fix change kind (#9964)

* bump sqlparse

* changelog
# Conflicts:
#	core/setup.py

.bumpversion.cfg

@@ -1,13 +1,19 @@
 [bumpversion]
-current_version = 1.0.1
-parse = (?P<major>\d+)
-	\.(?P<minor>\d+)
-	\.(?P<patch>\d+)
-	((?P<prekind>a|b|rc)
-	(?P<pre>\d+)  # pre-release version num
+current_version = 1.5.11
+parse = (?P<major>[\d]+) # major version number
+	\.(?P<minor>[\d]+) # minor version number
+	\.(?P<patch>[\d]+) # patch version number
+	(?P<prerelease>  # optional pre-release - ex: a1, b2, rc25
+	(?P<prekind>a|b|rc) # pre-release type
+	(?P<num>[\d]+) # pre-release version number
 	)?
+	( # optional nightly release indicator
+	\.(?P<nightly>dev[0-9]+) # ex: .dev02142023
+	)? # expected matches: `1.15.0`, `1.5.0a11`, `1.5.0a1.dev123`, `1.5.0.dev123457`, expected failures: `1`, `1.5`, `1.5.2-a1`, `text1.5.0`
 serialize =
-	{major}.{minor}.{patch}{prekind}{pre}
+	{major}.{minor}.{patch}{prekind}{num}.{nightly}
+	{major}.{minor}.{patch}.{nightly}
+	{major}.{minor}.{patch}{prekind}{num}
 	{major}.{minor}.{patch}
 commit = False
 tag = False
@@ -21,19 +27,21 @@ values =
 	rc
 	final
 
-[bumpversion:part:pre]
+[bumpversion:part:num]
 first_value = 1
 
-[bumpversion:file:setup.py]
+[bumpversion:part:nightly]
 
 [bumpversion:file:core/setup.py]
 
 [bumpversion:file:core/dbt/version.py]
 
-[bumpversion:file:core/scripts/create_adapter_plugins.py]
-
 [bumpversion:file:plugins/postgres/setup.py]
 
 [bumpversion:file:plugins/postgres/dbt/adapters/postgres/__version__.py]
 
 [bumpversion:file:docker/Dockerfile]
+
+[bumpversion:file:tests/adapter/setup.py]
+
+[bumpversion:file:tests/adapter/dbt/tests/adapter/__version__.py]

.changes/0.0.0.md

@@ -0,0 +1,21 @@
+## Previous Releases
+
+For information on prior major and minor releases, see their changelogs:
+
+
+* [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)
+* [1.3](https://github.com/dbt-labs/dbt-core/blob/1.3.latest/CHANGELOG.md)
+* [1.2](https://github.com/dbt-labs/dbt-core/blob/1.2.latest/CHANGELOG.md)
+* [1.1](https://github.com/dbt-labs/dbt-core/blob/1.1.latest/CHANGELOG.md)
+* [1.0](https://github.com/dbt-labs/dbt-core/blob/1.0.latest/CHANGELOG.md)
+* [0.21](https://github.com/dbt-labs/dbt-core/blob/0.21.latest/CHANGELOG.md)
+* [0.20](https://github.com/dbt-labs/dbt-core/blob/0.20.latest/CHANGELOG.md)
+* [0.19](https://github.com/dbt-labs/dbt-core/blob/0.19.latest/CHANGELOG.md)
+* [0.18](https://github.com/dbt-labs/dbt-core/blob/0.18.latest/CHANGELOG.md)
+* [0.17](https://github.com/dbt-labs/dbt-core/blob/0.17.latest/CHANGELOG.md)
+* [0.16](https://github.com/dbt-labs/dbt-core/blob/0.16.latest/CHANGELOG.md)
+* [0.15](https://github.com/dbt-labs/dbt-core/blob/0.15.latest/CHANGELOG.md)
+* [0.14](https://github.com/dbt-labs/dbt-core/blob/0.14.latest/CHANGELOG.md)
+* [0.13](https://github.com/dbt-labs/dbt-core/blob/0.13.latest/CHANGELOG.md)
+* [0.12](https://github.com/dbt-labs/dbt-core/blob/0.12.latest/CHANGELOG.md)
+* [0.11 and earlier](https://github.com/dbt-labs/dbt-core/blob/0.11.latest/CHANGELOG.md)

.changes/1.5.0.md

@@ -0,0 +1,189 @@
+## dbt-core 1.5.0 - April 27, 2023
+
+### Breaking Changes
+
+- Allow `--select` and `--exclude` multiple times ([#7158](https://github.com/dbt-labs/dbt-core/issues/7158))
+- Specifying "log-path" and "target-path" in "dbt_project.yml" is deprecated. This functionality will be removed in a future version of dbt-core. If you need to specify a custom path for logs or artifacts, please set via CLI flag or env var instead. ([#6882](https://github.com/dbt-labs/dbt-core/issues/6882))
+- Remove exception functions marked as deprecated in 1.4 release ([#6578](https://github.com/dbt-labs/dbt-core/issues/6578))
+
+### Features
+
+- Data type constraints are now native to SQL table materializations. Enforce columns are specific data types and not null depending on database functionality. ([#6079](https://github.com/dbt-labs/dbt-core/issues/6079))
+- Have dbt debug spit out structured json logs with flags enabled. ([#5353](https://github.com/dbt-labs/dbt-core/issues/5353))
+- ✨ add unix-style wildcard selector method ([#6598](https://github.com/dbt-labs/dbt-core/issues/6598))
+- add adapter_response to dbt test and freshness result ([#2964](https://github.com/dbt-labs/dbt-core/issues/2964))
+- add support for DBT_PROJECT_DIR env var ([#6078](https://github.com/dbt-labs/dbt-core/issues/6078))
+- Improve error message for packages missing `dbt_project.yml` ([#6663](https://github.com/dbt-labs/dbt-core/issues/6663))
+- Make project version optional ([#6603](https://github.com/dbt-labs/dbt-core/issues/6603))
+- Adjust makefile to have clearer instructions for CI env var changes. ([#6689](https://github.com/dbt-labs/dbt-core/issues/6689))
+- Stand-alone Python module for PostgresColumn ([#6772](https://github.com/dbt-labs/dbt-core/issues/6772))
+- Enable diff based partial parsing ([#6592](https://github.com/dbt-labs/dbt-core/issues/6592))
+- Exposure owner requires one of name or email keys, and accepts additional arbitrary keys ([#6833](https://github.com/dbt-labs/dbt-core/issues/6833))
+- Parse 'group' resource ([#6921](https://github.com/dbt-labs/dbt-core/issues/6921))
+- parse 'group' config on groupable nodes ([#6823](https://github.com/dbt-labs/dbt-core/issues/6823))
+- Implemented new log cli parameters for finer-grained control. ([#6639](https://github.com/dbt-labs/dbt-core/issues/6639))
+- Add access attribute to parsed nodes ([#6824](https://github.com/dbt-labs/dbt-core/issues/6824))
+- Enforce contracts on models materialized as tables, views, and incremental ([#6751](https://github.com/dbt-labs/dbt-core/issues/6751), [#7034](https://github.com/dbt-labs/dbt-core/issues/7034), [#6756](https://github.com/dbt-labs/dbt-core/issues/6756), [#7154](https://github.com/dbt-labs/dbt-core/issues/7154))
+- Add ability to select by group resource ([#6825](https://github.com/dbt-labs/dbt-core/issues/6825))
+- Disallow refing private model across groups ([#6826](https://github.com/dbt-labs/dbt-core/issues/6826))
+- make version configs optional ([#7054](https://github.com/dbt-labs/dbt-core/issues/7054))
+- [CT-1584] New top level commands: interactive compile ([#6358](https://github.com/dbt-labs/dbt-core/issues/6358))
+- Make model contracts agnostic to ordering ([#6975](https://github.com/dbt-labs/dbt-core/issues/6975), [#7064](https://github.com/dbt-labs/dbt-core/issues/7064))
+- Unified constraints and check_constraints properties for columns and models ([#7066](https://github.com/dbt-labs/dbt-core/issues/7066))
+- Switch from betterproto to google protobuf and enable more flexible meta dictionary in logs ([#6832](https://github.com/dbt-labs/dbt-core/issues/6832))
+- Ignore duplicate edges in subgraph to speed up dbt build ([#7191](https://github.com/dbt-labs/dbt-core/issues/7191))
+- Support setting of callbacks for programmatic uses of `dbtRunner` ([#6763](https://github.com/dbt-labs/dbt-core/issues/6763))
+- Detect breaking changes to contracts in state:modified check ([#6869](https://github.com/dbt-labs/dbt-core/issues/6869))
+- New command: dbt show ([#7207](https://github.com/dbt-labs/dbt-core/issues/7207), [#7179](https://github.com/dbt-labs/dbt-core/issues/7179), [#6359](https://github.com/dbt-labs/dbt-core/issues/6359))
+- Added prettier printing to ContractError class ([#7209](https://github.com/dbt-labs/dbt-core/issues/7209))
+- Add support for model-level constraints ([#6754](https://github.com/dbt-labs/dbt-core/issues/6754))
+- model versions ([##7263](https://github.com/dbt-labs/dbt-core/issues/#7263))
+- Add relation info (database, schema, alias) to node_info dictionary in structured logging ([#6724](https://github.com/dbt-labs/dbt-core/issues/6724))
+- Add --no-populate-cache to optionally skip relation cache population ([#1751](https://github.com/dbt-labs/dbt-core/issues/1751))
+- select resources by patch path ([#7315](https://github.com/dbt-labs/dbt-core/issues/7315))
+- Add version selector method ([#7199](https://github.com/dbt-labs/dbt-core/issues/7199))
+
+### Fixes
+
+- Remove trailing slashes from source paths (#6102) ([#6102](https://github.com/dbt-labs/dbt-core/issues/6102))
+- add merge_exclude_columns adapter tests ([#6699](https://github.com/dbt-labs/dbt-core/issues/6699))
+- Include adapter_response in NodeFinished run_result log event ([#6703](https://github.com/dbt-labs/dbt-core/issues/6703))
+- Sort cli vars before hashing for partial parsing ([#6710](https://github.com/dbt-labs/dbt-core/issues/6710))
+- [Regression] exposure_content referenced incorrectly ([#6738](https://github.com/dbt-labs/dbt-core/issues/6738))
+- Snapshot strategies: add a newline for subquery ([#6781](https://github.com/dbt-labs/dbt-core/issues/6781))
+- Remove pin on packaging and stop using it for prerelease comparisons ([#6834](https://github.com/dbt-labs/dbt-core/issues/6834))
+- Readd depends_on.macros to SeedNode, to support seeds with hooks calling macros ([#6806](https://github.com/dbt-labs/dbt-core/issues/6806))
+- Fix regression of --quiet cli parameter behavior ([#6749](https://github.com/dbt-labs/dbt-core/issues/6749))
+- Add double type to list of float column types for the column class ([#6876](https://github.com/dbt-labs/dbt-core/issues/6876))
+- Ensure results from hooks contain nodes when processing them ([#6796](https://github.com/dbt-labs/dbt-core/issues/6796))
+- Always flush stdout after logging ([#6901](https://github.com/dbt-labs/dbt-core/issues/6901))
+- Reapply logging fixes which were accidentally reverted ([#6936](https://github.com/dbt-labs/dbt-core/issues/6936))
+- Set relation_name in test nodes at compile time ([#6930](https://github.com/dbt-labs/dbt-core/issues/6930))
+- Readd initialization events, --log-cache-events in new CLI ([#6933](https://github.com/dbt-labs/dbt-core/issues/6933))
+- Fix previous state tests and disabled exposures, metrics ([#6752](https://github.com/dbt-labs/dbt-core/issues/6752), [#6753](https://github.com/dbt-labs/dbt-core/issues/6753))
+- Make use of hashlib.md5() FIPS compliant ([#6900](https://github.com/dbt-labs/dbt-core/issues/6900))
+- add timeout for dbt --version command ([#6992](https://github.com/dbt-labs/dbt-core/issues/6992))
+- Fix compilation logic for ephemeral nodes ([#6885](https://github.com/dbt-labs/dbt-core/issues/6885))
+- Fix semver comparison logic by ensuring numeric values ([#7039](https://github.com/dbt-labs/dbt-core/issues/7039))
+- add pytz dependency ([#7077](https://github.com/dbt-labs/dbt-core/issues/7077))
+- allow adapters to change model name resolution in py models ([#7114](https://github.com/dbt-labs/dbt-core/issues/7114))
+- Add exception handling in postflight decorator to address exit codes ([#7010](https://github.com/dbt-labs/dbt-core/issues/7010))
+- Recreates missing tracking events ([#6097](https://github.com/dbt-labs/dbt-core/issues/6097), [#6098](https://github.com/dbt-labs/dbt-core/issues/6098))
+- Fix partial parsing error due to not requiring "version" ([#7236](https://github.com/dbt-labs/dbt-core/issues/7236))
+- Handle internal exceptions ([#7118](https://github.com/dbt-labs/dbt-core/issues/7118))
+- Improved failed event serialization handling and associated tests ([#7113](https://github.com/dbt-labs/dbt-core/issues/7113), [#7108](https://github.com/dbt-labs/dbt-core/issues/7108), [#6568](https://github.com/dbt-labs/dbt-core/issues/6568))
+- Fix handling of artifacts in read_and_check_versions ([#7252](https://github.com/dbt-labs/dbt-core/issues/7252))
+- Stringify datetimes in logging for prettier messages ([#7255](https://github.com/dbt-labs/dbt-core/issues/7255))
+- avoid dbtRunner default callbacks being shared across instances ([#7278](https://github.com/dbt-labs/dbt-core/issues/7278))
+- Ensure same_contract is called for state:modified ([#7282](https://github.com/dbt-labs/dbt-core/issues/7282))
+- Avoid revoking grants for views when `copy_grants=true` ([#7280](https://github.com/dbt-labs/dbt-core/issues/7280))
+- Duplicated flags now throw errors instead of being overidden by parent-level flag ([#6913](https://github.com/dbt-labs/dbt-core/issues/6913))
+- Ensure that invocation_id changes between programmatic invocations. ([#7197](https://github.com/dbt-labs/dbt-core/issues/7197))
+- Adding a new column is not a breaking contract change ([#7332](https://github.com/dbt-labs/dbt-core/issues/7332))
+- fix versioned model selection in subdirectories ([#7348](https://github.com/dbt-labs/dbt-core/issues/7348))
+- safe version attribute access in _check_resource_uniqueness ([#7375](https://github.com/dbt-labs/dbt-core/issues/7375))
+- Fix dbt command missing target-path param ([#	7411](https://github.com/dbt-labs/dbt-core/issues/	7411))
+- Fix v0 ref resolution ([#7408](https://github.com/dbt-labs/dbt-core/issues/7408))
+- fix groupable node partial parsing, raise DbtReferenceError at runtime for safety ([#7437](https://github.com/dbt-labs/dbt-core/issues/7437))
+- Fix partial parsing of latest_version changes for downstream references ([#7369](https://github.com/dbt-labs/dbt-core/issues/7369))
+
+### Docs
+
+- Improve displayed message under "Arguments" section for argumentless macro ([dbt-docs/#358](https://github.com/dbt-labs/dbt-docs/issues/358))
+- update link to installation instructions ([dbt-docs/#None](https://github.com/dbt-labs/dbt-docs/issues/None))
+- Fix JSON path to overview docs ([dbt-docs/#366](https://github.com/dbt-labs/dbt-docs/issues/366))
+- Searchable column descriptions ([dbt-docs/#140](https://github.com/dbt-labs/dbt-docs/issues/140), [dbt-docs/#322](https://github.com/dbt-labs/dbt-docs/issues/322), [dbt-docs/#369](https://github.com/dbt-labs/dbt-docs/issues/369))
+- Add access property to model details ([dbt-docs/#381](https://github.com/dbt-labs/dbt-docs/issues/381))
+- Display model owner by name and email ([dbt-docs/#377](https://github.com/dbt-labs/dbt-docs/issues/377))
+- Add view of public models sorted by group to left navigation ([dbt-docs/#379](https://github.com/dbt-labs/dbt-docs/issues/379))
+- Distiguish node "access" in the DAG with node borders & opacity. ([dbt-docs/#378](https://github.com/dbt-labs/dbt-docs/issues/378))
+- Fix JSON path to package overview docs ([dbt-docs/#390](https://github.com/dbt-labs/dbt-docs/issues/390))
+- Add selection by group to DAG ([dbt-docs/#380](https://github.com/dbt-labs/dbt-docs/issues/380))
+- Add support for model versions ([dbt-docs/#406](https://github.com/dbt-labs/dbt-docs/issues/406))
+
+### Under the Hood
+
+- [CT-921] dbt compile works in click ([#5545](https://github.com/dbt-labs/dbt-core/issues/5545))
+- Fix use of ConnectionReused logging event ([#6168](https://github.com/dbt-labs/dbt-core/issues/6168))
+- Port docs tests to pytest ([#6573](https://github.com/dbt-labs/dbt-core/issues/6573))
+- Update deprecated github action command ([#6153](https://github.com/dbt-labs/dbt-core/issues/6153))
+- dbt snapshot works in click ([#5554](https://github.com/dbt-labs/dbt-core/issues/5554))
+- dbt list working with click ([#5549](https://github.com/dbt-labs/dbt-core/issues/5549))
+- Add dbt run-operation to click CLI ([#5552](https://github.com/dbt-labs/dbt-core/issues/5552))
+- dbt build working with new click framework ([#5541](https://github.com/dbt-labs/dbt-core/issues/5541))
+- dbt docs generate works with new click framework ([#5543](https://github.com/dbt-labs/dbt-core/issues/5543))
+- Replaced the EmptyLine event with a more general Formatting event, and added a Note event. ([#6481](https://github.com/dbt-labs/dbt-core/issues/6481))
+- Small optimization on manifest parsing benefitting large DAGs ([#6697](https://github.com/dbt-labs/dbt-core/issues/6697))
+- Revised and simplified various structured logging events ([#6664](https://github.com/dbt-labs/dbt-core/issues/6664), [#6665](https://github.com/dbt-labs/dbt-core/issues/6665), [#6666](https://github.com/dbt-labs/dbt-core/issues/6666))
+- dbt init works with click ([#5548](https://github.com/dbt-labs/dbt-core/issues/5548))
+- [CT-920][CT-1900] Create Click CLI runner and use it to fix dbt docs commands ([#5544](https://github.com/dbt-labs/dbt-core/issues/5544), [#6722](https://github.com/dbt-labs/dbt-core/issues/6722))
+- Migrate debug task to click ([#5546](https://github.com/dbt-labs/dbt-core/issues/5546))
+-  Optimized GraphQueue to remove graph analysis bottleneck in large dags. ([#6759](https://github.com/dbt-labs/dbt-core/issues/6759))
+- Implement --version for click cli ([#6757](https://github.com/dbt-labs/dbt-core/issues/6757))
+- [CT-1841] Convert custom target test to Pytest ([#6638](https://github.com/dbt-labs/dbt-core/issues/6638))
+- Remove BigQuery-specific btye abbreviations ([#6741](https://github.com/dbt-labs/dbt-core/issues/6741))
+- warn_error/warn_error_options mutual exclusivity in click ([#6579](https://github.com/dbt-labs/dbt-core/issues/6579))
+- Enables the new Click Cli on the commandline! 🚀 ([#6784](https://github.com/dbt-labs/dbt-core/issues/6784))
+- Lazily call --version ([#6812](https://github.com/dbt-labs/dbt-core/issues/6812))
+- Moving simple_seed to adapter zone to help adapter test conversions ([#CT-1959](https://github.com/dbt-labs/dbt-core/issues/CT-1959))
+- flags.THREADS defaults to None ([#6887](https://github.com/dbt-labs/dbt-core/issues/6887))
+- Fixing target type exposure error ([#6928](https://github.com/dbt-labs/dbt-core/issues/6928))
+- Test binary serialization of logging events ([#6852](https://github.com/dbt-labs/dbt-core/issues/6852))
+- Treat contract config as a python object ([#6748](https://github.com/dbt-labs/dbt-core/issues/6748), [#7184](https://github.com/dbt-labs/dbt-core/issues/7184))
+- Add deprecation warning for DBT_NO_PRINT ([#6960](https://github.com/dbt-labs/dbt-core/issues/6960))
+- Make output_keys click param multi-option instead of a string ([#6676](https://github.com/dbt-labs/dbt-core/issues/6676))
+- Remove cli doc generation workflow ([#7088](https://github.com/dbt-labs/dbt-core/issues/7088))
+- Move validation of group earlier ([#7087](https://github.com/dbt-labs/dbt-core/issues/7087))
+- Deprecate additional environment variables ([#6903](https://github.com/dbt-labs/dbt-core/issues/6903))
+- Add CommandCompleted event, and fire it upon completion of every command ([#6878](https://github.com/dbt-labs/dbt-core/issues/6878))
+- Improves build times for common selections by improving subgraph calculation ([#7195](https://github.com/dbt-labs/dbt-core/issues/7195))
+- Remove upper pin for hologram/jsonschema ([#6775](https://github.com/dbt-labs/dbt-core/issues/6775))
+- Generalize constraint compatibility warnings ([#7067](https://github.com/dbt-labs/dbt-core/issues/7067))
+- Add kwargs support to dbtRunner ([#7070](https://github.com/dbt-labs/dbt-core/issues/7070))
+- Add unique_id to ShowNode and CompiledNode logging events ([#7305](https://github.com/dbt-labs/dbt-core/issues/7305))
+- Prettify message for ListRelations event ([#7310](https://github.com/dbt-labs/dbt-core/issues/7310))
+- `Parse` now returns manifest when invoked via dbtRunner ([#6547](https://github.com/dbt-labs/dbt-core/issues/6547))
+- Track data about group, access, contract, version usage ([#7170](https://github.com/dbt-labs/dbt-core/issues/7170), [#7171](https://github.com/dbt-labs/dbt-core/issues/7171))
+- Update docs link in ContractBreakingChangeError message ([#7366](https://github.com/dbt-labs/dbt-core/issues/7366))
+- Update --help text for cache-related parameters ([#7381](https://github.com/dbt-labs/dbt-core/issues/7381))
+- Small UX improvements to model versions: Support defining latest_version in unsuffixed file by default. Notify on unpinned ref when a prerelease version is available.  ([#7443](https://github.com/dbt-labs/dbt-core/issues/7443))
+
+### Dependencies
+
+- Update pathspec requirement from <0.11,>=0.9 to >=0.9,<0.12 in /core ([#6737](https://github.com/dbt-labs/dbt-core/pull/6737))
+- Bump ubuntu from 22.04 to 23.04 ([#6865](https://github.com/dbt-labs/dbt-core/pull/6865))
+- Revert hoisting dbt.cli.main into the dbt.name namespace ([#](https://github.com/dbt-labs/dbt-core/pull/))
+- Bump python from 3.11.1-slim-bullseye to 3.11.2-slim-bullseye in /docker ([#7196](https://github.com/dbt-labs/dbt-core/pull/7196))
+- Bump black from 22.12.0 to 23.3.0 ([#7243](https://github.com/dbt-labs/dbt-core/pull/7243))
+- Bump mashumaro[msgpack] from 3.3.1 to 3.6 ([#7294](https://github.com/dbt-labs/dbt-core/pull/7294))
+
+### Dependency
+
+- Bump mypy from 0.971 to 0.981 ([#4904](https://github.com/dbt-labs/dbt-core/issues/4904))
+- Bump python from 3.10.7-slim-bullseye to 3.11.1-slim-bullseye in /docker ([#4904](https://github.com/dbt-labs/dbt-core/issues/4904))
+- Bump black from 22.10.0 to 22.12.0 ([#4904](https://github.com/dbt-labs/dbt-core/issues/4904))
+
+### Contributors
+- [@@ttusing](https://github.com/@ttusing) ([#7195](https://github.com/dbt-labs/dbt-core/issues/7195))
+- [@Goodkat](https://github.com/Goodkat) ([#6992](https://github.com/dbt-labs/dbt-core/issues/6992))
+- [@MartinGuindon](https://github.com/MartinGuindon) ([#358](https://github.com/dbt-labs/dbt-core/issues/358))
+- [@MatthieuBlais](https://github.com/MatthieuBlais) ([#7191](https://github.com/dbt-labs/dbt-core/issues/7191))
+- [@RobbertDM](https://github.com/RobbertDM) ([#6781](https://github.com/dbt-labs/dbt-core/issues/6781))
+- [@aezomz](https://github.com/aezomz) ([#2964](https://github.com/dbt-labs/dbt-core/issues/2964))
+- [@benallard](https://github.com/benallard) ([#7294](https://github.com/dbt-labs/dbt-core/pull/7294))
+- [@boxysean](https://github.com/boxysean) ([#6697](https://github.com/dbt-labs/dbt-core/issues/6697))
+- [@callum-mcdata](https://github.com/callum-mcdata) ([#6928](https://github.com/dbt-labs/dbt-core/issues/6928))
+- [@chamini2](https://github.com/chamini2) ([#7278](https://github.com/dbt-labs/dbt-core/issues/7278))
+- [@dave-connors-3](https://github.com/dave-connors-3) ([#7054](https://github.com/dbt-labs/dbt-core/issues/7054), [#7315](https://github.com/dbt-labs/dbt-core/issues/7315), [#6699](https://github.com/dbt-labs/dbt-core/issues/6699))
+- [@davidbloss](https://github.com/davidbloss) ([#6153](https://github.com/dbt-labs/dbt-core/issues/6153))
+- [@halvorlu](https://github.com/halvorlu) ([#366](https://github.com/dbt-labs/dbt-core/issues/366))
+- [@jmg-duarte](https://github.com/jmg-duarte) ([#6102](https://github.com/dbt-labs/dbt-core/issues/6102))
+- [@kentkr](https://github.com/kentkr) ([#7209](https://github.com/dbt-labs/dbt-core/issues/7209))
+- [@leo-schick](https://github.com/leo-schick) ([#6078](https://github.com/dbt-labs/dbt-core/issues/6078))
+- [@nielspardon](https://github.com/nielspardon) ([#6900](https://github.com/dbt-labs/dbt-core/issues/6900))
+- [@rlh1994](https://github.com/rlh1994) ([#6876](https://github.com/dbt-labs/dbt-core/issues/6876), [#390](https://github.com/dbt-labs/dbt-core/issues/390))
+- [@ryancharris](https://github.com/ryancharris) ([#None](https://github.com/dbt-labs/dbt-core/issues/None))
+- [@sdebruyn](https://github.com/sdebruyn) ([#7077](https://github.com/dbt-labs/dbt-core/issues/7077))
+- [@seub](https://github.com/seub) ([#6603](https://github.com/dbt-labs/dbt-core/issues/6603))
+- [@sungchun12](https://github.com/sungchun12) ([#6079](https://github.com/dbt-labs/dbt-core/issues/6079))
+- [@z3z1ma](https://github.com/z3z1ma) ([#6598](https://github.com/dbt-labs/dbt-core/issues/6598))

.changes/1.5.1.md

@@ -0,0 +1,23 @@
+## dbt-core 1.5.1 - May 30, 2023
+
+### Fixes
+
+- fix typo in unpacking statically parsed ref ([#7364](https://github.com/dbt-labs/dbt-core/issues/7364))
+- Fix inverted `--print/--no-print` flag ([#7517](https://github.com/dbt-labs/dbt-core/issues/7517))
+- Back-compat for previous return type of 'collect_freshness' macro ([#7489](https://github.com/dbt-labs/dbt-core/issues/7489))
+- print model version in dbt show if specified ([#7407](https://github.com/dbt-labs/dbt-core/issues/7407))
+- Allow missing `profiles.yml` for `dbt deps` and `dbt init` ([#7511](https://github.com/dbt-labs/dbt-core/issues/7511))
+- Do not rewrite manifest.json during 'docs serve' command ([#7553](https://github.com/dbt-labs/dbt-core/issues/7553))
+- Pin protobuf to greater than 4.0.0 ([#7565](https://github.com/dbt-labs/dbt-core/issues/7565))
+- Throw error for duplicated versioned and unversioned models ([#7487](https://github.com/dbt-labs/dbt-core/issues/7487))
+- Fix: Relative project paths weren't working with deps ([#7491](https://github.com/dbt-labs/dbt-core/issues/7491))
+- Fall back if rendering the password field fails. ([#7629](https://github.com/dbt-labs/dbt-core/issues/7629))
+- Stringify flag paths for Jinja context ([#7495](https://github.com/dbt-labs/dbt-core/issues/7495))
+
+### Under the Hood
+
+- Remove legacy file logger code ([#NA](https://github.com/dbt-labs/dbt-core/issues/NA))
+
+### Contributors
+- [@iknox-fa](https://github.com/iknox-fa) ([#7491](https://github.com/dbt-labs/dbt-core/issues/7491), [#NA](https://github.com/dbt-labs/dbt-core/issues/NA))
+- [@thomasgjerdekog](https://github.com/thomasgjerdekog) ([#7517](https://github.com/dbt-labs/dbt-core/issues/7517))

.changes/1.5.10.md

@@ -0,0 +1,9 @@
+## dbt-core 1.5.10 - February 28, 2024
+
+### Under the Hood
+
+- Restrict protobuf to major version 4. ([#9566](https://github.com/dbt-labs/dbt-core/issues/9566))
+
+### Security
+
+- Update Jinja2 to >= 3.1.3 to address CVE-2024-22195 ([#CVE-2024-22195](https://github.com/dbt-labs/dbt-core/pull/CVE-2024-22195))

.changes/1.5.11.md

@@ -0,0 +1,5 @@
+## dbt-core 1.5.11 - March 28, 2024
+
+### Dependencies
+
+- Restrict protobuf to 4.* versions ([#9566](https://github.com/dbt-labs/dbt-core/pull/9566))

.changes/1.5.2.md

@@ -0,0 +1,26 @@
+## dbt-core 1.5.2 - June 22, 2023
+
+### Features
+
+- add access selection syntax ([#7738](https://github.com/dbt-labs/dbt-core/issues/7738))
+- Add AdapterRegistered event log message ([#7038](https://github.com/dbt-labs/dbt-core/issues/7038))
+
+### Fixes
+
+- Add --target-path to dbt snapshot command. ([#7418](https://github.com/dbt-labs/dbt-core/issues/7418))
+- Constraint rendering fixes: wrap check expression in parentheses, foreign key 'references', support expression in all constraint types ([#7417](https://github.com/dbt-labs/dbt-core/issues/7417), [#7480](https://github.com/dbt-labs/dbt-core/issues/7480), [#7416](https://github.com/dbt-labs/dbt-core/issues/7416))
+- Fix warning messages for deprecated dbt_project.yml configs ([#7424](https://github.com/dbt-labs/dbt-core/issues/7424))
+- Respect column 'quote' config in model contracts ([#7370](https://github.com/dbt-labs/dbt-core/issues/7370))
+- Improve warnings for constraints and materialization types ([#7335](https://github.com/dbt-labs/dbt-core/issues/7335))
+- Incorrect paths used for "target" and "state" directories ([#7465](https://github.com/dbt-labs/dbt-core/issues/7465))
+- Using version 0 works when resolving single model ([#7372](https://github.com/dbt-labs/dbt-core/issues/7372))
+- Fix empty --warn-error-options error message ([#7730](https://github.com/dbt-labs/dbt-core/issues/7730))
+- send sql header on contract enforcement ([#7714](https://github.com/dbt-labs/dbt-core/issues/7714))
+- Fix path selector when using project-dir ([#7819](https://github.com/dbt-labs/dbt-core/issues/7819))
+- Allow dbt show --inline preview of private models ([#7837](https://github.com/dbt-labs/dbt-core/issues/7837))
+- Updating this error message to point to the correct URL ([#7789](https://github.com/dbt-labs/dbt-core/issues/7789))
+
+### Contributors
+- [@dave-connors-3](https://github.com/dave-connors-3) ([#7738](https://github.com/dbt-labs/dbt-core/issues/7738))
+- [@dwreeves](https://github.com/dwreeves) ([#7418](https://github.com/dbt-labs/dbt-core/issues/7418))
+- [@mirnawong1](https://github.com/mirnawong1) ([#7789](https://github.com/dbt-labs/dbt-core/issues/7789))

.changes/1.5.3.md

@@ -0,0 +1,18 @@
+## dbt-core 1.5.3 - July 17, 2023
+
+### Fixes
+
+- Add --target-path to more CLI subcommands ([#7646](https://github.com/dbt-labs/dbt-core/issues/7646))
+- Remove limitation on use of sqlparse 0.4.4 ([#7515](https://github.com/dbt-labs/dbt-core/issues/7515))
+- Move project_root contextvar into events.contextvars ([#7937](https://github.com/dbt-labs/dbt-core/issues/7937))
+- Inline query emit proper error message ([#7940](https://github.com/dbt-labs/dbt-core/issues/7940))
+- Allow on_schema_change = fail for contracted incremental models ([#7975](https://github.com/dbt-labs/dbt-core/issues/7975))
+- Nicer error message if model with enforced contract is missing 'columns' specification ([#7943](https://github.com/dbt-labs/dbt-core/issues/7943))
+- Detect breaking contract changes to versioned models ([#8030](https://github.com/dbt-labs/dbt-core/issues/8030))
+
+### Dependencies
+
+- Pin click>=7.0,<8.1.4 ([#8050](https://github.com/dbt-labs/dbt-core/pull/8050))
+
+### Contributors
+- [@dwreeves](https://github.com/dwreeves) ([#7646](https://github.com/dbt-labs/dbt-core/issues/7646))

.changes/1.5.4.md

@@ -0,0 +1,10 @@
+## dbt-core 1.5.4 - July 28, 2023
+
+### Fixes
+
+- Ensure `warn_error_options` get serialized in `invocation_args_dict` ([#7694](https://github.com/dbt-labs/dbt-core/issues/7694))
+- Improve handling of CTE injection with ephemeral models ([#8213](https://github.com/dbt-labs/dbt-core/issues/8213))
+
+### Under the Hood
+
+- Refactor flaky test pp_versioned_models ([#7781](https://github.com/dbt-labs/dbt-core/issues/7781))

.changes/1.5.5.md

@@ -0,0 +1,16 @@
+## dbt-core 1.5.5 - August 17, 2023
+
+### Fixes
+
+- Copy target_schema from config into snapshot node ([#6745](https://github.com/dbt-labs/dbt-core/issues/6745))
+- Add status to Parse Inline Error ([#8173](https://github.com/dbt-labs/dbt-core/issues/8173))
+- Fix using list command with path selector and project-dir ([#8385](https://github.com/dbt-labs/dbt-core/issues/8385))
+
+### Under the Hood
+
+- A way to control maxBytes for a single dbt.log file ([#8199](https://github.com/dbt-labs/dbt-core/issues/8199))
+
+### Dependencies
+
+- Update pin for click<9 ([#8232](https://github.com/dbt-labs/dbt-core/pull/8232))
+- Add upper bound to sqlparse pin of <0.5 ([#8236](https://github.com/dbt-labs/dbt-core/pull/8236))

.changes/1.5.6.md

@@ -0,0 +1,5 @@
+## dbt-core 1.5.6 - August 21, 2023
+
+### Under the Hood
+
+- Use python version 3.10.7 in Docker image. ([#8444](https://github.com/dbt-labs/dbt-core/issues/8444))

.changes/1.5.7.md

@@ -0,0 +1,12 @@
+## dbt-core 1.5.7 - September 28, 2023
+
+### Features
+
+- Accept a `dbt-cloud` config in dbt_project.yml ([#8438](https://github.com/dbt-labs/dbt-core/issues/8438))
+
+### Fixes
+
+- Fix snapshot success message ([#7583](https://github.com/dbt-labs/dbt-core/issues/7583))
+- update dbt show to include limit in DWH query  ([#8496,](https://github.com/dbt-labs/dbt-core/issues/8496,), [#8417](https://github.com/dbt-labs/dbt-core/issues/8417))
+- Support quoted parameter list for MultiOption CLI options. ([#8598](https://github.com/dbt-labs/dbt-core/issues/8598))
+- avoid double-rendering sql_header in dbt show ([#8739](https://github.com/dbt-labs/dbt-core/issues/8739))

.changes/1.5.8.md

@@ -0,0 +1,9 @@
+## dbt-core 1.5.8 - October 11, 2023
+
+### Fixes
+
+- Support global flags passed in after subcommands ([#6497](https://github.com/dbt-labs/dbt-core/issues/6497))
+- Foreign key constraint on incremental model results in Database Error ([#8022](https://github.com/dbt-labs/dbt-core/issues/8022))
+- Support docs blocks on versioned model column descriptions ([#8540](https://github.com/dbt-labs/dbt-core/issues/8540))
+- Enable seeds to be handled from stored manifest data ([#6875](https://github.com/dbt-labs/dbt-core/issues/6875))
+- Group updates on unmodified nodes are handled gracefully for state:modified ([#8371](https://github.com/dbt-labs/dbt-core/issues/8371))

.changes/1.5.9.md

@@ -0,0 +1,5 @@
+## dbt-core 1.5.9 - October 31, 2023
+
+### Fixes
+
+- Add back contract enforcement for temporary tables on postgres ([#8857](https://github.com/dbt-labs/dbt-core/issues/8857))

.changes/README.md

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

.changes/header.tpl.md

@@ -0,0 +1,6 @@
+# dbt Core Changelog
+
+- This file provides a full account of all changes to `dbt-core` and `dbt-postgres`
+- Changes are listed under the (pre)release in which they first appear. Subsequent releases include changes from previous releases.
+- "Breaking changes" listed under a version may require action from end users or external maintainers when upgrading to that version.
+- Do not edit this file directly. This file is auto-generated using [changie](https://github.com/miniscruff/changie). For details on how to document a change, see [the contributing guide](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#adding-changelog-entry)

.changes/unreleased/Security-20240417-141316.yaml

@@ -0,0 +1,6 @@
+kind: Security
+body: Bump sqlparse to >=0.5.0, <0.6.0 to address GHSA-2m57-hf25-phgg
+time: 2024-04-17T14:13:16.896353-05:00
+custom:
+  Author: emmoop
+  Issue: "9951"

.changie.yaml

@@ -0,0 +1,140 @@
+changesDir: .changes
+unreleasedDir: unreleased
+headerPath: header.tpl.md
+versionHeaderPath: ""
+changelogPath: CHANGELOG.md
+versionExt: md
+envPrefix: "CHANGIE_"
+versionFormat: '## dbt-core {{.Version}} - {{.Time.Format "January 02, 2006"}}'
+kindFormat: '### {{.Kind}}'
+changeFormat: |-
+  {{- $IssueList := list }}
+  {{- $changes := splitList " " $.Custom.Issue }}
+  {{- range $issueNbr := $changes }}
+    {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/issues/nbr)" | replace "nbr" $issueNbr }}
+    {{- $IssueList = append $IssueList $changeLink  }}
+  {{- end -}}
+  - {{.Body}} ({{ range $index, $element := $IssueList }}{{if $index}}, {{end}}{{$element}}{{end}})
+
+kinds:
+  - label: Breaking Changes
+  - label: Features
+  - label: Fixes
+  - label: Docs
+    changeFormat: |-
+      {{- $IssueList := list }}
+      {{- $changes := splitList " " $.Custom.Issue }}
+      {{- range $issueNbr := $changes }}
+        {{- $changeLink := "[dbt-docs/#nbr](https://github.com/dbt-labs/dbt-docs/issues/nbr)" | replace "nbr" $issueNbr }}
+        {{- $IssueList = append $IssueList $changeLink }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $IssueList }}{{if $index}}, {{end}}{{$element}}{{end}})
+  - label: Under the Hood
+  - label: Dependencies
+    changeFormat: |-
+      {{- $PRList := list }}
+      {{- $changes := splitList " " $.Custom.PR }}
+      {{- range $pullrequest := $changes }}
+        {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $pullrequest }}
+        {{- $PRList = append $PRList $changeLink  }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $PRList }}{{if $index}}, {{end}}{{$element}}{{end}})
+    skipGlobalChoices: true
+    additionalChoices:
+      - key: Author
+        label: GitHub Username(s) (separated by a single space if multiple)
+        type: string
+        minLength: 3
+      - key: PR
+        label: GitHub Pull Request Number (separated by a single space if multiple)
+        type: string
+        minLength: 1
+  - label: Security
+    changeFormat: |-
+      {{- $PRList := list }}
+      {{- $changes := splitList " " $.Custom.PR }}
+      {{- range $pullrequest := $changes }}
+        {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $pullrequest }}
+        {{- $PRList = append $PRList $changeLink  }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $PRList }}{{if $index}}, {{end}}{{$element}}{{end}})
+    skipGlobalChoices: true
+    additionalChoices:
+      - key: Author
+        label: GitHub Username(s) (separated by a single space if multiple)
+        type: string
+        minLength: 3
+      - key: PR
+        label: GitHub Pull Request Number (separated by a single space if multiple)
+        type: string
+        minLength: 1
+
+newlines:
+  afterChangelogHeader: 1
+  afterKind: 1
+  afterChangelogVersion: 1
+  beforeKind: 1
+  endOfVersion: 1
+
+custom:
+- key: Author
+  label: GitHub Username(s) (separated by a single space if multiple)
+  type: string
+  minLength: 3
+- key: Issue
+  label: GitHub Issue Number (separated by a single space if multiple)
+  type: string
+  minLength: 1
+
+footerFormat: |
+  {{- $contributorDict := dict }}
+  {{- /* ensure all names in this list are all lowercase for later matching purposes */}}
+  {{- $core_team := splitList " " .Env.CORE_TEAM }}
+  {{- /* ensure we always skip snyk and dependabot in addition to the core team */}}
+  {{- $maintainers := list "dependabot[bot]" "snyk-bot"}}
+  {{- range $team_member := $core_team }}
+    {{- $team_member_lower := lower $team_member }}
+    {{- $maintainers = append $maintainers $team_member_lower }}
+  {{- end }}
+  {{- range $change := .Changes }}
+    {{- $authorList := splitList " " $change.Custom.Author }}
+    {{- /* loop through all authors for a single changelog */}}
+    {{- range $author := $authorList }}
+      {{- $authorLower := lower $author }}
+      {{- /* we only want to include non-core team contributors */}}
+      {{- if not (has $authorLower $maintainers)}}
+        {{- $changeList := splitList " " $change.Custom.Author }}
+          {{- $IssueList := list }}
+          {{- $changeLink := $change.Kind }}
+          {{- if or (eq $change.Kind "Dependencies") (eq $change.Kind "Security") }}
+            {{- $changes := splitList " " $change.Custom.PR }}
+            {{- range $issueNbr := $changes }}
+              {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $issueNbr }}
+              {{- $IssueList = append $IssueList $changeLink  }}
+            {{- end -}}
+          {{- else }}
+            {{- $changes := splitList " " $change.Custom.Issue }}
+            {{- range $issueNbr := $changes }}
+              {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/issues/nbr)" | replace "nbr" $issueNbr }}
+              {{- $IssueList = append $IssueList $changeLink  }}
+            {{- end -}}
+          {{- end }}
+          {{- /* check if this contributor has other changes associated with them already */}}
+          {{- if hasKey $contributorDict $author }}
+            {{- $contributionList := get $contributorDict $author }}
+            {{- $contributionList = concat $contributionList $IssueList  }}
+            {{- $contributorDict := set $contributorDict $author $contributionList }}
+          {{- else }}
+            {{- $contributionList := $IssueList }}
+            {{- $contributorDict := set $contributorDict $author $contributionList }}
+          {{- end }}
+        {{- end}}
+    {{- end}}
+  {{- end }}
+  {{- /* no indentation here for formatting so the final markdown doesn't have unneeded indentations */}}
+  {{- if $contributorDict}}
+  ### Contributors
+  {{- range $k,$v := $contributorDict }}
+  - [@{{$k}}](https://github.com/{{$k}}) ({{ range $index, $element := $v }}{{if $index}}, {{end}}{{$element}}{{end}})
+  {{- end }}
+  {{- end }}

.flake8

@@ -8,5 +8,5 @@ ignore =
     W504
     E203 # makes Flake8 work like black
     E741
-max-line-length = 99
-exclude = test
+    E501 # long line checking is done in black
+exclude = test/

.git-blame-ignore-revs

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

.gitattributes

@@ -0,0 +1,6 @@
+core/dbt/include/index.html binary
+tests/functional/artifacts/data/state/*/manifest.json binary
+core/dbt/docs/build/html/searchindex.js binary
+core/dbt/docs/build/html/index.html binary
+performance/runner/Cargo.lock binary
+core/dbt/events/types_pb2.py binary

.github/CODEOWNERS

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

.github/ISSUE_TEMPLATE/bug-report.yml

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

.github/ISSUE_TEMPLATE/config.yml

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

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -1,22 +1,32 @@
 name: ✨ Feature
-description: Suggest an idea for dbt
+description: Propose a straightforward extension of dbt functionality
 title: "[Feature] <title>"
 labels: ["enhancement", "triage"]
 body:
   - type: markdown
     attributes:
       value: |
-        Thanks for taking the time to fill out this feature requests!
+        Thanks for taking the time to fill out this feature request!
   - type: checkboxes
     attributes:
-      label: Is there an existing feature request for this?
-      description: Please search to see if an issue already exists for the feature you would like.
+      label: Is this your first time submitting a feature request?
+      description: >
+        We want to make sure that features are distinct and discoverable,
+        so that other members of the community can find them and offer their thoughts.
+
+        Issues are the right place to request straightforward extensions of existing dbt functionality.
+        For "big ideas" about future capabilities of dbt, we ask that you open a
+        [discussion](https://github.com/dbt-labs/dbt-core/discussions) in the "Ideas" category instead.
       options:
-        - label: I have searched the existing issues
+        - label: I have read the [expectations for open source contributors](https://docs.getdbt.com/docs/contributing/oss-expectations)
+          required: true
+        - label: I have searched the existing issues, and I could not find an existing issue for this feature
+          required: true
+        - label: I am requesting a straightforward extension of existing dbt functionality, rather than a Big Idea better suited to a discussion
           required: true
   - type: textarea
     attributes:
-      label: Describe the Feature
+      label: Describe the feature
       description: A clear and concise description of what you want to happen.
     validations:
       required: true

.github/ISSUE_TEMPLATE/regression-report.yml

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

.github/_README.md

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

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

@@ -13,7 +13,7 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Wrangle latest tag
       id: is_latest
       uses: ./.github/actions/latest-wrangler

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

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

.github/pull_request_template.md

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

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

@@ -1,95 +0,0 @@
-module.exports = ({ context }) => {
-  const defaultPythonVersion = "3.8";
-  const supportedPythonVersions = ["3.7", "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

@@ -13,22 +13,28 @@
 # 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.
+# Once a PR is "Squash and merge"'d, by adding a backport label, this is triggered
 
 name: Backport
 on:
   pull_request:
     types:
-      - closed
       - labeled
 
+permissions:
+  contents: write
+  pull-requests: write
+
 jobs:
   backport:
-    runs-on: ubuntu-18.04
     name: Backport
+    runs-on: ubuntu-latest
+    # Only react to merged PRs for security reasons.
+    # See https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#pull_request_target.
+    if: >
+      github.event.pull_request.merged
+      && contains(github.event.label.name, 'backport')
     steps:
-      - name: Backport
-        uses: tibdex/backport@v1.1.1
+      - uses: tibdex/backport@v2.0.3
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/bot-changelog.yml

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

.github/workflows/changelog-existence.yml

@@ -0,0 +1,40 @@
+# **what?**
+# Checks that a file has been committed under the /.changes directory
+# as a new CHANGELOG entry.  Cannot check for a specific filename as
+# it is dynamically generated by change type and timestamp.
+# This workflow should not require any secrets since it runs for PRs
+# from forked repos.
+# By default, secrets are not passed to workflows running from
+# a forked repo.
+
+# **why?**
+# Ensure code change gets reflected in the CHANGELOG.
+
+# **when?**
+# This will run for all PRs going into main and *.latest.  It will
+# run when they are opened, reopened, when any label is added or removed
+# and when new code is pushed to the branch.  The action will then get
+# skipped if the 'Skip Changelog' label is present is any of the labels.
+
+name: Check Changelog Entry
+
+on:
+  pull_request:
+    types: [opened, reopened, labeled, unlabeled, synchronize]
+  workflow_dispatch:
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  changelog:
+    uses: dbt-labs/actions/.github/workflows/changelog-existence.yml@main
+    with:
+      changelog_comment: 'Thank you for your pull request! We could not find a changelog entry for this change. For details on how to document a change, see [the contributing guide](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#adding-changelog-entry).'
+      skip_label: 'Skip Changelog'
+    secrets: inherit

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

@@ -0,0 +1,41 @@
+# **what?**
+# Cuts a new `*.latest` branch
+# Also cleans up all files in `.changes/unreleased` and `.changes/previous verion on
+# `main` and bumps `main` to the input version.
+
+# **why?**
+# Generally reduces the workload of engineers and reduces error.  Allow automation.
+
+# **when?**
+# This will run when called manually.
+
+name: Cut new release branch
+
+on:
+  workflow_dispatch:
+    inputs:
+      version_to_bump_main:
+        description: 'The alpha version main should bump to (ex. 1.6.0a1)'
+        required: true
+      new_branch_name:
+        description: 'The full name of the new branch (ex. 1.5.latest)'
+        required: true
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+  contents: write
+
+jobs:
+  cut_branch:
+    name: "Cut branch and clean up main for dbt-core"
+    uses: dbt-labs/actions/.github/workflows/cut-release-branch.yml@main
+    with:
+      version_to_bump_main: ${{ inputs.version_to_bump_main }}
+      new_branch_name: ${{ inputs.new_branch_name }}
+      PR_title: "Cleanup main after cutting new ${{ inputs.new_branch_name }} branch"
+      PR_body: "All adapter PRs will fail CI until the dbt-core PR has been merged due to release version conflicts."
+    secrets:
+      FISHTOWN_BOT_PAT: ${{ secrets.FISHTOWN_BOT_PAT }}

.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-transition.yml

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

.github/workflows/main.yml

@@ -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:
@@ -35,29 +33,32 @@ defaults:
   run:
     shell: bash
 
+# top-level adjustments can be made here
+env:
+  # number of parallel processes to spawn for python integration testing
+  PYTHON_INTEGRATION_TEST_WORKERS: ${{ vars.PYTHON_INTEGRATION_TEST_WORKERS }}
+
 jobs:
   code-quality:
     name: code-quality
 
     runs-on: ubuntu-latest
+    timeout-minutes: 10
 
     steps:
       - name: Check out the repository
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
+        uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.8'
 
       - name: Install python dependencies
         run: |
-          pip install --user --upgrade pip
-          pip install pre-commit
-          pip install mypy==0.782
-          pip install -r editable-requirements.txt
-          pip --version
-          pre-commit --version
+          python -m pip install --user --upgrade pip
+          python -m pip --version
+          make dev
           mypy --version
           dbt --version
 
@@ -68,11 +69,12 @@ jobs:
     name: unit test / python ${{ matrix.python-version }}
 
     runs-on: ubuntu-latest
+    timeout-minutes: 10
 
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
 
     env:
       TOXENV: "unit"
@@ -80,20 +82,18 @@ jobs:
 
     steps:
       - name: Check out the repository
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
+        uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
       - name: Install python dependencies
         run: |
-          pip install --user --upgrade pip
-          pip install tox
-          pip --version
+          python -m pip install --user --upgrade pip
+          python -m pip --version
+          python -m pip install tox
           tox --version
 
       - name: Run tox
@@ -102,14 +102,140 @@ jobs:
       - name: Get current date
         if: always()
         id: date
-        run: echo "::set-output name=date::$(date +'%Y-%m-%dT%H_%M_%S')" #no colons allowed for artifacts
+        run: |
+          CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
+          echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
 
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v4
         if: always()
         with:
           name: unit_results_${{ matrix.python-version }}-${{ steps.date.outputs.date }}.csv
           path: unit_results.csv
 
+  integration-metadata:
+    name: integration test metadata generation
+    runs-on: ubuntu-latest
+    outputs:
+      split-groups: ${{ steps.generate-split-groups.outputs.split-groups }}
+      include: ${{ steps.generate-include.outputs.include }}
+
+    steps:
+      - name: generate split-groups
+        id: generate-split-groups
+        run: |
+          MATRIX_JSON="["
+          for B in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
+              MATRIX_JSON+=$(sed 's/^/"/;s/$/"/' <<< "${B}")
+          done
+          MATRIX_JSON="${MATRIX_JSON//\"\"/\", \"}"
+          MATRIX_JSON+="]"
+          echo "split-groups=${MATRIX_JSON}"
+          echo "split-groups=${MATRIX_JSON}" >> $GITHUB_OUTPUT
+
+      - name: generate include
+        id: generate-include
+        run: |
+          INCLUDE=('"python-version":"3.8","os":"windows-latest"' '"python-version":"3.8","os":"macos-latest"' )
+          INCLUDE_GROUPS="["
+          for include in ${INCLUDE[@]}; do
+              for group in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
+                  INCLUDE_GROUPS+=$(sed 's/$/, /' <<< "{\"split-group\":\"${group}\",${include}}")
+              done
+          done
+          INCLUDE_GROUPS=$(echo $INCLUDE_GROUPS | sed 's/,*$//g')
+          INCLUDE_GROUPS+="]"
+          echo "include=${INCLUDE_GROUPS}"
+          echo "include=${INCLUDE_GROUPS}" >> $GITHUB_OUTPUT
+
+  integration:
+    name: (${{ matrix.split-group }}) integration test / python ${{ matrix.python-version }} / ${{ matrix.os }}
+
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 30
+    needs:
+      - integration-metadata
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        os: [ubuntu-20.04]
+        split-group: ${{ fromJson(needs.integration-metadata.outputs.split-groups) }}
+        include: ${{ fromJson(needs.integration-metadata.outputs.include) }}
+    env:
+      TOXENV: integration
+      PYTEST_ADDOPTS: "-v --color=yes -n4 --csv integration_results.csv"
+      DBT_INVOCATION_ENV: github-actions
+      DBT_TEST_USER_1: dbt_test_user_1
+      DBT_TEST_USER_2: dbt_test_user_2
+      DBT_TEST_USER_3: dbt_test_user_3
+      DD_CIVISIBILITY_AGENTLESS_ENABLED: true
+      DD_API_KEY: ${{ secrets.DATADOG_API_KEY }}
+      DD_SITE: datadoghq.com
+      DD_ENV: ci
+      DD_SERVICE: ${{ github.event.repository.name }}
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Set up postgres (linux)
+        if: runner.os == 'Linux'
+        uses: ./.github/actions/setup-postgres-linux
+
+      - name: Set up postgres (macos)
+        if: runner.os == 'macOS'
+        uses: ./.github/actions/setup-postgres-macos
+
+      - name: Set up postgres (windows)
+        if: runner.os == 'Windows'
+        uses: ./.github/actions/setup-postgres-windows
+
+      - name: Install python tools
+        run: |
+          python -m pip install --user --upgrade pip
+          python -m pip --version
+          python -m pip install tox
+          tox --version
+
+      - name: Run tests
+        run: tox -- --ddtrace
+        env:
+          PYTEST_ADDOPTS: ${{ format('--splits {0} --group {1}', env.PYTHON_INTEGRATION_TEST_WORKERS, matrix.split-group) }}
+
+      - name: Get current date
+        if: always()
+        id: date
+        run: |
+          CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
+          echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
+
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: logs_${{ matrix.python-version }}_${{ matrix.os }}_${{ matrix.split-group }}_${{ steps.date.outputs.date }}
+          path: ./logs
+
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: integration_results_${{ matrix.python-version }}_${{ matrix.os }}_${{ steps.date.outputs.date }}.csv
+          path: integration_results.csv
+
+  integration-report:
+    if: ${{ always() }}
+    name: Integration Test Suite
+    runs-on: ubuntu-latest
+    needs: integration
+    steps:
+      - name: "[Notification] Integration test suite passes"
+        run: |
+          echo "::notice title="Integration test suite passes""
+
   build:
     name: build packages
 
@@ -117,20 +243,18 @@ jobs:
 
     steps:
       - name: Check out the repository
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
+        uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: '3.8'
 
       - name: Install python dependencies
         run: |
-          pip install --user --upgrade pip
-          pip install --upgrade setuptools wheel twine check-wheel-contents
-          pip --version
+          python -m pip install --user --upgrade pip
+          python -m pip install --upgrade setuptools wheel twine check-wheel-contents
+          python -m pip --version
 
       - name: Build distributions
         run: ./scripts/build-dist.sh
@@ -146,47 +270,9 @@ 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/
+          find ./dist/*.whl -maxdepth 1 -type f | xargs python -m pip install --force-reinstall --find-links=dist/
 
       - name: Check wheel distributions
         run: |
@@ -195,7 +281,7 @@ jobs:
       - name: Install source distributions
         # ignore dbt-1.0.0, which intentionally raises an error when installed from source
         run: |
-          find ./dist/dbt-[a-z]*.gz -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
+          find ./dist/*.gz -maxdepth 1 -type f | xargs python -m pip install --force-reinstall --find-links=dist/
 
       - name: Check source distributions
         run: |

.github/workflows/nightly-release.yml

@@ -0,0 +1,109 @@
+# **what?**
+# Nightly releases to GitHub and PyPI. This workflow produces the following outcome:
+# - generate and validate data for night release (commit SHA, version number, release branch);
+# - pass data to release workflow;
+# - night release will be pushed to GitHub as a draft release;
+# - night build will be pushed to test PyPI;
+#
+# **why?**
+# Ensure an automated and tested release process for nightly builds
+#
+# **when?**
+# This workflow runs on schedule or can be run manually on demand.
+
+name: Nightly Test Release to GitHub and PyPI
+
+on:
+  workflow_dispatch: # for manual triggering
+  schedule:
+    - cron: 0 9 * * *
+
+permissions:
+  contents: write # this is the permission that allows creating a new release
+
+defaults:
+  run:
+    shell: bash
+
+env:
+  RELEASE_BRANCH: "main"
+
+jobs:
+  aggregate-release-data:
+    runs-on: ubuntu-latest
+
+    outputs:
+      commit_sha: ${{ steps.resolve-commit-sha.outputs.release_commit }}
+      version_number: ${{ steps.nightly-release-version.outputs.number }}
+      release_branch: ${{ steps.release-branch.outputs.name }}
+
+    steps:
+      - name: "Checkout ${{ github.repository }} Branch ${{ env.RELEASE_BRANCH }}"
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ env.RELEASE_BRANCH }}
+
+      - name: "Resolve Commit To Release"
+        id: resolve-commit-sha
+        run: |
+          commit_sha=$(git rev-parse HEAD)
+          echo "release_commit=$commit_sha" >> $GITHUB_OUTPUT
+
+      - name: "Get Current Version Number"
+        id: version-number-sources
+        run: |
+          current_version=`awk -F"current_version = " '{print $2}' .bumpversion.cfg | tr '\n' ' '`
+          echo "current_version=$current_version" >> $GITHUB_OUTPUT
+
+      - name: "Audit Version And Parse Into Parts"
+        id: semver
+        uses: dbt-labs/actions/parse-semver@v1.1.0
+        with:
+          version: ${{ steps.version-number-sources.outputs.current_version }}
+
+      - name: "Get Current Date"
+        id: current-date
+        run: echo "date=$(date +'%m%d%Y')" >> $GITHUB_OUTPUT
+
+      - name: "Generate Nightly Release Version Number"
+        id: nightly-release-version
+        run: |
+          number="${{ steps.semver.outputs.version }}.dev${{ steps.current-date.outputs.date }}"
+          echo "number=$number" >> $GITHUB_OUTPUT
+
+      - name: "Audit Nightly Release Version And Parse Into Parts"
+        uses: dbt-labs/actions/parse-semver@v1.1.0
+        with:
+          version: ${{ steps.nightly-release-version.outputs.number }}
+
+      - name: "Set Release Branch"
+        id: release-branch
+        run: |
+          echo "name=${{ env.RELEASE_BRANCH }}" >> $GITHUB_OUTPUT
+
+  log-outputs-aggregate-release-data:
+    runs-on: ubuntu-latest
+    needs: [aggregate-release-data]
+
+    steps:
+      - name: "[DEBUG] Log Outputs"
+        run: |
+          echo commit_sha    : ${{ needs.aggregate-release-data.outputs.commit_sha }}
+          echo version_number: ${{ needs.aggregate-release-data.outputs.version_number }}
+          echo release_branch: ${{ needs.aggregate-release-data.outputs.release_branch }}
+
+  release-github-pypi:
+    needs: [aggregate-release-data]
+
+    uses: ./.github/workflows/release.yml
+    with:
+      sha: ${{ needs.aggregate-release-data.outputs.commit_sha }}
+      target_branch: ${{ needs.aggregate-release-data.outputs.release_branch }}
+      version_number: ${{ needs.aggregate-release-data.outputs.version_number }}
+      build_script_path: "scripts/build-dist.sh"
+      env_setup_script_path: "scripts/env-setup.sh"
+      s3_bucket_name: "core-team-artifacts"
+      package_test_command: "dbt --version"
+      test_run: true
+      nightly_release: true
+    secrets: inherit

.github/workflows/performance.yml

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

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

@@ -0,0 +1,90 @@
+# **what?**
+# The purpose of this workflow is to trigger CI to run for each
+# release branch and main branch on a regular cadence. If the CI workflow
+# fails for a branch, it will post to dev-core-alerts to raise awareness.
+# The 'aurelien-baudet/workflow-dispatch' Action triggers the existing
+# CI worklow file on the given branch to run so that even if we change the
+# CI workflow file in the future, the one that is tailored for the given
+# release branch will be used.
+
+# **why?**
+# Ensures release branches and main are always shippable and not broken.
+# Also, can catch any dependencies shifting beneath us that might
+# introduce breaking changes (could also impact Cloud).
+
+# **when?**
+# Mainly on a schedule of 9:00, 13:00, 18:00 UTC everyday.
+# Manual trigger can also test on demand
+
+name: Release branch scheduled testing
+
+on:
+  schedule:
+    - cron: '0 9,13,18 * * *' # 9:00, 13:00, 18:00 UTC
+
+  workflow_dispatch: # for manual triggering
+
+# no special access is needed
+permissions: read-all
+
+jobs:
+  fetch-latest-branches:
+    runs-on: ubuntu-latest
+
+    outputs:
+      latest-branches: ${{ steps.get-latest-branches.outputs.repo-branches }}
+
+    steps:
+      - name: "Fetch dbt-core Latest Branches"
+        uses: dbt-labs/actions/fetch-repo-branches@v1.1.1
+        id: get-latest-branches
+        with:
+          repo_name: ${{ github.event.repository.name }}
+          organization: "dbt-labs"
+          pat: ${{ secrets.GITHUB_TOKEN }}
+          fetch_protected_branches_only: true
+          regex: "^1.[0-9]+.latest$"
+          perform_match_method: "match"
+          retries: 3
+
+      - name: "[ANNOTATION] ${{ github.event.repository.name }} - branches to test"
+        run: |
+          title="${{ github.event.repository.name }} - branches to test"
+          message="The workflow will run tests for the following branches of the ${{ github.event.repository.name }} repo: ${{ steps.get-latest-branches.outputs.repo-branches }}"
+          echo "::notice $title::$message"
+
+  kick-off-ci:
+    needs: [fetch-latest-branches]
+    name: Kick-off CI
+    runs-on: ubuntu-latest
+
+    strategy:
+      # must run CI 1 branch at a time b/c the workflow-dispatch Action polls for
+      # latest run for results and it gets confused when we kick off multiple runs
+      # at once. There is a race condition so we will just run in sequential order.
+      max-parallel: 1
+      fail-fast: false
+      matrix:
+        branch: ${{ fromJSON(needs.fetch-latest-branches.outputs.latest-branches) }}
+        include:
+          - branch: 'main'
+
+    steps:
+    - name: Call CI workflow for ${{ matrix.branch }} branch
+      id: trigger-step
+      uses: aurelien-baudet/workflow-dispatch@v2.1.1
+      with:
+        workflow: main.yml
+        ref: ${{ matrix.branch }}
+        token: ${{ secrets.FISHTOWN_BOT_PAT }}
+
+    - name: Post failure to Slack
+      uses: ravsamhq/notify-slack-action@v1
+      if: ${{ always() && !contains(steps.trigger-step.outputs.workflow-conclusion,'success') }}
+      with:
+        status: ${{ job.status }}
+        notification_title: 'dbt-core scheduled run of "${{ matrix.branch }}" branch not successful'
+        message_format: ':x: CI on branch "${{ matrix.branch }}" ${{ steps.trigger-step.outputs.workflow-conclusion }}'
+        footer: 'Linked failed CI run ${{ steps.trigger-step.outputs.workflow-url }}'
+      env:
+        SLACK_WEBHOOK_URL: ${{ secrets.SLACK_DEV_CORE_ALERTS }}

.github/workflows/release-docker.yml

@@ -12,6 +12,9 @@
 
 name: Docker release
 
+permissions:
+  packages: write
+
 on:
   workflow_dispatch:
     inputs:
@@ -33,14 +36,14 @@ jobs:
       latest: ${{ steps.latest.outputs.latest }}
       minor_latest: ${{ steps.latest.outputs.minor_latest }}
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v4
       - 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"
+          echo "major=$MAJOR" >> $GITHUB_OUTPUT
+          echo "minor=$MINOR" >> $GITHUB_OUTPUT
+          echo "patch=$PATCH" >> $GITHUB_OUTPUT
 
       - name: Is pkg 'latest'
         id: latest
@@ -57,7 +60,7 @@ jobs:
     needs: [get_version_meta]
     steps:
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
+        uses: docker/setup-buildx-action@v2
 
   build_and_push:
     name: Build images and push to GHCR
@@ -67,18 +70,20 @@ jobs:
       - name: Get docker build arg
         id: build_arg
         run: |
-          echo "::set-output name=build_arg_name::"$(echo ${{ github.event.inputs.package }} | sed 's/\-/_/g')
-          echo "::set-output name=build_arg_value::"$(echo ${{ github.event.inputs.package }} | sed 's/postgres/core/g')
+          BUILD_ARG_NAME=$(echo ${{ github.event.inputs.package }} | sed 's/\-/_/g')
+          BUILD_ARG_VALUE=$(echo ${{ github.event.inputs.package }} | sed 's/postgres/core/g')
+          echo "build_arg_name=$BUILD_ARG_NAME" >> $GITHUB_OUTPUT
+          echo "build_arg_value=$BUILD_ARG_VALUE" >> $GITHUB_OUTPUT
 
       - name: Log in to the GHCR
-        uses: docker/login-action@v1
+        uses: docker/login-action@v2
         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
+        uses: docker/build-push-action@v4
         with:
           file: docker/Dockerfile
           push: True
@@ -89,7 +94,7 @@ jobs:
             ghcr.io/dbt-labs/${{ github.event.inputs.package }}:${{ github.event.inputs.version_number }}
 
       - name: Build and push MINOR.latest tag
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v4
         if: ${{ needs.get_version_meta.outputs.minor_latest == 'True' }}
         with:
           file: docker/Dockerfile
@@ -101,7 +106,7 @@ jobs:
             ghcr.io/dbt-labs/${{ github.event.inputs.package }}:${{ needs.get_version_meta.outputs.major }}.${{ needs.get_version_meta.outputs.minor }}.latest
 
       - name: Build and push latest tag
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v4
         if: ${{ needs.get_version_meta.outputs.latest == 'True' }}
         with:
           file: docker/Dockerfile

.github/workflows/release.yml

@@ -1,199 +1,229 @@
 # **what?**
-# Take the given commit, run unit tests specifically on that sha, build and
-# package it, and then release to GitHub and PyPi with that specific build
-
+# Release workflow provides the following steps:
+# - checkout the given commit;
+# - validate version in sources and changelog file for given version;
+# - bump the version and generate a changelog if needed;
+# - merge all changes to the target branch if needed;
+# - run unit and integration tests against given commit;
+# - build and package that SHA;
+# - release it to GitHub and PyPI with that specific build;
+#
 # **why?**
 # Ensure an automated and tested release process
-
+#
 # **when?**
-# This will only run manually with a given sha and version
+# This workflow can be run manually on demand or can be called by other workflows
 
-name: Release to GitHub and PyPi
+name: Release to GitHub and PyPI
 
 on:
   workflow_dispatch:
     inputs:
       sha:
-       description: 'The last commit sha in the release'
-       required: true
+        description: "The last commit sha in the release"
+        type: string
+        required: true
+      target_branch:
+        description: "The branch to release from"
+        type: string
+        required: true
       version_number:
-       description: 'The release version number (i.e. 1.0.0b1)'
-       required: true
+        description: "The release version number (i.e. 1.0.0b1)"
+        type: string
+        required: true
+      build_script_path:
+        description: "Build script path"
+        type: string
+        default: "scripts/build-dist.sh"
+        required: true
+      env_setup_script_path:
+        description: "Environment setup script path"
+        type: string
+        default: "scripts/env-setup.sh"
+        required: false
+      s3_bucket_name:
+        description: "AWS S3 bucket name"
+        type: string
+        default: "core-team-artifacts"
+        required: true
+      package_test_command:
+        description: "Package test command"
+        type: string
+        default: "dbt --version"
+        required: true
+      test_run:
+        description: "Test run (Publish release as draft)"
+        type: boolean
+        default: true
+        required: false
+      nightly_release:
+        description: "Nightly release to dev environment"
+        type: boolean
+        default: false
+        required: false
+  workflow_call:
+    inputs:
+      sha:
+        description: "The last commit sha in the release"
+        type: string
+        required: true
+      target_branch:
+        description: "The branch to release from"
+        type: string
+        required: true
+      version_number:
+        description: "The release version number (i.e. 1.0.0b1)"
+        type: string
+        required: true
+      build_script_path:
+        description: "Build script path"
+        type: string
+        default: "scripts/build-dist.sh"
+        required: true
+      env_setup_script_path:
+        description: "Environment setup script path"
+        type: string
+        default: "scripts/env-setup.sh"
+        required: false
+      s3_bucket_name:
+        description: "AWS S3 bucket name"
+        type: string
+        default: "core-team-artifacts"
+        required: true
+      package_test_command:
+        description: "Package test command"
+        type: string
+        default: "dbt --version"
+        required: true
+      test_run:
+        description: "Test run (Publish release as draft)"
+        type: boolean
+        default: true
+        required: false
+      nightly_release:
+        description: "Nightly release to dev environment"
+        type: boolean
+        default: false
+        required: false
+
+permissions:
+  contents: write # this is the permission that allows creating a new release
 
 defaults:
   run:
     shell: bash
 
 jobs:
-  unit:
-    name: Unit test
-
+  log-inputs:
+    name: Log Inputs
     runs-on: ubuntu-latest
-
-    env:
-      TOXENV: "unit"
-
     steps:
-      - name: Check out the repository
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
-          ref: ${{ github.event.inputs.sha }}
-
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.8
-
-      - name: Install python dependencies
+      - name: "[DEBUG] Print Variables"
         run: |
-          pip install --user --upgrade pip
-          pip install tox
-          pip --version
-          tox --version
+          echo The last commit sha in the release: ${{ inputs.sha }}
+          echo The branch to release from:         ${{ inputs.target_branch }}
+          echo The release version number:         ${{ inputs.version_number }}
+          echo Build script path:                  ${{ inputs.build_script_path }}
+          echo Environment setup script path:      ${{ inputs.env_setup_script_path }}
+          echo AWS S3 bucket name:                 ${{ inputs.s3_bucket_name }}
+          echo Package test command:               ${{ inputs.package_test_command }}
+          echo Test run:                           ${{ inputs.test_run }}
+          echo Nightly release:                    ${{ inputs.nightly_release }}
 
-      - name: Run tox
-        run: tox
+  bump-version-generate-changelog:
+    name: Bump package version, Generate changelog
 
-  build:
-    name: build packages
+    uses: dbt-labs/dbt-release/.github/workflows/release-prep.yml@main
+
+    with:
+      sha: ${{ inputs.sha }}
+      version_number: ${{ inputs.version_number }}
+      target_branch: ${{ inputs.target_branch }}
+      env_setup_script_path: ${{ inputs.env_setup_script_path }}
+      test_run: ${{ inputs.test_run }}
+      nightly_release: ${{ inputs.nightly_release }}
+
+    secrets: inherit
+
+  log-outputs-bump-version-generate-changelog:
+    name: "[Log output] Bump package version, Generate changelog"
+    if: ${{ !failure() && !cancelled() }}
+
+    needs: [bump-version-generate-changelog]
 
     runs-on: ubuntu-latest
 
     steps:
-      - name: Check out the repository
-        uses: actions/checkout@v2
-        with:
-          persist-credentials: false
-          ref: ${{ github.event.inputs.sha }}
-
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.8
-
-      - name: Install python dependencies
+      - name: Print variables
         run: |
-          pip install --user --upgrade pip
-          pip install --upgrade setuptools wheel twine check-wheel-contents
-          pip --version
+          echo Final SHA     : ${{ needs.bump-version-generate-changelog.outputs.final_sha }}
+          echo Changelog path: ${{ needs.bump-version-generate-changelog.outputs.changelog_path }}
 
-      - name: Build distributions
-        run: ./scripts/build-dist.sh
+  build-test-package:
+    name: Build, Test, Package
+    if: ${{ !failure() && !cancelled() }}
+    needs: [bump-version-generate-changelog]
 
-      - name: Show distributions
-        run: ls -lh dist/
+    uses: dbt-labs/dbt-release/.github/workflows/build.yml@main
 
-      - name: Check distribution descriptions
-        run: |
-          twine check dist/*
+    with:
+      sha: ${{ needs.bump-version-generate-changelog.outputs.final_sha }}
+      version_number: ${{ inputs.version_number }}
+      changelog_path: ${{ needs.bump-version-generate-changelog.outputs.changelog_path }}
+      build_script_path: ${{ inputs.build_script_path }}
+      s3_bucket_name: ${{ inputs.s3_bucket_name }}
+      package_test_command: ${{ inputs.package_test_command }}
+      test_run: ${{ inputs.test_run }}
+      nightly_release: ${{ inputs.nightly_release }}
 
-      - name: Check wheel contents
-        run: |
-          check-wheel-contents dist/*.whl --ignore W007,W008
-
-      - uses: actions/upload-artifact@v2
-        with:
-          name: dist
-          path: |
-            dist/
-            !dist/dbt-${{github.event.inputs.version_number}}.tar.gz
-
-  test-build:
-    name: verify packages
-
-    needs: [build, unit]
-
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.8
-
-      - name: Install python dependencies
-        run: |
-          pip install --user --upgrade pip
-          pip install --upgrade wheel
-          pip --version
-
-      - uses: actions/download-artifact@v2
-        with:
-          name: dist
-          path: dist/
-
-      - name: Show distributions
-        run: ls -lh dist/
-
-      - name: Install wheel distributions
-        run: |
-          find ./dist/*.whl -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
-
-      - name: Check wheel distributions
-        run: |
-          dbt --version
-
-      - name: Install source distributions
-        run: |
-          find ./dist/*.gz -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
-
-      - name: Check source distributions
-        run: |
-          dbt --version
+    secrets:
+      AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+      AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
 
   github-release:
     name: GitHub Release
+    if: ${{ !failure() && !cancelled() }}
 
-    needs: test-build
+    needs: [bump-version-generate-changelog, build-test-package]
 
-    runs-on: ubuntu-latest
+    uses: dbt-labs/dbt-release/.github/workflows/github-release.yml@main
 
-    steps:
-      - uses: actions/download-artifact@v2
-        with:
-          name: dist
-          path: '.'
-
-      # Need to set an output variable because env variables can't be taken as input
-      # This is needed for the next step with releasing to GitHub
-      - name: Find release type
-        id: release_type
-        env:
-          IS_PRERELEASE: ${{ contains(github.event.inputs.version_number, 'rc') ||  contains(github.event.inputs.version_number, 'b') }}
-        run: |
-          echo ::set-output name=isPrerelease::$IS_PRERELEASE
-
-      - name: Creating GitHub Release
-        uses: softprops/action-gh-release@v1
-        with:
-          name: dbt-core v${{github.event.inputs.version_number}}
-          tag_name: v${{github.event.inputs.version_number}}
-          prerelease: ${{ steps.release_type.outputs.isPrerelease }}
-          target_commitish: ${{github.event.inputs.sha}}
-          body: |
-            [Release notes](https://github.com/dbt-labs/dbt-core/blob/main/CHANGELOG.md)
-          files: |
-            dbt_postgres-${{github.event.inputs.version_number}}-py3-none-any.whl
-            dbt_core-${{github.event.inputs.version_number}}-py3-none-any.whl
-            dbt-postgres-${{github.event.inputs.version_number}}.tar.gz
-            dbt-core-${{github.event.inputs.version_number}}.tar.gz
+    with:
+      sha: ${{ needs.bump-version-generate-changelog.outputs.final_sha }}
+      version_number: ${{ inputs.version_number }}
+      changelog_path: ${{ needs.bump-version-generate-changelog.outputs.changelog_path }}
+      test_run: ${{ inputs.test_run }}
 
   pypi-release:
-    name: Pypi release
+    name: PyPI Release
 
-    runs-on: ubuntu-latest
+    needs: [github-release]
 
-    needs: github-release
+    uses: dbt-labs/dbt-release/.github/workflows/pypi-release.yml@main
 
-    environment: PypiProd
-    steps:
-      - uses: actions/download-artifact@v2
-        with:
-          name: dist
-          path: 'dist'
+    with:
+      version_number: ${{ inputs.version_number }}
+      test_run: ${{ inputs.test_run }}
 
-      - name: Publish distribution to PyPI
-        uses: pypa/gh-action-pypi-publish@v1.4.2
-        with:
-          password: ${{ secrets.PYPI_API_TOKEN }}
+    secrets:
+      PYPI_API_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
+      TEST_PYPI_API_TOKEN: ${{ secrets.TEST_PYPI_API_TOKEN }}
+
+  slack-notification:
+    name: Slack Notification
+    if: ${{ failure() && (!inputs.test_run || inputs.nightly_release) }}
+
+    needs:
+      [
+        bump-version-generate-changelog,
+        build-test-package,
+        github-release,
+        pypi-release,
+      ]
+
+    uses: dbt-labs/dbt-release/.github/workflows/slack-post-notification.yml@main
+    with:
+      status: "failure"
+
+    secrets:
+      SLACK_WEBHOOK_URL: ${{ secrets.SLACK_DEV_CORE_ALERTS }}

.github/workflows/schema-check.yml

@@ -21,6 +21,9 @@ on:
       - "*.latest"
       - "releases/*"
 
+# no special access is needed
+permissions: read-all
+
 env:
   LATEST_SCHEMA_PATH: ${{ github.workspace }}/new_schemas
   SCHEMA_DIFF_ARTIFACT: ${{ github.workspace }}//schema_schanges.txt
@@ -34,17 +37,17 @@ jobs:
 
     steps:
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: 3.8
 
       - name: Checkout dbt repo
-        uses: actions/checkout@v2.3.4
+        uses: actions/checkout@v4
         with:
             path: ${{ env.DBT_REPO_DIRECTORY }}
 
       - name: Checkout schemas.getdbt.com repo
-        uses: actions/checkout@v2.3.4
+        uses: actions/checkout@v4
         with:
           repository: dbt-labs/schemas.getdbt.com
           ref: 'main'
@@ -80,7 +83,7 @@ jobs:
           fi
 
       - name: Upload schema diff
-        uses: actions/upload-artifact@v2.2.4
+        uses: actions/upload-artifact@v4
         if: ${{ failure() }}
         with:
           name: 'schema_schanges.txt'

.github/workflows/stale.yml

@@ -3,16 +3,10 @@ on:
   schedule:
     - cron: "30 1 * * *"
 
+permissions:
+  issues: write
+  pull-requests: write
+
 jobs:
   stale:
-    runs-on: ubuntu-latest
-    steps:
-      # pinned at v4 (https://github.com/actions/stale/releases/tag/v4.0.0)
-      - uses: actions/stale@cdf15f641adb27a71842045a94023bef6945e3aa
-        with:
-          stale-issue-message: "This issue has been marked as Stale because it has been open for 180 days with no activity. If you would like the issue to remain open, please remove the stale label or comment on the issue, or it will be closed in 7 days."
-          stale-pr-message: "This PR has been marked as Stale because it has been open for 180 days with no activity. If you would like the PR to remain open, please remove the stale label or comment on the PR, or it will be closed in 7 days."
-          # mark issues/PRs stale when they haven't seen activity in 180 days
-          days-before-stale: 180
-          # ignore checking issues with the following labels
-          exempt-issue-labels: "epic,discussion"
+    uses: dbt-labs/actions/.github/workflows/stale-bot-matrix.yml@main

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

@@ -6,7 +6,6 @@
 # version of our structured logging and add new documentation to
 # communicate these changes.
 
-
 name: Structured Logging Schema Check
 on:
   push:
@@ -19,38 +18,72 @@ on:
 
 permissions: read-all
 
+# top-level adjustments can be made here
+env:
+  # number of parallel processes to spawn for python testing
+  PYTHON_INTEGRATION_TEST_WORKERS: ${{ vars.PYTHON_INTEGRATION_TEST_WORKERS }}
+
 jobs:
+  integration-metadata:
+    name: integration test metadata generation
+    runs-on: ubuntu-latest
+    outputs:
+      split-groups: ${{ steps.generate-split-groups.outputs.split-groups }}
+
+    steps:
+      - name: generate split-groups
+        id: generate-split-groups
+        run: |
+          MATRIX_JSON="["
+          for B in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
+              MATRIX_JSON+=$(sed 's/^/"/;s/$/"/' <<< "${B}")
+          done
+          MATRIX_JSON="${MATRIX_JSON//\"\"/\", \"}"
+          MATRIX_JSON+="]"
+          echo "split-groups=${MATRIX_JSON}" >> $GITHUB_OUTPUT
+
   # run the performance measurements on the current or default branch
   test-schema:
     name: Test Log Schema
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
+    timeout-minutes: 30
+    needs:
+      - integration-metadata
+    strategy:
+      fail-fast: false
+      matrix:
+        split-group: ${{ fromJson(needs.integration-metadata.outputs.split-groups) }}
     env:
       # turns warnings into errors
       RUSTFLAGS: "-D warnings"
       # 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'
-    steps:
+      DBT_LOG_FORMAT: "json"
+      # tell eventmgr to convert logging events into bytes
+      DBT_TEST_BINARY_SERIALIZATION: "true"
+      # Additional test users
+      DBT_TEST_USER_1: dbt_test_user_1
+      DBT_TEST_USER_2: dbt_test_user_2
+      DBT_TEST_USER_3: dbt_test_user_3
 
+    steps:
       - name: checkout dev
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
         with:
           persist-credentials: false
 
       - name: Setup Python
-        uses: actions/setup-python@v2.2.2
+        uses: actions/setup-python@v5
         with:
           python-version: "3.8"
 
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          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
@@ -61,11 +94,15 @@ 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
+        env:
+          PYTEST_ADDOPTS: ${{ format('--splits {0} --group {1}', env.PYTHON_INTEGRATION_TEST_WORKERS, matrix.split-group) }}
 
-      # apply our schema tests to every log event from the previous step
-      # skips any output that isn't valid json
-      - uses: actions-rs/cargo@v1
-        with:
-          command: run
-          args: --manifest-path test/interop/log_parsing/Cargo.toml
+  test-schema-report:
+    name: Log Schema Test Suite
+    runs-on: ubuntu-latest
+    needs: test-schema
+    steps:
+      - name: "[Notification] Log test suite passes"
+        run: |
+          echo "::notice title="Log test suite passes""

.github/workflows/test-repeater.yml

@@ -0,0 +1,155 @@
+# **what?**
+# This workflow will test all test(s) at the input path given number of times to determine if it's flaky or not.  You can test with any supported OS/Python combination.
+# This is batched in 10 to allow more test iterations faster.
+
+# **why?**
+# Testing if a test is flaky and if a previously flaky test has been fixed.  This allows easy testing on supported python versions and OS combinations.
+
+# **when?**
+# This is triggered manually from dbt-core.
+
+name: Flaky Tester
+
+on:
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to check out'
+        type: string
+        required: true
+        default: 'main'
+      test_path:
+        description: 'Path to single test to run (ex: tests/functional/retry/test_retry.py::TestRetry::test_fail_fast)'
+        type: string
+        required: true
+        default: 'tests/functional/...'
+      python_version:
+        description: 'Version of Python to Test Against'
+        type: choice
+        options:
+          - '3.8'
+          - '3.9'
+          - '3.10'
+          - '3.11'
+      os:
+        description: 'OS to run test in'
+        type: choice
+        options:
+          - 'ubuntu-latest'
+          - 'macos-latest'
+          - 'windows-latest'
+      num_runs_per_batch:
+        description: 'Max number of times to run the test per batch.  We always run 10 batches.'
+        type: number
+        required: true
+        default: '50'
+
+permissions: read-all
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  debug:
+    runs-on: ubuntu-latest
+    steps:
+      - name: "[DEBUG] Output Inputs"
+        run: |
+          echo "Branch: ${{ inputs.branch }}"
+          echo "test_path: ${{ inputs.test_path }}"
+          echo "python_version: ${{ inputs.python_version }}"
+          echo "os: ${{ inputs.os }}"
+          echo "num_runs_per_batch: ${{ inputs.num_runs_per_batch }}"
+
+  pytest:
+    runs-on: ${{ inputs.os }}
+    strategy:
+      # run all batches, even if one fails.  This informs how flaky the test may be.
+      fail-fast: false
+      # using a matrix to speed up the jobs since the matrix will run in parallel when runners are available
+      matrix:
+        batch: ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10"]
+    env:
+      PYTEST_ADDOPTS: "-v --color=yes -n4 --csv integration_results.csv"
+      DBT_TEST_USER_1: dbt_test_user_1
+      DBT_TEST_USER_2: dbt_test_user_2
+      DBT_TEST_USER_3: dbt_test_user_3
+      DD_CIVISIBILITY_AGENTLESS_ENABLED: true
+      DD_API_KEY: ${{ secrets.DATADOG_API_KEY }}
+      DD_SITE: datadoghq.com
+      DD_ENV: ci
+      DD_SERVICE: ${{ github.event.repository.name }}
+
+    steps:
+      - name: "Checkout code"
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.branch }}
+
+      - name: "Setup Python"
+        uses: actions/setup-python@v5
+        with:
+          python-version: "${{ inputs.python_version }}"
+
+      - name: "Setup Dev Environment"
+        run: make dev
+
+      - name: "Set up postgres (linux)"
+        if: inputs.os == 'ubuntu-latest'
+        run: make setup-db
+
+        # mac and windows don't use make due to limitations with docker with those runners in GitHub
+      - name: "Set up postgres (macos)"
+        if: inputs.os == 'macos-latest'
+        uses: ./.github/actions/setup-postgres-macos
+
+      - name: "Set up postgres (windows)"
+        if: inputs.os == 'windows-latest'
+        uses: ./.github/actions/setup-postgres-windows
+
+      - name: "Test Command"
+        id: command
+        run: |
+          test_command="python -m pytest ${{ inputs.test_path }}"
+          echo "test_command=$test_command" >> $GITHUB_OUTPUT
+
+      - name: "Run test ${{ inputs.num_runs_per_batch }} times"
+        id: pytest
+        run: |
+          set +e
+          for ((i=1; i<=${{ inputs.num_runs_per_batch }}; i++))
+          do
+            echo "Running pytest iteration $i..."
+            python -m pytest --ddtrace ${{ inputs.test_path }}
+            exit_code=$?
+
+            if [[ $exit_code -eq 0 ]]; then
+              success=$((success + 1))
+              echo "Iteration $i: Success"
+            else
+              failure=$((failure + 1))
+              echo "Iteration $i: Failure"
+            fi
+
+            echo
+            echo "==========================="
+            echo "Successful runs: $success"
+            echo "Failed runs: $failure"
+            echo "==========================="
+            echo
+          done
+
+          echo "failure=$failure" >> $GITHUB_OUTPUT
+
+      - name: "Success and Failure Summary: ${{ inputs.os }}/Python ${{ inputs.python_version }}"
+        run: |
+          echo "Batch: ${{ matrix.batch }}"
+          echo "Successful runs: ${{ steps.pytest.outputs.success }}"
+          echo "Failed runs: ${{ steps.pytest.outputs.failure }}"
+
+      - name: "Error for Failures"
+        if: ${{ steps.pytest.outputs.failure }}
+        run: |
+            echo "Batch ${{ matrix.batch }} failed ${{ steps.pytest.outputs.failure }} of ${{ inputs.num_runs_per_batch }} tests"
+            exit 1

.github/workflows/triage-labels.yml

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

.github/workflows/version-bump.yml

@@ -1,18 +1,15 @@
 # **what?**
-# This workflow will take a version number and a dry run flag. With that
+# This workflow will take the new version number to bump to. With that
 # it will run versionbump to update the version number everywhere in the
-# code base and then generate an update Docker requirements file. If this
-# is a dry run, a draft PR will open with the changes. If this isn't a dry
-# run, the changes will be committed to the branch this is run on.
+# code base and then run changie to create the corresponding changelog.
+# A PR will be created with the changes that can be reviewed before committing.
 
 # **why?**
 # This is to aid in releasing dbt and making sure we have updated
-# the versions and Docker requirements in all places.
+# the version in all places and generated the changelog.
 
 # **when?**
-# This is triggered either manually OR
-# from the repository_dispatch event "version-bump" which is sent from
-# the dbt-release repo Action
+# This is triggered manually
 
 name: Version Bump
 
@@ -20,90 +17,12 @@ on:
   workflow_dispatch:
     inputs:
       version_number:
-       description: 'The version number to bump to'
+       description: 'The version number to bump to (ex. 1.2.0, 1.3.0b1)'
        required: true
-      is_dry_run:
-       description: 'Creates a draft PR to allow testing instead of committing to a branch'
-       required: true
-       default: 'true'
-  repository_dispatch:
-    types: [version-bump]
 
 jobs:
-  bump:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out the repository
-        uses: actions/checkout@v2
-
-      - name: Set version and dry run values
-        id: variables
-        env:
-          VERSION_NUMBER: "${{ github.event.client_payload.version_number == '' && github.event.inputs.version_number || github.event.client_payload.version_number }}"
-          IS_DRY_RUN: "${{ github.event.client_payload.is_dry_run == '' && github.event.inputs.is_dry_run || github.event.client_payload.is_dry_run }}"
-        run: |
-          echo Repository dispatch event version: ${{ github.event.client_payload.version_number }}
-          echo Repository dispatch event dry run: ${{ github.event.client_payload.is_dry_run }}
-          echo Workflow dispatch event version: ${{ github.event.inputs.version_number }}
-          echo Workflow dispatch event dry run: ${{ github.event.inputs.is_dry_run }}
-          echo ::set-output name=VERSION_NUMBER::$VERSION_NUMBER
-          echo ::set-output name=IS_DRY_RUN::$IS_DRY_RUN
-
-      - uses: actions/setup-python@v2
-        with:
-          python-version: "3.8"
-
-      - name: Install python dependencies
-        run: |
-          python3 -m venv env
-          source env/bin/activate
-          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: Bump version
-        run: |
-          source env/bin/activate
-          pip install -r dev-requirements.txt
-          env/bin/bumpversion --allow-dirty --new-version ${{steps.variables.outputs.VERSION_NUMBER}} major
-          git status
-
-      - name: Commit version bump directly
-        uses: EndBug/add-and-commit@v7
-        if: ${{ steps.variables.outputs.IS_DRY_RUN == 'false' }}
-        with:
-          author_name: 'Github Build Bot'
-          author_email: 'buildbot@fishtownanalytics.com'
-          message: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
-
-      - name: Commit version bump to branch
-        uses: EndBug/add-and-commit@v7
-        if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
-        with:
-          author_name: 'Github Build Bot'
-          author_email: 'buildbot@fishtownanalytics.com'
-          message: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
-          branch: 'bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'
-          push: 'origin origin/bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'
-
-      - name: Create Pull Request
-        uses: peter-evans/create-pull-request@v3
-        if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
-        with:
-          author: 'Github Build Bot <buildbot@fishtownanalytics.com>'
-          draft: true
-          base: ${{github.ref}}
-          title: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
-          branch: 'bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'
+  version_bump_and_changie:
+    uses: dbt-labs/actions/.github/workflows/version-bump.yml@main
+    with:
+      version_number: ${{ inputs.version_number }}
+    secrets: inherit  # ok since what we are calling is internally maintained

.gitignore

@@ -11,6 +11,7 @@ __pycache__/
 env*/
 dbt_env/
 build/
+!core/dbt/docs/build
 develop-eggs/
 dist/
 downloads/
@@ -24,7 +25,8 @@ var/
 *.egg-info/
 .installed.cfg
 *.egg
-*.mypy_cache/
+.mypy_cache/
+.dmypy.json
 logs/
 
 # PyInstaller
@@ -49,6 +51,7 @@ coverage.xml
 *,cover
 .hypothesis/
 test.env
+makefile.test.env
 *.pytest_cache/
 
 
@@ -95,3 +98,7 @@ venv/
 
 # vscode
 .vscode/
+*.code-workspace
+
+# poetry
+poetry.lock

.pre-commit-config.yaml

@@ -1,12 +1,11 @@
 # 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/
+exclude: ^(core/dbt/docs/build/|core/dbt/events/types_pb2.py)
 
 # Force all unspecified python hooks to run python 3.8
 default_language_version:
-  python: python3.8
+  python: python3
 
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -21,21 +20,16 @@ repos:
       - "markdown"
   - id: check-case-conflict
 - repo: https://github.com/psf/black
-  rev: 21.12b0
+  rev: 22.3.0
   hooks:
   - id: black
-    args:
-    - "--line-length=99"
-    - "--target-version=py38"
   - id: black
     alias: black-check
     stages: [manual]
     args:
-    - "--line-length=99"
-    - "--target-version=py38"
     - "--check"
     - "--diff"
-- repo: https://gitlab.com/pycqa/flake8
+- repo: https://github.com/pycqa/flake8
   rev: 4.0.1
   hooks:
   - id: flake8
@@ -43,7 +37,7 @@ repos:
     alias: flake8-check
     stages: [manual]
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.782
+  rev: v0.981
   hooks:
   - id: mypy
     # N.B.: Mypy is... a bit fragile.

CONTRIBUTING.md

@@ -1,79 +1,30 @@
-# Contributing to `dbt`
+# Contributing to `dbt-core`
+
+`dbt-core` is open source software. It is what it is today because community members have opened issues, provided feedback, and [contributed to the knowledge loop](https://www.getdbt.com/dbt-labs/values/). Whether you are a seasoned open source contributor or a first-time committer, we welcome and encourage you to contribute code, documentation, ideas, or problem statements to this project.
 
 1. [About this document](#about-this-document)
-2. [Proposing a change](#proposing-a-change)
-3. [Getting the code](#getting-the-code)
-4. [Setting up an environment](#setting-up-an-environment)
-5. [Running `dbt` in development](#running-dbt-in-development)
-6. [Testing](#testing)
-7. [Submitting a Pull Request](#submitting-a-pull-request)
+2. [Getting the code](#getting-the-code)
+3. [Setting up an environment](#setting-up-an-environment)
+4. [Running `dbt` in development](#running-dbt-core-in-development)
+5. [Testing dbt-core](#testing)
+6. [Debugging](#debugging)
+7. [Adding a changelog entry](#adding-a-changelog-entry)
+8. [Submitting a Pull Request](#submitting-a-pull-request)
 
 ## About this document
 
-This document is a guide intended for folks interested in contributing to `dbt-core`. Below, we document the process by which members of the community should create issues and submit pull requests (PRs) in this repository. It is not intended as a guide for using `dbt-core`, and it assumes a certain level of familiarity with Python concepts such as virtualenvs, `pip`, python modules, filesystems, and so on. This guide assumes you are using macOS or Linux and are comfortable with the command line.
+There are many ways to contribute to the ongoing development of `dbt-core`, such as by participating in discussions and issues. We encourage you to first read our higher-level document: ["Expectations for Open Source Contributors"](https://docs.getdbt.com/docs/contributing/oss-expectations).
 
-If you're new to python development or contributing to open-source software, we encourage you to read this document from start to finish. If you get stuck, drop us a line in the `#dbt-core-development` channel on [slack](https://community.getdbt.com).
+The rest of this document serves as a more granular guide for contributing code changes to `dbt-core` (this repository). It is not intended as a guide for using `dbt-core`, and some pieces assume a level of familiarity with Python development (virtualenvs, `pip`, etc). Specific code snippets in this guide assume you are using macOS or Linux and are comfortable with the command line.
 
-#### Adapters
+If you get stuck, we're happy to help! Drop us a line in the `#dbt-core-development` channel in the [dbt Community Slack](https://community.getdbt.com).
 
-If you have an issue or code change suggestion related to a specific database [adapter](https://docs.getdbt.com/docs/available-adapters); please refer to that supported databases seperate repo for those contributions.
+### Notes
 
-### Signing the CLA
-
-Please note that all contributors to `dbt-core` must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements) to have their Pull Request merged into the `dbt-core` codebase. If you are unable to sign the CLA, then the `dbt-core` maintainers will unfortunately be unable to merge your Pull Request. You are, however, welcome to open issues and comment on existing ones.
-
-## Proposing a change
-
-`dbt-core` is Apache 2.0-licensed open source software. `dbt-core` is what it is today because community members like you have opened issues, provided feedback, and contributed to the knowledge loop for the entire communtiy. Whether you are a seasoned open source contributor or a first-time committer, we welcome and encourage you to contribute code, documentation, ideas, or problem statements to this project.
-
-### Defining the problem
-
-If you have an idea for a new feature or if you've discovered a bug in `dbt-core`, the first step is to open an issue. Please check the list of [open issues](https://github.com/dbt-labs/dbt-core/issues) before creating a new one. If you find a relevant issue, please add a comment to the open issue instead of creating a new one. There are hundreds of open issues in this repository and it can be hard to know where to look for a relevant open issue. **The `dbt-core` maintainers are always happy to point contributors in the right direction**, so please err on the side of documenting your idea in a new issue if you are unsure where a problem statement belongs.
-
-> **Note:** All community-contributed Pull Requests _must_ be associated with an open issue. If you submit a Pull Request that does not pertain to an open issue, you will be asked to create an issue describing the problem before the Pull Request can be reviewed.
-
-### Discussing the idea
-
-After you open an issue, a `dbt-core` maintainer will follow up by commenting on your issue (usually within 1-3 days) to explore your idea further and advise on how to implement the suggested changes. In many cases, community members will chime in with their own thoughts on the problem statement. If you as the issue creator are interested in submitting a Pull Request to address the issue, you should indicate this in the body of the issue. The `dbt-core` maintainers are _always_ happy to help contributors with the implementation of fixes and features, so please also indicate if there's anything you're unsure about or could use guidance around in the issue.
-
-### Submitting a change
-
-If an issue is appropriately well scoped and describes a beneficial change to the `dbt-core` codebase, then anyone may submit a Pull Request to implement the functionality described in the issue. See the sections below on how to do this.
-
-The `dbt-core` maintainers will add a `good first issue` label if an issue is suitable for a first-time contributor. This label often means that the required code change is small, limited to one database adapter, or a net-new addition that does not impact existing functionality. You can see the list of currently open issues on the [Contribute](https://github.com/dbt-labs/dbt-core/contribute) page.
-
-Here's a good workflow:
-- Comment on the open issue, expressing your interest in contributing the required code change
-- Outline your planned implementation. If you want help getting started, ask!
-- Follow the steps outlined below to develop locally. Once you have opened a PR, one of the `dbt-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.
-
-### Using issue labels
-
-The `dbt-core` maintainers use labels to categorize open issues. Most labels describe the domain in the `dbt-core` codebase germane to the discussion.
-
-| tag | description |
-| --- | ----------- |
-| [triage](https://github.com/dbt-labs/dbt-core/labels/triage) | This is a new issue which has not yet been reviewed by a `dbt-core` maintainer. This label is removed when a maintainer reviews and responds to the issue. |
-| [bug](https://github.com/dbt-labs/dbt-core/labels/bug) | This issue represents a defect or regression in `dbt-core` |
-| [enhancement](https://github.com/dbt-labs/dbt-core/labels/enhancement) | This issue represents net-new functionality in `dbt-core` |
-| [good first issue](https://github.com/dbt-labs/dbt-core/labels/good%20first%20issue) | This issue does not require deep knowledge of the `dbt-core` codebase to implement. This issue is appropriate for a first-time contributor. |
-| [help wanted](https://github.com/dbt-labs/dbt-core/labels/help%20wanted) / [discussion](https://github.com/dbt-labs/dbt-core/labels/discussion) | Conversation around this issue in ongoing, and there isn't yet a clear path forward. Input from community members is most welcome. |
-| [duplicate](https://github.com/dbt-labs/dbt-core/issues/duplicate) | This issue is functionally identical to another open issue. The `dbt-core` maintainers will close this issue and encourage community members to focus conversation on the other one. |
-| [snoozed](https://github.com/dbt-labs/dbt-core/labels/snoozed) | This issue describes a good idea, but one which will probably not be addressed in a six-month time horizon. The `dbt-core` maintainers will revist these issues periodically and re-prioritize them accordingly. |
-| [stale](https://github.com/dbt-labs/dbt-core/labels/stale) | This is an old issue which has not recently been updated. Stale issues will periodically be closed by `dbt-core` maintainers, but they can be re-opened if the discussion is restarted. |
-| [wontfix](https://github.com/dbt-labs/dbt-core/labels/wontfix) | This issue does not require a code change in the `dbt-core` repository, or the maintainers are unwilling/unable to merge a Pull Request which implements the behavior described in the issue. |
-
-#### Branching Strategy
-
-`dbt-core` has three types of branches:
-
-- **Trunks** are where active development of the next release takes place. There is one trunk named `main` at the time of writing this, and will be the default branch of the repository.
-- **Release Branches** track a specific, not yet complete release of `dbt-core`. Each minor version release has a corresponding release branch. For example, the `0.11.x` series of releases has a branch called `0.11.latest`. This allows us to release new patch versions under `0.11` without necessarily needing to pull them into the latest version of `dbt-core`.
-- **Feature Branches** track individual features and fixes. On completion they should be merged into the trunk branch or a specific release branch.
+- **Adapters:** Is your issue or proposed code change related to a specific [database adapter](https://docs.getdbt.com/docs/available-adapters)? If so, please open issues, PRs, and discussions in that adapter's repository instead. The sole exception is Postgres; the `dbt-postgres` plugin lives in this repository (`dbt-core`).
+- **CLA:** Please note that anyone contributing code to `dbt-core` must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements). If you are unable to sign the CLA, the `dbt-core` maintainers will unfortunately be unable to merge any of your Pull Requests. We welcome you to participate in discussions, open issues, and comment on existing ones.
+- **Branches:** All pull requests from community contributors should target the `main` branch (default). If the change is needed as a patch for a minor version of dbt that has already been released (or is already a release candidate), a maintainer will backport the changes in your PR to the relevant "latest" release branch (`1.0.latest`, `1.1.latest`, ...). If an issue fix applies to a release branch, that fix should be first committed to the development branch and then to the release branch (rarely release-branch fixes may not apply to `main`).
+- **Releases**: Before releasing a new minor version of Core, we prepare a series of alphas and release candidates to allow users (especially employees of dbt Labs!) to test the new version in live environments. This is an important quality assurance step, as it exposes the new code to a wide variety of complicated deployments and can surface bugs before official release. Releases are accessible via pip, homebrew, and dbt Cloud.
 
 ## Getting the code
 
@@ -85,15 +36,17 @@ You will need `git` in order to download and modify the `dbt-core` source code.
 
 If you are not a member of the `dbt-labs` GitHub organization, you can contribute to `dbt-core` by forking the `dbt-core` repository. For a detailed overview on forking, check out the [GitHub docs on forking](https://help.github.com/en/articles/fork-a-repo). In short, you will need to:
 
-1. fork the `dbt-core` repository
-2. clone your fork locally
-3. check out a new branch for your proposed changes
-4. push changes to your fork
-5. open a pull request against `dbt-labs/dbt` from your forked repository
+1. Fork the `dbt-core` repository
+2. Clone your fork locally
+3. Check out a new branch for your proposed changes
+4. Push changes to your fork
+5. Open a pull request against `dbt-labs/dbt-core` from your forked repository
 
 ### dbt Labs contributors
 
-If you are a member of the `dbt-labs` GitHub organization, you will have push access to the `dbt-core` repo. Rather than forking `dbt-core` to make your changes, just clone the repository, check out a new branch, and push directly to that branch.
+If you are a member of the `dbt-labs` GitHub organization, you will have push access to the `dbt-core` repo. Rather than forking `dbt-core` to make your changes, just clone the repository, check out a new branch, and push directly to that branch. Branch names should be fixed by `CT-XXX/` where:
+* CT stands for 'core team'
+* XXX stands for a JIRA ticket number
 
 ## Setting up an environment
 
@@ -101,19 +54,21 @@ There are some tools that will be helpful to you in developing locally. While th
 
 ### Tools
 
-A short list of tools used in `dbt-core` testing that will be helpful to your understanding:
+These are the tools used in `dbt-core` development and testing:
 
-- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, Python 3.8, and Python 3.9
-- [`pytest`](https://docs.pytest.org/en/latest/) to discover/run tests
-- [`make`](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) - but don't worry too much, nobody _really_ understands how make works and our Makefile is super simple
+- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, 3.8, 3.9, 3.10 and 3.11
+- [`pytest`](https://docs.pytest.org/en/latest/) to define, discover, and run tests
 - [`flake8`](https://flake8.pycqa.org/en/latest/) for code linting
 - [`black`](https://github.com/psf/black) for code formatting
 - [`mypy`](https://mypy.readthedocs.io/en/stable/) for static type checking
-- [Github Actions](https://github.com/features/actions)
+- [`pre-commit`](https://pre-commit.com) to easily run those checks
+- [`changie`](https://changie.dev/) to create changelog entries, without merge conflicts
+- [`make`](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) to run multiple setup or test steps in combination. Don't worry too much, nobody _really_ understands how `make` works, and our Makefile aims to be super simple.
+- [GitHub Actions](https://github.com/features/actions) for automating tests and checks, once a PR is pushed to the `dbt-core` repository
 
-A deep understanding of these tools in not required to effectively contribute to `dbt-core`, but we recommend checking out the attached documentation if you're interested in learning more about them.
+A deep understanding of these tools in not required to effectively contribute to `dbt-core`, but we recommend checking out the attached documentation if you're interested in learning more about each one.
 
-#### virtual environments
+#### Virtual environments
 
 We strongly recommend using virtual environments when developing code in `dbt-core`. We recommend creating this virtualenv
 in the root of the `dbt-core` repository. To create a new virtualenv, run:
@@ -124,12 +79,12 @@ source env/bin/activate
 
 This will create and activate a new Python virtual environment.
 
-#### docker and docker-compose
+#### Docker and `docker-compose`
 
-Docker and docker-compose are both used in testing. Specific instructions for you OS can be found [here](https://docs.docker.com/get-docker/).
+Docker and `docker-compose` are both used in testing. Specific instructions for you OS can be found [here](https://docs.docker.com/get-docker/).
 
 
-#### postgres (optional)
+#### Postgres (optional)
 
 For testing, and later in the examples in this document, you may want to have `psql` available so you can poke around in the database and see what happened. We recommend that you use [homebrew](https://brew.sh/) for that on macOS, and your package manager on Linux. You can install any version of the postgres client that you'd like. On macOS, with homebrew setup, you can run:
 
@@ -141,32 +96,37 @@ brew install postgresql
 
 ### Installation
 
-First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment).  Also ensure you have the latest version of pip installed with `pip install --upgrade pip`. Next, install `dbt-core` (and its dependencies) with:
+First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment).  Also ensure you have the latest version of pip installed with `pip install --upgrade pip`. Next, install `dbt-core` (and its dependencies):
 
 ```sh
 make dev
-# or
+```
+or, alternatively:
+```sh
 pip install -r dev-requirements.txt -r editable-requirements.txt
+pre-commit install
 ```
 
-When `dbt-core` is installed this way, any changes you make to the `dbt-core` source code will be reflected immediately in your next `dbt-core` run.
-
+When installed in this way, any changes you make to your local copy of the source code will be reflected immediately in your next `dbt` run.
 
 ### Running `dbt-core`
 
-With your virtualenv activated, the `dbt-core` script should point back to the source code you've cloned on your machine. You can verify this by running `which dbt`. This command should show you a path to an executable in your virtualenv.
+With your virtualenv activated, the `dbt` script should point back to the source code you've cloned on your machine. You can verify this by running `which dbt`. This command should show you a path to an executable in your virtualenv.
 
-Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as necessary to connect to your target databases. It may be a good idea to add a new profile pointing to a local postgres instance, or a specific test sandbox within your data warehouse if appropriate.
+Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as necessary to connect to your target databases. It may be a good idea to add a new profile pointing to a local Postgres instance, or a specific test sandbox within your data warehouse if appropriate.
 
 ## Testing
 
-Getting the `dbt-core` integration tests set up in your local environment will be very helpful as you start to make changes to your local version of `dbt-core`. The section that follows outlines some helpful tips for setting up the test environment.
+Once you're able to manually test that your code change is working as expected, it's important to run existing automated tests, as well as adding some new ones. These tests will ensure that:
+- Your code changes do not unexpectedly break other established functionality
+- Your code changes can handle all known edge cases
+- The functionality you're adding will _keep_ working in the future
 
-Although `dbt-core` works with a number of different databases, you won't need to supply credentials for every one of these databases in your test environment. Instead you can test all dbt-core code changes with Python and Postgres.
+Although `dbt-core` works with a number of different databases, you won't need to supply credentials for every one of these databases in your test environment. Instead, you can test most `dbt-core` code changes with Python and Postgres.
 
 ### Initial setup
 
-We recommend starting with `dbt-core`'s Postgres tests. These tests cover most of the functionality in `dbt-core`, are the fastest to run, and are the easiest to set up. To run the Postgres integration tests, you'll have to do one extra step of setting up the test database:
+Postgres offers the easiest way to test most `dbt-core` functionality today. They are the fastest to run, and the easiest to set up. To run the Postgres integration tests, you'll have to do one extra step of setting up the test database:
 
 ```sh
 make setup-db
@@ -192,39 +152,82 @@ make test
 # Runs postgres integration tests with py38 in "fail fast" mode.
 make integration
 ```
-> 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,
+> These make targets assume you have a local installation of a recent version of [`tox`](https://tox.readthedocs.io/en/latest/) for unit/integration testing and pre-commit for code quality checks,
 > unless you use choose a Docker container to run tests. Run `make help` for more info.
 
 Check out the other targets in the Makefile to see other commonly used test
 suites.
 
 #### `pre-commit`
-[`pre-commit`](https.pre-commit.com) takes care of running all code-checks for formatting and linting. Run `make dev` to install `pre-commit` in your local environment.  Once this is done you can use any of the linter-based make targets as well as a git pre-commit hook that will ensure proper formatting and linting.
+[`pre-commit`](https://pre-commit.com) takes care of running all code-checks for formatting and linting. Run `make dev` to install `pre-commit` in your local environment (we recommend running this command with a python virtual environment active). This command installs several pip executables including black, mypy, and flake8. Once this is done you can use any of the linter-based make targets as well as a git pre-commit hook that will ensure proper formatting and linting.
 
 #### `tox`
 
-[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.7, Python 3.8, and Python 3.9 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
+[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.7, Python 3.8, Python 3.9, Python 3.10 and Python 3.11 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
 
 #### `pytest`
 
-Finally, you can also run a specific test or group of tests using [`pytest`](https://docs.pytest.org/en/latest/) directly. With a virtualenv
-active and dev dependencies installed you can do things like:
+Finally, you can also run a specific test or group of tests using [`pytest`](https://docs.pytest.org/en/latest/) directly. With a virtualenv active and dev dependencies installed you can do things like:
+
 ```sh
-# run specific postgres integration tests
-python -m pytest -m profile_postgres test/integration/001_simple_copy_test
 # run all unit tests in a file
-python -m pytest test/unit/test_graph.py
+python3 -m pytest test/unit/test_graph.py
 # run a specific unit test
-python -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
+python3 -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
+# run specific Postgres integration tests (old way)
+python3 -m pytest -m profile_postgres test/integration/074_postgres_unlogged_table_tests
+# run specific Postgres integration tests (new way)
+python3 -m pytest tests/functional/sources
 ```
-> [Here](https://docs.pytest.org/en/reorganize-docs/new-docs/user/commandlineuseful.html)
-> is a list of useful command-line options for `pytest` to use while developing.
+
+> See [pytest usage docs](https://docs.pytest.org/en/6.2.x/usage.html) for an overview of useful command-line options.
+
+### Unit, Integration, Functional?
+
+Here are some general rules for adding tests:
+* unit tests (`test/unit` & `tests/unit`) don’t need to access a database; "pure Python" tests should be written as unit tests
+* functional tests (`test/integration` & `tests/functional`) cover anything that interacts with a database, namely adapter
+* *everything in* `test/*` *is being steadily migrated to* `tests/*`
+
+## Debugging
+
+1. The logs for a `dbt run` have stack traces and other information for debugging errors (in `logs/dbt.log` in your project directory).
+2. Try using a debugger, like `ipdb`. For pytest: `--pdb --pdbcls=IPython.terminal.debugger:pdb`
+3. Sometimes, it’s easier to debug on a single thread: `dbt --single-threaded run`
+4. To make print statements from Jinja macros:  `{{ log(msg, info=true) }}`
+5. You can also add `{{ debug() }}` statements, which will drop you into some auto-generated code that the macro wrote.
+6. The dbt “artifacts” are written out to the ‘target’ directory of your dbt project. They are in unformatted json, which can be hard to read. Format them with:
+> python -m json.tool target/run_results.json > run_results.json
+
+### Assorted development tips
+* Append `# type: ignore` to the end of a line if you need to disable `mypy` on that line.
+* Sometimes flake8 complains about lines that are actually fine, in which case you can put a comment on the line such as: # noqa or # noqa: ANNN, where ANNN is the error code that flake8 issues.
+* To collect output for `CProfile`, run dbt with the `-r` option and the name of an output file, i.e. `dbt -r dbt.cprof run`. If you just want to profile parsing, you can do: `dbt -r dbt.cprof parse`. `pip` install `snakeviz` to view the output. Run `snakeviz dbt.cprof` and output will be rendered in a browser window.
+
+## Adding or modifying a CHANGELOG Entry
+
+We use [changie](https://changie.dev) to generate `CHANGELOG` entries. **Note:** Do not edit the `CHANGELOG.md` directly. Your modifications will be lost.
+
+Follow the steps to [install `changie`](https://changie.dev/guide/installation/) for your system.
+
+Once changie is installed and your PR is created for a new feature, simply run the following command and changie will walk you through the process of creating a changelog entry:
+
+```shell
+changie new
+```
+
+Commit the file that's created and your changelog entry is complete!
+
+If you are contributing to a feature already in progress, you will modify the changie yaml file in dbt/.changes/unreleased/ related to your change. If you need help finding this file, please ask within the discussion for the pull request!
+
+You don't need to worry about which `dbt-core` version your change will go into. Just create the changelog entry with `changie`, and open your PR against the `main` branch. All merged changes will be included in the next minor version of `dbt-core`. The Core maintainers _may_ choose to "backport" specific changes in order to patch older minor versions. In that case, a maintainer will take care of that backport after merging your PR, before releasing the new version of `dbt-core`.
+
 ## Submitting a Pull Request
 
-dbt Labs provides a CI environment to test changes to specific adapters, and periodic maintenance checks of `dbt-core` through Github Actions. For example, if you submit a pull request to the `dbt-redshift` repo, GitHub will trigger automated code checks and tests against Redshift.
-
-A `dbt-core` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
-- First time contributors should note code checks + unit tests require a maintainer to approve.
+Code can be merged into the current development branch `main` by opening a pull request. A `dbt-core` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
 
+Automated tests run via GitHub Actions. If you're a first-time contributor, all tests (including code checks and unit tests) will require a maintainer to approve. Changes in the `dbt-core` repository trigger integration tests against Postgres. dbt Labs also provides CI environments in which to test changes to other adapters, triggered by PRs in those adapters' repositories, as well as periodic maintenance checks of each adapter in concert with the latest `dbt-core` code changes.
 
 Once all tests are passing and your PR has been approved, a `dbt-core` maintainer will merge your changes into the active development branch. And that's it! Happy developing :tada:
+
+Sometimes, the content license agreement auto-check bot doesn't find a user's entry in its roster. If you need to force a rerun, add `@cla-bot check` in a comment on the pull request.

Dockerfile.test

@@ -3,7 +3,7 @@
 #  See `/docker` for a generic and production-ready docker file
 ##
 
-FROM ubuntu:20.04
+FROM ubuntu:23.04
 
 ENV DEBIAN_FRONTEND noninteractive
 
@@ -46,6 +46,12 @@ RUN apt-get update \
     python3.9 \
     python3.9-dev \
     python3.9-venv \
+    python3.10 \
+    python3.10-dev \
+    python3.10-venv \
+    python3.11 \
+    python3.11-dev \
+    python3.11-venv \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 

Makefile

@@ -6,12 +6,42 @@ ifeq ($(USE_DOCKER),true)
 	DOCKER_CMD := docker-compose run --rm test
 endif
 
-.PHONY: dev
-dev: ## Installs dbt-* packages in develop mode along with development dependencies.
+#
+# To override CI_flags, create a file at this repo's root dir named `makefile.test.env`. Fill it
+# with any ENV_VAR overrides required by your test environment, e.g.
+#    DBT_TEST_USER_1=user
+#    LOG_DIR="dir with a space in it"
+#
+# Warn: Restrict each line to one variable only.
+#
+ifeq (./makefile.test.env,$(wildcard ./makefile.test.env))
+	include ./makefile.test.env
+endif
+
+CI_FLAGS =\
+	DBT_TEST_USER_1=$(if $(DBT_TEST_USER_1),$(DBT_TEST_USER_1),dbt_test_user_1)\
+	DBT_TEST_USER_2=$(if $(DBT_TEST_USER_2),$(DBT_TEST_USER_2),dbt_test_user_2)\
+	DBT_TEST_USER_3=$(if $(DBT_TEST_USER_3),$(DBT_TEST_USER_3),dbt_test_user_3)\
+	RUSTFLAGS=$(if $(RUSTFLAGS),$(RUSTFLAGS),"-D warnings")\
+	LOG_DIR=$(if $(LOG_DIR),$(LOG_DIR),./logs)\
+	DBT_LOG_FORMAT=$(if $(DBT_LOG_FORMAT),$(DBT_LOG_FORMAT),json)
+
+
+.PHONY: dev_req
+dev_req: ## Installs dbt-* packages in develop mode along with only development dependencies.
+	@\
+	pip install -r dev-requirements.txt
+	pip install -r editable-requirements.txt
+
+.PHONY: dev
+dev: dev_req ## Installs dbt-* packages in develop mode along with development dependencies and pre-commit.
 	@\
-	pip install -r dev-requirements.txt -r editable-requirements.txt && \
 	pre-commit install
 
+.PHONY: proto_types
+proto_types:  ## generates google protobuf python file from types.proto
+	protoc -I=./core/dbt/events --python_out=./core/dbt/events ./core/dbt/events/types.proto
+
 .PHONY: mypy
 mypy: .env ## Runs mypy against staged changes for static type checking.
 	@\
@@ -34,33 +64,34 @@ lint: .env ## Runs flake8 and mypy code checks against staged changes.
 	$(DOCKER_CMD) pre-commit run mypy-check --hook-stage manual | grep -v "INFO"
 
 .PHONY: unit
-unit: .env ## Runs unit tests with py38.
+unit: .env ## Runs unit tests with py
 	@\
-	$(DOCKER_CMD) tox -e py38
+	$(DOCKER_CMD) tox -e py
 
 .PHONY: test
-test: .env ## Runs unit tests with py38 and code checks against staged changes.
+test: .env ## Runs unit tests with py and code checks against staged changes.
 	@\
-	$(DOCKER_CMD) tox -p -e py38; \
+	$(DOCKER_CMD) tox -e py; \
 	$(DOCKER_CMD) pre-commit run black-check --hook-stage manual | grep -v "INFO"; \
 	$(DOCKER_CMD) pre-commit run flake8-check --hook-stage manual | grep -v "INFO"; \
 	$(DOCKER_CMD) pre-commit run mypy-check --hook-stage manual | grep -v "INFO"
 
 .PHONY: integration
-integration: .env integration-postgres ## Alias for integration-postgres.
+integration: .env ## Runs postgres integration tests with py-integration
+	@\
+	$(CI_FLAGS) $(DOCKER_CMD) tox -e py-integration -- -nauto
 
 .PHONY: integration-fail-fast
-integration-fail-fast: .env integration-postgres-fail-fast ## Alias for integration-postgres-fail-fast.
-
-.PHONY: integration-postgres
-integration-postgres: .env ## Runs postgres integration tests with py38.
+integration-fail-fast: .env ## Runs postgres integration tests with py-integration in "fail fast" mode.
 	@\
-	$(DOCKER_CMD) tox -e py38-postgres -- -nauto
+	$(DOCKER_CMD) tox -e py-integration -- -x -nauto
 
-.PHONY: integration-postgres-fail-fast
-integration-postgres-fail-fast: .env ## Runs postgres integration tests with py38 in "fail fast" mode.
+.PHONY: interop
+interop: clean
 	@\
-	$(DOCKER_CMD) tox -e py38-postgres -- -x -nauto
+	mkdir $(LOG_DIR) && \
+	$(CI_FLAGS) $(DOCKER_CMD) tox -e py-integration -- -nauto && \
+	LOG_DIR=$(LOG_DIR) cargo run --manifest-path test/interop/log_parsing/Cargo.toml
 
 .PHONY: setup-db
 setup-db: ## Setup Postgres database with docker-compose for system testing.
@@ -83,6 +114,7 @@ endif
 clean: ## Resets development environment.
 	@echo 'cleaning repo...'
 	@rm -f .coverage
+	@rm -f .coverage.*
 	@rm -rf .eggs/
 	@rm -f .env
 	@rm -rf .tox/

README.md

@@ -3,16 +3,13 @@
 </p>
 <p align="center">
   <a href="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml">
-    <img src="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml/badge.svg?event=push" alt="Unit Tests Badge"/>
-  </a>
-  <a href="https://github.com/dbt-labs/dbt-core/actions/workflows/integration.yml">
-    <img src="https://github.com/dbt-labs/dbt-core/actions/workflows/integration.yml/badge.svg?event=push" alt="Integration Tests Badge"/>
+    <img src="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml/badge.svg?event=push" alt="CI Badge"/>
   </a>
 </p>
 
 **[dbt](https://www.getdbt.com/)** enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.
 
-![architecture](https://raw.githubusercontent.com/dbt-labs/dbt-core/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-arch.png)
+![architecture](https://github.com/dbt-labs/dbt-core/blob/202cb7e51e218c7b29eb3b11ad058bd56b7739de/etc/dbt-transform.png)
 
 ## Understanding dbt
 
@@ -24,7 +21,7 @@ These select statements, or "models", form a dbt project. Models frequently buil
 
 ## Getting started
 
-- [Install dbt](https://docs.getdbt.com/docs/installation)
+- [Install dbt](https://docs.getdbt.com/docs/get-started/installation)
 - Read the [introduction](https://docs.getdbt.com/docs/introduction/) and [viewpoint](https://docs.getdbt.com/docs/about/viewpoint/)
 
 ## Join the dbt Community

core/MANIFEST.in

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

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

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

core/dbt/__init__.py

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

core/dbt/adapters/README.md

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

core/dbt/adapters/__init__.py

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

core/dbt/adapters/base/README.md

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

core/dbt/adapters/base/__init__.py

@@ -1,14 +1,19 @@
 # these are all just exports, #noqa them so flake8 will be happy
 
 # TODO: Should we still include this in the `adapters` namespace?
-from dbt.contracts.connection import Credentials  # noqa
-from dbt.adapters.base.meta import available  # noqa
-from dbt.adapters.base.connections import BaseConnectionManager  # noqa
-from dbt.adapters.base.relation import (  # noqa
+from dbt.contracts.connection import Credentials  # noqa: F401
+from dbt.adapters.base.meta import available  # noqa: F401
+from dbt.adapters.base.connections import BaseConnectionManager  # noqa: F401
+from dbt.adapters.base.relation import (  # noqa: F401
     BaseRelation,
     RelationType,
     SchemaSearchMap,
 )
-from dbt.adapters.base.column import Column  # noqa
-from dbt.adapters.base.impl import AdapterConfig, BaseAdapter  # noqa
-from dbt.adapters.base.plugin import AdapterPlugin  # noqa
+from dbt.adapters.base.column import Column  # noqa: F401
+from dbt.adapters.base.impl import (  # noqa: F401
+    AdapterConfig,
+    BaseAdapter,
+    PythonJobHelper,
+    ConstraintSupport,
+)
+from dbt.adapters.base.plugin import AdapterPlugin  # noqa: F401

core/dbt/adapters/base/column.py

@@ -2,7 +2,7 @@ from dataclasses import dataclass
 import re
 from typing import Dict, ClassVar, Any, Optional
 
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 @dataclass
@@ -12,6 +12,7 @@ class Column:
         "TIMESTAMP": "TIMESTAMP",
         "FLOAT": "FLOAT",
         "INTEGER": "INT",
+        "BOOLEAN": "BOOLEAN",
     }
     column: str
     dtype: str
@@ -59,6 +60,7 @@ class Column:
             "float",
             "double precision",
             "float8",
+            "double",
         ]
 
     def is_integer(self) -> bool:
@@ -84,7 +86,7 @@ class Column:
 
     def string_size(self) -> int:
         if not self.is_string():
-            raise RuntimeException("Called string_size() on non-string field!")
+            raise DbtRuntimeError("Called string_size() on non-string field!")
 
         if self.dtype == "text" or self.char_size is None:
             # char_size should never be None. Handle it reasonably just in case
@@ -123,7 +125,7 @@ class Column:
     def from_description(cls, name: str, raw_data_type: str) -> "Column":
         match = re.match(r"([^(]+)(\([^)]+\))?", raw_data_type)
         if match is None:
-            raise RuntimeException(f'Could not interpret data type "{raw_data_type}"')
+            raise DbtRuntimeError(f'Could not interpret data type "{raw_data_type}"')
         data_type, size_info = match.groups()
         char_size = None
         numeric_precision = None
@@ -136,7 +138,7 @@ class Column:
                 try:
                     char_size = int(parts[0])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[0]}" to an integer'
                     )
@@ -144,14 +146,14 @@ class Column:
                 try:
                     numeric_precision = int(parts[0])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[0]}" to an integer'
                     )
                 try:
                     numeric_scale = int(parts[1])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[1]}" to an integer'
                     )

core/dbt/adapters/base/connections.py

@@ -1,10 +1,25 @@
 import abc
 import os
+from time import sleep
+import sys
+import traceback
 
 # multiprocessing.RLock is a function returning this type
 from multiprocessing.synchronize import RLock
 from threading import get_ident
-from typing import Dict, Tuple, Hashable, Optional, ContextManager, List, Union
+from typing import (
+    Any,
+    Dict,
+    Tuple,
+    Hashable,
+    Optional,
+    ContextManager,
+    List,
+    Type,
+    Union,
+    Iterable,
+    Callable,
+)
 
 import agate
 
@@ -21,18 +36,24 @@ from dbt.contracts.graph.manifest import Manifest
 from dbt.adapters.base.query_headers import (
     MacroQueryStringSetter,
 )
+from dbt.events import AdapterLogger
 from dbt.events.functions import fire_event
 from dbt.events.types import (
     NewConnection,
     ConnectionReused,
+    ConnectionLeftOpenInCleanup,
     ConnectionLeftOpen,
-    ConnectionLeftOpen2,
+    ConnectionClosedInCleanup,
     ConnectionClosed,
-    ConnectionClosed2,
     Rollback,
     RollbackFailed,
 )
+from dbt.events.contextvars import get_node_info
 from dbt import flags
+from dbt.utils import cast_to_str
+
+SleepTime = Union[int, float]  # As taken by time.sleep.
+AdapterHandle = Any  # Adapter connection handle objects can be any class.
 
 
 class BaseConnectionManager(metaclass=abc.ABCMeta):
@@ -70,13 +91,13 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         key = self.get_thread_identifier()
         with self.lock:
             if key not in self.thread_connections:
-                raise dbt.exceptions.InvalidConnectionException(key, list(self.thread_connections))
+                raise dbt.exceptions.InvalidConnectionError(key, list(self.thread_connections))
             return self.thread_connections[key]
 
     def set_thread_connection(self, conn: Connection) -> None:
         key = self.get_thread_identifier()
         if key in self.thread_connections:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 "In set_thread_connection, existing connection exists for {}"
             )
         self.thread_connections[key] = conn
@@ -116,57 +137,148 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :return: A context manager that handles exceptions raised by the
             underlying database.
         """
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`exception_handler` is not implemented for this adapter!"
         )
 
     def set_connection_name(self, name: Optional[str] = None) -> Connection:
-        conn_name: str
-        if name is None:
-            # if a name isn't specified, we'll re-use a single handle
-            # named 'master'
-            conn_name = "master"
-        else:
-            if not isinstance(name, str):
-                raise dbt.exceptions.CompilerException(
-                    f"For connection name, got {name} - not a string!"
-                )
-            assert isinstance(name, str)
-            conn_name = name
+        """Called by 'acquire_connection' in BaseAdapter, which is called by
+        'connection_named', called by 'connection_for(node)'.
+        Creates a connection for this thread if one doesn't already
+        exist, and will rename an existing connection."""
 
+        conn_name: str = "master" if name is None else name
+
+        # Get a connection for this thread
         conn = self.get_if_exists()
+
+        if conn and conn.name == conn_name and conn.state == "open":
+            # Found a connection and nothing to do, so just return it
+            return conn
+
         if conn is None:
+            # Create a new connection
             conn = Connection(
                 type=Identifier(self.TYPE),
-                name=None,
+                name=conn_name,
                 state=ConnectionState.INIT,
                 transaction_open=False,
                 handle=None,
                 credentials=self.profile.credentials,
             )
-            self.set_thread_connection(conn)
-
-        if conn.name == conn_name and conn.state == "open":
-            return conn
-
-        fire_event(NewConnection(conn_name=conn_name, conn_type=self.TYPE))
-
-        if conn.state == "open":
-            fire_event(ConnectionReused(conn_name=conn_name))
-        else:
             conn.handle = LazyHandle(self.open)
+            # Add the connection to thread_connections for this thread
+            self.set_thread_connection(conn)
+            fire_event(
+                NewConnection(conn_name=conn_name, conn_type=self.TYPE, node_info=get_node_info())
+            )
+        else:  # existing connection either wasn't open or didn't have the right name
+            if conn.state != "open":
+                conn.handle = LazyHandle(self.open)
+            if conn.name != conn_name:
+                orig_conn_name: str = conn.name or ""
+                conn.name = conn_name
+                fire_event(ConnectionReused(orig_conn_name=orig_conn_name, conn_name=conn_name))
 
-        conn.name = conn_name
         return conn
 
+    @classmethod
+    def retry_connection(
+        cls,
+        connection: Connection,
+        connect: Callable[[], AdapterHandle],
+        logger: AdapterLogger,
+        retryable_exceptions: Iterable[Type[Exception]],
+        retry_limit: int = 1,
+        retry_timeout: Union[Callable[[int], SleepTime], SleepTime] = 1,
+        _attempts: int = 0,
+    ) -> Connection:
+        """Given a Connection, set its handle by calling connect.
+
+        The calls to connect will be retried up to retry_limit times to deal with transient
+        connection errors. By default, one retry will be attempted if retryable_exceptions is set.
+
+        :param Connection connection: An instance of a Connection that needs a handle to be set,
+            usually when attempting to open it.
+        :param connect: A callable that returns the appropiate connection handle for a
+            given adapter. This callable will be retried retry_limit times if a subclass of any
+            Exception in retryable_exceptions is raised by connect.
+        :type connect: Callable[[], AdapterHandle]
+        :param AdapterLogger logger: A logger to emit messages on retry attempts or errors. When
+            handling expected errors, we call debug, and call warning on unexpected errors or when
+            all retry attempts have been exhausted.
+        :param retryable_exceptions: An iterable of exception classes that if raised by
+            connect should trigger a retry.
+        :type retryable_exceptions: Iterable[Type[Exception]]
+        :param int retry_limit: How many times to retry the call to connect. If this limit
+            is exceeded before a successful call, a FailedToConnectError will be raised.
+            Must be non-negative.
+        :param retry_timeout: Time to wait between attempts to connect. Can also take a
+            Callable that takes the number of attempts so far, beginning at 0, and returns an int
+            or float to be passed to time.sleep.
+        :type retry_timeout: Union[Callable[[int], SleepTime], SleepTime] = 1
+        :param int _attempts: Parameter used to keep track of the number of attempts in calling the
+            connect function across recursive calls. Passed as an argument to retry_timeout if it
+            is a Callable. This parameter should not be set by the initial caller.
+        :raises dbt.exceptions.FailedToConnectError: Upon exhausting all retry attempts without
+            successfully acquiring a handle.
+        :return: The given connection with its appropriate state and handle attributes set
+            depending on whether we successfully acquired a handle or not.
+        """
+        timeout = retry_timeout(_attempts) if callable(retry_timeout) else retry_timeout
+        if timeout < 0:
+            raise dbt.exceptions.FailedToConnectError(
+                "retry_timeout cannot be negative or return a negative time."
+            )
+
+        if retry_limit < 0 or retry_limit > sys.getrecursionlimit():
+            # This guard is not perfect others may add to the recursion limit (e.g. built-ins).
+            connection.handle = None
+            connection.state = ConnectionState.FAIL
+            raise dbt.exceptions.FailedToConnectError("retry_limit cannot be negative")
+
+        try:
+            connection.handle = connect()
+            connection.state = ConnectionState.OPEN
+            return connection
+
+        except tuple(retryable_exceptions) as e:
+            if retry_limit <= 0:
+                connection.handle = None
+                connection.state = ConnectionState.FAIL
+                raise dbt.exceptions.FailedToConnectError(str(e))
+
+            logger.debug(
+                f"Got a retryable error when attempting to open a {cls.TYPE} connection.\n"
+                f"{retry_limit} attempts remaining. Retrying in {timeout} seconds.\n"
+                f"Error:\n{e}"
+            )
+
+            sleep(timeout)
+            return cls.retry_connection(
+                connection=connection,
+                connect=connect,
+                logger=logger,
+                retry_limit=retry_limit - 1,
+                retry_timeout=retry_timeout,
+                retryable_exceptions=retryable_exceptions,
+                _attempts=_attempts + 1,
+            )
+
+        except Exception as e:
+            connection.handle = None
+            connection.state = ConnectionState.FAIL
+            raise dbt.exceptions.FailedToConnectError(str(e))
+
     @abc.abstractmethod
     def cancel_open(self) -> Optional[List[str]]:
         """Cancel all open connections on the adapter. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`cancel_open` is not implemented for this adapter!"
         )
 
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def open(cls, connection: Connection) -> Connection:
         """Open the given connection on the adapter and return it.
 
@@ -176,7 +288,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         This should be thread-safe, or hold the lock if necessary. The given
         connection should not be in either in_use or available.
         """
-        raise dbt.exceptions.NotImplementedException("`open` is not implemented for this adapter!")
+        raise dbt.exceptions.NotImplementedError("`open` is not implemented for this adapter!")
 
     def release(self) -> None:
         with self.lock:
@@ -197,9 +309,9 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         with self.lock:
             for connection in self.thread_connections.values():
                 if connection.state not in {"closed", "init"}:
-                    fire_event(ConnectionLeftOpen(conn_name=connection.name))
+                    fire_event(ConnectionLeftOpenInCleanup(conn_name=cast_to_str(connection.name)))
                 else:
-                    fire_event(ConnectionClosed(conn_name=connection.name))
+                    fire_event(ConnectionClosedInCleanup(conn_name=cast_to_str(connection.name)))
                 self.close(connection)
 
             # garbage collect these connections
@@ -208,16 +320,12 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     @abc.abstractmethod
     def begin(self) -> None:
         """Begin a transaction. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
-            "`begin` is not implemented for this adapter!"
-        )
+        raise dbt.exceptions.NotImplementedError("`begin` is not implemented for this adapter!")
 
     @abc.abstractmethod
     def commit(self) -> None:
         """Commit a transaction. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
-            "`commit` is not implemented for this adapter!"
-        )
+        raise dbt.exceptions.NotImplementedError("`commit` is not implemented for this adapter!")
 
     @classmethod
     def _rollback_handle(cls, connection: Connection) -> None:
@@ -225,28 +333,40 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         try:
             connection.handle.rollback()
         except Exception:
-            fire_event(RollbackFailed(conn_name=connection.name))
+            fire_event(
+                RollbackFailed(
+                    conn_name=cast_to_str(connection.name),
+                    exc_info=traceback.format_exc(),
+                    node_info=get_node_info(),
+                )
+            )
 
     @classmethod
     def _close_handle(cls, connection: Connection) -> None:
         """Perform the actual close operation."""
         # On windows, sometimes connection handles don't have a close() attr.
         if hasattr(connection.handle, "close"):
-            fire_event(ConnectionClosed2(conn_name=connection.name))
+            fire_event(
+                ConnectionClosed(conn_name=cast_to_str(connection.name), node_info=get_node_info())
+            )
             connection.handle.close()
         else:
-            fire_event(ConnectionLeftOpen2(conn_name=connection.name))
+            fire_event(
+                ConnectionLeftOpen(
+                    conn_name=cast_to_str(connection.name), node_info=get_node_info()
+                )
+            )
 
     @classmethod
     def _rollback(cls, connection: Connection) -> None:
         """Roll back the given connection."""
         if connection.transaction_open is False:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Tried to rollback transaction on connection "
                 f'"{connection.name}", but it does not have one open!'
             )
 
-        fire_event(Rollback(conn_name=connection.name))
+        fire_event(Rollback(conn_name=cast_to_str(connection.name), node_info=get_node_info()))
         cls._rollback_handle(connection)
 
         connection.transaction_open = False
@@ -258,7 +378,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             return connection
 
         if connection.transaction_open and connection.handle:
-            fire_event(Rollback(conn_name=connection.name))
+            fire_event(Rollback(conn_name=cast_to_str(connection.name), node_info=get_node_info()))
             cls._rollback_handle(connection)
         connection.transaction_open = False
 
@@ -281,16 +401,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     @abc.abstractmethod
     def execute(
         self, sql: str, auto_begin: bool = False, fetch: bool = False
-    ) -> Tuple[Union[str, AdapterResponse], agate.Table]:
+    ) -> Tuple[AdapterResponse, agate.Table]:
         """Execute the given SQL.
 
         :param str sql: The sql to execute.
         :param bool auto_begin: If set, and dbt is not currently inside a
             transaction, automatically begin one.
         :param bool fetch: If set, fetch results.
-        :return: A tuple of the status and the results (empty if fetch=False).
-        :rtype: Tuple[Union[str, AdapterResponse], agate.Table]
+        :return: A tuple of the query status and results (empty if fetch=False).
+        :rtype: Tuple[AdapterResponse, agate.Table]
         """
-        raise dbt.exceptions.NotImplementedException(
-            "`execute` is not implemented for this adapter!"
-        )
+        raise dbt.exceptions.NotImplementedError("`execute` is not implemented for this adapter!")

core/dbt/adapters/base/impl.py

@@ -2,48 +2,63 @@ import abc
 from concurrent.futures import as_completed, Future
 from contextlib import contextmanager
 from datetime import datetime
+from enum import Enum
+import time
 from itertools import chain
 from typing import (
-    Optional,
-    Tuple,
-    Callable,
-    Iterable,
-    Type,
-    Dict,
     Any,
+    Callable,
+    Dict,
+    Iterable,
+    Iterator,
     List,
     Mapping,
-    Iterator,
-    Union,
+    Optional,
     Set,
+    Tuple,
+    Type,
+    Union,
 )
 
+from dbt.contracts.graph.nodes import ColumnLevelConstraint, ConstraintType, ModelLevelConstraint
+
 import agate
 import pytz
 
 from dbt.exceptions import (
-    raise_database_error,
-    raise_compiler_error,
-    invalid_type_error,
-    get_relation_returned_multiple_results,
-    InternalException,
-    NotImplementedException,
-    RuntimeException,
+    DbtInternalError,
+    DbtRuntimeError,
+    DbtValidationError,
+    MacroArgTypeError,
+    MacroResultError,
+    NotImplementedError,
+    NullRelationCacheAttemptedError,
+    NullRelationDropAttemptedError,
+    QuoteConfigTypeError,
+    RelationReturnedMultipleResultsError,
+    RenameToNoneAttemptedError,
+    SnapshotTargetIncompleteError,
+    SnapshotTargetNotSnapshotTableError,
+    UnexpectedNonTimestampError,
+    UnexpectedNullError,
 )
 
-from dbt.adapters.protocol import (
-    AdapterConfig,
-    ConnectionManagerProtocol,
-)
+from dbt.adapters.protocol import AdapterConfig, ConnectionManagerProtocol
 from dbt.clients.agate_helper import empty_table, merge_tables, table_from_rows
 from dbt.clients.jinja import MacroGenerator
-from dbt.contracts.graph.compiled import CompileResultNode, CompiledSeedNode
 from dbt.contracts.graph.manifest import Manifest, MacroManifest
-from dbt.contracts.graph.parsed import ParsedSeedNode
-from dbt.exceptions import warn_or_error
-from dbt.events.functions import fire_event
-from dbt.events.types import CacheMiss, ListRelations
-from dbt.utils import filter_null_values, executor
+from dbt.contracts.graph.nodes import ResultNode
+from dbt.events.functions import fire_event, warn_or_error
+from dbt.events.types import (
+    CacheMiss,
+    ListRelations,
+    CodeExecution,
+    CodeExecutionStatus,
+    CatalogGenerationError,
+    ConstraintNotSupported,
+    ConstraintNotEnforced,
+)
+from dbt.utils import filter_null_values, executor, cast_to_str, AttrDict
 
 from dbt.adapters.base.connections import Connection, AdapterResponse
 from dbt.adapters.base.meta import AdapterMeta, available
@@ -54,19 +69,23 @@ from dbt.adapters.base.relation import (
     SchemaSearchMap,
 )
 from dbt.adapters.base import Column as BaseColumn
-from dbt.adapters.cache import RelationsCache, _make_key
-
-
-SeedModel = Union[ParsedSeedNode, CompiledSeedNode]
-
+from dbt.adapters.base import Credentials
+from dbt.adapters.cache import RelationsCache, _make_ref_key_dict
+from dbt import deprecations
 
 GET_CATALOG_MACRO_NAME = "get_catalog"
 FRESHNESS_MACRO_NAME = "collect_freshness"
 
 
+class ConstraintSupport(str, Enum):
+    ENFORCED = "enforced"
+    NOT_ENFORCED = "not_enforced"
+    NOT_SUPPORTED = "not_supported"
+
+
 def _expect_row_value(key: str, row: agate.Row):
     if key not in row.keys():
-        raise InternalException(
+        raise DbtInternalError(
             'Got a row without "{}" column, columns: {}'.format(key, row.keys())
         )
     return row[key]
@@ -95,18 +114,10 @@ def _utc(dt: Optional[datetime], source: BaseRelation, field_name: str) -> datet
     assume the datetime is already for UTC and add the timezone.
     """
     if dt is None:
-        raise raise_database_error(
-            "Expected a non-null value when querying field '{}' of table "
-            " {} but received value 'null' instead".format(field_name, source)
-        )
+        raise UnexpectedNullError(field_name, source)
 
     elif not hasattr(dt, "tzinfo"):
-        raise raise_database_error(
-            "Expected a timestamp value when querying field '{}' of table "
-            "{} but received value of type '{}' instead".format(
-                field_name, source, type(dt).__name__
-            )
-        )
+        raise UnexpectedNonTimestampError(field_name, source, dt)
 
     elif dt.tzinfo:
         return dt.astimezone(pytz.UTC)
@@ -121,6 +132,35 @@ def _relation_name(rel: Optional[BaseRelation]) -> str:
         return str(rel)
 
 
+def log_code_execution(code_execution_function):
+    # decorator to log code and execution time
+    if code_execution_function.__name__ != "submit_python_job":
+        raise ValueError("this should be only used to log submit_python_job now")
+
+    def execution_with_log(*args):
+        self = args[0]
+        connection_name = self.connections.get_thread_connection().name
+        fire_event(CodeExecution(conn_name=connection_name, code_content=args[2]))
+        start_time = time.time()
+        response = code_execution_function(*args)
+        fire_event(
+            CodeExecutionStatus(
+                status=response._message, elapsed=round((time.time() - start_time), 2)
+            )
+        )
+        return response
+
+    return execution_with_log
+
+
+class PythonJobHelper:
+    def __init__(self, parsed_model: Dict, credential: Credentials) -> None:
+        raise NotImplementedError("PythonJobHelper is not implemented yet")
+
+    def submit(self, compiled_code: str) -> Any:
+        raise NotImplementedError("PythonJobHelper submit function is not implemented yet")
+
+
 class BaseAdapter(metaclass=AdapterMeta):
     """The BaseAdapter provides an abstract base class for adapters.
 
@@ -130,9 +170,15 @@ class BaseAdapter(metaclass=AdapterMeta):
     methods are marked with a (passable) in their docstrings. Check docstrings
     for type information, etc.
 
-    To implement a macro, implement "${adapter_type}__${macro_name}". in the
+    To implement a macro, implement "${adapter_type}__${macro_name}" in the
     adapter's internal project.
 
+    To invoke a method in an adapter macro, call it on the 'adapter' Jinja
+    object using dot syntax.
+
+    To invoke a method in model code, add the @available decorator atop a method
+    declaration. Methods are invoked as macros.
+
     Methods:
         - exception_handler
         - date_function
@@ -141,6 +187,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         - truncate_relation
         - rename_relation
         - get_columns_in_relation
+        - get_column_schema_from_query
         - expand_column_types
         - list_relations_without_caching
         - is_cancelable
@@ -153,6 +200,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         - convert_datetime_type
         - convert_date_type
         - convert_time_type
+        - standardize_grants_dict
 
     Macros:
         - get_catalog
@@ -166,6 +214,14 @@ class BaseAdapter(metaclass=AdapterMeta):
     # for use in materializations
     AdapterSpecificConfigs: Type[AdapterConfig] = AdapterConfig
 
+    CONSTRAINT_SUPPORT = {
+        ConstraintType.check: ConstraintSupport.NOT_SUPPORTED,
+        ConstraintType.not_null: ConstraintSupport.ENFORCED,
+        ConstraintType.unique: ConstraintSupport.NOT_ENFORCED,
+        ConstraintType.primary_key: ConstraintSupport.NOT_ENFORCED,
+        ConstraintType.foreign_key: ConstraintSupport.ENFORCED,
+    }
+
     def __init__(self, config):
         self.config = config
         self.cache = RelationsCache()
@@ -200,9 +256,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         return conn.name
 
     @contextmanager
-    def connection_named(
-        self, name: str, node: Optional[CompileResultNode] = None
-    ) -> Iterator[None]:
+    def connection_named(self, name: str, node: Optional[ResultNode] = None) -> Iterator[None]:
         try:
             if self.connections.query_header is not None:
                 self.connections.query_header.set(name, node)
@@ -214,14 +268,14 @@ class BaseAdapter(metaclass=AdapterMeta):
                 self.connections.query_header.reset()
 
     @contextmanager
-    def connection_for(self, node: CompileResultNode) -> Iterator[None]:
+    def connection_for(self, node: ResultNode) -> Iterator[None]:
         with self.connection_named(node.unique_id, node):
             yield
 
     @available.parse(lambda *a, **k: ("", empty_table()))
     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. This is a thin wrapper around
         ConnectionManager.execute.
 
@@ -229,11 +283,24 @@ class BaseAdapter(metaclass=AdapterMeta):
         :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]
         """
         return self.connections.execute(sql=sql, auto_begin=auto_begin, fetch=fetch)
 
+    @available.parse(lambda *a, **k: [])
+    def get_column_schema_from_query(self, sql: str) -> List[BaseColumn]:
+        """Get a list of the Columns with names and data types from the given sql."""
+        _, cursor = self.connections.add_select_query(sql)
+        columns = [
+            self.Column.create(
+                column_name, self.connections.data_type_code_to_name(column_type_code)
+            )
+            # https://peps.python.org/pep-0249/#description
+            for column_name, column_type_code, *_ in cursor.description
+        ]
+        return columns
+
     @available.parse(lambda *a, **k: ("", empty_table()))
     def get_partitions_metadata(self, table: str) -> Tuple[agate.Table]:
         """Obtain partitions metadata for a BigQuery partitioned table.
@@ -270,12 +337,17 @@ class BaseAdapter(metaclass=AdapterMeta):
         """
         return self._macro_manifest_lazy
 
-    def load_macro_manifest(self) -> MacroManifest:
+    def load_macro_manifest(self, base_macros_only=False) -> MacroManifest:
+        # base_macros_only is for the test framework
         if self._macro_manifest_lazy is None:
             # avoid a circular import
             from dbt.parser.manifest import ManifestLoader
 
-            manifest = ManifestLoader.load_macros(self.config, self.connections.set_query_header)
+            manifest = ManifestLoader.load_macros(
+                self.config,
+                self.connections.set_query_header,
+                base_macros_only=base_macros_only,
+            )
             # TODO CT-211
             self._macro_manifest_lazy = manifest  # type: ignore[assignment]
         # TODO CT-211
@@ -293,7 +365,11 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         if (database, schema) not in self.cache:
             fire_event(
-                CacheMiss(conn_name=self.nice_connection_name(), database=database, schema=schema)
+                CacheMiss(
+                    conn_name=self.nice_connection_name(),
+                    database=cast_to_str(database),
+                    schema=schema,
+                )
             )
             return False
         else:
@@ -320,7 +396,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         lowercase strings.
         """
         info_schema_name_map = SchemaSearchMap()
-        nodes: Iterator[CompileResultNode] = chain(
+        nodes: Iterator[ResultNode] = chain(
             [
                 node
                 for node in manifest.nodes.values()
@@ -337,11 +413,14 @@ class BaseAdapter(metaclass=AdapterMeta):
         # databases
         return info_schema_name_map
 
-    def _relations_cache_for_schemas(self, manifest: Manifest) -> None:
+    def _relations_cache_for_schemas(
+        self, manifest: Manifest, cache_schemas: Set[BaseRelation] = None
+    ) -> None:
         """Populate the relations cache for the given schemas. Returns an
         iterable of the schemas populated, as strings.
         """
-        cache_schemas = self._get_cache_schemas(manifest)
+        if not cache_schemas:
+            cache_schemas = self._get_cache_schemas(manifest)
         with executor(self.config) as tpe:
             futures: List[Future[List[BaseRelation]]] = []
             for cache_schema in cache_schemas:
@@ -367,21 +446,26 @@ class BaseAdapter(metaclass=AdapterMeta):
             cache_update.add((relation.database, relation.schema))
         self.cache.update_schemas(cache_update)
 
-    def set_relations_cache(self, manifest: Manifest, clear: bool = False) -> None:
+    def set_relations_cache(
+        self,
+        manifest: Manifest,
+        clear: bool = False,
+        required_schemas: Set[BaseRelation] = None,
+    ) -> None:
         """Run a query that gets a populated cache of the relations in the
         database and set the cache on this adapter.
         """
         with self.cache.lock:
             if clear:
                 self.cache.clear()
-            self._relations_cache_for_schemas(manifest)
+            self._relations_cache_for_schemas(manifest, required_schemas)
 
     @available
     def cache_added(self, relation: Optional[BaseRelation]) -> str:
         """Cache a new relation in dbt. It will show up in `list relations`."""
         if relation is None:
             name = self.nice_connection_name()
-            raise_compiler_error("Attempted to cache a null relation for {}".format(name))
+            raise NullRelationCacheAttemptedError(name)
         self.cache.add(relation)
         # so jinja doesn't render things
         return ""
@@ -393,7 +477,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         """
         if relation is None:
             name = self.nice_connection_name()
-            raise_compiler_error("Attempted to drop a null relation for {}".format(name))
+            raise NullRelationDropAttemptedError(name)
         self.cache.drop(relation)
         return ""
 
@@ -410,9 +494,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             name = self.nice_connection_name()
             src_name = _relation_name(from_relation)
             dst_name = _relation_name(to_relation)
-            raise_compiler_error(
-                "Attempted to rename {} to {} for {}".format(src_name, dst_name, name)
-            )
+            raise RenameToNoneAttemptedError(src_name, dst_name, name)
 
         self.cache.rename(from_relation, to_relation)
         return ""
@@ -420,14 +502,16 @@ class BaseAdapter(metaclass=AdapterMeta):
     ###
     # Abstract methods for database-specific values, attributes, and types
     ###
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def date_function(cls) -> str:
         """Get the date function used by this adapter's database."""
-        raise NotImplementedException("`date_function` is not implemented for this adapter!")
+        raise NotImplementedError("`date_function` is not implemented for this adapter!")
 
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def is_cancelable(cls) -> bool:
-        raise NotImplementedException("`is_cancelable` is not implemented for this adapter!")
+        raise NotImplementedError("`is_cancelable` is not implemented for this adapter!")
 
     ###
     # Abstract methods about schemas
@@ -435,7 +519,7 @@ class BaseAdapter(metaclass=AdapterMeta):
     @abc.abstractmethod
     def list_schemas(self, database: str) -> List[str]:
         """Get a list of existing schemas in database"""
-        raise NotImplementedException("`list_schemas` is not implemented for this adapter!")
+        raise NotImplementedError("`list_schemas` is not implemented for this adapter!")
 
     @available.parse(lambda *a, **k: False)
     def check_schema_exists(self, database: str, schema: str) -> bool:
@@ -458,13 +542,13 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         *Implementors must call self.cache.drop() to preserve cache state!*
         """
-        raise NotImplementedException("`drop_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`drop_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
     def truncate_relation(self, relation: BaseRelation) -> None:
         """Truncate the given relation."""
-        raise NotImplementedException("`truncate_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`truncate_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
@@ -473,15 +557,13 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         Implementors must call self.cache.rename() to preserve cache state.
         """
-        raise NotImplementedException("`rename_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`rename_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_list
     def get_columns_in_relation(self, relation: BaseRelation) -> List[BaseColumn]:
         """Get a list of the columns in the given Relation."""
-        raise NotImplementedException(
-            "`get_columns_in_relation` is not implemented for this adapter!"
-        )
+        raise NotImplementedError("`get_columns_in_relation` is not implemented for this adapter!")
 
     @available.deprecated("get_columns_in_relation", lambda *a, **k: [])
     def get_columns_in_table(self, schema: str, identifier: str) -> List[BaseColumn]:
@@ -503,7 +585,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param self.Relation current: A relation that currently exists in the
             database with columns of unspecified types.
         """
-        raise NotImplementedException(
+        raise NotImplementedError(
             "`expand_target_column_types` is not implemented for this adapter!"
         )
 
@@ -518,10 +600,37 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The relations in schema
         :rtype: List[self.Relation]
         """
-        raise NotImplementedException(
-            "`list_relations_without_caching` is not implemented for this " "adapter!"
+        raise NotImplementedError(
+            "`list_relations_without_caching` is not implemented for this adapter!"
         )
 
+    ###
+    # Methods about grants
+    ###
+    @available
+    def standardize_grants_dict(self, grants_table: agate.Table) -> dict:
+        """Translate the result of `show grants` (or equivalent) to match the
+        grants which a user would configure in their project.
+
+        Ideally, the SQL to show grants should also be filtering:
+        filter OUT any grants TO the current user/role (e.g. OWNERSHIP).
+        If that's not possible in SQL, it can be done in this method instead.
+
+        :param grants_table: An agate table containing the query result of
+            the SQL returned by get_show_grant_sql
+        :return: A standardized dictionary matching the `grants` config
+        :rtype: dict
+        """
+        grants_dict: Dict[str, List[str]] = {}
+        for row in grants_table:
+            grantee = row["grantee"]
+            privilege = row["privilege_type"]
+            if privilege in grants_dict.keys():
+                grants_dict[privilege].append(grantee)
+            else:
+                grants_dict.update({privilege: [grantee]})
+        return grants_dict
+
     ###
     # Provided methods about relations
     ###
@@ -533,7 +642,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         to_relation.
         """
         if not isinstance(from_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="get_missing_columns",
                 arg_name="from_relation",
                 got_value=from_relation,
@@ -541,7 +650,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             )
 
         if not isinstance(to_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="get_missing_columns",
                 arg_name="to_relation",
                 got_value=to_relation,
@@ -562,11 +671,11 @@ class BaseAdapter(metaclass=AdapterMeta):
         expected columns.
 
         :param Relation relation: The relation to check
-        :raises CompilationException: If the columns are
+        :raises InvalidMacroArgType: If the columns are
             incorrect.
         """
         if not isinstance(relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="valid_snapshot_target",
                 arg_name="relation",
                 got_value=relation,
@@ -587,24 +696,16 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         if missing:
             if extra:
-                msg = (
-                    'Snapshot target has ("{}") but not ("{}") - is it an '
-                    "unmigrated previous version archive?".format(
-                        '", "'.join(extra), '", "'.join(missing)
-                    )
-                )
+                raise SnapshotTargetIncompleteError(extra, missing)
             else:
-                msg = 'Snapshot target is not a snapshot table (missing "{}")'.format(
-                    '", "'.join(missing)
-                )
-            raise_compiler_error(msg)
+                raise SnapshotTargetNotSnapshotTableError(missing)
 
     @available.parse_none
     def expand_target_column_types(
         self, from_relation: BaseRelation, to_relation: BaseRelation
     ) -> None:
         if not isinstance(from_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="expand_target_column_types",
                 arg_name="from_relation",
                 got_value=from_relation,
@@ -612,7 +713,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             )
 
         if not isinstance(to_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="expand_target_column_types",
                 arg_name="to_relation",
                 got_value=to_relation,
@@ -626,15 +727,32 @@ class BaseAdapter(metaclass=AdapterMeta):
             return self.cache.get_relations(database, schema)
 
         schema_relation = self.Relation.create(
-            database=database, schema=schema, identifier="", quote_policy=self.config.quoting
+            database=database,
+            schema=schema,
+            identifier="",
+            quote_policy=self.config.quoting,
         ).without_identifier()
 
         # we can't build the relations cache because we don't have a
         # manifest so we can't run any operations.
         relations = self.list_relations_without_caching(schema_relation)
+
+        # if the cache is already populated, add this schema in
+        # otherwise, skip updating the cache and just ignore
+        if self.cache:
+            for relation in relations:
+                self.cache.add(relation)
+            if not relations:
+                # it's possible that there were no relations in some schemas. We want
+                # to insert the schemas we query into the cache's `.schemas` attribute
+                # so we can check it later
+                self.cache.update_schemas([(database, schema)])
+
         fire_event(
             ListRelations(
-                database=database, schema=schema, relations=[_make_key(x) for x in relations]
+                database=cast_to_str(database),
+                schema=schema,
+                relations=[_make_ref_key_dict(x) for x in relations],
             )
         )
 
@@ -689,7 +807,7 @@ class BaseAdapter(metaclass=AdapterMeta):
                 "schema": schema,
                 "database": database,
             }
-            get_relation_returned_multiple_results(kwargs, matches)
+            raise RelationReturnedMultipleResultsError(kwargs, matches)
 
         elif matches:
             return matches[0]
@@ -711,19 +829,20 @@ class BaseAdapter(metaclass=AdapterMeta):
     @available.parse_none
     def create_schema(self, relation: BaseRelation):
         """Create the given schema if it does not exist."""
-        raise NotImplementedException("`create_schema` is not implemented for this adapter!")
+        raise NotImplementedError("`create_schema` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
     def drop_schema(self, relation: BaseRelation):
         """Drop the given schema (and everything in it) if it exists."""
-        raise NotImplementedException("`drop_schema` is not implemented for this adapter!")
+        raise NotImplementedError("`drop_schema` is not implemented for this adapter!")
 
     @available
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def quote(cls, identifier: str) -> str:
         """Quote the given identifier, as appropriate for the database."""
-        raise NotImplementedException("`quote` is not implemented for this adapter!")
+        raise NotImplementedError("`quote` is not implemented for this adapter!")
 
     @available
     def quote_as_configured(self, identifier: str, quote_key: str) -> str:
@@ -752,10 +871,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         elif quote_config is None:
             pass
         else:
-            raise_compiler_error(
-                f'The seed configuration value of "quote_columns" has an '
-                f"invalid type {type(quote_config)}"
-            )
+            raise QuoteConfigTypeError(quote_config)
 
         if quote_columns:
             return self.quote(column)
@@ -766,7 +882,8 @@ class BaseAdapter(metaclass=AdapterMeta):
     # Conversions: These must be implemented by concrete implementations, for
     # converting agate types into their sql equivalents.
     ###
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def convert_text_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         """Return the type in the database that best maps to the agate.Text
         type for the given agate table and column index.
@@ -775,9 +892,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_text_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_text_type` is not implemented for this adapter!")
 
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def convert_number_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         """Return the type in the database that best maps to the agate.Number
         type for the given agate table and column index.
@@ -786,9 +904,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_number_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_number_type` is not implemented for this adapter!")
 
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         """Return the type in the database that best maps to the agate.Boolean
         type for the given agate table and column index.
@@ -797,11 +916,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException(
-            "`convert_boolean_type` is not implemented for this adapter!"
-        )
+        raise NotImplementedError("`convert_boolean_type` is not implemented for this adapter!")
 
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def convert_datetime_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         """Return the type in the database that best maps to the agate.DateTime
         type for the given agate table and column index.
@@ -810,11 +928,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException(
-            "`convert_datetime_type` is not implemented for this adapter!"
-        )
+        raise NotImplementedError("`convert_datetime_type` is not implemented for this adapter!")
 
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def convert_date_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         """Return the type in the database that best maps to the agate.Date
         type for the given agate table and column index.
@@ -823,9 +940,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_date_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_date_type` is not implemented for this adapter!")
 
-    @abc.abstractclassmethod
+    @classmethod
+    @abc.abstractmethod
     def convert_time_type(cls, agate_table: agate.Table, col_idx: int) -> str:
         """Return the type in the database that best maps to the
         agate.TimeDelta type for the given agate table and column index.
@@ -834,7 +952,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_time_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_time_type` is not implemented for this adapter!")
 
     @available
     @classmethod
@@ -869,7 +987,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         context_override: Optional[Dict[str, Any]] = None,
         kwargs: Dict[str, Any] = None,
         text_only_columns: Optional[Iterable[str]] = None,
-    ) -> agate.Table:
+    ) -> AttrDict:
         """Look macro_name up in the manifest and execute its results.
 
         :param macro_name: The name of the macro to execute.
@@ -901,7 +1019,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             else:
                 package_name = 'the "{}" package'.format(project)
 
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 'dbt could not find a macro with the name "{}" in {}'.format(
                     macro_name, package_name
                 )
@@ -954,7 +1072,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             manifest=manifest,
         )
 
-        results = self._catalog_filter_table(table, manifest)
+        results = self._catalog_filter_table(table, manifest)  # type: ignore[arg-type]
         return results
 
     def get_catalog(self, manifest: Manifest) -> Tuple[agate.Table, List[Exception]]:
@@ -986,7 +1104,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         loaded_at_field: str,
         filter: Optional[str],
         manifest: Optional[Manifest] = None,
-    ) -> Dict[str, Any]:
+    ) -> Tuple[Optional[AdapterResponse], Dict[str, Any]]:
         """Calculate the freshness of sources in dbt, and return it"""
         kwargs: Dict[str, Any] = {
             "source": source,
@@ -995,15 +1113,23 @@ class BaseAdapter(metaclass=AdapterMeta):
         }
 
         # run the macro
-        table = self.execute_macro(FRESHNESS_MACRO_NAME, kwargs=kwargs, manifest=manifest)
+        # in older versions of dbt-core, the 'collect_freshness' macro returned the table of results directly
+        # starting in v1.5, by default, we return both the table and the adapter response (metadata about the query)
+        result: Union[
+            AttrDict,  # current: contains AdapterResponse + agate.Table
+            agate.Table,  # previous: just table
+        ]
+        result = self.execute_macro(FRESHNESS_MACRO_NAME, kwargs=kwargs, manifest=manifest)
+        if isinstance(result, agate.Table):
+            deprecations.warn("collect-freshness-return-signature")
+            adapter_response = None
+            table = result
+        else:
+            adapter_response, table = result.response, result.table  # type: ignore[attr-defined]
         # now we have a 1-row table of the maximum `loaded_at_field` value and
         # the current time according to the db.
         if len(table) != 1 or len(table[0]) != 2:
-            raise_compiler_error(
-                'Got an invalid result from "{}" macro: {}'.format(
-                    FRESHNESS_MACRO_NAME, [tuple(r) for r in table]
-                )
-            )
+            raise MacroResultError(FRESHNESS_MACRO_NAME, table)
         if table[0][0] is None:
             # no records in the table, so really the max_loaded_at was
             # infinitely long ago. Just call it 0:00 January 1 year UTC
@@ -1013,11 +1139,12 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         snapshotted_at = _utc(table[0][1], source, loaded_at_field)
         age = (snapshotted_at - max_loaded_at).total_seconds()
-        return {
+        freshness = {
             "max_loaded_at": max_loaded_at,
             "snapshotted_at": snapshotted_at,
             "age": age,
         }
+        return adapter_response, freshness
 
     def pre_model_hook(self, config: Mapping[str, Any]) -> Any:
         """A hook for running some operation before the model materialization
@@ -1080,7 +1207,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         elif location == "prepend":
             return f"'{value}' || {add_to}"
         else:
-            raise RuntimeException(f'Got an unexpected location value of "{location}"')
+            raise DbtRuntimeError(f'Got an unexpected location value of "{location}"')
 
     def get_rows_different_sql(
         self,
@@ -1111,6 +1238,187 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         return sql
 
+    @property
+    def python_submission_helpers(self) -> Dict[str, Type[PythonJobHelper]]:
+        raise NotImplementedError("python_submission_helpers is not specified")
+
+    @property
+    def default_python_submission_method(self) -> str:
+        raise NotImplementedError("default_python_submission_method is not specified")
+
+    @log_code_execution
+    def submit_python_job(self, parsed_model: dict, compiled_code: str) -> AdapterResponse:
+        submission_method = parsed_model["config"].get(
+            "submission_method", self.default_python_submission_method
+        )
+        if submission_method not in self.python_submission_helpers:
+            raise NotImplementedError(
+                "Submission method {} is not supported for current adapter".format(
+                    submission_method
+                )
+            )
+        job_helper = self.python_submission_helpers[submission_method](
+            parsed_model, self.connections.profile.credentials
+        )
+        submission_result = job_helper.submit(compiled_code)
+        # process submission result to generate adapter response
+        return self.generate_python_submission_response(submission_result)
+
+    def generate_python_submission_response(self, submission_result: Any) -> AdapterResponse:
+        raise NotImplementedError(
+            "Your adapter need to implement generate_python_submission_response"
+        )
+
+    def valid_incremental_strategies(self):
+        """The set of standard builtin strategies which this adapter supports out-of-the-box.
+        Not used to validate custom strategies defined by end users.
+        """
+        return ["append"]
+
+    def builtin_incremental_strategies(self):
+        return ["append", "delete+insert", "merge", "insert_overwrite"]
+
+    @available.parse_none
+    def get_incremental_strategy_macro(self, model_context, strategy: str):
+        # Construct macro_name from strategy name
+        if strategy is None:
+            strategy = "default"
+
+        # validate strategies for this adapter
+        valid_strategies = self.valid_incremental_strategies()
+        valid_strategies.append("default")
+        builtin_strategies = self.builtin_incremental_strategies()
+        if strategy in builtin_strategies and strategy not in valid_strategies:
+            raise DbtRuntimeError(
+                f"The incremental strategy '{strategy}' is not valid for this adapter"
+            )
+
+        strategy = strategy.replace("+", "_")
+        macro_name = f"get_incremental_{strategy}_sql"
+        # The model_context should have MacroGenerator callable objects for all macros
+        if macro_name not in model_context:
+            raise DbtRuntimeError(
+                'dbt could not find an incremental strategy macro with the name "{}" in {}'.format(
+                    macro_name, self.config.project_name
+                )
+            )
+
+        # This returns a callable macro
+        return model_context[macro_name]
+
+    @classmethod
+    def _parse_column_constraint(cls, raw_constraint: Dict[str, Any]) -> ColumnLevelConstraint:
+        try:
+            ColumnLevelConstraint.validate(raw_constraint)
+            return ColumnLevelConstraint.from_dict(raw_constraint)
+        except Exception:
+            raise DbtValidationError(f"Could not parse constraint: {raw_constraint}")
+
+    @classmethod
+    def render_column_constraint(cls, constraint: ColumnLevelConstraint) -> Optional[str]:
+        """Render the given constraint as DDL text. Should be overriden by adapters which need custom constraint
+        rendering."""
+        constraint_expression = constraint.expression or ""
+
+        rendered_column_constraint = None
+        if constraint.type == ConstraintType.check and constraint_expression:
+            rendered_column_constraint = f"check ({constraint_expression})"
+        elif constraint.type == ConstraintType.not_null:
+            rendered_column_constraint = f"not null {constraint_expression}"
+        elif constraint.type == ConstraintType.unique:
+            rendered_column_constraint = f"unique {constraint_expression}"
+        elif constraint.type == ConstraintType.primary_key:
+            rendered_column_constraint = f"primary key {constraint_expression}"
+        elif constraint.type == ConstraintType.foreign_key and constraint_expression:
+            rendered_column_constraint = f"references {constraint_expression}"
+        elif constraint.type == ConstraintType.custom and constraint_expression:
+            rendered_column_constraint = constraint_expression
+
+        if rendered_column_constraint:
+            rendered_column_constraint = rendered_column_constraint.strip()
+
+        return rendered_column_constraint
+
+    @available
+    @classmethod
+    def render_raw_columns_constraints(cls, raw_columns: Dict[str, Dict[str, Any]]) -> List:
+        rendered_column_constraints = []
+
+        for v in raw_columns.values():
+            col_name = cls.quote(v["name"]) if v.get("quote") else v["name"]
+            rendered_column_constraint = [f"{col_name} {v['data_type']}"]
+            for con in v.get("constraints", None):
+                constraint = cls._parse_column_constraint(con)
+                c = cls.process_parsed_constraint(constraint, cls.render_column_constraint)
+                if c is not None:
+                    rendered_column_constraint.append(c)
+            rendered_column_constraints.append(" ".join(rendered_column_constraint))
+
+        return rendered_column_constraints
+
+    @classmethod
+    def process_parsed_constraint(
+        cls, parsed_constraint: Union[ColumnLevelConstraint, ModelLevelConstraint], render_func
+    ) -> Optional[str]:
+        if (
+            parsed_constraint.warn_unsupported
+            and cls.CONSTRAINT_SUPPORT[parsed_constraint.type] == ConstraintSupport.NOT_SUPPORTED
+        ):
+            warn_or_error(
+                ConstraintNotSupported(constraint=parsed_constraint.type.value, adapter=cls.type())
+            )
+        if (
+            parsed_constraint.warn_unenforced
+            and cls.CONSTRAINT_SUPPORT[parsed_constraint.type] == ConstraintSupport.NOT_ENFORCED
+        ):
+            warn_or_error(
+                ConstraintNotEnforced(constraint=parsed_constraint.type.value, adapter=cls.type())
+            )
+        if cls.CONSTRAINT_SUPPORT[parsed_constraint.type] != ConstraintSupport.NOT_SUPPORTED:
+            return render_func(parsed_constraint)
+
+        return None
+
+    @classmethod
+    def _parse_model_constraint(cls, raw_constraint: Dict[str, Any]) -> ModelLevelConstraint:
+        try:
+            ModelLevelConstraint.validate(raw_constraint)
+            c = ModelLevelConstraint.from_dict(raw_constraint)
+            return c
+        except Exception:
+            raise DbtValidationError(f"Could not parse constraint: {raw_constraint}")
+
+    @available
+    @classmethod
+    def render_raw_model_constraints(cls, raw_constraints: List[Dict[str, Any]]) -> List[str]:
+        return [c for c in map(cls.render_raw_model_constraint, raw_constraints) if c is not None]
+
+    @classmethod
+    def render_raw_model_constraint(cls, raw_constraint: Dict[str, Any]) -> Optional[str]:
+        constraint = cls._parse_model_constraint(raw_constraint)
+        return cls.process_parsed_constraint(constraint, cls.render_model_constraint)
+
+    @classmethod
+    def render_model_constraint(cls, constraint: ModelLevelConstraint) -> Optional[str]:
+        """Render the given constraint as DDL text. Should be overriden by adapters which need custom constraint
+        rendering."""
+        constraint_prefix = f"constraint {constraint.name} " if constraint.name else ""
+        column_list = ", ".join(constraint.columns)
+        if constraint.type == ConstraintType.check and constraint.expression:
+            return f"{constraint_prefix}check ({constraint.expression})"
+        elif constraint.type == ConstraintType.unique:
+            constraint_expression = f" {constraint.expression}" if constraint.expression else ""
+            return f"{constraint_prefix}unique{constraint_expression} ({column_list})"
+        elif constraint.type == ConstraintType.primary_key:
+            constraint_expression = f" {constraint.expression}" if constraint.expression else ""
+            return f"{constraint_prefix}primary key{constraint_expression} ({column_list})"
+        elif constraint.type == ConstraintType.foreign_key and constraint.expression:
+            return f"{constraint_prefix}foreign key ({column_list}) references {constraint.expression}"
+        elif constraint.type == ConstraintType.custom and constraint.expression:
+            return f"{constraint_prefix}{constraint.expression}"
+        else:
+            return None
+
 
 COLUMNS_EQUAL_SQL = """
 with diff_count as (
@@ -1158,7 +1466,7 @@ def catch_as_completed(
         elif isinstance(exc, KeyboardInterrupt) or not isinstance(exc, Exception):
             raise exc
         else:
-            warn_or_error(f"Encountered an error while generating catalog: {str(exc)}")
+            warn_or_error(CatalogGenerationError(exc=str(exc)))
             # exc is not None, derives from Exception, and isn't ctrl+c
             exceptions.append(exc)
     return merge_tables(tables), exceptions

core/dbt/adapters/base/plugin.py

@@ -1,17 +1,17 @@
 from typing import List, Optional, Type
 
 from dbt.adapters.base import Credentials
-from dbt.exceptions import CompilationException
+from dbt.exceptions import CompilationError
 from dbt.adapters.protocol import AdapterProtocol
 
 
 def project_name_from_path(include_path: str) -> str:
     # avoid an import cycle
-    from dbt.config.project import Project
+    from dbt.config.project import PartialProject
 
-    partial = Project.partial_load(include_path)
+    partial = PartialProject.from_project_root(include_path)
     if partial.project_name is None:
-        raise CompilationException(f"Invalid project at {include_path}: name not set!")
+        raise CompilationError(f"Invalid project at {include_path}: name not set!")
     return partial.project_name
 
 

core/dbt/adapters/base/query_headers.py

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

core/dbt/adapters/base/relation.py

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

core/dbt/adapters/cache.py

@@ -2,26 +2,22 @@ import threading
 from copy import deepcopy
 from typing import Any, Dict, Iterable, List, Optional, Set, Tuple
 
-from dbt.adapters.reference_keys import _make_key, _ReferenceKey
-import dbt.exceptions
-from dbt.events.functions import fire_event
-from dbt.events.types import (
-    AddLink,
-    AddRelation,
-    DropCascade,
-    DropMissingRelation,
-    DropRelation,
-    DumpAfterAddGraph,
-    DumpAfterRenameSchema,
-    DumpBeforeAddGraph,
-    DumpBeforeRenameSchema,
-    RenameSchema,
-    TemporaryRelation,
-    UncachedRelation,
-    UpdateReference,
+from dbt.adapters.reference_keys import (
+    _make_ref_key,
+    _make_ref_key_dict,
+    _ReferenceKey,
 )
+from dbt.exceptions import (
+    DependentLinkNotCachedError,
+    NewNameAlreadyInCacheError,
+    NoneRelationFoundError,
+    ReferencedLinkNotCachedError,
+    TruncatedModelNameCausedCollisionError,
+)
+from dbt.events.functions import fire_event, fire_event_if
+from dbt.events.types import CacheAction, CacheDumpGraph
+from dbt.flags import get_flags
 from dbt.utils import lowercase
-from dbt.helper_types import Lazy
 
 
 def dot_separated(key: _ReferenceKey) -> str:
@@ -81,7 +77,7 @@ class _CachedRelation:
 
         :return _ReferenceKey: A key for this relation.
         """
-        return _make_key(self)
+        return _make_ref_key(self)
 
     def add_reference(self, referrer: "_CachedRelation"):
         """Add a reference from referrer to self, indicating that if this node
@@ -144,11 +140,7 @@ class _CachedRelation:
         :raises InternalError: If the new key already exists.
         """
         if new_key in self.referenced_by:
-            dbt.exceptions.raise_cache_inconsistent(
-                'in rename of "{}" -> "{}", new name is in the cache already'.format(
-                    old_key, new_key
-                )
-            )
+            raise NewNameAlreadyInCacheError(old_key, new_key)
 
         if old_key not in self.referenced_by:
             return
@@ -237,7 +229,7 @@ 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): str(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.
@@ -264,21 +256,17 @@ class RelationsCache:
         if referenced is None:
             return
         if referenced is None:
-            dbt.exceptions.raise_cache_inconsistent(
-                "in add_link, referenced link key {} not in cache!".format(referenced_key)
-            )
+            raise ReferencedLinkNotCachedError(referenced_key)
 
         dependent = self.relations.get(dependent_key)
         if dependent is None:
-            dbt.exceptions.raise_cache_inconsistent(
-                "in add_link, dependent link key {} not in cache!".format(dependent_key)
-            )
+            raise DependentLinkNotCachedError(dependent_key)
 
         assert dependent is not None  # we just raised!
 
         referenced.add_reference(dependent)
 
-    # TODO: Is this dead code?  I can't seem to find it grepping the codebase.
+    # This is called in plugins/postgres/dbt/adapters/postgres/impl.py
     def add_link(self, referenced, dependent):
         """Add a link between two relations to the database. If either relation
         does not exist, it will be added as an "external" relation.
@@ -293,13 +281,18 @@ class RelationsCache:
         :param BaseRelation dependent: The dependent model.
         :raises InternalError: If either entry does not exist.
         """
-        ref_key = _make_key(referenced)
-        dep_key = _make_key(dependent)
+        ref_key = _make_ref_key(referenced)
+        dep_key = _make_ref_key(dependent)
         if (ref_key.database, ref_key.schema) not in self:
             # if we have not cached the referenced schema at all, we must be
             # referring to a table outside our control. There's no need to make
             # a link - we will never drop the referenced relation during a run.
-            fire_event(UncachedRelation(dep_key=dep_key, ref_key=ref_key))
+            fire_event(
+                CacheAction(
+                    ref_key=ref_key._asdict(),
+                    ref_key_2=dep_key._asdict(),
+                )
+            )
             return
         if ref_key not in self.relations:
             # Insert a dummy "external" relation.
@@ -309,7 +302,13 @@ class RelationsCache:
             # Insert a dummy "external" relation.
             dependent = dependent.replace(type=referenced.External)
             self.add(dependent)
-        fire_event(AddLink(dep_key=dep_key, ref_key=ref_key))
+        fire_event(
+            CacheAction(
+                action="add_link",
+                ref_key=dep_key._asdict(),
+                ref_key_2=ref_key._asdict(),
+            )
+        )
         with self.lock:
             self._add_link(ref_key, dep_key)
 
@@ -319,13 +318,20 @@ class RelationsCache:
 
         :param BaseRelation relation: The underlying relation.
         """
+        flags = get_flags()
         cached = _CachedRelation(relation)
-        fire_event(AddRelation(relation=_make_key(cached)))
-        fire_event(DumpBeforeAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="before", action="adding", dump=self.dump_graph()),
+        )
+        fire_event(CacheAction(action="add_relation", ref_key=_make_ref_key_dict(cached)))
 
         with self.lock:
             self._setdefault(cached)
-        fire_event(DumpAfterAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="after", action="adding", dump=self.dump_graph()),
+        )
 
     def _remove_refs(self, keys):
         """Removes all references to all entries in keys. This does not
@@ -340,19 +346,6 @@ class RelationsCache:
         for cached in self.relations.values():
             cached.release_references(keys)
 
-    def _drop_cascade_relation(self, dropped_key):
-        """Drop the given relation and cascade it appropriately to all
-        dependent relations.
-
-        :param _CachedRelation dropped: An existing _CachedRelation to drop.
-        """
-        if dropped_key not in self.relations:
-            fire_event(DropMissingRelation(relation=dropped_key))
-            return
-        consequences = self.relations[dropped_key].collect_consequences()
-        fire_event(DropCascade(dropped=dropped_key, consequences=consequences))
-        self._remove_refs(consequences)
-
     def drop(self, relation):
         """Drop the named relation and cascade it appropriately to all
         dependent relations.
@@ -364,10 +357,22 @@ class RelationsCache:
         :param str schema: The schema of the relation to drop.
         :param str identifier: The identifier of the relation to drop.
         """
-        dropped_key = _make_key(relation)
-        fire_event(DropRelation(dropped=dropped_key))
+        dropped_key = _make_ref_key(relation)
+        dropped_key_msg = _make_ref_key_dict(relation)
+        fire_event(CacheAction(action="drop_relation", ref_key=dropped_key_msg))
         with self.lock:
-            self._drop_cascade_relation(dropped_key)
+            if dropped_key not in self.relations:
+                fire_event(CacheAction(action="drop_missing_relation", ref_key=dropped_key_msg))
+                return
+            consequences = self.relations[dropped_key].collect_consequences()
+            # convert from a list of _ReferenceKeys to a list of ReferenceKeyMsgs
+            consequence_msgs = [key._asdict() for key in consequences]
+            fire_event(
+                CacheAction(
+                    action="drop_cascade", ref_key=dropped_key_msg, ref_list=consequence_msgs
+                )
+            )
+            self._remove_refs(consequences)
 
     def _rename_relation(self, old_key, new_relation):
         """Rename a relation named old_key to new_key, updating references.
@@ -383,14 +388,20 @@ class RelationsCache:
         relation = self.relations.pop(old_key)
         new_key = new_relation.key()
 
-        # relaton has to rename its innards, so it needs the _CachedRelation.
+        # relation has to rename its innards, so it needs the _CachedRelation.
         relation.rename(new_relation)
         # update all the relations that refer to it
         for cached in self.relations.values():
             if cached.is_referenced_by(old_key):
                 fire_event(
-                    UpdateReference(old_key=old_key, new_key=new_key, cached_key=cached.key())
+                    CacheAction(
+                        action="update_reference",
+                        ref_key=_make_ref_key_dict(old_key),
+                        ref_key_2=_make_ref_key_dict(new_key),
+                        ref_key_3=_make_ref_key_dict(cached.key()),
+                    )
                 )
+
                 cached.rename_key(old_key, new_key)
 
         self.relations[new_key] = relation
@@ -413,14 +424,12 @@ class RelationsCache:
         :raises InternalError: If the new key is already present.
         """
         if new_key in self.relations:
-            dbt.exceptions.raise_cache_inconsistent(
-                "in rename, new key {} already in cache: {}".format(
-                    new_key, list(self.relations.keys())
-                )
-            )
+            # Tell user when collision caused by model names truncated during
+            # materialization.
+            raise TruncatedModelNameCausedCollisionError(new_key, self.relations)
 
         if old_key not in self.relations:
-            fire_event(TemporaryRelation(key=old_key))
+            fire_event(CacheAction(action="temporary_relation", ref_key=old_key._asdict()))
             return False
         return True
 
@@ -436,11 +445,20 @@ class RelationsCache:
         :param BaseRelation new: The new relation name information.
         :raises InternalError: If the new key is already present.
         """
-        old_key = _make_key(old)
-        new_key = _make_key(new)
-        fire_event(RenameSchema(old_key=old_key, new_key=new_key))
-
-        fire_event(DumpBeforeRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
+        old_key = _make_ref_key(old)
+        new_key = _make_ref_key(new)
+        fire_event(
+            CacheAction(
+                action="rename_relation",
+                ref_key=old_key._asdict(),
+                ref_key_2=new_key._asdict(),
+            )
+        )
+        flags = get_flags()
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="before", action="rename", dump=self.dump_graph()),
+        )
 
         with self.lock:
             if self._check_rename_constraints(old_key, new_key):
@@ -448,7 +466,10 @@ class RelationsCache:
             else:
                 self._setdefault(_CachedRelation(new))
 
-        fire_event(DumpAfterRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="after", action="rename", dump=self.dump_graph()),
+        )
 
     def get_relations(self, database: Optional[str], schema: Optional[str]) -> List[Any]:
         """Case-insensitively yield all relations matching the given schema.
@@ -467,9 +488,7 @@ class RelationsCache:
             ]
 
         if None in results:
-            dbt.exceptions.raise_cache_inconsistent(
-                "in get_relations, a None relation was found in the cache!"
-            )
+            raise NoneRelationFoundError()
         return results
 
     def clear(self):
@@ -496,6 +515,6 @@ class RelationsCache:
         """
         for relation in to_remove:
             # it may have been cascaded out already
-            drop_key = _make_key(relation)
+            drop_key = _make_ref_key(relation)
             if drop_key in self.relations:
                 self.drop(drop_key)

core/dbt/adapters/factory.py

@@ -1,23 +1,19 @@
 import threading
-from pathlib import Path
+import traceback
+from contextlib import contextmanager
 from importlib import import_module
-from typing import Type, Dict, Any, List, Optional, Set
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Set, Type
 
-from dbt.exceptions import RuntimeException, InternalException
-from dbt.include.global_project import (
-    PACKAGE_PATH as GLOBAL_PROJECT_PATH,
-    PROJECT_NAME as GLOBAL_PROJECT_NAME,
-)
-from dbt.events.functions import fire_event
-from dbt.events.types import AdapterImportError, PluginLoadError
-from dbt.contracts.connection import Credentials, AdapterRequiredConfig
-from dbt.adapters.protocol import (
-    AdapterProtocol,
-    AdapterConfig,
-    RelationProtocol,
-)
 from dbt.adapters.base.plugin import AdapterPlugin
-
+from dbt.adapters.protocol import AdapterConfig, AdapterProtocol, RelationProtocol
+from dbt.contracts.connection import AdapterRequiredConfig, Credentials
+from dbt.events.functions import fire_event
+from dbt.events.types import AdapterImportError, PluginLoadError, AdapterRegistered
+from dbt.exceptions import DbtInternalError, DbtRuntimeError
+from dbt.include.global_project import PACKAGE_PATH as GLOBAL_PROJECT_PATH
+from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
+from dbt.semver import VersionSpecifier
 
 Adapter = AdapterProtocol
 
@@ -39,7 +35,7 @@ class AdapterContainer:
             names = ", ".join(self.plugins.keys())
 
         message = f"Invalid adapter type {name}! Must be one of {names}"
-        raise RuntimeException(message)
+        raise DbtRuntimeError(message)
 
     def get_adapter_class_by_name(self, name: str) -> Type[Adapter]:
         plugin = self.get_plugin_by_name(name)
@@ -64,18 +60,18 @@ class AdapterContainer:
             # if we failed to import the target module in particular, inform
             # the user about it via a runtime error
             if exc.name == "dbt.adapters." + name:
-                fire_event(AdapterImportError(exc=exc))
-                raise RuntimeException(f"Could not find adapter type {name}!")
+                fire_event(AdapterImportError(exc=str(exc)))
+                raise DbtRuntimeError(f"Could not find adapter type {name}!")
             # otherwise, the error had to have come from some underlying
             # library. Log the stack trace.
 
-            fire_event(PluginLoadError())
+            fire_event(PluginLoadError(exc_info=traceback.format_exc()))
             raise
         plugin: AdapterPlugin = mod.Plugin
         plugin_type = plugin.adapter.type()
 
         if plugin_type != name:
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f"Expected to find adapter with type named {name}, got "
                 f"adapter with type {plugin_type}"
             )
@@ -94,7 +90,13 @@ class AdapterContainer:
     def register_adapter(self, config: AdapterRequiredConfig) -> None:
         adapter_name = config.credentials.type
         adapter_type = self.get_adapter_class_by_name(adapter_name)
-
+        adapter_version = import_module(f".{adapter_name}.__version__", "dbt.adapters").version
+        adapter_version_specifier = VersionSpecifier.from_version_string(
+            adapter_version
+        ).to_version_string()
+        fire_event(
+            AdapterRegistered(adapter_name=adapter_name, adapter_version=adapter_version_specifier)
+        )
         with self.lock:
             if adapter_name in self.adapters:
                 # this shouldn't really happen...
@@ -137,11 +139,9 @@ class AdapterContainer:
             try:
                 plugin = self.plugins[plugin_name]
             except KeyError:
-                raise InternalException(f"No plugin found for {plugin_name}") from None
+                raise DbtInternalError(f"No plugin found for {plugin_name}") from None
             plugins.append(plugin)
             seen.add(plugin_name)
-            if plugin.dependencies is None:
-                continue
             for dep in plugin.dependencies:
                 if dep not in seen:
                     plugin_names.append(dep)
@@ -158,7 +158,7 @@ class AdapterContainer:
             try:
                 path = self.packages[package_name]
             except KeyError:
-                raise InternalException(f"No internal package listing found for {package_name}")
+                raise DbtInternalError(f"No internal package listing found for {package_name}")
             paths.append(path)
         return paths
 
@@ -177,6 +177,10 @@ 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."""
     FACTORY.reset_adapters()
@@ -215,3 +219,12 @@ def get_adapter_package_names(name: Optional[str]) -> List[str]:
 
 def get_adapter_type_names(name: Optional[str]) -> List[str]:
     return FACTORY.get_adapter_type_names(name)
+
+
+@contextmanager
+def adapter_management():
+    reset_adapters()
+    try:
+        yield
+    finally:
+        cleanup_connections()

core/dbt/adapters/protocol.py

@@ -7,9 +7,7 @@ from typing import (
     List,
     Generic,
     TypeVar,
-    ClassVar,
     Tuple,
-    Union,
     Dict,
     Any,
 )
@@ -18,8 +16,7 @@ from typing_extensions import Protocol
 import agate
 
 from dbt.contracts.connection import Connection, AdapterRequiredConfig, AdapterResponse
-from dbt.contracts.graph.compiled import CompiledNode, ManifestNode, NonSourceCompiledNode
-from dbt.contracts.graph.parsed import ParsedNode, ParsedSourceDefinition
+from dbt.contracts.graph.nodes import ResultNode, ManifestNode
 from dbt.contracts.graph.model_config import BaseConfig
 from dbt.contracts.graph.manifest import Manifest
 from dbt.contracts.relation import Policy, HasQuoting
@@ -49,11 +46,7 @@ class RelationProtocol(Protocol):
         ...
 
     @classmethod
-    def create_from(
-        cls: Type[Self],
-        config: HasQuoting,
-        node: Union[CompiledNode, ParsedNode, ParsedSourceDefinition],
-    ) -> Self:
+    def create_from(cls: Type[Self], config: HasQuoting, node: ResultNode) -> Self:
         ...
 
 
@@ -66,7 +59,7 @@ class CompilerProtocol(Protocol):
         node: ManifestNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestNode:
         ...
 
 
@@ -88,10 +81,13 @@ class AdapterProtocol(  # type: ignore[misc]
         Compiler_T,
     ],
 ):
-    AdapterSpecificConfigs: ClassVar[Type[AdapterConfig_T]]
-    Column: ClassVar[Type[Column_T]]
-    Relation: ClassVar[Type[Relation_T]]
-    ConnectionManager: ClassVar[Type[ConnectionManager_T]]
+    # N.B. Technically these are ClassVars, but mypy doesn't support putting type vars in a
+    # ClassVar due to the restrictiveness of PEP-526
+    # See: https://github.com/python/mypy/issues/5144
+    AdapterSpecificConfigs: Type[AdapterConfig_T]
+    Column: Type[Column_T]
+    Relation: Type[Relation_T]
+    ConnectionManager: Type[ConnectionManager_T]
     connections: ConnectionManager_T
 
     def __init__(self, config: AdapterRequiredConfig):
@@ -155,7 +151,7 @@ class AdapterProtocol(  # type: ignore[misc]
 
     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

@@ -1,7 +1,7 @@
 # this module exists to resolve circular imports with the events module
 
 from collections import namedtuple
-from typing import Optional
+from typing import Any, Optional
 
 
 _ReferenceKey = namedtuple("_ReferenceKey", "database schema identifier")
@@ -14,7 +14,12 @@ def lowercase(value: Optional[str]) -> Optional[str]:
         return value.lower()
 
 
-def _make_key(relation) -> _ReferenceKey:
+# For backwards compatibility. New code should use _make_ref_key
+def _make_key(relation: Any) -> _ReferenceKey:
+    return _make_ref_key(relation)
+
+
+def _make_ref_key(relation: Any) -> _ReferenceKey:
     """Make _ReferenceKeys with lowercase values for the cache so we don't have
     to keep track of quoting
     """
@@ -22,3 +27,11 @@ def _make_key(relation) -> _ReferenceKey:
     return _ReferenceKey(
         lowercase(relation.database), lowercase(relation.schema), lowercase(relation.identifier)
     )
+
+
+def _make_ref_key_dict(relation: Any):
+    return {
+        "database": relation.database,
+        "schema": relation.schema,
+        "identifier": relation.identifier,
+    }

core/dbt/adapters/sql/connections.py

@@ -10,6 +10,8 @@ from dbt.adapters.base import BaseConnectionManager
 from dbt.contracts.connection import Connection, ConnectionState, AdapterResponse
 from dbt.events.functions import fire_event
 from dbt.events.types import ConnectionUsed, SQLQuery, SQLCommit, SQLQueryStatus
+from dbt.events.contextvars import get_node_info
+from dbt.utils import cast_to_str
 
 
 class SQLConnectionManager(BaseConnectionManager):
@@ -25,9 +27,7 @@ class SQLConnectionManager(BaseConnectionManager):
     @abc.abstractmethod
     def cancel(self, connection: Connection):
         """Cancel the given connection."""
-        raise dbt.exceptions.NotImplementedException(
-            "`cancel` is not implemented for this adapter!"
-        )
+        raise dbt.exceptions.NotImplementedError("`cancel` is not implemented for this adapter!")
 
     def cancel_open(self) -> List[str]:
         names = []
@@ -52,10 +52,17 @@ class SQLConnectionManager(BaseConnectionManager):
         bindings: Optional[Any] = None,
         abridge_sql_log: bool = False,
     ) -> Tuple[Connection, Any]:
+
         connection = self.get_thread_connection()
         if auto_begin and connection.transaction_open is False:
             self.begin()
-        fire_event(ConnectionUsed(conn_type=self.TYPE, conn_name=connection.name))
+        fire_event(
+            ConnectionUsed(
+                conn_type=self.TYPE,
+                conn_name=cast_to_str(connection.name),
+                node_info=get_node_info(),
+            )
+        )
 
         with self.exception_handler(sql):
             if abridge_sql_log:
@@ -63,7 +70,11 @@ class SQLConnectionManager(BaseConnectionManager):
             else:
                 log_sql = sql
 
-            fire_event(SQLQuery(conn_name=connection.name, sql=log_sql))
+            fire_event(
+                SQLQuery(
+                    conn_name=cast_to_str(connection.name), sql=log_sql, node_info=get_node_info()
+                )
+            )
             pre = time.time()
 
             cursor = connection.handle.cursor()
@@ -71,16 +82,19 @@ class SQLConnectionManager(BaseConnectionManager):
 
             fire_event(
                 SQLQueryStatus(
-                    status=str(self.get_response(cursor)), elapsed=round((time.time() - pre), 2)
+                    status=str(self.get_response(cursor)),
+                    elapsed=round((time.time() - pre)),
+                    node_info=get_node_info(),
                 )
             )
 
             return connection, cursor
 
-    @abc.abstractclassmethod
-    def get_response(cls, cursor: Any) -> Union[AdapterResponse, str]:
+    @classmethod
+    @abc.abstractmethod
+    def get_response(cls, cursor: Any) -> AdapterResponse:
         """Get the status of the cursor."""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`get_response` is not implemented for this adapter!"
         )
 
@@ -115,9 +129,17 @@ class SQLConnectionManager(BaseConnectionManager):
 
         return dbt.clients.agate_helper.table_from_data_flat(data, column_names)
 
+    @classmethod
+    def data_type_code_to_name(cls, type_code: Union[int, str]) -> str:
+        """Get the string representation of the data type from the type_code."""
+        # https://peps.python.org/pep-0249/#type-objects
+        raise dbt.exceptions.NotImplementedError(
+            "`data_type_code_to_name` is not implemented for this adapter!"
+        )
+
     def execute(
         self, sql: str, auto_begin: bool = False, fetch: bool = False
-    ) -> 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)
@@ -133,10 +155,14 @@ class SQLConnectionManager(BaseConnectionManager):
     def add_commit_query(self):
         return self.add_query("COMMIT", auto_begin=False)
 
+    def add_select_query(self, sql: str) -> Tuple[Connection, Any]:
+        sql = self._add_query_comment(sql)
+        return self.add_query(sql, auto_begin=False)
+
     def begin(self):
         connection = self.get_thread_connection()
         if connection.transaction_open is True:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 'Tried to begin a new transaction on connection "{}", but '
                 "it already had one open!".format(connection.name)
             )
@@ -149,12 +175,12 @@ class SQLConnectionManager(BaseConnectionManager):
     def commit(self):
         connection = self.get_thread_connection()
         if connection.transaction_open is False:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 'Tried to commit transaction on connection "{}", but '
                 "it does not have one open!".format(connection.name)
             )
 
-        fire_event(SQLCommit(conn_name=connection.name))
+        fire_event(SQLCommit(conn_name=connection.name, node_info=get_node_info()))
         self.add_commit_query()
 
         connection.transaction_open = False

core/dbt/adapters/sql/impl.py

@@ -1,11 +1,10 @@
 import agate
 from typing import Any, Optional, Tuple, Type, List
 
-import dbt.clients.agate_helper
 from dbt.contracts.connection import Connection
-import dbt.exceptions
+from dbt.exceptions import RelationTypeNullError
 from dbt.adapters.base import BaseAdapter, available
-from dbt.adapters.cache import _make_key
+from dbt.adapters.cache import _make_ref_key_dict
 from dbt.adapters.sql import SQLConnectionManager
 from dbt.events.functions import fire_event
 from dbt.events.types import ColTypeChange, SchemaCreation, SchemaDrop
@@ -27,7 +26,7 @@ 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
@@ -110,7 +109,7 @@ class SQLAdapter(BaseAdapter):
                     ColTypeChange(
                         orig_type=target_column.data_type,
                         new_type=new_type,
-                        table=_make_key(current),
+                        table=_make_ref_key_dict(current),
                     )
                 )
 
@@ -132,9 +131,7 @@ class SQLAdapter(BaseAdapter):
 
     def drop_relation(self, relation):
         if relation.type is None:
-            dbt.exceptions.raise_compiler_error(
-                "Tried to drop relation {}, but its type is null.".format(relation)
-            )
+            raise RelationTypeNullError(relation)
 
         self.cache_dropped(relation)
         self.execute_macro(DROP_RELATION_MACRO_NAME, kwargs={"relation": relation})
@@ -155,7 +152,7 @@ class SQLAdapter(BaseAdapter):
 
     def create_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        fire_event(SchemaCreation(relation=_make_key(relation)))
+        fire_event(SchemaCreation(relation=_make_ref_key_dict(relation)))
         kwargs = {
             "relation": relation,
         }
@@ -166,11 +163,12 @@ class SQLAdapter(BaseAdapter):
 
     def drop_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        fire_event(SchemaDrop(relation=_make_key(relation)))
+        fire_event(SchemaDrop(relation=_make_ref_key_dict(relation)))
         kwargs = {
             "relation": relation,
         }
         self.execute_macro(DROP_SCHEMA_MACRO_NAME, kwargs=kwargs)
+        self.commit_if_has_connection()
         # we can update the cache here
         self.cache.drop_schema(relation.database, relation.schema)
 
@@ -199,6 +197,7 @@ class SQLAdapter(BaseAdapter):
             )
         return relations
 
+    @classmethod
     def quote(self, identifier):
         return '"{}"'.format(identifier)
 
@@ -218,3 +217,25 @@ class SQLAdapter(BaseAdapter):
         kwargs = {"information_schema": information_schema, "schema": schema}
         results = self.execute_macro(CHECK_SCHEMA_EXISTS_MACRO_NAME, kwargs=kwargs)
         return results[0][0] > 0
+
+    # This is for use in the test suite
+    def run_sql_for_tests(self, sql, fetch, conn):
+        cursor = conn.handle.cursor()
+        try:
+            cursor.execute(sql)
+            if hasattr(conn.handle, "commit"):
+                conn.handle.commit()
+            if fetch == "one":
+                return cursor.fetchone()
+            elif fetch == "all":
+                return cursor.fetchall()
+            else:
+                return
+        except BaseException as e:
+            if conn.handle and not getattr(conn.handle, "closed", True):
+                conn.handle.rollback()
+            print(sql)
+            print(e)
+            raise
+        finally:
+            conn.transaction_open = False

core/dbt/cli/README.md

@@ -0,0 +1,49 @@
+# Exception Handling
+
+## `requires.py`
+
+### `postflight`
+In the postflight decorator, the click command is invoked (i.e. `func(*args, **kwargs)`) and wrapped in a `try/except` block to handle any exceptions thrown.
+Any exceptions thrown from `postflight` are wrapped by custom exceptions from the `dbt.cli.exceptions` module (i.e. `ResultExit`, `ExceptionExit`) to instruct click to complete execution with a particular exit code.
+
+Some `dbt-core` handled exceptions have an attribute named `results` which contains results from running nodes (e.g. `FailFastError`). These are wrapped in the `ResultExit` exception to represent runs that have failed in a way that `dbt-core` expects.
+If the invocation of the command does not throw any exceptions but does not succeed, `postflight` will still raise the `ResultExit` exception to make use of the exit code.
+These exceptions produce an exit code of `1`.
+
+Exceptions wrapped with `ExceptionExit` may be thrown by `dbt-core` intentionally (i.e. an exception that inherits from `dbt.exceptions.Exception`) or unintentionally (i.e. exceptions thrown by the python runtime). In either case these are considered errors that `dbt-core` did not expect and are treated as genuine exceptions.
+These exceptions produce an exit code of `2`.
+
+If no exceptions are thrown from invoking the command and the command succeeds, `postflight` will not raise any exceptions.
+When no exceptions are raised an exit code of `0` is produced.
+
+## `main.py`
+
+### `dbtRunner`
+`dbtRunner` provides a programmatic interface for our click CLI and wraps the invocation of the click commands to handle any exceptions thrown.
+
+`dbtRunner.invoke` should ideally only ever return an instantiated `dbtRunnerResult` which contains the following fields:
+- `success`: A boolean representing whether the command invocation was successful
+- `result`: The optional result of the command invoked. This attribute can have many types, please see the definition of `dbtRunnerResult` for more information
+- `exception`: If an exception was thrown during command invocation it will be saved here, otherwise it will be `None`. Please note that the exceptions held in this attribute are not the exceptions thrown by `preflight` but instead the exceptions that `ResultExit` and `ExceptionExit` wrap
+
+Programmatic exception handling might look like the following:
+```python
+res = dbtRunner().invoke(["run"])
+if not res.success:
+    ...
+if type(res.exception) == SomeExceptionType:
+    ...
+```
+
+## `dbt/tests/util.py`
+
+### `run_dbt`
+In many of our functional and integration tests, we want to be sure that an invocation of `dbt` raises a certain exception.
+A common pattern for these assertions:
+```python
+class TestSomething:
+    def test_something(self, project):
+        with pytest.raises(SomeException):
+            run_dbt(["run"])
+```
+To allow these tests to assert that exceptions have been thrown, the `run_dbt` function will raise any exceptions it recieves from the invocation of a `dbt` command.

core/dbt/cli/__init__.py

@@ -0,0 +1 @@
+from .main import cli as dbt_cli  # noqa

core/dbt/cli/context.py

@@ -0,0 +1,16 @@
+import click
+from typing import Optional
+
+from dbt.cli.main import cli as dbt
+
+
+def make_context(args, command=dbt) -> Optional[click.Context]:
+    try:
+        ctx = command.make_context(command.name, args)
+    except click.exceptions.Exit:
+        return None
+
+    ctx.invoked_subcommand = ctx.protected_args[0] if ctx.protected_args else None
+    ctx.obj = {}
+
+    return ctx

core/dbt/cli/exceptions.py

@@ -0,0 +1,43 @@
+from typing import Optional, IO
+
+from click.exceptions import ClickException
+from dbt.utils import ExitCodes
+
+
+class DbtUsageException(Exception):
+    pass
+
+
+class DbtInternalException(Exception):
+    pass
+
+
+class CliException(ClickException):
+    """The base exception class for our implementation of the click CLI.
+    The exit_code attribute is used by click to determine which exit code to produce
+    after an invocation."""
+
+    def __init__(self, exit_code: ExitCodes) -> None:
+        self.exit_code = exit_code.value
+
+    # the typing of _file is to satisfy the signature of ClickException.show
+    # overriding this method prevents click from printing any exceptions to stdout
+    def show(self, _file: Optional[IO] = None) -> None:
+        pass
+
+
+class ResultExit(CliException):
+    """This class wraps any exception that contains results while invoking dbt, or the
+    results of an invocation that did not succeed but did not throw any exceptions."""
+
+    def __init__(self, result) -> None:
+        super().__init__(ExitCodes.ModelError)
+        self.result = result
+
+
+class ExceptionExit(CliException):
+    """This class wraps any exception that does not contain results thrown while invoking dbt."""
+
+    def __init__(self, exception: Exception) -> None:
+        super().__init__(ExitCodes.UnhandledError)
+        self.exception = exception

core/dbt/cli/flags.py

@@ -0,0 +1,279 @@
+import os
+import sys
+from dataclasses import dataclass
+from importlib import import_module
+from multiprocessing import get_context
+from pprint import pformat as pf
+from typing import Callable, Dict, List, Set, Union
+
+from click import Context, get_current_context
+from click.core import Command, Group, ParameterSource
+from dbt.cli.exceptions import DbtUsageException
+from dbt.cli.resolvers import default_log_path, default_project_dir
+from dbt.config.profile import read_user_config
+from dbt.contracts.project import UserConfig
+from dbt.deprecations import renamed_env_var
+from dbt.helper_types import WarnErrorOptions
+
+if os.name != "nt":
+    # https://bugs.python.org/issue41567
+    import multiprocessing.popen_spawn_posix  # type: ignore  # noqa: F401
+
+FLAGS_DEFAULTS = {
+    "INDIRECT_SELECTION": "eager",
+    "TARGET_PATH": None,
+    # Cli args without user_config or env var option.
+    "FULL_REFRESH": False,
+    "STRICT_MODE": False,
+    "STORE_FAILURES": False,
+    "INTROSPECT": True,
+}
+
+DEPRECATED_PARAMS = {
+    "deprecated_defer": "defer",
+    "deprecated_favor_state": "favor_state",
+    "deprecated_print": "print",
+    "deprecated_state": "state",
+}
+
+
+def convert_config(config_name, config_value):
+    """Convert the values from config and original set_from_args to the correct type."""
+    ret = config_value
+    if config_name.lower() == "warn_error_options" and type(config_value) == dict:
+        ret = WarnErrorOptions(
+            include=config_value.get("include", []), exclude=config_value.get("exclude", [])
+        )
+    return ret
+
+
+def args_to_context(args: List[str]) -> Context:
+    """Convert a list of args to a click context with proper hierarchy for dbt commands"""
+    from dbt.cli.main import cli
+
+    cli_ctx = cli.make_context(cli.name, args)
+    # Split args if they're a comma separated string.
+    if len(args) == 1 and "," in args[0]:
+        args = args[0].split(",")
+    sub_command_name, sub_command, args = cli.resolve_command(cli_ctx, args)
+
+    # Handle source and docs group.
+    if type(sub_command) == Group:
+        sub_command_name, sub_command, args = sub_command.resolve_command(cli_ctx, args)
+
+    assert type(sub_command) == Command
+    sub_command_ctx = sub_command.make_context(sub_command_name, args)
+    sub_command_ctx.parent = cli_ctx
+    return sub_command_ctx
+
+
+@dataclass(frozen=True)
+class Flags:
+    """Primary configuration artifact for running dbt"""
+
+    def __init__(self, ctx: Context = None, user_config: UserConfig = None) -> None:
+
+        # Set the default flags.
+        for key, value in FLAGS_DEFAULTS.items():
+            object.__setattr__(self, key, value)
+
+        if ctx is None:
+            ctx = get_current_context()
+
+        def _get_params_by_source(ctx: Context, source_type: ParameterSource):
+            """Generates all params of a given source type."""
+            yield from [
+                name for name, source in ctx._parameter_source.items() if source is source_type
+            ]
+            if ctx.parent:
+                yield from _get_params_by_source(ctx.parent, source_type)
+
+        # Ensure that any params sourced from the commandline are not present more than once.
+        # Click handles this exclusivity, but only at a per-subcommand level.
+        seen_params = []
+        for param in _get_params_by_source(ctx, ParameterSource.COMMANDLINE):
+            if param in seen_params:
+                raise DbtUsageException(
+                    f"{param.lower()} was provided both before and after the subcommand, it can only be set either before or after.",
+                )
+            seen_params.append(param)
+
+        def _assign_params(
+            ctx: Context,
+            params_assigned_from_default: set,
+            deprecated_env_vars: Dict[str, Callable],
+        ):
+            """Recursively adds all click params to flag object"""
+            for param_name, param_value in ctx.params.items():
+                # N.B. You have to use the base MRO method (object.__setattr__) to set attributes
+                # when using frozen dataclasses.
+                # https://docs.python.org/3/library/dataclasses.html#frozen-instances
+
+                # Handle deprecated env vars while still respecting old values
+                # e.g. DBT_NO_PRINT -> DBT_PRINT if DBT_NO_PRINT is set, it is
+                # respected over DBT_PRINT or --print.
+                new_name: Union[str, None] = None
+                if param_name in DEPRECATED_PARAMS:
+
+                    # Deprecated env vars can only be set via env var.
+                    # We use the deprecated option in click to serialize the value
+                    # from the env var string.
+                    param_source = ctx.get_parameter_source(param_name)
+                    if param_source == ParameterSource.DEFAULT:
+                        continue
+                    elif param_source != ParameterSource.ENVIRONMENT:
+                        raise DbtUsageException(
+                            "Deprecated parameters can only be set via environment variables",
+                        )
+
+                    # Rename for clarity.
+                    dep_name = param_name
+                    new_name = DEPRECATED_PARAMS.get(dep_name)
+                    try:
+                        assert isinstance(new_name, str)
+                    except AssertionError:
+                        raise Exception(
+                            f"No deprecated param name match in DEPRECATED_PARAMS from {dep_name} to {new_name}"
+                        )
+
+                    # Find param objects for their envvar name.
+                    try:
+                        dep_param = [x for x in ctx.command.params if x.name == dep_name][0]
+                        new_param = [x for x in ctx.command.params if x.name == new_name][0]
+                    except IndexError:
+                        raise Exception(
+                            f"No deprecated param name match in context from {dep_name} to {new_name}"
+                        )
+
+                    # Remove param from defaulted set since the deprecated
+                    # value is not set from default, but from an env var.
+                    if new_name in params_assigned_from_default:
+                        params_assigned_from_default.remove(new_name)
+
+                    # Add the deprecation warning function to the set.
+                    assert isinstance(dep_param.envvar, str)
+                    assert isinstance(new_param.envvar, str)
+                    deprecated_env_vars[new_name] = renamed_env_var(
+                        old_name=dep_param.envvar,
+                        new_name=new_param.envvar,
+                    )
+
+                # Set the flag value.
+                is_duplicate = hasattr(self, param_name.upper())
+                is_default = ctx.get_parameter_source(param_name) == ParameterSource.DEFAULT
+                flag_name = (new_name or param_name).upper()
+
+                if (is_duplicate and not is_default) or not is_duplicate:
+                    object.__setattr__(self, flag_name, param_value)
+
+                # Track default assigned params.
+                if is_default:
+                    params_assigned_from_default.add(param_name)
+
+            if ctx.parent:
+                _assign_params(ctx.parent, params_assigned_from_default, deprecated_env_vars)
+
+        params_assigned_from_default = set()  # type: Set[str]
+        deprecated_env_vars: Dict[str, Callable] = {}
+        _assign_params(ctx, params_assigned_from_default, deprecated_env_vars)
+
+        # Set deprecated_env_var_warnings to be fired later after events have been init.
+        object.__setattr__(
+            self, "deprecated_env_var_warnings", [x for x in deprecated_env_vars.values()]
+        )
+
+        # Get the invoked command flags.
+        invoked_subcommand_name = (
+            ctx.invoked_subcommand if hasattr(ctx, "invoked_subcommand") else None
+        )
+        if invoked_subcommand_name is not None:
+            invoked_subcommand = getattr(import_module("dbt.cli.main"), invoked_subcommand_name)
+            invoked_subcommand.allow_extra_args = True
+            invoked_subcommand.ignore_unknown_options = True
+            invoked_subcommand_ctx = invoked_subcommand.make_context(None, sys.argv)
+            _assign_params(
+                invoked_subcommand_ctx, params_assigned_from_default, deprecated_env_vars
+            )
+
+        if not user_config:
+            profiles_dir = getattr(self, "PROFILES_DIR", None)
+            user_config = read_user_config(profiles_dir) if profiles_dir else None
+
+        # Overwrite default assignments with user config if available.
+        if user_config:
+            param_assigned_from_default_copy = params_assigned_from_default.copy()
+            for param_assigned_from_default in params_assigned_from_default:
+                user_config_param_value = getattr(user_config, param_assigned_from_default, None)
+                if user_config_param_value is not None:
+                    object.__setattr__(
+                        self,
+                        param_assigned_from_default.upper(),
+                        convert_config(param_assigned_from_default, user_config_param_value),
+                    )
+                    param_assigned_from_default_copy.remove(param_assigned_from_default)
+            params_assigned_from_default = param_assigned_from_default_copy
+
+        # Set hard coded flags.
+        object.__setattr__(self, "WHICH", invoked_subcommand_name or ctx.info_name)
+        object.__setattr__(self, "MP_CONTEXT", get_context("spawn"))
+
+        # Apply the lead/follow relationship between some parameters.
+        self._override_if_set("USE_COLORS", "USE_COLORS_FILE", params_assigned_from_default)
+        self._override_if_set("LOG_LEVEL", "LOG_LEVEL_FILE", params_assigned_from_default)
+        self._override_if_set("LOG_FORMAT", "LOG_FORMAT_FILE", params_assigned_from_default)
+
+        # Set default LOG_PATH from PROJECT_DIR, if available.
+        # Starting in v1.5, if `log-path` is set in `dbt_project.yml`, it will raise a deprecation warning,
+        # with the possibility of removing it in a future release.
+        if getattr(self, "LOG_PATH", None) is None:
+            project_dir = getattr(self, "PROJECT_DIR", default_project_dir())
+            version_check = getattr(self, "VERSION_CHECK", True)
+            object.__setattr__(self, "LOG_PATH", default_log_path(project_dir, version_check))
+
+        # Support console DO NOT TRACK initiative.
+        if os.getenv("DO_NOT_TRACK", "").lower() in ("1", "t", "true", "y", "yes"):
+            object.__setattr__(self, "SEND_ANONYMOUS_USAGE_STATS", False)
+
+        # Check mutual exclusivity once all flags are set.
+        self._assert_mutually_exclusive(
+            params_assigned_from_default, ["WARN_ERROR", "WARN_ERROR_OPTIONS"]
+        )
+
+        # Support lower cased access for legacy code.
+        params = set(
+            x for x in dir(self) if not callable(getattr(self, x)) and not x.startswith("__")
+        )
+        for param in params:
+            object.__setattr__(self, param.lower(), getattr(self, param))
+
+    def __str__(self) -> str:
+        return str(pf(self.__dict__))
+
+    def _override_if_set(self, lead: str, follow: str, defaulted: Set[str]) -> None:
+        """If the value of the lead parameter was set explicitly, apply the value to follow, unless follow was also set explicitly."""
+        if lead.lower() not in defaulted and follow.lower() in defaulted:
+            object.__setattr__(self, follow.upper(), getattr(self, lead.upper(), None))
+
+    def _assert_mutually_exclusive(
+        self, params_assigned_from_default: Set[str], group: List[str]
+    ) -> None:
+        """
+        Ensure no elements from group are simultaneously provided by a user, as inferred from params_assigned_from_default.
+        Raises click.UsageError if any two elements from group are simultaneously provided by a user.
+        """
+        set_flag = None
+        for flag in group:
+            flag_set_by_user = flag.lower() not in params_assigned_from_default
+            if flag_set_by_user and set_flag:
+                raise DbtUsageException(
+                    f"{flag.lower()}: not allowed with argument {set_flag.lower()}"
+                )
+            elif flag_set_by_user:
+                set_flag = flag
+
+    def fire_deprecations(self):
+        """Fires events for deprecated env_var usage."""
+        [dep_fn() for dep_fn in self.deprecated_env_var_warnings]
+        # It is necessary to remove this attr from the class so it does
+        # not get pickled when written to disk as json.
+        object.__delattr__(self, "deprecated_env_var_warnings")

core/dbt/cli/main.py

@@ -0,0 +1,788 @@
+import functools
+from copy import copy
+from dataclasses import dataclass
+from typing import Callable, List, Optional, Union
+
+import click
+from click.exceptions import (
+    Exit as ClickExit,
+    BadOptionUsage,
+    NoSuchOption,
+    UsageError,
+)
+
+from dbt.cli import requires, params as p
+from dbt.cli.exceptions import (
+    DbtInternalException,
+    DbtUsageException,
+)
+from dbt.contracts.graph.manifest import Manifest
+from dbt.contracts.results import (
+    CatalogArtifact,
+    RunExecutionResult,
+    RunOperationResultsArtifact,
+)
+from dbt.events.base_types import EventMsg
+from dbt.task.build import BuildTask
+from dbt.task.clean import CleanTask
+from dbt.task.compile import CompileTask
+from dbt.task.debug import DebugTask
+from dbt.task.deps import DepsTask
+from dbt.task.freshness import FreshnessTask
+from dbt.task.generate import GenerateTask
+from dbt.task.init import InitTask
+from dbt.task.list import ListTask
+from dbt.task.run import RunTask
+from dbt.task.run_operation import RunOperationTask
+from dbt.task.seed import SeedTask
+from dbt.task.serve import ServeTask
+from dbt.task.show import ShowTask
+from dbt.task.snapshot import SnapshotTask
+from dbt.task.test import TestTask
+
+
+@dataclass
+class dbtRunnerResult:
+    """Contains the result of an invocation of the dbtRunner"""
+
+    success: bool
+
+    exception: Optional[BaseException] = None
+    result: Union[
+        bool,  # debug
+        CatalogArtifact,  # docs generate
+        List[str],  # list/ls
+        Manifest,  # parse
+        None,  # clean, deps, init, source
+        RunExecutionResult,  # build, compile, run, seed, snapshot, test
+        RunOperationResultsArtifact,  # run-operation
+    ] = None
+
+
+# Programmatic invocation
+class dbtRunner:
+    def __init__(
+        self,
+        manifest: Manifest = None,
+        callbacks: List[Callable[[EventMsg], None]] = None,
+    ):
+        self.manifest = manifest
+
+        if callbacks is None:
+            callbacks = []
+        self.callbacks = callbacks
+
+    def invoke(self, args: List[str], **kwargs) -> dbtRunnerResult:
+        try:
+            dbt_ctx = cli.make_context(cli.name, args)
+            dbt_ctx.obj = {
+                "manifest": self.manifest,
+                "callbacks": self.callbacks,
+            }
+
+            for key, value in kwargs.items():
+                dbt_ctx.params[key] = value
+                # Hack to set parameter source to custom string
+                dbt_ctx.set_parameter_source(key, "kwargs")  # type: ignore
+
+            result, success = cli.invoke(dbt_ctx)
+            return dbtRunnerResult(
+                result=result,
+                success=success,
+            )
+        except requires.ResultExit as e:
+            return dbtRunnerResult(
+                result=e.result,
+                success=False,
+            )
+        except requires.ExceptionExit as e:
+            return dbtRunnerResult(
+                exception=e.exception,
+                success=False,
+            )
+        except (BadOptionUsage, NoSuchOption, UsageError) as e:
+            return dbtRunnerResult(
+                exception=DbtUsageException(e.message),
+                success=False,
+            )
+        except ClickExit as e:
+            if e.exit_code == 0:
+                return dbtRunnerResult(success=True)
+            return dbtRunnerResult(
+                exception=DbtInternalException(f"unhandled exit code {e.exit_code}"),
+                success=False,
+            )
+        except BaseException as e:
+            return dbtRunnerResult(
+                exception=e,
+                success=False,
+            )
+
+
+# approach from https://github.com/pallets/click/issues/108#issuecomment-280489786
+def global_flags(func):
+    @p.cache_selected_only
+    @p.debug
+    @p.deprecated_print
+    @p.enable_legacy_logger
+    @p.fail_fast
+    @p.log_cache_events
+    @p.log_file_max_bytes
+    @p.log_format_file
+    @p.log_level
+    @p.log_level_file
+    @p.log_path
+    @p.macro_debugging
+    @p.partial_parse
+    @p.populate_cache
+    @p.print
+    @p.printer_width
+    @p.quiet
+    @p.record_timing_info
+    @p.send_anonymous_usage_stats
+    @p.single_threaded
+    @p.static_parser
+    @p.use_colors
+    @p.use_colors_file
+    @p.use_experimental_parser
+    @p.version
+    @p.version_check
+    @p.write_json
+    @functools.wraps(func)
+    def wrapper(*args, **kwargs):
+        return func(*args, **kwargs)
+
+    return wrapper
+
+
+# dbt
+@click.group(
+    context_settings={"help_option_names": ["-h", "--help"]},
+    invoke_without_command=True,
+    no_args_is_help=True,
+    epilog="Specify one of these sub-commands and you can find more help from there.",
+)
+@click.pass_context
+@global_flags
+@p.warn_error
+@p.warn_error_options
+@p.log_format
+def cli(ctx, **kwargs):
+    """An ELT tool for managing your SQL transformations and data models.
+    For more documentation on these commands, visit: docs.getdbt.com
+    """
+
+
+# dbt build
+@cli.command("build")
+@click.pass_context
+@global_flags
+@p.defer
+@p.deprecated_defer
+@p.exclude
+@p.favor_state
+@p.deprecated_favor_state
+@p.full_refresh
+@p.indirect_selection
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.resource_type
+@p.select
+@p.selector
+@p.show
+@p.state
+@p.deprecated_state
+@p.store_failures
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def build(ctx, **kwargs):
+    """Run all seeds, models, snapshots, and tests in DAG order"""
+    task = BuildTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt clean
+@cli.command("clean")
+@click.pass_context
+@global_flags
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.target_path
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.unset_profile
+@requires.project
+def clean(ctx, **kwargs):
+    """Delete all folders in the clean-targets list (usually the dbt_packages and target directories.)"""
+    task = CleanTask(ctx.obj["flags"], ctx.obj["project"])
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt docs
+@cli.group()
+@click.pass_context
+@global_flags
+def docs(ctx, **kwargs):
+    """Generate or serve the documentation website for your project"""
+
+
+# dbt docs generate
+@docs.command("generate")
+@click.pass_context
+@global_flags
+@p.compile_docs
+@p.defer
+@p.deprecated_defer
+@p.exclude
+@p.favor_state
+@p.deprecated_favor_state
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.state
+@p.deprecated_state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest(write=False)
+def docs_generate(ctx, **kwargs):
+    """Generate the documentation website for your project"""
+    task = GenerateTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt docs serve
+@docs.command("serve")
+@click.pass_context
+@global_flags
+@p.browser
+@p.port
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.target_path
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+def docs_serve(ctx, **kwargs):
+    """Serve the documentation website for your project"""
+    task = ServeTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt compile
+@cli.command("compile")
+@click.pass_context
+@global_flags
+@p.defer
+@p.deprecated_defer
+@p.exclude
+@p.favor_state
+@p.deprecated_favor_state
+@p.full_refresh
+@p.show_output_format
+@p.indirect_selection
+@p.introspect
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.inline
+@p.state
+@p.deprecated_state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def compile(ctx, **kwargs):
+    """Generates executable SQL from source, model, test, and analysis files. Compiled SQL files are written to the
+    target/ directory."""
+    task = CompileTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt show
+@cli.command("show")
+@click.pass_context
+@global_flags
+@p.defer
+@p.deprecated_defer
+@p.exclude
+@p.favor_state
+@p.deprecated_favor_state
+@p.full_refresh
+@p.show_output_format
+@p.show_limit
+@p.indirect_selection
+@p.introspect
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.inline
+@p.state
+@p.deprecated_state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def show(ctx, **kwargs):
+    """Generates executable SQL for a named resource or inline query, runs that SQL, and returns a preview of the
+    results. Does not materialize anything to the warehouse."""
+    task = ShowTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt debug
+@cli.command("debug")
+@click.pass_context
+@global_flags
+@p.config_dir
+@p.profile
+@p.profiles_dir_exists_false
+@p.project_dir
+@p.target
+@p.vars
+@requires.postflight
+@requires.preflight
+def debug(ctx, **kwargs):
+    """Test the database connection and show information for debugging purposes. Not to be confused with the --debug option which increases verbosity."""
+
+    task = DebugTask(
+        ctx.obj["flags"],
+        None,
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt deps
+@cli.command("deps")
+@click.pass_context
+@global_flags
+@p.profile
+@p.profiles_dir_exists_false
+@p.project_dir
+@p.target
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.unset_profile
+@requires.project
+def deps(ctx, **kwargs):
+    """Pull the most recent version of the dependencies listed in packages.yml"""
+    task = DepsTask(ctx.obj["flags"], ctx.obj["project"])
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt init
+@cli.command("init")
+@click.pass_context
+@global_flags
+# for backwards compatibility, accept 'project_name' as an optional positional argument
+@click.argument("project_name", required=False)
+@p.profile
+@p.profiles_dir_exists_false
+@p.project_dir
+@p.skip_profile_setup
+@p.target
+@p.vars
+@requires.postflight
+@requires.preflight
+def init(ctx, **kwargs):
+    """Initialize a new dbt project."""
+    task = InitTask(ctx.obj["flags"], None)
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt list
+@cli.command("list")
+@click.pass_context
+@global_flags
+@p.exclude
+@p.indirect_selection
+@p.models
+@p.output
+@p.output_keys
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.resource_type
+@p.raw_select
+@p.selector
+@p.state
+@p.deprecated_state
+@p.target
+@p.target_path
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def list(ctx, **kwargs):
+    """List the resources in your project"""
+    task = ListTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# Alias "list" to "ls"
+ls = copy(cli.commands["list"])
+ls.hidden = True
+cli.add_command(ls, "ls")
+
+
+# dbt parse
+@cli.command("parse")
+@click.pass_context
+@global_flags
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest(write_perf_info=True)
+def parse(ctx, **kwargs):
+    """Parses the project and provides information on performance"""
+    # manifest generation and writing happens in @requires.manifest
+
+    return ctx.obj["manifest"], True
+
+
+# dbt run
+@cli.command("run")
+@click.pass_context
+@global_flags
+@p.defer
+@p.deprecated_defer
+@p.favor_state
+@p.deprecated_favor_state
+@p.exclude
+@p.full_refresh
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.state
+@p.deprecated_state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def run(ctx, **kwargs):
+    """Compile SQL and execute against the current target database."""
+    task = RunTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt run operation
+@cli.command("run-operation")
+@click.pass_context
+@global_flags
+@click.argument("macro")
+@p.args
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.target
+@p.target_path
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def run_operation(ctx, **kwargs):
+    """Run the named macro with any supplied arguments."""
+    task = RunOperationTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt seed
+@cli.command("seed")
+@click.pass_context
+@global_flags
+@p.exclude
+@p.full_refresh
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.show
+@p.state
+@p.deprecated_state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def seed(ctx, **kwargs):
+    """Load data from csv files into your data warehouse."""
+    task = SeedTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt snapshot
+@cli.command("snapshot")
+@click.pass_context
+@global_flags
+@p.defer
+@p.deprecated_defer
+@p.exclude
+@p.favor_state
+@p.deprecated_favor_state
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.state
+@p.deprecated_state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def snapshot(ctx, **kwargs):
+    """Execute snapshots defined in your project"""
+    task = SnapshotTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# dbt source
+@cli.group()
+@click.pass_context
+@global_flags
+def source(ctx, **kwargs):
+    """Manage your project's sources"""
+
+
+# dbt source freshness
+@source.command("freshness")
+@click.pass_context
+@global_flags
+@p.exclude
+@p.output_path  # TODO: Is this ok to re-use?  We have three different output params, how much can we consolidate?
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.state
+@p.deprecated_state
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def freshness(ctx, **kwargs):
+    """check the current freshness of the project's sources"""
+    task = FreshnessTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# Alias "source freshness" to "snapshot-freshness"
+snapshot_freshness = copy(cli.commands["source"].commands["freshness"])  # type: ignore
+snapshot_freshness.hidden = True
+cli.commands["source"].add_command(snapshot_freshness, "snapshot-freshness")  # type: ignore
+
+
+# dbt test
+@cli.command("test")
+@click.pass_context
+@global_flags
+@p.defer
+@p.deprecated_defer
+@p.exclude
+@p.favor_state
+@p.deprecated_favor_state
+@p.indirect_selection
+@p.profile
+@p.profiles_dir
+@p.project_dir
+@p.select
+@p.selector
+@p.state
+@p.deprecated_state
+@p.store_failures
+@p.target
+@p.target_path
+@p.threads
+@p.vars
+@requires.postflight
+@requires.preflight
+@requires.profile
+@requires.project
+@requires.runtime_config
+@requires.manifest
+def test(ctx, **kwargs):
+    """Runs tests on data in deployed models. Run this after `dbt run`"""
+    task = TestTask(
+        ctx.obj["flags"],
+        ctx.obj["runtime_config"],
+        ctx.obj["manifest"],
+    )
+
+    results = task.run()
+    success = task.interpret_results(results)
+    return results, success
+
+
+# Support running as a module
+if __name__ == "__main__":
+    cli()

core/dbt/cli/option_types.py

@@ -0,0 +1,62 @@
+from click import ParamType, Choice
+
+from dbt.config.utils import parse_cli_yaml_string
+from dbt.exceptions import ValidationError, DbtValidationError, OptionNotYamlDictError
+
+from dbt.helper_types import WarnErrorOptions
+
+
+class YAML(ParamType):
+    """The Click YAML type. Converts YAML strings into objects."""
+
+    name = "YAML"
+
+    def convert(self, value, param, ctx):
+        # assume non-string values are a problem
+        if not isinstance(value, str):
+            self.fail(f"Cannot load YAML from type {type(value)}", param, ctx)
+        try:
+            param_option_name = param.opts[0] if param.opts else param.name
+            return parse_cli_yaml_string(value, param_option_name.strip("-"))
+        except (ValidationError, DbtValidationError, OptionNotYamlDictError):
+            self.fail(f"String '{value}' is not valid YAML", param, ctx)
+
+
+class WarnErrorOptionsType(YAML):
+    """The Click WarnErrorOptions type. Converts YAML strings into objects."""
+
+    name = "WarnErrorOptionsType"
+
+    def convert(self, value, param, ctx):
+        # this function is being used by param in click
+        include_exclude = super().convert(value, param, ctx)
+
+        return WarnErrorOptions(
+            include=include_exclude.get("include", []), exclude=include_exclude.get("exclude", [])
+        )
+
+
+class Truthy(ParamType):
+    """The Click Truthy type.  Converts strings into a "truthy" type"""
+
+    name = "TRUTHY"
+
+    def convert(self, value, param, ctx):
+        # assume non-string / non-None values are a problem
+        if not isinstance(value, (str, None)):
+            self.fail(f"Cannot load TRUTHY from type {type(value)}", param, ctx)
+
+        if value is None or value.lower() in ("0", "false", "f"):
+            return None
+        else:
+            return value
+
+
+class ChoiceTuple(Choice):
+    name = "CHOICE_TUPLE"
+
+    def convert(self, value, param, ctx):
+        for value_item in value:
+            super().convert(value_item, param, ctx)
+
+        return value

core/dbt/cli/options.py

@@ -0,0 +1,78 @@
+import click
+import inspect
+import typing as t
+from click import Context
+from click.parser import OptionParser, ParsingState
+from dbt.cli.option_types import ChoiceTuple
+
+
+# Implementation from: https://stackoverflow.com/a/48394004
+# Note MultiOption options must be specified with type=tuple or type=ChoiceTuple (https://github.com/pallets/click/issues/2012)
+class MultiOption(click.Option):
+    def __init__(self, *args, **kwargs):
+        self.save_other_options = kwargs.pop("save_other_options", True)
+        nargs = kwargs.pop("nargs", -1)
+        assert nargs == -1, "nargs, if set, must be -1 not {}".format(nargs)
+        super(MultiOption, self).__init__(*args, **kwargs)
+        # this makes mypy happy, setting these to None causes mypy failures
+        self._previous_parser_process = lambda *args, **kwargs: None
+        self._eat_all_parser = lambda *args, **kwargs: None
+
+        # validate that multiple=True
+        multiple = kwargs.pop("multiple", None)
+        msg = f"MultiOption named `{self.name}` must have multiple=True (rather than {multiple})"
+        assert multiple, msg
+
+        # validate that type=tuple or type=ChoiceTuple
+        option_type = kwargs.pop("type", None)
+        msg = f"MultiOption named `{self.name}` must be tuple or ChoiceTuple (rather than {option_type})"
+        if inspect.isclass(option_type):
+            assert issubclass(option_type, tuple), msg
+        else:
+            assert isinstance(option_type, ChoiceTuple), msg
+
+    def add_to_parser(self, parser: OptionParser, ctx: Context):
+        def parser_process(value: str, state: ParsingState):
+            # method to hook to the parser.process
+            done = False
+            value_list = str.split(value, " ")
+            if self.save_other_options:
+                # grab everything up to the next option
+                while state.rargs and not done:
+                    for prefix in self._eat_all_parser.prefixes:  # type: ignore[attr-defined]
+                        if state.rargs[0].startswith(prefix):
+                            done = True
+                    if not done:
+                        value_list.append(state.rargs.pop(0))
+            else:
+                # grab everything remaining
+                value_list += state.rargs
+                state.rargs[:] = []
+            value_tuple = tuple(value_list)
+            # call the actual process
+            self._previous_parser_process(value_tuple, state)
+
+        retval = super(MultiOption, self).add_to_parser(parser, ctx)
+        for name in self.opts:
+            our_parser = parser._long_opt.get(name) or parser._short_opt.get(name)
+            if our_parser:
+                self._eat_all_parser = our_parser  # type: ignore[assignment]
+                self._previous_parser_process = our_parser.process
+                # mypy doesnt like assingment to a method see https://github.com/python/mypy/issues/708
+                our_parser.process = parser_process  # type: ignore[assignment]
+                break
+        return retval
+
+    def type_cast_value(self, ctx: Context, value: t.Any) -> t.Any:
+        def flatten(data):
+            if isinstance(data, tuple):
+                for x in data:
+                    yield from flatten(x)
+            else:
+                yield data
+
+        # there will be nested tuples to flatten when multiple=True
+        value = super(MultiOption, self).type_cast_value(ctx, value)
+        if value:
+            value = tuple(flatten(value))
+        return value

core/dbt/cli/params.py

@@ -0,0 +1,556 @@
+from pathlib import Path
+
+import click
+from dbt.cli.options import MultiOption
+from dbt.cli.option_types import YAML, ChoiceTuple, WarnErrorOptionsType
+from dbt.cli.resolvers import default_project_dir, default_profiles_dir
+from dbt.version import get_version_information
+
+args = click.option(
+    "--args",
+    envvar=None,
+    help="Supply arguments to the macro. This dictionary will be mapped to the keyword arguments defined in the selected macro. This argument should be a YAML string, eg. '{my_variable: my_value}'",
+    type=YAML(),
+)
+
+browser = click.option(
+    "--browser/--no-browser",
+    envvar=None,
+    help="Wether or not to open a local web browser after starting the server",
+    default=True,
+)
+
+cache_selected_only = click.option(
+    "--cache-selected-only/--no-cache-selected-only",
+    envvar="DBT_CACHE_SELECTED_ONLY",
+    help="At start of run, populate relational cache only for schemas containing selected nodes, or for all schemas of interest.",
+)
+
+introspect = click.option(
+    "--introspect/--no-introspect",
+    envvar="DBT_INTROSPECT",
+    help="Whether to scaffold introspective queries as part of compilation",
+    default=True,
+)
+
+compile_docs = click.option(
+    "--compile/--no-compile",
+    envvar=None,
+    help="Whether or not to run 'dbt compile' as part of docs generation",
+    default=True,
+)
+
+config_dir = click.option(
+    "--config-dir",
+    envvar=None,
+    help="Show the configured location for the profiles.yml file and exit",
+    is_flag=True,
+)
+
+debug = click.option(
+    "--debug/--no-debug",
+    "-d/ ",
+    envvar="DBT_DEBUG",
+    help="Display debug logging during dbt execution. Useful for debugging and making bug reports.",
+)
+
+# flag was previously named DEFER_MODE
+defer = click.option(
+    "--defer/--no-defer",
+    envvar="DBT_DEFER",
+    help="If set, resolve unselected nodes by deferring to the manifest within the --state directory.",
+)
+
+deprecated_defer = click.option(
+    "--deprecated-defer",
+    envvar="DBT_DEFER_TO_STATE",
+    help="Internal flag for deprecating old env var.",
+    default=False,
+    hidden=True,
+)
+
+enable_legacy_logger = click.option(
+    "--enable-legacy-logger/--no-enable-legacy-logger",
+    envvar="DBT_ENABLE_LEGACY_LOGGER",
+    hidden=True,
+)
+
+exclude = click.option(
+    "--exclude",
+    envvar=None,
+    type=tuple,
+    cls=MultiOption,
+    multiple=True,
+    help="Specify the nodes to exclude.",
+)
+
+fail_fast = click.option(
+    "--fail-fast/--no-fail-fast",
+    "-x/ ",
+    envvar="DBT_FAIL_FAST",
+    help="Stop execution on first failure.",
+)
+
+favor_state = click.option(
+    "--favor-state/--no-favor-state",
+    envvar="DBT_FAVOR_STATE",
+    help="If set, defer to the argument provided to the state flag for resolving unselected nodes, even if the node(s) exist as a database object in the current environment.",
+)
+
+deprecated_favor_state = click.option(
+    "--deprecated-favor-state",
+    envvar="DBT_FAVOR_STATE_MODE",
+    help="Internal flag for deprecating old env var.",
+)
+
+full_refresh = click.option(
+    "--full-refresh",
+    "-f",
+    envvar="DBT_FULL_REFRESH",
+    help="If specified, dbt will drop incremental models and fully-recalculate the incremental table from the model definition.",
+    is_flag=True,
+)
+
+indirect_selection = click.option(
+    "--indirect-selection",
+    envvar="DBT_INDIRECT_SELECTION",
+    help="Choose which tests to select that are adjacent to selected resources. Eager is most inclusive, cautious is most exclusive, and buildable is in between. Empty includes no tests at all.",
+    type=click.Choice(["eager", "cautious", "buildable", "empty"], case_sensitive=False),
+    default="eager",
+)
+
+log_cache_events = click.option(
+    "--log-cache-events/--no-log-cache-events",
+    help="Enable verbose logging for relational cache events to help when debugging.",
+    envvar="DBT_LOG_CACHE_EVENTS",
+)
+
+log_format = click.option(
+    "--log-format",
+    envvar="DBT_LOG_FORMAT",
+    help="Specify the format of logging to the console and the log file. Use --log-format-file to configure the format for the log file differently than the console.",
+    type=click.Choice(["text", "debug", "json", "default"], case_sensitive=False),
+    default="default",
+)
+
+log_format_file = click.option(
+    "--log-format-file",
+    envvar="DBT_LOG_FORMAT_FILE",
+    help="Specify the format of logging to the log file by overriding the default value and the general --log-format setting.",
+    type=click.Choice(["text", "debug", "json", "default"], case_sensitive=False),
+    default="debug",
+)
+
+log_level = click.option(
+    "--log-level",
+    envvar="DBT_LOG_LEVEL",
+    help="Specify the minimum severity of events that are logged to the console and the log file. Use --log-level-file to configure the severity for the log file differently than the console.",
+    type=click.Choice(["debug", "info", "warn", "error", "none"], case_sensitive=False),
+    default="info",
+)
+
+log_level_file = click.option(
+    "--log-level-file",
+    envvar="DBT_LOG_LEVEL_FILE",
+    help="Specify the minimum severity of events that are logged to the log file by overriding the default value and the general --log-level setting.",
+    type=click.Choice(["debug", "info", "warn", "error", "none"], case_sensitive=False),
+    default="debug",
+)
+
+use_colors = click.option(
+    "--use-colors/--no-use-colors",
+    envvar="DBT_USE_COLORS",
+    help="Specify whether log output is colorized in the console and the log file. Use --use-colors-file/--no-use-colors-file to colorize the log file differently than the console.",
+    default=True,
+)
+
+use_colors_file = click.option(
+    "--use-colors-file/--no-use-colors-file",
+    envvar="DBT_USE_COLORS_FILE",
+    help="Specify whether log file output is colorized by overriding the default value and the general --use-colors/--no-use-colors setting.",
+    default=True,
+)
+
+log_file_max_bytes = click.option(
+    "--log-file-max-bytes",
+    envvar="DBT_LOG_FILE_MAX_BYTES",
+    help="Configure the max file size in bytes for a single dbt.log file, before rolling over. 0 means no limit.",
+    default=10 * 1024 * 1024,  # 10mb
+    type=click.INT,
+    hidden=True,
+)
+
+log_path = click.option(
+    "--log-path",
+    envvar="DBT_LOG_PATH",
+    help="Configure the 'log-path'. Only applies this setting for the current run. Overrides the 'DBT_LOG_PATH' if it is set.",
+    default=None,
+    type=click.Path(resolve_path=True, path_type=Path),
+)
+
+macro_debugging = click.option(
+    "--macro-debugging/--no-macro-debugging",
+    envvar="DBT_MACRO_DEBUGGING",
+    hidden=True,
+)
+
+# This less standard usage of --output where output_path below is more standard
+output = click.option(
+    "--output",
+    envvar=None,
+    help="Specify the output format: either JSON or a newline-delimited list of selectors, paths, or names",
+    type=click.Choice(["json", "name", "path", "selector"], case_sensitive=False),
+    default="selector",
+)
+
+show_output_format = click.option(
+    "--output",
+    envvar=None,
+    help="Output format for dbt compile and dbt show",
+    type=click.Choice(["json", "text"], case_sensitive=False),
+    default="text",
+)
+
+show_limit = click.option(
+    "--limit",
+    envvar=None,
+    help="Limit the number of results returned by dbt show",
+    type=click.INT,
+    default=5,
+)
+
+output_keys = click.option(
+    "--output-keys",
+    envvar=None,
+    help=(
+        "Space-delimited listing of node properties to include as custom keys for JSON output "
+        "(e.g. `--output json --output-keys name resource_type description`)"
+    ),
+    type=tuple,
+    cls=MultiOption,
+    multiple=True,
+    default=[],
+)
+
+output_path = click.option(
+    "--output",
+    "-o",
+    envvar=None,
+    help="Specify the output path for the JSON report. By default, outputs to 'target/sources.json'",
+    type=click.Path(file_okay=True, dir_okay=False, writable=True),
+    default=None,
+)
+
+partial_parse = click.option(
+    "--partial-parse/--no-partial-parse",
+    envvar="DBT_PARTIAL_PARSE",
+    help="Allow for partial parsing by looking for and writing to a pickle file in the target directory. This overrides the user configuration file.",
+    default=True,
+)
+
+populate_cache = click.option(
+    "--populate-cache/--no-populate-cache",
+    envvar="DBT_POPULATE_CACHE",
+    help="At start of run, use `show` or `information_schema` queries to populate a relational cache, which can speed up subsequent materializations.",
+    default=True,
+)
+
+port = click.option(
+    "--port",
+    envvar=None,
+    help="Specify the port number for the docs server",
+    default=8080,
+    type=click.INT,
+)
+
+print = click.option(
+    "--print/--no-print",
+    envvar="DBT_PRINT",
+    help="Output all {{ print() }} macro calls.",
+    default=True,
+)
+
+deprecated_print = click.option(
+    "--deprecated-print/--deprecated-no-print",
+    envvar="DBT_NO_PRINT",
+    help="Internal flag for deprecating old env var.",
+    default=True,
+    hidden=True,
+    callback=lambda ctx, param, value: not value,
+)
+
+printer_width = click.option(
+    "--printer-width",
+    envvar="DBT_PRINTER_WIDTH",
+    help="Sets the width of terminal output",
+    type=click.INT,
+    default=80,
+)
+
+profile = click.option(
+    "--profile",
+    envvar=None,
+    help="Which profile to load. Overrides setting in dbt_project.yml.",
+)
+
+profiles_dir = click.option(
+    "--profiles-dir",
+    envvar="DBT_PROFILES_DIR",
+    help="Which directory to look in for the profiles.yml file. If not set, dbt will look in the current working directory first, then HOME/.dbt/",
+    default=default_profiles_dir,
+    type=click.Path(exists=True),
+)
+
+# `dbt debug` uses this because it implements custom behaviour for non-existent profiles.yml directories
+# `dbt deps` does not load a profile at all
+# `dbt init` will write profiles.yml if it doesn't yet exist
+profiles_dir_exists_false = click.option(
+    "--profiles-dir",
+    envvar="DBT_PROFILES_DIR",
+    help="Which directory to look in for the profiles.yml file. If not set, dbt will look in the current working directory first, then HOME/.dbt/",
+    default=default_profiles_dir,
+    type=click.Path(exists=False),
+)
+
+project_dir = click.option(
+    "--project-dir",
+    envvar="DBT_PROJECT_DIR",
+    help="Which directory to look in for the dbt_project.yml file. Default is the current working directory and its parents.",
+    default=default_project_dir,
+    type=click.Path(exists=True),
+)
+
+quiet = click.option(
+    "--quiet/--no-quiet",
+    "-q",
+    envvar="DBT_QUIET",
+    help="Suppress all non-error logging to stdout. Does not affect {{ print() }} macro calls.",
+)
+
+record_timing_info = click.option(
+    "--record-timing-info",
+    "-r",
+    envvar=None,
+    help="When this option is passed, dbt will output low-level timing stats to the specified file. Example: `--record-timing-info output.profile`",
+    type=click.Path(exists=False),
+)
+
+resource_type = click.option(
+    "--resource-types",
+    "--resource-type",
+    envvar=None,
+    help="Restricts the types of resources that dbt will include",
+    type=ChoiceTuple(
+        [
+            "metric",
+            "source",
+            "analysis",
+            "model",
+            "test",
+            "exposure",
+            "snapshot",
+            "seed",
+            "default",
+            "all",
+        ],
+        case_sensitive=False,
+    ),
+    cls=MultiOption,
+    multiple=True,
+    default=(),
+)
+
+model_decls = ("-m", "--models", "--model")
+select_decls = ("-s", "--select")
+select_attrs = {
+    "envvar": None,
+    "help": "Specify the nodes to include.",
+    "cls": MultiOption,
+    "multiple": True,
+    "type": tuple,
+}
+
+inline = click.option(
+    "--inline",
+    envvar=None,
+    help="Pass SQL inline to dbt compile and show",
+)
+
+# `--select` and `--models` are analogous for most commands except `dbt list` for legacy reasons.
+# Most CLI arguments should use the combined `select` option that aliases `--models` to `--select`.
+# However, if you need to split out these separators (like `dbt ls`), use the `models` and `raw_select` options instead.
+# See https://github.com/dbt-labs/dbt-core/pull/6774#issuecomment-1408476095 for more info.
+models = click.option(*model_decls, **select_attrs)  # type: ignore[arg-type]
+raw_select = click.option(*select_decls, **select_attrs)  # type: ignore[arg-type]
+select = click.option(*select_decls, *model_decls, **select_attrs)  # type: ignore[arg-type]
+
+selector = click.option(
+    "--selector",
+    envvar=None,
+    help="The selector name to use, as defined in selectors.yml",
+)
+
+send_anonymous_usage_stats = click.option(
+    "--send-anonymous-usage-stats/--no-send-anonymous-usage-stats",
+    envvar="DBT_SEND_ANONYMOUS_USAGE_STATS",
+    help="Send anonymous usage stats to dbt Labs.",
+    default=True,
+)
+
+show = click.option(
+    "--show",
+    envvar=None,
+    help="Show a sample of the loaded data in the terminal",
+    is_flag=True,
+)
+
+# TODO:  The env var is a correction!
+# The original env var was `DBT_TEST_SINGLE_THREADED`.
+# This broke the existing naming convention.
+# This will need to be communicated as a change to the community!
+#
+# N.B. This flag is only used for testing, hence it's hidden from help text.
+single_threaded = click.option(
+    "--single-threaded/--no-single-threaded",
+    envvar="DBT_SINGLE_THREADED",
+    default=False,
+    hidden=True,
+)
+
+skip_profile_setup = click.option(
+    "--skip-profile-setup",
+    "-s",
+    envvar=None,
+    help="Skip interactive profile setup.",
+    is_flag=True,
+)
+
+state = click.option(
+    "--state",
+    envvar="DBT_STATE",
+    help="If set, use the given directory as the source for JSON files to compare with this project.",
+    type=click.Path(
+        dir_okay=True,
+        file_okay=False,
+        readable=True,
+        resolve_path=False,
+        path_type=Path,
+    ),
+)
+
+deprecated_state = click.option(
+    "--deprecated-state",
+    envvar="DBT_ARTIFACT_STATE_PATH",
+    help="Internal flag for deprecating old env var.",
+    hidden=True,
+    type=click.Path(
+        dir_okay=True,
+        file_okay=False,
+        readable=True,
+        resolve_path=True,
+        path_type=Path,
+    ),
+)
+
+static_parser = click.option(
+    "--static-parser/--no-static-parser",
+    envvar="DBT_STATIC_PARSER",
+    help="Use the static parser.",
+    default=True,
+)
+
+store_failures = click.option(
+    "--store-failures",
+    envvar="DBT_STORE_FAILURES",
+    help="Store test results (failing rows) in the database",
+    is_flag=True,
+)
+
+target = click.option(
+    "--target",
+    "-t",
+    envvar=None,
+    help="Which target to load for the given profile",
+)
+
+target_path = click.option(
+    "--target-path",
+    envvar="DBT_TARGET_PATH",
+    help="Configure the 'target-path'. Only applies this setting for the current run. Overrides the 'DBT_TARGET_PATH' if it is set.",
+    type=click.Path(),
+)
+
+threads = click.option(
+    "--threads",
+    envvar=None,
+    help="Specify number of threads to use while executing models. Overrides settings in profiles.yml.",
+    default=None,
+    type=click.INT,
+)
+
+use_experimental_parser = click.option(
+    "--use-experimental-parser/--no-use-experimental-parser",
+    envvar="DBT_USE_EXPERIMENTAL_PARSER",
+    help="Enable experimental parsing features.",
+)
+
+vars = click.option(
+    "--vars",
+    envvar=None,
+    help="Supply variables to the project. This argument overrides variables defined in your dbt_project.yml file. This argument should be a YAML string, eg. '{my_variable: my_value}'",
+    type=YAML(),
+    default="{}",
+)
+
+
+# TODO: when legacy flags are deprecated use
+# click.version_option instead of a callback
+def _version_callback(ctx, _param, value):
+    if not value or ctx.resilient_parsing:
+        return
+    click.echo(get_version_information())
+    ctx.exit()
+
+
+version = click.option(
+    "--version",
+    "-V",
+    "-v",
+    callback=_version_callback,
+    envvar=None,
+    expose_value=False,
+    help="Show version information and exit",
+    is_eager=True,
+    is_flag=True,
+)
+
+version_check = click.option(
+    "--version-check/--no-version-check",
+    envvar="DBT_VERSION_CHECK",
+    help="If set, ensure the installed dbt version matches the require-dbt-version specified in the dbt_project.yml file (if any). Otherwise, allow them to differ.",
+    default=True,
+)
+
+warn_error = click.option(
+    "--warn-error",
+    envvar="DBT_WARN_ERROR",
+    help="If dbt would normally warn, instead raise an exception. Examples include --select that selects nothing, deprecations, configurations with no associated models, invalid test configurations, and missing sources/refs in tests.",
+    default=None,
+    is_flag=True,
+)
+
+warn_error_options = click.option(
+    "--warn-error-options",
+    envvar="DBT_WARN_ERROR_OPTIONS",
+    default="{}",
+    help="""If dbt would normally warn, instead raise an exception based on include/exclude configuration. Examples include --select that selects nothing, deprecations, configurations with no associated models, invalid test configurations,
+    and missing sources/refs in tests. This argument should be a YAML string, with keys 'include' or 'exclude'. eg. '{"include": "all", "exclude": ["NoNodesForSelectionCriteria"]}'""",
+    type=WarnErrorOptionsType(),
+)
+
+write_json = click.option(
+    "--write-json/--no-write-json",
+    envvar="DBT_WRITE_JSON",
+    help="Whether or not to write the manifest.json and run_results.json files to the target directory",
+    default=True,
+)

core/dbt/cli/requires.py

@@ -0,0 +1,258 @@
+import dbt.tracking
+from dbt.version import installed as installed_version
+from dbt.adapters.factory import adapter_management, register_adapter
+from dbt.flags import set_flags, get_flag_dict
+from dbt.cli.exceptions import (
+    ExceptionExit,
+    ResultExit,
+)
+from dbt.cli.flags import Flags
+from dbt.config import RuntimeConfig
+from dbt.config.runtime import load_project, load_profile, UnsetProfile
+from dbt.events.functions import fire_event, LOG_VERSION, set_invocation_id, setup_event_logger
+from dbt.events.types import (
+    CommandCompleted,
+    MainReportVersion,
+    MainReportArgs,
+    MainTrackingUserState,
+)
+from dbt.events.helpers import get_json_string_utcnow
+from dbt.events.types import MainEncounteredError, MainStackTrace
+from dbt.exceptions import Exception as DbtException, DbtProjectError, FailFastError
+from dbt.parser.manifest import ManifestLoader, write_manifest
+from dbt.profiler import profiler
+from dbt.tracking import active_user, initialize_from_flags, track_run
+from dbt.utils import cast_dict_to_dict_of_strings
+
+from click import Context
+from functools import update_wrapper
+import time
+import traceback
+
+
+def preflight(func):
+    def wrapper(*args, **kwargs):
+        ctx = args[0]
+        assert isinstance(ctx, Context)
+        ctx.obj = ctx.obj or {}
+
+        # Flags
+        flags = Flags(ctx)
+        ctx.obj["flags"] = flags
+        set_flags(flags)
+
+        # Logging
+        callbacks = ctx.obj.get("callbacks", [])
+        set_invocation_id()
+        setup_event_logger(flags=flags, callbacks=callbacks)
+
+        # Tracking
+        initialize_from_flags(flags.SEND_ANONYMOUS_USAGE_STATS, flags.PROFILES_DIR)
+        ctx.with_resource(track_run(run_command=flags.WHICH))
+
+        # Now that we have our logger, fire away!
+        fire_event(MainReportVersion(version=str(installed_version), log_version=LOG_VERSION))
+        flags_dict_str = cast_dict_to_dict_of_strings(get_flag_dict())
+        fire_event(MainReportArgs(args=flags_dict_str))
+
+        # Deprecation warnings
+        flags.fire_deprecations()
+
+        if active_user is not None:  # mypy appeasement, always true
+            fire_event(MainTrackingUserState(user_state=active_user.state()))
+
+        # Profiling
+        if flags.RECORD_TIMING_INFO:
+            ctx.with_resource(profiler(enable=True, outfile=flags.RECORD_TIMING_INFO))
+
+        # Adapter management
+        ctx.with_resource(adapter_management())
+
+        return func(*args, **kwargs)
+
+    return update_wrapper(wrapper, func)
+
+
+def postflight(func):
+    """The decorator that handles all exception handling for the click commands.
+    This decorator must be used before any other decorators that may throw an exception."""
+
+    def wrapper(*args, **kwargs):
+        ctx = args[0]
+        start_func = time.perf_counter()
+        success = False
+
+        try:
+            result, success = func(*args, **kwargs)
+        except FailFastError as e:
+            fire_event(MainEncounteredError(exc=str(e)))
+            raise ResultExit(e.result)
+        except DbtException as e:
+            fire_event(MainEncounteredError(exc=str(e)))
+            raise ExceptionExit(e)
+        except BaseException as e:
+            fire_event(MainEncounteredError(exc=str(e)))
+            fire_event(MainStackTrace(stack_trace=traceback.format_exc()))
+            raise ExceptionExit(e)
+        finally:
+            fire_event(
+                CommandCompleted(
+                    command=ctx.command_path,
+                    success=success,
+                    completed_at=get_json_string_utcnow(),
+                    elapsed=time.perf_counter() - start_func,
+                )
+            )
+
+        if not success:
+            raise ResultExit(result)
+
+        return (result, success)
+
+    return update_wrapper(wrapper, func)
+
+
+# TODO: UnsetProfile is necessary for deps and clean to load a project.
+# This decorator and its usage can be removed once https://github.com/dbt-labs/dbt-core/issues/6257 is closed.
+def unset_profile(func):
+    def wrapper(*args, **kwargs):
+        ctx = args[0]
+        assert isinstance(ctx, Context)
+
+        profile = UnsetProfile()
+        ctx.obj["profile"] = profile
+
+        return func(*args, **kwargs)
+
+    return update_wrapper(wrapper, func)
+
+
+def profile(func):
+    def wrapper(*args, **kwargs):
+        ctx = args[0]
+        assert isinstance(ctx, Context)
+
+        flags = ctx.obj["flags"]
+        # TODO: Generalize safe access to flags.THREADS:
+        # https://github.com/dbt-labs/dbt-core/issues/6259
+        threads = getattr(flags, "THREADS", None)
+        profile = load_profile(flags.PROJECT_DIR, flags.VARS, flags.PROFILE, flags.TARGET, threads)
+        ctx.obj["profile"] = profile
+
+        return func(*args, **kwargs)
+
+    return update_wrapper(wrapper, func)
+
+
+def project(func):
+    def wrapper(*args, **kwargs):
+        ctx = args[0]
+        assert isinstance(ctx, Context)
+
+        # TODO: Decouple target from profile, and remove the need for profile here:
+        # https://github.com/dbt-labs/dbt-core/issues/6257
+        if not ctx.obj.get("profile"):
+            raise DbtProjectError("profile required for project")
+
+        flags = ctx.obj["flags"]
+        project = load_project(
+            flags.PROJECT_DIR, flags.VERSION_CHECK, ctx.obj["profile"], flags.VARS
+        )
+        ctx.obj["project"] = project
+
+        if dbt.tracking.active_user is not None:
+            project_id = None if project is None else project.hashed_name()
+
+            dbt.tracking.track_project_id({"project_id": project_id})
+
+        return func(*args, **kwargs)
+
+    return update_wrapper(wrapper, func)
+
+
+def runtime_config(func):
+    """A decorator used by click command functions for generating a runtime
+    config given a profile and project.
+    """
+
+    def wrapper(*args, **kwargs):
+        ctx = args[0]
+        assert isinstance(ctx, Context)
+
+        req_strs = ["profile", "project"]
+        reqs = [ctx.obj.get(req_str) for req_str in req_strs]
+
+        if None in reqs:
+            raise DbtProjectError("profile and project required for runtime_config")
+
+        config = RuntimeConfig.from_parts(
+            ctx.obj["project"],
+            ctx.obj["profile"],
+            ctx.obj["flags"],
+        )
+
+        ctx.obj["runtime_config"] = config
+
+        if dbt.tracking.active_user is not None:
+            adapter_type = (
+                getattr(config.credentials, "type", None)
+                if hasattr(config, "credentials")
+                else None
+            )
+            adapter_unique_id = (
+                config.credentials.hashed_unique_field()
+                if hasattr(config, "credentials")
+                else None
+            )
+
+            dbt.tracking.track_adapter_info(
+                {
+                    "adapter_type": adapter_type,
+                    "adapter_unique_id": adapter_unique_id,
+                }
+            )
+
+        return func(*args, **kwargs)
+
+    return update_wrapper(wrapper, func)
+
+
+def manifest(*args0, write=True, write_perf_info=False):
+    """A decorator used by click command functions for generating a manifest
+    given a profile, project, and runtime config. This also registers the adapter
+    from the runtime config and conditionally writes the manifest to disk.
+    """
+
+    def outer_wrapper(func):
+        def wrapper(*args, **kwargs):
+            ctx = args[0]
+            assert isinstance(ctx, Context)
+
+            req_strs = ["profile", "project", "runtime_config"]
+            reqs = [ctx.obj.get(dep) for dep in req_strs]
+
+            if None in reqs:
+                raise DbtProjectError("profile, project, and runtime_config required for manifest")
+
+            runtime_config = ctx.obj["runtime_config"]
+            register_adapter(runtime_config)
+
+            # a manifest has already been set on the context, so don't overwrite it
+            if ctx.obj.get("manifest") is None:
+                manifest = ManifestLoader.get_full_manifest(
+                    runtime_config, write_perf_info=write_perf_info
+                )
+
+                ctx.obj["manifest"] = manifest
+                if write and ctx.obj["flags"].write_json:
+                    write_manifest(manifest, ctx.obj["runtime_config"].project_target_path)
+
+            return func(*args, **kwargs)
+
+        return update_wrapper(wrapper, func)
+
+    # if there are no args, the decorator was used without params @decorator
+    # otherwise, the decorator was called with params @decorator(arg)
+    if len(args0) == 0:
+        return outer_wrapper
+    return outer_wrapper(args0[0])

core/dbt/cli/resolvers.py

@@ -0,0 +1,31 @@
+from pathlib import Path
+from dbt.config.project import PartialProject
+from dbt.exceptions import DbtProjectError
+
+
+def default_project_dir() -> Path:
+    paths = list(Path.cwd().parents)
+    paths.insert(0, Path.cwd())
+    return next((x for x in paths if (x / "dbt_project.yml").exists()), Path.cwd())
+
+
+def default_profiles_dir() -> Path:
+    return Path.cwd() if (Path.cwd() / "profiles.yml").exists() else Path.home() / ".dbt"
+
+
+def default_log_path(project_dir: Path, verify_version: bool = False) -> Path:
+    """If available, derive a default log path from dbt_project.yml. Otherwise, default to "logs".
+    Known limitations:
+    1. Using PartialProject here, so no jinja rendering of log-path.
+    2. Programmatic invocations of the cli via dbtRunner may pass a Project object directly,
+       which is not being taken into consideration here to extract a log-path.
+    """
+    default_log_path = Path("logs")
+    try:
+        partial = PartialProject.from_project_root(str(project_dir), verify_version=verify_version)
+        partial_log_path = partial.project_dict.get("log-path") or default_log_path
+        default_log_path = Path(project_dir) / partial_log_path
+    except DbtProjectError:
+        pass
+
+    return default_log_path

core/dbt/clients/README.md

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

core/dbt/clients/_jinja_blocks.py

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

core/dbt/clients/agate_helper.py

@@ -7,7 +7,7 @@ import json
 import dbt.utils
 from typing import Iterable, List, Dict, Union, Optional, Any
 
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 BOM = BOM_UTF8.decode("utf-8")  # '\ufeff'
@@ -80,7 +80,7 @@ def table_from_rows(
 
 
 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
@@ -168,7 +168,7 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
             return
         elif not isinstance(value, type(existing_type)):
             # actual type mismatch!
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f"Tables contain columns with the same names ({key}), "
                 f"but different types ({value} vs {existing_type})"
             )

core/dbt/clients/git.py

@@ -14,10 +14,10 @@ from dbt.events.types import (
 )
 from dbt.exceptions import (
     CommandResultError,
-    RuntimeException,
-    bad_package_spec,
-    raise_git_cloning_error,
-    raise_git_cloning_problem,
+    GitCheckoutError,
+    GitCloningError,
+    UnknownGitCloningProblemError,
+    DbtRuntimeError,
 )
 from packaging import version
 
@@ -27,16 +27,6 @@ def _is_commit(revision: str) -> bool:
     return bool(re.match(r"\b[0-9a-f]{40}\b", revision))
 
 
-def _raise_git_cloning_error(repo, revision, error):
-    stderr = error.stderr.decode("utf-8").strip()
-    if "usage: git" in stderr:
-        stderr = stderr.split("\nusage: git")[0]
-    if re.match("fatal: destination path '(.+)' already exists", stderr):
-        raise_git_cloning_error(error)
-
-    bad_package_spec(repo, revision, stderr)
-
-
 def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirectory=None):
     has_revision = revision is not None
     is_commit = _is_commit(revision or "")
@@ -64,7 +54,7 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
     try:
         result = run_cmd(cwd, clone_cmd, env={"LC_ALL": "C"})
     except CommandResultError as exc:
-        _raise_git_cloning_error(repo, revision, exc)
+        raise GitCloningError(repo, revision, exc)
 
     if subdirectory:
         cwd_subdir = os.path.join(cwd, dirname or "")
@@ -72,7 +62,7 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
         try:
             run_cmd(cwd_subdir, clone_cmd_subdir)
         except CommandResultError as exc:
-            _raise_git_cloning_error(repo, revision, exc)
+            raise GitCloningError(repo, revision, exc)
 
     if remove_git_dir:
         rmdir(os.path.join(dirname, ".git"))
@@ -115,8 +105,7 @@ def checkout(cwd, repo, revision=None):
     try:
         return _checkout(cwd, repo, revision)
     except CommandResultError as exc:
-        stderr = exc.stderr.decode("utf-8").strip()
-    bad_package_spec(repo, revision, stderr)
+        raise GitCheckoutError(repo=repo, revision=revision, error=exc)
 
 
 def get_current_sha(cwd):
@@ -142,10 +131,10 @@ def clone_and_checkout(
             subdirectory=subdirectory,
         )
     except CommandResultError as exc:
-        err = exc.stderr.decode("utf-8")
+        err = exc.stderr
         exists = re.match("fatal: destination path '(.+)' already exists", err)
         if not exists:
-            raise_git_cloning_problem(repo)
+            raise UnknownGitCloningProblemError(repo)
 
     directory = None
     start_sha = None
@@ -155,7 +144,7 @@ def clone_and_checkout(
     else:
         matches = re.match("Cloning into '(.+)'", err.decode("utf-8"))
         if matches is None:
-            raise RuntimeException(f'Error cloning {repo} - never saw "Cloning into ..." from git')
+            raise DbtRuntimeError(f'Error cloning {repo} - never saw "Cloning into ..." from git')
         directory = matches.group(1)
         fire_event(GitProgressPullingNewDependency(dir=directory))
     full_path = os.path.join(cwd, directory)

core/dbt/clients/jinja.py

@@ -25,18 +25,26 @@ from dbt.utils import (
 )
 
 from dbt.clients._jinja_blocks import BlockIterator, BlockData, BlockTag
-from dbt.contracts.graph.compiled import CompiledGenericTestNode
-from dbt.contracts.graph.parsed import ParsedGenericTestNode
+from dbt.contracts.graph.nodes import GenericTestNode
+
 from dbt.exceptions import (
-    InternalException,
-    raise_compiler_error,
-    CompilationException,
-    invalid_materialization_argument,
+    CaughtMacroError,
+    CaughtMacroErrorWithNodeError,
+    CompilationError,
+    DbtInternalError,
+    MaterializationArgError,
+    JinjaRenderingError,
     MacroReturn,
-    JinjaRenderingException,
-    UndefinedMacroException,
+    MaterializtionMacroNotUsedError,
+    NoSupportedLanguagesFoundError,
+    UndefinedCompilationError,
+    UndefinedMacroError,
 )
-from dbt import flags
+from dbt.flags import get_flags
+from dbt.node_types import ModelLanguage
+
+
+SUPPORTED_LANG_ARG = jinja2.nodes.Name("supported_languages", "param")
 
 
 def _linecache_inject(source, write):
@@ -91,8 +99,9 @@ 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"
+        macro_debugging = get_flags().MACRO_DEBUGGING
+        if filename == "<template>" and macro_debugging:
+            write = macro_debugging == "write"
             filename = _linecache_inject(source, write)
 
         return super()._compile(source, filename)  # type: ignore
@@ -103,7 +112,7 @@ 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!
     """
@@ -153,15 +162,15 @@ def quoted_native_concat(nodes):
     except (ValueError, SyntaxError, MemoryError):
         result = raw
     if isinstance(raw, BoolMarker) and not isinstance(result, bool):
-        raise JinjaRenderingException(f"Could not convert value '{raw!s}' into type 'bool'")
+        raise JinjaRenderingError(f"Could not convert value '{raw!s}' into type 'bool'")
     if isinstance(raw, NumberMarker) and not _is_number(result):
-        raise JinjaRenderingException(f"Could not convert value '{raw!s}' into type 'number'")
+        raise JinjaRenderingError(f"Could not convert value '{raw!s}' into type 'number'")
 
     return result
 
 
 class NativeSandboxTemplate(jinja2.nativetypes.NativeTemplate):  # mypy: ignore
-    environment_class = NativeSandboxEnvironment
+    environment_class = NativeSandboxEnvironment  # type: ignore
 
     def render(self, *args, **kwargs):
         """Render the template to produce a native Python type. If the
@@ -233,12 +242,12 @@ class BaseMacroGenerator:
         try:
             yield
         except (TypeError, jinja2.exceptions.TemplateRuntimeError) as e:
-            raise_compiler_error(str(e))
+            raise CaughtMacroError(e)
 
     def call_macro(self, *args, **kwargs):
         # called from __call__ methods
         if self.context is None:
-            raise InternalException("Context is still None in call_macro!")
+            raise DbtInternalError("Context is still None in call_macro!")
         assert self.context is not None
 
         macro = self.get_macro()
@@ -265,7 +274,7 @@ class MacroStack(threading.local):
     def pop(self, name):
         got = self.call_stack.pop()
         if got != name:
-            raise InternalException(f"popped {got}, expected {name}")
+            raise DbtInternalError(f"popped {got}, expected {name}")
 
 
 class MacroGenerator(BaseMacroGenerator):
@@ -292,8 +301,8 @@ class MacroGenerator(BaseMacroGenerator):
         try:
             yield
         except (TypeError, jinja2.exceptions.TemplateRuntimeError) as e:
-            raise_compiler_error(str(e), self.macro)
-        except CompilationException as e:
+            raise CaughtMacroErrorWithNodeError(exc=e, node=self.macro)
+        except CompilationError as e:
             e.stack.append(self.macro)
             raise e
 
@@ -301,13 +310,13 @@ class MacroGenerator(BaseMacroGenerator):
     @contextmanager
     def track_call(self):
         # This is only called from __call__
-        if self.stack is None or self.node is None:
+        if self.stack is None:
             yield
         else:
             unique_id = self.macro.unique_id
             depth = self.stack.depth
-            # only mark depth=0 as a dependency
-            if depth == 0:
+            # only mark depth=0 as a dependency, when creating this dependency we don't pass in stack
+            if depth == 0 and self.node:
                 self.node.depends_on.add_macro(unique_id)
             self.stack.push(unique_id)
             try:
@@ -364,8 +373,19 @@ class MaterializationExtension(jinja2.ext.Extension):
                 value = parser.parse_expression()
                 adapter_name = value.value
 
+            elif target.name == "supported_languages":
+                target.set_ctx("param")
+                node.args.append(target)
+                parser.stream.expect("assign")
+                languages = parser.parse_expression()
+                node.defaults.append(languages)
+
             else:
-                invalid_materialization_argument(materialization_name, target.name)
+                raise MaterializationArgError(materialization_name, target.name)
+
+        if SUPPORTED_LANG_ARG not in node.args:
+            node.args.append(SUPPORTED_LANG_ARG)
+            node.defaults.append(jinja2.nodes.List([jinja2.nodes.Const("sql")]))
 
         node.name = get_materialization_macro_name(materialization_name, adapter_name)
 
@@ -436,7 +456,7 @@ def create_undefined(node=None):
             return self
 
         def __reduce__(self):
-            raise_compiler_error(f"{self.name} is undefined", node=node)
+            raise UndefinedCompilationError(name=self.name, node=node)
 
     return Undefined
 
@@ -463,7 +483,7 @@ 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", "jinja2.ext.loopcontrols"]
     }
 
     if capture_macros:
@@ -494,10 +514,10 @@ def catch_jinja(node=None) -> Iterator[None]:
         yield
     except jinja2.exceptions.TemplateSyntaxError as e:
         e.translated = False
-        raise CompilationException(str(e), node) from e
+        raise CompilationError(str(e), node) from e
     except jinja2.exceptions.UndefinedError as e:
-        raise UndefinedMacroException(str(e), node) from e
-    except CompilationException as exc:
+        raise UndefinedMacroError(str(e), node) from e
+    except CompilationError as exc:
         exc.add_node(node)
         raise
 
@@ -580,7 +600,7 @@ 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.
@@ -604,7 +624,7 @@ GENERIC_TEST_KWARGS_NAME = "_dbt_generic_test_kwargs"
 
 def add_rendered_test_kwargs(
     context: Dict[str, Any],
-    node: Union[ParsedGenericTestNode, CompiledGenericTestNode],
+    node: GenericTestNode,
     capture_macros: bool = False,
 ) -> None:
     """Render each of the test kwargs in the given context using the native
@@ -632,3 +652,21 @@ def add_rendered_test_kwargs(
     # when the test node was created in _parse_generic_test.
     kwargs = deep_map_render(_convert_function, node.test_metadata.kwargs)
     context[GENERIC_TEST_KWARGS_NAME] = kwargs
+
+
+def get_supported_languages(node: jinja2.nodes.Macro) -> List[ModelLanguage]:
+    if "materialization" not in node.name:
+        raise MaterializtionMacroNotUsedError(node=node)
+
+    no_kwargs = not node.defaults
+    no_langs_found = SUPPORTED_LANG_ARG not in node.args
+
+    if no_kwargs or no_langs_found:
+        raise NoSupportedLanguagesFoundError(node=node)
+
+    lang_idx = node.args.index(SUPPORTED_LANG_ARG)
+    # indexing defaults from the end
+    # since supported_languages is a kwarg, and kwargs are at always after args
+    return [
+        ModelLanguage[item.value] for item in node.defaults[-(len(node.args) - lang_idx)].items
+    ]

core/dbt/clients/jinja_static.py

@@ -1,6 +1,6 @@
 import jinja2
 from dbt.clients.jinja import get_environment
-from dbt.exceptions import raise_compiler_error
+from dbt.exceptions import MacroNamespaceNotStringError, MacroNameNotStringError
 
 
 def statically_extract_macro_calls(string, ctx, db_wrapper=None):
@@ -15,7 +15,7 @@ def statically_extract_macro_calls(string, ctx, db_wrapper=None):
         if hasattr(func_call, "node") and hasattr(func_call.node, "name"):
             func_name = func_call.node.name
         else:
-            # func_call for dbt_utils.current_timestamp macro
+            # func_call for dbt.current_timestamp macro
             # Call(
             #   node=Getattr(
             #     node=Name(
@@ -117,20 +117,14 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
                     func_name = kwarg.value.value
                     possible_macro_calls.append(func_name)
                 else:
-                    raise_compiler_error(
-                        f"The macro_name parameter ({kwarg.value.value}) "
-                        "to adapter.dispatch was not a string"
-                    )
+                    raise MacroNameNotStringError(kwarg_value=kwarg.value.value)
             elif kwarg.key == "macro_namespace":
                 # This will remain to enable static resolution
                 kwarg_type = type(kwarg.value).__name__
                 if kwarg_type == "Const":
                     macro_namespace = kwarg.value.value
                 else:
-                    raise_compiler_error(
-                        "The macro_namespace parameter to adapter.dispatch "
-                        f"is a {kwarg_type}, not a string"
-                    )
+                    raise MacroNamespaceNotStringError(kwarg_type)
 
     # positional arguments
     if packages_arg:

core/dbt/clients/registry.py

@@ -1,9 +1,20 @@
 import functools
+from typing import Any, Dict, List
 import requests
 from dbt.events.functions import fire_event
-from dbt.events.types import RegistryProgressMakingGETRequest, RegistryProgressGETResponse
+from dbt.events.types import (
+    RegistryProgressGETRequest,
+    RegistryProgressGETResponse,
+    RegistryIndexProgressGETRequest,
+    RegistryIndexProgressGETResponse,
+    RegistryResponseUnexpectedType,
+    RegistryResponseMissingTopKeys,
+    RegistryResponseMissingNestedKeys,
+    RegistryResponseExtraNestedKeys,
+)
 from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
 from dbt import deprecations
+from dbt import semver
 import os
 
 if os.getenv("DBT_PACKAGE_HUB_URL"):
@@ -12,55 +23,86 @@ else:
     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)
 
 
-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)
-    fire_event(RegistryProgressMakingGETRequest(url=url))
+def _get(package_name, registry_base_url=None):
+    url = _get_url(package_name, registry_base_url)
+    fire_event(RegistryProgressGETRequest(url=url))
+    # all exceptions from requests get caught in the retry logic so no need to wrap this here
     resp = requests.get(url, timeout=30)
     fire_event(RegistryProgressGETResponse(url=url, resp_code=resp.status_code))
     resp.raise_for_status()
 
-    # It is unexpected for the content of the response to be None so if it is, raising this error
-    # will cause this function to retry (if called within _get_with_retries) and hopefully get
-    # a response.  This seems to happen when there's an issue with the Hub.
+    # 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
-    if resp.json() is None:
-        raise requests.exceptions.ContentDecodingError(
-            "Request error: The response is None", response=resp
+    # 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)
+
+    # 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)
+
+    # all version responses should contain identical keys.
+    has_extra_keys = set().difference(*(response["versions"][d] for d in response["versions"]))
+    if has_extra_keys:
+        error_msg = (
+            "Request error: Keys for all versions do not match.  Found extra key(s) "
+            f"of {has_extra_keys}."
+        )
+        fire_event(RegistryResponseExtraNestedKeys(response=response))
+        raise requests.exceptions.ContentDecodingError(error_msg, response=resp)
+
+    return response
 
 
-def index(registry_base_url=None):
-    return _get_with_retries("api/v1/index.json", registry_base_url)
+_get_cached = memoized(_get_with_retries)
 
 
-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)
-
+def package(package_name, registry_base_url=None) -> Dict[str, Any]:
+    # returns a dictionary of metadata for all versions of a package
+    response = _get_cached(package_name, registry_base_url)
     # Either redirectnamespace or redirectname in the JSON response indicate a redirect
     # redirectnamespace redirects based on package ownership
     # redirectname redirects based on package name
     # Both can be present at the same time, or neither. Fails gracefully to old name
-
     if ("redirectnamespace" in response) or ("redirectname" in response):
 
         if ("redirectnamespace" in response) and response["redirectnamespace"] is not None:
@@ -74,15 +116,76 @@ def package(name, registry_base_url=None):
             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["versions"]
+
+
+def package_version(package_name, version, registry_base_url=None) -> Dict[str, Any]:
+    # returns the metadata of a specific version of a package
+    response = package(package_name, registry_base_url)
+    return response[version]
+
+
+def is_compatible_version(package_spec, dbt_version) -> bool:
+    require_dbt_version = package_spec.get("require_dbt_version")
+    if not require_dbt_version:
+        # if version requirements are missing or empty, assume any version is compatible
+        return True
+    else:
+        # determine whether dbt_version satisfies this package's require-dbt-version config
+        if not isinstance(require_dbt_version, list):
+            require_dbt_version = [require_dbt_version]
+        supported_versions = [
+            semver.VersionSpecifier.from_version_string(v) for v in require_dbt_version
+        ]
+        return semver.versions_compatible(dbt_version, *supported_versions)
+
+
+def get_compatible_versions(package_name, dbt_version, should_version_check) -> List["str"]:
+    # returns a list of all available versions of a package
+    response = package(package_name)
+
+    # if the user doesn't care about installing compatible versions, just return them all
+    if not should_version_check:
+        return list(response)
+
+    # otherwise, only return versions that are compatible with the installed version of dbt-core
+    else:
+        compatible_versions = [
+            pkg_version
+            for pkg_version, info in response.items()
+            if is_compatible_version(info, dbt_version)
+        ]
+        return compatible_versions
+
+
+def _get_index(registry_base_url=None):
+
+    url = _get_url("index", registry_base_url)
+    fire_event(RegistryIndexProgressGETRequest(url=url))
+    # all exceptions from requests get caught in the retry logic so no need to wrap this here
+    resp = requests.get(url, timeout=30)
+    fire_event(RegistryIndexProgressGETResponse(url=url, resp_code=resp.status_code))
+    resp.raise_for_status()
+
+    # The response should be a list.  Anything else is unexpected, raise an error.
+    # Raising this error will cause this function to retry and hopefully get a valid response.
+
+    response = resp.json()
+
+    if not isinstance(response, list):  # This will also catch Nonetype
+        error_msg = (
+            f"Request error: The response type of {type(response)} is not valid: {resp.text}"
+        )
+        raise requests.exceptions.ContentDecodingError(error_msg, response=resp)
 
     return response
 
 
-def package_version(name, version, registry_base_url=None):
-    return _get_with_retries("api/v1/{}/{}.json".format(name, version), registry_base_url)
+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)
 
 
-def get_available_versions(name):
-    response = package(name)
-    return list(response["versions"])
+index_cached = memoized(index)

core/dbt/clients/system.py

@@ -1,29 +1,31 @@
 import errno
-import functools
 import fnmatch
+import functools
 import json
 import os
 import os.path
 import re
 import shutil
+import stat
 import subprocess
 import sys
 import tarfile
-import requests
-import stat
-from typing import Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
+from pathlib import Path
+from typing import Any, Callable, Dict, List, NoReturn, Optional, Tuple, Type, Union
 
+import dbt.exceptions
+import requests
 from dbt.events.functions import fire_event
 from dbt.events.types import (
-    SystemErrorRetrievingModTime,
     SystemCouldNotWrite,
     SystemExecutingCmd,
-    SystemStdOutMsg,
-    SystemStdErrMsg,
+    SystemStdOut,
+    SystemStdErr,
     SystemReportReturnCode,
 )
-import dbt.exceptions
+from dbt.exceptions import DbtInternalError
 from dbt.utils import _connection_exception_retry as connection_exception_retry
+from pathspec import PathSpec  # type: ignore
 
 if sys.platform == "win32":
     from ctypes import WinDLL, c_bool
@@ -36,6 +38,7 @@ def find_matching(
     root_path: str,
     relative_paths_to_search: List[str],
     file_pattern: str,
+    ignore_spec: Optional[PathSpec] = None,
 ) -> List[Dict[str, Any]]:
     """
     Given an absolute `root_path`, a list of relative paths to that
@@ -57,19 +60,26 @@ def find_matching(
     reobj = re.compile(regex, re.IGNORECASE)
 
     for relative_path_to_search in relative_paths_to_search:
+        # potential speedup for ignore_spec
+        # if ignore_spec.matches(relative_path_to_search):
+        #     continue
         absolute_path_to_search = os.path.join(root_path, relative_path_to_search)
         walk_results = os.walk(absolute_path_to_search)
 
         for current_path, subdirectories, local_files in walk_results:
+            # potential speedup for ignore_spec
+            # relative_dir = os.path.relpath(current_path, root_path) + os.sep
+            # if ignore_spec.match(relative_dir):
+            #     continue
             for local_file in local_files:
                 absolute_path = os.path.join(current_path, local_file)
                 relative_path = os.path.relpath(absolute_path, absolute_path_to_search)
-                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):
+                relative_path_to_root = os.path.join(relative_path_to_search, relative_path)
+
+                modification_time = os.path.getmtime(absolute_path)
+                if reobj.match(local_file) and (
+                    not ignore_spec or not ignore_spec.match_file(relative_path_to_root)
+                ):
                     matching.append(
                         {
                             "searched_path": relative_path_to_search,
@@ -93,12 +103,18 @@ def load_file_contents(path: str, strip: bool = True) -> str:
     return to_return
 
 
-def make_directory(path: str) -> None:
+@functools.singledispatch
+def make_directory(path=None) -> None:
     """
     Make a directory and any intermediate directories that don't already
     exist. This function handles the case where two threads try to create
     a directory at once.
     """
+    raise DbtInternalError(f"Can not create directory from {type(path)} ")
+
+
+@make_directory.register
+def _(path: str) -> None:
     path = convert_path(path)
     if not os.path.exists(path):
         # concurrent writes that try to create the same dir can fail
@@ -112,6 +128,11 @@ def make_directory(path: str) -> None:
                 raise e
 
 
+@make_directory.register
+def _(path: Path) -> None:
+    path.mkdir(parents=True, exist_ok=True)
+
+
 def make_file(path: str, contents: str = "", overwrite: bool = False) -> bool:
     """
     Make a file at `path` assuming that the directory it resides in already
@@ -131,7 +152,8 @@ def make_symlink(source: str, link_path: str) -> None:
     Create a symlink at `link_path` referring to `source`.
     """
     if not supports_symlinks():
-        dbt.exceptions.system_error("create a symbolic link")
+        # TODO: why not import these at top?
+        raise dbt.exceptions.SymbolicLinkError()
 
     os.symlink(source, link_path)
 
@@ -164,7 +186,7 @@ def write_file(path: str, contents: str = "") -> bool:
                 reason = "Path was possibly too long"
             # all our hard work and the path was still too long. Log and
             # continue.
-            fire_event(SystemCouldNotWrite(path=path, reason=reason, exc=exc))
+            fire_event(SystemCouldNotWrite(path=path, reason=reason, exc=str(exc)))
         else:
             raise
     return True
@@ -189,7 +211,7 @@ def _windows_rmdir_readonly(func: Callable[[str], Any], path: str, exc: Tuple[An
 
 def resolve_path_from_base(path_to_resolve: str, base_path: str) -> str:
     """
-    If path-to_resolve is a relative path, create an absolute path
+    If path_to_resolve is a relative path, create an absolute path
     with base_path as the base.
 
     If path_to_resolve is an absolute path or a user path (~), just
@@ -246,16 +268,17 @@ def _supports_long_paths() -> bool:
     # https://stackoverflow.com/a/35097999/11262881
     # I don't know exaclty what he means, but I am inclined to believe him as
     # he's pretty active on Python windows bugs!
-    try:
-        dll = WinDLL("ntdll")
-    except OSError:  # I don't think this happens? you need ntdll to run python
-        return False
-    # not all windows versions have it at all
-    if not hasattr(dll, "RtlAreLongPathsEnabled"):
-        return False
-    # tell windows we want to get back a single unsigned byte (a bool).
-    dll.RtlAreLongPathsEnabled.restype = c_bool
-    return dll.RtlAreLongPathsEnabled()
+    else:
+        try:
+            dll = WinDLL("ntdll")
+        except OSError:  # I don't think this happens? you need ntdll to run python
+            return False
+        # not all windows versions have it at all
+        if not hasattr(dll, "RtlAreLongPathsEnabled"):
+            return False
+        # tell windows we want to get back a single unsigned byte (a bool).
+        dll.RtlAreLongPathsEnabled.restype = c_bool
+        return dll.RtlAreLongPathsEnabled()
 
 
 def convert_path(path: str) -> str:
@@ -335,7 +358,7 @@ def _handle_posix_cmd_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
 
 
 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
@@ -386,7 +409,7 @@ def _handle_windows_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
 
 
 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)
 
@@ -397,7 +420,7 @@ def _interpret_oserror(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
         _handle_posix_error(exc, cwd, cmd)
 
     # this should not be reachable, raise _something_ at least!
-    raise dbt.exceptions.InternalException(
+    raise dbt.exceptions.DbtInternalError(
         "Unhandled exception in _interpret_oserror: {}".format(exc)
     )
 
@@ -426,8 +449,8 @@ def run_cmd(cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None) -> T
     except OSError as exc:
         _interpret_oserror(exc, cwd, cmd)
 
-    fire_event(SystemStdOutMsg(bmsg=out))
-    fire_event(SystemStdErrMsg(bmsg=err))
+    fire_event(SystemStdOut(bmsg=str(out)))
+    fire_event(SystemStdErr(bmsg=str(err)))
 
     if proc.returncode != 0:
         fire_event(SystemReportReturnCode(returncode=proc.returncode))
@@ -443,7 +466,11 @@ 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[float, float], Tuple[float, None]]] = None,
+) -> None:
     path = convert_path(path)
     connection_timeout = timeout or float(os.getenv("DBT_HTTP_TIMEOUT", 10))
     response = requests.get(url, timeout=connection_timeout)
@@ -501,7 +528,7 @@ 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)
@@ -536,7 +563,7 @@ 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

@@ -51,7 +51,7 @@ def safe_load(contents) -> Optional[Dict[str, Any]]:
     return yaml.load(contents, Loader=SafeLoader)
 
 
-def load_yaml_text(contents):
+def load_yaml_text(contents, path=None):
     try:
         return safe_load(contents)
     except (yaml.scanner.ScannerError, yaml.YAMLError) as e:
@@ -60,4 +60,4 @@ def load_yaml_text(contents):
         else:
             error = str(e)
 
-        raise dbt.exceptions.ValidationException(error)
+        raise dbt.exceptions.DbtValidationError(error)

core/dbt/compilation.py

@@ -1,49 +1,43 @@
-import os
-from collections import defaultdict
-from typing import List, Dict, Any, Tuple, cast, Optional
-
+import argparse
 import networkx as nx  # type: ignore
+import os
 import pickle
 import sqlparse
 
-from dbt import flags
+from collections import defaultdict
+from typing import List, Dict, Any, Tuple, Optional
+
+from dbt.flags import get_flags
 from dbt.adapters.factory import get_adapter
 from dbt.clients import jinja
 from dbt.clients.system import make_directory
 from dbt.context.providers import generate_runtime_model_context
 from dbt.contracts.graph.manifest import Manifest, UniqueID
-from dbt.contracts.graph.compiled import (
-    COMPILED_TYPES,
-    CompiledGenericTestNode,
+from dbt.contracts.graph.nodes import (
+    ManifestNode,
+    ManifestSQLNode,
+    GenericTestNode,
     GraphMemberNode,
     InjectedCTE,
-    ManifestNode,
-    NonSourceCompiledNode,
+    SeedNode,
 )
-from dbt.contracts.graph.parsed import ParsedNode
 from dbt.exceptions import (
-    dependency_not_found,
-    InternalException,
-    RuntimeException,
+    GraphDependencyNotFoundError,
+    DbtInternalError,
+    DbtRuntimeError,
 )
 from dbt.graph import Graph
 from dbt.events.functions import fire_event
-from dbt.events.types import FoundStats, CompilingNode, WritingInjectedSQLForNode
-from dbt.node_types import NodeType
+from dbt.events.types import FoundStats, WritingInjectedSQLForNode
+from dbt.events.contextvars import get_node_info
+from dbt.node_types import NodeType, ModelLanguage
 from dbt.events.format import pluralize
 import dbt.tracking
+import dbt.task.list as list_task
 
 graph_file_name = "graph.gpickle"
 
 
-def _compiled_type_for(model: ParsedNode):
-    if type(model) not in COMPILED_TYPES:
-        raise InternalException(
-            f"Asked to compile {type(model)} node, but it has no compiled form"
-        )
-    return COMPILED_TYPES[type(model)]
-
-
 def print_compile_stats(stats):
     names = {
         NodeType.Model: "model",
@@ -56,6 +50,7 @@ def print_compile_stats(stats):
         NodeType.Source: "source",
         NodeType.Exposure: "exposure",
         NodeType.Metric: "metric",
+        NodeType.Group: "group",
     }
 
     results = {k: 0 for k in names.keys()}
@@ -93,15 +88,18 @@ def _generate_stats(manifest: Manifest):
         stats[metric.resource_type] += 1
     for macro in manifest.macros.values():
         stats[macro.resource_type] += 1
+    for group in manifest.groups.values():
+        stats[group.resource_type] += 1
     return stats
 
 
 def _add_prepended_cte(prepended_ctes, new_cte):
     for cte in prepended_ctes:
-        if cte.id == new_cte.id:
+        if cte.id == new_cte.id and new_cte.sql:
             cte.sql = new_cte.sql
             return
-    prepended_ctes.append(new_cte)
+    if new_cte.sql:
+        prepended_ctes.append(new_cte)
 
 
 def _extend_prepended_ctes(prepended_ctes, new_prepended_ctes):
@@ -169,21 +167,22 @@ class Compiler:
         self.config = config
 
     def initialize(self):
-        make_directory(self.config.target_path)
+        make_directory(self.config.project_target_path)
         make_directory(self.config.packages_install_path)
 
     # creates a ModelContext which is converted to
     # a dict for jinja rendering of SQL
     def _create_node_context(
         self,
-        node: NonSourceCompiledNode,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Dict[str, Any],
     ) -> Dict[str, Any]:
 
         context = generate_runtime_model_context(node, self.config, manifest)
         context.update(extra_context)
-        if isinstance(node, CompiledGenericTestNode):
+
+        if isinstance(node, GenericTestNode):
             # for test nodes, add a special keyword args value to the context
             jinja.add_rendered_test_kwargs(context, node)
 
@@ -194,14 +193,6 @@ class Compiler:
         relation_cls = adapter.Relation
         return relation_cls.add_ephemeral_prefix(name)
 
-    def _get_relation_name(self, node: ParsedNode):
-        relation_name = None
-        if node.is_relational and not node.is_ephemeral_model:
-            adapter = get_adapter(self.config)
-            relation_cls = adapter.Relation
-            relation_name = str(relation_cls.create_from(self.config, node))
-        return relation_name
-
     def _inject_ctes_into_sql(self, sql: str, ctes: List[InjectedCTE]) -> str:
         """
         `ctes` is a list of InjectedCTEs like:
@@ -260,10 +251,10 @@ class Compiler:
 
     def _recursively_prepend_ctes(
         self,
-        model: NonSourceCompiledNode,
+        model: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]],
-    ) -> Tuple[NonSourceCompiledNode, List[InjectedCTE]]:
+    ) -> Tuple[ManifestSQLNode, List[InjectedCTE]]:
         """This method is called by the 'compile_node' method. Starting
         from the node that it is passed in, it will recursively call
         itself using the 'extra_ctes'.  The 'ephemeral' models do
@@ -271,16 +262,19 @@ class Compiler:
         are rolled up into the models that refer to them by
         inserting CTEs into the SQL.
         """
-        if model.compiled_sql is None:
-            raise RuntimeException("Cannot inject ctes into an unparsed node", model)
+        if model.compiled_code is None:
+            raise DbtRuntimeError("Cannot inject ctes into an uncompiled node", model)
+
+        # extra_ctes_injected flag says that we've already recursively injected the ctes
         if model.extra_ctes_injected:
             return (model, model.extra_ctes)
 
         # Just to make it plain that nothing is actually injected for this case
-        if not model.extra_ctes:
-            model.extra_ctes_injected = True
-            manifest.update_node(model)
-            return (model, model.extra_ctes)
+        if len(model.extra_ctes) == 0:
+            # SeedNodes don't have compilation attributes
+            if not isinstance(model, SeedNode):
+                model.extra_ctes_injected = True
+            return (model, [])
 
         # This stores the ctes which will all be recursively
         # gathered and then "injected" into the model.
@@ -289,103 +283,112 @@ class Compiler:
         # extra_ctes are added to the model by
         # RuntimeRefResolver.create_relation, which adds an
         # extra_cte for every model relation which is an
-        # ephemeral model.
+        # ephemeral model. InjectedCTEs have a unique_id and sql.
+        # extra_ctes start out with sql set to None, and the sql is set in this loop.
         for cte in model.extra_ctes:
             if cte.id not in manifest.nodes:
-                raise InternalException(
+                raise DbtInternalError(
                     f"During compilation, found a cte reference that "
                     f"could not be resolved: {cte.id}"
                 )
             cte_model = manifest.nodes[cte.id]
+            assert not isinstance(cte_model, SeedNode)
 
             if not cte_model.is_ephemeral_model:
-                raise InternalException(f"{cte.id} is not ephemeral")
+                raise DbtInternalError(f"{cte.id} is not ephemeral")
 
-            # This model has already been compiled, so it's been
-            # through here before
-            if getattr(cte_model, "compiled", False):
-                assert isinstance(cte_model, tuple(COMPILED_TYPES.values()))
-                cte_model = cast(NonSourceCompiledNode, cte_model)
+            # This model has already been compiled and extra_ctes_injected, so it's been
+            # through here before. We already checked above for extra_ctes_injected, but
+            # checking again because updates maybe have happened in another thread.
+            if cte_model.compiled is True and cte_model.extra_ctes_injected is True:
                 new_prepended_ctes = cte_model.extra_ctes
 
             # if the cte_model isn't compiled, i.e. first time here
             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)
-                # recursively call this method
+                # Render the raw_code and set compiled to True
+                cte_model = self._compile_code(cte_model, manifest, extra_context)
+                # recursively call this method, sets extra_ctes_injected to True
                 cte_model, new_prepended_ctes = self._recursively_prepend_ctes(
                     cte_model, manifest, extra_context
                 )
-                # Save compiled SQL file and sync manifest
+                # Write compiled SQL file
                 self._write_node(cte_model)
-                manifest.sync_update_node(cte_model)
 
             _extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
 
             new_cte_name = self.add_ephemeral_prefix(cte_model.name)
-            rendered_sql = cte_model._pre_injected_sql or cte_model.compiled_sql
+            rendered_sql = cte_model._pre_injected_sql or cte_model.compiled_code
             sql = f" {new_cte_name} as (\n{rendered_sql}\n)"
 
             _add_prepended_cte(prepended_ctes, InjectedCTE(id=cte.id, sql=sql))
 
-        injected_sql = self._inject_ctes_into_sql(
-            model.compiled_sql,
-            prepended_ctes,
-        )
-        model._pre_injected_sql = model.compiled_sql
-        model.compiled_sql = injected_sql
-        model.extra_ctes_injected = True
-        model.extra_ctes = prepended_ctes
-        model.validate(model.to_dict(omit_none=True))
+        # Check again before updating for multi-threading
+        if not model.extra_ctes_injected:
+            injected_sql = self._inject_ctes_into_sql(
+                model.compiled_code,
+                prepended_ctes,
+            )
+            model.extra_ctes_injected = True
+            model._pre_injected_sql = model.compiled_code
+            model.compiled_code = injected_sql
+            model.extra_ctes = prepended_ctes
 
-        manifest.update_node(model)
+        # if model.extra_ctes is not set to prepended ctes, something went wrong
+        return model, model.extra_ctes
 
-        return model, prepended_ctes
-
-    # creates a compiled_node from the ManifestNode passed in,
+    # Sets compiled_code and compiled flag in the ManifestSQLNode passed in,
     # creates a "context" dictionary for jinja rendering,
-    # and then renders the "compiled_sql" using the node, the
-    # raw_sql and the context.
-    def _compile_node(
+    # and then renders the "compiled_code" using the node, the
+    # raw_code and the context.
+    def _compile_code(
         self,
-        node: ManifestNode,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestSQLNode:
         if extra_context is None:
             extra_context = {}
 
-        fire_event(CompilingNode(unique_id=node.unique_id))
+        if node.language == ModelLanguage.python:
+            context = self._create_node_context(node, manifest, extra_context)
 
-        data = node.to_dict(omit_none=True)
-        data.update(
-            {
-                "compiled": False,
-                "compiled_sql": None,
-                "extra_ctes_injected": False,
-                "extra_ctes": [],
-            }
-        )
-        compiled_node = _compiled_type_for(node).from_dict(data)
+            postfix = jinja.get_rendered(
+                "{{ py_script_postfix(model) }}",
+                context,
+                node,
+            )
+            # we should NOT jinja render the python model's 'raw code'
+            node.compiled_code = f"{node.raw_code}\n\n{postfix}"
 
-        context = self._create_node_context(compiled_node, manifest, extra_context)
+        else:
+            context = self._create_node_context(node, manifest, extra_context)
+            node.compiled_code = jinja.get_rendered(
+                node.raw_code,
+                context,
+                node,
+            )
 
-        compiled_node.compiled_sql = jinja.get_rendered(
-            node.raw_sql,
-            context,
-            node,
-        )
+        node.compiled = True
 
-        compiled_node.relation_name = self._get_relation_name(node)
+        # relation_name is set at parse time, except for tests without store_failures,
+        # but cli param can turn on store_failures, so we set here.
+        if (
+            node.resource_type == NodeType.Test
+            and node.relation_name is None
+            and node.is_relational
+        ):
+            adapter = get_adapter(self.config)
+            relation_cls = adapter.Relation
+            relation_name = str(relation_cls.create_from(self.config, node))
+            node.relation_name = relation_name
 
-        compiled_node.compiled = True
-
-        return compiled_node
+        return node
 
     def write_graph_file(self, linker: Linker, manifest: Manifest):
         filename = graph_file_name
-        graph_path = os.path.join(self.config.target_path, filename)
+        graph_path = os.path.join(self.config.project_target_path, filename)
+        flags = get_flags()
         if flags.WRITE_JSON:
             linker.write_graph(graph_path, manifest)
 
@@ -397,8 +400,10 @@ class Compiler:
                 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))
+            elif dependency in manifest.metrics:
+                linker.dependency(node.unique_id, (manifest.metrics[dependency].unique_id))
             else:
-                dependency_not_found(node, dependency)
+                raise GraphDependencyNotFoundError(node, dependency)
 
     def link_graph(self, linker: Linker, manifest: Manifest, add_test_edges: bool = False):
         for source in manifest.sources.values():
@@ -481,36 +486,50 @@ class Compiler:
 
         if write:
             self.write_graph_file(linker, manifest)
-        print_compile_stats(stats)
+
+        # Do not print these for ListTask's
+        if not (
+            self.config.args.__class__ == argparse.Namespace
+            and self.config.args.cls == list_task.ListTask
+        ):
+            print_compile_stats(stats)
 
         return Graph(linker.graph)
 
-    # writes the "compiled_sql" into the target/compiled directory
-    def _write_node(self, node: NonSourceCompiledNode) -> ManifestNode:
-        if not node.extra_ctes_injected or node.resource_type == NodeType.Snapshot:
+    # writes the "compiled_code" into the target/compiled directory
+    def _write_node(self, node: ManifestSQLNode) -> ManifestSQLNode:
+        if not node.extra_ctes_injected or node.resource_type in (
+            NodeType.Snapshot,
+            NodeType.Seed,
+        ):
             return node
-        fire_event(WritingInjectedSQLForNode(unique_id=node.unique_id))
+        fire_event(WritingInjectedSQLForNode(node_info=get_node_info()))
 
-        if node.compiled_sql:
-            node.compiled_path = node.write_node(
-                self.config.target_path, "compiled", node.compiled_sql
-            )
+        if node.compiled_code:
+            node.compiled_path = node.get_target_write_path(self.config.target_path, "compiled")
+            node.write_node(self.config.project_root, node.compiled_path, node.compiled_code)
         return node
 
     def compile_node(
         self,
-        node: ManifestNode,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
         write: bool = True,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestSQLNode:
         """This is the main entry point into this code. It's called by
         CompileRunner.compile, GenericRPCRunner.compile, and
-        RunTask.get_hook_sql. It calls '_compile_node' to convert
-        the node into a compiled node, and then calls the
+        RunTask.get_hook_sql. It calls '_compile_code' to render
+        the node's raw_code into compiled_code, and then calls the
         recursive method to "prepend" the ctes.
         """
-        node = self._compile_node(node, manifest, extra_context)
+        # Make sure Lexer for sqlparse 0.4.4 is initialized
+        from sqlparse.lexer import Lexer  # type: ignore
+
+        if hasattr(Lexer, "get_default_instance"):
+            Lexer.get_default_instance()
+
+        node = self._compile_code(node, manifest, extra_context)
 
         node, _ = self._recursively_prepend_ctes(node, manifest, extra_context)
         if write:

core/dbt/config/__init__.py

@@ -1,4 +1,4 @@
 # all these are just exports, they need "noqa" so flake8 will not complain.
 from .profile import Profile, read_user_config  # noqa
-from .project import Project, IsFQNResource  # noqa
-from .runtime import RuntimeConfig, UnsetProfileConfig  # noqa
+from .project import Project, IsFQNResource, PartialProject  # noqa
+from .runtime import RuntimeConfig  # noqa

core/dbt/config/profile.py

@@ -4,17 +4,19 @@ import os
 
 from dbt.dataclass_schema import ValidationError
 
-from dbt import flags
+from dbt.flags import get_flags
 from dbt.clients.system import load_file_contents
 from dbt.clients.yaml_helper import load_yaml_text
 from dbt.contracts.connection import Credentials, HasCredentials
 from dbt.contracts.project import ProfileConfig, UserConfig
-from dbt.exceptions import CompilationException
-from dbt.exceptions import DbtProfileError
-from dbt.exceptions import DbtProjectError
-from dbt.exceptions import ValidationException
-from dbt.exceptions import RuntimeException
-from dbt.exceptions import validator_error_message
+from dbt.exceptions import (
+    CompilationError,
+    DbtProfileError,
+    DbtProjectError,
+    DbtValidationError,
+    DbtRuntimeError,
+    ProfileConfigError,
+)
 from dbt.events.types import MissingProfileTarget
 from dbt.events.functions import fire_event
 from dbt.utils import coerce_dict_str
@@ -23,8 +25,6 @@ from .renderer import ProfileRenderer
 
 DEFAULT_THREADS = 1
 
-DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser("~"), ".dbt")
-
 INVALID_PROFILE_MESSAGE = """
 dbt encountered an error while trying to read your profiles.yml file.
 
@@ -32,22 +32,6 @@ dbt encountered an error while trying to read your profiles.yml file.
 """
 
 
-NO_SUPPLIED_PROFILE_ERROR = """\
-dbt cannot run because no profile was specified for this dbt project.
-To specify a profile for this project, add a line like the this to
-your dbt_project.yml file:
-
-profile: [profile name]
-
-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
-)
-
-
 def read_profile(profiles_dir: str) -> Dict[str, Any]:
     path = os.path.join(profiles_dir, "profiles.yml")
 
@@ -60,9 +44,9 @@ def read_profile(profiles_dir: str) -> Dict[str, Any]:
                 msg = f"The profiles.yml file at {path} is empty"
                 raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
             return yaml_content
-        except ValidationException as e:
+        except DbtValidationError as e:
             msg = INVALID_PROFILE_MESSAGE.format(error_string=e)
-            raise ValidationException(msg) from e
+            raise DbtValidationError(msg) from e
 
     return {}
 
@@ -75,7 +59,7 @@ def read_user_config(directory: str) -> UserConfig:
             if user_config is not None:
                 UserConfig.validate(user_config)
                 return UserConfig.from_dict(user_config)
-    except (RuntimeException, ValidationError):
+    except (DbtRuntimeError, ValidationError):
         pass
     return UserConfig()
 
@@ -158,7 +142,7 @@ class Profile(HasCredentials):
             dct = self.to_profile_info(serialize_credentials=True)
             ProfileConfig.validate(dct)
         except ValidationError as exc:
-            raise DbtProfileError(validator_error_message(exc)) from exc
+            raise ProfileConfigError(exc) from exc
 
     @staticmethod
     def _credentials_from_profile(
@@ -182,8 +166,8 @@ class Profile(HasCredentials):
             data = cls.translate_aliases(profile)
             cls.validate(data)
             credentials = cls.from_dict(data)
-        except (RuntimeException, ValidationError) as e:
-            msg = str(e) if isinstance(e, RuntimeException) else e.message
+        except (DbtRuntimeError, ValidationError) as e:
+            msg = str(e) if isinstance(e, DbtRuntimeError) else e.message
             raise DbtProfileError(
                 'Credentials in profile "{}", target "{}" invalid: {}'.format(
                     profile_name, target_name, msg
@@ -197,10 +181,33 @@ class Profile(HasCredentials):
         args_profile_name: Optional[str],
         project_profile_name: Optional[str] = None,
     ) -> str:
+        # TODO: Duplicating this method as direct copy of the implementation in dbt.cli.resolvers
+        # dbt.cli.resolvers implementation can't be used because it causes a circular dependency.
+        # This should be removed and use a safe default access on the Flags module when
+        # https://github.com/dbt-labs/dbt-core/issues/6259 is closed.
+        def default_profiles_dir():
+            from pathlib import Path
+
+            return Path.cwd() if (Path.cwd() / "profiles.yml").exists() else Path.home() / ".dbt"
+
         profile_name = project_profile_name
         if args_profile_name is not None:
             profile_name = args_profile_name
         if profile_name is None:
+            NO_SUPPLIED_PROFILE_ERROR = """\
+dbt cannot run because no profile was specified for this dbt project.
+To specify a profile for this project, add a line like the this to
+your dbt_project.yml file:
+
+profile: [profile name]
+
+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()
+            )
             raise DbtProjectError(NO_SUPPLIED_PROFILE_ERROR)
         return profile_name
 
@@ -299,7 +306,7 @@ class Profile(HasCredentials):
 
         try:
             profile_data = renderer.render_data(raw_profile_data)
-        except CompilationException as exc:
+        except CompilationError as exc:
             raise DbtProfileError(str(exc)) from exc
         return target_name, profile_data
 
@@ -401,11 +408,13 @@ class Profile(HasCredentials):
         )
 
     @classmethod
-    def render_from_args(
+    def render(
         cls,
-        args: Any,
         renderer: ProfileRenderer,
         project_profile_name: Optional[str],
+        profile_name_override: Optional[str] = None,
+        target_override: Optional[str] = None,
+        threads_override: Optional[int] = None,
     ) -> "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
@@ -421,10 +430,9 @@ 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)
+        flags = get_flags()
         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(profile_name_override, project_profile_name)
         return cls.from_raw_profiles(
             raw_profiles=raw_profiles,
             profile_name=profile_name,