parsed update

* Consolidate date macros into dates.sql

* rename to timestamps.sql

* fix whitespace + add changie

* cleanup macros and add testing

* fix whitespace

* remove now macro

* fix functional test

* remove local config

* make snowflake backwards compat return utc

* move timestamps to adaptor base tests

* move backcompat macros to respective adapters

* change timestamp param to source_timestamp

* move timestamps.py to utils

* update changie.yaml

* make expected schema a fixture

* formatting

* add debug message to assert

* fix changie.yaml

* Update tests/adapter/dbt/tests/adapter/utils/test_timestamps.py

Co-authored-by: Doug Beatty <44704949+dbeatty10@users.noreply.github.com>

* Update plugins/postgres/dbt/include/postgres/macros/timestamps.sql

Co-authored-by: Doug Beatty <44704949+dbeatty10@users.noreply.github.com>

* Update .changie.yaml

* add backcompat utc

* remove current_timestamp_in_utc

* remove convert_timezone

* add _in_utc_backcompat

* fix macro_calls typo

* add expected sql validation to test_timestamps

* make expected_sql optional

* improve sql check string comparison test

* remove extraneous test file

* add timestamp casting back

* Update plugins/postgres/dbt/include/postgres/macros/adapters.sql

Co-authored-by: Doug Beatty <44704949+dbeatty10@users.noreply.github.com>

* add check_relation_has_expected_schema to comments

* fix whitespace

* remove default impl of current_timestamp

* manual changie log fix

Co-authored-by: Doug Beatty <44704949+dbeatty10@users.noreply.github.com>

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.3.0a1
+current_version = 1.4.0a1
 parse = (?P<major>\d+)
 	\.(?P<minor>\d+)
 	\.(?P<patch>\d+)

.changes/0.0.0.md

@@ -3,6 +3,7 @@
 For information on prior major and minor releases, see their changelogs:
 
 
+* [1.3](https://github.com/dbt-labs/dbt-core/blob/1.3.latest/CHANGELOG.md)
 * [1.2](https://github.com/dbt-labs/dbt-core/blob/1.2.latest/CHANGELOG.md)
 * [1.1](https://github.com/dbt-labs/dbt-core/blob/1.1.latest/CHANGELOG.md)
 * [1.0](https://github.com/dbt-labs/dbt-core/blob/1.0.latest/CHANGELOG.md)

.changes/unreleased/Features-20220715-035555.yaml

@@ -1,8 +0,0 @@
-kind: Features
-body: Add reusable function for retrying adapter connections. Utilize said function
-  to add retries for Postgres (and Redshift).
-time: 2022-07-15T03:55:55.270637265+02:00
-custom:
-  Author: tomasfarias
-  Issue: "5022"
-  PR: "5432"

.changes/unreleased/Features-20220914-095625.yaml

@@ -0,0 +1,7 @@
+kind: Features
+body: Migrate dbt-utils current_timestamp macros into core + adapters
+time: 2022-09-14T09:56:25.97818-07:00
+custom:
+  Author: colin-rogers-dbt
+  Issue: "5521"
+  PR: "5838"

.changes/unreleased/Fixes-20220715-231148.yaml

@@ -1,7 +0,0 @@
-kind: Fixes
-body: Rename try to strict for more intuitiveness
-time: 2022-07-15T23:11:48.327928+12:00
-custom:
-  Author: jeremyyeo
-  Issue: "5475"
-  PR: "5477"

.changes/unreleased/Fixes-20220916-104854.yaml

@@ -0,0 +1,7 @@
+kind: Fixes
+body: Account for disabled flags on models in schema files more completely
+time: 2022-09-16T10:48:54.162273-05:00
+custom:
+  Author: emmyoop
+  Issue: "3992"
+  PR: "5868"

.changie.yaml

@@ -7,14 +7,26 @@ versionExt: md
 versionFormat: '## dbt-core {{.Version}} - {{.Time.Format "January 02, 2006"}}'
 kindFormat: '### {{.Kind}}'
 changeFormat: '- {{.Body}} ([#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-core/issues/{{.Custom.Issue}}), [#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-core/pull/{{.Custom.PR}}))'
+
 kinds:
-- label: Breaking Changes
-- label: Features
-- label: Fixes
-- label: Docs
-- label: Under the Hood
-- label: Dependencies
-- label: Security
+  - label: Breaking Changes
+  - label: Features
+  - label: Fixes
+  - label: Docs
+    changeFormat: '- {{.Body}} ([dbt-docs/#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-docs/issues/{{.Custom.Issue}}), [dbt-docs/#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-docs/pull/{{.Custom.PR}}))'
+  - label: Under the Hood
+  - label: Dependencies
+    changeFormat: '- {{.Body}} ({{if ne .Custom.Issue ""}}[#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-core/issues/{{.Custom.Issue}}), {{end}}[#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-core/pull/{{.Custom.PR}}))'
+  - label: Security
+    changeFormat: '- {{.Body}} ({{if ne .Custom.Issue ""}}[#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-core/issues/{{.Custom.Issue}}), {{end}}[#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-core/pull/{{.Custom.PR}}))'
+
+newlines:
+  afterChangelogHeader: 1
+  afterKind: 1
+  afterChangelogVersion: 1
+  beforeKind: 1
+  endOfVersion: 1
+
 custom:
 - key: Author
   label: GitHub Username(s) (separated by a single space if multiple)
@@ -23,15 +35,16 @@ custom:
 - key: Issue
   label: GitHub Issue Number
   type: int
-  minLength: 4
+  minInt: 1
 - key: PR
   label: GitHub Pull Request Number
   type: int
-  minLength: 4
+  minInt: 1
+
 footerFormat: |
   {{- $contributorDict := dict }}
   {{- /* any names added to this list should be all lowercase for later matching purposes */}}
-  {{- $core_team := list "emmyoop" "nathaniel-may" "gshank" "leahwicz" "chenyulinx" "stu-k" "iknox-fa" "versusfacit" "mcknight-42" "jtcohen6" "dependabot" }}
+  {{- $core_team := list "peterallenwebb" "emmyoop" "nathaniel-may" "gshank" "leahwicz" "chenyulinx" "stu-k" "iknox-fa" "versusfacit" "mcknight-42" "jtcohen6" "dependabot[bot]" "snyk-bot" "colin-rogers-dbt" }}
   {{- range $change := .Changes }}
     {{- $authorList := splitList " " $change.Custom.Author }}
     {{- /* loop through all authors for a PR */}}
@@ -39,14 +52,20 @@ footerFormat: |
       {{- $authorLower := lower $author }}
       {{- /* we only want to include non-core team contributors */}}
       {{- if not (has $authorLower $core_team)}}
-        {{- $pr := $change.Custom.PR }}
+        {{- /* Docs kind link back to dbt-docs instead of dbt-core PRs */}}
+        {{- $prLink := $change.Kind }}
+        {{- if eq $change.Kind "Docs" }}
+          {{- $prLink = "[dbt-docs/#pr](https://github.com/dbt-labs/dbt-docs/pull/pr)" | replace "pr" $change.Custom.PR }}
+        {{- else }}
+          {{- $prLink = "[#pr](https://github.com/dbt-labs/dbt-core/pull/pr)" | replace "pr" $change.Custom.PR }}
+        {{- end }}
         {{- /* check if this contributor has other PRs associated with them already */}}
         {{- if hasKey $contributorDict $author }}
           {{- $prList := get $contributorDict $author }}
-          {{- $prList = append $prList $pr  }}
+          {{- $prList = append $prList $prLink  }}
           {{- $contributorDict := set $contributorDict $author $prList }}
         {{- else }}
-          {{- $prList := list $change.Custom.PR }}
+          {{- $prList := list $prLink }}
           {{- $contributorDict := set $contributorDict $author $prList }}
         {{- end }}
       {{- end}}
@@ -56,6 +75,6 @@ footerFormat: |
   {{- if $contributorDict}}
   ### Contributors
   {{- range $k,$v := $contributorDict }}
-  - [@{{$k}}](https://github.com/{{$k}}) ({{ range $index, $element := $v }}{{if $index}}, {{end}}[#{{$element}}](https://github.com/dbt-labs/dbt-core/pull/{{$element}}){{end}})
+  - [@{{$k}}](https://github.com/{{$k}}) ({{ range $index, $element := $v }}{{if $index}}, {{end}}{{$element}}{{end}})
   {{- end }}
   {{- end }}

.github/CODEOWNERS

@@ -16,25 +16,57 @@
 # Changes to GitHub configurations including Actions
 /.github/ @leahwicz
 
+### LANGUAGE
+
 # Language core modules
-/core/dbt/config/     @dbt-labs/core-language
-/core/dbt/context/    @dbt-labs/core-language
-/core/dbt/contracts/  @dbt-labs/core-language
-/core/dbt/deps/       @dbt-labs/core-language
-/core/dbt/parser/     @dbt-labs/core-language
+/core/dbt/config/               @dbt-labs/core-language
+/core/dbt/context/              @dbt-labs/core-language
+/core/dbt/contracts/            @dbt-labs/core-language
+/core/dbt/deps/                 @dbt-labs/core-language
+/core/dbt/events/               @dbt-labs/core-language  # structured logging
+/core/dbt/parser/               @dbt-labs/core-language
+
+# Language misc files
+/core/dbt/dataclass_schema.py   @dbt-labs/core-language
+/core/dbt/hooks.py              @dbt-labs/core-language
+/core/dbt/node_types.py         @dbt-labs/core-language
+/core/dbt/semver.py             @dbt-labs/core-language
+
+
+### EXECUTION
 
 # Execution core modules
-/core/dbt/events/     @dbt-labs/core-execution @dbt-labs/core-language # eventually remove language but they have knowledge here now
-/core/dbt/graph/      @dbt-labs/core-execution
-/core/dbt/task/       @dbt-labs/core-execution
+/core/dbt/graph/                @dbt-labs/core-execution
+/core/dbt/task/                 @dbt-labs/core-execution
 
-# Adapter interface, scaffold, Postgres plugin
-/core/dbt/adapters    @dbt-labs/core-adapters
-/core/scripts/create_adapter_plugin.py    @dbt-labs/core-adapters
-/plugins/             @dbt-labs/core-adapters
+# Execution misc files
+/core/dbt/compilation.py        @dbt-labs/core-execution
+/core/dbt/flags.py              @dbt-labs/core-execution
+/core/dbt/lib.py                @dbt-labs/core-execution
+/core/dbt/main.py               @dbt-labs/core-execution
+/core/dbt/profiler.py           @dbt-labs/core-execution
+/core/dbt/selected_resources.py @dbt-labs/core-execution
+/core/dbt/tracking.py           @dbt-labs/core-execution
+/core/dbt/version.py            @dbt-labs/core-execution
 
-# Global project: default macros, including generic tests + materializations
-/core/dbt/include/global_project    @dbt-labs/core-execution @dbt-labs/core-adapters
+
+### ADAPTERS
+
+# Adapter interface ("base" + "sql" adapter defaults, cache)
+/core/dbt/adapters              @dbt-labs/core-adapters
+
+# Global project (default macros + materializations), starter project
+/core/dbt/include               @dbt-labs/core-adapters
+
+# Postgres plugin
+/plugins/                       @dbt-labs/core-adapters
+
+# Functional tests for adapter plugins
+/tests/adapter                  @dbt-labs/core-adapters
+
+### TESTS
+
+# Overlapping ownership for vast majority of unit + functional tests
 
 # Perf regression testing framework
 # This excludes the test project files itself since those aren't specific

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -9,23 +9,33 @@ body:
         Thanks for taking the time to fill out this bug report!
   - type: checkboxes
     attributes:
-      label: Is there an existing issue for this?
-      description: Please search to see if an issue already exists for the bug you encountered.
+      label: Is this a new bug in dbt-core?
+      description: >
+        In other words, is this an error, flaw, failure or fault in our software?
+
+        If this is a bug that broke existing functionality that used to work, please open a regression issue.
+        If this is a bug in an adapter plugin, please open an issue in the adapter's repository.
+        If this is a bug experienced while using dbt Cloud, please report to [support](mailto:support@getdbt.com).
+        If this is a request for help or troubleshooting code in your own dbt project, please join our [dbt Community Slack](https://www.getdbt.com/community/join-the-community/) or open a [Discussion question](https://github.com/dbt-labs/docs.getdbt.com/discussions).
+
+        Please search to see if an issue already exists for the bug you encountered.
       options:
-        - label: I have searched the existing issues
+        - label: I believe this is a new bug in dbt-core
+          required: true
+        - label: I have searched the existing issues, and I could not find an existing issue for this bug
           required: true
   - type: textarea
     attributes:
       label: Current Behavior
       description: A concise description of what you're experiencing.
     validations:
-      required: false
+      required: true
   - type: textarea
     attributes:
       label: Expected Behavior
       description: A concise description of what you expected to happen.
     validations:
-      required: false
+      required: true
   - type: textarea
     attributes:
       label: Steps To Reproduce
@@ -36,7 +46,7 @@ body:
         3. Run '...'
         4. See error...
     validations:
-      required: false
+      required: true
   - type: textarea
     id: logs
     attributes:
@@ -52,8 +62,8 @@ body:
       description: |
         examples:
           - **OS**: Ubuntu 20.04
-          - **Python**: 3.7.2 (`python --version`)
-          - **dbt**: 0.21.0 (`dbt --version`)
+          - **Python**: 3.9.12 (`python3 --version`)
+          - **dbt-core**: 1.1.1 (`dbt --version`)
       value: |
         - OS:
         - Python:
@@ -64,13 +74,15 @@ body:
   - type: dropdown
     id: database
     attributes:
-      label: What database are you using dbt with?
+      label: Which database adapter are you using with dbt?
+      description: If the bug is specific to the database or adapter, please open the issue in that adapter's repository instead
       multiple: true
       options:
         - postgres
         - redshift
         - snowflake
         - bigquery
+        - spark
         - other (mention it in "Additional Context")
     validations:
       required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -1,4 +1,14 @@
+blank_issues_enabled: false
 contact_links:
+  - name: Ask the community for help
+    url: https://github.com/dbt-labs/docs.getdbt.com/discussions
+    about: Need help troubleshooting? Check out our guide on how to ask
+  - name: Contact dbt Cloud support
+    url: mailto:support@getdbt.com
+    about: Are you using dbt Cloud? Contact our support team for help!
+  - name: Participate in Discussions
+    url: https://github.com/dbt-labs/dbt-core/discussions
+    about: Do you have a Big Idea for dbt? Read open discussions, or start a new one
   - name: Create an issue for dbt-redshift
     url: https://github.com/dbt-labs/dbt-redshift/issues/new/choose
     about: Report a bug or request a feature for dbt-redshift
@@ -8,9 +18,6 @@ contact_links:
   - name: Create an issue for dbt-snowflake
     url: https://github.com/dbt-labs/dbt-snowflake/issues/new/choose
     about: Report a bug or request a feature for dbt-snowflake
-  - name: Ask a question or get support
-    url: https://docs.getdbt.com/docs/guides/getting-help
-    about: Ask a question or request support
-  - name: Questions on Stack Overflow
-    url: https://stackoverflow.com/questions/tagged/dbt
-    about: Look at questions/answers at Stack Overflow
+  - name: Create an issue for dbt-spark
+    url: https://github.com/dbt-labs/dbt-spark/issues/new/choose
+    about: Report a bug or request a feature for dbt-spark

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -1,5 +1,5 @@
 name: ✨ Feature
-description: Suggest an idea for dbt
+description: Propose a straightforward extension of dbt functionality
 title: "[Feature] <title>"
 labels: ["enhancement", "triage"]
 body:
@@ -9,18 +9,24 @@ body:
         Thanks for taking the time to fill out this feature request!
   - type: checkboxes
     attributes:
-      label: Is there an existing feature request for this?
-      description: Please search to see if an issue already exists for the feature you would like.
-      options:
-        - label: I have searched the existing issues
-          required: true
-      label: Is this your first time opening an issue?
+      label: Is this your first time submitting a feature request?
+      description: >
+        We want to make sure that features are distinct and discoverable,
+        so that other members of the community can find them and offer their thoughts.
+
+        Issues are the right place to request straightforward extensions of existing dbt functionality.
+        For "big ideas" about future capabilities of dbt, we ask that you open a
+        [discussion](https://github.com/dbt-labs/dbt-core/discussions) in the "Ideas" category instead.
       options:
         - label: I have read the [expectations for open source contributors](https://docs.getdbt.com/docs/contributing/oss-expectations)
           required: true
+        - label: I have searched the existing issues, and I could not find an existing issue for this feature
+          required: true
+        - label: I am requesting a straightforward extension of existing dbt functionality, rather than a Big Idea better suited to a discussion
+          required: true
   - type: textarea
     attributes:
-      label: Describe the Feature
+      label: Describe the feature
       description: A clear and concise description of what you want to happen.
     validations:
       required: true

.github/ISSUE_TEMPLATE/regression-report.yml

@@ -0,0 +1,93 @@
+name: ☣️ Regression
+description: Report a regression you've observed in a newer version of dbt
+title: "[Regression] <title>"
+labels: ["bug", "regression", "triage"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this regression report!
+  - type: checkboxes
+    attributes:
+      label: Is this a regression in a recent version of dbt-core?
+      description: >
+        A regression is when documented functionality works as expected in an older version of dbt-core,
+        and no longer works after upgrading to a newer version of dbt-core
+      options:
+        - label: I believe this is a regression in dbt-core functionality
+          required: true
+        - label: I have searched the existing issues, and I could not find an existing issue for this regression
+          required: true
+  - type: textarea
+    attributes:
+      label: Current Behavior
+      description: A concise description of what you're experiencing.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Expected/Previous Behavior
+      description: A concise description of what you expected to happen.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Steps To Reproduce
+      description: Steps to reproduce the behavior.
+      placeholder: |
+        1. In this environment...
+        2. With this config...
+        3. Run '...'
+        4. See error...
+    validations:
+      required: true
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: |
+        If applicable, log output to help explain your problem.
+      render: shell
+    validations:
+      required: false
+  - type: textarea
+    attributes:
+      label: Environment
+      description: |
+        examples:
+          - **OS**: Ubuntu 20.04
+          - **Python**: 3.9.12 (`python3 --version`)
+          - **dbt-core (working version)**: 1.1.1 (`dbt --version`)
+          - **dbt-core (regression version)**: 1.2.0 (`dbt --version`)
+      value: |
+        - OS:
+        - Python:
+        - dbt (working version):
+        - dbt (regression version):
+      render: markdown
+    validations:
+      required: true
+  - type: dropdown
+    id: database
+    attributes:
+      label: Which database adapter are you using with dbt?
+      description: If the regression is specific to the database or adapter, please open the issue in that adapter's repository instead
+      multiple: true
+      options:
+        - postgres
+        - redshift
+        - snowflake
+        - bigquery
+        - spark
+        - other (mention it in "Additional Context")
+    validations:
+      required: false
+  - type: textarea
+    attributes:
+      label: Additional Context
+      description: |
+        Links? References? Anything that will give us more context about the issue you are encountering!
+
+        Tip: You can attach images or log files by clicking this area to highlight it and then dragging files in.
+    validations:
+      required: false

.github/_README.md

@@ -0,0 +1,216 @@
+<!-- GitHub will publish this readme on the main repo page if the name is `README.md` so we've added the leading underscore to prevent this -->
+<!-- Do not rename this file `README.md` -->
+<!-- See https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-readmes -->
+
+## What are GitHub Actions?
+
+GitHub Actions are used for many different purposes.  We use them to run tests in CI, validate PRs are in an expected state, and automate processes.
+
+- [Overview of GitHub Actions](https://docs.github.com/en/actions/learn-github-actions/understanding-github-actions)
+- [What's a workflow?](https://docs.github.com/en/actions/using-workflows/about-workflows)
+- [GitHub Actions guides](https://docs.github.com/en/actions/guides)
+
+___
+
+## Where do actions and workflows live
+
+We try to maintain actions that are shared across repositories in a single place so that necesary changes can be made in a single place.
+
+[dbt-labs/actions](https://github.com/dbt-labs/actions/) is the central repository of actions and workflows we use across repositories.
+
+GitHub Actions also live locally within a repository.  The workflows can be found at `.github/workflows` from the root of the repository.  These should be specific to that code base.
+
+Note: We are actively moving actions into the central Action repository so there is currently some duplication across repositories.
+
+___
+
+## Basics of Using Actions
+
+### Viewing Output
+
+- View the detailed action output for your PR in the **Checks** tab of the PR.  This only shows the most recent run.  You can also view high level **Checks** output at the bottom on the PR.
+
+- View _all_ action output for a repository from the [**Actions**](https://github.com/dbt-labs/dbt-core/actions) tab.  Workflow results last 1 year.  Artifacts last 90 days, unless specified otherwise in individual workflows.
+
+  This view often shows what seem like duplicates of the same workflow.  This occurs when files are renamed but the workflow name has not changed.  These are in fact _not_ duplicates.
+
+  You can see the branch the workflow runs from in this view.  It is listed in the table between the workflow name and the time/duration of the run.  When blank, the workflow is running in the context of the  `main` branch.
+
+### How to view what workflow file is being referenced from a run
+
+- When viewing the output of a specific workflow run, click the 3 dots at the top right of the display.  There will be an option to `View workflow file`.
+
+### How to manually run a workflow
+
+- If a workflow has the `on: workflow_dispatch` trigger, it can be manually triggered
+- From the [**Actions**](https://github.com/dbt-labs/dbt-core/actions) tab, find the workflow you want to run, select it and fill in any inputs requied.  That's it!
+
+### How to re-run jobs
+
+- Some actions cannot be rerun in the GitHub UI.  Namely the snyk checks and the cla check.  Snyk checks are rerun by closing and reopening the PR.  You can retrigger the cla check by commenting on the PR with `@cla-bot check`
+
+___
+
+## General Standards
+
+### Permissions
+- By default, workflows have read permissions in the repository for the contents scope only when no permissions are explicitly set.
+- It is best practice to always define the permissions explicitly.  This will allow actions to continue to work when the default permissions on the repository are changed.  It also allows explicit grants of the least permissions possible.
+- There are a lot of permissions available.  [Read up on them](https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs) if you're unsure what to use.
+
+```yaml
+permissions:
+  contents: read
+  pull-requests: write
+```
+    
+### Secrets
+- When to use a [Personal Access Token (PAT)](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token) vs the [GITHUB_TOKEN](https://docs.github.com/en/actions/security-guides/automatic-token-authentication) generated for the action?
+
+    The `GITHUB_TOKEN` is used by default.  In most cases it is sufficient for what you need.
+    
+    If you expect the workflow to result in a commit to that should retrigger workflows, you will need to use a Personal Access Token for the bot to commit the file. When using the GITHUB_TOKEN, the resulting commit will not trigger another GitHub Actions Workflow run. This is due to limitations set by GitHub. See [the docs](https://docs.github.com/en/actions/security-guides/automatic-token-authentication#using-the-github_token-in-a-workflow) for a more detailed explanation.
+
+    For example, we must use a PAT in our workflow to commit a new changelog yaml file for bot PRs.  Once the file has been committed to the branch, it should retrigger the check to validate that a changelog exists on the PR.  Otherwise, it would stay in a failed state since the check would never retrigger.
+
+### Triggers
+You can configure your workflows to run when specific activity on GitHub happens, at a scheduled time, or when an event outside of GitHub occurs.  Read more details in the [GitHub docs](https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows).
+
+These triggers are under the `on` key of the workflow and more than one can be listed.
+
+```yaml
+on:
+  push:
+    branches:
+      - "main"
+      - "*.latest"
+      - "releases/*"
+  pull_request:
+    # catch when the PR is opened with the label or when the label is added
+    types: [opened, labeled]
+  workflow_dispatch:
+```
+
+Some triggers of note that we use:
+
+- `push` - Runs your workflow when you push a commit or tag.
+- `pull_request` - Runs your workflow when activity on a pull request in the workflow's repository occurs.  Takes in a list of activity types (opened, labeled, etc) if appropriate.
+- `pull_request_target` - Same as `pull_request` but runs in the context of the PR target branch.
+- `workflow_call` - used with reusable workflows.  Triggered by another workflow calling it.
+- `workflow_dispatch` - Gives the ability to manually trigger a workflow from the GitHub API, GitHub CLI, or GitHub browser interface.
+
+
+### Basic Formatting
+- Add a description of what your workflow does at the top in this format
+
+  ```
+  # **what?**
+  # Describe what the action does.  
+
+  # **why?**
+  # Why does this action exist?
+
+  # **when?**
+  # How/when will it be triggered?
+  ```
+
+- Leave blank lines between steps and jobs
+
+  ```yaml
+  jobs:
+    dependency_changelog:
+      runs-on: ubuntu-latest
+
+      steps:
+      - name: Get File Name Timestamp
+        id: filename_time
+        uses: nanzm/get-time-action@v1.1
+        with:
+          format: 'YYYYMMDD-HHmmss'
+
+      - name: Get File Content Timestamp
+        id: file_content_time
+        uses: nanzm/get-time-action@v1.1
+        with:
+          format: 'YYYY-MM-DDTHH:mm:ss.000000-05:00'
+
+      - name: Generate Filepath
+        id: fp
+        run: |
+          FILEPATH=.changes/unreleased/Dependencies-${{ steps.filename_time.outputs.time }}.yaml
+          echo "::set-output name=FILEPATH::$FILEPATH"
+  ```
+
+- Print out all variables you will reference as the first step of a job.  This allows for easier debugging.  The first job should log all inputs.  Subsequent jobs should reference outputs of other jobs, if present.
+
+  When possible, generate variables at the top of your workflow in a single place to reference later.  This is not always strictly possible since you may generate a value to be used later mid-workflow.
+
+  Be sure to use quotes around these logs so special characters are not interpreted.
+
+  ```yaml
+  job1:
+    - name: "[DEBUG] Print Variables"
+      run: |
+        echo "all variables defined as inputs"
+        echo "The last commit sha in the release: ${{ inputs.sha }}"
+        echo "The release version number:         ${{ inputs.version_number }}"
+        echo "The changelog_path:                 ${{ inputs.changelog_path }}"
+        echo "The build_script_path:              ${{ inputs.build_script_path }}"
+        echo "The s3_bucket_name:                 ${{ inputs.s3_bucket_name }}"
+        echo "The package_test_command:           ${{ inputs.package_test_command }}"
+      
+    # collect all the variables that need to be used in subsequent jobs
+    - name: Set Variables
+      id: variables
+      run: |
+        echo "::set-output name=important_path::'performance/runner/Cargo.toml'"
+        echo "::set-output name=release_id::${{github.event.inputs.release_id}}"
+        echo "::set-output name=open_prs::${{github.event.inputs.open_prs}}"
+
+  job2:
+    needs: [job1]
+      - name: "[DEBUG] Print Variables"
+      run: |
+        echo "all variables defined in job1 > Set Variables > outputs"
+        echo "important_path: ${{ needs.job1.outputs.important_path }}"
+        echo "release_id:     ${{ needs.job1.outputs.release_id }}"
+        echo "open_prs:       ${{ needs.job1.outputs.open_prs }}"
+  ```
+
+- When it's not obvious what something does, add a comment!
+
+___
+
+## Tips
+
+### Context
+- The [GitHub CLI](https://cli.github.com/) is available in the default runners
+- Actions run in your context.  ie, using an action from the marketplace that uses the GITHUB_TOKEN uses the GITHUB_TOKEN generated by your workflow run.
+
+### Actions from the Marketplace
+- Don’t use external actions for things that can easily be accomplished manually.
+- Always read through what an external action does before using it!  Often an action in the GitHub Actions Marketplace can be replaced with a few lines in bash.  This is much more maintainable (and won’t change under us) and clear as to what’s actually happening.  It also prevents any
+- Pin actions _we don't control_ to tags. 
+
+### Connecting to AWS
+- Authenticate with the aws managed workflow
+
+  ```yaml
+  - name: Configure AWS credentials from Test account
+    uses: aws-actions/configure-aws-credentials@v1
+    with:
+      aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+      aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+      aws-region: us-east-1
+  ```
+
+- Then access with the aws command that comes installed on the action runner machines
+
+  ```yaml
+  - name: Copy Artifacts from S3 via CLI
+    run: aws s3 cp ${{ env.s3_bucket }} . --recursive 
+  ```
+
+### Testing
+
+- Depending on what your action does, you may be able to use [`act`](https://github.com/nektos/act) to test the action locally.  Some features of GitHub Actions do not work with `act`, among those are reusable workflows.  If you can't use `act`, you'll have to push your changes up before being able to test.  This can be slow.

.github/pull_request_template.md

@@ -20,4 +20,4 @@ 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
 - [ ] I have [opened an issue to add/update docs](https://github.com/dbt-labs/docs.getdbt.com/issues/new/choose), or docs changes are not required/relevant for this PR
-- [ ] I have run `changie new` to [create a changelog entry](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#Adding-CHANGELOG-Entry)
+- [ ] I have run `changie new` to [create a changelog entry](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#adding-a-changelog-entry)

.github/workflows/bot-changelog.yml

@@ -0,0 +1,61 @@
+# **what?**
+# When bots create a PR, this action will add a corresponding changie yaml file to that
+# PR when a specific label is added.
+#
+# The file is created off a template:
+#
+# kind: <per action matrix>
+# body: <PR title>
+# time: <current timestamp>
+# custom:
+#   Author: <PR User Login (generally the bot)>
+#   Issue: 4904
+#   PR: <PR number>
+#
+# **why?**
+# Automate changelog generation for more visability with automated bot PRs.
+#
+# **when?**
+# Once a PR is created, label should be added to PR before or after creation. You can also
+#  manually trigger this by adding the appropriate label at any time.
+#
+# **how to add another bot?**
+# Add the label and changie kind to the include matrix.  That's it!
+#
+
+name: Bot Changelog
+
+on:
+  pull_request:
+    # catch when the PR is opened with the label or when the label is added
+    types: [labeled]
+
+permissions:
+  contents: write
+  pull-requests: read
+
+jobs:
+  generate_changelog:
+    strategy:
+      matrix:
+        include:
+          - label: "dependencies"
+            changie_kind: "Dependency"
+          - label: "snyk"
+            changie_kind: "Security"
+    runs-on: ubuntu-latest
+
+    steps:
+
+    - name: Create and commit changelog on bot PR
+      if: ${{ contains(github.event.pull_request.labels.*.name, matrix.label) }}
+      id: bot_changelog
+      uses: emmyoop/changie_bot@v1.0.1
+      with:
+        GITHUB_TOKEN: ${{ secrets.FISHTOWN_BOT_PAT }}
+        commit_author_name: "Github Build Bot"
+        commit_author_email: "<buildbot@fishtownanalytics.com>"
+        commit_message: "Add automated changelog yaml from template for bot PR"
+        changie_kind: ${{ matrix.changie_kind }}
+        label: ${{ matrix.label }}
+        custom_changelog_string: "custom:\n  Author: ${{ github.event.pull_request.user.login }}\n  Issue: 4904\n  PR: ${{ github.event.pull_request.number }}"

.github/workflows/changelog-check.yml

@@ -1,78 +0,0 @@
-# **what?**
-# 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.
-
-# **why?**
-# Ensure code change gets reflected in the CHANGELOG.
-
-# **when?**
-# This will run for all PRs going into main and *.latest.  It will
-# run when they are opened, reopened, when any label is added or removed
-# and when new code is pushed to the branch.  The action will then get
-# skipped if the 'Skip Changelog' label is present is any of the labels.
-
-name: Check Changelog Entry
-
-on:
-  pull_request:
-    types: [opened, reopened, labeled, unlabeled, synchronize]
-  workflow_dispatch:
-
-defaults:
-  run:
-    shell: bash
-
-permissions:
-  contents: read
-  pull-requests: write
-
-env:
-  changelog_comment: 'Thank you for your pull request! We could not find a changelog entry for this change. For details on how to document a change, see [the contributing guide](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#adding-changelog-entry).'
-
-jobs:
-  changelog:
-    name: changelog
-    if: "!contains(github.event.pull_request.labels.*.name, 'Skip Changelog')"
-
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Check if changelog file was added
-        # https://github.com/marketplace/actions/paths-changes-filter
-        # For each filter, it sets output variable named by the filter to the text:
-        #  'true' - if any of changed files matches any of filter rules
-        #  'false' - if none of changed files matches any of filter rules
-        # also, returns:
-        #  `changes` - JSON array with names of all filters matching any of the changed files
-        uses: dorny/paths-filter@v2
-        id: filter
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          filters: |
-            changelog:
-              - added: '.changes/unreleased/**.yaml'
-      - name: Check if comment already exists
-        uses: peter-evans/find-comment@v1
-        id: changelog_comment
-        with:
-          issue-number: ${{ github.event.pull_request.number }}
-          comment-author: 'github-actions[bot]'
-          body-includes: ${{ env.changelog_comment }}
-      - name: Create PR comment if changelog entry is missing, required, and does not exist
-        if: |
-          steps.filter.outputs.changelog == 'false' &&
-          steps.changelog_comment.outputs.comment-body == ''
-        uses: peter-evans/create-or-update-comment@v1
-        with:
-          issue-number: ${{ github.event.pull_request.number }}
-          body: ${{ env.changelog_comment }}
-      - name: Fail job if changelog entry is missing and required
-        if: steps.filter.outputs.changelog == 'false'
-        uses: actions/github-script@v6
-        with:
-          script: core.setFailed('Changelog entry required to merge.')

.github/workflows/changelog-existence.yml

@@ -0,0 +1,40 @@
+# **what?**
+# 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.
+
+# **why?**
+# Ensure code change gets reflected in the CHANGELOG.
+
+# **when?**
+# This will run for all PRs going into main and *.latest.  It will
+# run when they are opened, reopened, when any label is added or removed
+# and when new code is pushed to the branch.  The action will then get
+# skipped if the 'Skip Changelog' label is present is any of the labels.
+
+name: Check Changelog Entry
+
+on:
+  pull_request:
+    types: [opened, reopened, labeled, unlabeled, synchronize]
+  workflow_dispatch:
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  changelog:
+    uses: dbt-labs/actions/.github/workflows/changelog-existence.yml@main
+    with:
+      changelog_comment: 'Thank you for your pull request! We could not find a changelog entry for this change. For details on how to document a change, see [the contributing guide](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#adding-changelog-entry).'
+      skip_label: 'Skip Changelog'
+    secrets: inherit

.github/workflows/dependency-changelog.yml

@@ -1,114 +0,0 @@
-# **what?**
-# When dependabot create a PR, it always adds the `dependencies` label. This
-# action will add a corresponding changie yaml file to that PR when that label is added.
-# The file is created off a template:
-#
-# kind: Dependencies
-# body: <PR title>
-# time: <current timestamp>
-# custom:
-#   Author: dependabot
-#   Issue: 4904
-#   PR: <PR number>
-#
-# **why?**
-# Automate changelog generation for more visability with automated dependency updates via dependabot.
-
-# **when?**
-# Once a PR is created and it has been correctly labeled with `dependencies`.  The intended use
-# is for the PRs created by dependabot.  You can also manually trigger this by adding the
-# `dependencies` label at any time.
-
-name: Dependency Changelog
-
-on:
-  pull_request:
-    # catch when the PR is opened with the label or when the label is added
-    types: [opened, labeled]
-
-permissions:
-  contents: write
-  pull-requests: read
-
-jobs:
-  dependency_changelog:
-    if: "contains(github.event.pull_request.labels.*.name, 'dependencies')"
-    runs-on: ubuntu-latest
-
-    steps:
-    # timestamp changes the order the changelog entries are listed in the final Changelog.md file.  Precision is not
-    # important here.
-    # The timestamp on the filename and the timestamp in the contents of the file have different expected formats.
-    - name: Get File Name Timestamp
-      id: filename_time
-      uses: nanzm/get-time-action@v1.1
-      with:
-        format: 'YYYYMMDD-HHmmss'
-
-    - name: Get File Content Timestamp
-      id: file_content_time
-      uses: nanzm/get-time-action@v1.1
-      with:
-        format: 'YYYY-MM-DDTHH:mm:ss.000000-05:00'
-
-    # changie expects files to be named in a specific pattern.
-    - name: Generate Filepath
-      id: fp
-      run: |
-        FILEPATH=.changes/unreleased/Dependencies-${{ steps.filename_time.outputs.time }}.yaml
-        echo "::set-output name=FILEPATH::$FILEPATH"
-
-    - name: Check if changelog file exists already
-      # if there's already a changelog entry, don't add another one!
-      # https://github.com/marketplace/actions/paths-changes-filter
-      # For each filter, it sets output variable named by the filter to the text:
-      #  'true' - if any of changed files matches any of filter rules
-      #  'false' - if none of changed files matches any of filter rules
-      # also, returns:
-      #  `changes` - JSON array with names of all filters matching any of the changed files
-      uses: dorny/paths-filter@v2
-      id: changelog_check
-      with:
-        token: ${{ secrets.GITHUB_TOKEN }}
-        filters: |
-          exists:
-            - added: '.changes/unreleased/**.yaml'
-
-    - name: Checkout Branch
-      if: steps.changelog_check.outputs.exists == 'false'
-      uses: actions/checkout@v2
-      with:
-        # specifying the ref avoids checking out the repository in a detached state
-        ref: ${{ github.event.pull_request.head.ref }}
-        # If this is not set to false, Git push is performed with github.token and not the token
-        # configured using the env: GITHUB_TOKEN in commit step
-        persist-credentials: false
-
-    - name: Create file from template
-      if: steps.changelog_check.outputs.exists == 'false'
-      run: |
-        echo kind: Dependencies > "${{ steps.fp.outputs.FILEPATH }}"
-        echo 'body: "${{ github.event.pull_request.title }}"' >> "${{ steps.fp.outputs.FILEPATH }}"
-        echo time: "${{ steps.file_content_time.outputs.time }}" >> "${{ steps.fp.outputs.FILEPATH }}"
-        echo custom: >> "${{ steps.fp.outputs.FILEPATH }}"
-        echo '  Author: ${{ github.event.pull_request.user.login }}' >> "${{ steps.fp.outputs.FILEPATH }}"
-        echo '  Issue: "4904"' >> "${{ steps.fp.outputs.FILEPATH }}"  # github.event.pull_request.issue for auto id?
-        echo '  PR: "${{ github.event.pull_request.number }}"' >> "${{ steps.fp.outputs.FILEPATH }}"
-
-    - name: Commit Changelog File
-      if: steps.changelog_check.outputs.exists == 'false'
-      uses: gr2m/create-or-update-pull-request-action@v1
-      env:
-        # When using the GITHUB_TOKEN, the resulting commit will not trigger another GitHub Actions
-        # Workflow run. This is due to limitations set by GitHub.
-        # See: https://docs.github.com/en/actions/security-guides/automatic-token-authentication#using-the-github_token-in-a-workflow
-        # When you use the repository's GITHUB_TOKEN to perform tasks on behalf of the GitHub Actions
-        # app, events triggered by the GITHUB_TOKEN will not create a new workflow run. This prevents
-        # you from accidentally creating recursive workflow runs. To get around this, use a Personal
-        # Access Token to commit changes.
-        GITHUB_TOKEN: ${{ secrets.FISHTOWN_BOT_PAT }}
-      with:
-        branch: ${{ github.event.pull_request.head.ref }}
-        # author expected in the format "Lorem J. Ipsum <lorem@example.com>"
-        author: "Github Build Bot <buildbot@fishtownanalytics.com>"
-        commit-message: "Add automated changelog yaml from template"

.github/workflows/jira-transition.yml

@@ -15,6 +15,9 @@ on:
   issues:
     types: [closed, deleted, reopened]
 
+# no special access is needed
+permissions: read-all
+
 jobs:
   call-label-action:
     uses: dbt-labs/jira-actions/.github/workflows/jira-transition.yml@main

.github/workflows/release-branch-tests.yml

@@ -39,7 +39,7 @@ jobs:
       max-parallel: 1
       fail-fast: false
       matrix:
-        branch: [1.0.latest, 1.1.latest, main]
+        branch: [1.0.latest, 1.1.latest, 1.2.latest, main]
 
     steps:
     - name: Call CI workflow for ${{ matrix.branch }} branch

.github/workflows/release.yml

@@ -20,6 +20,9 @@ on:
        description: 'The release version number (i.e. 1.0.0b1)'
        required: true
 
+permissions:
+  contents: write # this is the permission that allows creating a new release
+
 defaults:
   run:
     shell: bash

.github/workflows/schema-check.yml

@@ -21,6 +21,9 @@ on:
       - "*.latest"
       - "releases/*"
 
+# no special access is needed
+permissions: read-all
+
 env:
   LATEST_SCHEMA_PATH: ${{ github.workspace }}/new_schemas
   SCHEMA_DIFF_ARTIFACT: ${{ github.workspace }}//schema_schanges.txt

.github/workflows/stale.yml

@@ -3,6 +3,10 @@ on:
   schedule:
     - cron: "30 1 * * *"
 
+permissions:
+  issues: write
+  pull-requests: write
+
 jobs:
   stale:
     runs-on: ubuntu-latest

.github/workflows/version-bump.yml

@@ -1,18 +1,15 @@
 # **what?**
-# This workflow will take a version number and a dry run flag. With that
+# This workflow will take the new version number to bump to. With that
 # it will run versionbump to update the version number everywhere in the
-# code base and then generate an update Docker requirements file. If this
-# is a dry run, a draft PR will open with the changes. If this isn't a dry
-# run, the changes will be committed to the branch this is run on.
+# code base and then run changie to create the corresponding changelog.
+# A PR will be created with the changes that can be reviewed before committing.
 
 # **why?**
 # This is to aid in releasing dbt and making sure we have updated
-# the versions and Docker requirements in all places.
+# the version in all places and generated the changelog.
 
 # **when?**
-# This is triggered either manually OR
-# from the repository_dispatch event "version-bump" which is sent from
-# the dbt-release repo Action
+# This is triggered manually
 
 name: Version Bump
 
@@ -20,35 +17,25 @@ on:
   workflow_dispatch:
     inputs:
       version_number:
-       description: 'The version number to bump to'
+       description: 'The version number to bump to (ex. 1.2.0, 1.3.0b1)'
        required: true
-      is_dry_run:
-       description: 'Creates a draft PR to allow testing instead of committing to a branch'
-       required: true
-       default: 'true'
-  repository_dispatch:
-    types: [version-bump]
+
+permissions:
+  contents: write
+  pull-requests: write
 
 jobs:
   bump:
     runs-on: ubuntu-latest
     steps:
+      - name: "[DEBUG] Print Variables"
+        run: |
+          echo "all variables defined as inputs"
+          echo The version_number: ${{ github.event.inputs.version_number }}
+
       - name: Check out the repository
         uses: actions/checkout@v2
 
-      - name: Set version and dry run values
-        id: variables
-        env:
-          VERSION_NUMBER: "${{ github.event.client_payload.version_number == '' && github.event.inputs.version_number || github.event.client_payload.version_number }}"
-          IS_DRY_RUN: "${{ github.event.client_payload.is_dry_run == '' && github.event.inputs.is_dry_run || github.event.client_payload.is_dry_run }}"
-        run: |
-          echo Repository dispatch event version: ${{ github.event.client_payload.version_number }}
-          echo Repository dispatch event dry run: ${{ github.event.client_payload.is_dry_run }}
-          echo Workflow dispatch event version: ${{ github.event.inputs.version_number }}
-          echo Workflow dispatch event dry run: ${{ github.event.inputs.is_dry_run }}
-          echo ::set-output name=VERSION_NUMBER::$VERSION_NUMBER
-          echo ::set-output name=IS_DRY_RUN::$IS_DRY_RUN
-
       - uses: actions/setup-python@v2
         with:
           python-version: "3.8"
@@ -59,53 +46,80 @@ jobs:
           source env/bin/activate
           pip install --upgrade pip
 
-      - name: Create PR branch
-        if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
+      - name: Add Homebrew to PATH
         run: |
-          git checkout -b bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_$GITHUB_RUN_ID
-          git push origin bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_$GITHUB_RUN_ID
-          git branch --set-upstream-to=origin/bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_$GITHUB_RUN_ID bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_$GITHUB_RUN_ID
+          echo "/home/linuxbrew/.linuxbrew/bin:/home/linuxbrew/.linuxbrew/sbin" >> $GITHUB_PATH
 
-      # - name: Generate Docker requirements
-      #  run: |
-      #    source env/bin/activate
-      #    pip install -r requirements.txt
-      #    pip freeze -l > docker/requirements/requirements.txt
-      #    git status
+      - name: Install Homebrew packages
+        run: |
+          brew install pre-commit
+          brew tap miniscruff/changie https://github.com/miniscruff/changie
+          brew install changie
+
+      - name: Audit Version and Parse Into Parts
+        id: semver
+        uses: dbt-labs/actions/parse-semver@v1
+        with:
+          version: ${{ github.event.inputs.version_number }}
+
+      - name: Set branch value
+        id: variables
+        run: |
+          echo "::set-output name=BRANCH_NAME::prep-release/${{ github.event.inputs.version_number }}_$GITHUB_RUN_ID"
+
+      - name: Create PR branch
+        run: |
+          git checkout -b ${{ steps.variables.outputs.BRANCH_NAME }}
+          git push origin ${{ steps.variables.outputs.BRANCH_NAME }}
+          git branch --set-upstream-to=origin/${{ steps.variables.outputs.BRANCH_NAME }} ${{ steps.variables.outputs.BRANCH_NAME }}
 
       - name: Bump version
         run: |
           source env/bin/activate
           pip install -r dev-requirements.txt
-          env/bin/bumpversion --allow-dirty --new-version ${{steps.variables.outputs.VERSION_NUMBER}} major
+          env/bin/bumpversion --allow-dirty --new-version ${{ github.event.inputs.version_number }} major
           git status
 
-      - name: Commit version bump directly
-        uses: EndBug/add-and-commit@v7
-        if: ${{ steps.variables.outputs.IS_DRY_RUN == 'false' }}
-        with:
-          author_name: 'Github Build Bot'
-          author_email: 'buildbot@fishtownanalytics.com'
-          message: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
+      - name: Run changie
+        run: |
+          if [[ ${{ steps.semver.outputs.is-pre-release }} -eq 1 ]]
+          then
+            changie batch ${{ steps.semver.outputs.base-version }}  --move-dir '${{ steps.semver.outputs.base-version }}' --prerelease '${{ steps.semver.outputs.pre-release }}'
+          else
+            changie batch ${{ steps.semver.outputs.base-version }}  --include '${{ steps.semver.outputs.base-version }}' --remove-prereleases
+          fi
+          changie merge
+          git status
+
+      # this step will fail on whitespace errors but also correct them
+      - name: Remove trailing whitespace
+        continue-on-error: true
+        run: |
+          pre-commit run trailing-whitespace --files .bumpversion.cfg CHANGELOG.md .changes/*
+          git status
+
+      # this step will fail on newline errors but also correct them
+      - name: Removing extra newlines
+        continue-on-error: true
+        run: |
+          pre-commit run end-of-file-fixer --files .bumpversion.cfg CHANGELOG.md .changes/*
+          git status
 
       - name: Commit version bump to branch
         uses: EndBug/add-and-commit@v7
-        if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
         with:
           author_name: 'Github Build Bot'
           author_email: 'buildbot@fishtownanalytics.com'
-          message: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
-          branch: 'bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'
-          push: 'origin origin/bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'
+          message: 'Bumping version to ${{ github.event.inputs.version_number }} and generate CHANGELOG'
+          branch: '${{ steps.variables.outputs.BRANCH_NAME }}'
+          push: 'origin origin/${{ steps.variables.outputs.BRANCH_NAME }}'
 
       - name: Create Pull Request
         uses: peter-evans/create-pull-request@v3
-        if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
         with:
           author: 'Github Build Bot <buildbot@fishtownanalytics.com>'
-          draft: true
           base: ${{github.ref}}
-          title: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
-          branch: 'bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'
+          title: 'Bumping version to ${{ github.event.inputs.version_number }} and generate changelog'
+          branch: '${{ steps.variables.outputs.BRANCH_NAME }}'
           labels: |
             Skip Changelog

.gitignore

@@ -95,3 +95,8 @@ venv/
 
 # vscode
 .vscode/
+*.code-workspace
+
+# poetry
+pyproject.toml
+poetry.lock

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ exclude: ^test/
 
 # Force all unspecified python hooks to run python 3.8
 default_language_version:
-  python: python3.8
+  python: python3
 
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks

CHANGELOG.md

@@ -11,6 +11,7 @@
 For information on prior major and minor releases, see their changelogs:
 
 
+* [1.3](https://github.com/dbt-labs/dbt-core/blob/1.3.latest/CHANGELOG.md)
 * [1.2](https://github.com/dbt-labs/dbt-core/blob/1.2.latest/CHANGELOG.md)
 * [1.1](https://github.com/dbt-labs/dbt-core/blob/1.1.latest/CHANGELOG.md)
 * [1.0](https://github.com/dbt-labs/dbt-core/blob/1.0.latest/CHANGELOG.md)

CONTRIBUTING.md

@@ -7,7 +7,9 @@
 3. [Setting up an environment](#setting-up-an-environment)
 4. [Running `dbt` in development](#running-dbt-core-in-development)
 5. [Testing dbt-core](#testing)
-6. [Submitting a Pull Request](#submitting-a-pull-request)
+6. [Debugging](#debugging)
+7. [Adding a changelog entry](#adding-a-changelog-entry)
+8. [Submitting a Pull Request](#submitting-a-pull-request)
 
 ## About this document
 
@@ -21,7 +23,8 @@ If you get stuck, we're happy to help! Drop us a line in the `#dbt-core-developm
 
 - **Adapters:** Is your issue or proposed code change related to a specific [database adapter](https://docs.getdbt.com/docs/available-adapters)? If so, please open issues, PRs, and discussions in that adapter's repository instead. The sole exception is Postgres; the `dbt-postgres` plugin lives in this repository (`dbt-core`).
 - **CLA:** Please note that anyone contributing code to `dbt-core` must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements). If you are unable to sign the CLA, the `dbt-core` maintainers will unfortunately be unable to merge any of your Pull Requests. We welcome you to participate in discussions, open issues, and comment on existing ones.
-- **Branches:** All pull requests from community contributors should target the `main` branch (default). If the change is needed as a patch for a minor version of dbt that has already been released (or is already a release candidate), a maintainer will backport the changes in your PR to the relevant "latest" release branch (`1.0.latest`, `1.1.latest`, ...)
+- **Branches:** All pull requests from community contributors should target the `main` branch (default). If the change is needed as a patch for a minor version of dbt that has already been released (or is already a release candidate), a maintainer will backport the changes in your PR to the relevant "latest" release branch (`1.0.latest`, `1.1.latest`, ...). If an issue fix applies to a release branch, that fix should be first committed to the development branch and then to the release branch (rarely release-branch fixes may not apply to `main`).
+- **Releases**: Before releasing a new minor version of Core, we prepare a series of alphas and release candidates to allow users (especially employees of dbt Labs!) to test the new version in live environments. This is an important quality assurance step, as it exposes the new code to a wide variety of complicated deployments and can surface bugs before official release. Releases are accessible via pip, homebrew, and dbt Cloud.
 
 ## Getting the code
 
@@ -41,7 +44,9 @@ If you are not a member of the `dbt-labs` GitHub organization, you can contribut
 
 ### dbt Labs contributors
 
-If you are a member of the `dbt-labs` GitHub organization, you will have push access to the `dbt-core` repo. Rather than forking `dbt-core` to make your changes, just clone the repository, check out a new branch, and push directly to that branch.
+If you are a member of the `dbt-labs` GitHub organization, you will have push access to the `dbt-core` repo. Rather than forking `dbt-core` to make your changes, just clone the repository, check out a new branch, and push directly to that branch. Branch names should be fixed by `CT-XXX/` where:
+* CT stands for 'core team'
+* XXX stands for a JIRA ticket number
 
 ## Setting up an environment
 
@@ -151,7 +156,7 @@ Check out the other targets in the Makefile to see other commonly used test
 suites.
 
 #### `pre-commit`
-[`pre-commit`](https://pre-commit.com) takes care of running all code-checks for formatting and linting. Run `make dev` to install `pre-commit` in your local environment.  Once this is done you can use any of the linter-based make targets as well as a git pre-commit hook that will ensure proper formatting and linting.
+[`pre-commit`](https://pre-commit.com) takes care of running all code-checks for formatting and linting. Run `make dev` to install `pre-commit` in your local environment (we recommend running this command with a python virtual environment active). This command installs several pip executables including black, mypy, and flake8. Once this is done you can use any of the linter-based make targets as well as a git pre-commit hook that will ensure proper formatting and linting.
 
 #### `tox`
 
@@ -174,7 +179,29 @@ python3 -m pytest tests/functional/sources
 
 > See [pytest usage docs](https://docs.pytest.org/en/6.2.x/usage.html) for an overview of useful command-line options.
 
-## Adding CHANGELOG Entry
+### Unit, Integration, Functional?
+
+Here are some general rules for adding tests:
+* unit tests (`test/unit` & `tests/unit`) don’t need to access a database; "pure Python" tests should be written as unit tests
+* functional tests (`test/integration` & `tests/functional`) cover anything that interacts with a database, namely adapter
+* *everything in* `test/*` *is being steadily migrated to* `tests/*`
+
+## Debugging
+
+1. The logs for a `dbt run` have stack traces and other information for debugging errors (in `logs/dbt.log` in your project directory).
+2. Try using a debugger, like `ipdb`. For pytest: `--pdb --pdbcls=IPython.terminal.debugger:pdb`
+3. Sometimes, it’s easier to debug on a single thread: `dbt --single-threaded run`
+4. To make print statements from Jinja macros:  `{{ log(msg, info=true) }}`
+5. You can also add `{{ debug() }}` statements, which will drop you into some auto-generated code that the macro wrote.
+6. The dbt “artifacts” are written out to the ‘target’ directory of your dbt project. They are in unformatted json, which can be hard to read. Format them with:
+> python -m json.tool target/run_results.json > run_results.json
+
+### Assorted development tips
+* Append `# type: ignore` to the end of a line if you need to disable `mypy` on that line.
+* Sometimes flake8 complains about lines that are actually fine, in which case you can put a comment on the line such as: # noqa or # noqa: ANNN, where ANNN is the error code that flake8 issues.
+* To collect output for `CProfile`, run dbt with the `-r` option and the name of an output file, i.e. `dbt -r dbt.cprof run`. If you just want to profile parsing, you can do: `dbt -r dbt.cprof parse`. `pip` install `snakeviz` to view the output. Run `snakeviz dbt.cprof` and output will be rendered in a browser window.
+
+## Adding a CHANGELOG Entry
 
 We use [changie](https://changie.dev) to generate `CHANGELOG` entries. **Note:** Do not edit the `CHANGELOG.md` directly. Your modifications will be lost.
 
@@ -186,8 +213,10 @@ You don't need to worry about which `dbt-core` version your change will go into.
 
 ## Submitting a Pull Request
 
-A `dbt-core` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
+Code can be merged into the current development branch `main` by opening a pull request. A `dbt-core` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
 
 Automated tests run via GitHub Actions. If you're a first-time contributor, all tests (including code checks and unit tests) will require a maintainer to approve. Changes in the `dbt-core` repository trigger integration tests against Postgres. dbt Labs also provides CI environments in which to test changes to other adapters, triggered by PRs in those adapters' repositories, as well as periodic maintenance checks of each adapter in concert with the latest `dbt-core` code changes.
 
 Once all tests are passing and your PR has been approved, a `dbt-core` maintainer will merge your changes into the active development branch. And that's it! Happy developing :tada:
+
+Sometimes, the content license agreement auto-check bot doesn't find a user's entry in its roster. If you need to force a rerun, add `@cla-bot check` in a comment on the pull request.

Makefile

@@ -6,6 +6,19 @@ ifeq ($(USE_DOCKER),true)
 	DOCKER_CMD := docker-compose run --rm test
 endif
 
+LOGS_DIR := ./logs
+
+# Optional flag to invoke tests using our CI env.
+# But we always want these active for structured
+# log testing.
+CI_FLAGS =\
+	DBT_TEST_USER_1=dbt_test_user_1\
+	DBT_TEST_USER_2=dbt_test_user_2\
+	DBT_TEST_USER_3=dbt_test_user_3\
+	RUSTFLAGS="-D warnings"\
+	LOG_DIR=./logs\
+	DBT_LOG_FORMAT=json
+
 .PHONY: dev
 dev: ## Installs dbt-* packages in develop mode along with development dependencies.
 	@\
@@ -48,13 +61,20 @@ test: .env ## Runs unit tests with py and code checks against staged changes.
 .PHONY: integration
 integration: .env ## Runs postgres integration tests with py-integration
 	@\
-	$(DOCKER_CMD) tox -e py-integration -- -nauto
+	$(if $(USE_CI_FLAGS), $(CI_FLAGS)) $(DOCKER_CMD) tox -e py-integration -- -nauto
 
 .PHONY: integration-fail-fast
 integration-fail-fast: .env ## Runs postgres integration tests with py-integration in "fail fast" mode.
 	@\
 	$(DOCKER_CMD) tox -e py-integration -- -x -nauto
 
+.PHONY: interop
+interop: clean
+	@\
+	mkdir $(LOGS_DIR) && \
+	$(CI_FLAGS) $(DOCKER_CMD) tox -e py-integration -- -nauto && \
+	LOG_DIR=$(LOGS_DIR) cargo run --manifest-path test/interop/log_parsing/Cargo.toml
+
 .PHONY: setup-db
 setup-db: ## Setup Postgres database with docker-compose for system testing.
 	@\
@@ -76,6 +96,7 @@ endif
 clean: ## Resets development environment.
 	@echo 'cleaning repo...'
 	@rm -f .coverage
+	@rm -f .coverage.*
 	@rm -rf .eggs/
 	@rm -f .env
 	@rm -rf .tox/

core/MANIFEST.in

@@ -1 +1,2 @@
 recursive-include dbt/include *.py *.sql *.yml *.html *.md .gitkeep .gitignore
+include dbt/py.typed

core/dbt/adapters/base/README.md

@@ -0,0 +1,10 @@
+
+## Base adapters
+
+### impl.py
+
+The class `SQLAdapter` in [base/imply.py](https://github.com/dbt-labs/dbt-core/blob/main/core/dbt/adapters/base/impl.py) is a (mostly) abstract object that adapter objects inherit from. The base class scaffolds out methods that every adapter project usually should implement for smooth communication between dbt and database.
+
+Some target databases require more or fewer methods--it all depends on what the warehouse's featureset is.
+
+Look into the class for function-level comments.

core/dbt/adapters/base/__init__.py

@@ -10,5 +10,5 @@ from dbt.adapters.base.relation import (  # noqa
     SchemaSearchMap,
 )
 from dbt.adapters.base.column import Column  # noqa
-from dbt.adapters.base.impl import AdapterConfig, BaseAdapter  # noqa
+from dbt.adapters.base.impl import AdapterConfig, BaseAdapter, PythonJobHelper  # noqa
 from dbt.adapters.base.plugin import AdapterPlugin  # noqa

core/dbt/adapters/base/column.py

@@ -12,6 +12,7 @@ class Column:
         "TIMESTAMP": "TIMESTAMP",
         "FLOAT": "FLOAT",
         "INTEGER": "INT",
+        "BOOLEAN": "BOOLEAN",
     }
     column: str
     dtype: str

core/dbt/adapters/base/impl.py

@@ -2,6 +2,7 @@ import abc
 from concurrent.futures import as_completed, Future
 from contextlib import contextmanager
 from datetime import datetime
+import time
 from itertools import chain
 from typing import (
     Optional,
@@ -42,7 +43,12 @@ from dbt.contracts.graph.manifest import Manifest, MacroManifest
 from dbt.contracts.graph.parsed import ParsedSeedNode
 from dbt.exceptions import warn_or_error
 from dbt.events.functions import fire_event
-from dbt.events.types import CacheMiss, ListRelations
+from dbt.events.types import (
+    CacheMiss,
+    ListRelations,
+    CodeExecution,
+    CodeExecutionStatus,
+)
 from dbt.utils import filter_null_values, executor
 
 from dbt.adapters.base.connections import Connection, AdapterResponse
@@ -54,6 +60,7 @@ from dbt.adapters.base.relation import (
     SchemaSearchMap,
 )
 from dbt.adapters.base import Column as BaseColumn
+from dbt.adapters.base import Credentials
 from dbt.adapters.cache import RelationsCache, _make_key
 
 
@@ -121,6 +128,35 @@ def _relation_name(rel: Optional[BaseRelation]) -> str:
         return str(rel)
 
 
+def log_code_execution(code_execution_function):
+    # decorator to log code and execution time
+    if code_execution_function.__name__ != "submit_python_job":
+        raise ValueError("this should be only used to log submit_python_job now")
+
+    def execution_with_log(*args):
+        self = args[0]
+        connection_name = self.connections.get_thread_connection().name
+        fire_event(CodeExecution(conn_name=connection_name, code_content=args[2]))
+        start_time = time.time()
+        response = code_execution_function(*args)
+        fire_event(
+            CodeExecutionStatus(
+                status=response._message, elapsed=round((time.time() - start_time), 2)
+            )
+        )
+        return response
+
+    return execution_with_log
+
+
+class PythonJobHelper:
+    def __init__(self, parsed_model: Dict, credential: Credentials) -> None:
+        raise NotImplementedError("PythonJobHelper is not implemented yet")
+
+    def submit(self, compiled_code: str) -> Any:
+        raise NotImplementedError("PythonJobHelper submit function is not implemented yet")
+
+
 class BaseAdapter(metaclass=AdapterMeta):
     """The BaseAdapter provides an abstract base class for adapters.
 
@@ -284,7 +320,9 @@ class BaseAdapter(metaclass=AdapterMeta):
             from dbt.parser.manifest import ManifestLoader
 
             manifest = ManifestLoader.load_macros(
-                self.config, self.connections.set_query_header, base_macros_only=base_macros_only
+                self.config,
+                self.connections.set_query_header,
+                base_macros_only=base_macros_only,
             )
             # TODO CT-211
             self._macro_manifest_lazy = manifest  # type: ignore[assignment]
@@ -303,7 +341,11 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         if (database, schema) not in self.cache:
             fire_event(
-                CacheMiss(conn_name=self.nice_connection_name(), database=database, schema=schema)
+                CacheMiss(
+                    conn_name=self.nice_connection_name(),
+                    database=database,
+                    schema=schema,
+                )
             )
             return False
         else:
@@ -381,7 +423,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         self.cache.update_schemas(cache_update)
 
     def set_relations_cache(
-        self, manifest: Manifest, clear: bool = False, required_schemas: Set[BaseRelation] = None
+        self,
+        manifest: Manifest,
+        clear: bool = False,
+        required_schemas: Set[BaseRelation] = None,
     ) -> None:
         """Run a query that gets a populated cache of the relations in the
         database and set the cache on this adapter.
@@ -670,7 +715,10 @@ class BaseAdapter(metaclass=AdapterMeta):
             return self.cache.get_relations(database, schema)
 
         schema_relation = self.Relation.create(
-            database=database, schema=schema, identifier="", quote_policy=self.config.quoting
+            database=database,
+            schema=schema,
+            identifier="",
+            quote_policy=self.config.quoting,
         ).without_identifier()
 
         # we can't build the relations cache because we don't have a
@@ -678,7 +726,9 @@ class BaseAdapter(metaclass=AdapterMeta):
         relations = self.list_relations_without_caching(schema_relation)
         fire_event(
             ListRelations(
-                database=database, schema=schema, relations=[_make_key(x) for x in relations]
+                database=database,
+                schema=schema,
+                relations=[_make_key(x) for x in relations],
             )
         )
 
@@ -1162,6 +1212,74 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         return sql
 
+    @property
+    def python_submission_helpers(self) -> Dict[str, Type[PythonJobHelper]]:
+        raise NotImplementedError("python_submission_helpers is not specified")
+
+    @property
+    def default_python_submission_method(self) -> str:
+        raise NotImplementedError("default_python_submission_method is not specified")
+
+    @log_code_execution
+    def submit_python_job(self, parsed_model: dict, compiled_code: str) -> AdapterResponse:
+        submission_method = parsed_model["config"].get(
+            "submission_method", self.default_python_submission_method
+        )
+        if submission_method not in self.python_submission_helpers:
+            raise NotImplementedError(
+                "Submission method {} is not supported for current adapter".format(
+                    submission_method
+                )
+            )
+        job_helper = self.python_submission_helpers[submission_method](
+            parsed_model, self.connections.profile.credentials
+        )
+        submission_result = job_helper.submit(compiled_code)
+        # process submission result to generate adapter response
+        return self.generate_python_submission_response(submission_result)
+
+    def generate_python_submission_response(self, submission_result: Any) -> AdapterResponse:
+        raise NotImplementedException(
+            "Your adapter need to implement generate_python_submission_response"
+        )
+
+    def valid_incremental_strategies(self):
+        """The set of standard builtin strategies which this adapter supports out-of-the-box.
+        Not used to validate custom strategies defined by end users.
+        """
+        return ["append"]
+
+    def builtin_incremental_strategies(self):
+        return ["append", "delete+insert", "merge", "insert_overwrite"]
+
+    @available.parse_none
+    def get_incremental_strategy_macro(self, model_context, strategy: str):
+        # Construct macro_name from strategy name
+        if strategy is None:
+            strategy = "default"
+
+        # validate strategies for this adapter
+        valid_strategies = self.valid_incremental_strategies()
+        valid_strategies.append("default")
+        builtin_strategies = self.builtin_incremental_strategies()
+        if strategy in builtin_strategies and strategy not in valid_strategies:
+            raise RuntimeException(
+                f"The incremental strategy '{strategy}' is not valid for this adapter"
+            )
+
+        strategy = strategy.replace("+", "_")
+        macro_name = f"get_incremental_{strategy}_sql"
+        # The model_context should have MacroGenerator callable objects for all macros
+        if macro_name not in model_context:
+            raise RuntimeException(
+                'dbt could not find an incremental strategy macro with the name "{}" in {}'.format(
+                    macro_name, self.config.project_name
+                )
+            )
+
+        # This returns a callable macro
+        return model_context[macro_name]
+
 
 COLUMNS_EQUAL_SQL = """
 with diff_count as (

core/dbt/adapters/cache.py

@@ -1,3 +1,4 @@
+import re
 import threading
 from copy import deepcopy
 from typing import Any, Dict, Iterable, List, Optional, Set, Tuple
@@ -383,7 +384,7 @@ class RelationsCache:
         relation = self.relations.pop(old_key)
         new_key = new_relation.key()
 
-        # relaton has to rename its innards, so it needs the _CachedRelation.
+        # relation has to rename its innards, so it needs the _CachedRelation.
         relation.rename(new_relation)
         # update all the relations that refer to it
         for cached in self.relations.values():
@@ -413,9 +414,24 @@ class RelationsCache:
         :raises InternalError: If the new key is already present.
         """
         if new_key in self.relations:
+            # Tell user when collision caused by model names truncated during
+            # materialization.
+            match = re.search("__dbt_backup|__dbt_tmp$", new_key.identifier)
+            if match:
+                truncated_model_name_prefix = new_key.identifier[: match.start()]
+                message_addendum = (
+                    "\n\nName collisions can occur when the length of two "
+                    "models' names approach your database's builtin limit. "
+                    "Try restructuring your project such that no two models "
+                    "share the prefix '{}'.".format(truncated_model_name_prefix)
+                    + " Then, clean your warehouse of any removed models."
+                )
+            else:
+                message_addendum = ""
+
             dbt.exceptions.raise_cache_inconsistent(
-                "in rename, new key {} already in cache: {}".format(
-                    new_key, list(self.relations.keys())
+                "in rename, new key {} already in cache: {}{}".format(
+                    new_key, list(self.relations.keys()), message_addendum
                 )
             )
 

core/dbt/adapters/factory.py

@@ -1,23 +1,17 @@
 import threading
-from pathlib import Path
+from contextlib import contextmanager
 from importlib import import_module
-from typing import Type, Dict, Any, List, Optional, Set
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Set, Type
 
-from dbt.exceptions import RuntimeException, InternalException
-from dbt.include.global_project import (
-    PACKAGE_PATH as GLOBAL_PROJECT_PATH,
-    PROJECT_NAME as GLOBAL_PROJECT_NAME,
-)
+from dbt.adapters.base.plugin import AdapterPlugin
+from dbt.adapters.protocol import AdapterConfig, AdapterProtocol, RelationProtocol
+from dbt.contracts.connection import AdapterRequiredConfig, Credentials
 from dbt.events.functions import fire_event
 from dbt.events.types import AdapterImportError, PluginLoadError
-from dbt.contracts.connection import Credentials, AdapterRequiredConfig
-from dbt.adapters.protocol import (
-    AdapterProtocol,
-    AdapterConfig,
-    RelationProtocol,
-)
-from dbt.adapters.base.plugin import AdapterPlugin
-
+from dbt.exceptions import InternalException, RuntimeException
+from dbt.include.global_project import PACKAGE_PATH as GLOBAL_PROJECT_PATH
+from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
 
 Adapter = AdapterProtocol
 
@@ -64,7 +58,7 @@ class AdapterContainer:
             # if we failed to import the target module in particular, inform
             # the user about it via a runtime error
             if exc.name == "dbt.adapters." + name:
-                fire_event(AdapterImportError(exc=exc))
+                fire_event(AdapterImportError(exc=str(exc)))
                 raise RuntimeException(f"Could not find adapter type {name}!")
             # otherwise, the error had to have come from some underlying
             # library. Log the stack trace.
@@ -217,3 +211,12 @@ def get_adapter_package_names(name: Optional[str]) -> List[str]:
 
 def get_adapter_type_names(name: Optional[str]) -> List[str]:
     return FACTORY.get_adapter_type_names(name)
+
+
+@contextmanager
+def adapter_management():
+    reset_adapters()
+    try:
+        yield
+    finally:
+        cleanup_connections()

core/dbt/adapters/protocol.py

@@ -88,7 +88,7 @@ class AdapterProtocol(  # type: ignore[misc]
     ],
 ):
     # N.B. Technically these are ClassVars, but mypy doesn't support putting type vars in a
-    # ClassVar due to the restirctiveness of PEP-526
+    # ClassVar due to the restrictiveness of PEP-526
     # See: https://github.com/python/mypy/issues/5144
     AdapterSpecificConfigs: Type[AdapterConfig_T]
     Column: Type[Column_T]

core/dbt/cli/README.md

@@ -0,0 +1 @@
+TODO

core/dbt/cli/flags.py

@@ -0,0 +1,44 @@
+# TODO  Move this to /core/dbt/flags.py when we're ready to break things
+import os
+from dataclasses import dataclass
+from multiprocessing import get_context
+from pprint import pformat as pf
+
+from click import get_current_context
+
+if os.name != "nt":
+    # https://bugs.python.org/issue41567
+    import multiprocessing.popen_spawn_posix  # type: ignore  # noqa: F401
+
+
+@dataclass(frozen=True)
+class Flags:
+    def __init__(self, ctx=None) -> None:
+
+        if ctx is None:
+            ctx = get_current_context()
+
+        def assign_params(ctx):
+            """Recursively adds all click params to flag object"""
+            for param_name, param_value in ctx.params.items():
+                # N.B. You have to use the base MRO method (object.__setattr__) to set attributes
+                # when using frozen dataclasses.
+                # https://docs.python.org/3/library/dataclasses.html#frozen-instances
+                if hasattr(self, param_name):
+                    raise Exception(f"Duplicate flag names found in click command: {param_name}")
+                object.__setattr__(self, param_name.upper(), param_value)
+            if ctx.parent:
+                assign_params(ctx.parent)
+
+        assign_params(ctx)
+
+        # Hard coded flags
+        object.__setattr__(self, "WHICH", ctx.info_name)
+        object.__setattr__(self, "MP_CONTEXT", get_context("spawn"))
+
+        # Support console DO NOT TRACK initiave
+        if os.getenv("DO_NOT_TRACK", "").lower() in (1, "t", "true", "y", "yes"):
+            object.__setattr__(self, "ANONYMOUS_USAGE_STATS", False)
+
+    def __str__(self) -> str:
+        return str(pf(self.__dict__))

core/dbt/cli/main.py

@@ -0,0 +1,412 @@
+import inspect  # This is temporary for RAT-ing
+from copy import copy
+from pprint import pformat as pf  # This is temporary for RAT-ing
+
+import click
+from dbt.adapters.factory import adapter_management
+from dbt.cli import params as p
+from dbt.cli.flags import Flags
+from dbt.profiler import profiler
+
+
+def cli_runner():
+    # Alias "list" to "ls"
+    ls = copy(cli.commands["list"])
+    ls.hidden = True
+    cli.add_command(ls, "ls")
+
+    # Run the cli
+    cli()
+
+
+# dbt
+@click.group(
+    context_settings={"help_option_names": ["-h", "--help"]},
+    invoke_without_command=True,
+    no_args_is_help=True,
+    epilog="Specify one of these sub-commands and you can find more help from there.",
+)
+@click.pass_context
+@p.anonymous_usage_stats
+@p.cache_selected_only
+@p.debug
+@p.enable_legacy_logger
+@p.event_buffer_size
+@p.fail_fast
+@p.log_cache_events
+@p.log_format
+@p.macro_debugging
+@p.partial_parse
+@p.print
+@p.printer_width
+@p.quiet
+@p.record_timing_info
+@p.static_parser
+@p.use_colors
+@p.use_experimental_parser
+@p.version
+@p.version_check
+@p.warn_error
+@p.write_json
+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
+    """
+    incomplete_flags = Flags()
+
+    # Profiling
+    if incomplete_flags.RECORD_TIMING_INFO:
+        ctx.with_resource(profiler(enable=True, outfile=incomplete_flags.RECORD_TIMING_INFO))
+
+    # Adapter management
+    ctx.with_resource(adapter_management())
+
+    # Version info
+    if incomplete_flags.VERSION:
+        click.echo(f"`version` called\n ctx.params: {pf(ctx.params)}")
+        return
+    else:
+        del ctx.params["version"]
+
+
+# dbt build
+@cli.command("build")
+@click.pass_context
+@p.defer
+@p.exclude
+@p.fail_fast
+@p.full_refresh
+@p.indirect_selection
+@p.log_path
+@p.models
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.selector
+@p.show
+@p.state
+@p.store_failures
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@p.version_check
+def build(ctx, **kwargs):
+    """Run all Seeds, Models, Snapshots, and tests in DAG order"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt clean
+@cli.command("clean")
+@click.pass_context
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.vars
+def clean(ctx, **kwargs):
+    """Delete all folders in the clean-targets list (usually the dbt_packages and target directories.)"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt docs
+@cli.group()
+@click.pass_context
+def docs(ctx, **kwargs):
+    """Generate or serve the documentation website for your project"""
+
+
+# dbt docs generate
+@docs.command("generate")
+@click.pass_context
+@p.compile_docs
+@p.defer
+@p.exclude
+@p.log_path
+@p.models
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.selector
+@p.state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@p.version_check
+def docs_generate(ctx, **kwargs):
+    """Generate the documentation website for your project"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt docs serve
+@docs.command("serve")
+@click.pass_context
+@p.browser
+@p.port
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.vars
+def docs_serve(ctx, **kwargs):
+    """Serve the documentation website for your project"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt compile
+@cli.command("compile")
+@click.pass_context
+@p.defer
+@p.exclude
+@p.full_refresh
+@p.log_path
+@p.models
+@p.parse_only
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.selector
+@p.state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@p.version_check
+def compile(ctx, **kwargs):
+    """Generates executable SQL from source, model, test, and analysis files. Compiled SQL files are written to the target/ directory."""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt debug
+@cli.command("debug")
+@click.pass_context
+@p.config_dir
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.vars
+@p.version_check
+def debug(ctx, **kwargs):
+    """Show some helpful information about dbt for debugging. Not to be confused with the --debug option which increases verbosity."""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt deps
+@cli.command("deps")
+@click.pass_context
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.vars
+def deps(ctx, **kwargs):
+    """Pull the most recent version of the dependencies listed in packages.yml"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt init
+@cli.command("init")
+@click.pass_context
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.skip_profile_setup
+@p.target
+@p.vars
+def init(ctx, **kwargs):
+    """Initialize a new DBT project."""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt list
+@cli.command("list")
+@click.pass_context
+@p.exclude
+@p.indirect_selection
+@p.models
+@p.output
+@p.output_keys
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.resource_type
+@p.selector
+@p.state
+@p.target
+@p.vars
+def list(ctx, **kwargs):
+    """List the resources in your project"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt parse
+@cli.command("parse")
+@click.pass_context
+@p.compile_parse
+@p.log_path
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@p.version_check
+@p.write_manifest
+def parse(ctx, **kwargs):
+    """Parses the project and provides information on performance"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt run
+@cli.command("run")
+@click.pass_context
+@p.defer
+@p.exclude
+@p.fail_fast
+@p.full_refresh
+@p.log_path
+@p.models
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.selector
+@p.state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@p.version_check
+def run(ctx, **kwargs):
+    """Compile SQL and execute against the current target database."""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt run operation
+@cli.command("run-operation")
+@click.pass_context
+@p.args
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.vars
+def run_operation(ctx, **kwargs):
+    """Run the named macro with any supplied arguments."""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt seed
+@cli.command("seed")
+@click.pass_context
+@p.exclude
+@p.full_refresh
+@p.log_path
+@p.models
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.selector
+@p.show
+@p.state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@p.version_check
+def seed(ctx, **kwargs):
+    """Load data from csv files into your data warehouse."""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt snapshot
+@cli.command("snapshot")
+@click.pass_context
+@p.defer
+@p.exclude
+@p.models
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.selector
+@p.state
+@p.target
+@p.threads
+@p.vars
+def snapshot(ctx, **kwargs):
+    """Execute snapshots defined in your project"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt source
+@cli.group()
+@click.pass_context
+def source(ctx, **kwargs):
+    """Manage your project's sources"""
+
+
+# dbt source freshness
+@source.command("freshness")
+@click.pass_context
+@p.exclude
+@p.models
+@p.output_path  # TODO: Is this ok to re-use?  We have three different output params, how much can we consolidate?
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.selector
+@p.state
+@p.target
+@p.threads
+@p.vars
+def freshness(ctx, **kwargs):
+    """Snapshots the current freshness of the project's sources"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# dbt test
+@cli.command("test")
+@click.pass_context
+@p.defer
+@p.exclude
+@p.fail_fast
+@p.indirect_selection
+@p.log_path
+@p.models
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.selector
+@p.state
+@p.store_failures
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@p.version_check
+def test(ctx, **kwargs):
+    """Runs tests on data in deployed models. Run this after `dbt run`"""
+    flags = Flags()
+    click.echo(f"`{inspect.stack()[0][3]}` called\n flags: {flags}")
+
+
+# Support running as a module
+if __name__ == "__main__":
+    cli_runner()

core/dbt/cli/option_types.py

@@ -0,0 +1,33 @@
+from click import ParamType
+import yaml
+
+
+class YAML(ParamType):
+    """The Click YAML type. Converts YAML strings into objects."""
+
+    name = "YAML"
+
+    def convert(self, value, param, ctx):
+        # assume non-string values are a problem
+        if not isinstance(value, str):
+            self.fail(f"Cannot load YAML from type {type(value)}", param, ctx)
+        try:
+            return yaml.load(value, Loader=yaml.Loader)
+        except yaml.parser.ParserError:
+            self.fail(f"String '{value}' is not valid YAML", param, ctx)
+
+
+class Truthy(ParamType):
+    """The Click Truthy type.  Converts strings into a "truthy" type"""
+
+    name = "TRUTHY"
+
+    def convert(self, value, param, ctx):
+        # assume non-string / non-None values are a problem
+        if not isinstance(value, (str, None)):
+            self.fail(f"Cannot load TRUTHY from type {type(value)}", param, ctx)
+
+        if value is None or value.lower() in ("0", "false", "f"):
+            return None
+        else:
+            return value

core/dbt/cli/params.py

@@ -0,0 +1,386 @@
+from pathlib import Path, PurePath
+
+import click
+from dbt.cli.option_types import YAML
+from dbt.cli.resolvers import default_project_dir, default_profiles_dir
+
+
+# TODO:  The name (reflected in flags) is a correction!
+# The original name was `SEND_ANONYMOUS_USAGE_STATS` and used an env var called "DBT_SEND_ANONYMOUS_USAGE_STATS"
+# Both of which break existing naming conventions (doesn't match param flag).
+# This will need to be fixed before use in the main codebase and communicated as a change to the community!
+anonymous_usage_stats = click.option(
+    "--anonymous-usage-stats/--no-anonymous-usage-stats",
+    envvar="DBT_ANONYMOUS_USAGE_STATS",
+    help="Send anonymous usage stats to dbt Labs.",
+    default=True,
+)
+
+args = click.option(
+    "--args",
+    envvar=None,
+    help="Supply arguments to the macro. This dictionary will be mapped to the keyword arguments defined in the selected macro. This argument should be a YAML string, eg. '{my_variable: my_value}'",
+    type=YAML(),
+)
+
+browser = click.option(
+    "--browser/--no-browser",
+    envvar=None,
+    help="Wether or not to open a local web browser after starting the server",
+    default=True,
+)
+
+cache_selected_only = click.option(
+    "--cache-selected-only/--no-cache-selected-only",
+    envvar="DBT_CACHE_SELECTED_ONLY",
+    help="Pre cache database objects relevant to selected resource only.",
+)
+
+compile_docs = click.option(
+    "--compile/--no-compile",
+    envvar=None,
+    help="Wether or not to run 'dbt compile' as part of docs generation",
+    default=True,
+)
+
+compile_parse = click.option(
+    "--compile/--no-compile",
+    envvar=None,
+    help="TODO: No help text currently available",
+    default=True,
+)
+
+config_dir = click.option(
+    "--config-dir",
+    envvar=None,
+    help="If specified, DBT will show path information for this project",
+    type=click.STRING,
+)
+
+debug = click.option(
+    "--debug/--no-debug",
+    "-d/ ",
+    envvar="DBT_DEBUG",
+    help="Display debug logging during dbt execution. Useful for debugging and making bug reports.",
+)
+
+# TODO:  The env var and name (reflected in flags) are corrections!
+# The original name was `DEFER_MODE` and used an env var called "DBT_DEFER_TO_STATE"
+# Both of which break existing naming conventions.
+# This will need to be fixed before use in the main codebase and communicated as a change to the community!
+defer = click.option(
+    "--defer/--no-defer",
+    envvar="DBT_DEFER",
+    help="If set, defer to the state variable for resolving unselected nodes.",
+)
+
+enable_legacy_logger = click.option(
+    "--enable-legacy-logger/--no-enable-legacy-logger",
+    envvar="DBT_ENABLE_LEGACY_LOGGER",
+    hidden=True,
+)
+
+event_buffer_size = click.option(
+    "--event-buffer-size",
+    envvar="DBT_EVENT_BUFFER_SIZE",
+    help="Sets the max number of events to buffer in EVENT_HISTORY.",
+    default=100000,
+    type=click.INT,
+)
+
+exclude = click.option("--exclude", envvar=None, help="Specify the nodes to exclude.")
+
+fail_fast = click.option(
+    "--fail-fast/--no-fail-fast",
+    "-x/ ",
+    envvar="DBT_FAIL_FAST",
+    help="Stop execution on first failure.",
+)
+
+full_refresh = click.option(
+    "--full-refresh",
+    "-f",
+    envvar="DBT_FULL_REFRESH",
+    help="If specified, dbt will drop incremental models and fully-recalculate the incremental table from the model definition.",
+    is_flag=True,
+)
+
+indirect_selection = click.option(
+    "--indirect-selection",
+    envvar="DBT_INDIRECT_SELECTION",
+    help="Select all tests that are adjacent to selected resources, even if they those resources have been explicitly selected.",
+    type=click.Choice(["eager", "cautious"], case_sensitive=False),
+    default="eager",
+)
+
+log_cache_events = click.option(
+    "--log-cache-events/--no-log-cache-events",
+    help="Enable verbose adapter cache logging.",
+    envvar="DBT_LOG_CACHE_EVENTS",
+)
+
+log_format = click.option(
+    "--log-format",
+    envvar="DBT_LOG_FORMAT",
+    help="Specify the log format, overriding the command's default.",
+    type=click.Choice(["text", "json", "default"], case_sensitive=False),
+    default="default",
+)
+
+log_path = click.option(
+    "--log-path",
+    envvar="DBT_LOG_PATH",
+    help="Configure the 'log-path'. Only applies this setting for the current run. Overrides the 'DBT_LOG_PATH' if it is set.",
+    type=click.Path(),
+)
+
+macro_debugging = click.option(
+    "--macro-debugging/--no-macro-debugging",
+    envvar="DBT_MACRO_DEBUGGING",
+    hidden=True,
+)
+
+models = click.option(
+    "-m",
+    "-s",
+    "models",
+    envvar=None,
+    help="Specify the nodes to include.",
+    multiple=True,
+)
+
+output = click.option(
+    "--output",
+    envvar=None,
+    help="TODO: No current help text",
+    type=click.Choice(["json", "name", "path", "selector"], case_sensitive=False),
+    default="name",
+)
+
+output_keys = click.option(
+    "--output-keys", envvar=None, help="TODO: No current help text", type=click.STRING
+)
+
+output_path = click.option(
+    "--output",
+    "-o",
+    envvar=None,
+    help="Specify the output path for the json report. By default, outputs to 'target/sources.json'",
+    type=click.Path(file_okay=True, dir_okay=False, writable=True),
+    default=PurePath.joinpath(Path.cwd(), "target/sources.json"),
+)
+
+parse_only = click.option(
+    "--parse-only",
+    envvar=None,
+    help="TODO:  No help text currently available",
+    is_flag=True,
+)
+
+partial_parse = click.option(
+    "--partial-parse/--no-partial-parse",
+    envvar="DBT_PARTIAL_PARSE",
+    help="Allow for partial parsing by looking for and writing to a pickle file in the target directory. This overrides the user configuration file.",
+    default=True,
+)
+
+port = click.option(
+    "--port",
+    envvar=None,
+    help="Specify the port number for the docs server",
+    default=8080,
+    type=click.INT,
+)
+
+# TODO:  The env var and name (reflected in flags) are corrections!
+# The original name was `NO_PRINT` and used the env var `DBT_NO_PRINT`.
+# Both of which break existing naming conventions.
+# This will need to be fixed before use in the main codebase and communicated as a change to the community!
+print = click.option(
+    "--print/--no-print",
+    envvar="DBT_PRINT",
+    help="Output all {{ print() }} macro calls.",
+    default=True,
+)
+
+printer_width = click.option(
+    "--printer-width",
+    envvar="DBT_PRINTER_WIDTH",
+    help="Sets the width of terminal output",
+    type=click.INT,
+    default=80,
+)
+
+profile = click.option(
+    "--profile",
+    envvar=None,
+    help="Which profile to load. Overrides setting in dbt_project.yml.",
+)
+
+profiles_dir = click.option(
+    "--profiles-dir",
+    envvar="DBT_PROFILES_DIR",
+    help="Which directory to look in for the profiles.yml file. If not set, dbt will look in the current working directory first, then HOME/.dbt/",
+    default=default_profiles_dir(),
+    type=click.Path(exists=True),
+)
+
+project_dir = click.option(
+    "--project-dir",
+    envvar=None,
+    help="Which directory to look in for the dbt_project.yml file. Default is the current working directory and its parents.",
+    default=default_project_dir(),
+    type=click.Path(exists=True),
+)
+
+quiet = click.option(
+    "--quiet/--no-quiet",
+    envvar="DBT_QUIET",
+    help="Suppress all non-error logging to stdout. Does not affect {{ print() }} macro calls.",
+)
+
+record_timing_info = click.option(
+    "--record-timing-info",
+    "-r",
+    envvar=None,
+    help="When this option is passed, dbt will output low-level timing stats to the specified file. Example: `--record-timing-info output.profile`",
+    type=click.Path(exists=False),
+)
+
+resource_type = click.option(
+    "--resource-type",
+    envvar=None,
+    help="TODO: No current help text",
+    type=click.Choice(
+        [
+            "metric",
+            "source",
+            "analysis",
+            "model",
+            "test",
+            "exposure",
+            "snapshot",
+            "seed",
+            "default",
+            "all",
+        ],
+        case_sensitive=False,
+    ),
+    default="default",
+)
+
+selector = click.option(
+    "--selector", envvar=None, help="The selector name to use, as defined in selectors.yml"
+)
+
+show = click.option(
+    "--show", envvar=None, help="Show a sample of the loaded data in the terminal", is_flag=True
+)
+
+skip_profile_setup = click.option(
+    "--skip-profile-setup", "-s", envvar=None, help="Skip interative profile setup.", is_flag=True
+)
+
+# TODO:  The env var and name (reflected in flags) are corrections!
+# The original name was `ARTIFACT_STATE_PATH` and used the env var `DBT_ARTIFACT_STATE_PATH`.
+# Both of which break existing naming conventions.
+# This will need to be fixed before use in the main codebase and communicated as a change to the community!
+state = click.option(
+    "--state",
+    envvar="DBT_STATE",
+    help="If set, use the given directory as the source for json files to compare with this project.",
+    type=click.Path(
+        dir_okay=True,
+        exists=True,
+        file_okay=False,
+        readable=True,
+        resolve_path=True,
+    ),
+)
+
+static_parser = click.option(
+    "--static-parser/--no-static-parser",
+    envvar="DBT_STATIC_PARSER",
+    help="Use the static parser.",
+    default=True,
+)
+
+store_failures = click.option(
+    "--store-failures",
+    envvar="DBT_STORE_FAILURES",
+    help="Store test results (failing rows) in the database",
+    is_flag=True,
+)
+
+target = click.option(
+    "--target", "-t", envvar=None, help="Which target to load for the given profile"
+)
+
+target_path = click.option(
+    "--target-path",
+    envvar="DBT_TARGET_PATH",
+    help="Configure the 'target-path'. Only applies this setting for the current run. Overrides the 'DBT_TARGET_PATH' if it is set.",
+    type=click.Path(),
+)
+
+threads = click.option(
+    "--threads",
+    envvar=None,
+    help="Specify number of threads to use while executing models. Overrides settings in profiles.yml.",
+    default=1,
+    type=click.INT,
+)
+
+use_colors = click.option(
+    "--use-colors/--no-use-colors",
+    envvar="DBT_USE_COLORS",
+    help="Output is colorized by default and may also be set in a profile or at the command line.",
+    default=True,
+)
+
+use_experimental_parser = click.option(
+    "--use-experimental-parser/--no-use-experimental-parser",
+    envvar="DBT_USE_EXPERIMENTAL_PARSER",
+    help="Enable experimental parsing features.",
+)
+
+vars = click.option(
+    "--vars",
+    envvar=None,
+    help="Supply variables to the project. This argument overrides variables defined in your dbt_project.yml file. This argument should be a YAML string, eg. '{my_variable: my_value}'",
+    type=YAML(),
+)
+
+version = click.option(
+    "--version",
+    envvar=None,
+    help="Show version information",
+    is_flag=True,
+)
+
+version_check = click.option(
+    "--version-check/--no-version-check",
+    envvar="DBT_VERSION_CHECK",
+    help="Ensure dbt's version matches the one specified in the dbt_project.yml file ('require-dbt-version')",
+    default=True,
+)
+
+warn_error = click.option(
+    "--warn-error/--no-warn-error",
+    envvar="DBT_WARN_ERROR",
+    help="If dbt would normally warn, instead raise an exception. Examples include --models that selects nothing, deprecations, configurations with no associated models, invalid test configurations, and missing sources/refs in tests.",
+)
+
+write_json = click.option(
+    "--write-json/--no-write-json",
+    envvar="DBT_WRITE_JSON",
+    help="Writing the manifest and run_results.json files to disk",
+    default=True,
+)
+
+write_manifest = click.option(
+    "--write-manifest/--no-write-manifest",
+    envvar=None,
+    help="TODO: No help text currently available",
+    default=True,
+)

core/dbt/cli/resolvers.py

@@ -0,0 +1,11 @@
+from pathlib import Path
+
+
+def default_project_dir():
+    paths = list(Path.cwd().parents)
+    paths.insert(0, Path.cwd())
+    return next((x for x in paths if (x / "dbt_project.yml").exists()), Path.cwd())
+
+
+def default_profiles_dir():
+    return Path.cwd() if (Path.cwd() / "profiles.yml").exists() else Path.home() / ".dbt"

core/dbt/clients/README.md

@@ -1 +1,19 @@
 # Clients README
+
+### Jinja
+
+#### How are materializations defined
+
+Model materializations are kept in `core/dbt/include/global_project/macros/materializations/models/`. Materializations are defined using syntax that isn't part of the Jinja standard library. These tags are referenced internally, and materializations can be overridden in user projects when users have specific needs.
+
+```
+-- Pseudocode for arguments
+{% materialization <name>, <target name := one_of{default, adapter}> %}'
+…
+{% endmaterialization %}
+```
+
+These blocks are referred to Jinja extensions. Extensions are defined as part of the accepted Jinja code encapsulated within a dbt project. This includes system code used internally by dbt and user space (i.e. user-defined) macros. Extensions exist to help Jinja users create reusable code blocks or abstract objects--for us, materializations are a great use-case since we pass these around as arguments within dbt system code.
+
+The code that defines this extension is a class `MaterializationExtension` and a `parse` routine. That code lives in [clients/jinja.py](https://github.com/dbt-labs/dbt-core/blob/main/core/dbt/clients/jinja.py). The routine
+enables Jinja to parse (i.e. recognize) the unique comma separated arg structure our `materialization` tags exhibit (the `table, default` as seen above).

core/dbt/clients/jinja.py

@@ -27,6 +27,7 @@ from dbt.utils import (
 from dbt.clients._jinja_blocks import BlockIterator, BlockData, BlockTag
 from dbt.contracts.graph.compiled import CompiledGenericTestNode
 from dbt.contracts.graph.parsed import ParsedGenericTestNode
+
 from dbt.exceptions import (
     InternalException,
     raise_compiler_error,
@@ -37,6 +38,10 @@ from dbt.exceptions import (
     UndefinedMacroException,
 )
 from dbt import flags
+from dbt.node_types import ModelLanguage
+
+
+SUPPORTED_LANG_ARG = jinja2.nodes.Name("supported_languages", "param")
 
 
 def _linecache_inject(source, write):
@@ -161,7 +166,7 @@ def quoted_native_concat(nodes):
 
 
 class NativeSandboxTemplate(jinja2.nativetypes.NativeTemplate):  # mypy: ignore
-    environment_class = NativeSandboxEnvironment
+    environment_class = NativeSandboxEnvironment  # type: ignore
 
     def render(self, *args, **kwargs):
         """Render the template to produce a native Python type. If the
@@ -301,13 +306,13 @@ class MacroGenerator(BaseMacroGenerator):
     @contextmanager
     def track_call(self):
         # This is only called from __call__
-        if self.stack is None or self.node is None:
+        if self.stack is None:
             yield
         else:
             unique_id = self.macro.unique_id
             depth = self.stack.depth
-            # only mark depth=0 as a dependency
-            if depth == 0:
+            # only mark depth=0 as a dependency, when creating this dependency we don't pass in stack
+            if depth == 0 and self.node:
                 self.node.depends_on.add_macro(unique_id)
             self.stack.push(unique_id)
             try:
@@ -364,9 +369,20 @@ class MaterializationExtension(jinja2.ext.Extension):
                 value = parser.parse_expression()
                 adapter_name = value.value
 
+            elif target.name == "supported_languages":
+                target.set_ctx("param")
+                node.args.append(target)
+                parser.stream.expect("assign")
+                languages = parser.parse_expression()
+                node.defaults.append(languages)
+
             else:
                 invalid_materialization_argument(materialization_name, target.name)
 
+        if SUPPORTED_LANG_ARG not in node.args:
+            node.args.append(SUPPORTED_LANG_ARG)
+            node.defaults.append(jinja2.nodes.List([jinja2.nodes.Const("sql")]))
+
         node.name = get_materialization_macro_name(materialization_name, adapter_name)
 
         node.body = parser.parse_statements(("name:endmaterialization",), drop_needle=True)
@@ -632,3 +648,21 @@ def add_rendered_test_kwargs(
     # when the test node was created in _parse_generic_test.
     kwargs = deep_map_render(_convert_function, node.test_metadata.kwargs)
     context[GENERIC_TEST_KWARGS_NAME] = kwargs
+
+
+def get_supported_languages(node: jinja2.nodes.Macro) -> List[ModelLanguage]:
+    if "materialization" not in node.name:
+        raise_compiler_error("Only materialization macros can be used with this function")
+
+    no_kwargs = not node.defaults
+    no_langs_found = SUPPORTED_LANG_ARG not in node.args
+
+    if no_kwargs or no_langs_found:
+        raise_compiler_error(f"No supported_languages found in materialization macro {node.name}")
+
+    lang_idx = node.args.index(SUPPORTED_LANG_ARG)
+    # indexing defaults from the end
+    # since supported_languages is a kwarg, and kwargs are at always after args
+    return [
+        ModelLanguage[item.value] for item in node.defaults[-(len(node.args) - lang_idx)].items
+    ]

core/dbt/clients/jinja_static.py

@@ -15,7 +15,7 @@ def statically_extract_macro_calls(string, ctx, db_wrapper=None):
         if hasattr(func_call, "node") and hasattr(func_call.node, "name"):
             func_name = func_call.node.name
         else:
-            # func_call for dbt_utils.current_timestamp macro
+            # func_call for dbt.current_timestamp macro
             # Call(
             #   node=Getattr(
             #     node=Name(

core/dbt/clients/registry.py

@@ -14,6 +14,7 @@ from dbt.events.types import (
 )
 from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
 from dbt import deprecations
+from dbt import semver
 import os
 
 if os.getenv("DBT_PACKAGE_HUB_URL"):
@@ -125,10 +126,37 @@ def package_version(package_name, version, registry_base_url=None) -> Dict[str,
     return response[version]
 
 
-def get_available_versions(package_name) -> List["str"]:
+def is_compatible_version(package_spec, dbt_version) -> bool:
+    require_dbt_version = package_spec.get("require_dbt_version")
+    if not require_dbt_version:
+        # if version requirements are missing or empty, assume any version is compatible
+        return True
+    else:
+        # determine whether dbt_version satisfies this package's require-dbt-version config
+        if not isinstance(require_dbt_version, list):
+            require_dbt_version = [require_dbt_version]
+        supported_versions = [
+            semver.VersionSpecifier.from_version_string(v) for v in require_dbt_version
+        ]
+        return semver.versions_compatible(dbt_version, *supported_versions)
+
+
+def get_compatible_versions(package_name, dbt_version, should_version_check) -> List["str"]:
     # returns a list of all available versions of a package
     response = package(package_name)
-    return list(response)
+
+    # if the user doesn't care about installing compatible versions, just return them all
+    if not should_version_check:
+        return list(response)
+
+    # otherwise, only return versions that are compatible with the installed version of dbt-core
+    else:
+        compatible_versions = [
+            pkg_version
+            for pkg_version, info in response.items()
+            if is_compatible_version(info, dbt_version)
+        ]
+        return compatible_versions
 
 
 def _get_index(registry_base_url=None):

core/dbt/clients/system.py

@@ -12,6 +12,7 @@ import tarfile
 import requests
 import stat
 from typing import Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
+from pathspec import PathSpec  # type: ignore
 
 from dbt.events.functions import fire_event
 from dbt.events.types import (
@@ -36,6 +37,7 @@ def find_matching(
     root_path: str,
     relative_paths_to_search: List[str],
     file_pattern: str,
+    ignore_spec: Optional[PathSpec] = None,
 ) -> List[Dict[str, Any]]:
     """
     Given an absolute `root_path`, a list of relative paths to that
@@ -57,19 +59,30 @@ def find_matching(
     reobj = re.compile(regex, re.IGNORECASE)
 
     for relative_path_to_search in relative_paths_to_search:
+        # potential speedup for ignore_spec
+        # if ignore_spec.matches(relative_path_to_search):
+        #     continue
         absolute_path_to_search = os.path.join(root_path, relative_path_to_search)
         walk_results = os.walk(absolute_path_to_search)
 
         for current_path, subdirectories, local_files in walk_results:
+            # potential speedup for ignore_spec
+            # relative_dir = os.path.relpath(current_path, root_path) + os.sep
+            # if ignore_spec.match(relative_dir):
+            #     continue
             for local_file in local_files:
                 absolute_path = os.path.join(current_path, local_file)
                 relative_path = os.path.relpath(absolute_path, absolute_path_to_search)
+                relative_path_to_root = os.path.join(relative_path_to_search, relative_path)
+
                 modification_time = 0.0
                 try:
                     modification_time = os.path.getmtime(absolute_path)
                 except OSError:
                     fire_event(SystemErrorRetrievingModTime(path=absolute_path))
-                if reobj.match(local_file):
+                if reobj.match(local_file) and (
+                    not ignore_spec or not ignore_spec.match_file(relative_path_to_root)
+                ):
                     matching.append(
                         {
                             "searched_path": relative_path_to_search,
@@ -164,7 +177,7 @@ def write_file(path: str, contents: str = "") -> bool:
                 reason = "Path was possibly too long"
             # all our hard work and the path was still too long. Log and
             # continue.
-            fire_event(SystemCouldNotWrite(path=path, reason=reason, exc=exc))
+            fire_event(SystemCouldNotWrite(path=path, reason=reason, exc=str(exc)))
         else:
             raise
     return True

core/dbt/compilation.py

@@ -29,7 +29,7 @@ from dbt.exceptions import (
 from dbt.graph import Graph
 from dbt.events.functions import fire_event
 from dbt.events.types import FoundStats, CompilingNode, WritingInjectedSQLForNode
-from dbt.node_types import NodeType
+from dbt.node_types import NodeType, ModelLanguage
 from dbt.events.format import pluralize
 import dbt.tracking
 
@@ -56,6 +56,7 @@ def print_compile_stats(stats):
         NodeType.Source: "source",
         NodeType.Exposure: "exposure",
         NodeType.Metric: "metric",
+        NodeType.Entity: "entity",
     }
 
     results = {k: 0 for k in names.keys()}
@@ -183,6 +184,7 @@ class Compiler:
 
         context = generate_runtime_model_context(node, self.config, manifest)
         context.update(extra_context)
+
         if isinstance(node, CompiledGenericTestNode):
             # for test nodes, add a special keyword args value to the context
             jinja.add_rendered_test_kwargs(context, node)
@@ -271,7 +273,7 @@ class Compiler:
         are rolled up into the models that refer to them by
         inserting CTEs into the SQL.
         """
-        if model.compiled_sql is None:
+        if model.compiled_code is None:
             raise RuntimeException("Cannot inject ctes into an unparsed node", model)
         if model.extra_ctes_injected:
             return (model, model.extra_ctes)
@@ -324,29 +326,28 @@ class Compiler:
             _extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
 
             new_cte_name = self.add_ephemeral_prefix(cte_model.name)
-            rendered_sql = cte_model._pre_injected_sql or cte_model.compiled_sql
+            rendered_sql = cte_model._pre_injected_sql or cte_model.compiled_code
             sql = f" {new_cte_name} as (\n{rendered_sql}\n)"
 
             _add_prepended_cte(prepended_ctes, InjectedCTE(id=cte.id, sql=sql))
 
         injected_sql = self._inject_ctes_into_sql(
-            model.compiled_sql,
+            model.compiled_code,
             prepended_ctes,
         )
-        model._pre_injected_sql = model.compiled_sql
-        model.compiled_sql = injected_sql
+        model._pre_injected_sql = model.compiled_code
+        model.compiled_code = injected_sql
         model.extra_ctes_injected = True
         model.extra_ctes = prepended_ctes
         model.validate(model.to_dict(omit_none=True))
-
         manifest.update_node(model)
 
         return model, prepended_ctes
 
     # creates a compiled_node from the ManifestNode passed in,
     # creates a "context" dictionary for jinja rendering,
-    # and then renders the "compiled_sql" using the node, the
-    # raw_sql and the context.
+    # and then renders the "compiled_code" using the node, the
+    # raw_code and the context.
     def _compile_node(
         self,
         node: ManifestNode,
@@ -362,20 +363,40 @@ class Compiler:
         data.update(
             {
                 "compiled": False,
-                "compiled_sql": None,
+                "compiled_code": None,
                 "extra_ctes_injected": False,
                 "extra_ctes": [],
             }
         )
         compiled_node = _compiled_type_for(node).from_dict(data)
 
-        context = self._create_node_context(compiled_node, manifest, extra_context)
+        if compiled_node.language == ModelLanguage.python:
+            # TODO could we also 'minify' this code at all? just aesthetic, not functional
 
-        compiled_node.compiled_sql = jinja.get_rendered(
-            node.raw_sql,
-            context,
-            node,
-        )
+            # quoating seems like something very specific to sql so far
+            # for all python implementations we are seeing there's no quating.
+            # TODO try to find better way to do this, given that
+            original_quoting = self.config.quoting
+            self.config.quoting = {key: False for key in original_quoting.keys()}
+            context = self._create_node_context(compiled_node, manifest, extra_context)
+
+            postfix = jinja.get_rendered(
+                "{{ py_script_postfix(model) }}",
+                context,
+                node,
+            )
+            # we should NOT jinja render the python model's 'raw code'
+            compiled_node.compiled_code = f"{node.raw_code}\n\n{postfix}"
+            # restore quoting settings in the end since context is lazy evaluated
+            self.config.quoting = original_quoting
+
+        else:
+            context = self._create_node_context(compiled_node, manifest, extra_context)
+            compiled_node.compiled_code = jinja.get_rendered(
+                node.raw_code,
+                context,
+                node,
+            )
 
         compiled_node.relation_name = self._get_relation_name(node)
 
@@ -411,6 +432,8 @@ class Compiler:
             self.link_node(linker, exposure, manifest)
         for metric in manifest.metrics.values():
             self.link_node(linker, metric, manifest)
+        for entity in manifest.entities.values():
+            self.link_node(linker, entity, manifest)
 
         cycle = linker.find_cycles()
 
@@ -487,15 +510,15 @@ class Compiler:
 
         return Graph(linker.graph)
 
-    # writes the "compiled_sql" into the target/compiled directory
+    # writes the "compiled_code" into the target/compiled directory
     def _write_node(self, node: NonSourceCompiledNode) -> ManifestNode:
         if not node.extra_ctes_injected or node.resource_type == NodeType.Snapshot:
             return node
         fire_event(WritingInjectedSQLForNode(unique_id=node.unique_id))
 
-        if node.compiled_sql:
+        if node.compiled_code:
             node.compiled_path = node.write_node(
-                self.config.target_path, "compiled", node.compiled_sql
+                self.config.target_path, "compiled", node.compiled_code
             )
         return node
 

core/dbt/config/profile.py

@@ -23,8 +23,6 @@ from .renderer import ProfileRenderer
 
 DEFAULT_THREADS = 1
 
-DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser("~"), ".dbt")
-
 INVALID_PROFILE_MESSAGE = """
 dbt encountered an error while trying to read your profiles.yml file.
 
@@ -44,7 +42,7 @@ defined in your profiles.yml file. You can find profiles.yml here:
 
 {profiles_file}/profiles.yml
 """.format(
-    profiles_file=DEFAULT_PROFILES_DIR
+    profiles_file=flags.DEFAULT_PROFILES_DIR
 )
 
 

core/dbt/config/project.py

@@ -380,6 +380,8 @@ class PartialProject(RenderComponents):
         snapshots: Dict[str, Any]
         sources: Dict[str, Any]
         tests: Dict[str, Any]
+        metrics: Dict[str, Any]
+        exposures: Dict[str, Any]
         vars_value: VarProvider
 
         dispatch = cfg.dispatch
@@ -388,6 +390,8 @@ class PartialProject(RenderComponents):
         snapshots = cfg.snapshots
         sources = cfg.sources
         tests = cfg.tests
+        metrics = cfg.metrics
+        exposures = cfg.exposures
         if cfg.vars is None:
             vars_dict: Dict[str, Any] = {}
         else:
@@ -441,6 +445,8 @@ class PartialProject(RenderComponents):
             query_comment=query_comment,
             sources=sources,
             tests=tests,
+            metrics=metrics,
+            exposures=exposures,
             vars=vars_value,
             config_version=cfg.config_version,
             unrendered=unrendered,
@@ -543,6 +549,8 @@ class Project:
     snapshots: Dict[str, Any]
     sources: Dict[str, Any]
     tests: Dict[str, Any]
+    metrics: Dict[str, Any]
+    exposures: Dict[str, Any]
     vars: VarProvider
     dbt_version: List[VersionSpecifier]
     packages: Dict[str, Any]
@@ -615,6 +623,8 @@ class Project:
                 "snapshots": self.snapshots,
                 "sources": self.sources,
                 "tests": self.tests,
+                "metrics": self.metrics,
+                "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,

core/dbt/config/renderer.py

@@ -3,13 +3,13 @@ import re
 import os
 
 from dbt.clients.jinja import get_rendered, catch_jinja
+from dbt.constants import SECRET_ENV_PREFIX
 from dbt.context.target import TargetContext
 from dbt.context.secret import SecretContext, SECRET_PLACEHOLDER
 from dbt.context.base import BaseContext
 from dbt.contracts.connection import HasCredentials
 from dbt.exceptions import DbtProjectError, CompilationException, RecursionException
 from dbt.utils import deep_map_render
-from dbt.logger import SECRET_ENV_PREFIX
 
 
 Keypath = Tuple[Union[str, int], ...]

core/dbt/config/runtime.py

@@ -105,6 +105,8 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             query_comment=project.query_comment,
             sources=project.sources,
             tests=project.tests,
+            metrics=project.metrics,
+            exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
             unrendered=project.unrendered,
@@ -274,6 +276,8 @@ 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),
+            "metrics": self._get_config_paths(self.metrics),
+            "exposures": self._get_config_paths(self.exposures),
         }
 
     def get_unused_resource_config_paths(
@@ -477,6 +481,8 @@ class UnsetProfileConfig(RuntimeConfig):
                 "snapshots": self.snapshots,
                 "sources": self.sources,
                 "tests": self.tests,
+                "metrics": self.metrics,
+                "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,
@@ -537,6 +543,8 @@ class UnsetProfileConfig(RuntimeConfig):
             query_comment=project.query_comment,
             sources=project.sources,
             tests=project.tests,
+            metrics=project.metrics,
+            exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
             unrendered=project.unrendered,

core/dbt/constants.py

@@ -0,0 +1,2 @@
+SECRET_ENV_PREFIX = "DBT_ENV_SECRET_"
+DEFAULT_ENV_PLACEHOLDER = "DBT_DEFAULT_PLACEHOLDER"

core/dbt/context/README.md

@@ -2,7 +2,7 @@
 
 Contexts are used for Jinja rendering. They include context methods, executable macros, and various settings that are available in Jinja.
 
-The most common entrypoint to Jinja rendering in dbt is a method named `get_rendered`, which takes two arguments: templated code (string), and a context used to render it (dictionary). 
+The most common entrypoint to Jinja rendering in dbt is a method named `get_rendered`, which takes two arguments: templated code (string), and a context used to render it (dictionary).
 
 The context is the bundle of information that is in "scope" when rendering Jinja-templated code. For instance, imagine a simple Jinja template:
 ```

core/dbt/context/base.py

@@ -6,6 +6,7 @@ from dbt import flags
 from dbt import tracking
 from dbt.clients.jinja import get_rendered
 from dbt.clients.yaml_helper import yaml, safe_load, SafeLoader, Loader, Dumper  # noqa: F401
+from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
 from dbt.contracts.graph.compiled import CompiledResource
 from dbt.exceptions import (
     CompilationException,
@@ -14,7 +15,6 @@ from dbt.exceptions import (
     raise_parsing_error,
     disallow_secret_env_var,
 )
-from dbt.logger import SECRET_ENV_PREFIX
 from dbt.events.functions import fire_event, get_invocation_id
 from dbt.events.types import MacroEventInfo, MacroEventDebug
 from dbt.version import __version__ as dbt_version
@@ -305,7 +305,12 @@ class BaseContext(metaclass=ContextMeta):
             return_value = default
 
         if return_value is not None:
-            self.env_vars[var] = return_value
+            # If the environment variable is set from a default, store a string indicating
+            # that so we can skip partial parsing.  Otherwise the file will be scheduled for
+            # reparsing. If the default changes, the file will have been updated and therefore
+            # will be scheduled for reparsing anyways.
+            self.env_vars[var] = return_value if var in os.environ else DEFAULT_ENV_PLACEHOLDER
+
             return return_value
         else:
             msg = f"Env var required but not provided: '{var}'"

core/dbt/context/configured.py

@@ -1,8 +1,8 @@
 import os
 from typing import Any, Dict, Optional
 
+from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
 from dbt.contracts.connection import AdapterRequiredConfig
-from dbt.logger import SECRET_ENV_PREFIX
 from dbt.node_types import NodeType
 from dbt.utils import MultiDict
 
@@ -94,7 +94,14 @@ class SchemaYamlContext(ConfiguredContext):
 
         if return_value is not None:
             if self.schema_yaml_vars:
-                self.schema_yaml_vars.env_vars[var] = return_value
+                # If the environment variable is set from a default, store a string indicating
+                # that so we can skip partial parsing.  Otherwise the file will be scheduled for
+                # reparsing. If the default changes, the file will have been updated and therefore
+                # will be scheduled for reparsing anyways.
+                self.schema_yaml_vars.env_vars[var] = (
+                    return_value if var in os.environ else DEFAULT_ENV_PLACEHOLDER
+                )
+
             return return_value
         else:
             msg = f"Env var required but not provided: '{var}'"

core/dbt/context/context_config.py

@@ -43,9 +43,12 @@ class UnrenderedConfig(ConfigSource):
             model_configs = unrendered.get("sources")
         elif resource_type == NodeType.Test:
             model_configs = unrendered.get("tests")
+        elif resource_type == NodeType.Metric:
+            model_configs = unrendered.get("metrics")
+        elif resource_type == NodeType.Exposure:
+            model_configs = unrendered.get("exposures")
         else:
             model_configs = unrendered.get("models")
-
         if model_configs is None:
             return {}
         else:
@@ -65,6 +68,10 @@ class RenderedConfig(ConfigSource):
             model_configs = self.project.sources
         elif resource_type == NodeType.Test:
             model_configs = self.project.tests
+        elif resource_type == NodeType.Metric:
+            model_configs = self.project.metrics
+        elif resource_type == NodeType.Exposure:
+            model_configs = self.project.exposures
         else:
             model_configs = self.project.models
         return model_configs

core/dbt/context/macro_resolver.py

@@ -109,9 +109,15 @@ class MacroResolver:
 
     def get_macro(self, local_package, macro_name):
         local_package_macros = {}
+        # If the macro is explicitly prefixed with an internal namespace
+        # (e.g. 'dbt.some_macro'), look there first
+        if local_package in self.internal_package_names:
+            local_package_macros = self.internal_packages[local_package]
+        # If the macro is explicitly prefixed with a different package name
+        # (e.g. 'dbt_utils.some_macro'), look there first
         if local_package not in self.internal_package_names and local_package in self.packages:
             local_package_macros = self.packages[local_package]
-        # First: search the local packages for this macro
+        # First: search the specified package for this macro
         if macro_name in local_package_macros:
             return local_package_macros[macro_name]
         # Now look up in the standard search order

core/dbt/context/manifest.py

@@ -4,6 +4,7 @@ from dbt.clients.jinja import MacroStack
 from dbt.contracts.connection import AdapterRequiredConfig
 from dbt.contracts.graph.manifest import Manifest
 from dbt.context.macro_resolver import TestMacroNamespace
+from .base import contextproperty
 
 
 from .configured import ConfiguredContext
@@ -66,6 +67,10 @@ class ManifestContext(ConfiguredContext):
             dct.update(self.namespace)
         return dct
 
+    @contextproperty
+    def context_macro_stack(self):
+        return self.macro_stack
+
 
 class QueryHeaderContext(ManifestContext):
     def __init__(self, config: AdapterRequiredConfig, manifest: Manifest) -> None:

core/dbt/context/providers.py

@@ -22,7 +22,7 @@ from dbt.config import RuntimeConfig, Project
 from .base import contextmember, contextproperty, Var
 from .configured import FQNLookup
 from .context_config import ContextConfig
-from dbt.logger import SECRET_ENV_PREFIX
+from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
 from dbt.context.macro_resolver import MacroResolver, TestMacroNamespace
 from .macros import MacroNamespaceBuilder, MacroNamespace
 from .manifest import ManifestContext
@@ -41,6 +41,7 @@ from dbt.contracts.graph.parsed import (
     ParsedSourceDefinition,
 )
 from dbt.contracts.graph.metrics import MetricReference, ResolvedMetricReference
+from dbt.contracts.util import get_metadata_env
 from dbt.exceptions import (
     CompilationException,
     ParsingException,
@@ -61,9 +62,9 @@ from dbt.exceptions import (
     disallow_secret_env_var,
 )
 from dbt.config import IsFQNResource
-from dbt.node_types import NodeType
+from dbt.node_types import NodeType, ModelLanguage
 
-from dbt.utils import merge, AttrDict, MultiDict
+from dbt.utils import merge, AttrDict, MultiDict, args_to_dict
 
 from dbt import selected_resources
 
@@ -710,6 +711,14 @@ class ProviderContext(ManifestContext):
             self.model,
         )
 
+    @contextproperty
+    def dbt_metadata_envs(self) -> Dict[str, str]:
+        return get_metadata_env()
+
+    @contextproperty
+    def invocation_args_dict(self):
+        return args_to_dict(self.config.args)
+
     @contextproperty
     def _sql_results(self) -> Dict[str, AttrDict]:
         return self.sql_results
@@ -1157,7 +1166,12 @@ class ProviderContext(ManifestContext):
 
     @contextproperty("model")
     def ctx_model(self) -> Dict[str, Any]:
-        return self.model.to_dict(omit_none=True)
+        ret = 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
 
     @contextproperty
     def pre_hooks(self) -> Optional[List[Dict[str, Any]]]:
@@ -1206,7 +1220,14 @@ class ProviderContext(ManifestContext):
             # Save the env_var value in the manifest and the var name in the source_file.
             # If this is compiling, do not save because it's irrelevant to parsing.
             if self.model and not hasattr(self.model, "compiled"):
-                self.manifest.env_vars[var] = return_value
+                # If the environment variable is set from a default, store a string indicating
+                # that so we can skip partial parsing.  Otherwise the file will be scheduled for
+                # reparsing. If the default changes, the file will have been updated and therefore
+                # will be scheduled for reparsing anyways.
+                self.manifest.env_vars[var] = (
+                    return_value if var in os.environ else DEFAULT_ENV_PLACEHOLDER
+                )
+
                 # hooks come from dbt_project.yml which doesn't have a real file_id
                 if self.model.file_id in self.manifest.files:
                     source_file = self.manifest.files[self.model.file_id]
@@ -1228,6 +1249,19 @@ class ProviderContext(ManifestContext):
         """
         return selected_resources.SELECTED_RESOURCES
 
+    @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 (
+            self.context_macro_stack.depth == 2
+            and self.context_macro_stack.call_stack[1] == "macro.dbt.statement"
+            and "materialization" in self.context_macro_stack.call_stack[0]
+        ):
+            raise RuntimeException(
+                f"submit_python_job is not intended to be called here, at model {parsed_model['alias']}, with macro call_stack {self.context_macro_stack.call_stack}."
+            )
+        return self.adapter.submit_python_job(parsed_model, compiled_code)
+
 
 class MacroContext(ProviderContext):
     """Internally, macros can be executed like nodes, with some restrictions:
@@ -1278,9 +1312,20 @@ class ModelContext(ProviderContext):
 
     @contextproperty
     def sql(self) -> Optional[str]:
+        # only doing this in sql model for backward compatible
+        if (
+            getattr(self.model, "extra_ctes_injected", None)
+            and self.model.language == ModelLanguage.sql  # type: ignore[union-attr]
+        ):
+            # TODO CT-211
+            return self.model.compiled_code  # type: ignore[union-attr]
+        return None
+
+    @contextproperty
+    def compiled_code(self) -> Optional[str]:
         if getattr(self.model, "extra_ctes_injected", None):
             # TODO CT-211
-            return self.model.compiled_sql  # type: ignore[union-attr]
+            return self.model.compiled_code  # type: ignore[union-attr]
         return None
 
     @contextproperty
@@ -1519,7 +1564,13 @@ class TestContext(ProviderContext):
         if return_value is not None:
             # Save the env_var value in the manifest and the var name in the source_file
             if self.model:
-                self.manifest.env_vars[var] = return_value
+                # If the environment variable is set from a default, store a string indicating
+                # that so we can skip partial parsing.  Otherwise the file will be scheduled for
+                # reparsing. If the default changes, the file will have been updated and therefore
+                # will be scheduled for reparsing anyways.
+                self.manifest.env_vars[var] = (
+                    return_value if var in os.environ else DEFAULT_ENV_PLACEHOLDER
+                )
                 # the "model" should only be test nodes, but just in case, check
                 # TODO CT-211
                 if self.model.resource_type == NodeType.Test and self.model.file_key_name:  # type: ignore[union-attr] # noqa

core/dbt/context/secret.py

@@ -3,8 +3,8 @@ from typing import Any, Dict, Optional
 
 from .base import BaseContext, contextmember
 
+from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
 from dbt.exceptions import raise_parsing_error
-from dbt.logger import SECRET_ENV_PREFIX
 
 
 SECRET_PLACEHOLDER = "$$$DBT_SECRET_START$$${}$$$DBT_SECRET_END$$$"
@@ -43,7 +43,11 @@ class SecretContext(BaseContext):
             # if it's a 'secret' env var, we shouldn't even get here
             # but just to be safe — don't save secrets
             if not var.startswith(SECRET_ENV_PREFIX):
-                self.env_vars[var] = return_value
+                # If the environment variable is set from a default, store a string indicating
+                # that so we can skip partial parsing.  Otherwise the file will be scheduled for
+                # reparsing. If the default changes, the file will have been updated and therefore
+                # will be scheduled for reparsing anyways.
+                self.env_vars[var] = return_value if var in os.environ else DEFAULT_ENV_PLACEHOLDER
             return return_value
         else:
             msg = f"Env var required but not provided: '{var}'"

core/dbt/contracts/files.py

@@ -114,25 +114,34 @@ class FileHash(dbtClassMixin):
 
 @dataclass
 class RemoteFile(dbtClassMixin):
+    def __init__(self, language) -> None:
+        if language == "sql":
+            self.path_end = ".sql"
+        elif language == "python":
+            self.path_end = ".py"
+        else:
+            raise RuntimeError(f"Invalid language for remote File {language}")
+        self.path = f"from remote system{self.path_end}"
+
     @property
     def searched_path(self) -> str:
-        return "from remote system"
+        return self.path
 
     @property
     def relative_path(self) -> str:
-        return "from remote system"
+        return self.path
 
     @property
     def absolute_path(self) -> str:
-        return "from remote system"
+        return self.path
 
     @property
     def original_file_path(self):
-        return "from remote system"
+        return self.path
 
     @property
     def modification_time(self):
-        return "from remote system"
+        return self.path
 
 
 @dataclass
@@ -202,9 +211,9 @@ class SourceFile(BaseSourceFile):
     # TODO: do this a different way. This remote file kludge isn't going
     # to work long term
     @classmethod
-    def remote(cls, contents: str, project_name: str) -> "SourceFile":
+    def remote(cls, contents: str, project_name: str, language: str) -> "SourceFile":
         self = cls(
-            path=RemoteFile(),
+            path=RemoteFile(language),
             checksum=FileHash.from_contents(contents),
             project_name=project_name,
             contents=contents,
@@ -220,6 +229,7 @@ class SchemaSourceFile(BaseSourceFile):
     sources: List[str] = field(default_factory=list)
     exposures: List[str] = field(default_factory=list)
     metrics: List[str] = field(default_factory=list)
+    entities: List[str] = field(default_factory=list)
     # node patches contain models, seeds, snapshots, analyses
     ndp: List[str] = field(default_factory=list)
     # any macro patches in this file by macro unique_id.
@@ -268,11 +278,13 @@ class SchemaSourceFile(BaseSourceFile):
             self.tests[key][name] = []
         self.tests[key][name].append(node_unique_id)
 
+    # this is only used in unit tests
     def remove_tests(self, yaml_key, name):
         if yaml_key in self.tests:
             if name in self.tests[yaml_key]:
                 del self.tests[yaml_key][name]
 
+    # this is only used in tests (unit + functional)
     def get_tests(self, yaml_key, name):
         if yaml_key in self.tests:
             if name in self.tests[yaml_key]:

core/dbt/contracts/graph/compiled.py

@@ -7,6 +7,7 @@ from dbt.contracts.graph.parsed import (
     ParsedModelNode,
     ParsedExposure,
     ParsedMetric,
+    ParsedEntity,
     ParsedResource,
     ParsedRPCNode,
     ParsedSqlNode,
@@ -41,7 +42,7 @@ class CompiledNodeMixin(dbtClassMixin):
 
 @dataclass
 class CompiledNode(ParsedNode, CompiledNodeMixin):
-    compiled_sql: Optional[str] = None
+    compiled_code: Optional[str] = None
     extra_ctes_injected: bool = False
     extra_ctes: List[InjectedCTE] = field(default_factory=list)
     relation_name: Optional[str] = None
@@ -232,4 +233,5 @@ GraphMemberNode = Union[
     CompileResultNode,
     ParsedExposure,
     ParsedMetric,
+    ParsedEntity,
 ]

core/dbt/contracts/graph/manifest.py

@@ -1,7 +1,7 @@
 import enum
 from dataclasses import dataclass, field
 from itertools import chain, islice
-from mashumaro import DataClassMessagePackMixin
+from mashumaro.mixins.msgpack import DataClassMessagePackMixin
 from multiprocessing.synchronize import Lock
 from typing import (
     Dict,
@@ -33,8 +33,10 @@ from dbt.contracts.graph.parsed import (
     ParsedMacro,
     ParsedDocumentation,
     ParsedSourceDefinition,
+    ParsedGenericTestNode,
     ParsedExposure,
     ParsedMetric,
+    ParsedEntity,
     HasUniqueID,
     UnpatchedSourceDefinition,
     ManifestNodes,
@@ -216,7 +218,40 @@ class MetricLookup(dbtClassMixin):
         return manifest.metrics[unique_id]
 
 
-# This handles both models/seeds/snapshots and sources
+class EntityLookup(dbtClassMixin):
+    def __init__(self, manifest: "Manifest"):
+        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_entity(self, entity: ParsedEntity):
+        if entity.search_name not in self.storage:
+            self.storage[entity.search_name] = {}
+
+        self.storage[entity.search_name][entity.package_name] = entity.unique_id
+
+    def populate(self, manifest):
+        for entity in manifest.entities.values():
+            if hasattr(entity, "name"):
+                self.add_entity(entity)
+
+    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> ParsedEntity:
+        if unique_id not in manifest.entities:
+            raise dbt.exceptions.InternalException(
+                f"Metric {unique_id} found in cache but not found in manifest"
+            )
+        return manifest.entities[unique_id]
+
+
+# This handles both models/seeds/snapshots and sources/metrics/exposures
 class DisabledLookup(dbtClassMixin):
     def __init__(self, manifest: "Manifest"):
         self.storage: Dict[str, Dict[PackageName, List[Any]]] = {}
@@ -464,7 +499,8 @@ class Disabled(Generic[D]):
     target: D
 
 
-MaybeMetricNode = Optional[ParsedMetric]
+MaybeMetricNode = Optional[Union[ParsedMetric, Disabled[ParsedMetric]]]
+MaybeEntityNode = Optional[Union[ParsedEntity, Disabled[ParsedEntity]]]
 
 
 MaybeDocumentation = Optional[ParsedDocumentation]
@@ -610,13 +646,14 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     docs: MutableMapping[str, ParsedDocumentation] = field(default_factory=dict)
     exposures: MutableMapping[str, ParsedExposure] = field(default_factory=dict)
     metrics: MutableMapping[str, ParsedMetric] = field(default_factory=dict)
+    entities: MutableMapping[str, ParsedEntity] = field(default_factory=dict)
     selectors: MutableMapping[str, Any] = field(default_factory=dict)
     files: MutableMapping[str, AnySourceFile] = field(default_factory=dict)
     metadata: ManifestMetadata = field(default_factory=ManifestMetadata)
     flat_graph: Dict[str, Any] = field(default_factory=dict)
     state_check: ManifestStateCheck = field(default_factory=ManifestStateCheck)
     source_patches: MutableMapping[SourceKey, SourcePatch] = field(default_factory=dict)
-    disabled: MutableMapping[str, List[CompileResultNode]] = field(default_factory=dict)
+    disabled: MutableMapping[str, List[GraphMemberNode]] = field(default_factory=dict)
     env_vars: MutableMapping[str, str] = field(default_factory=dict)
 
     _doc_lookup: Optional[DocLookup] = field(
@@ -631,6 +668,9 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     _metric_lookup: Optional[MetricLookup] = field(
         default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
+    _entity_lookup: Optional[EntityLookup] = field(
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
+    )
     _disabled_lookup: Optional[DisabledLookup] = field(
         default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
@@ -681,6 +721,9 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     def update_metric(self, new_metric: ParsedMetric):
         _update_into(self.metrics, new_metric)
 
+    def update_entity(self, new_entity: ParsedEntity):
+        _update_into(self.entities, new_entity)
+
     def update_node(self, new_node: ManifestNode):
         _update_into(self.nodes, new_node)
 
@@ -698,6 +741,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             "metrics": {k: v.to_dict(omit_none=False) for k, v in self.metrics.items()},
             "nodes": {k: v.to_dict(omit_none=False) for k, v in self.nodes.items()},
             "sources": {k: v.to_dict(omit_none=False) for k, v in self.sources.items()},
+            "entities": {k: v.to_dict(omit_none=False) for k, v in self.entities.items()},
         }
 
     def build_disabled_by_file_id(self):
@@ -758,6 +802,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self.nodes.values(),
             self.sources.values(),
             self.metrics.values(),
+            self.entities.values(),
         )
         for resource in all_resources:
             resource_type_plural = resource.resource_type.pluralize()
@@ -786,6 +831,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             docs={k: _deepcopy(v) for k, v in self.docs.items()},
             exposures={k: _deepcopy(v) for k, v in self.exposures.items()},
             metrics={k: _deepcopy(v) for k, v in self.metrics.items()},
+            entities={k: _deepcopy(v) for k, v in self.entities.items()},
             selectors={k: _deepcopy(v) for k, v in self.selectors.items()},
             metadata=self.metadata,
             disabled={k: _deepcopy(v) for k, v in self.disabled.items()},
@@ -800,6 +846,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
                 self.sources.values(),
                 self.exposures.values(),
                 self.metrics.values(),
+                self.entities.values(),
             )
         )
         forward_edges, backward_edges = build_node_edges(edge_members)
@@ -825,6 +872,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             docs=self.docs,
             exposures=self.exposures,
             metrics=self.metrics,
+            entities=self.entities,
             selectors=self.selectors,
             metadata=self.metadata,
             disabled=self.disabled,
@@ -846,6 +894,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             return self.exposures[unique_id]
         elif unique_id in self.metrics:
             return self.metrics[unique_id]
+        elif unique_id in self.entities:
+            return self.entities[unique_id]
         else:
             # something terrible has happened
             raise dbt.exceptions.InternalException(
@@ -882,6 +932,12 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self._metric_lookup = MetricLookup(self)
         return self._metric_lookup
 
+    @property
+    def entity_lookup(self) -> EntityLookup:
+        if self._entity_lookup is None:
+            self._entity_lookup = EntityLookup(self)
+        return self._entity_lookup
+
     def rebuild_ref_lookup(self):
         self._ref_lookup = RefableLookup(self)
 
@@ -964,13 +1020,47 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         current_project: str,
         node_package: str,
     ) -> MaybeMetricNode:
+
         metric: Optional[ParsedMetric] = None
+        disabled: Optional[List[ParsedMetric]] = None
 
         candidates = _search_packages(current_project, node_package, target_metric_package)
         for pkg in candidates:
             metric = self.metric_lookup.find(target_metric_name, pkg, self)
-            if metric is not None:
+
+            if metric is not None and metric.config.enabled:
                 return metric
+
+            # it's possible that the node is disabled
+            if disabled is None:
+                disabled = self.disabled_lookup.find(f"{target_metric_name}", pkg)
+        if disabled:
+            return Disabled(disabled[0])
+        return None
+
+    def resolve_entity(
+        self,
+        target_entity_name: str,
+        target_entity_package: Optional[str],
+        current_project: str,
+        node_package: str,
+    ) -> MaybeEntityNode:
+
+        entity: Optional[ParsedEntity] = None
+        disabled: Optional[List[ParsedEntity]] = None
+
+        candidates = _search_packages(current_project, node_package, target_entity_package)
+        for pkg in candidates:
+            entity = self.entity_lookup.find(target_entity_name, pkg, self)
+
+            if entity is not None and entity.config.enabled:
+                return entity
+
+            # it's possible that the node is disabled
+            if disabled is None:
+                disabled = self.disabled_lookup.find(f"{target_entity_name}", pkg)
+        if disabled:
+            return Disabled(disabled[0])
         return None
 
     # Called by DocsRuntimeContext.doc
@@ -1018,6 +1108,10 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
                 merged.add(unique_id)
                 self.nodes[unique_id] = node.replace(deferred=True)
 
+        # Rebuild the flat_graph, which powers the 'graph' context variable,
+        # now that we've deferred some nodes
+        self.build_flat_graph()
+
         # log up to 5 items
         sample = list(islice(merged, 5))
         fire_event(MergedFromState(nbr_merged=len(merged), sample=sample))
@@ -1074,8 +1168,13 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     def add_node(self, source_file: AnySourceFile, node: ManifestNodes, test_from=None):
         self.add_node_nofile(node)
         if isinstance(source_file, SchemaSourceFile):
-            assert test_from
-            source_file.add_test(node.unique_id, test_from)
+            if isinstance(node, ParsedGenericTestNode):
+                assert test_from
+                source_file.add_test(node.unique_id, test_from)
+            if isinstance(node, ParsedMetric):
+                source_file.metrics.append(node.unique_id)
+            if isinstance(node, ParsedExposure):
+                source_file.exposures.append(node.unique_id)
         else:
             source_file.nodes.append(node.unique_id)
 
@@ -1089,7 +1188,12 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         self.metrics[metric.unique_id] = metric
         source_file.metrics.append(metric.unique_id)
 
-    def add_disabled_nofile(self, node: CompileResultNode):
+    def add_entity(self, source_file: SchemaSourceFile, entity: ParsedEntity):
+        _check_duplicates(entity, self.entities)
+        self.entities[entity.unique_id] = entity
+        source_file.entities.append(entity.unique_id)
+
+    def add_disabled_nofile(self, node: GraphMemberNode):
         # There can be multiple disabled nodes for the same unique_id
         if node.unique_id in self.disabled:
             self.disabled[node.unique_id].append(node)
@@ -1099,8 +1203,15 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     def add_disabled(self, source_file: AnySourceFile, node: CompileResultNode, test_from=None):
         self.add_disabled_nofile(node)
         if isinstance(source_file, SchemaSourceFile):
-            assert test_from
-            source_file.add_test(node.unique_id, test_from)
+            if isinstance(node, ParsedGenericTestNode):
+                assert test_from
+                source_file.add_test(node.unique_id, test_from)
+            if isinstance(node, ParsedMetric):
+                source_file.metrics.append(node.unique_id)
+            if isinstance(node, ParsedEntity):
+                source_file.entities.append(node.unique_id)
+            if isinstance(node, ParsedExposure):
+                source_file.exposures.append(node.unique_id)
         else:
             source_file.nodes.append(node.unique_id)
 
@@ -1126,6 +1237,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self.docs,
             self.exposures,
             self.metrics,
+            self.entities,
             self.selectors,
             self.files,
             self.metadata,
@@ -1157,7 +1269,7 @@ AnyManifest = Union[Manifest, MacroManifest]
 
 
 @dataclass
-@schema_version("manifest", 6)
+@schema_version("manifest", 7)
 class WritableManifest(ArtifactMixin):
     nodes: Mapping[UniqueID, ManifestNode] = field(
         metadata=dict(description=("The nodes defined in the dbt project and its dependencies"))
@@ -1179,6 +1291,9 @@ class WritableManifest(ArtifactMixin):
     metrics: Mapping[UniqueID, ParsedMetric] = field(
         metadata=dict(description=("The metrics defined in the dbt project and its dependencies"))
     )
+    entities: Mapping[UniqueID, ParsedEntity] = field(
+        metadata=dict(description=("The entities defined in the dbt project and its dependencies"))
+    )
     selectors: Mapping[UniqueID, Any] = field(
         metadata=dict(description=("The selectors defined in selectors.yml"))
     )
@@ -1203,7 +1318,7 @@ class WritableManifest(ArtifactMixin):
 
     @classmethod
     def compatible_previous_versions(self):
-        return [("manifest", 4), ("manifest", 5)]
+        return [("manifest", 4), ("manifest", 5), ("manifest", 6)]
 
     def __post_serialize__(self, dct):
         for unique_id, node in dct["nodes"].items():

core/dbt/contracts/graph/metrics.py

@@ -38,33 +38,56 @@ class ResolvedMetricReference(MetricReference):
             if node and node.resource_type == NodeType.Metric:
                 yield from cls.parent_metrics(node, manifest)
 
-    def parent_models(self):
+    @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)
+
+    @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
+
+        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)
+
+    def full_metric_dependency(self):
+        to_return = list(set(self.parent_metrics_names(self.node, self.manifest)))
+        return to_return
+
+    def base_metric_dependency(self):
         in_scope_metrics = list(self.parent_metrics(self.node, self.manifest))
 
-        to_return = {
-            "base": [],
-            "derived": [],
-        }
+        to_return = []
         for metric in in_scope_metrics:
-            if metric.type == "expression":
-                to_return["derived"].append(
-                    {"metric_source": None, "metric": metric, "is_derived": True}
-                )
-            else:
-                for node_unique_id in metric.depends_on.nodes:
-                    node = self.manifest.nodes.get(node_unique_id)
-                    if node and node.resource_type in NodeType.refable():
-                        to_return["base"].append(
-                            {
-                                "metric_relation_node": node,
-                                "metric_relation": self.Relation.create(
-                                    database=node.database,
-                                    schema=node.schema,
-                                    identifier=node.alias,
-                                ),
-                                "metric": metric,
-                                "is_derived": False,
-                            }
-                        )
+            if metric.calculation_method != "derived" and metric.name not in to_return:
+                to_return.append(metric.name)
+
+        return to_return
+
+    def derived_metric_dependency(self):
+        in_scope_metrics = list(self.parent_metrics(self.node, self.manifest))
+
+        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 to_return
+
+    def derived_metric_dependency_depth(self):
+        metric_depth_count = 1
+        to_return = list(self.reverse_dag_parsing(self.node, self.manifest, metric_depth_count))
 
         return to_return

core/dbt/contracts/graph/model_config.py

@@ -7,7 +7,8 @@ from dbt.dataclass_schema import (
     ValidationError,
     register_pattern,
 )
-from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed
+from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed, Docs
+from dbt.contracts.graph.utils import validate_color
 from dbt.exceptions import InternalException, CompilationException
 from dbt.contracts.util import Replaceable, list_str
 from dbt import hooks
@@ -285,7 +286,7 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable):
     # 'meta' moved here from node
     mergebehavior = {
         "append": ["pre-hook", "pre_hook", "post-hook", "post_hook", "tags"],
-        "update": ["quoting", "column_types", "meta"],
+        "update": ["quoting", "column_types", "meta", "docs"],
         "dict_key_append": ["grants"],
     }
 
@@ -362,6 +363,21 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable):
         return self.from_dict(dct)
 
 
+@dataclass
+class MetricConfig(BaseConfig):
+    enabled: bool = True
+
+
+@dataclass
+class EntityConfig(BaseConfig):
+    enabled: bool = True
+
+
+@dataclass
+class ExposureConfig(BaseConfig):
+    enabled: bool = True
+
+
 @dataclass
 class SourceConfig(BaseConfig):
     enabled: bool = True
@@ -433,6 +449,7 @@ class NodeConfig(NodeAndTestConfig):
     # Note: if any new fields are added with MergeBehavior, also update the
     # 'mergebehavior' dictionary
     materialized: str = "view"
+    incremental_strategy: Optional[str] = None
     persist_docs: Dict[str, Any] = field(default_factory=dict)
     post_hook: List[Hook] = field(
         default_factory=list,
@@ -460,6 +477,24 @@ class NodeConfig(NodeAndTestConfig):
     grants: Dict[str, Any] = field(
         default_factory=dict, metadata=MergeBehavior.DictKeyAppend.meta()
     )
+    packages: List[str] = field(
+        default_factory=list,
+        metadata=MergeBehavior.Append.meta(),
+    )
+    docs: Docs = field(
+        default_factory=Docs,
+        metadata=MergeBehavior.Update.meta(),
+    )
+
+    # we validate that node_color has a suitable value to prevent dbt-docs from crashing
+    def __post_init__(self):
+        if self.docs.node_color:
+            node_color = self.docs.node_color
+            if not validate_color(node_color):
+                raise ValidationError(
+                    f"Invalid color name for docs.node_color: {node_color}. "
+                    "It is neither a valid HTML color name nor a valid HEX code."
+                )
 
     @classmethod
     def __pre_deserialize__(cls, data):
@@ -593,6 +628,9 @@ class SnapshotConfig(EmptySnapshotConfig):
 
 
 RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = {
+    NodeType.Metric: MetricConfig,
+    NodeType.Entity: EntityConfig,
+    NodeType.Exposure: ExposureConfig,
     NodeType.Source: SourceConfig,
     NodeType.Seed: SeedConfig,
     NodeType.Test: TestConfig,

core/dbt/contracts/graph/parsed.py

@@ -37,11 +37,14 @@ from dbt.contracts.graph.unparsed import (
     ExposureType,
     MaturityType,
     MetricFilter,
+    MetricTime,
+    UnparsedEntity,
+    EntityRelationship,
 )
 from dbt.contracts.util import Replaceable, AdditionalPropertiesMixin
 from dbt.exceptions import warn_or_error
 from dbt import flags
-from dbt.node_types import NodeType
+from dbt.node_types import ModelLanguage, NodeType
 
 
 from .model_config import (
@@ -49,8 +52,11 @@ from .model_config import (
     SeedConfig,
     TestConfig,
     SourceConfig,
+    MetricConfig,
+    ExposureConfig,
     EmptySnapshotConfig,
     SnapshotConfig,
+    EntityConfig,
 )
 
 
@@ -61,6 +67,8 @@ class ColumnInfo(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable
     meta: Dict[str, Any] = field(default_factory=dict)
     data_type: Optional[str] = None
     quote: Optional[bool] = None
+    is_entity_dimension: Optional[bool] = False
+    is_primary_key: Optional[bool] = False
     tags: List[str] = field(default_factory=list)
     _extra: Dict[str, Any] = field(default_factory=dict)
 
@@ -157,7 +165,7 @@ class ParsedNodeMixins(dbtClassMixin):
         self.created_at = time.time()
         self.description = patch.description
         self.columns = patch.columns
-        self.docs = patch.docs
+        self.is_entity = patch.is_entity
 
     def get_materialization(self):
         return self.config.materialized
@@ -174,6 +182,17 @@ class ParsedNodeMandatory(UnparsedNode, HasUniqueID, HasFqn, HasRelationMetadata
         return self.alias
 
 
+@dataclass
+class ParsedEntityMandatory(UnparsedEntity, HasUniqueID, HasFqn, Replaceable):
+    alias: str
+    checksum: FileHash
+    config: EntityConfig = field(default_factory=EntityConfig)
+
+    @property
+    def identifier(self):
+        return self.alias
+
+
 @dataclass
 class NodeInfoMixin:
     _event_status: Dict[str, Any] = field(default_factory=dict)
@@ -208,6 +227,7 @@ class ParsedNodeDefaults(NodeInfoMixin, ParsedNodeMandatory):
     compiled_path: Optional[str] = None
     build_path: Optional[str] = None
     deferred: bool = False
+    is_entity: Optional[bool] = False
     unrendered_config: Dict[str, Any] = field(default_factory=dict)
     created_at: float = field(default_factory=lambda: time.time())
     config_call_dict: Dict[str, Any] = field(default_factory=dict)
@@ -225,6 +245,73 @@ class ParsedNodeDefaults(NodeInfoMixin, ParsedNodeMandatory):
         return full_path
 
 
+class ParsedEntityMixins(dbtClassMixin):
+    resource_type: NodeType
+    depends_on: DependsOn
+    config: EntityConfig
+
+    @property
+    def is_refable(self):
+        return self.resource_type in NodeType.refable()
+
+    # will this node map to an object in the database?
+
+    @property
+    def depends_on_nodes(self):
+        return self.depends_on.nodes
+
+    def patch(self, patch: "ParsedEntityPatch"):
+        """Given a ParsedEntityPatch, add the new information to the node."""
+        # explicitly pick out the parts to update so we don't inadvertently
+        # step on the model name or anything
+        # Note: config should already be updated
+        self.patch_path: Optional[str] = patch.file_id
+        # update created_at so process_docs will run in partial parsing
+        self.created_at = time.time()
+        self.description = patch.description
+        self.columns = patch.columns
+        self.is_entity = patch.is_entity
+        self.relationships = patch.relationships
+
+    def get_materialization(self):
+        return self.config.materialized
+
+
+@dataclass
+class EntityInfoMixin:
+    @property
+    def entity_info(self):
+        entity_info = {
+            "entity_path": getattr(self, "path", None),
+            "entity_name": getattr(self, "name", None),
+            "unique_id": getattr(self, "unique_id", None),
+            "resource_type": str(getattr(self, "resource_type", "")),
+        }
+        return entity_info
+
+
+@dataclass
+class ParsedEntityDefaults(EntityInfoMixin, ParsedEntityMandatory):
+    tags: List[str] = field(default_factory=list)
+    refs: List[List[str]] = field(default_factory=list)
+    sources: List[List[str]] = field(default_factory=list)
+    metrics: List[List[str]] = field(default_factory=list)
+    depends_on: DependsOn = field(default_factory=DependsOn)
+    description: str = field(default="")
+    columns: Dict[str, ColumnInfo] = field(default_factory=dict)
+    meta: Dict[str, Any] = field(default_factory=dict)
+    docs: Docs = field(default_factory=Docs)
+    patch_path: Optional[str] = None
+    compiled_path: Optional[str] = None
+    build_path: Optional[str] = None
+    deferred: bool = False
+    is_entity: Optional[bool] = True
+    relationships: Optional[List[EntityRelationship]] = None
+    unrendered_config: Dict[str, Any] = field(default_factory=dict)
+    created_at: float = field(default_factory=lambda: time.time())
+    config_call_dict: Dict[str, Any] = field(default_factory=dict)
+
+
 T = TypeVar("T", bound="ParsedNode")
 
 
@@ -234,6 +321,7 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
         return self.to_dict()
 
     def __post_serialize__(self, dct):
+        dct = super().__post_serialize__(dct)
         if "_event_status" in dct:
             del dct["_event_status"]
         return dct
@@ -281,7 +369,7 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
         return False
 
     def same_body(self: T, other: T) -> bool:
-        return self.raw_sql == other.raw_sql
+        return self.raw_code == other.raw_code
 
     def same_persisted_description(self: T, other: T) -> bool:
         # the check on configs will handle the case where we have different
@@ -494,6 +582,12 @@ class ParsedPatch(HasYamlMetadata, Replaceable):
 @dataclass
 class ParsedNodePatch(ParsedPatch):
     columns: Dict[str, ColumnInfo]
+    is_entity: Optional[bool]
+
+
+@dataclass
+class ParsedEntityPatch(ParsedNodePatch):
+    relationships: Optional[List[EntityRelationship]]
 
 
 @dataclass
@@ -516,6 +610,7 @@ class ParsedMacro(UnparsedBaseNode, HasUniqueID):
     patch_path: Optional[str] = None
     arguments: List[MacroArgument] = field(default_factory=list)
     created_at: float = field(default_factory=lambda: time.time())
+    supported_languages: Optional[List[ModelLanguage]] = None
 
     def patch(self, patch: ParsedMacroPatch):
         self.patch_path: Optional[str] = patch.file_id
@@ -741,9 +836,12 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
     owner: ExposureOwner
     resource_type: NodeType = NodeType.Exposure
     description: str = ""
+    label: Optional[str] = None
     maturity: Optional[MaturityType] = None
     meta: Dict[str, Any] = field(default_factory=dict)
     tags: List[str] = field(default_factory=list)
+    config: ExposureConfig = field(default_factory=ExposureConfig)
+    unrendered_config: Dict[str, Any] = field(default_factory=dict)
     url: Optional[str] = None
     depends_on: DependsOn = field(default_factory=DependsOn)
     refs: List[List[str]] = field(default_factory=list)
@@ -764,6 +862,9 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
     def same_description(self, old: "ParsedExposure") -> bool:
         return self.description == old.description
 
+    def same_label(self, old: "ParsedExposure") -> bool:
+        return self.label == old.label
+
     def same_maturity(self, old: "ParsedExposure") -> bool:
         return self.maturity == old.maturity
 
@@ -776,6 +877,12 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
     def same_url(self, old: "ParsedExposure") -> bool:
         return self.url == old.url
 
+    def same_config(self, old: "ParsedExposure") -> bool:
+        return self.config.same_contents(
+            self.unrendered_config,
+            old.unrendered_config,
+        )
+
     def same_contents(self, old: Optional["ParsedExposure"]) -> bool:
         # existing when it didn't before is a change!
         # metadata/tags changes are not "changes"
@@ -789,7 +896,9 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
             and self.same_maturity(old)
             and self.same_url(old)
             and self.same_description(old)
+            and self.same_label(old)
             and self.same_depends_on(old)
+            and self.same_config(old)
             and True
         )
 
@@ -805,17 +914,20 @@ class ParsedMetric(UnparsedBaseNode, HasUniqueID, HasFqn):
     name: str
     description: str
     label: str
-    type: str
-    sql: str
-    timestamp: Optional[str]
+    calculation_method: str
+    timestamp: str
+    expression: str
     filters: List[MetricFilter]
     time_grains: List[str]
     dimensions: List[str]
+    window: Optional[MetricTime] = None
     model: Optional[str] = None
     model_unique_id: Optional[str] = None
     resource_type: NodeType = NodeType.Metric
     meta: Dict[str, Any] = field(default_factory=dict)
     tags: List[str] = field(default_factory=list)
+    config: MetricConfig = field(default_factory=MetricConfig)
+    unrendered_config: Dict[str, Any] = field(default_factory=dict)
     sources: List[List[str]] = field(default_factory=list)
     depends_on: DependsOn = field(default_factory=DependsOn)
     refs: List[List[str]] = field(default_factory=list)
@@ -833,6 +945,9 @@ class ParsedMetric(UnparsedBaseNode, HasUniqueID, HasFqn):
     def same_model(self, old: "ParsedMetric") -> bool:
         return self.model == old.model
 
+    def same_window(self, old: "ParsedMetric") -> bool:
+        return self.window == old.window
+
     def same_dimensions(self, old: "ParsedMetric") -> bool:
         return self.dimensions == old.dimensions
 
@@ -845,11 +960,11 @@ class ParsedMetric(UnparsedBaseNode, HasUniqueID, HasFqn):
     def same_label(self, old: "ParsedMetric") -> bool:
         return self.label == old.label
 
-    def same_type(self, old: "ParsedMetric") -> bool:
-        return self.type == old.type
+    def same_calculation_method(self, old: "ParsedMetric") -> bool:
+        return self.calculation_method == old.calculation_method
 
-    def same_sql(self, old: "ParsedMetric") -> bool:
-        return self.sql == old.sql
+    def same_expression(self, old: "ParsedMetric") -> bool:
+        return self.expression == old.expression
 
     def same_timestamp(self, old: "ParsedMetric") -> bool:
         return self.timestamp == old.timestamp
@@ -857,6 +972,12 @@ class ParsedMetric(UnparsedBaseNode, HasUniqueID, HasFqn):
     def same_time_grains(self, old: "ParsedMetric") -> bool:
         return self.time_grains == old.time_grains
 
+    def same_config(self, old: "ParsedMetric") -> bool:
+        return self.config.same_contents(
+            self.unrendered_config,
+            old.unrendered_config,
+        )
+
     def same_contents(self, old: Optional["ParsedMetric"]) -> bool:
         # existing when it didn't before is a change!
         # metadata/tags changes are not "changes"
@@ -865,18 +986,58 @@ class ParsedMetric(UnparsedBaseNode, HasUniqueID, HasFqn):
 
         return (
             self.same_model(old)
+            and self.same_window(old)
             and self.same_dimensions(old)
             and self.same_filters(old)
             and self.same_description(old)
             and self.same_label(old)
-            and self.same_type(old)
-            and self.same_sql(old)
+            and self.same_calculation_method(old)
+            and self.same_expression(old)
             and self.same_timestamp(old)
             and self.same_time_grains(old)
+            and self.same_config(old)
             and True
         )
 
 
+@dataclass
+class ParsedEntity(UnparsedEntity, ParsedEntityMixins, ParsedEntityDefaults, SerializableType):
+    name: str
+    resource_type: NodeType = NodeType.Entity
+    relationships: List[EntityRelationship] = field(default_factory=list)
+    tags: List[str] = field(default_factory=list)
+    config: EntityConfig = field(default_factory=EntityConfig)
+    unrendered_config: Dict[str, Any] = field(default_factory=dict)
+    depends_on: DependsOn = field(default_factory=DependsOn)
+    refs: List[List[str]] = field(default_factory=list)
+    created_at: float = field(default_factory=lambda: time.time())
+
+    @property
+    def depends_on_nodes(self):
+        return self.depends_on.nodes
+
+    @property
+    def search_name(self):
+        return self.name
+
+    def same_relationships(self, old: "ParsedEntity") -> bool:
+        return self.relationships == old.relationships
+
+    def same_config(self, old: "ParsedEntity") -> bool:
+        return self.config.same_contents(
+            self.unrendered_config,
+            old.unrendered_config,
+        )
+
+    def same_contents(self, old: Optional["ParsedEntity"]) -> bool:
+        # existing when it didn't before is a change!
+        # metadata/tags changes are not "changes"
+        if old is None:
+            return True
+
+        return self.same_relationships(old) and True
+
+
 ManifestNodes = Union[
     ParsedAnalysisNode,
     ParsedSingularTestNode,
@@ -896,5 +1057,6 @@ ParsedResource = Union[
     ParsedNode,
     ParsedExposure,
     ParsedMetric,
+    ParsedEntity,
     ParsedSourceDefinition,
 ]

core/dbt/contracts/graph/unparsed.py

@@ -1,5 +1,13 @@
+import re
+
+from dbt import deprecations
 from dbt.node_types import NodeType
-from dbt.contracts.util import AdditionalPropertiesMixin, Mergeable, Replaceable
+from dbt.contracts.util import (
+    AdditionalPropertiesMixin,
+    Mergeable,
+    Replaceable,
+    rename_metric_attr,
+)
 
 # trigger the PathEncoder
 import dbt.helper_types  # noqa:F401
@@ -26,26 +34,33 @@ class UnparsedBaseNode(dbtClassMixin, Replaceable):
 
 
 @dataclass
-class HasSQL:
-    raw_sql: str
+class HasCode(dbtClassMixin):
+    raw_code: str
+    language: str
 
     @property
     def empty(self):
-        return not self.raw_sql.strip()
+        return not self.raw_code.strip()
 
 
 @dataclass
-class UnparsedMacro(UnparsedBaseNode, HasSQL):
+class UnparsedMacro(UnparsedBaseNode, HasCode):
     resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
 
 
 @dataclass
-class UnparsedGenericTest(UnparsedBaseNode, HasSQL):
+class UnparsedGenericTest(UnparsedBaseNode, HasCode):
     resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
 
 
 @dataclass
-class UnparsedNode(UnparsedBaseNode, HasSQL):
+class UnparsedEntity(UnparsedBaseNode):
+    name: str
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Entity]})
+
+
+@dataclass
+class UnparsedNode(UnparsedBaseNode, HasCode):
     name: str
     resource_type: NodeType = field(
         metadata={
@@ -76,6 +91,36 @@ class UnparsedRunHook(UnparsedNode):
 @dataclass
 class Docs(dbtClassMixin, Replaceable):
     show: bool = True
+    node_color: Optional[str] = None
+
+
+@dataclass
+class EntityJoinType(StrEnum):
+    left_outer = "left_outer"
+    inner = "inner"
+
+
+@dataclass
+class EntityRelationshipType(StrEnum):
+    one_to_many = "one_to_many"
+    one_to_one = "one_to_one"
+    many_to_one = "many_to_one"
+
+    def reverse(self) -> str:
+        if self == "many_to_one":
+            return "one_to_many"
+        elif self == "one_to_many":
+            return "many_to_one"
+        else:
+            return self
+
+
+@dataclass
+class EntityRelationship(dbtClassMixin, Mergeable):
+    to: str
+    join_key: str
+    relationship_type: EntityRelationshipType = field(default_factory=EntityRelationshipType)
+    join_type: Optional[EntityJoinType] = field(default_factory=EntityJoinType)
 
 
 @dataclass
@@ -83,6 +128,8 @@ class HasDocs(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable):
     name: str
     description: str = ""
     meta: Dict[str, Any] = field(default_factory=dict)
+    is_entity: Optional[bool] = False
+    relationships: List[EntityRelationship] = field(default_factory=list)
     data_type: Optional[str] = None
     docs: Docs = field(default_factory=Docs)
     _extra: Dict[str, Any] = field(default_factory=dict)
@@ -142,6 +189,11 @@ class UnparsedNodeUpdate(HasConfig, HasColumnTests, HasTests, HasYamlMetadata):
     quote_columns: Optional[bool] = None
 
 
+@dataclass
+class UnparsedEntityUpdate(HasConfig, HasColumnTests, HasDocs, HasYamlMetadata):
+    pass
+
+
 @dataclass
 class MacroArgument(dbtClassMixin):
     name: str
@@ -427,11 +479,21 @@ class UnparsedExposure(dbtClassMixin, Replaceable):
     type: ExposureType
     owner: ExposureOwner
     description: str = ""
+    label: Optional[str] = None
     maturity: Optional[MaturityType] = None
     meta: Dict[str, Any] = field(default_factory=dict)
     tags: List[str] = field(default_factory=list)
     url: Optional[str] = None
     depends_on: List[str] = field(default_factory=list)
+    config: Dict[str, Any] = field(default_factory=dict)
+
+    @classmethod
+    def validate(cls, data):
+        super(UnparsedExposure, cls).validate(data)
+        if "name" in data:
+            # name can only contain alphanumeric chars and underscores
+            if not (re.match(r"[\w-]+$", data["name"])):
+                deprecations.warn("exposure-name", exposure=data["name"])
 
 
 @dataclass
@@ -442,35 +504,66 @@ class MetricFilter(dbtClassMixin, Replaceable):
     value: str
 
 
+class MetricTimePeriod(StrEnum):
+    day = "day"
+    week = "week"
+    month = "month"
+    year = "year"
+
+    def plural(self) -> str:
+        return str(self) + "s"
+
+
+@dataclass
+class MetricTime(dbtClassMixin, Mergeable):
+    count: Optional[int] = None
+    period: Optional[MetricTimePeriod] = None
+
+    def __bool__(self):
+        return self.count is not None and self.period is not None
+
+
 @dataclass
 class UnparsedMetric(dbtClassMixin, Replaceable):
-    # TODO : verify that this disallows metric names with spaces
-    # TODO: fix validation that you broke :p
-    # name: Identifier
     name: str
     label: str
-    type: str
-    model: Optional[str] = None
+    calculation_method: str
+    timestamp: str
+    expression: str
     description: str = ""
-    sql: Union[str, int] = ""
-    timestamp: Optional[str] = None
     time_grains: List[str] = field(default_factory=list)
     dimensions: List[str] = field(default_factory=list)
+    window: Optional[MetricTime] = None
+    model: Optional[str] = None
     filters: List[MetricFilter] = field(default_factory=list)
     meta: Dict[str, Any] = field(default_factory=dict)
     tags: List[str] = field(default_factory=list)
+    config: Dict[str, Any] = field(default_factory=dict)
 
     @classmethod
     def validate(cls, data):
-        # super().validate(data)
-        # TODO: putting this back for now to get tests passing.  Do we want to implement name: Identifier?
+        data = rename_metric_attr(data, raise_deprecation_warning=True)
         super(UnparsedMetric, cls).validate(data)
-        if "name" in data and " " in data["name"]:
-            raise ParsingException(f"Metrics name '{data['name']}' cannot contain spaces")
+        if "name" in data:
+            errors = []
+            if " " in data["name"]:
+                errors.append("cannot contain spaces")
+            # This handles failing queries due to too long metric names.
+            # It only occurs in BigQuery and Snowflake (Postgres/Redshift truncate)
+            if len(data["name"]) > 250:
+                errors.append("cannot contain more than 250 characters")
+            if not (re.match(r"^[A-Za-z]", data["name"])):
+                errors.append("must begin with a letter")
+            if not (re.match(r"[\w-]+$", data["name"])):
+                errors.append("must contain only letters, numbers and underscores")
 
-        # TODO: Expressions _cannot_ have `model` properties
-        if data.get("model") is None and data.get("type") != "expression":
-            raise ValidationError("Non-expression metrics require a 'model' property")
+            if errors:
+                raise ParsingException(
+                    f"The metric name '{data['name']}' is invalid.  It {', '.join(e for e in errors)}"
+                )
 
-        if data.get("model") is not None and data.get("type") == "expression":
-            raise ValidationError("Expression metrics cannot have a 'model' property")
+        if data.get("model") is None and data.get("calculation_method") != "derived":
+            raise ValidationError("Non-derived metrics require a 'model' property")
+
+        if data.get("model") is not None and data.get("calculation_method") == "derived":
+            raise ValidationError("Derived metrics cannot have a 'model' property")

core/dbt/contracts/graph/utils.py

@@ -0,0 +1,153 @@
+import re
+
+HTML_COLORS = [
+    "aliceblue",
+    "antiquewhite",
+    "aqua",
+    "aquamarine",
+    "azure",
+    "beige",
+    "bisque",
+    "black",
+    "blanchedalmond",
+    "blue",
+    "blueviolet",
+    "brown",
+    "burlywood",
+    "cadetblue",
+    "chartreuse",
+    "chocolate",
+    "coral",
+    "cornflowerblue",
+    "cornsilk",
+    "crimson",
+    "cyan",
+    "darkblue",
+    "darkcyan",
+    "darkgoldenrod",
+    "darkgray",
+    "darkgreen",
+    "darkkhaki",
+    "darkmagenta",
+    "darkolivegreen",
+    "darkorange",
+    "darkorchid",
+    "darkred",
+    "darksalmon",
+    "darkseagreen",
+    "darkslateblue",
+    "darkslategray",
+    "darkturquoise",
+    "darkviolet",
+    "deeppink",
+    "deepskyblue",
+    "dimgray",
+    "dodgerblue",
+    "firebrick",
+    "floralwhite",
+    "forestgreen",
+    "fuchsia",
+    "gainsboro",
+    "ghostwhite",
+    "gold",
+    "goldenrod",
+    "gray",
+    "green",
+    "greenyellow",
+    "honeydew",
+    "hotpink",
+    "indianred",
+    "indigo",
+    "ivory",
+    "khaki",
+    "lavender",
+    "lavenderblush",
+    "lawngreen",
+    "lemonchiffon",
+    "lightblue",
+    "lightcoral",
+    "lightcyan",
+    "lightgoldenrodyellow",
+    "lightgray",
+    "lightgreen",
+    "lightpink",
+    "lightsalmon",
+    "lightsalmon",
+    "lightseagreen",
+    "lightskyblue",
+    "lightslategray",
+    "lightsteelblue",
+    "lightyellow",
+    "lime",
+    "limegreen",
+    "linen",
+    "magenta",
+    "maroon",
+    "mediumaquamarine",
+    "mediumblue",
+    "mediumorchid",
+    "mediumpurple",
+    "mediumseagreen",
+    "mediumslateblue",
+    "mediumslateblue",
+    "mediumspringgreen",
+    "mediumturquoise",
+    "mediumvioletred",
+    "midnightblue",
+    "mintcream",
+    "mistyrose",
+    "moccasin",
+    "navajowhite",
+    "navy",
+    "oldlace",
+    "olive",
+    "olivedrab",
+    "orange",
+    "orangered",
+    "orchid",
+    "palegoldenrod",
+    "palegreen",
+    "paleturquoise",
+    "palevioletred",
+    "papayawhip",
+    "peachpuff",
+    "peru",
+    "pink",
+    "plum",
+    "powderblue",
+    "purple",
+    "rebeccapurple",
+    "red",
+    "rosybrown",
+    "royalblue",
+    "saddlebrown",
+    "salmon",
+    "sandybrown",
+    "seagreen",
+    "seashell",
+    "sienna",
+    "silver",
+    "skyblue",
+    "slateblue",
+    "slategray",
+    "snow",
+    "springgreen",
+    "steelblue",
+    "tan",
+    "teal",
+    "thistle",
+    "tomato",
+    "turquoise",
+    "violet",
+    "wheat",
+    "white",
+    "whitesmoke",
+    "yellow",
+    "yellowgreen",
+]
+
+
+def validate_color(color: str) -> bool:
+    match_hex = re.search(r"^#(?:[0-9a-f]{3}){1,2}$", color.lower())
+    match_html_color_name = color.lower() in HTML_COLORS
+    return bool(match_hex or match_html_color_name)

core/dbt/contracts/project.py

@@ -192,6 +192,8 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
     analyses: Dict[str, Any] = field(default_factory=dict)
     sources: Dict[str, Any] = field(default_factory=dict)
     tests: Dict[str, Any] = field(default_factory=dict)
+    metrics: Dict[str, Any] = field(default_factory=dict)
+    exposures: Dict[str, Any] = field(default_factory=dict)
     vars: Optional[Dict[str, Any]] = field(
         default=None,
         metadata=dict(
@@ -234,6 +236,7 @@ class UserConfig(ExtensibleDbtClassMixin, Replaceable, UserConfigContract):
     static_parser: Optional[bool] = None
     indirect_selection: Optional[str] = None
     cache_selected_only: Optional[bool] = None
+    event_buffer_size: Optional[int] = None
 
 
 @dataclass

core/dbt/contracts/sql.py

@@ -30,8 +30,8 @@ class RemoteResult(VersionedSchema):
 
 @dataclass
 class RemoteCompileResultMixin(RemoteResult):
-    raw_sql: str
-    compiled_sql: str
+    raw_code: str
+    compiled_code: str
     node: CompileResultNode
     timing: List[TimingInfo]
 

core/dbt/contracts/util.py

@@ -4,7 +4,12 @@ from datetime import datetime
 from typing import List, Tuple, ClassVar, Type, TypeVar, Dict, Any, Optional
 
 from dbt.clients.system import write_json, read_json
-from dbt.exceptions import InternalException, RuntimeException, IncompatibleSchemaException
+from dbt import deprecations
+from dbt.exceptions import (
+    InternalException,
+    RuntimeException,
+    IncompatibleSchemaException,
+)
 from dbt.version import __version__
 from dbt.events.functions import get_invocation_id
 from dbt.dataclass_schema import dbtClassMixin
@@ -196,6 +201,70 @@ def schema_version(name: str, version: int):
     return inner
 
 
+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])
+
+
+# we renamed these properties in v1.3
+# this method allows us to be nice to the early adopters
+def rename_metric_attr(data: dict, raise_deprecation_warning: bool = False) -> dict:
+    metric_name = data["name"]
+    if raise_deprecation_warning and (
+        "sql" in data.keys()
+        or "type" in data.keys()
+        or data.get("calculation_method") == "expression"
+    ):
+        deprecations.warn("metric-attr-renamed", metric_name=metric_name)
+    duplicated_attribute_msg = """\n
+The metric '{}' contains both the deprecated metric property '{}'
+and the up-to-date metric property '{}'. Please remove the deprecated property.
+"""
+    if "sql" in data.keys():
+        if "expression" in data.keys():
+            raise ValidationError(
+                duplicated_attribute_msg.format(metric_name, "sql", "expression")
+            )
+        else:
+            data["expression"] = data.pop("sql")
+    if "type" in data.keys():
+        if "calculation_method" in data.keys():
+            raise ValidationError(
+                duplicated_attribute_msg.format(metric_name, "type", "calculation_method")
+            )
+        else:
+            calculation_method = data.pop("type")
+            data["calculation_method"] = calculation_method
+    # we also changed "type: expression" -> "calculation_method: derived"
+    if data.get("calculation_method") == "expression":
+        data["calculation_method"] = "derived"
+    return data
+
+
+def rename_sql_attr(node_content: dict) -> dict:
+    if "raw_sql" in node_content:
+        node_content["raw_code"] = node_content.pop("raw_sql")
+    if "compiled_sql" in node_content:
+        node_content["compiled_code"] = node_content.pop("compiled_sql")
+    node_content["language"] = "sql"
+    return node_content
+
+
+def upgrade_manifest_json(manifest: dict) -> dict:
+    for node_content in manifest.get("nodes", {}).values():
+        node_content = rename_sql_attr(node_content)
+    for disabled in manifest.get("disabled", {}).values():
+        # There can be multiple disabled nodes for the same unique_id
+        # so make sure all the nodes get the attr renamed
+        disabled = [rename_sql_attr(n) for n in disabled]
+    for metric_content in manifest.get("metrics", {}).values():
+        # handle attr renames + value translation ("expression" -> "derived")
+        metric_content = rename_metric_attr(metric_content)
+    return manifest
+
+
 # This is used in the ArtifactMixin and RemoteResult classes
 @dataclasses.dataclass
 class VersionedSchema(dbtClassMixin):
@@ -234,9 +303,11 @@ class VersionedSchema(dbtClassMixin):
                 # cls.dbt_schema_version is a SchemaVersion object
                 if not cls.is_compatible_version(previous_schema_version):
                     raise IncompatibleSchemaException(
-                        expected=str(cls.dbt_schema_version), found=previous_schema_version
+                        expected=str(cls.dbt_schema_version),
+                        found=previous_schema_version,
                     )
-
+        if get_manifest_schema_version(data) <= 6:
+            data = upgrade_manifest_json(data)
         return cls.from_dict(data)  # type: ignore
 
 

core/dbt/deprecations.py

@@ -87,6 +87,30 @@ def renamed_method(old_name: str, new_name: str):
     deprecations[dep.name] = dep
 
 
+class MetricAttributesRenamed(DBTDeprecation):
+    _name = "metric-attr-renamed"
+    _description = """\
+dbt-core v1.3 renamed attributes for metrics:
+\n  'sql'              -> 'expression'
+\n  'type'             -> 'calculation_method'
+\n  'type: expression' -> 'calculation_method: derived'
+\nThe old metric parameter names will be fully deprecated in v1.4.
+\nPlease remove them from the metric definition of metric '{metric_name}'
+\nRelevant issue here: https://github.com/dbt-labs/dbt-core/issues/5849
+"""
+
+
+class ExposureNameDeprecation(DBTDeprecation):
+    _name = "exposure-name"
+    _description = """\
+    Starting in v1.3, the 'name' of an exposure should contain only letters, numbers, and underscores.
+    Exposures support a new property, 'label', which may contain spaces, capital letters, and special characters.
+    {exposure} does not follow this pattern.
+    Please update the 'name', and use the 'label' property for a human-friendly title.
+    This will raise an error in a future version of dbt-core.
+    """
+
+
 def warn(name, *args, **kwargs):
     if name not in deprecations:
         # this should (hopefully) never happen
@@ -101,10 +125,12 @@ def warn(name, *args, **kwargs):
 active_deprecations: Set[str] = set()
 
 deprecations_list: List[DBTDeprecation] = [
+    ExposureNameDeprecation(),
     ConfigSourcePathDeprecation(),
     ConfigDataPathDeprecation(),
     PackageInstallPathDeprecation(),
     PackageRedirectDeprecation(),
+    MetricAttributesRenamed(),
 ]
 
 deprecations: Dict[str, DBTDeprecation] = {d.name: d for d in deprecations_list}

core/dbt/deps/registry.py

@@ -3,6 +3,8 @@ import functools
 from typing import List
 
 from dbt import semver
+from dbt import flags
+from dbt.version import get_installed_version
 from dbt.clients import registry, system
 from dbt.contracts.project import (
     RegistryPackageMetadata,
@@ -125,20 +127,27 @@ class RegistryUnpinnedPackage(RegistryPackageMixin, UnpinnedPackage[RegistryPinn
             new_msg = "Version error for package {}: {}".format(self.name, e)
             raise DependencyException(new_msg) from e
 
-        available = registry.get_available_versions(self.package)
+        should_version_check = bool(flags.VERSION_CHECK)
+        dbt_version = get_installed_version()
+        compatible_versions = registry.get_compatible_versions(
+            self.package, dbt_version, should_version_check
+        )
         prerelease_version_specified = any(bool(version.prerelease) for version in self.versions)
         installable = semver.filter_installable(
-            available, self.install_prerelease or prerelease_version_specified
+            compatible_versions, self.install_prerelease or prerelease_version_specified
         )
-        available_latest = installable[-1]
-
-        # for now, pick a version and then recurse. later on,
-        # we'll probably want to traverse multiple options
-        # so we can match packages. not going to make a difference
-        # right now.
-        target = semver.resolve_to_specific_version(range_, installable)
+        if installable:
+            # for now, pick a version and then recurse. later on,
+            # we'll probably want to traverse multiple options
+            # so we can match packages. not going to make a difference
+            # right now.
+            target = semver.resolve_to_specific_version(range_, installable)
+        else:
+            target = None
         if not target:
-            package_version_not_found(self.package, range_, installable)
+            # raise an exception if no installable target version is found
+            package_version_not_found(self.package, range_, installable, should_version_check)
+        latest_compatible = installable[-1]
         return RegistryPinnedPackage(
-            package=self.package, version=target, version_latest=available_latest
+            package=self.package, version=target, version_latest=latest_compatible
         )

core/dbt/deps/resolver.py

@@ -120,7 +120,6 @@ def resolve_packages(
 ) -> List[PinnedPackage]:
     pending = PackageListing.from_contracts(packages)
     final = PackageListing()
-
     renderer = DbtProjectYamlRenderer(config, config.cli_vars)
 
     while pending:

core/dbt/events/base_types.py

@@ -105,6 +105,8 @@ class ErrorLevel(EventSerialization, Event):
 
 
 # prevents an event from going to the file
+# This should rarely be used in core code. It is currently
+# only used in integration tests and for the 'clean' command.
 class NoFile:
     pass
 

core/dbt/events/functions.py

@@ -1,11 +1,12 @@
 from colorama import Style
 import dbt.events.functions as this  # don't worry I hate it too.
 from dbt.events.base_types import NoStdOut, Event, NoFile, ShowException, Cache
-from dbt.events.types import EventBufferFull, T_Event, MainReportVersion, EmptyLine
+from dbt.events.types import T_Event, MainReportVersion, EmptyLine, EventBufferFull
 import dbt.flags as flags
+from dbt.constants import SECRET_ENV_PREFIX
 
 # TODO this will need to move eventually
-from dbt.logger import SECRET_ENV_PREFIX, make_log_dir_if_missing, GLOBAL_LOGGER
+from dbt.logger import make_log_dir_if_missing, GLOBAL_LOGGER
 from datetime import datetime
 import json
 import io
@@ -21,24 +22,16 @@ import threading
 from typing import Any, Dict, List, Optional, Union
 from collections import deque
 
-global LOG_VERSION
 LOG_VERSION = 2
-
-# create the global event history buffer with the default max size (10k)
-# python 3.7 doesn't support type hints on globals, but mypy requires them. hence the ignore.
-# TODO the flags module has not yet been resolved when this is created
-global EVENT_HISTORY
-EVENT_HISTORY = deque(maxlen=flags.EVENT_BUFFER_SIZE)  # type: ignore
+EVENT_HISTORY = None
 
 # create the global file logger with no configuration
-global FILE_LOG
 FILE_LOG = logging.getLogger("default_file")
 null_handler = logging.NullHandler()
 FILE_LOG.addHandler(null_handler)
 
 # set up logger to go to stdout with defaults
 # setup_event_logger will be called once args have been parsed
-global STDOUT_LOG
 STDOUT_LOG = logging.getLogger("default_stdout")
 STDOUT_LOG.setLevel(logging.INFO)
 stdout_handler = logging.StreamHandler(sys.stdout)
@@ -51,11 +44,8 @@ invocation_id: Optional[str] = None
 
 
 def setup_event_logger(log_path, level_override=None):
-    # flags have been resolved, and log_path is known
-    global EVENT_HISTORY
-    EVENT_HISTORY = deque(maxlen=flags.EVENT_BUFFER_SIZE)  # type: ignore
-
     make_log_dir_if_missing(log_path)
+
     this.format_json = flags.LOG_FORMAT == "json"
     # USE_COLORS can be None if the app just started and the cli flags
     # havent been applied yet
@@ -116,7 +106,7 @@ def stop_capture_stdout_logs() -> None:
 
 
 def env_secrets() -> List[str]:
-    return [v for k, v in os.environ.items() if k.startswith(SECRET_ENV_PREFIX)]
+    return [v for k, v in os.environ.items() if k.startswith(SECRET_ENV_PREFIX) and v.strip()]
 
 
 def scrub_secrets(msg: str, secrets: List[str]) -> str:
@@ -218,7 +208,7 @@ def create_log_line(e: T_Event, file_output=False) -> Optional[str]:
         return create_info_text_log_line(e)  # console output
 
 
-# allows for resuse of this obnoxious if else tree.
+# allows for reuse of this obnoxious if else tree.
 # do not use for exceptions, it doesn't pass along exc_info, stack_info, or extra
 def send_to_logger(l: Union[Logger, logbook.Logger], level_tag: str, log_line: str):
     if not log_line:
@@ -269,14 +259,7 @@ def fire_event(e: Event) -> None:
     if isinstance(e, Cache) and not flags.LOG_CACHE_EVENTS:
         return
 
-    # if and only if the event history deque will be completely filled by this event
-    # fire warning that old events are now being dropped
-    global EVENT_HISTORY
-    if len(EVENT_HISTORY) == (flags.EVENT_BUFFER_SIZE - 1):
-        EVENT_HISTORY.append(e)
-        fire_event(EventBufferFull())
-    else:
-        EVENT_HISTORY.append(e)
+    add_to_event_history(e)
 
     # backwards compatibility for plugins that require old logger (dbt-rpc)
     if flags.ENABLE_LEGACY_LOGGER:
@@ -342,3 +325,20 @@ def get_ts_rfc3339() -> str:
     ts = get_ts()
     ts_rfc3339 = ts.strftime("%Y-%m-%dT%H:%M:%S.%fZ")
     return ts_rfc3339
+
+
+def add_to_event_history(event):
+    if flags.EVENT_BUFFER_SIZE == 0:
+        return
+    global EVENT_HISTORY
+    if EVENT_HISTORY is None:
+        reset_event_history()
+    EVENT_HISTORY.append(event)
+    # We only set the EventBufferFull message for event buffers >= 10,000
+    if flags.EVENT_BUFFER_SIZE >= 10000 and len(EVENT_HISTORY) == (flags.EVENT_BUFFER_SIZE - 1):
+        fire_event(EventBufferFull())
+
+
+def reset_event_history():
+    global EVENT_HISTORY
+    EVENT_HISTORY = deque(maxlen=flags.EVENT_BUFFER_SIZE)

core/dbt/events/test_types.py

@@ -1,5 +1,6 @@
 from dataclasses import dataclass
-from .types import InfoLevel, DebugLevel, WarnLevel, ErrorLevel, ShowException, NoFile
+from dbt.events.types import InfoLevel, DebugLevel, WarnLevel, ErrorLevel, ShowException
+from dbt.events.base_types import NoFile
 
 
 # Keeping log messages for testing separate since they are used for debugging.

core/dbt/events/types.py

@@ -94,7 +94,7 @@ class AdapterEventError(ErrorLevel, AdapterEventBase, ShowException):
 
 
 @dataclass
-class MainKeyboardInterrupt(InfoLevel, NoFile):
+class MainKeyboardInterrupt(InfoLevel):
     code: str = "Z001"
 
     def message(self) -> str:
@@ -102,16 +102,16 @@ class MainKeyboardInterrupt(InfoLevel, NoFile):
 
 
 @dataclass
-class MainEncounteredError(ErrorLevel, NoFile):
-    e: BaseException
+class MainEncounteredError(ErrorLevel):
+    exc: str
     code: str = "Z002"
 
     def message(self) -> str:
-        return f"Encountered an error:\n{self.e}"
+        return f"Encountered an error:\n{self.exc}"
 
 
 @dataclass
-class MainStackTrace(DebugLevel, NoFile):
+class MainStackTrace(ErrorLevel):
     stack_trace: str
     code: str = "Z003"
 
@@ -382,7 +382,7 @@ class SystemErrorRetrievingModTime(ErrorLevel):
 class SystemCouldNotWrite(DebugLevel):
     path: str
     reason: str
-    exc: Exception
+    exc: str
     code: str = "Z005"
 
     def message(self) -> str:
@@ -762,7 +762,7 @@ class DumpAfterRenameSchema(DebugLevel, Cache):
 
 @dataclass
 class AdapterImportError(InfoLevel):
-    exc: Exception
+    exc: str
     code: str = "E035"
 
     def message(self) -> str:
@@ -786,6 +786,26 @@ class NewConnectionOpening(DebugLevel):
         return f"Opening a new connection, currently in state {self.connection_state}"
 
 
+@dataclass
+class CodeExecution(DebugLevel):
+    conn_name: Optional[str]
+    code_content: str
+    code: str = "E038"
+
+    def message(self) -> str:
+        return f"On {self.conn_name}: {self.code_content}"
+
+
+@dataclass
+class CodeExecutionStatus(DebugLevel):
+    status: str
+    elapsed: Optional[float]
+    code: str = "E039"
+
+    def message(self) -> str:
+        return f"Execution status: {self.status} in {self.elapsed} seconds"
+
+
 @dataclass
 class TimingInfoCollected(DebugLevel):
     code: str = "Z010"
@@ -988,7 +1008,7 @@ class PartialParsingNotEnabled(DebugLevel):
 @dataclass
 class ParsedFileLoadFailed(ShowException, DebugLevel):
     path: str
-    exc: Exception
+    exc: str
     code: str = "I029"
 
     def message(self) -> str:
@@ -1203,7 +1223,7 @@ class InvalidRefInTestNode(DebugLevel):
 
 @dataclass
 class RunningOperationCaughtError(ErrorLevel):
-    exc: Exception
+    exc: str
     code: str = "Q001"
 
     def message(self) -> str:
@@ -1212,7 +1232,7 @@ class RunningOperationCaughtError(ErrorLevel):
 
 @dataclass
 class RunningOperationUncaughtError(ErrorLevel):
-    exc: Exception
+    exc: str
     code: str = "FF01"
 
     def message(self) -> str:
@@ -1229,7 +1249,7 @@ class DbtProjectError(ErrorLevel):
 
 @dataclass
 class DbtProjectErrorException(ErrorLevel):
-    exc: Exception
+    exc: str
     code: str = "A010"
 
     def message(self) -> str:
@@ -1246,7 +1266,7 @@ class DbtProfileError(ErrorLevel):
 
 @dataclass
 class DbtProfileErrorException(ErrorLevel):
-    exc: Exception
+    exc: str
     code: str = "A012"
 
     def message(self) -> str:
@@ -1293,7 +1313,7 @@ https://docs.getdbt.com/docs/configure-your-profile
 
 @dataclass
 class CatchableExceptionOnRun(ShowException, DebugLevel):
-    exc: Exception
+    exc: str
     code: str = "W002"
 
     def message(self) -> str:
@@ -1303,7 +1323,7 @@ class CatchableExceptionOnRun(ShowException, DebugLevel):
 @dataclass
 class InternalExceptionOnRun(DebugLevel):
     build_path: str
-    exc: Exception
+    exc: str
     code: str = "W003"
 
     def message(self) -> str:
@@ -1332,7 +1352,7 @@ class PrintDebugStackTrace(ShowException, DebugLevel):
 class GenericExceptionOnRun(ErrorLevel):
     build_path: Optional[str]
     unique_id: str
-    exc: Exception
+    exc: str
     code: str = "W004"
 
     def message(self) -> str:
@@ -1346,13 +1366,15 @@ class GenericExceptionOnRun(ErrorLevel):
 @dataclass
 class NodeConnectionReleaseError(ShowException, DebugLevel):
     node_name: str
-    exc: Exception
+    exc: str
     code: str = "W005"
 
     def message(self) -> str:
         return "Error releasing connection for node {}: {!s}".format(self.node_name, self.exc)
 
 
+# We don't write "clean" events to the log, because the clean command
+# may have removed the log directory.
 @dataclass
 class CheckCleanPath(InfoLevel, NoFile):
     path: str
@@ -1618,6 +1640,15 @@ class RunResultWarning(WarnLevel):
         return ui.yellow(f"{info} in {self.resource_type} {self.node_name} ({self.path})")
 
 
+@dataclass
+class RunResultWarningMessage(WarnLevel):
+    msg: str
+    code: str = "Z049"
+
+    def message(self) -> str:
+        return f"  {self.msg}"
+
+
 @dataclass
 class RunResultFailure(ErrorLevel):
     resource_type: str
@@ -1664,12 +1695,12 @@ class SQLCompiledPath(InfoLevel):
     code: str = "Z026"
 
     def message(self) -> str:
-        return f"  compiled SQL at {self.path}"
+        return f"  compiled Code at {self.path}"
 
 
 @dataclass
 class SQlRunnerException(ShowException, DebugLevel):
-    exc: Exception
+    exc: str
     code: str = "Q006"
 
     def message(self) -> str:
@@ -2382,7 +2413,7 @@ class SendEventFailure(DebugLevel):
 
 
 @dataclass
-class FlushEvents(DebugLevel, NoFile):
+class FlushEvents(DebugLevel):
     code: str = "Z042"
 
     def message(self) -> str:
@@ -2390,7 +2421,7 @@ class FlushEvents(DebugLevel, NoFile):
 
 
 @dataclass
-class FlushEventsFailure(DebugLevel, NoFile):
+class FlushEventsFailure(DebugLevel):
     code: str = "Z043"
 
     def message(self) -> str:
@@ -2427,7 +2458,7 @@ class GeneralWarningMsg(WarnLevel):
 
 @dataclass
 class GeneralWarningException(WarnLevel):
-    exc: Exception
+    exc: str
     log_fmt: str
     code: str = "Z047"
 
@@ -2448,7 +2479,7 @@ class EventBufferFull(WarnLevel):
 
 @dataclass
 class RecordRetryException(DebugLevel):
-    exc: Exception
+    exc: str
     code: str = "M021"
 
     def message(self) -> str:
@@ -2464,7 +2495,7 @@ class RecordRetryException(DebugLevel):
 if 1 == 0:
     MainReportVersion(v="")
     MainKeyboardInterrupt()
-    MainEncounteredError(e=BaseException(""))
+    MainEncounteredError(exc="")
     MainStackTrace(stack_trace="")
     MainTrackingUserState(user_state="")
     ParsingStart()
@@ -2493,7 +2524,7 @@ if 1 == 0:
     RegistryResponseMissingNestedKeys(response=""),
     RegistryResponseExtraNestedKeys(response=""),
     SystemErrorRetrievingModTime(path="")
-    SystemCouldNotWrite(path="", reason="", exc=Exception(""))
+    SystemCouldNotWrite(path="", reason="", exc="")
     SystemExecutingCmd(cmd=[""])
     SystemStdOutMsg(bmsg=b"")
     SystemStdErrMsg(bmsg=b"")
@@ -2513,6 +2544,8 @@ if 1 == 0:
     ConnectionUsed(conn_type="", conn_name="")
     SQLQuery(conn_name="", sql="")
     SQLQueryStatus(status="", elapsed=0.1)
+    CodeExecution(conn_name="", code_content="")
+    CodeExecutionStatus(status="", elapsed=0.1)
     SQLCommit(conn_name="")
     ColTypeChange(
         orig_type="", new_type="", table=_ReferenceKey(database="", schema="", identifier="")
@@ -2547,7 +2580,7 @@ if 1 == 0:
     DumpAfterAddGraph(Lazy.defer(lambda: dict()))
     DumpBeforeRenameSchema(Lazy.defer(lambda: dict()))
     DumpAfterRenameSchema(Lazy.defer(lambda: dict()))
-    AdapterImportError(exc=Exception())
+    AdapterImportError(exc="")
     PluginLoadError()
     SystemReportReturnCode(returncode=0)
     NewConnectionOpening(connection_state="")
@@ -2570,7 +2603,7 @@ if 1 == 0:
     PartialParsingFailedBecauseNewProjectDependency()
     PartialParsingFailedBecauseHashChanged()
     PartialParsingDeletedMetric(id="")
-    ParsedFileLoadFailed(path="", exc=Exception(""))
+    ParsedFileLoadFailed(path="", exc="")
     PartialParseSaveFileNotFound()
     StaticParserCausedJinjaRendering(path="")
     UsingExperimentalParser(path="")
@@ -2593,20 +2626,20 @@ if 1 == 0:
     PartialParsingDeletedExposure(unique_id="")
     InvalidDisabledSourceInTestNode(msg="")
     InvalidRefInTestNode(msg="")
-    RunningOperationCaughtError(exc=Exception(""))
-    RunningOperationUncaughtError(exc=Exception(""))
+    RunningOperationCaughtError(exc="")
+    RunningOperationUncaughtError(exc="")
     DbtProjectError()
-    DbtProjectErrorException(exc=Exception(""))
+    DbtProjectErrorException(exc="")
     DbtProfileError()
-    DbtProfileErrorException(exc=Exception(""))
+    DbtProfileErrorException(exc="")
     ProfileListTitle()
     ListSingleProfile(profile="")
     NoDefinedProfiles()
     ProfileHelpMessage()
-    CatchableExceptionOnRun(exc=Exception(""))
-    InternalExceptionOnRun(build_path="", exc=Exception(""))
-    GenericExceptionOnRun(build_path="", unique_id="", exc=Exception(""))
-    NodeConnectionReleaseError(node_name="", exc=Exception(""))
+    CatchableExceptionOnRun(exc="")
+    InternalExceptionOnRun(build_path="", exc="")
+    GenericExceptionOnRun(build_path="", unique_id="", exc="")
+    NodeConnectionReleaseError(node_name="", exc="")
     CheckCleanPath(path="")
     ConfirmCleanPath(path="")
     ProtectedCleanPath(path="")
@@ -2814,6 +2847,6 @@ if 1 == 0:
     TrackingInitializeFailure()
     RetryExternalCall(attempt=0, max=0)
     GeneralWarningMsg(msg="", log_fmt="")
-    GeneralWarningException(exc=Exception(""), log_fmt="")
+    GeneralWarningException(exc="", log_fmt="")
     EventBufferFull()
-    RecordRetryException(exc=Exception(""))
+    RecordRetryException(exc="")

core/dbt/exceptions.py

@@ -122,9 +122,9 @@ class RuntimeException(RuntimeError, Exception):
 
         result.update(
             {
-                "raw_sql": self.node.raw_sql,
+                "raw_code": self.node.raw_code,
                 # the node isn't always compiled, but if it is, include that!
-                "compiled_sql": getattr(self.node, "compiled_sql", None),
+                "compiled_code": getattr(self.node, "compiled_code", None),
             }
         )
         return result
@@ -203,7 +203,7 @@ class DatabaseException(RuntimeException):
         lines = []
 
         if hasattr(self.node, "build_path") and self.node.build_path:
-            lines.append("compiled SQL at {}".format(self.node.build_path))
+            lines.append("compiled Code at {}".format(self.node.build_path))
 
         return lines + RuntimeException.process_stack(self)
 
@@ -631,13 +631,13 @@ def ref_target_not_found(
     raise_compiler_error(msg, model)
 
 
-def get_source_not_found_or_disabled_msg(
-    model,
+def get_not_found_or_disabled_msg(
+    node,
     target_name: str,
-    target_table_name: str,
+    target_kind: str,
+    target_package: Optional[str] = None,
     disabled: Optional[bool] = None,
 ) -> str:
-    full_name = f"{target_name}.{target_table_name}"
     if disabled is None:
         reason = "was not found or is disabled"
     elif disabled is True:
@@ -645,34 +645,57 @@ def get_source_not_found_or_disabled_msg(
     else:
         reason = "was not found"
     return _get_target_failure_msg(
-        model, full_name, None, include_path=True, reason=reason, target_kind="source"
+        node,
+        target_name,
+        target_package,
+        include_path=True,
+        reason=reason,
+        target_kind=target_kind,
     )
 
 
 def source_target_not_found(
     model, target_name: str, target_table_name: str, disabled: Optional[bool] = None
 ) -> NoReturn:
-    msg = get_source_not_found_or_disabled_msg(model, target_name, target_table_name, disabled)
+    msg = get_not_found_or_disabled_msg(
+        node=model,
+        target_name=f"{target_name}.{target_table_name}",
+        target_kind="source",
+        disabled=disabled,
+    )
     raise_compiler_error(msg, model)
 
 
-def get_metric_not_found_msg(
-    model,
-    target_name: str,
-    target_package: Optional[str],
-) -> str:
-    reason = "was not found"
-    return _get_target_failure_msg(
-        model, target_name, target_package, include_path=True, reason=reason, target_kind="metric"
+def metric_target_not_found(
+    metric, target_name: str, target_package: Optional[str], disabled: Optional[bool] = None
+) -> NoReturn:
+
+    msg = get_not_found_or_disabled_msg(
+        node=metric,
+        target_name=target_name,
+        target_kind="metric",
+        target_package=target_package,
+        disabled=disabled,
     )
 
-
-def metric_target_not_found(metric, target_name: str, target_package: Optional[str]) -> NoReturn:
-    msg = get_metric_not_found_msg(metric, target_name, target_package)
-
     raise_compiler_error(msg, metric)
 
 
+def exposure_target_not_found(
+    exposure, target_name: str, target_package: Optional[str], disabled: Optional[bool] = None
+) -> NoReturn:
+
+    msg = get_not_found_or_disabled_msg(
+        node=exposure,
+        target_name=target_name,
+        target_kind="exposure",
+        target_package=target_package,
+        disabled=disabled,
+    )
+
+    raise_compiler_error(msg, exposure)
+
+
 def dependency_not_found(model, target_model_name):
     raise_compiler_error(
         "'{}' depends on '{}' which is not in the graph!".format(
@@ -776,13 +799,25 @@ def package_not_found(package_name):
     raise_dependency_error("Package {} was not found in the package index".format(package_name))
 
 
-def package_version_not_found(package_name, version_range, available_versions):
+def package_version_not_found(
+    package_name, version_range, available_versions, should_version_check
+):
     base_msg = (
-        "Could not find a matching version for package {}\n"
+        "Could not find a matching compatible version for package {}\n"
         "  Requested range: {}\n"
-        "  Available versions: {}"
+        "  Compatible versions: {}\n"
     )
-    raise_dependency_error(base_msg.format(package_name, version_range, available_versions))
+    addendum = (
+        (
+            "\n"
+            "  Not shown: package versions incompatible with installed version of dbt-core\n"
+            "  To include them, run 'dbt --no-version-check deps'"
+        )
+        if should_version_check
+        else ""
+    )
+    msg = base_msg.format(package_name, version_range, available_versions) + addendum
+    raise_dependency_error(msg)
 
 
 def invalid_materialization_argument(name, argument):
@@ -1063,7 +1098,7 @@ def warn_or_raise(exc, log_fmt=None):
     if flags.WARN_ERROR:
         raise exc
     else:
-        fire_event(GeneralWarningException(exc=exc, log_fmt=log_fmt))
+        fire_event(GeneralWarningException(exc=str(exc), log_fmt=log_fmt))
 
 
 def warn(msg, node=None):

core/dbt/flags.py

@@ -10,7 +10,13 @@ from typing import Optional
 # PROFILES_DIR must be set before the other flags
 # It also gets set in main.py and in set_from_args because the rpc server
 # doesn't go through exactly the same main arg processing.
-DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser("~"), ".dbt")
+GLOBAL_PROFILES_DIR = os.path.join(os.path.expanduser("~"), ".dbt")
+LOCAL_PROFILES_DIR = os.getcwd()
+# Use the current working directory if there is a profiles.yml file present there
+if os.path.exists(Path(LOCAL_PROFILES_DIR) / Path("profiles.yml")):
+    DEFAULT_PROFILES_DIR = LOCAL_PROFILES_DIR
+else:
+    DEFAULT_PROFILES_DIR = GLOBAL_PROFILES_DIR
 PROFILES_DIR = os.path.expanduser(os.getenv("DBT_PROFILES_DIR", DEFAULT_PROFILES_DIR))
 
 STRICT_MODE = False  # Only here for backwards compatibility
@@ -52,6 +58,7 @@ _NON_BOOLEAN_FLAGS = [
 
 _NON_DBT_ENV_FLAGS = ["DO_NOT_TRACK"]
 
+
 # Global CLI defaults. These flags are set from three places:
 # CLI args, environment variables, and user_config (profiles.yml).
 # Environment variables use the pattern 'DBT_{flag name}', like DBT_PROFILES_DIR

core/dbt/graph/selector.py

@@ -165,7 +165,8 @@ class NodeSelector(MethodManager):
         elif unique_id in self.manifest.exposures:
             return True
         elif unique_id in self.manifest.metrics:
-            return True
+            metric = self.manifest.metrics[unique_id]
+            return metric.config.enabled
         node = self.manifest.nodes[unique_id]
         return not node.empty and node.config.enabled
 

core/dbt/graph/selector_methods.py

@@ -356,8 +356,21 @@ class ConfigSelectorMethod(SelectorMethod):
             except AttributeError:
                 continue
             else:
-                if selector == value:
-                    yield node
+                if isinstance(value, list):
+                    if (
+                        (selector in value)
+                        or (CaseInsensitive(selector) == "true" and True in value)
+                        or (CaseInsensitive(selector) == "false" and False in value)
+                    ):
+                        yield node
+                else:
+                    if (
+                        (selector == value)
+                        or (CaseInsensitive(selector) == "true" and value is True)
+                        or (CaseInsensitive(selector) == "false")
+                        and value is False
+                    ):
+                        yield node
 
 
 class ResourceTypeSelectorMethod(SelectorMethod):

core/dbt/graph/selector_spec.py

@@ -80,7 +80,7 @@ class SelectionCriteria:
     def default_method(cls, value: str) -> MethodName:
         if _probably_path(value):
             return MethodName.Path
-        elif value.lower().endswith(".sql"):
+        elif value.lower().endswith((".sql", ".py", ".csv")):
             return MethodName.File
         else:
             return MethodName.FQN

core/dbt/include/README.md

@@ -1,15 +1,63 @@
 # Include Module
 
-The Include module is reponsible for housing default macro definitions, starter project scaffold, and the html file used to generate the docs page.
+The Include module is responsible for housing default macro definitions, starter project scaffold, and the html file used to generate the docs page.
 
 # Directories
 
 ## `global_project`
 Defines the default implementations of jinja2 macros for `dbt-core` which can be overwritten in each adapter repo to work more in line with those adapter plugins. To view adapter specific jinja2 changes please check the relevant adapter repo [`adapter.sql` ](https://github.com/dbt-labs/dbt-bigquery/blob/main/dbt/include/bigquery/macros/adapters.sql) file in the `include` directory or in the [`impl.py`](https://github.com/dbt-labs/dbt-bigquery/blob/main/dbt/adapters/bigquery/impl.py) file for some ex. BigQuery (truncate_relation).
 
+These directories contain the macros which wrap model code in DDL/DML. That code, in turn, “materializes” as a fully fledged database object in a warehouse pointed to by the current `target`. Here’re the major steps of this process:
+    1. the SQL `select` query is compiled. In its current state, it could be run directly through a query editor to retrieve a dataset that will match 1:1 the database object materialized by `dbt`.
+2. `dbt` embeds this SQL query into a materialization macro.
+3. `dbt` executes this materialization macro which unravels a table into a DML/DDL statement that creates/truncate-and-replenishes/replaces a relation (e.g. view, table) in the `target`.
+
+Note: `dbt compile` will not progress past step 1. It places the code produced in `target/compiled`.
+
+### adapter.dispatch
+Packages (e.g. `include` directories of adapters, any [hub](https://hub.getdbt.com/)-hosted package) can be interpreted as namespaces of functions a.k.a macros. In `dbt`'s macrospace, we take advantage of the multiple dispatch programming language concept. In short, multiple dispatch supports dynamic searching for a function across several namespaces—usually in a manually specified manner/order.
+
+Adapters can have their own implementation of the same macro X. For example, a macro executed by `dbt-redshift` may need a specific implementation different from `dbt-snowflake`'s macro. We use multiple dispatch via `adapter.dispatch`, a Jinja function, which enables polymorphic macro invocations. The chosen implementation is selected according to what the `adapter` object is set to at runtime (it could be for redshift, postgres, and so on).
+
+For more on this object, check out the dbt docs [here](https://docs.getdbt.com/reference/dbt-jinja-functions/adapter).
+
 ## `starter_project`
 Produces the default project after running the `dbt init` command for the CLI. `dbt-cloud` initializes the project by using [dbt-starter-project](https://github.com/dbt-labs/dbt-starter-project).
 
 
 # Files
  - `index.html` a file generated from [dbt-docs](https://github.com/dbt-labs/dbt-docs) prior to new releases and replaced in the `dbt-core` directory. It is used to generate the docs page after using the `generate docs` command in dbt.
+
+# dbt and database adapter python package interop
+
+Let’s say we have a fictional python app named `dbt-core` with this structure
+
+```
+dbt
+├── adapters
+│   └── base.py
+├── cli.py
+└── main.py
+```
+
+`pip install dbt-core` will install this application in my python environment, maintaining the same structure. Note that `dbt.adapters` only contains a `base.py`. In this example, we can assume that base.py includes an abstract class for creating connections. Let’s say we wanted to create an postgres adapter that this app could use, and can be installed independently. We can create a python package with the following structure called `dbt-postgres`
+```
+dbt
+└── adapters
+    └── postgres
+        └── impl.py
+```
+
+`pip install dbt-postgres` will install this package in the python environment, maintaining the same structure again. Let’s say `impl.py` imports `dbt.adapters.base` and implements a concrete class inheriting from the abstract class in `base.py` from the `dbt-core` package. Since our top level package is named the same in both packages, `pip` will put this in the same place. We end up with this installed in our python environment.
+
+```
+dbt
+├── adapters
+│   ├── base.py
+│   └── postgres
+│       └── impl.py
+├── cli.py
+└── main.py
+```
+
+`dbt.adapters` now has a postgres module that dbt can easily find and call directly. dbt and its adapters follows the same type of file structure convention. This is the magic that allows you to import `dbt.*` in database adapters, and using a factory pattern in dbt-core, we can create instances of concrete classes defined in the database adapter packages (for creating connections, defining database configuration, defining credentials, etc.)

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

@@ -1,13 +1,3 @@
-{% macro current_timestamp() -%}
-  {{ adapter.dispatch('current_timestamp', 'dbt')() }}
-{%- endmacro %}
-
-{% macro default__current_timestamp() -%}
-  {{ exceptions.raise_not_implemented(
-    'current_timestamp macro not implemented for adapter '+adapter.type()) }}
-{%- endmacro %}
-
-
 {% macro collect_freshness(source, loaded_at_field, filter) %}
   {{ return(adapter.dispatch('collect_freshness', 'dbt')(source, loaded_at_field, filter))}}
 {% endmacro %}

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

@@ -0,0 +1,44 @@
+{%- macro current_timestamp() -%}
+    {{ adapter.dispatch('current_timestamp', 'dbt')() }}
+{%- endmacro -%}
+
+{% macro default__current_timestamp() -%}
+  {{ exceptions.raise_not_implemented(
+    'current_timestamp macro not implemented for adapter ' + adapter.type()) }}
+{%- endmacro %}
+
+{%- macro snapshot_get_time() -%}
+    {{ adapter.dispatch('snapshot_get_time', 'dbt')() }}
+{%- endmacro -%}
+
+{% macro default__snapshot_get_time() %}
+    {{ current_timestamp() }}
+{% endmacro %}
+
+---------------------------------------------
+
+/* {#
+    DEPRECATED: DO NOT USE IN NEW PROJECTS
+
+    This is ONLY to handle the fact that Snowflake + Postgres had functionally
+    different implementations of {{ dbt.current_timestamp }} + {{ dbt_utils.current_timestamp }}
+
+    If you had a project or package that called {{ dbt_utils.current_timestamp() }}, you should
+    continue to use this macro to guarantee identical behavior on those two databases.
+#} */
+
+{% macro current_timestamp_backcompat() %}
+    {{ return(adapter.dispatch('current_timestamp_backcompat', 'dbt')()) }}
+{% endmacro %}
+
+{% macro default__current_timestamp_backcompat() %}
+    current_timestamp::timestamp
+{% endmacro %}
+
+{% macro current_timestamp_in_utc_backcompat() %}
+    {{ return(adapter.dispatch('current_timestamp_in_utc_backcompat', 'dbt')()) }}
+{% endmacro %}
+
+{% macro default__current_timestamp_in_utc_backcompat() %}
+    {{ return(adapter.dispatch('current_timestamp_backcompat', 'dbt')()) }}
+{% endmacro %}

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

@@ -1,13 +1,24 @@
-{% macro statement(name=None, fetch_result=False, auto_begin=True) -%}
+{#--
+The macro override naming method (spark__statement) only works for macros which are called with adapter.dispatch. For macros called directly, you can just redefine them.
+--#}
+{%- macro statement(name=None, fetch_result=False, auto_begin=True, language='sql') -%}
   {%- if execute: -%}
-    {%- set sql = caller() -%}
+    {%- set compiled_code = caller() -%}
 
     {%- if name == 'main' -%}
-      {{ log('Writing runtime SQL for node "{}"'.format(model['unique_id'])) }}
-      {{ write(sql) }}
+      {{ log('Writing runtime {} for node "{}"'.format(language, model['unique_id'])) }}
+      {{ write(compiled_code) }}
+    {%- endif -%}
+    {%- if language == 'sql'-%}
+      {%- set res, table = adapter.execute(compiled_code, auto_begin=auto_begin, fetch=fetch_result) -%}
+    {%- elif language == 'python' -%}
+      {%- set res = submit_python_job(model, compiled_code) -%}
+      {#-- TODO: What should table be for python models? --#}
+      {%- set table = None -%}
+    {%- else -%}
+      {% do exceptions.raise_compiler_error("statement macro didn't get supported language") %}
     {%- endif -%}
 
-    {%- set res, table = adapter.execute(sql, auto_begin=auto_begin, fetch=fetch_result) -%}
     {%- if name is not none -%}
       {{ store_result(name, response=res, agate_table=table) }}
     {%- endif -%}

core/dbt/include/global_project/macros/materializations/models/incremental/column_helpers.sql

@@ -41,7 +41,7 @@
   {% for sc in source_columns %}
     {% set tc = target_columns | selectattr("name", "equalto", sc.name) | list | first %}
     {% if tc %}
-      {% if sc.data_type != tc.data_type %}
+      {% if sc.data_type != tc.data_type and not sc.can_expand_to(other_column=tc) %}
         {{ result.append( { 'column_name': tc.name, 'new_type': sc.data_type } ) }}
       {% endif %}
     {% endif %}
@@ -50,3 +50,31 @@
   {{ return(result) }}
 
 {% endmacro %}
+
+{% macro get_merge_update_columns(merge_update_columns, merge_exclude_columns, dest_columns) %}
+  {{ return(adapter.dispatch('get_merge_update_columns', 'dbt')(merge_update_columns, merge_exclude_columns, dest_columns)) }}
+{% endmacro %}
+
+{% macro default__get_merge_update_columns(merge_update_columns, merge_exclude_columns, dest_columns) %}
+  {%- set default_cols = dest_columns | map(attribute="quoted") | list -%}
+
+  {%- if merge_update_columns and merge_exclude_columns -%}
+    {{ exceptions.raise_compiler_error(
+        'Model cannot specify merge_update_columns and merge_exclude_columns. Please update model to use only one config'
+    )}}
+  {%- elif merge_update_columns -%}
+    {%- set update_columns = merge_update_columns -%}
+  {%- elif merge_exclude_columns -%}
+    {%- set update_columns = [] -%}
+    {%- for column in dest_columns -%}
+      {% if column.column | lower not in merge_exclude_columns | map("lower") | list %}
+        {%- do update_columns.append(column.quoted) -%}
+      {% endif %}
+    {%- endfor -%}
+  {%- else -%}
+    {%- set update_columns = default_cols -%}
+  {%- endif -%}
+
+  {{ return(update_columns) }}
+
+{% endmacro %}

core/dbt/include/global_project/macros/materializations/models/incremental/incremental.sql

@@ -47,7 +47,13 @@
     {% if not dest_columns %}
       {% set dest_columns = adapter.get_columns_in_relation(existing_relation) %}
     {% endif %}
-    {% set build_sql = get_delete_insert_merge_sql(target_relation, temp_relation, unique_key, dest_columns) %}
+
+    {#-- Get the incremental_strategy, the macro to use for the strategy, and build the sql --#}
+    {% set incremental_strategy = config.get('incremental_strategy') or 'default' %}
+    {% set incremental_predicates = config.get('incremental_predicates', none) %}
+    {% set strategy_sql_macro_func = adapter.get_incremental_strategy_macro(context, incremental_strategy) %}
+    {% set strategy_arg_dict = ({'target_relation': target_relation, 'temp_relation': temp_relation, 'unique_key': unique_key, 'dest_columns': dest_columns, 'predicates': incremental_predicates }) %}
+    {% set build_sql = strategy_sql_macro_func(strategy_arg_dict) %}
 
   {% endif %}
 

core/dbt/include/global_project/macros/materializations/models/incremental/merge.sql

@@ -5,7 +5,9 @@
 {% macro default__get_merge_sql(target, source, unique_key, dest_columns, predicates) -%}
     {%- set predicates = [] if predicates is none else [] + predicates -%}
     {%- set dest_cols_csv = get_quoted_csv(dest_columns | map(attribute="name")) -%}
-    {%- set update_columns = config.get('merge_update_columns', default = dest_columns | map(attribute="quoted") | list) -%}
+    {%- set merge_update_columns = config.get('merge_update_columns') -%}
+    {%- set merge_exclude_columns = config.get('merge_exclude_columns') -%}
+    {%- set update_columns = get_merge_update_columns(merge_update_columns, merge_exclude_columns, dest_columns) -%}
     {%- set sql_header = config.get('sql_header', none) -%}
 
     {% if unique_key %}
@@ -75,7 +77,7 @@
             );
 
         {% endif %}
-        {% endif %}
+    {% endif %}
 
     insert into {{ target }} ({{ dest_cols_csv }})
     (
@@ -91,6 +93,10 @@
 {%- endmacro %}
 
 {% macro default__get_insert_overwrite_merge_sql(target, source, dest_columns, predicates, include_sql_header) -%}
+    {#-- The only time include_sql_header is True: --#}
+    {#-- BigQuery + insert_overwrite strategy + "static" partitions config --#}
+    {#-- We should consider including the sql header at the materialization level instead --#}
+
     {%- set predicates = [] if predicates is none else [] + predicates -%}
     {%- set dest_cols_csv = get_quoted_csv(dest_columns | map(attribute="name")) -%}
     {%- set sql_header = config.get('sql_header', none) -%}

core/dbt/include/global_project/macros/materializations/models/incremental/on_schema_change.sql

@@ -119,6 +119,11 @@
                 - set the `on_schema_change` config to either append_new_columns or sync_all_columns, depending on your situation.
                 - Re-run the incremental model with `full_refresh: True` to update the target schema.
                 - update the schema manually and re-run the process.
+
+              Additional troubleshooting context:
+                 Source columns not in target: {{ schema_changes_dict['source_not_in_target'] }}
+                 Target columns not in source: {{ schema_changes_dict['target_not_in_source'] }}
+                 New column types: {{ schema_changes_dict['new_target_types'] }}
           {% endset %}
 
           {% do exceptions.raise_compiler_error(fail_msg) %}

core/dbt/include/global_project/macros/materializations/models/incremental/strategies.sql

@@ -0,0 +1,79 @@
+{% macro get_incremental_append_sql(arg_dict) %}
+
+  {{ return(adapter.dispatch('get_incremental_append_sql', 'dbt')(arg_dict)) }}
+
+{% endmacro %}
+
+
+{% macro default__get_incremental_append_sql(arg_dict) %}
+
+  {% do return(get_insert_into_sql(arg_dict["target_relation"], arg_dict["temp_relation"], arg_dict["dest_columns"])) %}
+
+{% endmacro %}
+
+
+{# snowflake #}
+{% macro get_incremental_delete_insert_sql(arg_dict) %}
+
+  {{ return(adapter.dispatch('get_incremental_delete_insert_sql', 'dbt')(arg_dict)) }}
+
+{% endmacro %}
+
+{% macro default__get_incremental_delete_insert_sql(arg_dict) %}
+
+  {% do return(get_delete_insert_merge_sql(arg_dict["target_relation"], arg_dict["temp_relation"], arg_dict["unique_key"], arg_dict["dest_columns"])) %}
+
+{% endmacro %}
+
+
+{# snowflake, bigquery, spark #}
+{% macro get_incremental_merge_sql(arg_dict) %}
+
+  {{ return(adapter.dispatch('get_incremental_merge_sql', 'dbt')(arg_dict)) }}
+
+{% endmacro %}
+
+{% macro default__get_incremental_merge_sql(arg_dict) %}
+
+  {% do return(get_merge_sql(arg_dict["target_relation"], arg_dict["temp_relation"], arg_dict["unique_key"], arg_dict["dest_columns"])) %}
+
+{% endmacro %}
+
+
+{% macro get_incremental_insert_overwrite_sql(arg_dict) %}
+
+  {{ return(adapter.dispatch('get_incremental_insert_overwrite_sql', 'dbt')(arg_dict)) }}
+
+{% endmacro %}
+
+{% macro default__get_incremental_insert_overwrite_sql(arg_dict) %}
+
+  {% do return(get_insert_overwrite_merge_sql(arg_dict["target_relation"], arg_dict["temp_relation"], arg_dict["dest_columns"], arg_dict["predicates"])) %}
+
+{% endmacro %}
+
+
+{% macro get_incremental_default_sql(arg_dict) %}
+
+  {{ return(adapter.dispatch('get_incremental_default_sql', 'dbt')(arg_dict)) }}
+
+{% endmacro %}
+
+{% macro default__get_incremental_default_sql(arg_dict) %}
+
+  {% do return(get_incremental_append_sql(arg_dict)) %}
+
+{% endmacro %}
+
+
+{% macro get_insert_into_sql(target_relation, temp_relation, dest_columns) %}
+
+    {%- set dest_cols_csv = get_quoted_csv(dest_columns | map(attribute="name")) -%}
+
+    insert into {{ target_relation }} ({{ dest_cols_csv }})
+    (
+        select {{ dest_cols_csv }}
+        from {{ temp_relation }}
+    )
+
+{% endmacro %}

core/dbt/include/global_project/macros/materializations/models/table/create_table_as.sql

@@ -8,8 +8,14 @@
 
 
 /* {# keep logic under old macro name for backwards compatibility #} */
-{% macro create_table_as(temporary, relation, sql) -%}
-  {{ adapter.dispatch('create_table_as', 'dbt')(temporary, relation, sql) }}
+{% macro create_table_as(temporary, relation, compiled_code, language='sql') -%}
+  {# backward compatibility for create_table_as that does not support language #}
+  {% if language == "sql" %}
+    {{ adapter.dispatch('create_table_as', 'dbt')(temporary, relation, compiled_code)}}
+  {% else %}
+    {{ adapter.dispatch('create_table_as', 'dbt')(temporary, relation, compiled_code, language) }}
+  {% endif %}
+
 {%- endmacro %}
 
 {% macro default__create_table_as(temporary, relation, sql) -%}

core/dbt/include/global_project/macros/materializations/snapshots/snapshot.sql

@@ -28,7 +28,7 @@
 
   {% if not target_relation_exists %}
 
-      {% set build_sql = build_snapshot_table(strategy, model['compiled_sql']) %}
+      {% set build_sql = build_snapshot_table(strategy, model['compiled_code']) %}
       {% set final_sql = create_table_as(False, target_relation, build_sql) %}
 
   {% else %}

core/dbt/include/global_project/macros/materializations/snapshots/strategies.sql

@@ -46,19 +46,6 @@
     {%- endfor -%})
 {%- endmacro %}
 
-
-{#
-    Get the current time cross-db
-#}
-{% macro snapshot_get_time() -%}
-  {{ adapter.dispatch('snapshot_get_time', 'dbt')() }}
-{%- endmacro %}
-
-{% macro default__snapshot_get_time() -%}
-  {{ current_timestamp() }}
-{%- endmacro %}
-
-
 {#
     Core strategy definitions
 #}
@@ -113,12 +100,12 @@
     {%- set target_relation = adapter.get_relation(database=node.database, schema=node.schema, identifier=node.alias) -%}
 
     {% if check_cols_config == 'all' %}
-        {%- set query_columns = get_columns_in_query(node['compiled_sql']) -%}
+        {%- set query_columns = get_columns_in_query(node['compiled_code']) -%}
 
     {% elif check_cols_config is iterable and (check_cols_config | length) > 0 %}
         {#-- query for proper casing/quoting, to support comparison below --#}
         {%- set select_check_cols_from_target -%}
-          select {{ check_cols_config | join(', ') }} from ({{ node['compiled_sql'] }}) subq
+          select {{ check_cols_config | join(', ') }} from ({{ node['compiled_code'] }}) subq
         {%- endset -%}
         {% set query_columns = get_columns_in_query(select_check_cols_from_target) %}
 

core/dbt/include/global_project/macros/python_model/python.sql

@@ -0,0 +1,85 @@
+{% macro build_ref_function(model) %}
+
+    {%- set ref_dict = {} -%}
+    {%- for _ref in model.refs -%}
+        {%- set resolved = ref(*_ref) -%}
+        {%- do ref_dict.update({_ref | join("."): resolved.quote(database=False, schema=False, identifier=False) | string}) -%}
+    {%- endfor -%}
+
+def ref(*args,dbt_load_df_function):
+    refs = {{ ref_dict | tojson }}
+    key = ".".join(args)
+    return dbt_load_df_function(refs[key])
+
+{% endmacro %}
+
+{% macro build_source_function(model) %}
+
+    {%- set source_dict = {} -%}
+    {%- for _source in model.sources -%}
+        {%- set resolved = source(*_source) -%}
+        {%- do source_dict.update({_source | join("."): resolved.quote(database=False, schema=False, identifier=False) | string}) -%}
+    {%- endfor -%}
+
+def source(*args, dbt_load_df_function):
+    sources = {{ source_dict | tojson }}
+    key = ".".join(args)
+    return dbt_load_df_function(sources[key])
+
+{% endmacro %}
+
+{% macro build_config_dict(model) %}
+    {%- set config_dict = {} -%}
+    {%- for key in model.config.config_keys_used -%}
+        {# weird type testing with enum, would be much easier to write this logic in Python! #}
+        {%- if key == 'language' -%}
+          {%- set value = 'python' -%}
+        {%- endif -%}
+        {%- set value = model.config[key] -%}
+        {%- do config_dict.update({key: value}) -%}
+    {%- endfor -%}
+config_dict = {{ config_dict }}
+{% endmacro %}
+
+{% macro py_script_postfix(model) %}
+# This part is user provided model code
+# you will need to copy the next section to run the code
+# COMMAND ----------
+# this part is dbt logic for get ref work, do not modify
+
+{{ build_ref_function(model ) }}
+{{ build_source_function(model ) }}
+{{ build_config_dict(model) }}
+
+class config:
+    def __init__(self, *args, **kwargs):
+        pass
+
+    @staticmethod
+    def get(key, default=None):
+        return config_dict.get(key, default)
+
+class this:
+    """dbt.this() or dbt.this.identifier"""
+    database = '{{ this.database }}'
+    schema = '{{ this.schema }}'
+    identifier = '{{ this.identifier }}'
+    def __repr__(self):
+        return '{{ this }}'
+
+
+class dbtObj:
+    def __init__(self, load_df_function) -> None:
+        self.source = lambda *args: source(*args, dbt_load_df_function=load_df_function)
+        self.ref = lambda *args: ref(*args, dbt_load_df_function=load_df_function)
+        self.config = config
+        self.this = this()
+        self.is_incremental = {{ is_incremental() }}
+
+# COMMAND ----------
+{{py_script_comment()}}
+{% endmacro %}
+
+{#-- entry point for add instuctions for running compiled_code --#}
+{%macro py_script_comment()%}
+{%endmacro%}

core/dbt/include/global_project/macros/utils/array_append.sql

@@ -0,0 +1,8 @@
+{% macro array_append(array, new_element) -%}
+  {{ return(adapter.dispatch('array_append', 'dbt')(array, new_element)) }}
+{%- endmacro %}
+
+{# new_element must be the same data type as elements in array to match postgres functionality #}
+{% macro default__array_append(array, new_element) -%}
+    array_append({{ array }}, {{ new_element }})
+{%- endmacro %}