Adding entity node to core (#6648)

* first draft

* finishing first commit

* adding testing project

* adding changie

* cleaning

* removing blocks

* fixing proto error message

* updates to events

* fixing issues

* adding test dimension

* updating schemas

* updating manfiest.json

* removing old versions from compatability

* updating

* fixes

* fixing more bugs caught by tests

* updating tests

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.3.0a1
+current_version = 1.5.0a1
 parse = (?P<major>\d+)
 	\.(?P<minor>\d+)
 	\.(?P<patch>\d+)

.changes/0.0.0.md

@@ -3,6 +3,8 @@
 For information on prior major and minor releases, see their changelogs:
 
 
+* [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)
+* [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-20230118-134804.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Adding the entity node
+time: 2023-01-18T13:48:04.487817-06:00
+custom:
+  Author: callum-mcdata
+  Issue: "6627"

.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/Under the Hood-20230113-132513.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Fix use of ConnectionReused logging event
+time: 2023-01-13T13:25:13.023168-05:00
+custom:
+  Author: gshank
+  Issue: "6168"

.changes/unreleased/Under the Hood-20230117-111737.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Update deprecated github action command
+time: 2023-01-17T11:17:37.046095-06:00
+custom:
+  Author: davidbloss
+  Issue: "6153"

.changie.yaml

@@ -6,56 +6,122 @@ changelogPath: CHANGELOG.md
 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}}))'
+changeFormat: |-
+  {{- $IssueList := list }}
+  {{- $changes := splitList " " $.Custom.Issue }}
+  {{- range $issueNbr := $changes }}
+    {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/issues/nbr)" | replace "nbr" $issueNbr }}
+    {{- $IssueList = append $IssueList $changeLink  }}
+  {{- end -}}
+  - {{.Body}} ({{ range $index, $element := $IssueList }}{{if $index}}, {{end}}{{$element}}{{end}})
+
 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: |-
+      {{- $IssueList := list }}
+      {{- $changes := splitList " " $.Custom.Issue }}
+      {{- range $issueNbr := $changes }}
+        {{- $changeLink := "[dbt-docs/#nbr](https://github.com/dbt-labs/dbt-docs/issues/nbr)" | replace "nbr" $issueNbr }}
+        {{- $IssueList = append $IssueList $changeLink }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $IssueList }}{{if $index}}, {{end}}{{$element}}{{end}})
+  - label: Under the Hood
+  - label: Dependencies
+    changeFormat: |-
+      {{- $PRList := list }}
+      {{- $changes := splitList " " $.Custom.PR }}
+      {{- range $pullrequest := $changes }}
+        {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $pullrequest }}
+        {{- $PRList = append $PRList $changeLink  }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $PRList }}{{if $index}}, {{end}}{{$element}}{{end}})
+    skipGlobalChoices: true
+    additionalChoices:
+      - key: Author
+        label: GitHub Username(s) (separated by a single space if multiple)
+        type: string
+        minLength: 3
+      - key: PR
+        label: GitHub Pull Request Number (separated by a single space if multiple)
+        type: string
+        minLength: 1
+  - label: Security
+    changeFormat: |-
+      {{- $PRList := list }}
+      {{- $changes := splitList " " $.Custom.PR }}
+      {{- range $pullrequest := $changes }}
+        {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $pullrequest }}
+        {{- $PRList = append $PRList $changeLink  }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $PRList }}{{if $index}}, {{end}}{{$element}}{{end}})
+    skipGlobalChoices: true
+    additionalChoices:
+      - key: Author
+        label: GitHub Username(s) (separated by a single space if multiple)
+        type: string
+        minLength: 3
+      - key: PR
+        label: GitHub Pull Request Number (separated by a single space if multiple)
+        type: string
+        minLength: 1
+
+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)
   type: string
   minLength: 3
 - key: Issue
-  label: GitHub Issue Number
-  type: int
-  minLength: 4
-- key: PR
-  label: GitHub Pull Request Number
-  type: int
-  minLength: 4
+  label: GitHub Issue Number (separated by a single space if multiple)
+  type: string
+  minLength: 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 "michelleark" "peterallenwebb" "emmyoop" "nathaniel-may" "gshank" "leahwicz" "chenyulinx" "stu-k" "iknox-fa" "versusfacit" "mcknight-42" "jtcohen6" "aranke" "dependabot[bot]" "snyk-bot" "colin-rogers-dbt" }}
   {{- range $change := .Changes }}
     {{- $authorList := splitList " " $change.Custom.Author }}
-    {{- /* loop through all authors for a PR */}}
+    {{- /* loop through all authors for a single changelog */}}
     {{- range $author := $authorList }}
       {{- $authorLower := lower $author }}
       {{- /* we only want to include non-core team contributors */}}
       {{- if not (has $authorLower $core_team)}}
-        {{- $pr := $change.Custom.PR }}
-        {{- /* check if this contributor has other PRs associated with them already */}}
-        {{- if hasKey $contributorDict $author }}
-          {{- $prList := get $contributorDict $author }}
-          {{- $prList = append $prList $pr  }}
-          {{- $contributorDict := set $contributorDict $author $prList }}
-        {{- else }}
-          {{- $prList := list $change.Custom.PR }}
-          {{- $contributorDict := set $contributorDict $author $prList }}
-        {{- end }}
-      {{- end}}
+        {{- $changeList := splitList " " $change.Custom.Author }}
+          {{- /* Docs kind link back to dbt-docs instead of dbt-core issues */}}
+          {{- $changeLink := $change.Kind }}
+          {{- if or (eq $change.Kind "Dependencies") (eq $change.Kind "Security") }}
+            {{- $changeLink = "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $change.Custom.PR }}
+          {{- else if eq $change.Kind "Docs"}}
+            {{- $changeLink = "[dbt-docs/#nbr](https://github.com/dbt-labs/dbt-docs/issues/nbr)" | replace "nbr" $change.Custom.Issue }}
+          {{- else }}
+            {{- $changeLink = "[#nbr](https://github.com/dbt-labs/dbt-core/issues/nbr)" | replace "nbr" $change.Custom.Issue }}
+          {{- end }}
+          {{- /* check if this contributor has other changes associated with them already */}}
+          {{- if hasKey $contributorDict $author }}
+            {{- $contributionList := get $contributorDict $author }}
+            {{- $contributionList = append $contributionList $changeLink  }}
+            {{- $contributorDict := set $contributorDict $author $contributionList }}
+          {{- else }}
+            {{- $contributionList := list $changeLink }}
+            {{- $contributorDict := set $contributorDict $author $contributionList }}
+          {{- end }}
+        {{- end}}
     {{- end}}
   {{- end }}
   {{- /* no indentation here for formatting so the final markdown doesn't have unneeded indentations */}}
   {{- 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 }}

.flake8

@@ -9,4 +9,4 @@ ignore =
     E203 # makes Flake8 work like black
     E741
     E501 # long line checking is done in black
-exclude = test
+exclude = test/

.gitattributes

@@ -0,0 +1,2 @@
+core/dbt/include/index.html binary
+tests/functional/artifacts/data/state/*/manifest.json binary

.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-${{ steps.filename_time.outputs.time }}.yaml
+          echo "FILEPATH=$FILEPATH" >> $GITHUB_OUTPUT
+  ```
+
+- 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 "important_path='performance/runner/Cargo.toml'" >> $GITHUB_OUTPUT
+        echo "release_id=${{github.event.inputs.release_id}}" >> $GITHUB_OUTPUT
+        echo "open_prs=${{github.event.inputs.open_prs}}" >> $GITHUB_OUTPUT
+
+  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/actions/latest-wrangler/main.py

@@ -28,11 +28,12 @@ if __name__ == "__main__":
     if package_request.status_code == 404:
         if halt_on_missing:
             sys.exit(1)
-        else:
-            # everything is the latest if the package doesn't exist
-            print(f"::set-output name=latest::{True}")
-            print(f"::set-output name=minor_latest::{True}")
-            sys.exit(0)
+        # everything is the latest if the package doesn't exist
+        github_output = os.environ.get("GITHUB_OUTPUT")
+        with open(github_output, "at", encoding="utf-8") as gh_output:
+            gh_output.write("latest=True")
+            gh_output.write("minor_latest=True")
+        sys.exit(0)
 
     # TODO: verify package meta is "correct"
     # https://github.com/dbt-labs/dbt-core/issues/4640
@@ -91,5 +92,7 @@ if __name__ == "__main__":
     latest = is_latest(pre_rel, new_version, current_latest)
     minor_latest = is_latest(pre_rel, new_version, current_minor_latest)
 
-    print(f"::set-output name=latest::{latest}")
-    print(f"::set-output name=minor_latest::{minor_latest}")
+    github_output = os.environ.get("GITHUB_OUTPUT")
+    with open(github_output, "at", encoding="utf-8") as gh_output:
+        gh_output.write(f"latest={latest}")
+        gh_output.write(f"minor_latest={minor_latest}")

.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: "Dependencies"
+          - 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  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/generate-cli-api-docs.yml

@@ -0,0 +1,165 @@
+# **what?**
+# On push, if anything in core/dbt/docs or core/dbt/cli has been
+# created or modified, regenerate the CLI API docs using sphinx.
+
+# **why?**
+# We watch for changes in core/dbt/cli because the CLI API docs rely on click
+# and all supporting flags/params to be generated. We watch for changes in
+# core/dbt/docs since any changes to sphinx configuration or any of the
+# .rst files there could result in a differently build final index.html file.
+
+# **when?**
+# Whenever a change has been pushed to a branch, and only if there is a diff
+# between the PR branch and main's core/dbt/cli and or core/dbt/docs dirs.
+
+# TODO: add bot comment to PR informing contributor that the docs have been committed
+# TODO: figure out why github action triggered pushes cause github to fail to report
+#       the status of jobs
+
+name: Generate CLI API docs
+
+on:
+  pull_request:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+env:
+  CLI_DIR: ${{ github.workspace }}/core/dbt/cli
+  DOCS_DIR: ${{ github.workspace }}/core/dbt/docs
+  DOCS_BUILD_DIR: ${{ github.workspace }}/core/dbt/docs/build
+
+jobs:
+  check_gen:
+    name: check if generation needed
+    runs-on: ubuntu-latest
+    if: ${{ github.event.pull_request.head.repo.fork == false }}
+    outputs:
+      cli_dir_changed: ${{ steps.check_cli.outputs.cli_dir_changed }}
+      docs_dir_changed: ${{ steps.check_docs.outputs.docs_dir_changed }}
+
+    steps:
+    - name: "[DEBUG] print variables"
+      run: |
+        echo "env.CLI_DIR:        ${{ env.CLI_DIR }}"
+        echo "env.DOCS_BUILD_DIR: ${{ env.DOCS_BUILD_DIR }}"
+        echo "env.DOCS_DIR:       ${{ env.DOCS_DIR }}"
+
+    - name: git checkout
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 0
+        ref: ${{ github.head_ref }}
+
+    - name: set shas
+      id: set_shas
+      run: |
+        THIS_SHA=$(git rev-parse @)
+        LAST_SHA=$(git rev-parse @~1)
+
+        echo "this sha: $THIS_SHA"
+        echo "last sha: $LAST_SHA"
+
+        echo "this_sha=$THIS_SHA" >> $GITHUB_OUTPUT
+        echo "last_sha=$LAST_SHA" >> $GITHUB_OUTPUT
+
+    - name: check for changes in core/dbt/cli
+      id: check_cli
+      run: |
+        CLI_DIR_CHANGES=$(git diff \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.CLI_DIR }})
+
+        if [ -n "$CLI_DIR_CHANGES" ]; then
+          echo "changes found"
+          echo $CLI_DIR_CHANGES
+          echo "cli_dir_changed=true" >> $GITHUB_OUTPUT
+          exit 0
+        fi
+        echo "cli_dir_changed=false" >> $GITHUB_OUTPUT
+        echo "no changes found"
+
+    - name: check for changes in core/dbt/docs
+      id: check_docs
+      if: steps.check_cli.outputs.cli_dir_changed == 'false'
+      run: |
+        DOCS_DIR_CHANGES=$(git diff --name-only \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.DOCS_DIR }} ':!${{ env.DOCS_BUILD_DIR }}')
+
+        DOCS_BUILD_DIR_CHANGES=$(git diff --name-only \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.DOCS_BUILD_DIR }})
+
+        if [ -n "$DOCS_DIR_CHANGES" ] && [ -z "$DOCS_BUILD_DIR_CHANGES" ]; then
+          echo "changes found"
+          echo $DOCS_DIR_CHANGES
+          echo "docs_dir_changed=true" >> $GITHUB_OUTPUT
+          exit 0
+        fi
+        echo "docs_dir_changed=false" >> $GITHUB_OUTPUT
+        echo "no changes found"
+
+  gen_docs:
+    name: generate docs
+    runs-on: ubuntu-latest
+    needs: [check_gen]
+    if: |
+      needs.check_gen.outputs.cli_dir_changed == 'true'
+      || needs.check_gen.outputs.docs_dir_changed == 'true'
+
+    steps:
+      - name: "[DEBUG] print variables"
+        run: |
+          echo "env.DOCS_DIR:    ${{ env.DOCS_DIR }}"
+          echo "github head_ref: ${{ github.head_ref }}"
+
+      - name: git checkout
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ github.head_ref }}
+
+      - name: install python
+        uses: actions/setup-python@v4.3.0
+        with:
+          python-version: 3.8
+
+      - name: install dev requirements
+        run: |
+          python3 -m venv env
+          source env/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt -r dev-requirements.txt
+
+      - name: generate docs
+        run: |
+          source env/bin/activate
+          cd ${{ env.DOCS_DIR }}
+
+          echo "cleaning existing docs"
+          make clean
+
+          echo "creating docs"
+          make html
+
+      - name: debug
+        run: |
+          echo ">>>>> status"
+          git status
+          echo ">>>>> remotes"
+          git remote -v
+          echo ">>>>> branch"
+          git branch -v
+          echo ">>>>> log"
+          git log --pretty=oneline | head -5
+
+      - name: commit docs
+        run: |
+          git config user.name 'Github Build Bot'
+          git config user.email 'buildbot@fishtownanalytics.com'
+          git commit -am "Add generated CLI API docs"
+          git push -u origin ${{ github.head_ref }}

.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/main.yml

@@ -45,7 +45,9 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
+        with:
+          python-version: '3.8'
 
       - name: Install python dependencies
         run: |
@@ -71,7 +73,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
 
     env:
       TOXENV: "unit"
@@ -82,7 +84,7 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -99,7 +101,9 @@ jobs:
       - name: Get current date
         if: always()
         id: date
-        run: echo "::set-output name=date::$(date +'%Y-%m-%dT%H_%M_%S')" #no colons allowed for artifacts
+        run: |
+          CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
+          echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
 
       - uses: actions/upload-artifact@v2
         if: always()
@@ -116,8 +120,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10"]
-        os: [ubuntu-latest]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        os: [ubuntu-20.04]
         include:
           - python-version: 3.8
             os: windows-latest
@@ -137,7 +141,7 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -166,7 +170,9 @@ jobs:
       - name: Get current date
         if: always()
         id: date
-        run: echo "::set-output name=date::$(date +'%Y_%m_%dT%H_%M_%S')" #no colons allowed for artifacts
+        run: |
+          CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
+          echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
 
       - uses: actions/upload-artifact@v2
         if: always()
@@ -190,9 +196,9 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
-          python-version: 3.8
+          python-version: '3.8'
 
       - name: Install python dependencies
         run: |

.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, 1.3.latest, main]
 
     steps:
     - name: Call CI workflow for ${{ matrix.branch }} branch

.github/workflows/release-docker.yml

@@ -41,9 +41,9 @@ jobs:
         id: version
         run: |
           IFS="." read -r MAJOR MINOR PATCH <<< ${{ github.event.inputs.version_number }}
-          echo "::set-output name=major::$MAJOR"
-          echo "::set-output name=minor::$MINOR"
-          echo "::set-output name=patch::$PATCH"
+          echo "major=$MAJOR" >> $GITHUB_OUTPUT
+          echo "minor=$MINOR" >> $GITHUB_OUTPUT
+          echo "patch=$PATCH" >> $GITHUB_OUTPUT
 
       - name: Is pkg 'latest'
         id: latest
@@ -70,8 +70,10 @@ jobs:
       - name: Get docker build arg
         id: build_arg
         run: |
-          echo "::set-output name=build_arg_name::"$(echo ${{ github.event.inputs.package }} | sed 's/\-/_/g')
-          echo "::set-output name=build_arg_value::"$(echo ${{ github.event.inputs.package }} | sed 's/postgres/core/g')
+          BUILD_ARG_NAME=$(echo ${{ github.event.inputs.package }} | sed 's/\-/_/g')
+          BUILD_ARG_VALUE=$(echo ${{ github.event.inputs.package }} | sed 's/postgres/core/g')
+          echo "build_arg_name=$BUILD_ARG_NAME" >> $GITHUB_OUTPUT
+          echo "build_arg_value=$BUILD_ARG_VALUE" >> $GITHUB_OUTPUT
 
       - name: Log in to the GHCR
         uses: docker/login-action@v1

.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
@@ -162,7 +165,7 @@ jobs:
         env:
           IS_PRERELEASE: ${{ contains(github.event.inputs.version_number, 'rc') ||  contains(github.event.inputs.version_number, 'b') }}
         run: |
-          echo ::set-output name=isPrerelease::$IS_PRERELEASE
+          echo "isPrerelease=$IS_PRERELEASE" >> $GITHUB_OUTPUT
 
       - name: Creating GitHub Release
         uses: softprops/action-gh-release@v1

.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

@@ -3,15 +3,10 @@ on:
   schedule:
     - cron: "30 1 * * *"
 
+permissions:
+  issues: write
+  pull-requests: write
+
 jobs:
   stale:
-    runs-on: ubuntu-latest
-    steps:
-      # pinned at v4 (https://github.com/actions/stale/releases/tag/v4.0.0)
-      - uses: actions/stale@cdf15f641adb27a71842045a94023bef6945e3aa
-        with:
-          stale-issue-message: "This issue has been marked as Stale because it has been open for 180 days with no activity. If you would like the issue to remain open, please remove the stale label or comment on the issue, or it will be closed in 7 days."
-          stale-pr-message: "This PR has been marked as Stale because it has been open for 180 days with no activity. If you would like the PR to remain open, please remove the stale label or comment on the PR, or it will be closed in 7 days."
-          close-issue-message: "Although we are closing this issue as stale, it's not gone forever. Issues can be reopened if there is renewed community interest; add a comment to notify the maintainers."
-          # mark issues/PRs stale when they haven't seen activity in 180 days
-          days-before-stale: 180
+    uses: dbt-labs/actions/.github/workflows/stale-bot-matrix.yml@main

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

@@ -22,7 +22,7 @@ jobs:
   # run the performance measurements on the current or default branch
   test-schema:
     name: Test Log Schema
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
     env:
       # turns warnings into errors
       RUSTFLAGS: "-D warnings"
@@ -46,12 +46,6 @@ jobs:
         with:
           python-version: "3.8"
 
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-
       - name: Install python dependencies
         run: |
           pip install --user --upgrade pip
@@ -69,10 +63,3 @@ jobs:
       # we actually care if these pass, because the normal test run doesn't usually include many json log outputs
       - name: Run integration tests
         run: tox -e integration -- -nauto
-
-      # apply our schema tests to every log event from the previous step
-      # skips any output that isn't valid json
-      - uses: actions-rs/cargo@v1
-        with:
-          command: run
-          args: --manifest-path test/interop/log_parsing/Cargo.toml

.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: ${{ github.event.inputs.version_number }}
+
+      - name: Set branch value
+        id: variables
+        run: |
+          echo "BRANCH_NAME=prep-release/${{ github.event.inputs.version_number }}_$GITHUB_RUN_ID" >> $GITHUB_OUTPUT
+
+      - 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

@@ -11,6 +11,7 @@ __pycache__/
 env*/
 dbt_env/
 build/
+!core/dbt/docs/build
 develop-eggs/
 dist/
 downloads/
@@ -24,7 +25,8 @@ var/
 *.egg-info/
 .installed.cfg
 *.egg
-*.mypy_cache/
+.mypy_cache/
+.dmypy.json
 logs/
 
 # PyInstaller
@@ -95,3 +97,7 @@ venv/
 
 # vscode
 .vscode/
+*.code-workspace
+
+# poetry
+poetry.lock

.pre-commit-config.yaml

@@ -2,11 +2,11 @@
 # Eventually the hooks described here will be run as tests before merging each PR.
 
 # TODO: remove global exclusion of tests when testing overhaul is complete
-exclude: ^test/
+exclude: ^(test/|core/dbt/docs/build/)
 
 # 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
@@ -24,18 +24,13 @@ repos:
   rev: 22.3.0
   hooks:
   - id: black
-    args:
-    - "--line-length=99"
-    - "--target-version=py38"
   - id: black
     alias: black-check
     stages: [manual]
     args:
-    - "--line-length=99"
-    - "--target-version=py38"
     - "--check"
     - "--diff"
-- repo: https://gitlab.com/pycqa/flake8
+- repo: https://github.com/pycqa/flake8
   rev: 4.0.1
   hooks:
   - id: flake8

CHANGELOG.md

@@ -5,12 +5,13 @@
 - "Breaking changes" listed under a version may require action from end users or external maintainers when upgrading to that version.
 - Do not edit this file directly. This file is auto-generated using [changie](https://github.com/miniscruff/changie). 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)
 
-
 ## Previous Releases
 
 For information on prior major and minor releases, see their changelogs:
 
 
+* [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)
+* [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
 
@@ -51,7 +56,7 @@ There are some tools that will be helpful to you in developing locally. While th
 
 These are the tools used in `dbt-core` development and testing:
 
-- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, 3.8, 3.9, and 3.10
+- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, 3.8, 3.9, 3.10 and 3.11
 - [`pytest`](https://docs.pytest.org/en/latest/) to define, discover, and run tests
 - [`flake8`](https://flake8.pycqa.org/en/latest/) for code linting
 - [`black`](https://github.com/psf/black) for code formatting
@@ -91,12 +96,15 @@ brew install postgresql
 
 ### Installation
 
-First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment).  Also ensure you have the latest version of pip installed with `pip install --upgrade pip`. Next, install `dbt-core` (and its dependencies) with:
+First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment).  Also ensure you have the latest version of pip installed with `pip install --upgrade pip`. Next, install `dbt-core` (and its dependencies):
 
 ```sh
 make dev
-# or
+```
+or, alternatively:
+```sh
 pip install -r dev-requirements.txt -r editable-requirements.txt
+pre-commit install
 ```
 
 When installed in this way, any changes you make to your local copy of the source code will be reflected immediately in your next `dbt` run.
@@ -151,11 +159,11 @@ 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`
 
-[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.7, Python 3.8, Python 3.9, and Python 3.10 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
+[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.7, Python 3.8, Python 3.9, Python 3.10 and Python 3.11 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
 
 #### `pytest`
 
@@ -174,20 +182,52 @@ 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 or modifying 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.
 
 Follow the steps to [install `changie`](https://changie.dev/guide/installation/) for your system.
 
-Once changie is installed and your PR is created, simply run `changie new` and changie will walk you through the process of creating a changelog entry.  Commit the file that's created and your changelog entry is complete!
+Once changie is installed and your PR is created for a new feature, simply run the following command and changie will walk you through the process of creating a changelog entry:
+
+```shell
+changie new
+```
+
+Commit the file that's created and your changelog entry is complete!
+
+If you are contributing to a feature already in progress, you will modify the changie yaml file in dbt/.changes/unreleased/ related to your change. If you need help finding this file, please ask within the discussion for the pull request!
 
 You don't need to worry about which `dbt-core` version your change will go into. Just create the changelog entry with `changie`, and open your PR against the `main` branch. All merged changes will be included in the next minor version of `dbt-core`. The Core maintainers _may_ choose to "backport" specific changes in order to patch older minor versions. In that case, a maintainer will take care of that backport after merging your PR, before releasing the new version of `dbt-core`.
 
 ## 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.

Dockerfile.test

@@ -49,6 +49,9 @@ RUN apt-get update \
     python3.10 \
     python3.10-dev \
     python3.10-venv \
+    python3.11 \
+    python3.11-dev \
+    python3.11-venv \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 

Makefile

@@ -6,11 +6,29 @@ ifeq ($(USE_DOCKER),true)
 	DOCKER_CMD := docker-compose run --rm test
 endif
 
-.PHONY: dev
-dev: ## Installs dbt-* packages in develop mode along with development dependencies.
+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_req
+dev_req: ## Installs dbt-* packages in develop mode along with only development dependencies.
 	@\
 	pip install -r dev-requirements.txt -r editable-requirements.txt
 
+.PHONY: dev
+dev: dev_req ## Installs dbt-* packages in develop mode along with development dependencies and pre-commit.
+	@\
+	pre-commit install
+
 .PHONY: mypy
 mypy: .env ## Runs mypy against staged changes for static type checking.
 	@\
@@ -48,13 +66,20 @@ 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 +101,7 @@ 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/README.md

@@ -2,50 +2,59 @@
 
 ## The following are individual files in this directory.
 
-### deprecations.py
-
-### flags.py
-
-### main.py
-
-### tracking.py
-
-### version.py
-
-### lib.py
-
-### node_types.py
-
-### helper_types.py
-
-### links.py
-
-### semver.py
-
-### ui.py
-
 ### compilation.py
 
+### constants.py
+
 ### dataclass_schema.py
 
+### deprecations.py
+
 ### exceptions.py
 
+### flags.py
+
+### helper_types.py
+
 ### hooks.py
 
+### lib.py
+
+### links.py
+
 ### logger.py
 
+### main.py
+
+### node_types.py
+
 ### profiler.py
 
+### selected_resources.py
+
+### semver.py
+
+### tracking.py
+
+### ui.py
+
 ### utils.py
 
+### version.py
+
 
 ## The subdirectories will be documented in a README in the subdirectory
-* config
-* include
 * adapters
-* context
-* deps
-* graph
-* task
+* cli
 * clients
+* config
+* context
+* contracts
+* deps
+* docs
 * events
+* graph
+* include
+* parser
+* task
+* tests

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

@@ -2,7 +2,7 @@ from dataclasses import dataclass
 import re
 from typing import Dict, ClassVar, Any, Optional
 
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 @dataclass
@@ -12,6 +12,7 @@ class Column:
         "TIMESTAMP": "TIMESTAMP",
         "FLOAT": "FLOAT",
         "INTEGER": "INT",
+        "BOOLEAN": "BOOLEAN",
     }
     column: str
     dtype: str
@@ -84,7 +85,7 @@ class Column:
 
     def string_size(self) -> int:
         if not self.is_string():
-            raise RuntimeException("Called string_size() on non-string field!")
+            raise DbtRuntimeError("Called string_size() on non-string field!")
 
         if self.dtype == "text" or self.char_size is None:
             # char_size should never be None. Handle it reasonably just in case
@@ -123,7 +124,7 @@ class Column:
     def from_description(cls, name: str, raw_data_type: str) -> "Column":
         match = re.match(r"([^(]+)(\([^)]+\))?", raw_data_type)
         if match is None:
-            raise RuntimeException(f'Could not interpret data type "{raw_data_type}"')
+            raise DbtRuntimeError(f'Could not interpret data type "{raw_data_type}"')
         data_type, size_info = match.groups()
         char_size = None
         numeric_precision = None
@@ -136,7 +137,7 @@ class Column:
                 try:
                     char_size = int(parts[0])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[0]}" to an integer'
                     )
@@ -144,14 +145,14 @@ class Column:
                 try:
                     numeric_precision = int(parts[0])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[0]}" to an integer'
                     )
                 try:
                     numeric_scale = int(parts[1])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[1]}" to an integer'
                     )

core/dbt/adapters/base/connections.py

@@ -2,6 +2,7 @@ import abc
 import os
 from time import sleep
 import sys
+import traceback
 
 # multiprocessing.RLock is a function returning this type
 from multiprocessing.synchronize import RLock
@@ -40,14 +41,16 @@ from dbt.events.functions import fire_event
 from dbt.events.types import (
     NewConnection,
     ConnectionReused,
+    ConnectionLeftOpenInCleanup,
     ConnectionLeftOpen,
-    ConnectionLeftOpen2,
+    ConnectionClosedInCleanup,
     ConnectionClosed,
-    ConnectionClosed2,
     Rollback,
     RollbackFailed,
 )
+from dbt.events.contextvars import get_node_info
 from dbt import flags
+from dbt.utils import cast_to_str
 
 SleepTime = Union[int, float]  # As taken by time.sleep.
 AdapterHandle = Any  # Adapter connection handle objects can be any class.
@@ -88,13 +91,13 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         key = self.get_thread_identifier()
         with self.lock:
             if key not in self.thread_connections:
-                raise dbt.exceptions.InvalidConnectionException(key, list(self.thread_connections))
+                raise dbt.exceptions.InvalidConnectionError(key, list(self.thread_connections))
             return self.thread_connections[key]
 
     def set_thread_connection(self, conn: Connection) -> None:
         key = self.get_thread_identifier()
         if key in self.thread_connections:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 "In set_thread_connection, existing connection exists for {}"
             )
         self.thread_connections[key] = conn
@@ -134,47 +137,49 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :return: A context manager that handles exceptions raised by the
             underlying database.
         """
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`exception_handler` is not implemented for this adapter!"
         )
 
     def set_connection_name(self, name: Optional[str] = None) -> Connection:
-        conn_name: str
-        if name is None:
-            # if a name isn't specified, we'll re-use a single handle
-            # named 'master'
-            conn_name = "master"
-        else:
-            if not isinstance(name, str):
-                raise dbt.exceptions.CompilerException(
-                    f"For connection name, got {name} - not a string!"
-                )
-            assert isinstance(name, str)
-            conn_name = name
+        """Called by 'acquire_connection' in BaseAdapter, which is called by
+        'connection_named', called by 'connection_for(node)'.
+        Creates a connection for this thread if one doesn't already
+        exist, and will rename an existing connection."""
 
+        conn_name: str = "master" if name is None else name
+
+        # Get a connection for this thread
         conn = self.get_if_exists()
+
+        if conn and conn.name == conn_name and conn.state == "open":
+            # Found a connection and nothing to do, so just return it
+            return conn
+
         if conn is None:
+            # Create a new connection
             conn = Connection(
                 type=Identifier(self.TYPE),
-                name=None,
+                name=conn_name,
                 state=ConnectionState.INIT,
                 transaction_open=False,
                 handle=None,
                 credentials=self.profile.credentials,
             )
-            self.set_thread_connection(conn)
-
-        if conn.name == conn_name and conn.state == "open":
-            return conn
-
-        fire_event(NewConnection(conn_name=conn_name, conn_type=self.TYPE))
-
-        if conn.state == "open":
-            fire_event(ConnectionReused(conn_name=conn_name))
-        else:
             conn.handle = LazyHandle(self.open)
+            # Add the connection to thread_connections for this thread
+            self.set_thread_connection(conn)
+            fire_event(
+                NewConnection(conn_name=conn_name, conn_type=self.TYPE, node_info=get_node_info())
+            )
+        else:  # existing connection either wasn't open or didn't have the right name
+            if conn.state != "open":
+                conn.handle = LazyHandle(self.open)
+            if conn.name != conn_name:
+                orig_conn_name: str = conn.name or ""
+                conn.name = conn_name
+                fire_event(ConnectionReused(orig_conn_name=orig_conn_name, conn_name=conn_name))
 
-        conn.name = conn_name
         return conn
 
     @classmethod
@@ -206,7 +211,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             connect should trigger a retry.
         :type retryable_exceptions: Iterable[Type[Exception]]
         :param int retry_limit: How many times to retry the call to connect. If this limit
-            is exceeded before a successful call, a FailedToConnectException will be raised.
+            is exceeded before a successful call, a FailedToConnectError will be raised.
             Must be non-negative.
         :param retry_timeout: Time to wait between attempts to connect. Can also take a
             Callable that takes the number of attempts so far, beginning at 0, and returns an int
@@ -215,14 +220,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :param int _attempts: Parameter used to keep track of the number of attempts in calling the
             connect function across recursive calls. Passed as an argument to retry_timeout if it
             is a Callable. This parameter should not be set by the initial caller.
-        :raises dbt.exceptions.FailedToConnectException: Upon exhausting all retry attempts without
+        :raises dbt.exceptions.FailedToConnectError: Upon exhausting all retry attempts without
             successfully acquiring a handle.
         :return: The given connection with its appropriate state and handle attributes set
             depending on whether we successfully acquired a handle or not.
         """
         timeout = retry_timeout(_attempts) if callable(retry_timeout) else retry_timeout
         if timeout < 0:
-            raise dbt.exceptions.FailedToConnectException(
+            raise dbt.exceptions.FailedToConnectError(
                 "retry_timeout cannot be negative or return a negative time."
             )
 
@@ -230,7 +235,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             # This guard is not perfect others may add to the recursion limit (e.g. built-ins).
             connection.handle = None
             connection.state = ConnectionState.FAIL
-            raise dbt.exceptions.FailedToConnectException("retry_limit cannot be negative")
+            raise dbt.exceptions.FailedToConnectError("retry_limit cannot be negative")
 
         try:
             connection.handle = connect()
@@ -241,7 +246,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             if retry_limit <= 0:
                 connection.handle = None
                 connection.state = ConnectionState.FAIL
-                raise dbt.exceptions.FailedToConnectException(str(e))
+                raise dbt.exceptions.FailedToConnectError(str(e))
 
             logger.debug(
                 f"Got a retryable error when attempting to open a {cls.TYPE} connection.\n"
@@ -263,12 +268,12 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         except Exception as e:
             connection.handle = None
             connection.state = ConnectionState.FAIL
-            raise dbt.exceptions.FailedToConnectException(str(e))
+            raise dbt.exceptions.FailedToConnectError(str(e))
 
     @abc.abstractmethod
     def cancel_open(self) -> Optional[List[str]]:
         """Cancel all open connections on the adapter. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`cancel_open` is not implemented for this adapter!"
         )
 
@@ -283,7 +288,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         This should be thread-safe, or hold the lock if necessary. The given
         connection should not be in either in_use or available.
         """
-        raise dbt.exceptions.NotImplementedException("`open` is not implemented for this adapter!")
+        raise dbt.exceptions.NotImplementedError("`open` is not implemented for this adapter!")
 
     def release(self) -> None:
         with self.lock:
@@ -304,9 +309,9 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         with self.lock:
             for connection in self.thread_connections.values():
                 if connection.state not in {"closed", "init"}:
-                    fire_event(ConnectionLeftOpen(conn_name=connection.name))
+                    fire_event(ConnectionLeftOpenInCleanup(conn_name=cast_to_str(connection.name)))
                 else:
-                    fire_event(ConnectionClosed(conn_name=connection.name))
+                    fire_event(ConnectionClosedInCleanup(conn_name=cast_to_str(connection.name)))
                 self.close(connection)
 
             # garbage collect these connections
@@ -315,16 +320,12 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     @abc.abstractmethod
     def begin(self) -> None:
         """Begin a transaction. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
-            "`begin` is not implemented for this adapter!"
-        )
+        raise dbt.exceptions.NotImplementedError("`begin` is not implemented for this adapter!")
 
     @abc.abstractmethod
     def commit(self) -> None:
         """Commit a transaction. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
-            "`commit` is not implemented for this adapter!"
-        )
+        raise dbt.exceptions.NotImplementedError("`commit` is not implemented for this adapter!")
 
     @classmethod
     def _rollback_handle(cls, connection: Connection) -> None:
@@ -332,28 +333,40 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         try:
             connection.handle.rollback()
         except Exception:
-            fire_event(RollbackFailed(conn_name=connection.name))
+            fire_event(
+                RollbackFailed(
+                    conn_name=cast_to_str(connection.name),
+                    exc_info=traceback.format_exc(),
+                    node_info=get_node_info(),
+                )
+            )
 
     @classmethod
     def _close_handle(cls, connection: Connection) -> None:
         """Perform the actual close operation."""
         # On windows, sometimes connection handles don't have a close() attr.
         if hasattr(connection.handle, "close"):
-            fire_event(ConnectionClosed2(conn_name=connection.name))
+            fire_event(
+                ConnectionClosed(conn_name=cast_to_str(connection.name), node_info=get_node_info())
+            )
             connection.handle.close()
         else:
-            fire_event(ConnectionLeftOpen2(conn_name=connection.name))
+            fire_event(
+                ConnectionLeftOpen(
+                    conn_name=cast_to_str(connection.name), node_info=get_node_info()
+                )
+            )
 
     @classmethod
     def _rollback(cls, connection: Connection) -> None:
         """Roll back the given connection."""
         if connection.transaction_open is False:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Tried to rollback transaction on connection "
                 f'"{connection.name}", but it does not have one open!'
             )
 
-        fire_event(Rollback(conn_name=connection.name))
+        fire_event(Rollback(conn_name=cast_to_str(connection.name), node_info=get_node_info()))
         cls._rollback_handle(connection)
 
         connection.transaction_open = False
@@ -365,7 +378,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             return connection
 
         if connection.transaction_open and connection.handle:
-            fire_event(Rollback(conn_name=connection.name))
+            fire_event(Rollback(conn_name=cast_to_str(connection.name), node_info=get_node_info()))
             cls._rollback_handle(connection)
         connection.transaction_open = False
 
@@ -398,6 +411,4 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :return: A tuple of the query status and results (empty if fetch=False).
         :rtype: Tuple[AdapterResponse, agate.Table]
         """
-        raise dbt.exceptions.NotImplementedException(
-            "`execute` is not implemented for this adapter!"
-        )
+        raise dbt.exceptions.NotImplementedError("`execute` is not implemented for this adapter!")

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,
@@ -14,7 +15,6 @@ from typing import (
     List,
     Mapping,
     Iterator,
-    Union,
     Set,
 )
 
@@ -22,13 +22,20 @@ import agate
 import pytz
 
 from dbt.exceptions import (
-    raise_database_error,
-    raise_compiler_error,
-    invalid_type_error,
-    get_relation_returned_multiple_results,
-    InternalException,
-    NotImplementedException,
-    RuntimeException,
+    DbtInternalError,
+    MacroArgTypeError,
+    MacroResultError,
+    QuoteConfigTypeError,
+    NotImplementedError,
+    NullRelationCacheAttemptedError,
+    NullRelationDropAttemptedError,
+    RelationReturnedMultipleResultsError,
+    RenameToNoneAttemptedError,
+    DbtRuntimeError,
+    SnapshotTargetIncompleteError,
+    SnapshotTargetNotSnapshotTableError,
+    UnexpectedNullError,
+    UnexpectedNonTimestampError,
 )
 
 from dbt.adapters.protocol import (
@@ -37,13 +44,17 @@ from dbt.adapters.protocol import (
 )
 from dbt.clients.agate_helper import empty_table, merge_tables, table_from_rows
 from dbt.clients.jinja import MacroGenerator
-from dbt.contracts.graph.compiled import CompileResultNode, CompiledSeedNode
 from dbt.contracts.graph.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.utils import filter_null_values, executor
+from dbt.contracts.graph.nodes import ResultNode
+from dbt.events.functions import fire_event, warn_or_error
+from dbt.events.types import (
+    CacheMiss,
+    ListRelations,
+    CodeExecution,
+    CodeExecutionStatus,
+    CatalogGenerationError,
+)
+from dbt.utils import filter_null_values, executor, cast_to_str
 
 from dbt.adapters.base.connections import Connection, AdapterResponse
 from dbt.adapters.base.meta import AdapterMeta, available
@@ -54,10 +65,8 @@ from dbt.adapters.base.relation import (
     SchemaSearchMap,
 )
 from dbt.adapters.base import Column as BaseColumn
-from dbt.adapters.cache import RelationsCache, _make_key
-
-
-SeedModel = Union[ParsedSeedNode, CompiledSeedNode]
+from dbt.adapters.base import Credentials
+from dbt.adapters.cache import RelationsCache, _make_ref_key_msg
 
 
 GET_CATALOG_MACRO_NAME = "get_catalog"
@@ -66,7 +75,7 @@ FRESHNESS_MACRO_NAME = "collect_freshness"
 
 def _expect_row_value(key: str, row: agate.Row):
     if key not in row.keys():
-        raise InternalException(
+        raise DbtInternalError(
             'Got a row without "{}" column, columns: {}'.format(key, row.keys())
         )
     return row[key]
@@ -95,18 +104,10 @@ def _utc(dt: Optional[datetime], source: BaseRelation, field_name: str) -> datet
     assume the datetime is already for UTC and add the timezone.
     """
     if dt is None:
-        raise raise_database_error(
-            "Expected a non-null value when querying field '{}' of table "
-            " {} but received value 'null' instead".format(field_name, source)
-        )
+        raise UnexpectedNullError(field_name, source)
 
     elif not hasattr(dt, "tzinfo"):
-        raise raise_database_error(
-            "Expected a timestamp value when querying field '{}' of table "
-            "{} but received value of type '{}' instead".format(
-                field_name, source, type(dt).__name__
-            )
-        )
+        raise UnexpectedNonTimestampError(field_name, source, dt)
 
     elif dt.tzinfo:
         return dt.astimezone(pytz.UTC)
@@ -121,6 +122,35 @@ 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.
 
@@ -207,9 +237,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         return conn.name
 
     @contextmanager
-    def connection_named(
-        self, name: str, node: Optional[CompileResultNode] = None
-    ) -> Iterator[None]:
+    def connection_named(self, name: str, node: Optional[ResultNode] = None) -> Iterator[None]:
         try:
             if self.connections.query_header is not None:
                 self.connections.query_header.set(name, node)
@@ -221,7 +249,7 @@ class BaseAdapter(metaclass=AdapterMeta):
                 self.connections.query_header.reset()
 
     @contextmanager
-    def connection_for(self, node: CompileResultNode) -> Iterator[None]:
+    def connection_for(self, node: ResultNode) -> Iterator[None]:
         with self.connection_named(node.unique_id, node):
             yield
 
@@ -284,7 +312,9 @@ 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 +333,11 @@ 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=cast_to_str(database),
+                    schema=schema,
+                )
             )
             return False
         else:
@@ -330,7 +364,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         lowercase strings.
         """
         info_schema_name_map = SchemaSearchMap()
-        nodes: Iterator[CompileResultNode] = chain(
+        nodes: Iterator[ResultNode] = chain(
             [
                 node
                 for node in manifest.nodes.values()
@@ -381,7 +415,10 @@ 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.
@@ -396,7 +433,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         """Cache a new relation in dbt. It will show up in `list relations`."""
         if relation is None:
             name = self.nice_connection_name()
-            raise_compiler_error("Attempted to cache a null relation for {}".format(name))
+            raise NullRelationCacheAttemptedError(name)
         self.cache.add(relation)
         # so jinja doesn't render things
         return ""
@@ -408,7 +445,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         """
         if relation is None:
             name = self.nice_connection_name()
-            raise_compiler_error("Attempted to drop a null relation for {}".format(name))
+            raise NullRelationDropAttemptedError(name)
         self.cache.drop(relation)
         return ""
 
@@ -425,9 +462,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             name = self.nice_connection_name()
             src_name = _relation_name(from_relation)
             dst_name = _relation_name(to_relation)
-            raise_compiler_error(
-                "Attempted to rename {} to {} for {}".format(src_name, dst_name, name)
-            )
+            raise RenameToNoneAttemptedError(src_name, dst_name, name)
 
         self.cache.rename(from_relation, to_relation)
         return ""
@@ -439,12 +474,12 @@ class BaseAdapter(metaclass=AdapterMeta):
     @abc.abstractmethod
     def date_function(cls) -> str:
         """Get the date function used by this adapter's database."""
-        raise NotImplementedException("`date_function` is not implemented for this adapter!")
+        raise NotImplementedError("`date_function` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
     def is_cancelable(cls) -> bool:
-        raise NotImplementedException("`is_cancelable` is not implemented for this adapter!")
+        raise NotImplementedError("`is_cancelable` is not implemented for this adapter!")
 
     ###
     # Abstract methods about schemas
@@ -452,7 +487,7 @@ class BaseAdapter(metaclass=AdapterMeta):
     @abc.abstractmethod
     def list_schemas(self, database: str) -> List[str]:
         """Get a list of existing schemas in database"""
-        raise NotImplementedException("`list_schemas` is not implemented for this adapter!")
+        raise NotImplementedError("`list_schemas` is not implemented for this adapter!")
 
     @available.parse(lambda *a, **k: False)
     def check_schema_exists(self, database: str, schema: str) -> bool:
@@ -475,13 +510,13 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         *Implementors must call self.cache.drop() to preserve cache state!*
         """
-        raise NotImplementedException("`drop_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`drop_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
     def truncate_relation(self, relation: BaseRelation) -> None:
         """Truncate the given relation."""
-        raise NotImplementedException("`truncate_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`truncate_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
@@ -490,15 +525,13 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         Implementors must call self.cache.rename() to preserve cache state.
         """
-        raise NotImplementedException("`rename_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`rename_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_list
     def get_columns_in_relation(self, relation: BaseRelation) -> List[BaseColumn]:
         """Get a list of the columns in the given Relation."""
-        raise NotImplementedException(
-            "`get_columns_in_relation` is not implemented for this adapter!"
-        )
+        raise NotImplementedError("`get_columns_in_relation` is not implemented for this adapter!")
 
     @available.deprecated("get_columns_in_relation", lambda *a, **k: [])
     def get_columns_in_table(self, schema: str, identifier: str) -> List[BaseColumn]:
@@ -520,7 +553,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param self.Relation current: A relation that currently exists in the
             database with columns of unspecified types.
         """
-        raise NotImplementedException(
+        raise NotImplementedError(
             "`expand_target_column_types` is not implemented for this adapter!"
         )
 
@@ -535,8 +568,8 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The relations in schema
         :rtype: List[self.Relation]
         """
-        raise NotImplementedException(
-            "`list_relations_without_caching` is not implemented for this " "adapter!"
+        raise NotImplementedError(
+            "`list_relations_without_caching` is not implemented for this adapter!"
         )
 
     ###
@@ -577,7 +610,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         to_relation.
         """
         if not isinstance(from_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="get_missing_columns",
                 arg_name="from_relation",
                 got_value=from_relation,
@@ -585,7 +618,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             )
 
         if not isinstance(to_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="get_missing_columns",
                 arg_name="to_relation",
                 got_value=to_relation,
@@ -606,11 +639,11 @@ class BaseAdapter(metaclass=AdapterMeta):
         expected columns.
 
         :param Relation relation: The relation to check
-        :raises CompilationException: If the columns are
+        :raises InvalidMacroArgType: If the columns are
             incorrect.
         """
         if not isinstance(relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="valid_snapshot_target",
                 arg_name="relation",
                 got_value=relation,
@@ -631,24 +664,16 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         if missing:
             if extra:
-                msg = (
-                    'Snapshot target has ("{}") but not ("{}") - is it an '
-                    "unmigrated previous version archive?".format(
-                        '", "'.join(extra), '", "'.join(missing)
-                    )
-                )
+                raise SnapshotTargetIncompleteError(extra, missing)
             else:
-                msg = 'Snapshot target is not a snapshot table (missing "{}")'.format(
-                    '", "'.join(missing)
-                )
-            raise_compiler_error(msg)
+                raise SnapshotTargetNotSnapshotTableError(missing)
 
     @available.parse_none
     def expand_target_column_types(
         self, from_relation: BaseRelation, to_relation: BaseRelation
     ) -> None:
         if not isinstance(from_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="expand_target_column_types",
                 arg_name="from_relation",
                 got_value=from_relation,
@@ -656,7 +681,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             )
 
         if not isinstance(to_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="expand_target_column_types",
                 arg_name="to_relation",
                 got_value=to_relation,
@@ -670,7 +695,10 @@ 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 +706,9 @@ 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=cast_to_str(database),
+                schema=schema,
+                relations=[_make_ref_key_msg(x) for x in relations],
             )
         )
 
@@ -733,7 +763,7 @@ class BaseAdapter(metaclass=AdapterMeta):
                 "schema": schema,
                 "database": database,
             }
-            get_relation_returned_multiple_results(kwargs, matches)
+            raise RelationReturnedMultipleResultsError(kwargs, matches)
 
         elif matches:
             return matches[0]
@@ -755,20 +785,20 @@ class BaseAdapter(metaclass=AdapterMeta):
     @available.parse_none
     def create_schema(self, relation: BaseRelation):
         """Create the given schema if it does not exist."""
-        raise NotImplementedException("`create_schema` is not implemented for this adapter!")
+        raise NotImplementedError("`create_schema` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
     def drop_schema(self, relation: BaseRelation):
         """Drop the given schema (and everything in it) if it exists."""
-        raise NotImplementedException("`drop_schema` is not implemented for this adapter!")
+        raise NotImplementedError("`drop_schema` is not implemented for this adapter!")
 
     @available
     @classmethod
     @abc.abstractmethod
     def quote(cls, identifier: str) -> str:
         """Quote the given identifier, as appropriate for the database."""
-        raise NotImplementedException("`quote` is not implemented for this adapter!")
+        raise NotImplementedError("`quote` is not implemented for this adapter!")
 
     @available
     def quote_as_configured(self, identifier: str, quote_key: str) -> str:
@@ -797,10 +827,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         elif quote_config is None:
             pass
         else:
-            raise_compiler_error(
-                f'The seed configuration value of "quote_columns" has an '
-                f"invalid type {type(quote_config)}"
-            )
+            raise QuoteConfigTypeError(quote_config)
 
         if quote_columns:
             return self.quote(column)
@@ -821,7 +848,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_text_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_text_type` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
@@ -833,7 +860,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_number_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_number_type` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
@@ -845,9 +872,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException(
-            "`convert_boolean_type` is not implemented for this adapter!"
-        )
+        raise NotImplementedError("`convert_boolean_type` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
@@ -859,9 +884,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException(
-            "`convert_datetime_type` is not implemented for this adapter!"
-        )
+        raise NotImplementedError("`convert_datetime_type` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
@@ -873,7 +896,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_date_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_date_type` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
@@ -885,7 +908,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_time_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_time_type` is not implemented for this adapter!")
 
     @available
     @classmethod
@@ -952,7 +975,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             else:
                 package_name = 'the "{}" package'.format(project)
 
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 'dbt could not find a macro with the name "{}" in {}'.format(
                     macro_name, package_name
                 )
@@ -1050,11 +1073,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         # now we have a 1-row table of the maximum `loaded_at_field` value and
         # the current time according to the db.
         if len(table) != 1 or len(table[0]) != 2:
-            raise_compiler_error(
-                'Got an invalid result from "{}" macro: {}'.format(
-                    FRESHNESS_MACRO_NAME, [tuple(r) for r in table]
-                )
-            )
+            raise MacroResultError(FRESHNESS_MACRO_NAME, table)
         if table[0][0] is None:
             # no records in the table, so really the max_loaded_at was
             # infinitely long ago. Just call it 0:00 January 1 year UTC
@@ -1131,7 +1150,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         elif location == "prepend":
             return f"'{value}' || {add_to}"
         else:
-            raise RuntimeException(f'Got an unexpected location value of "{location}"')
+            raise DbtRuntimeError(f'Got an unexpected location value of "{location}"')
 
     def get_rows_different_sql(
         self,
@@ -1162,6 +1181,74 @@ 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 NotImplementedError(
+            "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 DbtRuntimeError(
+                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 DbtRuntimeError(
+                '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 (
@@ -1209,7 +1296,7 @@ def catch_as_completed(
         elif isinstance(exc, KeyboardInterrupt) or not isinstance(exc, Exception):
             raise exc
         else:
-            warn_or_error(f"Encountered an error while generating catalog: {str(exc)}")
+            warn_or_error(CatalogGenerationError(exc=str(exc)))
             # exc is not None, derives from Exception, and isn't ctrl+c
             exceptions.append(exc)
     return merge_tables(tables), exceptions

core/dbt/adapters/base/plugin.py

@@ -1,7 +1,7 @@
 from typing import List, Optional, Type
 
 from dbt.adapters.base import Credentials
-from dbt.exceptions import CompilationException
+from dbt.exceptions import CompilationError
 from dbt.adapters.protocol import AdapterProtocol
 
 
@@ -11,7 +11,7 @@ def project_name_from_path(include_path: str) -> str:
 
     partial = Project.partial_load(include_path)
     if partial.project_name is None:
-        raise CompilationException(f"Invalid project at {include_path}: name not set!")
+        raise CompilationError(f"Invalid project at {include_path}: name not set!")
     return partial.project_name
 
 

core/dbt/adapters/base/query_headers.py

@@ -5,9 +5,9 @@ from dbt.clients.jinja import QueryStringGenerator
 
 from dbt.context.manifest import generate_query_header_context
 from dbt.contracts.connection import AdapterRequiredConfig, QueryComment
-from dbt.contracts.graph.compiled import CompileResultNode
+from dbt.contracts.graph.nodes import ResultNode
 from dbt.contracts.graph.manifest import Manifest
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 class NodeWrapper:
@@ -48,7 +48,7 @@ class _QueryComment(local):
         if isinstance(comment, str) and "*/" in comment:
             # tell the user "no" so they don't hurt themselves by writing
             # garbage
-            raise RuntimeException(f'query comment contains illegal value "*/": {comment}')
+            raise DbtRuntimeError(f'query comment contains illegal value "*/": {comment}')
         self.query_comment = comment
         self.append = append
 
@@ -90,7 +90,7 @@ class MacroQueryStringSetter:
     def reset(self):
         self.set("master", None)
 
-    def set(self, name: str, node: Optional[CompileResultNode]):
+    def set(self, name: str, node: Optional[ResultNode]):
         wrapped: Optional[NodeWrapper] = None
         if node is not None:
             wrapped = NodeWrapper(node)

core/dbt/adapters/base/relation.py

@@ -1,9 +1,8 @@
 from collections.abc import Hashable
-from dataclasses import dataclass
-from typing import Optional, TypeVar, Any, Type, Dict, Union, Iterator, Tuple, Set
+from dataclasses import dataclass, field
+from typing import Optional, TypeVar, Any, Type, Dict, Iterator, Tuple, Set
 
-from dbt.contracts.graph.compiled import CompiledNode
-from dbt.contracts.graph.parsed import ParsedSourceDefinition, ParsedNode
+from dbt.contracts.graph.nodes import SourceDefinition, ManifestNode, ResultNode, ParsedNode
 from dbt.contracts.relation import (
     RelationType,
     ComponentName,
@@ -12,7 +11,11 @@ from dbt.contracts.relation import (
     Policy,
     Path,
 )
-from dbt.exceptions import InternalException
+from dbt.exceptions import (
+    ApproximateMatchError,
+    DbtInternalError,
+    MultipleDatabasesNotAllowedError,
+)
 from dbt.node_types import NodeType
 from dbt.utils import filter_null_values, deep_merge, classproperty
 
@@ -27,8 +30,10 @@ class BaseRelation(FakeAPIObject, Hashable):
     path: Path
     type: Optional[RelationType] = None
     quote_character: str = '"'
-    include_policy: Policy = Policy()
-    quote_policy: Policy = Policy()
+    # Python 3.11 requires that these use default_factory instead of simple default
+    # ValueError: mutable default <class 'dbt.contracts.relation.Policy'> for field include_policy is not allowed: use default_factory
+    include_policy: Policy = field(default_factory=lambda: Policy())
+    quote_policy: Policy = field(default_factory=lambda: Policy())
     dbt_created: bool = False
 
     def _is_exactish_match(self, field: ComponentName, value: str) -> bool:
@@ -39,9 +44,9 @@ class BaseRelation(FakeAPIObject, Hashable):
 
     @classmethod
     def _get_field_named(cls, field_name):
-        for field, _ in cls._get_fields():
-            if field.name == field_name:
-                return field
+        for f, _ in cls._get_fields():
+            if f.name == field_name:
+                return f
         # this should be unreachable
         raise ValueError(f"BaseRelation has no {field_name} field!")
 
@@ -52,11 +57,11 @@ class BaseRelation(FakeAPIObject, Hashable):
 
     @classmethod
     def get_default_quote_policy(cls) -> Policy:
-        return cls._get_field_named("quote_policy").default
+        return cls._get_field_named("quote_policy").default_factory()
 
     @classmethod
     def get_default_include_policy(cls) -> Policy:
-        return cls._get_field_named("include_policy").default
+        return cls._get_field_named("include_policy").default_factory()
 
     def get(self, key, default=None):
         """Override `.get` to return a metadata object so we don't break
@@ -82,7 +87,7 @@ class BaseRelation(FakeAPIObject, Hashable):
 
         if not search:
             # nothing was passed in
-            raise dbt.exceptions.RuntimeException(
+            raise dbt.exceptions.DbtRuntimeError(
                 "Tried to match relation, but no search path was passed!"
             )
 
@@ -99,7 +104,7 @@ class BaseRelation(FakeAPIObject, Hashable):
 
         if approximate_match and not exact_match:
             target = self.create(database=database, schema=schema, identifier=identifier)
-            dbt.exceptions.approximate_relation_match(target, self)
+            raise ApproximateMatchError(target, self)
 
         return exact_match
 
@@ -184,7 +189,7 @@ class BaseRelation(FakeAPIObject, Hashable):
         )
 
     @classmethod
-    def create_from_source(cls: Type[Self], source: ParsedSourceDefinition, **kwargs: Any) -> Self:
+    def create_from_source(cls: Type[Self], source: SourceDefinition, **kwargs: Any) -> Self:
         source_quoting = source.quoting.to_dict(omit_none=True)
         source_quoting.pop("column", None)
         quote_policy = deep_merge(
@@ -209,7 +214,7 @@ class BaseRelation(FakeAPIObject, Hashable):
     def create_ephemeral_from_node(
         cls: Type[Self],
         config: HasQuoting,
-        node: Union[ParsedNode, CompiledNode],
+        node: ManifestNode,
     ) -> Self:
         # Note that ephemeral models are based on the name.
         identifier = cls.add_ephemeral_prefix(node.name)
@@ -222,7 +227,7 @@ class BaseRelation(FakeAPIObject, Hashable):
     def create_from_node(
         cls: Type[Self],
         config: HasQuoting,
-        node: Union[ParsedNode, CompiledNode],
+        node: ManifestNode,
         quote_policy: Optional[Dict[str, bool]] = None,
         **kwargs: Any,
     ) -> Self:
@@ -243,20 +248,20 @@ class BaseRelation(FakeAPIObject, Hashable):
     def create_from(
         cls: Type[Self],
         config: HasQuoting,
-        node: Union[CompiledNode, ParsedNode, ParsedSourceDefinition],
+        node: ResultNode,
         **kwargs: Any,
     ) -> Self:
         if node.resource_type == NodeType.Source:
-            if not isinstance(node, ParsedSourceDefinition):
-                raise InternalException(
-                    "type mismatch, expected ParsedSourceDefinition but got {}".format(type(node))
+            if not isinstance(node, SourceDefinition):
+                raise DbtInternalError(
+                    "type mismatch, expected SourceDefinition but got {}".format(type(node))
                 )
             return cls.create_from_source(node, **kwargs)
         else:
-            if not isinstance(node, (ParsedNode, CompiledNode)):
-                raise InternalException(
-                    "type mismatch, expected ParsedNode or CompiledNode but "
-                    "got {}".format(type(node))
+            # Can't use ManifestNode here because of parameterized generics
+            if not isinstance(node, (ParsedNode)):
+                raise DbtInternalError(
+                    f"type mismatch, expected ManifestNode but got {type(node)}"
                 )
             return cls.create_from_node(config, node, **kwargs)
 
@@ -353,7 +358,7 @@ class InformationSchema(BaseRelation):
 
     def __post_init__(self):
         if not isinstance(self.information_schema_view, (type(None), str)):
-            raise dbt.exceptions.CompilationException(
+            raise dbt.exceptions.CompilationError(
                 "Got an invalid name: {}".format(self.information_schema_view)
             )
 
@@ -437,7 +442,7 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
         if not allow_multiple_databases:
             seen = {r.database.lower() for r in self if r.database}
             if len(seen) > 1:
-                dbt.exceptions.raise_compiler_error(str(seen))
+                raise MultipleDatabasesNotAllowedError(seen)
 
         for information_schema_name, schema in self.search():
             path = {"database": information_schema_name.database, "schema": schema}

core/dbt/adapters/cache.py

@@ -2,26 +2,23 @@ import threading
 from copy import deepcopy
 from typing import Any, Dict, Iterable, List, Optional, Set, Tuple
 
-from dbt.adapters.reference_keys import _make_key, _ReferenceKey
-import dbt.exceptions
-from dbt.events.functions import fire_event
-from dbt.events.types import (
-    AddLink,
-    AddRelation,
-    DropCascade,
-    DropMissingRelation,
-    DropRelation,
-    DumpAfterAddGraph,
-    DumpAfterRenameSchema,
-    DumpBeforeAddGraph,
-    DumpBeforeRenameSchema,
-    RenameSchema,
-    TemporaryRelation,
-    UncachedRelation,
-    UpdateReference,
+from dbt.adapters.reference_keys import (
+    _make_ref_key,
+    _make_ref_key_msg,
+    _make_msg_from_ref_key,
+    _ReferenceKey,
 )
+from dbt.exceptions import (
+    DependentLinkNotCachedError,
+    NewNameAlreadyInCacheError,
+    NoneRelationFoundError,
+    ReferencedLinkNotCachedError,
+    TruncatedModelNameCausedCollisionError,
+)
+from dbt.events.functions import fire_event, fire_event_if
+from dbt.events.types import CacheAction, CacheDumpGraph
+import dbt.flags as flags
 from dbt.utils import lowercase
-from dbt.helper_types import Lazy
 
 
 def dot_separated(key: _ReferenceKey) -> str:
@@ -81,7 +78,7 @@ class _CachedRelation:
 
         :return _ReferenceKey: A key for this relation.
         """
-        return _make_key(self)
+        return _make_ref_key(self)
 
     def add_reference(self, referrer: "_CachedRelation"):
         """Add a reference from referrer to self, indicating that if this node
@@ -144,11 +141,7 @@ class _CachedRelation:
         :raises InternalError: If the new key already exists.
         """
         if new_key in self.referenced_by:
-            dbt.exceptions.raise_cache_inconsistent(
-                'in rename of "{}" -> "{}", new name is in the cache already'.format(
-                    old_key, new_key
-                )
-            )
+            raise NewNameAlreadyInCacheError(old_key, new_key)
 
         if old_key not in self.referenced_by:
             return
@@ -264,21 +257,17 @@ class RelationsCache:
         if referenced is None:
             return
         if referenced is None:
-            dbt.exceptions.raise_cache_inconsistent(
-                "in add_link, referenced link key {} not in cache!".format(referenced_key)
-            )
+            raise ReferencedLinkNotCachedError(referenced_key)
 
         dependent = self.relations.get(dependent_key)
         if dependent is None:
-            dbt.exceptions.raise_cache_inconsistent(
-                "in add_link, dependent link key {} not in cache!".format(dependent_key)
-            )
+            raise DependentLinkNotCachedError(dependent_key)
 
         assert dependent is not None  # we just raised!
 
         referenced.add_reference(dependent)
 
-    # TODO: Is this dead code?  I can't seem to find it grepping the codebase.
+    # This is called in plugins/postgres/dbt/adapters/postgres/impl.py
     def add_link(self, referenced, dependent):
         """Add a link between two relations to the database. If either relation
         does not exist, it will be added as an "external" relation.
@@ -293,13 +282,18 @@ class RelationsCache:
         :param BaseRelation dependent: The dependent model.
         :raises InternalError: If either entry does not exist.
         """
-        ref_key = _make_key(referenced)
-        dep_key = _make_key(dependent)
+        ref_key = _make_ref_key(referenced)
+        dep_key = _make_ref_key(dependent)
         if (ref_key.database, ref_key.schema) not in self:
             # if we have not cached the referenced schema at all, we must be
             # referring to a table outside our control. There's no need to make
             # a link - we will never drop the referenced relation during a run.
-            fire_event(UncachedRelation(dep_key=dep_key, ref_key=ref_key))
+            fire_event(
+                CacheAction(
+                    ref_key=_make_msg_from_ref_key(ref_key),
+                    ref_key_2=_make_msg_from_ref_key(dep_key),
+                )
+            )
             return
         if ref_key not in self.relations:
             # Insert a dummy "external" relation.
@@ -309,7 +303,13 @@ class RelationsCache:
             # Insert a dummy "external" relation.
             dependent = dependent.replace(type=referenced.External)
             self.add(dependent)
-        fire_event(AddLink(dep_key=dep_key, ref_key=ref_key))
+        fire_event(
+            CacheAction(
+                action="add_link",
+                ref_key=_make_msg_from_ref_key(dep_key),
+                ref_key_2=_make_msg_from_ref_key(ref_key),
+            )
+        )
         with self.lock:
             self._add_link(ref_key, dep_key)
 
@@ -320,12 +320,18 @@ class RelationsCache:
         :param BaseRelation relation: The underlying relation.
         """
         cached = _CachedRelation(relation)
-        fire_event(AddRelation(relation=_make_key(cached)))
-        fire_event(DumpBeforeAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="before", action="adding", dump=self.dump_graph()),
+        )
+        fire_event(CacheAction(action="add_relation", ref_key=_make_ref_key_msg(cached)))
 
         with self.lock:
             self._setdefault(cached)
-        fire_event(DumpAfterAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="after", action="adding", dump=self.dump_graph()),
+        )
 
     def _remove_refs(self, keys):
         """Removes all references to all entries in keys. This does not
@@ -340,19 +346,6 @@ class RelationsCache:
         for cached in self.relations.values():
             cached.release_references(keys)
 
-    def _drop_cascade_relation(self, dropped_key):
-        """Drop the given relation and cascade it appropriately to all
-        dependent relations.
-
-        :param _CachedRelation dropped: An existing _CachedRelation to drop.
-        """
-        if dropped_key not in self.relations:
-            fire_event(DropMissingRelation(relation=dropped_key))
-            return
-        consequences = self.relations[dropped_key].collect_consequences()
-        fire_event(DropCascade(dropped=dropped_key, consequences=consequences))
-        self._remove_refs(consequences)
-
     def drop(self, relation):
         """Drop the named relation and cascade it appropriately to all
         dependent relations.
@@ -364,10 +357,22 @@ class RelationsCache:
         :param str schema: The schema of the relation to drop.
         :param str identifier: The identifier of the relation to drop.
         """
-        dropped_key = _make_key(relation)
-        fire_event(DropRelation(dropped=dropped_key))
+        dropped_key = _make_ref_key(relation)
+        dropped_key_msg = _make_ref_key_msg(relation)
+        fire_event(CacheAction(action="drop_relation", ref_key=dropped_key_msg))
         with self.lock:
-            self._drop_cascade_relation(dropped_key)
+            if dropped_key not in self.relations:
+                fire_event(CacheAction(action="drop_missing_relation", ref_key=dropped_key_msg))
+                return
+            consequences = self.relations[dropped_key].collect_consequences()
+            # convert from a list of _ReferenceKeys to a list of ReferenceKeyMsgs
+            consequence_msgs = [_make_msg_from_ref_key(key) for key in consequences]
+            fire_event(
+                CacheAction(
+                    action="drop_cascade", ref_key=dropped_key_msg, ref_list=consequence_msgs
+                )
+            )
+            self._remove_refs(consequences)
 
     def _rename_relation(self, old_key, new_relation):
         """Rename a relation named old_key to new_key, updating references.
@@ -383,14 +388,20 @@ 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():
             if cached.is_referenced_by(old_key):
                 fire_event(
-                    UpdateReference(old_key=old_key, new_key=new_key, cached_key=cached.key())
+                    CacheAction(
+                        action="update_reference",
+                        ref_key=_make_ref_key_msg(old_key),
+                        ref_key_2=_make_ref_key_msg(new_key),
+                        ref_key_3=_make_ref_key_msg(cached.key()),
+                    )
                 )
+
                 cached.rename_key(old_key, new_key)
 
         self.relations[new_key] = relation
@@ -413,14 +424,14 @@ class RelationsCache:
         :raises InternalError: If the new key is already present.
         """
         if new_key in self.relations:
-            dbt.exceptions.raise_cache_inconsistent(
-                "in rename, new key {} already in cache: {}".format(
-                    new_key, list(self.relations.keys())
-                )
-            )
+            # Tell user when collision caused by model names truncated during
+            # materialization.
+            raise TruncatedModelNameCausedCollisionError(new_key, self.relations)
 
         if old_key not in self.relations:
-            fire_event(TemporaryRelation(key=old_key))
+            fire_event(
+                CacheAction(action="temporary_relation", ref_key=_make_msg_from_ref_key(old_key))
+            )
             return False
         return True
 
@@ -436,11 +447,20 @@ class RelationsCache:
         :param BaseRelation new: The new relation name information.
         :raises InternalError: If the new key is already present.
         """
-        old_key = _make_key(old)
-        new_key = _make_key(new)
-        fire_event(RenameSchema(old_key=old_key, new_key=new_key))
+        old_key = _make_ref_key(old)
+        new_key = _make_ref_key(new)
+        fire_event(
+            CacheAction(
+                action="rename_relation",
+                ref_key=_make_msg_from_ref_key(old_key),
+                ref_key_2=_make_msg_from_ref_key(new),
+            )
+        )
 
-        fire_event(DumpBeforeRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="before", action="rename", dump=self.dump_graph()),
+        )
 
         with self.lock:
             if self._check_rename_constraints(old_key, new_key):
@@ -448,7 +468,10 @@ class RelationsCache:
             else:
                 self._setdefault(_CachedRelation(new))
 
-        fire_event(DumpAfterRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="after", action="rename", dump=self.dump_graph()),
+        )
 
     def get_relations(self, database: Optional[str], schema: Optional[str]) -> List[Any]:
         """Case-insensitively yield all relations matching the given schema.
@@ -467,9 +490,7 @@ class RelationsCache:
             ]
 
         if None in results:
-            dbt.exceptions.raise_cache_inconsistent(
-                "in get_relations, a None relation was found in the cache!"
-            )
+            raise NoneRelationFoundError()
         return results
 
     def clear(self):
@@ -496,6 +517,6 @@ class RelationsCache:
         """
         for relation in to_remove:
             # it may have been cascaded out already
-            drop_key = _make_key(relation)
+            drop_key = _make_ref_key(relation)
             if drop_key in self.relations:
                 self.drop(drop_key)

core/dbt/adapters/factory.py

@@ -1,23 +1,18 @@
 import threading
-from pathlib import Path
+import traceback
+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 DbtInternalError, DbtRuntimeError
+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
 
@@ -39,7 +34,7 @@ class AdapterContainer:
             names = ", ".join(self.plugins.keys())
 
         message = f"Invalid adapter type {name}! Must be one of {names}"
-        raise RuntimeException(message)
+        raise DbtRuntimeError(message)
 
     def get_adapter_class_by_name(self, name: str) -> Type[Adapter]:
         plugin = self.get_plugin_by_name(name)
@@ -64,18 +59,18 @@ 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))
-                raise RuntimeException(f"Could not find adapter type {name}!")
+                fire_event(AdapterImportError(exc=str(exc)))
+                raise DbtRuntimeError(f"Could not find adapter type {name}!")
             # otherwise, the error had to have come from some underlying
             # library. Log the stack trace.
 
-            fire_event(PluginLoadError())
+            fire_event(PluginLoadError(exc_info=traceback.format_exc()))
             raise
         plugin: AdapterPlugin = mod.Plugin
         plugin_type = plugin.adapter.type()
 
         if plugin_type != name:
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f"Expected to find adapter with type named {name}, got "
                 f"adapter with type {plugin_type}"
             )
@@ -137,7 +132,7 @@ class AdapterContainer:
             try:
                 plugin = self.plugins[plugin_name]
             except KeyError:
-                raise InternalException(f"No plugin found for {plugin_name}") from None
+                raise DbtInternalError(f"No plugin found for {plugin_name}") from None
             plugins.append(plugin)
             seen.add(plugin_name)
             for dep in plugin.dependencies:
@@ -156,7 +151,7 @@ class AdapterContainer:
             try:
                 path = self.packages[package_name]
             except KeyError:
-                raise InternalException(f"No internal package listing found for {package_name}")
+                raise DbtInternalError(f"No internal package listing found for {package_name}")
             paths.append(path)
         return paths
 
@@ -217,3 +212,12 @@ 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

@@ -8,7 +8,6 @@ from typing import (
     Generic,
     TypeVar,
     Tuple,
-    Union,
     Dict,
     Any,
 )
@@ -17,8 +16,7 @@ from typing_extensions import Protocol
 import agate
 
 from dbt.contracts.connection import Connection, AdapterRequiredConfig, AdapterResponse
-from dbt.contracts.graph.compiled import CompiledNode, ManifestNode, NonSourceCompiledNode
-from dbt.contracts.graph.parsed import ParsedNode, ParsedSourceDefinition
+from dbt.contracts.graph.nodes import ResultNode, ManifestNode
 from dbt.contracts.graph.model_config import BaseConfig
 from dbt.contracts.graph.manifest import Manifest
 from dbt.contracts.relation import Policy, HasQuoting
@@ -48,11 +46,7 @@ class RelationProtocol(Protocol):
         ...
 
     @classmethod
-    def create_from(
-        cls: Type[Self],
-        config: HasQuoting,
-        node: Union[CompiledNode, ParsedNode, ParsedSourceDefinition],
-    ) -> Self:
+    def create_from(cls: Type[Self], config: HasQuoting, node: ResultNode) -> Self:
         ...
 
 
@@ -65,7 +59,7 @@ class CompilerProtocol(Protocol):
         node: ManifestNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestNode:
         ...
 
 
@@ -88,7 +82,7 @@ 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/adapters/reference_keys.py

@@ -2,6 +2,7 @@
 
 from collections import namedtuple
 from typing import Any, Optional
+from dbt.events.proto_types import ReferenceKeyMsg
 
 
 _ReferenceKey = namedtuple("_ReferenceKey", "database schema identifier")
@@ -14,7 +15,12 @@ def lowercase(value: Optional[str]) -> Optional[str]:
         return value.lower()
 
 
+# For backwards compatibility. New code should use _make_ref_key
 def _make_key(relation: Any) -> _ReferenceKey:
+    return _make_ref_key(relation)
+
+
+def _make_ref_key(relation: Any) -> _ReferenceKey:
     """Make _ReferenceKeys with lowercase values for the cache so we don't have
     to keep track of quoting
     """
@@ -22,3 +28,13 @@ def _make_key(relation: Any) -> _ReferenceKey:
     return _ReferenceKey(
         lowercase(relation.database), lowercase(relation.schema), lowercase(relation.identifier)
     )
+
+
+def _make_ref_key_msg(relation: Any):
+    return _make_msg_from_ref_key(_make_ref_key(relation))
+
+
+def _make_msg_from_ref_key(ref_key: _ReferenceKey) -> ReferenceKeyMsg:
+    return ReferenceKeyMsg(
+        database=ref_key.database, schema=ref_key.schema, identifier=ref_key.identifier
+    )

core/dbt/adapters/sql/connections.py

@@ -10,6 +10,8 @@ from dbt.adapters.base import BaseConnectionManager
 from dbt.contracts.connection import Connection, ConnectionState, AdapterResponse
 from dbt.events.functions import fire_event
 from dbt.events.types import ConnectionUsed, SQLQuery, SQLCommit, SQLQueryStatus
+from dbt.events.contextvars import get_node_info
+from dbt.utils import cast_to_str
 
 
 class SQLConnectionManager(BaseConnectionManager):
@@ -25,9 +27,7 @@ class SQLConnectionManager(BaseConnectionManager):
     @abc.abstractmethod
     def cancel(self, connection: Connection):
         """Cancel the given connection."""
-        raise dbt.exceptions.NotImplementedException(
-            "`cancel` is not implemented for this adapter!"
-        )
+        raise dbt.exceptions.NotImplementedError("`cancel` is not implemented for this adapter!")
 
     def cancel_open(self) -> List[str]:
         names = []
@@ -55,7 +55,13 @@ class SQLConnectionManager(BaseConnectionManager):
         connection = self.get_thread_connection()
         if auto_begin and connection.transaction_open is False:
             self.begin()
-        fire_event(ConnectionUsed(conn_type=self.TYPE, conn_name=connection.name))
+        fire_event(
+            ConnectionUsed(
+                conn_type=self.TYPE,
+                conn_name=cast_to_str(connection.name),
+                node_info=get_node_info(),
+            )
+        )
 
         with self.exception_handler(sql):
             if abridge_sql_log:
@@ -63,7 +69,11 @@ class SQLConnectionManager(BaseConnectionManager):
             else:
                 log_sql = sql
 
-            fire_event(SQLQuery(conn_name=connection.name, sql=log_sql))
+            fire_event(
+                SQLQuery(
+                    conn_name=cast_to_str(connection.name), sql=log_sql, node_info=get_node_info()
+                )
+            )
             pre = time.time()
 
             cursor = connection.handle.cursor()
@@ -71,7 +81,9 @@ class SQLConnectionManager(BaseConnectionManager):
 
             fire_event(
                 SQLQueryStatus(
-                    status=str(self.get_response(cursor)), elapsed=round((time.time() - pre), 2)
+                    status=str(self.get_response(cursor)),
+                    elapsed=round((time.time() - pre)),
+                    node_info=get_node_info(),
                 )
             )
 
@@ -81,7 +93,7 @@ class SQLConnectionManager(BaseConnectionManager):
     @abc.abstractmethod
     def get_response(cls, cursor: Any) -> AdapterResponse:
         """Get the status of the cursor."""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`get_response` is not implemented for this adapter!"
         )
 
@@ -137,7 +149,7 @@ class SQLConnectionManager(BaseConnectionManager):
     def begin(self):
         connection = self.get_thread_connection()
         if connection.transaction_open is True:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 'Tried to begin a new transaction on connection "{}", but '
                 "it already had one open!".format(connection.name)
             )
@@ -150,12 +162,12 @@ class SQLConnectionManager(BaseConnectionManager):
     def commit(self):
         connection = self.get_thread_connection()
         if connection.transaction_open is False:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 'Tried to commit transaction on connection "{}", but '
                 "it does not have one open!".format(connection.name)
             )
 
-        fire_event(SQLCommit(conn_name=connection.name))
+        fire_event(SQLCommit(conn_name=connection.name, node_info=get_node_info()))
         self.add_commit_query()
 
         connection.transaction_open = False

core/dbt/adapters/sql/impl.py

@@ -1,11 +1,10 @@
 import agate
 from typing import Any, Optional, Tuple, Type, List
 
-import dbt.clients.agate_helper
 from dbt.contracts.connection import Connection
-import dbt.exceptions
+from dbt.exceptions import RelationTypeNullError
 from dbt.adapters.base import BaseAdapter, available
-from dbt.adapters.cache import _make_key
+from dbt.adapters.cache import _make_ref_key_msg
 from dbt.adapters.sql import SQLConnectionManager
 from dbt.events.functions import fire_event
 from dbt.events.types import ColTypeChange, SchemaCreation, SchemaDrop
@@ -110,7 +109,7 @@ class SQLAdapter(BaseAdapter):
                     ColTypeChange(
                         orig_type=target_column.data_type,
                         new_type=new_type,
-                        table=_make_key(current),
+                        table=_make_ref_key_msg(current),
                     )
                 )
 
@@ -132,9 +131,7 @@ class SQLAdapter(BaseAdapter):
 
     def drop_relation(self, relation):
         if relation.type is None:
-            dbt.exceptions.raise_compiler_error(
-                "Tried to drop relation {}, but its type is null.".format(relation)
-            )
+            raise RelationTypeNullError(relation)
 
         self.cache_dropped(relation)
         self.execute_macro(DROP_RELATION_MACRO_NAME, kwargs={"relation": relation})
@@ -155,7 +152,7 @@ class SQLAdapter(BaseAdapter):
 
     def create_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        fire_event(SchemaCreation(relation=_make_key(relation)))
+        fire_event(SchemaCreation(relation=_make_ref_key_msg(relation)))
         kwargs = {
             "relation": relation,
         }
@@ -166,7 +163,7 @@ class SQLAdapter(BaseAdapter):
 
     def drop_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        fire_event(SchemaDrop(relation=_make_key(relation)))
+        fire_event(SchemaDrop(relation=_make_ref_key_msg(relation)))
         kwargs = {
             "relation": relation,
         }

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.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.warn_error_options
+@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 +1,48 @@
+from click import ParamType
+import yaml
+
+from dbt.helper_types import WarnErrorOptions
+
+
+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 WarnErrorOptionsType(YAML):
+    """The Click WarnErrorOptions type. Converts YAML strings into objects."""
+
+    name = "WarnErrorOptionsType"
+
+    def convert(self, value, param, ctx):
+        include_exclude = super().convert(value, param, ctx)
+
+        return WarnErrorOptions(
+            include=include_exclude.get("include", []), exclude=include_exclude.get("exclude", [])
+        )
+
+
+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 +1,389 @@
+from pathlib import Path, PurePath
+
+import click
+from dbt.cli.option_types import YAML, WarnErrorOptionsType
+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,
+)
+
+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 interactive 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",
+    envvar="DBT_WARN_ERROR",
+    help="If dbt would normally warn, instead raise an exception. Examples include --select that selects nothing, deprecations, configurations with no associated models, invalid test configurations, and missing sources/refs in tests.",
+    default=None,
+    flag_value=True,
+)
+
+warn_error_options = click.option(
+    "--warn-error-options",
+    envvar="DBT_WARN_ERROR_OPTIONS",
+    default=None,
+    help="""If dbt would normally warn, instead raise an exception based on include/exclude configuration. Examples include --select that selects nothing, deprecations, configurations with no associated models, invalid test configurations,
+    and missing sources/refs in tests. This argument should be a YAML string, with keys 'include' or 'exclude'. eg. '{"include": "all", "exclude": ["NoNodesForSelectionCriteria"]}'""",
+    type=WarnErrorOptionsType(),
+)
+
+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_blocks.py

@@ -1,7 +1,15 @@
 import re
 from collections import namedtuple
 
-import dbt.exceptions
+from dbt.exceptions import (
+    BlockDefinitionNotAtTopError,
+    DbtInternalError,
+    MissingCloseTagError,
+    MissingControlFlowStartTagError,
+    NestedTagsError,
+    UnexpectedControlFlowEndTagError,
+    UnexpectedMacroEOFError,
+)
 
 
 def regex(pat):
@@ -139,10 +147,7 @@ class TagIterator:
     def _expect_match(self, expected_name, *patterns, **kwargs):
         match = self._first_match(*patterns, **kwargs)
         if match is None:
-            msg = 'unexpected EOF, expected {}, got "{}"'.format(
-                expected_name, self.data[self.pos :]
-            )
-            dbt.exceptions.raise_compiler_error(msg)
+            raise UnexpectedMacroEOFError(expected_name, self.data[self.pos :])
         return match
 
     def handle_expr(self, match):
@@ -256,7 +261,7 @@ class TagIterator:
             elif block_type_name is not None:
                 yield self.handle_tag(match)
             else:
-                raise dbt.exceptions.InternalException(
+                raise DbtInternalError(
                     "Invalid regex match in next_block, expected block start, "
                     "expr start, or comment start"
                 )
@@ -265,13 +270,6 @@ class TagIterator:
         return self.find_tags()
 
 
-duplicate_tags = (
-    "Got nested tags: {outer.block_type_name} (started at {outer.start}) did "
-    "not have a matching {{% end{outer.block_type_name} %}} before a "
-    "subsequent {inner.block_type_name} was found (started at {inner.start})"
-)
-
-
 _CONTROL_FLOW_TAGS = {
     "if": "endif",
     "for": "endfor",
@@ -319,33 +317,16 @@ class BlockIterator:
                     found = self.stack.pop()
                 else:
                     expected = _CONTROL_FLOW_END_TAGS[tag.block_type_name]
-                    dbt.exceptions.raise_compiler_error(
-                        (
-                            "Got an unexpected control flow end tag, got {} but "
-                            "never saw a preceeding {} (@ {})"
-                        ).format(tag.block_type_name, expected, self.tag_parser.linepos(tag.start))
-                    )
+                    raise UnexpectedControlFlowEndTagError(tag, expected, self.tag_parser)
                 expected = _CONTROL_FLOW_TAGS[found]
                 if expected != tag.block_type_name:
-                    dbt.exceptions.raise_compiler_error(
-                        (
-                            "Got an unexpected control flow end tag, got {} but "
-                            "expected {} next (@ {})"
-                        ).format(tag.block_type_name, expected, self.tag_parser.linepos(tag.start))
-                    )
+                    raise MissingControlFlowStartTagError(tag, expected, self.tag_parser)
 
             if tag.block_type_name in allowed_blocks:
                 if self.stack:
-                    dbt.exceptions.raise_compiler_error(
-                        (
-                            "Got a block definition inside control flow at {}. "
-                            "All dbt block definitions must be at the top level"
-                        ).format(self.tag_parser.linepos(tag.start))
-                    )
+                    raise BlockDefinitionNotAtTopError(self.tag_parser, tag.start)
                 if self.current is not None:
-                    dbt.exceptions.raise_compiler_error(
-                        duplicate_tags.format(outer=self.current, inner=tag)
-                    )
+                    raise NestedTagsError(outer=self.current, inner=tag)
                 if collect_raw_data:
                     raw_data = self.data[self.last_position : tag.start]
                     self.last_position = tag.start
@@ -366,11 +347,7 @@ class BlockIterator:
 
         if self.current:
             linecount = self.data[: self.current.end].count("\n") + 1
-            dbt.exceptions.raise_compiler_error(
-                (
-                    "Reached EOF without finding a close tag for " "{} (searched from line {})"
-                ).format(self.current.block_type_name, linecount)
-            )
+            raise MissingCloseTagError(self.current.block_type_name, linecount)
 
         if collect_raw_data:
             raw_data = self.data[self.last_position :]

core/dbt/clients/agate_helper.py

@@ -7,7 +7,7 @@ import json
 import dbt.utils
 from typing import Iterable, List, Dict, Union, Optional, Any
 
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 BOM = BOM_UTF8.decode("utf-8")  # '\ufeff'
@@ -168,7 +168,7 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
             return
         elif not isinstance(value, type(existing_type)):
             # actual type mismatch!
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f"Tables contain columns with the same names ({key}), "
                 f"but different types ({value} vs {existing_type})"
             )

core/dbt/clients/git.py

@@ -14,10 +14,10 @@ from dbt.events.types import (
 )
 from dbt.exceptions import (
     CommandResultError,
-    RuntimeException,
-    bad_package_spec,
-    raise_git_cloning_error,
-    raise_git_cloning_problem,
+    GitCheckoutError,
+    GitCloningError,
+    UnknownGitCloningProblemError,
+    DbtRuntimeError,
 )
 from packaging import version
 
@@ -27,16 +27,6 @@ def _is_commit(revision: str) -> bool:
     return bool(re.match(r"\b[0-9a-f]{40}\b", revision))
 
 
-def _raise_git_cloning_error(repo, revision, error):
-    stderr = error.stderr.strip()
-    if "usage: git" in stderr:
-        stderr = stderr.split("\nusage: git")[0]
-    if re.match("fatal: destination path '(.+)' already exists", stderr):
-        raise_git_cloning_error(error)
-
-    bad_package_spec(repo, revision, stderr)
-
-
 def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirectory=None):
     has_revision = revision is not None
     is_commit = _is_commit(revision or "")
@@ -64,7 +54,7 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
     try:
         result = run_cmd(cwd, clone_cmd, env={"LC_ALL": "C"})
     except CommandResultError as exc:
-        _raise_git_cloning_error(repo, revision, exc)
+        raise GitCloningError(repo, revision, exc)
 
     if subdirectory:
         cwd_subdir = os.path.join(cwd, dirname or "")
@@ -72,7 +62,7 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
         try:
             run_cmd(cwd_subdir, clone_cmd_subdir)
         except CommandResultError as exc:
-            _raise_git_cloning_error(repo, revision, exc)
+            raise GitCloningError(repo, revision, exc)
 
     if remove_git_dir:
         rmdir(os.path.join(dirname, ".git"))
@@ -115,8 +105,7 @@ def checkout(cwd, repo, revision=None):
     try:
         return _checkout(cwd, repo, revision)
     except CommandResultError as exc:
-        stderr = exc.stderr.strip()
-        bad_package_spec(repo, revision, stderr)
+        raise GitCheckoutError(repo=repo, revision=revision, error=exc)
 
 
 def get_current_sha(cwd):
@@ -145,7 +134,7 @@ def clone_and_checkout(
         err = exc.stderr
         exists = re.match("fatal: destination path '(.+)' already exists", err)
         if not exists:
-            raise_git_cloning_problem(repo)
+            raise UnknownGitCloningProblemError(repo)
 
     directory = None
     start_sha = None
@@ -155,7 +144,7 @@ def clone_and_checkout(
     else:
         matches = re.match("Cloning into '(.+)'", err.decode("utf-8"))
         if matches is None:
-            raise RuntimeException(f'Error cloning {repo} - never saw "Cloning into ..." from git')
+            raise DbtRuntimeError(f'Error cloning {repo} - never saw "Cloning into ..." from git')
         directory = matches.group(1)
         fire_event(GitProgressPullingNewDependency(dir=directory))
     full_path = os.path.join(cwd, directory)

core/dbt/clients/jinja.py

@@ -25,18 +25,26 @@ 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.contracts.graph.nodes import GenericTestNode
+
 from dbt.exceptions import (
-    InternalException,
-    raise_compiler_error,
-    CompilationException,
-    invalid_materialization_argument,
+    CaughtMacroError,
+    CaughtMacroErrorWithNodeError,
+    CompilationError,
+    DbtInternalError,
+    MaterializationArgError,
+    JinjaRenderingError,
     MacroReturn,
-    JinjaRenderingException,
-    UndefinedMacroException,
+    MaterializtionMacroNotUsedError,
+    NoSupportedLanguagesFoundError,
+    UndefinedCompilationError,
+    UndefinedMacroError,
 )
 from dbt import flags
+from dbt.node_types import ModelLanguage
+
+
+SUPPORTED_LANG_ARG = jinja2.nodes.Name("supported_languages", "param")
 
 
 def _linecache_inject(source, write):
@@ -153,15 +161,15 @@ def quoted_native_concat(nodes):
     except (ValueError, SyntaxError, MemoryError):
         result = raw
     if isinstance(raw, BoolMarker) and not isinstance(result, bool):
-        raise JinjaRenderingException(f"Could not convert value '{raw!s}' into type 'bool'")
+        raise JinjaRenderingError(f"Could not convert value '{raw!s}' into type 'bool'")
     if isinstance(raw, NumberMarker) and not _is_number(result):
-        raise JinjaRenderingException(f"Could not convert value '{raw!s}' into type 'number'")
+        raise JinjaRenderingError(f"Could not convert value '{raw!s}' into type 'number'")
 
     return result
 
 
 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
@@ -233,12 +241,12 @@ class BaseMacroGenerator:
         try:
             yield
         except (TypeError, jinja2.exceptions.TemplateRuntimeError) as e:
-            raise_compiler_error(str(e))
+            raise CaughtMacroError(e)
 
     def call_macro(self, *args, **kwargs):
         # called from __call__ methods
         if self.context is None:
-            raise InternalException("Context is still None in call_macro!")
+            raise DbtInternalError("Context is still None in call_macro!")
         assert self.context is not None
 
         macro = self.get_macro()
@@ -265,7 +273,7 @@ class MacroStack(threading.local):
     def pop(self, name):
         got = self.call_stack.pop()
         if got != name:
-            raise InternalException(f"popped {got}, expected {name}")
+            raise DbtInternalError(f"popped {got}, expected {name}")
 
 
 class MacroGenerator(BaseMacroGenerator):
@@ -292,8 +300,8 @@ class MacroGenerator(BaseMacroGenerator):
         try:
             yield
         except (TypeError, jinja2.exceptions.TemplateRuntimeError) as e:
-            raise_compiler_error(str(e), self.macro)
-        except CompilationException as e:
+            raise CaughtMacroErrorWithNodeError(exc=e, node=self.macro)
+        except CompilationError as e:
             e.stack.append(self.macro)
             raise e
 
@@ -301,13 +309,13 @@ 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:
@@ -364,8 +372,19 @@ 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)
+                raise MaterializationArgError(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)
 
@@ -436,7 +455,7 @@ def create_undefined(node=None):
             return self
 
         def __reduce__(self):
-            raise_compiler_error(f"{self.name} is undefined", node=node)
+            raise UndefinedCompilationError(name=self.name, node=node)
 
     return Undefined
 
@@ -494,10 +513,10 @@ def catch_jinja(node=None) -> Iterator[None]:
         yield
     except jinja2.exceptions.TemplateSyntaxError as e:
         e.translated = False
-        raise CompilationException(str(e), node) from e
+        raise CompilationError(str(e), node) from e
     except jinja2.exceptions.UndefinedError as e:
-        raise UndefinedMacroException(str(e), node) from e
-    except CompilationException as exc:
+        raise UndefinedMacroError(str(e), node) from e
+    except CompilationError as exc:
         exc.add_node(node)
         raise
 
@@ -604,7 +623,7 @@ GENERIC_TEST_KWARGS_NAME = "_dbt_generic_test_kwargs"
 
 def add_rendered_test_kwargs(
     context: Dict[str, Any],
-    node: Union[ParsedGenericTestNode, CompiledGenericTestNode],
+    node: GenericTestNode,
     capture_macros: bool = False,
 ) -> None:
     """Render each of the test kwargs in the given context using the native
@@ -632,3 +651,21 @@ 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 MaterializtionMacroNotUsedError(node=node)
+
+    no_kwargs = not node.defaults
+    no_langs_found = SUPPORTED_LANG_ARG not in node.args
+
+    if no_kwargs or no_langs_found:
+        raise NoSupportedLanguagesFoundError(node=node)
+
+    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

@@ -1,6 +1,6 @@
 import jinja2
 from dbt.clients.jinja import get_environment
-from dbt.exceptions import raise_compiler_error
+from dbt.exceptions import MacroNamespaceNotStringError, MacroNameNotStringError
 
 
 def statically_extract_macro_calls(string, ctx, db_wrapper=None):
@@ -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(
@@ -117,20 +117,14 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
                     func_name = kwarg.value.value
                     possible_macro_calls.append(func_name)
                 else:
-                    raise_compiler_error(
-                        f"The macro_name parameter ({kwarg.value.value}) "
-                        "to adapter.dispatch was not a string"
-                    )
+                    raise MacroNameNotStringError(kwarg_value=kwarg.value.value)
             elif kwarg.key == "macro_namespace":
                 # This will remain to enable static resolution
                 kwarg_type = type(kwarg.value).__name__
                 if kwarg_type == "Const":
                     macro_namespace = kwarg.value.value
                 else:
-                    raise_compiler_error(
-                        "The macro_namespace parameter to adapter.dispatch "
-                        f"is a {kwarg_type}, not a string"
-                    )
+                    raise MacroNamespaceNotStringError(kwarg_type)
 
     # positional arguments
     if packages_arg:

core/dbt/clients/registry.py

@@ -3,9 +3,9 @@ from typing import Any, Dict, List
 import requests
 from dbt.events.functions import fire_event
 from dbt.events.types import (
-    RegistryProgressMakingGETRequest,
+    RegistryProgressGETRequest,
     RegistryProgressGETResponse,
-    RegistryIndexProgressMakingGETRequest,
+    RegistryIndexProgressGETRequest,
     RegistryIndexProgressGETResponse,
     RegistryResponseUnexpectedType,
     RegistryResponseMissingTopKeys,
@@ -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"):
@@ -37,7 +38,7 @@ def _get_with_retries(package_name, registry_base_url=None):
 
 def _get(package_name, registry_base_url=None):
     url = _get_url(package_name, registry_base_url)
-    fire_event(RegistryProgressMakingGETRequest(url=url))
+    fire_event(RegistryProgressGETRequest(url=url))
     # all exceptions from requests get caught in the retry logic so no need to wrap this here
     resp = requests.get(url, timeout=30)
     fire_event(RegistryProgressGETResponse(url=url, resp_code=resp.status_code))
@@ -125,16 +126,43 @@ 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):
 
     url = _get_url("index", registry_base_url)
-    fire_event(RegistryIndexProgressMakingGETRequest(url=url))
+    fire_event(RegistryIndexProgressGETRequest(url=url))
     # all exceptions from requests get caught in the retry logic so no need to wrap this here
     resp = requests.get(url, timeout=30)
     fire_event(RegistryIndexProgressGETResponse(url=url, resp_code=resp.status_code))

core/dbt/clients/system.py

@@ -12,14 +12,15 @@ 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 (
     SystemErrorRetrievingModTime,
     SystemCouldNotWrite,
     SystemExecutingCmd,
-    SystemStdOutMsg,
-    SystemStdErrMsg,
+    SystemStdOut,
+    SystemStdErr,
     SystemReportReturnCode,
 )
 import dbt.exceptions
@@ -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,
@@ -131,7 +144,8 @@ def make_symlink(source: str, link_path: str) -> None:
     Create a symlink at `link_path` referring to `source`.
     """
     if not supports_symlinks():
-        dbt.exceptions.system_error("create a symbolic link")
+        # TODO: why not import these at top?
+        raise dbt.exceptions.SymbolicLinkError()
 
     os.symlink(source, link_path)
 
@@ -164,7 +178,7 @@ 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
@@ -398,7 +412,7 @@ def _interpret_oserror(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
         _handle_posix_error(exc, cwd, cmd)
 
     # this should not be reachable, raise _something_ at least!
-    raise dbt.exceptions.InternalException(
+    raise dbt.exceptions.DbtInternalError(
         "Unhandled exception in _interpret_oserror: {}".format(exc)
     )
 
@@ -427,8 +441,8 @@ def run_cmd(cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None) -> T
     except OSError as exc:
         _interpret_oserror(exc, cwd, cmd)
 
-    fire_event(SystemStdOutMsg(bmsg=out))
-    fire_event(SystemStdErrMsg(bmsg=err))
+    fire_event(SystemStdOut(bmsg=out))
+    fire_event(SystemStdErr(bmsg=err))
 
     if proc.returncode != 0:
         fire_event(SystemReportReturnCode(returncode=proc.returncode))

core/dbt/clients/yaml_helper.py

@@ -60,4 +60,4 @@ def load_yaml_text(contents, path=None):
         else:
             error = str(e)
 
-        raise dbt.exceptions.ValidationException(error)
+        raise dbt.exceptions.DbtValidationError(error)

core/dbt/compilation.py

@@ -1,6 +1,6 @@
 import os
 from collections import defaultdict
-from typing import List, Dict, Any, Tuple, cast, Optional
+from typing import List, Dict, Any, Tuple, Optional
 
 import networkx as nx  # type: ignore
 import pickle
@@ -12,38 +12,30 @@ from dbt.clients import jinja
 from dbt.clients.system import make_directory
 from dbt.context.providers import generate_runtime_model_context
 from dbt.contracts.graph.manifest import Manifest, UniqueID
-from dbt.contracts.graph.compiled import (
-    COMPILED_TYPES,
-    CompiledGenericTestNode,
+from dbt.contracts.graph.nodes import (
+    ManifestNode,
+    ManifestSQLNode,
+    GenericTestNode,
     GraphMemberNode,
     InjectedCTE,
-    ManifestNode,
-    NonSourceCompiledNode,
+    SeedNode,
 )
-from dbt.contracts.graph.parsed import ParsedNode
 from dbt.exceptions import (
-    dependency_not_found,
-    InternalException,
-    RuntimeException,
+    GraphDependencyNotFoundError,
+    DbtInternalError,
+    DbtRuntimeError,
 )
 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.events.types import FoundStats, WritingInjectedSQLForNode
+from dbt.events.contextvars import get_node_info
+from dbt.node_types import NodeType, ModelLanguage
 from dbt.events.format import pluralize
 import dbt.tracking
 
 graph_file_name = "graph.gpickle"
 
 
-def _compiled_type_for(model: ParsedNode):
-    if type(model) not in COMPILED_TYPES:
-        raise InternalException(
-            f"Asked to compile {type(model)} node, but it has no compiled form"
-        )
-    return COMPILED_TYPES[type(model)]
-
-
 def print_compile_stats(stats):
     names = {
         NodeType.Model: "model",
@@ -56,6 +48,7 @@ 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()}
@@ -91,6 +84,8 @@ def _generate_stats(manifest: Manifest):
         stats[exposure.resource_type] += 1
     for metric in manifest.metrics.values():
         stats[metric.resource_type] += 1
+    for entity in manifest.entities.values():
+        stats[entity.resource_type] += 1
     for macro in manifest.macros.values():
         stats[macro.resource_type] += 1
     return stats
@@ -176,14 +171,15 @@ class Compiler:
     # a dict for jinja rendering of SQL
     def _create_node_context(
         self,
-        node: NonSourceCompiledNode,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Dict[str, Any],
     ) -> Dict[str, Any]:
 
         context = generate_runtime_model_context(node, self.config, manifest)
         context.update(extra_context)
-        if isinstance(node, CompiledGenericTestNode):
+
+        if isinstance(node, GenericTestNode):
             # for test nodes, add a special keyword args value to the context
             jinja.add_rendered_test_kwargs(context, node)
 
@@ -194,14 +190,6 @@ class Compiler:
         relation_cls = adapter.Relation
         return relation_cls.add_ephemeral_prefix(name)
 
-    def _get_relation_name(self, node: ParsedNode):
-        relation_name = None
-        if node.is_relational and not node.is_ephemeral_model:
-            adapter = get_adapter(self.config)
-            relation_cls = adapter.Relation
-            relation_name = str(relation_cls.create_from(self.config, node))
-        return relation_name
-
     def _inject_ctes_into_sql(self, sql: str, ctes: List[InjectedCTE]) -> str:
         """
         `ctes` is a list of InjectedCTEs like:
@@ -260,10 +248,10 @@ class Compiler:
 
     def _recursively_prepend_ctes(
         self,
-        model: NonSourceCompiledNode,
+        model: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]],
-    ) -> Tuple[NonSourceCompiledNode, List[InjectedCTE]]:
+    ) -> Tuple[ManifestSQLNode, List[InjectedCTE]]:
         """This method is called by the 'compile_node' method. Starting
         from the node that it is passed in, it will recursively call
         itself using the 'extra_ctes'.  The 'ephemeral' models do
@@ -271,14 +259,15 @@ class Compiler:
         are rolled up into the models that refer to them by
         inserting CTEs into the SQL.
         """
-        if model.compiled_sql is None:
-            raise RuntimeException("Cannot inject ctes into an unparsed node", model)
+        if model.compiled_code is None:
+            raise DbtRuntimeError("Cannot inject ctes into an unparsed node", model)
         if model.extra_ctes_injected:
             return (model, model.extra_ctes)
 
         # Just to make it plain that nothing is actually injected for this case
         if not model.extra_ctes:
-            model.extra_ctes_injected = True
+            if not isinstance(model, SeedNode):
+                model.extra_ctes_injected = True
             manifest.update_node(model)
             return (model, model.extra_ctes)
 
@@ -292,20 +281,19 @@ class Compiler:
         # ephemeral model.
         for cte in model.extra_ctes:
             if cte.id not in manifest.nodes:
-                raise InternalException(
+                raise DbtInternalError(
                     f"During compilation, found a cte reference that "
                     f"could not be resolved: {cte.id}"
                 )
             cte_model = manifest.nodes[cte.id]
+            assert not isinstance(cte_model, SeedNode)
 
             if not cte_model.is_ephemeral_model:
-                raise InternalException(f"{cte.id} is not ephemeral")
+                raise DbtInternalError(f"{cte.id} is not ephemeral")
 
             # This model has already been compiled, so it's been
             # through here before
             if getattr(cte_model, "compiled", False):
-                assert isinstance(cte_model, tuple(COMPILED_TYPES.values()))
-                cte_model = cast(NonSourceCompiledNode, cte_model)
                 new_prepended_ctes = cte_model.extra_ctes
 
             # if the cte_model isn't compiled, i.e. first time here
@@ -324,64 +312,78 @@ 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,
+    # Sets compiled fields in the ManifestSQLNode 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,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestSQLNode:
         if extra_context is None:
             extra_context = {}
 
-        fire_event(CompilingNode(unique_id=node.unique_id))
-
         data = node.to_dict(omit_none=True)
         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 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(node, manifest, extra_context)
 
-        compiled_node.relation_name = self._get_relation_name(node)
+            postfix = jinja.get_rendered(
+                "{{ py_script_postfix(model) }}",
+                context,
+                node,
+            )
+            # we should NOT jinja render the python model's 'raw code'
+            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
 
-        compiled_node.compiled = True
+        else:
+            context = self._create_node_context(node, manifest, extra_context)
+            node.compiled_code = jinja.get_rendered(
+                node.raw_code,
+                context,
+                node,
+            )
 
-        return compiled_node
+        node.compiled = True
+
+        return node
 
     def write_graph_file(self, linker: Linker, manifest: Manifest):
         filename = graph_file_name
@@ -399,8 +401,10 @@ class Compiler:
                 linker.dependency(node.unique_id, (manifest.sources[dependency].unique_id))
             elif dependency in manifest.metrics:
                 linker.dependency(node.unique_id, (manifest.metrics[dependency].unique_id))
+            elif dependency in manifest.entities:
+                linker.dependency(node.unique_id, (manifest.entities[dependency].unique_id))
             else:
-                dependency_not_found(node, dependency)
+                raise GraphDependencyNotFoundError(node, dependency)
 
     def link_graph(self, linker: Linker, manifest: Manifest, add_test_edges: bool = False):
         for source in manifest.sources.values():
@@ -411,6 +415,8 @@ 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()
 
@@ -487,25 +493,28 @@ class Compiler:
 
         return Graph(linker.graph)
 
-    # writes the "compiled_sql" into the target/compiled directory
-    def _write_node(self, node: NonSourceCompiledNode) -> ManifestNode:
-        if not node.extra_ctes_injected or node.resource_type == NodeType.Snapshot:
+    # writes the "compiled_code" into the target/compiled directory
+    def _write_node(self, node: ManifestSQLNode) -> ManifestSQLNode:
+        if not node.extra_ctes_injected or node.resource_type in (
+            NodeType.Snapshot,
+            NodeType.Seed,
+        ):
             return node
-        fire_event(WritingInjectedSQLForNode(unique_id=node.unique_id))
+        fire_event(WritingInjectedSQLForNode(node_info=get_node_info()))
 
-        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
 
     def compile_node(
         self,
-        node: ManifestNode,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
         write: bool = True,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestSQLNode:
         """This is the main entry point into this code. It's called by
         CompileRunner.compile, GenericRPCRunner.compile, and
         RunTask.get_hook_sql. It calls '_compile_node' to convert

core/dbt/config/profile.py

@@ -9,12 +9,14 @@ from dbt.clients.system import load_file_contents
 from dbt.clients.yaml_helper import load_yaml_text
 from dbt.contracts.connection import Credentials, HasCredentials
 from dbt.contracts.project import ProfileConfig, UserConfig
-from dbt.exceptions import CompilationException
-from dbt.exceptions import DbtProfileError
-from dbt.exceptions import DbtProjectError
-from dbt.exceptions import ValidationException
-from dbt.exceptions import RuntimeException
-from dbt.exceptions import validator_error_message
+from dbt.exceptions import (
+    CompilationError,
+    DbtProfileError,
+    DbtProjectError,
+    DbtValidationError,
+    DbtRuntimeError,
+    ProfileConfigError,
+)
 from dbt.events.types import MissingProfileTarget
 from dbt.events.functions import fire_event
 from dbt.utils import coerce_dict_str
@@ -23,8 +25,6 @@ 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 +44,7 @@ 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
 )
 
 
@@ -60,9 +60,9 @@ def read_profile(profiles_dir: str) -> Dict[str, Any]:
                 msg = f"The profiles.yml file at {path} is empty"
                 raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
             return yaml_content
-        except ValidationException as e:
+        except DbtValidationError as e:
             msg = INVALID_PROFILE_MESSAGE.format(error_string=e)
-            raise ValidationException(msg) from e
+            raise DbtValidationError(msg) from e
 
     return {}
 
@@ -75,7 +75,7 @@ def read_user_config(directory: str) -> UserConfig:
             if user_config is not None:
                 UserConfig.validate(user_config)
                 return UserConfig.from_dict(user_config)
-    except (RuntimeException, ValidationError):
+    except (DbtRuntimeError, ValidationError):
         pass
     return UserConfig()
 
@@ -158,7 +158,7 @@ class Profile(HasCredentials):
             dct = self.to_profile_info(serialize_credentials=True)
             ProfileConfig.validate(dct)
         except ValidationError as exc:
-            raise DbtProfileError(validator_error_message(exc)) from exc
+            raise ProfileConfigError(exc) from exc
 
     @staticmethod
     def _credentials_from_profile(
@@ -182,8 +182,8 @@ class Profile(HasCredentials):
             data = cls.translate_aliases(profile)
             cls.validate(data)
             credentials = cls.from_dict(data)
-        except (RuntimeException, ValidationError) as e:
-            msg = str(e) if isinstance(e, RuntimeException) else e.message
+        except (DbtRuntimeError, ValidationError) as e:
+            msg = str(e) if isinstance(e, DbtRuntimeError) else e.message
             raise DbtProfileError(
                 'Credentials in profile "{}", target "{}" invalid: {}'.format(
                     profile_name, target_name, msg
@@ -299,7 +299,7 @@ class Profile(HasCredentials):
 
         try:
             profile_data = renderer.render_data(raw_profile_data)
-        except CompilationException as exc:
+        except CompilationError as exc:
             raise DbtProfileError(str(exc)) from exc
         return target_name, profile_data
 

core/dbt/config/project.py

@@ -16,19 +16,19 @@ import hashlib
 import os
 
 from dbt import flags, deprecations
-from dbt.clients.system import resolve_path_from_base
-from dbt.clients.system import path_exists
-from dbt.clients.system import load_file_contents
+from dbt.clients.system import path_exists, resolve_path_from_base, load_file_contents
 from dbt.clients.yaml_helper import load_yaml_text
 from dbt.contracts.connection import QueryComment
-from dbt.exceptions import DbtProjectError
-from dbt.exceptions import SemverException
-from dbt.exceptions import validator_error_message
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import (
+    DbtProjectError,
+    SemverError,
+    ProjectContractBrokenError,
+    ProjectContractError,
+    DbtRuntimeError,
+)
 from dbt.graph import SelectionSpec
 from dbt.helper_types import NoValue
-from dbt.semver import VersionSpecifier
-from dbt.semver import versions_compatible
+from dbt.semver import VersionSpecifier, versions_compatible
 from dbt.version import get_installed_version
 from dbt.utils import MultiDict
 from dbt.node_types import NodeType
@@ -219,7 +219,7 @@ def _get_required_version(
 
     try:
         dbt_version = _parse_versions(dbt_raw_version)
-    except SemverException as e:
+    except SemverError as e:
         raise DbtProjectError(str(e)) from e
 
     if verify_version:
@@ -248,7 +248,7 @@ class PartialProject(RenderComponents):
     project_name: Optional[str] = field(
         metadata=dict(
             description=(
-                "The name of the project. This should always be set and will not " "be rendered"
+                "The name of the project. This should always be set and will not be rendered"
             )
         )
     )
@@ -325,7 +325,7 @@ class PartialProject(RenderComponents):
             ProjectContract.validate(rendered.project_dict)
             cfg = ProjectContract.from_dict(rendered.project_dict)
         except ValidationError as e:
-            raise DbtProjectError(validator_error_message(e)) from e
+            raise ProjectContractError(e) from e
         # name/version are required in the Project definition, so we can assume
         # they are present
         name = cfg.name
@@ -380,6 +380,9 @@ class PartialProject(RenderComponents):
         snapshots: Dict[str, Any]
         sources: Dict[str, Any]
         tests: Dict[str, Any]
+        metrics: Dict[str, Any]
+        entities: Dict[str, Any]
+        exposures: Dict[str, Any]
         vars_value: VarProvider
 
         dispatch = cfg.dispatch
@@ -388,6 +391,9 @@ class PartialProject(RenderComponents):
         snapshots = cfg.snapshots
         sources = cfg.sources
         tests = cfg.tests
+        metrics = cfg.metrics
+        entities = cfg.entities
+        exposures = cfg.exposures
         if cfg.vars is None:
             vars_dict: Dict[str, Any] = {}
         else:
@@ -441,6 +447,9 @@ class PartialProject(RenderComponents):
             query_comment=query_comment,
             sources=sources,
             tests=tests,
+            metrics=metrics,
+            entities=entities,
+            exposures=exposures,
             vars=vars_value,
             config_version=cfg.config_version,
             unrendered=unrendered,
@@ -543,6 +552,9 @@ class Project:
     snapshots: Dict[str, Any]
     sources: Dict[str, Any]
     tests: Dict[str, Any]
+    metrics: Dict[str, Any]
+    entities: Dict[str, Any]
+    exposures: Dict[str, Any]
     vars: VarProvider
     dbt_version: List[VersionSpecifier]
     packages: Dict[str, Any]
@@ -615,6 +627,9 @@ class Project:
                 "snapshots": self.snapshots,
                 "sources": self.sources,
                 "tests": self.tests,
+                "metrics": self.metrics,
+                "entities": self.entities,
+                "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,
@@ -632,7 +647,7 @@ class Project:
         try:
             ProjectContract.validate(self.to_project_config())
         except ValidationError as e:
-            raise DbtProjectError(validator_error_message(e)) from e
+            raise ProjectContractBrokenError(e) from e
 
     @classmethod
     def partial_load(cls, project_root: str, *, verify_version: bool = False) -> PartialProject:
@@ -657,8 +672,8 @@ class Project:
 
     def get_selector(self, name: str) -> Union[SelectionSpec, bool]:
         if name not in self.selectors:
-            raise RuntimeException(
-                f"Could not find selector named {name}, expected one of " f"{list(self.selectors)}"
+            raise DbtRuntimeError(
+                f"Could not find selector named {name}, expected one of {list(self.selectors)}"
             )
         return self.selectors[name]["definition"]
 

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.exceptions import DbtProjectError, CompilationError, RecursionError
 from dbt.utils import deep_map_render
-from dbt.logger import SECRET_ENV_PREFIX
 
 
 Keypath = Tuple[Union[str, int], ...]
@@ -40,14 +40,14 @@ class BaseRenderer:
         try:
             with catch_jinja():
                 return get_rendered(value, self.context, native=True)
-        except CompilationException as exc:
+        except CompilationError as exc:
             msg = f"Could not render {value}: {exc.msg}"
-            raise CompilationException(msg) from exc
+            raise CompilationError(msg) from exc
 
     def render_data(self, data: Dict[str, Any]) -> Dict[str, Any]:
         try:
             return deep_map_render(self.render_entry, data)
-        except RecursionException:
+        except RecursionError:
             raise DbtProjectError(
                 f"Cycle detected: {self.name} input has a reference to itself", project=data
             )
@@ -159,7 +159,8 @@ class DbtProjectYamlRenderer(BaseRenderer):
         if first in {"seeds", "models", "snapshots", "tests"}:
             keypath_parts = {(k.lstrip("+ ") if isinstance(k, str) else k) for k in keypath}
             # model-level hooks
-            if "pre-hook" in keypath_parts or "post-hook" in keypath_parts:
+            late_rendered_hooks = {"pre-hook", "post-hook", "pre_hook", "post_hook"}
+            if keypath_parts.intersection(late_rendered_hooks):
                 return False
 
         return True

core/dbt/config/runtime.py

@@ -3,31 +3,42 @@ import os
 from copy import deepcopy
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Dict, Any, Optional, Mapping, Iterator, Iterable, Tuple, List, MutableSet, Type
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    Iterator,
+    Mapping,
+    MutableSet,
+    Optional,
+    Tuple,
+    Type,
+    Union,
+)
 
-from .profile import Profile
-from .project import Project
-from .renderer import DbtProjectYamlRenderer, ProfileRenderer
-from .utils import parse_cli_vars
 from dbt import flags
-from dbt.adapters.factory import get_relation_class_by_name, get_include_paths
-from dbt.helper_types import FQNPath, PathSet, DictDefaultEmptyStr
+from dbt.adapters.factory import get_include_paths, get_relation_class_by_name
 from dbt.config.profile import read_user_config
 from dbt.contracts.connection import AdapterRequiredConfig, Credentials
 from dbt.contracts.graph.manifest import ManifestMetadata
-from dbt.contracts.relation import ComponentName
-from dbt.ui import warning_tag
-
 from dbt.contracts.project import Configuration, UserConfig
-from dbt.exceptions import (
-    RuntimeException,
-    DbtProjectError,
-    validator_error_message,
-    warn_or_error,
-    raise_compiler_error,
-)
-
+from dbt.contracts.relation import ComponentName
 from dbt.dataclass_schema import ValidationError
+from dbt.exceptions import (
+    ConfigContractBrokenError,
+    DbtProjectError,
+    NonUniquePackageNameError,
+    DbtRuntimeError,
+    UninstalledPackagesFoundError,
+)
+from dbt.events.functions import warn_or_error
+from dbt.events.types import UnusedResourceConfigPath
+from dbt.helper_types import DictDefaultEmptyStr, FQNPath, PathSet
+
+from .profile import Profile
+from .project import Project, PartialProject
+from .renderer import DbtProjectYamlRenderer, ProfileRenderer
+from .utils import parse_cli_vars
 
 
 def _project_quoting_dict(proj: Project, profile: Profile) -> Dict[ComponentName, bool]:
@@ -105,6 +116,9 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             query_comment=project.query_comment,
             sources=project.sources,
             tests=project.tests,
+            metrics=project.metrics,
+            entities=project.entities,
+            exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
             unrendered=project.unrendered,
@@ -174,7 +188,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         try:
             Configuration.validate(self.serialize())
         except ValidationError as e:
-            raise DbtProjectError(validator_error_message(e)) from e
+            raise ConfigContractBrokenError(e) from e
 
     @classmethod
     def _get_rendered_profile(
@@ -188,28 +202,52 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
     @classmethod
     def collect_parts(cls: Type["RuntimeConfig"], args: Any) -> Tuple[Project, Profile]:
-        # profile_name from the project
-        project_root = args.project_dir if args.project_dir else os.getcwd()
-        version_check = bool(flags.VERSION_CHECK)
-        partial = Project.partial_load(project_root, verify_version=version_check)
 
-        # build the profile using the base renderer and the one fact we know
-        # Note: only the named profile section is rendered. The rest of the
-        # profile is ignored.
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
+
+        profile = cls.collect_profile(args=args)
+        project_renderer = DbtProjectYamlRenderer(profile, cli_vars)
+        project = cls.collect_project(args=args, project_renderer=project_renderer)
+        assert type(project) is Project
+        return (project, profile)
+
+    @classmethod
+    def collect_profile(
+        cls: Type["RuntimeConfig"], args: Any, profile_name: Optional[str] = None
+    ) -> Profile:
+
         cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
         profile_renderer = ProfileRenderer(cli_vars)
-        profile_name = partial.render_profile_name(profile_renderer)
+
+        # build the profile using the base renderer and the one fact we know
+        if profile_name is None:
+            # Note: only the named profile section is rendered here. The rest of the
+            # profile is ignored.
+            partial = cls.collect_project(args)
+            assert type(partial) is PartialProject
+            profile_name = partial.render_profile_name(profile_renderer)
+
         profile = cls._get_rendered_profile(args, profile_renderer, profile_name)
         # Save env_vars encountered in rendering for partial parsing
         profile.profile_env_vars = profile_renderer.ctx_obj.env_vars
+        return profile
 
-        # get a new renderer using our target information and render the
-        # project
-        project_renderer = DbtProjectYamlRenderer(profile, cli_vars)
-        project = partial.render(project_renderer)
-        # Save env_vars encountered in rendering for partial parsing
-        project.project_env_vars = project_renderer.ctx_obj.env_vars
-        return (project, profile)
+    @classmethod
+    def collect_project(
+        cls: Type["RuntimeConfig"],
+        args: Any,
+        project_renderer: Optional[DbtProjectYamlRenderer] = None,
+    ) -> Union[Project, PartialProject]:
+
+        project_root = args.project_dir if args.project_dir else os.getcwd()
+        version_check = bool(flags.VERSION_CHECK)
+        partial = Project.partial_load(project_root, verify_version=version_check)
+        if project_renderer is None:
+            return partial
+        else:
+            project = partial.render(project_renderer)
+            project.project_env_vars = project_renderer.ctx_obj.env_vars
+            return project
 
     # Called in main.py, lib.py, task/base.py
     @classmethod
@@ -221,7 +259,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         :param args: The arguments as parsed from the cli.
         :raises DbtProjectError: If the project is invalid or missing.
         :raises DbtProfileError: If the profile is invalid or missing.
-        :raises ValidationException: If the cli variables are invalid.
+        :raises DbtValidationError: If the cli variables are invalid.
         """
         project, profile = cls.collect_parts(args)
 
@@ -274,13 +312,16 @@ 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),
+            "entities": self._get_config_paths(self.entities),
+            "exposures": self._get_config_paths(self.exposures),
         }
 
-    def get_unused_resource_config_paths(
+    def warn_for_unused_resource_config_paths(
         self,
         resource_fqns: Mapping[str, PathSet],
         disabled: PathSet,
-    ) -> List[FQNPath]:
+    ) -> None:
         """Return a list of lists of strings, where each inner list of strings
         represents a type + FQN path of a resource configuration that is not
         used.
@@ -294,23 +335,13 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
             for config_path in config_paths:
                 if not _is_config_used(config_path, fqns):
-                    unused_resource_config_paths.append((resource_type,) + config_path)
-        return unused_resource_config_paths
+                    resource_path = ".".join(i for i in ((resource_type,) + config_path))
+                    unused_resource_config_paths.append(resource_path)
 
-    def warn_for_unused_resource_config_paths(
-        self,
-        resource_fqns: Mapping[str, PathSet],
-        disabled: PathSet,
-    ) -> None:
-        unused = self.get_unused_resource_config_paths(resource_fqns, disabled)
-        if len(unused) == 0:
+        if len(unused_resource_config_paths) == 0:
             return
 
-        msg = UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE.format(
-            len(unused), "\n".join("- {}".format(".".join(u)) for u in unused)
-        )
-
-        warn_or_error(msg, log_fmt=warning_tag("{}"))
+        warn_or_error(UnusedResourceConfigPath(unused_config_paths=unused_resource_config_paths))
 
     def load_dependencies(self, base_only=False) -> Mapping[str, "RuntimeConfig"]:
         if self.dependencies is None:
@@ -324,22 +355,15 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
                 count_packages_specified = len(self.packages.packages)  # type: ignore
                 count_packages_installed = len(tuple(self._get_project_directories()))
                 if count_packages_specified > count_packages_installed:
-                    raise_compiler_error(
-                        f"dbt found {count_packages_specified} package(s) "
-                        f"specified in packages.yml, but only "
-                        f"{count_packages_installed} package(s) installed "
-                        f'in {self.packages_install_path}. Run "dbt deps" to '
-                        f"install package dependencies."
+                    raise UninstalledPackagesFoundError(
+                        count_packages_specified,
+                        count_packages_installed,
+                        self.packages_install_path,
                     )
                 project_paths = itertools.chain(internal_packages, self._get_project_directories())
             for project_name, project in self.load_projects(project_paths):
                 if project_name in all_projects:
-                    raise_compiler_error(
-                        f"dbt found more than one package with the name "
-                        f'"{project_name}" included in this project. Package '
-                        f"names must be unique in a project. Please rename "
-                        f"one of these packages."
-                    )
+                    raise NonUniquePackageNameError(project_name)
                 all_projects[project_name] = project
             self.dependencies = all_projects
         return self.dependencies
@@ -404,7 +428,7 @@ class UnsetProfile(Profile):
 
     def __getattribute__(self, name):
         if name in {"profile_name", "target_name", "threads"}:
-            raise RuntimeException(f'Error: disallowed attribute "{name}" - no profile!')
+            raise DbtRuntimeError(f'Error: disallowed attribute "{name}" - no profile!')
 
         return Profile.__getattribute__(self, name)
 
@@ -431,7 +455,7 @@ class UnsetProfileConfig(RuntimeConfig):
     def __getattribute__(self, name):
         # Override __getattribute__ to check that the attribute isn't 'banned'.
         if name in {"profile_name", "target_name"}:
-            raise RuntimeException(f'Error: disallowed attribute "{name}" - no profile!')
+            raise DbtRuntimeError(f'Error: disallowed attribute "{name}" - no profile!')
 
         # avoid every attribute access triggering infinite recursion
         return RuntimeConfig.__getattribute__(self, name)
@@ -477,6 +501,9 @@ class UnsetProfileConfig(RuntimeConfig):
                 "snapshots": self.snapshots,
                 "sources": self.sources,
                 "tests": self.tests,
+                "metrics": self.metrics,
+                "entities": self.entities,
+                "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 +564,9 @@ class UnsetProfileConfig(RuntimeConfig):
             query_comment=project.query_comment,
             sources=project.sources,
             tests=project.tests,
+            metrics=project.metrics,
+            entities=project.entities,
+            exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
             unrendered=project.unrendered,
@@ -576,21 +606,13 @@ class UnsetProfileConfig(RuntimeConfig):
         :param args: The arguments as parsed from the cli.
         :raises DbtProjectError: If the project is invalid or missing.
         :raises DbtProfileError: If the profile is invalid or missing.
-        :raises ValidationException: If the cli variables are invalid.
+        :raises DbtValidationError: If the cli variables are invalid.
         """
         project, profile = cls.collect_parts(args)
 
         return cls.from_parts(project=project, profile=profile, args=args)
 
 
-UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE = """\
-Configuration paths exist in your dbt_project.yml file which do not \
-apply to any resources.
-There are {} unused configuration paths:
-{}
-"""
-
-
 def _is_config_used(path, fqns):
     if fqns:
         for fqn in fqns:

core/dbt/config/selectors.py

@@ -12,7 +12,7 @@ from dbt.clients.system import (
     resolve_path_from_base,
 )
 from dbt.contracts.selection import SelectorFile
-from dbt.exceptions import DbtSelectorsError, RuntimeException
+from dbt.exceptions import DbtSelectorsError, DbtRuntimeError
 from dbt.graph import parse_from_selectors_definition, SelectionSpec
 from dbt.graph.selector_spec import SelectionCriteria
 
@@ -46,7 +46,7 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
                 f"yaml-selectors",
                 result_type="invalid_selector",
             ) from exc
-        except RuntimeException as exc:
+        except DbtRuntimeError as exc:
             raise DbtSelectorsError(
                 f"Could not read selector file data: {exc}",
                 result_type="invalid_selector",
@@ -62,7 +62,7 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
     ) -> "SelectorConfig":
         try:
             rendered = renderer.render_data(data)
-        except (ValidationError, RuntimeException) as exc:
+        except (ValidationError, DbtRuntimeError) as exc:
             raise DbtSelectorsError(
                 f"Could not render selector data: {exc}",
                 result_type="invalid_selector",
@@ -77,7 +77,7 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
     ) -> "SelectorConfig":
         try:
             data = load_yaml_text(load_file_contents(str(path)))
-        except (ValidationError, RuntimeException) as exc:
+        except (ValidationError, DbtRuntimeError) as exc:
             raise DbtSelectorsError(
                 f"Could not read selector file: {exc}",
                 result_type="invalid_selector",

core/dbt/config/utils.py

@@ -8,24 +8,24 @@ from dbt.clients import yaml_helper
 from dbt.config import Profile, Project, read_user_config
 from dbt.config.renderer import DbtProjectYamlRenderer, ProfileRenderer
 from dbt.events.functions import fire_event
-from dbt.events.types import InvalidVarsYAML
-from dbt.exceptions import ValidationException, raise_compiler_error
+from dbt.events.types import InvalidOptionYAML
+from dbt.exceptions import DbtValidationError, OptionNotYamlDictError
 
 
 def parse_cli_vars(var_string: str) -> Dict[str, Any]:
+    return parse_cli_yaml_string(var_string, "vars")
+
+
+def parse_cli_yaml_string(var_string: str, cli_option_name: str) -> Dict[str, Any]:
     try:
         cli_vars = yaml_helper.load_yaml_text(var_string)
         var_type = type(cli_vars)
         if var_type is dict:
             return cli_vars
         else:
-            type_name = var_type.__name__
-            raise_compiler_error(
-                "The --vars argument must be a YAML dictionary, but was "
-                "of type '{}'".format(type_name)
-            )
-    except ValidationException:
-        fire_event(InvalidVarsYAML())
+            raise OptionNotYamlDictError(var_type, cli_option_name)
+    except DbtValidationError:
+        fire_event(InvalidOptionYAML(option_name=cli_option_name))
         raise
 
 

core/dbt/constants.py

@@ -0,0 +1,10 @@
+SECRET_ENV_PREFIX = "DBT_ENV_SECRET_"
+DEFAULT_ENV_PLACEHOLDER = "DBT_DEFAULT_PLACEHOLDER"
+METADATA_ENV_PREFIX = "DBT_ENV_CUSTOM_ENV_"
+
+MAXIMUM_SEED_SIZE = 1 * 1024 * 1024
+MAXIMUM_SEED_SIZE_NAME = "1MB"
+
+PIN_PACKAGE_URL = (
+    "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"
+)

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

@@ -4,19 +4,22 @@ from typing import Any, Dict, NoReturn, Optional, Mapping, Iterable, Set, List
 
 from dbt import flags
 from dbt import tracking
+from dbt import utils
 from dbt.clients.jinja import get_rendered
 from dbt.clients.yaml_helper import yaml, safe_load, SafeLoader, Loader, Dumper  # noqa: F401
-from dbt.contracts.graph.compiled import CompiledResource
+from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
+from dbt.contracts.graph.nodes import Resource
 from dbt.exceptions import (
-    CompilationException,
+    SecretEnvVarLocationError,
+    EnvVarMissingError,
     MacroReturn,
-    raise_compiler_error,
-    raise_parsing_error,
-    disallow_secret_env_var,
+    RequiredVarNotFoundError,
+    SetStrictWrongTypeError,
+    ZipStrictWrongTypeError,
 )
-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.events.types import JinjaLogInfo, JinjaLogDebug
+from dbt.events.contextvars import get_node_info
 from dbt.version import __version__ as dbt_version
 
 # These modules are added to the context. Consider alternative
@@ -126,18 +129,17 @@ class ContextMeta(type):
 
 
 class Var:
-    UndefinedVarError = "Required var '{}' not found in config:\nVars " "supplied to {} = {}"
     _VAR_NOTSET = object()
 
     def __init__(
         self,
         context: Mapping[str, Any],
         cli_vars: Mapping[str, Any],
-        node: Optional[CompiledResource] = None,
+        node: Optional[Resource] = None,
     ) -> None:
         self._context: Mapping[str, Any] = context
         self._cli_vars: Mapping[str, Any] = cli_vars
-        self._node: Optional[CompiledResource] = node
+        self._node: Optional[Resource] = node
         self._merged: Mapping[str, Any] = self._generate_merged()
 
     def _generate_merged(self) -> Mapping[str, Any]:
@@ -151,10 +153,7 @@ class Var:
             return "<Configuration>"
 
     def get_missing_var(self, var_name):
-        dct = {k: self._merged[k] for k in self._merged}
-        pretty_vars = json.dumps(dct, sort_keys=True, indent=4)
-        msg = self.UndefinedVarError.format(var_name, self.node_name, pretty_vars)
-        raise_compiler_error(msg, self._node)
+        raise RequiredVarNotFoundError(var_name, self._merged, self._node)
 
     def has_var(self, var_name: str):
         return var_name in self._merged
@@ -298,18 +297,22 @@ class BaseContext(metaclass=ContextMeta):
         """
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
-            disallow_secret_env_var(var)
+            raise SecretEnvVarLocationError(var)
         if var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
             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}'"
-            raise_parsing_error(msg)
+            raise EnvVarMissingError(var)
 
     if os.environ.get("DBT_MACRO_DEBUGGING"):
 
@@ -490,7 +493,7 @@ class BaseContext(metaclass=ContextMeta):
         try:
             return set(value)
         except TypeError as e:
-            raise CompilationException(e)
+            raise SetStrictWrongTypeError(e)
 
     @contextmember("zip")
     @staticmethod
@@ -534,7 +537,7 @@ class BaseContext(metaclass=ContextMeta):
         try:
             return zip(*args)
         except TypeError as e:
-            raise CompilationException(e)
+            raise ZipStrictWrongTypeError(e)
 
     @contextmember
     @staticmethod
@@ -552,9 +555,9 @@ class BaseContext(metaclass=ContextMeta):
             {% endmacro %}"
         """
         if info:
-            fire_event(MacroEventInfo(msg=msg))
+            fire_event(JinjaLogInfo(msg=msg, node_info=get_node_info()))
         else:
-            fire_event(MacroEventDebug(msg=msg))
+            fire_event(JinjaLogDebug(msg=msg, node_info=get_node_info()))
         return ""
 
     @contextproperty
@@ -631,9 +634,8 @@ class BaseContext(metaclass=ContextMeta):
             {% endif %}
 
         This supports all flags defined in flags submodule (core/dbt/flags.py)
-        TODO: Replace with object that provides read-only access to flag values
         """
-        return flags
+        return flags.get_flag_obj()
 
     @contextmember
     @staticmethod
@@ -682,6 +684,19 @@ class BaseContext(metaclass=ContextMeta):
                 dict_diff.update({k: dict_a[k]})
         return dict_diff
 
+    @contextmember
+    @staticmethod
+    def local_md5(value: str) -> str:
+        """Calculates an MD5 hash of the given string.
+        It's called "local_md5" to emphasize that it runs locally in dbt (in jinja context) and not an MD5 SQL command.
+
+        :param value: The value to hash
+
+        Usage:
+            {% set value_hash = local_md5("hello world") %}
+        """
+        return utils.md5(value)
+
 
 def generate_base_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:
     ctx = BaseContext(cli_vars)

core/dbt/context/configured.py

@@ -1,14 +1,14 @@
 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
 
 from dbt.context.base import contextproperty, contextmember, Var
 from dbt.context.target import TargetContext
-from dbt.exceptions import raise_parsing_error, disallow_secret_env_var
+from dbt.exceptions import EnvVarMissingError, SecretEnvVarLocationError
 
 
 class ConfiguredContext(TargetContext):
@@ -86,7 +86,7 @@ class SchemaYamlContext(ConfiguredContext):
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
-            disallow_secret_env_var(var)
+            raise SecretEnvVarLocationError(var)
         if var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
@@ -94,11 +94,17 @@ 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}'"
-            raise_parsing_error(msg)
+            raise EnvVarMissingError(var)
 
 
 class MacroResolvingContext(ConfiguredContext):

core/dbt/context/context_config.py

@@ -5,7 +5,7 @@ from typing import List, Iterator, Dict, Any, TypeVar, Generic
 
 from dbt.config import RuntimeConfig, Project, IsFQNResource
 from dbt.contracts.graph.model_config import BaseConfig, get_config_for, _listify
-from dbt.exceptions import InternalException
+from dbt.exceptions import DbtInternalError
 from dbt.node_types import NodeType
 from dbt.utils import fqn_search
 
@@ -43,9 +43,14 @@ 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.Entity:
+            model_configs = unrendered.get("entities")
+        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 +70,12 @@ 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.Entity:
+            model_configs = self.project.entities
+        elif resource_type == NodeType.Exposure:
+            model_configs = self.project.exposures
         else:
             model_configs = self.project.models
         return model_configs
@@ -82,7 +93,7 @@ class BaseContextConfigGenerator(Generic[T]):
             return self._active_project
         dependencies = self._active_project.load_dependencies()
         if project_name not in dependencies:
-            raise InternalException(
+            raise DbtInternalError(
                 f"Project name {project_name} not found in dependencies "
                 f"(found {list(dependencies)})"
             )
@@ -280,14 +291,14 @@ class ContextConfig:
 
             elif k in BaseConfig.mergebehavior["update"]:
                 if not isinstance(v, dict):
-                    raise InternalException(f"expected dict, got {v}")
+                    raise DbtInternalError(f"expected dict, got {v}")
                 if k in config_call_dict and isinstance(config_call_dict[k], dict):
                     config_call_dict[k].update(v)
                 else:
                     config_call_dict[k] = v
             elif k in BaseConfig.mergebehavior["dict_key_append"]:
                 if not isinstance(v, dict):
-                    raise InternalException(f"expected dict, got {v}")
+                    raise DbtInternalError(f"expected dict, got {v}")
                 if k in config_call_dict:  # should always be a dict
                     for key, value in v.items():
                         extend = False

core/dbt/context/docs.py

@@ -1,13 +1,12 @@
 from typing import Any, Dict, Union
 
 from dbt.exceptions import (
-    doc_invalid_args,
-    doc_target_not_found,
+    DocTargetNotFoundError,
+    DocArgsError,
 )
 from dbt.config.runtime import RuntimeConfig
-from dbt.contracts.graph.compiled import CompileResultNode
 from dbt.contracts.graph.manifest import Manifest
-from dbt.contracts.graph.parsed import ParsedMacro
+from dbt.contracts.graph.nodes import Macro, ResultNode
 
 from dbt.context.base import contextmember
 from dbt.context.configured import SchemaYamlContext
@@ -17,7 +16,7 @@ class DocsRuntimeContext(SchemaYamlContext):
     def __init__(
         self,
         config: RuntimeConfig,
-        node: Union[ParsedMacro, CompileResultNode],
+        node: Union[Macro, ResultNode],
         manifest: Manifest,
         current_project: str,
     ) -> None:
@@ -53,9 +52,9 @@ class DocsRuntimeContext(SchemaYamlContext):
         elif len(args) == 2:
             doc_package_name, doc_name = args
         else:
-            doc_invalid_args(self.node, args)
+            raise DocArgsError(self.node, args)
 
-        # ParsedDocumentation
+        # Documentation
         target_doc = self.manifest.resolve_doc(
             doc_name,
             doc_package_name,
@@ -69,7 +68,9 @@ class DocsRuntimeContext(SchemaYamlContext):
                 # TODO CT-211
                 source_file.add_node(self.node.unique_id)  # type: ignore[union-attr]
         else:
-            doc_target_not_found(self.node, doc_name, doc_package_name)
+            raise DocTargetNotFoundError(
+                node=self.node, target_doc_name=doc_name, target_doc_package=doc_package_name
+            )
 
         return target_doc.block_contents
 

core/dbt/context/exceptions_jinja.py

@@ -0,0 +1,144 @@
+import functools
+from typing import NoReturn
+
+from dbt.events.functions import warn_or_error
+from dbt.events.helpers import env_secrets, scrub_secrets
+from dbt.events.types import JinjaLogWarning
+
+from dbt.exceptions import (
+    DbtRuntimeError,
+    MissingConfigError,
+    MissingMaterializationError,
+    MissingRelationError,
+    AmbiguousAliasError,
+    AmbiguousCatalogMatchError,
+    CacheInconsistencyError,
+    DataclassNotDictError,
+    CompilationError,
+    DbtDatabaseError,
+    DependencyNotFoundError,
+    DependencyError,
+    DuplicatePatchPathError,
+    DuplicateResourceNameError,
+    PropertyYMLError,
+    NotImplementedError,
+    RelationWrongTypeError,
+)
+
+
+def warn(msg, node=None):
+    warn_or_error(JinjaLogWarning(msg=msg), node=node)
+    return ""
+
+
+def missing_config(model, name) -> NoReturn:
+    raise MissingConfigError(unique_id=model.unique_id, name=name)
+
+
+def missing_materialization(model, adapter_type) -> NoReturn:
+    raise MissingMaterializationError(
+        materialization=model.config.materialized, adapter_type=adapter_type
+    )
+
+
+def missing_relation(relation, model=None) -> NoReturn:
+    raise MissingRelationError(relation, model)
+
+
+def raise_ambiguous_alias(node_1, node_2, duped_name=None) -> NoReturn:
+    raise AmbiguousAliasError(node_1, node_2, duped_name)
+
+
+def raise_ambiguous_catalog_match(unique_id, match_1, match_2) -> NoReturn:
+    raise AmbiguousCatalogMatchError(unique_id, match_1, match_2)
+
+
+def raise_cache_inconsistent(message) -> NoReturn:
+    raise CacheInconsistencyError(message)
+
+
+def raise_dataclass_not_dict(obj) -> NoReturn:
+    raise DataclassNotDictError(obj)
+
+
+def raise_compiler_error(msg, node=None) -> NoReturn:
+    raise CompilationError(msg, node)
+
+
+def raise_database_error(msg, node=None) -> NoReturn:
+    raise DbtDatabaseError(msg, node)
+
+
+def raise_dep_not_found(node, node_description, required_pkg) -> NoReturn:
+    raise DependencyNotFoundError(node, node_description, required_pkg)
+
+
+def raise_dependency_error(msg) -> NoReturn:
+    raise DependencyError(scrub_secrets(msg, env_secrets()))
+
+
+def raise_duplicate_patch_name(patch_1, existing_patch_path) -> NoReturn:
+    raise DuplicatePatchPathError(patch_1, existing_patch_path)
+
+
+def raise_duplicate_resource_name(node_1, node_2) -> NoReturn:
+    raise DuplicateResourceNameError(node_1, node_2)
+
+
+def raise_invalid_property_yml_version(path, issue) -> NoReturn:
+    raise PropertyYMLError(path, issue)
+
+
+def raise_not_implemented(msg) -> NoReturn:
+    raise NotImplementedError(msg)
+
+
+def relation_wrong_type(relation, expected_type, model=None) -> NoReturn:
+    raise RelationWrongTypeError(relation, expected_type, model)
+
+
+# Update this when a new function should be added to the
+# dbt context's `exceptions` key!
+CONTEXT_EXPORTS = {
+    fn.__name__: fn
+    for fn in [
+        warn,
+        missing_config,
+        missing_materialization,
+        missing_relation,
+        raise_ambiguous_alias,
+        raise_ambiguous_catalog_match,
+        raise_cache_inconsistent,
+        raise_dataclass_not_dict,
+        raise_compiler_error,
+        raise_database_error,
+        raise_dep_not_found,
+        raise_dependency_error,
+        raise_duplicate_patch_name,
+        raise_duplicate_resource_name,
+        raise_invalid_property_yml_version,
+        raise_not_implemented,
+        relation_wrong_type,
+    ]
+}
+
+
+# wraps context based exceptions in node info
+def wrapper(model):
+    def wrap(func):
+        @functools.wraps(func)
+        def inner(*args, **kwargs):
+            try:
+                return func(*args, **kwargs)
+            except DbtRuntimeError as exc:
+                exc.add_node(model)
+                raise exc
+
+        return inner
+
+    return wrap
+
+
+def wrapped_exports(model):
+    wrap = wrapper(model)
+    return {name: wrap(export) for name, export in CONTEXT_EXPORTS.items()}

core/dbt/context/macro_resolver.py

@@ -1,10 +1,10 @@
 from typing import Dict, MutableMapping, Optional
-from dbt.contracts.graph.parsed import ParsedMacro
-from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
+from dbt.contracts.graph.nodes import Macro
+from dbt.exceptions import DuplicateMacroNameError, PackageNotFoundForMacroError
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
 from dbt.clients.jinja import MacroGenerator
 
-MacroNamespace = Dict[str, ParsedMacro]
+MacroNamespace = Dict[str, Macro]
 
 
 # This class builds the MacroResolver by adding macros
@@ -21,7 +21,7 @@ MacroNamespace = Dict[str, ParsedMacro]
 class MacroResolver:
     def __init__(
         self,
-        macros: MutableMapping[str, ParsedMacro],
+        macros: MutableMapping[str, Macro],
         root_project_name: str,
         internal_package_names,
     ) -> None:
@@ -77,7 +77,7 @@ class MacroResolver:
     def _add_macro_to(
         self,
         package_namespaces: Dict[str, MacroNamespace],
-        macro: ParsedMacro,
+        macro: Macro,
     ):
         if macro.package_name in package_namespaces:
             namespace = package_namespaces[macro.package_name]
@@ -86,10 +86,10 @@ class MacroResolver:
             package_namespaces[macro.package_name] = namespace
 
         if macro.name in namespace:
-            raise_duplicate_macro_name(macro, macro, macro.package_name)
+            raise DuplicateMacroNameError(macro, macro, macro.package_name)
         package_namespaces[macro.package_name][macro.name] = macro
 
-    def add_macro(self, macro: ParsedMacro):
+    def add_macro(self, macro: Macro):
         macro_name: str = macro.name
 
         # internal macros (from plugins) will be processed separately from
@@ -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
@@ -181,7 +187,7 @@ class TestMacroNamespace:
         elif package_name in self.macro_resolver.packages:
             macro = self.macro_resolver.packages[package_name].get(name)
         else:
-            raise_compiler_error(f"Could not find package '{package_name}'")
+            raise PackageNotFoundForMacroError(package_name)
         if not macro:
             return None
         macro_func = MacroGenerator(macro, self.ctx, self.node, self.thread_ctx)

core/dbt/context/macros.py

@@ -1,9 +1,9 @@
 from typing import Any, Dict, Iterable, Union, Optional, List, Iterator, Mapping, Set
 
 from dbt.clients.jinja import MacroGenerator, MacroStack
-from dbt.contracts.graph.parsed import ParsedMacro
+from dbt.contracts.graph.nodes import Macro
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
-from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
+from dbt.exceptions import DuplicateMacroNameError, PackageNotFoundForMacroError
 
 
 FlatNamespace = Dict[str, MacroGenerator]
@@ -75,7 +75,7 @@ class MacroNamespace(Mapping):
         elif package_name in self.packages:
             return self.packages[package_name].get(name)
         else:
-            raise_compiler_error(f"Could not find package '{package_name}'")
+            raise PackageNotFoundForMacroError(package_name)
 
 
 # This class builds the MacroNamespace by adding macros to
@@ -112,7 +112,7 @@ class MacroNamespaceBuilder:
     def _add_macro_to(
         self,
         hierarchy: Dict[str, FlatNamespace],
-        macro: ParsedMacro,
+        macro: Macro,
         macro_func: MacroGenerator,
     ):
         if macro.package_name in hierarchy:
@@ -122,10 +122,10 @@ class MacroNamespaceBuilder:
             hierarchy[macro.package_name] = namespace
 
         if macro.name in namespace:
-            raise_duplicate_macro_name(macro_func.macro, macro, macro.package_name)
+            raise DuplicateMacroNameError(macro_func.macro, macro, macro.package_name)
         hierarchy[macro.package_name][macro.name] = macro_func
 
-    def add_macro(self, macro: ParsedMacro, ctx: Dict[str, Any]):
+    def add_macro(self, macro: Macro, ctx: Dict[str, Any]):
         macro_name: str = macro.name
 
         # MacroGenerator is in clients/jinja.py
@@ -147,13 +147,11 @@ class MacroNamespaceBuilder:
             elif macro.package_name == self.root_package:
                 self.globals[macro_name] = macro_func
 
-    def add_macros(self, macros: Iterable[ParsedMacro], ctx: Dict[str, Any]):
+    def add_macros(self, macros: Iterable[Macro], ctx: Dict[str, Any]):
         for macro in macros:
             self.add_macro(macro, ctx)
 
-    def build_namespace(
-        self, macros: Iterable[ParsedMacro], ctx: Dict[str, Any]
-    ) -> MacroNamespace:
+    def build_namespace(self, macros: Iterable[Macro], ctx: Dict[str, Any]) -> MacroNamespace:
         self.add_macros(macros, ctx)
 
         # Iterate in reverse-order and overwrite: the packages that are first

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

@@ -19,51 +19,56 @@ from dbt.adapters.factory import get_adapter, get_adapter_package_names, get_ada
 from dbt.clients import agate_helper
 from dbt.clients.jinja import get_rendered, MacroGenerator, MacroStack
 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.base import contextmember, contextproperty, Var
+from dbt.context.configured import FQNLookup
+from dbt.context.context_config import ContextConfig
+from dbt.context.exceptions_jinja import wrapped_exports
 from dbt.context.macro_resolver import MacroResolver, TestMacroNamespace
-from .macros import MacroNamespaceBuilder, MacroNamespace
-from .manifest import ManifestContext
+from dbt.context.macros import MacroNamespaceBuilder, MacroNamespace
+from dbt.context.manifest import ManifestContext
 from dbt.contracts.connection import AdapterResponse
 from dbt.contracts.graph.manifest import Manifest, Disabled
-from dbt.contracts.graph.compiled import (
-    CompiledResource,
-    CompiledSeedNode,
+from dbt.contracts.graph.nodes import (
+    Macro,
+    Exposure,
+    Metric,
+    Entity,
+    SeedNode,
+    SourceDefinition,
+    Resource,
     ManifestNode,
 )
-from dbt.contracts.graph.parsed import (
-    ParsedMacro,
-    ParsedExposure,
-    ParsedMetric,
-    ParsedSeedNode,
-    ParsedSourceDefinition,
-)
 from dbt.contracts.graph.metrics import MetricReference, ResolvedMetricReference
+from dbt.events.functions import get_metadata_vars
 from dbt.exceptions import (
-    CompilationException,
-    ParsingException,
-    InternalException,
-    ValidationException,
-    RuntimeException,
-    macro_invalid_dispatch_arg,
-    missing_config,
-    raise_compiler_error,
-    ref_invalid_args,
-    metric_invalid_args,
-    ref_target_not_found,
-    metric_target_not_found,
-    ref_bad_context,
-    source_target_not_found,
-    wrapped_exports,
-    raise_parsing_error,
-    disallow_secret_env_var,
+    CompilationError,
+    ConflictingConfigKeysError,
+    SecretEnvVarLocationError,
+    EnvVarMissingError,
+    DbtInternalError,
+    InlineModelConfigError,
+    NumberSourceArgsError,
+    PersistDocsValueTypeError,
+    LoadAgateTableNotSeedError,
+    LoadAgateTableValueError,
+    MacroDispatchArgError,
+    MacrosSourcesUnWriteableError,
+    MetricArgsError,
+    MissingConfigError,
+    OperationsCannotRefEphemeralNodesError,
+    PackageNotInDepsError,
+    ParsingError,
+    RefBadContextError,
+    RefArgsError,
+    DbtRuntimeError,
+    TargetNotFoundError,
+    DbtValidationError,
 )
 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
 
@@ -140,10 +145,10 @@ class BaseDatabaseWrapper:
                 f'`adapter.dispatch("{suggest_macro_name}", '
                 f'macro_namespace="{suggest_macro_namespace}")`?'
             )
-            raise CompilationException(msg)
+            raise CompilationError(msg)
 
         if packages is not None:
-            raise macro_invalid_dispatch_arg(macro_name)
+            raise MacroDispatchArgError(macro_name)
 
         namespace = macro_namespace
 
@@ -155,7 +160,7 @@ class BaseDatabaseWrapper:
                 search_packages = [self.config.project_name, namespace]
         else:
             # Not a string and not None so must be a list
-            raise CompilationException(
+            raise CompilationError(
                 f"In adapter.dispatch, got a list macro_namespace argument "
                 f'("{macro_namespace}"), but macro_namespace should be None or a string.'
             )
@@ -168,8 +173,8 @@ class BaseDatabaseWrapper:
                 try:
                     # this uses the namespace from the context
                     macro = self._namespace.get_from_package(package_name, search_name)
-                except CompilationException:
-                    # Only raise CompilationException if macro is not found in
+                except CompilationError:
+                    # Only raise CompilationError if macro is not found in
                     # any package
                     macro = None
 
@@ -182,8 +187,8 @@ class BaseDatabaseWrapper:
                     return macro
 
         searched = ", ".join(repr(a) for a in attempts)
-        msg = f"In dispatch: No macro named '{macro_name}' found\n" f"    Searched for: {searched}"
-        raise CompilationException(msg)
+        msg = f"In dispatch: No macro named '{macro_name}' found\n    Searched for: {searched}"
+        raise CompilationError(msg)
 
 
 class BaseResolver(metaclass=abc.ABCMeta):
@@ -219,13 +224,13 @@ class BaseRefResolver(BaseResolver):
 
     def validate_args(self, name: str, package: Optional[str]):
         if not isinstance(name, str):
-            raise CompilationException(
-                f"The name argument to ref() must be a string, got " f"{type(name)}"
+            raise CompilationError(
+                f"The name argument to ref() must be a string, got {type(name)}"
             )
 
         if package is not None and not isinstance(package, str):
-            raise CompilationException(
-                f"The package argument to ref() must be a string or None, got " f"{type(package)}"
+            raise CompilationError(
+                f"The package argument to ref() must be a string or None, got {type(package)}"
             )
 
     def __call__(self, *args: str) -> RelationProxy:
@@ -237,7 +242,7 @@ class BaseRefResolver(BaseResolver):
         elif len(args) == 2:
             package, name = args
         else:
-            ref_invalid_args(self.model, args)
+            raise RefArgsError(node=self.model, args=args)
         self.validate_args(name, package)
         return self.resolve(name, package)
 
@@ -249,21 +254,19 @@ class BaseSourceResolver(BaseResolver):
 
     def validate_args(self, source_name: str, table_name: str):
         if not isinstance(source_name, str):
-            raise CompilationException(
+            raise CompilationError(
                 f"The source name (first) argument to source() must be a "
                 f"string, got {type(source_name)}"
             )
         if not isinstance(table_name, str):
-            raise CompilationException(
+            raise CompilationError(
                 f"The table name (second) argument to source() must be a "
                 f"string, got {type(table_name)}"
             )
 
     def __call__(self, *args: str) -> RelationProxy:
         if len(args) != 2:
-            raise_compiler_error(
-                f"source() takes exactly two arguments ({len(args)} given)", self.model
-            )
+            raise NumberSourceArgsError(args, node=self.model)
         self.validate_args(args[0], args[1])
         return self.resolve(args[0], args[1])
 
@@ -280,12 +283,12 @@ class BaseMetricResolver(BaseResolver):
 
     def validate_args(self, name: str, package: Optional[str]):
         if not isinstance(name, str):
-            raise CompilationException(
+            raise CompilationError(
                 f"The name argument to metric() must be a string, got {type(name)}"
             )
 
         if package is not None and not isinstance(package, str):
-            raise CompilationException(
+            raise CompilationError(
                 f"The package argument to metric() must be a string or None, got {type(package)}"
             )
 
@@ -298,7 +301,7 @@ class BaseMetricResolver(BaseResolver):
         elif len(args) == 2:
             package, name = args
         else:
-            metric_invalid_args(self.model, args)
+            raise MetricArgsError(node=self.model, args=args)
         self.validate_args(name, package)
         return self.resolve(name, package)
 
@@ -319,12 +322,7 @@ class ParseConfigObject(Config):
             if oldkey in config:
                 newkey = oldkey.replace("_", "-")
                 if newkey in config:
-                    raise_compiler_error(
-                        'Invalid config, has conflicting keys "{}" and "{}"'.format(
-                            oldkey, newkey
-                        ),
-                        self.model,
-                    )
+                    raise ConflictingConfigKeysError(oldkey, newkey, node=self.model)
                 config[newkey] = config.pop(oldkey)
         return config
 
@@ -334,14 +332,14 @@ class ParseConfigObject(Config):
         elif len(args) == 0 and len(kwargs) > 0:
             opts = kwargs
         else:
-            raise_compiler_error("Invalid inline model config", self.model)
+            raise InlineModelConfigError(node=self.model)
 
         opts = self._transform_config(opts)
 
         # it's ok to have a parse context with no context config, but you must
         # not call it!
         if self.context_config is None:
-            raise RuntimeException("At parse time, did not receive a context config")
+            raise DbtRuntimeError("At parse time, did not receive a context config")
         self.context_config.add_config_call(opts)
         return ""
 
@@ -382,7 +380,7 @@ class RuntimeConfigObject(Config):
         else:
             result = self.model.config.get(name, default)
         if result is _MISSING:
-            missing_config(self.model, name)
+            raise MissingConfigError(unique_id=self.model.unique_id, name=name)
         return result
 
     def require(self, name, validator=None):
@@ -404,20 +402,14 @@ class RuntimeConfigObject(Config):
     def persist_relation_docs(self) -> bool:
         persist_docs = self.get("persist_docs", default={})
         if not isinstance(persist_docs, dict):
-            raise_compiler_error(
-                f"Invalid value provided for 'persist_docs'. Expected dict "
-                f"but received {type(persist_docs)}"
-            )
+            raise PersistDocsValueTypeError(persist_docs)
 
         return persist_docs.get("relation", False)
 
     def persist_column_docs(self) -> bool:
         persist_docs = self.get("persist_docs", default={})
         if not isinstance(persist_docs, dict):
-            raise_compiler_error(
-                f"Invalid value provided for 'persist_docs'. Expected dict "
-                f"but received {type(persist_docs)}"
-            )
+            raise PersistDocsValueTypeError(persist_docs)
 
         return persist_docs.get("columns", False)
 
@@ -476,10 +468,11 @@ class RuntimeRefResolver(BaseRefResolver):
         )
 
         if target_model is None or isinstance(target_model, Disabled):
-            ref_target_not_found(
-                self.model,
-                target_name,
-                target_package,
+            raise TargetNotFoundError(
+                node=self.model,
+                target_name=target_name,
+                target_kind="node",
+                target_package=target_package,
                 disabled=isinstance(target_model, Disabled),
             )
         self.validate(target_model, target_name, target_package)
@@ -497,7 +490,7 @@ class RuntimeRefResolver(BaseRefResolver):
     ) -> None:
         if resolved.unique_id not in self.model.depends_on.nodes:
             args = self._repack_args(target_name, target_package)
-            ref_bad_context(self.model, args)
+            raise RefBadContextError(node=self.model, args=args)
 
 
 class OperationRefResolver(RuntimeRefResolver):
@@ -512,13 +505,8 @@ class OperationRefResolver(RuntimeRefResolver):
     def create_relation(self, target_model: ManifestNode, name: str) -> RelationProxy:
         if target_model.is_ephemeral_model:
             # In operations, we can't ref() ephemeral nodes, because
-            # ParsedMacros do not support set_cte
-            raise_compiler_error(
-                "Operations can not ref() ephemeral nodes, but {} is ephemeral".format(
-                    target_model.name
-                ),
-                self.model,
-            )
+            # Macros do not support set_cte
+            raise OperationsCannotRefEphemeralNodesError(target_model.name, node=self.model)
         else:
             return super().create_relation(target_model, name)
 
@@ -541,10 +529,11 @@ class RuntimeSourceResolver(BaseSourceResolver):
         )
 
         if target_source is None or isinstance(target_source, Disabled):
-            source_target_not_found(
-                self.model,
-                source_name,
-                table_name,
+            raise TargetNotFoundError(
+                node=self.model,
+                target_name=f"{source_name}.{table_name}",
+                target_kind="source",
+                disabled=(isinstance(target_source, Disabled)),
             )
         return self.Relation.create_from_source(target_source)
 
@@ -567,11 +556,11 @@ class RuntimeMetricResolver(BaseMetricResolver):
         )
 
         if target_metric is None or isinstance(target_metric, Disabled):
-            # TODO : Use a different exception!!
-            metric_target_not_found(
-                self.model,
-                target_name,
-                target_package,
+            raise TargetNotFoundError(
+                node=self.model,
+                target_name=target_name,
+                target_kind="metric",
+                target_package=target_package,
             )
 
         return ResolvedMetricReference(target_metric, self.manifest, self.Relation)
@@ -583,9 +572,9 @@ class ModelConfiguredVar(Var):
         self,
         context: Dict[str, Any],
         config: RuntimeConfig,
-        node: CompiledResource,
+        node: Resource,
     ) -> None:
-        self._node: CompiledResource
+        self._node: Resource
         self._config: RuntimeConfig = config
         super().__init__(context, config.cli_vars, node=node)
 
@@ -596,7 +585,7 @@ class ModelConfiguredVar(Var):
         if package_name != self._config.project_name:
             if package_name not in dependencies:
                 # I don't think this is actually reachable
-                raise_compiler_error(f"Node package named {package_name} not found!", self._node)
+                raise PackageNotInDepsError(package_name, node=self._node)
             yield dependencies[package_name]
         yield self._config
 
@@ -686,10 +675,10 @@ class ProviderContext(ManifestContext):
         context_config: Optional[ContextConfig],
     ) -> None:
         if provider is None:
-            raise InternalException(f"Invalid provider given to context: {provider}")
+            raise DbtInternalError(f"Invalid provider given to context: {provider}")
         # mypy appeasement - we know it'll be a RuntimeConfig
         self.config: RuntimeConfig
-        self.model: Union[ParsedMacro, ManifestNode] = model
+        self.model: Union[Macro, ManifestNode] = model
         super().__init__(config, manifest, model.package_name)
         self.sql_results: Dict[str, AttrDict] = {}
         self.context_config: Optional[ContextConfig] = context_config
@@ -710,6 +699,14 @@ class ProviderContext(ManifestContext):
             self.model,
         )
 
+    @contextproperty
+    def dbt_metadata_envs(self) -> Dict[str, str]:
+        return get_metadata_vars()
+
+    @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
@@ -755,7 +752,7 @@ class ProviderContext(ManifestContext):
                         return
                     elif value == arg:
                         return
-                raise ValidationException(
+                raise DbtValidationError(
                     'Expected value "{}" to be one of {}'.format(value, ",".join(map(str, args)))
                 )
 
@@ -770,8 +767,8 @@ class ProviderContext(ManifestContext):
     @contextmember
     def write(self, payload: str) -> str:
         # macros/source defs aren't 'writeable'.
-        if isinstance(self.model, (ParsedMacro, ParsedSourceDefinition)):
-            raise_compiler_error('cannot "write" macros or sources')
+        if isinstance(self.model, (Macro, SourceDefinition)):
+            raise MacrosSourcesUnWriteableError(node=self.model)
         self.model.build_path = self.model.write_node(self.config.target_path, "run", payload)
         return ""
 
@@ -786,20 +783,19 @@ class ProviderContext(ManifestContext):
         try:
             return func(*args, **kwargs)
         except Exception:
-            raise_compiler_error(message_if_exception, self.model)
+            raise CompilationError(message_if_exception, self.model)
 
     @contextmember
     def load_agate_table(self) -> agate.Table:
-        if not isinstance(self.model, (ParsedSeedNode, CompiledSeedNode)):
-            raise_compiler_error(
-                "can only load_agate_table for seeds (got a {})".format(self.model.resource_type)
-            )
+        if not isinstance(self.model, SeedNode):
+            raise LoadAgateTableNotSeedError(self.model.resource_type, node=self.model)
+        assert self.model.root_path
         path = os.path.join(self.model.root_path, self.model.original_file_path)
         column_types = self.model.config.column_types
         try:
             table = agate_helper.from_csv(path, text_columns=column_types)
         except ValueError as e:
-            raise_compiler_error(str(e))
+            raise LoadAgateTableValueError(e, node=self.model)
         table.original_abspath = os.path.abspath(path)
         return table
 
@@ -1157,7 +1153,12 @@ 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]]]:
@@ -1185,7 +1186,7 @@ class ProviderContext(ManifestContext):
             "https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch)"
             " adapter_macro was called for: {macro_name}".format(macro_name=name)
         )
-        raise CompilationException(msg)
+        raise CompilationError(msg)
 
     @contextmember
     def env_var(self, var: str, default: Optional[str] = None) -> str:
@@ -1196,7 +1197,7 @@ class ProviderContext(ManifestContext):
         """
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
-            disallow_secret_env_var(var)
+            raise SecretEnvVarLocationError(var)
         if var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
@@ -1205,8 +1206,21 @@ class ProviderContext(ManifestContext):
         if return_value is not None:
             # 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
+            compiling = (
+                True
+                if hasattr(self.model, "compiled")
+                and getattr(self.model, "compiled", False) is True
+                else False
+            )
+            if self.model and not compiling:
+                # 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]
@@ -1216,8 +1230,7 @@ class ProviderContext(ManifestContext):
                         source_file.env_vars.append(var)  # type: ignore[union-attr]
             return return_value
         else:
-            msg = f"Env var required but not provided: '{var}'"
-            raise_parsing_error(msg)
+            raise EnvVarMissingError(var)
 
     @contextproperty
     def selected_resources(self) -> List[str]:
@@ -1228,6 +1241,19 @@ 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 DbtRuntimeError(
+                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:
@@ -1240,7 +1266,7 @@ class MacroContext(ProviderContext):
 
     def __init__(
         self,
-        model: ParsedMacro,
+        model: Macro,
         config: RuntimeConfig,
         manifest: Manifest,
         provider: Provider,
@@ -1278,9 +1304,20 @@ 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
@@ -1344,7 +1381,7 @@ def generate_parser_model_context(
 
 
 def generate_generate_name_macro_context(
-    macro: ParsedMacro,
+    macro: Macro,
     config: RuntimeConfig,
     manifest: Manifest,
 ) -> Dict[str, Any]:
@@ -1362,7 +1399,7 @@ def generate_runtime_model_context(
 
 
 def generate_runtime_macro_context(
-    macro: ParsedMacro,
+    macro: Macro,
     config: RuntimeConfig,
     manifest: Manifest,
     package_name: Optional[str],
@@ -1374,7 +1411,7 @@ def generate_runtime_macro_context(
 class ExposureRefResolver(BaseResolver):
     def __call__(self, *args) -> str:
         if len(args) not in (1, 2):
-            ref_invalid_args(self.model, args)
+            raise RefArgsError(node=self.model, args=args)
         self.model.refs.append(list(args))
         return ""
 
@@ -1382,15 +1419,21 @@ class ExposureRefResolver(BaseResolver):
 class ExposureSourceResolver(BaseResolver):
     def __call__(self, *args) -> str:
         if len(args) != 2:
-            raise_compiler_error(
-                f"source() takes exactly two arguments ({len(args)} given)", self.model
-            )
+            raise NumberSourceArgsError(args, node=self.model)
         self.model.sources.append(list(args))
         return ""
 
 
+class ExposureMetricResolver(BaseResolver):
+    def __call__(self, *args) -> str:
+        if len(args) not in (1, 2):
+            raise MetricArgsError(node=self.model, args=args)
+        self.model.metrics.append(list(args))
+        return ""
+
+
 def generate_parse_exposure(
-    exposure: ParsedExposure,
+    exposure: Exposure,
     config: RuntimeConfig,
     manifest: Manifest,
     package_name: str,
@@ -1409,6 +1452,12 @@ def generate_parse_exposure(
             project,
             manifest,
         ),
+        "metric": ExposureMetricResolver(
+            None,
+            exposure,
+            project,
+            manifest,
+        ),
     }
 
 
@@ -1420,21 +1469,21 @@ class MetricRefResolver(BaseResolver):
         elif len(args) == 2:
             package, name = args
         else:
-            ref_invalid_args(self.model, args)
+            raise RefArgsError(node=self.model, args=args)
         self.validate_args(name, package)
         self.model.refs.append(list(args))
         return ""
 
     def validate_args(self, name, package):
         if not isinstance(name, str):
-            raise ParsingException(
+            raise ParsingError(
                 f"In a metrics section in {self.model.original_file_path} "
                 "the name argument to ref() must be a string"
             )
 
 
 def generate_parse_metrics(
-    metric: ParsedMetric,
+    metric: Metric,
     config: RuntimeConfig,
     manifest: Manifest,
     package_name: str,
@@ -1456,6 +1505,44 @@ def generate_parse_metrics(
     }
 
 
+class EntityRefResolver(BaseResolver):
+    def __call__(self, *args) -> str:
+        package = None
+        if len(args) == 1:
+            name = args[0]
+        elif len(args) == 2:
+            package, name = args
+        else:
+            raise RefArgsError(node=self.model, args=args)
+        self.validate_args(name, package)
+        self.model.refs.append(list(args))
+        return ""
+
+    def validate_args(self, name, package):
+        if not isinstance(name, str):
+            raise ParsingError(
+                f"In the entity associated with {self.model.original_file_path} "
+                "the name argument to ref() must be a string"
+            )
+
+
+def generate_parse_entities(
+    entity: Entity,
+    config: RuntimeConfig,
+    manifest: Manifest,
+    package_name: str,
+) -> Dict[str, Any]:
+    project = config.load_dependencies()[package_name]
+    return {
+        "ref": EntityRefResolver(
+            None,
+            entity,
+            project,
+            manifest,
+        ),
+    }
+
+
 # This class is currently used by the schema parser in order
 # to limit the number of macros in the context by using
 # the TestMacroNamespace
@@ -1510,7 +1597,7 @@ class TestContext(ProviderContext):
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
-            disallow_secret_env_var(var)
+            raise SecretEnvVarLocationError(var)
         if var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
@@ -1519,7 +1606,13 @@ 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
@@ -1530,8 +1623,7 @@ class TestContext(ProviderContext):
                     source_file.add_env_var(var, yaml_key, name)  # type: ignore[union-attr]
             return return_value
         else:
-            msg = f"Env var required but not provided: '{var}'"
-            raise_parsing_error(msg)
+            raise EnvVarMissingError(var)
 
 
 def generate_test_context(

core/dbt/context/secret.py

@@ -3,8 +3,8 @@ from typing import Any, Dict, Optional
 
 from .base import BaseContext, contextmember
 
-from dbt.exceptions import raise_parsing_error
-from dbt.logger import SECRET_ENV_PREFIX
+from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
+from dbt.exceptions import EnvVarMissingError
 
 
 SECRET_PLACEHOLDER = "$$$DBT_SECRET_START$$${}$$$DBT_SECRET_END$$$"
@@ -43,11 +43,14 @@ 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}'"
-            raise_parsing_error(msg)
+            raise EnvVarMissingError(var)
 
 
 def generate_secret_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:

core/dbt/contracts/connection.py

@@ -12,10 +12,11 @@ from typing import (
     List,
     Callable,
 )
-from dbt.exceptions import InternalException
+from dbt.exceptions import DbtInternalError
 from dbt.utils import translate_aliases
 from dbt.events.functions import fire_event
 from dbt.events.types import NewConnectionOpening
+from dbt.events.contextvars import get_node_info
 from typing_extensions import Protocol
 from dbt.dataclass_schema import (
     dbtClassMixin,
@@ -93,8 +94,8 @@ class Connection(ExtensibleDbtClassMixin, Replaceable):
                 # this will actually change 'self._handle'.
                 self._handle.resolve(self)
             except RecursionError as exc:
-                raise InternalException(
-                    "A connection's open() method attempted to read the " "handle value"
+                raise DbtInternalError(
+                    "A connection's open() method attempted to read the handle value"
                 ) from exc
         return self._handle
 
@@ -112,7 +113,9 @@ class LazyHandle:
         self.opener = opener
 
     def resolve(self, connection: Connection) -> Connection:
-        fire_event(NewConnectionOpening(connection_state=connection.state))
+        fire_event(
+            NewConnectionOpening(connection_state=connection.state, node_info=get_node_info())
+        )
         return self.opener(connection)
 
 

core/dbt/contracts/files.py

@@ -1,18 +1,16 @@
 import hashlib
 import os
 from dataclasses import dataclass, field
+
 from mashumaro.types import SerializableType
 from typing import List, Optional, Union, Dict, Any
 
+from dbt.constants import MAXIMUM_SEED_SIZE
 from dbt.dataclass_schema import dbtClassMixin, StrEnum
 
 from .util import SourceKey
 
 
-MAXIMUM_SEED_SIZE = 1 * 1024 * 1024
-MAXIMUM_SEED_SIZE_NAME = "1MB"
-
-
 class ParseFileType(StrEnum):
     Macro = "macro"
     Model = "model"
@@ -114,25 +112,34 @@ 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 +209,9 @@ 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 +227,7 @@ 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 +276,13 @@ 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

@@ -1,235 +0,0 @@
-from dbt.contracts.graph.parsed import (
-    HasTestMetadata,
-    ParsedNode,
-    ParsedAnalysisNode,
-    ParsedSingularTestNode,
-    ParsedHookNode,
-    ParsedModelNode,
-    ParsedExposure,
-    ParsedMetric,
-    ParsedResource,
-    ParsedRPCNode,
-    ParsedSqlNode,
-    ParsedGenericTestNode,
-    ParsedSeedNode,
-    ParsedSnapshotNode,
-    ParsedSourceDefinition,
-    SeedConfig,
-    TestConfig,
-    same_seeds,
-)
-from dbt.node_types import NodeType
-from dbt.contracts.util import Replaceable
-
-from dbt.dataclass_schema import dbtClassMixin
-from dataclasses import dataclass, field
-from typing import Optional, List, Union, Dict, Type
-
-
-@dataclass
-class InjectedCTE(dbtClassMixin, Replaceable):
-    id: str
-    sql: str
-
-
-@dataclass
-class CompiledNodeMixin(dbtClassMixin):
-    # this is a special mixin class to provide a required argument. If a node
-    # is missing a `compiled` flag entirely, it must not be a CompiledNode.
-    compiled: bool
-
-
-@dataclass
-class CompiledNode(ParsedNode, CompiledNodeMixin):
-    compiled_sql: Optional[str] = None
-    extra_ctes_injected: bool = False
-    extra_ctes: List[InjectedCTE] = field(default_factory=list)
-    relation_name: Optional[str] = None
-    _pre_injected_sql: Optional[str] = None
-
-    def set_cte(self, cte_id: str, sql: str):
-        """This is the equivalent of what self.extra_ctes[cte_id] = sql would
-        do if extra_ctes were an OrderedDict
-        """
-        for cte in self.extra_ctes:
-            if cte.id == cte_id:
-                cte.sql = sql
-                break
-        else:
-            self.extra_ctes.append(InjectedCTE(id=cte_id, sql=sql))
-
-    def __post_serialize__(self, dct):
-        dct = super().__post_serialize__(dct)
-        if "_pre_injected_sql" in dct:
-            del dct["_pre_injected_sql"]
-        return dct
-
-
-@dataclass
-class CompiledAnalysisNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Analysis]})
-
-
-@dataclass
-class CompiledHookNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
-    index: Optional[int] = None
-
-
-@dataclass
-class CompiledModelNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Model]})
-
-
-# TODO: rm?
-@dataclass
-class CompiledRPCNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.RPCCall]})
-
-
-@dataclass
-class CompiledSqlNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.SqlOperation]})
-
-
-@dataclass
-class CompiledSeedNode(CompiledNode):
-    # keep this in sync with ParsedSeedNode!
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Seed]})
-    config: SeedConfig = field(default_factory=SeedConfig)
-
-    @property
-    def empty(self):
-        """Seeds are never empty"""
-        return False
-
-    def same_body(self, other) -> bool:
-        return same_seeds(self, other)
-
-
-@dataclass
-class CompiledSnapshotNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
-
-
-@dataclass
-class CompiledSingularTestNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
-    # Was not able to make mypy happy and keep the code working. We need to
-    # refactor the various configs.
-    config: TestConfig = field(default_factory=TestConfig)  # type:ignore
-
-
-@dataclass
-class CompiledGenericTestNode(CompiledNode, HasTestMetadata):
-    # keep this in sync with ParsedGenericTestNode!
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
-    column_name: Optional[str] = None
-    file_key_name: Optional[str] = None
-    # Was not able to make mypy happy and keep the code working. We need to
-    # refactor the various configs.
-    config: TestConfig = field(default_factory=TestConfig)  # type:ignore
-
-    def same_contents(self, other) -> bool:
-        if other is None:
-            return False
-
-        return self.same_config(other) and self.same_fqn(other) and True
-
-
-CompiledTestNode = Union[CompiledSingularTestNode, CompiledGenericTestNode]
-
-
-PARSED_TYPES: Dict[Type[CompiledNode], Type[ParsedResource]] = {
-    CompiledAnalysisNode: ParsedAnalysisNode,
-    CompiledModelNode: ParsedModelNode,
-    CompiledHookNode: ParsedHookNode,
-    CompiledRPCNode: ParsedRPCNode,
-    CompiledSqlNode: ParsedSqlNode,
-    CompiledSeedNode: ParsedSeedNode,
-    CompiledSnapshotNode: ParsedSnapshotNode,
-    CompiledSingularTestNode: ParsedSingularTestNode,
-    CompiledGenericTestNode: ParsedGenericTestNode,
-}
-
-
-COMPILED_TYPES: Dict[Type[ParsedResource], Type[CompiledNode]] = {
-    ParsedAnalysisNode: CompiledAnalysisNode,
-    ParsedModelNode: CompiledModelNode,
-    ParsedHookNode: CompiledHookNode,
-    ParsedRPCNode: CompiledRPCNode,
-    ParsedSqlNode: CompiledSqlNode,
-    ParsedSeedNode: CompiledSeedNode,
-    ParsedSnapshotNode: CompiledSnapshotNode,
-    ParsedSingularTestNode: CompiledSingularTestNode,
-    ParsedGenericTestNode: CompiledGenericTestNode,
-}
-
-
-# for some types, the compiled type is the parsed type, so make this easy
-CompiledType = Union[Type[CompiledNode], Type[ParsedResource]]
-CompiledResource = Union[ParsedResource, CompiledNode]
-
-
-def compiled_type_for(parsed: ParsedNode) -> CompiledType:
-    if type(parsed) in COMPILED_TYPES:
-        return COMPILED_TYPES[type(parsed)]
-    else:
-        return type(parsed)
-
-
-def parsed_instance_for(compiled: CompiledNode) -> ParsedResource:
-    cls = PARSED_TYPES.get(type(compiled))
-    if cls is None:
-        # how???
-        raise ValueError("invalid resource_type: {}".format(compiled.resource_type))
-
-    return cls.from_dict(compiled.to_dict(omit_none=True))
-
-
-NonSourceCompiledNode = Union[
-    CompiledAnalysisNode,
-    CompiledSingularTestNode,
-    CompiledModelNode,
-    CompiledHookNode,
-    CompiledRPCNode,
-    CompiledSqlNode,
-    CompiledGenericTestNode,
-    CompiledSeedNode,
-    CompiledSnapshotNode,
-]
-
-NonSourceParsedNode = Union[
-    ParsedAnalysisNode,
-    ParsedSingularTestNode,
-    ParsedHookNode,
-    ParsedModelNode,
-    ParsedRPCNode,
-    ParsedSqlNode,
-    ParsedGenericTestNode,
-    ParsedSeedNode,
-    ParsedSnapshotNode,
-]
-
-
-# This is anything that can be in manifest.nodes.
-ManifestNode = Union[
-    NonSourceCompiledNode,
-    NonSourceParsedNode,
-]
-
-# We allow either parsed or compiled nodes, or parsed sources, as some
-# 'compile()' calls in the runner actually just return the original parsed
-# node they were given.
-CompileResultNode = Union[
-    ManifestNode,
-    ParsedSourceDefinition,
-]
-
-# anything that participates in the graph: sources, exposures, metrics,
-# or manifest nodes
-GraphMemberNode = Union[
-    CompileResultNode,
-    ParsedExposure,
-    ParsedMetric,
-]

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,
@@ -16,43 +16,40 @@ from typing import (
     TypeVar,
     Callable,
     Generic,
-    cast,
     AbstractSet,
     ClassVar,
 )
 from typing_extensions import Protocol
 from uuid import UUID
 
-from dbt.contracts.graph.compiled import (
-    CompileResultNode,
-    ManifestNode,
-    NonSourceCompiledNode,
-    GraphMemberNode,
-)
-from dbt.contracts.graph.parsed import (
-    ParsedMacro,
-    ParsedDocumentation,
-    ParsedSourceDefinition,
-    ParsedExposure,
-    ParsedMetric,
-    HasUniqueID,
+from dbt.contracts.graph.nodes import (
+    Macro,
+    Documentation,
+    SourceDefinition,
+    GenericTestNode,
+    Exposure,
+    Metric,
+    Entity,
     UnpatchedSourceDefinition,
-    ManifestNodes,
+    ManifestNode,
+    GraphMemberNode,
+    ResultNode,
+    BaseNode,
 )
 from dbt.contracts.graph.unparsed import SourcePatch
 from dbt.contracts.files import SourceFile, SchemaSourceFile, FileHash, AnySourceFile
 from dbt.contracts.util import BaseArtifactMetadata, SourceKey, ArtifactMixin, schema_version
 from dbt.dataclass_schema import dbtClassMixin
 from dbt.exceptions import (
-    CompilationException,
-    raise_duplicate_resource_name,
-    raise_compiler_error,
+    CompilationError,
+    DuplicateResourceNameError,
+    DuplicateMacroInPackageError,
+    DuplicateMaterializationNameError,
 )
 from dbt.helper_types import PathSet
 from dbt.events.functions import fire_event
 from dbt.events.types import MergedFromState
 from dbt.node_types import NodeType
-from dbt.ui import line_wrap_message
 from dbt import flags
 from dbt import tracking
 import dbt.utils
@@ -95,7 +92,7 @@ class DocLookup(dbtClassMixin):
             return self.perform_lookup(unique_id, manifest)
         return None
 
-    def add_doc(self, doc: ParsedDocumentation):
+    def add_doc(self, doc: Documentation):
         if doc.name not in self.storage:
             self.storage[doc.name] = {}
         self.storage[doc.name][doc.package_name] = doc.unique_id
@@ -104,9 +101,9 @@ class DocLookup(dbtClassMixin):
         for doc in manifest.docs.values():
             self.add_doc(doc)
 
-    def perform_lookup(self, unique_id: UniqueID, manifest) -> ParsedDocumentation:
+    def perform_lookup(self, unique_id: UniqueID, manifest) -> Documentation:
         if unique_id not in manifest.docs:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Doc {unique_id} found in cache but not found in manifest"
             )
         return manifest.docs[unique_id]
@@ -126,7 +123,7 @@ class SourceLookup(dbtClassMixin):
             return self.perform_lookup(unique_id, manifest)
         return None
 
-    def add_source(self, source: ParsedSourceDefinition):
+    def add_source(self, source: SourceDefinition):
         if source.search_name not in self.storage:
             self.storage[source.search_name] = {}
 
@@ -137,9 +134,9 @@ class SourceLookup(dbtClassMixin):
             if hasattr(source, "source_name"):
                 self.add_source(source)
 
-    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> ParsedSourceDefinition:
+    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> SourceDefinition:
         if unique_id not in manifest.sources:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Source {unique_id} found in cache but not found in manifest"
             )
         return manifest.sources[unique_id]
@@ -177,7 +174,7 @@ class RefableLookup(dbtClassMixin):
 
     def perform_lookup(self, unique_id: UniqueID, manifest) -> ManifestNode:
         if unique_id not in manifest.nodes:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Node {unique_id} found in cache but not found in manifest"
             )
         return manifest.nodes[unique_id]
@@ -197,7 +194,7 @@ class MetricLookup(dbtClassMixin):
             return self.perform_lookup(unique_id, manifest)
         return None
 
-    def add_metric(self, metric: ParsedMetric):
+    def add_metric(self, metric: Metric):
         if metric.search_name not in self.storage:
             self.storage[metric.search_name] = {}
 
@@ -208,15 +205,48 @@ class MetricLookup(dbtClassMixin):
             if hasattr(metric, "name"):
                 self.add_metric(metric)
 
-    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> ParsedMetric:
+    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> Metric:
         if unique_id not in manifest.metrics:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Metric {unique_id} found in cache but not found in manifest"
             )
         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: Entity):
+        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") -> Entity:
+        if unique_id not in manifest.entities:
+            raise dbt.exceptions.DbtInternalError(
+                f"Entity {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]]] = {}
@@ -324,7 +354,7 @@ def _sort_values(dct):
 
 
 def build_node_edges(nodes: List[ManifestNode]):
-    """Build the forward and backward edges on the given list of ParsedNodes
+    """Build the forward and backward edges on the given list of ManifestNodes
     and return them as two separate dictionaries, each mapping unique IDs to
     lists of edges.
     """
@@ -342,10 +372,10 @@ def build_node_edges(nodes: List[ManifestNode]):
 # Build a map of children of macros and generic tests
 def build_macro_edges(nodes: List[Any]):
     forward_edges: Dict[str, List[str]] = {
-        n.unique_id: [] for n in nodes if n.unique_id.startswith("macro") or n.depends_on.macros
+        n.unique_id: [] for n in nodes if n.unique_id.startswith("macro") or n.depends_on_macros
     }
     for node in nodes:
-        for unique_id in node.depends_on.macros:
+        for unique_id in node.depends_on_macros:
             if unique_id in forward_edges.keys():
                 forward_edges[unique_id].append(node.unique_id)
     return _sort_values(forward_edges)
@@ -364,7 +394,7 @@ class Locality(enum.IntEnum):
 @dataclass
 class MacroCandidate:
     locality: Locality
-    macro: ParsedMacro
+    macro: Macro
 
     def __eq__(self, other: object) -> bool:
         if not isinstance(other, MacroCandidate):
@@ -402,12 +432,7 @@ class MaterializationCandidate(MacroCandidate):
             return NotImplemented
         equal = self.specificity == other.specificity and self.locality == other.locality
         if equal:
-            raise_compiler_error(
-                "Found two materializations with the name {} (packages {} and "
-                "{}). dbt cannot resolve this ambiguity".format(
-                    self.macro.name, self.macro.package_name, other.macro.package_name
-                )
-            )
+            raise DuplicateMaterializationNameError(self.macro, other)
 
         return equal
 
@@ -429,16 +454,14 @@ M = TypeVar("M", bound=MacroCandidate)
 
 
 class CandidateList(List[M]):
-    def last(self) -> Optional[ParsedMacro]:
+    def last(self) -> Optional[Macro]:
         if not self:
             return None
         self.sort()
         return self[-1].macro
 
 
-def _get_locality(
-    macro: ParsedMacro, root_project_name: str, internal_packages: Set[str]
-) -> Locality:
+def _get_locality(macro: Macro, root_project_name: str, internal_packages: Set[str]) -> Locality:
     if macro.package_name == root_project_name:
         return Locality.Root
     elif macro.package_name in internal_packages:
@@ -464,16 +487,19 @@ class Disabled(Generic[D]):
     target: D
 
 
-MaybeMetricNode = Optional[ParsedMetric]
+MaybeMetricNode = Optional[Union[Metric, Disabled[Metric]]]
 
 
-MaybeDocumentation = Optional[ParsedDocumentation]
+MaybeEntityNode = Optional[Union[Entity, Disabled[Entity]]]
+
+
+MaybeDocumentation = Optional[Documentation]
 
 
 MaybeParsedSource = Optional[
     Union[
-        ParsedSourceDefinition,
-        Disabled[ParsedSourceDefinition],
+        SourceDefinition,
+        Disabled[SourceDefinition],
     ]
 ]
 
@@ -491,14 +517,14 @@ def _update_into(dest: MutableMapping[str, T], new_item: T):
     """
     unique_id = new_item.unique_id
     if unique_id not in dest:
-        raise dbt.exceptions.RuntimeException(
+        raise dbt.exceptions.DbtRuntimeError(
             f"got an update_{new_item.resource_type} call with an "
             f"unrecognized {new_item.resource_type}: {new_item.unique_id}"
         )
     existing = dest[unique_id]
     if new_item.original_file_path != existing.original_file_path:
-        raise dbt.exceptions.RuntimeException(
-            f"cannot update a {new_item.resource_type} to have a new file " f"path!"
+        raise dbt.exceptions.DbtRuntimeError(
+            f"cannot update a {new_item.resource_type} to have a new file path!"
         )
     dest[unique_id] = new_item
 
@@ -513,7 +539,7 @@ class MacroMethods:
 
     def find_macro_by_name(
         self, name: str, root_project_name: str, package: Optional[str]
-    ) -> Optional[ParsedMacro]:
+    ) -> Optional[Macro]:
         """Find a macro in the graph by its name and package name, or None for
         any package. The root project name is used to determine priority:
          - locally defined macros come first
@@ -536,7 +562,7 @@ class MacroMethods:
 
     def find_generate_macro_by_name(
         self, component: str, root_project_name: str
-    ) -> Optional[ParsedMacro]:
+    ) -> Optional[Macro]:
         """
         The `generate_X_name` macros are similar to regular ones, but ignore
         imported packages.
@@ -605,18 +631,19 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     # is added it must all be added in the __reduce_ex__ method in the
     # args tuple in the right position.
     nodes: MutableMapping[str, ManifestNode] = field(default_factory=dict)
-    sources: MutableMapping[str, ParsedSourceDefinition] = field(default_factory=dict)
-    macros: MutableMapping[str, ParsedMacro] = field(default_factory=dict)
-    docs: MutableMapping[str, ParsedDocumentation] = field(default_factory=dict)
-    exposures: MutableMapping[str, ParsedExposure] = field(default_factory=dict)
-    metrics: MutableMapping[str, ParsedMetric] = field(default_factory=dict)
+    sources: MutableMapping[str, SourceDefinition] = field(default_factory=dict)
+    macros: MutableMapping[str, Macro] = field(default_factory=dict)
+    docs: MutableMapping[str, Documentation] = field(default_factory=dict)
+    exposures: MutableMapping[str, Exposure] = field(default_factory=dict)
+    metrics: MutableMapping[str, Metric] = field(default_factory=dict)
+    entities: MutableMapping[str, Entity] = 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 +658,9 @@ 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}
     )
@@ -657,7 +687,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         obj._lock = flags.MP_CONTEXT.Lock()
         return obj
 
-    def sync_update_node(self, new_node: NonSourceCompiledNode) -> NonSourceCompiledNode:
+    def sync_update_node(self, new_node: ManifestNode) -> ManifestNode:
         """update the node with a lock. The only time we should want to lock is
         when compiling an ephemeral ancestor of a node at runtime, because
         multiple threads could be just-in-time compiling the same ephemeral
@@ -670,21 +700,24 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         with self._lock:
             existing = self.nodes[new_node.unique_id]
             if getattr(existing, "compiled", False):
-                # already compiled -> must be a NonSourceCompiledNode
-                return cast(NonSourceCompiledNode, existing)
+                # already compiled
+                return existing
             _update_into(self.nodes, new_node)
             return new_node
 
-    def update_exposure(self, new_exposure: ParsedExposure):
+    def update_exposure(self, new_exposure: Exposure):
         _update_into(self.exposures, new_exposure)
 
-    def update_metric(self, new_metric: ParsedMetric):
+    def update_metric(self, new_metric: Metric):
         _update_into(self.metrics, new_metric)
 
+    def update_entity(self, new_entity: Entity):
+        _update_into(self.entities, new_entity)
+
     def update_node(self, new_node: ManifestNode):
         _update_into(self.nodes, new_node)
 
-    def update_source(self, new_source: ParsedSourceDefinition):
+    def update_source(self, new_source: SourceDefinition):
         _update_into(self.sources, new_source)
 
     def build_flat_graph(self):
@@ -696,6 +729,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         self.flat_graph = {
             "exposures": {k: v.to_dict(omit_none=False) for k, v in self.exposures.items()},
             "metrics": {k: v.to_dict(omit_none=False) for k, v in self.metrics.items()},
+            "entities": {k: v.to_dict(omit_none=False) for k, v in self.entities.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()},
         }
@@ -737,7 +771,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
 
     def find_materialization_macro_by_name(
         self, project_name: str, materialization_name: str, adapter_type: str
-    ) -> Optional[ParsedMacro]:
+    ) -> Optional[Macro]:
         candidates: CandidateList = CandidateList(
             chain.from_iterable(
                 self._materialization_candidates_for(
@@ -758,6 +792,7 @@ 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()
@@ -779,19 +814,22 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         return frozenset(x.database for x in chain(self.nodes.values(), self.sources.values()))
 
     def deepcopy(self):
-        return Manifest(
+        copy = Manifest(
             nodes={k: _deepcopy(v) for k, v in self.nodes.items()},
             sources={k: _deepcopy(v) for k, v in self.sources.items()},
             macros={k: _deepcopy(v) for k, v in self.macros.items()},
             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()},
             files={k: _deepcopy(v) for k, v in self.files.items()},
             state_check=_deepcopy(self.state_check),
         )
+        copy.build_flat_graph()
+        return copy
 
     def build_parent_and_child_maps(self):
         edge_members = list(
@@ -800,6 +838,7 @@ 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 +864,7 @@ 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,
@@ -846,9 +886,11 @@ 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(
+            raise dbt.exceptions.DbtInternalError(
                 "Expected node {} not found in manifest".format(unique_id)
             )
 
@@ -882,6 +924,12 @@ 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)
 
@@ -940,8 +988,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         search_name = f"{target_source_name}.{target_table_name}"
         candidates = _search_packages(current_project, node_package)
 
-        source: Optional[ParsedSourceDefinition] = None
-        disabled: Optional[List[ParsedSourceDefinition]] = None
+        source: Optional[SourceDefinition] = None
+        disabled: Optional[List[SourceDefinition]] = None
 
         for pkg in candidates:
             source = self.source_lookup.find(search_name, pkg, self)
@@ -964,13 +1012,47 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         current_project: str,
         node_package: str,
     ) -> MaybeMetricNode:
-        metric: Optional[ParsedMetric] = None
+
+        metric: Optional[Metric] = None
+        disabled: Optional[List[Metric]] = 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[Entity] = None
+        disabled: Optional[List[Entity]] = 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
@@ -980,7 +1062,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         package: Optional[str],
         current_project: str,
         node_package: str,
-    ) -> Optional[ParsedDocumentation]:
+    ) -> Optional[Documentation]:
         """Resolve the given documentation. This follows the same algorithm as
         resolve_ref except the is_enabled checks are unnecessary as docs are
         always enabled.
@@ -999,6 +1081,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         adapter,
         other: "WritableManifest",
         selected: AbstractSet[UniqueID],
+        favor_state: bool = False,
     ) -> None:
         """Given the selected unique IDs and a writable manifest, update this
         manifest by replacing any unselected nodes with their counterpart.
@@ -1013,40 +1096,28 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
                 node.resource_type in refables
                 and not node.is_ephemeral
                 and unique_id not in selected
-                and not adapter.get_relation(current.database, current.schema, current.identifier)
+                and (
+                    not adapter.get_relation(current.database, current.schema, current.identifier)
+                    or favor_state
+                )
             ):
                 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))
+        fire_event(MergedFromState(num_merged=len(merged), sample=sample))
 
     # Methods that were formerly in ParseResult
 
-    def add_macro(self, source_file: SourceFile, macro: ParsedMacro):
+    def add_macro(self, source_file: SourceFile, macro: Macro):
         if macro.unique_id in self.macros:
             # detect that the macro exists and emit an error
-            other_path = self.macros[macro.unique_id].original_file_path
-            # subtract 2 for the "Compilation Error" indent
-            # note that the line wrap eats newlines, so if you want newlines,
-            # this is the result :(
-            msg = line_wrap_message(
-                f"""\
-                dbt found two macros named "{macro.name}" in the project
-                "{macro.package_name}".
-
-
-                To fix this error, rename or remove one of the following
-                macros:
-
-                    - {macro.original_file_path}
-
-                    - {other_path}
-                """,
-                subtract=2,
-            )
-            raise_compiler_error(msg)
+            raise DuplicateMacroInPackageError(macro=macro, macro_mapping=self.macros)
 
         self.macros[macro.unique_id] = macro
         source_file.macros.append(macro.unique_id)
@@ -1066,45 +1137,62 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         self.sources[source.unique_id] = source  # type: ignore
         source_file.sources.append(source.unique_id)
 
-    def add_node_nofile(self, node: ManifestNodes):
+    def add_node_nofile(self, node: ManifestNode):
         # nodes can't be overwritten!
         _check_duplicates(node, self.nodes)
         self.nodes[node.unique_id] = node
 
-    def add_node(self, source_file: AnySourceFile, node: ManifestNodes, test_from=None):
+    def add_node(self, source_file: AnySourceFile, node: ManifestNode, 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, GenericTestNode):
+                assert test_from
+                source_file.add_test(node.unique_id, test_from)
+            if isinstance(node, Metric):
+                source_file.metrics.append(node.unique_id)
+            if isinstance(node, Exposure):
+                source_file.exposures.append(node.unique_id)
         else:
             source_file.nodes.append(node.unique_id)
 
-    def add_exposure(self, source_file: SchemaSourceFile, exposure: ParsedExposure):
+    def add_exposure(self, source_file: SchemaSourceFile, exposure: Exposure):
         _check_duplicates(exposure, self.exposures)
         self.exposures[exposure.unique_id] = exposure
         source_file.exposures.append(exposure.unique_id)
 
-    def add_metric(self, source_file: SchemaSourceFile, metric: ParsedMetric):
+    def add_metric(self, source_file: SchemaSourceFile, metric: Metric):
         _check_duplicates(metric, self.metrics)
         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: Entity):
+        _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)
         else:
             self.disabled[node.unique_id] = [node]
 
-    def add_disabled(self, source_file: AnySourceFile, node: CompileResultNode, test_from=None):
+    def add_disabled(self, source_file: AnySourceFile, node: ResultNode, 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, GenericTestNode):
+                assert test_from
+                source_file.add_test(node.unique_id, test_from)
+            if isinstance(node, Metric):
+                source_file.metrics.append(node.unique_id)
+            if isinstance(node, Entity):
+                source_file.entities.append(node.unique_id)
+            if isinstance(node, Exposure):
+                source_file.exposures.append(node.unique_id)
         else:
             source_file.nodes.append(node.unique_id)
 
-    def add_doc(self, source_file: SourceFile, doc: ParsedDocumentation):
+    def add_doc(self, source_file: SourceFile, doc: Documentation):
         _check_duplicates(doc, self.docs)
         self.docs[doc.unique_id] = doc
         source_file.docs.append(doc.unique_id)
@@ -1126,6 +1214,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self.docs,
             self.exposures,
             self.metrics,
+            self.entities,
             self.selectors,
             self.files,
             self.metadata,
@@ -1138,6 +1227,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self._source_lookup,
             self._ref_lookup,
             self._metric_lookup,
+            self._entity_lookup,
             self._disabled_lookup,
             self._analysis_lookup,
         )
@@ -1157,32 +1247,35 @@ AnyManifest = Union[Manifest, MacroManifest]
 
 
 @dataclass
-@schema_version("manifest", 6)
+@schema_version("manifest", 8)
 class WritableManifest(ArtifactMixin):
     nodes: Mapping[UniqueID, ManifestNode] = field(
         metadata=dict(description=("The nodes defined in the dbt project and its dependencies"))
     )
-    sources: Mapping[UniqueID, ParsedSourceDefinition] = field(
+    sources: Mapping[UniqueID, SourceDefinition] = field(
         metadata=dict(description=("The sources defined in the dbt project and its dependencies"))
     )
-    macros: Mapping[UniqueID, ParsedMacro] = field(
+    macros: Mapping[UniqueID, Macro] = field(
         metadata=dict(description=("The macros defined in the dbt project and its dependencies"))
     )
-    docs: Mapping[UniqueID, ParsedDocumentation] = field(
+    docs: Mapping[UniqueID, Documentation] = field(
         metadata=dict(description=("The docs defined in the dbt project and its dependencies"))
     )
-    exposures: Mapping[UniqueID, ParsedExposure] = field(
+    exposures: Mapping[UniqueID, Exposure] = field(
         metadata=dict(
             description=("The exposures defined in the dbt project and its dependencies")
         )
     )
-    metrics: Mapping[UniqueID, ParsedMetric] = field(
+    metrics: Mapping[UniqueID, Metric] = field(
         metadata=dict(description=("The metrics defined in the dbt project and its dependencies"))
     )
+    entities: Mapping[UniqueID, Entity] = 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"))
     )
-    disabled: Optional[Mapping[UniqueID, List[CompileResultNode]]] = field(
+    disabled: Optional[Mapping[UniqueID, List[ResultNode]]] = field(
         metadata=dict(description="A mapping of the disabled nodes in the target")
     )
     parent_map: Optional[NodeEdgeMap] = field(
@@ -1203,7 +1296,8 @@ class WritableManifest(ArtifactMixin):
 
     @classmethod
     def compatible_previous_versions(self):
-        return [("manifest", 4), ("manifest", 5)]
+        # return [("manifest", 4), ("manifest", 5), ("manifest", 6), ("manifest", 7)]
+        return []
 
     def __post_serialize__(self, dct):
         for unique_id, node in dct["nodes"].items():
@@ -1212,9 +1306,9 @@ class WritableManifest(ArtifactMixin):
         return dct
 
 
-def _check_duplicates(value: HasUniqueID, src: Mapping[str, HasUniqueID]):
+def _check_duplicates(value: BaseNode, src: Mapping[str, BaseNode]):
     if value.unique_id in src:
-        raise_duplicate_resource_name(value, src[value.unique_id])
+        raise DuplicateResourceNameError(value, src[value.unique_id])
 
 
 K_T = TypeVar("K_T")
@@ -1223,7 +1317,7 @@ V_T = TypeVar("V_T")
 
 def _expect_value(key: K_T, src: Mapping[K_T, V_T], old_file: SourceFile, name: str) -> V_T:
     if key not in src:
-        raise CompilationException(
+        raise CompilationError(
             'Expected to find "{}" in cached "result.{}" based '
             "on cached file information: {}!".format(key, name, old_file)
         )

core/dbt/contracts/graph/metrics.py

@@ -12,7 +12,7 @@ class MetricReference(object):
 
 class ResolvedMetricReference(MetricReference):
     """
-    Simple proxy over a ParsedMetric which delegates property
+    Simple proxy over a Metric which delegates property
     lookups to the underlying node. Also adds helper functions
     for working with metrics (ie. __str__ and templating functions)
     """
@@ -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

@@ -7,8 +7,9 @@ from dbt.dataclass_schema import (
     ValidationError,
     register_pattern,
 )
-from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed
-from dbt.exceptions import InternalException, CompilationException
+from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed, Docs
+from dbt.contracts.graph.utils import validate_color
+from dbt.exceptions import DbtInternalError, CompilationError
 from dbt.contracts.util import Replaceable, list_str
 from dbt import hooks
 from dbt.node_types import NodeType
@@ -29,7 +30,7 @@ def _get_meta_value(cls: Type[M], fld: Field, key: str, default: Any) -> M:
     try:
         return cls(value)
     except ValueError as exc:
-        raise InternalException(f"Invalid {cls} value: {value}") from exc
+        raise DbtInternalError(f"Invalid {cls} value: {value}") from exc
 
 
 def _set_meta_value(obj: M, key: str, existing: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
@@ -139,17 +140,17 @@ def _merge_field_value(
         return _listify(self_value) + _listify(other_value)
     elif merge_behavior == MergeBehavior.Update:
         if not isinstance(self_value, dict):
-            raise InternalException(f"expected dict, got {self_value}")
+            raise DbtInternalError(f"expected dict, got {self_value}")
         if not isinstance(other_value, dict):
-            raise InternalException(f"expected dict, got {other_value}")
+            raise DbtInternalError(f"expected dict, got {other_value}")
         value = self_value.copy()
         value.update(other_value)
         return value
     elif merge_behavior == MergeBehavior.DictKeyAppend:
         if not isinstance(self_value, dict):
-            raise InternalException(f"expected dict, got {self_value}")
+            raise DbtInternalError(f"expected dict, got {self_value}")
         if not isinstance(other_value, dict):
-            raise InternalException(f"expected dict, got {other_value}")
+            raise DbtInternalError(f"expected dict, got {other_value}")
         new_dict = {}
         for key in self_value.keys():
             new_dict[key] = _listify(self_value[key])
@@ -171,7 +172,7 @@ def _merge_field_value(
         return new_dict
 
     else:
-        raise InternalException(f"Got an invalid merge_behavior: {merge_behavior}")
+        raise DbtInternalError(f"Got an invalid merge_behavior: {merge_behavior}")
 
 
 def insensitive_patterns(*patterns: str):
@@ -226,7 +227,7 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable):
             msg = (
                 'Error, tried to delete config key "{}": Cannot delete ' "built-in keys"
             ).format(key)
-            raise CompilationException(msg)
+            raise CompilationError(msg)
         else:
             del self._extra[key]
 
@@ -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"],
     }
 
@@ -362,43 +363,24 @@ 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
-    # to be implmented to complete CT-201
-    # quoting: Dict[str, Any] = field(
-    #     default_factory=dict,
-    #     metadata=MergeBehavior.Update.meta(),
-    # )
-    # freshness: Optional[Dict[str, Any]] = field(
-    #     default=None,
-    #     metadata=CompareBehavior.Exclude.meta(),
-    # )
-    # loader: Optional[str] = field(
-    #     default=None,
-    #     metadata=CompareBehavior.Exclude.meta(),
-    # )
-    # # TODO what type is this? docs say: "<column_name_or_expression>"
-    # loaded_at_field: Optional[str] = field(
-    #     default=None,
-    #     metadata=CompareBehavior.Exclude.meta(),
-    # )
-    # database: Optional[str] = field(
-    #     default=None,
-    #     metadata=CompareBehavior.Exclude.meta(),
-    # )
-    # schema: Optional[str] = field(
-    #     default=None,
-    #     metadata=CompareBehavior.Exclude.meta(),
-    # )
-    # meta: Dict[str, Any] = field(
-    #     default_factory=dict,
-    #     metadata=MergeBehavior.Update.meta(),
-    # )
-    # tags: Union[List[str], str] = field(
-    #     default_factory=list_str,
-    #     metadata=metas(ShowBehavior.Hide, MergeBehavior.Append, CompareBehavior.Exclude),
-    # )
 
 
 @dataclass
@@ -433,6 +415,7 @@ 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 +443,24 @@ 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):
@@ -499,6 +500,12 @@ class SeedConfig(NodeConfig):
     materialized: str = "seed"
     quote_columns: Optional[bool] = None
 
+    @classmethod
+    def validate(cls, data):
+        super().validate(data)
+        if data.get("materialized") and data.get("materialized") != "seed":
+            raise ValidationError("A seed must have a materialized value of 'seed'")
+
 
 @dataclass
 class TestConfig(NodeAndTestConfig):
@@ -538,6 +545,12 @@ class TestConfig(NodeAndTestConfig):
                     return False
         return True
 
+    @classmethod
+    def validate(cls, data):
+        super().validate(data)
+        if data.get("materialized") and data.get("materialized") != "test":
+            raise ValidationError("A test must have a materialized value of 'test'")
+
 
 @dataclass
 class EmptySnapshotConfig(NodeConfig):
@@ -574,7 +587,6 @@ class SnapshotConfig(EmptySnapshotConfig):
                     f"Invalid value for 'check_cols': {data['check_cols']}. "
                     "Expected 'all' or a list of strings."
                 )
-
         elif data.get("strategy") == "timestamp":
             if not data.get("updated_at"):
                 raise ValidationError(
@@ -586,6 +598,9 @@ class SnapshotConfig(EmptySnapshotConfig):
         # If the strategy is not 'check' or 'timestamp' it's a custom strategy,
         # formerly supported with GenericSnapshotConfig
 
+        if data.get("materialized") and data.get("materialized") != "snapshot":
+            raise ValidationError("A snapshot must have a materialized value of 'snapshot'")
+
     def finalize_and_validate(self):
         data = self.to_dict(omit_none=True)
         self.validate(data)
@@ -593,6 +608,9 @@ 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/unparsed.py

@@ -1,9 +1,17 @@
+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
-from dbt.exceptions import CompilationException, ParsingException
+from dbt.exceptions import CompilationError, ParsingError
 
 from dbt.dataclass_schema import dbtClassMixin, StrEnum, ExtensibleDbtClassMixin, ValidationError
 
@@ -16,7 +24,6 @@ from typing import Optional, List, Union, Dict, Any, Sequence
 @dataclass
 class UnparsedBaseNode(dbtClassMixin, Replaceable):
     package_name: str
-    root_path: str
     path: str
     original_file_path: str
 
@@ -26,26 +33,27 @@ 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 UnparsedNode(UnparsedBaseNode, HasCode):
     name: str
     resource_type: NodeType = field(
         metadata={
@@ -76,6 +84,7 @@ class UnparsedRunHook(UnparsedNode):
 @dataclass
 class Docs(dbtClassMixin, Replaceable):
     show: bool = True
+    node_color: Optional[str] = None
 
 
 @dataclass
@@ -213,7 +222,7 @@ class ExternalPartition(AdditionalPropertiesAllowed, Replaceable):
 
     def __post_init__(self):
         if self.name == "" or self.data_type == "":
-            raise CompilationException("External partition columns must have names and data types")
+            raise CompilationError("External partition columns must have names and data types")
 
 
 @dataclass
@@ -222,7 +231,7 @@ class ExternalTable(AdditionalPropertiesAllowed, Mergeable):
     file_format: Optional[str] = None
     row_format: Optional[str] = None
     tbl_properties: Optional[str] = None
-    partitions: Optional[List[ExternalPartition]] = None
+    partitions: Optional[Union[List[str], List[ExternalPartition]]] = None
 
     def __bool__(self):
         return self.location is not None
@@ -354,7 +363,6 @@ class SourcePatch(dbtClassMixin, Replaceable):
 @dataclass
 class UnparsedDocumentation(dbtClassMixin, Replaceable):
     package_name: str
-    root_path: str
     path: str
     original_file_path: str
 
@@ -427,11 +435,21 @@ 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 +460,94 @@ 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
+    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 ParsingError(
+                    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("timestamp") is None and data.get("time_grains") is not None:
+            raise ValidationError(
+                f"The metric '{data['name']} has time_grains defined but is missing a timestamp dimension."
+            )
+
+        if data.get("timestamp") is None and data.get("window") is not None:
+            raise ValidationError(
+                f"The metric '{data['name']} has a window defined but is missing a timestamp dimension."
+            )
+
+        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")
+
+
+@dataclass
+class UnparsedEntity(dbtClassMixin, Replaceable):
+    """This class is used for entity information"""
+
+    name: str
+    model: str
+    description: str = ""
+    dimensions: List[str] = 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(UnparsedEntity, cls).validate(data)
+        # TODO: Add validation here around include/exclude and others

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

@@ -12,9 +12,7 @@ from dataclasses import dataclass, field
 from typing import Optional, List, Dict, Union, Any
 from mashumaro.types import SerializableType
 
-PIN_PACKAGE_URL = (
-    "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"  # noqa
-)
+
 DEFAULT_SEND_ANONYMOUS_USAGE_STATS = True
 
 
@@ -57,6 +55,12 @@ class LocalPackage(Package):
 RawVersion = Union[str, float]
 
 
+@dataclass
+class TarballPackage(Package):
+    tarball: str
+    name: str
+
+
 @dataclass
 class GitPackage(Package):
     git: str
@@ -84,13 +88,30 @@ class RegistryPackage(Package):
             return [str(self.version)]
 
 
-PackageSpec = Union[LocalPackage, GitPackage, RegistryPackage]
+PackageSpec = Union[LocalPackage, TarballPackage, GitPackage, RegistryPackage]
 
 
 @dataclass
 class PackageConfig(dbtClassMixin, Replaceable):
     packages: List[PackageSpec]
 
+    @classmethod
+    def validate(cls, data):
+        for package in data.get("packages", data):
+            if isinstance(package, dict) and package.get("package"):
+                if not package["version"]:
+                    raise ValidationError(
+                        f"{package['package']} is missing the version. When installing from the Hub "
+                        "package index, version is a required property"
+                    )
+
+                if "/" not in package["package"]:
+                    raise ValidationError(
+                        f"{package['package']} was not found in the package index. Packages on the index "
+                        "require a namespace, e.g dbt-labs/dbt_utils"
+                    )
+        super().validate(data)
+
 
 @dataclass
 class ProjectPackageMetadata:
@@ -192,6 +213,9 @@ 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)
+    entities: 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(
@@ -199,7 +223,7 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
         ),
     )
     packages: List[PackageSpec] = field(default_factory=list)
-    query_comment: Optional[Union[QueryComment, NoValue, str]] = NoValue()
+    query_comment: Optional[Union[QueryComment, NoValue, str]] = field(default_factory=NoValue)
 
     @classmethod
     def validate(cls, data):
@@ -226,6 +250,7 @@ class UserConfig(ExtensibleDbtClassMixin, Replaceable, UserConfigContract):
     printer_width: Optional[int] = None
     write_json: Optional[bool] = None
     warn_error: Optional[bool] = None
+    warn_error_options: Optional[Dict[str, Union[str, List[str]]]] = None
     log_format: Optional[str] = None
     debug: Optional[bool] = None
     version_check: Optional[bool] = None

core/dbt/contracts/relation.py

@@ -9,7 +9,7 @@ from typing_extensions import Protocol
 from dbt.dataclass_schema import dbtClassMixin, StrEnum
 
 from dbt.contracts.util import Replaceable
-from dbt.exceptions import raise_dataclass_not_dict, CompilationException
+from dbt.exceptions import CompilationError, DataclassNotDictError
 from dbt.utils import deep_merge
 
 
@@ -43,10 +43,10 @@ class FakeAPIObject(dbtClassMixin, Replaceable, Mapping):
             raise KeyError(key) from None
 
     def __iter__(self):
-        raise_dataclass_not_dict(self)
+        raise DataclassNotDictError(self)
 
     def __len__(self):
-        raise_dataclass_not_dict(self)
+        raise DataclassNotDictError(self)
 
     def incorporate(self, **kwargs):
         value = self.to_dict(omit_none=True)
@@ -88,13 +88,11 @@ class Path(FakeAPIObject):
     def __post_init__(self):
         # handle pesky jinja2.Undefined sneaking in here and messing up rende
         if not isinstance(self.database, (type(None), str)):
-            raise CompilationException("Got an invalid path database: {}".format(self.database))
+            raise CompilationError("Got an invalid path database: {}".format(self.database))
         if not isinstance(self.schema, (type(None), str)):
-            raise CompilationException("Got an invalid path schema: {}".format(self.schema))
+            raise CompilationError("Got an invalid path schema: {}".format(self.schema))
         if not isinstance(self.identifier, (type(None), str)):
-            raise CompilationException(
-                "Got an invalid path identifier: {}".format(self.identifier)
-            )
+            raise CompilationError("Got an invalid path identifier: {}".format(self.identifier))
 
     def get_lowered_part(self, key: ComponentName) -> Optional[str]:
         part = self.get_part(key)