Dict[str, Any]:
+    ctx = UnitTestContext(unit_test, config, manifest, RuntimeUnitTestProvider(), None)
+    ctx_dict = ctx.to_dict()
+
+    if unit_test.overrides and unit_test.overrides.macros:
+        for macro_name, macro_value in unit_test.overrides.macros.items():
+            context_value = ctx_dict.get(macro_name)
+            if isinstance(context_value, MacroGenerator):
+                ctx_dict[macro_name] = UnitTestMacroGenerator(context_value, macro_value)
+            else:
+                ctx_dict[macro_name] = macro_value
+    return ctx_dict
+
+
 class ExposureRefResolver(BaseResolver):
     def __call__(self, *args, **kwargs) -> str:
         package = None
@@ -1660,7 +1790,7 @@ class TestContext(ProviderContext):
         )
         self.namespace = macro_namespace
 
-    @contextmember
+    @contextmember()
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):

core/dbt/context/secret.py

@@ -14,7 +14,7 @@ class SecretContext(BaseContext):
     """This context is used in profiles.yml + packages.yml. It can render secret
     env vars that aren't usable elsewhere"""
 
-    @contextmember
+    @contextmember()
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         """The env_var() function. Return the environment variable named 'var'.
         If there is no such environment variable set, return the default.

core/dbt/context/target.py

@@ -9,7 +9,7 @@ class TargetContext(BaseContext):
         super().__init__(cli_vars=cli_vars)
         self.target_dict = target_dict
 
-    @contextproperty
+    @contextproperty()
     def target(self) -> Dict[str, Any]:
         """`target` contains information about your connection to the warehouse
         (specified in profiles.yml). Some configs are shared between all

core/dbt/contracts/README.md

@@ -1 +1,35 @@
 # Contracts README
+
+
+## Artifacts
+
+### Generating JSON schemas
+A helper script, `sripts/collect-artifact-schema.py` is available to generate json schemas corresponding to versioned artifacts (`ArtifactMixin`s).
+
+This script is necessary to run when a new artifact schema version is created, or when changes are made to existing artifact versions, and writes json schema to `schema/dbt/<artifact>/v<version>.json`.
+
+Schemas in `schema/dbt` power the rendering in https://schemas.getdbt.com/ via https://github.com/dbt-labs/schemas.getdbt.com/
+
+#### Example Usage
+
+Available arguments:
+```sh
+❯ scripts/collect-artifact-schema.py --help
+usage: Collect and write dbt arfifact schema [-h] [--path PATH] [--artifact {manifest,sources,run-results,catalog}]
+
+options:
+  -h, --help            show this help message and exit
+  --path PATH           The dir to write artifact schema
+  --artifact {manifest,sources,run-results,catalog}
+                        The name of the artifact to update
+```
+
+Generate latest version of schemas of all artifacts to `schema/dbt/<artifact>/v<version>.json`
+```sh
+> sripts/collect-artifact-schema.py --path schemas
+```
+
+Generate latest version of schemas of manifest to `schema/dbt/manifest/v<version>.json`
+```sh
+> sripts/collect-artifact-schema.py --path schemas --artifact manifest
+```

core/dbt/contracts/connection.py

@@ -16,26 +16,21 @@ from dbt.utils import translate_aliases, md5
 from dbt.events.functions import fire_event
 from dbt.events.types import NewConnectionOpening
 from dbt.events.contextvars import get_node_info
-from typing_extensions import Protocol
+from typing_extensions import Protocol, Annotated
 from dbt.dataclass_schema import (
     dbtClassMixin,
     StrEnum,
     ExtensibleDbtClassMixin,
-    HyphenatedDbtClassMixin,
     ValidatedStringMixin,
-    register_pattern,
 )
 from dbt.contracts.util import Replaceable
+from mashumaro.jsonschema.annotations import Pattern
 
 
 class Identifier(ValidatedStringMixin):
     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_]+$")
-
-
 @dataclass
 class AdapterResponse(dbtClassMixin):
     _message: str
@@ -55,7 +50,8 @@ class ConnectionState(StrEnum):
 
 @dataclass(init=False)
 class Connection(ExtensibleDbtClassMixin, Replaceable):
-    type: Identifier
+    # Annotated is used by mashumaro for jsonschema generation
+    type: Annotated[Identifier, Pattern(r"^[A-Za-z_][A-Za-z0-9_]+$")]
     name: Optional[str] = None
     state: ConnectionState = ConnectionState.INIT
     transaction_open: bool = False
@@ -108,7 +104,7 @@ class LazyHandle:
     connection, updating the handle on the Connection.
     """
 
-    def __init__(self, opener: Callable[[Connection], Connection]):
+    def __init__(self, opener: Callable[[Connection], Connection]) -> None:
         self.opener = opener
 
     def resolve(self, connection: Connection) -> Connection:
@@ -161,6 +157,7 @@ class Credentials(ExtensibleDbtClassMixin, Replaceable, metaclass=abc.ABCMeta):
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
+        # Need to fixup dbname => database, pass => password
         data = cls.translate_aliases(data)
         return data
 
@@ -220,10 +217,10 @@ DEFAULT_QUERY_COMMENT = """
 
 
 @dataclass
-class QueryComment(HyphenatedDbtClassMixin):
+class QueryComment(dbtClassMixin):
     comment: str = DEFAULT_QUERY_COMMENT
     append: bool = False
-    job_label: bool = False
+    job_label: bool = field(default=False, metadata={"alias": "job-label"})
 
 
 class AdapterRequiredConfig(HasCredentials, Protocol):

core/dbt/contracts/files.py

@@ -225,10 +225,14 @@ class SchemaSourceFile(BaseSourceFile):
     sources: List[str] = field(default_factory=list)
     exposures: List[str] = field(default_factory=list)
     metrics: List[str] = field(default_factory=list)
+    # metrics generated from semantic_model measures
+    generated_metrics: List[str] = field(default_factory=list)
     groups: List[str] = field(default_factory=list)
     # node patches contain models, seeds, snapshots, analyses
     ndp: List[str] = field(default_factory=list)
     semantic_models: List[str] = field(default_factory=list)
+    unit_tests: List[str] = field(default_factory=list)
+    saved_queries: 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

core/dbt/contracts/graph/manifest.py

@@ -20,6 +20,7 @@ from typing import (
     Generic,
     AbstractSet,
     ClassVar,
+    Iterable,
 )
 from typing_extensions import Protocol
 from uuid import UUID
@@ -37,14 +38,22 @@ from dbt.contracts.graph.nodes import (
     ModelNode,
     DeferRelation,
     ResultNode,
+    SavedQuery,
     SemanticModel,
     SourceDefinition,
     UnpatchedSourceDefinition,
+    UnitTestDefinition,
 )
 from dbt.contracts.graph.unparsed import SourcePatch, NodeVersion, UnparsedVersion
 from dbt.contracts.graph.manifest_upgrade import upgrade_manifest_json
 from dbt.contracts.files import SourceFile, SchemaSourceFile, FileHash, AnySourceFile
-from dbt.contracts.util import BaseArtifactMetadata, SourceKey, ArtifactMixin, schema_version
+from dbt.contracts.util import (
+    BaseArtifactMetadata,
+    SourceKey,
+    ArtifactMixin,
+    schema_version,
+    get_artifact_schema_version,
+)
 from dbt.dataclass_schema import dbtClassMixin
 from dbt.exceptions import (
     CompilationError,
@@ -88,7 +97,7 @@ def find_unique_id_for_package(storage, key, package: Optional[PackageName]):
 
 
 class DocLookup(dbtClassMixin):
-    def __init__(self, manifest: "Manifest"):
+    def __init__(self, manifest: "Manifest") -> None:
         self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
         self.populate(manifest)
 
@@ -119,7 +128,7 @@ class DocLookup(dbtClassMixin):
 
 
 class SourceLookup(dbtClassMixin):
-    def __init__(self, manifest: "Manifest"):
+    def __init__(self, manifest: "Manifest") -> None:
         self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
         self.populate(manifest)
 
@@ -156,7 +165,7 @@ class RefableLookup(dbtClassMixin):
     _lookup_types: ClassVar[set] = set(NodeType.refable())
     _versioned_types: ClassVar[set] = set(NodeType.versioned())
 
-    def __init__(self, manifest: "Manifest"):
+    def __init__(self, manifest: "Manifest") -> None:
         self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
         self.populate(manifest)
 
@@ -267,7 +276,7 @@ class RefableLookup(dbtClassMixin):
 
 
 class MetricLookup(dbtClassMixin):
-    def __init__(self, manifest: "Manifest"):
+    def __init__(self, manifest: "Manifest") -> None:
         self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
         self.populate(manifest)
 
@@ -299,6 +308,41 @@ class MetricLookup(dbtClassMixin):
         return manifest.metrics[unique_id]
 
 
+class SavedQueryLookup(dbtClassMixin):
+    """Lookup utility for finding SavedQuery nodes"""
+
+    def __init__(self, manifest: "Manifest") -> None:
+        self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
+        self.populate(manifest)
+
+    def get_unique_id(self, search_name, package: Optional[PackageName]):
+        return find_unique_id_for_package(self.storage, search_name, package)
+
+    def find(self, search_name, package: Optional[PackageName], manifest: "Manifest"):
+        unique_id = self.get_unique_id(search_name, package)
+        if unique_id is not None:
+            return self.perform_lookup(unique_id, manifest)
+        return None
+
+    def add_saved_query(self, saved_query: SavedQuery):
+        if saved_query.search_name not in self.storage:
+            self.storage[saved_query.search_name] = {}
+
+        self.storage[saved_query.search_name][saved_query.package_name] = saved_query.unique_id
+
+    def populate(self, manifest):
+        for saved_query in manifest.saved_queries.values():
+            if hasattr(saved_query, "name"):
+                self.add_saved_query(saved_query)
+
+    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> SavedQuery:
+        if unique_id not in manifest.saved_queries:
+            raise dbt.exceptions.DbtInternalError(
+                f"SavedQUery {unique_id} found in cache but not found in manifest"
+            )
+        return manifest.saved_queries[unique_id]
+
+
 class SemanticModelByMeasureLookup(dbtClassMixin):
     """Lookup utility for finding SemanticModel by measure
 
@@ -306,7 +350,7 @@ class SemanticModelByMeasureLookup(dbtClassMixin):
     the semantic models in a manifest.
     """
 
-    def __init__(self, manifest: "Manifest"):
+    def __init__(self, manifest: "Manifest") -> None:
         self.storage: DefaultDict[str, Dict[PackageName, UniqueID]] = defaultdict(dict)
         self.populate(manifest)
 
@@ -331,20 +375,31 @@ class SemanticModelByMeasureLookup(dbtClassMixin):
         """Populate storage with all the measure + package paths to the Manifest's SemanticModels"""
         for semantic_model in manifest.semantic_models.values():
             self.add(semantic_model=semantic_model)
+        for disabled in manifest.disabled.values():
+            for node in disabled:
+                if isinstance(node, SemanticModel):
+                    self.add(semantic_model=node)
 
     def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> SemanticModel:
         """Tries to get a SemanticModel from the Manifest"""
-        semantic_model = manifest.semantic_models.get(unique_id)
-        if semantic_model is None:
+        enabled_semantic_model: Optional[SemanticModel] = manifest.semantic_models.get(unique_id)
+        disabled_semantic_model: Optional[List] = manifest.disabled.get(unique_id)
+
+        if isinstance(enabled_semantic_model, SemanticModel):
+            return enabled_semantic_model
+        elif disabled_semantic_model is not None and isinstance(
+            disabled_semantic_model[0], SemanticModel
+        ):
+            return disabled_semantic_model[0]
+        else:
             raise dbt.exceptions.DbtInternalError(
                 f"Semantic model `{unique_id}` found in cache but not found in manifest"
             )
-        return semantic_model
 
 
-# This handles both models/seeds/snapshots and sources/metrics/exposures
+# This handles both models/seeds/snapshots and sources/metrics/exposures/semantic_models
 class DisabledLookup(dbtClassMixin):
-    def __init__(self, manifest: "Manifest"):
+    def __init__(self, manifest: "Manifest") -> None:
         self.storage: Dict[str, Dict[PackageName, List[Any]]] = {}
         self.populate(manifest)
 
@@ -598,6 +653,9 @@ class Disabled(Generic[D]):
 MaybeMetricNode = Optional[Union[Metric, Disabled[Metric]]]
 
 
+MaybeSavedQueryNode = Optional[Union[SavedQuery, Disabled[SavedQuery]]]
+
+
 MaybeDocumentation = Optional[Documentation]
 
 
@@ -742,6 +800,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     disabled: MutableMapping[str, List[GraphMemberNode]] = field(default_factory=dict)
     env_vars: MutableMapping[str, str] = field(default_factory=dict)
     semantic_models: MutableMapping[str, SemanticModel] = field(default_factory=dict)
+    unit_tests: MutableMapping[str, UnitTestDefinition] = field(default_factory=dict)
+    saved_queries: MutableMapping[str, SavedQuery] = field(default_factory=dict)
 
     _doc_lookup: Optional[DocLookup] = field(
         default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
@@ -755,6 +815,9 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     _metric_lookup: Optional[MetricLookup] = field(
         default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
+    _saved_query_lookup: Optional[SavedQueryLookup] = field(
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
+    )
     _semantic_model_by_measure_lookup: Optional[SemanticModelByMeasureLookup] = field(
         default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
@@ -799,6 +862,9 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             "semantic_models": {
                 k: v.to_dict(omit_none=False) for k, v in self.semantic_models.items()
             },
+            "saved_queries": {
+                k: v.to_dict(omit_none=False) for k, v in self.saved_queries.items()
+            },
         }
 
     def build_disabled_by_file_id(self):
@@ -860,6 +926,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self.sources.values(),
             self.metrics.values(),
             self.semantic_models.values(),
+            self.saved_queries.values(),
         )
         for resource in all_resources:
             resource_type_plural = resource.resource_type.pluralize()
@@ -895,6 +962,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             files={k: _deepcopy(v) for k, v in self.files.items()},
             state_check=_deepcopy(self.state_check),
             semantic_models={k: _deepcopy(v) for k, v in self.semantic_models.items()},
+            unit_tests={k: _deepcopy(v) for k, v in self.unit_tests.items()},
+            saved_queries={k: _deepcopy(v) for k, v in self.saved_queries.items()},
         )
         copy.build_flat_graph()
         return copy
@@ -907,6 +976,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
                 self.exposures.values(),
                 self.metrics.values(),
                 self.semantic_models.values(),
+                self.saved_queries.values(),
             )
         )
         forward_edges, backward_edges = build_node_edges(edge_members)
@@ -927,13 +997,22 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         groupable_nodes = list(
             chain(
                 self.nodes.values(),
+                self.saved_queries.values(),
+                self.semantic_models.values(),
                 self.metrics.values(),
             )
         )
         group_map = {group.name: [] for group in self.groups.values()}
         for node in groupable_nodes:
             if node.group is not None:
-                group_map[node.group].append(node.unique_id)
+                # group updates are not included with state:modified and
+                # by ignoring the groups that aren't in the group map we
+                # can avoid hitting errors for groups that are not getting
+                # updated.  This is a hack but any groups that are not
+                # valid will be caught in
+                # parser.manifest.ManifestLoader.check_valid_group_config_node
+                if node.group in group_map:
+                    group_map[node.group].append(node.unique_id)
         self.group_map = group_map
 
     def writable_manifest(self) -> "WritableManifest":
@@ -954,6 +1033,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             parent_map=self.parent_map,
             group_map=self.group_map,
             semantic_models=self.semantic_models,
+            unit_tests=self.unit_tests,
+            saved_queries=self.saved_queries,
         )
 
     def write(self, path):
@@ -972,6 +1053,10 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             return self.metrics[unique_id]
         elif unique_id in self.semantic_models:
             return self.semantic_models[unique_id]
+        elif unique_id in self.unit_tests:
+            return self.unit_tests[unique_id]
+        elif unique_id in self.saved_queries:
+            return self.saved_queries[unique_id]
         else:
             # something terrible has happened
             raise dbt.exceptions.DbtInternalError(
@@ -1008,6 +1093,13 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self._metric_lookup = MetricLookup(self)
         return self._metric_lookup
 
+    @property
+    def saved_query_lookup(self) -> SavedQueryLookup:
+        """Retuns a SavedQueryLookup, instantiating it first if necessary."""
+        if self._saved_query_lookup is None:
+            self._saved_query_lookup = SavedQueryLookup(self)
+        return self._saved_query_lookup
+
     @property
     def semantic_model_by_measure_lookup(self) -> SemanticModelByMeasureLookup:
         """Gets (and creates if necessary) the lookup utility for getting SemanticModels by measures"""
@@ -1056,8 +1148,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
 
         return resolved_refs
 
-    # Called by dbt.parser.manifest._process_refs_for_exposure, _process_refs_for_metric,
-    # and dbt.parser.manifest._process_refs_for_node
+    # Called by dbt.parser.manifest._process_refs & ManifestLoader.check_for_model_deprecations
     def resolve_ref(
         self,
         source_node: GraphMemberNode,
@@ -1142,6 +1233,35 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             return Disabled(disabled[0])
         return None
 
+    def resolve_saved_query(
+        self,
+        target_saved_query_name: str,
+        target_saved_query_package: Optional[str],
+        current_project: str,
+        node_package: str,
+    ) -> MaybeSavedQueryNode:
+        """Tries to find the SavedQuery by name within the available project and packages.
+
+        Will return the first enabled SavedQuery matching the name found while iterating over
+        the scoped packages. If no enabled SavedQuery node match is found, returns the last
+        disabled SavedQuery node. Otherwise it returns None.
+        """
+        disabled: Optional[List[SavedQuery]] = None
+        candidates = _packages_to_search(current_project, node_package, target_saved_query_package)
+        for pkg in candidates:
+            saved_query = self.saved_query_lookup.find(target_saved_query_name, pkg, self)
+
+            if saved_query is not None and saved_query.config.enabled:
+                return saved_query
+
+            # it's possible that the node is disabled
+            if disabled is None:
+                disabled = self.disabled_lookup.find(f"{target_saved_query_name}", pkg)
+        if disabled:
+            return Disabled(disabled[0])
+
+        return None
+
     def resolve_semantic_model_for_measure(
         self,
         target_measure_name: str,
@@ -1156,6 +1276,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             semantic_model = self.semantic_model_by_measure_lookup.find(
                 target_measure_name, pkg, self
             )
+            # need to return it even if it's disabled so know it's not fully missing
             if semantic_model is not None:
                 return semantic_model
 
@@ -1331,10 +1452,13 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         self.exposures[exposure.unique_id] = exposure
         source_file.exposures.append(exposure.unique_id)
 
-    def add_metric(self, source_file: SchemaSourceFile, metric: Metric):
+    def add_metric(self, source_file: SchemaSourceFile, metric: Metric, generated: bool = False):
         _check_duplicates(metric, self.metrics)
         self.metrics[metric.unique_id] = metric
-        source_file.metrics.append(metric.unique_id)
+        if not generated:
+            source_file.metrics.append(metric.unique_id)
+        else:
+            source_file.generated_metrics.append(metric.unique_id)
 
     def add_group(self, source_file: SchemaSourceFile, group: Group):
         _check_duplicates(group, self.groups)
@@ -1356,6 +1480,10 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
                 source_file.add_test(node.unique_id, test_from)
             if isinstance(node, Metric):
                 source_file.metrics.append(node.unique_id)
+            if isinstance(node, SavedQuery):
+                source_file.saved_queries.append(node.unique_id)
+            if isinstance(node, SemanticModel):
+                source_file.semantic_models.append(node.unique_id)
             if isinstance(node, Exposure):
                 source_file.exposures.append(node.unique_id)
         else:
@@ -1371,6 +1499,17 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         self.semantic_models[semantic_model.unique_id] = semantic_model
         source_file.semantic_models.append(semantic_model.unique_id)
 
+    def add_unit_test(self, source_file: SchemaSourceFile, unit_test: UnitTestDefinition):
+        if unit_test.unique_id in self.unit_tests:
+            raise DuplicateResourceNameError(unit_test, self.unit_tests[unit_test.unique_id])
+        self.unit_tests[unit_test.unique_id] = unit_test
+        source_file.unit_tests.append(unit_test.unique_id)
+
+    def add_saved_query(self, source_file: SchemaSourceFile, saved_query: SavedQuery) -> None:
+        _check_duplicates(saved_query, self.saved_queries)
+        self.saved_queries[saved_query.unique_id] = saved_query
+        source_file.saved_queries.append(saved_query.unique_id)
+
     # end of methods formerly in ParseResult
 
     # Provide support for copy.deepcopy() - we just need to avoid the lock!
@@ -1398,6 +1537,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self.disabled,
             self.env_vars,
             self.semantic_models,
+            self.unit_tests,
+            self.saved_queries,
             self._doc_lookup,
             self._source_lookup,
             self._ref_lookup,
@@ -1410,19 +1551,19 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
 
 
 class MacroManifest(MacroMethods):
-    def __init__(self, macros):
+    def __init__(self, macros) -> None:
         self.macros = macros
         self.metadata = ManifestMetadata()
         # This is returned by the 'graph' context property
         # in the ProviderContext class.
-        self.flat_graph = {}
+        self.flat_graph: Dict[str, Any] = {}
 
 
 AnyManifest = Union[Manifest, MacroManifest]
 
 
 @dataclass
-@schema_version("manifest", 10)
+@schema_version("manifest", 11)
 class WritableManifest(ArtifactMixin):
     nodes: Mapping[UniqueID, ManifestNode] = field(
         metadata=dict(description=("The nodes defined in the dbt project and its dependencies"))
@@ -1468,6 +1609,9 @@ class WritableManifest(ArtifactMixin):
             description="A mapping from group names to their nodes",
         )
     )
+    saved_queries: Mapping[UniqueID, SavedQuery] = field(
+        metadata=dict(description=("The saved queries defined in the dbt project"))
+    )
     semantic_models: Mapping[UniqueID, SemanticModel] = field(
         metadata=dict(description=("The semantic models defined in the dbt project"))
     )
@@ -1476,9 +1620,14 @@ class WritableManifest(ArtifactMixin):
             description="Metadata about the manifest",
         )
     )
+    unit_tests: Mapping[UniqueID, UnitTestDefinition] = field(
+        metadata=dict(
+            description="The unit tests defined in the project",
+        )
+    )
 
     @classmethod
-    def compatible_previous_versions(self):
+    def compatible_previous_versions(cls) -> Iterable[Tuple[str, int]]:
         return [
             ("manifest", 4),
             ("manifest", 5),
@@ -1486,14 +1635,15 @@ class WritableManifest(ArtifactMixin):
             ("manifest", 7),
             ("manifest", 8),
             ("manifest", 9),
+            ("manifest", 10),
         ]
 
     @classmethod
     def upgrade_schema_version(cls, data):
         """This overrides the "upgrade_schema_version" call in VersionedSchema (via
         ArtifactMixin) to modify the dictionary passed in from earlier versions of the manifest."""
-        manifest_schema_version = get_manifest_schema_version(data)
-        if manifest_schema_version <= 9:
+        manifest_schema_version = get_artifact_schema_version(data)
+        if manifest_schema_version <= 10:
             data = upgrade_manifest_json(data, manifest_schema_version)
         return cls.from_dict(data)
 
@@ -1506,13 +1656,6 @@ class WritableManifest(ArtifactMixin):
         return dct
 
 
-def get_manifest_schema_version(dct: dict) -> int:
-    schema_version = dct.get("metadata", {}).get("dbt_schema_version", None)
-    if not schema_version:
-        raise ValueError("Manifest doesn't have schema version")
-    return int(schema_version.split(".")[-2][-1])
-
-
 def _check_duplicates(value: BaseNode, src: Mapping[str, BaseNode]):
     if value.unique_id in src:
         raise DuplicateResourceNameError(value, src[value.unique_id])

core/dbt/contracts/graph/manifest_upgrade.py

@@ -62,10 +62,72 @@ def drop_v9_and_prior_metrics(manifest: dict) -> None:
     manifest["disabled"] = filtered_disabled_entries
 
 
+def _convert_dct_with_filter(v10_dct_with_opt_filter):
+    """Upgrage the filter object from v10 to v11.
+
+    v10 filters from a serialized manifest looked like:
+    {..., 'filter': {'where_sql_template': '<filter_value>'}}
+    whereas v11 filters look like:
+    {..., 'filter': {'where_filters': [{'where_sql_template': '<filter_value>'}, ...]}}
+    """
+    if v10_dct_with_opt_filter is not None and v10_dct_with_opt_filter.get("filter") is not None:
+        v10_dct_with_opt_filter["filter"] = {"where_filters": [v10_dct_with_opt_filter["filter"]]}
+
+
+def _convert_metric(v10_metric_dict):
+    """Upgrades a v10 metric object to a v11 metric object.
+
+    Specifcally the following properties change
+    1. metric.filter
+    2. metric.type_params.measure.filter
+    3. metric.type_params.input_measures[x].filter
+    4. metric.type_params.numerator.filter
+    5. metric.type_params.denominator.filter
+    6. metric.type_params.metrics[x].filter"
+    """
+
+    # handles top level metric filter
+    _convert_dct_with_filter(v10_metric_dict)
+
+    type_params = v10_metric_dict.get("type_params")
+    if type_params is not None:
+        _convert_dct_with_filter(type_params.get("measure"))
+        _convert_dct_with_filter(type_params.get("numerator"))
+        _convert_dct_with_filter(type_params.get("denominator"))
+
+        # handles metric.type_params.input_measures[x].filter
+        input_measures = type_params.get("input_measures")
+        if input_measures is not None:
+            for input_measure in input_measures:
+                _convert_dct_with_filter(input_measure)
+
+        # handles metric.type_params.metrics[x].filter
+        metrics = type_params.get("metrics")
+        if metrics is not None:
+            for metric in metrics:
+                _convert_dct_with_filter(metric)
+
+
+def upgrade_v10_metric_filters(manifest: dict):
+    """Handles metric filters changes from v10 to v11."""
+
+    metrics = manifest.get("metrics", {})
+    for metric in metrics.values():
+        _convert_metric(metric)
+
+    disabled_nodes = manifest.get("disabled", {})
+    for unique_id, nodes in disabled_nodes.items():
+        if unique_id.split(".")[0] == "metric":
+            for node in nodes:
+                _convert_metric(node)
+
+
 def upgrade_manifest_json(manifest: dict, manifest_schema_version: int) -> dict:
     # this should remain 9 while the check in `upgrade_schema_version` may change
     if manifest_schema_version <= 9:
         drop_v9_and_prior_metrics(manifest=manifest)
+    elif manifest_schema_version == 10:
+        upgrade_v10_metric_filters(manifest=manifest)
 
     for node_content in manifest.get("nodes", {}).values():
         upgrade_node_content(node_content)
@@ -83,6 +145,9 @@ def upgrade_manifest_json(manifest: dict, manifest_schema_version: int) -> dict:
         manifest["groups"] = {}
     if "group_map" not in manifest:
         manifest["group_map"] = {}
+    # add unit_tests key
+    if "unit_tests" not in manifest:
+        manifest["unit_tests"] = {}
     for metric_content in manifest.get("metrics", {}).values():
         # handle attr renames + value translation ("expression" -> "derived")
         metric_content = upgrade_ref_content(metric_content)
@@ -104,4 +169,6 @@ def upgrade_manifest_json(manifest: dict, manifest_schema_version: int) -> dict:
         doc_content["resource_type"] = "doc"
     if "semantic_models" not in manifest:
         manifest["semantic_models"] = {}
+    if "saved_queries" not in manifest:
+        manifest["saved_queries"] = {}
     return manifest

core/dbt/contracts/graph/metrics.py

@@ -1,8 +1,15 @@
-from dbt.node_types import NodeType
+from dbt.contracts.graph.manifest import Manifest, Metric
+from dbt_semantic_interfaces.type_enums import MetricType
+
+from typing import Any, Dict, Iterator, List
+
+
+DERIVED_METRICS = [MetricType.DERIVED, MetricType.RATIO]
+BASE_METRICS = [MetricType.SIMPLE, MetricType.CUMULATIVE]
 
 
 class MetricReference(object):
-    def __init__(self, metric_name, package_name=None):
+    def __init__(self, metric_name, package_name=None) -> None:
         self.metric_name = metric_name
         self.package_name = package_name
 
@@ -17,76 +24,74 @@ class ResolvedMetricReference(MetricReference):
     for working with metrics (ie. __str__ and templating functions)
     """
 
-    def __init__(self, node, manifest, Relation):
+    def __init__(self, node: Metric, manifest: Manifest) -> None:
         super().__init__(node.name, node.package_name)
         self.node = node
         self.manifest = manifest
-        self.Relation = Relation
 
-    def __getattr__(self, key):
+    def __getattr__(self, key) -> Any:
         return getattr(self.node, key)
 
-    def __str__(self):
+    def __str__(self) -> str:
         return f"{self.node.name}"
 
     @classmethod
-    def parent_metrics(cls, metric_node, manifest):
+    def parent_metrics(cls, metric_node: Metric, manifest: Manifest) -> Iterator[Metric]:
+        """For a given metric, yeilds all upstream metrics."""
         yield metric_node
 
         for parent_unique_id in metric_node.depends_on.nodes:
-            node = manifest.metrics.get(parent_unique_id)
-            if node and node.resource_type == NodeType.Metric:
+            node = manifest.expect(parent_unique_id)
+            if isinstance(node, Metric):
                 yield from cls.parent_metrics(node, manifest)
 
     @classmethod
-    def parent_metrics_names(cls, metric_node, manifest):
-        yield metric_node.name
-
-        for parent_unique_id in metric_node.depends_on.nodes:
-            node = manifest.metrics.get(parent_unique_id)
-            if node and node.resource_type == NodeType.Metric:
-                yield from cls.parent_metrics_names(node, manifest)
+    def parent_metrics_names(cls, metric_node: Metric, manifest: Manifest) -> Iterator[str]:
+        """For a given metric, yeilds all upstream metric names"""
+        for metric in cls.parent_metrics(metric_node, manifest):
+            yield metric.name
 
     @classmethod
-    def reverse_dag_parsing(cls, metric_node, manifest, metric_depth_count):
-        if metric_node.calculation_method == "derived":
-            yield {metric_node.name: metric_depth_count}
-            metric_depth_count = metric_depth_count + 1
+    def reverse_dag_parsing(
+        cls, metric_node: Metric, manifest: Manifest, metric_depth_count: int
+    ) -> Iterator[Dict[str, int]]:
+        """For the given metric, yeilds dictionaries having {<metric_name>: <depth_from_initial_metric} of upstream derived metrics.
 
-        for parent_unique_id in metric_node.depends_on.nodes:
-            node = manifest.metrics.get(parent_unique_id)
-            if (
-                node
-                and node.resource_type == NodeType.Metric
-                and node.calculation_method == "derived"
-            ):
-                yield from cls.reverse_dag_parsing(node, manifest, metric_depth_count)
+        This function is intended as a helper function for other metric helper functions.
+        """
+        if metric_node.type in DERIVED_METRICS:
+            yield {metric_node.name: metric_depth_count}
+
+            for parent_unique_id in metric_node.depends_on.nodes:
+                node = manifest.expect(parent_unique_id)
+                if isinstance(node, Metric):
+                    yield from cls.reverse_dag_parsing(node, manifest, metric_depth_count + 1)
 
     def full_metric_dependency(self):
+        """Returns a unique list of all upstream metric names."""
         to_return = list(set(self.parent_metrics_names(self.node, self.manifest)))
         return to_return
 
-    def base_metric_dependency(self):
+    def base_metric_dependency(self) -> List[str]:
+        """Returns a unique list of names for all upstream non-derived metrics."""
         in_scope_metrics = list(self.parent_metrics(self.node, self.manifest))
+        base_metrics = {
+            metric.name for metric in in_scope_metrics if metric.type not in DERIVED_METRICS
+        }
 
-        to_return = []
-        for metric in in_scope_metrics:
-            if metric.calculation_method != "derived" and metric.name not in to_return:
-                to_return.append(metric.name)
+        return list(base_metrics)
 
-        return to_return
-
-    def derived_metric_dependency(self):
+    def derived_metric_dependency(self) -> List[str]:
+        """Returns a unique list of names for all upstream derived metrics."""
         in_scope_metrics = list(self.parent_metrics(self.node, self.manifest))
+        derived_metrics = {
+            metric.name for metric in in_scope_metrics if metric.type in DERIVED_METRICS
+        }
 
-        to_return = []
-        for metric in in_scope_metrics:
-            if metric.calculation_method == "derived" and metric.name not in to_return:
-                to_return.append(metric.name)
+        return list(derived_metrics)
 
-        return to_return
-
-    def derived_metric_dependency_depth(self):
+    def derived_metric_dependency_depth(self) -> List[Dict[str, int]]:
+        """Returns a list of {<metric_name>: <depth_from_initial_metric>} for all upstream metrics."""
         metric_depth_count = 1
         to_return = list(self.reverse_dag_parsing(self.node, self.manifest, metric_depth_count))
 

core/dbt/contracts/graph/model_config.py

@@ -2,11 +2,11 @@ from dataclasses import field, Field, dataclass
 from enum import Enum
 from itertools import chain
 from typing import Any, List, Optional, Dict, Union, Type, TypeVar, Callable
+from typing_extensions import Annotated
 
 from dbt.dataclass_schema import (
     dbtClassMixin,
     ValidationError,
-    register_pattern,
     StrEnum,
 )
 from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed, Docs
@@ -14,7 +14,9 @@ from dbt.contracts.graph.utils import validate_color
 from dbt.contracts.util import Replaceable, list_str
 from dbt.exceptions import DbtInternalError, CompilationError
 from dbt import hooks
-from dbt.node_types import NodeType
+from dbt.node_types import NodeType, AccessType
+from dbt_semantic_interfaces.type_enums.export_destination_type import ExportDestinationType
+from mashumaro.jsonschema.annotations import Pattern
 
 
 M = TypeVar("M", bound="Metadata")
@@ -188,9 +190,6 @@ class Severity(str):
     pass
 
 
-register_pattern(Severity, insensitive_patterns("warn", "error"))
-
-
 class OnConfigurationChangeOption(StrEnum):
     Apply = "apply"
     Continue = "continue"
@@ -204,6 +203,7 @@ class OnConfigurationChangeOption(StrEnum):
 @dataclass
 class ContractConfig(dbtClassMixin, Replaceable):
     enforced: bool = False
+    alias_types: bool = True
 
 
 @dataclass
@@ -218,7 +218,6 @@ T = TypeVar("T", bound="BaseConfig")
 
 @dataclass
 class BaseConfig(AdditionalPropertiesAllowed, Replaceable):
-
     # enable syntax like: config['key']
     def __getitem__(self, key):
         return self.get(key)
@@ -376,25 +375,50 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable):
         self.validate(dct)
         return self.from_dict(dct)
 
-    def replace(self, **kwargs):
-        dct = self.to_dict(omit_none=True)
-
-        mapping = self.field_mapping()
-        for key, value in kwargs.items():
-            new_key = mapping.get(key, key)
-            dct[new_key] = value
-        return self.from_dict(dct)
-
 
 @dataclass
 class SemanticModelConfig(BaseConfig):
     enabled: bool = True
+    group: Optional[str] = field(
+        default=None,
+        metadata=CompareBehavior.Exclude.meta(),
+    )
+    meta: Dict[str, Any] = field(
+        default_factory=dict,
+        metadata=MergeBehavior.Update.meta(),
+    )
+
+
+@dataclass
+class SavedQueryConfig(BaseConfig):
+    """Where config options for SavedQueries are stored.
+
+    This class is much like many other node config classes. It's likely that
+    this class will expand in the direction of what's in the `NodeAndTestConfig`
+    class. It might make sense to clean the various *Config classes into one at
+    some point.
+    """
+
+    enabled: bool = True
+    group: Optional[str] = field(
+        default=None,
+        metadata=CompareBehavior.Exclude.meta(),
+    )
+    meta: Dict[str, Any] = field(
+        default_factory=dict,
+        metadata=MergeBehavior.Update.meta(),
+    )
+    export_as: Optional[ExportDestinationType] = None
+    schema: Optional[str] = None
 
 
 @dataclass
 class MetricConfig(BaseConfig):
     enabled: bool = True
-    group: Optional[str] = None
+    group: Optional[str] = field(
+        default=None,
+        metadata=CompareBehavior.Exclude.meta(),
+    )
 
 
 @dataclass
@@ -447,11 +471,11 @@ class NodeConfig(NodeAndTestConfig):
     persist_docs: Dict[str, Any] = field(default_factory=dict)
     post_hook: List[Hook] = field(
         default_factory=list,
-        metadata=MergeBehavior.Append.meta(),
+        metadata={"merge": MergeBehavior.Append, "alias": "post-hook"},
     )
     pre_hook: List[Hook] = field(
         default_factory=list,
-        metadata=MergeBehavior.Append.meta(),
+        metadata={"merge": MergeBehavior.Append, "alias": "pre-hook"},
     )
     quoting: Dict[str, Any] = field(
         default_factory=dict,
@@ -511,39 +535,34 @@ class NodeConfig(NodeAndTestConfig):
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        field_map = {"post-hook": "post_hook", "pre-hook": "pre_hook"}
-        # create a new dict because otherwise it gets overwritten in
-        # tests
-        new_dict = {}
-        for key in data:
-            new_dict[key] = data[key]
-        data = new_dict
         for key in hooks.ModelHookType:
             if key in data:
                 data[key] = [hooks.get_hook_dict(h) for h in data[key]]
-        for field_name in field_map:
-            if field_name in data:
-                new_name = field_map[field_name]
-                data[new_name] = data.pop(field_name)
         return data
 
-    def __post_serialize__(self, dct):
-        dct = super().__post_serialize__(dct)
-        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)
-        return dct
-
     # this is still used by jsonschema validation
     @classmethod
     def field_mapping(cls):
         return {"post_hook": "post-hook", "pre_hook": "pre-hook"}
 
 
+@dataclass
+class ModelConfig(NodeConfig):
+    access: AccessType = field(
+        default=AccessType.Protected,
+        metadata=MergeBehavior.Update.meta(),
+    )
+
+
+@dataclass
+class UnitTestNodeConfig(NodeConfig):
+    expected_rows: List[Dict[str, Any]] = field(default_factory=list)
+
+
 @dataclass
 class SeedConfig(NodeConfig):
     materialized: str = "seed"
+    delimiter: str = ","
     quote_columns: Optional[bool] = None
 
     @classmethod
@@ -553,6 +572,9 @@ class SeedConfig(NodeConfig):
             raise ValidationError("A seed must have a materialized value of 'seed'")
 
 
+SEVERITY_PATTERN = r"^([Ww][Aa][Rr][Nn]|[Ee][Rr][Rr][Oo][Rr])$"
+
+
 @dataclass
 class TestConfig(NodeAndTestConfig):
     __test__ = False
@@ -563,14 +585,64 @@ class TestConfig(NodeAndTestConfig):
         metadata=CompareBehavior.Exclude.meta(),
     )
     materialized: str = "test"
-    severity: Severity = Severity("ERROR")
+    # Annotated is used by mashumaro for jsonschema generation
+    severity: Annotated[Severity, Pattern(SEVERITY_PATTERN)] = Severity("ERROR")
     store_failures: Optional[bool] = None
+    store_failures_as: Optional[str] = None
     where: Optional[str] = None
     limit: Optional[int] = None
     fail_calc: str = "count(*)"
     warn_if: str = "!= 0"
     error_if: str = "!= 0"
 
+    def __post_init__(self):
+        """
+        The presence of a setting for `store_failures_as` overrides any existing setting for `store_failures`,
+        regardless of level of granularity. If `store_failures_as` is not set, then `store_failures` takes effect.
+        At the time of implementation, `store_failures = True` would always create a table; the user could not
+        configure this. Hence, if `store_failures = True` and `store_failures_as` is not specified, then it
+        should be set to "table" to mimic the existing functionality.
+
+        A side effect of this overriding functionality is that `store_failures_as="view"` at the project
+        level cannot be turned off at the model level without setting both `store_failures_as` and
+        `store_failures`. The former would cascade down and override `store_failures=False`. The proposal
+        is to include "ephemeral" as a value for `store_failures_as`, which effectively sets
+        `store_failures=False`.
+
+        The exception handling for this is tricky. If we raise an exception here, the entire run fails at
+        parse time. We would rather well-formed models run successfully, leaving only exceptions to be rerun
+        if necessary. Hence, the exception needs to be raised in the test materialization. In order to do so,
+        we need to make sure that we go down the `store_failures = True` route with the invalid setting for
+        `store_failures_as`. This results in the `.get()` defaulted to `True` below, instead of a normal
+        dictionary lookup as is done in the `if` block. Refer to the test materialization for the
+        exception that is raise as a result of an invalid value.
+
+        The intention of this block is to behave as if `store_failures_as` is the only setting,
+        but still allow for backwards compatibility for `store_failures`.
+        See https://github.com/dbt-labs/dbt-core/issues/6914 for more information.
+        """
+
+        # if `store_failures_as` is not set, it gets set by `store_failures`
+        # the settings below mimic existing behavior prior to `store_failures_as`
+        get_store_failures_as_map = {
+            True: "table",
+            False: "ephemeral",
+            None: None,
+        }
+
+        # if `store_failures_as` is set, it dictates what `store_failures` gets set to
+        # the settings below overrides whatever `store_failures` is set to by the user
+        get_store_failures_map = {
+            "ephemeral": False,
+            "table": True,
+            "view": True,
+        }
+
+        if self.store_failures_as is None:
+            self.store_failures_as = get_store_failures_as_map[self.store_failures]
+        else:
+            self.store_failures = get_store_failures_map.get(self.store_failures_as, True)
+
     @classmethod
     def same_contents(cls, unrendered: Dict[str, Any], other: Dict[str, Any]) -> bool:
         """This is like __eq__, except it explicitly checks certain fields."""
@@ -582,6 +654,7 @@ class TestConfig(NodeAndTestConfig):
             "warn_if",
             "error_if",
             "store_failures",
+            "store_failures_as",
         ]
 
         seen = set()
@@ -619,6 +692,8 @@ class SnapshotConfig(EmptySnapshotConfig):
     @classmethod
     def validate(cls, data):
         super().validate(data)
+        # Note: currently you can't just set these keys in schema.yml because this validation
+        # will fail when parsing the snapshot node.
         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', "
@@ -649,20 +724,36 @@ class SnapshotConfig(EmptySnapshotConfig):
         if data.get("materialized") and data.get("materialized") != "snapshot":
             raise ValidationError("A snapshot must have a materialized value of 'snapshot'")
 
+    # Called by "calculate_node_config_dict" in ContextConfigGenerator
     def finalize_and_validate(self):
         data = self.to_dict(omit_none=True)
         self.validate(data)
         return self.from_dict(data)
 
 
+@dataclass
+class UnitTestConfig(BaseConfig):
+    tags: Union[str, List[str]] = field(
+        default_factory=list_str,
+        metadata=metas(ShowBehavior.Hide, MergeBehavior.Append, CompareBehavior.Exclude),
+    )
+    meta: Dict[str, Any] = field(
+        default_factory=dict,
+        metadata=MergeBehavior.Update.meta(),
+    )
+
+
 RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = {
     NodeType.Metric: MetricConfig,
+    NodeType.SemanticModel: SemanticModelConfig,
+    NodeType.SavedQuery: SavedQueryConfig,
     NodeType.Exposure: ExposureConfig,
     NodeType.Source: SourceConfig,
     NodeType.Seed: SeedConfig,
     NodeType.Test: TestConfig,
     NodeType.Model: NodeConfig,
     NodeType.Snapshot: SnapshotConfig,
+    NodeType.Unit: UnitTestConfig,
 }