move source functional tests to adapters

resolves https://github.com/dbt-labs/dbt-core/issues/2964

.bumpversion.cfg

@@ -1,12 +1,12 @@
 [bumpversion]
-current_version = 1.0.0b2
+current_version = 1.5.0a1
 parse = (?P<major>\d+)
 	\.(?P<minor>\d+)
 	\.(?P<patch>\d+)
 	((?P<prekind>a|b|rc)
 	(?P<pre>\d+)  # pre-release version num
 	)?
-serialize = 
+serialize =
 	{major}.{minor}.{patch}{prekind}{pre}
 	{major}.{minor}.{patch}
 commit = False
@@ -15,7 +15,7 @@ tag = False
 [bumpversion:part:prekind]
 first_value = a
 optional_value = final
-values = 
+values =
 	a
 	b
 	rc
@@ -24,14 +24,16 @@ values =
 [bumpversion:part:pre]
 first_value = 1
 
-[bumpversion:file:setup.py]
-
 [bumpversion:file:core/setup.py]
 
 [bumpversion:file:core/dbt/version.py]
 
-[bumpversion:file:core/scripts/create_adapter_plugins.py]
-
 [bumpversion:file:plugins/postgres/setup.py]
 
 [bumpversion:file:plugins/postgres/dbt/adapters/postgres/__version__.py]
+
+[bumpversion:file:docker/Dockerfile]
+
+[bumpversion:file:tests/adapter/setup.py]
+
+[bumpversion:file:tests/adapter/dbt/tests/adapter/__version__.py]

.changes/0.0.0.md

@@ -0,0 +1,21 @@
+## 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)
+* [0.21](https://github.com/dbt-labs/dbt-core/blob/0.21.latest/CHANGELOG.md)
+* [0.20](https://github.com/dbt-labs/dbt-core/blob/0.20.latest/CHANGELOG.md)
+* [0.19](https://github.com/dbt-labs/dbt-core/blob/0.19.latest/CHANGELOG.md)
+* [0.18](https://github.com/dbt-labs/dbt-core/blob/0.18.latest/CHANGELOG.md)
+* [0.17](https://github.com/dbt-labs/dbt-core/blob/0.17.latest/CHANGELOG.md)
+* [0.16](https://github.com/dbt-labs/dbt-core/blob/0.16.latest/CHANGELOG.md)
+* [0.15](https://github.com/dbt-labs/dbt-core/blob/0.15.latest/CHANGELOG.md)
+* [0.14](https://github.com/dbt-labs/dbt-core/blob/0.14.latest/CHANGELOG.md)
+* [0.13](https://github.com/dbt-labs/dbt-core/blob/0.13.latest/CHANGELOG.md)
+* [0.12](https://github.com/dbt-labs/dbt-core/blob/0.12.latest/CHANGELOG.md)
+* [0.11 and earlier](https://github.com/dbt-labs/dbt-core/blob/0.11.latest/CHANGELOG.md)

.changes/README.md

@@ -0,0 +1,53 @@
+# CHANGELOG Automation
+
+We use [changie](https://changie.dev/) to automate `CHANGELOG` generation.  For installation and format/command specifics, see the documentation.
+
+### Quick Tour
+
+- All new change entries get generated under `/.changes/unreleased` as a yaml file
+- `header.tpl.md` contains the contents of the entire CHANGELOG file
+- `0.0.0.md` contains the contents of the footer for the entire CHANGELOG file.  changie looks to be in the process of supporting a footer file the same as it supports a header file.  Switch to that when available.  For now, the 0.0.0 in the file name forces it to the bottom of the changelog no matter what version we are releasing.
+- `.changie.yaml` contains the fields in a change, the format of a single change, as well as the format of the Contributors section for each version.
+
+### Workflow
+
+#### Daily workflow
+Almost every code change we make associated with an issue will require a `CHANGELOG` entry.  After you have created the PR in GitHub, run `changie new` and follow the command prompts to generate a yaml file with your change details.  This only needs to be done once per PR.
+
+The `changie new` command will ensure correct file format and file name.  There is a one to one mapping of issues to changes.  Multiple issues cannot be lumped into a single entry. If you make a mistake, the yaml file may be directly modified and saved as long as the format is preserved.
+
+Note: If your PR has been cleared by the Core Team as not needing a changelog entry, the `Skip Changelog` label may be put on the PR to bypass the GitHub action that blacks PRs from being merged when they are missing a `CHANGELOG` entry.
+
+#### Prerelease Workflow
+These commands batch up changes in `/.changes/unreleased` to be included in this prerelease and move those files to a directory named for the release version.  The `--move-dir` will be created if it does not exist and is created in `/.changes`.
+
+```
+changie batch <version>  --move-dir '<version>' --prerelease 'rc1'
+changie merge
+```
+
+Example
+```
+changie batch 1.0.5  --move-dir '1.0.5' --prerelease 'rc1'
+changie merge
+```
+
+#### Final Release Workflow
+These commands batch up changes in `/.changes/unreleased` as well as `/.changes/<version>` to be included in this final release and delete all prereleases.  This rolls all prereleases up into a single final release.  All `yaml` files in `/unreleased` and `<version>` will be deleted at this point.
+
+```
+changie batch <version>  --include '<version>' --remove-prereleases
+changie merge
+```
+
+Example
+```
+changie batch 1.0.5  --include '1.0.5' --remove-prereleases
+changie merge
+```
+
+### A Note on Manual Edits & Gotchas
+- Changie generates markdown files in the `.changes` directory that are parsed together with the `changie merge` command.  Every time `changie merge` is run, it regenerates the entire file.  For this reason, any changes made directly to `CHANGELOG.md` will be overwritten on the next run of `changie merge`.
+- If changes need to be made to the `CHANGELOG.md`, make the changes to the relevant `<version>.md` file located in the `/.changes` directory.  You will then run `changie merge` to regenerate the `CHANGELOG.MD`.
+- Do not run `changie batch` again on released versions.  Our final release workflow deletes all of the yaml files associated with individual changes.  If for some reason modifications to the `CHANGELOG.md` are required after we've generated the final release `CHANGELOG.md`, the modifications need to be done manually to the `<version>.md` file in the `/.changes` directory.
+- changie can modify, create and delete files depending on the command you run.  This is expected.  Be sure to commit everything that has been modified and deleted.

.changes/header.tpl.md

@@ -0,0 +1,6 @@
+# dbt Core Changelog
+
+- This file provides a full account of all changes to `dbt-core` and `dbt-postgres`
+- Changes are listed under the (pre)release in which they first appear. Subsequent releases include changes from previous releases.
+- "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)

.changes/unreleased/Features-20230107-003157.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Have dbt debug spit out structured json logs with flags enabled.
+time: 2023-01-07T00:31:57.516063-08:00
+custom:
+  Author: versusfacit
+  Issue: "5353"

.changes/unreleased/Features-20230118-233801.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: add adapter_response to dbt test and freshness result
+time: 2023-01-18T23:38:01.857342+08:00
+custom:
+  Author: aezomz
+  Issue: "2964"

.changes/unreleased/Features-20230120-112921.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Improve error message for packages missing `dbt_project.yml`
+time: 2023-01-20T11:29:21.509967-07:00
+custom:
+  Author: dbeatty10
+  Issue: "6663"

.changes/unreleased/Fixes-20230116-123645.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Respect quoting config for dbt.ref(), dbt.source(), and dbt.this() in dbt-py models
+time: 2023-01-16T12:36:45.63092+01:00
+custom:
+  Author: jtcohen6
+  Issue: 6103 6619

.changes/unreleased/Fixes-20230117-101342.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Provide backward compatibility for `get_merge_sql` arguments
+time: 2023-01-17T10:13:42.118336-06:00
+custom:
+  Author: dave-connors-3
+  Issue: "6625"

.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-20230113-150700.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Port docs tests to pytest
+time: 2023-01-13T15:07:00.477038-05:00
+custom:
+  Author: peterallenwebb
+  Issue: "6573"

.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"

.changes/unreleased/Under the Hood-20230120-172254.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Replaced the EmptyLine event with a more general Formatting event, and added
+  a Note event.
+time: 2023-01-20T17:22:54.45828-05:00
+custom:
+  Author: peterallenwebb
+  Issue: "6481"

.changes/unreleased/Under the Hood-20230122-215235.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Small optimization on manifest parsing benefitting large DAGs
+time: 2023-01-22T21:52:35.549814+01:00
+custom:
+  Author: boxysean
+  Issue: "6697"

.changie.yaml

@@ -0,0 +1,127 @@
+changesDir: .changes
+unreleasedDir: unreleased
+headerPath: header.tpl.md
+versionHeaderPath: ""
+changelogPath: CHANGELOG.md
+versionExt: md
+versionFormat: '## dbt-core {{.Version}} - {{.Time.Format "January 02, 2006"}}'
+kindFormat: '### {{.Kind}}'
+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
+    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 (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 "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 single changelog */}}
+    {{- range $author := $authorList }}
+      {{- $authorLower := lower $author }}
+      {{- /* we only want to include non-core team contributors */}}
+      {{- if not (has $authorLower $core_team)}}
+        {{- $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}}{{end}})
+  {{- end }}
+  {{- end }}

.flake8

@@ -0,0 +1,12 @@
+[flake8]
+select =
+    E
+    W
+    F
+ignore =
+    W503 # makes Flake8 work like black
+    W504
+    E203 # makes Flake8 work like black
+    E741
+    E501 # long line checking is done in black
+exclude = test/

.git-blame-ignore-revs

@@ -0,0 +1,2 @@
+# Reformatting dbt-core via black, flake8, mypy, and assorted pre-commit hooks.
+43e3fc22c4eae4d3d901faba05e33c40f1f1dc5a

.gitattributes

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

.github/CODEOWNERS

@@ -0,0 +1,75 @@
+# This file contains the code owners for the dbt-core repo.
+# PRs will be automatically assigned for review to the associated
+# team(s) or person(s) that touches any files that are mapped to them.
+#
+# A statement takes precedence over the statements above it so more general
+# assignments are found at the top with specific assignments being lower in
+# the ordering (i.e. catch all assignment should be the first item)
+#
+# Consult GitHub documentation for formatting guidelines:
+# https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners#example-of-a-codeowners-file
+
+# As a default for areas with no assignment,
+# the core team as a whole will be assigned
+*       @dbt-labs/core
+
+# 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/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/graph/                @dbt-labs/core-execution
+/core/dbt/task/                 @dbt-labs/core-execution
+
+# 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
+
+
+### 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
+# framework changes (excluded by not setting an owner next to it- no owner)
+/performance @nathaniel-may
+/performance/projects

.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

@@ -1,22 +1,32 @@
 name: ✨ Feature
-description: Suggest an idea for dbt
+description: Propose a straightforward extension of dbt functionality
 title: "[Feature] <title>"
 labels: ["enhancement", "triage"]
 body:
   - type: markdown
     attributes:
       value: |
-        Thanks for taking the time to fill out this feature requests!
+        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.
+      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 searched the existing issues
+        - 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/Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3-slim AS builder
+ADD . /app
+WORKDIR /app
+
+# We are installing a dependency here directly into our app source dir
+RUN pip install --target=/app requests packaging
+
+# A distroless container image with Python and some basics like SSL certificates
+# https://github.com/GoogleContainerTools/distroless
+FROM gcr.io/distroless/python3-debian10
+COPY --from=builder /app /app
+WORKDIR /app
+ENV PYTHONPATH /app
+CMD ["/app/main.py"]

.github/actions/latest-wrangler/README.md

@@ -0,0 +1,50 @@
+# Github package 'latest' tag wrangler for containers
+## Usage
+
+Plug in the necessary inputs to determine if the container being built should be tagged 'latest; at the package level, for example `dbt-redshift:latest`.
+
+## Inputs
+| Input | Description |
+| - | - |
+| `package` | Name of the GH package to check against |
+| `new_version` | Semver of new container |
+| `gh_token` | GH token with package read scope|
+| `halt_on_missing` | Return non-zero exit code if requested package does not exist. (defaults to false)|
+
+
+## Outputs
+| Output | Description |
+| - | - |
+| `latest` | Wether or not the new container should be tagged 'latest'|
+| `minor_latest` | Wether or not the new container should be tagged major.minor.latest |
+
+## Example workflow
+```yaml
+name: Ship it!
+on:
+  workflow_dispatch:
+    inputs:
+      package:
+       description: The package to publish
+       required: true
+      version_number:
+       description: The version number
+       required: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v1
+    - name: Wrangle latest tag
+      id: is_latest
+      uses: ./.github/actions/latest-wrangler
+      with:
+        package: ${{ github.event.inputs.package }}
+        new_version: ${{ github.event.inputs.new_version }}
+        gh_token: ${{ secrets.GITHUB_TOKEN }}
+    - name: Print the results
+      run: |
+        echo "Is it latest?  Survey says: ${{ steps.is_latest.outputs.latest }} !"
+        echo "Is it minor.latest?  Survey says: ${{ steps.is_latest.outputs.minor_latest }} !"
+```

.github/actions/latest-wrangler/action.yml

@@ -0,0 +1,20 @@
+name: "Github package 'latest' tag wrangler for containers"
+description: "Determines wether or not a given dbt container should be given a bare 'latest' tag (I.E. dbt-core:latest)"
+inputs:
+  package_name:
+    description: "Package to check (I.E. dbt-core, dbt-redshift, etc)"
+    required: true
+  new_version:
+    description: "Semver of the container being built (I.E. 1.0.4)"
+    required: true
+  gh_token:
+    description: "Auth token for github (must have view packages scope)"
+    required: true
+outputs:
+  latest:
+    description: "Wether or not built container should be tagged latest (bool)"
+  minor_latest:
+    description: "Wether or not built container should be tagged minor.latest (bool)"
+runs:
+  using: "docker"
+  image: "Dockerfile"

.github/actions/latest-wrangler/examples/example_workflow.yml

@@ -0,0 +1,26 @@
+name: Ship it!
+on:
+  workflow_dispatch:
+    inputs:
+      package:
+       description: The package to publish
+       required: true
+      version_number:
+       description: The version number
+       required: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v1
+    - name: Wrangle latest tag
+      id: is_latest
+      uses: ./.github/actions/latest-wrangler
+      with:
+        package: ${{ github.event.inputs.package }}
+        new_version: ${{ github.event.inputs.new_version }}
+        gh_token: ${{ secrets.GITHUB_TOKEN }}
+    - name: Print the results
+      run: |
+        echo "Is it latest?  Survey says: ${{ steps.is_latest.outputs.latest }} !"

.github/actions/latest-wrangler/examples/example_workflow_dispatch.json

@@ -0,0 +1,6 @@
+{
+    "inputs": {
+      "version_number": "1.0.1",
+      "package": "dbt-redshift"
+    }
+}

.github/actions/latest-wrangler/main.py

@@ -0,0 +1,98 @@
+import os
+import sys
+import requests
+from distutils.util import strtobool
+from typing import Union
+from packaging.version import parse, Version
+
+if __name__ == "__main__":
+
+    # get inputs
+    package = os.environ["INPUT_PACKAGE"]
+    new_version = parse(os.environ["INPUT_NEW_VERSION"])
+    gh_token = os.environ["INPUT_GH_TOKEN"]
+    halt_on_missing = strtobool(os.environ.get("INPUT_HALT_ON_MISSING", "False"))
+
+    # get package metadata from github
+    package_request = requests.get(
+        f"https://api.github.com/orgs/dbt-labs/packages/container/{package}/versions",
+        auth=("", gh_token),
+    )
+    package_meta = package_request.json()
+
+    # Log info if we don't get a 200
+    if package_request.status_code != 200:
+        print(f"Call to GH API failed: {package_request.status_code} {package_meta['message']}")
+
+    # Make an early exit if there is no matching package in github
+    if package_request.status_code == 404:
+        if halt_on_missing:
+            sys.exit(1)
+        # 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
+
+    # map versions and tags
+    version_tag_map = {
+        version["id"]: version["metadata"]["container"]["tags"] for version in package_meta
+    }
+
+    # is pre-release
+    pre_rel = True if any(x in str(new_version) for x in ["a", "b", "rc"]) else False
+
+    # semver of current latest
+    for version, tags in version_tag_map.items():
+        if "latest" in tags:
+            # N.B. This seems counterintuitive, but we expect any version tagged
+            # 'latest' to have exactly three associated tags:
+            # latest, major.minor.latest, and major.minor.patch.
+            # Subtracting everything that contains the string 'latest' gets us
+            # the major.minor.patch which is what's needed for comparison.
+            current_latest = parse([tag for tag in tags if "latest" not in tag][0])
+        else:
+            current_latest = False
+
+    # semver of current_minor_latest
+    for version, tags in version_tag_map.items():
+        if f"{new_version.major}.{new_version.minor}.latest" in tags:
+            # Similar to above, only now we expect exactly two tags:
+            # major.minor.patch and major.minor.latest
+            current_minor_latest = parse([tag for tag in tags if "latest" not in tag][0])
+        else:
+            current_minor_latest = False
+
+    def is_latest(
+        pre_rel: bool, new_version: Version, remote_latest: Union[bool, Version]
+    ) -> bool:
+        """Determine if a given contaier should be tagged 'latest' based on:
+         - it's pre-release status
+         - it's version
+         - the version of a previously identified container tagged 'latest'
+
+        :param pre_rel: Wether or not the version of the new container is a pre-release
+        :param new_version: The version of the new container
+        :param remote_latest: The version of the previously identified container that's
+            already tagged latest or False
+        """
+        # is a pre-release = not latest
+        if pre_rel:
+            return False
+        # + no latest tag found = is latest
+        if not remote_latest:
+            return True
+        # + if remote version is lower than current = is latest, else not latest
+        return True if remote_latest <= new_version else False
+
+    latest = is_latest(pre_rel, new_version, current_latest)
+    minor_latest = is_latest(pre_rel, new_version, current_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

@@ -15,7 +15,9 @@ resolves #
 
 ### Checklist
 
+- [ ] I have read [the contributing guide](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md) and understand what's expected of me
 - [ ] I have signed the [CLA](https://docs.getdbt.com/docs/contributor-license-agreements)
 - [ ] I have run this code in development and it appears to resolve the stated issue
 - [ ] This PR includes tests, or tests are not required/relevant for this PR
-- [ ] I have updated the `CHANGELOG.md` and added information about my change
+- [ ] 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-a-changelog-entry)

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

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

.github/workflows/backport.yml

@@ -0,0 +1,40 @@
+# **what?**
+# When a PR is merged, if it has the backport label, it will create
+# a new PR to backport those changes to the given branch. If it can't
+# cleanly do a backport, it will comment on the merged PR of the failure.
+#
+# Label naming convention: "backport <branch name to backport to>"
+# Example: backport 1.0.latest
+#
+# You MUST "Squash and merge" the original PR or this won't work.
+
+# **why?**
+# Changes sometimes need to be backported to release branches.
+# This automates the backporting process
+
+# **when?**
+# Once a PR is "Squash and merge"'d, by adding a backport label, this is triggered
+
+name: Backport
+on:
+  pull_request:
+    types:
+      - labeled
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  backport:
+    name: Backport
+    runs-on: ubuntu-latest
+    # Only react to merged PRs for security reasons.
+    # See https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#pull_request_target.
+    if: >
+      github.event.pull_request.merged
+      && contains(github.event.label.name, 'backport')
+    steps:
+      - uses: tibdex/backport@v2.0.2
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}

.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-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/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/integration.yml

@@ -1,222 +0,0 @@
-# **what?**
-# This workflow runs all integration tests for supported OS
-# and python versions and core adapters. If triggered by PR,
-# the workflow will only run tests for adapters related
-# to code changes. Use the `test all` and `test ${adapter}`
-# label to run all or additional tests. Use `ok to test`
-# label to mark PRs from forked repositories that are safe
-# to run integration tests for. Requires secrets to run
-# against different warehouses.
-
-# **why?**
-# This checks the functionality of dbt from a user's perspective
-# and attempts to catch functional regressions.
-
-# **when?**
-# This workflow will run on every push to a protected branch
-# and when manually triggered. It will also run for all PRs, including
-# PRs from forks. The workflow will be skipped until there is a label
-# to mark the PR as safe to run.
-
-name: Adapter Integration Tests
-
-on:
-  # pushes to release branches
-  push:
-    branches:
-      - "main"
-      - "develop"
-      - "*.latest"
-      - "releases/*"
-  # all PRs, important to note that `pull_request_target` workflows
-  # will run in the context of the target branch of a PR
-  pull_request_target:
-  # manual tigger
-  workflow_dispatch:
-
-# explicitly turn off permissions for `GITHUB_TOKEN`
-permissions: read-all
-
-# will cancel previous workflows triggered by the same event and for the same ref for PRs or same SHA otherwise
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event_name }}-${{ contains(github.event_name, 'pull_request') && github.event.pull_request.head.ref || github.sha }}
-  cancel-in-progress: true
-
-# sets default shell to bash, for all operating systems
-defaults:
-  run:
-    shell: bash
-
-jobs:
-  # generate test metadata about what files changed and the testing matrix to use
-  test-metadata:
-    # run if not a PR from a forked repository or has a label to mark as safe to test
-    if: >-
-      github.event_name != 'pull_request_target' ||
-      github.event.pull_request.head.repo.full_name == github.repository ||
-      contains(github.event.pull_request.labels.*.name, 'ok to test')
-
-    runs-on: ubuntu-latest
-
-    outputs:
-      matrix: ${{ steps.generate-matrix.outputs.result }}
-
-    steps:
-      - name: Check out the repository (non-PR)
-        if: github.event_name != 'pull_request_target'
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
-
-      - name: Check out the repository (PR)
-        if: github.event_name == 'pull_request_target'
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
-          ref: ${{ github.event.pull_request.head.sha }}
-
-      - name: Check if relevant files changed
-        # https://github.com/marketplace/actions/paths-changes-filter
-        # For each filter, it sets output variable named by the filter to the text:
-        #  'true' - if any of changed files matches any of filter rules
-        #  'false' - if none of changed files matches any of filter rules
-        # also, returns:
-        #  `changes` - JSON array with names of all filters matching any of the changed files
-        uses: dorny/paths-filter@v2
-        id: get-changes
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          filters: |
-            postgres:
-              - 'core/**'
-              - 'plugins/postgres/**'
-              - 'dev-requirements.txt'
-
-      - name: Generate integration test matrix
-        id: generate-matrix
-        uses: actions/github-script@v4
-        env:
-          CHANGES: ${{ steps.get-changes.outputs.changes }}
-        with:
-          script: |
-            const script = require('./.github/scripts/integration-test-matrix.js')
-            const matrix = script({ context })
-            console.log(matrix)
-            return matrix
-
-  test:
-    name: ${{ matrix.adapter }} / python ${{ matrix.python-version }} / ${{ matrix.os }}
-
-    # run if not a PR from a forked repository or has a label to mark as safe to test
-    # also checks that the matrix generated is not empty
-    if: >-
-      needs.test-metadata.outputs.matrix &&
-      fromJSON( needs.test-metadata.outputs.matrix ).include[0] &&
-      (
-        github.event_name != 'pull_request_target' ||
-        github.event.pull_request.head.repo.full_name == github.repository ||
-        contains(github.event.pull_request.labels.*.name, 'ok to test')
-      )
-
-    runs-on: ${{ matrix.os }}
-
-    needs: test-metadata
-
-    strategy:
-      fail-fast: false
-      matrix: ${{ fromJSON(needs.test-metadata.outputs.matrix) }}
-
-    env:
-      TOXENV: integration-${{ matrix.adapter }}
-      PYTEST_ADDOPTS: "-v --color=yes -n4 --csv integration_results.csv"
-      DBT_INVOCATION_ENV: github-actions
-
-    steps:
-      - name: Check out the repository
-        if: github.event_name != 'pull_request_target'
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
-
-      # explicity checkout the branch for the PR,
-      # this is necessary for the `pull_request_target` event
-      - name: Check out the repository (PR)
-        if: github.event_name == 'pull_request_target'
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
-          ref: ${{ github.event.pull_request.head.sha }}
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Set up postgres (linux)
-        if: |
-          matrix.adapter == 'postgres' &&
-          runner.os == 'Linux'
-        uses: ./.github/actions/setup-postgres-linux
-
-      - name: Set up postgres (macos)
-        if: |
-          matrix.adapter == 'postgres' &&
-          runner.os == 'macOS'
-        uses: ./.github/actions/setup-postgres-macos
-
-      - name: Set up postgres (windows)
-        if: |
-          matrix.adapter == 'postgres' &&
-          runner.os == 'Windows'
-        uses: ./.github/actions/setup-postgres-windows
-
-      - name: Install python dependencies
-        run: |
-          pip install --user --upgrade pip
-          pip install tox
-          pip --version
-          tox --version
-
-      - name: Run tox (postgres)
-        if: matrix.adapter == 'postgres'
-        run: tox
-
-      - uses: actions/upload-artifact@v2
-        if: always()
-        with:
-          name: logs
-          path: ./logs
-
-      - name: Get current date
-        if: always()
-        id: date
-        run: echo "::set-output name=date::$(date +'%Y-%m-%dT%H_%M_%S')" #no colons allowed for artifacts
-
-      - uses: actions/upload-artifact@v2
-        if: always()
-        with:
-          name: integration_results_${{ matrix.python-version }}_${{ matrix.os }}_${{ matrix.adapter }}-${{ steps.date.outputs.date }}.csv
-          path: integration_results.csv
-
-  require-label-comment:
-    runs-on: ubuntu-latest
-
-    needs: test
-
-    permissions:
-      pull-requests: write
-
-    steps:
-      - name: Needs permission PR comment
-        if: >-
-          needs.test.result == 'skipped' &&
-          github.event_name == 'pull_request_target' &&
-          github.event.pull_request.head.repo.full_name != github.repository
-        uses: unsplash/comment-on-pr@master
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          msg: |
-            "You do not have permissions to run integration tests, @dbt-labs/core "\
-            "needs to label this PR with `ok to test` in order to run integration tests!"
-          check_for_duplicate_msg: true

.github/workflows/jira-creation.yml

@@ -0,0 +1,26 @@
+# **what?**
+# Mirrors issues into Jira. Includes the information: title,
+# GitHub Issue ID and URL
+
+# **why?**
+# Jira is our tool for tracking and we need to see these issues in there
+
+# **when?**
+# On issue creation or when an issue is labeled `Jira`
+
+name: Jira Issue Creation
+
+on:
+  issues:
+    types: [opened, labeled]
+
+permissions:
+  issues: write
+
+jobs:
+  call-label-action:
+    uses: dbt-labs/jira-actions/.github/workflows/jira-creation.yml@main
+    secrets:
+      JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
+      JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
+      JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}

.github/workflows/jira-label.yml

@@ -0,0 +1,26 @@
+# **what?**
+# Calls mirroring Jira label Action. Includes adding a new label
+# to an existing issue or removing a label as well
+
+# **why?**
+# Jira is our tool for tracking and we need to see these labels in there
+
+# **when?**
+# On labels being added or removed from issues
+
+name: Jira Label Mirroring
+
+on:
+  issues:
+    types: [labeled, unlabeled]
+
+permissions:
+  issues: read
+
+jobs:
+  call-label-action:
+    uses: dbt-labs/jira-actions/.github/workflows/jira-label.yml@main
+    secrets:
+      JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
+      JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
+      JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}

.github/workflows/jira-transition.yml

@@ -0,0 +1,27 @@
+# **what?**
+# Transition a Jira issue to a new state
+# Only supports these GitHub Issue transitions:
+#   closed, deleted, reopened
+
+# **why?**
+# Jira needs to be kept up-to-date
+
+# **when?**
+# On issue closing, deletion, reopened
+
+name: Jira Issue Transition
+
+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
+    secrets:
+      JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
+      JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
+      JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}

.github/workflows/main.yml

@@ -1,9 +1,8 @@
 # **what?**
-# Runs code quality checks, unit tests, and verifies python build on
-# all code commited to the repository. This workflow should not
-# require any secrets since it runs for PRs from forked repos.
-# By default, secrets are not passed to workflows running from
-# a forked repo.
+# Runs code quality checks, unit tests, integration tests and
+# verifies python build on all code commited to the repository. This workflow
+# should not require any secrets since it runs for PRs from forked repos. By
+# default, secrets are not passed to workflows running from a forked repos.
 
 # **why?**
 # Ensure code for dbt meets a certain quality standard.
@@ -18,7 +17,6 @@ on:
   push:
     branches:
       - "main"
-      - "develop"
       - "*.latest"
       - "releases/*"
   pull_request:
@@ -37,47 +35,45 @@ defaults:
 
 jobs:
   code-quality:
-    name: ${{ matrix.toxenv }}
+    name: code-quality
 
     runs-on: ubuntu-latest
-
-    strategy:
-      fail-fast: false
-      matrix:
-        toxenv: [flake8, mypy]
-
-    env:
-      TOXENV: ${{ matrix.toxenv }}
-      PYTEST_ADDOPTS: "-v --color=yes"
+    timeout-minutes: 10
 
     steps:
       - name: Check out the repository
         uses: actions/checkout@v2
-        with:
-          persist-credentials: false
 
       - 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: |
-          pip install --user --upgrade pip
-          pip install tox
-          pip --version
-          tox --version
+          python -m pip install --user --upgrade pip
+          python -m pip --version
+          python -m pip install pre-commit
+          pre-commit --version
+          python -m pip install mypy==0.942
+          mypy --version
+          python -m pip install -r requirements.txt
+          python -m pip install -r dev-requirements.txt
+          dbt --version
 
-      - name: Run tox
-        run: tox
+      - name: Run pre-commit hooks
+        run: pre-commit run --all-files --show-diff-on-failure
 
   unit:
     name: unit test / python ${{ matrix.python-version }}
 
     runs-on: ubuntu-latest
+    timeout-minutes: 10
 
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.6, 3.7, 3.8] # TODO: support unit testing for python 3.9 (https://github.com/dbt-labs/dbt/issues/3689)
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
 
     env:
       TOXENV: "unit"
@@ -86,19 +82,17 @@ jobs:
     steps:
       - name: Check out the repository
         uses: actions/checkout@v2
-        with:
-          persist-credentials: false
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
           python-version: ${{ matrix.python-version }}
 
       - name: Install python dependencies
         run: |
-          pip install --user --upgrade pip
-          pip install tox
-          pip --version
+          python -m pip install --user --upgrade pip
+          python -m pip --version
+          python -m pip install tox
           tox --version
 
       - name: Run tox
@@ -107,7 +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()
@@ -115,6 +111,81 @@ jobs:
           name: unit_results_${{ matrix.python-version }}-${{ steps.date.outputs.date }}.csv
           path: unit_results.csv
 
+  integration:
+    name: integration test / python ${{ matrix.python-version }} / ${{ matrix.os }}
+
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 45
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        os: [ubuntu-20.04]
+        include:
+          - python-version: 3.8
+            os: windows-latest
+          - python-version: 3.8
+            os: macos-latest
+
+    env:
+      TOXENV: integration
+      PYTEST_ADDOPTS: "-v --color=yes -n4 --csv integration_results.csv"
+      DBT_INVOCATION_ENV: github-actions
+      DBT_TEST_USER_1: dbt_test_user_1
+      DBT_TEST_USER_2: dbt_test_user_2
+      DBT_TEST_USER_3: dbt_test_user_3
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v2
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4.3.0
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Set up postgres (linux)
+        if: runner.os == 'Linux'
+        uses: ./.github/actions/setup-postgres-linux
+
+      - name: Set up postgres (macos)
+        if: runner.os == 'macOS'
+        uses: ./.github/actions/setup-postgres-macos
+
+      - name: Set up postgres (windows)
+        if: runner.os == 'Windows'
+        uses: ./.github/actions/setup-postgres-windows
+
+      - name: Install python tools
+        run: |
+          python -m pip install --user --upgrade pip
+          python -m pip --version
+          python -m pip install tox
+          tox --version
+
+      - name: Run tests
+        run: tox
+
+      - name: Get current date
+        if: always()
+        id: date
+        run: |
+          CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
+          echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
+
+      - uses: actions/upload-artifact@v2
+        if: always()
+        with:
+          name: logs_${{ matrix.python-version }}_${{ matrix.os }}_${{ steps.date.outputs.date }}
+          path: ./logs
+
+      - uses: actions/upload-artifact@v2
+        if: always()
+        with:
+          name: integration_results_${{ matrix.python-version }}_${{ matrix.os }}_${{ steps.date.outputs.date }}.csv
+          path: integration_results.csv
+
   build:
     name: build packages
 
@@ -123,19 +194,17 @@ jobs:
     steps:
       - name: Check out the repository
         uses: actions/checkout@v2
-        with:
-          persist-credentials: false
 
       - 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: |
-          pip install --user --upgrade pip
-          pip install --upgrade setuptools wheel twine check-wheel-contents
-          pip --version
+          python -m pip install --user --upgrade pip
+          python -m pip install --upgrade setuptools wheel twine check-wheel-contents
+          python -m pip --version
 
       - name: Build distributions
         run: ./scripts/build-dist.sh
@@ -151,55 +220,18 @@ jobs:
         run: |
           check-wheel-contents dist/*.whl --ignore W007,W008
 
-      - uses: actions/upload-artifact@v2
-        with:
-          name: dist
-          path: dist/
-
-  test-build:
-    name: verify packages / python ${{ matrix.python-version }} / ${{ matrix.os }}
-
-    needs: build
-
-    runs-on: ${{ matrix.os }}
-
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: [3.6, 3.7, 3.8, 3.9]
-
-    steps:
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Install python dependencies
-        run: |
-          pip install --user --upgrade pip
-          pip install --upgrade wheel
-          pip --version
-
-      - uses: actions/download-artifact@v2
-        with:
-          name: dist
-          path: dist/
-
-      - name: Show distributions
-        run: ls -lh dist/
-
       - name: Install wheel distributions
         run: |
-          find ./dist/*.whl -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
+          find ./dist/*.whl -maxdepth 1 -type f | xargs python -m pip install --force-reinstall --find-links=dist/
 
       - name: Check wheel distributions
         run: |
           dbt --version
 
       - name: Install source distributions
+        # ignore dbt-1.0.0, which intentionally raises an error when installed from source
         run: |
-          find ./dist/*.gz -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
+          find ./dist/dbt-[a-z]*.gz -maxdepth 1 -type f | xargs python -m pip install --force-reinstall --find-links=dist/
 
       - name: Check source distributions
         run: |

.github/workflows/performance.yml

@@ -1,176 +0,0 @@
-name: Performance Regression Tests
-# Schedule triggers
-on:
-  # runs twice a day at 10:05am and 10:05pm
-  schedule:
-    - cron: "5 10,22 * * *"
-  # Allows you to run this workflow manually from the Actions tab
-  workflow_dispatch:
-
-jobs:
-  # checks fmt of runner code
-  # purposefully not a dependency of any other job
-  # will block merging, but not prevent developing
-  fmt:
-    name: Cargo fmt
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-      - run: rustup component add rustfmt
-      - uses: actions-rs/cargo@v1
-        with:
-          command: fmt
-          args: --manifest-path performance/runner/Cargo.toml --all -- --check
-
-  # runs any tests associated with the runner
-  # these tests make sure the runner logic is correct
-  test-runner:
-    name: Test Runner
-    runs-on: ubuntu-latest
-    env:
-      # turns errors into warnings
-      RUSTFLAGS: "-D warnings"
-    steps:
-      - uses: actions/checkout@v2
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-      - uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --manifest-path performance/runner/Cargo.toml
-
-  # build an optimized binary to be used as the runner in later steps
-  build-runner:
-    needs: [test-runner]
-    name: Build Runner
-    runs-on: ubuntu-latest
-    env:
-      RUSTFLAGS: "-D warnings"
-    steps:
-      - uses: actions/checkout@v2
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-      - uses: actions-rs/cargo@v1
-        with:
-          command: build
-          args: --release --manifest-path performance/runner/Cargo.toml
-      - uses: actions/upload-artifact@v2
-        with:
-          name: runner
-          path: performance/runner/target/release/runner
-
-  # run the performance measurements on the current or default branch
-  measure-dev:
-    needs: [build-runner]
-    name: Measure Dev Branch
-    runs-on: ubuntu-latest
-    steps:
-      - name: checkout dev
-        uses: actions/checkout@v2
-      - name: Setup Python
-        uses: actions/setup-python@v2.2.2
-        with:
-          python-version: "3.8"
-      - name: install dbt
-        run: pip install -r dev-requirements.txt -r editable-requirements.txt
-      - name: install hyperfine
-        run: wget https://github.com/sharkdp/hyperfine/releases/download/v1.11.0/hyperfine_1.11.0_amd64.deb && sudo dpkg -i hyperfine_1.11.0_amd64.deb
-      - uses: actions/download-artifact@v2
-        with:
-          name: runner
-      - name: change permissions
-        run: chmod +x ./runner
-      - name: run
-        run: ./runner measure -b dev -p ${{ github.workspace }}/performance/projects/
-      - uses: actions/upload-artifact@v2
-        with:
-          name: dev-results
-          path: performance/results/
-
-  # run the performance measurements on the release branch which we use
-  # as a performance baseline. This part takes by far the longest, so
-  # we do everything we can first so the job fails fast.
-  # -----
-  # we need to checkout dbt twice in this job: once for the baseline dbt
-  # version, and once to get the latest regression testing projects,
-  # metrics, and runner code from the develop or current branch so that
-  # the calculations match for both versions of dbt we are comparing.
-  measure-baseline:
-    needs: [build-runner]
-    name: Measure Baseline Branch
-    runs-on: ubuntu-latest
-    steps:
-      - name: checkout latest
-        uses: actions/checkout@v2
-        with:
-          ref: "0.20.latest"
-      - name: Setup Python
-        uses: actions/setup-python@v2.2.2
-        with:
-          python-version: "3.8"
-      - name: move repo up a level
-        run: mkdir ${{ github.workspace }}/../baseline/ && cp -r ${{ github.workspace }} ${{ github.workspace }}/../baseline
-      - name: "[debug] ls new dbt location"
-        run: ls ${{ github.workspace }}/../baseline/dbt/
-      # installation creates egg-links so we have to preserve source
-      - name: install dbt from new location
-        run: cd ${{ github.workspace }}/../baseline/dbt/ && pip install -r dev-requirements.txt -r editable-requirements.txt
-      # checkout the current branch to get all the target projects
-      # this deletes the old checked out code which is why we had to copy before
-      - name: checkout dev
-        uses: actions/checkout@v2
-      - name: install hyperfine
-        run: wget https://github.com/sharkdp/hyperfine/releases/download/v1.11.0/hyperfine_1.11.0_amd64.deb && sudo dpkg -i hyperfine_1.11.0_amd64.deb
-      - uses: actions/download-artifact@v2
-        with:
-          name: runner
-      - name: change permissions
-        run: chmod +x ./runner
-      - name: run runner
-        run: ./runner measure -b baseline -p ${{ github.workspace }}/performance/projects/
-      - uses: actions/upload-artifact@v2
-        with:
-          name: baseline-results
-          path: performance/results/
-
-  # detect regressions on the output generated from measuring
-  # the two branches. Exits with non-zero code if a regression is detected.
-  calculate-regressions:
-    needs: [measure-dev, measure-baseline]
-    name: Compare Results
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/download-artifact@v2
-        with:
-          name: dev-results
-      - uses: actions/download-artifact@v2
-        with:
-          name: baseline-results
-      - name: "[debug] ls result files"
-        run: ls
-      - uses: actions/download-artifact@v2
-        with:
-          name: runner
-      - name: change permissions
-        run: chmod +x ./runner
-      - name: make results directory
-        run: mkdir ./final-output/
-      - name: run calculation
-        run: ./runner calculate -r ./ -o ./final-output/
-        # always attempt to upload the results even if there were regressions found
-      - uses: actions/upload-artifact@v2
-        if: ${{ always() }}
-        with:
-          name: final-calculations
-          path: ./final-output/*

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

@@ -0,0 +1,62 @@
+# **what?**
+# The purpose of this workflow is to trigger CI to run for each
+# release branch and main branch on a regular cadence. If the CI workflow
+# fails for a branch, it will post to dev-core-alerts to raise awareness.
+# The 'aurelien-baudet/workflow-dispatch' Action triggers the existing
+# CI worklow file on the given branch to run so that even if we change the
+# CI workflow file in the future, the one that is tailored for the given
+# release branch will be used.
+
+# **why?**
+# Ensures release branches and main are always shippable and not broken.
+# Also, can catch any dependencies shifting beneath us that might
+# introduce breaking changes (could also impact Cloud).
+
+# **when?**
+# Mainly on a schedule of 9:00, 13:00, 18:00 UTC everyday.
+# Manual trigger can also test on demand
+
+name: Release branch scheduled testing
+
+on:
+  schedule:
+    - cron: '0 9,13,18 * * *' # 9:00, 13:00, 18:00 UTC
+
+  workflow_dispatch: # for manual triggering
+
+# no special access is needed
+permissions: read-all
+
+jobs:
+  kick-off-ci:
+    name: Kick-off CI
+    runs-on: ubuntu-latest
+
+    strategy:
+      # must run CI 1 branch at a time b/c the workflow-dispatch Action polls for
+      # latest run for results and it gets confused when we kick off multiple runs
+      # at once. There is a race condition so we will just run in sequential order.
+      max-parallel: 1
+      fail-fast: false
+      matrix:
+        branch: [1.0.latest, 1.1.latest, 1.2.latest, 1.3.latest, 1.4.latest, main]
+
+    steps:
+    - name: Call CI workflow for ${{ matrix.branch }} branch
+      id: trigger-step
+      uses: aurelien-baudet/workflow-dispatch@v2.1.1
+      with:
+        workflow: main.yml
+        ref: ${{ matrix.branch }}
+        token: ${{ secrets.FISHTOWN_BOT_PAT }}
+
+    - name: Post failure to Slack
+      uses: ravsamhq/notify-slack-action@v1
+      if: ${{ always() && !contains(steps.trigger-step.outputs.workflow-conclusion,'success') }}
+      with:
+        status: ${{ job.status }}
+        notification_title: 'dbt-core scheduled run of "${{ matrix.branch }}" branch not successful'
+        message_format: ':x: CI on branch "${{ matrix.branch }}" ${{ steps.trigger-step.outputs.workflow-conclusion }}'
+        footer: 'Linked failed CI run ${{ steps.trigger-step.outputs.workflow-url }}'
+      env:
+        SLACK_WEBHOOK_URL: ${{ secrets.SLACK_DEV_CORE_ALERTS }}

.github/workflows/release-docker.yml

@@ -0,0 +1,118 @@
+# **what?**
+# This workflow will generate a series of docker images for dbt and push them to the github container registry
+
+# **why?**
+# Docker images for dbt are used in a number of important places throughout the dbt ecosystem.  This is how we keep those images up-to-date.
+
+# **when?**
+# This is triggered manually
+
+# **next steps**
+# - build this into the release workflow (or conversly, break out the different release methods into their own workflow files)
+
+name: Docker release
+
+permissions:
+  packages: write
+
+on:
+  workflow_dispatch:
+    inputs:
+      package:
+       description: The package to release. _One_ of [dbt-core, dbt-redshift, dbt-bigquery, dbt-snowflake, dbt-spark, dbt-postgres]
+       required: true
+      version_number:
+       description: The release version number (i.e. 1.0.0b1). Do not include `latest` tags or a leading `v`!
+       required: true
+
+jobs:
+  get_version_meta:
+    name: Get version meta
+    runs-on: ubuntu-latest
+    outputs:
+      major: ${{ steps.version.outputs.major }}
+      minor: ${{ steps.version.outputs.minor }}
+      patch: ${{ steps.version.outputs.patch }}
+      latest: ${{ steps.latest.outputs.latest }}
+      minor_latest: ${{ steps.latest.outputs.minor_latest }}
+    steps:
+      - uses: actions/checkout@v1
+      - name: Split version
+        id: version
+        run: |
+          IFS="." read -r MAJOR MINOR PATCH <<< ${{ github.event.inputs.version_number }}
+          echo "major=$MAJOR" >> $GITHUB_OUTPUT
+          echo "minor=$MINOR" >> $GITHUB_OUTPUT
+          echo "patch=$PATCH" >> $GITHUB_OUTPUT
+
+      - name: Is pkg 'latest'
+        id: latest
+        uses: ./.github/actions/latest-wrangler
+        with:
+          package: ${{ github.event.inputs.package }}
+          new_version: ${{ github.event.inputs.version_number }}
+          gh_token: ${{ secrets.GITHUB_TOKEN }}
+          halt_on_missing: False
+
+  setup_image_builder:
+    name: Set up docker image builder
+    runs-on: ubuntu-latest
+    needs: [get_version_meta]
+    steps:
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+
+  build_and_push:
+    name: Build images and push to GHCR
+    runs-on: ubuntu-latest
+    needs: [setup_image_builder, get_version_meta]
+    steps:
+      - name: Get docker build arg
+        id: build_arg
+        run: |
+          BUILD_ARG_NAME=$(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
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build and push MAJOR.MINOR.PATCH tag
+        uses: docker/build-push-action@v2
+        with:
+          file: docker/Dockerfile
+          push: True
+          target: ${{ github.event.inputs.package }}
+          build-args: |
+            ${{ steps.build_arg.outputs.build_arg_name }}_ref=${{ steps.build_arg.outputs.build_arg_value }}@v${{ github.event.inputs.version_number }}
+          tags: |
+            ghcr.io/dbt-labs/${{ github.event.inputs.package }}:${{ github.event.inputs.version_number }}
+
+      - name: Build and push MINOR.latest tag
+        uses: docker/build-push-action@v2
+        if: ${{ needs.get_version_meta.outputs.minor_latest == 'True' }}
+        with:
+          file: docker/Dockerfile
+          push: True
+          target: ${{ github.event.inputs.package }}
+          build-args: |
+            ${{ steps.build_arg.outputs.build_arg_name }}_ref=${{ steps.build_arg.outputs.build_arg_value }}@v${{ github.event.inputs.version_number }}
+          tags: |
+            ghcr.io/dbt-labs/${{ github.event.inputs.package }}:${{ needs.get_version_meta.outputs.major }}.${{ needs.get_version_meta.outputs.minor }}.latest
+
+      - name: Build and push latest tag
+        uses: docker/build-push-action@v2
+        if: ${{ needs.get_version_meta.outputs.latest == 'True' }}
+        with:
+          file: docker/Dockerfile
+          push: True
+          target: ${{ github.event.inputs.package }}
+          build-args: |
+            ${{ steps.build_arg.outputs.build_arg_name }}_ref=${{ steps.build_arg.outputs.build_arg_value }}@v${{ github.event.inputs.version_number }}
+          tags: |
+            ghcr.io/dbt-labs/${{ github.event.inputs.package }}:latest

.github/workflows/release.yml

@@ -0,0 +1,202 @@
+# **what?**
+# Take the given commit, run unit tests specifically on that sha, build and
+# package it, and then release to GitHub and PyPi with that specific build
+
+# **why?**
+# Ensure an automated and tested release process
+
+# **when?**
+# This will only run manually with a given sha and version
+
+name: Release to GitHub and PyPi
+
+on:
+  workflow_dispatch:
+    inputs:
+      sha:
+       description: 'The last commit sha in the release'
+       required: true
+      version_number:
+       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
+
+jobs:
+  unit:
+    name: Unit test
+
+    runs-on: ubuntu-latest
+
+    env:
+      TOXENV: "unit"
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+          ref: ${{ github.event.inputs.sha }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+
+      - name: Install python dependencies
+        run: |
+          pip install --user --upgrade pip
+          pip install tox
+          pip --version
+          tox --version
+
+      - name: Run tox
+        run: tox
+
+  build:
+    name: build packages
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+          ref: ${{ github.event.inputs.sha }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+
+      - name: Install python dependencies
+        run: |
+          pip install --user --upgrade pip
+          pip install --upgrade setuptools wheel twine check-wheel-contents
+          pip --version
+
+      - name: Build distributions
+        run: ./scripts/build-dist.sh
+
+      - name: Show distributions
+        run: ls -lh dist/
+
+      - name: Check distribution descriptions
+        run: |
+          twine check dist/*
+
+      - name: Check wheel contents
+        run: |
+          check-wheel-contents dist/*.whl --ignore W007,W008
+
+      - uses: actions/upload-artifact@v2
+        with:
+          name: dist
+          path: |
+            dist/
+            !dist/dbt-${{github.event.inputs.version_number}}.tar.gz
+
+  test-build:
+    name: verify packages
+
+    needs: [build, unit]
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+
+      - name: Install python dependencies
+        run: |
+          pip install --user --upgrade pip
+          pip install --upgrade wheel
+          pip --version
+
+      - uses: actions/download-artifact@v2
+        with:
+          name: dist
+          path: dist/
+
+      - name: Show distributions
+        run: ls -lh dist/
+
+      - name: Install wheel distributions
+        run: |
+          find ./dist/*.whl -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
+
+      - name: Check wheel distributions
+        run: |
+          dbt --version
+
+      - name: Install source distributions
+        run: |
+          find ./dist/*.gz -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
+
+      - name: Check source distributions
+        run: |
+          dbt --version
+
+  github-release:
+    name: GitHub Release
+
+    needs: test-build
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/download-artifact@v2
+        with:
+          name: dist
+          path: '.'
+
+      # Need to set an output variable because env variables can't be taken as input
+      # This is needed for the next step with releasing to GitHub
+      - name: Find release type
+        id: release_type
+        env:
+          IS_PRERELEASE: ${{ contains(github.event.inputs.version_number, 'rc') ||  contains(github.event.inputs.version_number, 'b') }}
+        run: |
+          echo "isPrerelease=$IS_PRERELEASE" >> $GITHUB_OUTPUT
+
+      - name: Creating GitHub Release
+        uses: softprops/action-gh-release@v1
+        with:
+          name: dbt-core v${{github.event.inputs.version_number}}
+          tag_name: v${{github.event.inputs.version_number}}
+          prerelease: ${{ steps.release_type.outputs.isPrerelease }}
+          target_commitish: ${{github.event.inputs.sha}}
+          body: |
+            [Release notes](https://github.com/dbt-labs/dbt-core/blob/main/CHANGELOG.md)
+          files: |
+            dbt_postgres-${{github.event.inputs.version_number}}-py3-none-any.whl
+            dbt_core-${{github.event.inputs.version_number}}-py3-none-any.whl
+            dbt-postgres-${{github.event.inputs.version_number}}.tar.gz
+            dbt-core-${{github.event.inputs.version_number}}.tar.gz
+
+  pypi-release:
+    name: Pypi release
+
+    runs-on: ubuntu-latest
+
+    needs: github-release
+
+    environment: PypiProd
+    steps:
+      - uses: actions/download-artifact@v2
+        with:
+          name: dist
+          path: 'dist'
+
+      - name: Publish distribution to PyPI
+        uses: pypa/gh-action-pypi-publish@v1.4.2
+        with:
+          password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/schema-check.yml

@@ -1,5 +1,5 @@
 # **what?**
-# Compares the schema of the dbt version of the given ref vs 
+# Compares the schema of the dbt version of the given ref vs
 # the latest official schema releases found in schemas.getdbt.com.
 # If there are differences, the workflow will fail and upload the
 # diff as an artifact. The metadata team should be alerted to the change.
@@ -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
@@ -37,20 +40,20 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: 3.8
-                
+
       - name: Checkout dbt repo
         uses: actions/checkout@v2.3.4
         with:
             path: ${{ env.DBT_REPO_DIRECTORY }}
-                       
+
       - name: Checkout schemas.getdbt.com repo
-        uses: actions/checkout@v2.3.4    
-        with: 
+        uses: actions/checkout@v2.3.4
+        with:
           repository: dbt-labs/schemas.getdbt.com
           ref: 'main'
           ssh-key: ${{ secrets.SCHEMA_SSH_PRIVATE_KEY }}
           path: ${{ env.SCHEMA_REPO_DIRECTORY }}
-        
+
       - name: Generate current schema
         run: |
           cd ${{ env.DBT_REPO_DIRECTORY }}
@@ -59,7 +62,7 @@ jobs:
           pip install --upgrade pip
           pip install -r dev-requirements.txt -r editable-requirements.txt
           python scripts/collect-artifact-schema.py --path ${{ env.LATEST_SCHEMA_PATH }}
-          
+
       # Copy generated schema files into the schemas.getdbt.com repo
       # Do a git diff to find any changes
       # Ignore any date or version changes though

.github/workflows/stale.yml

@@ -3,16 +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."
-          # mark issues/PRs stale when they haven't seen activity in 180 days
-          days-before-stale: 180
-          # ignore checking issues with the following labels
-          exempt-issue-labels: "epic,discussion"
+    uses: dbt-labs/actions/.github/workflows/stale-bot-matrix.yml@main

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

@@ -0,0 +1,65 @@
+# This Action checks makes a dbt run to sample json structured logs
+# and checks that they conform to the currently documented schema.
+#
+# If this action fails it either means we have unintentionally deviated
+# from our documented structured logging schema, or we need to bump the
+# version of our structured logging and add new documentation to
+# communicate these changes.
+
+name: Structured Logging Schema Check
+on:
+  push:
+    branches:
+      - "main"
+      - "*.latest"
+      - "releases/*"
+  pull_request:
+  workflow_dispatch:
+
+permissions: read-all
+
+jobs:
+  # run the performance measurements on the current or default branch
+  test-schema:
+    name: Test Log Schema
+    runs-on: ubuntu-20.04
+    env:
+      # turns warnings into errors
+      RUSTFLAGS: "-D warnings"
+      # points tests to the log file
+      LOG_DIR: "/home/runner/work/dbt-core/dbt-core/logs"
+      # tells integration tests to output into json format
+      DBT_LOG_FORMAT: "json"
+      # Additional test users
+      DBT_TEST_USER_1: dbt_test_user_1
+      DBT_TEST_USER_2: dbt_test_user_2
+      DBT_TEST_USER_3: dbt_test_user_3
+
+    steps:
+      - name: checkout dev
+        uses: actions/checkout@v2
+        with:
+          persist-credentials: false
+
+      - name: Setup Python
+        uses: actions/setup-python@v2.2.2
+        with:
+          python-version: "3.8"
+
+      - name: Install python dependencies
+        run: |
+          pip install --user --upgrade pip
+          pip --version
+          pip install tox
+          tox --version
+
+      - name: Set up postgres
+        uses: ./.github/actions/setup-postgres-linux
+
+      - name: ls
+        run: ls
+
+      # integration tests generate a ton of logs in different files. the next step will find them all.
+      # 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

.github/workflows/test/.actrc

@@ -0,0 +1 @@
+-P ubuntu-latest=ghcr.io/catthehacker/ubuntu:act-latest

.github/workflows/test/.gitignore

@@ -0,0 +1 @@
+.secrets

.github/workflows/test/.secrets.EXAMPLE

@@ -0,0 +1 @@
+GITHUB_TOKEN=GH_PERSONAL_ACCESS_TOKEN_GOES_HERE

.github/workflows/test/inputs/release_docker.json

@@ -0,0 +1,6 @@
+{
+    "inputs": {
+      "version_number": "1.0.1",
+      "package": "dbt-postgres"
+    }
+}

.github/workflows/triage-labels.yml

@@ -0,0 +1,33 @@
+# **what?**
+# When the core team triages, we sometimes need more information from the issue creator.  In
+# those cases we remove the `triage` label and add the `awaiting_response` label.  Once we
+# recieve a response in the form of a comment, we want the `awaiting_response` label removed
+# in favor of the `triage` label so we are aware that the issue needs action.
+
+# **why?**
+# To help with out team triage issue tracking
+
+# **when?**
+# This will run when a comment is added to an issue and that issue has to `awaiting_response` label.
+
+name: Update Triage Label
+
+on: issue_comment
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+  issues: write
+
+jobs:
+  triage_label:
+    if: contains(github.event.issue.labels.*.name, 'awaiting_response')
+    runs-on: ubuntu-latest
+    steps:
+      - name: initial labeling
+        uses: andymckay/labeler@master
+        with:
+          add-labels: "triage"
+          remove-labels: "awaiting_response"

.github/workflows/version-bump.yml

@@ -1,18 +1,15 @@
 # **what?**
-# This workflow will take a version number and a dry run flag. 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.
+# 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 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.
+# This is to aid in releasing dbt and making sure we have updated
+# 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"
@@ -57,53 +44,82 @@ jobs:
         run: |
           python3 -m venv env
           source env/bin/activate
-          pip install --upgrade pip     
-          
+          pip install --upgrade pip
+
+      - name: Add Homebrew to PATH
+        run: |
+          echo "/home/linuxbrew/.linuxbrew/bin:/home/linuxbrew/.linuxbrew/sbin" >> $GITHUB_PATH
+
+      - 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
-        if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
         run: |
-          git checkout -b bumping-version/${{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
-      
-      - name: Generate Docker requirements
-        run: |
-          source env/bin/activate
-          pip install -r requirements.txt 
-          pip freeze -l > docker/requirements/requirements.txt
-          git status
+          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
+          pip install -r dev-requirements.txt
+          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
@@ -49,9 +51,8 @@ coverage.xml
 *,cover
 .hypothesis/
 test.env
+*.pytest_cache/
 
-# Mypy
-.mypy_cache/
 
 # Translations
 *.mo
@@ -66,10 +67,10 @@ docs/_build/
 # PyBuilder
 target/
 
-#Ipython Notebook
+# Ipython Notebook
 .ipynb_checkpoints
 
-#Emacs
+# Emacs
 *~
 
 # Sublime Text
@@ -78,6 +79,7 @@ target/
 # Vim
 *.sw*
 
+# Pyenv
 .python-version
 
 # Vim
@@ -90,7 +92,12 @@ venv/
 # AWS credentials
 .aws/
 
+# MacOS
 .DS_Store
 
 # vscode
 .vscode/
+*.code-workspace
+
+# poetry
+poetry.lock

.pre-commit-config.yaml

@@ -0,0 +1,63 @@
+# Configuration for pre-commit hooks (see https://pre-commit.com/).
+# 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/|core/dbt/docs/build/)
+
+# Force all unspecified python hooks to run python 3.8
+default_language_version:
+  python: python3
+
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v3.2.0
+  hooks:
+  - id: check-yaml
+    args: [--unsafe]
+  - id: check-json
+  - id: end-of-file-fixer
+  - id: trailing-whitespace
+    exclude_types:
+      - "markdown"
+  - id: check-case-conflict
+- repo: https://github.com/psf/black
+  rev: 22.3.0
+  hooks:
+  - id: black
+  - id: black
+    alias: black-check
+    stages: [manual]
+    args:
+    - "--check"
+    - "--diff"
+- repo: https://github.com/pycqa/flake8
+  rev: 4.0.1
+  hooks:
+  - id: flake8
+  - id: flake8
+    alias: flake8-check
+    stages: [manual]
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.942
+  hooks:
+  - id: mypy
+    # N.B.: Mypy is... a bit fragile.
+    #
+    # By using `language: system` we run this hook in the local
+    # environment instead of a pre-commit isolated one.  This is needed
+    # to ensure mypy correctly parses the project.
+
+    # It may cause trouble
+    # in that it adds environmental variables out of our control to the
+    # mix.  Unfortunately, there's nothing we can do about per pre-commit's
+    # author.
+    # See https://github.com/pre-commit/pre-commit/issues/730 for details.
+    args: [--show-error-codes]
+    files: ^core/dbt/
+    language: system
+  - id: mypy
+    alias: mypy-check
+    stages: [manual]
+    args: [--show-error-codes, --pretty]
+    files: ^core/dbt/
+    language: system

ARCHITECTURE.md

@@ -2,18 +2,25 @@ The core function of dbt is SQL compilation and execution. Users create projects
 
 ## dbt-core
 
-Most of the python code in the repository is within the `core/dbt` directory. Currently the main subdirectories are:
+Most of the python code in the repository is within the `core/dbt` directory.
+- [`single python files`](core/dbt/README.md): A number of individual files, such as 'compilation.py' and 'exceptions.py'
 
-- [`adapters`](core/dbt/adapters): Define base classes for behavior that is likely to differ across databases
-- [`clients`](core/dbt/clients): Interface with dependencies (agate, jinja) or across operating systems
-- [`config`](core/dbt/config): Reconcile user-supplied configuration from connection profiles, project files, and Jinja macros
-- [`context`](core/dbt/context): Build and expose dbt-specific Jinja functionality
-- [`contracts`](core/dbt/contracts): Define Python objects (dataclasses) that dbt expects to create and validate
-- [`deps`](core/dbt/deps): Package installation and dependency resolution
-- [`graph`](core/dbt/graph): Produce a `networkx` DAG of project resources, and selecting those resources given user-supplied criteria
-- [`include`](core/dbt/include): The dbt "global project," which defines default implementations of Jinja2 macros
-- [`parser`](core/dbt/parser): Read project files, validate, construct python objects
-- [`task`](core/dbt/task): Set forth the actions that dbt can perform when invoked
+The main subdirectories of core/dbt:
+- [`adapters`](core/dbt/adapters/README.md): Define base classes for behavior that is likely to differ across databases
+- [`clients`](core/dbt/clients/README.md): Interface with dependencies (agate, jinja) or across operating systems
+- [`config`](core/dbt/config/README.md): Reconcile user-supplied configuration from connection profiles, project files, and Jinja macros
+- [`context`](core/dbt/context/README.md): Build and expose dbt-specific Jinja functionality
+- [`contracts`](core/dbt/contracts/README.md): Define Python objects (dataclasses) that dbt expects to create and validate
+- [`deps`](core/dbt/deps/README.md): Package installation and dependency resolution
+- [`events`](core/dbt/events/README.md): Logging events
+- [`graph`](core/dbt/graph/README.md): Produce a `networkx` DAG of project resources, and selecting those resources given user-supplied criteria
+- [`include`](core/dbt/include/README.md): The dbt "global project," which defines default implementations of Jinja2 macros
+- [`parser`](core/dbt/parser/README.md): Read project files, validate, construct python objects
+- [`task`](core/dbt/task/README.md): Set forth the actions that dbt can perform when invoked
+
+Legacy tests are found in the 'test' directory:
+- [`unit tests`](core/dbt/test/unit/README.md): Unit tests
+- [`integration tests`](core/dbt/test/integration/README.md): Integration tests
 
 ### Invoking dbt
 
@@ -44,4 +51,4 @@ The [`test/`](test/) subdirectory includes unit and integration tests that run a
 
 - [docker](docker/): All dbt versions are published as Docker images on DockerHub. This subfolder contains the `Dockerfile` (constant) and `requirements.txt` (one for each version).
 - [etc](etc/): Images for README
-- [scripts](scripts/): Helper scripts for testing, releasing, and producing JSON schemas. These are not included in distributions of dbt, not are they rigorously tested—they're just handy tools for the dbt maintainers :)
+- [scripts](scripts/): Helper scripts for testing, releasing, and producing JSON schemas. These are not included in distributions of dbt, nor are they rigorously tested—they're just handy tools for the dbt maintainers :)

CONTRIBUTING.md

@@ -1,120 +1,77 @@
-# Contributing to `dbt`
+# Contributing to `dbt-core`
+
+`dbt-core` is open source software. It is what it is today because community members have opened issues, provided feedback, and [contributed to the knowledge loop](https://www.getdbt.com/dbt-labs/values/). Whether you are a seasoned open source contributor or a first-time committer, we welcome and encourage you to contribute code, documentation, ideas, or problem statements to this project.
 
 1. [About this document](#about-this-document)
-2. [Proposing a change](#proposing-a-change)
-3. [Getting the code](#getting-the-code)
-4. [Setting up an environment](#setting-up-an-environment)
-5. [Running `dbt` in development](#running-dbt-in-development)
-6. [Testing](#testing)
-7. [Submitting a Pull Request](#submitting-a-pull-request)
+2. [Getting the code](#getting-the-code)
+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. [Debugging](#debugging)
+7. [Adding a changelog entry](#adding-a-changelog-entry)
+8. [Submitting a Pull Request](#submitting-a-pull-request)
 
 ## About this document
 
-This document is a guide intended for folks interested in contributing to `dbt`. Below, we document the process by which members of the community should create issues and submit pull requests (PRs) in this repository. It is not intended as a guide for using `dbt`, and it assumes a certain level of familiarity with Python concepts such as virtualenvs, `pip`, python modules, filesystems, and so on. This guide assumes you are using macOS or Linux and are comfortable with the command line.
+There are many ways to contribute to the ongoing development of `dbt-core`, such as by participating in discussions and issues. We encourage you to first read our higher-level document: ["Expectations for Open Source Contributors"](https://docs.getdbt.com/docs/contributing/oss-expectations).
 
-If you're new to python development or contributing to open-source software, we encourage you to read this document from start to finish. If you get stuck, drop us a line in the `#dbt-core-development` channel on [slack](https://community.getdbt.com).
+The rest of this document serves as a more granular guide for contributing code changes to `dbt-core` (this repository). It is not intended as a guide for using `dbt-core`, and some pieces assume a level of familiarity with Python development (virtualenvs, `pip`, etc). Specific code snippets in this guide assume you are using macOS or Linux and are comfortable with the command line.
 
-#### Adapters
+If you get stuck, we're happy to help! Drop us a line in the `#dbt-core-development` channel in the [dbt Community Slack](https://community.getdbt.com).
 
-If you have an issue or code change suggestion related to a specific database [adapter](https://docs.getdbt.com/docs/available-adapters); please refer to that supported databases seperate repo for those contributions.
+### Notes
 
-### Signing the CLA
-
-Please note that all contributors to `dbt` must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements) to have their Pull Request merged into the `dbt` codebase. If you are unable to sign the CLA, then the `dbt` maintainers will unfortunately be unable to merge your Pull Request. You are, however, welcome to open issues and comment on existing ones.
-
-## Proposing a change
-
-`dbt` is Apache 2.0-licensed open source software. `dbt` is what it is today because community members like you have opened issues, provided feedback, and contributed to the knowledge loop for the entire communtiy. Whether you are a seasoned open source contributor or a first-time committer, we welcome and encourage you to contribute code, documentation, ideas, or problem statements to this project.
-
-### Defining the problem
-
-If you have an idea for a new feature or if you've discovered a bug in `dbt`, the first step is to open an issue. Please check the list of [open issues](https://github.com/dbt-labs/dbt-core/issues) before creating a new one. If you find a relevant issue, please add a comment to the open issue instead of creating a new one. There are hundreds of open issues in this repository and it can be hard to know where to look for a relevant open issue. **The `dbt` maintainers are always happy to point contributors in the right direction**, so please err on the side of documenting your idea in a new issue if you are unsure where a problem statement belongs.
-
-> **Note:** All community-contributed Pull Requests _must_ be associated with an open issue. If you submit a Pull Request that does not pertain to an open issue, you will be asked to create an issue describing the problem before the Pull Request can be reviewed.
-
-### Discussing the idea
-
-After you open an issue, a `dbt` maintainer will follow up by commenting on your issue (usually within 1-3 days) to explore your idea further and advise on how to implement the suggested changes. In many cases, community members will chime in with their own thoughts on the problem statement. If you as the issue creator are interested in submitting a Pull Request to address the issue, you should indicate this in the body of the issue. The `dbt` maintainers are _always_ happy to help contributors with the implementation of fixes and features, so please also indicate if there's anything you're unsure about or could use guidance around in the issue.
-
-### Submitting a change
-
-If an issue is appropriately well scoped and describes a beneficial change to the `dbt` codebase, then anyone may submit a Pull Request to implement the functionality described in the issue. See the sections below on how to do this.
-
-The `dbt` maintainers will add a `good first issue` label if an issue is suitable for a first-time contributor. This label often means that the required code change is small, limited to one database adapter, or a net-new addition that does not impact existing functionality. You can see the list of currently open issues on the [Contribute](https://github.com/dbt-labs/dbt-core/contribute) page.
-
-Here's a good workflow:
-- Comment on the open issue, expressing your interest in contributing the required code change
-- Outline your planned implementation. If you want help getting started, ask!
-- Follow the steps outlined below to develop locally. Once you have opened a PR, one of the `dbt` maintainers will work with you to review your code.
-- Add a test! Tests are crucial for both fixes and new features alike. We want to make sure that code works as intended, and that it avoids any bugs  previously encountered. Currently, the best resource for understanding `dbt`'s [unit](test/unit) and [integration](test/integration) tests is the tests themselves. One of the maintainers can help by pointing out relevant examples.
-
-In some cases, the right resolution to an open issue might be tangential to the `dbt` codebase. The right path forward might be a documentation update or a change that can be made in user-space. In other cases, the issue might describe functionality that the `dbt` maintainers are unwilling or unable to incorporate into the `dbt` codebase. When it is determined that an open issue describes functionality that will not translate to a code change in the `dbt` repository, the issue will be tagged with the `wontfix` label (see below) and closed.
-
-### Using issue labels
-
-The `dbt` maintainers use labels to categorize open issues. Some labels indicate the databases impacted by the issue, while others describe the domain in the `dbt` codebase germane to the discussion. While most of these labels are self-explanatory (eg. `snowflake` or `bigquery`), there are others that are worth describing.
-
-| tag | description |
-| --- | ----------- |
-| [triage](https://github.com/dbt-labs/dbt-core/labels/triage) | This is a new issue which has not yet been reviewed by a `dbt` maintainer. This label is removed when a maintainer reviews and responds to the issue. |
-| [bug](https://github.com/dbt-labs/dbt-core/labels/bug) | This issue represents a defect or regression in `dbt` |
-| [enhancement](https://github.com/dbt-labs/dbt-core/labels/enhancement) | This issue represents net-new functionality in `dbt` |
-| [good first issue](https://github.com/dbt-labs/dbt-core/labels/good%20first%20issue) | This issue does not require deep knowledge of the `dbt` codebase to implement. This issue is appropriate for a first-time contributor. |
-| [help wanted](https://github.com/dbt-labs/dbt-core/labels/help%20wanted) / [discussion](https://github.com/dbt-labs/dbt-core/labels/discussion) | Conversation around this issue in ongoing, and there isn't yet a clear path forward. Input from community members is most welcome. |
-| [duplicate](https://github.com/dbt-labs/dbt-core/issues/duplicate) | This issue is functionally identical to another open issue. The `dbt` maintainers will close this issue and encourage community members to focus conversation on the other one. |
-| [snoozed](https://github.com/dbt-labs/dbt-core/labels/snoozed) | This issue describes a good idea, but one which will probably not be addressed in a six-month time horizon. The `dbt` maintainers will revist these issues periodically and re-prioritize them accordingly. |
-| [stale](https://github.com/dbt-labs/dbt-core/labels/stale) | This is an old issue which has not recently been updated. Stale issues will periodically be closed by `dbt` maintainers, but they can be re-opened if the discussion is restarted. |
-| [wontfix](https://github.com/dbt-labs/dbt-core/labels/wontfix) | This issue does not require a code change in the `dbt` repository, or the maintainers are unwilling/unable to merge a Pull Request which implements the behavior described in the issue. |
-
-#### Branching Strategy
-
-`dbt` has three types of branches:
-
-- **Trunks** are where active development of the next release takes place. There is one trunk named `develop` at the time of writing this, and will be the default branch of the repository.
-- **Release Branches** track a specific, not yet complete release of `dbt`. Each minor version release has a corresponding release branch. For example, the `0.11.x` series of releases has a branch called `0.11.latest`. This allows us to release new patch versions under `0.11` without necessarily needing to pull them into the latest version of `dbt`.
-- **Feature Branches** track individual features and fixes. On completion they should be merged into the trunk branch or a specific release branch.
+- **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`, ...). 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
 
 ### Installing git
 
-You will need `git` in order to download and modify the `dbt` source code. On macOS, the best way to download git is to just install [Xcode](https://developer.apple.com/support/xcode/).
+You will need `git` in order to download and modify the `dbt-core` source code. On macOS, the best way to download git is to just install [Xcode](https://developer.apple.com/support/xcode/).
 
 ### External contributors
 
-If you are not a member of the `dbt-labs` GitHub organization, you can contribute to `dbt` by forking the `dbt` repository. For a detailed overview on forking, check out the [GitHub docs on forking](https://help.github.com/en/articles/fork-a-repo). In short, you will need to:
+If you are not a member of the `dbt-labs` GitHub organization, you can contribute to `dbt-core` by forking the `dbt-core` repository. For a detailed overview on forking, check out the [GitHub docs on forking](https://help.github.com/en/articles/fork-a-repo). In short, you will need to:
 
-1. fork the `dbt` repository
-2. clone your fork locally
-3. check out a new branch for your proposed changes
-4. push changes to your fork
-5. open a pull request against `dbt-labs/dbt` from your forked repository
+1. Fork the `dbt-core` repository
+2. Clone your fork locally
+3. Check out a new branch for your proposed changes
+4. Push changes to your fork
+5. Open a pull request against `dbt-labs/dbt-core` from your forked repository
 
-### Core contributors
+### dbt Labs contributors
 
-If you are a member of the `dbt-labs` GitHub organization, you will have push access to the `dbt` repo. Rather than forking `dbt` to make your changes, just clone the repository, check out a new branch, and push directly to that branch.
+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
 
-There are some tools that will be helpful to you in developing locally. While this is the list relevant for `dbt` development, many of these tools are used commonly across open-source python projects.
+There are some tools that will be helpful to you in developing locally. While this is the list relevant for `dbt-core` development, many of these tools are used commonly across open-source python projects.
 
 ### Tools
 
-A short list of tools used in `dbt` testing that will be helpful to your understanding:
+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 3.6, Python 3.7, Python 3.8, and Python 3.9
-- [`pytest`](https://docs.pytest.org/en/latest/) to discover/run tests
-- [`make`](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) - but don't worry too much, nobody _really_ understands how make works and our Makefile is super simple
+- [`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
 - [`mypy`](https://mypy.readthedocs.io/en/stable/) for static type checking
-- [Github Actions](https://github.com/features/actions)
+- [`pre-commit`](https://pre-commit.com) to easily run those checks
+- [`changie`](https://changie.dev/) to create changelog entries, without merge conflicts
+- [`make`](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) to run multiple setup or test steps in combination. Don't worry too much, nobody _really_ understands how `make` works, and our Makefile aims to be super simple.
+- [GitHub Actions](https://github.com/features/actions) for automating tests and checks, once a PR is pushed to the `dbt-core` repository
 
-A deep understanding of these tools in not required to effectively contribute to `dbt`, but we recommend checking out the attached documentation if you're interested in learning more about them.
+A deep understanding of these tools in not required to effectively contribute to `dbt-core`, but we recommend checking out the attached documentation if you're interested in learning more about each one.
 
-#### virtual environments
+#### Virtual environments
 
-We strongly recommend using virtual environments when developing code in `dbt`. We recommend creating this virtualenv
-in the root of the `dbt` repository. To create a new virtualenv, run:
+We strongly recommend using virtual environments when developing code in `dbt-core`. We recommend creating this virtualenv
+in the root of the `dbt-core` repository. To create a new virtualenv, run:
 ```sh
 python3 -m venv env
 source env/bin/activate
@@ -122,12 +79,12 @@ source env/bin/activate
 
 This will create and activate a new Python virtual environment.
 
-#### docker and docker-compose
+#### Docker and `docker-compose`
 
-Docker and docker-compose are both used in testing. Specific instructions for you OS can be found [here](https://docs.docker.com/get-docker/).
+Docker and `docker-compose` are both used in testing. Specific instructions for you OS can be found [here](https://docs.docker.com/get-docker/).
 
 
-#### postgres (optional)
+#### Postgres (optional)
 
 For testing, and later in the examples in this document, you may want to have `psql` available so you can poke around in the database and see what happened. We recommend that you use [homebrew](https://brew.sh/) for that on macOS, and your package manager on Linux. You can install any version of the postgres client that you'd like. On macOS, with homebrew setup, you can run:
 
@@ -135,35 +92,41 @@ For testing, and later in the examples in this document, you may want to have `p
 brew install postgresql
 ```
 
-## Running `dbt` in development
+## Running `dbt-core` in development
 
 ### 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` (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 `dbt` is installed this way, any changes you make to the `dbt` source code will be reflected immediately in your next `dbt` run.
+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.
 
-### Running `dbt`
+### Running `dbt-core`
 
 With your virtualenv activated, the `dbt` script should point back to the source code you've cloned on your machine. You can verify this by running `which dbt`. This command should show you a path to an executable in your virtualenv.
 
-Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as necessary to connect to your target databases. It may be a good idea to add a new profile pointing to a local postgres instance, or a specific test sandbox within your data warehouse if appropriate.
+Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as necessary to connect to your target databases. It may be a good idea to add a new profile pointing to a local Postgres instance, or a specific test sandbox within your data warehouse if appropriate.
 
 ## Testing
 
-Getting the `dbt` integration tests set up in your local environment will be very helpful as you start to make changes to your local version of `dbt`. The section that follows outlines some helpful tips for setting up the test environment.
+Once you're able to manually test that your code change is working as expected, it's important to run existing automated tests, as well as adding some new ones. These tests will ensure that:
+- Your code changes do not unexpectedly break other established functionality
+- Your code changes can handle all known edge cases
+- The functionality you're adding will _keep_ working in the future
 
-Although `dbt` works with a number of different databases, you won't need to supply credentials for every one of these databases in your test environment. Instead you can test all dbt-core code changes with Python and Postgres.
+Although `dbt-core` works with a number of different databases, you won't need to supply credentials for every one of these databases in your test environment. Instead, you can test most `dbt-core` code changes with Python and Postgres.
 
 ### Initial setup
 
-We recommend starting with `dbt`'s Postgres tests. These tests cover most of the functionality in `dbt`, are the fastest to run, and are the easiest to set up. To run the Postgres integration tests, you'll have to do one extra step of setting up the test database:
+Postgres offers the easiest way to test most `dbt-core` functionality today. They are the fastest to run, and the easiest to set up. To run the Postgres integration tests, you'll have to do one extra step of setting up the test database:
 
 ```sh
 make setup-db
@@ -174,15 +137,6 @@ docker-compose up -d database
 PGHOST=localhost PGUSER=root PGPASSWORD=password PGDATABASE=postgres bash test/setup_db.sh
 ```
 
-`dbt` uses test credentials specified in a `test.env` file in the root of the repository for non-Postgres databases. This `test.env` file is git-ignored, but please be _extra_ careful to never check in credentials or other sensitive information when developing against `dbt`. To create your `test.env` file, copy the provided sample file, then supply your relevant credentials. This step is only required to use non-Postgres databases.
-
-```
-cp test.env.sample test.env
-$EDITOR test.env
-```
-
-> In general, it's most important to have successful unit and Postgres tests. Once you open a PR, `dbt` will automatically run integration tests for the other three core database adapters. Of course, if you are a BigQuery user, contributing a BigQuery-only feature, it's important to run BigQuery tests as well.
-
 ### Test commands
 
 There are a few methods for running tests locally.
@@ -198,38 +152,82 @@ make test
 # Runs postgres integration tests with py38 in "fail fast" mode.
 make integration
 ```
-> These make targets assume you have a recent version of [`tox`](https://tox.readthedocs.io/en/latest/) installed locally,
+> These make targets assume you have a local installation of a recent version of [`tox`](https://tox.readthedocs.io/en/latest/) for unit/integration testing and pre-commit for code quality checks,
 > unless you use choose a Docker container to run tests. Run `make help` for more info.
 
 Check out the other targets in the Makefile to see other commonly used test
 suites.
 
+#### `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 (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 3.6, Python 3.7, Python 3.8, `flake8` checks, and `mypy` checks in
-parallel with `tox -p`. Also, you can run unit tests for specific python versions
-with `tox -e py36`. The configuration for these tests in located in `tox.ini`.
+[`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`
 
-Finally, you can also run a specific test or group of tests using [`pytest`](https://docs.pytest.org/en/latest/) directly. With a virtualenv
-active and dev dependencies installed you can do things like:
+Finally, you can also run a specific test or group of tests using [`pytest`](https://docs.pytest.org/en/latest/) directly. With a virtualenv active and dev dependencies installed you can do things like:
+
 ```sh
-# run specific postgres integration tests
-python -m pytest -m profile_postgres test/integration/001_simple_copy_test
 # run all unit tests in a file
-python -m pytest test/unit/test_graph.py
+python3 -m pytest test/unit/test_graph.py
 # run a specific unit test
-python -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
+python3 -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
+# run specific Postgres integration tests (old way)
+python3 -m pytest -m profile_postgres test/integration/074_postgres_unlogged_table_tests
+# run specific Postgres integration tests (new way)
+python3 -m pytest tests/functional/sources
 ```
-> [Here](https://docs.pytest.org/en/reorganize-docs/new-docs/user/commandlineuseful.html)
-> is a list of useful command-line options for `pytest` to use while developing.
+
+> See [pytest usage docs](https://docs.pytest.org/en/6.2.x/usage.html) for an overview of useful command-line options.
+
+### 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 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
 
-dbt Labs provides a CI environment to test changes to specific adapters, and periodic maintenance checks of `dbt-core` through Github Actions. For example, if you submit a pull request to the `dbt-redshift` repo, GitHub will trigger automated code checks and tests against Redshift.
+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.
 
-A `dbt` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
+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` maintainer will merge your changes into the active development branch. And that's it! Happy developing :tada:
+Once all tests are passing and your PR has been approved, a `dbt-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

@@ -1,4 +1,9 @@
-FROM ubuntu:20.04
+##
+#  This dockerfile is used for local development and adapter testing only.
+#  See `/docker` for a generic and production-ready docker file
+##
+
+FROM ubuntu:22.04
 
 ENV DEBIAN_FRONTEND noninteractive
 
@@ -41,6 +46,12 @@ RUN apt-get update \
     python3.9 \
     python3.9-dev \
     python3.9-venv \
+    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

@@ -6,47 +6,84 @@ 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 for static type checking.
-	$(DOCKER_CMD) tox -e mypy
+mypy: .env ## Runs mypy against staged changes for static type checking.
+	@\
+	$(DOCKER_CMD) pre-commit run --hook-stage manual mypy-check | grep -v "INFO"
 
 .PHONY: flake8
-flake8: .env ## Runs flake8 to enforce style guide.
-	$(DOCKER_CMD) tox -e flake8
+flake8: .env ## Runs flake8 against staged changes to enforce style guide.
+	@\
+	$(DOCKER_CMD) pre-commit run --hook-stage manual flake8-check | grep -v "INFO"
+
+.PHONY: black
+black: .env ## Runs black  against staged changes to enforce style guide.
+	@\
+	$(DOCKER_CMD) pre-commit run --hook-stage manual black-check -v | grep -v "INFO"
 
 .PHONY: lint
-lint: .env ## Runs all code checks in parallel.
-	$(DOCKER_CMD) tox -p -e flake8,mypy
+lint: .env ## Runs flake8 and mypy code checks against staged changes.
+	@\
+	$(DOCKER_CMD) pre-commit run flake8-check --hook-stage manual | grep -v "INFO"; \
+	$(DOCKER_CMD) pre-commit run mypy-check --hook-stage manual | grep -v "INFO"
 
 .PHONY: unit
-unit: .env ## Runs unit tests with py38.
-	$(DOCKER_CMD) tox -e py38
+unit: .env ## Runs unit tests with py
+	@\
+	$(DOCKER_CMD) tox -e py
 
 .PHONY: test
-test: .env ## Runs unit tests with py38 and code checks in parallel.
-	$(DOCKER_CMD) tox -p -e py38,flake8,mypy
+test: .env ## Runs unit tests with py and code checks against staged changes.
+	@\
+	$(DOCKER_CMD) tox -e py; \
+	$(DOCKER_CMD) pre-commit run black-check --hook-stage manual | grep -v "INFO"; \
+	$(DOCKER_CMD) pre-commit run flake8-check --hook-stage manual | grep -v "INFO"; \
+	$(DOCKER_CMD) pre-commit run mypy-check --hook-stage manual | grep -v "INFO"
 
 .PHONY: integration
-integration: .env integration-postgres ## Alias for integration-postgres.
+integration: .env ## Runs postgres integration tests with py-integration
+	@\
+	$(if $(USE_CI_FLAGS), $(CI_FLAGS)) $(DOCKER_CMD) tox -e py-integration -- -nauto
 
 .PHONY: integration-fail-fast
-integration-fail-fast: .env integration-postgres-fail-fast ## Alias for integration-postgres-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: integration-postgres
-integration-postgres: .env ## Runs postgres integration tests with py38.
-	$(DOCKER_CMD) tox -e py38-postgres -- -nauto
-
-.PHONY: integration-postgres-fail-fast
-integration-postgres-fail-fast: .env ## Runs postgres integration tests with py38 in "fail fast" mode.
-	$(DOCKER_CMD) tox -e py38-postgres -- -x -nauto
+.PHONY: 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.
-	docker-compose up -d database
+	@\
+	docker-compose up -d database && \
 	PGHOST=localhost PGUSER=root PGPASSWORD=password PGDATABASE=postgres bash test/setup_db.sh
 
 # This rule creates a file named .env that is used by docker-compose for passing
@@ -62,27 +99,30 @@ endif
 
 .PHONY: clean
 clean: ## Resets development environment.
-	rm -f .coverage
-	rm -rf .eggs/
-	rm -f .env
-	rm -rf .tox/
-	rm -rf build/
-	rm -rf dbt.egg-info/
-	rm -f dbt_project.yml
-	rm -rf dist/
-	rm -f htmlcov/*.{css,html,js,json,png}
-	rm -rf logs/
-	rm -rf target/
-	find . -type f -name '*.pyc' -delete
-	find . -type d -name '__pycache__' -depth -delete
+	@echo 'cleaning repo...'
+	@rm -f .coverage
+	@rm -f .coverage.*
+	@rm -rf .eggs/
+	@rm -f .env
+	@rm -rf .tox/
+	@rm -rf build/
+	@rm -rf dbt.egg-info/
+	@rm -f dbt_project.yml
+	@rm -rf dist/
+	@rm -f htmlcov/*.{css,html,js,json,png}
+	@rm -rf logs/
+	@rm -rf target/
+	@find . -type f -name '*.pyc' -delete
+	@find . -type d -name '__pycache__' -depth -delete
+	@echo 'done.'
+
 
 .PHONY: help
 help: ## Show this help message.
 	@echo 'usage: make [target] [USE_DOCKER=true]'
 	@echo
 	@echo 'targets:'
-	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
+	@grep -E '^[8+a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
 	@echo
 	@echo 'options:'
 	@echo 'use USE_DOCKER=true to run target in a docker container'
-

README.md

@@ -3,16 +3,13 @@
 </p>
 <p align="center">
   <a href="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml">
-    <img src="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml/badge.svg?event=push" alt="Unit Tests Badge"/>
-  </a>
-  <a href="https://github.com/dbt-labs/dbt-core/actions/workflows/integration.yml">
-    <img src="https://github.com/dbt-labs/dbt-core/actions/workflows/integration.yml/badge.svg?event=push" alt="Integration Tests Badge"/>
+    <img src="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml/badge.svg?event=push" alt="CI Badge"/>
   </a>
 </p>
 
 **[dbt](https://www.getdbt.com/)** enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.
 
-![architecture](https://raw.githubusercontent.com/dbt-labs/dbt-core/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-arch.png)
+![architecture](https://github.com/dbt-labs/dbt-core/blob/202cb7e51e218c7b29eb3b11ad058bd56b7739de/etc/dbt-transform.png)
 
 ## Understanding dbt
 

core/MANIFEST.in

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

core/README.md

@@ -0,0 +1,39 @@
+<p align="center">
+  <img src="https://raw.githubusercontent.com/dbt-labs/dbt-core/fa1ea14ddfb1d5ae319d5141844910dd53ab2834/etc/dbt-core.svg" alt="dbt logo" width="750"/>
+</p>
+<p align="center">
+  <a href="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml">
+    <img src="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml/badge.svg?event=push" alt="CI Badge"/>
+  </a>
+</p>
+
+**[dbt](https://www.getdbt.com/)** enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.
+
+![architecture](https://raw.githubusercontent.com/dbt-labs/dbt-core/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-arch.png)
+
+## Understanding dbt
+
+Analysts using dbt can transform their data by simply writing select statements, while dbt handles turning these statements into tables and views in a data warehouse.
+
+These select statements, or "models", form a dbt project. Models frequently build on top of one another – dbt makes it easy to [manage relationships](https://docs.getdbt.com/docs/ref) between models, and [visualize these relationships](https://docs.getdbt.com/docs/documentation), as well as assure the quality of your transformations through [testing](https://docs.getdbt.com/docs/testing).
+
+![dbt dag](https://raw.githubusercontent.com/dbt-labs/dbt-core/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-dag.png)
+
+## Getting started
+
+- [Install dbt](https://docs.getdbt.com/docs/installation)
+- Read the [introduction](https://docs.getdbt.com/docs/introduction/) and [viewpoint](https://docs.getdbt.com/docs/about/viewpoint/)
+
+## Join the dbt Community
+
+- Be part of the conversation in the [dbt Community Slack](http://community.getdbt.com/)
+- Read more on the [dbt Community Discourse](https://discourse.getdbt.com)
+
+## Reporting bugs and contributing code
+
+- Want to report a bug or request a feature? Let us know on [Slack](http://community.getdbt.com/), or open [an issue](https://github.com/dbt-labs/dbt-core/issues/new)
+- Want to help us build dbt? Check out the [Contributing Guide](https://github.com/dbt-labs/dbt-core/blob/HEAD/CONTRIBUTING.md)
+
+## Code of Conduct
+
+Everyone interacting in the dbt project's codebases, issue trackers, chat rooms, and mailing lists is expected to follow the [dbt Code of Conduct](https://community.getdbt.com/code-of-conduct).

core/dbt/README.md

@@ -0,0 +1,60 @@
+# core/dbt directory README
+
+## The following are individual files in this directory.
+
+### 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
+* adapters
+* cli
+* clients
+* config
+* context
+* contracts
+* deps
+* docs
+* events
+* graph
+* include
+* parser
+* task
+* tests

core/dbt/__init__.py

@@ -0,0 +1,7 @@
+# N.B.
+# This will add to the package’s __path__ all subdirectories of directories on sys.path named after the package which effectively combines both modules into a single namespace (dbt.adapters)
+# The matching statement is in plugins/postgres/dbt/__init__.py
+
+from pkgutil import extend_path
+
+__path__ = extend_path(__path__, __name__)

core/dbt/adapters/README.md

@@ -0,0 +1,30 @@
+# Adapters README
+
+The Adapters module is responsible for defining database connection methods, caching information from databases, how relations are defined, and the two major connection types we have - base and sql.
+
+# Directories
+
+## `base`
+
+Defines the base implementation Adapters can use to build out full functionality.
+
+## `sql`
+
+Defines a sql implementation for adapters that initially inherits the above base implementation and  comes with some premade methods and macros that can be overwritten as needed per adapter. (most common type of adapter.)
+
+# Files
+
+## `cache.py`
+
+Cached information from the database.
+
+## `factory.py`
+Defines how we generate adapter objects
+
+## `protocol.py`
+
+Defines various interfaces for various adapter objects. Helps mypy correctly resolve methods.
+
+## `reference_keys.py`
+
+Configures naming scheme for cache elements to be universal.

core/dbt/adapters/__init__.py

@@ -0,0 +1,7 @@
+# N.B.
+# This will add to the package’s __path__ all subdirectories of directories on sys.path named after the package which effectively combines both modules into a single namespace (dbt.adapters)
+# The matching statement is in plugins/postgres/dbt/adapters/__init__.py
+
+from pkgutil import extend_path
+
+__path__ = extend_path(__path__, __name__)

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

@@ -2,16 +2,17 @@ from dataclasses import dataclass
 import re
 from typing import Dict, ClassVar, Any, Optional
 
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 @dataclass
 class Column:
     TYPE_LABELS: ClassVar[Dict[str, str]] = {
-        'STRING': 'TEXT',
-        'TIMESTAMP': 'TIMESTAMP',
-        'FLOAT': 'FLOAT',
-        'INTEGER': 'INT'
+        "STRING": "TEXT",
+        "TIMESTAMP": "TIMESTAMP",
+        "FLOAT": "FLOAT",
+        "INTEGER": "INT",
+        "BOOLEAN": "BOOLEAN",
     }
     column: str
     dtype: str
@@ -24,7 +25,7 @@ class Column:
         return cls.TYPE_LABELS.get(dtype.upper(), dtype)
 
     @classmethod
-    def create(cls, name, label_or_dtype: str) -> 'Column':
+    def create(cls, name, label_or_dtype: str) -> "Column":
         column_type = cls.translate_type(label_or_dtype)
         return cls(name, column_type)
 
@@ -39,16 +40,14 @@ class Column:
     @property
     def data_type(self) -> str:
         if self.is_string():
-            return Column.string_type(self.string_size())
+            return self.string_type(self.string_size())
         elif self.is_numeric():
-            return Column.numeric_type(self.dtype, self.numeric_precision,
-                                       self.numeric_scale)
+            return self.numeric_type(self.dtype, self.numeric_precision, self.numeric_scale)
         else:
             return self.dtype
 
     def is_string(self) -> bool:
-        return self.dtype.lower() in ['text', 'character varying', 'character',
-                                      'varchar']
+        return self.dtype.lower() in ["text", "character varying", "character", "varchar"]
 
     def is_number(self):
         return any([self.is_integer(), self.is_numeric(), self.is_float()])
@@ -56,33 +55,45 @@ class Column:
     def is_float(self):
         return self.dtype.lower() in [
             # floats
-            'real', 'float4', 'float', 'double precision', 'float8'
+            "real",
+            "float4",
+            "float",
+            "double precision",
+            "float8",
         ]
 
     def is_integer(self) -> bool:
         return self.dtype.lower() in [
             # real types
-            'smallint', 'integer', 'bigint',
-            'smallserial', 'serial', 'bigserial',
+            "smallint",
+            "integer",
+            "bigint",
+            "smallserial",
+            "serial",
+            "bigserial",
             # aliases
-            'int2', 'int4', 'int8',
-            'serial2', 'serial4', 'serial8',
+            "int2",
+            "int4",
+            "int8",
+            "serial2",
+            "serial4",
+            "serial8",
         ]
 
     def is_numeric(self) -> bool:
-        return self.dtype.lower() in ['numeric', 'decimal']
+        return self.dtype.lower() in ["numeric", "decimal"]
 
     def string_size(self) -> int:
         if not self.is_string():
-            raise RuntimeException("Called string_size() on non-string field!")
+            raise DbtRuntimeError("Called string_size() on non-string field!")
 
-        if self.dtype == 'text' or self.char_size is None:
+        if self.dtype == "text" or self.char_size is None:
             # char_size should never be None. Handle it reasonably just in case
             return 256
         else:
             return int(self.char_size)
 
-    def can_expand_to(self, other_column: 'Column') -> bool:
+    def can_expand_to(self, other_column: "Column") -> bool:
         """returns True if this column can be expanded to the size of the
         other column"""
         if not self.is_string() or not other_column.is_string():
@@ -110,12 +121,10 @@ class Column:
         return "<Column {} ({})>".format(self.name, self.data_type)
 
     @classmethod
-    def from_description(cls, name: str, raw_data_type: str) -> 'Column':
-        match = re.match(r'([^(]+)(\([^)]+\))?', raw_data_type)
+    def from_description(cls, name: str, raw_data_type: str) -> "Column":
+        match = re.match(r"([^(]+)(\([^)]+\))?", raw_data_type)
         if match is None:
-            raise RuntimeException(
-                f'Could not interpret data type "{raw_data_type}"'
-            )
+            raise DbtRuntimeError(f'Could not interpret data type "{raw_data_type}"')
         data_type, size_info = match.groups()
         char_size = None
         numeric_precision = None
@@ -123,12 +132,12 @@ class Column:
         if size_info is not None:
             # strip out the parentheses
             size_info = size_info[1:-1]
-            parts = size_info.split(',')
+            parts = size_info.split(",")
             if len(parts) == 1:
                 try:
                     char_size = int(parts[0])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[0]}" to an integer'
                     )
@@ -136,18 +145,16 @@ 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'
                     )
 
-        return cls(
-            name, data_type, char_size, numeric_precision, numeric_scale
-        )
+        return cls(name, data_type, char_size, numeric_precision, numeric_scale)

core/dbt/adapters/base/connections.py

@@ -1,25 +1,59 @@
 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
 from threading import get_ident
 from typing import (
-    Dict, Tuple, Hashable, Optional, ContextManager, List, Union
+    Any,
+    Dict,
+    Tuple,
+    Hashable,
+    Optional,
+    ContextManager,
+    List,
+    Type,
+    Union,
+    Iterable,
+    Callable,
 )
 
 import agate
 
 import dbt.exceptions
 from dbt.contracts.connection import (
-    Connection, Identifier, ConnectionState,
-    AdapterRequiredConfig, LazyHandle, AdapterResponse
+    Connection,
+    Identifier,
+    ConnectionState,
+    AdapterRequiredConfig,
+    LazyHandle,
+    AdapterResponse,
 )
 from dbt.contracts.graph.manifest import Manifest
 from dbt.adapters.base.query_headers import (
     MacroQueryStringSetter,
 )
-from dbt.logger import GLOBAL_LOGGER as logger
+from dbt.events import AdapterLogger
+from dbt.events.functions import fire_event
+from dbt.events.types import (
+    NewConnection,
+    ConnectionReused,
+    ConnectionLeftOpenInCleanup,
+    ConnectionLeftOpen,
+    ConnectionClosedInCleanup,
+    ConnectionClosed,
+    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.
 
 
 class BaseConnectionManager(metaclass=abc.ABCMeta):
@@ -35,6 +69,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     You must also set the 'TYPE' class attribute with a class-unique constant
     string.
     """
+
     TYPE: str = NotImplemented
 
     def __init__(self, profile: AdapterRequiredConfig):
@@ -56,16 +91,14 @@ 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(
-                'In set_thread_connection, existing connection exists for {}'
+            raise dbt.exceptions.DbtInternalError(
+                "In set_thread_connection, existing connection exists for {}"
             )
         self.thread_connections[key] = conn
 
@@ -104,60 +137,148 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :return: A context manager that handles exceptions raised by the
             underlying database.
         """
-        raise dbt.exceptions.NotImplementedException(
-            '`exception_handler` is not implemented for this adapter!')
+        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
+                credentials=self.profile.credentials,
             )
-            self.set_thread_connection(conn)
-
-        if conn.name == conn_name and conn.state == 'open':
-            return conn
-
-        logger.debug(
-            'Acquiring new {} connection "{}".'.format(self.TYPE, conn_name))
-
-        if conn.state == 'open':
-            logger.debug(
-                'Re-using an available connection from the pool (formerly {}).'
-                .format(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
+    def retry_connection(
+        cls,
+        connection: Connection,
+        connect: Callable[[], AdapterHandle],
+        logger: AdapterLogger,
+        retryable_exceptions: Iterable[Type[Exception]],
+        retry_limit: int = 1,
+        retry_timeout: Union[Callable[[int], SleepTime], SleepTime] = 1,
+        _attempts: int = 0,
+    ) -> Connection:
+        """Given a Connection, set its handle by calling connect.
+
+        The calls to connect will be retried up to retry_limit times to deal with transient
+        connection errors. By default, one retry will be attempted if retryable_exceptions is set.
+
+        :param Connection connection: An instance of a Connection that needs a handle to be set,
+            usually when attempting to open it.
+        :param connect: A callable that returns the appropiate connection handle for a
+            given adapter. This callable will be retried retry_limit times if a subclass of any
+            Exception in retryable_exceptions is raised by connect.
+        :type connect: Callable[[], AdapterHandle]
+        :param AdapterLogger logger: A logger to emit messages on retry attempts or errors. When
+            handling expected errors, we call debug, and call warning on unexpected errors or when
+            all retry attempts have been exhausted.
+        :param retryable_exceptions: An iterable of exception classes that if raised by
+            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 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
+            or float to be passed to time.sleep.
+        :type retry_timeout: Union[Callable[[int], SleepTime], SleepTime] = 1
+        :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.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.FailedToConnectError(
+                "retry_timeout cannot be negative or return a negative time."
+            )
+
+        if retry_limit < 0 or retry_limit > sys.getrecursionlimit():
+            # 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.FailedToConnectError("retry_limit cannot be negative")
+
+        try:
+            connection.handle = connect()
+            connection.state = ConnectionState.OPEN
+            return connection
+
+        except tuple(retryable_exceptions) as e:
+            if retry_limit <= 0:
+                connection.handle = None
+                connection.state = ConnectionState.FAIL
+                raise dbt.exceptions.FailedToConnectError(str(e))
+
+            logger.debug(
+                f"Got a retryable error when attempting to open a {cls.TYPE} connection.\n"
+                f"{retry_limit} attempts remaining. Retrying in {timeout} seconds.\n"
+                f"Error:\n{e}"
+            )
+
+            sleep(timeout)
+            return cls.retry_connection(
+                connection=connection,
+                connect=connect,
+                logger=logger,
+                retry_limit=retry_limit - 1,
+                retry_timeout=retry_timeout,
+                retryable_exceptions=retryable_exceptions,
+                _attempts=_attempts + 1,
+            )
+
+        except Exception as e:
+            connection.handle = None
+            connection.state = ConnectionState.FAIL
+            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(
-            '`cancel_open` is not implemented for this adapter!'
+        raise dbt.exceptions.NotImplementedError(
+            "`cancel_open` is not implemented for this adapter!"
         )
 
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def open(cls, connection: Connection) -> Connection:
         """Open the given connection on the adapter and return it.
 
@@ -167,9 +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:
@@ -189,12 +308,10 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     def cleanup_all(self) -> None:
         with self.lock:
             for connection in self.thread_connections.values():
-                if connection.state not in {'closed', 'init'}:
-                    logger.debug("Connection '{}' was left open."
-                                 .format(connection.name))
+                if connection.state not in {"closed", "init"}:
+                    fire_event(ConnectionLeftOpenInCleanup(conn_name=cast_to_str(connection.name)))
                 else:
-                    logger.debug("Connection '{}' was properly closed."
-                                 .format(connection.name))
+                    fire_event(ConnectionClosedInCleanup(conn_name=cast_to_str(connection.name)))
                 self.close(connection)
 
             # garbage collect these connections
@@ -203,16 +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:
@@ -220,31 +333,40 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         try:
             connection.handle.rollback()
         except Exception:
-            logger.debug(
-                'Failed to rollback {}'.format(connection.name),
-                exc_info=True
+            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'):
-            logger.debug(f'On {connection.name}: Close')
+        if hasattr(connection.handle, "close"):
+            fire_event(
+                ConnectionClosed(conn_name=cast_to_str(connection.name), node_info=get_node_info())
+            )
             connection.handle.close()
         else:
-            logger.debug(f'On {connection.name}: No close available on handle')
+            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(
-                f'Tried to rollback transaction on connection '
+            raise dbt.exceptions.DbtInternalError(
+                f"Tried to rollback transaction on connection "
                 f'"{connection.name}", but it does not have one open!'
             )
 
-        logger.debug(f'On {connection.name}: ROLLBACK')
+        fire_event(Rollback(conn_name=cast_to_str(connection.name), node_info=get_node_info()))
         cls._rollback_handle(connection)
 
         connection.transaction_open = False
@@ -256,7 +378,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             return connection
 
         if connection.transaction_open and connection.handle:
-            logger.debug('On {}: ROLLBACK'.format(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
 
@@ -279,16 +401,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     @abc.abstractmethod
     def execute(
         self, sql: str, auto_begin: bool = False, fetch: bool = False
-    ) -> Tuple[Union[str, AdapterResponse], agate.Table]:
+    ) -> Tuple[AdapterResponse, agate.Table]:
         """Execute the given SQL.
 
         :param str sql: The sql to execute.
         :param bool auto_begin: If set, and dbt is not currently inside a
             transaction, automatically begin one.
         :param bool fetch: If set, fetch results.
-        :return: A tuple of the status and the results (empty if fetch=False).
-        :rtype: Tuple[Union[str, AdapterResponse], agate.Table]
+        :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/meta.py

@@ -30,9 +30,11 @@ class _Available:
             x.update(big_expensive_db_query())
             return x
         """
+
         def inner(func):
             func._parse_replacement_ = parse_replacement
             return self(func)
+
         return inner
 
     def deprecated(
@@ -57,13 +59,14 @@ class _Available:
         The optional parse_replacement, if provided, will provide a parse-time
         replacement for the actual method (see `available.parse`).
         """
+
         def wrapper(func):
             func_name = func.__name__
             renamed_method(func_name, supported_name)
 
             @wraps(func)
             def inner(*args, **kwargs):
-                warn('adapter:{}'.format(func_name))
+                warn("adapter:{}".format(func_name))
                 return func(*args, **kwargs)
 
             if parse_replacement:
@@ -71,6 +74,7 @@ class _Available:
             else:
                 available_function = self
             return available_function(inner)
+
         return wrapper
 
     def parse_none(self, func: Callable) -> Callable:
@@ -95,9 +99,7 @@ class AdapterMeta(abc.ABCMeta):
         # I'm not sure there is any benefit to it after poking around a bit,
         # but having it doesn't hurt on the python side (and omitting it could
         # hurt for obscure metaclass reasons, for all I know)
-        cls = abc.ABCMeta.__new__(  # type: ignore
-            mcls, name, bases, namespace, **kwargs
-        )
+        cls = abc.ABCMeta.__new__(mcls, name, bases, namespace, **kwargs)  # type: ignore
 
         # this is very much inspired by ABCMeta's own implementation
 
@@ -109,14 +111,14 @@ class AdapterMeta(abc.ABCMeta):
 
         # collect base class data first
         for base in bases:
-            available.update(getattr(base, '_available_', set()))
-            replacements.update(getattr(base, '_parse_replacements_', set()))
+            available.update(getattr(base, "_available_", set()))
+            replacements.update(getattr(base, "_parse_replacements_", set()))
 
         # override with local data if it exists
         for name, value in namespace.items():
-            if getattr(value, '_is_available_', False):
+            if getattr(value, "_is_available_", False):
                 available.add(name)
-            parse_replacement = getattr(value, '_parse_replacement_', None)
+            parse_replacement = getattr(value, "_parse_replacement_", None)
             if parse_replacement is not None:
                 replacements[name] = parse_replacement
 

core/dbt/adapters/base/plugin.py

@@ -1,18 +1,17 @@
 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
 
 
 def project_name_from_path(include_path: str) -> str:
     # avoid an import cycle
     from dbt.config.project import Project
+
     partial = Project.partial_load(include_path)
     if partial.project_name is None:
-        raise CompilationException(
-            f'Invalid project at {include_path}: name not set!'
-        )
+        raise CompilationError(f"Invalid project at {include_path}: name not set!")
     return partial.project_name
 
 
@@ -23,12 +22,13 @@ class AdapterPlugin:
     :param dependencies: A list of adapter names that this adapter depends
         upon.
     """
+
     def __init__(
         self,
         adapter: Type[AdapterProtocol],
         credentials: Type[Credentials],
         include_path: str,
-        dependencies: Optional[List[str]] = None
+        dependencies: Optional[List[str]] = None,
     ):
 
         self.adapter: Type[AdapterProtocol] = adapter

core/dbt/adapters/base/query_headers.py

@@ -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:
@@ -15,7 +15,7 @@ class NodeWrapper:
         self._inner_node = node
 
     def __getattr__(self, name):
-        return getattr(self._inner_node, name, '')
+        return getattr(self._inner_node, name, "")
 
 
 class _QueryComment(local):
@@ -24,6 +24,7 @@ class _QueryComment(local):
         - the current thread's query comment.
         - a source_name indicating what set the current thread's query comment
     """
+
     def __init__(self, initial):
         self.query_comment: Optional[str] = initial
         self.append = False
@@ -35,21 +36,19 @@ class _QueryComment(local):
         if self.append:
             # replace last ';' with '<comment>;'
             sql = sql.rstrip()
-            if sql[-1] == ';':
+            if sql[-1] == ";":
                 sql = sql[:-1]
-                return '{}\n/* {} */;'.format(sql, self.query_comment.strip())
+                return "{}\n/* {} */;".format(sql, self.query_comment.strip())
 
-            return '{}\n/* {} */'.format(sql, self.query_comment.strip())
+            return "{}\n/* {} */".format(sql, self.query_comment.strip())
 
-        return '/* {} */\n{}'.format(self.query_comment.strip(), sql)
+        return "/* {} */\n{}".format(self.query_comment.strip(), sql)
 
     def set(self, comment: Optional[str], append: bool):
-        if isinstance(comment, str) and '*/' in comment:
+        if isinstance(comment, str) and "*/" in comment:
             # tell the user "no" so they don't hurt themselves by writing
             # garbage
-            raise RuntimeException(
-                f'query comment contains illegal value "*/": {comment}'
-            )
+            raise DbtRuntimeError(f'query comment contains illegal value "*/": {comment}')
         self.query_comment = comment
         self.append = append
 
@@ -63,15 +62,17 @@ class MacroQueryStringSetter:
         self.config = config
 
         comment_macro = self._get_comment_macro()
-        self.generator: QueryStringFunc = lambda name, model: ''
+        self.generator: QueryStringFunc = lambda name, model: ""
         # if the comment value was None or the empty string, just skip it
         if comment_macro:
             assert isinstance(comment_macro, str)
-            macro = '\n'.join((
-                '{%- macro query_comment_macro(connection_name, node) -%}',
-                comment_macro,
-                '{% endmacro %}'
-            ))
+            macro = "\n".join(
+                (
+                    "{%- macro query_comment_macro(connection_name, node) -%}",
+                    comment_macro,
+                    "{% endmacro %}",
+                )
+            )
             ctx = self._get_context()
             self.generator = QueryStringGenerator(macro, ctx)
         self.comment = _QueryComment(None)
@@ -87,9 +88,9 @@ class MacroQueryStringSetter:
         return self.comment.add(sql)
 
     def reset(self):
-        self.set('master', None)
+        self.set("master", None)
 
-    def set(self, name: str, node: Optional[CompileResultNode]):
+    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

@@ -1,22 +1,28 @@
 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, HasQuoting, FakeAPIObject, Policy, Path
+    RelationType,
+    ComponentName,
+    HasQuoting,
+    FakeAPIObject,
+    Policy,
+    Path,
+)
+from dbt.exceptions import (
+    ApproximateMatchError,
+    DbtInternalError,
+    MultipleDatabasesNotAllowedError,
 )
-from dbt.exceptions import InternalException
 from dbt.node_types import NodeType
 from dbt.utils import filter_null_values, deep_merge, classproperty
 
 import dbt.exceptions
 
 
-Self = TypeVar('Self', bound='BaseRelation')
+Self = TypeVar("Self", bound="BaseRelation")
 
 
 @dataclass(frozen=True, eq=False, repr=False)
@@ -24,8 +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:
@@ -36,11 +44,11 @@ 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!')
+        raise ValueError(f"BaseRelation has no {field_name} field!")
 
     def __eq__(self, other):
         if not isinstance(other, self.__class__):
@@ -49,20 +57,18 @@ 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
         dbt_utils.
         """
-        if key == 'metadata':
-            return {
-                'type': self.__class__.__name__
-            }
+        if key == "metadata":
+            return {"type": self.__class__.__name__}
         return super().get(key, default)
 
     def matches(
@@ -71,16 +77,19 @@ class BaseRelation(FakeAPIObject, Hashable):
         schema: Optional[str] = None,
         identifier: Optional[str] = None,
     ) -> bool:
-        search = filter_null_values({
-            ComponentName.Database: database,
-            ComponentName.Schema: schema,
-            ComponentName.Identifier: identifier
-        })
+        search = filter_null_values(
+            {
+                ComponentName.Database: database,
+                ComponentName.Schema: schema,
+                ComponentName.Identifier: identifier,
+            }
+        )
 
         if not search:
             # nothing was passed in
-            raise dbt.exceptions.RuntimeException(
-                "Tried to match relation, but no search path was passed!")
+            raise dbt.exceptions.DbtRuntimeError(
+                "Tried to match relation, but no search path was passed!"
+            )
 
         exact_match = True
         approximate_match = True
@@ -88,15 +97,14 @@ class BaseRelation(FakeAPIObject, Hashable):
         for k, v in search.items():
             if not self._is_exactish_match(k, v):
                 exact_match = False
-
-            if self.path.get_lowered_part(k) != v.lower():
-                approximate_match = False
+            if str(self.path.get_lowered_part(k)).strip(self.quote_character) != v.lower().strip(
+                self.quote_character
+            ):
+                approximate_match = False  # type: ignore[union-attr]
 
         if approximate_match and not exact_match:
-            target = self.create(
-                database=database, schema=schema, identifier=identifier
-            )
-            dbt.exceptions.approximate_relation_match(target, self)
+            target = self.create(database=database, schema=schema, identifier=identifier)
+            raise ApproximateMatchError(target, self)
 
         return exact_match
 
@@ -109,11 +117,13 @@ class BaseRelation(FakeAPIObject, Hashable):
         schema: Optional[bool] = None,
         identifier: Optional[bool] = None,
     ) -> Self:
-        policy = filter_null_values({
-            ComponentName.Database: database,
-            ComponentName.Schema: schema,
-            ComponentName.Identifier: identifier
-        })
+        policy = filter_null_values(
+            {
+                ComponentName.Database: database,
+                ComponentName.Schema: schema,
+                ComponentName.Identifier: identifier,
+            }
+        )
 
         new_quote_policy = self.quote_policy.replace_dict(policy)
         return self.replace(quote_policy=new_quote_policy)
@@ -124,16 +134,18 @@ class BaseRelation(FakeAPIObject, Hashable):
         schema: Optional[bool] = None,
         identifier: Optional[bool] = None,
     ) -> Self:
-        policy = filter_null_values({
-            ComponentName.Database: database,
-            ComponentName.Schema: schema,
-            ComponentName.Identifier: identifier
-        })
+        policy = filter_null_values(
+            {
+                ComponentName.Database: database,
+                ComponentName.Schema: schema,
+                ComponentName.Identifier: identifier,
+            }
+        )
 
         new_include_policy = self.include_policy.replace_dict(policy)
         return self.replace(include_policy=new_include_policy)
 
-    def information_schema(self, view_name=None) -> 'InformationSchema':
+    def information_schema(self, view_name=None) -> "InformationSchema":
         # some of our data comes from jinja, where things can be `Undefined`.
         if not isinstance(view_name, str):
             view_name = None
@@ -143,10 +155,10 @@ class BaseRelation(FakeAPIObject, Hashable):
         info_schema = InformationSchema.from_relation(self, view_name)
         return info_schema.incorporate(path={"schema": None})
 
-    def information_schema_only(self) -> 'InformationSchema':
+    def information_schema_only(self) -> "InformationSchema":
         return self.information_schema()
 
-    def without_identifier(self) -> 'BaseRelation':
+    def without_identifier(self) -> "BaseRelation":
         """Return a form of this relation that only has the database and schema
         set to included. To get the appropriately-quoted form the schema out of
         the result (for use as part of a query), use `.render()`. To get the
@@ -156,9 +168,7 @@ class BaseRelation(FakeAPIObject, Hashable):
         """
         return self.include(identifier=False).replace_path(identifier=None)
 
-    def _render_iterator(
-        self
-    ) -> Iterator[Tuple[Optional[ComponentName], Optional[str]]]:
+    def _render_iterator(self) -> Iterator[Tuple[Optional[ComponentName], Optional[str]]]:
 
         for key in ComponentName:
             path_part: Optional[str] = None
@@ -170,27 +180,22 @@ class BaseRelation(FakeAPIObject, Hashable):
 
     def render(self) -> str:
         # if there is nothing set, this will return the empty string.
-        return '.'.join(
-            part for _, part in self._render_iterator()
-            if part is not None
-        )
+        return ".".join(part for _, part in self._render_iterator() if part is not None)
 
     def quoted(self, identifier):
-        return '{quote_char}{identifier}{quote_char}'.format(
+        return "{quote_char}{identifier}{quote_char}".format(
             quote_char=self.quote_character,
             identifier=identifier,
         )
 
     @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)
+        source_quoting.pop("column", None)
         quote_policy = deep_merge(
             cls.get_default_quote_policy().to_dict(omit_none=True),
             source_quoting,
-            kwargs.get('quote_policy', {}),
+            kwargs.get("quote_policy", {}),
         )
 
         return cls.create(
@@ -198,18 +203,18 @@ class BaseRelation(FakeAPIObject, Hashable):
             schema=source.schema,
             identifier=source.identifier,
             quote_policy=quote_policy,
-            **kwargs
+            **kwargs,
         )
 
     @staticmethod
     def add_ephemeral_prefix(name: str):
-        return f'__dbt__cte__{name}'
+        return f"__dbt__cte__{name}"
 
     @classmethod
     def create_ephemeral_from_node(
         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:
@@ -236,27 +241,27 @@ class BaseRelation(FakeAPIObject, Hashable):
             schema=node.schema,
             identifier=node.alias,
             quote_policy=quote_policy,
-            **kwargs)
+            **kwargs,
+        )
 
     @classmethod
     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)
 
@@ -269,14 +274,16 @@ class BaseRelation(FakeAPIObject, Hashable):
         type: Optional[RelationType] = None,
         **kwargs,
     ) -> Self:
-        kwargs.update({
-            'path': {
-                'database': database,
-                'schema': schema,
-                'identifier': identifier,
-            },
-            'type': type,
-        })
+        kwargs.update(
+            {
+                "path": {
+                    "database": database,
+                    "schema": schema,
+                    "identifier": identifier,
+                },
+                "type": type,
+            }
+        )
         return cls.from_dict(kwargs)
 
     def __repr__(self) -> str:
@@ -342,7 +349,7 @@ class BaseRelation(FakeAPIObject, Hashable):
         return RelationType
 
 
-Info = TypeVar('Info', bound='InformationSchema')
+Info = TypeVar("Info", bound="InformationSchema")
 
 
 @dataclass(frozen=True, eq=False, repr=False)
@@ -351,18 +358,16 @@ class InformationSchema(BaseRelation):
 
     def __post_init__(self):
         if not isinstance(self.information_schema_view, (type(None), str)):
-            raise dbt.exceptions.CompilationException(
-                'Got an invalid name: {}'.format(self.information_schema_view)
+            raise dbt.exceptions.CompilationError(
+                "Got an invalid name: {}".format(self.information_schema_view)
             )
 
     @classmethod
-    def get_path(
-        cls, relation: BaseRelation, information_schema_view: Optional[str]
-    ) -> Path:
+    def get_path(cls, relation: BaseRelation, information_schema_view: Optional[str]) -> Path:
         return Path(
             database=relation.database,
             schema=relation.schema,
-            identifier='INFORMATION_SCHEMA',
+            identifier="INFORMATION_SCHEMA",
         )
 
     @classmethod
@@ -393,9 +398,7 @@ class InformationSchema(BaseRelation):
         relation: BaseRelation,
         information_schema_view: Optional[str],
     ) -> Info:
-        include_policy = cls.get_include_policy(
-            relation, information_schema_view
-        )
+        include_policy = cls.get_include_policy(relation, information_schema_view)
         quote_policy = cls.get_quote_policy(relation, information_schema_view)
         path = cls.get_path(relation, information_schema_view)
         return cls(
@@ -417,6 +420,7 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
     search for what schemas. The schema values are all lowercased to avoid
     duplication.
     """
+
     def add(self, relation: BaseRelation):
         key = relation.information_schema_only()
         if key not in self:
@@ -426,9 +430,7 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
             schema = relation.schema.lower()
         self[key].add(schema)
 
-    def search(
-        self
-    ) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
+    def search(self) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
         for information_schema_name, schemas in self.items():
             for schema in schemas:
                 yield information_schema_name, schema
@@ -440,17 +442,16 @@ 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
-            }
-            new.add(information_schema_name.incorporate(
-                path=path,
-                quote_policy={'database': False},
-                include_policy={'database': False},
-            ))
+            path = {"database": information_schema_name.database, "schema": schema}
+            new.add(
+                information_schema_name.incorporate(
+                    path=path,
+                    quote_policy={"database": False},
+                    include_policy={"database": False},
+                )
+            )
 
         return new

core/dbt/adapters/cache.py

@@ -1,23 +1,24 @@
-from collections import namedtuple
-from copy import deepcopy
-from typing import List, Iterable, Optional, Dict, Set, Tuple, Any
 import threading
+from copy import deepcopy
+from typing import Any, Dict, Iterable, List, Optional, Set, Tuple
 
-from dbt.logger import CACHE_LOGGER as logger
+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
-import dbt.exceptions
-
-_ReferenceKey = namedtuple('_ReferenceKey', 'database schema identifier')
-
-
-def _make_key(relation) -> _ReferenceKey:
-    """Make _ReferenceKeys with lowercase values for the cache so we don't have
-    to keep track of quoting
-    """
-    # databases and schemas can both be None
-    return _ReferenceKey(lowercase(relation.database),
-                         lowercase(relation.schema),
-                         lowercase(relation.identifier))
 
 
 def dot_separated(key: _ReferenceKey) -> str:
@@ -25,7 +26,7 @@ def dot_separated(key: _ReferenceKey) -> str:
 
     :param _ReferenceKey key: The key to stringify.
     """
-    return '.'.join(map(str, key))
+    return ".".join(map(str, key))
 
 
 class _CachedRelation:
@@ -37,14 +38,15 @@ class _CachedRelation:
         that refer to this relation.
     :attr BaseRelation inner: The underlying dbt relation.
     """
+
     def __init__(self, inner):
         self.referenced_by = {}
         self.inner = inner
 
     def __str__(self) -> str:
-        return (
-            '_CachedRelation(database={}, schema={}, identifier={}, inner={})'
-        ).format(self.database, self.schema, self.identifier, self.inner)
+        return ("_CachedRelation(database={}, schema={}, identifier={}, inner={})").format(
+            self.database, self.schema, self.identifier, self.inner
+        )
 
     @property
     def database(self) -> Optional[str]:
@@ -76,9 +78,9 @@ class _CachedRelation:
 
         :return _ReferenceKey: A key for this relation.
         """
-        return _make_key(self)
+        return _make_ref_key(self)
 
-    def add_reference(self, referrer: '_CachedRelation'):
+    def add_reference(self, referrer: "_CachedRelation"):
         """Add a reference from referrer to self, indicating that if this node
         were drop...cascaded, the referrer would be dropped as well.
 
@@ -122,9 +124,9 @@ class _CachedRelation:
         # table_name is ever anything but the identifier (via .create())
         self.inner = self.inner.incorporate(
             path={
-                'database': new_relation.inner.database,
-                'schema': new_relation.inner.schema,
-                'identifier': new_relation.inner.identifier
+                "database": new_relation.inner.database,
+                "schema": new_relation.inner.schema,
+                "identifier": new_relation.inner.identifier,
             },
         )
 
@@ -139,10 +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
@@ -157,12 +156,6 @@ class _CachedRelation:
         return [dot_separated(r) for r in self.referenced_by]
 
 
-def lazy_log(msg, func):
-    if logger.disabled:
-        return
-    logger.debug(msg.format(func()))
-
-
 class RelationsCache:
     """A cache of the relations known to dbt. Keeps track of relationships
     declared between tables and handles renames/drops as a real database would.
@@ -172,13 +165,16 @@ class RelationsCache:
         The adapters also hold this lock while filling the cache.
     :attr Set[str] schemas: The set of known/cached schemas, all lowercased.
     """
+
     def __init__(self) -> None:
         self.relations: Dict[_ReferenceKey, _CachedRelation] = {}
         self.lock = threading.RLock()
         self.schemas: Set[Tuple[Optional[str], Optional[str]]] = set()
 
     def add_schema(
-        self, database: Optional[str], schema: Optional[str],
+        self,
+        database: Optional[str],
+        schema: Optional[str],
     ) -> None:
         """Add a schema to the set of known schemas (case-insensitive)
 
@@ -188,7 +184,9 @@ class RelationsCache:
         self.schemas.add((lowercase(database), lowercase(schema)))
 
     def drop_schema(
-        self, database: Optional[str], schema: Optional[str],
+        self,
+        database: Optional[str],
+        schema: Optional[str],
     ) -> None:
         """Drop the given schema and remove it from the set of known schemas.
 
@@ -232,10 +230,7 @@ class RelationsCache:
         # self.relations or any cache entry's referenced_by during iteration
         # it's a runtime error!
         with self.lock:
-            return {
-                dot_separated(k): v.dump_graph_entry()
-                for k, v in self.relations.items()
-            }
+            return {dot_separated(k): v.dump_graph_entry() for k, v in self.relations.items()}
 
     def _setdefault(self, relation: _CachedRelation):
         """Add a relation to the cache, or return it if it already exists.
@@ -262,22 +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)
 
+    # 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.
@@ -292,33 +282,33 @@ class RelationsCache:
         :param BaseRelation dependent: The dependent model.
         :raises InternalError: If either entry does not exist.
         """
-        ref_key = _make_key(referenced)
+        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.
-            logger.debug(
-                '{dep!s} references {ref!s} but {ref.database}.{ref.schema} '
-                'is not in the cache, skipping assumed external relation'
-                .format(dep=dependent, ref=ref_key)
+            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.
-            referenced = referenced.replace(
-                type=referenced.External
-            )
+            referenced = referenced.replace(type=referenced.External)
             self.add(referenced)
-
-        dep_key = _make_key(dependent)
         if dep_key not in self.relations:
             # Insert a dummy "external" relation.
-            dependent = dependent.replace(
-                type=referenced.External
-            )
+            dependent = dependent.replace(type=referenced.External)
             self.add(dependent)
-        logger.debug(
-            'adding link, {!s} references {!s}'.format(dep_key, ref_key)
+        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)
@@ -330,14 +320,18 @@ class RelationsCache:
         :param BaseRelation relation: The underlying relation.
         """
         cached = _CachedRelation(relation)
-        logger.debug('Adding relation: {!s}'.format(cached))
-
-        lazy_log('before adding: {!s}', 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)
-
-        lazy_log('after adding: {!s}', 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
@@ -352,22 +346,6 @@ class RelationsCache:
         for cached in self.relations.values():
             cached.release_references(keys)
 
-    def _drop_cascade_relation(self, dropped):
-        """Drop the given relation and cascade it appropriately to all
-        dependent relations.
-
-        :param _CachedRelation dropped: An existing _CachedRelation to drop.
-        """
-        if dropped not in self.relations:
-            logger.debug('dropped a nonexistent relationship: {!s}'
-                         .format(dropped))
-            return
-        consequences = self.relations[dropped].collect_consequences()
-        logger.debug(
-            'drop {} is cascading to {}'.format(dropped, consequences)
-        )
-        self._remove_refs(consequences)
-
     def drop(self, relation):
         """Drop the named relation and cascade it appropriately to all
         dependent relations.
@@ -379,10 +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 = _make_key(relation)
-        logger.debug('Dropping relation: {!s}'.format(dropped))
+        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)
+            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.
@@ -398,15 +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):
-                logger.debug(
-                    'updated reference from {0} -> {2} to {1} -> {2}'
-                    .format(old_key, new_key, cached.key())
+                fire_event(
+                    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
@@ -429,15 +424,13 @@ 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:
-            logger.debug(
-                'old key {} not found in self.relations, assuming temporary'
-                .format(old_key)
+            fire_event(
+                CacheAction(action="temporary_relation", ref_key=_make_msg_from_ref_key(old_key))
             )
             return False
         return True
@@ -454,13 +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)
-        logger.debug('Renaming relation {!s} to {!s}'.format(
-            old_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),
+            )
+        )
 
-        lazy_log('before rename: {!s}', 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):
@@ -468,11 +468,12 @@ class RelationsCache:
             else:
                 self._setdefault(_CachedRelation(new))
 
-        lazy_log('after rename: {!s}', 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]:
+    def get_relations(self, database: Optional[str], schema: Optional[str]) -> List[Any]:
         """Case-insensitively yield all relations matching the given schema.
 
         :param str schema: The case-insensitive schema name to list from.
@@ -483,15 +484,13 @@ class RelationsCache:
         schema = lowercase(schema)
         with self.lock:
             results = [
-                r.inner for r in self.relations.values()
-                if (lowercase(r.schema) == schema and
-                    lowercase(r.database) == database)
+                r.inner
+                for r in self.relations.values()
+                if (lowercase(r.schema) == schema and lowercase(r.database) == database)
             ]
 
         if None in results:
-            dbt.exceptions.raise_cache_inconsistent(
-                'in get_relations, a None relation was found in the cache!'
-            )
+            raise NoneRelationFoundError()
         return results
 
     def clear(self):
@@ -518,6 +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

@@ -1,24 +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.logger import GLOBAL_LOGGER as logger
-from dbt.contracts.connection import Credentials, AdapterRequiredConfig
-
-
-from dbt.adapters.protocol import (
-    AdapterProtocol,
-    AdapterConfig,
-    RelationProtocol,
-)
 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.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
 
@@ -40,7 +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)
@@ -50,9 +44,7 @@ class AdapterContainer:
         adapter = self.get_adapter_class_by_name(name)
         return adapter.Relation
 
-    def get_config_class_by_name(
-        self, name: str
-    ) -> Type[AdapterConfig]:
+    def get_config_class_by_name(self, name: str) -> Type[AdapterConfig]:
         adapter = self.get_adapter_class_by_name(name)
         return adapter.AdapterSpecificConfigs
 
@@ -62,24 +54,25 @@ class AdapterContainer:
         # singletons
         try:
             # mypy doesn't think modules have any attributes.
-            mod: Any = import_module('.' + name, 'dbt.adapters')
+            mod: Any = import_module("." + name, "dbt.adapters")
         except ModuleNotFoundError as exc:
             # if we failed to import the target module in particular, inform
             # the user about it via a runtime error
-            if exc.name == 'dbt.adapters.' + name:
-                raise RuntimeException(f'Could not find adapter type {name}!')
-            logger.info(f'Error importing adapter: {exc}')
+            if exc.name == "dbt.adapters." + name:
+                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.
-            logger.debug('', exc_info=True)
+
+            fire_event(PluginLoadError(exc_info=traceback.format_exc()))
             raise
         plugin: AdapterPlugin = mod.Plugin
         plugin_type = plugin.adapter.type()
 
         if plugin_type != name:
-            raise RuntimeException(
-                f'Expected to find adapter with type named {name}, got '
-                f'adapter with type {plugin_type}'
+            raise DbtRuntimeError(
+                f"Expected to find adapter with type named {name}, got "
+                f"adapter with type {plugin_type}"
             )
 
         with self.lock:
@@ -109,8 +102,7 @@ class AdapterContainer:
         return self.adapters[adapter_name]
 
     def reset_adapters(self):
-        """Clear the adapters. This is useful for tests, which change configs.
-        """
+        """Clear the adapters. This is useful for tests, which change configs."""
         with self.lock:
             for adapter in self.adapters.values():
                 adapter.cleanup_connections()
@@ -140,22 +132,16 @@ 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)
-            if plugin.dependencies is None:
-                continue
             for dep in plugin.dependencies:
                 if dep not in seen:
                     plugin_names.append(dep)
         return plugins
 
     def get_adapter_package_names(self, name: Optional[str]) -> List[str]:
-        package_names: List[str] = [
-            p.project_name for p in self.get_adapter_plugins(name)
-        ]
+        package_names: List[str] = [p.project_name for p in self.get_adapter_plugins(name)]
         package_names.append(GLOBAL_PROJECT_NAME)
         return package_names
 
@@ -165,9 +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
 
@@ -186,9 +170,12 @@ def get_adapter(config: AdapterRequiredConfig):
     return FACTORY.lookup_adapter(config.credentials.type)
 
 
+def get_adapter_by_type(adapter_type):
+    return FACTORY.lookup_adapter(adapter_type)
+
+
 def reset_adapters():
-    """Clear the adapters. This is useful for tests, which change configs.
-    """
+    """Clear the adapters. This is useful for tests, which change configs."""
     FACTORY.reset_adapters()
 
 
@@ -225,3 +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

@@ -1,19 +1,22 @@
 from dataclasses import dataclass
 from typing import (
-    Type, Hashable, Optional, ContextManager, List, Generic, TypeVar, ClassVar,
-    Tuple, Union, Dict, Any
+    Type,
+    Hashable,
+    Optional,
+    ContextManager,
+    List,
+    Generic,
+    TypeVar,
+    Tuple,
+    Dict,
+    Any,
 )
 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.connection import Connection, AdapterRequiredConfig, AdapterResponse
+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
@@ -34,7 +37,7 @@ class ColumnProtocol(Protocol):
     pass
 
 
-Self = TypeVar('Self', bound='RelationProtocol')
+Self = TypeVar("Self", bound="RelationProtocol")
 
 
 class RelationProtocol(Protocol):
@@ -43,11 +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:
         ...
 
 
@@ -60,26 +59,19 @@ class CompilerProtocol(Protocol):
         node: ManifestNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestNode:
         ...
 
 
-AdapterConfig_T = TypeVar(
-    'AdapterConfig_T', bound=AdapterConfig
-)
-ConnectionManager_T = TypeVar(
-    'ConnectionManager_T', bound=ConnectionManagerProtocol
-)
-Relation_T = TypeVar(
-    'Relation_T', bound=RelationProtocol
-)
-Column_T = TypeVar(
-    'Column_T', bound=ColumnProtocol
-)
-Compiler_T = TypeVar('Compiler_T', bound=CompilerProtocol)
+AdapterConfig_T = TypeVar("AdapterConfig_T", bound=AdapterConfig)
+ConnectionManager_T = TypeVar("ConnectionManager_T", bound=ConnectionManagerProtocol)
+Relation_T = TypeVar("Relation_T", bound=RelationProtocol)
+Column_T = TypeVar("Column_T", bound=ColumnProtocol)
+Compiler_T = TypeVar("Compiler_T", bound=CompilerProtocol)
 
 
-class AdapterProtocol(
+# TODO CT-211
+class AdapterProtocol(  # type: ignore[misc]
     Protocol,
     Generic[
         AdapterConfig_T,
@@ -87,12 +79,15 @@ class AdapterProtocol(
         Relation_T,
         Column_T,
         Compiler_T,
-    ]
+    ],
 ):
-    AdapterSpecificConfigs: ClassVar[Type[AdapterConfig_T]]
-    Column: ClassVar[Type[Column_T]]
-    Relation: ClassVar[Type[Relation_T]]
-    ConnectionManager: ClassVar[Type[ConnectionManager_T]]
+    # N.B. Technically these are ClassVars, but mypy doesn't support putting type vars in a
+    # ClassVar due to the restrictiveness of PEP-526
+    # See: https://github.com/python/mypy/issues/5144
+    AdapterSpecificConfigs: Type[AdapterConfig_T]
+    Column: Type[Column_T]
+    Relation: Type[Relation_T]
+    ConnectionManager: Type[ConnectionManager_T]
     connections: ConnectionManager_T
 
     def __init__(self, config: AdapterRequiredConfig):
@@ -156,7 +151,7 @@ class AdapterProtocol(
 
     def execute(
         self, sql: str, auto_begin: bool = False, fetch: bool = False
-    ) -> Tuple[Union[str, AdapterResponse], agate.Table]:
+    ) -> Tuple[AdapterResponse, agate.Table]:
         ...
 
     def get_compiler(self) -> Compiler_T:

core/dbt/adapters/reference_keys.py

@@ -0,0 +1,40 @@
+# this module exists to resolve circular imports with the events module
+
+from collections import namedtuple
+from typing import Any, Optional
+from dbt.events.proto_types import ReferenceKeyMsg
+
+
+_ReferenceKey = namedtuple("_ReferenceKey", "database schema identifier")
+
+
+def lowercase(value: Optional[str]) -> Optional[str]:
+    if value is None:
+        return None
+    else:
+        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
+    """
+    # databases and schemas can both be None
+    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

@@ -1,16 +1,17 @@
 import abc
 import time
-from typing import List, Optional, Tuple, Any, Iterable, Dict, Union
+from typing import List, Optional, Tuple, Any, Iterable, Dict
 
 import agate
 
 import dbt.clients.agate_helper
 import dbt.exceptions
 from dbt.adapters.base import BaseConnectionManager
-from dbt.contracts.connection import (
-    Connection, ConnectionState, AdapterResponse
-)
-from dbt.logger import GLOBAL_LOGGER as logger
+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):
@@ -22,12 +23,11 @@ class SQLConnectionManager(BaseConnectionManager):
         - get_response
         - open
     """
+
     @abc.abstractmethod
     def cancel(self, connection: Connection):
         """Cancel the given connection."""
-        raise dbt.exceptions.NotImplementedException(
-            '`cancel` is not implemented for this adapter!'
-        )
+        raise dbt.exceptions.NotImplementedError("`cancel` is not implemented for this adapter!")
 
     def cancel_open(self) -> List[str]:
         names = []
@@ -39,10 +39,7 @@ class SQLConnectionManager(BaseConnectionManager):
 
                 # if the connection failed, the handle will be None so we have
                 # nothing to cancel.
-                if (
-                    connection.handle is not None and
-                    connection.state == ConnectionState.OPEN
-                ):
+                if connection.handle is not None and connection.state == ConnectionState.OPEN:
                     self.cancel(connection)
                 if connection.name is not None:
                     names.append(connection.name)
@@ -53,59 +50,70 @@ class SQLConnectionManager(BaseConnectionManager):
         sql: str,
         auto_begin: bool = True,
         bindings: Optional[Any] = None,
-        abridge_sql_log: bool = False
+        abridge_sql_log: bool = False,
     ) -> Tuple[Connection, Any]:
         connection = self.get_thread_connection()
         if auto_begin and connection.transaction_open is False:
             self.begin()
-
-        logger.debug('Using {} connection "{}".'
-                     .format(self.TYPE, connection.name))
+        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:
-                log_sql = '{}...'.format(sql[:512])
+                log_sql = "{}...".format(sql[:512])
             else:
                 log_sql = sql
 
-            logger.debug(
-                'On {connection_name}: {sql}',
-                connection_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()
             cursor.execute(sql, bindings)
-            logger.debug(
-                "SQL status: {status} in {elapsed:0.2f} seconds",
-                status=self.get_response(cursor),
-                elapsed=(time.time() - pre)
+
+            fire_event(
+                SQLQueryStatus(
+                    status=str(self.get_response(cursor)),
+                    elapsed=round((time.time() - pre)),
+                    node_info=get_node_info(),
+                )
             )
 
             return connection, cursor
 
-    @abc.abstractclassmethod
-    def get_response(cls, cursor: Any) -> Union[AdapterResponse, str]:
+    @classmethod
+    @abc.abstractmethod
+    def get_response(cls, cursor: Any) -> AdapterResponse:
         """Get the status of the cursor."""
-        raise dbt.exceptions.NotImplementedException(
-            '`get_response` is not implemented for this adapter!'
+        raise dbt.exceptions.NotImplementedError(
+            "`get_response` is not implemented for this adapter!"
         )
 
     @classmethod
     def process_results(
-        cls,
-        column_names: Iterable[str],
-        rows: Iterable[Any]
+        cls, column_names: Iterable[str], rows: Iterable[Any]
     ) -> List[Dict[str, Any]]:
-        unique_col_names = dict()
-        for idx in range(len(column_names)):
-            col_name = column_names[idx]
+        # TODO CT-211
+        unique_col_names = dict()  # type: ignore[var-annotated]
+        # TODO CT-211
+        for idx in range(len(column_names)):  # type: ignore[arg-type]
+            # TODO CT-211
+            col_name = column_names[idx]  # type: ignore[index]
             if col_name in unique_col_names:
                 unique_col_names[col_name] += 1
-                column_names[idx] = f'{col_name}_{unique_col_names[col_name]}'
+                # TODO CT-211
+                column_names[idx] = f"{col_name}_{unique_col_names[col_name]}"  # type: ignore[index] # noqa
             else:
-                unique_col_names[column_names[idx]] = 1
+                # TODO CT-211
+                unique_col_names[column_names[idx]] = 1  # type: ignore[index]
         return [dict(zip(column_names, row)) for row in rows]
 
     @classmethod
@@ -118,14 +126,11 @@ class SQLConnectionManager(BaseConnectionManager):
             rows = cursor.fetchall()
             data = cls.process_results(column_names, rows)
 
-        return dbt.clients.agate_helper.table_from_data_flat(
-            data,
-            column_names
-        )
+        return dbt.clients.agate_helper.table_from_data_flat(data, column_names)
 
     def execute(
         self, sql: str, auto_begin: bool = False, fetch: bool = False
-    ) -> Tuple[Union[AdapterResponse, str], agate.Table]:
+    ) -> Tuple[AdapterResponse, agate.Table]:
         sql = self._add_query_comment(sql)
         _, cursor = self.add_query(sql, auto_begin)
         response = self.get_response(cursor)
@@ -136,17 +141,18 @@ class SQLConnectionManager(BaseConnectionManager):
         return response, table
 
     def add_begin_query(self):
-        return self.add_query('BEGIN', auto_begin=False)
+        return self.add_query("BEGIN", auto_begin=False)
 
     def add_commit_query(self):
-        return self.add_query('COMMIT', auto_begin=False)
+        return self.add_query("COMMIT", auto_begin=False)
 
     def begin(self):
         connection = self.get_thread_connection()
         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))
+                "it already had one open!".format(connection.name)
+            )
 
         self.add_begin_query()
 
@@ -156,11 +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))
+                "it does not have one open!".format(connection.name)
+            )
 
-        logger.debug('On {}: COMMIT'.format(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

@@ -1,30 +1,32 @@
 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_ref_key_msg
 from dbt.adapters.sql import SQLConnectionManager
-from dbt.logger import GLOBAL_LOGGER as logger
+from dbt.events.functions import fire_event
+from dbt.events.types import ColTypeChange, SchemaCreation, SchemaDrop
+
 
 from dbt.adapters.base.relation import BaseRelation
 
-LIST_RELATIONS_MACRO_NAME = 'list_relations_without_caching'
-GET_COLUMNS_IN_RELATION_MACRO_NAME = 'get_columns_in_relation'
-LIST_SCHEMAS_MACRO_NAME = 'list_schemas'
-CHECK_SCHEMA_EXISTS_MACRO_NAME = 'check_schema_exists'
-CREATE_SCHEMA_MACRO_NAME = 'create_schema'
-DROP_SCHEMA_MACRO_NAME = 'drop_schema'
-RENAME_RELATION_MACRO_NAME = 'rename_relation'
-TRUNCATE_RELATION_MACRO_NAME = 'truncate_relation'
-DROP_RELATION_MACRO_NAME = 'drop_relation'
-ALTER_COLUMN_TYPE_MACRO_NAME = 'alter_column_type'
+LIST_RELATIONS_MACRO_NAME = "list_relations_without_caching"
+GET_COLUMNS_IN_RELATION_MACRO_NAME = "get_columns_in_relation"
+LIST_SCHEMAS_MACRO_NAME = "list_schemas"
+CHECK_SCHEMA_EXISTS_MACRO_NAME = "check_schema_exists"
+CREATE_SCHEMA_MACRO_NAME = "create_schema"
+DROP_SCHEMA_MACRO_NAME = "drop_schema"
+RENAME_RELATION_MACRO_NAME = "rename_relation"
+TRUNCATE_RELATION_MACRO_NAME = "truncate_relation"
+DROP_RELATION_MACRO_NAME = "drop_relation"
+ALTER_COLUMN_TYPE_MACRO_NAME = "alter_column_type"
 
 
 class SQLAdapter(BaseAdapter):
     """The default adapter with the common agate conversions and some SQL
-    methods implemented. This adapter has a different much shorter list of
+    methods was implemented. This adapter has a different much shorter list of
     methods to implement, but some more macros that must be implemented.
 
     To implement a macro, implement "${adapter_type}__${macro_name}". in the
@@ -60,30 +62,24 @@ class SQLAdapter(BaseAdapter):
         :param abridge_sql_log: If set, limit the raw sql logged to 512
             characters
         """
-        return self.connections.add_query(sql, auto_begin, bindings,
-                                          abridge_sql_log)
+        return self.connections.add_query(sql, auto_begin, bindings, abridge_sql_log)
 
     @classmethod
     def convert_text_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         return "text"
 
     @classmethod
-    def convert_number_type(
-        cls, agate_table: agate.Table, col_idx: int
-    ) -> str:
-        decimals = agate_table.aggregate(agate.MaxPrecision(col_idx))
+    def convert_number_type(cls, agate_table: agate.Table, col_idx: int) -> str:
+        # TODO CT-211
+        decimals = agate_table.aggregate(agate.MaxPrecision(col_idx))  # type: ignore[attr-defined]
         return "float8" if decimals else "integer"
 
     @classmethod
-    def convert_boolean_type(
-            cls, agate_table: agate.Table, col_idx: int
-    ) -> str:
+    def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         return "boolean"
 
     @classmethod
-    def convert_datetime_type(
-            cls, agate_table: agate.Table, col_idx: int
-    ) -> str:
+    def convert_datetime_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         return "timestamp without time zone"
 
     @classmethod
@@ -99,31 +95,27 @@ class SQLAdapter(BaseAdapter):
         return True
 
     def expand_column_types(self, goal, current):
-        reference_columns = {
-            c.name: c for c in
-            self.get_columns_in_relation(goal)
-        }
+        reference_columns = {c.name: c for c in self.get_columns_in_relation(goal)}
 
-        target_columns = {
-            c.name: c for c
-            in self.get_columns_in_relation(current)
-        }
+        target_columns = {c.name: c for c in self.get_columns_in_relation(current)}
 
         for column_name, reference_column in reference_columns.items():
             target_column = target_columns.get(column_name)
 
-            if target_column is not None and \
-               target_column.can_expand_to(reference_column):
+            if target_column is not None and target_column.can_expand_to(reference_column):
                 col_string_size = reference_column.string_size()
                 new_type = self.Column.string_type(col_string_size)
-                logger.debug("Changing col type from {} to {} in table {}",
-                             target_column.data_type, new_type, current)
+                fire_event(
+                    ColTypeChange(
+                        orig_type=target_column.data_type,
+                        new_type=new_type,
+                        table=_make_ref_key_msg(current),
+                    )
+                )
 
                 self.alter_column_type(current, column_name, new_type)
 
-    def alter_column_type(
-            self, relation, column_name, new_column_type
-    ) -> None:
+    def alter_column_type(self, relation, column_name, new_column_type) -> None:
         """
         1. Create a new column (w/ temp name and correct type)
         2. Copy data over to it
@@ -131,53 +123,38 @@ class SQLAdapter(BaseAdapter):
         4. Rename the new column to existing column
         """
         kwargs = {
-            'relation': relation,
-            'column_name': column_name,
-            'new_column_type': new_column_type,
+            "relation": relation,
+            "column_name": column_name,
+            "new_column_type": new_column_type,
         }
-        self.execute_macro(
-            ALTER_COLUMN_TYPE_MACRO_NAME,
-            kwargs=kwargs
-        )
+        self.execute_macro(ALTER_COLUMN_TYPE_MACRO_NAME, kwargs=kwargs)
 
     def drop_relation(self, relation):
         if relation.type is None:
-            dbt.exceptions.raise_compiler_error(
-                'Tried to drop relation {}, but its type is null.'
-                .format(relation))
+            raise RelationTypeNullError(relation)
 
         self.cache_dropped(relation)
-        self.execute_macro(
-            DROP_RELATION_MACRO_NAME,
-            kwargs={'relation': relation}
-        )
+        self.execute_macro(DROP_RELATION_MACRO_NAME, kwargs={"relation": relation})
 
     def truncate_relation(self, relation):
-        self.execute_macro(
-            TRUNCATE_RELATION_MACRO_NAME,
-            kwargs={'relation': relation}
-        )
+        self.execute_macro(TRUNCATE_RELATION_MACRO_NAME, kwargs={"relation": relation})
 
     def rename_relation(self, from_relation, to_relation):
         self.cache_renamed(from_relation, to_relation)
 
-        kwargs = {'from_relation': from_relation, 'to_relation': to_relation}
-        self.execute_macro(
-            RENAME_RELATION_MACRO_NAME,
-            kwargs=kwargs
-        )
+        kwargs = {"from_relation": from_relation, "to_relation": to_relation}
+        self.execute_macro(RENAME_RELATION_MACRO_NAME, kwargs=kwargs)
 
     def get_columns_in_relation(self, relation):
         return self.execute_macro(
-            GET_COLUMNS_IN_RELATION_MACRO_NAME,
-            kwargs={'relation': relation}
+            GET_COLUMNS_IN_RELATION_MACRO_NAME, kwargs={"relation": relation}
         )
 
     def create_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        logger.debug('Creating schema "{}"', relation)
+        fire_event(SchemaCreation(relation=_make_ref_key_msg(relation)))
         kwargs = {
-            'relation': relation,
+            "relation": relation,
         }
         self.execute_macro(CREATE_SCHEMA_MACRO_NAME, kwargs=kwargs)
         self.commit_if_has_connection()
@@ -186,51 +163,45 @@ class SQLAdapter(BaseAdapter):
 
     def drop_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        logger.debug('Dropping schema "{}".', relation)
+        fire_event(SchemaDrop(relation=_make_ref_key_msg(relation)))
         kwargs = {
-            'relation': relation,
+            "relation": relation,
         }
         self.execute_macro(DROP_SCHEMA_MACRO_NAME, kwargs=kwargs)
+        self.commit_if_has_connection()
         # we can update the cache here
         self.cache.drop_schema(relation.database, relation.schema)
 
     def list_relations_without_caching(
-        self, schema_relation: BaseRelation,
+        self,
+        schema_relation: BaseRelation,
     ) -> List[BaseRelation]:
-        kwargs = {'schema_relation': schema_relation}
-        results = self.execute_macro(
-            LIST_RELATIONS_MACRO_NAME,
-            kwargs=kwargs
-        )
+        kwargs = {"schema_relation": schema_relation}
+        results = self.execute_macro(LIST_RELATIONS_MACRO_NAME, kwargs=kwargs)
 
         relations = []
-        quote_policy = {
-            'database': True,
-            'schema': True,
-            'identifier': True
-        }
+        quote_policy = {"database": True, "schema": True, "identifier": True}
         for _database, name, _schema, _type in results:
             try:
                 _type = self.Relation.get_relation_type(_type)
             except ValueError:
                 _type = self.Relation.External
-            relations.append(self.Relation.create(
-                database=_database,
-                schema=_schema,
-                identifier=name,
-                quote_policy=quote_policy,
-                type=_type
-            ))
+            relations.append(
+                self.Relation.create(
+                    database=_database,
+                    schema=_schema,
+                    identifier=name,
+                    quote_policy=quote_policy,
+                    type=_type,
+                )
+            )
         return relations
 
     def quote(self, identifier):
         return '"{}"'.format(identifier)
 
     def list_schemas(self, database: str) -> List[str]:
-        results = self.execute_macro(
-            LIST_SCHEMAS_MACRO_NAME,
-            kwargs={'database': database}
-        )
+        results = self.execute_macro(LIST_SCHEMAS_MACRO_NAME, kwargs={"database": database})
 
         return [row[0] for row in results]
 
@@ -238,13 +209,32 @@ class SQLAdapter(BaseAdapter):
         information_schema = self.Relation.create(
             database=database,
             schema=schema,
-            identifier='INFORMATION_SCHEMA',
-            quote_policy=self.config.quoting
+            identifier="INFORMATION_SCHEMA",
+            quote_policy=self.config.quoting,
         ).information_schema()
 
-        kwargs = {'information_schema': information_schema, 'schema': schema}
-        results = self.execute_macro(
-            CHECK_SCHEMA_EXISTS_MACRO_NAME,
-            kwargs=kwargs
-        )
+        kwargs = {"information_schema": information_schema, "schema": schema}
+        results = self.execute_macro(CHECK_SCHEMA_EXISTS_MACRO_NAME, kwargs=kwargs)
         return results[0][0] > 0
+
+    # This is for use in the test suite
+    def run_sql_for_tests(self, sql, fetch, conn):
+        cursor = conn.handle.cursor()
+        try:
+            cursor.execute(sql)
+            if hasattr(conn.handle, "commit"):
+                conn.handle.commit()
+            if fetch == "one":
+                return cursor.fetchone()
+            elif fetch == "all":
+                return cursor.fetchall()
+            else:
+                return
+        except BaseException as e:
+            if conn.handle and not getattr(conn.handle, "closed", True):
+                conn.handle.rollback()
+            print(sql)
+            print(e)
+            raise
+        finally:
+            conn.transaction_open = False

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

@@ -0,0 +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):
@@ -10,79 +18,83 @@ def regex(pat):
 
 class BlockData:
     """raw plaintext data from the top level of the file."""
+
     def __init__(self, contents):
-        self.block_type_name = '__dbt__data'
+        self.block_type_name = "__dbt__data"
         self.contents = contents
         self.full_block = contents
 
 
 class BlockTag:
-    def __init__(self, block_type_name, block_name, contents=None,
-                 full_block=None, **kw):
+    def __init__(self, block_type_name, block_name, contents=None, full_block=None, **kw):
         self.block_type_name = block_type_name
         self.block_name = block_name
         self.contents = contents
         self.full_block = full_block
 
     def __str__(self):
-        return 'BlockTag({!r}, {!r})'.format(self.block_type_name,
-                                             self.block_name)
+        return "BlockTag({!r}, {!r})".format(self.block_type_name, self.block_name)
 
     def __repr__(self):
         return str(self)
 
     @property
     def end_block_type_name(self):
-        return 'end{}'.format(self.block_type_name)
+        return "end{}".format(self.block_type_name)
 
     def end_pat(self):
         # we don't want to use string formatting here because jinja uses most
         # of the string formatting operators in its syntax...
-        pattern = ''.join((
-            r'(?P<endblock>((?:\s*\{\%\-|\{\%)\s*',
-            self.end_block_type_name,
-            r'\s*(?:\-\%\}\s*|\%\})))',
-        ))
+        pattern = "".join(
+            (
+                r"(?P<endblock>((?:\s*\{\%\-|\{\%)\s*",
+                self.end_block_type_name,
+                r"\s*(?:\-\%\}\s*|\%\})))",
+            )
+        )
         return regex(pattern)
 
 
-Tag = namedtuple('Tag', 'block_type_name block_name start end')
+Tag = namedtuple("Tag", "block_type_name block_name start end")
 
 
-_NAME_PATTERN = r'[A-Za-z_][A-Za-z_0-9]*'
+_NAME_PATTERN = r"[A-Za-z_][A-Za-z_0-9]*"
 
-COMMENT_START_PATTERN = regex(r'(?:(?P<comment_start>(\s*\{\#)))')
-COMMENT_END_PATTERN = regex(r'(.*?)(\s*\#\})')
-RAW_START_PATTERN = regex(
-    r'(?:\s*\{\%\-|\{\%)\s*(?P<raw_start>(raw))\s*(?:\-\%\}\s*|\%\})'
+COMMENT_START_PATTERN = regex(r"(?:(?P<comment_start>(\s*\{\#)))")
+COMMENT_END_PATTERN = regex(r"(.*?)(\s*\#\})")
+RAW_START_PATTERN = regex(r"(?:\s*\{\%\-|\{\%)\s*(?P<raw_start>(raw))\s*(?:\-\%\}\s*|\%\})")
+EXPR_START_PATTERN = regex(r"(?P<expr_start>(\{\{\s*))")
+EXPR_END_PATTERN = regex(r"(?P<expr_end>(\s*\}\}))")
+
+BLOCK_START_PATTERN = regex(
+    "".join(
+        (
+            r"(?:\s*\{\%\-|\{\%)\s*",
+            r"(?P<block_type_name>({}))".format(_NAME_PATTERN),
+            # some blocks have a 'block name'.
+            r"(?:\s+(?P<block_name>({})))?".format(_NAME_PATTERN),
+        )
+    )
 )
-EXPR_START_PATTERN = regex(r'(?P<expr_start>(\{\{\s*))')
-EXPR_END_PATTERN = regex(r'(?P<expr_end>(\s*\}\}))')
-
-BLOCK_START_PATTERN = regex(''.join((
-    r'(?:\s*\{\%\-|\{\%)\s*',
-    r'(?P<block_type_name>({}))'.format(_NAME_PATTERN),
-    # some blocks have a 'block name'.
-    r'(?:\s+(?P<block_name>({})))?'.format(_NAME_PATTERN),
-)))
 
 
-RAW_BLOCK_PATTERN = regex(''.join((
-    r'(?:\s*\{\%\-|\{\%)\s*raw\s*(?:\-\%\}\s*|\%\})',
-    r'(?:.*?)',
-    r'(?:\s*\{\%\-|\{\%)\s*endraw\s*(?:\-\%\}\s*|\%\})',
-)))
+RAW_BLOCK_PATTERN = regex(
+    "".join(
+        (
+            r"(?:\s*\{\%\-|\{\%)\s*raw\s*(?:\-\%\}\s*|\%\})",
+            r"(?:.*?)",
+            r"(?:\s*\{\%\-|\{\%)\s*endraw\s*(?:\-\%\}\s*|\%\})",
+        )
+    )
+)
 
-TAG_CLOSE_PATTERN = regex(r'(?:(?P<tag_close>(\-\%\}\s*|\%\})))')
+TAG_CLOSE_PATTERN = regex(r"(?:(?P<tag_close>(\-\%\}\s*|\%\})))")
 
 # stolen from jinja's lexer. Note that we've consumed all prefix whitespace by
 # the time we want to use this.
-STRING_PATTERN = regex(
-    r"(?P<string>('([^'\\]*(?:\\.[^'\\]*)*)'|"
-    r'"([^"\\]*(?:\\.[^"\\]*)*)"))'
-)
+STRING_PATTERN = regex(r"(?P<string>('([^'\\]*(?:\\.[^'\\]*)*)'|" r'"([^"\\]*(?:\\.[^"\\]*)*)"))')
 
-QUOTE_START_PATTERN = regex(r'''(?P<quote>(['"]))''')
+QUOTE_START_PATTERN = regex(r"""(?P<quote>(['"]))""")
 
 
 class TagIterator:
@@ -99,10 +111,10 @@ class TagIterator:
         end_val: int = self.pos if end is None else end
         data = self.data[:end_val]
         # if not found, rfind returns -1, and -1+1=0, which is perfect!
-        last_line_start = data.rfind('\n') + 1
+        last_line_start = data.rfind("\n") + 1
         # it's easy to forget this, but line numbers are 1-indexed
-        line_number = data.count('\n') + 1
-        return f'{line_number}:{end_val - last_line_start}'
+        line_number = data.count("\n") + 1
+        return f"{line_number}:{end_val - last_line_start}"
 
     def advance(self, new_position):
         self.pos = new_position
@@ -120,7 +132,7 @@ class TagIterator:
         matches = []
         for pattern in patterns:
             # default to 'search', but sometimes we want to 'match'.
-            if kwargs.get('method', 'search') == 'search':
+            if kwargs.get("method", "search") == "search":
                 match = self._search(pattern)
             else:
                 match = self._match(pattern)
@@ -135,10 +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):
@@ -156,22 +165,20 @@ class TagIterator:
         """
         self.advance(match.end())
         while True:
-            match = self._expect_match('}}',
-                                       EXPR_END_PATTERN,
-                                       QUOTE_START_PATTERN)
-            if match.groupdict().get('expr_end') is not None:
+            match = self._expect_match("}}", EXPR_END_PATTERN, QUOTE_START_PATTERN)
+            if match.groupdict().get("expr_end") is not None:
                 break
             else:
                 # it's a quote. we haven't advanced for this match yet, so
                 # just slurp up the whole string, no need to rewind.
-                match = self._expect_match('string', STRING_PATTERN)
+                match = self._expect_match("string", STRING_PATTERN)
                 self.advance(match.end())
 
         self.advance(match.end())
 
     def handle_comment(self, match):
         self.advance(match.end())
-        match = self._expect_match('#}', COMMENT_END_PATTERN)
+        match = self._expect_match("#}", COMMENT_END_PATTERN)
         self.advance(match.end())
 
     def _expect_block_close(self):
@@ -188,22 +195,19 @@ class TagIterator:
         """
         while True:
             end_match = self._expect_match(
-                'tag close ("%}")',
-                QUOTE_START_PATTERN,
-                TAG_CLOSE_PATTERN
+                'tag close ("%}")', QUOTE_START_PATTERN, TAG_CLOSE_PATTERN
             )
             self.advance(end_match.end())
-            if end_match.groupdict().get('tag_close') is not None:
+            if end_match.groupdict().get("tag_close") is not None:
                 return
             # must be a string. Rewind to its start and advance past it.
             self.rewind()
-            string_match = self._expect_match('string', STRING_PATTERN)
+            string_match = self._expect_match("string", STRING_PATTERN)
             self.advance(string_match.end())
 
     def handle_raw(self):
         # raw blocks are super special, they are a single complete regex
-        match = self._expect_match('{% raw %}...{% endraw %}',
-                                   RAW_BLOCK_PATTERN)
+        match = self._expect_match("{% raw %}...{% endraw %}", RAW_BLOCK_PATTERN)
         self.advance(match.end())
         return match.end()
 
@@ -220,30 +224,24 @@ class TagIterator:
         """
         groups = match.groupdict()
         # always a value
-        block_type_name = groups['block_type_name']
+        block_type_name = groups["block_type_name"]
         # might be None
-        block_name = groups.get('block_name')
+        block_name = groups.get("block_name")
         start_pos = self.pos
-        if block_type_name == 'raw':
-            match = self._expect_match('{% raw %}...{% endraw %}',
-                                       RAW_BLOCK_PATTERN)
+        if block_type_name == "raw":
+            match = self._expect_match("{% raw %}...{% endraw %}", RAW_BLOCK_PATTERN)
             self.advance(match.end())
         else:
             self.advance(match.end())
             self._expect_block_close()
         return Tag(
-            block_type_name=block_type_name,
-            block_name=block_name,
-            start=start_pos,
-            end=self.pos
+            block_type_name=block_type_name, block_name=block_name, start=start_pos, end=self.pos
         )
 
     def find_tags(self):
         while True:
             match = self._first_match(
-                BLOCK_START_PATTERN,
-                COMMENT_START_PATTERN,
-                EXPR_START_PATTERN
+                BLOCK_START_PATTERN, COMMENT_START_PATTERN, EXPR_START_PATTERN
             )
             if match is None:
                 break
@@ -252,9 +250,9 @@ class TagIterator:
             # start = self.pos
 
             groups = match.groupdict()
-            comment_start = groups.get('comment_start')
-            expr_start = groups.get('expr_start')
-            block_type_name = groups.get('block_type_name')
+            comment_start = groups.get("comment_start")
+            expr_start = groups.get("expr_start")
+            block_type_name = groups.get("block_type_name")
 
             if comment_start is not None:
                 self.handle_comment(match)
@@ -263,31 +261,21 @@ class TagIterator:
             elif block_type_name is not None:
                 yield self.handle_tag(match)
             else:
-                raise dbt.exceptions.InternalException(
-                    'Invalid regex match in next_block, expected block start, '
-                    'expr start, or comment start'
+                raise DbtInternalError(
+                    "Invalid regex match in next_block, expected block start, "
+                    "expr start, or comment start"
                 )
 
     def __iter__(self):
         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',
+    "if": "endif",
+    "for": "endfor",
 }
 
-_CONTROL_FLOW_END_TAGS = {
-    v: k
-    for k, v in _CONTROL_FLOW_TAGS.items()
-}
+_CONTROL_FLOW_END_TAGS = {v: k for k, v in _CONTROL_FLOW_TAGS.items()}
 
 
 class BlockIterator:
@@ -310,15 +298,15 @@ class BlockIterator:
 
     def is_current_end(self, tag):
         return (
-            tag.block_type_name.startswith('end') and
-            self.current is not None and
-            tag.block_type_name[3:] == self.current.block_type_name
+            tag.block_type_name.startswith("end")
+            and self.current is not None
+            and tag.block_type_name[3:] == self.current.block_type_name
         )
 
     def find_blocks(self, allowed_blocks=None, collect_raw_data=True):
         """Find all top-level blocks in the data."""
         if allowed_blocks is None:
-            allowed_blocks = {'snapshot', 'macro', 'materialization', 'docs'}
+            allowed_blocks = {"snapshot", "macro", "materialization", "docs"}
 
         for tag in self.tag_parser.find_tags():
             if tag.block_type_name in _CONTROL_FLOW_TAGS:
@@ -329,37 +317,18 @@ 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]
+                    raw_data = self.data[self.last_position : tag.start]
                     self.last_position = tag.start
                     if raw_data:
                         yield BlockData(raw_data)
@@ -371,23 +340,21 @@ class BlockIterator:
                 yield BlockTag(
                     block_type_name=self.current.block_type_name,
                     block_name=self.current.block_name,
-                    contents=self.data[self.current.end:tag.start],
-                    full_block=self.data[self.current.start:tag.end]
+                    contents=self.data[self.current.end : tag.start],
+                    full_block=self.data[self.current.start : tag.end],
                 )
                 self.current = None
 
         if self.current:
-            linecount = self.data[:self.current.end].count('\n') + 1
-            dbt.exceptions.raise_compiler_error((
-                'Reached EOF without finding a close tag for '
-                '{} (searched from line {})'
-            ).format(self.current.block_type_name, linecount))
+            linecount = self.data[: self.current.end].count("\n") + 1
+            raise MissingCloseTagError(self.current.block_type_name, linecount)
 
         if collect_raw_data:
-            raw_data = self.data[self.last_position:]
+            raw_data = self.data[self.last_position :]
             if raw_data:
                 yield BlockData(raw_data)
 
     def lex_for_blocks(self, allowed_blocks=None, collect_raw_data=True):
-        return list(self.find_blocks(allowed_blocks=allowed_blocks,
-                                     collect_raw_data=collect_raw_data))
+        return list(
+            self.find_blocks(allowed_blocks=allowed_blocks, collect_raw_data=collect_raw_data)
+        )

core/dbt/clients/agate_helper.py

@@ -7,10 +7,20 @@ 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'
+BOM = BOM_UTF8.decode("utf-8")  # '\ufeff'
+
+
+class Number(agate.data_types.Number):
+    # undo the change in https://github.com/wireservice/agate/pull/733
+    # i.e. do not cast True and False to numeric 1 and 0
+    def cast(self, d):
+        if type(d) == bool:
+            raise agate.exceptions.CastError("Do not cast True to 1 or False to 0.")
+        else:
+            return super().cast(d)
 
 
 class ISODateTime(agate.data_types.DateTime):
@@ -30,32 +40,24 @@ class ISODateTime(agate.data_types.DateTime):
         except:  # noqa
             pass
 
-        raise agate.exceptions.CastError(
-            'Can not parse value "%s" as datetime.' % d
-        )
+        raise agate.exceptions.CastError('Can not parse value "%s" as datetime.' % d)
 
 
 def build_type_tester(
-    text_columns: Iterable[str],
-    string_null_values: Optional[Iterable[str]] = ('null', '')
+    text_columns: Iterable[str], string_null_values: Optional[Iterable[str]] = ("null", "")
 ) -> agate.TypeTester:
 
     types = [
-        agate.data_types.Number(null_values=('null', '')),
-        agate.data_types.Date(null_values=('null', ''),
-                              date_format='%Y-%m-%d'),
-        agate.data_types.DateTime(null_values=('null', ''),
-                                  datetime_format='%Y-%m-%d %H:%M:%S'),
-        ISODateTime(null_values=('null', '')),
-        agate.data_types.Boolean(true_values=('true',),
-                                 false_values=('false',),
-                                 null_values=('null', '')),
-        agate.data_types.Text(null_values=string_null_values)
+        Number(null_values=("null", "")),
+        agate.data_types.Date(null_values=("null", ""), date_format="%Y-%m-%d"),
+        agate.data_types.DateTime(null_values=("null", ""), datetime_format="%Y-%m-%d %H:%M:%S"),
+        ISODateTime(null_values=("null", "")),
+        agate.data_types.Boolean(
+            true_values=("true",), false_values=("false",), null_values=("null", "")
+        ),
+        agate.data_types.Text(null_values=string_null_values),
     ]
-    force = {
-        k: agate.data_types.Text(null_values=string_null_values)
-        for k in text_columns
-    }
+    force = {k: agate.data_types.Text(null_values=string_null_values) for k in text_columns}
     return agate.TypeTester(force=force, types=types)
 
 
@@ -72,16 +74,13 @@ def table_from_rows(
     else:
         # If text_only_columns are present, prevent coercing empty string or
         # literal 'null' strings to a None representation.
-        column_types = build_type_tester(
-            text_only_columns,
-            string_null_values=()
-        )
+        column_types = build_type_tester(text_only_columns, string_null_values=())
 
     return agate.Table(rows, column_names, column_types=column_types)
 
 
 def table_from_data(data, column_names: Iterable[str]) -> agate.Table:
-    "Convert list of dictionaries into an Agate table"
+    "Convert a list of dictionaries into an Agate table"
 
     # The agate table is generated from a list of dicts, so the column order
     # from `data` is not preserved. We can use `select` to reorder the columns
@@ -120,9 +119,7 @@ def table_from_data_flat(data, column_names: Iterable[str]) -> agate.Table:
         rows.append(row)
 
     return table_from_rows(
-        rows=rows,
-        column_names=column_names,
-        text_only_columns=text_only_columns
+        rows=rows, column_names=column_names, text_only_columns=text_only_columns
     )
 
 
@@ -140,7 +137,7 @@ def as_matrix(table):
 
 def from_csv(abspath, text_columns):
     type_tester = build_type_tester(text_columns=text_columns)
-    with open(abspath, encoding='utf-8') as fp:
+    with open(abspath, encoding="utf-8") as fp:
         if fp.read(1) != BOM:
             fp.seek(0)
         return agate.Table.from_csv(fp, column_types=type_tester)
@@ -171,9 +168,9 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
             return
         elif not isinstance(value, type(existing_type)):
             # actual type mismatch!
-            raise RuntimeException(
-                f'Tables contain columns with the same names ({key}), '
-                f'but different types ({value} vs {existing_type})'
+            raise DbtRuntimeError(
+                f"Tables contain columns with the same names ({key}), "
+                f"but different types ({value} vs {existing_type})"
             )
 
     def finalize(self) -> Dict[str, agate.data_types.DataType]:
@@ -187,9 +184,7 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
         return result
 
 
-def _merged_column_types(
-    tables: List[agate.Table]
-) -> Dict[str, agate.data_types.DataType]:
+def _merged_column_types(tables: List[agate.Table]) -> Dict[str, agate.data_types.DataType]:
     # this is a lot like agate.Table.merge, but with handling for all-null
     # rows being "any type".
     new_columns: ColumnTypeBuilder = ColumnTypeBuilder()
@@ -215,10 +210,7 @@ def merge_tables(tables: List[agate.Table]) -> agate.Table:
 
     rows: List[agate.Row] = []
     for table in tables:
-        if (
-            table.column_names == column_names and
-            table.column_types == column_types
-        ):
+        if table.column_names == column_names and table.column_types == column_types:
             rows.extend(table.rows)
         else:
             for row in table.rows:

core/dbt/clients/git.py

@@ -2,8 +2,23 @@ import re
 import os.path
 
 from dbt.clients.system import run_cmd, rmdir
-from dbt.logger import GLOBAL_LOGGER as logger
-import dbt.exceptions
+from dbt.events.functions import fire_event
+from dbt.events.types import (
+    GitSparseCheckoutSubdirectory,
+    GitProgressCheckoutRevision,
+    GitProgressUpdatingExistingDependency,
+    GitProgressPullingNewDependency,
+    GitNothingToDo,
+    GitProgressUpdatedCheckoutRange,
+    GitProgressCheckedOutAt,
+)
+from dbt.exceptions import (
+    CommandResultError,
+    GitCheckoutError,
+    GitCloningError,
+    UnknownGitCloningProblemError,
+    DbtRuntimeError,
+)
 from packaging import version
 
 
@@ -16,10 +31,10 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
     has_revision = revision is not None
     is_commit = _is_commit(revision or "")
 
-    clone_cmd = ['git', 'clone', '--depth', '1']
+    clone_cmd = ["git", "clone", "--depth", "1"]
     if subdirectory:
-        logger.debug('  Subdirectory specified: {}, using sparse checkout.'.format(subdirectory))
-        out, _ = run_cmd(cwd, ['git', '--version'], env={'LC_ALL': 'C'})
+        fire_event(GitSparseCheckoutSubdirectory(subdir=subdirectory))
+        out, _ = run_cmd(cwd, ["git", "--version"], env={"LC_ALL": "C"})
         git_version = version.parse(re.search(r"\d+\.\d+\.\d+", out.decode("utf-8")).group(0))
         if not git_version >= version.parse("2.25.0"):
             # 2.25.0 introduces --sparse
@@ -27,78 +42,85 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
                 "Please update your git version to pull a dbt package "
                 "from a subdirectory: your version is {}, >= 2.25.0 needed".format(git_version)
             )
-        clone_cmd.extend(['--filter=blob:none', '--sparse'])
+        clone_cmd.extend(["--filter=blob:none", "--sparse"])
 
     if has_revision and not is_commit:
-        clone_cmd.extend(['--branch', revision])
+        clone_cmd.extend(["--branch", revision])
 
     clone_cmd.append(repo)
 
     if dirname is not None:
         clone_cmd.append(dirname)
-    result = run_cmd(cwd, clone_cmd, env={'LC_ALL': 'C'})
+    try:
+        result = run_cmd(cwd, clone_cmd, env={"LC_ALL": "C"})
+    except CommandResultError as exc:
+        raise GitCloningError(repo, revision, exc)
 
     if subdirectory:
-        run_cmd(os.path.join(cwd, dirname or ''), ['git', 'sparse-checkout', 'set', subdirectory])
+        cwd_subdir = os.path.join(cwd, dirname or "")
+        clone_cmd_subdir = ["git", "sparse-checkout", "set", subdirectory]
+        try:
+            run_cmd(cwd_subdir, clone_cmd_subdir)
+        except CommandResultError as exc:
+            raise GitCloningError(repo, revision, exc)
 
     if remove_git_dir:
-        rmdir(os.path.join(dirname, '.git'))
+        rmdir(os.path.join(dirname, ".git"))
 
     return result
 
 
 def list_tags(cwd):
-    out, err = run_cmd(cwd, ['git', 'tag', '--list'], env={'LC_ALL': 'C'})
-    tags = out.decode('utf-8').strip().split("\n")
+    out, err = run_cmd(cwd, ["git", "tag", "--list"], env={"LC_ALL": "C"})
+    tags = out.decode("utf-8").strip().split("\n")
     return tags
 
 
 def _checkout(cwd, repo, revision):
-    logger.debug('  Checking out revision {}.'.format(revision))
+    fire_event(GitProgressCheckoutRevision(revision=revision))
 
     fetch_cmd = ["git", "fetch", "origin", "--depth", "1"]
 
     if _is_commit(revision):
         run_cmd(cwd, fetch_cmd + [revision])
     else:
-        run_cmd(cwd, ['git', 'remote', 'set-branches', 'origin', revision])
+        run_cmd(cwd, ["git", "remote", "set-branches", "origin", revision])
         run_cmd(cwd, fetch_cmd + ["--tags", revision])
 
     if _is_commit(revision):
         spec = revision
     # Prefer tags to branches if one exists
     elif revision in list_tags(cwd):
-        spec = 'tags/{}'.format(revision)
+        spec = "tags/{}".format(revision)
     else:
-        spec = 'origin/{}'.format(revision)
+        spec = "origin/{}".format(revision)
 
-    out, err = run_cmd(cwd, ['git', 'reset', '--hard', spec],
-                       env={'LC_ALL': 'C'})
+    out, err = run_cmd(cwd, ["git", "reset", "--hard", spec], env={"LC_ALL": "C"})
     return out, err
 
 
 def checkout(cwd, repo, revision=None):
     if revision is None:
-        revision = 'HEAD'
+        revision = "HEAD"
     try:
         return _checkout(cwd, repo, revision)
-    except dbt.exceptions.CommandResultError as exc:
-        stderr = exc.stderr.decode('utf-8').strip()
-    dbt.exceptions.bad_package_spec(repo, revision, stderr)
+    except CommandResultError as exc:
+        raise GitCheckoutError(repo=repo, revision=revision, error=exc)
 
 
 def get_current_sha(cwd):
-    out, err = run_cmd(cwd, ['git', 'rev-parse', 'HEAD'], env={'LC_ALL': 'C'})
+    out, err = run_cmd(cwd, ["git", "rev-parse", "HEAD"], env={"LC_ALL": "C"})
 
-    return out.decode('utf-8')
+    return out.decode("utf-8")
 
 
 def remove_remote(cwd):
-    return run_cmd(cwd, ['git', 'remote', 'rm', 'origin'], env={'LC_ALL': 'C'})
+    return run_cmd(cwd, ["git", "remote", "rm", "origin"], env={"LC_ALL": "C"})
 
 
-def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
-                       revision=None, subdirectory=None):
+def clone_and_checkout(
+    repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirectory=None
+):
     exists = None
     try:
         _, err = clone(
@@ -108,35 +130,34 @@ def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
             remove_git_dir=remove_git_dir,
             subdirectory=subdirectory,
         )
-    except dbt.exceptions.CommandResultError as exc:
-        err = exc.stderr.decode('utf-8')
+    except CommandResultError as exc:
+        err = exc.stderr
         exists = re.match("fatal: destination path '(.+)' already exists", err)
-        if not exists:  # something else is wrong, raise it
-            raise
+        if not exists:
+            raise UnknownGitCloningProblemError(repo)
 
     directory = None
     start_sha = None
     if exists:
         directory = exists.group(1)
-        logger.debug('Updating existing dependency {}.', directory)
+        fire_event(GitProgressUpdatingExistingDependency(dir=directory))
     else:
-        matches = re.match("Cloning into '(.+)'", err.decode('utf-8'))
+        matches = re.match("Cloning into '(.+)'", err.decode("utf-8"))
         if matches is None:
-            raise dbt.exceptions.RuntimeException(
-                f'Error cloning {repo} - never saw "Cloning into ..." from git'
-            )
+            raise DbtRuntimeError(f'Error cloning {repo} - never saw "Cloning into ..." from git')
         directory = matches.group(1)
-        logger.debug('Pulling new dependency {}.', directory)
+        fire_event(GitProgressPullingNewDependency(dir=directory))
     full_path = os.path.join(cwd, directory)
     start_sha = get_current_sha(full_path)
     checkout(full_path, repo, revision)
     end_sha = get_current_sha(full_path)
     if exists:
         if start_sha == end_sha:
-            logger.debug('  Already at {}, nothing to do.', start_sha[:7])
+            fire_event(GitNothingToDo(sha=start_sha[:7]))
         else:
-            logger.debug('  Updated checkout from {} to {}.',
-                         start_sha[:7], end_sha[:7])
+            fire_event(
+                GitProgressUpdatedCheckoutRange(start_sha=start_sha[:7], end_sha=end_sha[:7])
+            )
     else:
-        logger.debug('  Checked out at {}.', end_sha[:7])
-    return os.path.join(directory, subdirectory or '')
+        fire_event(GitProgressCheckedOutAt(end_sha=end_sha[:7]))
+    return os.path.join(directory, subdirectory or "")

core/dbt/clients/jinja.py

@@ -7,10 +7,7 @@ import threading
 from ast import literal_eval
 from contextlib import contextmanager
 from itertools import chain, islice
-from typing import (
-    List, Union, Set, Optional, Dict, Any, Iterator, Type, NoReturn, Tuple,
-    Callable
-)
+from typing import List, Union, Set, Optional, Dict, Any, Iterator, Type, NoReturn, Tuple, Callable
 
 import jinja2
 import jinja2.ext
@@ -20,20 +17,34 @@ import jinja2.parser
 import jinja2.sandbox
 
 from dbt.utils import (
-    get_dbt_macro_name, get_docs_macro_name, get_materialization_macro_name,
-    get_test_macro_name, deep_map
+    get_dbt_macro_name,
+    get_docs_macro_name,
+    get_materialization_macro_name,
+    get_test_macro_name,
+    deep_map_render,
 )
 
 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, MacroReturn, JinjaRenderingException,
-    UndefinedMacroException
+    CaughtMacroError,
+    CaughtMacroErrorWithNodeError,
+    CompilationError,
+    DbtInternalError,
+    MaterializationArgError,
+    JinjaRenderingError,
+    MacroReturn,
+    MaterializtionMacroNotUsedError,
+    NoSupportedLanguagesFoundError,
+    UndefinedCompilationError,
+    UndefinedMacroError,
 )
 from dbt import flags
-from dbt.logger import GLOBAL_LOGGER as logger  # noqa
+from dbt.node_types import ModelLanguage
+
+
+SUPPORTED_LANG_ARG = jinja2.nodes.Name("supported_languages", "param")
 
 
 def _linecache_inject(source, write):
@@ -41,27 +52,22 @@ def _linecache_inject(source, write):
         # this is the only reliable way to accomplish this. Obviously, it's
         # really darn noisy and will fill your temporary directory
         tmp_file = tempfile.NamedTemporaryFile(
-            prefix='dbt-macro-compiled-',
-            suffix='.py',
+            prefix="dbt-macro-compiled-",
+            suffix=".py",
             delete=False,
-            mode='w+',
-            encoding='utf-8',
+            mode="w+",
+            encoding="utf-8",
         )
         tmp_file.write(source)
         filename = tmp_file.name
     else:
         # `codecs.encode` actually takes a `bytes` as the first argument if
         # the second argument is 'hex' - mypy does not know this.
-        rnd = codecs.encode(os.urandom(12), 'hex')  # type: ignore
-        filename = rnd.decode('ascii')
+        rnd = codecs.encode(os.urandom(12), "hex")  # type: ignore
+        filename = rnd.decode("ascii")
 
     # put ourselves in the cache
-    cache_entry = (
-        len(source),
-        None,
-        [line + '\n' for line in source.splitlines()],
-        filename
-    )
+    cache_entry = (len(source), None, [line + "\n" for line in source.splitlines()], filename)
     # linecache does in fact have an attribute `cache`, thanks
     linecache.cache[filename] = cache_entry  # type: ignore
     return filename
@@ -74,12 +80,10 @@ class MacroFuzzParser(jinja2.parser.Parser):
         # modified to fuzz macros defined in the same file. this way
         # dbt can understand the stack of macros being called.
         #  - @cmcarthur
-        node.name = get_dbt_macro_name(
-            self.parse_assign_target(name_only=True).name)
+        node.name = get_dbt_macro_name(self.parse_assign_target(name_only=True).name)
 
         self.parse_signature(node)
-        node.body = self.parse_statements(('name:endmacro',),
-                                          drop_needle=True)
+        node.body = self.parse_statements(("name:endmacro",), drop_needle=True)
         return node
 
 
@@ -95,8 +99,8 @@ class MacroFuzzEnvironment(jinja2.sandbox.SandboxedEnvironment):
         If the value is 'write', also write the files to disk.
         WARNING: This can write a ton of data if you aren't careful.
         """
-        if filename == '<template>' and flags.MACRO_DEBUGGING:
-            write = flags.MACRO_DEBUGGING == 'write'
+        if filename == "<template>" and flags.MACRO_DEBUGGING:
+            write = flags.MACRO_DEBUGGING == "write"
             filename = _linecache_inject(source, write)
 
         return super()._compile(source, filename)  # type: ignore
@@ -107,7 +111,7 @@ class NativeSandboxEnvironment(MacroFuzzEnvironment):
 
 
 class TextMarker(str):
-    """A special native-env marker that indicates that a value is text and is
+    """A special native-env marker that indicates a value is text and is
     not to be evaluated. Use this to prevent your numbery-strings from becoming
     numbers!
     """
@@ -139,7 +143,7 @@ def quoted_native_concat(nodes):
     head = list(islice(nodes, 2))
 
     if not head:
-        return ''
+        return ""
 
     if len(head) == 1:
         raw = head[0]
@@ -157,19 +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
@@ -181,9 +181,7 @@ class NativeSandboxTemplate(jinja2.nativetypes.NativeTemplate):  # mypy: ignore
         vars = dict(*args, **kwargs)
 
         try:
-            return quoted_native_concat(
-                self.root_render_func(self.new_context(vars))
-            )
+            return quoted_native_concat(self.root_render_func(self.new_context(vars)))
         except Exception:
             return self.environment.handle_exception()
 
@@ -222,10 +220,10 @@ class BaseMacroGenerator:
         self.context: Optional[Dict[str, Any]] = context
 
     def get_template(self):
-        raise NotImplementedError('get_template not implemented!')
+        raise NotImplementedError("get_template not implemented!")
 
     def get_name(self) -> str:
-        raise NotImplementedError('get_name not implemented!')
+        raise NotImplementedError("get_name not implemented!")
 
     def get_macro(self):
         name = self.get_name()
@@ -243,14 +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()
@@ -277,7 +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):
@@ -286,7 +282,7 @@ class MacroGenerator(BaseMacroGenerator):
         macro,
         context: Optional[Dict[str, Any]] = None,
         node: Optional[Any] = None,
-        stack: Optional[MacroStack] = None
+        stack: Optional[MacroStack] = None,
     ) -> None:
         super().__init__(context)
         self.macro = macro
@@ -304,8 +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
 
@@ -313,13 +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:
@@ -334,9 +330,7 @@ class MacroGenerator(BaseMacroGenerator):
 
 
 class QueryStringGenerator(BaseMacroGenerator):
-    def __init__(
-        self, template_str: str, context: Dict[str, Any]
-    ) -> None:
+    def __init__(self, template_str: str, context: Dict[str, Any]) -> None:
         super().__init__(context)
         self.template_str: str = template_str
         env = get_environment()
@@ -346,7 +340,7 @@ class QueryStringGenerator(BaseMacroGenerator):
         )
 
     def get_name(self) -> str:
-        return 'query_comment_macro'
+        return "query_comment_macro"
 
     def get_template(self):
         """Don't use the template cache, we don't have a node"""
@@ -357,45 +351,50 @@ class QueryStringGenerator(BaseMacroGenerator):
 
 
 class MaterializationExtension(jinja2.ext.Extension):
-    tags = ['materialization']
+    tags = ["materialization"]
 
     def parse(self, parser):
         node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
-        materialization_name = \
-            parser.parse_assign_target(name_only=True).name
+        materialization_name = parser.parse_assign_target(name_only=True).name
 
-        adapter_name = 'default'
+        adapter_name = "default"
         node.args = []
         node.defaults = []
 
-        while parser.stream.skip_if('comma'):
+        while parser.stream.skip_if("comma"):
             target = parser.parse_assign_target(name_only=True)
 
-            if target.name == 'default':
+            if target.name == "default":
                 pass
 
-            elif target.name == 'adapter':
-                parser.stream.expect('assign')
+            elif target.name == "adapter":
+                parser.stream.expect("assign")
                 value = parser.parse_expression()
                 adapter_name = value.value
 
+            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)
 
-        node.name = get_materialization_macro_name(
-            materialization_name, adapter_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.body = parser.parse_statements(('name:endmaterialization',),
-                                            drop_needle=True)
+        node.name = get_materialization_macro_name(materialization_name, adapter_name)
+
+        node.body = parser.parse_statements(("name:endmaterialization",), drop_needle=True)
 
         return node
 
 
 class DocumentationExtension(jinja2.ext.Extension):
-    tags = ['docs']
+    tags = ["docs"]
 
     def parse(self, parser):
         node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
@@ -404,13 +403,12 @@ class DocumentationExtension(jinja2.ext.Extension):
         node.args = []
         node.defaults = []
         node.name = get_docs_macro_name(docs_name)
-        node.body = parser.parse_statements(('name:enddocs',),
-                                            drop_needle=True)
+        node.body = parser.parse_statements(("name:enddocs",), drop_needle=True)
         return node
 
 
 class TestExtension(jinja2.ext.Extension):
-    tags = ['test']
+    tags = ["test"]
 
     def parse(self, parser):
         node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
@@ -418,13 +416,12 @@ class TestExtension(jinja2.ext.Extension):
 
         parser.parse_signature(node)
         node.name = get_test_macro_name(test_name)
-        node.body = parser.parse_statements(('name:endtest',),
-                                            drop_needle=True)
+        node.body = parser.parse_statements(("name:endtest",), drop_needle=True)
         return node
 
 
 def _is_dunder_name(name):
-    return name.startswith('__') and name.endswith('__')
+    return name.startswith("__") and name.endswith("__")
 
 
 def create_undefined(node=None):
@@ -445,10 +442,9 @@ def create_undefined(node=None):
             return self
 
         def __getattr__(self, name):
-            if name == 'name' or _is_dunder_name(name):
+            if name == "name" or _is_dunder_name(name):
                 raise AttributeError(
-                    "'{}' object has no attribute '{}'"
-                    .format(type(self).__name__, name)
+                    "'{}' object has no attribute '{}'".format(type(self).__name__, name)
                 )
 
             self.name = name
@@ -459,24 +455,24 @@ 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
 
 
 NATIVE_FILTERS: Dict[str, Callable[[Any], Any]] = {
-    'as_text': TextMarker,
-    'as_bool': BoolMarker,
-    'as_native': NativeMarker,
-    'as_number': NumberMarker,
+    "as_text": TextMarker,
+    "as_bool": BoolMarker,
+    "as_native": NativeMarker,
+    "as_number": NumberMarker,
 }
 
 
 TEXT_FILTERS: Dict[str, Callable[[Any], Any]] = {
-    'as_text': lambda x: x,
-    'as_bool': lambda x: x,
-    'as_native': lambda x: x,
-    'as_number': lambda x: x,
+    "as_text": lambda x: x,
+    "as_bool": lambda x: x,
+    "as_native": lambda x: x,
+    "as_number": lambda x: x,
 }
 
 
@@ -486,15 +482,15 @@ def get_environment(
     native: bool = False,
 ) -> jinja2.Environment:
     args: Dict[str, List[Union[str, Type[jinja2.ext.Extension]]]] = {
-        'extensions': ['jinja2.ext.do']
+        "extensions": ["jinja2.ext.do"]
     }
 
     if capture_macros:
-        args['undefined'] = create_undefined(node)
+        args["undefined"] = create_undefined(node)
 
-    args['extensions'].append(MaterializationExtension)
-    args['extensions'].append(DocumentationExtension)
-    args['extensions'].append(TestExtension)
+    args["extensions"].append(MaterializationExtension)
+    args["extensions"].append(DocumentationExtension)
+    args["extensions"].append(TestExtension)
 
     env_cls: Type[jinja2.Environment]
     text_filter: Type
@@ -517,10 +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
 
@@ -557,8 +553,8 @@ def _requote_result(raw_value: str, rendered: str) -> str:
     elif single_quoted:
         quote_char = "'"
     else:
-        quote_char = ''
-    return f'{quote_char}{rendered}{quote_char}'
+        quote_char = ""
+    return f"{quote_char}{rendered}{quote_char}"
 
 
 # performance note: Local benmcharking (so take it with a big grain of salt!)
@@ -566,7 +562,7 @@ def _requote_result(raw_value: str, rendered: str) -> str:
 # checking two separate patterns, but the standard deviation is smaller with
 # one pattern. The time difference between the two was ~2 std deviations, which
 # is small enough that I've just chosen the more readable option.
-_HAS_RENDER_CHARS_PAT = re.compile(r'({[{%#]|[#}%]})')
+_HAS_RENDER_CHARS_PAT = re.compile(r"({[{%#]|[#}%]})")
 
 
 def get_rendered(
@@ -582,11 +578,7 @@ def get_rendered(
     # If this is desirable in the native env as well, we could handle the
     # native=True case by passing the input string to ast.literal_eval, like
     # the native renderer does.
-    if (
-        not native and
-        isinstance(string, str) and
-        _HAS_RENDER_CHARS_PAT.search(string) is None
-    ):
+    if not native and isinstance(string, str) and _HAS_RENDER_CHARS_PAT.search(string) is None:
         return string
     template = get_template(
         string,
@@ -607,7 +599,7 @@ def extract_toplevel_blocks(
     allowed_blocks: Optional[Set[str]] = None,
     collect_raw_data: bool = True,
 ) -> List[Union[BlockData, BlockTag]]:
-    """Extract the top level blocks with matching block types from a jinja
+    """Extract the top-level blocks with matching block types from a jinja
     file, with some special handling for block nesting.
 
     :param data: The data to extract blocks from.
@@ -622,44 +614,58 @@ def extract_toplevel_blocks(
         `collect_raw_data` is `True`) `BlockData` objects.
     """
     return BlockIterator(data).lex_for_blocks(
-        allowed_blocks=allowed_blocks,
-        collect_raw_data=collect_raw_data
+        allowed_blocks=allowed_blocks, collect_raw_data=collect_raw_data
     )
 
 
-GENERIC_TEST_KWARGS_NAME = '_dbt_generic_test_kwargs'
+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
     renderer, then insert that value into the given context as the special test
     keyword arguments member.
     """
-    looks_like_func = r'^\s*(env_var|ref|var|source|doc)\s*\(.+\)\s*$'
+    looks_like_func = r"^\s*(env_var|ref|var|source|doc)\s*\(.+\)\s*$"
 
-    def _convert_function(
-        value: Any, keypath: Tuple[Union[str, int], ...]
-    ) -> Any:
+    def _convert_function(value: Any, keypath: Tuple[Union[str, int], ...]) -> Any:
         if isinstance(value, str):
-            if keypath == ('column_name',):
+            if keypath == ("column_name",):
                 # special case: Don't render column names as native, make them
                 # be strings
                 return value
 
             if re.match(looks_like_func, value) is not None:
                 # curly braces to make rendering happy
-                value = f'{{{{ {value} }}}}'
+                value = f"{{{{ {value} }}}}"
 
-            value = get_rendered(
-                value, context, node, capture_macros=capture_macros,
-                native=True
-            )
+            value = get_rendered(value, context, node, capture_macros=capture_macros, native=True)
 
         return value
 
-    kwargs = deep_map(_convert_function, node.test_metadata.kwargs)
+    # The test_metadata.kwargs come from the test builder, and were set
+    # 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):
@@ -8,14 +8,14 @@ def statically_extract_macro_calls(string, ctx, db_wrapper=None):
     env = get_environment(None, capture_macros=True)
     parsed = env.parse(string)
 
-    standard_calls = ['source', 'ref', 'config']
+    standard_calls = ["source", "ref", "config"]
     possible_macro_calls = []
     for func_call in parsed.find_all(jinja2.nodes.Call):
         func_name = None
-        if hasattr(func_call, 'node') and hasattr(func_call.node, 'name'):
+        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(
@@ -30,22 +30,25 @@ def statically_extract_macro_calls(string, ctx, db_wrapper=None):
             #   dyn_args=None,
             #   dyn_kwargs=None
             # )
-            if (hasattr(func_call, 'node') and
-                    hasattr(func_call.node, 'node') and
-                    type(func_call.node.node).__name__ == 'Name' and
-                    hasattr(func_call.node, 'attr')):
+            if (
+                hasattr(func_call, "node")
+                and hasattr(func_call.node, "node")
+                and type(func_call.node.node).__name__ == "Name"
+                and hasattr(func_call.node, "attr")
+            ):
                 package_name = func_call.node.node.name
                 macro_name = func_call.node.attr
-                if package_name == 'adapter':
-                    if macro_name == 'dispatch':
+                if package_name == "adapter":
+                    if macro_name == "dispatch":
                         ad_macro_calls = statically_parse_adapter_dispatch(
-                            func_call, ctx, db_wrapper)
+                            func_call, ctx, db_wrapper
+                        )
                         possible_macro_calls.extend(ad_macro_calls)
                     else:
                         # This skips calls such as adapter.parse_index
                         continue
                 else:
-                    func_name = f'{package_name}.{macro_name}'
+                    func_name = f"{package_name}.{macro_name}"
             else:
                 continue
         if not func_name:
@@ -108,40 +111,35 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
     # keyword arguments
     if func_call.kwargs:
         for kwarg in func_call.kwargs:
-            if kwarg.key == 'macro_name':
+            if kwarg.key == "macro_name":
                 # This will remain to enable static resolution
-                if type(kwarg.value).__name__ == 'Const':
+                if type(kwarg.value).__name__ == "Const":
                     func_name = kwarg.value.value
                     possible_macro_calls.append(func_name)
                 else:
-                    raise_compiler_error(f"The macro_name parameter ({kwarg.value.value}) "
-                                         "to adapter.dispatch was not a string")
-            elif kwarg.key == 'macro_namespace':
+                    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':
+                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:
-        if packages_arg_type == 'List':
+        if packages_arg_type == "List":
             # This will remain to enable static resolution
             packages = []
             for item in packages_arg.items:
                 packages.append(item.value)
-        elif packages_arg_type == 'Const':
+        elif packages_arg_type == "Const":
             # This will remain to enable static resolution
             macro_namespace = packages_arg.value
 
     if db_wrapper:
-        macro = db_wrapper.dispatch(
-            func_name,
-            macro_namespace=macro_namespace
-        ).macro
-        func_name = f'{macro.package_name}.{macro.name}'
+        macro = db_wrapper.dispatch(func_name, macro_namespace=macro_namespace).macro
+        func_name = f"{macro.package_name}.{macro.name}"
         possible_macro_calls.append(func_name)
     else:  # this is only for test/unit/test_macro_calls.py
         if macro_namespace:
@@ -149,6 +147,6 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
         else:
             packages = []
         for package_name in packages:
-            possible_macro_calls.append(f'{package_name}.{func_name}')
+            possible_macro_calls.append(f"{package_name}.{func_name}")
 
     return possible_macro_calls

core/dbt/clients/registry.py

@@ -1,79 +1,191 @@
 import functools
+from typing import Any, Dict, List
 import requests
+from dbt.events.functions import fire_event
+from dbt.events.types import (
+    RegistryProgressGETRequest,
+    RegistryProgressGETResponse,
+    RegistryIndexProgressGETRequest,
+    RegistryIndexProgressGETResponse,
+    RegistryResponseUnexpectedType,
+    RegistryResponseMissingTopKeys,
+    RegistryResponseMissingNestedKeys,
+    RegistryResponseExtraNestedKeys,
+)
 from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
-from dbt.logger import GLOBAL_LOGGER as logger
 from dbt import deprecations
+from dbt import semver
 import os
 
-if os.getenv('DBT_PACKAGE_HUB_URL'):
-    DEFAULT_REGISTRY_BASE_URL = os.getenv('DBT_PACKAGE_HUB_URL')
+if os.getenv("DBT_PACKAGE_HUB_URL"):
+    DEFAULT_REGISTRY_BASE_URL = os.getenv("DBT_PACKAGE_HUB_URL")
 else:
-    DEFAULT_REGISTRY_BASE_URL = 'https://hub.getdbt.com/'
+    DEFAULT_REGISTRY_BASE_URL = "https://hub.getdbt.com/"
 
 
-def _get_url(url, registry_base_url=None):
+def _get_url(name, registry_base_url=None):
     if registry_base_url is None:
         registry_base_url = DEFAULT_REGISTRY_BASE_URL
+    url = "api/v1/{}.json".format(name)
 
-    return '{}{}'.format(registry_base_url, url)
+    return "{}{}".format(registry_base_url, url)
 
 
-def _get_with_retries(path, registry_base_url=None):
-    get_fn = functools.partial(_get, path, registry_base_url)
+def _get_with_retries(package_name, registry_base_url=None):
+    get_fn = functools.partial(_get, package_name, registry_base_url)
     return connection_exception_retry(get_fn, 5)
 
 
-def _get(path, registry_base_url=None):
-    url = _get_url(path, registry_base_url)
-    logger.debug('Making package registry request: GET {}'.format(url))
+def _get(package_name, registry_base_url=None):
+    url = _get_url(package_name, registry_base_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)
-    logger.debug('Response from registry: GET {} {}'.format(url,
-                                                            resp.status_code))
+    fire_event(RegistryProgressGETResponse(url=url, resp_code=resp.status_code))
     resp.raise_for_status()
-    return resp.json()
 
+    # The response should always be a dictionary.  Anything else is unexpected, raise error.
+    # Raising this error will cause this function to retry (if called within _get_with_retries)
+    # and hopefully get a valid response.  This seems to happen when there's an issue with the Hub.
+    # Since we control what we expect the HUB to return, this is safe.
+    # See https://github.com/dbt-labs/dbt-core/issues/4577
+    # and https://github.com/dbt-labs/dbt-core/issues/4849
+    response = resp.json()
 
-def index(registry_base_url=None):
-    return _get_with_retries('api/v1/index.json', registry_base_url)
+    if not isinstance(response, dict):  # This will also catch Nonetype
+        error_msg = (
+            f"Request error: Expected a response type of <dict> but got {type(response)} instead"
+        )
+        fire_event(RegistryResponseUnexpectedType(response=response))
+        raise requests.exceptions.ContentDecodingError(error_msg, response=resp)
 
+    # check for expected top level keys
+    expected_keys = {"name", "versions"}
+    if not expected_keys.issubset(response):
+        error_msg = (
+            f"Request error: Expected the response to contain keys {expected_keys} "
+            f"but is missing {expected_keys.difference(set(response))}"
+        )
+        fire_event(RegistryResponseMissingTopKeys(response=response))
+        raise requests.exceptions.ContentDecodingError(error_msg, response=resp)
 
-index_cached = memoized(index)
+    # check for the keys we need nested under each version
+    expected_version_keys = {"name", "packages", "downloads"}
+    all_keys = set().union(*(response["versions"][d] for d in response["versions"]))
+    if not expected_version_keys.issubset(all_keys):
+        error_msg = (
+            "Request error: Expected the response for the version to contain keys "
+            f"{expected_version_keys} but is missing {expected_version_keys.difference(all_keys)}"
+        )
+        fire_event(RegistryResponseMissingNestedKeys(response=response))
+        raise requests.exceptions.ContentDecodingError(error_msg, response=resp)
 
-
-def packages(registry_base_url=None):
-    return _get_with_retries('api/v1/packages.json', registry_base_url)
-
-
-def package(name, registry_base_url=None):
-    response = _get_with_retries('api/v1/{}.json'.format(name), registry_base_url)
-
-    # Either redirectnamespace or redirectname in the JSON response indicate a redirect
-    # redirectnamespace redirects based on package ownership
-    # redirectname redirects based on package name
-    # Both can be present at the same time, or neither. Fails gracefully to old name
-
-    if ('redirectnamespace' in response) or ('redirectname' in response):
-
-        if ('redirectnamespace' in response) and response['redirectnamespace'] is not None:
-            use_namespace = response['redirectnamespace']
-        else:
-            use_namespace = response['namespace']
-
-        if ('redirectname' in response) and response['redirectname'] is not None:
-            use_name = response['redirectname']
-        else:
-            use_name = response['name']
-
-        new_nwo = use_namespace + "/" + use_name
-        deprecations.warn('package-redirect', old_name=name, new_name=new_nwo)
+    # all version responses should contain identical keys.
+    has_extra_keys = set().difference(*(response["versions"][d] for d in response["versions"]))
+    if has_extra_keys:
+        error_msg = (
+            "Request error: Keys for all versions do not match.  Found extra key(s) "
+            f"of {has_extra_keys}."
+        )
+        fire_event(RegistryResponseExtraNestedKeys(response=response))
+        raise requests.exceptions.ContentDecodingError(error_msg, response=resp)
 
     return response
 
 
-def package_version(name, version, registry_base_url=None):
-    return _get_with_retries('api/v1/{}/{}.json'.format(name, version), registry_base_url)
+_get_cached = memoized(_get_with_retries)
 
 
-def get_available_versions(name):
-    response = package(name)
-    return list(response['versions'])
+def package(package_name, registry_base_url=None) -> Dict[str, Any]:
+    # returns a dictionary of metadata for all versions of a package
+    response = _get_cached(package_name, registry_base_url)
+    # Either redirectnamespace or redirectname in the JSON response indicate a redirect
+    # redirectnamespace redirects based on package ownership
+    # redirectname redirects based on package name
+    # Both can be present at the same time, or neither. Fails gracefully to old name
+    if ("redirectnamespace" in response) or ("redirectname" in response):
+
+        if ("redirectnamespace" in response) and response["redirectnamespace"] is not None:
+            use_namespace = response["redirectnamespace"]
+        else:
+            use_namespace = response["namespace"]
+
+        if ("redirectname" in response) and response["redirectname"] is not None:
+            use_name = response["redirectname"]
+        else:
+            use_name = response["name"]
+
+        new_nwo = use_namespace + "/" + use_name
+        deprecations.warn("package-redirect", old_name=package_name, new_name=new_nwo)
+    return response["versions"]
+
+
+def package_version(package_name, version, registry_base_url=None) -> Dict[str, Any]:
+    # returns the metadata of a specific version of a package
+    response = package(package_name, registry_base_url)
+    return response[version]
+
+
+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)
+
+    # 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(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))
+    resp.raise_for_status()
+
+    # The response should be a list.  Anything else is unexpected, raise an error.
+    # Raising this error will cause this function to retry and hopefully get a valid response.
+
+    response = resp.json()
+
+    if not isinstance(response, list):  # This will also catch Nonetype
+        error_msg = (
+            f"Request error: The response type of {type(response)} is not valid: {resp.text}"
+        )
+        raise requests.exceptions.ContentDecodingError(error_msg, response=resp)
+
+    return response
+
+
+def index(registry_base_url=None) -> List[str]:
+    # this returns a list of all packages on the Hub
+    get_index_fn = functools.partial(_get_index, registry_base_url)
+    return connection_exception_retry(get_index_fn, 5)
+
+
+index_cached = memoized(index)

core/dbt/clients/system.py

@@ -11,15 +11,22 @@ import sys
 import tarfile
 import requests
 import stat
-from typing import (
-    Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
-)
+from typing import Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
+from pathspec import PathSpec  # type: ignore
 
+from dbt.events.functions import fire_event
+from dbt.events.types import (
+    SystemErrorRetrievingModTime,
+    SystemCouldNotWrite,
+    SystemExecutingCmd,
+    SystemStdOut,
+    SystemStdErr,
+    SystemReportReturnCode,
+)
 import dbt.exceptions
-from dbt.logger import GLOBAL_LOGGER as logger
 from dbt.utils import _connection_exception_retry as connection_exception_retry
 
-if sys.platform == 'win32':
+if sys.platform == "win32":
     from ctypes import WinDLL, c_bool
 else:
     WinDLL = None
@@ -30,6 +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
@@ -51,38 +59,46 @@ def find_matching(
     reobj = re.compile(regex, re.IGNORECASE)
 
     for relative_path_to_search in relative_paths_to_search:
-        absolute_path_to_search = os.path.join(
-            root_path, relative_path_to_search)
+        # 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 = 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:
-                    logger.exception(
-                        f"Error retrieving modification time for file {absolute_path}"
+                    fire_event(SystemErrorRetrievingModTime(path=absolute_path))
+                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,
+                            "absolute_path": absolute_path,
+                            "relative_path": relative_path,
+                            "modification_time": modification_time,
+                        }
                     )
-                if reobj.match(local_file):
-                    matching.append({
-                        'searched_path': relative_path_to_search,
-                        'absolute_path': absolute_path,
-                        'relative_path': relative_path,
-                        'modification_time': modification_time,
-                    })
 
     return matching
 
 
 def load_file_contents(path: str, strip: bool = True) -> str:
     path = convert_path(path)
-    with open(path, 'rb') as handle:
-        to_return = handle.read().decode('utf-8')
+    with open(path, "rb") as handle:
+        to_return = handle.read().decode("utf-8")
 
     if strip:
         to_return = to_return.strip()
@@ -109,14 +125,14 @@ def make_directory(path: str) -> None:
                 raise e
 
 
-def make_file(path: str, contents: str = '', overwrite: bool = False) -> bool:
+def make_file(path: str, contents: str = "", overwrite: bool = False) -> bool:
     """
     Make a file at `path` assuming that the directory it resides in already
     exists. The file is saved with contents `contents`
     """
     if overwrite or not os.path.exists(path):
         path = convert_path(path)
-        with open(path, 'w') as fh:
+        with open(path, "w") as fh:
             fh.write(contents)
         return True
 
@@ -128,7 +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)
 
@@ -137,11 +154,11 @@ def supports_symlinks() -> bool:
     return getattr(os, "symlink", None) is not None
 
 
-def write_file(path: str, contents: str = '') -> bool:
+def write_file(path: str, contents: str = "") -> bool:
     path = convert_path(path)
     try:
         make_directory(os.path.dirname(path))
-        with open(path, 'w', encoding='utf-8') as f:
+        with open(path, "w", encoding="utf-8") as f:
             f.write(str(contents))
     except Exception as exc:
         # note that you can't just catch FileNotFound, because sometimes
@@ -150,21 +167,18 @@ def write_file(path: str, contents: str = '') -> bool:
         # sometimes windows fails to write paths that are less than the length
         # limit. So on windows, suppress all errors that happen from writing
         # to disk.
-        if os.name == 'nt':
+        if os.name == "nt":
             # sometimes we get a winerror of 3 which means the path was
             # definitely too long, but other times we don't and it means the
             # path was just probably too long. This is probably based on the
             # windows/python version.
-            if getattr(exc, 'winerror', 0) == 3:
-                reason = 'Path was too long'
+            if getattr(exc, "winerror", 0) == 3:
+                reason = "Path was too long"
             else:
-                reason = 'Path was possibly too long'
+                reason = "Path was possibly too long"
             # all our hard work and the path was still too long. Log and
             # continue.
-            logger.debug(
-                f'Could not write to path {path}({len(path)} characters): '
-                f'{reason}\nexception: {exc}'
-            )
+            fire_event(SystemCouldNotWrite(path=path, reason=reason, exc=str(exc)))
         else:
             raise
     return True
@@ -178,9 +192,7 @@ def write_json(path: str, data: Dict[str, Any]) -> bool:
     return write_file(path, json.dumps(data, cls=dbt.utils.JSONEncoder))
 
 
-def _windows_rmdir_readonly(
-    func: Callable[[str], Any], path: str, exc: Tuple[Any, OSError, Any]
-):
+def _windows_rmdir_readonly(func: Callable[[str], Any], path: str, exc: Tuple[Any, OSError, Any]):
     exception_val = exc[1]
     if exception_val.errno == errno.EACCES:
         os.chmod(path, stat.S_IWUSR)
@@ -197,10 +209,7 @@ def resolve_path_from_base(path_to_resolve: str, base_path: str) -> str:
     If path_to_resolve is an absolute path or a user path (~), just
     resolve it to an absolute path and return.
     """
-    return os.path.abspath(
-        os.path.join(
-            base_path,
-            os.path.expanduser(path_to_resolve)))
+    return os.path.abspath(os.path.join(base_path, os.path.expanduser(path_to_resolve)))
 
 
 def rmdir(path: str) -> None:
@@ -210,7 +219,7 @@ def rmdir(path: str) -> None:
     cloned via git) can cause rmtree to throw a PermissionError exception
     """
     path = convert_path(path)
-    if sys.platform == 'win32':
+    if sys.platform == "win32":
         onerror = _windows_rmdir_readonly
     else:
         onerror = None
@@ -229,7 +238,7 @@ def _win_prepare_path(path: str) -> str:
     # letter back in.
     # Unless it starts with '\\'. In that case, the path is a UNC mount point
     # and splitdrive will be fine.
-    if not path.startswith('\\\\') and path.startswith('\\'):
+    if not path.startswith("\\\\") and path.startswith("\\"):
         curdrive = os.path.splitdrive(os.getcwd())[0]
         path = curdrive + path
 
@@ -244,23 +253,24 @@ def _win_prepare_path(path: str) -> str:
 
 
 def _supports_long_paths() -> bool:
-    if sys.platform != 'win32':
+    if sys.platform != "win32":
         return True
     # Eryk Sun says to use `WinDLL('ntdll')` instead of `windll.ntdll` because
     # of pointer caching in a comment here:
     # https://stackoverflow.com/a/35097999/11262881
     # I don't know exaclty what he means, but I am inclined to believe him as
     # he's pretty active on Python windows bugs!
-    try:
-        dll = WinDLL('ntdll')
-    except OSError:  # I don't think this happens? you need ntdll to run python
-        return False
-    # not all windows versions have it at all
-    if not hasattr(dll, 'RtlAreLongPathsEnabled'):
-        return False
-    # tell windows we want to get back a single unsigned byte (a bool).
-    dll.RtlAreLongPathsEnabled.restype = c_bool
-    return dll.RtlAreLongPathsEnabled()
+    else:
+        try:
+            dll = WinDLL("ntdll")
+        except OSError:  # I don't think this happens? you need ntdll to run python
+            return False
+        # not all windows versions have it at all
+        if not hasattr(dll, "RtlAreLongPathsEnabled"):
+            return False
+        # tell windows we want to get back a single unsigned byte (a bool).
+        dll.RtlAreLongPathsEnabled.restype = c_bool
+        return dll.RtlAreLongPathsEnabled()
 
 
 def convert_path(path: str) -> str:
@@ -276,7 +286,7 @@ def convert_path(path: str) -> str:
     if _supports_long_paths():
         return path
 
-    prefix = '\\\\?\\'
+    prefix = "\\\\?\\"
     # Nothing to do
     if path.startswith(prefix):
         return path
@@ -307,44 +317,40 @@ def path_is_symlink(path: str) -> bool:
 
 def open_dir_cmd() -> str:
     # https://docs.python.org/2/library/sys.html#sys.platform
-    if sys.platform == 'win32':
-        return 'start'
+    if sys.platform == "win32":
+        return "start"
 
-    elif sys.platform == 'darwin':
-        return 'open'
+    elif sys.platform == "darwin":
+        return "open"
 
     else:
-        return 'xdg-open'
+        return "xdg-open"
 
 
-def _handle_posix_cwd_error(
-    exc: OSError, cwd: str, cmd: List[str]
-) -> NoReturn:
+def _handle_posix_cwd_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
     if exc.errno == errno.ENOENT:
-        message = 'Directory does not exist'
+        message = "Directory does not exist"
     elif exc.errno == errno.EACCES:
-        message = 'Current user cannot access directory, check permissions'
+        message = "Current user cannot access directory, check permissions"
     elif exc.errno == errno.ENOTDIR:
-        message = 'Not a directory'
+        message = "Not a directory"
     else:
-        message = 'Unknown OSError: {} - cwd'.format(str(exc))
+        message = "Unknown OSError: {} - cwd".format(str(exc))
     raise dbt.exceptions.WorkingDirectoryError(cwd, cmd, message)
 
 
-def _handle_posix_cmd_error(
-    exc: OSError, cwd: str, cmd: List[str]
-) -> NoReturn:
+def _handle_posix_cmd_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
     if exc.errno == errno.ENOENT:
         message = "Could not find command, ensure it is in the user's PATH"
     elif exc.errno == errno.EACCES:
-        message = 'User does not have permissions for this command'
+        message = "User does not have permissions for this command"
     else:
-        message = 'Unknown OSError: {} - cmd'.format(str(exc))
+        message = "Unknown OSError: {} - cmd".format(str(exc))
     raise dbt.exceptions.ExecutableError(cwd, cmd, message)
 
 
 def _handle_posix_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
-    """OSError handling for posix systems.
+    """OSError handling for POSIX systems.
 
     Some things that could happen to trigger an OSError:
         - cwd could not exist
@@ -364,7 +370,7 @@ def _handle_posix_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
             - exc.errno == EACCES
             - exc.filename == None(?)
     """
-    if getattr(exc, 'filename', None) == cwd:
+    if getattr(exc, "filename", None) == cwd:
         _handle_posix_cwd_error(exc, cwd, cmd)
     else:
         _handle_posix_cmd_error(exc, cwd, cmd)
@@ -373,46 +379,46 @@ def _handle_posix_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
 def _handle_windows_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
     cls: Type[dbt.exceptions.Exception] = dbt.exceptions.CommandError
     if exc.errno == errno.ENOENT:
-        message = ("Could not find command, ensure it is in the user's PATH "
-                   "and that the user has permissions to run it")
+        message = (
+            "Could not find command, ensure it is in the user's PATH "
+            "and that the user has permissions to run it"
+        )
         cls = dbt.exceptions.ExecutableError
     elif exc.errno == errno.ENOEXEC:
-        message = ('Command was not executable, ensure it is valid')
+        message = "Command was not executable, ensure it is valid"
         cls = dbt.exceptions.ExecutableError
     elif exc.errno == errno.ENOTDIR:
-        message = ('Unable to cd: path does not exist, user does not have'
-                   ' permissions, or not a directory')
+        message = (
+            "Unable to cd: path does not exist, user does not have"
+            " permissions, or not a directory"
+        )
         cls = dbt.exceptions.WorkingDirectoryError
     else:
         message = 'Unknown error: {} (errno={}: "{}")'.format(
-            str(exc), exc.errno, errno.errorcode.get(exc.errno, '<Unknown!>')
+            str(exc), exc.errno, errno.errorcode.get(exc.errno, "<Unknown!>")
         )
     raise cls(cwd, cmd, message)
 
 
 def _interpret_oserror(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
-    """Interpret an OSError exc and raise the appropriate dbt exception.
-
-    """
+    """Interpret an OSError exception and raise the appropriate dbt exception."""
     if len(cmd) == 0:
         raise dbt.exceptions.CommandError(cwd, cmd)
 
     # all of these functions raise unconditionally
-    if os.name == 'nt':
+    if os.name == "nt":
         _handle_windows_error(exc, cwd, cmd)
     else:
         _handle_posix_error(exc, cwd, cmd)
 
     # this should not be reachable, raise _something_ at least!
-    raise dbt.exceptions.InternalException(
-        'Unhandled exception in _interpret_oserror: {}'.format(exc)
+    raise dbt.exceptions.DbtInternalError(
+        "Unhandled exception in _interpret_oserror: {}".format(exc)
     )
 
 
-def run_cmd(
-    cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None
-) -> Tuple[bytes, bytes]:
-    logger.debug('Executing "{}"'.format(' '.join(cmd)))
+def run_cmd(cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None) -> Tuple[bytes, bytes]:
+    fire_event(SystemExecutingCmd(cmd=cmd))
     if len(cmd) == 0:
         raise dbt.exceptions.CommandError(cwd, cmd)
 
@@ -428,23 +434,19 @@ def run_cmd(
         if exe_pth:
             cmd = [os.path.abspath(exe_pth)] + list(cmd[1:])
         proc = subprocess.Popen(
-            cmd,
-            cwd=cwd,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            env=full_env)
+            cmd, cwd=cwd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=full_env
+        )
 
         out, err = proc.communicate()
     except OSError as exc:
         _interpret_oserror(exc, cwd, cmd)
 
-    logger.debug('STDOUT: "{!s}"'.format(out))
-    logger.debug('STDERR: "{!s}"'.format(err))
+    fire_event(SystemStdOut(bmsg=out))
+    fire_event(SystemStdErr(bmsg=err))
 
     if proc.returncode != 0:
-        logger.debug('command return code={}'.format(proc.returncode))
-        raise dbt.exceptions.CommandResultError(cwd, cmd, proc.returncode,
-                                                out, err)
+        fire_event(SystemReportReturnCode(returncode=proc.returncode))
+        raise dbt.exceptions.CommandResultError(cwd, cmd, proc.returncode, out, err)
 
     return out, err
 
@@ -457,12 +459,14 @@ def download_with_retries(
 
 
 def download(
-    url: str, path: str, timeout: Optional[Union[float, tuple]] = None
+    url: str,
+    path: str,
+    timeout: Optional[Union[float, Tuple[float, float], Tuple[float, None]]] = None,
 ) -> None:
     path = convert_path(path)
-    connection_timeout = timeout or float(os.getenv('DBT_HTTP_TIMEOUT', 10))
+    connection_timeout = timeout or float(os.getenv("DBT_HTTP_TIMEOUT", 10))
     response = requests.get(url, timeout=connection_timeout)
-    with open(path, 'wb') as handle:
+    with open(path, "wb") as handle:
         for block in response.iter_content(1024 * 64):
             handle.write(block)
 
@@ -481,12 +485,10 @@ def rename(from_path: str, to_path: str, force: bool = False) -> None:
     shutil.move(from_path, to_path)
 
 
-def untar_package(
-    tar_path: str, dest_dir: str, rename_to: Optional[str] = None
-) -> None:
+def untar_package(tar_path: str, dest_dir: str, rename_to: Optional[str] = None) -> None:
     tar_path = convert_path(tar_path)
     tar_dir_name = None
-    with tarfile.open(tar_path, 'r') as tarball:
+    with tarfile.open(tar_path, "r:gz") as tarball:
         tarball.extractall(dest_dir)
         tar_dir_name = os.path.commonprefix(tarball.getnames())
     if rename_to:
@@ -502,7 +504,7 @@ def chmod_and_retry(func, path, exc_info):
     We want to retry most operations here, but listdir is one that we know will
     be useless.
     """
-    if func is os.listdir or os.name != 'nt':
+    if func is os.listdir or os.name != "nt":
         raise
     os.chmod(path, stat.S_IREAD | stat.S_IWRITE)
     # on error,this will raise.
@@ -518,12 +520,12 @@ def move(src, dst):
     directory on windows when it has read-only files in it and the move is
     between two drives.
 
-    This is almost identical to the real shutil.move, except it uses our rmtree
+    This is almost identical to the real shutil.move, except it, uses our rmtree
     and skips handling non-windows OSes since the existing one works ok there.
     """
     src = convert_path(src)
     dst = convert_path(dst)
-    if os.name != 'nt':
+    if os.name != "nt":
         return shutil.move(src, dst)
 
     if os.path.isdir(dst):
@@ -531,7 +533,7 @@ def move(src, dst):
             os.rename(src, dst)
             return
 
-        dst = os.path.join(dst, os.path.basename(src.rstrip('/\\')))
+        dst = os.path.join(dst, os.path.basename(src.rstrip("/\\")))
         if os.path.exists(dst):
             raise EnvironmentError("Path '{}' already exists".format(dst))
 
@@ -540,11 +542,10 @@ def move(src, dst):
     except OSError:
         # probably different drives
         if os.path.isdir(src):
-            if _absnorm(dst + '\\').startswith(_absnorm(src + '\\')):
+            if _absnorm(dst + "\\").startswith(_absnorm(src + "\\")):
                 # dst is inside src
                 raise EnvironmentError(
-                    "Cannot move a directory '{}' into itself '{}'"
-                    .format(src, dst)
+                    "Cannot move a directory '{}' into itself '{}'".format(src, dst)
                 )
             shutil.copytree(src, dst, symlinks=True)
             rmtree(src)
@@ -554,7 +555,7 @@ def move(src, dst):
 
 
 def rmtree(path):
-    """Recursively remove path. On permissions errors on windows, try to remove
+    """Recursively remove the path. On permissions errors on windows, try to remove
     the read-only flag and try again.
     """
     path = convert_path(path)

core/dbt/clients/yaml_helper.py

@@ -4,15 +4,9 @@ import yaml
 
 # the C version is faster, but it doesn't always exist
 try:
-    from yaml import (
-        CLoader as Loader,
-        CSafeLoader as SafeLoader,
-        CDumper as Dumper
-    )
+    from yaml import CLoader as Loader, CSafeLoader as SafeLoader, CDumper as Dumper
 except ImportError:
-    from yaml import (  # type: ignore  # noqa: F401
-        Loader, SafeLoader, Dumper
-    )
+    from yaml import Loader, SafeLoader, Dumper  # type: ignore  # noqa: F401
 
 
 YAML_ERROR_MESSAGE = """
@@ -32,14 +26,12 @@ def line_no(i, line, width=3):
 
 
 def prefix_with_line_numbers(string, no_start, no_end):
-    line_list = string.split('\n')
+    line_list = string.split("\n")
 
     numbers = range(no_start, no_end)
     relevant_lines = line_list[no_start:no_end]
 
-    return "\n".join([
-        line_no(i + 1, line) for (i, line) in zip(numbers, relevant_lines)
-    ])
+    return "\n".join([line_no(i + 1, line) for (i, line) in zip(numbers, relevant_lines)])
 
 
 def contextualized_yaml_error(raw_contents, error):
@@ -50,22 +42,22 @@ def contextualized_yaml_error(raw_contents, error):
 
     nice_error = prefix_with_line_numbers(raw_contents, min_line, max_line)
 
-    return YAML_ERROR_MESSAGE.format(line_number=mark.line + 1,
-                                     nice_error=nice_error,
-                                     raw_error=error)
+    return YAML_ERROR_MESSAGE.format(
+        line_number=mark.line + 1, nice_error=nice_error, raw_error=error
+    )
 
 
 def safe_load(contents) -> Optional[Dict[str, Any]]:
     return yaml.load(contents, Loader=SafeLoader)
 
 
-def load_yaml_text(contents):
+def load_yaml_text(contents, path=None):
     try:
         return safe_load(contents)
     except (yaml.scanner.ScannerError, yaml.YAMLError) as e:
-        if hasattr(e, 'problem_mark'):
+        if hasattr(e, "problem_mark"):
             error = contextualized_yaml_error(contents, e)
         else:
             error = str(e)
 
-        raise dbt.exceptions.ValidationException(error)
+        raise dbt.exceptions.DbtValidationError(error)