Bumping version to 1.1.1 (#5377)

* Bumping version to 1.1.1

* Fix whitespace

* Add Changelog

Co-authored-by: Github Build Bot <buildbot@fishtownanalytics.com>
Co-authored-by: Leah Antkiewicz <leah.antkiewicz@fishtownanalytics.com>

.bumpversion.cfg

@@ -1,12 +1,12 @@
 [bumpversion]
-current_version = 1.0.0
+current_version = 1.1.1
 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
@@ -24,8 +24,6 @@ values =
 [bumpversion:part:pre]
 first_value = 1
 
-[bumpversion:file:setup.py]
-
 [bumpversion:file:core/setup.py]
 
 [bumpversion:file:core/dbt/version.py]
@@ -36,4 +34,8 @@ first_value = 1
 
 [bumpversion:file:plugins/postgres/dbt/adapters/postgres/__version__.py]
 
-[bumpversion:file:docker/requirements/requirements.txt]
+[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 +1,16 @@
+## Previous Releases
+
+For information on prior major and minor releases, see their changelogs:
+
+* [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/1.1.0.md

@@ -0,0 +1,96 @@
+## dbt-core 1.1.0 - April 28, 2022
+### Breaking Changes
+- **Relevant to maintainers of adapter plugins _only_:** The abstractmethods `get_response` and `execute` now only return a `connection.AdapterReponse` in type hints. (Previously, they could return a string.) We encourage you to update your methods to return an object of class `AdapterResponse`, or implement a subclass specific to your adapter
+ ([#4499](https://github.com/dbt-labs/dbt-core/issues/4499), [#4869](https://github.com/dbt-labs/dbt-core/pull/4869))
+- For adapter plugin maintainers only: Internal adapter methods `set_relations_cache` + `_relations_cache_for_schemas` each take an additional argument, for use with experimental `CACHE_SELECTED_ONLY` config ([#4688](https://github.com/dbt-labs/dbt-core/issues/4688), [#4860](https://github.com/dbt-labs/dbt-core/pull/4860))
+### Features
+- Change behaviour of `non_null` test so that it only `select`s all columns if `--store-failures` is enabled. ([#4769](https://github.com/dbt-labs/dbt-core/issues/4769), [#4777](https://github.com/dbt-labs/dbt-core/pull/4777))
+- Testing framework for dbt adapter testing ([#4730](https://github.com/dbt-labs/dbt-core/issues/4730), [#4846](https://github.com/dbt-labs/dbt-core/pull/4846))
+- Allow unique key to take a list implementation for postgres/redshift ([#4738](https://github.com/dbt-labs/dbt-core/issues/4738), [#4858](https://github.com/dbt-labs/dbt-core/pull/4858))
+- Add `--cache_selected_only` flag to cache schema object of selected models only. ([#4688](https://github.com/dbt-labs/dbt-core/issues/4688), [#4860](https://github.com/dbt-labs/dbt-core/pull/4860))
+- Support custom names for generic tests ([#3348](https://github.com/dbt-labs/dbt-core/issues/3348), [#4898](https://github.com/dbt-labs/dbt-core/pull/4898))
+- Added Support for Semantic Versioning ([#4453](https://github.com/dbt-labs/dbt-core/issues/4453), [#4644](https://github.com/dbt-labs/dbt-core/pull/4644))
+- New Dockerfile to support specific db adapters and platforms. See docker/README.md for details ([#4495](https://github.com/dbt-labs/dbt-core/issues/4495), [#4487](https://github.com/dbt-labs/dbt-core/pull/4487))
+- Allow unique_key to take a list ([#2479](https://github.com/dbt-labs/dbt-core/issues/2479), [#4618](https://github.com/dbt-labs/dbt-core/pull/4618))
+- Add `--quiet` global flag and `print` Jinja function ([#3451](https://github.com/dbt-labs/dbt-core/issues/3451), [#4701](https://github.com/dbt-labs/dbt-core/pull/4701))
+- Add space before justification periods ([#4737](https://github.com/dbt-labs/dbt-core/issues/4737), [#4744](https://github.com/dbt-labs/dbt-core/pull/4744))
+- Enable dbt jobs to run downstream models based on fresher sources. Compare the source freshness results between previous and current state. If any source is fresher and/or new in current vs. previous state, dbt will run and test the downstream models in scope. Example command: `dbt build --select source_status:fresher+`  ([#4050](https://github.com/dbt-labs/dbt-core/issues/4050), [#4256](https://github.com/dbt-labs/dbt-core/pull/4256))
+- converting unique key as list tests to new pytest format ([#4882](https://github.com/dbt-labs/dbt-core/issues/4882), [#4958](https://github.com/dbt-labs/dbt-core/pull/4958))
+- Add a variable called selected_resources in the Jinja context containing a list of all the resources matching the nodes for  the --select, --exclude and/or --selector parameters. ([#3471](https://github.com/dbt-labs/dbt-core/issues/3471), [#5001](https://github.com/dbt-labs/dbt-core/pull/5001))
+- Support the DO_NOT_TRACK environment variable from the consoledonottrack.com initiative ([#3540](https://github.com/dbt-labs/dbt-core/issues/3540), [#5000](https://github.com/dbt-labs/dbt-core/pull/5000))
+- Add `--no-print` global flag ([#4710](https://github.com/dbt-labs/dbt-core/issues/4710), [#4854](https://github.com/dbt-labs/dbt-core/pull/4854))
+- add enabled as a source config ([#3662](https://github.com/dbt-labs/dbt-core/issues/3662), [#5008](https://github.com/dbt-labs/dbt-core/pull/5008))
+### Fixes
+- Fix bug causing empty node level meta, snapshot config errors ([#4459](https://github.com/dbt-labs/dbt-core/issues/4459), [#4726](https://github.com/dbt-labs/dbt-core/pull/4726))
+- Inconsistent timestamps between inserted/updated and deleted rows in snapshots ([#4347](https://github.com/dbt-labs/dbt-core/issues/4347), [#4513](https://github.com/dbt-labs/dbt-core/pull/4513))
+- Catch all Requests Exceptions on deps install to attempt retries.  Also log the exceptions hit. ([#4849](https://github.com/dbt-labs/dbt-core/issues/4849), [#4865](https://github.com/dbt-labs/dbt-core/pull/4865))
+- Use cli_vars instead of context to create package and selector renderers ([#4876](https://github.com/dbt-labs/dbt-core/issues/4876), [#4878](https://github.com/dbt-labs/dbt-core/pull/4878))
+- depend on new dbt-extractor version with fixed github links ([#4891](https://github.com/dbt-labs/dbt-core/issues/4891), [#4890](https://github.com/dbt-labs/dbt-core/pull/4890))
+- Update bumpervsion config to stop looking for missing setup.py ([#-1](https://github.com/dbt-labs/dbt-core/issues/-1), [#4896](https://github.com/dbt-labs/dbt-core/pull/4896))
+- Corrected permissions settings for docker release workflow ([#4902](https://github.com/dbt-labs/dbt-core/issues/4902), [#4903](https://github.com/dbt-labs/dbt-core/pull/4903))
+- User wasn't asked for permission to overwite a profile entry when running init inside an existing project ([#4375](https://github.com/dbt-labs/dbt-core/issues/4375), [#4447](https://github.com/dbt-labs/dbt-core/pull/4447))
+- Add project name validation to `dbt init` ([#4490](https://github.com/dbt-labs/dbt-core/issues/4490), [#4536](https://github.com/dbt-labs/dbt-core/pull/4536))
+- Allow override of string and numeric types for adapters. ([#4603](https://github.com/dbt-labs/dbt-core/issues/4603), [#4604](https://github.com/dbt-labs/dbt-core/pull/4604))
+- A change in secret environment variables won't trigger a full reparse ([#4650](https://github.com/dbt-labs/dbt-core/issues/4650), [#4665](https://github.com/dbt-labs/dbt-core/pull/4665))
+- Fix misspellings and typos in docstrings ([#4904](https://github.com/dbt-labs/dbt-core/issues/4904), [#4545](https://github.com/dbt-labs/dbt-core/pull/4545))
+- Catch more cases to retry package retrieval for deps pointing to the hub.  Also start to cache the package requests. ([#4849](https://github.com/dbt-labs/dbt-core/issues/4849), [#4982](https://github.com/dbt-labs/dbt-core/pull/4982))
+- Make the warning message for a full event deque more descriptive ([#4962](https://github.com/dbt-labs/dbt-core/issues/4962), [#5011](https://github.com/dbt-labs/dbt-core/pull/5011))
+- Fix hard delete snapshot test ([#4916](https://github.com/dbt-labs/dbt-core/issues/4916), [#5020](https://github.com/dbt-labs/dbt-core/pull/5020))
+- Restore ability to utilize `updated_at` for check_cols snapshots ([#5076](https://github.com/dbt-labs/dbt-core/issues/5076), [#5077](https://github.com/dbt-labs/dbt-core/pull/5077))
+- Use yaml renderer (with target context) for rendering selectors ([#5131](https://github.com/dbt-labs/dbt-core/issues/5131), [#5136](https://github.com/dbt-labs/dbt-core/pull/5136))
+- Fix retry logic to return values after initial try ([#5023](https://github.com/dbt-labs/dbt-core/issues/5023), [#5137](https://github.com/dbt-labs/dbt-core/pull/5137))
+- Scrub secret env vars from CommandError in exception stacktrace ([#5151](https://github.com/dbt-labs/dbt-core/issues/5151), [#5152](https://github.com/dbt-labs/dbt-core/pull/5152))
+### Docs
+- Resolve errors related to operations preventing DAG from generating in the docs.  Also patch a spark issue to allow search to filter accurately past the missing columns. ([#4578](https://github.com/dbt-labs/dbt-core/issues/4578), [#4763](https://github.com/dbt-labs/dbt-core/pull/4763))
+- Fixed capitalization in UI for exposures of `type: ml` ([#4984](https://github.com/dbt-labs/dbt-core/issues/4984), [#4995](https://github.com/dbt-labs/dbt-core/pull/4995))
+- List packages and tags in alphabetical order ([#4984](https://github.com/dbt-labs/dbt-core/issues/4984), [#4995](https://github.com/dbt-labs/dbt-core/pull/4995))
+- Bump jekyll from 3.8.7 to 3.9.0 ([#4984](https://github.com/dbt-labs/dbt-core/issues/4984), [#4995](https://github.com/dbt-labs/dbt-core/pull/4995))
+- Updated docker README to reflect necessity of using BuildKit ([#4990](https://github.com/dbt-labs/dbt-core/issues/4990), [#5018](https://github.com/dbt-labs/dbt-core/pull/5018))
+### Under the Hood
+- Automate changelog generation with changie ([#4652](https://github.com/dbt-labs/dbt-core/issues/4652), [#4743](https://github.com/dbt-labs/dbt-core/pull/4743))
+- add performance regression testing runner without orchestration ([#4021](https://github.com/dbt-labs/dbt-core/issues/4021), [#4602](https://github.com/dbt-labs/dbt-core/pull/4602))
+- Fix broken links for changelog generation and tweak GHA to only post a comment once when changelog entry is missing. ([#4848](https://github.com/dbt-labs/dbt-core/issues/4848), [#4857](https://github.com/dbt-labs/dbt-core/pull/4857))
+- Add support for Python 3.10 ([#4562](https://github.com/dbt-labs/dbt-core/issues/4562), [#4866](https://github.com/dbt-labs/dbt-core/pull/4866))
+- Enable more dialects to snapshot sources with added columns, even those that don't support boolean datatypes ([#4488](https://github.com/dbt-labs/dbt-core/issues/4488), [#4871](https://github.com/dbt-labs/dbt-core/pull/4871))
+- Add Graph Compilation and Adapter Cache tracking ([#4625](https://github.com/dbt-labs/dbt-core/issues/4625), [#4912](https://github.com/dbt-labs/dbt-core/pull/4912))
+- Testing cleanup ([#3648](https://github.com/dbt-labs/dbt-core/issues/3648), [#4509](https://github.com/dbt-labs/dbt-core/pull/4509))
+- Clean up test deprecation warnings ([#3988](https://github.com/dbt-labs/dbt-core/issues/3988), [#4556](https://github.com/dbt-labs/dbt-core/pull/4556))
+- Use mashumaro for serialization in event logging ([#4504](https://github.com/dbt-labs/dbt-core/issues/4504), [#4505](https://github.com/dbt-labs/dbt-core/pull/4505))
+- Drop support for Python 3.7.0 + 3.7.1 ([#4584](https://github.com/dbt-labs/dbt-core/issues/4584), [#4585](https://github.com/dbt-labs/dbt-core/pull/4585))
+- Drop support for Python <3.7.2 ([#4584](https://github.com/dbt-labs/dbt-core/issues/4584), [#4643](https://github.com/dbt-labs/dbt-core/pull/4643))
+- Re-format codebase (except tests) using pre-commit hooks ([#3195](https://github.com/dbt-labs/dbt-core/issues/3195), [#4697](https://github.com/dbt-labs/dbt-core/pull/4697))
+- Add deps module README ([#4904](https://github.com/dbt-labs/dbt-core/issues/4904), [#4686](https://github.com/dbt-labs/dbt-core/pull/4686))
+- Initial conversion of tests to pytest ([#4690](https://github.com/dbt-labs/dbt-core/issues/4690), [#4691](https://github.com/dbt-labs/dbt-core/pull/4691))
+- Fix errors in Windows for tests/functions ([#4782](https://github.com/dbt-labs/dbt-core/issues/4782), [#4767](https://github.com/dbt-labs/dbt-core/pull/4767))
+- Create a dbt.tests.adapter release when releasing dbt and postgres ([#4812](https://github.com/dbt-labs/dbt-core/issues/4812), [#4948](https://github.com/dbt-labs/dbt-core/pull/4948))
+- update docker image to use python 3.10.3 ([#4904](https://github.com/dbt-labs/dbt-core/issues/4904), [#4963](https://github.com/dbt-labs/dbt-core/pull/4963))
+- updates black to 22.3.0 which fixes dependency incompatibility when running with precommit. ([#4904](https://github.com/dbt-labs/dbt-core/issues/4904), [#4972](https://github.com/dbt-labs/dbt-core/pull/4972))
+- Adds config util for ad-hoc creation of project objs or dicts ([#4808](https://github.com/dbt-labs/dbt-core/issues/4808), [#4981](https://github.com/dbt-labs/dbt-core/pull/4981))
+- Remove TableComparison and convert existing calls to use dbt.tests.util ([#4778](https://github.com/dbt-labs/dbt-core/issues/4778), [#4986](https://github.com/dbt-labs/dbt-core/pull/4986))
+- Remove unneeded create_schema in snapshot materialization ([#4742](https://github.com/dbt-labs/dbt-core/issues/4742), [#4993](https://github.com/dbt-labs/dbt-core/pull/4993))
+- Added .git-blame-ignore-revs file to mask re-formmating commits from git blame ([#5004](https://github.com/dbt-labs/dbt-core/issues/5004), [#5019](https://github.com/dbt-labs/dbt-core/pull/5019))
+- Convert version tests to pytest ([#5024](https://github.com/dbt-labs/dbt-core/issues/5024), [#5026](https://github.com/dbt-labs/dbt-core/pull/5026))
+- Updating tests and docs to show that we now support Python 3.10 ([#4974](https://github.com/dbt-labs/dbt-core/issues/4974), [#5025](https://github.com/dbt-labs/dbt-core/pull/5025))
+- Update --version output and logic ([#4724](https://github.com/dbt-labs/dbt-core/issues/4724), [#5029](https://github.com/dbt-labs/dbt-core/pull/5029))
+-  ([#5033](https://github.com/dbt-labs/dbt-core/issues/5033), [#5032](https://github.com/dbt-labs/dbt-core/pull/5032))
+
+### Contributors
+- [@NiallRees](https://github.com/NiallRees) ([#4447](https://github.com/dbt-labs/dbt-core/pull/4447))
+- [@agoblet](https://github.com/agoblet) ([#5000](https://github.com/dbt-labs/dbt-core/pull/5000))
+- [@alswang18](https://github.com/alswang18) ([#4644](https://github.com/dbt-labs/dbt-core/pull/4644))
+- [@amirkdv](https://github.com/amirkdv) ([#4536](https://github.com/dbt-labs/dbt-core/pull/4536))
+- [@anaisvaillant](https://github.com/anaisvaillant) ([#4256](https://github.com/dbt-labs/dbt-core/pull/4256))
+- [@b-per](https://github.com/b-per) ([#5001](https://github.com/dbt-labs/dbt-core/pull/5001))
+- [@dbeatty10](https://github.com/dbeatty10) ([#5077](https://github.com/dbt-labs/dbt-core/pull/5077))
+- [@ehmartens](https://github.com/ehmartens) ([#4701](https://github.com/dbt-labs/dbt-core/pull/4701))
+- [@joellabes](https://github.com/joellabes) ([#4744](https://github.com/dbt-labs/dbt-core/pull/4744))
+- [@jonstacks](https://github.com/jonstacks) ([#4995](https://github.com/dbt-labs/dbt-core/pull/4995))
+- [@kadero](https://github.com/kadero) ([#4513](https://github.com/dbt-labs/dbt-core/pull/4513))
+- [@karunpoudel](https://github.com/karunpoudel) ([#4860](https://github.com/dbt-labs/dbt-core/pull/4860), [#4860](https://github.com/dbt-labs/dbt-core/pull/4860))
+- [@kazanzhy](https://github.com/kazanzhy) ([#4545](https://github.com/dbt-labs/dbt-core/pull/4545))
+- [@matt-winkler](https://github.com/matt-winkler) ([#4256](https://github.com/dbt-labs/dbt-core/pull/4256))
+- [@mdesmet](https://github.com/mdesmet) ([#4604](https://github.com/dbt-labs/dbt-core/pull/4604))
+- [@pgoslatara](https://github.com/pgoslatara) ([#4995](https://github.com/dbt-labs/dbt-core/pull/4995))
+- [@poloaraujo](https://github.com/poloaraujo) ([#4854](https://github.com/dbt-labs/dbt-core/pull/4854))
+- [@sungchun12](https://github.com/sungchun12) ([#4256](https://github.com/dbt-labs/dbt-core/pull/4256))
+- [@willbowditch](https://github.com/willbowditch) ([#4777](https://github.com/dbt-labs/dbt-core/pull/4777))

.changes/1.1.1.md

@@ -0,0 +1,14 @@
+## dbt-core 1.1.1 - June 15, 2022
+### Fixes
+- Relax minimum supported version of MarkupSafe ([#4745](https://github.com/dbt-labs/dbt-core/issues/4745), [#5039](https://github.com/dbt-labs/dbt-core/pull/5039))
+- When parsing 'all_sources' should be a list of unique dirs ([#5120](https://github.com/dbt-labs/dbt-core/issues/5120), [#5176](https://github.com/dbt-labs/dbt-core/pull/5176))
+- Remove docs file from manifest when removing doc node ([#4146](https://github.com/dbt-labs/dbt-core/issues/4146), [#5270](https://github.com/dbt-labs/dbt-core/pull/5270))
+- Fixing Windows color regression ([#5191](https://github.com/dbt-labs/dbt-core/issues/5191), [#5327](https://github.com/dbt-labs/dbt-core/pull/5327))
+### Under the Hood
+- Update context readme + clean up context code" ([#4796](https://github.com/dbt-labs/dbt-core/issues/4796), [#5334](https://github.com/dbt-labs/dbt-core/pull/5334))
+### Dependencies
+- Bumping hologram version ([#5219](https://github.com/dbt-labs/dbt-core/issues/5219), [#5218](https://github.com/dbt-labs/dbt-core/pull/5218))
+- Pin networkx to <2.8.4 for v1.1 patches ([#5286](https://github.com/dbt-labs/dbt-core/issues/5286), [#5334](https://github.com/dbt-labs/dbt-core/pull/5334))
+
+### Contributors
+- [@adamantike](https://github.com/adamantike) ([#5039](https://github.com/dbt-labs/dbt-core/pull/5039))

.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)

.changie.yaml

@@ -0,0 +1,60 @@
+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: '- {{.Body}} ([#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-core/issues/{{.Custom.Issue}}), [#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-core/pull/{{.Custom.PR}}))'
+kinds:
+- label: Breaking Changes
+- label: Features
+- label: Fixes
+- label: Docs
+- label: Under the Hood
+- label: Dependencies
+custom:
+- key: Author
+  label: GitHub Username(s) (separated by a single space if multiple)
+  type: string
+  minLength: 3
+- key: Issue
+  label: GitHub Issue Number
+  type: int
+  minLength: 4
+- key: PR
+  label: GitHub Pull Request Number
+  type: int
+  minLength: 4
+footerFormat: |
+  {{- $contributorDict := dict }}
+  {{- /* any names added to this list should be all lowercase for later matching purposes */}}
+  {{- $core_team := list "emmyoop" "nathaniel-may" "gshank" "leahwicz" "chenyulinx" "stu-k" "iknox-fa" "versusfacit" "mcknight-42" "jtcohen6" "dependabot" }}
+  {{- range $change := .Changes }}
+    {{- $authorList := splitList " " $change.Custom.Author }}
+    {{- /* loop through all authors for a PR */}}
+    {{- range $author := $authorList }}
+      {{- $authorLower := lower $author }}
+      {{- /* we only want to include non-core team contributors */}}
+      {{- if not (has $authorLower $core_team)}}
+        {{- $pr := $change.Custom.PR }}
+        {{- /* check if this contributor has other PRs associated with them already */}}
+        {{- if hasKey $contributorDict $author }}
+          {{- $prList := get $contributorDict $author }}
+          {{- $prList = append $prList $pr  }}
+          {{- $contributorDict := set $contributorDict $author $prList }}
+        {{- else }}
+          {{- $prList := list $change.Custom.PR }}
+          {{- $contributorDict := set $contributorDict $author $prList }}
+        {{- end }}
+      {{- end}}
+    {{- end}}
+  {{- end }}
+  {{- /* no indentation here for formatting so the final markdown doesn't have unneeded indentations */}}
+  {{- if $contributorDict}}
+  ### Contributors
+  {{- range $k,$v := $contributorDict }}
+  - [@{{$k}}](https://github.com/{{$k}}) ({{ range $index, $element := $v }}{{if $index}}, {{end}}[#{{$element}}](https://github.com/dbt-labs/dbt-core/pull/{{$element}}){{end}})
+  {{- 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

.github/CODEOWNERS

@@ -0,0 +1,43 @@
+# 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 core modules
+/core/dbt/config/     @dbt-labs/core-language
+/core/dbt/context/    @dbt-labs/core-language
+/core/dbt/contracts/  @dbt-labs/core-language
+/core/dbt/deps/       @dbt-labs/core-language
+/core/dbt/parser/     @dbt-labs/core-language
+
+# Execution core modules
+/core/dbt/events/     @dbt-labs/core-execution @dbt-labs/core-language # eventually remove language but they have knowledge here now
+/core/dbt/graph/      @dbt-labs/core-execution
+/core/dbt/task/       @dbt-labs/core-execution
+
+# Adapter interface, scaffold, Postgres plugin
+/core/dbt/adapters    @dbt-labs/core-adapters
+/core/scripts/create_adapter_plugin.py    @dbt-labs/core-adapters
+/plugins/             @dbt-labs/core-adapters
+
+# Global project: default macros, including generic tests + materializations
+/core/dbt/include/global_project    @dbt-labs/core-execution @dbt-labs/core-adapters
+
+# 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/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 +1,95 @@
+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)
+        else:
+            # everything is the latest if the package doesn't exist
+            print(f"::set-output name=latest::{True}")
+            print(f"::set-output name=minor_latest::{True}")
+            sys.exit(0)
+
+    # 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)
+
+    print(f"::set-output name=latest::{latest}")
+    print(f"::set-output name=minor_latest::{minor_latest}")

.github/pull_request_template.md

@@ -18,4 +18,4 @@ resolves #
 - [ ] 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 added information about my change to be included in the [CHANGELOG](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#Adding-CHANGELOG-Entry).

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

@@ -1,95 +0,0 @@
-module.exports = ({ context }) => {
-  const defaultPythonVersion = "3.8";
-  const supportedPythonVersions = ["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 +1,34 @@
+# **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 and it has been correctly labeled
+# according to the naming convention.
+
+name: Backport
+on:
+  pull_request:
+    types:
+      - closed
+      - labeled
+
+jobs:
+  backport:
+    runs-on: ubuntu-18.04
+    name: Backport
+    steps:
+      - name: Backport
+        uses: dbt-labs/backport@v1.1.1
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/changelog-check.yml

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

.github/workflows/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 +1,24 @@
+# **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]
+
+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:
@@ -37,24 +35,13 @@ 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"
-
     steps:
       - name: Check out the repository
         uses: actions/checkout@v2
-        with:
-          persist-credentials: false
 
       - name: Set up Python
         uses: actions/setup-python@v2
@@ -62,12 +49,16 @@ jobs:
       - name: Install python dependencies
         run: |
           pip install --user --upgrade pip
-          pip install tox
           pip --version
-          tox --version
+          pip install pre-commit
+          pre-commit --version
+          pip install mypy==0.782
+          mypy --version
+          pip install -r editable-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 }}
@@ -77,7 +68,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: ['3.7', '3.8', '3.9', '3.10']
 
     env:
       TOXENV: "unit"
@@ -86,8 +77,6 @@ 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
@@ -97,8 +86,8 @@ jobs:
       - name: Install python dependencies
         run: |
           pip install --user --upgrade pip
-          pip install tox
           pip --version
+          pip install tox
           tox --version
 
       - name: Run tox
@@ -115,6 +104,75 @@ 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 }}
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ['3.7', '3.8', '3.9', '3.10']
+        os: [ubuntu-latest]
+        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
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v2
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Set up postgres (linux)
+        if: runner.os == 'Linux'
+        uses: ./.github/actions/setup-postgres-linux
+
+      - name: Set up postgres (macos)
+        if: runner.os == 'macOS'
+        uses: ./.github/actions/setup-postgres-macos
+
+      - name: Set up postgres (windows)
+        if: runner.os == 'Windows'
+        uses: ./.github/actions/setup-postgres-windows
+
+      - name: Install python tools
+        run: |
+          # pip install --user --upgrade pip
+          # pip --version
+          pip install tox
+          tox --version
+
+      - name: Run tests
+        run: tox
+
+      - name: Get current date
+        if: always()
+        id: date
+        run: echo "::set-output name=date::$(date +'%Y_%m_%dT%H_%M_%S')" #no colons allowed for artifacts
+
+      - uses: actions/upload-artifact@v2
+        if: always()
+        with:
+          name: 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
 
@@ -123,8 +181,6 @@ jobs:
     steps:
       - name: Check out the repository
         uses: actions/checkout@v2
-        with:
-          persist-credentials: false
 
       - name: Set up Python
         uses: actions/setup-python@v2
@@ -151,44 +207,6 @@ 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: [3.7, 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/

.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-docker.yml

@@ -0,0 +1,116 @@
+# **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 <<< ${{ github.event.inputs.version_number }}
+          echo "::set-output name=major::$MAJOR"
+          echo "::set-output name=minor::$MINOR"
+          echo "::set-output name=patch::$PATCH"
+
+      - 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: ${{ secrets.GITHUB_TOKEN }}
+          halt_on_missing: False
+
+  setup_image_builder:
+    name: Set up docker image builder
+    runs-on: ubuntu-latest
+    needs: [get_version_meta]
+    steps:
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+
+  build_and_push:
+    name: Build images and push to GHCR
+    runs-on: ubuntu-latest
+    needs: [setup_image_builder, get_version_meta]
+    steps:
+      - name: Get docker build arg
+        id: build_arg
+        run: |
+          echo "::set-output name=build_arg_name::"$(echo ${{ github.event.inputs.package }} | sed 's/\-/_/g')
+          echo "::set-output name=build_arg_value::"$(echo ${{ github.event.inputs.package }} | sed 's/postgres/core/g')
+
+      - 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

@@ -1,5 +1,5 @@
 # **what?**
-# Take the given commit, run unit tests specifically on that sha, build and 
+# 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?**
@@ -142,9 +142,8 @@ jobs:
         run: |
           dbt --version
 
-
   github-release:
-    name: GitHub Release 
+    name: GitHub Release
 
     needs: test-build
 
@@ -155,7 +154,7 @@ jobs:
         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
@@ -179,7 +178,7 @@ jobs:
             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
 
@@ -188,12 +187,12 @@ jobs:
     needs: github-release
 
     environment: PypiProd
-    steps:    
+    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:

.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.
@@ -37,20 +37,20 @@ 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 +59,7 @@ 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/structured-logging-schema-check.yml

@@ -1,12 +1,11 @@
 # 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:
@@ -30,9 +29,8 @@ jobs:
       # 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'
+      DBT_LOG_FORMAT: "json"
     steps:
-
       - name: checkout dev
         uses: actions/checkout@v2
         with:
@@ -49,8 +47,12 @@ jobs:
           toolchain: stable
           override: true
 
-      - name: install dbt
-        run: pip install -r dev-requirements.txt -r editable-requirements.txt
+      - 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
@@ -61,7 +63,7 @@ jobs:
       # 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 py38-postgres -- -nauto
+        run: tox -e integration -- -nauto
 
       # apply our schema tests to every log event from the previous step
       # skips any output that isn't valid json

.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/version-bump.yml

@@ -1,16 +1,16 @@
 # **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 
+# 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.
 
 # **why?**
-# This is to aid in releasing dbt and making sure we have updated 
+# This is to aid in releasing dbt and making sure we have updated
 # the versions and Docker requirements in all places.
 
 # **when?**
-# This is triggered either manually OR 
+# This is triggered either manually OR
 # from the repository_dispatch event "version-bump" which is sent from
 # the dbt-release repo Action
 
@@ -25,10 +25,10 @@ on:
       is_dry_run:
        description: 'Creates a draft PR to allow testing instead of committing to a branch'
        required: true
-       default: 'true'  
+       default: 'true'
   repository_dispatch:
     types: [version-bump]
-  
+
 jobs:
   bump:
     runs-on: ubuntu-latest
@@ -57,26 +57,26 @@ jobs:
         run: |
           python3 -m venv env
           source env/bin/activate
-          pip install --upgrade pip     
-          
+          pip install --upgrade pip
+
       - 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
+
+      # - name: Generate Docker requirements
+      #  run: |
+      #    source env/bin/activate
+      #    pip install -r requirements.txt
+      #    pip freeze -l > docker/requirements/requirements.txt
+      #    git status
 
       - name: Bump version
         run: |
           source env/bin/activate
-          pip install -r dev-requirements.txt 
+          pip install -r dev-requirements.txt
           env/bin/bumpversion --allow-dirty --new-version ${{steps.variables.outputs.VERSION_NUMBER}} major
           git status
 

.gitignore

@@ -49,9 +49,8 @@ coverage.xml
 *,cover
 .hypothesis/
 test.env
+*.pytest_cache/
 
-# Mypy
-.mypy_cache/
 
 # Translations
 *.mo
@@ -66,10 +65,10 @@ docs/_build/
 # PyBuilder
 target/
 
-#Ipython Notebook
+# Ipython Notebook
 .ipynb_checkpoints
 
-#Emacs
+# Emacs
 *~
 
 # Sublime Text
@@ -78,6 +77,7 @@ target/
 # Vim
 *.sw*
 
+# Pyenv
 .python-version
 
 # Vim
@@ -90,6 +90,7 @@ venv/
 # AWS credentials
 .aws/
 
+# MacOS
 .DS_Store
 
 # vscode

.pre-commit-config.yaml

@@ -0,0 +1,68 @@
+# 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/
+
+# Force all unspecified python hooks to run python 3.8
+default_language_version:
+  python: python3.8
+
+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
+    args:
+    - "--line-length=99"
+    - "--target-version=py38"
+  - id: black
+    alias: black-check
+    stages: [manual]
+    args:
+    - "--line-length=99"
+    - "--target-version=py38"
+    - "--check"
+    - "--diff"
+- repo: https://gitlab.com/pycqa/flake8
+  rev: 4.0.1
+  hooks:
+  - id: flake8
+  - id: flake8
+    alias: flake8-check
+    stages: [manual]
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.782
+  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

@@ -47,6 +47,7 @@ Here's a good workflow:
 - 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-core` 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-core`'s [unit](test/unit) and [integration](test/integration) tests is the tests themselves. One of the maintainers can help by pointing out relevant examples.
+- Check your formatting and linting with [Flake8](https://flake8.pycqa.org/en/latest/#), [Black](https://github.com/psf/black), and the rest of the hooks we have in our [pre-commit](https://pre-commit.com/) [config](https://github.com/dbt-labs/dbt-core/blob/75201be9db1cb2c6c01fa7e71a314f5e5beb060a/.pre-commit-config.yaml).
 
 In some cases, the right resolution to an open issue might be tangential to the `dbt-core` 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-core` maintainers are unwilling or unable to incorporate into the `dbt-core` codebase. When it is determined that an open issue describes functionality that will not translate to a code change in the `dbt-core` repository, the issue will be tagged with the `wontfix` label (see below) and closed.
 
@@ -102,10 +103,11 @@ There are some tools that will be helpful to you in developing locally. While th
 
 A short list of tools used in `dbt-core` testing that will be helpful to your understanding:
 
-- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, Python 3.8, and Python 3.9
+- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, Python 3.8, Python 3.9, and Python 3.10
 - [`pytest`](https://docs.pytest.org/en/latest/) to discover/run tests
 - [`make`](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) - but don't worry too much, nobody _really_ understands how make works and our Makefile is super simple
 - [`flake8`](https://flake8.pycqa.org/en/latest/) for code linting
+- [`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)
 
@@ -190,19 +192,18 @@ 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 install 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.  Once this is done you can use any of the linter-based make targets as well as a git pre-commit hook that will ensure proper formatting and linting.
+
 #### `tox`
 
-[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run
-tests. You can also run tests in parallel, for example, you can run unit tests
-for Python 3.7, Python 3.8, Python 3.9, `flake8` checks, and `mypy` checks in
-parallel with `tox -p`. Also, you can run unit tests for specific python versions
-with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
+[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.7, Python 3.8, Python 3.9, and Python 3.10 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
 
 #### `pytest`
 
@@ -218,6 +219,15 @@ python -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
 ```
 > [Here](https://docs.pytest.org/en/reorganize-docs/new-docs/user/commandlineuseful.html)
 > is a list of useful command-line options for `pytest` to use while developing.
+
+## Adding CHANGELOG Entry
+
+We use [changie](https://changie.dev) to generate `CHANGELOG` entries.  Do not edit the `CHANGELOG.md` directly.  Your modifications will be lost.
+
+Follow the steps to [install `changie`](https://changie.dev/guide/installation/) for your system.
+
+Once changie is installed and your PR is created, simply run `changie new` and changie will walk you through the process of creating a changelog entry.  Commit the file that's created and your changelog entry is complete!
+
 ## 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.

Dockerfile.test

@@ -1,3 +1,8 @@
+##
+#  This dockerfile is used for local development and adapter testing only.
+#  See `/docker` for a generic and production-ready docker file
+##
+
 FROM ubuntu:20.04
 
 ENV DEBIAN_FRONTEND noninteractive
@@ -41,6 +46,9 @@ RUN apt-get update \
     python3.9 \
     python3.9-dev \
     python3.9-venv \
+    python3.10 \
+    python3.10-dev \
+    python3.10-venv \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 

Makefile

@@ -8,45 +8,58 @@ endif
 
 .PHONY: dev
 dev: ## Installs dbt-* packages in develop mode along with development dependencies.
-	pip install -r dev-requirements.txt -r editable-requirements.txt
+	@\
+	pip install -r dev-requirements.txt -r editable-requirements.txt && \
+	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
 
 .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 py38 and code checks against staged changes.
+	@\
+	$(DOCKER_CMD) tox -e py38; \
+	$(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 py38.
+	@\
+	$(DOCKER_CMD) tox -e py38-integration -- -nauto
 
 .PHONY: integration-fail-fast
-integration-fail-fast: .env integration-postgres-fail-fast ## Alias for integration-postgres-fail-fast.
-
-.PHONY: integration-postgres
-integration-postgres: .env ## Runs postgres integration tests with py38.
-	$(DOCKER_CMD) tox -e py38-postgres -- -nauto
-
-.PHONY: integration-postgres-fail-fast
-integration-postgres-fail-fast: .env ## Runs postgres integration tests with py38 in "fail fast" mode.
-	$(DOCKER_CMD) tox -e py38-postgres -- -x -nauto
+integration-fail-fast: .env ## Runs postgres integration tests with py38 in "fail fast" mode.
+	@\
+	$(DOCKER_CMD) tox -e py38-integration -- -x -nauto
 
 .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 +75,29 @@ 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 -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

@@ -3,10 +3,7 @@
 </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>
 

core/README.md

@@ -3,10 +3,7 @@
 </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>
 

core/dbt/README.md

@@ -0,0 +1,51 @@
+# core/dbt directory README
+
+## The following are individual files in this directory.
+
+### deprecations.py
+
+### flags.py
+
+### main.py
+
+### tracking.py
+
+### version.py
+
+### lib.py
+
+### node_types.py
+
+### helper_types.py
+
+### links.py
+
+### semver.py
+
+### ui.py
+
+### compilation.py
+
+### dataclass_schema.py
+
+### exceptions.py
+
+### hooks.py
+
+### logger.py
+
+### profiler.py
+
+### utils.py
+
+
+## The subdirectories will be documented in a README in the subdirectory
+* config
+* include
+* adapters
+* context
+* deps
+* graph
+* task
+* clients
+* events

core/dbt/adapters/README.md

@@ -0,0 +1 @@
+# Adapters README

core/dbt/adapters/base/column.py

@@ -8,10 +8,10 @@ from dbt.exceptions import RuntimeException
 @dataclass
 class Column:
     TYPE_LABELS: ClassVar[Dict[str, str]] = {
-        'STRING': 'TEXT',
-        'TIMESTAMP': 'TIMESTAMP',
-        'FLOAT': 'FLOAT',
-        'INTEGER': 'INT'
+        "STRING": "TEXT",
+        "TIMESTAMP": "TIMESTAMP",
+        "FLOAT": "FLOAT",
+        "INTEGER": "INT",
     }
     column: str
     dtype: str
@@ -24,7 +24,7 @@ class Column:
         return cls.TYPE_LABELS.get(dtype.upper(), dtype)
 
     @classmethod
-    def create(cls, name, label_or_dtype: str) -> 'Column':
+    def create(cls, name, label_or_dtype: str) -> "Column":
         column_type = cls.translate_type(label_or_dtype)
         return cls(name, column_type)
 
@@ -39,16 +39,14 @@ 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 +54,45 @@ 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!")
 
-        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 +120,10 @@ 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 RuntimeException(f'Could not interpret data type "{raw_data_type}"')
         data_type, size_info = match.groups()
         char_size = None
         numeric_precision = None
@@ -123,7 +131,7 @@ class Column:
         if size_info is not None:
             # strip out the parentheses
             size_info = size_info[1:-1]
-            parts = size_info.split(',')
+            parts = size_info.split(",")
             if len(parts) == 1:
                 try:
                     char_size = int(parts[0])
@@ -148,6 +156,4 @@ class Column:
                         f'could not convert "{parts[1]}" to an integer'
                     )
 
-        return cls(
-            name, data_type, char_size, numeric_precision, numeric_scale
-        )
+        return cls(name, data_type, char_size, numeric_precision, numeric_scale)

core/dbt/adapters/base/connections.py

@@ -1,18 +1,21 @@
 import abc
 import os
+
 # multiprocessing.RLock is a function returning this type
 from multiprocessing.synchronize import RLock
 from threading import get_ident
-from typing import (
-    Dict, Tuple, Hashable, Optional, ContextManager, List, Union
-)
+from typing import Dict, Tuple, Hashable, Optional, ContextManager, List
 
 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 (
@@ -27,7 +30,7 @@ from dbt.events.types import (
     ConnectionClosed,
     ConnectionClosed2,
     Rollback,
-    RollbackFailed
+    RollbackFailed,
 )
 from dbt import flags
 
@@ -45,6 +48,7 @@ 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):
@@ -66,16 +70,14 @@ 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.InvalidConnectionException(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 {}'
+                "In set_thread_connection, existing connection exists for {}"
             )
         self.thread_connections[key] = conn
 
@@ -115,18 +117,19 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             underlying database.
         """
         raise dbt.exceptions.NotImplementedException(
-            '`exception_handler` is not implemented for this adapter!')
+            "`exception_handler` is not implemented for this adapter!"
+        )
 
     def set_connection_name(self, name: Optional[str] = None) -> Connection:
         conn_name: str
         if name is None:
             # if a name isn't specified, we'll re-use a single handle
             # named 'master'
-            conn_name = 'master'
+            conn_name = "master"
         else:
             if not isinstance(name, str):
                 raise dbt.exceptions.CompilerException(
-                    f'For connection name, got {name} - not a string!'
+                    f"For connection name, got {name} - not a string!"
                 )
             assert isinstance(name, str)
             conn_name = name
@@ -139,16 +142,16 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
                 state=ConnectionState.INIT,
                 transaction_open=False,
                 handle=None,
-                credentials=self.profile.credentials
+                credentials=self.profile.credentials,
             )
             self.set_thread_connection(conn)
 
-        if conn.name == conn_name and conn.state == 'open':
+        if conn.name == conn_name and conn.state == "open":
             return conn
 
         fire_event(NewConnection(conn_name=conn_name, conn_type=self.TYPE))
 
-        if conn.state == 'open':
+        if conn.state == "open":
             fire_event(ConnectionReused(conn_name=conn_name))
         else:
             conn.handle = LazyHandle(self.open)
@@ -160,7 +163,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     def cancel_open(self) -> Optional[List[str]]:
         """Cancel all open connections on the adapter. (passable)"""
         raise dbt.exceptions.NotImplementedException(
-            '`cancel_open` is not implemented for this adapter!'
+            "`cancel_open` is not implemented for this adapter!"
         )
 
     @abc.abstractclassmethod
@@ -173,9 +176,7 @@ 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.NotImplementedException("`open` is not implemented for this adapter!")
 
     def release(self) -> None:
         with self.lock:
@@ -195,7 +196,7 @@ 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'}:
+                if connection.state not in {"closed", "init"}:
                     fire_event(ConnectionLeftOpen(conn_name=connection.name))
                 else:
                     fire_event(ConnectionClosed(conn_name=connection.name))
@@ -208,14 +209,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     def begin(self) -> None:
         """Begin a transaction. (passable)"""
         raise dbt.exceptions.NotImplementedException(
-            '`begin` is not implemented for this adapter!'
+            "`begin` is not implemented for this adapter!"
         )
 
     @abc.abstractmethod
     def commit(self) -> None:
         """Commit a transaction. (passable)"""
         raise dbt.exceptions.NotImplementedException(
-            '`commit` is not implemented for this adapter!'
+            "`commit` is not implemented for this adapter!"
         )
 
     @classmethod
@@ -230,7 +231,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     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'):
+        if hasattr(connection.handle, "close"):
             fire_event(ConnectionClosed2(conn_name=connection.name))
             connection.handle.close()
         else:
@@ -241,7 +242,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         """Roll back the given connection."""
         if connection.transaction_open is False:
             raise dbt.exceptions.InternalException(
-                f'Tried to rollback transaction on connection '
+                f"Tried to rollback transaction on connection "
                 f'"{connection.name}", but it does not have one open!'
             )
 
@@ -280,16 +281,16 @@ 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!'
+            "`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

@@ -8,11 +8,10 @@ from dbt.adapters.protocol import AdapterProtocol
 def project_name_from_path(include_path: str) -> str:
     # avoid an import cycle
     from dbt.config.project import Project
+
     partial = Project.partial_load(include_path)
     if partial.project_name is None:
-        raise CompilationException(
-            f'Invalid project at {include_path}: name not set!'
-        )
+        raise CompilationException(f"Invalid project at {include_path}: name not set!")
     return partial.project_name
 
 
@@ -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

@@ -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 RuntimeException(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)
@@ -87,7 +88,7 @@ class MacroQueryStringSetter:
         return self.comment.add(sql)
 
     def reset(self):
-        self.set('master', None)
+        self.set("master", None)
 
     def set(self, name: str, node: Optional[CompileResultNode]):
         wrapped: Optional[NodeWrapper] = None

core/dbt/adapters/base/relation.py

@@ -1,13 +1,16 @@
 from collections.abc import Hashable
 from dataclasses import dataclass
-from typing import (
-    Optional, TypeVar, Any, Type, Dict, Union, Iterator, Tuple, Set
-)
+from typing import Optional, TypeVar, Any, Type, Dict, Union, Iterator, Tuple, Set
 
 from dbt.contracts.graph.compiled import CompiledNode
 from dbt.contracts.graph.parsed import ParsedSourceDefinition, ParsedNode
 from dbt.contracts.relation import (
-    RelationType, ComponentName, HasQuoting, FakeAPIObject, Policy, Path
+    RelationType,
+    ComponentName,
+    HasQuoting,
+    FakeAPIObject,
+    Policy,
+    Path,
 )
 from dbt.exceptions import InternalException
 from dbt.node_types import NodeType
@@ -16,7 +19,7 @@ from dbt.utils import filter_null_values, deep_merge, classproperty
 import dbt.exceptions
 
 
-Self = TypeVar('Self', bound='BaseRelation')
+Self = TypeVar("Self", bound="BaseRelation")
 
 
 @dataclass(frozen=True, eq=False, repr=False)
@@ -40,7 +43,7 @@ class BaseRelation(FakeAPIObject, Hashable):
             if field.name == field_name:
                 return field
         # this should be unreachable
-        raise ValueError(f'BaseRelation has no {field_name} field!')
+        raise ValueError(f"BaseRelation has no {field_name} field!")
 
     def __eq__(self, other):
         if not isinstance(other, self.__class__):
@@ -49,20 +52,18 @@ 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
 
     @classmethod
     def get_default_include_policy(cls) -> Policy:
-        return cls._get_field_named('include_policy').default
+        return cls._get_field_named("include_policy").default
 
     def get(self, key, default=None):
         """Override `.get` to return a metadata object so we don't break
         dbt_utils.
         """
-        if key == 'metadata':
-            return {
-                'type': self.__class__.__name__
-            }
+        if key == "metadata":
+            return {"type": self.__class__.__name__}
         return super().get(key, default)
 
     def matches(
@@ -71,16 +72,19 @@ 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!")
+                "Tried to match relation, but no search path was passed!"
+            )
 
         exact_match = True
         approximate_match = True
@@ -88,17 +92,13 @@ 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).strip(self.quote_character) !=
-                v.lower().strip(self.quote_character)
+            if str(self.path.get_lowered_part(k)).strip(self.quote_character) != v.lower().strip(
+                self.quote_character
             ):
-                approximate_match = False
+                approximate_match = False  # type: ignore[union-attr]
 
         if approximate_match and not exact_match:
-            target = self.create(
-                database=database, schema=schema, identifier=identifier
-            )
+            target = self.create(database=database, schema=schema, identifier=identifier)
             dbt.exceptions.approximate_relation_match(target, self)
 
         return exact_match
@@ -112,11 +112,13 @@ 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)
@@ -127,16 +129,18 @@ 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
@@ -146,10 +150,10 @@ 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
@@ -159,9 +163,7 @@ 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
@@ -173,27 +175,22 @@ 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: ParsedSourceDefinition, **kwargs: Any) -> Self:
         source_quoting = source.quoting.to_dict(omit_none=True)
-        source_quoting.pop('column', None)
+        source_quoting.pop("column", None)
         quote_policy = deep_merge(
             cls.get_default_quote_policy().to_dict(omit_none=True),
             source_quoting,
-            kwargs.get('quote_policy', {}),
+            kwargs.get("quote_policy", {}),
         )
 
         return cls.create(
@@ -201,12 +198,12 @@ class BaseRelation(FakeAPIObject, Hashable):
             schema=source.schema,
             identifier=source.identifier,
             quote_policy=quote_policy,
-            **kwargs
+            **kwargs,
         )
 
     @staticmethod
     def add_ephemeral_prefix(name: str):
-        return f'__dbt__cte__{name}'
+        return f"__dbt__cte__{name}"
 
     @classmethod
     def create_ephemeral_from_node(
@@ -239,7 +236,8 @@ class BaseRelation(FakeAPIObject, Hashable):
             schema=node.schema,
             identifier=node.alias,
             quote_policy=quote_policy,
-            **kwargs)
+            **kwargs,
+        )
 
     @classmethod
     def create_from(
@@ -251,15 +249,14 @@ class BaseRelation(FakeAPIObject, Hashable):
         if node.resource_type == NodeType.Source:
             if not isinstance(node, ParsedSourceDefinition):
                 raise InternalException(
-                    'type mismatch, expected ParsedSourceDefinition but got {}'
-                    .format(type(node))
+                    "type mismatch, expected ParsedSourceDefinition but got {}".format(type(node))
                 )
             return cls.create_from_source(node, **kwargs)
         else:
             if not isinstance(node, (ParsedNode, CompiledNode)):
                 raise InternalException(
-                    'type mismatch, expected ParsedNode or CompiledNode but '
-                    'got {}'.format(type(node))
+                    "type mismatch, expected ParsedNode or CompiledNode but "
+                    "got {}".format(type(node))
                 )
             return cls.create_from_node(config, node, **kwargs)
 
@@ -272,14 +269,16 @@ 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:
@@ -345,7 +344,7 @@ class BaseRelation(FakeAPIObject, Hashable):
         return RelationType
 
 
-Info = TypeVar('Info', bound='InformationSchema')
+Info = TypeVar("Info", bound="InformationSchema")
 
 
 @dataclass(frozen=True, eq=False, repr=False)
@@ -355,17 +354,15 @@ class InformationSchema(BaseRelation):
     def __post_init__(self):
         if not isinstance(self.information_schema_view, (type(None), str)):
             raise dbt.exceptions.CompilationException(
-                'Got an invalid name: {}'.format(self.information_schema_view)
+                "Got an invalid name: {}".format(self.information_schema_view)
             )
 
     @classmethod
-    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
@@ -396,9 +393,7 @@ 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(
@@ -420,6 +415,7 @@ 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:
@@ -429,9 +425,7 @@ 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
@@ -446,14 +440,13 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
                 dbt.exceptions.raise_compiler_error(str(seen))
 
         for information_schema_name, schema in self.search():
-            path = {
-                'database': information_schema_name.database,
-                'schema': schema
-            }
-            new.add(information_schema_name.incorporate(
-                path=path,
-                quote_policy={'database': False},
-                include_policy={'database': False},
-            ))
+            path = {"database": information_schema_name.database, "schema": schema}
+            new.add(
+                information_schema_name.incorporate(
+                    path=path,
+                    quote_policy={"database": False},
+                    include_policy={"database": False},
+                )
+            )
 
         return new

core/dbt/adapters/cache.py

@@ -18,9 +18,10 @@ from dbt.events.types import (
     RenameSchema,
     TemporaryRelation,
     UncachedRelation,
-    UpdateReference
+    UpdateReference,
 )
 from dbt.utils import lowercase
+from dbt.helper_types import Lazy
 
 
 def dot_separated(key: _ReferenceKey) -> str:
@@ -28,7 +29,7 @@ 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:
@@ -40,14 +41,15 @@ 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]:
@@ -81,7 +83,7 @@ class _CachedRelation:
         """
         return _make_key(self)
 
-    def add_reference(self, referrer: '_CachedRelation'):
+    def add_reference(self, referrer: "_CachedRelation"):
         """Add a reference from referrer to self, indicating that if this node
         were drop...cascaded, the referrer would be dropped as well.
 
@@ -125,9 +127,9 @@ class _CachedRelation:
         # table_name is ever anything but the identifier (via .create())
         self.inner = self.inner.incorporate(
             path={
-                'database': new_relation.inner.database,
-                'schema': new_relation.inner.schema,
-                'identifier': new_relation.inner.identifier
+                "database": new_relation.inner.database,
+                "schema": new_relation.inner.schema,
+                "identifier": new_relation.inner.identifier,
             },
         )
 
@@ -143,8 +145,9 @@ class _CachedRelation:
         """
         if new_key in self.referenced_by:
             dbt.exceptions.raise_cache_inconsistent(
-                'in rename of "{}" -> "{}", new name is in the cache already'
-                .format(old_key, new_key)
+                'in rename of "{}" -> "{}", new name is in the cache already'.format(
+                    old_key, new_key
+                )
             )
 
         if old_key not in self.referenced_by:
@@ -169,13 +172,16 @@ 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)
 
@@ -185,7 +191,9 @@ 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.
 
@@ -229,10 +237,7 @@ 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.
@@ -260,15 +265,13 @@ class RelationsCache:
             return
         if referenced is None:
             dbt.exceptions.raise_cache_inconsistent(
-                'in add_link, referenced link key {} not in cache!'
-                .format(referenced_key)
+                "in add_link, referenced link key {} not in cache!".format(referenced_key)
             )
 
         dependent = self.relations.get(dependent_key)
         if dependent is None:
             dbt.exceptions.raise_cache_inconsistent(
-                'in add_link, dependent link key {} not in cache!'
-                .format(dependent_key)
+                "in add_link, dependent link key {} not in cache!".format(dependent_key)
             )
 
         assert dependent is not None  # we just raised!
@@ -291,25 +294,20 @@ class RelationsCache:
         :raises InternalError: If either entry does not exist.
         """
         ref_key = _make_key(referenced)
+        dep_key = _make_key(dependent)
         if (ref_key.database, ref_key.schema) not in self:
             # if we have not cached the referenced schema at all, we must be
             # referring to a table outside our control. There's no need to make
             # a link - we will never drop the referenced relation during a run.
-            fire_event(UncachedRelation(dep_key=dependent, ref_key=ref_key))
+            fire_event(UncachedRelation(dep_key=dep_key, ref_key=ref_key))
             return
         if ref_key not in self.relations:
             # Insert a dummy "external" relation.
-            referenced = referenced.replace(
-                type=referenced.External
-            )
+            referenced = referenced.replace(type=referenced.External)
             self.add(referenced)
-
-        dep_key = _make_key(dependent)
         if dep_key not in self.relations:
             # Insert a dummy "external" relation.
-            dependent = dependent.replace(
-                type=referenced.External
-            )
+            dependent = dependent.replace(type=referenced.External)
             self.add(dependent)
         fire_event(AddLink(dep_key=dep_key, ref_key=ref_key))
         with self.lock:
@@ -323,11 +321,11 @@ class RelationsCache:
         """
         cached = _CachedRelation(relation)
         fire_event(AddRelation(relation=_make_key(cached)))
-        fire_event(DumpBeforeAddGraph(dump=self.dump_graph()))
+        fire_event(DumpBeforeAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
 
         with self.lock:
             self._setdefault(cached)
-        fire_event(DumpAfterAddGraph(dump=self.dump_graph()))
+        fire_event(DumpAfterAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
 
     def _remove_refs(self, keys):
         """Removes all references to all entries in keys. This does not
@@ -342,17 +340,17 @@ class RelationsCache:
         for cached in self.relations.values():
             cached.release_references(keys)
 
-    def _drop_cascade_relation(self, dropped):
+    def _drop_cascade_relation(self, dropped_key):
         """Drop the given relation and cascade it appropriately to all
         dependent relations.
 
         :param _CachedRelation dropped: An existing _CachedRelation to drop.
         """
-        if dropped not in self.relations:
-            fire_event(DropMissingRelation(relation=dropped))
+        if dropped_key not in self.relations:
+            fire_event(DropMissingRelation(relation=dropped_key))
             return
-        consequences = self.relations[dropped].collect_consequences()
-        fire_event(DropCascade(dropped=dropped, consequences=consequences))
+        consequences = self.relations[dropped_key].collect_consequences()
+        fire_event(DropCascade(dropped=dropped_key, consequences=consequences))
         self._remove_refs(consequences)
 
     def drop(self, relation):
@@ -366,10 +364,10 @@ 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)
-        fire_event(DropRelation(dropped=dropped))
+        dropped_key = _make_key(relation)
+        fire_event(DropRelation(dropped=dropped_key))
         with self.lock:
-            self._drop_cascade_relation(dropped)
+            self._drop_cascade_relation(dropped_key)
 
     def _rename_relation(self, old_key, new_relation):
         """Rename a relation named old_key to new_key, updating references.
@@ -416,8 +414,9 @@ class RelationsCache:
         """
         if new_key in self.relations:
             dbt.exceptions.raise_cache_inconsistent(
-                'in rename, new key {} already in cache: {}'
-                .format(new_key, list(self.relations.keys()))
+                "in rename, new key {} already in cache: {}".format(
+                    new_key, list(self.relations.keys())
+                )
             )
 
         if old_key not in self.relations:
@@ -441,7 +440,7 @@ class RelationsCache:
         new_key = _make_key(new)
         fire_event(RenameSchema(old_key=old_key, new_key=new_key))
 
-        fire_event(DumpBeforeRenameSchema(dump=self.dump_graph()))
+        fire_event(DumpBeforeRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
 
         with self.lock:
             if self._check_rename_constraints(old_key, new_key):
@@ -449,11 +448,9 @@ class RelationsCache:
             else:
                 self._setdefault(_CachedRelation(new))
 
-        fire_event(DumpAfterRenameSchema(dump=self.dump_graph()))
+        fire_event(DumpAfterRenameSchema(dump=Lazy.defer(lambda: 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.
@@ -464,14 +461,14 @@ class RelationsCache:
         schema = lowercase(schema)
         with self.lock:
             results = [
-                r.inner for r in self.relations.values()
-                if (lowercase(r.schema) == schema and
-                    lowercase(r.database) == database)
+                r.inner
+                for r in self.relations.values()
+                if (lowercase(r.schema) == schema and lowercase(r.database) == database)
             ]
 
         if None in results:
             dbt.exceptions.raise_cache_inconsistent(
-                'in get_relations, a None relation was found in the cache!'
+                "in get_relations, a None relation was found in the cache!"
             )
         return results
 

core/dbt/adapters/factory.py

@@ -49,9 +49,7 @@ 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
 
@@ -61,13 +59,13 @@ 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:
+            if exc.name == "dbt.adapters." + name:
                 fire_event(AdapterImportError(exc=exc))
-                raise RuntimeException(f'Could not find adapter type {name}!')
+                raise RuntimeException(f"Could not find adapter type {name}!")
             # otherwise, the error had to have come from some underlying
             # library. Log the stack trace.
 
@@ -78,8 +76,8 @@ class AdapterContainer:
 
         if plugin_type != name:
             raise RuntimeException(
-                f'Expected to find adapter with type named {name}, got '
-                f'adapter with type {plugin_type}'
+                f"Expected to find adapter with type named {name}, got "
+                f"adapter with type {plugin_type}"
             )
 
         with self.lock:
@@ -109,8 +107,7 @@ 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()
@@ -140,9 +137,7 @@ class AdapterContainer:
             try:
                 plugin = self.plugins[plugin_name]
             except KeyError:
-                raise InternalException(
-                    f'No plugin found for {plugin_name}'
-                ) from None
+                raise InternalException(f"No plugin found for {plugin_name}") from None
             plugins.append(plugin)
             seen.add(plugin_name)
             if plugin.dependencies is None:
@@ -153,9 +148,7 @@ class AdapterContainer:
         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 +158,7 @@ class AdapterContainer:
             try:
                 path = self.packages[package_name]
             except KeyError:
-                raise InternalException(
-                    f'No internal package listing found for {package_name}'
-                )
+                raise InternalException(f"No internal package listing found for {package_name}")
             paths.append(path)
         return paths
 
@@ -186,9 +177,12 @@ 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()
 
 

core/dbt/adapters/protocol.py

@@ -1,18 +1,24 @@
 from dataclasses import dataclass
 from typing import (
-    Type, Hashable, Optional, ContextManager, List, Generic, TypeVar, ClassVar,
-    Tuple, Union, Dict, Any
+    Type,
+    Hashable,
+    Optional,
+    ContextManager,
+    List,
+    Generic,
+    TypeVar,
+    ClassVar,
+    Tuple,
+    Union,
+    Dict,
+    Any,
 )
 from typing_extensions import Protocol
 
 import agate
 
-from dbt.contracts.connection import (
-    Connection, AdapterRequiredConfig, AdapterResponse
-)
-from dbt.contracts.graph.compiled import (
-    CompiledNode, ManifestNode, NonSourceCompiledNode
-)
+from dbt.contracts.connection import Connection, AdapterRequiredConfig, AdapterResponse
+from dbt.contracts.graph.compiled import CompiledNode, ManifestNode, NonSourceCompiledNode
 from dbt.contracts.graph.parsed import ParsedNode, ParsedSourceDefinition
 from dbt.contracts.graph.model_config import BaseConfig
 from dbt.contracts.graph.manifest import Manifest
@@ -34,7 +40,7 @@ class ColumnProtocol(Protocol):
     pass
 
 
-Self = TypeVar('Self', bound='RelationProtocol')
+Self = TypeVar("Self", bound="RelationProtocol")
 
 
 class RelationProtocol(Protocol):
@@ -64,22 +70,15 @@ class CompilerProtocol(Protocol):
         ...
 
 
-AdapterConfig_T = TypeVar(
-    'AdapterConfig_T', bound=AdapterConfig
-)
-ConnectionManager_T = TypeVar(
-    'ConnectionManager_T', bound=ConnectionManagerProtocol
-)
-Relation_T = TypeVar(
-    'Relation_T', bound=RelationProtocol
-)
-Column_T = TypeVar(
-    'Column_T', bound=ColumnProtocol
-)
-Compiler_T = TypeVar('Compiler_T', bound=CompilerProtocol)
+AdapterConfig_T = TypeVar("AdapterConfig_T", bound=AdapterConfig)
+ConnectionManager_T = TypeVar("ConnectionManager_T", bound=ConnectionManagerProtocol)
+Relation_T = TypeVar("Relation_T", bound=RelationProtocol)
+Column_T = TypeVar("Column_T", bound=ColumnProtocol)
+Compiler_T = TypeVar("Compiler_T", bound=CompilerProtocol)
 
 
-class AdapterProtocol(
+# TODO CT-211
+class AdapterProtocol(  # type: ignore[misc]
     Protocol,
     Generic[
         AdapterConfig_T,
@@ -87,7 +86,7 @@ class AdapterProtocol(
         Relation_T,
         Column_T,
         Compiler_T,
-    ]
+    ],
 ):
     AdapterSpecificConfigs: ClassVar[Type[AdapterConfig_T]]
     Column: ClassVar[Type[Column_T]]
@@ -156,7 +155,7 @@ 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

@@ -4,7 +4,7 @@ from collections import namedtuple
 from typing import Optional
 
 
-_ReferenceKey = namedtuple('_ReferenceKey', 'database schema identifier')
+_ReferenceKey = namedtuple("_ReferenceKey", "database schema identifier")
 
 
 def lowercase(value: Optional[str]) -> Optional[str]:
@@ -19,6 +19,6 @@ def _make_key(relation) -> _ReferenceKey:
     to keep track of quoting
     """
     # databases and schemas can both be None
-    return _ReferenceKey(lowercase(relation.database),
-                         lowercase(relation.schema),
-                         lowercase(relation.identifier))
+    return _ReferenceKey(
+        lowercase(relation.database), lowercase(relation.schema), lowercase(relation.identifier)
+    )

core/dbt/adapters/sql/connections.py

@@ -1,15 +1,13 @@
 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.contracts.connection import Connection, ConnectionState, AdapterResponse
 from dbt.events.functions import fire_event
 from dbt.events.types import ConnectionUsed, SQLQuery, SQLCommit, SQLQueryStatus
 
@@ -23,11 +21,12 @@ class SQLConnectionManager(BaseConnectionManager):
         - get_response
         - open
     """
+
     @abc.abstractmethod
     def cancel(self, connection: Connection):
         """Cancel the given connection."""
         raise dbt.exceptions.NotImplementedException(
-            '`cancel` is not implemented for this adapter!'
+            "`cancel` is not implemented for this adapter!"
         )
 
     def cancel_open(self) -> List[str]:
@@ -40,10 +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)
@@ -54,7 +50,7 @@ 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:
@@ -63,7 +59,7 @@ class SQLConnectionManager(BaseConnectionManager):
 
         with self.exception_handler(sql):
             if abridge_sql_log:
-                log_sql = '{}...'.format(sql[:512])
+                log_sql = "{}...".format(sql[:512])
             else:
                 log_sql = sql
 
@@ -75,34 +71,36 @@ class SQLConnectionManager(BaseConnectionManager):
 
             fire_event(
                 SQLQueryStatus(
-                    status=str(self.get_response(cursor)),
-                    elapsed=round((time.time() - pre), 2)
+                    status=str(self.get_response(cursor)), elapsed=round((time.time() - pre), 2)
                 )
             )
 
             return connection, cursor
 
     @abc.abstractclassmethod
-    def get_response(cls, cursor: Any) -> Union[AdapterResponse, str]:
+    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!'
+            "`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
@@ -115,14 +113,11 @@ 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)
@@ -133,17 +128,18 @@ 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(
                 '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()
 
@@ -155,7 +151,8 @@ class SQLConnectionManager(BaseConnectionManager):
         if connection.transaction_open is False:
             raise dbt.exceptions.InternalException(
                 'Tried to commit transaction on connection "{}", but '
-                'it does not have one open!'.format(connection.name))
+                "it does not have one open!".format(connection.name)
+            )
 
         fire_event(SQLCommit(conn_name=connection.name))
         self.add_commit_query()

core/dbt/adapters/sql/impl.py

@@ -13,21 +13,21 @@ 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
@@ -63,30 +63,24 @@ 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
@@ -102,36 +96,27 @@ 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)
                 fire_event(
                     ColTypeChange(
                         orig_type=target_column.data_type,
                         new_type=new_type,
-                        table=current,
+                        table=_make_key(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
@@ -139,53 +124,40 @@ class SQLAdapter(BaseAdapter):
         4. Rename the new column to existing column
         """
         kwargs = {
-            'relation': relation,
-            'column_name': column_name,
-            'new_column_type': new_column_type,
+            "relation": relation,
+            "column_name": column_name,
+            "new_column_type": new_column_type,
         }
-        self.execute_macro(
-            ALTER_COLUMN_TYPE_MACRO_NAME,
-            kwargs=kwargs
-        )
+        self.execute_macro(ALTER_COLUMN_TYPE_MACRO_NAME, kwargs=kwargs)
 
     def drop_relation(self, relation):
         if relation.type is None:
             dbt.exceptions.raise_compiler_error(
-                'Tried to drop relation {}, but its type is null.'
-                .format(relation))
+                "Tried to drop relation {}, but its type is null.".format(relation)
+            )
 
         self.cache_dropped(relation)
-        self.execute_macro(
-            DROP_RELATION_MACRO_NAME,
-            kwargs={'relation': relation}
-        )
+        self.execute_macro(DROP_RELATION_MACRO_NAME, kwargs={"relation": relation})
 
     def truncate_relation(self, relation):
-        self.execute_macro(
-            TRUNCATE_RELATION_MACRO_NAME,
-            kwargs={'relation': relation}
-        )
+        self.execute_macro(TRUNCATE_RELATION_MACRO_NAME, kwargs={"relation": relation})
 
     def rename_relation(self, from_relation, to_relation):
         self.cache_renamed(from_relation, to_relation)
 
-        kwargs = {'from_relation': from_relation, 'to_relation': to_relation}
-        self.execute_macro(
-            RENAME_RELATION_MACRO_NAME,
-            kwargs=kwargs
-        )
+        kwargs = {"from_relation": from_relation, "to_relation": to_relation}
+        self.execute_macro(RENAME_RELATION_MACRO_NAME, kwargs=kwargs)
 
     def get_columns_in_relation(self, relation):
         return self.execute_macro(
-            GET_COLUMNS_IN_RELATION_MACRO_NAME,
-            kwargs={'relation': relation}
+            GET_COLUMNS_IN_RELATION_MACRO_NAME, kwargs={"relation": relation}
         )
 
     def create_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
         fire_event(SchemaCreation(relation=_make_key(relation)))
         kwargs = {
-            'relation': relation,
+            "relation": relation,
         }
         self.execute_macro(CREATE_SCHEMA_MACRO_NAME, kwargs=kwargs)
         self.commit_if_has_connection()
@@ -196,49 +168,42 @@ class SQLAdapter(BaseAdapter):
         relation = relation.without_identifier()
         fire_event(SchemaDrop(relation=_make_key(relation)))
         kwargs = {
-            'relation': relation,
+            "relation": relation,
         }
         self.execute_macro(DROP_SCHEMA_MACRO_NAME, kwargs=kwargs)
         # we can update the cache here
         self.cache.drop_schema(relation.database, relation.schema)
 
     def list_relations_without_caching(
-        self, schema_relation: BaseRelation,
+        self,
+        schema_relation: BaseRelation,
     ) -> List[BaseRelation]:
-        kwargs = {'schema_relation': schema_relation}
-        results = self.execute_macro(
-            LIST_RELATIONS_MACRO_NAME,
-            kwargs=kwargs
-        )
+        kwargs = {"schema_relation": schema_relation}
+        results = self.execute_macro(LIST_RELATIONS_MACRO_NAME, kwargs=kwargs)
 
         relations = []
-        quote_policy = {
-            'database': True,
-            'schema': True,
-            'identifier': True
-        }
+        quote_policy = {"database": True, "schema": True, "identifier": True}
         for _database, name, _schema, _type in results:
             try:
                 _type = self.Relation.get_relation_type(_type)
             except ValueError:
                 _type = self.Relation.External
-            relations.append(self.Relation.create(
-                database=_database,
-                schema=_schema,
-                identifier=name,
-                quote_policy=quote_policy,
-                type=_type
-            ))
+            relations.append(
+                self.Relation.create(
+                    database=_database,
+                    schema=_schema,
+                    identifier=name,
+                    quote_policy=quote_policy,
+                    type=_type,
+                )
+            )
         return relations
 
     def quote(self, identifier):
         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]
 
@@ -246,13 +211,32 @@ 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/clients/README.md

@@ -0,0 +1 @@
+# Clients README

core/dbt/clients/_jinja_blocks.py

@@ -10,79 +10,83 @@ 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 +103,10 @@ 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 +124,7 @@ 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)
@@ -136,7 +140,7 @@ class TagIterator:
         match = self._first_match(*patterns, **kwargs)
         if match is None:
             msg = 'unexpected EOF, expected {}, got "{}"'.format(
-                expected_name, self.data[self.pos:]
+                expected_name, self.data[self.pos :]
             )
             dbt.exceptions.raise_compiler_error(msg)
         return match
@@ -156,22 +160,20 @@ 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 +190,19 @@ 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 +219,24 @@ 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 +245,9 @@ 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)
@@ -264,8 +257,8 @@ class TagIterator:
                 yield self.handle_tag(match)
             else:
                 raise dbt.exceptions.InternalException(
-                    'Invalid regex match in next_block, expected block start, '
-                    'expr start, or comment start'
+                    "Invalid regex match in next_block, expected block start, "
+                    "expr start, or comment start"
                 )
 
     def __iter__(self):
@@ -273,21 +266,18 @@ class TagIterator:
 
 
 duplicate_tags = (
-    'Got nested tags: {outer.block_type_name} (started at {outer.start}) did '
-    'not have a matching {{% end{outer.block_type_name} %}} before a '
-    'subsequent {inner.block_type_name} was found (started at {inner.start})'
+    "Got nested tags: {outer.block_type_name} (started at {outer.start}) did "
+    "not have a matching {{% end{outer.block_type_name} %}} before a "
+    "subsequent {inner.block_type_name} was found (started at {inner.start})"
 )
 
 
 _CONTROL_FLOW_TAGS = {
-    'if': 'endif',
-    'for': 'endfor',
+    "if": "endif",
+    "for": "endfor",
 }
 
-_CONTROL_FLOW_END_TAGS = {
-    v: k
-    for k, v in _CONTROL_FLOW_TAGS.items()
-}
+_CONTROL_FLOW_END_TAGS = {v: k for k, v in _CONTROL_FLOW_TAGS.items()}
 
 
 class BlockIterator:
@@ -310,15 +300,15 @@ 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 +319,35 @@ class BlockIterator:
                     found = self.stack.pop()
                 else:
                     expected = _CONTROL_FLOW_END_TAGS[tag.block_type_name]
-                    dbt.exceptions.raise_compiler_error((
-                        'Got an unexpected control flow end tag, got {} but '
-                        'never saw a preceeding {} (@ {})'
-                    ).format(
-                        tag.block_type_name,
-                        expected,
-                        self.tag_parser.linepos(tag.start)
-                    ))
+                    dbt.exceptions.raise_compiler_error(
+                        (
+                            "Got an unexpected control flow end tag, got {} but "
+                            "never saw a preceeding {} (@ {})"
+                        ).format(tag.block_type_name, expected, self.tag_parser.linepos(tag.start))
+                    )
                 expected = _CONTROL_FLOW_TAGS[found]
                 if expected != tag.block_type_name:
-                    dbt.exceptions.raise_compiler_error((
-                        'Got an unexpected control flow end tag, got {} but '
-                        'expected {} next (@ {})'
-                    ).format(
-                        tag.block_type_name,
-                        expected,
-                        self.tag_parser.linepos(tag.start)
-                    ))
+                    dbt.exceptions.raise_compiler_error(
+                        (
+                            "Got an unexpected control flow end tag, got {} but "
+                            "expected {} next (@ {})"
+                        ).format(tag.block_type_name, expected, self.tag_parser.linepos(tag.start))
+                    )
 
             if tag.block_type_name in allowed_blocks:
                 if self.stack:
-                    dbt.exceptions.raise_compiler_error((
-                        'Got a block definition inside control flow at {}. '
-                        'All dbt block definitions must be at the top level'
-                    ).format(self.tag_parser.linepos(tag.start)))
+                    dbt.exceptions.raise_compiler_error(
+                        (
+                            "Got a block definition inside control flow at {}. "
+                            "All dbt block definitions must be at the top level"
+                        ).format(self.tag_parser.linepos(tag.start))
+                    )
                 if self.current is not None:
                     dbt.exceptions.raise_compiler_error(
                         duplicate_tags.format(outer=self.current, inner=tag)
                     )
                 if collect_raw_data:
-                    raw_data = self.data[self.last_position:tag.start]
+                    raw_data = self.data[self.last_position : tag.start]
                     self.last_position = tag.start
                     if raw_data:
                         yield BlockData(raw_data)
@@ -371,23 +359,25 @@ class BlockIterator:
                 yield BlockTag(
                     block_type_name=self.current.block_type_name,
                     block_name=self.current.block_name,
-                    contents=self.data[self.current.end:tag.start],
-                    full_block=self.data[self.current.start:tag.end]
+                    contents=self.data[self.current.end : tag.start],
+                    full_block=self.data[self.current.start : tag.end],
                 )
                 self.current = None
 
         if self.current:
-            linecount = self.data[:self.current.end].count('\n') + 1
-            dbt.exceptions.raise_compiler_error((
-                'Reached EOF without finding a close tag for '
-                '{} (searched from line {})'
-            ).format(self.current.block_type_name, linecount))
+            linecount = self.data[: self.current.end].count("\n") + 1
+            dbt.exceptions.raise_compiler_error(
+                (
+                    "Reached EOF without finding a close tag for " "{} (searched from line {})"
+                ).format(self.current.block_type_name, linecount)
+            )
 
         if collect_raw_data:
-            raw_data = self.data[self.last_position:]
+            raw_data = self.data[self.last_position :]
             if raw_data:
                 yield BlockData(raw_data)
 
     def lex_for_blocks(self, allowed_blocks=None, collect_raw_data=True):
-        return list(self.find_blocks(allowed_blocks=allowed_blocks,
-                                     collect_raw_data=collect_raw_data))
+        return list(
+            self.find_blocks(allowed_blocks=allowed_blocks, collect_raw_data=collect_raw_data)
+        )

core/dbt/clients/agate_helper.py

@@ -10,7 +10,17 @@ from typing import Iterable, List, Dict, Union, Optional, Any
 from dbt.exceptions import RuntimeException
 
 
-BOM = BOM_UTF8.decode('utf-8')  # '\ufeff'
+BOM = BOM_UTF8.decode("utf-8")  # '\ufeff'
+
+
+class 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)
@@ -172,8 +169,8 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
         elif not isinstance(value, type(existing_type)):
             # actual type mismatch!
             raise RuntimeException(
-                f'Tables contain columns with the same names ({key}), '
-                f'but different types ({value} vs {existing_type})'
+                f"Tables contain columns with the same names ({key}), "
+                f"but different types ({value} vs {existing_type})"
             )
 
     def finalize(self) -> Dict[str, agate.data_types.DataType]:
@@ -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

@@ -4,11 +4,21 @@ import os.path
 from dbt.clients.system import run_cmd, rmdir
 from dbt.events.functions import fire_event
 from dbt.events.types import (
-    GitSparseCheckoutSubdirectory, GitProgressCheckoutRevision,
-    GitProgressUpdatingExistingDependency, GitProgressPullingNewDependency,
-    GitNothingToDo, GitProgressUpdatedCheckoutRange, GitProgressCheckedOutAt
+    GitSparseCheckoutSubdirectory,
+    GitProgressCheckoutRevision,
+    GitProgressUpdatingExistingDependency,
+    GitProgressPullingNewDependency,
+    GitNothingToDo,
+    GitProgressUpdatedCheckoutRange,
+    GitProgressCheckedOutAt,
+)
+from dbt.exceptions import (
+    CommandResultError,
+    RuntimeException,
+    bad_package_spec,
+    raise_git_cloning_error,
+    raise_git_cloning_problem,
 )
-import dbt.exceptions
 from packaging import version
 
 
@@ -18,23 +28,23 @@ def _is_commit(revision: str) -> bool:
 
 
 def _raise_git_cloning_error(repo, revision, error):
-    stderr = error.stderr.decode('utf-8').strip()
-    if 'usage: git' in stderr:
-        stderr = stderr.split('\nusage: git')[0]
+    stderr = error.stderr.strip()
+    if "usage: git" in stderr:
+        stderr = stderr.split("\nusage: git")[0]
     if re.match("fatal: destination path '(.+)' already exists", stderr):
-        raise error
+        raise_git_cloning_error(error)
 
-    dbt.exceptions.bad_package_spec(repo, revision, stderr)
+    bad_package_spec(repo, revision, stderr)
 
 
 def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirectory=None):
     has_revision = revision is not None
     is_commit = _is_commit(revision or "")
 
-    clone_cmd = ['git', 'clone', '--depth', '1']
+    clone_cmd = ["git", "clone", "--depth", "1"]
     if subdirectory:
         fire_event(GitSparseCheckoutSubdirectory(subdir=subdirectory))
-        out, _ = run_cmd(cwd, ['git', '--version'], env={'LC_ALL': 'C'})
+        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
@@ -42,37 +52,37 @@ 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)
     try:
-        result = run_cmd(cwd, clone_cmd, env={'LC_ALL': 'C'})
-    except dbt.exceptions.CommandResultError as exc:
+        result = run_cmd(cwd, clone_cmd, env={"LC_ALL": "C"})
+    except CommandResultError as exc:
         _raise_git_cloning_error(repo, revision, exc)
 
     if subdirectory:
-        cwd_subdir = os.path.join(cwd, dirname or '')
-        clone_cmd_subdir = ['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 dbt.exceptions.CommandResultError as exc:
+        except CommandResultError as exc:
             _raise_git_cloning_error(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
 
 
@@ -84,44 +94,44 @@ def _checkout(cwd, repo, revision):
     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:
+        stderr = exc.stderr.strip()
+        bad_package_spec(repo, revision, stderr)
 
 
 def get_current_sha(cwd):
-    out, err = run_cmd(cwd, ['git', 'rev-parse', 'HEAD'], env={'LC_ALL': 'C'})
+    out, err = run_cmd(cwd, ["git", "rev-parse", "HEAD"], env={"LC_ALL": "C"})
 
-    return out.decode('utf-8')
+    return out.decode("utf-8")
 
 
 def remove_remote(cwd):
-    return run_cmd(cwd, ['git', 'remote', 'rm', 'origin'], env={'LC_ALL': 'C'})
+    return run_cmd(cwd, ["git", "remote", "rm", "origin"], env={"LC_ALL": "C"})
 
 
-def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
-                       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(
@@ -131,14 +141,11 @@ 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:
-            print(
-                '\nSomething went wrong while cloning {}'.format(repo) +
-                '\nCheck the debug logs for more information')
-            raise
+            raise_git_cloning_problem(repo)
 
     directory = None
     start_sha = None
@@ -146,11 +153,9 @@ def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
         directory = exists.group(1)
         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 RuntimeException(f'Error cloning {repo} - never saw "Cloning into ..." from git')
         directory = matches.group(1)
         fire_event(GitProgressPullingNewDependency(dir=directory))
     full_path = os.path.join(cwd, directory)
@@ -161,9 +166,9 @@ def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
         if start_sha == end_sha:
             fire_event(GitNothingToDo(sha=start_sha[:7]))
         else:
-            fire_event(GitProgressUpdatedCheckoutRange(
-                start_sha=start_sha[:7], end_sha=end_sha[:7]
-            ))
+            fire_event(
+                GitProgressUpdatedCheckoutRange(start_sha=start_sha[:7], end_sha=end_sha[:7])
+            )
     else:
         fire_event(GitProgressCheckedOutAt(end_sha=end_sha[:7]))
-    return os.path.join(directory, subdirectory or '')
+    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
@@ -20,17 +17,24 @@ 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_render
+    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.exceptions import (
-    InternalException, raise_compiler_error, CompilationException,
-    invalid_materialization_argument, MacroReturn, JinjaRenderingException,
-    UndefinedMacroException
+    InternalException,
+    raise_compiler_error,
+    CompilationException,
+    invalid_materialization_argument,
+    MacroReturn,
+    JinjaRenderingException,
+    UndefinedMacroException,
 )
 from dbt import flags
 
@@ -40,27 +44,22 @@ 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
@@ -73,12 +72,10 @@ 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
 
 
@@ -94,8 +91,8 @@ 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
@@ -106,7 +103,7 @@ 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!
     """
@@ -138,7 +135,7 @@ def quoted_native_concat(nodes):
     head = list(islice(nodes, 2))
 
     if not head:
-        return ''
+        return ""
 
     if len(head) == 1:
         raw = head[0]
@@ -156,13 +153,9 @@ 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 JinjaRenderingException(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 JinjaRenderingException(f"Could not convert value '{raw!s}' into type 'number'")
 
     return result
 
@@ -180,9 +173,7 @@ 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()
 
@@ -221,10 +212,10 @@ 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()
@@ -247,9 +238,7 @@ class BaseMacroGenerator:
     def call_macro(self, *args, **kwargs):
         # called from __call__ methods
         if self.context is None:
-            raise InternalException(
-                'Context is still None in call_macro!'
-            )
+            raise InternalException("Context is still None in call_macro!")
         assert self.context is not None
 
         macro = self.get_macro()
@@ -276,7 +265,7 @@ class MacroStack(threading.local):
     def pop(self, name):
         got = self.call_stack.pop()
         if got != name:
-            raise InternalException(f'popped {got}, expected {name}')
+            raise InternalException(f"popped {got}, expected {name}")
 
 
 class MacroGenerator(BaseMacroGenerator):
@@ -285,7 +274,7 @@ 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
@@ -333,9 +322,7 @@ 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()
@@ -345,7 +332,7 @@ 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"""
@@ -356,45 +343,39 @@ class QueryStringGenerator(BaseMacroGenerator):
 
 
 class MaterializationExtension(jinja2.ext.Extension):
-    tags = ['materialization']
+    tags = ["materialization"]
 
     def parse(self, parser):
         node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
-        materialization_name = \
-            parser.parse_assign_target(name_only=True).name
+        materialization_name = parser.parse_assign_target(name_only=True).name
 
-        adapter_name = 'default'
+        adapter_name = "default"
         node.args = []
         node.defaults = []
 
-        while parser.stream.skip_if('comma'):
+        while parser.stream.skip_if("comma"):
             target = parser.parse_assign_target(name_only=True)
 
-            if target.name == 'default':
+            if target.name == "default":
                 pass
 
-            elif target.name == 'adapter':
-                parser.stream.expect('assign')
+            elif target.name == "adapter":
+                parser.stream.expect("assign")
                 value = parser.parse_expression()
                 adapter_name = value.value
 
             else:
-                invalid_materialization_argument(
-                    materialization_name, target.name
-                )
+                invalid_materialization_argument(materialization_name, target.name)
 
-        node.name = get_materialization_macro_name(
-            materialization_name, adapter_name
-        )
+        node.name = get_materialization_macro_name(materialization_name, adapter_name)
 
-        node.body = parser.parse_statements(('name:endmaterialization',),
-                                            drop_needle=True)
+        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)
@@ -403,13 +384,12 @@ 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)
@@ -417,13 +397,12 @@ 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):
@@ -444,10 +423,9 @@ 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
@@ -458,24 +436,24 @@ def create_undefined(node=None):
             return self
 
         def __reduce__(self):
-            raise_compiler_error(f'{self.name} is undefined', node=node)
+            raise_compiler_error(f"{self.name} is undefined", node=node)
 
     return Undefined
 
 
 NATIVE_FILTERS: Dict[str, Callable[[Any], Any]] = {
-    'as_text': TextMarker,
-    'as_bool': BoolMarker,
-    'as_native': NativeMarker,
-    'as_number': NumberMarker,
+    "as_text": TextMarker,
+    "as_bool": BoolMarker,
+    "as_native": NativeMarker,
+    "as_number": NumberMarker,
 }
 
 
 TEXT_FILTERS: Dict[str, Callable[[Any], Any]] = {
-    'as_text': lambda x: x,
-    'as_bool': lambda x: x,
-    'as_native': lambda x: x,
-    'as_number': lambda x: x,
+    "as_text": lambda x: x,
+    "as_bool": lambda x: x,
+    "as_native": lambda x: x,
+    "as_number": lambda x: x,
 }
 
 
@@ -485,15 +463,15 @@ 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
@@ -556,8 +534,8 @@ 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!)
@@ -565,7 +543,7 @@ 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(
@@ -581,11 +559,7 @@ 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,
@@ -606,7 +580,7 @@ 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.
@@ -621,12 +595,11 @@ 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(
@@ -638,25 +611,20 @@ def add_rendered_test_kwargs(
     renderer, then insert that value into the given context as the special test
     keyword arguments member.
     """
-    looks_like_func = r'^\s*(env_var|ref|var|source|doc)\s*\(.+\)\s*$'
+    looks_like_func = r"^\s*(env_var|ref|var|source|doc)\s*\(.+\)\s*$"
 
-    def _convert_function(
-        value: Any, keypath: Tuple[Union[str, int], ...]
-    ) -> Any:
+    def _convert_function(value: Any, keypath: Tuple[Union[str, int], ...]) -> Any:
         if isinstance(value, str):
-            if keypath == ('column_name',):
+            if keypath == ("column_name",):
                 # special case: Don't render column names as native, make them
                 # be strings
                 return value
 
             if re.match(looks_like_func, value) is not None:
                 # curly braces to make rendering happy
-                value = f'{{{{ {value} }}}}'
+                value = f"{{{{ {value} }}}}"
 
-            value = get_rendered(
-                value, context, node, capture_macros=capture_macros,
-                native=True
-            )
+            value = get_rendered(value, context, node, capture_macros=capture_macros, native=True)
 
         return value
 

core/dbt/clients/jinja_static.py

@@ -8,11 +8,11 @@ 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
@@ -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 +111,41 @@ 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_compiler_error(
+                        f"The macro_name parameter ({kwarg.value.value}) "
+                        "to adapter.dispatch was not a string"
+                    )
+            elif kwarg.key == "macro_namespace":
                 # This will remain to enable static resolution
                 kwarg_type = type(kwarg.value).__name__
-                if kwarg_type == 'Const':
+                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_compiler_error(
+                        "The macro_namespace parameter to adapter.dispatch "
+                        f"is a {kwarg_type}, not a string"
+                    )
 
     # positional arguments
     if packages_arg:
-        if packages_arg_type == 'List':
+        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 +153,6 @@ 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

@@ -1,86 +1,164 @@
 import functools
+from typing import Any, Dict, List
 import requests
 from dbt.events.functions import fire_event
 from dbt.events.types import (
     RegistryProgressMakingGETRequest,
-    RegistryProgressGETResponse
+    RegistryProgressGETResponse,
+    RegistryIndexProgressMakingGETRequest,
+    RegistryIndexProgressGETResponse,
+    RegistryResponseUnexpectedType,
+    RegistryResponseMissingTopKeys,
+    RegistryResponseMissingNestedKeys,
+    RegistryResponseExtraNestedKeys,
 )
 from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
 from dbt import deprecations
 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)
+def _get(package_name, registry_base_url=None):
+    url = _get_url(package_name, registry_base_url)
     fire_event(RegistryProgressMakingGETRequest(url=url))
+    # all exceptions from requests get caught in the retry logic so no need to wrap this here
     resp = requests.get(url, timeout=30)
     fire_event(RegistryProgressGETResponse(url=url, resp_code=resp.status_code))
     resp.raise_for_status()
-    if resp is None:
-        raise requests.exceptions.ContentDecodingError(
-            'Request error: The response is None', response=resp
+
+    # 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()
+
+    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"
         )
-    return resp.json()
+        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)
 
-def index(registry_base_url=None):
-    return _get_with_retries('api/v1/index.json', registry_base_url)
+    # 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)
 
-
-index_cached = memoized(index)
-
-
-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)
+    # 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)
 
     # 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) or ('redirectname' in response):
-
-        if ('redirectnamespace' in response) and response['redirectnamespace'] is not None:
-            use_namespace = response['redirectnamespace']
+        if ("redirectnamespace" in response) and response["redirectnamespace"] is not None:
+            use_namespace = response["redirectnamespace"]
         else:
-            use_namespace = response['namespace']
+            use_namespace = response["namespace"]
 
-        if ('redirectname' in response) and response['redirectname'] is not None:
-            use_name = response['redirectname']
+        if ("redirectname" in response) and response["redirectname"] is not None:
+            use_name = response["redirectname"]
         else:
-            use_name = response['name']
+            use_name = response["name"]
 
         new_nwo = use_namespace + "/" + use_name
-        deprecations.warn('package-redirect', old_name=name, new_name=new_nwo)
+        deprecations.warn("package-redirect", old_name=package_name, new_name=new_nwo)
 
     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)
+    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 get_available_versions(package_name) -> List["str"]:
+    # returns a list of all available versions of a package
+    response = package(package_name)
+    return list(response)
+
+
+def _get_index(registry_base_url=None):
+
+    url = _get_url("index", registry_base_url)
+    fire_event(RegistryIndexProgressMakingGETRequest(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

@@ -11,19 +11,21 @@ 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 dbt.events.functions import fire_event
 from dbt.events.types import (
-    SystemErrorRetrievingModTime, SystemCouldNotWrite, SystemExecutingCmd, SystemStdOutMsg,
-    SystemStdErrMsg, SystemReportReturnCode
+    SystemErrorRetrievingModTime,
+    SystemCouldNotWrite,
+    SystemExecutingCmd,
+    SystemStdOutMsg,
+    SystemStdErrMsg,
+    SystemReportReturnCode,
 )
 import dbt.exceptions
 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
@@ -55,36 +57,35 @@ def find_matching(
     reobj = re.compile(regex, re.IGNORECASE)
 
     for relative_path_to_search in relative_paths_to_search:
-        absolute_path_to_search = os.path.join(
-            root_path, relative_path_to_search)
+        absolute_path_to_search = os.path.join(root_path, relative_path_to_search)
         walk_results = os.walk(absolute_path_to_search)
 
         for current_path, subdirectories, local_files in walk_results:
             for local_file in local_files:
                 absolute_path = os.path.join(current_path, local_file)
-                relative_path = os.path.relpath(
-                    absolute_path, absolute_path_to_search
-                )
+                relative_path = os.path.relpath(absolute_path, absolute_path_to_search)
                 modification_time = 0.0
                 try:
                     modification_time = os.path.getmtime(absolute_path)
                 except OSError:
                     fire_event(SystemErrorRetrievingModTime(path=absolute_path))
                 if reobj.match(local_file):
-                    matching.append({
-                        'searched_path': relative_path_to_search,
-                        'absolute_path': absolute_path,
-                        'relative_path': relative_path,
-                        'modification_time': modification_time,
-                    })
+                    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()
@@ -111,14 +112,14 @@ 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
 
@@ -130,7 +131,7 @@ def make_symlink(source: str, link_path: str) -> None:
     Create a symlink at `link_path` referring to `source`.
     """
     if not supports_symlinks():
-        dbt.exceptions.system_error('create a symbolic link')
+        dbt.exceptions.system_error("create a symbolic link")
 
     os.symlink(source, link_path)
 
@@ -139,11 +140,11 @@ 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
@@ -152,15 +153,15 @@ 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.
             fire_event(SystemCouldNotWrite(path=path, reason=reason, exc=exc))
@@ -177,9 +178,7 @@ 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)
@@ -196,10 +195,7 @@ 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:
@@ -209,7 +205,7 @@ 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
@@ -228,7 +224,7 @@ 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
 
@@ -243,7 +239,7 @@ def _win_prepare_path(path: str) -> str:
 
 
 def _supports_long_paths() -> bool:
-    if sys.platform != 'win32':
+    if sys.platform != "win32":
         return True
     # Eryk Sun says to use `WinDLL('ntdll')` instead of `windll.ntdll` because
     # of pointer caching in a comment here:
@@ -251,11 +247,11 @@ def _supports_long_paths() -> bool:
     # I don't know exaclty what he means, but I am inclined to believe him as
     # he's pretty active on Python windows bugs!
     try:
-        dll = WinDLL('ntdll')
+        dll = WinDLL("ntdll")
     except OSError:  # I don't think this happens? you need ntdll to run python
         return False
     # not all windows versions have it at all
-    if not hasattr(dll, 'RtlAreLongPathsEnabled'):
+    if not hasattr(dll, "RtlAreLongPathsEnabled"):
         return False
     # tell windows we want to get back a single unsigned byte (a bool).
     dll.RtlAreLongPathsEnabled.restype = c_bool
@@ -275,7 +271,7 @@ def convert_path(path: str) -> str:
     if _supports_long_paths():
         return path
 
-    prefix = '\\\\?\\'
+    prefix = "\\\\?\\"
     # Nothing to do
     if path.startswith(prefix):
         return path
@@ -306,44 +302,40 @@ 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
@@ -363,7 +355,7 @@ 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)
@@ -372,45 +364,45 @@ 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)
+        "Unhandled exception in _interpret_oserror: {}".format(exc)
     )
 
 
-def run_cmd(
-    cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None
-) -> Tuple[bytes, bytes]:
+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)
@@ -427,11 +419,8 @@ 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:
@@ -442,8 +431,7 @@ def run_cmd(
 
     if proc.returncode != 0:
         fire_event(SystemReportReturnCode(returncode=proc.returncode))
-        raise dbt.exceptions.CommandResultError(cwd, cmd, proc.returncode,
-                                                out, err)
+        raise dbt.exceptions.CommandResultError(cwd, cmd, proc.returncode, out, err)
 
     return out, err
 
@@ -455,13 +443,11 @@ def download_with_retries(
     connection_exception_retry(download_fn, 5)
 
 
-def download(
-    url: str, path: str, timeout: Optional[Union[float, tuple]] = None
-) -> None:
+def download(url: str, path: str, timeout: Optional[Union[float, tuple]] = None) -> None:
     path = convert_path(path)
-    connection_timeout = timeout or float(os.getenv('DBT_HTTP_TIMEOUT', 10))
+    connection_timeout = timeout or float(os.getenv("DBT_HTTP_TIMEOUT", 10))
     response = requests.get(url, timeout=connection_timeout)
-    with open(path, 'wb') as handle:
+    with open(path, "wb") as handle:
         for block in response.iter_content(1024 * 64):
             handle.write(block)
 
@@ -480,12 +466,10 @@ 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:
@@ -501,7 +485,7 @@ 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.
@@ -517,12 +501,12 @@ 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):
@@ -530,7 +514,7 @@ 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))
 
@@ -539,11 +523,10 @@ 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)
@@ -553,7 +536,7 @@ 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):
@@ -50,9 +42,9 @@ 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]]:
@@ -63,7 +55,7 @@ def load_yaml_text(contents):
     try:
         return safe_load(contents)
     except (yaml.scanner.ScannerError, yaml.YAMLError) as e:
-        if hasattr(e, 'problem_mark'):
+        if hasattr(e, "problem_mark"):
             error = contextualized_yaml_error(contents, e)
         else:
             error = str(e)

core/dbt/compilation.py

@@ -3,6 +3,7 @@ from collections import defaultdict
 from typing import List, Dict, Any, Tuple, cast, Optional
 
 import networkx as nx  # type: ignore
+import pickle
 import sqlparse
 
 from dbt import flags
@@ -32,29 +33,29 @@ from dbt.node_types import NodeType
 from dbt.events.format import pluralize
 import dbt.tracking
 
-graph_file_name = 'graph.gpickle'
+graph_file_name = "graph.gpickle"
 
 
 def _compiled_type_for(model: ParsedNode):
     if type(model) not in COMPILED_TYPES:
         raise InternalException(
-            f'Asked to compile {type(model)} node, but it has no compiled form'
+            f"Asked to compile {type(model)} node, but it has no compiled form"
         )
     return COMPILED_TYPES[type(model)]
 
 
 def print_compile_stats(stats):
     names = {
-        NodeType.Model: 'model',
-        NodeType.Test: 'test',
-        NodeType.Snapshot: 'snapshot',
-        NodeType.Analysis: 'analysis',
-        NodeType.Macro: 'macro',
-        NodeType.Operation: 'operation',
-        NodeType.Seed: 'seed file',
-        NodeType.Source: 'source',
-        NodeType.Exposure: 'exposure',
-        NodeType.Metric: 'metric'
+        NodeType.Model: "model",
+        NodeType.Test: "test",
+        NodeType.Snapshot: "snapshot",
+        NodeType.Analysis: "analysis",
+        NodeType.Macro: "macro",
+        NodeType.Operation: "operation",
+        NodeType.Seed: "seed file",
+        NodeType.Source: "source",
+        NodeType.Exposure: "exposure",
+        NodeType.Metric: "metric",
     }
 
     results = {k: 0 for k in names.keys()}
@@ -65,10 +66,7 @@ def print_compile_stats(stats):
         resource_counts = {k.pluralize(): v for k, v in results.items()}
         dbt.tracking.track_resource_counts(resource_counts)
 
-    stat_line = ", ".join([
-        pluralize(ct, names.get(t)) for t, ct in results.items()
-        if t in names
-    ])
+    stat_line = ", ".join([pluralize(ct, names.get(t)) for t, ct in results.items() if t in names])
 
     fire_event(FoundStats(stat_line=stat_line))
 
@@ -112,13 +110,13 @@ def _extend_prepended_ctes(prepended_ctes, new_prepended_ctes):
 
 
 def _get_tests_for_node(manifest: Manifest, unique_id: UniqueID) -> List[UniqueID]:
-    """ Get a list of tests that depend on the node with the
-    provided unique id """
+    """Get a list of tests that depend on the node with the
+    provided unique id"""
 
     tests = []
     if unique_id in manifest.child_map:
         for child_unique_id in manifest.child_map[unique_id]:
-            if child_unique_id.startswith('test.'):
+            if child_unique_id.startswith("test."):
                 tests.append(child_unique_id)
 
     return tests
@@ -162,7 +160,8 @@ class Linker:
         for node_id in self.graph:
             data = manifest.expect(node_id).to_dict(omit_none=True)
             out_graph.add_node(node_id, **data)
-        nx.write_gpickle(out_graph, outfile)
+        with open(outfile, "wb") as outfh:
+            pickle.dump(out_graph, outfh, protocol=pickle.HIGHEST_PROTOCOL)
 
 
 class Compiler:
@@ -182,9 +181,7 @@ class Compiler:
         extra_context: Dict[str, Any],
     ) -> Dict[str, Any]:
 
-        context = generate_runtime_model_context(
-            node, self.config, manifest
-        )
+        context = generate_runtime_model_context(node, self.config, manifest)
         context.update(extra_context)
         if isinstance(node, CompiledGenericTestNode):
             # for test nodes, add a special keyword args value to the context
@@ -242,26 +239,21 @@ class Compiler:
 
         with_stmt = None
         for token in parsed.tokens:
-            if token.is_keyword and token.normalized == 'WITH':
+            if token.is_keyword and token.normalized == "WITH":
                 with_stmt = token
                 break
 
         if with_stmt is None:
             # no with stmt, add one, and inject CTEs right at the beginning
             first_token = parsed.token_first()
-            with_stmt = sqlparse.sql.Token(sqlparse.tokens.Keyword, 'with')
+            with_stmt = sqlparse.sql.Token(sqlparse.tokens.Keyword, "with")
             parsed.insert_before(first_token, with_stmt)
         else:
             # stmt exists, add a comma (which will come after injected CTEs)
-            trailing_comma = sqlparse.sql.Token(
-                sqlparse.tokens.Punctuation, ','
-            )
+            trailing_comma = sqlparse.sql.Token(sqlparse.tokens.Punctuation, ",")
             parsed.insert_after(with_stmt, trailing_comma)
 
-        token = sqlparse.sql.Token(
-            sqlparse.tokens.Keyword,
-            ", ".join(c.sql for c in ctes)
-        )
+        token = sqlparse.sql.Token(sqlparse.tokens.Keyword, ", ".join(c.sql for c in ctes))
         parsed.insert_after(with_stmt, token)
 
         return str(parsed)
@@ -280,9 +272,7 @@ class Compiler:
         inserting CTEs into the SQL.
         """
         if model.compiled_sql is None:
-            raise RuntimeException(
-                'Cannot inject ctes into an unparsed node', model
-            )
+            raise RuntimeException("Cannot inject ctes into an unparsed node", model)
         if model.extra_ctes_injected:
             return (model, model.extra_ctes)
 
@@ -303,17 +293,17 @@ class Compiler:
         for cte in model.extra_ctes:
             if cte.id not in manifest.nodes:
                 raise InternalException(
-                    f'During compilation, found a cte reference that '
-                    f'could not be resolved: {cte.id}'
+                    f"During compilation, found a cte reference that "
+                    f"could not be resolved: {cte.id}"
                 )
             cte_model = manifest.nodes[cte.id]
 
             if not cte_model.is_ephemeral_model:
-                raise InternalException(f'{cte.id} is not ephemeral')
+                raise InternalException(f"{cte.id} is not ephemeral")
 
             # This model has already been compiled, so it's been
             # through here before
-            if getattr(cte_model, 'compiled', False):
+            if getattr(cte_model, "compiled", False):
                 assert isinstance(cte_model, tuple(COMPILED_TYPES.values()))
                 cte_model = cast(NonSourceCompiledNode, cte_model)
                 new_prepended_ctes = cte_model.extra_ctes
@@ -322,13 +312,11 @@ class Compiler:
             else:
                 # This is an ephemeral parsed model that we can compile.
                 # Compile and update the node
-                cte_model = self._compile_node(
-                    cte_model, manifest, extra_context)
+                cte_model = self._compile_node(cte_model, manifest, extra_context)
                 # recursively call this method
-                cte_model, new_prepended_ctes = \
-                    self._recursively_prepend_ctes(
-                        cte_model, manifest, extra_context
-                    )
+                cte_model, new_prepended_ctes = self._recursively_prepend_ctes(
+                    cte_model, manifest, extra_context
+                )
                 # Save compiled SQL file and sync manifest
                 self._write_node(cte_model)
                 manifest.sync_update_node(cte_model)
@@ -336,10 +324,8 @@ class Compiler:
             _extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
 
             new_cte_name = self.add_ephemeral_prefix(cte_model.name)
-            rendered_sql = (
-                cte_model._pre_injected_sql or cte_model.compiled_sql
-            )
-            sql = f' {new_cte_name} as (\n{rendered_sql}\n)'
+            rendered_sql = cte_model._pre_injected_sql or cte_model.compiled_sql
+            sql = f" {new_cte_name} as (\n{rendered_sql}\n)"
 
             _add_prepended_cte(prepended_ctes, InjectedCTE(id=cte.id, sql=sql))
 
@@ -373,17 +359,17 @@ class Compiler:
         fire_event(CompilingNode(unique_id=node.unique_id))
 
         data = node.to_dict(omit_none=True)
-        data.update({
-            'compiled': False,
-            'compiled_sql': None,
-            'extra_ctes_injected': False,
-            'extra_ctes': [],
-        })
+        data.update(
+            {
+                "compiled": False,
+                "compiled_sql": None,
+                "extra_ctes_injected": False,
+                "extra_ctes": [],
+            }
+        )
         compiled_node = _compiled_type_for(node).from_dict(data)
 
-        context = self._create_node_context(
-            compiled_node, manifest, extra_context
-        )
+        context = self._create_node_context(compiled_node, manifest, extra_context)
 
         compiled_node.compiled_sql = jinja.get_rendered(
             node.raw_sql,
@@ -403,22 +389,14 @@ class Compiler:
         if flags.WRITE_JSON:
             linker.write_graph(graph_path, manifest)
 
-    def link_node(
-        self, linker: Linker, node: GraphMemberNode, manifest: Manifest
-    ):
+    def link_node(self, linker: Linker, node: GraphMemberNode, manifest: Manifest):
         linker.add_node(node.unique_id)
 
         for dependency in node.depends_on_nodes:
             if dependency in manifest.nodes:
-                linker.dependency(
-                    node.unique_id,
-                    (manifest.nodes[dependency].unique_id)
-                )
+                linker.dependency(node.unique_id, (manifest.nodes[dependency].unique_id))
             elif dependency in manifest.sources:
-                linker.dependency(
-                    node.unique_id,
-                    (manifest.sources[dependency].unique_id)
-                )
+                linker.dependency(node.unique_id, (manifest.sources[dependency].unique_id))
             else:
                 dependency_not_found(node, dependency)
 
@@ -442,10 +420,10 @@ class Compiler:
             self.add_test_edges(linker, manifest)
 
     def add_test_edges(self, linker: Linker, manifest: Manifest) -> None:
-        """ This method adds additional edges to the DAG. For a given non-test
+        """This method adds additional edges to the DAG. For a given non-test
         executable node, add an edge from an upstream test to the given node if
         the set of nodes the test depends on is a subset of the upstream nodes
-        for the given node. """
+        for the given node."""
 
         # Given a graph:
         # model1 --> model2 --> model3
@@ -465,25 +443,18 @@ class Compiler:
             # If node is executable (in manifest.nodes) and does _not_
             # represent a test, continue.
             if (
-                node_id in manifest.nodes and
-                manifest.nodes[node_id].resource_type != NodeType.Test
+                node_id in manifest.nodes
+                and manifest.nodes[node_id].resource_type != NodeType.Test
             ):
                 # Get *everything* upstream of the node
-                all_upstream_nodes = nx.traversal.bfs_tree(
-                    linker.graph, node_id, reverse=True
-                )
+                all_upstream_nodes = nx.traversal.bfs_tree(linker.graph, node_id, reverse=True)
                 # Get the set of upstream nodes not including the current node.
-                upstream_nodes = set([
-                    n for n in all_upstream_nodes if n != node_id
-                ])
+                upstream_nodes = set([n for n in all_upstream_nodes if n != node_id])
 
                 # Get all tests that depend on any upstream nodes.
                 upstream_tests = []
                 for upstream_node in upstream_nodes:
-                    upstream_tests += _get_tests_for_node(
-                        manifest,
-                        upstream_node
-                    )
+                    upstream_tests += _get_tests_for_node(manifest, upstream_node)
 
                 for upstream_test in upstream_tests:
                     # Get the set of all nodes that the test depends on
@@ -492,18 +463,13 @@ class Compiler:
                     # relationship tests). Test nodes do not distinguish
                     # between what node the test is "testing" and what
                     # node(s) it depends on.
-                    test_depends_on = set(
-                        manifest.nodes[upstream_test].depends_on_nodes
-                    )
+                    test_depends_on = set(manifest.nodes[upstream_test].depends_on_nodes)
 
                     # If the set of nodes that an upstream test depends on
                     # is a subset of all upstream nodes of the current node,
                     # add an edge from the upstream test to the current node.
-                    if (test_depends_on.issubset(upstream_nodes)):
-                        linker.graph.add_edge(
-                            upstream_test,
-                            node_id
-                        )
+                    if test_depends_on.issubset(upstream_nodes):
+                        linker.graph.add_edge(upstream_test, node_id)
 
     def compile(self, manifest: Manifest, write=True, add_test_edges=False) -> Graph:
         self.initialize()
@@ -521,16 +487,13 @@ class Compiler:
 
     # writes the "compiled_sql" into the target/compiled directory
     def _write_node(self, node: NonSourceCompiledNode) -> ManifestNode:
-        if (not node.extra_ctes_injected or
-                node.resource_type == NodeType.Snapshot):
+        if not node.extra_ctes_injected or node.resource_type == NodeType.Snapshot:
             return node
         fire_event(WritingInjectedSQLForNode(unique_id=node.unique_id))
 
         if node.compiled_sql:
             node.compiled_path = node.write_node(
-                self.config.target_path,
-                'compiled',
-                node.compiled_sql
+                self.config.target_path, "compiled", node.compiled_sql
             )
         return node
 
@@ -549,9 +512,7 @@ class Compiler:
         """
         node = self._compile_node(node, manifest, extra_context)
 
-        node, _ = self._recursively_prepend_ctes(
-            node, manifest, extra_context
-        )
+        node, _ = self._recursively_prepend_ctes(node, manifest, extra_context)
         if write:
             self._write_node(node)
         return node

core/dbt/config/README.md

@@ -0,0 +1 @@
+# Config README

core/dbt/config/profile.py

@@ -23,7 +23,7 @@ from .renderer import ProfileRenderer
 
 DEFAULT_THREADS = 1
 
-DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser('~'), '.dbt')
+DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser("~"), ".dbt")
 
 INVALID_PROFILE_MESSAGE = """
 dbt encountered an error while trying to read your profiles.yml file.
@@ -43,11 +43,13 @@ Here, [profile name] should be replaced with a profile name
 defined in your profiles.yml file. You can find profiles.yml here:
 
 {profiles_file}/profiles.yml
-""".format(profiles_file=DEFAULT_PROFILES_DIR)
+""".format(
+    profiles_file=DEFAULT_PROFILES_DIR
+)
 
 
 def read_profile(profiles_dir: str) -> Dict[str, Any]:
-    path = os.path.join(profiles_dir, 'profiles.yml')
+    path = os.path.join(profiles_dir, "profiles.yml")
 
     contents = None
     if os.path.isfile(path):
@@ -55,12 +57,8 @@ def read_profile(profiles_dir: str) -> Dict[str, Any]:
             contents = load_file_contents(path, strip=False)
             yaml_content = load_yaml_text(contents)
             if not yaml_content:
-                msg = f'The profiles.yml file at {path} is empty'
-                raise DbtProfileError(
-                    INVALID_PROFILE_MESSAGE.format(
-                        error_string=msg
-                    )
-                )
+                msg = f"The profiles.yml file at {path} is empty"
+                raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
             return yaml_content
         except ValidationException as e:
             msg = INVALID_PROFILE_MESSAGE.format(error_string=e)
@@ -73,7 +71,7 @@ def read_user_config(directory: str) -> UserConfig:
     try:
         profile = read_profile(directory)
         if profile:
-            user_config = coerce_dict_str(profile.get('config', {}))
+            user_config = coerce_dict_str(profile.get("config", {}))
             if user_config is not None:
                 UserConfig.validate(user_config)
                 return UserConfig.from_dict(user_config)
@@ -100,7 +98,7 @@ class Profile(HasCredentials):
         target_name: str,
         user_config: UserConfig,
         threads: int,
-        credentials: Credentials
+        credentials: Credentials,
     ):
         """Explicitly defining `__init__` to work around bug in Python 3.9.7
         https://bugs.python.org/issue45081
@@ -112,9 +110,7 @@ class Profile(HasCredentials):
         self.credentials = credentials
         self.profile_env_vars = {}  # never available on init
 
-    def to_profile_info(
-        self, serialize_credentials: bool = False
-    ) -> Dict[str, Any]:
+    def to_profile_info(self, serialize_credentials: bool = False) -> Dict[str, Any]:
         """Unlike to_project_config, this dict is not a mirror of any existing
         on-disk data structure. It's used when creating a new profile from an
         existing one.
@@ -124,34 +120,33 @@ class Profile(HasCredentials):
         :returns dict: The serialized profile.
         """
         result = {
-            'profile_name': self.profile_name,
-            'target_name': self.target_name,
-            'user_config': self.user_config,
-            'threads': self.threads,
-            'credentials': self.credentials,
+            "profile_name": self.profile_name,
+            "target_name": self.target_name,
+            "user_config": self.user_config,
+            "threads": self.threads,
+            "credentials": self.credentials,
         }
         if serialize_credentials:
-            result['user_config'] = self.user_config.to_dict(omit_none=True)
-            result['credentials'] = self.credentials.to_dict(omit_none=True)
+            result["user_config"] = self.user_config.to_dict(omit_none=True)
+            result["credentials"] = self.credentials.to_dict(omit_none=True)
         return result
 
     def to_target_dict(self) -> Dict[str, Any]:
-        target = dict(
-            self.credentials.connection_info(with_aliases=True)
+        target = dict(self.credentials.connection_info(with_aliases=True))
+        target.update(
+            {
+                "type": self.credentials.type,
+                "threads": self.threads,
+                "name": self.target_name,
+                "target_name": self.target_name,
+                "profile_name": self.profile_name,
+                "config": self.user_config.to_dict(omit_none=True),
+            }
         )
-        target.update({
-            'type': self.credentials.type,
-            'threads': self.threads,
-            'name': self.target_name,
-            'target_name': self.target_name,
-            'profile_name': self.profile_name,
-            'config': self.user_config.to_dict(omit_none=True),
-        })
         return target
 
     def __eq__(self, other: object) -> bool:
-        if not (isinstance(other, self.__class__) and
-                isinstance(self, other.__class__)):
+        if not (isinstance(other, self.__class__) and isinstance(self, other.__class__)):
             return NotImplemented
         return self.to_profile_info() == other.to_profile_info()
 
@@ -171,14 +166,17 @@ class Profile(HasCredentials):
     ) -> Credentials:
         # avoid an import cycle
         from dbt.adapters.factory import load_plugin
+
         # credentials carry their 'type' in their actual type, not their
         # attributes. We do want this in order to pick our Credentials class.
-        if 'type' not in profile:
+        if "type" not in profile:
             raise DbtProfileError(
-                'required field "type" not found in profile {} and target {}'
-                .format(profile_name, target_name))
+                'required field "type" not found in profile {} and target {}'.format(
+                    profile_name, target_name
+                )
+            )
 
-        typename = profile.pop('type')
+        typename = profile.pop("type")
         try:
             cls = load_plugin(typename)
             data = cls.translate_aliases(profile)
@@ -187,8 +185,9 @@ class Profile(HasCredentials):
         except (RuntimeException, ValidationError) as e:
             msg = str(e) if isinstance(e, RuntimeException) else e.message
             raise DbtProfileError(
-                'Credentials in profile "{}", target "{}" invalid: {}'
-                .format(profile_name, target_name, msg)
+                'Credentials in profile "{}", target "{}" invalid: {}'.format(
+                    profile_name, target_name, msg
+                )
             ) from e
 
         return credentials
@@ -209,19 +208,19 @@ class Profile(HasCredentials):
     def _get_profile_data(
         profile: Dict[str, Any], profile_name: str, target_name: str
     ) -> Dict[str, Any]:
-        if 'outputs' not in profile:
-            raise DbtProfileError(
-                "outputs not specified in profile '{}'".format(profile_name)
-            )
-        outputs = profile['outputs']
+        if "outputs" not in profile:
+            raise DbtProfileError("outputs not specified in profile '{}'".format(profile_name))
+        outputs = profile["outputs"]
 
         if target_name not in outputs:
-            outputs = '\n'.join(' - {}'.format(output)
-                                for output in outputs)
-            msg = ("The profile '{}' does not have a target named '{}'. The "
-                   "valid target names for this profile are:\n{}"
-                   .format(profile_name, target_name, outputs))
-            raise DbtProfileError(msg, result_type='invalid_target')
+            outputs = "\n".join(" - {}".format(output) for output in outputs)
+            msg = (
+                "The profile '{}' does not have a target named '{}'. The "
+                "valid target names for this profile are:\n{}".format(
+                    profile_name, target_name, outputs
+                )
+            )
+            raise DbtProfileError(msg, result_type="invalid_target")
         profile_data = outputs[target_name]
 
         if not isinstance(profile_data, dict):
@@ -229,7 +228,7 @@ class Profile(HasCredentials):
                 f"output '{target_name}' of profile '{profile_name}' is "
                 f"misconfigured in profiles.yml"
             )
-            raise DbtProfileError(msg, result_type='invalid_target')
+            raise DbtProfileError(msg, result_type="invalid_target")
 
         return profile_data
 
@@ -240,8 +239,8 @@ class Profile(HasCredentials):
         threads: int,
         profile_name: str,
         target_name: str,
-        user_config: Optional[Dict[str, Any]] = None
-    ) -> 'Profile':
+        user_config: Optional[Dict[str, Any]] = None,
+    ) -> "Profile":
         """Create a profile from an existing set of Credentials and the
         remaining information.
 
@@ -264,7 +263,7 @@ class Profile(HasCredentials):
             target_name=target_name,
             user_config=user_config_obj,
             threads=threads,
-            credentials=credentials
+            credentials=credentials,
         )
         profile.validate()
         return profile
@@ -289,16 +288,14 @@ class Profile(HasCredentials):
         # name to extract a profile that we can render.
         if target_override is not None:
             target_name = target_override
-        elif 'target' in raw_profile:
+        elif "target" in raw_profile:
             # render the target if it was parsed from yaml
-            target_name = renderer.render_value(raw_profile['target'])
+            target_name = renderer.render_value(raw_profile["target"])
         else:
-            target_name = 'default'
+            target_name = "default"
             fire_event(MissingProfileTarget(profile_name=profile_name, target_name=target_name))
 
-        raw_profile_data = cls._get_profile_data(
-            raw_profile, profile_name, target_name
-        )
+        raw_profile_data = cls._get_profile_data(raw_profile, profile_name, target_name)
 
         try:
             profile_data = renderer.render_data(raw_profile_data)
@@ -315,7 +312,7 @@ class Profile(HasCredentials):
         user_config: Optional[Dict[str, Any]] = None,
         target_override: Optional[str] = None,
         threads_override: Optional[int] = None,
-    ) -> 'Profile':
+    ) -> "Profile":
         """Create a profile from its raw profile information.
 
          (this is an intermediate step, mostly useful for unit testing)
@@ -336,7 +333,7 @@ class Profile(HasCredentials):
         """
         # user_config is not rendered.
         if user_config is None:
-            user_config = raw_profile.get('config')
+            user_config = raw_profile.get("config")
         # TODO: should it be, and the values coerced to bool?
         target_name, profile_data = cls.render_profile(
             raw_profile, profile_name, target_override, renderer
@@ -344,7 +341,7 @@ class Profile(HasCredentials):
 
         # valid connections never include the number of threads, but it's
         # stored on a per-connection level in the raw configs
-        threads = profile_data.pop('threads', DEFAULT_THREADS)
+        threads = profile_data.pop("threads", DEFAULT_THREADS)
         if threads_override is not None:
             threads = threads_override
 
@@ -357,7 +354,7 @@ class Profile(HasCredentials):
             profile_name=profile_name,
             target_name=target_name,
             threads=threads,
-            user_config=user_config
+            user_config=user_config,
         )
 
     @classmethod
@@ -368,7 +365,7 @@ class Profile(HasCredentials):
         renderer: ProfileRenderer,
         target_override: Optional[str] = None,
         threads_override: Optional[int] = None,
-    ) -> 'Profile':
+    ) -> "Profile":
         """
         :param raw_profiles: The profile data, from disk as yaml.
         :param profile_name: The profile name to use.
@@ -384,23 +381,15 @@ class Profile(HasCredentials):
         :returns: The new Profile object.
         """
         if profile_name not in raw_profiles:
-            raise DbtProjectError(
-                "Could not find profile named '{}'".format(profile_name)
-            )
+            raise DbtProjectError("Could not find profile named '{}'".format(profile_name))
 
         # First, we've already got our final decision on profile name, and we
         # don't render keys, so we can pluck that out
         raw_profile = raw_profiles[profile_name]
         if not raw_profile:
-            msg = (
-                f'Profile {profile_name} in profiles.yml is empty'
-            )
-            raise DbtProfileError(
-                INVALID_PROFILE_MESSAGE.format(
-                    error_string=msg
-                )
-            )
-        user_config = raw_profiles.get('config')
+            msg = f"Profile {profile_name} in profiles.yml is empty"
+            raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
+        user_config = raw_profiles.get("config")
 
         return cls.from_raw_profile_info(
             raw_profile=raw_profile,
@@ -417,7 +406,7 @@ class Profile(HasCredentials):
         args: Any,
         renderer: ProfileRenderer,
         project_profile_name: Optional[str],
-    ) -> 'Profile':
+    ) -> "Profile":
         """Given the raw profiles as read from disk and the name of the desired
         profile if specified, return the profile component of the runtime
         config.
@@ -432,15 +421,14 @@ class Profile(HasCredentials):
             target could not be found.
         :returns Profile: The new Profile object.
         """
-        threads_override = getattr(args, 'threads', None)
-        target_override = getattr(args, 'target', None)
+        threads_override = getattr(args, "threads", None)
+        target_override = getattr(args, "target", None)
         raw_profiles = read_profile(flags.PROFILES_DIR)
-        profile_name = cls.pick_profile_name(getattr(args, 'profile', None),
-                                             project_profile_name)
+        profile_name = cls.pick_profile_name(getattr(args, "profile", None), project_profile_name)
         return cls.from_raw_profiles(
             raw_profiles=raw_profiles,
             profile_name=profile_name,
             renderer=renderer,
             target_override=target_override,
-            threads_override=threads_override
+            threads_override=threads_override,
         )

core/dbt/config/project.py

@@ -2,7 +2,13 @@ from copy import deepcopy
 from dataclasses import dataclass, field
 from itertools import chain
 from typing import (
-    List, Dict, Any, Optional, TypeVar, Union, Mapping,
+    List,
+    Dict,
+    Any,
+    Optional,
+    TypeVar,
+    Union,
+    Mapping,
 )
 from typing_extensions import Protocol, runtime_checkable
 
@@ -45,7 +51,7 @@ INVALID_VERSION_ERROR = """\
 This version of dbt is not supported with the '{package}' package.
   Installed version of dbt: {installed}
   Required version of dbt for '{package}': {version_spec}
-Check the requirements for the '{package}' package, or run dbt again with \
+Check for a different version of the '{package}' package, or run dbt again with \
 --no-version-check
 """
 
@@ -54,7 +60,7 @@ IMPOSSIBLE_VERSION_ERROR = """\
 The package version requirement can never be satisfied for the '{package}
 package.
   Required versions of dbt for '{package}': {version_spec}
-Check the requirements for the '{package}' package, or run dbt again with \
+Check for a different version of the '{package}' package, or run dbt again with \
 --no-version-check
 """
 
@@ -83,9 +89,7 @@ def _load_yaml(path):
 
 
 def package_data_from_root(project_root):
-    package_filepath = resolve_path_from_base(
-        'packages.yml', project_root
-    )
+    package_filepath = resolve_path_from_base("packages.yml", project_root)
 
     if path_exists(package_filepath):
         packages_dict = _load_yaml(package_filepath)
@@ -96,15 +100,13 @@ def package_data_from_root(project_root):
 
 def package_config_from_data(packages_data: Dict[str, Any]):
     if not packages_data:
-        packages_data = {'packages': []}
+        packages_data = {"packages": []}
 
     try:
         PackageConfig.validate(packages_data)
         packages = PackageConfig.from_dict(packages_data)
     except ValidationError as e:
-        raise DbtProjectError(
-            MALFORMED_PACKAGE_ERROR.format(error=str(e.message))
-        ) from e
+        raise DbtProjectError(MALFORMED_PACKAGE_ERROR.format(error=str(e.message))) from e
     return packages
 
 
@@ -119,7 +121,7 @@ def _parse_versions(versions: Union[List[str], str]) -> List[VersionSpecifier]:
     Regardless, this will return a list of VersionSpecifiers
     """
     if isinstance(versions, str):
-        versions = versions.split(',')
+        versions = versions.split(",")
     return [VersionSpecifier.from_version_string(v) for v in versions]
 
 
@@ -130,11 +132,14 @@ def _all_source_paths(
     analysis_paths: List[str],
     macro_paths: List[str],
 ) -> List[str]:
-    return list(chain(model_paths, seed_paths, snapshot_paths, analysis_paths,
-                      macro_paths))
+    # We need to turn a list of lists into just a list, then convert to a set to
+    # get only unique elements, then back to a list
+    return list(
+        set(list(chain(model_paths, seed_paths, snapshot_paths, analysis_paths, macro_paths)))
+    )
 
 
-T = TypeVar('T')
+T = TypeVar("T")
 
 
 def value_or(value: Optional[T], default: T) -> T:
@@ -147,30 +152,27 @@ def value_or(value: Optional[T], default: T) -> T:
 def _raw_project_from(project_root: str) -> Dict[str, Any]:
 
     project_root = os.path.normpath(project_root)
-    project_yaml_filepath = os.path.join(project_root, 'dbt_project.yml')
+    project_yaml_filepath = os.path.join(project_root, "dbt_project.yml")
 
     # get the project.yml contents
     if not path_exists(project_yaml_filepath):
         raise DbtProjectError(
-            'no dbt_project.yml found at expected path {}'
-            .format(project_yaml_filepath)
+            "no dbt_project.yml found at expected path {}".format(project_yaml_filepath)
         )
 
     project_dict = _load_yaml(project_yaml_filepath)
 
     if not isinstance(project_dict, dict):
-        raise DbtProjectError(
-            'dbt_project.yml does not parse to a dictionary'
-        )
+        raise DbtProjectError("dbt_project.yml does not parse to a dictionary")
 
     return project_dict
 
 
 def _query_comment_from_cfg(
-        cfg_query_comment: Union[QueryComment, NoValue, str, None]
+    cfg_query_comment: Union[QueryComment, NoValue, str, None]
 ) -> QueryComment:
     if not cfg_query_comment:
-        return QueryComment(comment='')
+        return QueryComment(comment="")
 
     if isinstance(cfg_query_comment, str):
         return QueryComment(comment=cfg_query_comment)
@@ -186,10 +188,7 @@ def validate_version(dbt_version: List[VersionSpecifier], project_name: str):
     installed = get_installed_version()
     if not versions_compatible(*dbt_version):
         msg = IMPOSSIBLE_VERSION_ERROR.format(
-            package=project_name,
-            version_spec=[
-                x.to_version_string() for x in dbt_version
-            ]
+            package=project_name, version_spec=[x.to_version_string() for x in dbt_version]
         )
         raise DbtProjectError(msg)
 
@@ -197,9 +196,7 @@ def validate_version(dbt_version: List[VersionSpecifier], project_name: str):
         msg = INVALID_VERSION_ERROR.format(
             package=project_name,
             installed=installed.to_version_string(),
-            version_spec=[
-                x.to_version_string() for x in dbt_version
-            ]
+            version_spec=[x.to_version_string() for x in dbt_version],
         )
         raise DbtProjectError(msg)
 
@@ -208,8 +205,8 @@ def _get_required_version(
     project_dict: Dict[str, Any],
     verify_version: bool,
 ) -> List[VersionSpecifier]:
-    dbt_raw_version: Union[List[str], str] = '>=0.0.0'
-    required = project_dict.get('require-dbt-version')
+    dbt_raw_version: Union[List[str], str] = ">=0.0.0"
+    required = project_dict.get("require-dbt-version")
     if required is not None:
         dbt_raw_version = required
 
@@ -220,46 +217,39 @@ def _get_required_version(
 
     if verify_version:
         # no name is also an error that we want to raise
-        if 'name' not in project_dict:
+        if "name" not in project_dict:
             raise DbtProjectError(
                 'Required "name" field not present in project',
             )
-        validate_version(dbt_version, project_dict['name'])
+        validate_version(dbt_version, project_dict["name"])
 
     return dbt_version
 
 
 @dataclass
 class RenderComponents:
-    project_dict: Dict[str, Any] = field(
-        metadata=dict(description='The project dictionary')
-    )
-    packages_dict: Dict[str, Any] = field(
-        metadata=dict(description='The packages dictionary')
-    )
-    selectors_dict: Dict[str, Any] = field(
-        metadata=dict(description='The selectors dictionary')
-    )
+    project_dict: Dict[str, Any] = field(metadata=dict(description="The project dictionary"))
+    packages_dict: Dict[str, Any] = field(metadata=dict(description="The packages dictionary"))
+    selectors_dict: Dict[str, Any] = field(metadata=dict(description="The selectors dictionary"))
 
 
 @dataclass
 class PartialProject(RenderComponents):
-    profile_name: Optional[str] = field(metadata=dict(
-        description='The unrendered profile name in the project, if set'
-    ))
-    project_name: Optional[str] = field(metadata=dict(
-        description=(
-            'The name of the project. This should always be set and will not '
-            'be rendered'
+    profile_name: Optional[str] = field(
+        metadata=dict(description="The unrendered profile name in the project, if set")
+    )
+    project_name: Optional[str] = field(
+        metadata=dict(
+            description=(
+                "The name of the project. This should always be set and will not " "be rendered"
+            )
         )
-    ))
+    )
     project_root: str = field(
-        metadata=dict(description='The root directory of the project'),
+        metadata=dict(description="The root directory of the project"),
     )
     verify_version: bool = field(
-        metadata=dict(description=(
-            'If True, verify the dbt version matches the required version'
-        ))
+        metadata=dict(description=("If True, verify the dbt version matches the required version"))
     )
 
     def render_profile_name(self, renderer) -> Optional[str]:
@@ -272,9 +262,7 @@ class PartialProject(RenderComponents):
         renderer: DbtProjectYamlRenderer,
     ) -> RenderComponents:
 
-        rendered_project = renderer.render_project(
-            self.project_dict, self.project_root
-        )
+        rendered_project = renderer.render_project(self.project_dict, self.project_root)
         rendered_packages = renderer.render_packages(self.packages_dict)
         rendered_selectors = renderer.render_selectors(self.selectors_dict)
 
@@ -285,31 +273,34 @@ class PartialProject(RenderComponents):
         )
 
     # Called by 'collect_parts' in RuntimeConfig
-    def render(self, renderer: DbtProjectYamlRenderer) -> 'Project':
+    def render(self, renderer: DbtProjectYamlRenderer) -> "Project":
         try:
             rendered = self.get_rendered(renderer)
             return self.create_project(rendered)
         except DbtProjectError as exc:
             if exc.path is None:
-                exc.path = os.path.join(self.project_root, 'dbt_project.yml')
+                exc.path = os.path.join(self.project_root, "dbt_project.yml")
             raise
 
     def check_config_path(self, project_dict, deprecated_path, exp_path):
         if deprecated_path in project_dict:
             if exp_path in project_dict:
                 msg = (
-                    '{deprecated_path} and {exp_path} cannot both be defined. The '
-                    '`{deprecated_path}` config has been deprecated in favor of `{exp_path}`. '
-                    'Please update your `dbt_project.yml` configuration to reflect this '
-                    'change.'
+                    "{deprecated_path} and {exp_path} cannot both be defined. The "
+                    "`{deprecated_path}` config has been deprecated in favor of `{exp_path}`. "
+                    "Please update your `dbt_project.yml` configuration to reflect this "
+                    "change."
                 )
-                raise DbtProjectError(msg.format(deprecated_path=deprecated_path,
-                                                 exp_path=exp_path))
-            deprecations.warn(f'project-config-{deprecated_path}',
-                              deprecated_path=deprecated_path,
-                              exp_path=exp_path)
+                raise DbtProjectError(
+                    msg.format(deprecated_path=deprecated_path, exp_path=exp_path)
+                )
+            deprecations.warn(
+                f"project-config-{deprecated_path}",
+                deprecated_path=deprecated_path,
+                exp_path=exp_path,
+            )
 
-    def create_project(self, rendered: RenderComponents) -> 'Project':
+    def create_project(self, rendered: RenderComponents) -> "Project":
         unrendered = RenderComponents(
             project_dict=self.project_dict,
             packages_dict=self.packages_dict,
@@ -320,14 +311,12 @@ class PartialProject(RenderComponents):
             verify_version=self.verify_version,
         )
 
-        self.check_config_path(rendered.project_dict, 'source-paths', 'model-paths')
-        self.check_config_path(rendered.project_dict, 'data-paths', 'seed-paths')
+        self.check_config_path(rendered.project_dict, "source-paths", "model-paths")
+        self.check_config_path(rendered.project_dict, "data-paths", "seed-paths")
 
         try:
             ProjectContract.validate(rendered.project_dict)
-            cfg = ProjectContract.from_dict(
-                rendered.project_dict
-            )
+            cfg = ProjectContract.from_dict(rendered.project_dict)
         except ValidationError as e:
             raise DbtProjectError(validator_error_message(e)) from e
         # name/version are required in the Project definition, so we can assume
@@ -337,7 +326,7 @@ class PartialProject(RenderComponents):
         # this is added at project_dict parse time and should always be here
         # once we see it.
         if cfg.project_root is None:
-            raise DbtProjectError('cfg must have a project root!')
+            raise DbtProjectError("cfg must have a project root!")
         else:
             project_root = cfg.project_root
         # this is only optional in the sense that if it's not present, it needs
@@ -347,30 +336,30 @@ class PartialProject(RenderComponents):
 
         # `source_paths` is deprecated but still allowed. Copy it into
         # `model_paths` to simlify logic throughout the rest of the system.
-        model_paths: List[str] = value_or(cfg.model_paths
-                                          if 'model-paths' in rendered.project_dict
-                                          else cfg.source_paths, ['models'])
-        macro_paths: List[str] = value_or(cfg.macro_paths, ['macros'])
+        model_paths: List[str] = value_or(
+            cfg.model_paths if "model-paths" in rendered.project_dict else cfg.source_paths,
+            ["models"],
+        )
+        macro_paths: List[str] = value_or(cfg.macro_paths, ["macros"])
         # `data_paths` is deprecated but still allowed. Copy it into
         # `seed_paths` to simlify logic throughout the rest of the system.
-        seed_paths: List[str] = value_or(cfg.seed_paths
-                                         if 'seed-paths' in rendered.project_dict
-                                         else cfg.data_paths, ['seeds'])
-        test_paths: List[str] = value_or(cfg.test_paths, ['tests'])
-        analysis_paths: List[str] = value_or(cfg.analysis_paths, ['analyses'])
-        snapshot_paths: List[str] = value_or(cfg.snapshot_paths, ['snapshots'])
+        seed_paths: List[str] = value_or(
+            cfg.seed_paths if "seed-paths" in rendered.project_dict else cfg.data_paths, ["seeds"]
+        )
+        test_paths: List[str] = value_or(cfg.test_paths, ["tests"])
+        analysis_paths: List[str] = value_or(cfg.analysis_paths, ["analyses"])
+        snapshot_paths: List[str] = value_or(cfg.snapshot_paths, ["snapshots"])
 
         all_source_paths: List[str] = _all_source_paths(
-            model_paths, seed_paths, snapshot_paths, analysis_paths,
-            macro_paths
+            model_paths, seed_paths, snapshot_paths, analysis_paths, macro_paths
         )
 
         docs_paths: List[str] = value_or(cfg.docs_paths, all_source_paths)
         asset_paths: List[str] = value_or(cfg.asset_paths, [])
-        target_path: str = value_or(cfg.target_path, 'target')
+        target_path: str = value_or(cfg.target_path, "target")
         clean_targets: List[str] = value_or(cfg.clean_targets, [target_path])
-        log_path: str = value_or(cfg.log_path, 'logs')
-        packages_install_path: str = value_or(cfg.packages_install_path, 'dbt_packages')
+        log_path: str = value_or(cfg.log_path, "logs")
+        packages_install_path: str = value_or(cfg.packages_install_path, "dbt_packages")
         # in the default case we'll populate this once we know the adapter type
         # It would be nice to just pass along a Quoting here, but that would
         # break many things
@@ -408,11 +397,12 @@ class PartialProject(RenderComponents):
         packages = package_config_from_data(rendered.packages_dict)
         selectors = selector_config_from_data(rendered.selectors_dict)
         manifest_selectors: Dict[str, Any] = {}
-        if rendered.selectors_dict and rendered.selectors_dict['selectors']:
+        if rendered.selectors_dict and rendered.selectors_dict["selectors"]:
             # this is a dict with a single key 'selectors' pointing to a list
             # of dicts.
             manifest_selectors = SelectorDict.parse_from_selectors_list(
-                rendered.selectors_dict['selectors'])
+                rendered.selectors_dict["selectors"]
+            )
         project = Project(
             project_name=name,
             version=version,
@@ -463,10 +453,9 @@ class PartialProject(RenderComponents):
         *,
         verify_version: bool = False,
     ):
-        """Construct a partial project from its constituent dicts.
-        """
-        project_name = project_dict.get('name')
-        profile_name = project_dict.get('profile')
+        """Construct a partial project from its constituent dicts."""
+        project_name = project_dict.get("name")
+        profile_name = project_dict.get("profile")
 
         return cls(
             profile_name=profile_name,
@@ -481,14 +470,14 @@ class PartialProject(RenderComponents):
     @classmethod
     def from_project_root(
         cls, project_root: str, *, verify_version: bool = False
-    ) -> 'PartialProject':
+    ) -> "PartialProject":
         project_root = os.path.normpath(project_root)
         project_dict = _raw_project_from(project_root)
-        config_version = project_dict.get('config-version', 1)
+        config_version = project_dict.get("config-version", 1)
         if config_version != 2:
             raise DbtProjectError(
-                f'Invalid config version: {config_version}, expected 2',
-                path=os.path.join(project_root, 'dbt_project.yml')
+                f"Invalid config version: {config_version}, expected 2",
+                path=os.path.join(project_root, "dbt_project.yml"),
             )
 
         packages_dict = package_data_from_root(project_root)
@@ -505,15 +494,10 @@ class PartialProject(RenderComponents):
 class VarProvider:
     """Var providers are tied to a particular Project."""
 
-    def __init__(
-        self,
-        vars: Dict[str, Dict[str, Any]]
-    ) -> None:
+    def __init__(self, vars: Dict[str, Dict[str, Any]]) -> None:
         self.vars = vars
 
-    def vars_for(
-        self, node: IsFQNResource, adapter_type: str
-    ) -> Mapping[str, Any]:
+    def vars_for(self, node: IsFQNResource, adapter_type: str) -> Mapping[str, Any]:
         # in v2, vars are only either project or globally scoped
         merged = MultiDict([self.vars])
         merged.add(self.vars.get(node.package_name, {}))
@@ -565,15 +549,18 @@ class Project:
     @property
     def all_source_paths(self) -> List[str]:
         return _all_source_paths(
-            self.model_paths, self.seed_paths, self.snapshot_paths,
-            self.analysis_paths, self.macro_paths
+            self.model_paths,
+            self.seed_paths,
+            self.snapshot_paths,
+            self.analysis_paths,
+            self.macro_paths,
         )
 
     @property
     def generic_test_paths(self):
         generic_test_paths = []
         for test_path in self.test_paths:
-            generic_test_paths.append(os.path.join(test_path, 'generic'))
+            generic_test_paths.append(os.path.join(test_path, "generic"))
         return generic_test_paths
 
     def __str__(self):
@@ -581,11 +568,11 @@ class Project:
         return str(cfg)
 
     def __eq__(self, other):
-        if not (isinstance(other, self.__class__) and
-                isinstance(self, other.__class__)):
+        if not (isinstance(other, self.__class__) and isinstance(self, other.__class__)):
             return False
-        return self.to_project_config(with_packages=True) == \
-            other.to_project_config(with_packages=True)
+        return self.to_project_config(with_packages=True) == other.to_project_config(
+            with_packages=True
+        )
 
     def to_project_config(self, with_packages=False):
         """Return a dict representation of the config that could be written to
@@ -595,40 +582,39 @@ class Project:
             file in the root.
         :returns dict: The serialized profile.
         """
-        result = deepcopy({
-            'name': self.project_name,
-            'version': self.version,
-            'project-root': self.project_root,
-            'profile': self.profile_name,
-            'model-paths': self.model_paths,
-            'macro-paths': self.macro_paths,
-            'seed-paths': self.seed_paths,
-            'test-paths': self.test_paths,
-            'analysis-paths': self.analysis_paths,
-            'docs-paths': self.docs_paths,
-            'asset-paths': self.asset_paths,
-            'target-path': self.target_path,
-            'snapshot-paths': self.snapshot_paths,
-            'clean-targets': self.clean_targets,
-            'log-path': self.log_path,
-            'quoting': self.quoting,
-            'models': self.models,
-            'on-run-start': self.on_run_start,
-            'on-run-end': self.on_run_end,
-            'dispatch': self.dispatch,
-            'seeds': self.seeds,
-            'snapshots': self.snapshots,
-            'sources': self.sources,
-            'tests': self.tests,
-            'vars': self.vars.to_dict(),
-            'require-dbt-version': [
-                v.to_version_string() for v in self.dbt_version
-            ],
-            'config-version': self.config_version,
-        })
+        result = deepcopy(
+            {
+                "name": self.project_name,
+                "version": self.version,
+                "project-root": self.project_root,
+                "profile": self.profile_name,
+                "model-paths": self.model_paths,
+                "macro-paths": self.macro_paths,
+                "seed-paths": self.seed_paths,
+                "test-paths": self.test_paths,
+                "analysis-paths": self.analysis_paths,
+                "docs-paths": self.docs_paths,
+                "asset-paths": self.asset_paths,
+                "target-path": self.target_path,
+                "snapshot-paths": self.snapshot_paths,
+                "clean-targets": self.clean_targets,
+                "log-path": self.log_path,
+                "quoting": self.quoting,
+                "models": self.models,
+                "on-run-start": self.on_run_start,
+                "on-run-end": self.on_run_end,
+                "dispatch": self.dispatch,
+                "seeds": self.seeds,
+                "snapshots": self.snapshots,
+                "sources": self.sources,
+                "tests": self.tests,
+                "vars": self.vars.to_dict(),
+                "require-dbt-version": [v.to_version_string() for v in self.dbt_version],
+                "config-version": self.config_version,
+            }
+        )
         if self.query_comment:
-            result['query-comment'] = \
-                self.query_comment.to_dict(omit_none=True)
+            result["query-comment"] = self.query_comment.to_dict(omit_none=True)
 
         if with_packages:
             result.update(self.packages.to_dict(omit_none=True))
@@ -642,9 +628,7 @@ class Project:
             raise DbtProjectError(validator_error_message(e)) from e
 
     @classmethod
-    def partial_load(
-        cls, project_root: str, *, verify_version: bool = False
-    ) -> PartialProject:
+    def partial_load(cls, project_root: str, *, verify_version: bool = False) -> PartialProject:
         return PartialProject.from_project_root(
             project_root,
             verify_version=verify_version,
@@ -657,18 +641,17 @@ class Project:
         renderer: DbtProjectYamlRenderer,
         *,
         verify_version: bool = False,
-    ) -> 'Project':
+    ) -> "Project":
         partial = cls.partial_load(project_root, verify_version=verify_version)
         return partial.render(renderer)
 
     def hashed_name(self):
-        return hashlib.md5(self.project_name.encode('utf-8')).hexdigest()
+        return hashlib.md5(self.project_name.encode("utf-8")).hexdigest()
 
     def get_selector(self, name: str) -> Union[SelectionSpec, bool]:
         if name not in self.selectors:
             raise RuntimeException(
-                f'Could not find selector named {name}, expected one of '
-                f'{list(self.selectors)}'
+                f"Could not find selector named {name}, expected one of " f"{list(self.selectors)}"
             )
         return self.selectors[name]["definition"]
 
@@ -685,6 +668,6 @@ class Project:
 
     def get_macro_search_order(self, macro_namespace: str):
         for dispatch_entry in self.dispatch:
-            if dispatch_entry['macro_namespace'] == macro_namespace:
-                return dispatch_entry['search_order']
+            if dispatch_entry["macro_namespace"] == macro_namespace:
+                return dispatch_entry["search_order"]
         return None

core/dbt/config/renderer.py

@@ -1,14 +1,15 @@
 from typing import Dict, Any, Tuple, Optional, Union, Callable
+import re
+import os
 
 from dbt.clients.jinja import get_rendered, catch_jinja
 from dbt.context.target import TargetContext
-from dbt.context.secret import SecretContext
+from dbt.context.secret import SecretContext, SECRET_PLACEHOLDER
 from dbt.context.base import BaseContext
 from dbt.contracts.connection import HasCredentials
-from dbt.exceptions import (
-    DbtProjectError, CompilationException, RecursionException
-)
+from dbt.exceptions import DbtProjectError, CompilationException, RecursionException
 from dbt.utils import deep_map_render
+from dbt.logger import SECRET_ENV_PREFIX
 
 
 Keypath = Tuple[Union[str, int], ...]
@@ -20,7 +21,7 @@ class BaseRenderer:
 
     @property
     def name(self):
-        return 'Rendering'
+        return "Rendering"
 
     def should_render_keypath(self, keypath: Keypath) -> bool:
         return True
@@ -31,9 +32,7 @@ class BaseRenderer:
 
         return self.render_value(value, keypath)
 
-    def render_value(
-        self, value: Any, keypath: Optional[Keypath] = None
-    ) -> Any:
+    def render_value(self, value: Any, keypath: Optional[Keypath] = None) -> Any:
         # keypath is ignored.
         # if it wasn't read as a string, ignore it
         if not isinstance(value, str):
@@ -42,18 +41,15 @@ class BaseRenderer:
             with catch_jinja():
                 return get_rendered(value, self.context, native=True)
         except CompilationException as exc:
-            msg = f'Could not render {value}: {exc.msg}'
+            msg = f"Could not render {value}: {exc.msg}"
             raise CompilationException(msg) from exc
 
-    def render_data(
-        self, data: Dict[str, Any]
-    ) -> Dict[str, Any]:
+    def render_data(self, data: Dict[str, Any]) -> Dict[str, Any]:
         try:
             return deep_map_render(self.render_entry, data)
         except RecursionException:
             raise DbtProjectError(
-                f'Cycle detected: {self.name} input has a reference to itself',
-                project=data
+                f"Cycle detected: {self.name} input has a reference to itself", project=data
             )
 
 
@@ -80,15 +76,15 @@ class ProjectPostprocessor(Dict[Keypath, Callable[[Any], Any]]):
     def __init__(self):
         super().__init__()
 
-        self[('on-run-start',)] = _list_if_none_or_string
-        self[('on-run-end',)] = _list_if_none_or_string
+        self[("on-run-start",)] = _list_if_none_or_string
+        self[("on-run-end",)] = _list_if_none_or_string
 
-        for k in ('models', 'seeds', 'snapshots'):
+        for k in ("models", "seeds", "snapshots"):
             self[(k,)] = _dict_if_none
-            self[(k, 'vars')] = _dict_if_none
-            self[(k, 'pre-hook')] = _list_if_none_or_string
-            self[(k, 'post-hook')] = _list_if_none_or_string
-        self[('seeds', 'column_types')] = _dict_if_none
+            self[(k, "vars")] = _dict_if_none
+            self[(k, "pre-hook")] = _list_if_none_or_string
+            self[(k, "post-hook")] = _list_if_none_or_string
+        self[("seeds", "column_types")] = _dict_if_none
 
     def postprocess(self, value: Any, key: Keypath) -> Any:
         if key in self:
@@ -102,8 +98,7 @@ class DbtProjectYamlRenderer(BaseRenderer):
     _KEYPATH_HANDLERS = ProjectPostprocessor()
 
     def __init__(
-        self, profile: Optional[HasCredentials] = None,
-        cli_vars: Optional[Dict[str, Any]] = None
+        self, profile: Optional[HasCredentials] = None, cli_vars: Optional[Dict[str, Any]] = None
     ) -> None:
         # Generate contexts here because we want to save the context
         # object in order to retrieve the env_vars. This is almost always
@@ -120,13 +115,11 @@ class DbtProjectYamlRenderer(BaseRenderer):
 
     @property
     def name(self):
-        'Project config'
+        "Project config"
 
+    # Uses SecretRenderer
     def get_package_renderer(self) -> BaseRenderer:
-        return PackageRenderer(self.context)
-
-    def get_selector_renderer(self) -> BaseRenderer:
-        return SelectorRenderer(self.context)
+        return PackageRenderer(self.ctx_obj.cli_vars)
 
     def render_project(
         self,
@@ -135,7 +128,7 @@ class DbtProjectYamlRenderer(BaseRenderer):
     ) -> Dict[str, Any]:
         """Render the project and insert the project root after rendering."""
         rendered_project = self.render_data(project)
-        rendered_project['project-root'] = project_root
+        rendered_project["project-root"] = project_root
         return rendered_project
 
     def render_packages(self, packages: Dict[str, Any]):
@@ -144,8 +137,7 @@ class DbtProjectYamlRenderer(BaseRenderer):
         return package_renderer.render_data(packages)
 
     def render_selectors(self, selectors: Dict[str, Any]):
-        selector_renderer = self.get_selector_renderer()
-        return selector_renderer.render_data(selectors)
+        return self.render_data(selectors)
 
     def render_entry(self, value: Any, keypath: Keypath) -> Any:
         result = super().render_entry(value, keypath)
@@ -157,55 +149,59 @@ class DbtProjectYamlRenderer(BaseRenderer):
 
         first = keypath[0]
         # run hooks are not rendered
-        if first in {'on-run-start', 'on-run-end', 'query-comment'}:
+        if first in {"on-run-start", "on-run-end", "query-comment"}:
             return False
 
         # don't render vars blocks until runtime
-        if first == 'vars':
+        if first == "vars":
             return False
 
-        if first in {'seeds', 'models', 'snapshots', 'tests'}:
-            keypath_parts = {
-                (k.lstrip('+ ') if isinstance(k, str) else k)
-                for k in keypath
-            }
+        if first in {"seeds", "models", "snapshots", "tests"}:
+            keypath_parts = {(k.lstrip("+ ") if isinstance(k, str) else k) for k in keypath}
             # model-level hooks
-            if 'pre-hook' in keypath_parts or 'post-hook' in keypath_parts:
+            if "pre-hook" in keypath_parts or "post-hook" in keypath_parts:
                 return False
 
         return True
 
 
-class SelectorRenderer(BaseRenderer):
-    @property
-    def name(self):
-        return 'Selector config'
-
-
 class SecretRenderer(BaseRenderer):
-    def __init__(
-        self, cli_vars: Optional[Dict[str, Any]] = None
-    ) -> None:
+    def __init__(self, cli_vars: Dict[str, Any] = {}) -> None:
         # Generate contexts here because we want to save the context
         # object in order to retrieve the env_vars.
-        if cli_vars is None:
-            cli_vars = {}
         self.ctx_obj = SecretContext(cli_vars)
         context = self.ctx_obj.to_dict()
         super().__init__(context)
 
     @property
     def name(self):
-        return 'Secret'
+        return "Secret"
+
+    def render_value(self, value: Any, keypath: Optional[Keypath] = None) -> Any:
+        rendered = super().render_value(value, keypath)
+        if SECRET_ENV_PREFIX in str(rendered):
+            search_group = f"({SECRET_ENV_PREFIX}(.*))"
+            pattern = SECRET_PLACEHOLDER.format(search_group).replace("$", r"\$")
+            m = re.search(
+                pattern,
+                rendered,
+            )
+            if m:
+                found = m.group(1)
+                value = os.environ[found]
+                replace_this = SECRET_PLACEHOLDER.format(found)
+                return rendered.replace(replace_this, value)
+        else:
+            return rendered
 
 
 class ProfileRenderer(SecretRenderer):
     @property
     def name(self):
-        return 'Profile'
+        return "Profile"
 
 
 class PackageRenderer(SecretRenderer):
     @property
     def name(self):
-        return 'Packages config'
+        return "Packages config"

core/dbt/config/runtime.py

@@ -1,44 +1,36 @@
 import itertools
 import os
 from copy import deepcopy
-from dataclasses import dataclass, fields
+from dataclasses import dataclass
 from pathlib import Path
-from typing import (
-    Dict, Any, Optional, Mapping, Iterator, Iterable, Tuple, List, MutableSet,
-    Type
-)
+from typing import Dict, Any, Optional, Mapping, Iterator, Iterable, Tuple, List, MutableSet, Type
 
 from .profile import Profile
 from .project import Project
 from .renderer import DbtProjectYamlRenderer, ProfileRenderer
 from .utils import parse_cli_vars
 from dbt import flags
-from dbt import tracking
 from dbt.adapters.factory import get_relation_class_by_name, get_include_paths
-from dbt.helper_types import FQNPath, PathSet
+from dbt.helper_types import FQNPath, PathSet, DictDefaultEmptyStr
+from dbt.config.profile import read_user_config
 from dbt.contracts.connection import AdapterRequiredConfig, Credentials
 from dbt.contracts.graph.manifest import ManifestMetadata
 from dbt.contracts.relation import ComponentName
-from dbt.events.types import ProfileLoadError, ProfileNotFound
-from dbt.events.functions import fire_event
 from dbt.ui import warning_tag
 
 from dbt.contracts.project import Configuration, UserConfig
 from dbt.exceptions import (
     RuntimeException,
-    DbtProfileError,
     DbtProjectError,
     validator_error_message,
     warn_or_error,
-    raise_compiler_error
+    raise_compiler_error,
 )
 
 from dbt.dataclass_schema import ValidationError
 
 
-def _project_quoting_dict(
-    proj: Project, profile: Profile
-) -> Dict[ComponentName, bool]:
+def _project_quoting_dict(proj: Project, profile: Profile) -> Dict[ComponentName, bool]:
     src: Dict[str, Any] = profile.credentials.translate_aliases(proj.quoting)
     result: Dict[ComponentName, bool] = {}
     for key in ComponentName:
@@ -54,7 +46,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
     args: Any
     profile_name: str
     cli_vars: Dict[str, Any]
-    dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None
+    dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None
 
     def __post_init__(self):
         self.validate()
@@ -66,8 +58,8 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         project: Project,
         profile: Profile,
         args: Any,
-        dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None,
-    ) -> 'RuntimeConfig':
+        dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None,
+    ) -> "RuntimeConfig":
         """Instantiate a RuntimeConfig from its components.
 
         :param profile: A parsed dbt Profile.
@@ -81,7 +73,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             .replace_dict(_project_quoting_dict(project, profile))
         ).to_dict(omit_none=True)
 
-        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
 
         return cls(
             project_name=project.project_name,
@@ -129,7 +121,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         )
 
     # Called by 'load_projects' in this class
-    def new_project(self, project_root: str) -> 'RuntimeConfig':
+    def new_project(self, project_root: str) -> "RuntimeConfig":
         """Given a new project root, read in its project dictionary, supply the
         existing project's profile info, and create a new project file.
 
@@ -171,7 +163,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         """
         result = self.to_project_config(with_packages=True)
         result.update(self.to_profile_info(serialize_credentials=True))
-        result['cli_vars'] = deepcopy(self.cli_vars)
+        result["cli_vars"] = deepcopy(self.cli_vars)
         return result
 
     def validate(self):
@@ -191,31 +183,23 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         profile_renderer: ProfileRenderer,
         profile_name: Optional[str],
     ) -> Profile:
-        return Profile.render_from_args(
-            args, profile_renderer, profile_name
-        )
+
+        return Profile.render_from_args(args, profile_renderer, profile_name)
 
     @classmethod
-    def collect_parts(
-        cls: Type['RuntimeConfig'], args: Any
-    ) -> Tuple[Project, Profile]:
+    def collect_parts(cls: Type["RuntimeConfig"], args: Any) -> Tuple[Project, Profile]:
         # profile_name from the project
         project_root = args.project_dir if args.project_dir else os.getcwd()
         version_check = bool(flags.VERSION_CHECK)
-        partial = Project.partial_load(
-            project_root,
-            verify_version=version_check
-        )
+        partial = Project.partial_load(project_root, verify_version=version_check)
 
         # build the profile using the base renderer and the one fact we know
         # Note: only the named profile section is rendered. The rest of the
         # profile is ignored.
-        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
         profile_renderer = ProfileRenderer(cli_vars)
         profile_name = partial.render_profile_name(profile_renderer)
-        profile = cls._get_rendered_profile(
-            args, profile_renderer, profile_name
-        )
+        profile = cls._get_rendered_profile(args, profile_renderer, profile_name)
         # Save env_vars encountered in rendering for partial parsing
         profile.profile_env_vars = profile_renderer.ctx_obj.env_vars
 
@@ -229,7 +213,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
     # Called in main.py, lib.py, task/base.py
     @classmethod
-    def from_args(cls, args: Any) -> 'RuntimeConfig':
+    def from_args(cls, args: Any) -> "RuntimeConfig":
         """Given arguments, read in dbt_project.yml from the current directory,
         read in packages.yml if it exists, and use them to find the profile to
         load.
@@ -248,10 +232,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         )
 
     def get_metadata(self) -> ManifestMetadata:
-        return ManifestMetadata(
-            project_id=self.hashed_name(),
-            adapter_type=self.credentials.type
-        )
+        return ManifestMetadata(project_id=self.hashed_name(), adapter_type=self.credentials.type)
 
     def _get_v2_config_paths(
         self,
@@ -260,7 +241,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         paths: MutableSet[FQNPath],
     ) -> PathSet:
         for key, value in config.items():
-            if isinstance(value, dict) and not key.startswith('+'):
+            if isinstance(value, dict) and not key.startswith("+"):
                 self._get_config_paths(value, path + (key,), paths)
             else:
                 paths.add(path)
@@ -276,7 +257,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             paths = set()
 
         for key, value in config.items():
-            if isinstance(value, dict) and not key.startswith('+'):
+            if isinstance(value, dict) and not key.startswith("+"):
                 self._get_v2_config_paths(value, path + (key,), paths)
             else:
                 paths.add(path)
@@ -288,11 +269,11 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         a configured path in the resource.
         """
         return {
-            'models': self._get_config_paths(self.models),
-            'seeds': self._get_config_paths(self.seeds),
-            'snapshots': self._get_config_paths(self.snapshots),
-            'sources': self._get_config_paths(self.sources),
-            'tests': self._get_config_paths(self.tests),
+            "models": self._get_config_paths(self.models),
+            "seeds": self._get_config_paths(self.seeds),
+            "snapshots": self._get_config_paths(self.snapshots),
+            "sources": self._get_config_paths(self.sources),
+            "tests": self._get_config_paths(self.tests),
         }
 
     def get_unused_resource_config_paths(
@@ -313,9 +294,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
             for config_path in config_paths:
                 if not _is_config_used(config_path, fqns):
-                    unused_resource_config_paths.append(
-                        (resource_type,) + config_path
-                    )
+                    unused_resource_config_paths.append((resource_type,) + config_path)
         return unused_resource_config_paths
 
     def warn_for_unused_resource_config_paths(
@@ -328,38 +307,38 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             return
 
         msg = UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE.format(
-            len(unused),
-            '\n'.join('- {}'.format('.'.join(u)) for u in unused)
+            len(unused), "\n".join("- {}".format(".".join(u)) for u in unused)
         )
 
-        warn_or_error(msg, log_fmt=warning_tag('{}'))
+        warn_or_error(msg, log_fmt=warning_tag("{}"))
 
-    def load_dependencies(self) -> Mapping[str, 'RuntimeConfig']:
+    def load_dependencies(self, base_only=False) -> Mapping[str, "RuntimeConfig"]:
         if self.dependencies is None:
             all_projects = {self.project_name: self}
             internal_packages = get_include_paths(self.credentials.type)
-            # raise exception if fewer installed packages than in packages.yml
-            count_packages_specified = len(self.packages.packages)  # type: ignore
-            count_packages_installed = len(tuple(self._get_project_directories()))
-            if count_packages_specified > count_packages_installed:
-                raise_compiler_error(
-                    f'dbt found {count_packages_specified} package(s) '
-                    f'specified in packages.yml, but only '
-                    f'{count_packages_installed} package(s) installed '
-                    f'in {self.packages_install_path}. Run "dbt deps" to '
-                    f'install package dependencies.'
-                )
-            project_paths = itertools.chain(
-                internal_packages,
-                self._get_project_directories()
-            )
+            if base_only:
+                # Test setup -- we want to load macros without dependencies
+                project_paths = itertools.chain(internal_packages)
+            else:
+                # raise exception if fewer installed packages than in packages.yml
+                count_packages_specified = len(self.packages.packages)  # type: ignore
+                count_packages_installed = len(tuple(self._get_project_directories()))
+                if count_packages_specified > count_packages_installed:
+                    raise_compiler_error(
+                        f"dbt found {count_packages_specified} package(s) "
+                        f"specified in packages.yml, but only "
+                        f"{count_packages_installed} package(s) installed "
+                        f'in {self.packages_install_path}. Run "dbt deps" to '
+                        f"install package dependencies."
+                    )
+                project_paths = itertools.chain(internal_packages, self._get_project_directories())
             for project_name, project in self.load_projects(project_paths):
                 if project_name in all_projects:
                     raise_compiler_error(
-                        f'dbt found more than one package with the name '
+                        f"dbt found more than one package with the name "
                         f'"{project_name}" included in this project. Package '
-                        f'names must be unique in a project. Please rename '
-                        f'one of these packages.'
+                        f"names must be unique in a project. Please rename "
+                        f"one of these packages."
                     )
                 all_projects[project_name] = project
             self.dependencies = all_projects
@@ -369,16 +348,14 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         self.dependencies = None
 
     # Called by 'load_dependencies' in this class
-    def load_projects(
-        self, paths: Iterable[Path]
-    ) -> Iterator[Tuple[str, 'RuntimeConfig']]:
+    def load_projects(self, paths: Iterable[Path]) -> Iterator[Tuple[str, "RuntimeConfig"]]:
         for path in paths:
             try:
                 project = self.new_project(str(path))
             except DbtProjectError as e:
                 raise DbtProjectError(
-                    f'Failed to read package: {e}',
-                    result_type='invalid_project',
+                    f"Failed to read package: {e}",
+                    result_type="invalid_project",
                     path=path,
                 ) from e
             else:
@@ -389,13 +366,13 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
         if root.exists():
             for path in root.iterdir():
-                if path.is_dir() and not path.name.startswith('__'):
+                if path.is_dir() and not path.name.startswith("__"):
                     yield path
 
 
 class UnsetCredentials(Credentials):
     def __init__(self):
-        super().__init__('', '')
+        super().__init__("", "")
 
     @property
     def type(self):
@@ -412,37 +389,28 @@ class UnsetCredentials(Credentials):
         return ()
 
 
-class UnsetConfig(UserConfig):
-    def __getattribute__(self, name):
-        if name in {f.name for f in fields(UserConfig)}:
-            raise AttributeError(
-                f"'UnsetConfig' object has no attribute {name}"
-            )
-
-    def __post_serialize__(self, dct):
-        return {}
-
-
+# This is used by UnsetProfileConfig, for commands which do
+# not require a profile, i.e. dbt deps and clean
 class UnsetProfile(Profile):
     def __init__(self):
         self.credentials = UnsetCredentials()
-        self.user_config = UnsetConfig()
-        self.profile_name = ''
-        self.target_name = ''
+        self.user_config = UserConfig()  # This will be read in _get_rendered_profile
+        self.profile_name = ""
+        self.target_name = ""
         self.threads = -1
 
     def to_target_dict(self):
-        return {}
+        return DictDefaultEmptyStr({})
 
     def __getattribute__(self, name):
-        if name in {'profile_name', 'target_name', 'threads'}:
-            raise RuntimeException(
-                f'Error: disallowed attribute "{name}" - no profile!'
-            )
+        if name in {"profile_name", "target_name", "threads"}:
+            raise RuntimeException(f'Error: disallowed attribute "{name}" - no profile!')
 
         return Profile.__getattribute__(self, name)
 
 
+# This class is used by the dbt deps and clean commands, because they don't
+# require a functioning profile.
 @dataclass
 class UnsetProfileConfig(RuntimeConfig):
     """This class acts a lot _like_ a RuntimeConfig, except if your profile is
@@ -459,17 +427,15 @@ class UnsetProfileConfig(RuntimeConfig):
 
     def __getattribute__(self, name):
         # Override __getattribute__ to check that the attribute isn't 'banned'.
-        if name in {'profile_name', 'target_name'}:
-            raise RuntimeException(
-                f'Error: disallowed attribute "{name}" - no profile!'
-            )
+        if name in {"profile_name", "target_name"}:
+            raise RuntimeException(f'Error: disallowed attribute "{name}" - no profile!')
 
         # avoid every attribute access triggering infinite recursion
         return RuntimeConfig.__getattribute__(self, name)
 
     def to_target_dict(self):
         # re-override the poisoned profile behavior
-        return {}
+        return DictDefaultEmptyStr({})
 
     @classmethod
     def from_parts(
@@ -477,8 +443,8 @@ class UnsetProfileConfig(RuntimeConfig):
         project: Project,
         profile: Profile,
         args: Any,
-        dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None,
-    ) -> 'RuntimeConfig':
+        dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None,
+    ) -> "RuntimeConfig":
         """Instantiate a RuntimeConfig from its components.
 
         :param profile: Ignored.
@@ -486,7 +452,7 @@ class UnsetProfileConfig(RuntimeConfig):
         :param args: The parsed command-line arguments.
         :returns RuntimeConfig: The new configuration.
         """
-        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
 
         return cls(
             project_name=project.project_name,
@@ -523,10 +489,10 @@ class UnsetProfileConfig(RuntimeConfig):
             unrendered=project.unrendered,
             project_env_vars=project.project_env_vars,
             profile_env_vars=profile.profile_env_vars,
-            profile_name='',
-            target_name='',
-            user_config=UnsetConfig(),
-            threads=getattr(args, 'threads', 1),
+            profile_name="",
+            target_name="",
+            user_config=UserConfig(),
+            threads=getattr(args, "threads", 1),
             credentials=UnsetCredentials(),
             args=args,
             cli_vars=cli_vars,
@@ -540,25 +506,16 @@ class UnsetProfileConfig(RuntimeConfig):
         profile_renderer: ProfileRenderer,
         profile_name: Optional[str],
     ) -> Profile:
-        try:
-            profile = Profile.render_from_args(
-                args, profile_renderer, profile_name
-            )
-        except (DbtProjectError, DbtProfileError) as exc:
-            selected_profile_name = Profile.pick_profile_name(
-                args_profile_name=getattr(args, 'profile', None),
-                project_profile_name=profile_name
-            )
-            fire_event(ProfileLoadError(exc=exc))
-            fire_event(ProfileNotFound(profile_name=selected_profile_name))
-            # return the poisoned form
-            profile = UnsetProfile()
-            # disable anonymous usage statistics
-            tracking.disable_tracking()
+
+        profile = UnsetProfile()
+        # The profile (for warehouse connection) is not needed, but we want
+        # to get the UserConfig, which is also in profiles.yml
+        user_config = read_user_config(flags.PROFILES_DIR)
+        profile.user_config = user_config
         return profile
 
     @classmethod
-    def from_args(cls: Type[RuntimeConfig], args: Any) -> 'RuntimeConfig':
+    def from_args(cls: Type[RuntimeConfig], args: Any) -> "RuntimeConfig":
         """Given arguments, read in dbt_project.yml from the current directory,
         read in packages.yml if it exists, and use them to find the profile to
         load.
@@ -569,15 +526,8 @@ class UnsetProfileConfig(RuntimeConfig):
         :raises ValidationException: If the cli variables are invalid.
         """
         project, profile = cls.collect_parts(args)
-        if not isinstance(profile, UnsetProfile):
-            # if it's a real profile, return a real config
-            cls = RuntimeConfig
 
-        return cls.from_parts(
-            project=project,
-            profile=profile,
-            args=args
-        )
+        return cls.from_parts(project=project, profile=profile, args=args)
 
 
 UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE = """\
@@ -591,6 +541,6 @@ There are {} unused configuration paths:
 def _is_config_used(path, fqns):
     if fqns:
         for fqn in fqns:
-            if len(path) <= len(fqn) and fqn[:len(path)] == path:
+            if len(path) <= len(fqn) and fqn[: len(path)] == path:
                 return True
     return False

core/dbt/config/selectors.py

@@ -1,11 +1,9 @@
 from pathlib import Path
 from typing import Dict, Any, Union
-from dbt.clients.yaml_helper import (  # noqa: F401
-    yaml, Loader, Dumper, load_yaml_text
-)
+from dbt.clients.yaml_helper import yaml, Loader, Dumper, load_yaml_text  # noqa: F401
 from dbt.dataclass_schema import ValidationError
 
-from .renderer import SelectorRenderer
+from .renderer import BaseRenderer
 
 from dbt.clients.system import (
     load_file_contents,
@@ -30,9 +28,8 @@ Validator Error:
 
 
 class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
-
     @classmethod
-    def selectors_from_dict(cls, data: Dict[str, Any]) -> 'SelectorConfig':
+    def selectors_from_dict(cls, data: Dict[str, Any]) -> "SelectorConfig":
         try:
             SelectorFile.validate(data)
             selector_file = SelectorFile.from_dict(data)
@@ -46,12 +43,12 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
                 f"union, intersection, string, dictionary. No lists. "
                 f"\nhttps://docs.getdbt.com/reference/node-selection/"
                 f"yaml-selectors",
-                result_type='invalid_selector'
+                result_type="invalid_selector",
             ) from exc
         except RuntimeException as exc:
             raise DbtSelectorsError(
-                f'Could not read selector file data: {exc}',
-                result_type='invalid_selector',
+                f"Could not read selector file data: {exc}",
+                result_type="invalid_selector",
             ) from exc
 
         return cls(selectors)
@@ -60,27 +57,29 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
     def render_from_dict(
         cls,
         data: Dict[str, Any],
-        renderer: SelectorRenderer,
-    ) -> 'SelectorConfig':
+        renderer: BaseRenderer,
+    ) -> "SelectorConfig":
         try:
             rendered = renderer.render_data(data)
         except (ValidationError, RuntimeException) as exc:
             raise DbtSelectorsError(
-                f'Could not render selector data: {exc}',
-                result_type='invalid_selector',
+                f"Could not render selector data: {exc}",
+                result_type="invalid_selector",
             ) from exc
         return cls.selectors_from_dict(rendered)
 
     @classmethod
     def from_path(
-        cls, path: Path, renderer: SelectorRenderer,
-    ) -> 'SelectorConfig':
+        cls,
+        path: Path,
+        renderer: BaseRenderer,
+    ) -> "SelectorConfig":
         try:
             data = load_yaml_text(load_file_contents(str(path)))
         except (ValidationError, RuntimeException) as exc:
             raise DbtSelectorsError(
-                f'Could not read selector file: {exc}',
-                result_type='invalid_selector',
+                f"Could not read selector file: {exc}",
+                result_type="invalid_selector",
                 path=path,
             ) from exc
 
@@ -92,9 +91,7 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
 
 
 def selector_data_from_root(project_root: str) -> Dict[str, Any]:
-    selector_filepath = resolve_path_from_base(
-        'selectors.yml', project_root
-    )
+    selector_filepath = resolve_path_from_base("selectors.yml", project_root)
 
     if path_exists(selector_filepath):
         selectors_dict = load_yaml_text(load_file_contents(selector_filepath))
@@ -103,18 +100,16 @@ def selector_data_from_root(project_root: str) -> Dict[str, Any]:
     return selectors_dict
 
 
-def selector_config_from_data(
-    selectors_data: Dict[str, Any]
-) -> SelectorConfig:
+def selector_config_from_data(selectors_data: Dict[str, Any]) -> SelectorConfig:
     if not selectors_data:
-        selectors_data = {'selectors': []}
+        selectors_data = {"selectors": []}
 
     try:
         selectors = SelectorConfig.selectors_from_dict(selectors_data)
     except ValidationError as e:
         raise DbtSelectorsError(
             MALFORMED_SELECTOR_ERROR.format(error=str(e.message)),
-            result_type='invalid_selector',
+            result_type="invalid_selector",
         ) from e
     return selectors
 
@@ -144,7 +139,6 @@ def validate_selector_default(selector_file: SelectorFile) -> None:
 # be necessary to make changes here. Ideally it would be
 # good to combine the two flows into one at some point.
 class SelectorDict:
-
     @classmethod
     def parse_dict_definition(cls, definition):
         key = list(definition)[0]
@@ -155,10 +149,10 @@ class SelectorDict:
                 new_value = cls.parse_from_definition(sel_def)
                 new_values.append(new_value)
             value = new_values
-        if key == 'exclude':
+        if key == "exclude":
             definition = {key: value}
         elif len(definition) == 1:
-            definition = {'method': key, 'value': value}
+            definition = {"method": key, "value": value}
         return definition
 
     @classmethod
@@ -180,10 +174,10 @@ class SelectorDict:
     def parse_from_definition(cls, definition):
         if isinstance(definition, str):
             definition = SelectionCriteria.dict_from_single_spec(definition)
-        elif 'union' in definition:
-            definition = cls.parse_a_definition('union', definition)
-        elif 'intersection' in definition:
-            definition = cls.parse_a_definition('intersection', definition)
+        elif "union" in definition:
+            definition = cls.parse_a_definition("union", definition)
+        elif "intersection" in definition:
+            definition = cls.parse_a_definition("intersection", definition)
         elif isinstance(definition, dict):
             definition = cls.parse_dict_definition(definition)
         return definition
@@ -194,8 +188,8 @@ class SelectorDict:
     def parse_from_selectors_list(cls, selectors):
         selector_dict = {}
         for selector in selectors:
-            sel_name = selector['name']
+            sel_name = selector["name"]
             selector_dict[sel_name] = selector
-            definition = cls.parse_from_definition(selector['definition'])
-            selector_dict[sel_name]['definition'] = definition
+            definition = cls.parse_from_definition(selector["definition"])
+            selector_dict[sel_name]["definition"] = definition
         return selector_dict

core/dbt/config/utils.py

@@ -1,9 +1,15 @@
-from typing import Dict, Any
+from argparse import Namespace
+from typing import Any, Dict, Optional, Union
+from xmlrpc.client import Boolean
+from dbt.contracts.project import UserConfig
 
+import dbt.flags as flags
 from dbt.clients import yaml_helper
+from dbt.config import Profile, Project, read_user_config
+from dbt.config.renderer import DbtProjectYamlRenderer, ProfileRenderer
 from dbt.events.functions import fire_event
-from dbt.exceptions import raise_compiler_error, ValidationException
 from dbt.events.types import InvalidVarsYAML
+from dbt.exceptions import ValidationException, raise_compiler_error
 
 
 def parse_cli_vars(var_string: str) -> Dict[str, Any]:
@@ -16,7 +22,54 @@ def parse_cli_vars(var_string: str) -> Dict[str, Any]:
             type_name = var_type.__name__
             raise_compiler_error(
                 "The --vars argument must be a YAML dictionary, but was "
-                "of type '{}'".format(type_name))
+                "of type '{}'".format(type_name)
+            )
     except ValidationException:
         fire_event(InvalidVarsYAML())
         raise
+
+
+def get_project_config(
+    project_path: str,
+    profile_name: str,
+    args: Namespace = Namespace(),
+    cli_vars: Optional[Dict[str, Any]] = None,
+    profile: Optional[Profile] = None,
+    user_config: Optional[UserConfig] = None,
+    return_dict: Boolean = True,
+) -> Union[Project, Dict]:
+    """Returns a project config (dict or object) from a given project path and profile name.
+
+    Args:
+        project_path: Path to project
+        profile_name: Name of profile
+        args: An argparse.Namespace that represents what would have been passed in on the
+            command line (optional)
+        cli_vars: A dict of any vars that would have been passed in on the command line (optional)
+            (see parse_cli_vars above for formatting details)
+        profile: A dbt.config.profile.Profile object (optional)
+        user_config: A dbt.contracts.project.UserConfig object (optional)
+        return_dict: Return a dict if true, return the full dbt.config.project.Project object if false
+
+    Returns:
+        A full project config
+
+    """
+    # Generate a profile if not provided
+    if profile is None:
+        # Generate user_config if not provided
+        if user_config is None:
+            user_config = read_user_config(flags.PROFILES_DIR)
+        # Update flags
+        flags.set_from_args(args, user_config)
+        if cli_vars is None:
+            cli_vars = {}
+        profile = Profile.render_from_args(args, ProfileRenderer(cli_vars), profile_name)
+    # Generate a project
+    project = Project.from_project_root(
+        project_path,
+        DbtProjectYamlRenderer(profile),
+        verify_version=bool(flags.VERSION_CHECK),
+    )
+    # Return
+    return project.to_project_config() if return_dict else project

core/dbt/context/README.md

@@ -0,0 +1,51 @@
+# Contexts and Jinja rendering
+
+Contexts are used for Jinja rendering. They include context methods, executable macros, and various settings that are available in Jinja.
+
+The most common entrypoint to Jinja rendering in dbt is a method named `get_rendered`, which takes two arguments: templated code (string), and a context used to render it (dictionary). 
+
+The context is the bundle of information that is in "scope" when rendering Jinja-templated code. For instance, imagine a simple Jinja template:
+```
+{% set new_value = some_macro(some_variable) %}
+```
+Both `some_macro()` and `some_variable` must be defined in that context. Otherwise, it will raise an error when rendering.
+
+Different contexts are used in different places because we allow access to different methods and data in different places. Executable SQL, for example, includes all available macros and the model being run. The variables and macros in scope for Jinja defined in yaml files is much more limited.
+
+### Implementation
+
+The context that is passed to Jinja is always in a dictionary format, not an actual class, so a `to_dict()` is executed on a context class before it is used for rendering.
+
+Each context has a `generate_<name>_context` function to create the context. `ProviderContext` subclasses have different generate functions for parsing and for execution, so that certain functions (notably `ref`, `source`, and `config`) can return different results
+
+### Hierarchy
+
+All contexts inherit from the `BaseContext`, which includes "pure" methods (e.g. `tojson`), `env_var()`, and `var()` (but only CLI values, passed via `--vars`).
+
+Methods available in parent contexts are also available in child contexts.
+
+```
+   BaseContext -- core/dbt/context/base.py
+     SecretContext -- core/dbt/context/secret.py
+     TargetContext -- core/dbt/context/target.py
+       ConfiguredContext -- core/dbt/context/configured.py
+         SchemaYamlContext -- core/dbt/context/configured.py
+           DocsRuntimeContext -- core/dbt/context/configured.py
+         MacroResolvingContext -- core/dbt/context/configured.py
+         ManifestContext -- core/dbt/context/manifest.py
+           QueryHeaderContext -- core/dbt/context/manifest.py
+           ProviderContext -- core/dbt/context/provider.py
+             MacroContext -- core/dbt/context/provider.py
+             ModelContext -- core/dbt/context/provider.py
+             TestContext -- core/dbt/context/provider.py
+```
+
+### Contexts for configuration
+
+Contexts for rendering "special" `.yml` (configuration) files:
+- `SecretContext`: Supports "secret" env vars, which are prefixed with `DBT_ENV_SECRET_`. Used for rendering in `profiles.yml` and `packages.yml` ONLY. Secrets defined elsewhere will raise explicit errors.
+- `TargetContext`: The same as `Base`, plus `target` (connection profile). Used most notably in `dbt_project.yml` and `selectors.yml`.
+
+Contexts for other `.yml` files in the project:
+- `SchemaYamlContext`: Supports `vars` declared on the CLI and in `dbt_project.yml`. Does not support custom macros, beyond `var()` + `env_var()` methods. Used for all `.yml` files, to define properties and configuration.
+- `DocsRuntimeContext`: Standard `.yml` file context, plus `doc()` method (with all `docs` blocks in scope). Used to resolve `description` properties.

core/dbt/context/base.py

@@ -1,18 +1,17 @@
 import json
 import os
-from typing import (
-    Any, Dict, NoReturn, Optional, Mapping
-)
+from typing import Any, Dict, NoReturn, Optional, Mapping
 
 from dbt import flags
 from dbt import tracking
 from dbt.clients.jinja import get_rendered
-from dbt.clients.yaml_helper import (  # noqa: F401
-    yaml, safe_load, SafeLoader, Loader, Dumper
-)
+from dbt.clients.yaml_helper import yaml, safe_load, SafeLoader, Loader, Dumper  # noqa: F401
 from dbt.contracts.graph.compiled import CompiledResource
 from dbt.exceptions import (
-    raise_compiler_error, MacroReturn, raise_parsing_error, disallow_secret_env_var
+    raise_compiler_error,
+    MacroReturn,
+    raise_parsing_error,
+    disallow_secret_env_var,
 )
 from dbt.logger import SECRET_ENV_PREFIX
 from dbt.events.functions import fire_event, get_invocation_id
@@ -25,75 +24,33 @@ import pytz
 import datetime
 import re
 
-# Contexts in dbt Core
-# Contexts are used for Jinja rendering. They include context methods,
-# executable macros, and various settings that are available in Jinja.
-#
-# Different contexts are used in different places because we allow access
-# to different methods and data in different places. Executable SQL, for
-# example, includes the available macros and the model, while Jinja in
-# yaml files is more limited.
-#
-# The context that is passed to Jinja is always in a dictionary format,
-# not an actual class, so a 'to_dict()' is executed on a context class
-# before it is used for rendering.
-#
-# Each context has a generate_<name>_context function to create the context.
-# ProviderContext subclasses have different generate functions for
-# parsing and for execution.
-#
-# Context class hierarchy
-#
-#   BaseContext -- core/dbt/context/base.py
-#     SecretContext -- core/dbt/context/secret.py
-#     TargetContext -- core/dbt/context/target.py
-#       ConfiguredContext -- core/dbt/context/configured.py
-#         SchemaYamlContext -- core/dbt/context/configured.py
-#           DocsRuntimeContext -- core/dbt/context/configured.py
-#         MacroResolvingContext -- core/dbt/context/configured.py
-#         ManifestContext -- core/dbt/context/manifest.py
-#           QueryHeaderContext -- core/dbt/context/manifest.py
-#           ProviderContext -- core/dbt/context/provider.py
-#             MacroContext -- core/dbt/context/provider.py
-#             ModelContext -- core/dbt/context/provider.py
-#             TestContext -- core/dbt/context/provider.py
+# See the `contexts` module README for more information on how contexts work
 
 
 def get_pytz_module_context() -> Dict[str, Any]:
     context_exports = pytz.__all__  # type: ignore
 
-    return {
-        name: getattr(pytz, name) for name in context_exports
-    }
+    return {name: getattr(pytz, name) for name in context_exports}
 
 
 def get_datetime_module_context() -> Dict[str, Any]:
-    context_exports = [
-        'date',
-        'datetime',
-        'time',
-        'timedelta',
-        'tzinfo'
-    ]
+    context_exports = ["date", "datetime", "time", "timedelta", "tzinfo"]
 
-    return {
-        name: getattr(datetime, name) for name in context_exports
-    }
+    return {name: getattr(datetime, name) for name in context_exports}
 
 
 def get_re_module_context() -> Dict[str, Any]:
-    context_exports = re.__all__
+    # TODO CT-211
+    context_exports = re.__all__  # type: ignore[attr-defined]
 
-    return {
-        name: getattr(re, name) for name in context_exports
-    }
+    return {name: getattr(re, name) for name in context_exports}
 
 
 def get_context_modules() -> Dict[str, Dict[str, Any]]:
     return {
-        'pytz': get_pytz_module_context(),
-        'datetime': get_datetime_module_context(),
-        're': get_re_module_context(),
+        "pytz": get_pytz_module_context(),
+        "datetime": get_datetime_module_context(),
+        "re": get_re_module_context(),
     }
 
 
@@ -127,8 +84,8 @@ class ContextMeta(type):
         new_dct = {}
 
         for base in bases:
-            context_members.update(getattr(base, '_context_members_', {}))
-            context_attrs.update(getattr(base, '_context_attrs_', {}))
+            context_members.update(getattr(base, "_context_members_", {}))
+            context_attrs.update(getattr(base, "_context_attrs_", {}))
 
         for key, value in dct.items():
             if isinstance(value, ContextMember):
@@ -137,21 +94,20 @@ class ContextMeta(type):
                 context_attrs[context_key] = key
                 value = value.inner
             new_dct[key] = value
-        new_dct['_context_members_'] = context_members
-        new_dct['_context_attrs_'] = context_attrs
+        new_dct["_context_members_"] = context_members
+        new_dct["_context_attrs_"] = context_attrs
         return type.__new__(mcls, name, bases, new_dct)
 
 
 class Var:
-    UndefinedVarError = "Required var '{}' not found in config:\nVars "\
-                        "supplied to {} = {}"
+    UndefinedVarError = "Required var '{}' not found in config:\nVars " "supplied to {} = {}"
     _VAR_NOTSET = object()
 
     def __init__(
         self,
         context: Mapping[str, Any],
         cli_vars: Mapping[str, Any],
-        node: Optional[CompiledResource] = None
+        node: Optional[CompiledResource] = None,
     ) -> None:
         self._context: Mapping[str, Any] = context
         self._cli_vars: Mapping[str, Any] = cli_vars
@@ -166,14 +122,12 @@ class Var:
         if self._node is not None:
             return self._node.name
         else:
-            return '<Configuration>'
+            return "<Configuration>"
 
     def get_missing_var(self, var_name):
         dct = {k: self._merged[k] for k in self._merged}
         pretty_vars = json.dumps(dct, sort_keys=True, indent=4)
-        msg = self.UndefinedVarError.format(
-            var_name, self.node_name, pretty_vars
-        )
+        msg = self.UndefinedVarError.format(var_name, self.node_name, pretty_vars)
         raise_compiler_error(msg, self._node)
 
     def has_var(self, var_name: str):
@@ -206,7 +160,7 @@ class BaseContext(metaclass=ContextMeta):
     def generate_builtins(self):
         builtins: Dict[str, Any] = {}
         for key, value in self._context_members_.items():
-            if hasattr(value, '__get__'):
+            if hasattr(value, "__get__"):
                 # handle properties, bound methods, etc
                 value = value.__get__(self)
             builtins[key] = value
@@ -214,9 +168,9 @@ class BaseContext(metaclass=ContextMeta):
 
     # no dbtClassMixin so this is not an actual override
     def to_dict(self):
-        self._ctx['context'] = self._ctx
+        self._ctx["context"] = self._ctx
         builtins = self.generate_builtins()
-        self._ctx['builtins'] = builtins
+        self._ctx["builtins"] = builtins
         self._ctx.update(builtins)
         return self._ctx
 
@@ -331,18 +285,20 @@ class BaseContext(metaclass=ContextMeta):
             msg = f"Env var required but not provided: '{var}'"
             raise_parsing_error(msg)
 
-    if os.environ.get('DBT_MACRO_DEBUGGING'):
+    if os.environ.get("DBT_MACRO_DEBUGGING"):
+
         @contextmember
         @staticmethod
         def debug():
             """Enter a debugger at this line in the compiled jinja code."""
             import sys
             import ipdb  # type: ignore
+
             frame = sys._getframe(3)
             ipdb.set_trace(frame)
-            return ''
+            return ""
 
-    @contextmember('return')
+    @contextmember("return")
     @staticmethod
     def _return(data: Any) -> NoReturn:
         """The `return` function can be used in macros to return data to the
@@ -393,9 +349,7 @@ class BaseContext(metaclass=ContextMeta):
 
     @contextmember
     @staticmethod
-    def tojson(
-        value: Any, default: Any = None, sort_keys: bool = False
-    ) -> Any:
+    def tojson(value: Any, default: Any = None, sort_keys: bool = False) -> Any:
         """The `tojson` context method can be used to serialize a Python
         object primitive, eg. a `dict` or `list` to a json string.
 
@@ -488,10 +442,10 @@ class BaseContext(metaclass=ContextMeta):
             {% endmacro %}"
         """
         if info:
-            fire_event(MacroEventInfo(msg))
+            fire_event(MacroEventInfo(msg=msg))
         else:
-            fire_event(MacroEventDebug(msg))
-        return ''
+            fire_event(MacroEventDebug(msg=msg))
+        return ""
 
     @contextproperty
     def run_started_at(self) -> Optional[datetime.datetime]:
@@ -571,6 +525,24 @@ class BaseContext(metaclass=ContextMeta):
         """
         return flags
 
+    @contextmember
+    @staticmethod
+    def print(msg: str) -> str:
+        """Prints a line to stdout.
+
+        :param msg: The message to print
+
+        > macros/my_log_macro.sql
+
+            {% macro some_macro(arg1, arg2) %}
+              {{ print("Running some_macro: " ~ arg1 ~ ", " ~ arg2) }}
+            {% endmacro %}"
+        """
+
+        if not flags.NO_PRINT:
+            print(msg)
+        return ""
+
 
 def generate_base_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:
     ctx = BaseContext(cli_vars)

core/dbt/context/configured.py

@@ -15,9 +15,7 @@ class ConfiguredContext(TargetContext):
     # subclasses are SchemaYamlContext, MacroResolvingContext, ManifestContext
     config: AdapterRequiredConfig
 
-    def __init__(
-        self, config: AdapterRequiredConfig
-    ) -> None:
+    def __init__(self, config: AdapterRequiredConfig) -> None:
         super().__init__(config, config.cli_vars)
 
     @contextproperty
@@ -67,7 +65,7 @@ class ConfiguredVar(Var):
         return self.get_missing_var(var_name)
 
 
-class SchemaYamlVars():
+class SchemaYamlVars:
     def __init__(self):
         self.env_vars = {}
         self.vars = {}
@@ -82,9 +80,7 @@ class SchemaYamlContext(ConfiguredContext):
 
     @contextproperty
     def var(self) -> ConfiguredVar:
-        return ConfiguredVar(
-            self._ctx, self.config, self._project_name
-        )
+        return ConfiguredVar(self._ctx, self.config, self._project_name)
 
     @contextmember
     def env_var(self, var: str, default: Optional[str] = None) -> str:
@@ -111,13 +107,11 @@ class MacroResolvingContext(ConfiguredContext):
 
     @contextproperty
     def var(self) -> ConfiguredVar:
-        return ConfiguredVar(
-            self._ctx, self.config, self.config.project_name
-        )
+        return ConfiguredVar(self._ctx, self.config, self.config.project_name)
 
 
 def generate_schema_yml_context(
-        config: AdapterRequiredConfig, project_name: str, schema_yaml_vars: SchemaYamlVars = None
+    config: AdapterRequiredConfig, project_name: str, schema_yaml_vars: SchemaYamlVars = None
 ) -> Dict[str, Any]:
     ctx = SchemaYamlContext(config, project_name, schema_yaml_vars)
     return ctx.to_dict()

core/dbt/context/context_config.py

@@ -17,8 +17,8 @@ class ModelParts(IsFQNResource):
     package_name: str
 
 
-T = TypeVar('T')  # any old type
-C = TypeVar('C', bound=BaseConfig)
+T = TypeVar("T")  # any old type
+C = TypeVar("C", bound=BaseConfig)
 
 
 class ConfigSource:
@@ -36,15 +36,15 @@ class UnrenderedConfig(ConfigSource):
     def get_config_dict(self, resource_type: NodeType) -> Dict[str, Any]:
         unrendered = self.project.unrendered.project_dict
         if resource_type == NodeType.Seed:
-            model_configs = unrendered.get('seeds')
+            model_configs = unrendered.get("seeds")
         elif resource_type == NodeType.Snapshot:
-            model_configs = unrendered.get('snapshots')
+            model_configs = unrendered.get("snapshots")
         elif resource_type == NodeType.Source:
-            model_configs = unrendered.get('sources')
+            model_configs = unrendered.get("sources")
         elif resource_type == NodeType.Test:
-            model_configs = unrendered.get('tests')
+            model_configs = unrendered.get("tests")
         else:
-            model_configs = unrendered.get('models')
+            model_configs = unrendered.get("models")
 
         if model_configs is None:
             return {}
@@ -83,8 +83,8 @@ class BaseContextConfigGenerator(Generic[T]):
         dependencies = self._active_project.load_dependencies()
         if project_name not in dependencies:
             raise InternalException(
-                f'Project name {project_name} not found in dependencies '
-                f'(found {list(dependencies)})'
+                f"Project name {project_name} not found in dependencies "
+                f"(found {list(dependencies)})"
             )
         return dependencies[project_name]
 
@@ -96,7 +96,7 @@ class BaseContextConfigGenerator(Generic[T]):
         for level_config in fqn_search(model_configs, fqn):
             result = {}
             for key, value in level_config.items():
-                if key.startswith('+'):
+                if key.startswith("+"):
                     result[key[1:].strip()] = deepcopy(value)
                 elif not isinstance(value, dict):
                     result[key] = deepcopy(value)
@@ -109,9 +109,7 @@ class BaseContextConfigGenerator(Generic[T]):
         return self._project_configs(self._active_project, fqn, resource_type)
 
     @abstractmethod
-    def _update_from_config(
-        self, result: T, partial: Dict[str, Any], validate: bool = False
-    ) -> T:
+    def _update_from_config(self, result: T, partial: Dict[str, Any], validate: bool = False) -> T:
         ...
 
     @abstractmethod
@@ -125,7 +123,7 @@ class BaseContextConfigGenerator(Generic[T]):
         resource_type: NodeType,
         project_name: str,
         base: bool,
-        patch_config_dict: Dict[str, Any] = None
+        patch_config_dict: Dict[str, Any] = None,
     ) -> BaseConfig:
         own_config = self.get_node_project(project_name)
 
@@ -150,7 +148,8 @@ class BaseContextConfigGenerator(Generic[T]):
                 result = self._update_from_config(result, fqn_config)
 
         # this is mostly impactful in the snapshot config case
-        return result
+        # TODO CT-211
+        return result  # type: ignore[return-value]
 
     @abstractmethod
     def calculate_node_config_dict(
@@ -181,16 +180,10 @@ class ContextConfigGenerator(BaseContextConfigGenerator[C]):
         result = config_cls.from_dict({})
         return result
 
-    def _update_from_config(
-        self, result: C, partial: Dict[str, Any], validate: bool = False
-    ) -> C:
-        translated = self._active_project.credentials.translate_aliases(
-            partial
-        )
+    def _update_from_config(self, result: C, partial: Dict[str, Any], validate: bool = False) -> C:
+        translated = self._active_project.credentials.translate_aliases(partial)
         return result.update_from(
-            translated,
-            self._active_project.credentials.type,
-            validate=validate
+            translated, self._active_project.credentials.type, validate=validate
         )
 
     def calculate_node_config_dict(
@@ -200,7 +193,7 @@ class ContextConfigGenerator(BaseContextConfigGenerator[C]):
         resource_type: NodeType,
         project_name: str,
         base: bool,
-        patch_config_dict: dict = None
+        patch_config_dict: dict = None,
     ) -> Dict[str, Any]:
         config = self.calculate_node_config(
             config_call_dict=config_call_dict,
@@ -208,7 +201,7 @@ class ContextConfigGenerator(BaseContextConfigGenerator[C]):
             resource_type=resource_type,
             project_name=project_name,
             base=base,
-            patch_config_dict=patch_config_dict
+            patch_config_dict=patch_config_dict,
         )
         finalized = config.finalize_and_validate()
         return finalized.to_dict(omit_none=True)
@@ -225,22 +218,19 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
         resource_type: NodeType,
         project_name: str,
         base: bool,
-        patch_config_dict: dict = None
+        patch_config_dict: dict = None,
     ) -> Dict[str, Any]:
+        # TODO CT-211
         return self.calculate_node_config(
             config_call_dict=config_call_dict,
             fqn=fqn,
             resource_type=resource_type,
             project_name=project_name,
             base=base,
-            patch_config_dict=patch_config_dict
-        )
+            patch_config_dict=patch_config_dict,
+        )  # type: ignore[return-value]
 
-    def initial_result(
-        self,
-        resource_type: NodeType,
-        base: bool
-    ) -> Dict[str, Any]:
+    def initial_result(self, resource_type: NodeType, base: bool) -> Dict[str, Any]:
         return {}
 
     def _update_from_config(
@@ -249,9 +239,7 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
         partial: Dict[str, Any],
         validate: bool = False,
     ) -> Dict[str, Any]:
-        translated = self._active_project.credentials.translate_aliases(
-            partial
-        )
+        translated = self._active_project.credentials.translate_aliases(partial)
         result.update(translated)
         return result
 
@@ -279,11 +267,11 @@ class ContextConfig:
         for k, v in opts.items():
             # MergeBehavior for post-hook and pre-hook is to collect all
             # values, instead of overwriting
-            if k in BaseConfig.mergebehavior['append']:
+            if k in BaseConfig.mergebehavior["append"]:
                 if not isinstance(v, list):
                     v = [v]
-            if k in BaseConfig.mergebehavior['update'] and not isinstance(v, dict):
-                raise InternalException(f'expected dict, got {v}')
+            if k in BaseConfig.mergebehavior["update"] and not isinstance(v, dict):
+                raise InternalException(f"expected dict, got {v}")
             if k in config_call_dict and isinstance(config_call_dict[k], list):
                 config_call_dict[k].extend(v)
             elif k in config_call_dict and isinstance(config_call_dict[k], dict):
@@ -292,16 +280,14 @@ class ContextConfig:
                 config_call_dict[k] = v
 
     def build_config_dict(
-        self,
-        base: bool = False,
-        *,
-        rendered: bool = True,
-        patch_config_dict: dict = None
+        self, base: bool = False, *, rendered: bool = True, patch_config_dict: dict = None
     ) -> Dict[str, Any]:
         if rendered:
-            src = ContextConfigGenerator(self._active_project)
+            # TODO CT-211
+            src = ContextConfigGenerator(self._active_project)  # type: ignore[var-annotated]
         else:
-            src = UnrenderedConfigGenerator(self._active_project)
+            # TODO CT-211
+            src = UnrenderedConfigGenerator(self._active_project)  # type: ignore[assignment]
 
         return src.calculate_node_config_dict(
             config_call_dict=self._config_call_dict,
@@ -309,5 +295,5 @@ class ContextConfig:
             resource_type=self._resource_type,
             project_name=self._project_name,
             base=base,
-            patch_config_dict=patch_config_dict
+            patch_config_dict=patch_config_dict,
         )

core/dbt/context/docs.py

@@ -1,6 +1,4 @@
-from typing import (
-    Any, Dict, Union
-)
+from typing import Any, Dict, Union
 
 from dbt.exceptions import (
     doc_invalid_args,
@@ -68,7 +66,8 @@ class DocsRuntimeContext(SchemaYamlContext):
             file_id = target_doc.file_id
             if file_id in self.manifest.files:
                 source_file = self.manifest.files[file_id]
-                source_file.add_node(self.node.unique_id)
+                # TODO CT-211
+                source_file.add_node(self.node.unique_id)  # type: ignore[union-attr]
         else:
             doc_target_not_found(self.node, doc_name, doc_package_name)
 

core/dbt/context/macro_resolver.py

@@ -1,6 +1,4 @@
-from typing import (
-    Dict, MutableMapping, Optional
-)
+from typing import Dict, MutableMapping, Optional
 from dbt.contracts.graph.parsed import ParsedMacro
 from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
@@ -49,8 +47,7 @@ class MacroResolver:
         for pkg in reversed(self.internal_package_names):
             if pkg in self.internal_packages:
                 # Turn the internal packages into a flat namespace
-                self.internal_packages_namespace.update(
-                    self.internal_packages[pkg])
+                self.internal_packages_namespace.update(self.internal_packages[pkg])
 
     # search order:
     # local_namespace (package of particular node), not including
@@ -89,9 +86,7 @@ class MacroResolver:
             package_namespaces[macro.package_name] = namespace
 
         if macro.name in namespace:
-            raise_duplicate_macro_name(
-                macro, macro, macro.package_name
-            )
+            raise_duplicate_macro_name(macro, macro, macro.package_name)
         package_namespaces[macro.package_name][macro.name] = macro
 
     def add_macro(self, macro: ParsedMacro):
@@ -114,8 +109,7 @@ class MacroResolver:
 
     def get_macro(self, local_package, macro_name):
         local_package_macros = {}
-        if (local_package not in self.internal_package_names and
-                local_package in self.packages):
+        if local_package not in self.internal_package_names and local_package in self.packages:
             local_package_macros = self.packages[local_package]
         # First: search the local packages for this macro
         if macro_name in local_package_macros:
@@ -140,9 +134,7 @@ class MacroResolver:
 # is that you can limit the number of macros provided to the
 # context dictionary in the 'to_dict' manifest method.
 class TestMacroNamespace:
-    def __init__(
-        self, macro_resolver, ctx, node, thread_ctx, depends_on_macros
-    ):
+    def __init__(self, macro_resolver, ctx, node, thread_ctx, depends_on_macros):
         self.macro_resolver = macro_resolver
         self.ctx = ctx
         self.node = node  # can be none
@@ -155,11 +147,14 @@ class TestMacroNamespace:
             for macro_unique_id in dep_macros:
                 if macro_unique_id in self.macro_resolver.macros:
                     # Split up the macro unique_id to get the project_name
-                    (_, project_name, macro_name) = macro_unique_id.split('.')
+                    (_, project_name, macro_name) = macro_unique_id.split(".")
                     # Save the plain macro_name in the local_namespace
                     macro = self.macro_resolver.macros[macro_unique_id]
                     macro_gen = MacroGenerator(
-                        macro, self.ctx, self.node, self.thread_ctx,
+                        macro,
+                        self.ctx,
+                        self.node,
+                        self.thread_ctx,
                     )
                     self.local_namespace[macro_name] = macro_gen
                     # We also need the two part macro name
@@ -177,9 +172,7 @@ class TestMacroNamespace:
                 if macro.depends_on.macros:
                     self.recursively_get_depends_on_macros(macro.depends_on.macros, dep_macros)
 
-    def get_from_package(
-        self, package_name: Optional[str], name: str
-    ) -> Optional[MacroGenerator]:
+    def get_from_package(self, package_name: Optional[str], name: str) -> Optional[MacroGenerator]:
         macro = None
         if package_name is None:
             macro = self.macro_resolver.macros_by_name.get(name)
@@ -188,12 +181,8 @@ class TestMacroNamespace:
         elif package_name in self.macro_resolver.packages:
             macro = self.macro_resolver.packages[package_name].get(name)
         else:
-            raise_compiler_error(
-                f"Could not find package '{package_name}'"
-            )
+            raise_compiler_error(f"Could not find package '{package_name}'")
         if not macro:
             return None
-        macro_func = MacroGenerator(
-            macro, self.ctx, self.node, self.thread_ctx
-        )
+        macro_func = MacroGenerator(macro, self.ctx, self.node, self.thread_ctx)
         return macro_func

core/dbt/context/macros.py

@@ -1,13 +1,9 @@
-from typing import (
-    Any, Dict, Iterable, Union, Optional, List, Iterator, Mapping, Set
-)
+from typing import Any, Dict, Iterable, Union, Optional, List, Iterator, Mapping, Set
 
 from dbt.clients.jinja import MacroGenerator, MacroStack
 from dbt.contracts.graph.parsed import ParsedMacro
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
-from dbt.exceptions import (
-    raise_duplicate_macro_name, raise_compiler_error
-)
+from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
 
 
 FlatNamespace = Dict[str, MacroGenerator]
@@ -27,7 +23,7 @@ class MacroNamespace(Mapping):
     def __init__(
         self,
         global_namespace: FlatNamespace,  # root package macros
-        local_namespace: FlatNamespace,   # packages for *this* node
+        local_namespace: FlatNamespace,  # packages for *this* node
         global_project_namespace: FlatNamespace,  # internal packages
         packages: Dict[str, FlatNamespace],  # non-internal packages
     ):
@@ -37,11 +33,13 @@ class MacroNamespace(Mapping):
         self.global_project_namespace: FlatNamespace = global_project_namespace
 
     def _search_order(self) -> Iterable[Union[FullNamespace, FlatNamespace]]:
-        yield self.local_namespace   # local package
+        yield self.local_namespace  # local package
         yield self.global_namespace  # root package
-        yield self.packages          # non-internal packages
+        # TODO CT-211
+        yield self.packages  # type: ignore[misc] # non-internal packages
         yield {
-            GLOBAL_PROJECT_NAME: self.global_project_namespace,  # dbt
+            # TODO CT-211
+            GLOBAL_PROJECT_NAME: self.global_project_namespace,  # type: ignore[misc] # dbt
         }
         yield self.global_project_namespace  # other internal project besides dbt
 
@@ -68,9 +66,7 @@ class MacroNamespace(Mapping):
                 return dct[key]
         raise KeyError(key)
 
-    def get_from_package(
-        self, package_name: Optional[str], name: str
-    ) -> Optional[MacroGenerator]:
+    def get_from_package(self, package_name: Optional[str], name: str) -> Optional[MacroGenerator]:
         pkg: FlatNamespace
         if package_name is None:
             return self.get(name)
@@ -79,9 +75,7 @@ class MacroNamespace(Mapping):
         elif package_name in self.packages:
             return self.packages[package_name].get(name)
         else:
-            raise_compiler_error(
-                f"Could not find package '{package_name}'"
-            )
+            raise_compiler_error(f"Could not find package '{package_name}'")
 
 
 # This class builds the MacroNamespace by adding macros to
@@ -128,9 +122,7 @@ class MacroNamespaceBuilder:
             hierarchy[macro.package_name] = namespace
 
         if macro.name in namespace:
-            raise_duplicate_macro_name(
-                macro_func.macro, macro, macro.package_name
-            )
+            raise_duplicate_macro_name(macro_func.macro, macro, macro.package_name)
         hierarchy[macro.package_name][macro.name] = macro_func
 
     def add_macro(self, macro: ParsedMacro, ctx: Dict[str, Any]):
@@ -139,9 +131,7 @@ class MacroNamespaceBuilder:
         # MacroGenerator is in clients/jinja.py
         # a MacroGenerator object is a callable object that will
         # execute the MacroGenerator.__call__ function
-        macro_func: MacroGenerator = MacroGenerator(
-            macro, ctx, self.node, self.thread_ctx
-        )
+        macro_func: MacroGenerator = MacroGenerator(macro, ctx, self.node, self.thread_ctx)
 
         # internal macros (from plugins) will be processed separately from
         # project macros, so store them in a different place

core/dbt/context/manifest.py

@@ -17,6 +17,7 @@ class ManifestContext(ConfiguredContext):
     The given macros can override any previous context values, which will be
     available as if they were accessed relative to the package name.
     """
+
     # subclasses are QueryHeaderContext and ProviderContext
     def __init__(
         self,
@@ -38,16 +39,13 @@ class ManifestContext(ConfiguredContext):
         # this takes all the macros in the manifest and adds them
         # to the MacroNamespaceBuilder stored in self.namespace
         builder = self._get_namespace_builder()
-        return builder.build_namespace(
-            self.manifest.macros.values(), self._ctx
-        )
+        return builder.build_namespace(self.manifest.macros.values(), self._ctx)
 
     def _get_namespace_builder(self) -> MacroNamespaceBuilder:
         # avoid an import loop
         from dbt.adapters.factory import get_adapter_package_names
-        internal_packages: List[str] = get_adapter_package_names(
-            self.config.credentials.type
-        )
+
+        internal_packages: List[str] = get_adapter_package_names(self.config.credentials.type)
         return MacroNamespaceBuilder(
             self.config.project_name,
             self.search_package,
@@ -70,14 +68,10 @@ class ManifestContext(ConfiguredContext):
 
 
 class QueryHeaderContext(ManifestContext):
-    def __init__(
-        self, config: AdapterRequiredConfig, manifest: Manifest
-    ) -> None:
+    def __init__(self, config: AdapterRequiredConfig, manifest: Manifest) -> None:
         super().__init__(config, manifest, config.project_name)
 
 
-def generate_query_header_context(
-    config: AdapterRequiredConfig, manifest: Manifest
-):
+def generate_query_header_context(config: AdapterRequiredConfig, manifest: Manifest):
     ctx = QueryHeaderContext(config, manifest)
     return ctx.to_dict()

core/dbt/context/providers.py

@@ -1,15 +1,21 @@
 import abc
 import os
 from typing import (
-    Callable, Any, Dict, Optional, Union, List, TypeVar, Type, Iterable,
+    Callable,
+    Any,
+    Dict,
+    Optional,
+    Union,
+    List,
+    TypeVar,
+    Type,
+    Iterable,
     Mapping,
 )
 from typing_extensions import Protocol
 
 from dbt.adapters.base.column import Column
-from dbt.adapters.factory import (
-    get_adapter, get_adapter_package_names, get_adapter_type_names
-)
+from dbt.adapters.factory import get_adapter, get_adapter_package_names, get_adapter_type_names
 from dbt.clients import agate_helper
 from dbt.clients.jinja import get_rendered, MacroGenerator, MacroStack
 from dbt.config import RuntimeConfig, Project
@@ -21,9 +27,7 @@ from dbt.context.macro_resolver import MacroResolver, TestMacroNamespace
 from .macros import MacroNamespaceBuilder, MacroNamespace
 from .manifest import ManifestContext
 from dbt.contracts.connection import AdapterResponse
-from dbt.contracts.graph.manifest import (
-    Manifest, Disabled
-)
+from dbt.contracts.graph.manifest import Manifest, Disabled
 from dbt.contracts.graph.compiled import (
     CompiledResource,
     CompiledSeedNode,
@@ -56,9 +60,9 @@ from dbt.exceptions import (
 from dbt.config import IsFQNResource
 from dbt.node_types import NodeType
 
-from dbt.utils import (
-    merge, AttrDict, MultiDict
-)
+from dbt.utils import merge, AttrDict, MultiDict
+
+from dbt import selected_resources
 
 import agate
 
@@ -81,10 +85,7 @@ class RelationProxy:
         return self._relation_type.create_from_source(*args, **kwargs)
 
     def create(self, *args, **kwargs):
-        kwargs['quote_policy'] = merge(
-            self._quoting_config,
-            kwargs.pop('quote_policy', {})
-        )
+        kwargs["quote_policy"] = merge(self._quoting_config, kwargs.pop("quote_policy", {}))
         return self._relation_type.create(*args, **kwargs)
 
 
@@ -100,7 +101,7 @@ class BaseDatabaseWrapper:
         self._namespace = namespace
 
     def __getattr__(self, name):
-        raise NotImplementedError('subclasses need to implement this')
+        raise NotImplementedError("subclasses need to implement this")
 
     @property
     def config(self):
@@ -117,7 +118,7 @@ class BaseDatabaseWrapper:
         #  1. current adapter
         #  2. any parent adapters (dependencies)
         #  3. 'default'
-        search_prefixes = get_adapter_type_names(self._adapter.type()) + ['default']
+        search_prefixes = get_adapter_type_names(self._adapter.type()) + ["default"]
         return search_prefixes
 
     def dispatch(
@@ -128,8 +129,8 @@ class BaseDatabaseWrapper:
     ) -> MacroGenerator:
         search_packages: List[Optional[str]]
 
-        if '.' in macro_name:
-            suggest_macro_namespace, suggest_macro_name = macro_name.split('.', 1)
+        if "." in macro_name:
+            suggest_macro_namespace, suggest_macro_name = macro_name.split(".", 1)
             msg = (
                 f'In adapter.dispatch, got a macro name of "{macro_name}", '
                 f'but "." is not a valid macro name component. Did you mean '
@@ -152,7 +153,7 @@ class BaseDatabaseWrapper:
         else:
             # Not a string and not None so must be a list
             raise CompilationException(
-                f'In adapter.dispatch, got a list macro_namespace argument '
+                f"In adapter.dispatch, got a list macro_namespace argument "
                 f'("{macro_namespace}"), but macro_namespace should be None or a string.'
             )
 
@@ -160,12 +161,10 @@ class BaseDatabaseWrapper:
 
         for package_name in search_packages:
             for prefix in self._get_adapter_macro_prefixes():
-                search_name = f'{prefix}__{macro_name}'
+                search_name = f"{prefix}__{macro_name}"
                 try:
                     # this uses the namespace from the context
-                    macro = self._namespace.get_from_package(
-                        package_name, search_name
-                    )
+                    macro = self._namespace.get_from_package(package_name, search_name)
                 except CompilationException:
                     # Only raise CompilationException if macro is not found in
                     # any package
@@ -174,16 +173,13 @@ class BaseDatabaseWrapper:
                 if package_name is None:
                     attempts.append(search_name)
                 else:
-                    attempts.append(f'{package_name}.{search_name}')
+                    attempts.append(f"{package_name}.{search_name}")
 
                 if macro is not None:
                     return macro
 
-        searched = ', '.join(repr(a) for a in attempts)
-        msg = (
-            f"In dispatch: No macro named '{macro_name}' found\n"
-            f"    Searched for: {searched}"
-        )
+        searched = ", ".join(repr(a) for a in attempts)
+        msg = f"In dispatch: No macro named '{macro_name}' found\n" f"    Searched for: {searched}"
         raise CompilationException(msg)
 
 
@@ -209,14 +205,10 @@ class BaseResolver(metaclass=abc.ABCMeta):
 
 class BaseRefResolver(BaseResolver):
     @abc.abstractmethod
-    def resolve(
-        self, name: str, package: Optional[str] = None
-    ) -> RelationProxy:
+    def resolve(self, name: str, package: Optional[str] = None) -> RelationProxy:
         ...
 
-    def _repack_args(
-        self, name: str, package: Optional[str]
-    ) -> List[str]:
+    def _repack_args(self, name: str, package: Optional[str]) -> List[str]:
         if package is None:
             return [name]
         else:
@@ -225,14 +217,12 @@ class BaseRefResolver(BaseResolver):
     def validate_args(self, name: str, package: Optional[str]):
         if not isinstance(name, str):
             raise CompilationException(
-                f'The name argument to ref() must be a string, got '
-                f'{type(name)}'
+                f"The name argument to ref() must be a string, got " f"{type(name)}"
             )
 
         if package is not None and not isinstance(package, str):
             raise CompilationException(
-                f'The package argument to ref() must be a string or None, got '
-                f'{type(package)}'
+                f"The package argument to ref() must be a string or None, got " f"{type(package)}"
             )
 
     def __call__(self, *args: str) -> RelationProxy:
@@ -257,20 +247,19 @@ class BaseSourceResolver(BaseResolver):
     def validate_args(self, source_name: str, table_name: str):
         if not isinstance(source_name, str):
             raise CompilationException(
-                f'The source name (first) argument to source() must be a '
-                f'string, got {type(source_name)}'
+                f"The source name (first) argument to source() must be a "
+                f"string, got {type(source_name)}"
             )
         if not isinstance(table_name, str):
             raise CompilationException(
-                f'The table name (second) argument to source() must be a '
-                f'string, got {type(table_name)}'
+                f"The table name (second) argument to source() must be a "
+                f"string, got {type(table_name)}"
             )
 
     def __call__(self, *args: str) -> RelationProxy:
         if len(args) != 2:
             raise_compiler_error(
-                f"source() takes exactly two arguments ({len(args)} given)",
-                self.model
+                f"source() takes exactly two arguments ({len(args)} given)", self.model
             )
         self.validate_args(args[0], args[1])
         return self.resolve(args[0], args[1])
@@ -288,14 +277,15 @@ class ParseConfigObject(Config):
         self.context_config = context_config
 
     def _transform_config(self, config):
-        for oldkey in ('pre_hook', 'post_hook'):
+        for oldkey in ("pre_hook", "post_hook"):
             if oldkey in config:
-                newkey = oldkey.replace('_', '-')
+                newkey = oldkey.replace("_", "-")
                 if newkey in config:
                     raise_compiler_error(
-                        'Invalid config, has conflicting keys "{}" and "{}"'
-                        .format(oldkey, newkey),
-                        self.model
+                        'Invalid config, has conflicting keys "{}" and "{}"'.format(
+                            oldkey, newkey
+                        ),
+                        self.model,
                     )
                 config[newkey] = config.pop(oldkey)
         return config
@@ -306,29 +296,25 @@ class ParseConfigObject(Config):
         elif len(args) == 0 and len(kwargs) > 0:
             opts = kwargs
         else:
-            raise_compiler_error(
-                "Invalid inline model config",
-                self.model)
+            raise_compiler_error("Invalid inline model config", self.model)
 
         opts = self._transform_config(opts)
 
         # it's ok to have a parse context with no context config, but you must
         # not call it!
         if self.context_config is None:
-            raise RuntimeException(
-                'At parse time, did not receive a context config'
-            )
+            raise RuntimeException("At parse time, did not receive a context config")
         self.context_config.add_config_call(opts)
-        return ''
+        return ""
 
     def set(self, name, value):
         return self.__call__({name: value})
 
     def require(self, name, validator=None):
-        return ''
+        return ""
 
     def get(self, name, default=None, validator=None):
-        return ''
+        return ""
 
     def persist_relation_docs(self) -> bool:
         return False
@@ -338,14 +324,12 @@ class ParseConfigObject(Config):
 
 
 class RuntimeConfigObject(Config):
-    def __init__(
-        self, model, context_config: Optional[ContextConfig] = None
-    ):
+    def __init__(self, model, context_config: Optional[ContextConfig] = None):
         self.model = model
         # we never use or get a config, only the parser cares
 
     def __call__(self, *args, **kwargs):
-        return ''
+        return ""
 
     def set(self, name, value):
         return self.__call__({name: value})
@@ -355,7 +339,7 @@ class RuntimeConfigObject(Config):
 
     def _lookup(self, name, default=_MISSING):
         # if this is a macro, there might be no `model.config`.
-        if not hasattr(self.model, 'config'):
+        if not hasattr(self.model, "config"):
             result = default
         else:
             result = self.model.config.get(name, default)
@@ -380,22 +364,24 @@ class RuntimeConfigObject(Config):
         return to_return
 
     def persist_relation_docs(self) -> bool:
-        persist_docs = self.get('persist_docs', default={})
+        persist_docs = self.get("persist_docs", default={})
         if not isinstance(persist_docs, dict):
             raise_compiler_error(
                 f"Invalid value provided for 'persist_docs'. Expected dict "
-                f"but received {type(persist_docs)}")
+                f"but received {type(persist_docs)}"
+            )
 
-        return persist_docs.get('relation', False)
+        return persist_docs.get("relation", False)
 
     def persist_column_docs(self) -> bool:
-        persist_docs = self.get('persist_docs', default={})
+        persist_docs = self.get("persist_docs", default={})
         if not isinstance(persist_docs, dict):
             raise_compiler_error(
                 f"Invalid value provided for 'persist_docs'. Expected dict "
-                f"but received {type(persist_docs)}")
+                f"but received {type(persist_docs)}"
+            )
 
-        return persist_docs.get('columns', False)
+        return persist_docs.get("columns", False)
 
 
 # `adapter` implementations
@@ -405,8 +391,7 @@ class ParseDatabaseWrapper(BaseDatabaseWrapper):
     """
 
     def __getattr__(self, name):
-        override = (name in self._adapter._available_ and
-                    name in self._adapter._parse_replacements_)
+        override = name in self._adapter._available_ and name in self._adapter._parse_replacements_
 
         if override:
             return self._adapter._parse_replacements_[name]
@@ -414,9 +399,7 @@ class ParseDatabaseWrapper(BaseDatabaseWrapper):
             return getattr(self._adapter, name)
         else:
             raise AttributeError(
-                "'{}' object has no attribute '{}'".format(
-                    self.__class__.__name__, name
-                )
+                "'{}' object has no attribute '{}'".format(self.__class__.__name__, name)
             )
 
 
@@ -430,17 +413,13 @@ class RuntimeDatabaseWrapper(BaseDatabaseWrapper):
             return getattr(self._adapter, name)
         else:
             raise AttributeError(
-                "'{}' object has no attribute '{}'".format(
-                    self.__class__.__name__, name
-                )
+                "'{}' object has no attribute '{}'".format(self.__class__.__name__, name)
             )
 
 
 # `ref` implementations
 class ParseRefResolver(BaseRefResolver):
-    def resolve(
-        self, name: str, package: Optional[str] = None
-    ) -> RelationProxy:
+    def resolve(self, name: str, package: Optional[str] = None) -> RelationProxy:
         self.model.refs.append(self._repack_args(name, package))
 
         return self.Relation.create_from(self.config, self.model)
@@ -450,9 +429,7 @@ ResolveRef = Union[Disabled, ManifestNode]
 
 
 class RuntimeRefResolver(BaseRefResolver):
-    def resolve(
-        self, target_name: str, target_package: Optional[str] = None
-    ) -> RelationProxy:
+    def resolve(self, target_name: str, target_package: Optional[str] = None) -> RelationProxy:
         target_model = self.manifest.resolve_ref(
             target_name,
             target_package,
@@ -470,22 +447,15 @@ class RuntimeRefResolver(BaseRefResolver):
         self.validate(target_model, target_name, target_package)
         return self.create_relation(target_model, target_name)
 
-    def create_relation(
-        self, target_model: ManifestNode, name: str
-    ) -> RelationProxy:
+    def create_relation(self, target_model: ManifestNode, name: str) -> RelationProxy:
         if target_model.is_ephemeral_model:
             self.model.set_cte(target_model.unique_id, None)
-            return self.Relation.create_ephemeral_from_node(
-                self.config, target_model
-            )
+            return self.Relation.create_ephemeral_from_node(self.config, target_model)
         else:
             return self.Relation.create_from(self.config, target_model)
 
     def validate(
-        self,
-        resolved: ManifestNode,
-        target_name: str,
-        target_package: Optional[str]
+        self, resolved: ManifestNode, target_name: str, target_package: Optional[str]
     ) -> None:
         if resolved.unique_id not in self.model.depends_on.nodes:
             args = self._repack_args(target_name, target_package)
@@ -501,16 +471,15 @@ class OperationRefResolver(RuntimeRefResolver):
     ) -> None:
         pass
 
-    def create_relation(
-        self, target_model: ManifestNode, name: str
-    ) -> RelationProxy:
+    def create_relation(self, target_model: ManifestNode, name: str) -> RelationProxy:
         if target_model.is_ephemeral_model:
             # In operations, we can't ref() ephemeral nodes, because
             # ParsedMacros do not support set_cte
             raise_compiler_error(
-                'Operations can not ref() ephemeral nodes, but {} is ephemeral'
-                .format(target_model.name),
-                self.model
+                "Operations can not ref() ephemeral nodes, but {} is ephemeral".format(
+                    target_model.name
+                ),
+                self.model,
             )
         else:
             return super().create_relation(target_model, name)
@@ -561,10 +530,7 @@ class ModelConfiguredVar(Var):
         if package_name != self._config.project_name:
             if package_name not in dependencies:
                 # I don't think this is actually reachable
-                raise_compiler_error(
-                    f'Node package named {package_name} not found!',
-                    self._node
-                )
+                raise_compiler_error(f"Node package named {package_name} not found!", self._node)
             yield dependencies[package_name]
         yield self._config
 
@@ -635,7 +601,7 @@ class OperationProvider(RuntimeProvider):
     ref = OperationRefResolver
 
 
-T = TypeVar('T')
+T = TypeVar("T")
 
 
 # Base context collection, used for parsing configs.
@@ -650,9 +616,7 @@ class ProviderContext(ManifestContext):
         context_config: Optional[ContextConfig],
     ) -> None:
         if provider is None:
-            raise InternalException(
-                f"Invalid provider given to context: {provider}"
-            )
+            raise InternalException(f"Invalid provider given to context: {provider}")
         # mypy appeasement - we know it'll be a RuntimeConfig
         self.config: RuntimeConfig
         self.model: Union[ParsedMacro, ManifestNode] = model
@@ -662,16 +626,12 @@ class ProviderContext(ManifestContext):
         self.provider: Provider = provider
         self.adapter = get_adapter(self.config)
         # The macro namespace is used in creating the DatabaseWrapper
-        self.db_wrapper = self.provider.DatabaseWrapper(
-            self.adapter, self.namespace
-        )
+        self.db_wrapper = self.provider.DatabaseWrapper(self.adapter, self.namespace)
 
     # This overrides the method in ManifestContext, and provides
     # a model, which the ManifestContext builder does not
     def _get_namespace_builder(self):
-        internal_packages = get_adapter_package_names(
-            self.config.credentials.type
-        )
+        internal_packages = get_adapter_package_names(self.config.credentials.type)
         return MacroNamespaceBuilder(
             self.config.project_name,
             self.search_package,
@@ -690,19 +650,19 @@ class ProviderContext(ManifestContext):
 
     @contextmember
     def store_result(
-        self, name: str,
-        response: Any,
-        agate_table: Optional[agate.Table] = None
+        self, name: str, response: Any, agate_table: Optional[agate.Table] = None
     ) -> str:
         if agate_table is None:
             agate_table = agate_helper.empty_table()
 
-        self.sql_results[name] = AttrDict({
-            'response': response,
-            'data': agate_helper.as_matrix(agate_table),
-            'table': agate_table
-        })
-        return ''
+        self.sql_results[name] = AttrDict(
+            {
+                "response": response,
+                "data": agate_helper.as_matrix(agate_table),
+                "table": agate_table,
+            }
+        )
+        return ""
 
     @contextmember
     def store_raw_result(
@@ -711,10 +671,9 @@ class ProviderContext(ManifestContext):
         message=Optional[str],
         code=Optional[str],
         rows_affected=Optional[str],
-        agate_table: Optional[agate.Table] = None
+        agate_table: Optional[agate.Table] = None,
     ) -> str:
-        response = AdapterResponse(
-            _message=message, code=code, rows_affected=rows_affected)
+        response = AdapterResponse(_message=message, code=code, rows_affected=rows_affected)
         return self.store_result(name, response, agate_table)
 
     @contextproperty
@@ -727,25 +686,24 @@ class ProviderContext(ManifestContext):
                     elif value == arg:
                         return
                 raise ValidationException(
-                    'Expected value "{}" to be one of {}'
-                    .format(value, ','.join(map(str, args))))
+                    'Expected value "{}" to be one of {}'.format(value, ",".join(map(str, args)))
+                )
+
             return inner
 
-        return AttrDict({
-            'any': validate_any,
-        })
+        return AttrDict(
+            {
+                "any": validate_any,
+            }
+        )
 
     @contextmember
     def write(self, payload: str) -> str:
         # macros/source defs aren't 'writeable'.
         if isinstance(self.model, (ParsedMacro, ParsedSourceDefinition)):
-            raise_compiler_error(
-                'cannot "write" macros or sources'
-            )
-        self.model.build_path = self.model.write_node(
-            self.config.target_path, 'run', payload
-        )
-        return ''
+            raise_compiler_error('cannot "write" macros or sources')
+        self.model.build_path = self.model.write_node(self.config.target_path, "run", payload)
+        return ""
 
     @contextmember
     def render(self, string: str) -> str:
@@ -758,20 +716,15 @@ class ProviderContext(ManifestContext):
         try:
             return func(*args, **kwargs)
         except Exception:
-            raise_compiler_error(
-                message_if_exception, self.model
-            )
+            raise_compiler_error(message_if_exception, self.model)
 
     @contextmember
     def load_agate_table(self) -> agate.Table:
         if not isinstance(self.model, (ParsedSeedNode, CompiledSeedNode)):
             raise_compiler_error(
-                'can only load_agate_table for seeds (got a {})'
-                .format(self.model.resource_type)
+                "can only load_agate_table for seeds (got a {})".format(self.model.resource_type)
             )
-        path = os.path.join(
-            self.model.root_path, self.model.original_file_path
-        )
+        path = os.path.join(self.model.root_path, self.model.original_file_path)
         column_types = self.model.config.column_types
         try:
             table = agate_helper.from_csv(path, text_columns=column_types)
@@ -819,17 +772,13 @@ class ProviderContext(ManifestContext):
 
             select * from {{ ref('package_name', 'model_name') }}"
         """
-        return self.provider.ref(
-            self.db_wrapper, self.model, self.config, self.manifest
-        )
+        return self.provider.ref(self.db_wrapper, self.model, self.config, self.manifest)
 
     @contextproperty
     def source(self) -> Callable:
-        return self.provider.source(
-            self.db_wrapper, self.model, self.config, self.manifest
-        )
+        return self.provider.source(self.db_wrapper, self.model, self.config, self.manifest)
 
-    @contextproperty('config')
+    @contextproperty("config")
     def ctx_config(self) -> Config:
         """The `config` variable exists to handle end-user configuration for
         custom materializations. Configs like `unique_key` can be implemented
@@ -1001,7 +950,7 @@ class ProviderContext(ManifestContext):
             node=self.model,
         )
 
-    @contextproperty('adapter')
+    @contextproperty("adapter")
     def ctx_adapter(self) -> BaseDatabaseWrapper:
         """`adapter` is a wrapper around the internal database adapter used by
         dbt. It allows users to make calls to the database in their dbt models.
@@ -1013,8 +962,8 @@ class ProviderContext(ManifestContext):
     @contextproperty
     def api(self) -> Dict[str, Any]:
         return {
-            'Relation': self.db_wrapper.Relation,
-            'Column': self.adapter.Column,
+            "Relation": self.db_wrapper.Relation,
+            "Column": self.adapter.Column,
         }
 
     @contextproperty
@@ -1132,7 +1081,7 @@ class ProviderContext(ManifestContext):
         """  # noqa
         return self.manifest.flat_graph
 
-    @contextproperty('model')
+    @contextproperty("model")
     def ctx_model(self) -> Dict[str, Any]:
         return self.model.to_dict(omit_none=True)
 
@@ -1154,15 +1103,13 @@ class ProviderContext(ManifestContext):
 
     @contextmember
     def adapter_macro(self, name: str, *args, **kwargs):
-        """This was deprecated in v0.18 in favor of adapter.dispatch
-        """
+        """This was deprecated in v0.18 in favor of adapter.dispatch"""
         msg = (
             'The "adapter_macro" macro has been deprecated. Instead, use '
-            'the `adapter.dispatch` method to find a macro and call the '
-            'result.  For more information, see: '
-            'https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch)'
-            ' adapter_macro was called for: {macro_name}'
-            .format(macro_name=name)
+            "the `adapter.dispatch` method to find a macro and call the "
+            "result.  For more information, see: "
+            "https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch)"
+            " adapter_macro was called for: {macro_name}".format(macro_name=name)
         )
         raise CompilationException(msg)
 
@@ -1184,25 +1131,37 @@ class ProviderContext(ManifestContext):
         if return_value is not None:
             # Save the env_var value in the manifest and the var name in the source_file.
             # If this is compiling, do not save because it's irrelevant to parsing.
-            if self.model and not hasattr(self.model, 'compiled'):
+            if self.model and not hasattr(self.model, "compiled"):
                 self.manifest.env_vars[var] = return_value
-                source_file = self.manifest.files[self.model.file_id]
-                # Schema files should never get here
-                if source_file.parse_file_type != 'schema':
-                    source_file.env_vars.append(var)
+                # hooks come from dbt_project.yml which doesn't have a real file_id
+                if self.model.file_id in self.manifest.files:
+                    source_file = self.manifest.files[self.model.file_id]
+                    # Schema files should never get here
+                    if source_file.parse_file_type != "schema":
+                        # TODO CT-211
+                        source_file.env_vars.append(var)  # type: ignore[union-attr]
             return return_value
         else:
             msg = f"Env var required but not provided: '{var}'"
             raise_parsing_error(msg)
 
+    @contextproperty
+    def selected_resources(self) -> List[str]:
+        """The `selected_resources` variable contains a list of the resources
+        selected based on the parameters provided to the dbt command.
+        Currently, is not populated for the command `run-operation` that
+        doesn't support `--select`.
+        """
+        return selected_resources.SELECTED_RESOURCES
+
 
 class MacroContext(ProviderContext):
     """Internally, macros can be executed like nodes, with some restrictions:
 
-     - they don't have have all values available that nodes do:
-        - 'this', 'pre_hooks', 'post_hooks', and 'sql' are missing
-        - 'schema' does not use any 'model' information
-     - they can't be configured with config() directives
+    - they don't have all values available that nodes do:
+       - 'this', 'pre_hooks', 'post_hooks', and 'sql' are missing
+       - 'schema' does not use any 'model' information
+    - they can't be configured with config() directives
     """
 
     def __init__(
@@ -1229,35 +1188,34 @@ class ModelContext(ProviderContext):
     def pre_hooks(self) -> List[Dict[str, Any]]:
         if self.model.resource_type in [NodeType.Source, NodeType.Test]:
             return []
+        # TODO CT-211
         return [
-            h.to_dict(omit_none=True) for h in self.model.config.pre_hook
+            h.to_dict(omit_none=True) for h in self.model.config.pre_hook  # type: ignore[union-attr] # noqa
         ]
 
     @contextproperty
     def post_hooks(self) -> List[Dict[str, Any]]:
         if self.model.resource_type in [NodeType.Source, NodeType.Test]:
             return []
+        # TODO CT-211
         return [
-            h.to_dict(omit_none=True) for h in self.model.config.post_hook
+            h.to_dict(omit_none=True) for h in self.model.config.post_hook  # type: ignore[union-attr] # noqa
         ]
 
     @contextproperty
     def sql(self) -> Optional[str]:
-        if getattr(self.model, 'extra_ctes_injected', None):
-            return self.model.compiled_sql
+        if getattr(self.model, "extra_ctes_injected", None):
+            # TODO CT-211
+            return self.model.compiled_sql  # type: ignore[union-attr]
         return None
 
     @contextproperty
     def database(self) -> str:
-        return getattr(
-            self.model, 'database', self.config.credentials.database
-        )
+        return getattr(self.model, "database", self.config.credentials.database)
 
     @contextproperty
     def schema(self) -> str:
-        return getattr(
-            self.model, 'schema', self.config.credentials.schema
-        )
+        return getattr(self.model, "schema", self.config.credentials.schema)
 
     @contextproperty
     def this(self) -> Optional[RelationProxy]:
@@ -1305,9 +1263,7 @@ def generate_parser_model_context(
     # The __init__ method of ModelContext also initializes
     # a ManifestContext object which creates a MacroNamespaceBuilder
     # which adds every macro in the Manifest.
-    ctx = ModelContext(
-        model, config, manifest, ParseProvider(), context_config
-    )
+    ctx = ModelContext(model, config, manifest, ParseProvider(), context_config)
     # The 'to_dict' method in ManifestContext moves all of the macro names
     # in the macro 'namespace' up to top level keys
     return ctx.to_dict()
@@ -1318,9 +1274,7 @@ def generate_generate_name_macro_context(
     config: RuntimeConfig,
     manifest: Manifest,
 ) -> Dict[str, Any]:
-    ctx = MacroContext(
-        macro, config, manifest, GenerateNameProvider(), None
-    )
+    ctx = MacroContext(macro, config, manifest, GenerateNameProvider(), None)
     return ctx.to_dict()
 
 
@@ -1329,9 +1283,7 @@ def generate_runtime_model_context(
     config: RuntimeConfig,
     manifest: Manifest,
 ) -> Dict[str, Any]:
-    ctx = ModelContext(
-        model, config, manifest, RuntimeProvider(), None
-    )
+    ctx = ModelContext(model, config, manifest, RuntimeProvider(), None)
     return ctx.to_dict()
 
 
@@ -1341,9 +1293,7 @@ def generate_runtime_macro_context(
     manifest: Manifest,
     package_name: Optional[str],
 ) -> Dict[str, Any]:
-    ctx = MacroContext(
-        macro, config, manifest, OperationProvider(), package_name
-    )
+    ctx = MacroContext(macro, config, manifest, OperationProvider(), package_name)
     return ctx.to_dict()
 
 
@@ -1352,18 +1302,17 @@ class ExposureRefResolver(BaseResolver):
         if len(args) not in (1, 2):
             ref_invalid_args(self.model, args)
         self.model.refs.append(list(args))
-        return ''
+        return ""
 
 
 class ExposureSourceResolver(BaseResolver):
     def __call__(self, *args) -> str:
         if len(args) != 2:
             raise_compiler_error(
-                f"source() takes exactly two arguments ({len(args)} given)",
-                self.model
+                f"source() takes exactly two arguments ({len(args)} given)", self.model
             )
         self.model.sources.append(list(args))
-        return ''
+        return ""
 
 
 def generate_parse_exposure(
@@ -1374,18 +1323,18 @@ def generate_parse_exposure(
 ) -> Dict[str, Any]:
     project = config.load_dependencies()[package_name]
     return {
-        'ref': ExposureRefResolver(
+        "ref": ExposureRefResolver(
             None,
             exposure,
             project,
             manifest,
         ),
-        'source': ExposureSourceResolver(
+        "source": ExposureSourceResolver(
             None,
             exposure,
             project,
             manifest,
-        )
+        ),
     }
 
 
@@ -1400,13 +1349,13 @@ class MetricRefResolver(BaseResolver):
             ref_invalid_args(self.model, args)
         self.validate_args(name, package)
         self.model.refs.append(list(args))
-        return ''
+        return ""
 
     def validate_args(self, name, package):
         if not isinstance(name, str):
             raise ParsingException(
-                f'In a metrics section in {self.model.original_file_path} '
-                f'the name argument to ref() must be a string'
+                f"In a metrics section in {self.model.original_file_path} "
+                f"the name argument to ref() must be a string"
             )
 
 
@@ -1418,7 +1367,7 @@ def generate_parse_metrics(
 ) -> Dict[str, Any]:
     project = config.load_dependencies()[package_name]
     return {
-        'ref': MetricRefResolver(
+        "ref": MetricRefResolver(
             None,
             metric,
             project,
@@ -1448,9 +1397,7 @@ class TestContext(ProviderContext):
         self._build_test_namespace()
         # We need to rebuild this because it's already been built by
         # the ProviderContext with the wrong namespace.
-        self.db_wrapper = self.provider.DatabaseWrapper(
-            self.adapter, self.namespace
-        )
+        self.db_wrapper = self.provider.DatabaseWrapper(self.adapter, self.namespace)
 
     def _build_namespace(self):
         return {}
@@ -1463,7 +1410,7 @@ class TestContext(ProviderContext):
         depends_on_macros = []
         # all generic tests use a macro named 'get_where_subquery' to wrap 'model' arg
         # see generic_test_builders.build_model_str
-        get_where_subquery = self.macro_resolver.macros_by_name.get('get_where_subquery')
+        get_where_subquery = self.macro_resolver.macros_by_name.get("get_where_subquery")
         if get_where_subquery:
             depends_on_macros.append(get_where_subquery.unique_id)
         if self.model.depends_on and self.model.depends_on.macros:
@@ -1475,8 +1422,7 @@ class TestContext(ProviderContext):
                 depends_on_macros.extend(lookup_macro.depends_on.macros)
 
         macro_namespace = TestMacroNamespace(
-            self.macro_resolver, self._ctx, self.model, self.thread_ctx,
-            depends_on_macros
+            self.macro_resolver, self._ctx, self.model, self.thread_ctx, depends_on_macros
         )
         self.namespace = macro_namespace
 
@@ -1495,10 +1441,13 @@ class TestContext(ProviderContext):
             if self.model:
                 self.manifest.env_vars[var] = return_value
                 # the "model" should only be test nodes, but just in case, check
-                if self.model.resource_type == NodeType.Test and self.model.file_key_name:
+                # TODO CT-211
+                if self.model.resource_type == NodeType.Test and self.model.file_key_name:  # type: ignore[union-attr] # noqa
                     source_file = self.manifest.files[self.model.file_id]
-                    (yaml_key, name) = self.model.file_key_name.split('.')
-                    source_file.add_env_var(var, yaml_key, name)
+                    # TODO CT-211
+                    (yaml_key, name) = self.model.file_key_name.split(".")  # type: ignore[union-attr] # noqa
+                    # TODO CT-211
+                    source_file.add_env_var(var, yaml_key, name)  # type: ignore[union-attr]
             return return_value
         else:
             msg = f"Env var required but not provided: '{var}'"
@@ -1510,12 +1459,9 @@ def generate_test_context(
     config: RuntimeConfig,
     manifest: Manifest,
     context_config: ContextConfig,
-    macro_resolver: MacroResolver
+    macro_resolver: MacroResolver,
 ) -> Dict[str, Any]:
-    ctx = TestContext(
-        model, config, manifest, ParseProvider(), context_config,
-        macro_resolver
-    )
+    ctx = TestContext(model, config, manifest, ParseProvider(), context_config, macro_resolver)
     # The 'to_dict' method in ManifestContext moves all of the macro names
     # in the macro 'namespace' up to top level keys
     return ctx.to_dict()

core/dbt/context/secret.py

@@ -4,6 +4,10 @@ from typing import Any, Dict, Optional
 from .base import BaseContext, contextmember
 
 from dbt.exceptions import raise_parsing_error
+from dbt.logger import SECRET_ENV_PREFIX
+
+
+SECRET_PLACEHOLDER = "$$$DBT_SECRET_START$$${}$$$DBT_SECRET_END$$$"
 
 
 class SecretContext(BaseContext):
@@ -17,17 +21,29 @@ class SecretContext(BaseContext):
 
         If the default is None, raise an exception for an undefined variable.
 
-        In this context *only*, env_var will return the actual values of
-        env vars prefixed with DBT_ENV_SECRET_
+        In this context *only*, env_var will accept env vars prefixed with DBT_ENV_SECRET_.
+        It will return the name of the secret env var, wrapped in 'start' and 'end' identifiers.
+        The actual value will be subbed in later in SecretRenderer.render_value()
         """
         return_value = None
-        if var in os.environ:
+
+        # if this is a 'secret' env var, just return the name of the env var
+        # instead of rendering the actual value here, to avoid any risk of
+        # Jinja manipulation. it will be subbed out later, in SecretRenderer.render_value
+        if var in os.environ and var.startswith(SECRET_ENV_PREFIX):
+            return SECRET_PLACEHOLDER.format(var)
+
+        elif var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
             return_value = default
 
         if return_value is not None:
-            self.env_vars[var] = return_value
+            # store env vars in the internal manifest to power partial parsing
+            # if it's a 'secret' env var, we shouldn't even get here
+            # but just to be safe — don't save secrets
+            if not var.startswith(SECRET_ENV_PREFIX):
+                self.env_vars[var] = return_value
             return return_value
         else:
             msg = f"Env var required but not provided: '{var}'"

core/dbt/context/target.py

@@ -2,9 +2,7 @@ from typing import Any, Dict
 
 from dbt.contracts.connection import HasCredentials
 
-from dbt.context.base import (
-    BaseContext, contextproperty
-)
+from dbt.context.base import BaseContext, contextproperty
 
 
 class TargetContext(BaseContext):
@@ -78,8 +76,6 @@ class TargetContext(BaseContext):
         return self.config.to_target_dict()
 
 
-def generate_target_context(
-    config: HasCredentials, cli_vars: Dict[str, Any]
-) -> Dict[str, Any]:
+def generate_target_context(config: HasCredentials, cli_vars: Dict[str, Any]) -> Dict[str, Any]:
     ctx = TargetContext(config, cli_vars)
     return ctx.to_dict()

core/dbt/contracts/README.md

@@ -0,0 +1 @@
+# Contracts README

core/dbt/contracts/connection.py

@@ -3,7 +3,14 @@ import itertools
 import hashlib
 from dataclasses import dataclass, field
 from typing import (
-    Any, ClassVar, Dict, Tuple, Iterable, Optional, List, Callable,
+    Any,
+    ClassVar,
+    Dict,
+    Tuple,
+    Iterable,
+    Optional,
+    List,
+    Callable,
 )
 from dbt.exceptions import InternalException
 from dbt.utils import translate_aliases
@@ -11,18 +18,22 @@ from dbt.events.functions import fire_event
 from dbt.events.types import NewConnectionOpening
 from typing_extensions import Protocol
 from dbt.dataclass_schema import (
-    dbtClassMixin, StrEnum, ExtensibleDbtClassMixin, HyphenatedDbtClassMixin,
-    ValidatedStringMixin, register_pattern
+    dbtClassMixin,
+    StrEnum,
+    ExtensibleDbtClassMixin,
+    HyphenatedDbtClassMixin,
+    ValidatedStringMixin,
+    register_pattern,
 )
 from dbt.contracts.util import Replaceable
 
 
 class Identifier(ValidatedStringMixin):
-    ValidationRegex = r'^[A-Za-z_][A-Za-z0-9_]+$'
+    ValidationRegex = r"^[A-Za-z_][A-Za-z0-9_]+$"
 
 
 # we need register_pattern for jsonschema validation
-register_pattern(Identifier, r'^[A-Za-z_][A-Za-z0-9_]+$')
+register_pattern(Identifier, r"^[A-Za-z_][A-Za-z0-9_]+$")
 
 
 @dataclass
@@ -36,10 +47,10 @@ class AdapterResponse(dbtClassMixin):
 
 
 class ConnectionState(StrEnum):
-    INIT = 'init'
-    OPEN = 'open'
-    CLOSED = 'closed'
-    FAIL = 'fail'
+    INIT = "init"
+    OPEN = "open"
+    CLOSED = "closed"
+    FAIL = "fail"
 
 
 @dataclass(init=False)
@@ -83,8 +94,7 @@ class Connection(ExtensibleDbtClassMixin, Replaceable):
                 self._handle.resolve(self)
             except RecursionError as exc:
                 raise InternalException(
-                    "A connection's open() method attempted to read the "
-                    "handle value"
+                    "A connection's open() method attempted to read the " "handle value"
                 ) from exc
         return self._handle
 
@@ -94,7 +104,7 @@ class Connection(ExtensibleDbtClassMixin, Replaceable):
 
 
 class LazyHandle:
-    """Opener must be a callable that takes a Connection object and opens the
+    """The opener must be a callable that takes a Connection object and opens the
     connection, updating the handle on the Connection.
     """
 
@@ -111,20 +121,14 @@ class LazyHandle:
 # for why we have type: ignore. Maybe someday dataclasses + abstract classes
 # will work.
 @dataclass  # type: ignore
-class Credentials(
-    ExtensibleDbtClassMixin,
-    Replaceable,
-    metaclass=abc.ABCMeta
-):
+class Credentials(ExtensibleDbtClassMixin, Replaceable, metaclass=abc.ABCMeta):
     database: str
     schema: str
     _ALIASES: ClassVar[Dict[str, str]] = field(default={}, init=False)
 
     @abc.abstractproperty
     def type(self) -> str:
-        raise NotImplementedError(
-            'type not implemented for base credentials class'
-        )
+        raise NotImplementedError("type not implemented for base credentials class")
 
     @property
     def unique_field(self) -> str:
@@ -132,25 +136,18 @@ class Credentials(
         Return the field from Credentials that can uniquely identify
         one team/organization using this adapter
         """
-        raise NotImplementedError(
-            'unique_field not implemented for base credentials class'
-        )
+        raise NotImplementedError("unique_field not implemented for base credentials class")
 
     def hashed_unique_field(self) -> str:
-        return hashlib.md5(self.unique_field.encode('utf-8')).hexdigest()
+        return hashlib.md5(self.unique_field.encode("utf-8")).hexdigest()
 
-    def connection_info(
-        self, *, with_aliases: bool = False
-    ) -> Iterable[Tuple[str, Any]]:
-        """Return an ordered iterator of key/value pairs for pretty-printing.
-        """
+    def connection_info(self, *, with_aliases: bool = False) -> Iterable[Tuple[str, Any]]:
+        """Return an ordered iterator of key/value pairs for pretty-printing."""
         as_dict = self.to_dict(omit_none=False)
         connection_keys = set(self._connection_keys())
         aliases: List[str] = []
         if with_aliases:
-            aliases = [
-                k for k, v in self._ALIASES.items() if v in connection_keys
-            ]
+            aliases = [k for k, v in self._ALIASES.items() if v in connection_keys]
         for key in itertools.chain(self._connection_keys(), aliases):
             if key in as_dict:
                 yield key, as_dict[key]
@@ -166,19 +163,19 @@ class Credentials(
         return data
 
     @classmethod
-    def translate_aliases(
-        cls, kwargs: Dict[str, Any], recurse: bool = False
-    ) -> Dict[str, Any]:
+    def translate_aliases(cls, kwargs: Dict[str, Any], recurse: bool = False) -> Dict[str, Any]:
         return translate_aliases(kwargs, cls._ALIASES, recurse)
 
     def __post_serialize__(self, dct):
         # no super() -- do we need it?
         if self._ALIASES:
-            dct.update({
-                new_name: dct[canonical_name]
-                for new_name, canonical_name in self._ALIASES.items()
-                if canonical_name in dct
-            })
+            dct.update(
+                {
+                    new_name: dct[canonical_name]
+                    for new_name, canonical_name in self._ALIASES.items()
+                    if canonical_name in dct
+                }
+            )
         return dct
 
 
@@ -197,10 +194,10 @@ class HasCredentials(Protocol):
     threads: int
 
     def to_target_dict(self):
-        raise NotImplementedError('to_target_dict not implemented')
+        raise NotImplementedError("to_target_dict not implemented")
 
 
-DEFAULT_QUERY_COMMENT = '''
+DEFAULT_QUERY_COMMENT = """
 {%- set comment_dict = {} -%}
 {%- do comment_dict.update(
     app='dbt',
@@ -217,7 +214,7 @@ DEFAULT_QUERY_COMMENT = '''
   {%- do comment_dict.update(connection_name=connection_name) -%}
 {%- endif -%}
 {{ return(tojson(comment_dict)) }}
-'''
+"""
 
 
 @dataclass

core/dbt/contracts/files.py

@@ -10,33 +10,33 @@ from .util import SourceKey
 
 
 MAXIMUM_SEED_SIZE = 1 * 1024 * 1024
-MAXIMUM_SEED_SIZE_NAME = '1MB'
+MAXIMUM_SEED_SIZE_NAME = "1MB"
 
 
 class ParseFileType(StrEnum):
-    Macro = 'macro'
-    Model = 'model'
-    Snapshot = 'snapshot'
-    Analysis = 'analysis'
-    SingularTest = 'singular_test'
-    GenericTest = 'generic_test'
-    Seed = 'seed'
-    Documentation = 'docs'
-    Schema = 'schema'
-    Hook = 'hook'   # not a real filetype, from dbt_project.yml
+    Macro = "macro"
+    Model = "model"
+    Snapshot = "snapshot"
+    Analysis = "analysis"
+    SingularTest = "singular_test"
+    GenericTest = "generic_test"
+    Seed = "seed"
+    Documentation = "docs"
+    Schema = "schema"
+    Hook = "hook"  # not a real filetype, from dbt_project.yml
 
 
 parse_file_type_to_parser = {
-    ParseFileType.Macro: 'MacroParser',
-    ParseFileType.Model: 'ModelParser',
-    ParseFileType.Snapshot: 'SnapshotParser',
-    ParseFileType.Analysis: 'AnalysisParser',
-    ParseFileType.SingularTest: 'SingularTestParser',
-    ParseFileType.GenericTest: 'GenericTestParser',
-    ParseFileType.Seed: 'SeedParser',
-    ParseFileType.Documentation: 'DocumentationParser',
-    ParseFileType.Schema: 'SchemaParser',
-    ParseFileType.Hook: 'HookParser',
+    ParseFileType.Macro: "MacroParser",
+    ParseFileType.Model: "ModelParser",
+    ParseFileType.Snapshot: "SnapshotParser",
+    ParseFileType.Analysis: "AnalysisParser",
+    ParseFileType.SingularTest: "SingularTestParser",
+    ParseFileType.GenericTest: "GenericTestParser",
+    ParseFileType.Seed: "SeedParser",
+    ParseFileType.Documentation: "DocumentationParser",
+    ParseFileType.Schema: "SchemaParser",
+    ParseFileType.Hook: "HookParser",
 }
 
 
@@ -55,9 +55,7 @@ class FilePath(dbtClassMixin):
     @property
     def full_path(self) -> str:
         # useful for symlink preservation
-        return os.path.join(
-            self.project_root, self.searched_path, self.relative_path
-        )
+        return os.path.join(self.project_root, self.searched_path, self.relative_path)
 
     @property
     def absolute_path(self) -> str:
@@ -67,13 +65,10 @@ class FilePath(dbtClassMixin):
     def original_file_path(self) -> str:
         # this is mostly used for reporting errors. It doesn't show the project
         # name, should it?
-        return os.path.join(
-            self.searched_path, self.relative_path
-        )
+        return os.path.join(self.searched_path, self.relative_path)
 
     def seed_too_large(self) -> bool:
-        """Return whether the file this represents is over the seed size limit
-        """
+        """Return whether the file this represents is over the seed size limit"""
         return os.stat(self.full_path).st_size > MAXIMUM_SEED_SIZE
 
 
@@ -84,35 +79,35 @@ class FileHash(dbtClassMixin):
 
     @classmethod
     def empty(cls):
-        return FileHash(name='none', checksum='')
+        return FileHash(name="none", checksum="")
 
     @classmethod
     def path(cls, path: str):
-        return FileHash(name='path', checksum=path)
+        return FileHash(name="path", checksum=path)
 
     def __eq__(self, other):
         if not isinstance(other, FileHash):
             return NotImplemented
 
-        if self.name == 'none' or self.name != other.name:
+        if self.name == "none" or self.name != other.name:
             return False
 
         return self.checksum == other.checksum
 
     def compare(self, contents: str) -> bool:
         """Compare the file contents with the given hash"""
-        if self.name == 'none':
+        if self.name == "none":
             return False
 
         return self.from_contents(contents, name=self.name) == self.checksum
 
     @classmethod
-    def from_contents(cls, contents: str, name='sha256') -> 'FileHash':
+    def from_contents(cls, contents: str, name="sha256") -> "FileHash":
         """Create a file hash from the given file contents. The hash is always
         the utf-8 encoding of the contents given, because dbt only reads files
         as utf-8.
         """
-        data = contents.encode('utf-8')
+        data = contents.encode("utf-8")
         checksum = hashlib.new(name, data).hexdigest()
         return cls(name=name, checksum=checksum)
 
@@ -121,28 +116,29 @@ class FileHash(dbtClassMixin):
 class RemoteFile(dbtClassMixin):
     @property
     def searched_path(self) -> str:
-        return 'from remote system'
+        return "from remote system"
 
     @property
     def relative_path(self) -> str:
-        return 'from remote system'
+        return "from remote system"
 
     @property
     def absolute_path(self) -> str:
-        return 'from remote system'
+        return "from remote system"
 
     @property
     def original_file_path(self):
-        return 'from remote system'
+        return "from remote system"
 
     @property
     def modification_time(self):
-        return 'from remote system'
+        return "from remote system"
 
 
 @dataclass
 class BaseSourceFile(dbtClassMixin, SerializableType):
     """Define a source file in dbt"""
+
     path: Union[FilePath, RemoteFile]  # the path information
     checksum: FileHash
     # Seems like knowing which project the file came from would be useful
@@ -157,7 +153,7 @@ class BaseSourceFile(dbtClassMixin, SerializableType):
     def file_id(self):
         if isinstance(self.path, RemoteFile):
             return None
-        return f'{self.project_name}://{self.path.original_file_path}'
+        return f"{self.project_name}://{self.path.original_file_path}"
 
     def _serialize(self):
         dct = self.to_dict()
@@ -165,7 +161,7 @@ class BaseSourceFile(dbtClassMixin, SerializableType):
 
     @classmethod
     def _deserialize(cls, dct: Dict[str, int]):
-        if dct['parse_file_type'] == 'schema':
+        if dct["parse_file_type"] == "schema":
             sf = SchemaSourceFile.from_dict(dct)
         else:
             sf = SourceFile.from_dict(dct)
@@ -180,8 +176,8 @@ class BaseSourceFile(dbtClassMixin, SerializableType):
                 del dct[key]
         # remove contents. Schema files will still have 'dict_from_yaml'
         # from the contents
-        if 'contents' in dct:
-            del dct['contents']
+        if "contents" in dct:
+            del dct["contents"]
         return dct
 
 
@@ -193,10 +189,10 @@ class SourceFile(BaseSourceFile):
     env_vars: List[str] = field(default_factory=list)
 
     @classmethod
-    def big_seed(cls, path: FilePath) -> 'SourceFile':
+    def big_seed(cls, path: FilePath) -> "SourceFile":
         """Parse seeds over the size limit with just the path"""
         self = cls(path=path, checksum=FileHash.path(path.original_file_path))
-        self.contents = ''
+        self.contents = ""
         return self
 
     def add_node(self, value):
@@ -206,7 +202,7 @@ class SourceFile(BaseSourceFile):
     # TODO: do this a different way. This remote file kludge isn't going
     # to work long term
     @classmethod
-    def remote(cls, contents: str, project_name: str) -> 'SourceFile':
+    def remote(cls, contents: str, project_name: str) -> "SourceFile":
         self = cls(
             path=RemoteFile(),
             checksum=FileHash.from_contents(contents),
@@ -255,7 +251,7 @@ class SchemaSourceFile(BaseSourceFile):
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
         # Remove partial parsing specific data
-        for key in ('pp_test_index', 'pp_dict'):
+        for key in ("pp_test_index", "pp_dict"):
             if key in dct:
                 del dct[key]
         return dct
@@ -264,8 +260,8 @@ class SchemaSourceFile(BaseSourceFile):
         self.node_patches.append(unique_id)
 
     def add_test(self, node_unique_id, test_from):
-        name = test_from['name']
-        key = test_from['key']
+        name = test_from["name"]
+        key = test_from["key"]
         if key not in self.tests:
             self.tests[key] = {}
         if name not in self.tests[key]:

core/dbt/contracts/graph/compiled.py

@@ -60,49 +60,47 @@ class CompiledNode(ParsedNode, CompiledNodeMixin):
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        if '_pre_injected_sql' in dct:
-            del dct['_pre_injected_sql']
+        if "_pre_injected_sql" in dct:
+            del dct["_pre_injected_sql"]
         return dct
 
 
 @dataclass
 class CompiledAnalysisNode(CompiledNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Analysis]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Analysis]})
 
 
 @dataclass
 class CompiledHookNode(CompiledNode):
-    resource_type: NodeType = field(
-        metadata={'restrict': [NodeType.Operation]}
-    )
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
     index: Optional[int] = None
 
 
 @dataclass
 class CompiledModelNode(CompiledNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Model]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Model]})
 
 
 # TODO: rm?
 @dataclass
 class CompiledRPCNode(CompiledNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.RPCCall]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.RPCCall]})
 
 
 @dataclass
 class CompiledSqlNode(CompiledNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.SqlOperation]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.SqlOperation]})
 
 
 @dataclass
 class CompiledSeedNode(CompiledNode):
     # keep this in sync with ParsedSeedNode!
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Seed]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Seed]})
     config: SeedConfig = field(default_factory=SeedConfig)
 
     @property
     def empty(self):
-        """ Seeds are never empty"""
+        """Seeds are never empty"""
         return False
 
     def same_body(self, other) -> bool:
@@ -111,12 +109,12 @@ class CompiledSeedNode(CompiledNode):
 
 @dataclass
 class CompiledSnapshotNode(CompiledNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
 
 
 @dataclass
 class CompiledSingularTestNode(CompiledNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
     # Was not able to make mypy happy and keep the code working. We need to
     # refactor the various configs.
     config: TestConfig = field(default_factory=TestConfig)  # type:ignore
@@ -125,7 +123,7 @@ class CompiledSingularTestNode(CompiledNode):
 @dataclass
 class CompiledGenericTestNode(CompiledNode, HasTestMetadata):
     # keep this in sync with ParsedGenericTestNode!
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
     column_name: Optional[str] = None
     file_key_name: Optional[str] = None
     # Was not able to make mypy happy and keep the code working. We need to
@@ -136,11 +134,7 @@ class CompiledGenericTestNode(CompiledNode, HasTestMetadata):
         if other is None:
             return False
 
-        return (
-            self.same_config(other) and
-            self.same_fqn(other) and
-            True
-        )
+        return self.same_config(other) and self.same_fqn(other) and True
 
 
 CompiledTestNode = Union[CompiledSingularTestNode, CompiledGenericTestNode]
@@ -188,8 +182,7 @@ def parsed_instance_for(compiled: CompiledNode) -> ParsedResource:
     cls = PARSED_TYPES.get(type(compiled))
     if cls is None:
         # how???
-        raise ValueError('invalid resource_type: {}'
-                         .format(compiled.resource_type))
+        raise ValueError("invalid resource_type: {}".format(compiled.resource_type))
 
     return cls.from_dict(compiled.to_dict(omit_none=True))
 

core/dbt/contracts/graph/manifest.py

@@ -4,29 +4,49 @@ from itertools import chain, islice
 from mashumaro import DataClassMessagePackMixin
 from multiprocessing.synchronize import Lock
 from typing import (
-    Dict, List, Optional, Union, Mapping, MutableMapping, Any, Set, Tuple,
-    TypeVar, Callable, Generic, cast, AbstractSet, ClassVar
+    Dict,
+    List,
+    Optional,
+    Union,
+    Mapping,
+    MutableMapping,
+    Any,
+    Set,
+    Tuple,
+    TypeVar,
+    Callable,
+    Generic,
+    cast,
+    AbstractSet,
+    ClassVar,
 )
 from typing_extensions import Protocol
 from uuid import UUID
 
 from dbt.contracts.graph.compiled import (
-    CompileResultNode, ManifestNode, NonSourceCompiledNode, GraphMemberNode
+    CompileResultNode,
+    ManifestNode,
+    NonSourceCompiledNode,
+    GraphMemberNode,
 )
 from dbt.contracts.graph.parsed import (
-    ParsedMacro, ParsedDocumentation,
-    ParsedSourceDefinition, ParsedExposure, ParsedMetric,
-    HasUniqueID, UnpatchedSourceDefinition, ManifestNodes
+    ParsedMacro,
+    ParsedDocumentation,
+    ParsedSourceDefinition,
+    ParsedExposure,
+    ParsedMetric,
+    HasUniqueID,
+    UnpatchedSourceDefinition,
+    ManifestNodes,
 )
 from dbt.contracts.graph.unparsed import SourcePatch
 from dbt.contracts.files import SourceFile, SchemaSourceFile, FileHash, AnySourceFile
-from dbt.contracts.util import (
-    BaseArtifactMetadata, SourceKey, ArtifactMixin, schema_version
-)
+from dbt.contracts.util import BaseArtifactMetadata, SourceKey, ArtifactMixin, schema_version
 from dbt.dataclass_schema import dbtClassMixin
 from dbt.exceptions import (
     CompilationException,
-    raise_duplicate_resource_name, raise_compiler_error,
+    raise_duplicate_resource_name,
+    raise_compiler_error,
 )
 from dbt.helper_types import PathSet
 from dbt.events.functions import fire_event
@@ -62,14 +82,14 @@ def find_unique_id_for_package(storage, key, package: Optional[PackageName]):
 
 
 class DocLookup(dbtClassMixin):
-    def __init__(self, manifest: 'Manifest'):
+    def __init__(self, manifest: "Manifest"):
         self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
         self.populate(manifest)
 
     def get_unique_id(self, key, package: Optional[PackageName]):
         return find_unique_id_for_package(self.storage, key, package)
 
-    def find(self, key, package: Optional[PackageName], manifest: 'Manifest'):
+    def find(self, key, package: Optional[PackageName], manifest: "Manifest"):
         unique_id = self.get_unique_id(key, package)
         if unique_id is not None:
             return self.perform_lookup(unique_id, manifest)
@@ -84,25 +104,23 @@ class DocLookup(dbtClassMixin):
         for doc in manifest.docs.values():
             self.add_doc(doc)
 
-    def perform_lookup(
-        self, unique_id: UniqueID, manifest
-    ) -> ParsedDocumentation:
+    def perform_lookup(self, unique_id: UniqueID, manifest) -> ParsedDocumentation:
         if unique_id not in manifest.docs:
             raise dbt.exceptions.InternalException(
-                f'Doc {unique_id} found in cache but not found in manifest'
+                f"Doc {unique_id} found in cache but not found in manifest"
             )
         return manifest.docs[unique_id]
 
 
 class SourceLookup(dbtClassMixin):
-    def __init__(self, manifest: 'Manifest'):
+    def __init__(self, manifest: "Manifest"):
         self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
         self.populate(manifest)
 
     def get_unique_id(self, search_name, package: Optional[PackageName]):
         return find_unique_id_for_package(self.storage, search_name, package)
 
-    def find(self, search_name, package: Optional[PackageName], manifest: 'Manifest'):
+    def find(self, search_name, package: Optional[PackageName], manifest: "Manifest"):
         unique_id = self.get_unique_id(search_name, package)
         if unique_id is not None:
             return self.perform_lookup(unique_id, manifest)
@@ -116,15 +134,13 @@ class SourceLookup(dbtClassMixin):
 
     def populate(self, manifest):
         for source in manifest.sources.values():
-            if hasattr(source, 'source_name'):
+            if hasattr(source, "source_name"):
                 self.add_source(source)
 
-    def perform_lookup(
-        self, unique_id: UniqueID, manifest: 'Manifest'
-    ) -> ParsedSourceDefinition:
+    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> ParsedSourceDefinition:
         if unique_id not in manifest.sources:
             raise dbt.exceptions.InternalException(
-                f'Source {unique_id} found in cache but not found in manifest'
+                f"Source {unique_id} found in cache but not found in manifest"
             )
         return manifest.sources[unique_id]
 
@@ -136,14 +152,14 @@ class RefableLookup(dbtClassMixin):
     # refables are actually unique, so the Dict[PackageName, UniqueID] will
     # only ever have exactly one value, but doing 3 dict lookups instead of 1
     # is not a big deal at all and retains consistency
-    def __init__(self, manifest: 'Manifest'):
+    def __init__(self, manifest: "Manifest"):
         self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
         self.populate(manifest)
 
     def get_unique_id(self, key, package: Optional[PackageName]):
         return find_unique_id_for_package(self.storage, key, package)
 
-    def find(self, key, package: Optional[PackageName], manifest: 'Manifest'):
+    def find(self, key, package: Optional[PackageName], manifest: "Manifest"):
         unique_id = self.get_unique_id(key, package)
         if unique_id is not None:
             return self.perform_lookup(unique_id, manifest)
@@ -159,20 +175,17 @@ class RefableLookup(dbtClassMixin):
         for node in manifest.nodes.values():
             self.add_node(node)
 
-    def perform_lookup(
-        self, unique_id: UniqueID, manifest
-    ) -> ManifestNode:
+    def perform_lookup(self, unique_id: UniqueID, manifest) -> ManifestNode:
         if unique_id not in manifest.nodes:
             raise dbt.exceptions.InternalException(
-                f'Node {unique_id} found in cache but not found in manifest'
+                f"Node {unique_id} found in cache but not found in manifest"
             )
         return manifest.nodes[unique_id]
 
 
 # This handles both models/seeds/snapshots and sources
 class DisabledLookup(dbtClassMixin):
-
-    def __init__(self, manifest: 'Manifest'):
+    def __init__(self, manifest: "Manifest"):
         self.storage: Dict[str, Dict[PackageName, List[Any]]] = {}
         self.populate(manifest)
 
@@ -226,30 +239,31 @@ def _search_packages(
 @dataclass
 class ManifestMetadata(BaseArtifactMetadata):
     """Metadata for the manifest."""
+
     dbt_schema_version: str = field(
         default_factory=lambda: str(WritableManifest.dbt_schema_version)
     )
     project_id: Optional[str] = field(
         default=None,
         metadata={
-            'description': 'A unique identifier for the project',
+            "description": "A unique identifier for the project",
         },
     )
     user_id: Optional[UUID] = field(
         default=None,
         metadata={
-            'description': 'A unique identifier for the user',
+            "description": "A unique identifier for the user",
         },
     )
     send_anonymous_usage_stats: Optional[bool] = field(
         default=None,
-        metadata=dict(description=(
-            'Whether dbt is configured to send anonymous usage statistics'
-        )),
+        metadata=dict(
+            description=("Whether dbt is configured to send anonymous usage statistics")
+        ),
     )
     adapter_type: Optional[str] = field(
         default=None,
-        metadata=dict(description='The type name of the adapter'),
+        metadata=dict(description="The type name of the adapter"),
     )
 
     def __post_init__(self):
@@ -295,7 +309,7 @@ def build_node_edges(nodes: List[ManifestNode]):
 # Build a map of children of macros and generic tests
 def build_macro_edges(nodes: List[Any]):
     forward_edges: Dict[str, List[str]] = {
-        n.unique_id: [] for n in nodes if n.unique_id.startswith('macro') or n.depends_on.macros
+        n.unique_id: [] for n in nodes if n.unique_id.startswith("macro") or n.depends_on.macros
     }
     for node in nodes:
         for unique_id in node.depends_on.macros:
@@ -346,7 +360,7 @@ class MaterializationCandidate(MacroCandidate):
     @classmethod
     def from_macro(
         cls, candidate: MacroCandidate, specificity: Specificity
-    ) -> 'MaterializationCandidate':
+    ) -> "MaterializationCandidate":
         return cls(
             locality=candidate.locality,
             macro=candidate.macro,
@@ -356,16 +370,13 @@ class MaterializationCandidate(MacroCandidate):
     def __eq__(self, other: object) -> bool:
         if not isinstance(other, MaterializationCandidate):
             return NotImplemented
-        equal = (
-            self.specificity == other.specificity and
-            self.locality == other.locality
-        )
+        equal = self.specificity == other.specificity and self.locality == other.locality
         if equal:
             raise_compiler_error(
-                'Found two materializations with the name {} (packages {} and '
-                '{}). dbt cannot resolve this ambiguity'
-                .format(self.macro.name, self.macro.package_name,
-                        other.macro.package_name)
+                "Found two materializations with the name {} (packages {} and "
+                "{}). dbt cannot resolve this ambiguity".format(
+                    self.macro.name, self.macro.package_name, other.macro.package_name
+                )
             )
 
         return equal
@@ -384,7 +395,7 @@ class MaterializationCandidate(MacroCandidate):
         return False
 
 
-M = TypeVar('M', bound=MacroCandidate)
+M = TypeVar("M", bound=MacroCandidate)
 
 
 class CandidateList(List[M]):
@@ -412,10 +423,10 @@ class Searchable(Protocol):
 
     @property
     def search_name(self) -> str:
-        raise NotImplementedError('search_name not implemented')
+        raise NotImplementedError("search_name not implemented")
 
 
-D = TypeVar('D')
+D = TypeVar("D")
 
 
 @dataclass
@@ -426,37 +437,35 @@ class Disabled(Generic[D]):
 MaybeDocumentation = Optional[ParsedDocumentation]
 
 
-MaybeParsedSource = Optional[Union[
-    ParsedSourceDefinition,
-    Disabled[ParsedSourceDefinition],
-]]
+MaybeParsedSource = Optional[
+    Union[
+        ParsedSourceDefinition,
+        Disabled[ParsedSourceDefinition],
+    ]
+]
 
 
-MaybeNonSource = Optional[Union[
-    ManifestNode,
-    Disabled[ManifestNode]
-]]
+MaybeNonSource = Optional[Union[ManifestNode, Disabled[ManifestNode]]]
 
 
-T = TypeVar('T', bound=GraphMemberNode)
+T = TypeVar("T", bound=GraphMemberNode)
 
 
 def _update_into(dest: MutableMapping[str, T], new_item: T):
     """Update dest to overwrite whatever is at dest[new_item.unique_id] with
-    new_itme. There must be an existing value to overwrite, and they two nodes
+    new_itme. There must be an existing value to overwrite, and the two nodes
     must have the same original file path.
     """
     unique_id = new_item.unique_id
     if unique_id not in dest:
         raise dbt.exceptions.RuntimeException(
-            f'got an update_{new_item.resource_type} call with an '
-            f'unrecognized {new_item.resource_type}: {new_item.unique_id}'
+            f"got an update_{new_item.resource_type} call with an "
+            f"unrecognized {new_item.resource_type}: {new_item.unique_id}"
         )
     existing = dest[unique_id]
     if new_item.original_file_path != existing.original_file_path:
         raise dbt.exceptions.RuntimeException(
-            f'cannot update a {new_item.resource_type} to have a new file '
-            f'path!'
+            f"cannot update a {new_item.resource_type} to have a new file " f"path!"
         )
     dest[unique_id] = new_item
 
@@ -480,6 +489,7 @@ class MacroMethods:
         """
         filter: Optional[Callable[[MacroCandidate], bool]] = None
         if package is not None:
+
             def filter(candidate: MacroCandidate) -> bool:
                 return package == candidate.macro.package_name
 
@@ -502,11 +512,12 @@ class MacroMethods:
             - return the `generate_{component}_name` macro from the 'dbt'
               internal project
         """
+
         def filter(candidate: MacroCandidate) -> bool:
             return candidate.locality != Locality.Imported
 
         candidates: CandidateList = self._find_macros_by_name(
-            name=f'generate_{component}_name',
+            name=f"generate_{component}_name",
             root_project_name=root_project_name,
             # filter out imported packages
             filter=filter,
@@ -517,12 +528,12 @@ class MacroMethods:
         self,
         name: str,
         root_project_name: str,
-        filter: Optional[Callable[[MacroCandidate], bool]] = None
+        filter: Optional[Callable[[MacroCandidate], bool]] = None,
     ) -> CandidateList:
-        """Find macros by their name.
-        """
+        """Find macros by their name."""
         # avoid an import cycle
         from dbt.adapters.factory import get_adapter_package_names
+
         candidates: CandidateList = CandidateList()
         packages = set(get_adapter_package_names(self.metadata.adapter_type))
         for unique_id, macro in self.macros.items():
@@ -555,8 +566,8 @@ class ManifestStateCheck(dbtClassMixin):
 
 @dataclass
 class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
-    """The manifest for the full graph, after parsing and during compilation.
-    """
+    """The manifest for the full graph, after parsing and during compilation."""
+
     # These attributes are both positional and by keyword. If an attribute
     # is added it must all be added in the __reduce_ex__ method in the
     # args tuple in the right position.
@@ -576,27 +587,27 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     env_vars: MutableMapping[str, str] = field(default_factory=dict)
 
     _doc_lookup: Optional[DocLookup] = field(
-        default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
     _source_lookup: Optional[SourceLookup] = field(
-        default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
     _ref_lookup: Optional[RefableLookup] = field(
-        default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
     _disabled_lookup: Optional[DisabledLookup] = field(
-        default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
     _analysis_lookup: Optional[AnalysisLookup] = field(
-        default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
     _parsing_info: ParsingInfo = field(
         default_factory=ParsingInfo,
-        metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
+        metadata={"serialize": lambda x: None, "deserialize": lambda x: None},
     )
     _lock: Lock = field(
         default_factory=flags.MP_CONTEXT.Lock,
-        metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
+        metadata={"serialize": lambda x: None, "deserialize": lambda x: None},
     )
 
     def __pre_serialize__(self):
@@ -610,9 +621,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         obj._lock = flags.MP_CONTEXT.Lock()
         return obj
 
-    def sync_update_node(
-        self, new_node: NonSourceCompiledNode
-    ) -> NonSourceCompiledNode:
+    def sync_update_node(self, new_node: NonSourceCompiledNode) -> NonSourceCompiledNode:
         """update the node with a lock. The only time we should want to lock is
         when compiling an ephemeral ancestor of a node at runtime, because
         multiple threads could be just-in-time compiling the same ephemeral
@@ -624,7 +633,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         """
         with self._lock:
             existing = self.nodes[new_node.unique_id]
-            if getattr(existing, 'compiled', False):
+            if getattr(existing, "compiled", False):
                 # already compiled -> must be a NonSourceCompiledNode
                 return cast(NonSourceCompiledNode, existing)
             _update_into(self.nodes, new_node)
@@ -649,22 +658,10 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         manifest!
         """
         self.flat_graph = {
-            'exposures': {
-                k: v.to_dict(omit_none=False)
-                for k, v in self.exposures.items()
-            },
-            'metrics': {
-                k: v.to_dict(omit_none=False)
-                for k, v in self.metrics.items()
-            },
-            'nodes': {
-                k: v.to_dict(omit_none=False)
-                for k, v in self.nodes.items()
-            },
-            'sources': {
-                k: v.to_dict(omit_none=False)
-                for k, v in self.sources.items()
-            }
+            "exposures": {k: v.to_dict(omit_none=False) for k, v in self.exposures.items()},
+            "metrics": {k: v.to_dict(omit_none=False) for k, v in self.metrics.items()},
+            "nodes": {k: v.to_dict(omit_none=False) for k, v in self.nodes.items()},
+            "sources": {k: v.to_dict(omit_none=False) for k, v in self.sources.items()},
         }
 
     def build_disabled_by_file_id(self):
@@ -675,7 +672,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         return disabled_by_file_id
 
     def _materialization_candidates_for(
-        self, project_name: str,
+        self,
+        project_name: str,
         materialization_name: str,
         adapter_type: Optional[str],
     ) -> CandidateList:
@@ -698,13 +696,16 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     def find_materialization_macro_by_name(
         self, project_name: str, materialization_name: str, adapter_type: str
     ) -> Optional[ParsedMacro]:
-        candidates: CandidateList = CandidateList(chain.from_iterable(
-            self._materialization_candidates_for(
-                project_name=project_name,
-                materialization_name=materialization_name,
-                adapter_type=atype,
-            ) for atype in (adapter_type, None)
-        ))
+        candidates: CandidateList = CandidateList(
+            chain.from_iterable(
+                self._materialization_candidates_for(
+                    project_name=project_name,
+                    materialization_name=materialization_name,
+                    adapter_type=atype,
+                )
+                for atype in (adapter_type, None)
+            )
+        )
         return candidates.last()
 
     def get_resource_fqns(self) -> Mapping[str, PathSet]:
@@ -713,7 +714,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self.exposures.values(),
             self.nodes.values(),
             self.sources.values(),
-            self.metrics.values()
+            self.metrics.values(),
         )
         for resource in all_resources:
             resource_type_plural = resource.resource_type.pluralize()
@@ -723,17 +724,16 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         return resource_fqns
 
     def get_used_schemas(self, resource_types=None):
-        return frozenset({
-            (node.database, node.schema) for node in
-            chain(self.nodes.values(), self.sources.values())
-            if not resource_types or node.resource_type in resource_types
-        })
+        return frozenset(
+            {
+                (node.database, node.schema)
+                for node in chain(self.nodes.values(), self.sources.values())
+                if not resource_types or node.resource_type in resource_types
+            }
+        )
 
     def get_used_databases(self):
-        return frozenset(
-            x.database for x in
-            chain(self.nodes.values(), self.sources.values())
-        )
+        return frozenset(x.database for x in chain(self.nodes.values(), self.sources.values()))
 
     def deepcopy(self):
         return Manifest(
@@ -751,21 +751,25 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         )
 
     def build_parent_and_child_maps(self):
-        edge_members = list(chain(
-            self.nodes.values(),
-            self.sources.values(),
-            self.exposures.values(),
-            self.metrics.values(),
-        ))
+        edge_members = list(
+            chain(
+                self.nodes.values(),
+                self.sources.values(),
+                self.exposures.values(),
+                self.metrics.values(),
+            )
+        )
         forward_edges, backward_edges = build_node_edges(edge_members)
         self.child_map = forward_edges
         self.parent_map = backward_edges
 
     def build_macro_child_map(self):
-        edge_members = list(chain(
-            self.nodes.values(),
-            self.macros.values(),
-        ))
+        edge_members = list(
+            chain(
+                self.nodes.values(),
+                self.macros.values(),
+            )
+        )
         forward_edges = build_macro_edges(edge_members)
         return forward_edges
 
@@ -802,7 +806,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         else:
             # something terrible has happened
             raise dbt.exceptions.InternalException(
-                'Expected node {} not found in manifest'.format(unique_id)
+                "Expected node {} not found in manifest".format(unique_id)
             )
 
     @property
@@ -860,9 +864,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         node: Optional[ManifestNode] = None
         disabled: Optional[List[ManifestNode]] = None
 
-        candidates = _search_packages(
-            current_project, node_package, target_model_package
-        )
+        candidates = _search_packages(current_project, node_package, target_model_package)
         for pkg in candidates:
             node = self.ref_lookup.find(target_model_name, pkg, self)
 
@@ -871,9 +873,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
 
             # it's possible that the node is disabled
             if disabled is None:
-                disabled = self.disabled_lookup.find(
-                    target_model_name, pkg
-                )
+                disabled = self.disabled_lookup.find(target_model_name, pkg)
 
         if disabled:
             return Disabled(disabled[0])
@@ -886,9 +886,9 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         target_source_name: str,
         target_table_name: str,
         current_project: str,
-        node_package: str
+        node_package: str,
     ) -> MaybeParsedSource:
-        search_name = f'{target_source_name}.{target_table_name}'
+        search_name = f"{target_source_name}.{target_table_name}"
         candidates = _search_packages(current_project, node_package)
 
         source: Optional[ParsedSourceDefinition] = None
@@ -901,7 +901,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
 
             if disabled is None:
                 disabled = self.disabled_lookup.find(
-                    f'{target_source_name}.{target_table_name}', pkg
+                    f"{target_source_name}.{target_table_name}", pkg
                 )
 
         if disabled:
@@ -920,9 +920,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         resolve_ref except the is_enabled checks are unnecessary as docs are
         always enabled.
         """
-        candidates = _search_packages(
-            current_project, node_package, package
-        )
+        candidates = _search_packages(current_project, node_package, package)
 
         for pkg in candidates:
             result = self.doc_lookup.find(name, pkg, self)
@@ -934,7 +932,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     def merge_from_artifact(
         self,
         adapter,
-        other: 'WritableManifest',
+        other: "WritableManifest",
         selected: AbstractSet[UniqueID],
     ) -> None:
         """Given the selected unique IDs and a writable manifest, update this
@@ -947,12 +945,10 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         for unique_id, node in other.nodes.items():
             current = self.nodes.get(unique_id)
             if current and (
-                node.resource_type in refables and
-                not node.is_ephemeral and
-                unique_id not in selected and
-                not adapter.get_relation(
-                    current.database, current.schema, current.identifier
-                )
+                node.resource_type in refables
+                and not node.is_ephemeral
+                and unique_id not in selected
+                and not adapter.get_relation(current.database, current.schema, current.identifier)
             ):
                 merged.add(unique_id)
                 self.nodes[unique_id] = node.replace(deferred=True)
@@ -971,7 +967,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             # note that the line wrap eats newlines, so if you want newlines,
             # this is the result :(
             msg = line_wrap_message(
-                f'''\
+                f"""\
                 dbt found two macros named "{macro.name}" in the project
                 "{macro.package_name}".
 
@@ -982,8 +978,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
                     - {macro.original_file_path}
 
                     - {other_path}
-                ''',
-                subtract=2
+                """,
+                subtract=2,
             )
             raise_compiler_error(msg)
 
@@ -999,9 +995,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         my_checksum = self.files[key].checksum
         return my_checksum == source_file.checksum
 
-    def add_source(
-        self, source_file: SchemaSourceFile, source: UnpatchedSourceDefinition
-    ):
+    def add_source(self, source_file: SchemaSourceFile, source: UnpatchedSourceDefinition):
         # sources can't be overwritten!
         _check_duplicates(source, self.sources)
         self.sources[source.unique_id] = source  # type: ignore
@@ -1097,75 +1091,64 @@ AnyManifest = Union[Manifest, MacroManifest]
 
 
 @dataclass
-@schema_version('manifest', 4)
+@schema_version("manifest", 5)
 class WritableManifest(ArtifactMixin):
     nodes: Mapping[UniqueID, ManifestNode] = field(
-        metadata=dict(description=(
-            'The nodes defined in the dbt project and its dependencies'
-        ))
+        metadata=dict(description=("The nodes defined in the dbt project and its dependencies"))
     )
     sources: Mapping[UniqueID, ParsedSourceDefinition] = field(
-        metadata=dict(description=(
-            'The sources defined in the dbt project and its dependencies'
-        ))
+        metadata=dict(description=("The sources defined in the dbt project and its dependencies"))
     )
     macros: Mapping[UniqueID, ParsedMacro] = field(
-        metadata=dict(description=(
-            'The macros defined in the dbt project and its dependencies'
-        ))
+        metadata=dict(description=("The macros defined in the dbt project and its dependencies"))
     )
     docs: Mapping[UniqueID, ParsedDocumentation] = field(
-        metadata=dict(description=(
-            'The docs defined in the dbt project and its dependencies'
-        ))
+        metadata=dict(description=("The docs defined in the dbt project and its dependencies"))
     )
     exposures: Mapping[UniqueID, ParsedExposure] = field(
-        metadata=dict(description=(
-            'The exposures defined in the dbt project and its dependencies'
-        ))
+        metadata=dict(
+            description=("The exposures defined in the dbt project and its dependencies")
+        )
     )
     metrics: Mapping[UniqueID, ParsedMetric] = field(
-        metadata=dict(description=(
-            'The metrics defined in the dbt project and its dependencies'
-        ))
+        metadata=dict(description=("The metrics defined in the dbt project and its dependencies"))
     )
     selectors: Mapping[UniqueID, Any] = field(
-        metadata=dict(description=(
-            'The selectors defined in selectors.yml'
-        ))
+        metadata=dict(description=("The selectors defined in selectors.yml"))
+    )
+    disabled: Optional[Mapping[UniqueID, List[CompileResultNode]]] = field(
+        metadata=dict(description="A mapping of the disabled nodes in the target")
+    )
+    parent_map: Optional[NodeEdgeMap] = field(
+        metadata=dict(
+            description="A mapping from child nodes to their dependencies",
+        )
+    )
+    child_map: Optional[NodeEdgeMap] = field(
+        metadata=dict(
+            description="A mapping from parent nodes to their dependents",
+        )
+    )
+    metadata: ManifestMetadata = field(
+        metadata=dict(
+            description="Metadata about the manifest",
+        )
     )
-    disabled: Optional[Mapping[UniqueID, List[CompileResultNode]]] = field(metadata=dict(
-        description='A mapping of the disabled nodes in the target'
-    ))
-    parent_map: Optional[NodeEdgeMap] = field(metadata=dict(
-        description='A mapping from child nodes to their dependencies',
-    ))
-    child_map: Optional[NodeEdgeMap] = field(metadata=dict(
-        description='A mapping from parent nodes to their dependents',
-    ))
-    metadata: ManifestMetadata = field(metadata=dict(
-        description='Metadata about the manifest',
-    ))
 
 
-def _check_duplicates(
-    value: HasUniqueID, src: Mapping[str, HasUniqueID]
-):
+def _check_duplicates(value: HasUniqueID, src: Mapping[str, HasUniqueID]):
     if value.unique_id in src:
         raise_duplicate_resource_name(value, src[value.unique_id])
 
 
-K_T = TypeVar('K_T')
-V_T = TypeVar('V_T')
+K_T = TypeVar("K_T")
+V_T = TypeVar("V_T")
 
 
-def _expect_value(
-    key: K_T, src: Mapping[K_T, V_T], old_file: SourceFile, name: str
-) -> V_T:
+def _expect_value(key: K_T, src: Mapping[K_T, V_T], old_file: SourceFile, name: str) -> V_T:
     if key not in src:
         raise CompilationException(
             'Expected to find "{}" in cached "result.{}" based '
-            'on cached file information: {}!'
-            .format(key, name, old_file)
+            "on cached file information: {}!".format(key, name, old_file)
         )
     return src[key]

core/dbt/contracts/graph/model_config.py

@@ -1,11 +1,11 @@
 from dataclasses import field, Field, dataclass
 from enum import Enum
 from itertools import chain
-from typing import (
-    Any, List, Optional, Dict, Union, Type, TypeVar, Callable
-)
+from typing import Any, List, Optional, Dict, Union, Type, TypeVar, Callable
 from dbt.dataclass_schema import (
-    dbtClassMixin, ValidationError, register_pattern,
+    dbtClassMixin,
+    ValidationError,
+    register_pattern,
 )
 from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed
 from dbt.exceptions import InternalException, CompilationException
@@ -14,7 +14,7 @@ from dbt import hooks
 from dbt.node_types import NodeType
 
 
-M = TypeVar('M', bound='Metadata')
+M = TypeVar("M", bound="Metadata")
 
 
 def _get_meta_value(cls: Type[M], fld: Field, key: str, default: Any) -> M:
@@ -29,14 +29,10 @@ def _get_meta_value(cls: Type[M], fld: Field, key: str, default: Any) -> M:
     try:
         return cls(value)
     except ValueError as exc:
-        raise InternalException(
-            f'Invalid {cls} value: {value}'
-        ) from exc
+        raise InternalException(f"Invalid {cls} value: {value}") from exc
 
 
-def _set_meta_value(
-    obj: M, key: str, existing: Optional[Dict[str, Any]] = None
-) -> Dict[str, Any]:
+def _set_meta_value(obj: M, key: str, existing: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
     if existing is None:
         result = {}
     else:
@@ -53,19 +49,17 @@ class Metadata(Enum):
 
         return _get_meta_value(cls, fld, key, default)
 
-    def meta(
-        self, existing: Optional[Dict[str, Any]] = None
-    ) -> Dict[str, Any]:
+    def meta(self, existing: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
         key = self.metadata_key()
         return _set_meta_value(self, key, existing)
 
     @classmethod
-    def default_field(cls) -> 'Metadata':
-        raise NotImplementedError('Not implemented')
+    def default_field(cls) -> "Metadata":
+        raise NotImplementedError("Not implemented")
 
     @classmethod
     def metadata_key(cls) -> str:
-        raise NotImplementedError('Not implemented')
+        raise NotImplementedError("Not implemented")
 
 
 class MergeBehavior(Metadata):
@@ -74,12 +68,12 @@ class MergeBehavior(Metadata):
     Clobber = 3
 
     @classmethod
-    def default_field(cls) -> 'MergeBehavior':
+    def default_field(cls) -> "MergeBehavior":
         return cls.Clobber
 
     @classmethod
     def metadata_key(cls) -> str:
-        return 'merge'
+        return "merge"
 
 
 class ShowBehavior(Metadata):
@@ -87,12 +81,12 @@ class ShowBehavior(Metadata):
     Hide = 2
 
     @classmethod
-    def default_field(cls) -> 'ShowBehavior':
+    def default_field(cls) -> "ShowBehavior":
         return cls.Show
 
     @classmethod
     def metadata_key(cls) -> str:
-        return 'show_hide'
+        return "show_hide"
 
     @classmethod
     def should_show(cls, fld: Field) -> bool:
@@ -104,12 +98,12 @@ class CompareBehavior(Metadata):
     Exclude = 2
 
     @classmethod
-    def default_field(cls) -> 'CompareBehavior':
+    def default_field(cls) -> "CompareBehavior":
         return cls.Include
 
     @classmethod
     def metadata_key(cls) -> str:
-        return 'compare'
+        return "compare"
 
     @classmethod
     def should_include(cls, fld: Field) -> bool:
@@ -141,32 +135,28 @@ def _merge_field_value(
         return _listify(self_value) + _listify(other_value)
     elif merge_behavior == MergeBehavior.Update:
         if not isinstance(self_value, dict):
-            raise InternalException(f'expected dict, got {self_value}')
+            raise InternalException(f"expected dict, got {self_value}")
         if not isinstance(other_value, dict):
-            raise InternalException(f'expected dict, got {other_value}')
+            raise InternalException(f"expected dict, got {other_value}")
         value = self_value.copy()
         value.update(other_value)
         return value
     else:
-        raise InternalException(
-            f'Got an invalid merge_behavior: {merge_behavior}'
-        )
+        raise InternalException(f"Got an invalid merge_behavior: {merge_behavior}")
 
 
 def insensitive_patterns(*patterns: str):
     lowercased = []
     for pattern in patterns:
-        lowercased.append(
-            ''.join('[{}{}]'.format(s.upper(), s.lower()) for s in pattern)
-        )
-    return '^({})$'.format('|'.join(lowercased))
+        lowercased.append("".join("[{}{}]".format(s.upper(), s.lower()) for s in pattern))
+    return "^({})$".format("|".join(lowercased))
 
 
 class Severity(str):
     pass
 
 
-register_pattern(Severity, insensitive_patterns('warn', 'error'))
+register_pattern(Severity, insensitive_patterns("warn", "error"))
 
 
 @dataclass
@@ -176,13 +166,11 @@ class Hook(dbtClassMixin, Replaceable):
     index: Optional[int] = None
 
 
-T = TypeVar('T', bound='BaseConfig')
+T = TypeVar("T", bound="BaseConfig")
 
 
 @dataclass
-class BaseConfig(
-    AdditionalPropertiesAllowed, Replaceable
-):
+class BaseConfig(AdditionalPropertiesAllowed, Replaceable):
 
     # enable syntax like: config['key']
     def __getitem__(self, key):
@@ -207,8 +195,7 @@ class BaseConfig(
     def __delitem__(self, key):
         if hasattr(self, key):
             msg = (
-                'Error, tried to delete config key "{}": Cannot delete '
-                'built-in keys'
+                'Error, tried to delete config key "{}": Cannot delete ' "built-in keys"
             ).format(key)
             raise CompilationException(msg)
         else:
@@ -248,9 +235,7 @@ class BaseConfig(
             return unrendered[key] == other[key]
 
     @classmethod
-    def same_contents(
-        cls, unrendered: Dict[str, Any], other: Dict[str, Any]
-    ) -> bool:
+    def same_contents(cls, unrendered: Dict[str, Any], other: Dict[str, Any]) -> bool:
         """This is like __eq__, except it ignores some fields."""
         seen = set()
         for fld, target_name in cls._get_fields():
@@ -270,14 +255,12 @@ class BaseConfig(
     # This is used in 'add_config_call' to created the combined config_call_dict.
     # 'meta' moved here from node
     mergebehavior = {
-        "append": ['pre-hook', 'pre_hook', 'post-hook', 'post_hook', 'tags'],
-        "update": ['quoting', 'column_types', 'meta'],
+        "append": ["pre-hook", "pre_hook", "post-hook", "post_hook", "tags"],
+        "update": ["quoting", "column_types", "meta"],
     }
 
     @classmethod
-    def _merge_dicts(
-        cls, src: Dict[str, Any], data: Dict[str, Any]
-    ) -> Dict[str, Any]:
+    def _merge_dicts(cls, src: Dict[str, Any], data: Dict[str, Any]) -> Dict[str, Any]:
         """Find all the items in data that match a target_field on this class,
         and merge them with the data found in `src` for target_field, using the
         field's specified merge behavior. Matching items will be removed from
@@ -309,14 +292,13 @@ class BaseConfig(
             )
         return result
 
-    def update_from(
-        self: T, data: Dict[str, Any], adapter_type: str, validate: bool = True
-    ) -> T:
+    def update_from(self: T, data: Dict[str, Any], adapter_type: str, validate: bool = True) -> T:
         """Given a dict of keys, update the current config from them, validate
         it, and return a new config with the updated values
         """
         # sadly, this is a circular import
         from dbt.adapters.factory import get_config_class_by_name
+
         dct = self.to_dict(omit_none=False)
 
         adapter_config_cls = get_config_class_by_name(adapter_type)
@@ -353,6 +335,40 @@ class BaseConfig(
 @dataclass
 class SourceConfig(BaseConfig):
     enabled: bool = True
+    # to be implmented to complete CT-201
+    # quoting: Dict[str, Any] = field(
+    #     default_factory=dict,
+    #     metadata=MergeBehavior.Update.meta(),
+    # )
+    # freshness: Optional[Dict[str, Any]] = field(
+    #     default=None,
+    #     metadata=CompareBehavior.Exclude.meta(),
+    # )
+    # loader: Optional[str] = field(
+    #     default=None,
+    #     metadata=CompareBehavior.Exclude.meta(),
+    # )
+    # # TODO what type is this? docs say: "<column_name_or_expression>"
+    # loaded_at_field: Optional[str] = field(
+    #     default=None,
+    #     metadata=CompareBehavior.Exclude.meta(),
+    # )
+    # database: Optional[str] = field(
+    #     default=None,
+    #     metadata=CompareBehavior.Exclude.meta(),
+    # )
+    # schema: Optional[str] = field(
+    #     default=None,
+    #     metadata=CompareBehavior.Exclude.meta(),
+    # )
+    # meta: Dict[str, Any] = field(
+    #     default_factory=dict,
+    #     metadata=MergeBehavior.Update.meta(),
+    # )
+    # tags: Union[List[str], str] = field(
+    #     default_factory=list_str,
+    #     metadata=metas(ShowBehavior.Hide, MergeBehavior.Append, CompareBehavior.Exclude),
+    # )
 
 
 @dataclass
@@ -374,9 +390,7 @@ class NodeAndTestConfig(BaseConfig):
     )
     tags: Union[List[str], str] = field(
         default_factory=list_str,
-        metadata=metas(ShowBehavior.Hide,
-                       MergeBehavior.Append,
-                       CompareBehavior.Exclude),
+        metadata=metas(ShowBehavior.Hide, MergeBehavior.Append, CompareBehavior.Exclude),
     )
     meta: Dict[str, Any] = field(
         default_factory=dict,
@@ -388,7 +402,7 @@ class NodeAndTestConfig(BaseConfig):
 class NodeConfig(NodeAndTestConfig):
     # Note: if any new fields are added with MergeBehavior, also update the
     # 'mergebehavior' dictionary
-    materialized: str = 'view'
+    materialized: str = "view"
     persist_docs: Dict[str, Any] = field(default_factory=dict)
     post_hook: List[Hook] = field(
         default_factory=list,
@@ -409,12 +423,15 @@ class NodeConfig(NodeAndTestConfig):
         metadata=MergeBehavior.Update.meta(),
     )
     full_refresh: Optional[bool] = None
-    on_schema_change: Optional[str] = 'ignore'
+    # 'unique_key' doesn't use 'Optional' because typing.get_type_hints was
+    # sometimes getting the Union order wrong, causing serialization failures.
+    unique_key: Union[str, List[str], None] = None
+    on_schema_change: Optional[str] = "ignore"
 
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        field_map = {'post-hook': 'post_hook', 'pre-hook': 'pre_hook'}
+        field_map = {"post-hook": "post_hook", "pre-hook": "pre_hook"}
         # create a new dict because otherwise it gets overwritten in
         # tests
         new_dict = {}
@@ -432,7 +449,7 @@ class NodeConfig(NodeAndTestConfig):
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        field_map = {'post_hook': 'post-hook', 'pre_hook': 'pre-hook'}
+        field_map = {"post_hook": "post-hook", "pre_hook": "pre-hook"}
         for field_name in field_map:
             if field_name in dct:
                 dct[field_map[field_name]] = dct.pop(field_name)
@@ -441,12 +458,12 @@ class NodeConfig(NodeAndTestConfig):
     # this is still used by jsonschema validation
     @classmethod
     def field_mapping(cls):
-        return {'post_hook': 'post-hook', 'pre_hook': 'pre-hook'}
+        return {"post_hook": "post-hook", "pre_hook": "pre-hook"}
 
 
 @dataclass
 class SeedConfig(NodeConfig):
-    materialized: str = 'seed'
+    materialized: str = "seed"
     quote_columns: Optional[bool] = None
 
 
@@ -454,31 +471,29 @@ class SeedConfig(NodeConfig):
 class TestConfig(NodeAndTestConfig):
     # this is repeated because of a different default
     schema: Optional[str] = field(
-        default='dbt_test__audit',
+        default="dbt_test__audit",
         metadata=CompareBehavior.Exclude.meta(),
     )
-    materialized: str = 'test'
-    severity: Severity = Severity('ERROR')
+    materialized: str = "test"
+    severity: Severity = Severity("ERROR")
     store_failures: Optional[bool] = None
     where: Optional[str] = None
     limit: Optional[int] = None
-    fail_calc: str = 'count(*)'
-    warn_if: str = '!= 0'
-    error_if: str = '!= 0'
+    fail_calc: str = "count(*)"
+    warn_if: str = "!= 0"
+    error_if: str = "!= 0"
 
     @classmethod
-    def same_contents(
-        cls, unrendered: Dict[str, Any], other: Dict[str, Any]
-    ) -> bool:
+    def same_contents(cls, unrendered: Dict[str, Any], other: Dict[str, Any]) -> bool:
         """This is like __eq__, except it explicitly checks certain fields."""
         modifiers = [
-            'severity',
-            'where',
-            'limit',
-            'fail_calc',
-            'warn_if',
-            'error_if',
-            'store_failures'
+            "severity",
+            "where",
+            "limit",
+            "fail_calc",
+            "warn_if",
+            "error_if",
+            "store_failures",
         ]
 
         seen = set()
@@ -493,7 +508,8 @@ class TestConfig(NodeAndTestConfig):
 
 @dataclass
 class EmptySnapshotConfig(NodeConfig):
-    materialized: str = 'snapshot'
+    materialized: str = "snapshot"
+    unique_key: Optional[str] = None  # override NodeConfig unique_key definition
 
 
 @dataclass
@@ -503,35 +519,37 @@ class SnapshotConfig(EmptySnapshotConfig):
     target_schema: Optional[str] = None
     target_database: Optional[str] = None
     updated_at: Optional[str] = None
-    check_cols: Optional[Union[str, List[str]]] = None
+    # Not using Optional because of serialization issues with a Union of str and List[str]
+    check_cols: Union[str, List[str], None] = None
 
     @classmethod
     def validate(cls, data):
         super().validate(data)
-        if not data.get('strategy') or not data.get('unique_key') or not \
-                data.get('target_schema'):
+        if not data.get("strategy") or not data.get("unique_key") or not data.get("target_schema"):
             raise ValidationError(
                 "Snapshots must be configured with a 'strategy', 'unique_key', "
-                "and 'target_schema'.")
-        if data.get('strategy') == 'check':
-            if not data.get('check_cols'):
+                "and 'target_schema'."
+            )
+        if data.get("strategy") == "check":
+            if not data.get("check_cols"):
                 raise ValidationError(
                     "A snapshot configured with the check strategy must "
-                    "specify a check_cols configuration.")
-            if (isinstance(data['check_cols'], str) and
-                    data['check_cols'] != 'all'):
+                    "specify a check_cols configuration."
+                )
+            if isinstance(data["check_cols"], str) and data["check_cols"] != "all":
                 raise ValidationError(
                     f"Invalid value for 'check_cols': {data['check_cols']}. "
-                    "Expected 'all' or a list of strings.")
+                    "Expected 'all' or a list of strings."
+                )
 
-        elif data.get('strategy') == 'timestamp':
-            if not data.get('updated_at'):
+        elif data.get("strategy") == "timestamp":
+            if not data.get("updated_at"):
                 raise ValidationError(
                     "A snapshot configured with the timestamp strategy "
-                    "must specify an updated_at configuration.")
-            if data.get('check_cols'):
-                raise ValidationError(
-                    "A 'timestamp' snapshot should not have 'check_cols'")
+                    "must specify an updated_at configuration."
+                )
+            if data.get("check_cols"):
+                raise ValidationError("A 'timestamp' snapshot should not have 'check_cols'")
         # If the strategy is not 'check' or 'timestamp' it's a custom strategy,
         # formerly supported with GenericSnapshotConfig
 
@@ -553,9 +571,7 @@ RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = {
 # base resource types are like resource types, except nothing has mandatory
 # configs.
 BASE_RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = RESOURCE_TYPES.copy()
-BASE_RESOURCE_TYPES.update({
-    NodeType.Snapshot: EmptySnapshotConfig
-})
+BASE_RESOURCE_TYPES.update({NodeType.Snapshot: EmptySnapshotConfig})
 
 
 def get_config_for(resource_type: NodeType, base=False) -> Type[BaseConfig]:

core/dbt/contracts/graph/parsed.py

@@ -15,18 +15,28 @@ from typing import (
     TypeVar,
 )
 
-from dbt.dataclass_schema import (
-    dbtClassMixin, ExtensibleDbtClassMixin
-)
+from dbt.dataclass_schema import dbtClassMixin, ExtensibleDbtClassMixin
 
 from dbt.clients.system import write_file
 from dbt.contracts.files import FileHash, MAXIMUM_SEED_SIZE_NAME
 from dbt.contracts.graph.unparsed import (
-    UnparsedNode, UnparsedDocumentation, Quoting, Docs,
-    UnparsedBaseNode, FreshnessThreshold, ExternalTable,
-    HasYamlMetadata, MacroArgument, UnparsedSourceDefinition,
-    UnparsedSourceTableDefinition, UnparsedColumn, TestDef,
-    ExposureOwner, ExposureType, MaturityType, MetricFilter
+    UnparsedNode,
+    UnparsedDocumentation,
+    Quoting,
+    Docs,
+    UnparsedBaseNode,
+    FreshnessThreshold,
+    ExternalTable,
+    HasYamlMetadata,
+    MacroArgument,
+    UnparsedSourceDefinition,
+    UnparsedSourceTableDefinition,
+    UnparsedColumn,
+    TestDef,
+    ExposureOwner,
+    ExposureType,
+    MaturityType,
+    MetricFilter,
 )
 from dbt.contracts.util import Replaceable, AdditionalPropertiesMixin
 from dbt.exceptions import warn_or_error
@@ -45,13 +55,9 @@ from .model_config import (
 
 
 @dataclass
-class ColumnInfo(
-    AdditionalPropertiesMixin,
-    ExtensibleDbtClassMixin,
-    Replaceable
-):
+class ColumnInfo(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable):
     name: str
-    description: str = ''
+    description: str = ""
     meta: Dict[str, Any] = field(default_factory=dict)
     data_type: Optional[str] = None
     quote: Optional[bool] = None
@@ -63,7 +69,7 @@ class ColumnInfo(
 class HasFqn(dbtClassMixin, Replaceable):
     fqn: List[str]
 
-    def same_fqn(self, other: 'HasFqn') -> bool:
+    def same_fqn(self, other: "HasFqn") -> bool:
         return self.fqn == other.fqn
 
 
@@ -102,8 +108,8 @@ class HasRelationMetadata(dbtClassMixin, Replaceable):
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        if 'database' not in data:
-            data['database'] = None
+        if "database" not in data:
+            data["database"] = None
         return data
 
 
@@ -119,21 +125,19 @@ class ParsedNodeMixins(dbtClassMixin):
     @property
     def should_store_failures(self):
         return self.resource_type == NodeType.Test and (
-            self.config.store_failures if self.config.store_failures is not None
+            self.config.store_failures
+            if self.config.store_failures is not None
             else flags.STORE_FAILURES
         )
 
     # will this node map to an object in the database?
     @property
     def is_relational(self):
-        return (
-            self.resource_type in NodeType.refable() or
-            self.should_store_failures
-        )
+        return self.resource_type in NodeType.refable() or self.should_store_failures
 
     @property
     def is_ephemeral(self):
-        return self.config.materialized == 'ephemeral'
+        return self.config.materialized == "ephemeral"
 
     @property
     def is_ephemeral_model(self):
@@ -143,7 +147,7 @@ class ParsedNodeMixins(dbtClassMixin):
     def depends_on_nodes(self):
         return self.depends_on.nodes
 
-    def patch(self, patch: 'ParsedNodePatch'):
+    def patch(self, patch: "ParsedNodePatch"):
         """Given a ParsedNodePatch, add the new information to the node."""
         # explicitly pick out the parts to update so we don't inadvertently
         # step on the model name or anything
@@ -153,7 +157,6 @@ class ParsedNodeMixins(dbtClassMixin):
         self.created_at = time.time()
         self.description = patch.description
         self.columns = patch.columns
-        self.meta = patch.meta
         self.docs = patch.docs
 
     def get_materialization(self):
@@ -161,13 +164,7 @@ class ParsedNodeMixins(dbtClassMixin):
 
 
 @dataclass
-class ParsedNodeMandatory(
-    UnparsedNode,
-    HasUniqueID,
-    HasFqn,
-    HasRelationMetadata,
-    Replaceable
-):
+class ParsedNodeMandatory(UnparsedNode, HasUniqueID, HasFqn, HasRelationMetadata, Replaceable):
     alias: str
     checksum: FileHash
     config: NodeConfig = field(default_factory=NodeConfig)
@@ -178,12 +175,31 @@ class ParsedNodeMandatory(
 
 
 @dataclass
-class ParsedNodeDefaults(ParsedNodeMandatory):
+class NodeInfoMixin:
+    _event_status: Dict[str, Any] = field(default_factory=dict)
+
+    @property
+    def node_info(self):
+        node_info = {
+            "node_path": getattr(self, "path", None),
+            "node_name": getattr(self, "name", None),
+            "unique_id": getattr(self, "unique_id", None),
+            "resource_type": str(getattr(self, "resource_type", "")),
+            "materialized": self.config.get("materialized"),
+            "node_status": str(self._event_status.get("node_status")),
+            "node_started_at": self._event_status.get("started_at"),
+            "node_finished_at": self._event_status.get("finished_at"),
+        }
+        return node_info
+
+
+@dataclass
+class ParsedNodeDefaults(NodeInfoMixin, ParsedNodeMandatory):
     tags: List[str] = field(default_factory=list)
     refs: List[List[str]] = field(default_factory=list)
     sources: List[List[str]] = field(default_factory=list)
     depends_on: DependsOn = field(default_factory=DependsOn)
-    description: str = field(default='')
+    description: str = field(default="")
     columns: Dict[str, ColumnInfo] = field(default_factory=dict)
     meta: Dict[str, Any] = field(default_factory=dict)
     docs: Docs = field(default_factory=Docs)
@@ -194,38 +210,33 @@ class ParsedNodeDefaults(ParsedNodeMandatory):
     unrendered_config: Dict[str, Any] = field(default_factory=dict)
     created_at: float = field(default_factory=lambda: time.time())
     config_call_dict: Dict[str, Any] = field(default_factory=dict)
-    _event_status: Dict[str, Any] = field(default_factory=dict)
 
     def write_node(self, target_path: str, subdirectory: str, payload: str):
-        if (os.path.basename(self.path) ==
-                os.path.basename(self.original_file_path)):
+        if os.path.basename(self.path) == os.path.basename(self.original_file_path):
             # One-to-one relationship of nodes to files.
             path = self.original_file_path
         else:
             #  Many-to-one relationship of nodes to files.
             path = os.path.join(self.original_file_path, self.path)
-        full_path = os.path.join(
-            target_path, subdirectory, self.package_name, path
-        )
+        full_path = os.path.join(target_path, subdirectory, self.package_name, path)
 
         write_file(full_path, payload)
         return full_path
 
 
-T = TypeVar('T', bound='ParsedNode')
+T = TypeVar("T", bound="ParsedNode")
 
 
 @dataclass
 class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
-
     def _serialize(self):
         return self.to_dict()
 
     def __post_serialize__(self, dct):
-        if 'config_call_dict' in dct:
-            del dct['config_call_dict']
-        if '_event_status' in dct:
-            del dct['_event_status']
+        if "config_call_dict" in dct:
+            del dct["config_call_dict"]
+        if "_event_status" in dct:
+            del dct["_event_status"]
         return dct
 
     @classmethod
@@ -233,41 +244,41 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
         # The serialized ParsedNodes do not differ from each other
         # in fields that would allow 'from_dict' to distinguis
         # between them.
-        resource_type = dct['resource_type']
-        if resource_type == 'model':
+        resource_type = dct["resource_type"]
+        if resource_type == "model":
             return ParsedModelNode.from_dict(dct)
-        elif resource_type == 'analysis':
+        elif resource_type == "analysis":
             return ParsedAnalysisNode.from_dict(dct)
-        elif resource_type == 'seed':
+        elif resource_type == "seed":
             return ParsedSeedNode.from_dict(dct)
-        elif resource_type == 'rpc':
+        elif resource_type == "rpc":
             return ParsedRPCNode.from_dict(dct)
-        elif resource_type == 'sql':
+        elif resource_type == "sql":
             return ParsedSqlNode.from_dict(dct)
-        elif resource_type == 'test':
-            if 'test_metadata' in dct:
+        elif resource_type == "test":
+            if "test_metadata" in dct:
                 return ParsedGenericTestNode.from_dict(dct)
             else:
                 return ParsedSingularTestNode.from_dict(dct)
-        elif resource_type == 'operation':
+        elif resource_type == "operation":
             return ParsedHookNode.from_dict(dct)
-        elif resource_type == 'seed':
+        elif resource_type == "seed":
             return ParsedSeedNode.from_dict(dct)
-        elif resource_type == 'snapshot':
+        elif resource_type == "snapshot":
             return ParsedSnapshotNode.from_dict(dct)
         else:
             return cls.from_dict(dct)
 
     def _persist_column_docs(self) -> bool:
-        if hasattr(self.config, 'persist_docs'):
+        if hasattr(self.config, "persist_docs"):
             assert isinstance(self.config, NodeConfig)
-            return bool(self.config.persist_docs.get('columns'))
+            return bool(self.config.persist_docs.get("columns"))
         return False
 
     def _persist_relation_docs(self) -> bool:
-        if hasattr(self.config, 'persist_docs'):
+        if hasattr(self.config, "persist_docs"):
             assert isinstance(self.config, NodeConfig)
-            return bool(self.config.persist_docs.get('relation'))
+            return bool(self.config.persist_docs.get("relation"))
         return False
 
     def same_body(self: T, other: T) -> bool:
@@ -283,12 +294,8 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
 
         if self._persist_column_docs():
             # assert other._persist_column_docs()
-            column_descriptions = {
-                k: v.description for k, v in self.columns.items()
-            }
-            other_column_descriptions = {
-                k: v.description for k, v in other.columns.items()
-            }
+            column_descriptions = {k: v.description for k, v in self.columns.items()}
+            other_column_descriptions = {k: v.description for k, v in other.columns.items()}
             if column_descriptions != other_column_descriptions:
                 return False
 
@@ -299,7 +306,7 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
         # compares the configured value, rather than the ultimate value (so
         # generate_*_name and unset values derived from the target are
         # ignored)
-        keys = ('database', 'schema', 'alias')
+        keys = ("database", "schema", "alias")
         for key in keys:
             mine = self.unrendered_config.get(key)
             others = other.unrendered_config.get(key)
@@ -318,42 +325,40 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
             return False
 
         return (
-            self.same_body(old) and
-            self.same_config(old) and
-            self.same_persisted_description(old) and
-            self.same_fqn(old) and
-            self.same_database_representation(old) and
-            True
+            self.same_body(old)
+            and self.same_config(old)
+            and self.same_persisted_description(old)
+            and self.same_fqn(old)
+            and self.same_database_representation(old)
+            and True
         )
 
 
 @dataclass
 class ParsedAnalysisNode(ParsedNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Analysis]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Analysis]})
 
 
 @dataclass
 class ParsedHookNode(ParsedNode):
-    resource_type: NodeType = field(
-        metadata={'restrict': [NodeType.Operation]}
-    )
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
     index: Optional[int] = None
 
 
 @dataclass
 class ParsedModelNode(ParsedNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Model]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Model]})
 
 
 # TODO: rm?
 @dataclass
 class ParsedRPCNode(ParsedNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.RPCCall]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.RPCCall]})
 
 
 @dataclass
 class ParsedSqlNode(ParsedNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.SqlOperation]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.SqlOperation]})
 
 
 def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
@@ -363,31 +368,31 @@ def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
     # if the current checksum is a path, we want to log a warning.
     result = first.checksum == second.checksum
 
-    if first.checksum.name == 'path':
+    if first.checksum.name == "path":
         msg: str
-        if second.checksum.name != 'path':
+        if second.checksum.name != "path":
             msg = (
-                f'Found a seed ({first.package_name}.{first.name}) '
-                f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was '
-                f'<={MAXIMUM_SEED_SIZE_NAME}, so it has changed'
+                f"Found a seed ({first.package_name}.{first.name}) "
+                f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was "
+                f"<={MAXIMUM_SEED_SIZE_NAME}, so it has changed"
             )
         elif result:
             msg = (
-                f'Found a seed ({first.package_name}.{first.name}) '
-                f'>{MAXIMUM_SEED_SIZE_NAME} in size at the same path, dbt '
-                f'cannot tell if it has changed: assuming they are the same'
+                f"Found a seed ({first.package_name}.{first.name}) "
+                f">{MAXIMUM_SEED_SIZE_NAME} in size at the same path, dbt "
+                f"cannot tell if it has changed: assuming they are the same"
             )
         elif not result:
             msg = (
-                f'Found a seed ({first.package_name}.{first.name}) '
-                f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was in '
-                f'a different location, assuming it has changed'
+                f"Found a seed ({first.package_name}.{first.name}) "
+                f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was in "
+                f"a different location, assuming it has changed"
             )
         else:
             msg = (
-                f'Found a seed ({first.package_name}.{first.name}) '
-                f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file had a '
-                f'checksum type of {second.checksum.name}, so it has changed'
+                f"Found a seed ({first.package_name}.{first.name}) "
+                f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file had a "
+                f"checksum type of {second.checksum.name}, so it has changed"
             )
         warn_or_error(msg, node=first)
 
@@ -397,12 +402,12 @@ def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
 @dataclass
 class ParsedSeedNode(ParsedNode):
     # keep this in sync with CompiledSeedNode!
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Seed]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Seed]})
     config: SeedConfig = field(default_factory=SeedConfig)
 
     @property
     def empty(self):
-        """ Seeds are never empty"""
+        """Seeds are never empty"""
         return False
 
     def same_body(self: T, other: T) -> bool:
@@ -426,20 +431,20 @@ class HasTestMetadata(dbtClassMixin):
 
 @dataclass
 class ParsedSingularTestNode(ParsedNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
     # Was not able to make mypy happy and keep the code working. We need to
     # refactor the various configs.
     config: TestConfig = field(default_factory=TestConfig)  # type: ignore
 
     @property
     def test_node_type(self):
-        return 'singular'
+        return "singular"
 
 
 @dataclass
 class ParsedGenericTestNode(ParsedNode, HasTestMetadata):
     # keep this in sync with CompiledGenericTestNode!
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
     column_name: Optional[str] = None
     file_key_name: Optional[str] = None
     # Was not able to make mypy happy and keep the code working. We need to
@@ -450,15 +455,11 @@ class ParsedGenericTestNode(ParsedNode, HasTestMetadata):
         if other is None:
             return False
 
-        return (
-            self.same_config(other) and
-            self.same_fqn(other) and
-            True
-        )
+        return self.same_config(other) and self.same_fqn(other) and True
 
     @property
     def test_node_type(self):
-        return 'generic'
+        return "generic"
 
 
 @dataclass
@@ -469,13 +470,13 @@ class IntermediateSnapshotNode(ParsedNode):
     # defined in config blocks. To fix that, we have an intermediate type that
     # uses a regular node config, which the snapshot parser will then convert
     # into a full ParsedSnapshotNode after rendering.
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
     config: EmptySnapshotConfig = field(default_factory=EmptySnapshotConfig)
 
 
 @dataclass
 class ParsedSnapshotNode(ParsedNode):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
     config: SnapshotConfig
 
 
@@ -505,12 +506,12 @@ class ParsedMacroPatch(ParsedPatch):
 class ParsedMacro(UnparsedBaseNode, HasUniqueID):
     name: str
     macro_sql: str
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Macro]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
     # TODO: can macros even have tags?
     tags: List[str] = field(default_factory=list)
     # TODO: is this ever populated?
     depends_on: MacroDependsOn = field(default_factory=MacroDependsOn)
-    description: str = ''
+    description: str = ""
     meta: Dict[str, Any] = field(default_factory=dict)
     docs: Docs = field(default_factory=Docs)
     patch_path: Optional[str] = None
@@ -525,7 +526,7 @@ class ParsedMacro(UnparsedBaseNode, HasUniqueID):
         self.docs = patch.docs
         self.arguments = patch.arguments
 
-    def same_contents(self, other: Optional['ParsedMacro']) -> bool:
+    def same_contents(self, other: Optional["ParsedMacro"]) -> bool:
         if other is None:
             return False
         # the only thing that makes one macro different from another with the
@@ -542,7 +543,7 @@ class ParsedDocumentation(UnparsedDocumentation, HasUniqueID):
     def search_name(self):
         return self.name
 
-    def same_contents(self, other: Optional['ParsedDocumentation']) -> bool:
+    def same_contents(self, other: Optional["ParsedDocumentation"]) -> bool:
         if other is None:
             return False
         # the only thing that makes one doc different from another with the
@@ -561,11 +562,11 @@ def normalize_test(testdef: TestDef) -> Dict[str, Any]:
 class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
     source: UnparsedSourceDefinition
     table: UnparsedSourceTableDefinition
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Source]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Source]})
     patch_path: Optional[Path] = None
 
     def get_full_source_name(self):
-        return f'{self.source.name}_{self.table.name}'
+        return f"{self.source.name}_{self.table.name}"
 
     def get_source_representation(self):
         return f'source("{self.source.name}", "{self.table.name}")'
@@ -590,9 +591,7 @@ class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
         else:
             return self.table.columns
 
-    def get_tests(
-        self
-    ) -> Iterator[Tuple[Dict[str, Any], Optional[UnparsedColumn]]]:
+    def get_tests(self) -> Iterator[Tuple[Dict[str, Any], Optional[UnparsedColumn]]]:
         for test in self.tests:
             yield normalize_test(test), None
 
@@ -610,24 +609,27 @@ class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
 
 
 @dataclass
-class ParsedSourceDefinition(
+class ParsedSourceMandatory(
     UnparsedBaseNode,
     HasUniqueID,
     HasRelationMetadata,
     HasFqn,
-
 ):
     name: str
     source_name: str
     source_description: str
     loader: str
     identifier: str
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Source]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Source]})
+
+
+@dataclass
+class ParsedSourceDefinition(NodeInfoMixin, ParsedSourceMandatory):
     quoting: Quoting = field(default_factory=Quoting)
     loaded_at_field: Optional[str] = None
     freshness: Optional[FreshnessThreshold] = None
     external: Optional[ExternalTable] = None
-    description: str = ''
+    description: str = ""
     columns: Dict[str, ColumnInfo] = field(default_factory=dict)
     meta: Dict[str, Any] = field(default_factory=dict)
     source_meta: Dict[str, Any] = field(default_factory=dict)
@@ -637,43 +639,40 @@ class ParsedSourceDefinition(
     unrendered_config: Dict[str, Any] = field(default_factory=dict)
     relation_name: Optional[str] = None
     created_at: float = field(default_factory=lambda: time.time())
-    _event_status: Dict[str, Any] = field(default_factory=dict)
 
     def __post_serialize__(self, dct):
-        if '_event_status' in dct:
-            del dct['_event_status']
+        if "_event_status" in dct:
+            del dct["_event_status"]
         return dct
 
-    def same_database_representation(
-        self, other: 'ParsedSourceDefinition'
-    ) -> bool:
+    def same_database_representation(self, other: "ParsedSourceDefinition") -> bool:
         return (
-            self.database == other.database and
-            self.schema == other.schema and
-            self.identifier == other.identifier and
-            True
+            self.database == other.database
+            and self.schema == other.schema
+            and self.identifier == other.identifier
+            and True
         )
 
-    def same_quoting(self, other: 'ParsedSourceDefinition') -> bool:
+    def same_quoting(self, other: "ParsedSourceDefinition") -> bool:
         return self.quoting == other.quoting
 
-    def same_freshness(self, other: 'ParsedSourceDefinition') -> bool:
+    def same_freshness(self, other: "ParsedSourceDefinition") -> bool:
         return (
-            self.freshness == other.freshness and
-            self.loaded_at_field == other.loaded_at_field and
-            True
+            self.freshness == other.freshness
+            and self.loaded_at_field == other.loaded_at_field
+            and True
         )
 
-    def same_external(self, other: 'ParsedSourceDefinition') -> bool:
+    def same_external(self, other: "ParsedSourceDefinition") -> bool:
         return self.external == other.external
 
-    def same_config(self, old: 'ParsedSourceDefinition') -> bool:
+    def same_config(self, old: "ParsedSourceDefinition") -> bool:
         return self.config.same_contents(
             self.unrendered_config,
             old.unrendered_config,
         )
 
-    def same_contents(self, old: Optional['ParsedSourceDefinition']) -> bool:
+    def same_contents(self, old: Optional["ParsedSourceDefinition"]) -> bool:
         # existing when it didn't before is a change!
         if old is None:
             return True
@@ -687,17 +686,17 @@ class ParsedSourceDefinition(
         # metadata/tags changes are not "changes"
         # patching/description changes are not "changes"
         return (
-            self.same_database_representation(old) and
-            self.same_fqn(old) and
-            self.same_config(old) and
-            self.same_quoting(old) and
-            self.same_freshness(old) and
-            self.same_external(old) and
-            True
+            self.same_database_representation(old)
+            and self.same_fqn(old)
+            and self.same_config(old)
+            and self.same_quoting(old)
+            and self.same_freshness(old)
+            and self.same_external(old)
+            and True
         )
 
     def get_full_source_name(self):
-        return f'{self.source_name}_{self.name}'
+        return f"{self.source_name}_{self.name}"
 
     def get_source_representation(self):
         return f'source("{self.source.name}", "{self.table.name}")'
@@ -736,7 +735,7 @@ class ParsedSourceDefinition(
 
     @property
     def search_name(self):
-        return f'{self.source_name}.{self.name}'
+        return f"{self.source_name}.{self.name}"
 
 
 @dataclass
@@ -745,7 +744,7 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
     type: ExposureType
     owner: ExposureOwner
     resource_type: NodeType = NodeType.Exposure
-    description: str = ''
+    description: str = ""
     maturity: Optional[MaturityType] = None
     meta: Dict[str, Any] = field(default_factory=dict)
     tags: List[str] = field(default_factory=list)
@@ -763,39 +762,39 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
     def search_name(self):
         return self.name
 
-    def same_depends_on(self, old: 'ParsedExposure') -> bool:
+    def same_depends_on(self, old: "ParsedExposure") -> bool:
         return set(self.depends_on.nodes) == set(old.depends_on.nodes)
 
-    def same_description(self, old: 'ParsedExposure') -> bool:
+    def same_description(self, old: "ParsedExposure") -> bool:
         return self.description == old.description
 
-    def same_maturity(self, old: 'ParsedExposure') -> bool:
+    def same_maturity(self, old: "ParsedExposure") -> bool:
         return self.maturity == old.maturity
 
-    def same_owner(self, old: 'ParsedExposure') -> bool:
+    def same_owner(self, old: "ParsedExposure") -> bool:
         return self.owner == old.owner
 
-    def same_exposure_type(self, old: 'ParsedExposure') -> bool:
+    def same_exposure_type(self, old: "ParsedExposure") -> bool:
         return self.type == old.type
 
-    def same_url(self, old: 'ParsedExposure') -> bool:
+    def same_url(self, old: "ParsedExposure") -> bool:
         return self.url == old.url
 
-    def same_contents(self, old: Optional['ParsedExposure']) -> bool:
+    def same_contents(self, old: Optional["ParsedExposure"]) -> bool:
         # existing when it didn't before is a change!
         # metadata/tags changes are not "changes"
         if old is None:
             return True
 
         return (
-            self.same_fqn(old) and
-            self.same_exposure_type(old) and
-            self.same_owner(old) and
-            self.same_maturity(old) and
-            self.same_url(old) and
-            self.same_description(old) and
-            self.same_depends_on(old) and
-            True
+            self.same_fqn(old)
+            and self.same_exposure_type(old)
+            and self.same_owner(old)
+            and self.same_maturity(old)
+            and self.same_url(old)
+            and self.same_description(old)
+            and self.same_depends_on(old)
+            and True
         )
 
 
@@ -827,50 +826,50 @@ class ParsedMetric(UnparsedBaseNode, HasUniqueID, HasFqn):
     def search_name(self):
         return self.name
 
-    def same_model(self, old: 'ParsedMetric') -> bool:
+    def same_model(self, old: "ParsedMetric") -> bool:
         return self.model == old.model
 
-    def same_dimensions(self, old: 'ParsedMetric') -> bool:
+    def same_dimensions(self, old: "ParsedMetric") -> bool:
         return self.dimensions == old.dimensions
 
-    def same_filters(self, old: 'ParsedMetric') -> bool:
+    def same_filters(self, old: "ParsedMetric") -> bool:
         return self.filters == old.filters
 
-    def same_description(self, old: 'ParsedMetric') -> bool:
+    def same_description(self, old: "ParsedMetric") -> bool:
         return self.description == old.description
 
-    def same_label(self, old: 'ParsedMetric') -> bool:
+    def same_label(self, old: "ParsedMetric") -> bool:
         return self.label == old.label
 
-    def same_type(self, old: 'ParsedMetric') -> bool:
+    def same_type(self, old: "ParsedMetric") -> bool:
         return self.type == old.type
 
-    def same_sql(self, old: 'ParsedMetric') -> bool:
+    def same_sql(self, old: "ParsedMetric") -> bool:
         return self.sql == old.sql
 
-    def same_timestamp(self, old: 'ParsedMetric') -> bool:
+    def same_timestamp(self, old: "ParsedMetric") -> bool:
         return self.timestamp == old.timestamp
 
-    def same_time_grains(self, old: 'ParsedMetric') -> bool:
+    def same_time_grains(self, old: "ParsedMetric") -> bool:
         return self.time_grains == old.time_grains
 
-    def same_contents(self, old: Optional['ParsedMetric']) -> bool:
+    def same_contents(self, old: Optional["ParsedMetric"]) -> bool:
         # existing when it didn't before is a change!
         # metadata/tags changes are not "changes"
         if old is None:
             return True
 
         return (
-            self.same_model(old) and
-            self.same_dimensions(old) and
-            self.same_filters(old) and
-            self.same_description(old) and
-            self.same_label(old) and
-            self.same_type(old) and
-            self.same_sql(old) and
-            self.same_timestamp(old) and
-            self.same_time_grains(old) and
-            True
+            self.same_model(old)
+            and self.same_dimensions(old)
+            and self.same_filters(old)
+            and self.same_description(old)
+            and self.same_label(old)
+            and self.same_type(old)
+            and self.same_sql(old)
+            and self.same_timestamp(old)
+            and self.same_time_grains(old)
+            and True
         )
 
 

core/dbt/contracts/graph/unparsed.py

@@ -4,13 +4,12 @@ from dbt.contracts.util import (
     Mergeable,
     Replaceable,
 )
+
 # trigger the PathEncoder
 import dbt.helper_types  # noqa:F401
 from dbt.exceptions import CompilationException
 
-from dbt.dataclass_schema import (
-    dbtClassMixin, StrEnum, ExtensibleDbtClassMixin
-)
+from dbt.dataclass_schema import dbtClassMixin, StrEnum, ExtensibleDbtClassMixin
 
 from dataclasses import dataclass, field
 from datetime import timedelta
@@ -27,7 +26,7 @@ class UnparsedBaseNode(dbtClassMixin, Replaceable):
 
     @property
     def file_id(self):
-        return f'{self.package_name}://{self.original_file_path}'
+        return f"{self.package_name}://{self.original_file_path}"
 
 
 @dataclass
@@ -41,27 +40,31 @@ class HasSQL:
 
 @dataclass
 class UnparsedMacro(UnparsedBaseNode, HasSQL):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Macro]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
 
 
 @dataclass
 class UnparsedGenericTest(UnparsedBaseNode, HasSQL):
-    resource_type: NodeType = field(metadata={'restrict': [NodeType.Macro]})
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
 
 
 @dataclass
 class UnparsedNode(UnparsedBaseNode, HasSQL):
     name: str
-    resource_type: NodeType = field(metadata={'restrict': [
-        NodeType.Model,
-        NodeType.Analysis,
-        NodeType.Test,
-        NodeType.Snapshot,
-        NodeType.Operation,
-        NodeType.Seed,
-        NodeType.RPCCall,
-        NodeType.SqlOperation,
-    ]})
+    resource_type: NodeType = field(
+        metadata={
+            "restrict": [
+                NodeType.Model,
+                NodeType.Analysis,
+                NodeType.Test,
+                NodeType.Snapshot,
+                NodeType.Operation,
+                NodeType.Seed,
+                NodeType.RPCCall,
+                NodeType.SqlOperation,
+            ]
+        }
+    )
 
     @property
     def search_name(self):
@@ -70,9 +73,7 @@ class UnparsedNode(UnparsedBaseNode, HasSQL):
 
 @dataclass
 class UnparsedRunHook(UnparsedNode):
-    resource_type: NodeType = field(
-        metadata={'restrict': [NodeType.Operation]}
-    )
+    resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
     index: Optional[int] = None
 
 
@@ -82,10 +83,9 @@ class Docs(dbtClassMixin, Replaceable):
 
 
 @dataclass
-class HasDocs(AdditionalPropertiesMixin, ExtensibleDbtClassMixin,
-              Replaceable):
+class HasDocs(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable):
     name: str
-    description: str = ''
+    description: str = ""
     meta: Dict[str, Any] = field(default_factory=dict)
     data_type: Optional[str] = None
     docs: Docs = field(default_factory=Docs)
@@ -128,11 +128,11 @@ class HasYamlMetadata(dbtClassMixin):
 
     @property
     def file_id(self):
-        return f'{self.package_name}://{self.original_file_path}'
+        return f"{self.package_name}://{self.original_file_path}"
 
 
 @dataclass
-class HasConfig():
+class HasConfig:
     config: Dict[str, Any] = field(default_factory=dict)
 
 
@@ -150,7 +150,7 @@ class UnparsedNodeUpdate(HasConfig, HasColumnTests, HasTests, HasYamlMetadata):
 class MacroArgument(dbtClassMixin):
     name: str
     type: Optional[str] = None
-    description: str = ''
+    description: str = ""
 
 
 @dataclass
@@ -159,12 +159,12 @@ class UnparsedMacroUpdate(HasConfig, HasDocs, HasYamlMetadata):
 
 
 class TimePeriod(StrEnum):
-    minute = 'minute'
-    hour = 'hour'
-    day = 'day'
+    minute = "minute"
+    hour = "hour"
+    day = "day"
 
     def plural(self) -> str:
-        return str(self) + 's'
+        return str(self) + "s"
 
 
 @dataclass
@@ -191,6 +191,7 @@ class FreshnessThreshold(dbtClassMixin, Mergeable):
 
     def status(self, age: float) -> "dbt.contracts.results.FreshnessStatus":
         from dbt.contracts.results import FreshnessStatus
+
         if self.error_after and self.error_after.exceeded(age):
             return FreshnessStatus.Error
         elif self.warn_after and self.warn_after.exceeded(age):
@@ -203,25 +204,20 @@ class FreshnessThreshold(dbtClassMixin, Mergeable):
 
 
 @dataclass
-class AdditionalPropertiesAllowed(
-    AdditionalPropertiesMixin,
-    ExtensibleDbtClassMixin
-):
+class AdditionalPropertiesAllowed(AdditionalPropertiesMixin, ExtensibleDbtClassMixin):
     _extra: Dict[str, Any] = field(default_factory=dict)
 
 
 @dataclass
 class ExternalPartition(AdditionalPropertiesAllowed, Replaceable):
-    name: str = ''
-    description: str = ''
-    data_type: str = ''
+    name: str = ""
+    description: str = ""
+    data_type: str = ""
     meta: Dict[str, Any] = field(default_factory=dict)
 
     def __post_init__(self):
-        if self.name == '' or self.data_type == '':
-            raise CompilationException(
-                'External partition columns must have names and data types'
-            )
+        if self.name == "" or self.data_type == "":
+            raise CompilationException("External partition columns must have names and data types")
 
 
 @dataclass
@@ -246,47 +242,44 @@ class Quoting(dbtClassMixin, Mergeable):
 
 @dataclass
 class UnparsedSourceTableDefinition(HasColumnTests, HasTests):
+    config: Dict[str, Any] = field(default_factory=dict)
     loaded_at_field: Optional[str] = None
     identifier: Optional[str] = None
     quoting: Quoting = field(default_factory=Quoting)
-    freshness: Optional[FreshnessThreshold] = field(
-        default_factory=FreshnessThreshold
-    )
+    freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
     external: Optional[ExternalTable] = None
     tags: List[str] = field(default_factory=list)
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        if 'freshness' not in dct and self.freshness is None:
-            dct['freshness'] = None
+        if "freshness" not in dct and self.freshness is None:
+            dct["freshness"] = None
         return dct
 
 
 @dataclass
 class UnparsedSourceDefinition(dbtClassMixin, Replaceable):
     name: str
-    description: str = ''
+    description: str = ""
     meta: Dict[str, Any] = field(default_factory=dict)
     database: Optional[str] = None
     schema: Optional[str] = None
-    loader: str = ''
+    loader: str = ""
     quoting: Quoting = field(default_factory=Quoting)
-    freshness: Optional[FreshnessThreshold] = field(
-        default_factory=FreshnessThreshold
-    )
+    freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
     loaded_at_field: Optional[str] = None
     tables: List[UnparsedSourceTableDefinition] = field(default_factory=list)
     tags: List[str] = field(default_factory=list)
     config: Dict[str, Any] = field(default_factory=dict)
 
     @property
-    def yaml_key(self) -> 'str':
-        return 'sources'
+    def yaml_key(self) -> "str":
+        return "sources"
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        if 'freshness' not in dct and self.freshness is None:
-            dct['freshness'] = None
+        if "freshness" not in dct and self.freshness is None:
+            dct["freshness"] = None
         return dct
 
 
@@ -300,9 +293,7 @@ class SourceTablePatch(dbtClassMixin):
     loaded_at_field: Optional[str] = None
     identifier: Optional[str] = None
     quoting: Quoting = field(default_factory=Quoting)
-    freshness: Optional[FreshnessThreshold] = field(
-        default_factory=FreshnessThreshold
-    )
+    freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
     external: Optional[ExternalTable] = None
     tags: Optional[List[str]] = None
     tests: Optional[List[TestDef]] = None
@@ -310,13 +301,13 @@ class SourceTablePatch(dbtClassMixin):
 
     def to_patch_dict(self) -> Dict[str, Any]:
         dct = self.to_dict(omit_none=True)
-        remove_keys = ('name')
+        remove_keys = "name"
         for key in remove_keys:
             if key in dct:
                 del dct[key]
 
         if self.freshness is None:
-            dct['freshness'] = None
+            dct["freshness"] = None
 
         return dct
 
@@ -324,36 +315,35 @@ class SourceTablePatch(dbtClassMixin):
 @dataclass
 class SourcePatch(dbtClassMixin, Replaceable):
     name: str = field(
-        metadata=dict(description='The name of the source to override'),
+        metadata=dict(description="The name of the source to override"),
     )
     overrides: str = field(
-        metadata=dict(description='The package of the source to override'),
+        metadata=dict(description="The package of the source to override"),
     )
     path: Path = field(
-        metadata=dict(description='The path to the patch-defining yml file'),
+        metadata=dict(description="The path to the patch-defining yml file"),
     )
+    config: Dict[str, Any] = field(default_factory=dict)
     description: Optional[str] = None
     meta: Optional[Dict[str, Any]] = None
     database: Optional[str] = None
     schema: Optional[str] = None
     loader: Optional[str] = None
     quoting: Optional[Quoting] = None
-    freshness: Optional[Optional[FreshnessThreshold]] = field(
-        default_factory=FreshnessThreshold
-    )
+    freshness: Optional[Optional[FreshnessThreshold]] = field(default_factory=FreshnessThreshold)
     loaded_at_field: Optional[str] = None
     tables: Optional[List[SourceTablePatch]] = None
     tags: Optional[List[str]] = None
 
     def to_patch_dict(self) -> Dict[str, Any]:
         dct = self.to_dict(omit_none=True)
-        remove_keys = ('name', 'overrides', 'tables', 'path')
+        remove_keys = ("name", "overrides", "tables", "path")
         for key in remove_keys:
             if key in dct:
                 del dct[key]
 
         if self.freshness is None:
-            dct['freshness'] = None
+            dct["freshness"] = None
 
         return dct
 
@@ -374,7 +364,7 @@ class UnparsedDocumentation(dbtClassMixin, Replaceable):
 
     @property
     def file_id(self):
-        return f'{self.package_name}://{self.original_file_path}'
+        return f"{self.package_name}://{self.original_file_path}"
 
     @property
     def resource_type(self):
@@ -389,9 +379,9 @@ class UnparsedDocumentationFile(UnparsedDocumentation):
 # can't use total_ordering decorator here, as str provides an ordering already
 # and it's not the one we want.
 class Maturity(StrEnum):
-    low = 'low'
-    medium = 'medium'
-    high = 'high'
+    low = "low"
+    medium = "medium"
+    high = "high"
 
     def __lt__(self, other):
         if not isinstance(other, Maturity):
@@ -416,17 +406,17 @@ class Maturity(StrEnum):
 
 
 class ExposureType(StrEnum):
-    Dashboard = 'dashboard'
-    Notebook = 'notebook'
-    Analysis = 'analysis'
-    ML = 'ml'
-    Application = 'application'
+    Dashboard = "dashboard"
+    Notebook = "notebook"
+    Analysis = "analysis"
+    ML = "ml"
+    Application = "application"
 
 
 class MaturityType(StrEnum):
-    Low = 'low'
-    Medium = 'medium'
-    High = 'high'
+    Low = "low"
+    Medium = "medium"
+    High = "high"
 
 
 @dataclass
@@ -440,7 +430,7 @@ class UnparsedExposure(dbtClassMixin, Replaceable):
     name: str
     type: ExposureType
     owner: ExposureOwner
-    description: str = ''
+    description: str = ""
     maturity: Optional[MaturityType] = None
     meta: Dict[str, Any] = field(default_factory=dict)
     tags: List[str] = field(default_factory=list)
@@ -462,7 +452,7 @@ class UnparsedMetric(dbtClassMixin, Replaceable):
     name: str
     label: str
     type: str
-    description: str = ''
+    description: str = ""
     sql: Optional[str] = None
     timestamp: Optional[str] = None
     time_grains: List[str] = field(default_factory=list)

core/dbt/contracts/project.py

@@ -2,24 +2,40 @@ from dbt.contracts.util import Replaceable, Mergeable, list_str
 from dbt.contracts.connection import QueryComment, UserConfigContract
 from dbt.helper_types import NoValue
 from dbt.dataclass_schema import (
-    dbtClassMixin, ValidationError,
+    dbtClassMixin,
+    ValidationError,
     HyphenatedDbtClassMixin,
     ExtensibleDbtClassMixin,
-    register_pattern, ValidatedStringMixin
+    register_pattern,
+    ValidatedStringMixin,
 )
 from dataclasses import dataclass, field
 from typing import Optional, List, Dict, Union, Any
 from mashumaro.types import SerializableType
 
-PIN_PACKAGE_URL = 'https://docs.getdbt.com/docs/package-management#section-specifying-package-versions'  # noqa
+PIN_PACKAGE_URL = (
+    "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"  # noqa
+)
 DEFAULT_SEND_ANONYMOUS_USAGE_STATS = True
 
 
 class Name(ValidatedStringMixin):
-    ValidationRegex = r'^[^\d\W]\w*$'
+    ValidationRegex = r"^[^\d\W]\w*$"
+
+    @classmethod
+    def is_valid(cls, value: Any) -> bool:
+        if not isinstance(value, str):
+            return False
+
+        try:
+            cls.validate(value)
+        except ValidationError:
+            return False
+
+        return True
 
 
-register_pattern(Name, r'^[^\d\W]\w*$')
+register_pattern(Name, r"^[^\d\W]\w*$")
 
 
 class SemverString(str, SerializableType):
@@ -27,16 +43,15 @@ class SemverString(str, SerializableType):
         return self
 
     @classmethod
-    def _deserialize(cls, value: str) -> 'SemverString':
+    def _deserialize(cls, value: str) -> "SemverString":
         return SemverString(value)
 
 
-# this does not support the full semver (does not allow a trailing -fooXYZ) and
-# is not restrictive enough for full semver, (allows '1.0'). But it's like
-# 'semver lite'.
+# this supports full semver,
+# but also allows for 2 group version numbers, (allows '1.0').
 register_pattern(
     SemverString,
-    r'^(?:0|[1-9]\d*)\.(?:0|[1-9]\d*)(\.(?:0|[1-9]\d*))?$',
+    r"^(0|[1-9]\d*)\.(0|[1-9]\d*)(\.(0|[1-9]\d*)(?:-((?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\.(?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\+([0-9a-zA-Z-]+(?:\.[0-9a-zA-Z-]+)*))?)?$",  # noqa
 )
 
 
@@ -104,8 +119,7 @@ class ProjectPackageMetadata:
 
     @classmethod
     def from_project(cls, project):
-        return cls(name=project.project_name,
-                   packages=project.packages.packages)
+        return cls(name=project.project_name, packages=project.packages.packages)
 
 
 @dataclass
@@ -123,46 +137,46 @@ class RegistryPackageMetadata(
 
 # A list of all the reserved words that packages may not have as names.
 BANNED_PROJECT_NAMES = {
-    '_sql_results',
-    'adapter',
-    'api',
-    'column',
-    'config',
-    'context',
-    'database',
-    'env',
-    'env_var',
-    'exceptions',
-    'execute',
-    'flags',
-    'fromjson',
-    'fromyaml',
-    'graph',
-    'invocation_id',
-    'load_agate_table',
-    'load_result',
-    'log',
-    'model',
-    'modules',
-    'post_hooks',
-    'pre_hooks',
-    'ref',
-    'render',
-    'return',
-    'run_started_at',
-    'schema',
-    'source',
-    'sql',
-    'sql_now',
-    'store_result',
-    'store_raw_result',
-    'target',
-    'this',
-    'tojson',
-    'toyaml',
-    'try_or_compiler_error',
-    'var',
-    'write',
+    "_sql_results",
+    "adapter",
+    "api",
+    "column",
+    "config",
+    "context",
+    "database",
+    "env",
+    "env_var",
+    "exceptions",
+    "execute",
+    "flags",
+    "fromjson",
+    "fromyaml",
+    "graph",
+    "invocation_id",
+    "load_agate_table",
+    "load_result",
+    "log",
+    "model",
+    "modules",
+    "post_hooks",
+    "pre_hooks",
+    "ref",
+    "render",
+    "return",
+    "run_started_at",
+    "schema",
+    "source",
+    "sql",
+    "sql_now",
+    "store_result",
+    "store_raw_result",
+    "target",
+    "this",
+    "tojson",
+    "toyaml",
+    "try_or_compiler_error",
+    "var",
+    "write",
 }
 
 
@@ -201,7 +215,7 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
     vars: Optional[Dict[str, Any]] = field(
         default=None,
         metadata=dict(
-            description='map project names to their vars override dicts',
+            description="map project names to their vars override dicts",
         ),
     )
     packages: List[PackageSpec] = field(default_factory=list)
@@ -210,16 +224,17 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
     @classmethod
     def validate(cls, data):
         super().validate(data)
-        if data['name'] in BANNED_PROJECT_NAMES:
-            raise ValidationError(
-                f"Invalid project name: {data['name']} is a reserved word"
-            )
+        if data["name"] in BANNED_PROJECT_NAMES:
+            raise ValidationError(f"Invalid project name: {data['name']} is a reserved word")
         # validate dispatch config
-        if 'dispatch' in data and data['dispatch']:
-            entries = data['dispatch']
+        if "dispatch" in data and data["dispatch"]:
+            entries = data["dispatch"]
             for entry in entries:
-                if ('macro_namespace' not in entry or 'search_order' not in entry or
-                        not isinstance(entry['search_order'], list)):
+                if (
+                    "macro_namespace" not in entry
+                    or "search_order" not in entry
+                    or not isinstance(entry["search_order"], list)
+                ):
                     raise ValidationError(f"Invalid project dispatch config: {entry}")
 
 
@@ -238,13 +253,14 @@ class UserConfig(ExtensibleDbtClassMixin, Replaceable, UserConfigContract):
     use_experimental_parser: Optional[bool] = None
     static_parser: Optional[bool] = None
     indirect_selection: Optional[str] = None
+    cache_selected_only: Optional[bool] = None
 
 
 @dataclass
 class ProfileConfig(HyphenatedDbtClassMixin, Replaceable):
-    profile_name: str = field(metadata={'preserve_underscore': True})
-    target_name: str = field(metadata={'preserve_underscore': True})
-    user_config: UserConfig = field(metadata={'preserve_underscore': True})
+    profile_name: str = field(metadata={"preserve_underscore": True})
+    target_name: str = field(metadata={"preserve_underscore": True})
+    user_config: UserConfig = field(metadata={"preserve_underscore": True})
     threads: int
     # TODO: make this a dynamic union of some kind?
     credentials: Optional[Dict[str, Any]]
@@ -262,7 +278,7 @@ class ConfiguredQuoting(Quoting, Replaceable):
 class Configuration(Project, ProfileConfig):
     cli_vars: Dict[str, Any] = field(
         default_factory=dict,
-        metadata={'preserve_underscore': True},
+        metadata={"preserve_underscore": True},
     )
     quoting: Optional[ConfiguredQuoting] = None
 

core/dbt/contracts/relation.py

@@ -1,7 +1,8 @@
 from collections.abc import Mapping
 from dataclasses import dataclass
 from typing import (
-    Optional, Dict,
+    Optional,
+    Dict,
 )
 from typing_extensions import Protocol
 
@@ -13,17 +14,17 @@ from dbt.utils import deep_merge
 
 
 class RelationType(StrEnum):
-    Table = 'table'
-    View = 'view'
-    CTE = 'cte'
-    MaterializedView = 'materializedview'
-    External = 'external'
+    Table = "table"
+    View = "view"
+    CTE = "cte"
+    MaterializedView = "materializedview"
+    External = "external"
 
 
 class ComponentName(StrEnum):
-    Database = 'database'
-    Schema = 'schema'
-    Identifier = 'identifier'
+    Database = "database"
+    Schema = "schema"
+    Identifier = "identifier"
 
 
 class HasQuoting(Protocol):
@@ -68,8 +69,7 @@ class Policy(FakeAPIObject):
             return self.identifier
         else:
             raise ValueError(
-                'Got a key of {}, expected one of {}'
-                .format(key, list(ComponentName))
+                "Got a key of {}, expected one of {}".format(key, list(ComponentName))
             )
 
     def replace_dict(self, dct: Dict[ComponentName, bool]):
@@ -88,16 +88,12 @@ class Path(FakeAPIObject):
     def __post_init__(self):
         # handle pesky jinja2.Undefined sneaking in here and messing up rende
         if not isinstance(self.database, (type(None), str)):
-            raise CompilationException(
-                'Got an invalid path database: {}'.format(self.database)
-            )
+            raise CompilationException("Got an invalid path database: {}".format(self.database))
         if not isinstance(self.schema, (type(None), str)):
-            raise CompilationException(
-                'Got an invalid path schema: {}'.format(self.schema)
-            )
+            raise CompilationException("Got an invalid path schema: {}".format(self.schema))
         if not isinstance(self.identifier, (type(None), str)):
             raise CompilationException(
-                'Got an invalid path identifier: {}'.format(self.identifier)
+                "Got an invalid path identifier: {}".format(self.identifier)
             )
 
     def get_lowered_part(self, key: ComponentName) -> Optional[str]:
@@ -115,8 +111,7 @@ class Path(FakeAPIObject):
             return self.identifier
         else:
             raise ValueError(
-                'Got a key of {}, expected one of {}'
-                .format(key, list(ComponentName))
+                "Got a key of {}, expected one of {}".format(key, list(ComponentName))
             )
 
     def replace_dict(self, dct: Dict[ComponentName, str]):

core/dbt/contracts/results.py

@@ -1,7 +1,5 @@
 from dbt.contracts.graph.manifest import CompileResultNode
-from dbt.contracts.graph.unparsed import (
-    FreshnessThreshold
-)
+from dbt.contracts.graph.unparsed import FreshnessThreshold
 from dbt.contracts.graph.parsed import ParsedSourceDefinition
 from dbt.contracts.util import (
     BaseArtifactMetadata,
@@ -25,7 +23,13 @@ import agate
 from dataclasses import dataclass, field
 from datetime import datetime
 from typing import (
-    Union, Dict, List, Optional, Any, NamedTuple, Sequence,
+    Union,
+    Dict,
+    List,
+    Optional,
+    Any,
+    NamedTuple,
+    Sequence,
 )
 
 from dbt.clients.system import write_json
@@ -59,9 +63,9 @@ class collect_timing_info:
 
 
 class RunningStatus(StrEnum):
-    Started = 'started'
-    Compiling = 'compiling'
-    Executing = 'executing'
+    Started = "started"
+    Compiling = "compiling"
+    Executing = "executing"
 
 
 class NodeStatus(StrEnum):
@@ -81,6 +85,7 @@ class RunStatus(StrEnum):
 
 
 class TestStatus(StrEnum):
+    __test__ = False
     Pass = NodeStatus.Pass
     Error = NodeStatus.Error
     Fail = NodeStatus.Fail
@@ -108,10 +113,10 @@ class BaseResult(dbtClassMixin):
     @classmethod
     def __pre_deserialize__(cls, data):
         data = super().__pre_deserialize__(data)
-        if 'message' not in data:
-            data['message'] = None
-        if 'failures' not in data:
-            data['failures'] = None
+        if "message" not in data:
+            data["message"] = None
+        if "failures" not in data:
+            data["failures"] = None
         return data
 
 
@@ -123,9 +128,7 @@ class NodeResult(BaseResult):
 @dataclass
 class RunResult(NodeResult):
     agate_table: Optional[agate.Table] = field(
-        default=None, metadata={
-            'serialize': lambda x: None, 'deserialize': lambda x: None
-        }
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
 
     @property
@@ -169,7 +172,7 @@ def process_run_result(result: RunResult) -> RunResultOutput:
         execution_time=result.execution_time,
         message=result.message,
         adapter_response=result.adapter_response,
-        failures=result.failures
+        failures=result.failures,
     )
 
 
@@ -192,7 +195,7 @@ class RunExecutionResult(
 
 
 @dataclass
-@schema_version('run-results', 4)
+@schema_version("run-results", 4)
 class RunResultsArtifact(ExecutionResult, ArtifactMixin):
     results: Sequence[RunResultOutput]
     args: Dict[str, Any] = field(default_factory=dict)
@@ -210,12 +213,7 @@ class RunResultsArtifact(ExecutionResult, ArtifactMixin):
             dbt_schema_version=str(cls.dbt_schema_version),
             generated_at=generated_at,
         )
-        return cls(
-            metadata=meta,
-            results=processed_results,
-            elapsed_time=elapsed_time,
-            args=args
-        )
+        return cls(metadata=meta, results=processed_results, elapsed_time=elapsed_time, args=args)
 
     def write(self, path: str):
         write_json(path, self.to_dict(omit_none=False))
@@ -228,15 +226,14 @@ class RunOperationResult(ExecutionResult):
 
 @dataclass
 class RunOperationResultMetadata(BaseArtifactMetadata):
-    dbt_schema_version: str = field(default_factory=lambda: str(
-        RunOperationResultsArtifact.dbt_schema_version
-    ))
+    dbt_schema_version: str = field(
+        default_factory=lambda: str(RunOperationResultsArtifact.dbt_schema_version)
+    )
 
 
 @dataclass
-@schema_version('run-operation-result', 1)
+@schema_version("run-operation-result", 1)
 class RunOperationResultsArtifact(RunOperationResult, ArtifactMixin):
-
     @classmethod
     def from_success(
         cls,
@@ -255,6 +252,7 @@ class RunOperationResultsArtifact(RunOperationResult, ArtifactMixin):
             success=success,
         )
 
+
 # due to issues with typing.Union collapsing subclasses, this can't subclass
 # PartialResult
 
@@ -273,7 +271,7 @@ class SourceFreshnessResult(NodeResult):
 
 
 class FreshnessErrorEnum(StrEnum):
-    runtime_error = 'runtime error'
+    runtime_error = "runtime error"
 
 
 @dataclass
@@ -306,14 +304,11 @@ class PartialSourceFreshnessResult(NodeResult):
         return False
 
 
-FreshnessNodeResult = Union[PartialSourceFreshnessResult,
-                            SourceFreshnessResult]
+FreshnessNodeResult = Union[PartialSourceFreshnessResult, SourceFreshnessResult]
 FreshnessNodeOutput = Union[SourceFreshnessRuntimeError, SourceFreshnessOutput]
 
 
-def process_freshness_result(
-    result: FreshnessNodeResult
-) -> FreshnessNodeOutput:
+def process_freshness_result(result: FreshnessNodeResult) -> FreshnessNodeOutput:
     unique_id = result.node.unique_id
     if result.status == FreshnessStatus.RuntimeErr:
         return SourceFreshnessRuntimeError(
@@ -325,16 +320,14 @@ def process_freshness_result(
     # we know that this must be a SourceFreshnessResult
     if not isinstance(result, SourceFreshnessResult):
         raise InternalException(
-            'Got {} instead of a SourceFreshnessResult for a '
-            'non-error result in freshness execution!'
-            .format(type(result))
+            "Got {} instead of a SourceFreshnessResult for a "
+            "non-error result in freshness execution!".format(type(result))
         )
     # if we're here, we must have a non-None freshness threshold
     criteria = result.node.freshness
     if criteria is None:
         raise InternalException(
-            'Somehow evaluated a freshness result for a source '
-            'that has no freshness criteria!'
+            "Somehow evaluated a freshness result for a source " "that has no freshness criteria!"
         )
     return SourceFreshnessOutput(
         unique_id=unique_id,
@@ -353,9 +346,7 @@ def process_freshness_result(
 @dataclass
 class FreshnessMetadata(BaseArtifactMetadata):
     dbt_schema_version: str = field(
-        default_factory=lambda: str(
-            FreshnessExecutionResultArtifact.dbt_schema_version
-        )
+        default_factory=lambda: str(FreshnessExecutionResultArtifact.dbt_schema_version)
     )
 
 
@@ -376,7 +367,7 @@ class FreshnessResult(ExecutionResult):
 
 
 @dataclass
-@schema_version('sources', 3)
+@schema_version("sources", 3)
 class FreshnessExecutionResultArtifact(
     ArtifactMixin,
     VersionedSchema,
@@ -399,8 +390,7 @@ Primitive = Union[bool, str, float, None]
 PrimitiveDict = Dict[str, Primitive]
 
 CatalogKey = NamedTuple(
-    'CatalogKey',
-    [('database', Optional[str]), ('schema', str), ('name', str)]
+    "CatalogKey", [("database", Optional[str]), ("schema", str), ("name", str)]
 )
 
 
@@ -469,13 +459,13 @@ class CatalogResults(dbtClassMixin):
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
-        if '_compile_results' in dct:
-            del dct['_compile_results']
+        if "_compile_results" in dct:
+            del dct["_compile_results"]
         return dct
 
 
 @dataclass
-@schema_version('catalog', 1)
+@schema_version("catalog", 1)
 class CatalogArtifact(CatalogResults, ArtifactMixin):
     metadata: CatalogMetadata
 
@@ -486,8 +476,8 @@ class CatalogArtifact(CatalogResults, ArtifactMixin):
         nodes: Dict[str, CatalogTable],
         sources: Dict[str, CatalogTable],
         compile_results: Optional[Any],
-        errors: Optional[List[str]]
-    ) -> 'CatalogArtifact':
+        errors: Optional[List[str]],
+    ) -> "CatalogArtifact":
         meta = CatalogMetadata(generated_at=generated_at)
         return cls(
             metadata=meta,