adding entity inheritence

* Reverting back to older ubuntu image

* Updating the structured logging workflow as well

.bumpversion.cfg

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

.changes/0.0.0.md

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

.changes/unreleased/Dependency-20220923-000646.yaml

@@ -0,0 +1,7 @@
+kind: "Dependency"
+body: "Update pathspec requirement from ~=0.9.0 to >=0.9,<0.11 in /core"
+time: 2022-09-23T00:06:46.00000Z
+custom:
+  Author: dependabot[bot]
+  Issue: 4904
+  PR: 5917

.changes/unreleased/Dependency-20221007-000848.yaml

@@ -0,0 +1,7 @@
+kind: "Dependency"
+body: "Bump black from 22.8.0 to 22.10.0"
+time: 2022-10-07T00:08:48.00000Z
+custom:
+  Author: dependabot[bot]
+  Issue: 4904
+  PR: 6019

.changes/unreleased/Dependency-20221020-000753.yaml

@@ -0,0 +1,7 @@
+kind: "Dependency"
+body: "Bump mashumaro[msgpack] from 3.0.4 to 3.1.1 in /core"
+time: 2022-10-20T00:07:53.00000Z
+custom:
+  Author: dependabot[bot]
+  Issue: 4904
+  PR: 6108

.changes/unreleased/Dependency-20221026-000910.yaml

@@ -0,0 +1,7 @@
+kind: "Dependency"
+body: "Update colorama requirement from <0.4.6,>=0.3.9 to >=0.3.9,<0.4.7 in /core"
+time: 2022-10-26T00:09:10.00000Z
+custom:
+  Author: dependabot[bot]
+  Issue: 4904
+  PR: 6144

.changes/unreleased/Docs-20220908-154157.yaml

@@ -0,0 +1,7 @@
+kind: Docs
+body: minor doc correction
+time: 2022-09-08T15:41:57.689162-04:00
+custom:
+  Author: andy-clapson
+  Issue: "5791"
+  PR: "5684"

.changes/unreleased/Docs-20221007-090656.yaml

@@ -0,0 +1,7 @@
+kind: Docs
+body: Generate API docs for new CLI interface
+time: 2022-10-07T09:06:56.446078-05:00
+custom:
+  Author: stu-k
+  Issue: "5528"
+  PR: "6022"

.changes/unreleased/Docs-20221017-171411.yaml

@@ -0,0 +1,6 @@
+kind: Docs
+time: 2022-10-17T17:14:11.715348-05:00
+custom:
+  Author: paulbenschmidt
+  Issue: "5880"
+  PR: "324"

.changes/unreleased/Docs-20221116-155743.yaml

@@ -0,0 +1,7 @@
+kind: Docs
+body: Fix rendering of sample code for metrics
+time: 2022-11-16T15:57:43.204201+01:00
+custom:
+  Author: jtcohen6
+  Issue: "323"
+  PR: "346"

.changes/unreleased/Features-20220408-165459.yaml

@@ -0,0 +1,8 @@
+kind: Features
+body: Added favor-state flag to optionally favor state nodes even if unselected node
+  exists
+time: 2022-04-08T16:54:59.696564+01:00
+custom:
+  Author: daniel-murray josephberni
+  Issue: "2968"
+  PR: "5859"

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

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

.changes/unreleased/Features-20220817-154857.yaml

@@ -0,0 +1,7 @@
+kind: Features
+body: Proto logging messages
+time: 2022-08-17T15:48:57.225267-04:00
+custom:
+  Author: gshank
+  Issue: "5610"
+  PR: "5643"

.changes/unreleased/Features-20220912-125935.yaml

@@ -0,0 +1,7 @@
+kind: Features
+body: Friendlier error messages when packages.yml is malformed
+time: 2022-09-12T12:59:35.121188+01:00
+custom:
+  Author: jared-rimmer
+  Issue: "5486"
+  PR: "5812"

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

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

.changes/unreleased/Features-20220925-211651.yaml

@@ -0,0 +1,7 @@
+kind: Features
+body: Allow partitions in external tables to be supplied as a list
+time: 2022-09-25T21:16:51.051239654+02:00
+custom:
+  Author: pgoslatara
+  Issue: "5929"
+  PR: "5930"

.changes/unreleased/Features-20221003-110705.yaml

@@ -0,0 +1,7 @@
+kind: Features
+body: extend -f flag shorthand for seed command
+time: 2022-10-03T11:07:05.381632-05:00
+custom:
+  Author: dave-connors-3
+  Issue: "5990"
+  PR: "5991"

.changes/unreleased/Features-20221102-150003.yaml

@@ -0,0 +1,8 @@
+kind: Features
+body: This pulls the profile name from args when constructing a RuntimeConfig in lib.py,
+  enabling the dbt-server to override the value that's in the dbt_project.yml
+time: 2022-11-02T15:00:03.000805-05:00
+custom:
+  Author: racheldaniel
+  Issue: "6201"
+  PR: "6202"

.changes/unreleased/Features-20221114-185207.yaml

@@ -0,0 +1,7 @@
+kind: Features
+body: Added an md5 function to the base context
+time: 2022-11-14T18:52:07.788593+02:00
+custom:
+  Author: haritamar
+  Issue: "6246"
+  PR: "6247"

.changes/unreleased/Features-20221130-112913.yaml

@@ -0,0 +1,7 @@
+kind: Features
+body: Exposures support metrics in lineage
+time: 2022-11-30T11:29:13.256034-05:00
+custom:
+  Author: michelleark
+  Issue: "6057"
+  PR: "6342"

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

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

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

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

.changes/unreleased/Fixes-20221010-113218.yaml

@@ -0,0 +1,7 @@
+kind: Fixes
+body: Add validation of enabled config for metrics, exposures and sources
+time: 2022-10-10T11:32:18.752322-05:00
+custom:
+  Author: emmyoop
+  Issue: "6030"
+  PR: "6038"

.changes/unreleased/Fixes-20221011-160715.yaml

@@ -0,0 +1,7 @@
+kind: Fixes
+body: check length of args of python model function before accessing it
+time: 2022-10-11T16:07:15.464093-04:00
+custom:
+  Author: chamini2
+  Issue: "6041"
+  PR: "6042"

.changes/unreleased/Fixes-20221016-173742.yaml

@@ -0,0 +1,8 @@
+kind: Fixes
+body: Add functors to ensure event types with str-type attributes are initialized
+  to spec, even when provided non-str type params.
+time: 2022-10-16T17:37:42.846683-07:00
+custom:
+  Author: versusfacit
+  Issue: "5436"
+  PR: "5874"

.changes/unreleased/Fixes-20221107-095314.yaml

@@ -0,0 +1,7 @@
+kind: Fixes
+body: Allow hooks to fail without halting execution flow
+time: 2022-11-07T09:53:14.340257-06:00
+custom:
+  Author: ChenyuLInx
+  Issue: "5625"
+  PR: "6059"

.changes/unreleased/Fixes-20221115-081021.yaml

@@ -0,0 +1,7 @@
+kind: Fixes
+body: Clarify Error Message for how many models are allowed in a Python file
+time: 2022-11-15T08:10:21.527884-05:00
+custom:
+  Author: justbldwn
+  Issue: "6245"
+  PR: "6251"

.changes/unreleased/Under the Hood-20220927-194259.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Put black config in explicit config
+time: 2022-09-27T19:42:59.241433-07:00
+custom:
+  Author: max-sixty
+  Issue: "5946"
+  PR: "5947"

.changes/unreleased/Under the Hood-20220929-134406.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Added flat_graph attribute the Manifest class's deepcopy() coverage
+time: 2022-09-29T13:44:06.275941-04:00
+custom:
+  Author: peterallenwebb
+  Issue: "5809"
+  PR: "5975"

.changes/unreleased/Under the Hood-20221005-120310.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Add mypy configs so `mypy` passes from CLI
+time: 2022-10-05T12:03:10.061263-07:00
+custom:
+  Author: max-sixty
+  Issue: "5983"
+  PR: "5983"

.changes/unreleased/Under the Hood-20221007-094627.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Exception message cleanup.
+time: 2022-10-07T09:46:27.682872-05:00
+custom:
+  Author: emmyoop
+  Issue: "6023"
+  PR: "6024"

.changes/unreleased/Under the Hood-20221007-140044.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Add dmypy cache to gitignore
+time: 2022-10-07T14:00:44.227644-07:00
+custom:
+  Author: max-sixty
+  Issue: "6028"
+  PR: "5978"

.changes/unreleased/Under the Hood-20221013-181912.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Provide useful errors when the value of 'materialized' is invalid
+time: 2022-10-13T18:19:12.167548-04:00
+custom:
+  Author: peterallenwebb
+  Issue: "5229"
+  PR: "6025"

.changes/unreleased/Under the Hood-20221017-151511.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Fixed extra whitespace in strings introduced by black.
+time: 2022-10-17T15:15:11.499246-05:00
+custom:
+  Author: luke-bassett
+  Issue: "1350"
+  PR: "6086"

.changes/unreleased/Under the Hood-20221017-155844.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Clean up string formatting
+time: 2022-10-17T15:58:44.676549-04:00
+custom:
+  Author: eve-johns
+  Issue: "6068"
+  PR: "6082"

.changes/unreleased/Under the Hood-20221028-104837.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Remove the 'root_path' field from most nodes
+time: 2022-10-28T10:48:37.687886-04:00
+custom:
+  Author: gshank
+  Issue: "6171"
+  PR: "6172"

.changes/unreleased/Under the Hood-20221028-110344.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Combine certain logging events with different levels
+time: 2022-10-28T11:03:44.887836-04:00
+custom:
+  Author: gshank
+  Issue: "6173"
+  PR: "6174"

.changes/unreleased/Under the Hood-20221108-074550.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Convert threading tests to pytest
+time: 2022-11-08T07:45:50.589147-06:00
+custom:
+  Author: stu-k
+  Issue: "5942"
+  PR: "6226"

.changes/unreleased/Under the Hood-20221108-115633.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Convert postgres index tests to pytest
+time: 2022-11-08T11:56:33.743042-06:00
+custom:
+  Author: stu-k
+  Issue: "5770"
+  PR: "6228"

.changes/unreleased/Under the Hood-20221108-133104.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Convert use color tests to pytest
+time: 2022-11-08T13:31:04.788547-06:00
+custom:
+  Author: stu-k
+  Issue: "5771"
+  PR: "6230"

.changes/unreleased/Under the Hood-20221116-130037.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Add github actions workflow to generate high level CLI API docs
+time: 2022-11-16T13:00:37.916202-06:00
+custom:
+  Author: stu-k
+  Issue: "5942"
+  PR: "6187"

.changie.yaml

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

.github/CODEOWNERS

@@ -16,25 +16,57 @@
 # Changes to GitHub configurations including Actions
 /.github/ @leahwicz
 
+### LANGUAGE
+
 # Language core modules
 /core/dbt/config/               @dbt-labs/core-language
 /core/dbt/context/              @dbt-labs/core-language
 /core/dbt/contracts/            @dbt-labs/core-language
 /core/dbt/deps/                 @dbt-labs/core-language
+/core/dbt/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
 
-# Adapter interface, scaffold, Postgres plugin
+# Execution misc files
+/core/dbt/compilation.py        @dbt-labs/core-execution
+/core/dbt/flags.py              @dbt-labs/core-execution
+/core/dbt/lib.py                @dbt-labs/core-execution
+/core/dbt/main.py               @dbt-labs/core-execution
+/core/dbt/profiler.py           @dbt-labs/core-execution
+/core/dbt/selected_resources.py @dbt-labs/core-execution
+/core/dbt/tracking.py           @dbt-labs/core-execution
+/core/dbt/version.py            @dbt-labs/core-execution
+
+
+### ADAPTERS
+
+# Adapter interface ("base" + "sql" adapter defaults, cache)
 /core/dbt/adapters              @dbt-labs/core-adapters
-/core/scripts/create_adapter_plugin.py    @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
 
-# Global project: default macros, including generic tests + materializations
+# Functional tests for adapter plugins
-/core/dbt/include/global_project    @dbt-labs/core-execution @dbt-labs/core-adapters
+/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?
+      label: Is this a new bug in dbt-core?
-      description: Please search to see if an issue already exists for the bug you encountered.
+      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`)
+          - **Python**: 3.9.12 (`python3 --version`)
-          - **dbt**: 0.21.0 (`dbt --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
+  - name: Create an issue for dbt-spark
-    url: https://docs.getdbt.com/docs/guides/getting-help
+    url: https://github.com/dbt-labs/dbt-spark/issues/new/choose
-    about: Ask a question or request support
+    about: Report a bug or request a feature for dbt-spark
-  - name: Questions on Stack Overflow
-    url: https://stackoverflow.com/questions/tagged/dbt
-    about: Look at questions/answers at Stack Overflow

.github/ISSUE_TEMPLATE/feature-request.yml

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

.github/ISSUE_TEMPLATE/regression-report.yml

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

.github/_README.md

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

.github/pull_request_template.md

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

.github/workflows/bot-changelog.yml

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

.github/workflows/changelog-check.yml

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

.github/workflows/changelog-existence.yml

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

.github/workflows/dependency-changelog.yml

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

.github/workflows/generate-cli-api-docs.yml

@@ -0,0 +1,166 @@
+# **what?**
+# On push, if anything in core/dbt/docs or core/dbt/cli has been
+# created or modified, regenerate the CLI API docs using sphinx.
+
+# **why?**
+# We watch for changes in core/dbt/cli because the CLI API docs rely on click
+# and all supporting flags/params to be generated. We watch for changes in
+# core/dbt/docs since any changes to sphinx configuration or any of the
+# .rst files there could result in a differently build final index.html file.
+
+# **when?**
+# Whenever a change has been pushed to a branch, and only if there is a diff
+# between the PR branch and main's core/dbt/cli and or core/dbt/docs dirs.
+
+# TODO: add bot comment to PR informing contributor that the docs have been committed
+# TODO: figure out why github action triggered pushes cause github to fail to report
+#       the status of jobs
+
+name: Generate CLI API docs
+
+on:
+  pull_request:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+env:
+  CLI_DIR: ${{ github.workspace }}/core/dbt/cli
+  DOCS_DIR: ${{ github.workspace }}/core/dbt/docs
+  DOCS_BUILD_DIR: ${{ github.workspace }}/core/dbt/docs/build
+
+jobs:
+  check_gen:
+    name: check if generation needed
+    runs-on: ubuntu-latest
+    outputs:
+      cli_dir_changed: ${{ steps.check_cli.outputs.cli_dir_changed }}
+      docs_dir_changed: ${{ steps.check_docs.outputs.docs_dir_changed }}
+
+    steps:
+    - name: "[DEBUG] print variables"
+      run: |
+        echo "env.CLI_DIR:        ${{ env.CLI_DIR }}"
+        echo "env.DOCS_BUILD_DIR: ${{ env.DOCS_BUILD_DIR }}"
+        echo "env.DOCS_DIR:       ${{ env.DOCS_DIR }}"
+        echo ">>>>> git log"
+        git log --pretty=oneline | head -5
+
+    - name: git checkout
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 0
+        ref: ${{ github.head_ref }}
+
+    - name: set shas
+      id: set_shas
+      run: |
+        THIS_SHA=$(git rev-parse @)
+        LAST_SHA=$(git rev-parse @~1)
+
+        echo "this sha: $THIS_SHA"
+        echo "last sha: $LAST_SHA"
+
+        echo "this_sha=$THIS_SHA" >> $GITHUB_OUTPUT
+        echo "last_sha=$LAST_SHA" >> $GITHUB_OUTPUT
+
+    - name: check for changes in core/dbt/cli
+      id: check_cli
+      run: |
+        CLI_DIR_CHANGES=$(git diff \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.CLI_DIR }})
+
+        if [ -n "$CLI_DIR_CHANGES" ]; then
+          echo "changes found"
+          echo $CLI_DIR_CHANGES
+          echo "cli_dir_changed=true" >> $GITHUB_OUTPUT
+          exit 0
+        fi
+        echo "cli_dir_changed=false" >> $GITHUB_OUTPUT
+        echo "no changes found"
+
+    - name: check for changes in core/dbt/docs
+      id: check_docs
+      if: steps.check_cli.outputs.cli_dir_changed == 'false'
+      run: |
+        DOCS_DIR_CHANGES=$(git diff --name-only \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.DOCS_DIR }} ':!${{ env.DOCS_BUILD_DIR }}')
+
+        DOCS_BUILD_DIR_CHANGES=$(git diff --name-only \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.DOCS_BUILD_DIR }})
+
+        if [ -n "$DOCS_DIR_CHANGES" ] && [ -z "$DOCS_BUILD_DIR_CHANGES" ]; then
+          echo "changes found"
+          echo $DOCS_DIR_CHANGES
+          echo "docs_dir_changed=true" >> $GITHUB_OUTPUT
+          exit 0
+        fi
+        echo "docs_dir_changed=false" >> $GITHUB_OUTPUT
+        echo "no changes found"
+
+  gen_docs:
+    name: generate docs
+    runs-on: ubuntu-latest
+    needs: [check_gen]
+    if: |
+      needs.check_gen.outputs.cli_dir_changed == 'true'
+      || needs.check_gen.outputs.docs_dir_changed == 'true'
+
+    steps:
+      - name: "[DEBUG] print variables"
+        run: |
+          echo "env.DOCS_DIR:    ${{ env.DOCS_DIR }}"
+          echo "github head_ref: ${{ github.head_ref }}"
+
+      - name: git checkout
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ github.head_ref }}
+
+      - name: install python
+        uses: actions/setup-python@v4.3.0
+        with:
+          python-version: 3.8
+
+      - name: install dev requirements
+        run: |
+          python3 -m venv env
+          source env/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt -r dev-requirements.txt
+
+      - name: generate docs
+        run: |
+          source env/bin/activate
+          cd ${{ env.DOCS_DIR }}
+
+          echo "cleaning existing docs"
+          make clean
+
+          echo "creating docs"
+          make html
+
+      - name: debug
+        run: |
+          echo ">>>>> status"
+          git status
+          echo ">>>>> remotes"
+          git remote -v
+          echo ">>>>> branch"
+          git branch -v
+          echo ">>>>> log"
+          git log --pretty=oneline | head -5
+
+      - name: commit docs
+        run: |
+          git config user.name 'Github Build Bot'
+          git config user.email 'buildbot@fishtownanalytics.com'
+          git commit -am "Add generated CLI API docs"
+          git push -u origin ${{ github.head_ref }}

.github/workflows/jira-transition.yml

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

.github/workflows/main.yml

@@ -45,7 +45,9 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
+        with:
+          python-version: '3.8'
 
       - name: Install python dependencies
         run: |
@@ -82,7 +84,7 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -117,7 +119,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.7", "3.8", "3.9", "3.10"]
-        os: [ubuntu-latest]
+        os: [ubuntu-20.04]
         include:
           - python-version: 3.8
             os: windows-latest
@@ -137,7 +139,7 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -190,9 +192,9 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
-          python-version: 3.8
+          python-version: '3.8'
 
       - name: Install python dependencies
         run: |

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

@@ -39,7 +39,7 @@ jobs:
       max-parallel: 1
       fail-fast: false
       matrix:
-        branch: [1.0.latest, 1.1.latest, main]
+        branch: [1.0.latest, 1.1.latest, 1.2.latest, 1.3.latest, main]
 
     steps:
     - name: Call CI workflow for ${{ matrix.branch }} branch

.github/workflows/release.yml

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

.github/workflows/schema-check.yml

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

.github/workflows/stale.yml

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

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

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

.github/workflows/version-bump.yml

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

.gitignore

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

.pre-commit-config.yaml

@@ -2,11 +2,11 @@
 # Eventually the hooks described here will be run as tests before merging each PR.
 
 # TODO: remove global exclusion of tests when testing overhaul is complete
-exclude: ^test/
+exclude: ^(test/|core/dbt/docs/build/)
 
 # Force all unspecified python hooks to run python 3.8
 default_language_version:
-  python: python3.8
+  python: python3
 
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -24,18 +24,13 @@ repos:
   rev: 22.3.0
   hooks:
   - id: black
-    args:
-    - "--line-length=99"
-    - "--target-version=py38"
   - id: black
     alias: black-check
     stages: [manual]
     args:
-    - "--line-length=99"
-    - "--target-version=py38"
     - "--check"
     - "--diff"
-- repo: https://gitlab.com/pycqa/flake8
+- repo: https://github.com/pycqa/flake8
   rev: 4.0.1
   hooks:
   - id: flake8

CHANGELOG.md

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

CONTRIBUTING.md

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

Makefile

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

core/MANIFEST.in

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

core/dbt/adapters/base/README.md

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

core/dbt/adapters/base/__init__.py

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

core/dbt/adapters/base/column.py

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

core/dbt/adapters/base/connections.py

@@ -2,6 +2,7 @@ import abc
 import os
 from time import sleep
 import sys
+import traceback
 
 # multiprocessing.RLock is a function returning this type
 from multiprocessing.synchronize import RLock
@@ -40,14 +41,15 @@ from dbt.events.functions import fire_event
 from dbt.events.types import (
     NewConnection,
     ConnectionReused,
+    ConnectionLeftOpenInCleanup,
     ConnectionLeftOpen,
-    ConnectionLeftOpen2,
+    ConnectionClosedInCleanup,
     ConnectionClosed,
-    ConnectionClosed2,
     Rollback,
     RollbackFailed,
 )
 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.
@@ -304,9 +306,9 @@ 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
@@ -332,17 +334,21 @@ 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()
+                )
+            )
 
     @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)))
             connection.handle.close()
         else:
-            fire_event(ConnectionLeftOpen2(conn_name=connection.name))
+            fire_event(ConnectionLeftOpen(conn_name=cast_to_str(connection.name)))
 
     @classmethod
     def _rollback(cls, connection: Connection) -> None:
@@ -353,7 +359,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
                 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)))
         cls._rollback_handle(connection)
 
         connection.transaction_open = False
@@ -365,7 +371,7 @@ 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)))
             cls._rollback_handle(connection)
         connection.transaction_open = False
 

core/dbt/adapters/base/impl.py

@@ -2,6 +2,7 @@ import abc
 from concurrent.futures import as_completed, Future
 from contextlib import contextmanager
 from datetime import datetime
+import time
 from itertools import chain
 from typing import (
     Optional,
@@ -40,10 +41,15 @@ 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, warn_or_error
-from dbt.events.functions import fire_event
+from dbt.events.types import (
-from dbt.events.types import CacheMiss, ListRelations
+    CacheMiss,
-from dbt.utils import filter_null_values, executor
+    ListRelations,
+    CodeExecution,
+    CodeExecutionStatus,
+    CatalogGenerationError,
+)
+from dbt.utils import filter_null_values, executor, cast_to_str
 
 from dbt.adapters.base.connections import Connection, AdapterResponse
 from dbt.adapters.base.meta import AdapterMeta, available
@@ -54,7 +60,8 @@ from dbt.adapters.base.relation import (
     SchemaSearchMap,
 )
 from dbt.adapters.base import Column as BaseColumn
-from dbt.adapters.cache import RelationsCache, _make_key
+from dbt.adapters.base import Credentials
+from dbt.adapters.cache import RelationsCache, _make_ref_key_msg
 
 
 SeedModel = Union[ParsedSeedNode, CompiledSeedNode]
@@ -121,6 +128,35 @@ def _relation_name(rel: Optional[BaseRelation]) -> str:
         return str(rel)
 
 
+def log_code_execution(code_execution_function):
+    # decorator to log code and execution time
+    if code_execution_function.__name__ != "submit_python_job":
+        raise ValueError("this should be only used to log submit_python_job now")
+
+    def execution_with_log(*args):
+        self = args[0]
+        connection_name = self.connections.get_thread_connection().name
+        fire_event(CodeExecution(conn_name=connection_name, code_content=args[2]))
+        start_time = time.time()
+        response = code_execution_function(*args)
+        fire_event(
+            CodeExecutionStatus(
+                status=response._message, elapsed=round((time.time() - start_time), 2)
+            )
+        )
+        return response
+
+    return execution_with_log
+
+
+class PythonJobHelper:
+    def __init__(self, parsed_model: Dict, credential: Credentials) -> None:
+        raise NotImplementedError("PythonJobHelper is not implemented yet")
+
+    def submit(self, compiled_code: str) -> Any:
+        raise NotImplementedError("PythonJobHelper submit function is not implemented yet")
+
+
 class BaseAdapter(metaclass=AdapterMeta):
     """The BaseAdapter provides an abstract base class for adapters.
 
@@ -284,7 +320,9 @@ class BaseAdapter(metaclass=AdapterMeta):
             from dbt.parser.manifest import ManifestLoader
 
             manifest = ManifestLoader.load_macros(
-                self.config, self.connections.set_query_header, base_macros_only=base_macros_only
+                self.config,
+                self.connections.set_query_header,
+                base_macros_only=base_macros_only,
             )
             # TODO CT-211
             self._macro_manifest_lazy = manifest  # type: ignore[assignment]
@@ -303,7 +341,11 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         if (database, schema) not in self.cache:
             fire_event(
-                CacheMiss(conn_name=self.nice_connection_name(), database=database, schema=schema)
+                CacheMiss(
+                    conn_name=self.nice_connection_name(),
+                    database=cast_to_str(database),
+                    schema=schema,
+                )
             )
             return False
         else:
@@ -381,7 +423,10 @@ class BaseAdapter(metaclass=AdapterMeta):
         self.cache.update_schemas(cache_update)
 
     def set_relations_cache(
-        self, manifest: Manifest, clear: bool = False, required_schemas: Set[BaseRelation] = None
+        self,
+        manifest: Manifest,
+        clear: bool = False,
+        required_schemas: Set[BaseRelation] = None,
     ) -> None:
         """Run a query that gets a populated cache of the relations in the
         database and set the cache on this adapter.
@@ -536,7 +581,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :rtype: List[self.Relation]
         """
         raise NotImplementedException(
-            "`list_relations_without_caching` is not implemented for this " "adapter!"
+            "`list_relations_without_caching` is not implemented for this adapter!"
         )
 
     ###
@@ -670,7 +715,10 @@ class BaseAdapter(metaclass=AdapterMeta):
             return self.cache.get_relations(database, schema)
 
         schema_relation = self.Relation.create(
-            database=database, schema=schema, identifier="", quote_policy=self.config.quoting
+            database=database,
+            schema=schema,
+            identifier="",
+            quote_policy=self.config.quoting,
         ).without_identifier()
 
         # we can't build the relations cache because we don't have a
@@ -678,7 +726,9 @@ class BaseAdapter(metaclass=AdapterMeta):
         relations = self.list_relations_without_caching(schema_relation)
         fire_event(
             ListRelations(
-                database=database, schema=schema, relations=[_make_key(x) for x in relations]
+                database=cast_to_str(database),
+                schema=schema,
+                relations=[_make_ref_key_msg(x) for x in relations],
             )
         )
 
@@ -1162,6 +1212,74 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         return sql
 
+    @property
+    def python_submission_helpers(self) -> Dict[str, Type[PythonJobHelper]]:
+        raise NotImplementedError("python_submission_helpers is not specified")
+
+    @property
+    def default_python_submission_method(self) -> str:
+        raise NotImplementedError("default_python_submission_method is not specified")
+
+    @log_code_execution
+    def submit_python_job(self, parsed_model: dict, compiled_code: str) -> AdapterResponse:
+        submission_method = parsed_model["config"].get(
+            "submission_method", self.default_python_submission_method
+        )
+        if submission_method not in self.python_submission_helpers:
+            raise NotImplementedError(
+                "Submission method {} is not supported for current adapter".format(
+                    submission_method
+                )
+            )
+        job_helper = self.python_submission_helpers[submission_method](
+            parsed_model, self.connections.profile.credentials
+        )
+        submission_result = job_helper.submit(compiled_code)
+        # process submission result to generate adapter response
+        return self.generate_python_submission_response(submission_result)
+
+    def generate_python_submission_response(self, submission_result: Any) -> AdapterResponse:
+        raise NotImplementedException(
+            "Your adapter need to implement generate_python_submission_response"
+        )
+
+    def valid_incremental_strategies(self):
+        """The set of standard builtin strategies which this adapter supports out-of-the-box.
+        Not used to validate custom strategies defined by end users.
+        """
+        return ["append"]
+
+    def builtin_incremental_strategies(self):
+        return ["append", "delete+insert", "merge", "insert_overwrite"]
+
+    @available.parse_none
+    def get_incremental_strategy_macro(self, model_context, strategy: str):
+        # Construct macro_name from strategy name
+        if strategy is None:
+            strategy = "default"
+
+        # validate strategies for this adapter
+        valid_strategies = self.valid_incremental_strategies()
+        valid_strategies.append("default")
+        builtin_strategies = self.builtin_incremental_strategies()
+        if strategy in builtin_strategies and strategy not in valid_strategies:
+            raise RuntimeException(
+                f"The incremental strategy '{strategy}' is not valid for this adapter"
+            )
+
+        strategy = strategy.replace("+", "_")
+        macro_name = f"get_incremental_{strategy}_sql"
+        # The model_context should have MacroGenerator callable objects for all macros
+        if macro_name not in model_context:
+            raise RuntimeException(
+                'dbt could not find an incremental strategy macro with the name "{}" in {}'.format(
+                    macro_name, self.config.project_name
+                )
+            )
+
+        # This returns a callable macro
+        return model_context[macro_name]
+
 
 COLUMNS_EQUAL_SQL = """
 with diff_count as (
@@ -1209,7 +1327,7 @@ 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/cache.py

@@ -1,10 +1,16 @@
+import re
 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
+from dbt.adapters.reference_keys import (
+    _make_ref_key,
+    _make_ref_key_msg,
+    _make_msg_from_ref_key,
+    _ReferenceKey,
+)
 import dbt.exceptions
-from dbt.events.functions import fire_event
+from dbt.events.functions import fire_event, fire_event_if
 from dbt.events.types import (
     AddLink,
     AddRelation,
@@ -20,8 +26,8 @@ from dbt.events.types import (
     UncachedRelation,
     UpdateReference,
 )
+import dbt.flags as flags
 from dbt.utils import lowercase
-from dbt.helper_types import Lazy
 
 
 def dot_separated(key: _ReferenceKey) -> str:
@@ -81,7 +87,7 @@ 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
@@ -293,13 +299,18 @@ class RelationsCache:
         :param BaseRelation dependent: The dependent model.
         :raises InternalError: If either entry does not exist.
         """
-        ref_key = _make_key(referenced)
+        ref_key = _make_ref_key(referenced)
-        dep_key = _make_key(dependent)
+        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(
+                UncachedRelation(
+                    dep_key=_make_msg_from_ref_key(dep_key),
+                    ref_key=_make_msg_from_ref_key(ref_key),
+                )
+            )
             return
         if ref_key not in self.relations:
             # Insert a dummy "external" relation.
@@ -309,7 +320,11 @@ 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(
+            AddLink(
+                dep_key=_make_msg_from_ref_key(dep_key), ref_key=_make_msg_from_ref_key(ref_key)
+            )
+        )
         with self.lock:
             self._add_link(ref_key, dep_key)
 
@@ -320,12 +335,12 @@ class RelationsCache:
         :param BaseRelation relation: The underlying relation.
         """
         cached = _CachedRelation(relation)
-        fire_event(AddRelation(relation=_make_key(cached)))
+        fire_event(AddRelation(relation=_make_ref_key_msg(cached)))
-        fire_event(DumpBeforeAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(flags.LOG_CACHE_EVENTS, lambda: DumpBeforeAddGraph(dump=self.dump_graph()))
 
         with self.lock:
             self._setdefault(cached)
-        fire_event(DumpAfterAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(flags.LOG_CACHE_EVENTS, lambda: DumpAfterAddGraph(dump=self.dump_graph()))
 
     def _remove_refs(self, keys):
         """Removes all references to all entries in keys. This does not
@@ -340,19 +355,6 @@ 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 +366,19 @@ 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)
+        dropped_key = _make_ref_key(relation)
-        fire_event(DropRelation(dropped=dropped_key))
+        dropped_key_msg = _make_ref_key_msg(relation)
+        fire_event(DropRelation(dropped=dropped_key_msg))
         with self.lock:
-            self._drop_cascade_relation(dropped_key)
+            if dropped_key not in self.relations:
+                fire_event(DropMissingRelation(relation=dropped_key_msg))
+                return
+            consequences = self.relations[dropped_key].collect_consequences()
+            # convert from a list of _ReferenceKeys to a list of ReferenceKeyMsgs
+            consequence_msgs = [_make_msg_from_ref_key(key) for key in consequences]
+
+            fire_event(DropCascade(dropped=dropped_key_msg, consequences=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.
@@ -383,13 +394,17 @@ 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())
+                    UpdateReference(
+                        old_key=_make_ref_key_msg(old_key),
+                        new_key=_make_ref_key_msg(new_key),
+                        cached_key=_make_ref_key_msg(cached.key()),
+                    )
                 )
                 cached.rename_key(old_key, new_key)
 
@@ -413,14 +428,29 @@ class RelationsCache:
         :raises InternalError: If the new key is already present.
         """
         if new_key in self.relations:
+            # Tell user when collision caused by model names truncated during
+            # materialization.
+            match = re.search("__dbt_backup|__dbt_tmp$", new_key.identifier)
+            if match:
+                truncated_model_name_prefix = new_key.identifier[: match.start()]
+                message_addendum = (
+                    "\n\nName collisions can occur when the length of two "
+                    "models' names approach your database's builtin limit. "
+                    "Try restructuring your project such that no two models "
+                    "share the prefix '{}'.".format(truncated_model_name_prefix)
+                    + " Then, clean your warehouse of any removed models."
+                )
+            else:
+                message_addendum = ""
+
             dbt.exceptions.raise_cache_inconsistent(
-                "in rename, new key {} already in cache: {}".format(
+                "in rename, new key {} already in cache: {}{}".format(
-                    new_key, list(self.relations.keys())
+                    new_key, list(self.relations.keys()), message_addendum
                 )
             )
 
         if old_key not in self.relations:
-            fire_event(TemporaryRelation(key=old_key))
+            fire_event(TemporaryRelation(key=_make_msg_from_ref_key(old_key)))
             return False
         return True
 
@@ -436,11 +466,17 @@ class RelationsCache:
         :param BaseRelation new: The new relation name information.
         :raises InternalError: If the new key is already present.
         """
-        old_key = _make_key(old)
+        old_key = _make_ref_key(old)
-        new_key = _make_key(new)
+        new_key = _make_ref_key(new)
-        fire_event(RenameSchema(old_key=old_key, new_key=new_key))
+        fire_event(
+            RenameSchema(
+                old_key=_make_msg_from_ref_key(old_key), new_key=_make_msg_from_ref_key(new)
+            )
+        )
 
-        fire_event(DumpBeforeRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS, lambda: DumpBeforeRenameSchema(dump=self.dump_graph())
+        )
 
         with self.lock:
             if self._check_rename_constraints(old_key, new_key):
@@ -448,7 +484,9 @@ 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: DumpAfterRenameSchema(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.
@@ -496,6 +534,6 @@ class RelationsCache:
         """
         for relation in to_remove:
             # it may have been cascaded out already
-            drop_key = _make_key(relation)
+            drop_key = _make_ref_key(relation)
             if drop_key in self.relations:
                 self.drop(drop_key)

core/dbt/adapters/factory.py

@@ -1,23 +1,18 @@
 import threading
-from pathlib import Path
+import traceback
+from contextlib import contextmanager
 from importlib import import_module
-from typing import Type, Dict, Any, List, Optional, Set
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Set, Type
 
-from dbt.exceptions import RuntimeException, InternalException
+from dbt.adapters.base.plugin import AdapterPlugin
-from dbt.include.global_project import (
+from dbt.adapters.protocol import AdapterConfig, AdapterProtocol, RelationProtocol
-    PACKAGE_PATH as GLOBAL_PROJECT_PATH,
+from dbt.contracts.connection import AdapterRequiredConfig, Credentials
-    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.exceptions import InternalException, RuntimeException
-from dbt.adapters.protocol import (
+from dbt.include.global_project import PACKAGE_PATH as GLOBAL_PROJECT_PATH
-    AdapterProtocol,
+from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
-    AdapterConfig,
-    RelationProtocol,
-)
-from dbt.adapters.base.plugin import AdapterPlugin
-
 
 Adapter = AdapterProtocol
 
@@ -64,12 +59,12 @@ class AdapterContainer:
             # if we failed to import the target module in particular, inform
             # the user about it via a runtime error
             if exc.name == "dbt.adapters." + name:
-                fire_event(AdapterImportError(exc=exc))
+                fire_event(AdapterImportError(exc=str(exc)))
                 raise RuntimeException(f"Could not find adapter type {name}!")
             # otherwise, the error had to have come from some underlying
             # library. Log the stack trace.
 
-            fire_event(PluginLoadError())
+            fire_event(PluginLoadError(exc_info=traceback.format_exc()))
             raise
         plugin: AdapterPlugin = mod.Plugin
         plugin_type = plugin.adapter.type()
@@ -217,3 +212,12 @@ def get_adapter_package_names(name: Optional[str]) -> List[str]:
 
 def get_adapter_type_names(name: Optional[str]) -> List[str]:
     return FACTORY.get_adapter_type_names(name)
+
+
+@contextmanager
+def adapter_management():
+    reset_adapters()
+    try:
+        yield
+    finally:
+        cleanup_connections()

core/dbt/adapters/protocol.py

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

core/dbt/adapters/reference_keys.py

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

core/dbt/adapters/sql/connections.py

@@ -10,6 +10,7 @@ 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.utils import cast_to_str
 
 
 class SQLConnectionManager(BaseConnectionManager):
@@ -55,7 +56,7 @@ class SQLConnectionManager(BaseConnectionManager):
         connection = self.get_thread_connection()
         if auto_begin and connection.transaction_open is False:
             self.begin()
-        fire_event(ConnectionUsed(conn_type=self.TYPE, conn_name=connection.name))
+        fire_event(ConnectionUsed(conn_type=self.TYPE, conn_name=cast_to_str(connection.name)))
 
         with self.exception_handler(sql):
             if abridge_sql_log:
@@ -63,7 +64,7 @@ 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))
             pre = time.time()
 
             cursor = connection.handle.cursor()

core/dbt/adapters/sql/impl.py

@@ -5,7 +5,7 @@ import dbt.clients.agate_helper
 from dbt.contracts.connection import Connection
 import dbt.exceptions
 from dbt.adapters.base import BaseAdapter, available
-from dbt.adapters.cache import _make_key
+from dbt.adapters.cache import _make_ref_key_msg
 from dbt.adapters.sql import SQLConnectionManager
 from dbt.events.functions import fire_event
 from dbt.events.types import ColTypeChange, SchemaCreation, SchemaDrop
@@ -110,7 +110,7 @@ class SQLAdapter(BaseAdapter):
                     ColTypeChange(
                         orig_type=target_column.data_type,
                         new_type=new_type,
-                        table=_make_key(current),
+                        table=_make_ref_key_msg(current),
                     )
                 )
 
@@ -155,7 +155,7 @@ class SQLAdapter(BaseAdapter):
 
     def create_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        fire_event(SchemaCreation(relation=_make_key(relation)))
+        fire_event(SchemaCreation(relation=_make_ref_key_msg(relation)))
         kwargs = {
             "relation": relation,
         }
@@ -166,7 +166,7 @@ class SQLAdapter(BaseAdapter):
 
     def drop_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        fire_event(SchemaDrop(relation=_make_key(relation)))
+        fire_event(SchemaDrop(relation=_make_ref_key_msg(relation)))
         kwargs = {
             "relation": relation,
         }

core/dbt/cli/README.md

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

core/dbt/cli/flags.py

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

core/dbt/cli/main.py

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

core/dbt/cli/option_types.py

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

core/dbt/cli/params.py

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

core/dbt/cli/resolvers.py

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

core/dbt/clients/README.md

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

core/dbt/clients/_jinja_blocks.py

@@ -367,9 +367,9 @@ 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(
-                    "Reached EOF without finding a close tag for " "{} (searched from line {})"
+                    self.current.block_type_name, linecount
-                ).format(self.current.block_type_name, linecount)
+                )
             )
 
         if collect_raw_data:

core/dbt/clients/jinja.py

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

core/dbt/clients/jinja_static.py

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

core/dbt/clients/registry.py

@@ -3,9 +3,9 @@ from typing import Any, Dict, List
 import requests
 from dbt.events.functions import fire_event
 from dbt.events.types import (
-    RegistryProgressMakingGETRequest,
+    RegistryProgressGETRequest,
     RegistryProgressGETResponse,
-    RegistryIndexProgressMakingGETRequest,
+    RegistryIndexProgressGETRequest,
     RegistryIndexProgressGETResponse,
     RegistryResponseUnexpectedType,
     RegistryResponseMissingTopKeys,
@@ -14,6 +14,7 @@ from dbt.events.types import (
 )
 from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
 from dbt import deprecations
+from dbt import semver
 import os
 
 if os.getenv("DBT_PACKAGE_HUB_URL"):
@@ -37,7 +38,7 @@ def _get_with_retries(package_name, registry_base_url=None):
 
 def _get(package_name, registry_base_url=None):
     url = _get_url(package_name, registry_base_url)
-    fire_event(RegistryProgressMakingGETRequest(url=url))
+    fire_event(RegistryProgressGETRequest(url=url))
     # all exceptions from requests get caught in the retry logic so no need to wrap this here
     resp = requests.get(url, timeout=30)
     fire_event(RegistryProgressGETResponse(url=url, resp_code=resp.status_code))
@@ -125,16 +126,43 @@ def package_version(package_name, version, registry_base_url=None) -> Dict[str,
     return response[version]
 
 
-def get_available_versions(package_name) -> List["str"]:
+def is_compatible_version(package_spec, dbt_version) -> bool:
+    require_dbt_version = package_spec.get("require_dbt_version")
+    if not require_dbt_version:
+        # if version requirements are missing or empty, assume any version is compatible
+        return True
+    else:
+        # determine whether dbt_version satisfies this package's require-dbt-version config
+        if not isinstance(require_dbt_version, list):
+            require_dbt_version = [require_dbt_version]
+        supported_versions = [
+            semver.VersionSpecifier.from_version_string(v) for v in require_dbt_version
+        ]
+        return semver.versions_compatible(dbt_version, *supported_versions)
+
+
+def get_compatible_versions(package_name, dbt_version, should_version_check) -> List["str"]:
     # returns a list of all available versions of a package
     response = package(package_name)
+
+    # if the user doesn't care about installing compatible versions, just return them all
+    if not should_version_check:
         return list(response)
 
+    # otherwise, only return versions that are compatible with the installed version of dbt-core
+    else:
+        compatible_versions = [
+            pkg_version
+            for pkg_version, info in response.items()
+            if is_compatible_version(info, dbt_version)
+        ]
+        return compatible_versions
+
 
 def _get_index(registry_base_url=None):
 
     url = _get_url("index", registry_base_url)
-    fire_event(RegistryIndexProgressMakingGETRequest(url=url))
+    fire_event(RegistryIndexProgressGETRequest(url=url))
     # all exceptions from requests get caught in the retry logic so no need to wrap this here
     resp = requests.get(url, timeout=30)
     fire_event(RegistryIndexProgressGETResponse(url=url, resp_code=resp.status_code))

core/dbt/clients/system.py

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

core/dbt/compilation.py

@@ -29,7 +29,7 @@ from dbt.exceptions import (
 from dbt.graph import Graph
 from dbt.events.functions import fire_event
 from dbt.events.types import FoundStats, CompilingNode, WritingInjectedSQLForNode
-from dbt.node_types import NodeType
+from dbt.node_types import NodeType, ModelLanguage
 from dbt.events.format import pluralize
 import dbt.tracking
 
@@ -56,6 +56,7 @@ def print_compile_stats(stats):
         NodeType.Source: "source",
         NodeType.Exposure: "exposure",
         NodeType.Metric: "metric",
+        NodeType.Entity: "entity",
     }
 
     results = {k: 0 for k in names.keys()}
@@ -91,6 +92,8 @@ def _generate_stats(manifest: Manifest):
         stats[exposure.resource_type] += 1
     for metric in manifest.metrics.values():
         stats[metric.resource_type] += 1
+    for entity in manifest.entities.values():
+        stats[entity.resource_type] += 1
     for macro in manifest.macros.values():
         stats[macro.resource_type] += 1
     return stats
@@ -183,6 +186,7 @@ class Compiler:
 
         context = generate_runtime_model_context(node, self.config, manifest)
         context.update(extra_context)
+
         if isinstance(node, CompiledGenericTestNode):
             # for test nodes, add a special keyword args value to the context
             jinja.add_rendered_test_kwargs(context, node)
@@ -271,7 +275,7 @@ class Compiler:
         are rolled up into the models that refer to them by
         inserting CTEs into the SQL.
         """
-        if model.compiled_sql is None:
+        if model.compiled_code is None:
             raise RuntimeException("Cannot inject ctes into an unparsed node", model)
         if model.extra_ctes_injected:
             return (model, model.extra_ctes)
@@ -324,29 +328,28 @@ class Compiler:
             _extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
 
             new_cte_name = self.add_ephemeral_prefix(cte_model.name)
-            rendered_sql = cte_model._pre_injected_sql or cte_model.compiled_sql
+            rendered_sql = cte_model._pre_injected_sql or cte_model.compiled_code
             sql = f" {new_cte_name} as (\n{rendered_sql}\n)"
 
             _add_prepended_cte(prepended_ctes, InjectedCTE(id=cte.id, sql=sql))
 
         injected_sql = self._inject_ctes_into_sql(
-            model.compiled_sql,
+            model.compiled_code,
             prepended_ctes,
         )
-        model._pre_injected_sql = model.compiled_sql
+        model._pre_injected_sql = model.compiled_code
-        model.compiled_sql = injected_sql
+        model.compiled_code = injected_sql
         model.extra_ctes_injected = True
         model.extra_ctes = prepended_ctes
         model.validate(model.to_dict(omit_none=True))
-
         manifest.update_node(model)
 
         return model, prepended_ctes
 
     # creates a compiled_node from the ManifestNode passed in,
     # creates a "context" dictionary for jinja rendering,
-    # and then renders the "compiled_sql" using the node, the
+    # and then renders the "compiled_code" using the node, the
-    # raw_sql and the context.
+    # raw_code and the context.
     def _compile_node(
         self,
         node: ManifestNode,
@@ -362,17 +365,37 @@ class Compiler:
         data.update(
             {
                 "compiled": False,
-                "compiled_sql": None,
+                "compiled_code": None,
                 "extra_ctes_injected": False,
                 "extra_ctes": [],
             }
         )
         compiled_node = _compiled_type_for(node).from_dict(data)
 
+        if compiled_node.language == ModelLanguage.python:
+            # TODO could we also 'minify' this code at all? just aesthetic, not functional
+
+            # quoating seems like something very specific to sql so far
+            # for all python implementations we are seeing there's no quating.
+            # TODO try to find better way to do this, given that
+            original_quoting = self.config.quoting
+            self.config.quoting = {key: False for key in original_quoting.keys()}
             context = self._create_node_context(compiled_node, manifest, extra_context)
 
-        compiled_node.compiled_sql = jinja.get_rendered(
+            postfix = jinja.get_rendered(
-            node.raw_sql,
+                "{{ py_script_postfix(model) }}",
+                context,
+                node,
+            )
+            # we should NOT jinja render the python model's 'raw code'
+            compiled_node.compiled_code = f"{node.raw_code}\n\n{postfix}"
+            # restore quoting settings in the end since context is lazy evaluated
+            self.config.quoting = original_quoting
+
+        else:
+            context = self._create_node_context(compiled_node, manifest, extra_context)
+            compiled_node.compiled_code = jinja.get_rendered(
+                node.raw_code,
                 context,
                 node,
             )
@@ -487,15 +510,15 @@ class Compiler:
 
         return Graph(linker.graph)
 
-    # writes the "compiled_sql" into the target/compiled directory
+    # writes the "compiled_code" into the target/compiled directory
     def _write_node(self, node: NonSourceCompiledNode) -> ManifestNode:
         if not node.extra_ctes_injected or node.resource_type == NodeType.Snapshot:
             return node
         fire_event(WritingInjectedSQLForNode(unique_id=node.unique_id))
 
-        if node.compiled_sql:
+        if node.compiled_code:
             node.compiled_path = node.write_node(
-                self.config.target_path, "compiled", node.compiled_sql
+                self.config.target_path, "compiled", node.compiled_code
             )
         return node
 

core/dbt/config/profile.py

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

core/dbt/config/project.py

@@ -248,7 +248,7 @@ class PartialProject(RenderComponents):
     project_name: Optional[str] = field(
         metadata=dict(
             description=(
-                "The name of the project. This should always be set and will not " "be rendered"
+                "The name of the project. This should always be set and will not be rendered"
             )
         )
     )
@@ -380,6 +380,9 @@ class PartialProject(RenderComponents):
         snapshots: Dict[str, Any]
         sources: Dict[str, Any]
         tests: Dict[str, Any]
+        metrics: Dict[str, Any]
+        entities: Dict[str, Any]
+        exposures: Dict[str, Any]
         vars_value: VarProvider
 
         dispatch = cfg.dispatch
@@ -388,6 +391,9 @@ class PartialProject(RenderComponents):
         snapshots = cfg.snapshots
         sources = cfg.sources
         tests = cfg.tests
+        metrics = cfg.metrics
+        entities = cfg.entities
+        exposures = cfg.exposures
         if cfg.vars is None:
             vars_dict: Dict[str, Any] = {}
         else:
@@ -441,6 +447,9 @@ class PartialProject(RenderComponents):
             query_comment=query_comment,
             sources=sources,
             tests=tests,
+            metrics=metrics,
+            entities=entities,
+            exposures=exposures,
             vars=vars_value,
             config_version=cfg.config_version,
             unrendered=unrendered,
@@ -543,6 +552,9 @@ class Project:
     snapshots: Dict[str, Any]
     sources: Dict[str, Any]
     tests: Dict[str, Any]
+    metrics: Dict[str, Any]
+    entities: Dict[str, Any]
+    exposures: Dict[str, Any]
     vars: VarProvider
     dbt_version: List[VersionSpecifier]
     packages: Dict[str, Any]
@@ -615,6 +627,9 @@ class Project:
                 "snapshots": self.snapshots,
                 "sources": self.sources,
                 "tests": self.tests,
+                "metrics": self.metrics,
+                "entities": self.entities,
+                "exposures": self.exposures,
                 "vars": self.vars.to_dict(),
                 "require-dbt-version": [v.to_version_string() for v in self.dbt_version],
                 "config-version": self.config_version,
@@ -658,7 +673,7 @@ class Project:
     def get_selector(self, name: str) -> Union[SelectionSpec, bool]:
         if name not in self.selectors:
             raise RuntimeException(
-                f"Could not find selector named {name}, expected one of " f"{list(self.selectors)}"
+                f"Could not find selector named {name}, expected one of {list(self.selectors)}"
             )
         return self.selectors[name]["definition"]
 

core/dbt/config/renderer.py

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

core/dbt/config/runtime.py

@@ -3,31 +3,41 @@ import os
 from copy import deepcopy
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Dict, Any, Optional, Mapping, Iterator, Iterable, Tuple, List, MutableSet, Type
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    Iterator,
+    Mapping,
+    MutableSet,
+    Optional,
+    Tuple,
+    Type,
+    Union,
+)
 
-from .profile import Profile
-from .project import Project
-from .renderer import DbtProjectYamlRenderer, ProfileRenderer
-from .utils import parse_cli_vars
 from dbt import flags
-from dbt.adapters.factory import get_relation_class_by_name, get_include_paths
+from dbt.adapters.factory import get_include_paths, get_relation_class_by_name
-from dbt.helper_types import FQNPath, PathSet, DictDefaultEmptyStr
 from dbt.config.profile import read_user_config
 from dbt.contracts.connection import AdapterRequiredConfig, Credentials
 from dbt.contracts.graph.manifest import ManifestMetadata
-from dbt.contracts.relation import ComponentName
-from dbt.ui import warning_tag
-
 from dbt.contracts.project import Configuration, UserConfig
-from dbt.exceptions import (
+from dbt.contracts.relation import ComponentName
-    RuntimeException,
-    DbtProjectError,
-    validator_error_message,
-    warn_or_error,
-    raise_compiler_error,
-)
-
 from dbt.dataclass_schema import ValidationError
+from dbt.exceptions import (
+    DbtProjectError,
+    RuntimeException,
+    raise_compiler_error,
+    validator_error_message,
+)
+from dbt.events.functions import warn_or_error
+from dbt.events.types import UnusedResourceConfigPath
+from dbt.helper_types import DictDefaultEmptyStr, FQNPath, PathSet
+
+from .profile import Profile
+from .project import Project, PartialProject
+from .renderer import DbtProjectYamlRenderer, ProfileRenderer
+from .utils import parse_cli_vars
 
 
 def _project_quoting_dict(proj: Project, profile: Profile) -> Dict[ComponentName, bool]:
@@ -105,6 +115,9 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             query_comment=project.query_comment,
             sources=project.sources,
             tests=project.tests,
+            metrics=project.metrics,
+            entities=project.entities,
+            exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
             unrendered=project.unrendered,
@@ -188,28 +201,52 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
     @classmethod
     def collect_parts(cls: Type["RuntimeConfig"], args: Any) -> Tuple[Project, Profile]:
-        # profile_name from the project
-        project_root = args.project_dir if args.project_dir else os.getcwd()
-        version_check = bool(flags.VERSION_CHECK)
-        partial = Project.partial_load(project_root, verify_version=version_check)
 
-        # build the profile using the base renderer and the one fact we know
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
-        # Note: only the named profile section is rendered. The rest of the
+
-        # profile is ignored.
+        profile = cls.collect_profile(args=args)
+        project_renderer = DbtProjectYamlRenderer(profile, cli_vars)
+        project = cls.collect_project(args=args, project_renderer=project_renderer)
+        assert type(project) is Project
+        return (project, profile)
+
+    @classmethod
+    def collect_profile(
+        cls: Type["RuntimeConfig"], args: Any, profile_name: Optional[str] = None
+    ) -> Profile:
+
         cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
         profile_renderer = ProfileRenderer(cli_vars)
+
+        # build the profile using the base renderer and the one fact we know
+        if profile_name is None:
+            # Note: only the named profile section is rendered here. The rest of the
+            # profile is ignored.
+            partial = cls.collect_project(args)
+            assert type(partial) is PartialProject
             profile_name = partial.render_profile_name(profile_renderer)
+
         profile = cls._get_rendered_profile(args, profile_renderer, profile_name)
         # Save env_vars encountered in rendering for partial parsing
         profile.profile_env_vars = profile_renderer.ctx_obj.env_vars
+        return profile
 
-        # get a new renderer using our target information and render the
+    @classmethod
-        # project
+    def collect_project(
-        project_renderer = DbtProjectYamlRenderer(profile, cli_vars)
+        cls: Type["RuntimeConfig"],
+        args: Any,
+        project_renderer: Optional[DbtProjectYamlRenderer] = None,
+    ) -> Union[Project, PartialProject]:
+
+        project_root = args.project_dir if args.project_dir else os.getcwd()
+        version_check = bool(flags.VERSION_CHECK)
+        partial = Project.partial_load(project_root, verify_version=version_check)
+        if project_renderer is None:
+            return partial
+        else:
             project = partial.render(project_renderer)
-        # Save env_vars encountered in rendering for partial parsing
             project.project_env_vars = project_renderer.ctx_obj.env_vars
-        return (project, profile)
+            return project
 
     # Called in main.py, lib.py, task/base.py
     @classmethod
@@ -274,13 +311,16 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             "snapshots": self._get_config_paths(self.snapshots),
             "sources": self._get_config_paths(self.sources),
             "tests": self._get_config_paths(self.tests),
+            "metrics": self._get_config_paths(self.metrics),
+            "entities": self._get_config_paths(self.entities),
+            "exposures": self._get_config_paths(self.exposures),
         }
 
-    def get_unused_resource_config_paths(
+    def warn_for_unused_resource_config_paths(
         self,
         resource_fqns: Mapping[str, PathSet],
         disabled: PathSet,
-    ) -> List[FQNPath]:
+    ) -> None:
         """Return a list of lists of strings, where each inner list of strings
         represents a type + FQN path of a resource configuration that is not
         used.
@@ -294,23 +334,13 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
             for config_path in config_paths:
                 if not _is_config_used(config_path, fqns):
-                    unused_resource_config_paths.append((resource_type,) + config_path)
+                    resource_path = ".".join(i for i in ((resource_type,) + config_path))
-        return unused_resource_config_paths
+                    unused_resource_config_paths.append(resource_path)
 
-    def warn_for_unused_resource_config_paths(
+        if len(unused_resource_config_paths) == 0:
-        self,
-        resource_fqns: Mapping[str, PathSet],
-        disabled: PathSet,
-    ) -> None:
-        unused = self.get_unused_resource_config_paths(resource_fqns, disabled)
-        if len(unused) == 0:
             return
 
-        msg = UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE.format(
+        warn_or_error(UnusedResourceConfigPath(unused_config_paths=unused_resource_config_paths))
-            len(unused), "\n".join("- {}".format(".".join(u)) for u in unused)
-        )
-
-        warn_or_error(msg, log_fmt=warning_tag("{}"))
 
     def load_dependencies(self, base_only=False) -> Mapping[str, "RuntimeConfig"]:
         if self.dependencies is None:
@@ -477,6 +507,9 @@ class UnsetProfileConfig(RuntimeConfig):
                 "snapshots": self.snapshots,
                 "sources": self.sources,
                 "tests": self.tests,
+                "metrics": self.metrics,
+                "entities": self.entities,
+                "exposures": self.exposures,
                 "vars": self.vars.to_dict(),
                 "require-dbt-version": [v.to_version_string() for v in self.dbt_version],
                 "config-version": self.config_version,
@@ -537,6 +570,9 @@ class UnsetProfileConfig(RuntimeConfig):
             query_comment=project.query_comment,
             sources=project.sources,
             tests=project.tests,
+            metrics=project.metrics,
+            entities=project.entities,
+            exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
             unrendered=project.unrendered,
@@ -583,14 +619,6 @@ class UnsetProfileConfig(RuntimeConfig):
         return cls.from_parts(project=project, profile=profile, args=args)
 
 
-UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE = """\
-Configuration paths exist in your dbt_project.yml file which do not \
-apply to any resources.
-There are {} unused configuration paths:
-{}
-"""
-
-
 def _is_config_used(path, fqns):
     if fqns:
         for fqn in fqns:

core/dbt/constants.py

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

core/dbt/context/base.py

@@ -4,8 +4,10 @@ from typing import Any, Dict, NoReturn, Optional, Mapping, Iterable, Set, List
 
 from dbt import flags
 from dbt import tracking
+from dbt import utils
 from dbt.clients.jinja import get_rendered
 from dbt.clients.yaml_helper import yaml, safe_load, SafeLoader, Loader, Dumper  # noqa: F401
+from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
 from dbt.contracts.graph.compiled import CompiledResource
 from dbt.exceptions import (
     CompilationException,
@@ -14,9 +16,8 @@ from dbt.exceptions import (
     raise_parsing_error,
     disallow_secret_env_var,
 )
-from dbt.logger import SECRET_ENV_PREFIX
 from dbt.events.functions import fire_event, get_invocation_id
-from dbt.events.types import MacroEventInfo, MacroEventDebug
+from dbt.events.types import JinjaLogInfo, JinjaLogDebug
 from dbt.version import __version__ as dbt_version
 
 # These modules are added to the context. Consider alternative
@@ -126,7 +127,7 @@ class ContextMeta(type):
 
 
 class Var:
-    UndefinedVarError = "Required var '{}' not found in config:\nVars " "supplied to {} = {}"
+    UndefinedVarError = "Required var '{}' not found in config:\nVars supplied to {} = {}"
     _VAR_NOTSET = object()
 
     def __init__(
@@ -305,7 +306,12 @@ class BaseContext(metaclass=ContextMeta):
             return_value = default
 
         if return_value is not None:
-            self.env_vars[var] = return_value
+            # If the environment variable is set from a default, store a string indicating
+            # that so we can skip partial parsing.  Otherwise the file will be scheduled for
+            # reparsing. If the default changes, the file will have been updated and therefore
+            # will be scheduled for reparsing anyways.
+            self.env_vars[var] = return_value if var in os.environ else DEFAULT_ENV_PLACEHOLDER
+
             return return_value
         else:
             msg = f"Env var required but not provided: '{var}'"
@@ -552,9 +558,9 @@ class BaseContext(metaclass=ContextMeta):
             {% endmacro %}"
         """
         if info:
-            fire_event(MacroEventInfo(msg=msg))
+            fire_event(JinjaLogInfo(msg=msg))
         else:
-            fire_event(MacroEventDebug(msg=msg))
+            fire_event(JinjaLogDebug(msg=msg))
         return ""
 
     @contextproperty
@@ -682,6 +688,19 @@ class BaseContext(metaclass=ContextMeta):
                 dict_diff.update({k: dict_a[k]})
         return dict_diff
 
+    @contextmember
+    @staticmethod
+    def local_md5(value: str) -> str:
+        """Calculates an MD5 hash of the given string.
+        It's called "local_md5" to emphasize that it runs locally in dbt (in jinja context) and not an MD5 SQL command.
+
+        :param value: The value to hash
+
+        Usage:
+            {% set value_hash = local_md5("hello world") %}
+        """
+        return utils.md5(value)
+
 
 def generate_base_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:
     ctx = BaseContext(cli_vars)

core/dbt/context/configured.py

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