Compare commits

..

1 Commits

Author SHA1 Message Date
Callum McCann
2da925aa25 Adding entity node to core (#6648)
* first draft

* finishing first commit

* adding testing project

* adding changie

* cleaning

* removing blocks

* fixing proto error message

* updates to events

* fixing issues

* adding test dimension

* updating schemas

* updating manfiest.json

* removing old versions from compatability

* updating

* fixes

* fixing more bugs caught by tests

* updating tests
2023-01-31 09:03:06 -06:00
858 changed files with 35879 additions and 114868 deletions

View File

@@ -1,19 +1,13 @@
[bumpversion]
current_version = 1.8.0a1
parse = (?P<major>[\d]+) # major version number
\.(?P<minor>[\d]+) # minor version number
\.(?P<patch>[\d]+) # patch version number
(?P<prerelease> # optional pre-release - ex: a1, b2, rc25
(?P<prekind>a|b|rc) # pre-release type
(?P<num>[\d]+) # pre-release version number
current_version = 1.5.0a1
parse = (?P<major>\d+)
\.(?P<minor>\d+)
\.(?P<patch>\d+)
((?P<prekind>a|b|rc)
(?P<pre>\d+) # pre-release version num
)?
( # optional nightly release indicator
\.(?P<nightly>dev[0-9]+) # ex: .dev02142023
)? # expected matches: `1.15.0`, `1.5.0a11`, `1.5.0a1.dev123`, `1.5.0.dev123457`, expected failures: `1`, `1.5`, `1.5.2-a1`, `text1.5.0`
serialize =
{major}.{minor}.{patch}{prekind}{num}.{nightly}
{major}.{minor}.{patch}.{nightly}
{major}.{minor}.{patch}{prekind}{num}
{major}.{minor}.{patch}{prekind}{pre}
{major}.{minor}.{patch}
commit = False
tag = False
@@ -27,11 +21,9 @@ values =
rc
final
[bumpversion:part:num]
[bumpversion:part:pre]
first_value = 1
[bumpversion:part:nightly]
[bumpversion:file:core/setup.py]
[bumpversion:file:core/dbt/version.py]

View File

@@ -3,9 +3,6 @@
For information on prior major and minor releases, see their changelogs:
* [1.7](https://github.com/dbt-labs/dbt-core/blob/1.7.latest/CHANGELOG.md)
* [1.6](https://github.com/dbt-labs/dbt-core/blob/1.6.latest/CHANGELOG.md)
* [1.5](https://github.com/dbt-labs/dbt-core/blob/1.5.latest/CHANGELOG.md)
* [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)
* [1.3](https://github.com/dbt-labs/dbt-core/blob/1.3.latest/CHANGELOG.md)
* [1.2](https://github.com/dbt-labs/dbt-core/blob/1.2.latest/CHANGELOG.md)

View File

@@ -1,6 +0,0 @@
kind: Dependencies
body: Begin using DSI 0.4.x
time: 2023-10-31T13:19:54.750009-07:00
custom:
Author: QMalcolm peterallenwebb
PR: "8892"

View File

@@ -1,6 +0,0 @@
kind: Dependencies
body: Update typing-extensions version to >=4.4
time: 2023-11-06T13:00:51.062386-08:00
custom:
Author: tlento
PR: "9012"

View File

@@ -1,6 +0,0 @@
kind: Docs
body: fix get_custom_database docstring
time: 2023-11-06T12:31:57.525711Z
custom:
Author: LeoTheGriff
Issue: "9003"

View File

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

View File

@@ -1,6 +0,0 @@
kind: Features
body: Initial implementation of unit testing
time: 2023-08-02T14:50:11.391992-04:00
custom:
Author: gshank
Issue: "8287"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Unit test manifest artifacts and selection
time: 2023-08-28T10:18:25.958929-04:00
custom:
Author: gshank
Issue: "8295"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Support config with tags & meta for unit tests
time: 2023-09-06T23:47:41.059915-04:00
custom:
Author: michelleark
Issue: "8294"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Enable inline csv fixtures in unit tests
time: 2023-09-28T16:32:05.573776-04:00
custom:
Author: gshank
Issue: "8626"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Add drop_schema_named macro
time: 2023-10-17T14:36:20.612289-07:00
custom:
Author: colin-rogers-dbt
Issue: "8025"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Add exports to SavedQuery spec
time: 2023-10-31T13:20:22.448158-07:00
custom:
Author: QMalcolm peterallenwebb
Issue: "8892"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Support unit testing incremental models
time: 2023-11-01T10:18:45.341781-04:00
custom:
Author: michelleark
Issue: "8422"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Add support of csv file fixtures to unit testing
time: 2023-11-06T19:47:52.501495-06:00
custom:
Author: emmyoop
Issue: "8290"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Unit tests support --defer and state:modified
time: 2023-11-07T23:10:06.376588-05:00
custom:
Author: jtcohen6
Issue: "8517"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Support setting export configs hierarchically via saved query and project configs
time: 2023-11-10T15:42:55.042317-08:00
custom:
Author: QMalcolm
Issue: "8956"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Support source inputs in unit tests
time: 2023-11-11T19:11:50.870494-05:00
custom:
Author: gshank
Issue: "8507"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Use daff to render diff displayed in stdout when unit test fails
time: 2023-11-14T10:15:55.689307-05:00
custom:
Author: michelleark
Issue: "8558"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Move unit testing to test command
time: 2023-11-16T14:40:06.121336-05:00
custom:
Author: gshank
Issue: "8979"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Support --empty flag for schema-only dry runs
time: 2023-11-16T23:40:49.96651-05:00
custom:
Author: michelleark
Issue: "8971"

View File

@@ -1,6 +0,0 @@
kind: Features
body: Support unit tests in non-root packages
time: 2023-11-30T13:09:48.206007-05:00
custom:
Author: gshank
Issue: "8285"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: For packages installed with tarball method, fetch metadata to resolve nested dependencies
time: 2023-10-13T13:09:43.188308-04:00
custom:
Author: adamlopez
Issue: "8621"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Fix partial parsing not working for semantic model change
time: 2023-10-16T16:39:53.05058-07:00
custom:
Author: ChenyuLInx
Issue: "8859"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Handle unknown `type_code` for model contracts
time: 2023-10-24T11:01:51.980781-06:00
custom:
Author: dbeatty10
Issue: 8877 8353

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Add back contract enforcement for temporary tables on postgres
time: 2023-10-24T14:55:04.051683-05:00
custom:
Author: emmyoop
Issue: "8857"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Rework get_catalog implementation to retain previous adapter interface semantics
time: 2023-10-24T15:54:00.628086-04:00
custom:
Author: peterallenwebb
Issue: "8846"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Add version to fqn when version==0
time: 2023-10-26T00:25:36.259356-05:00
custom:
Author: aranke
Issue: "8836"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Fix cased comparison in catalog-retrieval function.
time: 2023-10-30T09:37:34.258612-04:00
custom:
Author: peterallenwebb
Issue: "8939"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Catalog queries now assign the correct type to materialized views
time: 2023-10-31T00:53:45.486203-04:00
custom:
Author: mikealfare
Issue: "8864"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Fix compilation exception running empty seed file and support new Integer agate data_type
time: 2023-10-31T14:48:37.774871-04:00
custom:
Author: gshank
Issue: "8895"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Make relation filtering None-tolerant for maximal flexibility across adapters.
time: 2023-11-01T15:58:24.552054-04:00
custom:
Author: peterallenwebb
Issue: "8974"

View File

@@ -1,7 +0,0 @@
kind: Fixes
body: Update run_results.json from previous versions of dbt to support deferral and
rerun from failure
time: 2023-11-06T15:59:33.677915-05:00
custom:
Author: jtcohen6 peterallenwebb
Issue: "9010"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Fix git repository with subdirectory for Deps
time: 2023-11-07T09:23:58.214271-08:00
custom:
Author: ChenyuLInx
Issue: "9000"

View File

@@ -1,7 +0,0 @@
kind: Fixes
body: Use MANIFEST.in to recursively include all jinja templates; fixes issue where
some templates were not included in the distribution
time: 2023-11-07T09:41:30.121733-05:00
custom:
Author: mikealfare
Issue: "9016"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Fix formatting of tarball information in packages-lock.yml
time: 2023-11-13T11:49:56.437007-08:00
custom:
Author: ChenyuLInx QMalcolm
Issue: "9062"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: Use seed file from disk for unit testing if rows not specified in YAML config
time: 2023-11-13T15:45:35.008565Z
custom:
Author: aranke
Issue: "8652"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: 'deps: Lock git packages to commit SHA during resolution'
time: 2023-11-27T15:43:10.122069+01:00
custom:
Author: jtcohen6
Issue: "9050"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: 'deps: Use PackageRenderer to read package-lock.json'
time: 2023-11-27T15:43:47.842423+01:00
custom:
Author: jtcohen6
Issue: "9127"

View File

@@ -1,6 +0,0 @@
kind: Fixes
body: 'Get sources working again in dbt docs generate'
time: 2023-11-28T15:52:25.738256Z
custom:
Author: aranke
Issue: "9119"

View File

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

View File

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

View File

@@ -1,6 +0,0 @@
kind: Under the Hood
body: Add unit testing functional tests
time: 2023-09-12T19:05:06.023126-04:00
custom:
Author: gshank
Issue: "8512"

View File

@@ -1,6 +0,0 @@
kind: Under the Hood
body: Add a no-op runner for Saved Qeury
time: 2023-10-27T14:00:48.4755-07:00
custom:
Author: ChenyuLInx
Issue: "8893"

View File

@@ -1,7 +0,0 @@
kind: Under the Hood
body: Move CatalogRelationTypes test case to the shared test suite to be reused by
adapter maintainers
time: 2023-11-03T19:52:22.694394-04:00
custom:
Author: mikealfare
Issue: "8952"

View File

@@ -1,6 +0,0 @@
kind: Under the Hood
body: Treat SystemExit as an interrupt if raised during node execution.
time: 2023-11-06T08:04:22.022179-05:00
custom:
Author: benmosher
Issue: n/a

View File

@@ -1,6 +0,0 @@
kind: Under the Hood
body: Removing unused 'documentable'
time: 2023-11-06T10:57:30.694056-08:00
custom:
Author: QMalcolm
Issue: "8871"

View File

@@ -1,6 +0,0 @@
kind: Under the Hood
body: Cache dbt plugin modules to improve integration test performance
time: 2023-11-07T19:15:46.170151-05:00
custom:
Author: peterallenwebb
Issue: "9029"

View File

@@ -1,7 +0,0 @@
kind: Under the Hood
body: Fix test_current_timestamp_matches_utc test; allow for MacOS runner system clock
variance
time: 2023-11-11T17:53:50.098843-05:00
custom:
Author: mikealfare
Issue: "9057"

View File

@@ -1,6 +0,0 @@
kind: Under the Hood
body: Clean up unused adaptor folders
time: 2023-11-20T13:47:35.923794-08:00
custom:
Author: ChenyuLInx
Issue: "9123"

View File

@@ -4,7 +4,6 @@ headerPath: header.tpl.md
versionHeaderPath: ""
changelogPath: CHANGELOG.md
versionExt: md
envPrefix: "CHANGIE_"
versionFormat: '## dbt-core {{.Version}} - {{.Time.Format "January 02, 2006"}}'
kindFormat: '### {{.Kind}}'
changeFormat: |-
@@ -88,44 +87,32 @@ custom:
footerFormat: |
{{- $contributorDict := dict }}
{{- /* ensure all names in this list are all lowercase for later matching purposes */}}
{{- $core_team := splitList " " .Env.CORE_TEAM }}
{{- /* ensure we always skip snyk and dependabot in addition to the core team */}}
{{- $maintainers := list "dependabot[bot]" "snyk-bot"}}
{{- range $team_member := $core_team }}
{{- $team_member_lower := lower $team_member }}
{{- $maintainers = append $maintainers $team_member_lower }}
{{- end }}
{{- /* any names added to this list should be all lowercase for later matching purposes */}}
{{- $core_team := list "michelleark" "peterallenwebb" "emmyoop" "nathaniel-may" "gshank" "leahwicz" "chenyulinx" "stu-k" "iknox-fa" "versusfacit" "mcknight-42" "jtcohen6" "aranke" "dependabot[bot]" "snyk-bot" "colin-rogers-dbt" }}
{{- range $change := .Changes }}
{{- $authorList := splitList " " $change.Custom.Author }}
{{- /* loop through all authors for a single changelog */}}
{{- range $author := $authorList }}
{{- $authorLower := lower $author }}
{{- /* we only want to include non-core team contributors */}}
{{- if not (has $authorLower $maintainers)}}
{{- if not (has $authorLower $core_team)}}
{{- $changeList := splitList " " $change.Custom.Author }}
{{- $IssueList := list }}
{{- /* Docs kind link back to dbt-docs instead of dbt-core issues */}}
{{- $changeLink := $change.Kind }}
{{- if or (eq $change.Kind "Dependencies") (eq $change.Kind "Security") }}
{{- $changes := splitList " " $change.Custom.PR }}
{{- range $issueNbr := $changes }}
{{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $issueNbr }}
{{- $IssueList = append $IssueList $changeLink }}
{{- end -}}
{{- $changeLink = "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $change.Custom.PR }}
{{- else if eq $change.Kind "Docs"}}
{{- $changeLink = "[dbt-docs/#nbr](https://github.com/dbt-labs/dbt-docs/issues/nbr)" | replace "nbr" $change.Custom.Issue }}
{{- else }}
{{- $changes := splitList " " $change.Custom.Issue }}
{{- range $issueNbr := $changes }}
{{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/issues/nbr)" | replace "nbr" $issueNbr }}
{{- $IssueList = append $IssueList $changeLink }}
{{- end -}}
{{- $changeLink = "[#nbr](https://github.com/dbt-labs/dbt-core/issues/nbr)" | replace "nbr" $change.Custom.Issue }}
{{- end }}
{{- /* check if this contributor has other changes associated with them already */}}
{{- if hasKey $contributorDict $author }}
{{- $contributionList := get $contributorDict $author }}
{{- $contributionList = concat $contributionList $IssueList }}
{{- $contributionList = append $contributionList $changeLink }}
{{- $contributorDict := set $contributorDict $author $contributionList }}
{{- else }}
{{- $contributionList := $IssueList }}
{{- $contributionList := list $changeLink }}
{{- $contributorDict := set $contributorDict $author $contributionList }}
{{- end }}
{{- end}}

4
.gitattributes vendored
View File

@@ -1,6 +1,2 @@
core/dbt/include/index.html binary
tests/functional/artifacts/data/state/*/manifest.json binary
core/dbt/docs/build/html/searchindex.js binary
core/dbt/docs/build/html/index.html binary
performance/runner/Cargo.lock binary
core/dbt/events/types_pb2.py binary

46
.github/CODEOWNERS vendored
View File

@@ -11,7 +11,44 @@
# As a default for areas with no assignment,
# the core team as a whole will be assigned
* @dbt-labs/core-team
* @dbt-labs/core
# Changes to GitHub configurations including Actions
/.github/ @leahwicz
### LANGUAGE
# Language core modules
/core/dbt/config/ @dbt-labs/core-language
/core/dbt/context/ @dbt-labs/core-language
/core/dbt/contracts/ @dbt-labs/core-language
/core/dbt/deps/ @dbt-labs/core-language
/core/dbt/events/ @dbt-labs/core-language # structured logging
/core/dbt/parser/ @dbt-labs/core-language
# Language misc files
/core/dbt/dataclass_schema.py @dbt-labs/core-language
/core/dbt/hooks.py @dbt-labs/core-language
/core/dbt/node_types.py @dbt-labs/core-language
/core/dbt/semver.py @dbt-labs/core-language
### EXECUTION
# Execution core modules
/core/dbt/graph/ @dbt-labs/core-execution
/core/dbt/task/ @dbt-labs/core-execution
# Execution misc files
/core/dbt/compilation.py @dbt-labs/core-execution
/core/dbt/flags.py @dbt-labs/core-execution
/core/dbt/lib.py @dbt-labs/core-execution
/core/dbt/main.py @dbt-labs/core-execution
/core/dbt/profiler.py @dbt-labs/core-execution
/core/dbt/selected_resources.py @dbt-labs/core-execution
/core/dbt/tracking.py @dbt-labs/core-execution
/core/dbt/version.py @dbt-labs/core-execution
### ADAPTERS
@@ -23,7 +60,6 @@
# Postgres plugin
/plugins/ @dbt-labs/core-adapters
/plugins/postgres/setup.py @dbt-labs/core-adapters
# Functional tests for adapter plugins
/tests/adapter @dbt-labs/core-adapters
@@ -35,9 +71,5 @@
# Perf regression testing framework
# This excludes the test project files itself since those aren't specific
# framework changes (excluded by not setting an owner next to it- no owner)
/performance @nathaniel-may
/performance @nathaniel-may
/performance/projects
### ARTIFACTS
/schemas/dbt @dbt-labs/cloud-artifacts

View File

@@ -1,58 +0,0 @@
name: 🛠️ Implementation
description: This is an implementation ticket intended for use by the maintainers of dbt-core
title: "[<project>] <title>"
labels: ["user docs"]
body:
- type: markdown
attributes:
value: This is an implementation ticket intended for use by the maintainers of dbt-core
- type: checkboxes
attributes:
label: Housekeeping
description: >
A couple friendly reminders:
1. Remove the `user docs` label if the scope of this work does not require changes to https://docs.getdbt.com/docs: no end-user interface (e.g. yml spec, CLI, error messages, etc) or functional changes
2. Link any blocking issues in the "Blocked on" field under the "Core devs & maintainers" project.
options:
- label: I am a maintainer of dbt-core
required: true
- type: textarea
attributes:
label: Short description
description: |
Describe the scope of the ticket, a high-level implementation approach and any tradeoffs to consider
validations:
required: true
- type: textarea
attributes:
label: Acceptance criteria
description: |
What is the definition of done for this ticket? Include any relevant edge cases and/or test cases
validations:
required: true
- type: textarea
attributes:
label: Impact to Other Teams
description: |
Will this change impact other teams? Include details of the kinds of changes required (new tests, code changes, related tickets) and _add the relevant `Impact:[team]` label_.
placeholder: |
Example: This change impacts `dbt-redshift` because the tests will need to be modified. The `Impact:[Adapter]` label has been added.
validations:
required: true
- type: textarea
attributes:
label: Will backports be required?
description: |
Will this change need to be backported to previous versions? Add details, possible blockers to backporting and _add the relevant backport labels `backport 1.x.latest`_
placeholder: |
Example: Backport to 1.6.latest, 1.5.latest and 1.4.latest. Since 1.4 isn't using click, the backport may be complicated. The `backport 1.6.latest`, `backport 1.5.latest` and `backport 1.4.latest` labels have been added.
validations:
required: true
- type: textarea
attributes:
label: Context
description: |
Provide the "why", motivation, and alternative approaches considered -- linking to previous refinement issues, spikes, Notion docs as appropriate
validations:
validations:
required: false

2
.github/_README.md vendored
View File

@@ -197,7 +197,7 @@ ___
```yaml
- name: Configure AWS credentials from Test account
uses: aws-actions/configure-aws-credentials@v2
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 }}

View File

@@ -35,7 +35,7 @@ jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v1
- name: Wrangle latest tag
id: is_latest
uses: ./.github/actions/latest-wrangler

View File

@@ -13,7 +13,7 @@ jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v1
- name: Wrangle latest tag
id: is_latest
uses: ./.github/actions/latest-wrangler

View File

@@ -28,10 +28,3 @@ updates:
schedule:
interval: "weekly"
rebase-strategy: "disabled"
# github dependencies
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "weekly"
rebase-strategy: "disabled"

View File

@@ -4,30 +4,20 @@ resolves #
Include the number of the issue addressed by this PR above if applicable.
PRs for code changes without an associated issue *will not be merged*.
See CONTRIBUTING.md for more information.
Add the `user docs` label to this PR if it will need docs changes. An
issue will get opened in docs.getdbt.com upon successful merge of this PR.
-->
### Problem
### Description
<!---
Describe the problem this PR is solving. What is the application state
before this PR is merged?
-->
### Solution
<!---
Describe the way this PR solves the above problem. Add as much detail as you
can to help reviewers understand your changes. Include any alternatives and
tradeoffs you considered.
Describe the Pull Request here. Add any references and info to help reviewers
understand your changes. Include any tradeoffs you considered.
-->
### Checklist
- [ ] I have read [the contributing guide](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md) and understand what's expected of me
- [ ] I have run this code in development and it appears to resolve the stated issue
- [ ] I have read [the contributing guide](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md) and understand what's expected of me
- [ ] I have signed the [CLA](https://docs.getdbt.com/docs/contributor-license-agreements)
- [ ] I have run this code in development and it appears to resolve the stated issue
- [ ] This PR includes tests, or tests are not required/relevant for this PR
- [ ] This PR has no interface changes (e.g. macros, cli, logs, json artifacts, config files, adapter interface, etc) or this PR has already received feedback and approval from Product or DX
- [ ] This PR includes [type annotations](https://docs.python.org/3/library/typing.html) for new and modified functions
- [ ] I have [opened an issue to add/update docs](https://github.com/dbt-labs/docs.getdbt.com/issues/new/choose), or docs changes are not required/relevant for this PR
- [ ] I have run `changie new` to [create a changelog entry](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#adding-a-changelog-entry)

View File

@@ -35,6 +35,6 @@ jobs:
github.event.pull_request.merged
&& contains(github.event.label.name, 'backport')
steps:
- uses: tibdex/backport@v2.0.3
- uses: tibdex/backport@v2.0.2
with:
github_token: ${{ secrets.GITHUB_TOKEN }}

View File

@@ -50,7 +50,7 @@ jobs:
- 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@v1.1.0
uses: emmyoop/changie_bot@v1.0.1
with:
GITHUB_TOKEN: ${{ secrets.FISHTOWN_BOT_PAT }}
commit_author_name: "Github Build Bot"

View File

@@ -2,8 +2,10 @@
# 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 runs on pull_request_target because it requires
# secrets to post comments.
# 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.
@@ -17,7 +19,7 @@
name: Check Changelog Entry
on:
pull_request_target:
pull_request:
types: [opened, reopened, labeled, unlabeled, synchronize]
workflow_dispatch:

View File

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

View File

@@ -1,43 +0,0 @@
# **what?**
# Open an issue in docs.getdbt.com when a PR is labeled `user docs`
# **why?**
# To reduce barriers for keeping docs up to date
# **when?**
# When a PR is labeled `user docs` and is merged. Runs on pull_request_target to run off the workflow already merged,
# not the workflow that existed on the PR branch. This allows old PRs to get comments.
name: Open issues in docs.getdbt.com repo when a PR is labeled
run-name: "Open an issue in docs.getdbt.com for PR #${{ github.event.pull_request.number }}"
on:
pull_request_target:
types: [labeled, closed]
defaults:
run:
shell: bash
permissions:
issues: write # opens new issues
pull-requests: write # comments on PRs
jobs:
open_issues:
# we only want to run this when the PR has been merged or the label in the labeled event is `user docs`. Otherwise it runs the
# risk of duplicaton of issues being created due to merge and label both triggering this workflow to run and neither having
# generating the comment before the other runs. This lives here instead of the shared workflow because this is where we
# decide if it should run or not.
if: |
(github.event.pull_request.merged == true) &&
((github.event.action == 'closed' && contains( github.event.pull_request.labels.*.name, 'user docs')) ||
(github.event.action == 'labeled' && github.event.label.name == 'user docs'))
uses: dbt-labs/actions/.github/workflows/open-issue-in-repo.yml@main
with:
issue_repository: "dbt-labs/docs.getdbt.com"
issue_title: "Docs Changes Needed from ${{ github.event.repository.name }} PR #${{ github.event.pull_request.number }}"
issue_body: "At a minimum, update body to include a link to the page on docs.getdbt.com requiring updates and what part(s) of the page you would like to see updated."
secrets: inherit

View File

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

View File

@@ -18,8 +18,8 @@ permissions:
issues: write
jobs:
call-creation-action:
uses: dbt-labs/actions/.github/workflows/jira-creation-actions.yml@main
call-label-action:
uses: dbt-labs/jira-actions/.github/workflows/jira-creation.yml@main
secrets:
JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}

View File

@@ -19,7 +19,7 @@ permissions:
jobs:
call-label-action:
uses: dbt-labs/actions/.github/workflows/jira-label-actions.yml@main
uses: dbt-labs/jira-actions/.github/workflows/jira-label.yml@main
secrets:
JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}

View File

@@ -19,8 +19,8 @@ on:
permissions: read-all
jobs:
call-transition-action:
uses: dbt-labs/actions/.github/workflows/jira-transition-actions.yml@main
call-label-action:
uses: dbt-labs/jira-actions/.github/workflows/jira-transition.yml@main
secrets:
JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}

View File

@@ -33,11 +33,6 @@ defaults:
run:
shell: bash
# top-level adjustments can be made here
env:
# number of parallel processes to spawn for python integration testing
PYTHON_INTEGRATION_TEST_WORKERS: 5
jobs:
code-quality:
name: code-quality
@@ -47,10 +42,10 @@ jobs:
steps:
- name: Check out the repository
uses: actions/checkout@v3
uses: actions/checkout@v2
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v4.3.0
with:
python-version: '3.8'
@@ -58,8 +53,12 @@ jobs:
run: |
python -m pip install --user --upgrade pip
python -m pip --version
make dev
python -m pip install pre-commit
pre-commit --version
python -m pip install mypy==0.942
mypy --version
python -m pip install -r requirements.txt
python -m pip install -r dev-requirements.txt
dbt --version
- name: Run pre-commit hooks
@@ -74,17 +73,18 @@ jobs:
strategy:
fail-fast: false
matrix:
python-version: ["3.8", "3.9", "3.10", "3.11"]
python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
env:
TOXENV: "unit"
PYTEST_ADDOPTS: "-v --color=yes --csv unit_results.csv"
steps:
- name: Check out the repository
uses: actions/checkout@v3
uses: actions/checkout@v2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v4.3.0
with:
python-version: ${{ matrix.python-version }}
@@ -105,80 +105,43 @@ jobs:
CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
- name: Upload Unit Test Coverage to Codecov
if: ${{ matrix.python-version == '3.11' }}
uses: codecov/codecov-action@v3
- uses: actions/upload-artifact@v2
if: always()
with:
token: ${{ secrets.CODECOV_TOKEN }}
flags: unit
integration-metadata:
name: integration test metadata generation
runs-on: ubuntu-latest
outputs:
split-groups: ${{ steps.generate-split-groups.outputs.split-groups }}
include: ${{ steps.generate-include.outputs.include }}
steps:
- name: generate split-groups
id: generate-split-groups
run: |
MATRIX_JSON="["
for B in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
MATRIX_JSON+=$(sed 's/^/"/;s/$/"/' <<< "${B}")
done
MATRIX_JSON="${MATRIX_JSON//\"\"/\", \"}"
MATRIX_JSON+="]"
echo "split-groups=${MATRIX_JSON}"
echo "split-groups=${MATRIX_JSON}" >> $GITHUB_OUTPUT
- name: generate include
id: generate-include
run: |
INCLUDE=('"python-version":"3.8","os":"windows-latest"' '"python-version":"3.8","os":"macos-latest"' )
INCLUDE_GROUPS="["
for include in ${INCLUDE[@]}; do
for group in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
INCLUDE_GROUPS+=$(sed 's/$/, /' <<< "{\"split-group\":\"${group}\",${include}}")
done
done
INCLUDE_GROUPS=$(echo $INCLUDE_GROUPS | sed 's/,*$//g')
INCLUDE_GROUPS+="]"
echo "include=${INCLUDE_GROUPS}"
echo "include=${INCLUDE_GROUPS}" >> $GITHUB_OUTPUT
name: unit_results_${{ matrix.python-version }}-${{ steps.date.outputs.date }}.csv
path: unit_results.csv
integration:
name: (${{ matrix.split-group }}) integration test / python ${{ matrix.python-version }} / ${{ matrix.os }}
name: integration test / python ${{ matrix.python-version }} / ${{ matrix.os }}
runs-on: ${{ matrix.os }}
timeout-minutes: 30
needs:
- integration-metadata
timeout-minutes: 45
strategy:
fail-fast: false
matrix:
python-version: ["3.8", "3.9", "3.10", "3.11"]
python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
os: [ubuntu-20.04]
split-group: ${{ fromJson(needs.integration-metadata.outputs.split-groups) }}
include: ${{ fromJson(needs.integration-metadata.outputs.include) }}
include:
- python-version: 3.8
os: windows-latest
- python-version: 3.8
os: macos-latest
env:
TOXENV: integration
PYTEST_ADDOPTS: "-v --color=yes -n4 --csv integration_results.csv"
DBT_INVOCATION_ENV: github-actions
DBT_TEST_USER_1: dbt_test_user_1
DBT_TEST_USER_2: dbt_test_user_2
DBT_TEST_USER_3: dbt_test_user_3
DD_CIVISIBILITY_AGENTLESS_ENABLED: true
DD_API_KEY: ${{ secrets.DATADOG_API_KEY }}
DD_SITE: datadoghq.com
DD_ENV: ci
DD_SERVICE: ${{ github.event.repository.name }}
steps:
- name: Check out the repository
uses: actions/checkout@v3
uses: actions/checkout@v2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v4.3.0
with:
python-version: ${{ matrix.python-version }}
@@ -202,9 +165,7 @@ jobs:
tox --version
- name: Run tests
run: tox -- --ddtrace
env:
PYTEST_ADDOPTS: ${{ format('--splits {0} --group {1}', env.PYTHON_INTEGRATION_TEST_WORKERS, matrix.split-group) }}
run: tox
- name: Get current date
if: always()
@@ -213,35 +174,17 @@ jobs:
CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
- uses: actions/upload-artifact@v3
- uses: actions/upload-artifact@v2
if: always()
with:
name: logs_${{ matrix.python-version }}_${{ matrix.os }}_${{ steps.date.outputs.date }}
path: ./logs
- name: Upload Integration Test Coverage to Codecov
if: ${{ matrix.python-version == '3.11' }}
uses: codecov/codecov-action@v3
- uses: actions/upload-artifact@v2
if: always()
with:
token: ${{ secrets.CODECOV_TOKEN }}
flags: integration
integration-report:
if: ${{ always() }}
name: Integration Test Suite
runs-on: ubuntu-latest
needs: integration
steps:
- name: "Integration Tests Failed"
if: ${{ contains(needs.integration.result, 'failure') || contains(needs.integration.result, 'cancelled') }}
# when this is true the next step won't execute
run: |
echo "::notice title='Integration test suite failed'"
exit 1
- name: "Integration Tests Passed"
run: |
echo "::notice title='Integration test suite passed'"
name: integration_results_${{ matrix.python-version }}_${{ matrix.os }}_${{ steps.date.outputs.date }}.csv
path: integration_results.csv
build:
name: build packages
@@ -250,10 +193,10 @@ jobs:
steps:
- name: Check out the repository
uses: actions/checkout@v3
uses: actions/checkout@v2
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v4.3.0
with:
python-version: '3.8'

View File

@@ -1,265 +0,0 @@
# **what?**
# This workflow models the performance characteristics of a point in time in dbt.
# It runs specific dbt commands on committed projects multiple times to create and
# commit information about the distribution to the current branch. For more information
# see the readme in the performance module at /performance/README.md.
#
# **why?**
# When developing new features, we can take quick performance samples and compare
# them against the commited baseline measurements produced by this workflow to detect
# some performance regressions at development time before they reach users.
#
# **when?**
# This is only run once directly after each release (for non-prereleases). If for some
# reason the results of a run are not satisfactory, it can also be triggered manually.
name: Model Performance Characteristics
on:
# runs after non-prereleases are published.
release:
types: [released]
# run manually from the actions tab
workflow_dispatch:
inputs:
release_id:
description: 'dbt version to model (must be non-prerelease in Pypi)'
type: string
required: true
env:
RUNNER_CACHE_PATH: performance/runner/target/release/runner
# both jobs need to write
permissions:
contents: write
pull-requests: write
jobs:
set-variables:
name: Setting Variables
runs-on: ubuntu-latest
outputs:
cache_key: ${{ steps.variables.outputs.cache_key }}
release_id: ${{ steps.semver.outputs.base-version }}
release_branch: ${{ steps.variables.outputs.release_branch }}
steps:
# explicitly checkout the performance runner from main regardless of which
# version we are modeling.
- name: Checkout
uses: actions/checkout@v3
with:
ref: main
- name: Parse version into parts
id: semver
uses: dbt-labs/actions/parse-semver@v1
with:
version: ${{ github.event.inputs.release_id || github.event.release.tag_name }}
# collect all the variables that need to be used in subsequent jobs
- name: Set variables
id: variables
run: |
# create a cache key that will be used in the next job. without this the
# next job would have to checkout from main and hash the files itself.
echo "cache_key=${{ runner.os }}-${{ hashFiles('performance/runner/Cargo.toml')}}-${{ hashFiles('performance/runner/src/*') }}" >> $GITHUB_OUTPUT
branch_name="${{steps.semver.outputs.major}}.${{steps.semver.outputs.minor}}.latest"
echo "release_branch=$branch_name" >> $GITHUB_OUTPUT
echo "release branch is inferred to be ${branch_name}"
latest-runner:
name: Build or Fetch Runner
runs-on: ubuntu-latest
needs: [set-variables]
env:
RUSTFLAGS: "-D warnings"
steps:
- name: '[DEBUG] print variables'
run: |
echo "all variables defined in set-variables"
echo "cache_key: ${{ needs.set-variables.outputs.cache_key }}"
echo "release_id: ${{ needs.set-variables.outputs.release_id }}"
echo "release_branch: ${{ needs.set-variables.outputs.release_branch }}"
# explicitly checkout the performance runner from main regardless of which
# version we are modeling.
- name: Checkout
uses: actions/checkout@v3
with:
ref: main
# attempts to access a previously cached runner
- uses: actions/cache@v3
id: cache
with:
path: ${{ env.RUNNER_CACHE_PATH }}
key: ${{ needs.set-variables.outputs.cache_key }}
- name: Fetch Rust Toolchain
if: steps.cache.outputs.cache-hit != 'true'
uses: actions-rs/toolchain@v1
with:
profile: minimal
toolchain: stable
override: true
- name: Add fmt
if: steps.cache.outputs.cache-hit != 'true'
run: rustup component add rustfmt
- name: Cargo fmt
if: steps.cache.outputs.cache-hit != 'true'
uses: actions-rs/cargo@v1
with:
command: fmt
args: --manifest-path performance/runner/Cargo.toml --all -- --check
- name: Test
if: steps.cache.outputs.cache-hit != 'true'
uses: actions-rs/cargo@v1
with:
command: test
args: --manifest-path performance/runner/Cargo.toml
- name: Build (optimized)
if: steps.cache.outputs.cache-hit != 'true'
uses: actions-rs/cargo@v1
with:
command: build
args: --release --manifest-path performance/runner/Cargo.toml
# the cache action automatically caches this binary at the end of the job
model:
# depends on `latest-runner` as a separate job so that failures in this job do not prevent
# a successfully tested and built binary from being cached.
needs: [set-variables, latest-runner]
name: Model a release
runs-on: ubuntu-latest
steps:
- name: '[DEBUG] print variables'
run: |
echo "all variables defined in set-variables"
echo "cache_key: ${{ needs.set-variables.outputs.cache_key }}"
echo "release_id: ${{ needs.set-variables.outputs.release_id }}"
echo "release_branch: ${{ needs.set-variables.outputs.release_branch }}"
- name: Setup Python
uses: actions/setup-python@v4
with:
python-version: "3.8"
- name: Install dbt
run: pip install dbt-postgres==${{ needs.set-variables.outputs.release_id }}
- name: Install Hyperfine
run: wget https://github.com/sharkdp/hyperfine/releases/download/v1.11.0/hyperfine_1.11.0_amd64.deb && sudo dpkg -i hyperfine_1.11.0_amd64.deb
# explicitly checkout main to get the latest project definitions
- name: Checkout
uses: actions/checkout@v3
with:
ref: main
# this was built in the previous job so it will be there.
- name: Fetch Runner
uses: actions/cache@v3
id: cache
with:
path: ${{ env.RUNNER_CACHE_PATH }}
key: ${{ needs.set-variables.outputs.cache_key }}
- name: Move Runner
run: mv performance/runner/target/release/runner performance/app
- name: Change Runner Permissions
run: chmod +x ./performance/app
- name: '[DEBUG] ls baseline directory before run'
run: ls -R performance/baselines/
# `${{ github.workspace }}` is used to pass the absolute path
- name: Create directories
run: |
mkdir ${{ github.workspace }}/performance/tmp/
mkdir -p performance/baselines/${{ needs.set-variables.outputs.release_id }}/
# Run modeling with taking 20 samples
- name: Run Measurement
run: |
performance/app model -v ${{ needs.set-variables.outputs.release_id }} -b ${{ github.workspace }}/performance/baselines/ -p ${{ github.workspace }}/performance/projects/ -t ${{ github.workspace }}/performance/tmp/ -n 20
- name: '[DEBUG] ls baseline directory after run'
run: ls -R performance/baselines/
- uses: actions/upload-artifact@v3
with:
name: baseline
path: performance/baselines/${{ needs.set-variables.outputs.release_id }}/
create-pr:
name: Open PR for ${{ matrix.base-branch }}
# depends on `model` as a separate job so that the baseline can be committed to more than one branch
# i.e. release branch and main
needs: [set-variables, latest-runner, model]
runs-on: ubuntu-latest
strategy:
matrix:
include:
- base-branch: refs/heads/main
target-branch: performance-bot/main_${{ needs.set-variables.outputs.release_id }}_${{GITHUB.RUN_ID}}
- base-branch: refs/heads/${{ needs.set-variables.outputs.release_branch }}
target-branch: performance-bot/release_${{ needs.set-variables.outputs.release_id }}_${{GITHUB.RUN_ID}}
steps:
- name: '[DEBUG] print variables'
run: |
echo "all variables defined in set-variables"
echo "cache_key: ${{ needs.set-variables.outputs.cache_key }}"
echo "release_id: ${{ needs.set-variables.outputs.release_id }}"
echo "release_branch: ${{ needs.set-variables.outputs.release_branch }}"
- name: Checkout
uses: actions/checkout@v3
with:
ref: ${{ matrix.base-branch }}
- name: Create PR branch
run: |
git checkout -b ${{ matrix.target-branch }}
git push origin ${{ matrix.target-branch }}
git branch --set-upstream-to=origin/${{ matrix.target-branch }} ${{ matrix.target-branch }}
- uses: actions/download-artifact@v3
with:
name: baseline
path: performance/baselines/${{ needs.set-variables.outputs.release_id }}
- name: '[DEBUG] ls baselines after artifact download'
run: ls -R performance/baselines/
- name: Commit baseline
uses: EndBug/add-and-commit@v9
with:
add: 'performance/baselines/*'
author_name: 'Github Build Bot'
author_email: 'buildbot@fishtownanalytics.com'
message: 'adding performance baseline for ${{ needs.set-variables.outputs.release_id }}'
push: 'origin origin/${{ matrix.target-branch }}'
- name: Create Pull Request
uses: peter-evans/create-pull-request@v5
with:
author: 'Github Build Bot <buildbot@fishtownanalytics.com>'
base: ${{ matrix.base-branch }}
branch: '${{ matrix.target-branch }}'
title: 'Adding performance modeling for ${{needs.set-variables.outputs.release_id}} to ${{ matrix.base-branch }}'
body: 'Committing perf results for tracking for the ${{needs.set-variables.outputs.release_id}}'
labels: |
Skip Changelog
Performance

View File

@@ -1,109 +0,0 @@
# **what?**
# Nightly releases to GitHub and PyPI. This workflow produces the following outcome:
# - generate and validate data for night release (commit SHA, version number, release branch);
# - pass data to release workflow;
# - night release will be pushed to GitHub as a draft release;
# - night build will be pushed to test PyPI;
#
# **why?**
# Ensure an automated and tested release process for nightly builds
#
# **when?**
# This workflow runs on schedule or can be run manually on demand.
name: Nightly Test Release to GitHub and PyPI
on:
workflow_dispatch: # for manual triggering
schedule:
- cron: 0 9 * * *
permissions:
contents: write # this is the permission that allows creating a new release
defaults:
run:
shell: bash
env:
RELEASE_BRANCH: "main"
jobs:
aggregate-release-data:
runs-on: ubuntu-latest
outputs:
commit_sha: ${{ steps.resolve-commit-sha.outputs.release_commit }}
version_number: ${{ steps.nightly-release-version.outputs.number }}
release_branch: ${{ steps.release-branch.outputs.name }}
steps:
- name: "Checkout ${{ github.repository }} Branch ${{ env.RELEASE_BRANCH }}"
uses: actions/checkout@v3
with:
ref: ${{ env.RELEASE_BRANCH }}
- name: "Resolve Commit To Release"
id: resolve-commit-sha
run: |
commit_sha=$(git rev-parse HEAD)
echo "release_commit=$commit_sha" >> $GITHUB_OUTPUT
- name: "Get Current Version Number"
id: version-number-sources
run: |
current_version=`awk -F"current_version = " '{print $2}' .bumpversion.cfg | tr '\n' ' '`
echo "current_version=$current_version" >> $GITHUB_OUTPUT
- name: "Audit Version And Parse Into Parts"
id: semver
uses: dbt-labs/actions/parse-semver@v1.1.0
with:
version: ${{ steps.version-number-sources.outputs.current_version }}
- name: "Get Current Date"
id: current-date
run: echo "date=$(date +'%m%d%Y')" >> $GITHUB_OUTPUT
- name: "Generate Nightly Release Version Number"
id: nightly-release-version
run: |
number="${{ steps.semver.outputs.version }}.dev${{ steps.current-date.outputs.date }}"
echo "number=$number" >> $GITHUB_OUTPUT
- name: "Audit Nightly Release Version And Parse Into Parts"
uses: dbt-labs/actions/parse-semver@v1.1.0
with:
version: ${{ steps.nightly-release-version.outputs.number }}
- name: "Set Release Branch"
id: release-branch
run: |
echo "name=${{ env.RELEASE_BRANCH }}" >> $GITHUB_OUTPUT
log-outputs-aggregate-release-data:
runs-on: ubuntu-latest
needs: [aggregate-release-data]
steps:
- name: "[DEBUG] Log Outputs"
run: |
echo commit_sha : ${{ needs.aggregate-release-data.outputs.commit_sha }}
echo version_number: ${{ needs.aggregate-release-data.outputs.version_number }}
echo release_branch: ${{ needs.aggregate-release-data.outputs.release_branch }}
release-github-pypi:
needs: [aggregate-release-data]
uses: ./.github/workflows/release.yml
with:
sha: ${{ needs.aggregate-release-data.outputs.commit_sha }}
target_branch: ${{ needs.aggregate-release-data.outputs.release_branch }}
version_number: ${{ needs.aggregate-release-data.outputs.version_number }}
build_script_path: "scripts/build-dist.sh"
env_setup_script_path: "scripts/env-setup.sh"
s3_bucket_name: "core-team-artifacts"
package_test_command: "dbt --version"
test_run: true
nightly_release: true
secrets: inherit

View File

@@ -1,7 +1,11 @@
# **what?**
# The purpose of this workflow is to trigger CI to run for each
# release branch and main branch on a regular cadence. If the CI workflow
# fails for a branch, it will post to #dev-core-alerts to raise awareness.
# fails for a branch, it will post to dev-core-alerts to raise awareness.
# The 'aurelien-baudet/workflow-dispatch' Action triggers the existing
# CI worklow file on the given branch to run so that even if we change the
# CI workflow file in the future, the one that is tailored for the given
# release branch will be used.
# **why?**
# Ensures release branches and main are always shippable and not broken.
@@ -24,8 +28,35 @@ on:
permissions: read-all
jobs:
run_tests:
uses: dbt-labs/actions/.github/workflows/release-branch-tests.yml@main
with:
workflows_to_run: '["main.yml"]'
secrets: inherit
kick-off-ci:
name: Kick-off CI
runs-on: ubuntu-latest
strategy:
# must run CI 1 branch at a time b/c the workflow-dispatch Action polls for
# latest run for results and it gets confused when we kick off multiple runs
# at once. There is a race condition so we will just run in sequential order.
max-parallel: 1
fail-fast: false
matrix:
branch: [1.0.latest, 1.1.latest, 1.2.latest, 1.3.latest, main]
steps:
- name: Call CI workflow for ${{ matrix.branch }} branch
id: trigger-step
uses: aurelien-baudet/workflow-dispatch@v2.1.1
with:
workflow: main.yml
ref: ${{ matrix.branch }}
token: ${{ secrets.FISHTOWN_BOT_PAT }}
- name: Post failure to Slack
uses: ravsamhq/notify-slack-action@v1
if: ${{ always() && !contains(steps.trigger-step.outputs.workflow-conclusion,'success') }}
with:
status: ${{ job.status }}
notification_title: 'dbt-core scheduled run of "${{ matrix.branch }}" branch not successful'
message_format: ':x: CI on branch "${{ matrix.branch }}" ${{ steps.trigger-step.outputs.workflow-conclusion }}'
footer: 'Linked failed CI run ${{ steps.trigger-step.outputs.workflow-url }}'
env:
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_DEV_CORE_ALERTS }}

View File

@@ -36,7 +36,7 @@ jobs:
latest: ${{ steps.latest.outputs.latest }}
minor_latest: ${{ steps.latest.outputs.minor_latest }}
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v1
- name: Split version
id: version
run: |
@@ -60,7 +60,7 @@ jobs:
needs: [get_version_meta]
steps:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v2
uses: docker/setup-buildx-action@v1
build_and_push:
name: Build images and push to GHCR
@@ -76,14 +76,14 @@ jobs:
echo "build_arg_value=$BUILD_ARG_VALUE" >> $GITHUB_OUTPUT
- name: Log in to the GHCR
uses: docker/login-action@v2
uses: docker/login-action@v1
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Build and push MAJOR.MINOR.PATCH tag
uses: docker/build-push-action@v5
uses: docker/build-push-action@v2
with:
file: docker/Dockerfile
push: True
@@ -94,7 +94,7 @@ jobs:
ghcr.io/dbt-labs/${{ github.event.inputs.package }}:${{ github.event.inputs.version_number }}
- name: Build and push MINOR.latest tag
uses: docker/build-push-action@v5
uses: docker/build-push-action@v2
if: ${{ needs.get_version_meta.outputs.minor_latest == 'True' }}
with:
file: docker/Dockerfile
@@ -106,7 +106,7 @@ jobs:
ghcr.io/dbt-labs/${{ github.event.inputs.package }}:${{ needs.get_version_meta.outputs.major }}.${{ needs.get_version_meta.outputs.minor }}.latest
- name: Build and push latest tag
uses: docker/build-push-action@v5
uses: docker/build-push-action@v2
if: ${{ needs.get_version_meta.outputs.latest == 'True' }}
with:
file: docker/Dockerfile

View File

@@ -1,110 +1,24 @@
# **what?**
# Release workflow provides the following steps:
# - checkout the given commit;
# - validate version in sources and changelog file for given version;
# - bump the version and generate a changelog if needed;
# - merge all changes to the target branch if needed;
# - run unit and integration tests against given commit;
# - build and package that SHA;
# - release it to GitHub and PyPI with that specific build;
#
# Take the given commit, run unit tests specifically on that sha, build and
# package it, and then release to GitHub and PyPi with that specific build
# **why?**
# Ensure an automated and tested release process
#
# **when?**
# This workflow can be run manually on demand or can be called by other workflows
name: Release to GitHub and PyPI
# **when?**
# This will only run manually with a given sha and version
name: Release to GitHub and PyPi
on:
workflow_dispatch:
inputs:
sha:
description: "The last commit sha in the release"
type: string
required: true
target_branch:
description: "The branch to release from"
type: string
required: true
description: 'The last commit sha in the release'
required: true
version_number:
description: "The release version number (i.e. 1.0.0b1)"
type: string
required: true
build_script_path:
description: "Build script path"
type: string
default: "scripts/build-dist.sh"
required: true
env_setup_script_path:
description: "Environment setup script path"
type: string
default: "scripts/env-setup.sh"
required: false
s3_bucket_name:
description: "AWS S3 bucket name"
type: string
default: "core-team-artifacts"
required: true
package_test_command:
description: "Package test command"
type: string
default: "dbt --version"
required: true
test_run:
description: "Test run (Publish release as draft)"
type: boolean
default: true
required: false
nightly_release:
description: "Nightly release to dev environment"
type: boolean
default: false
required: false
workflow_call:
inputs:
sha:
description: "The last commit sha in the release"
type: string
required: true
target_branch:
description: "The branch to release from"
type: string
required: true
version_number:
description: "The release version number (i.e. 1.0.0b1)"
type: string
required: true
build_script_path:
description: "Build script path"
type: string
default: "scripts/build-dist.sh"
required: true
env_setup_script_path:
description: "Environment setup script path"
type: string
default: "scripts/env-setup.sh"
required: false
s3_bucket_name:
description: "AWS S3 bucket name"
type: string
default: "core-team-artifacts"
required: true
package_test_command:
description: "Package test command"
type: string
default: "dbt --version"
required: true
test_run:
description: "Test run (Publish release as draft)"
type: boolean
default: true
required: false
nightly_release:
description: "Nightly release to dev environment"
type: boolean
default: false
required: false
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
@@ -114,116 +28,175 @@ defaults:
shell: bash
jobs:
log-inputs:
name: Log Inputs
unit:
name: Unit test
runs-on: ubuntu-latest
env:
TOXENV: "unit"
steps:
- name: "[DEBUG] Print Variables"
- name: Check out the repository
uses: actions/checkout@v2
with:
persist-credentials: false
ref: ${{ github.event.inputs.sha }}
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Install python dependencies
run: |
echo The last commit sha in the release: ${{ inputs.sha }}
echo The branch to release from: ${{ inputs.target_branch }}
echo The release version number: ${{ inputs.version_number }}
echo Build script path: ${{ inputs.build_script_path }}
echo Environment setup script path: ${{ inputs.env_setup_script_path }}
echo AWS S3 bucket name: ${{ inputs.s3_bucket_name }}
echo Package test command: ${{ inputs.package_test_command }}
echo Test run: ${{ inputs.test_run }}
echo Nightly release: ${{ inputs.nightly_release }}
pip install --user --upgrade pip
pip install tox
pip --version
tox --version
bump-version-generate-changelog:
name: Bump package version, Generate changelog
- name: Run tox
run: tox
uses: dbt-labs/dbt-release/.github/workflows/release-prep.yml@main
with:
sha: ${{ inputs.sha }}
version_number: ${{ inputs.version_number }}
target_branch: ${{ inputs.target_branch }}
env_setup_script_path: ${{ inputs.env_setup_script_path }}
test_run: ${{ inputs.test_run }}
nightly_release: ${{ inputs.nightly_release }}
secrets: inherit
log-outputs-bump-version-generate-changelog:
name: "[Log output] Bump package version, Generate changelog"
if: ${{ !failure() && !cancelled() }}
needs: [bump-version-generate-changelog]
build:
name: build packages
runs-on: ubuntu-latest
steps:
- name: Print variables
- name: Check out the repository
uses: actions/checkout@v2
with:
persist-credentials: false
ref: ${{ github.event.inputs.sha }}
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Install python dependencies
run: |
echo Final SHA : ${{ needs.bump-version-generate-changelog.outputs.final_sha }}
echo Changelog path: ${{ needs.bump-version-generate-changelog.outputs.changelog_path }}
pip install --user --upgrade pip
pip install --upgrade setuptools wheel twine check-wheel-contents
pip --version
build-test-package:
name: Build, Test, Package
if: ${{ !failure() && !cancelled() }}
needs: [bump-version-generate-changelog]
- name: Build distributions
run: ./scripts/build-dist.sh
uses: dbt-labs/dbt-release/.github/workflows/build.yml@main
- name: Show distributions
run: ls -lh dist/
with:
sha: ${{ needs.bump-version-generate-changelog.outputs.final_sha }}
version_number: ${{ inputs.version_number }}
changelog_path: ${{ needs.bump-version-generate-changelog.outputs.changelog_path }}
build_script_path: ${{ inputs.build_script_path }}
s3_bucket_name: ${{ inputs.s3_bucket_name }}
package_test_command: ${{ inputs.package_test_command }}
test_run: ${{ inputs.test_run }}
nightly_release: ${{ inputs.nightly_release }}
- name: Check distribution descriptions
run: |
twine check dist/*
secrets:
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
- name: Check wheel contents
run: |
check-wheel-contents dist/*.whl --ignore W007,W008
- uses: actions/upload-artifact@v2
with:
name: dist
path: |
dist/
!dist/dbt-${{github.event.inputs.version_number}}.tar.gz
test-build:
name: verify packages
needs: [build, unit]
runs-on: ubuntu-latest
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Install python dependencies
run: |
pip install --user --upgrade pip
pip install --upgrade wheel
pip --version
- uses: actions/download-artifact@v2
with:
name: dist
path: dist/
- name: Show distributions
run: ls -lh dist/
- name: Install wheel distributions
run: |
find ./dist/*.whl -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
- name: Check wheel distributions
run: |
dbt --version
- name: Install source distributions
run: |
find ./dist/*.gz -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
- name: Check source distributions
run: |
dbt --version
github-release:
name: GitHub Release
if: ${{ !failure() && !cancelled() }}
needs: [bump-version-generate-changelog, build-test-package]
needs: test-build
uses: dbt-labs/dbt-release/.github/workflows/github-release.yml@main
runs-on: ubuntu-latest
with:
sha: ${{ needs.bump-version-generate-changelog.outputs.final_sha }}
version_number: ${{ inputs.version_number }}
changelog_path: ${{ needs.bump-version-generate-changelog.outputs.changelog_path }}
test_run: ${{ inputs.test_run }}
steps:
- uses: actions/download-artifact@v2
with:
name: dist
path: '.'
# Need to set an output variable because env variables can't be taken as input
# This is needed for the next step with releasing to GitHub
- name: Find release type
id: release_type
env:
IS_PRERELEASE: ${{ contains(github.event.inputs.version_number, 'rc') || contains(github.event.inputs.version_number, 'b') }}
run: |
echo "isPrerelease=$IS_PRERELEASE" >> $GITHUB_OUTPUT
- name: Creating GitHub Release
uses: softprops/action-gh-release@v1
with:
name: dbt-core v${{github.event.inputs.version_number}}
tag_name: v${{github.event.inputs.version_number}}
prerelease: ${{ steps.release_type.outputs.isPrerelease }}
target_commitish: ${{github.event.inputs.sha}}
body: |
[Release notes](https://github.com/dbt-labs/dbt-core/blob/main/CHANGELOG.md)
files: |
dbt_postgres-${{github.event.inputs.version_number}}-py3-none-any.whl
dbt_core-${{github.event.inputs.version_number}}-py3-none-any.whl
dbt-postgres-${{github.event.inputs.version_number}}.tar.gz
dbt-core-${{github.event.inputs.version_number}}.tar.gz
pypi-release:
name: PyPI Release
name: Pypi release
needs: [github-release]
runs-on: ubuntu-latest
uses: dbt-labs/dbt-release/.github/workflows/pypi-release.yml@main
needs: github-release
with:
version_number: ${{ inputs.version_number }}
test_run: ${{ inputs.test_run }}
environment: PypiProd
steps:
- uses: actions/download-artifact@v2
with:
name: dist
path: 'dist'
secrets:
PYPI_API_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
TEST_PYPI_API_TOKEN: ${{ secrets.TEST_PYPI_API_TOKEN }}
slack-notification:
name: Slack Notification
if: ${{ failure() && (!inputs.test_run || inputs.nightly_release) }}
needs:
[
bump-version-generate-changelog,
build-test-package,
github-release,
pypi-release,
]
uses: dbt-labs/dbt-release/.github/workflows/slack-post-notification.yml@main
with:
status: "failure"
secrets:
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_DEV_CORE_ALERTS }}
- name: Publish distribution to PyPI
uses: pypa/gh-action-pypi-publish@v1.4.2
with:
password: ${{ secrets.PYPI_API_TOKEN }}

View File

@@ -1,30 +0,0 @@
# **what?**
# Cleanup branches left over from automation and testing. Also cleanup
# draft releases from release testing.
# **why?**
# The automations are leaving behind branches and releases that clutter
# the repository. Sometimes we need them to debug processes so we don't
# want them immediately deleted. Running on Saturday to avoid running
# at the same time as an actual release to prevent breaking a release
# mid-release.
# **when?**
# Mainly on a schedule of 12:00 Saturday.
# Manual trigger can also run on demand
name: Repository Cleanup
on:
schedule:
- cron: '0 12 * * SAT' # At 12:00 on Saturday - details in `why` above
workflow_dispatch: # for manual triggering
permissions:
contents: write
jobs:
cleanup-repo:
uses: dbt-labs/actions/.github/workflows/repository-cleanup.yml@main
secrets: inherit

View File

@@ -37,17 +37,17 @@ jobs:
steps:
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Checkout dbt repo
uses: actions/checkout@v3
uses: actions/checkout@v2.3.4
with:
path: ${{ env.DBT_REPO_DIRECTORY }}
- name: Checkout schemas.getdbt.com repo
uses: actions/checkout@v3
uses: actions/checkout@v2.3.4
with:
repository: dbt-labs/schemas.getdbt.com
ref: 'main'
@@ -83,7 +83,7 @@ jobs:
fi
- name: Upload schema diff
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2.2.4
if: ${{ failure() }}
with:
name: 'schema_schanges.txt'

View File

@@ -18,41 +18,11 @@ on:
permissions: read-all
# top-level adjustments can be made here
env:
# number of parallel processes to spawn for python testing
PYTHON_INTEGRATION_TEST_WORKERS: 5
jobs:
integration-metadata:
name: integration test metadata generation
runs-on: ubuntu-latest
outputs:
split-groups: ${{ steps.generate-split-groups.outputs.split-groups }}
steps:
- name: generate split-groups
id: generate-split-groups
run: |
MATRIX_JSON="["
for B in $(seq 1 ${{ env.PYTHON_INTEGRATION_TEST_WORKERS }}); do
MATRIX_JSON+=$(sed 's/^/"/;s/$/"/' <<< "${B}")
done
MATRIX_JSON="${MATRIX_JSON//\"\"/\", \"}"
MATRIX_JSON+="]"
echo "split-groups=${MATRIX_JSON}" >> $GITHUB_OUTPUT
# run the performance measurements on the current or default branch
test-schema:
name: Test Log Schema
runs-on: ubuntu-20.04
timeout-minutes: 30
needs:
- integration-metadata
strategy:
fail-fast: false
matrix:
split-group: ${{ fromJson(needs.integration-metadata.outputs.split-groups) }}
env:
# turns warnings into errors
RUSTFLAGS: "-D warnings"
@@ -60,8 +30,6 @@ jobs:
LOG_DIR: "/home/runner/work/dbt-core/dbt-core/logs"
# tells integration tests to output into json format
DBT_LOG_FORMAT: "json"
# tell eventmgr to convert logging events into bytes
DBT_TEST_BINARY_SERIALIZATION: "true"
# Additional test users
DBT_TEST_USER_1: dbt_test_user_1
DBT_TEST_USER_2: dbt_test_user_2
@@ -69,12 +37,12 @@ jobs:
steps:
- name: checkout dev
uses: actions/checkout@v3
uses: actions/checkout@v2
with:
persist-credentials: false
- name: Setup Python
uses: actions/setup-python@v4
uses: actions/setup-python@v2.2.2
with:
python-version: "3.8"
@@ -95,14 +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
env:
PYTEST_ADDOPTS: ${{ format('--splits {0} --group {1}', env.PYTHON_INTEGRATION_TEST_WORKERS, matrix.split-group) }}
test-schema-report:
name: Log Schema Test Suite
runs-on: ubuntu-latest
needs: test-schema
steps:
- name: "[Notification] Log test suite passes"
run: |
echo "::notice title="Log test suite passes""

View File

@@ -1,155 +0,0 @@
# **what?**
# This workflow will test all test(s) at the input path given number of times to determine if it's flaky or not. You can test with any supported OS/Python combination.
# This is batched in 10 to allow more test iterations faster.
# **why?**
# Testing if a test is flaky and if a previously flaky test has been fixed. This allows easy testing on supported python versions and OS combinations.
# **when?**
# This is triggered manually from dbt-core.
name: Flaky Tester
on:
workflow_dispatch:
inputs:
branch:
description: 'Branch to check out'
type: string
required: true
default: 'main'
test_path:
description: 'Path to single test to run (ex: tests/functional/retry/test_retry.py::TestRetry::test_fail_fast)'
type: string
required: true
default: 'tests/functional/...'
python_version:
description: 'Version of Python to Test Against'
type: choice
options:
- '3.8'
- '3.9'
- '3.10'
- '3.11'
os:
description: 'OS to run test in'
type: choice
options:
- 'ubuntu-latest'
- 'macos-latest'
- 'windows-latest'
num_runs_per_batch:
description: 'Max number of times to run the test per batch. We always run 10 batches.'
type: number
required: true
default: '50'
permissions: read-all
defaults:
run:
shell: bash
jobs:
debug:
runs-on: ubuntu-latest
steps:
- name: "[DEBUG] Output Inputs"
run: |
echo "Branch: ${{ inputs.branch }}"
echo "test_path: ${{ inputs.test_path }}"
echo "python_version: ${{ inputs.python_version }}"
echo "os: ${{ inputs.os }}"
echo "num_runs_per_batch: ${{ inputs.num_runs_per_batch }}"
pytest:
runs-on: ${{ inputs.os }}
strategy:
# run all batches, even if one fails. This informs how flaky the test may be.
fail-fast: false
# using a matrix to speed up the jobs since the matrix will run in parallel when runners are available
matrix:
batch: ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10"]
env:
PYTEST_ADDOPTS: "-v --color=yes -n4 --csv integration_results.csv"
DBT_TEST_USER_1: dbt_test_user_1
DBT_TEST_USER_2: dbt_test_user_2
DBT_TEST_USER_3: dbt_test_user_3
DD_CIVISIBILITY_AGENTLESS_ENABLED: true
DD_API_KEY: ${{ secrets.DATADOG_API_KEY }}
DD_SITE: datadoghq.com
DD_ENV: ci
DD_SERVICE: ${{ github.event.repository.name }}
steps:
- name: "Checkout code"
uses: actions/checkout@v3
with:
ref: ${{ inputs.branch }}
- name: "Setup Python"
uses: actions/setup-python@v4
with:
python-version: "${{ inputs.python_version }}"
- name: "Setup Dev Environment"
run: make dev
- name: "Set up postgres (linux)"
if: inputs.os == 'ubuntu-latest'
run: make setup-db
# mac and windows don't use make due to limitations with docker with those runners in GitHub
- name: "Set up postgres (macos)"
if: inputs.os == 'macos-latest'
uses: ./.github/actions/setup-postgres-macos
- name: "Set up postgres (windows)"
if: inputs.os == 'windows-latest'
uses: ./.github/actions/setup-postgres-windows
- name: "Test Command"
id: command
run: |
test_command="python -m pytest ${{ inputs.test_path }}"
echo "test_command=$test_command" >> $GITHUB_OUTPUT
- name: "Run test ${{ inputs.num_runs_per_batch }} times"
id: pytest
run: |
set +e
for ((i=1; i<=${{ inputs.num_runs_per_batch }}; i++))
do
echo "Running pytest iteration $i..."
python -m pytest --ddtrace ${{ inputs.test_path }}
exit_code=$?
if [[ $exit_code -eq 0 ]]; then
success=$((success + 1))
echo "Iteration $i: Success"
else
failure=$((failure + 1))
echo "Iteration $i: Failure"
fi
echo
echo "==========================="
echo "Successful runs: $success"
echo "Failed runs: $failure"
echo "==========================="
echo
done
echo "failure=$failure" >> $GITHUB_OUTPUT
- name: "Success and Failure Summary: ${{ inputs.os }}/Python ${{ inputs.python_version }}"
run: |
echo "Batch: ${{ matrix.batch }}"
echo "Successful runs: ${{ steps.pytest.outputs.success }}"
echo "Failed runs: ${{ steps.pytest.outputs.failure }}"
- name: "Error for Failures"
if: ${{ steps.pytest.outputs.failure }}
run: |
echo "Batch ${{ matrix.batch }} failed ${{ steps.pytest.outputs.failure }} of ${{ inputs.num_runs_per_batch }} tests"
exit 1

View File

@@ -24,8 +24,10 @@ permissions:
jobs:
triage_label:
if: contains(github.event.issue.labels.*.name, 'awaiting_response')
uses: dbt-labs/actions/.github/workflows/swap-labels.yml@main
with:
add_label: "triage"
remove_label: "awaiting_response"
secrets: inherit
runs-on: ubuntu-latest
steps:
- name: initial labeling
uses: andymckay/labeler@master
with:
add-labels: "triage"
remove-labels: "awaiting_response"

View File

@@ -20,9 +20,106 @@ on:
description: 'The version number to bump to (ex. 1.2.0, 1.3.0b1)'
required: true
permissions:
contents: write
pull-requests: write
jobs:
version_bump_and_changie:
uses: dbt-labs/actions/.github/workflows/version-bump.yml@main
with:
version_number: ${{ inputs.version_number }}
secrets: inherit # ok since what we are calling is internally maintained
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
- uses: actions/setup-python@v2
with:
python-version: "3.8"
- name: Install python dependencies
run: |
python3 -m venv env
source env/bin/activate
pip install --upgrade pip
- name: Add Homebrew to PATH
run: |
echo "/home/linuxbrew/.linuxbrew/bin:/home/linuxbrew/.linuxbrew/sbin" >> $GITHUB_PATH
- name: Install Homebrew packages
run: |
brew install pre-commit
brew tap miniscruff/changie https://github.com/miniscruff/changie
brew install changie
- name: Audit Version and Parse Into Parts
id: semver
uses: dbt-labs/actions/parse-semver@v1
with:
version: ${{ github.event.inputs.version_number }}
- name: Set branch value
id: variables
run: |
echo "BRANCH_NAME=prep-release/${{ github.event.inputs.version_number }}_$GITHUB_RUN_ID" >> $GITHUB_OUTPUT
- name: Create PR branch
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 ${{ github.event.inputs.version_number }} major
git status
- name: Run changie
run: |
if [[ ${{ steps.semver.outputs.is-pre-release }} -eq 1 ]]
then
changie batch ${{ steps.semver.outputs.base-version }} --move-dir '${{ steps.semver.outputs.base-version }}' --prerelease '${{ steps.semver.outputs.pre-release }}'
else
changie batch ${{ steps.semver.outputs.base-version }} --include '${{ steps.semver.outputs.base-version }}' --remove-prereleases
fi
changie merge
git status
# this step will fail on whitespace errors but also correct them
- name: Remove trailing whitespace
continue-on-error: true
run: |
pre-commit run trailing-whitespace --files .bumpversion.cfg CHANGELOG.md .changes/*
git status
# this step will fail on newline errors but also correct them
- name: Removing extra newlines
continue-on-error: true
run: |
pre-commit run end-of-file-fixer --files .bumpversion.cfg CHANGELOG.md .changes/*
git status
- name: Commit version bump to branch
uses: EndBug/add-and-commit@v7
with:
author_name: 'Github Build Bot'
author_email: 'buildbot@fishtownanalytics.com'
message: 'Bumping version to ${{ github.event.inputs.version_number }} and generate CHANGELOG'
branch: '${{ steps.variables.outputs.BRANCH_NAME }}'
push: 'origin origin/${{ steps.variables.outputs.BRANCH_NAME }}'
- name: Create Pull Request
uses: peter-evans/create-pull-request@v3
with:
author: 'Github Build Bot <buildbot@fishtownanalytics.com>'
base: ${{github.ref}}
title: 'Bumping version to ${{ github.event.inputs.version_number }} and generate changelog'
branch: '${{ steps.variables.outputs.BRANCH_NAME }}'
labels: |
Skip Changelog

4
.gitignore vendored
View File

@@ -11,7 +11,6 @@ __pycache__/
env*/
dbt_env/
build/
!tests/functional/build
!core/dbt/docs/build
develop-eggs/
dist/
@@ -29,8 +28,6 @@ var/
.mypy_cache/
.dmypy.json
logs/
.user.yml
profiles.yml
# PyInstaller
# Usually these files are written by a python script from a template
@@ -54,7 +51,6 @@ coverage.xml
*,cover
.hypothesis/
test.env
makefile.test.env
*.pytest_cache/

View File

@@ -1,7 +1,8 @@
# Configuration for pre-commit hooks (see https://pre-commit.com/).
# Eventually the hooks described here will be run as tests before merging each PR.
exclude: ^(core/dbt/docs/build/|core/dbt/events/types_pb2.py)
# TODO: remove global exclusion of tests when testing overhaul is complete
exclude: ^(test/|core/dbt/docs/build/)
# Force all unspecified python hooks to run python 3.8
default_language_version:
@@ -37,7 +38,7 @@ repos:
alias: flake8-check
stages: [manual]
- repo: https://github.com/pre-commit/mirrors-mypy
rev: v1.4.1
rev: v0.942
hooks:
- id: mypy
# N.B.: Mypy is... a bit fragile.

View File

@@ -10,9 +10,6 @@
For information on prior major and minor releases, see their changelogs:
* [1.7](https://github.com/dbt-labs/dbt-core/blob/1.7.latest/CHANGELOG.md)
* [1.6](https://github.com/dbt-labs/dbt-core/blob/1.6.latest/CHANGELOG.md)
* [1.5](https://github.com/dbt-labs/dbt-core/blob/1.5.latest/CHANGELOG.md)
* [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)
* [1.3](https://github.com/dbt-labs/dbt-core/blob/1.3.latest/CHANGELOG.md)
* [1.2](https://github.com/dbt-labs/dbt-core/blob/1.2.latest/CHANGELOG.md)

View File

@@ -5,10 +5,10 @@
1. [About this document](#about-this-document)
2. [Getting the code](#getting-the-code)
3. [Setting up an environment](#setting-up-an-environment)
4. [Running dbt-core in development](#running-dbt-core-in-development)
4. [Running `dbt` in development](#running-dbt-core-in-development)
5. [Testing dbt-core](#testing)
6. [Debugging](#debugging)
7. [Adding or modifying a changelog entry](#adding-or-modifying-a-changelog-entry)
7. [Adding a changelog entry](#adding-a-changelog-entry)
8. [Submitting a Pull Request](#submitting-a-pull-request)
## About this document
@@ -56,7 +56,7 @@ There are some tools that will be helpful to you in developing locally. While th
These are the tools used in `dbt-core` development and testing:
- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.8, 3.9, 3.10 and 3.11
- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, 3.8, 3.9, 3.10 and 3.11
- [`pytest`](https://docs.pytest.org/en/latest/) to define, discover, and run tests
- [`flake8`](https://flake8.pycqa.org/en/latest/) for code linting
- [`black`](https://github.com/psf/black) for code formatting
@@ -113,7 +113,7 @@ When installed in this way, any changes you make to your local copy of the sourc
With your virtualenv activated, the `dbt` script should point back to the source code you've cloned on your machine. You can verify this by running `which dbt`. This command should show you a path to an executable in your virtualenv.
Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as necessary to connect to your target databases. It may be a good idea to add a new profile pointing to a local Postgres instance, or a specific test sandbox within your data warehouse if appropriate. Make sure to create a profile before running integration tests.
Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as necessary to connect to your target databases. It may be a good idea to add a new profile pointing to a local Postgres instance, or a specific test sandbox within your data warehouse if appropriate.
## Testing
@@ -163,7 +163,7 @@ suites.
#### `tox`
[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.8, Python 3.9, Python 3.10 and Python 3.11 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py38`. The configuration for these tests in located in `tox.ini`.
[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.7, Python 3.8, Python 3.9, Python 3.10 and Python 3.11 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
#### `pytest`
@@ -171,10 +171,12 @@ Finally, you can also run a specific test or group of tests using [`pytest`](htt
```sh
# run all unit tests in a file
python3 -m pytest tests/unit/test_graph.py
python3 -m pytest test/unit/test_graph.py
# run a specific unit test
python3 -m pytest tests/unit/test_graph.py::GraphTest::test__dependency_list
# run specific Postgres functional tests
python3 -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
# run specific Postgres integration tests (old way)
python3 -m pytest -m profile_postgres test/integration/074_postgres_unlogged_table_tests
# run specific Postgres integration tests (new way)
python3 -m pytest tests/functional/sources
```
@@ -183,8 +185,9 @@ python3 -m pytest tests/functional/sources
### Unit, Integration, Functional?
Here are some general rules for adding tests:
* unit tests (`tests/unit`) dont need to access a database; "pure Python" tests should be written as unit tests
* functional tests (`tests/functional`) cover anything that interacts with a database, namely adapter
* unit tests (`test/unit` & `tests/unit`) dont 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

View File

@@ -9,7 +9,7 @@ ENV DEBIAN_FRONTEND noninteractive
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
software-properties-common gpg-agent \
software-properties-common \
&& add-apt-repository ppa:git-core/ppa -y \
&& apt-get dist-upgrade -y \
&& apt-get install -y --no-install-recommends \
@@ -30,9 +30,16 @@ RUN apt-get update \
unixodbc-dev \
&& add-apt-repository ppa:deadsnakes/ppa \
&& apt-get install -y \
python-is-python3 \
python-dev-is-python3 \
python \
python-dev \
python3-pip \
python3.6 \
python3.6-dev \
python3-pip \
python3.6-venv \
python3.7 \
python3.7-dev \
python3.7-venv \
python3.8 \
python3.8-dev \
python3.8-venv \

View File

@@ -6,42 +6,29 @@ ifeq ($(USE_DOCKER),true)
DOCKER_CMD := docker-compose run --rm test
endif
#
# To override CI_flags, create a file at this repo's root dir named `makefile.test.env`. Fill it
# with any ENV_VAR overrides required by your test environment, e.g.
# DBT_TEST_USER_1=user
# LOG_DIR="dir with a space in it"
#
# Warn: Restrict each line to one variable only.
#
ifeq (./makefile.test.env,$(wildcard ./makefile.test.env))
include ./makefile.test.env
endif
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=$(if $(DBT_TEST_USER_1),$(DBT_TEST_USER_1),dbt_test_user_1)\
DBT_TEST_USER_2=$(if $(DBT_TEST_USER_2),$(DBT_TEST_USER_2),dbt_test_user_2)\
DBT_TEST_USER_3=$(if $(DBT_TEST_USER_3),$(DBT_TEST_USER_3),dbt_test_user_3)\
RUSTFLAGS=$(if $(RUSTFLAGS),$(RUSTFLAGS),"-D warnings")\
LOG_DIR=$(if $(LOG_DIR),$(LOG_DIR),./logs)\
DBT_LOG_FORMAT=$(if $(DBT_LOG_FORMAT),$(DBT_LOG_FORMAT),json)
DBT_TEST_USER_1=dbt_test_user_1\
DBT_TEST_USER_2=dbt_test_user_2\
DBT_TEST_USER_3=dbt_test_user_3\
RUSTFLAGS="-D warnings"\
LOG_DIR=./logs\
DBT_LOG_FORMAT=json
.PHONY: dev_req
dev_req: ## Installs dbt-* packages in develop mode along with only development dependencies.
@\
pip install -r dev-requirements.txt
pip install -r editable-requirements.txt
pip install -r dev-requirements.txt -r editable-requirements.txt
.PHONY: dev
dev: dev_req ## Installs dbt-* packages in develop mode along with development dependencies and pre-commit.
@\
pre-commit install
.PHONY: proto_types
proto_types: ## generates google protobuf python file from types.proto
protoc -I=./core/dbt/events --python_out=./core/dbt/events ./core/dbt/events/types.proto
.PHONY: mypy
mypy: .env ## Runs mypy against staged changes for static type checking.
@\
@@ -79,7 +66,7 @@ test: .env ## Runs unit tests with py and code checks against staged changes.
.PHONY: integration
integration: .env ## Runs postgres integration tests with py-integration
@\
$(CI_FLAGS) $(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.
@@ -89,9 +76,9 @@ integration-fail-fast: .env ## Runs postgres integration tests with py-integrati
.PHONY: interop
interop: clean
@\
mkdir $(LOG_DIR) && \
mkdir $(LOGS_DIR) && \
$(CI_FLAGS) $(DOCKER_CMD) tox -e py-integration -- -nauto && \
LOG_DIR=$(LOG_DIR) cargo run --manifest-path test/interop/log_parsing/Cargo.toml
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.

View File

@@ -21,7 +21,7 @@ These select statements, or "models", form a dbt project. Models frequently buil
## Getting started
- [Install dbt](https://docs.getdbt.com/docs/get-started/installation)
- [Install dbt](https://docs.getdbt.com/docs/installation)
- Read the [introduction](https://docs.getdbt.com/docs/introduction/) and [viewpoint](https://docs.getdbt.com/docs/about/viewpoint/)
## Join the dbt Community

View File

@@ -1,13 +0,0 @@
ignore:
- ".github"
- ".changes"
coverage:
status:
project:
default:
target: auto
threshold: 0.1% # Reduce noise by ignoring rounding errors in coverage drops
patch:
default:
target: auto
threshold: 80%

View File

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

View File

@@ -7,12 +7,12 @@ from dbt.exceptions import DbtRuntimeError
@dataclass
class Column:
# Note: This is automatically used by contract code
# No-op conversions (INTEGER => INT) have been removed.
# Any adapter that wants to take advantage of "translate_type"
# should create a ClassVar with the appropriate conversions.
TYPE_LABELS: ClassVar[Dict[str, str]] = {
"STRING": "TEXT",
"TIMESTAMP": "TIMESTAMP",
"FLOAT": "FLOAT",
"INTEGER": "INT",
"BOOLEAN": "BOOLEAN",
}
column: str
dtype: str
@@ -60,7 +60,6 @@ class Column:
"float",
"double precision",
"float8",
"double",
]
def is_integer(self) -> bool:

View File

@@ -72,7 +72,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
TYPE: str = NotImplemented
def __init__(self, profile: AdapterRequiredConfig) -> None:
def __init__(self, profile: AdapterRequiredConfig):
self.profile = profile
self.thread_connections: Dict[Hashable, Connection] = {}
self.lock: RLock = flags.MP_CONTEXT.RLock()
@@ -400,7 +400,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
@abc.abstractmethod
def execute(
self, sql: str, auto_begin: bool = False, fetch: bool = False, limit: Optional[int] = None
self, sql: str, auto_begin: bool = False, fetch: bool = False
) -> Tuple[AdapterResponse, agate.Table]:
"""Execute the given SQL.
@@ -408,28 +408,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
:param bool auto_begin: If set, and dbt is not currently inside a
transaction, automatically begin one.
:param bool fetch: If set, fetch results.
:param int limit: If set, limits the result set
:return: A tuple of the query status and results (empty if fetch=False).
:rtype: Tuple[AdapterResponse, agate.Table]
"""
raise dbt.exceptions.NotImplementedError("`execute` is not implemented for this adapter!")
def add_select_query(self, sql: str) -> Tuple[Connection, Any]:
"""
This was added here because base.impl.BaseAdapter.get_column_schema_from_query expects it to be here.
That method wouldn't work unless the adapter used sql.impl.SQLAdapter, sql.connections.SQLConnectionManager
or defined this method on <Adapter>ConnectionManager before passing it in to <Adapter>Adapter.
See https://github.com/dbt-labs/dbt-core/issues/8396 for more information.
"""
raise dbt.exceptions.NotImplementedError(
"`add_select_query` is not implemented for this adapter!"
)
@classmethod
def data_type_code_to_name(cls, type_code: Union[int, str]) -> str:
"""Get the string representation of the data type from the type_code."""
# https://peps.python.org/pep-0249/#type-objects
raise dbt.exceptions.NotImplementedError(
"`data_type_code_to_name` is not implemented for this adapter!"
)

View File

@@ -2,57 +2,47 @@ import abc
from concurrent.futures import as_completed, Future
from contextlib import contextmanager
from datetime import datetime
from enum import Enum
import time
from itertools import chain
from typing import (
Any,
Optional,
Tuple,
Callable,
Dict,
Iterable,
Iterator,
Type,
Dict,
Any,
List,
Mapping,
Optional,
Iterator,
Set,
Tuple,
Type,
TypedDict,
Union,
)
from dbt.adapters.capability import Capability, CapabilityDict
from dbt.contracts.graph.nodes import ColumnLevelConstraint, ConstraintType, ModelLevelConstraint
import agate
import pytz
from dbt.exceptions import (
DbtInternalError,
DbtRuntimeError,
DbtValidationError,
MacroArgTypeError,
MacroResultError,
QuoteConfigTypeError,
NotImplementedError,
NullRelationCacheAttemptedError,
NullRelationDropAttemptedError,
QuoteConfigTypeError,
RelationReturnedMultipleResultsError,
RenameToNoneAttemptedError,
DbtRuntimeError,
SnapshotTargetIncompleteError,
SnapshotTargetNotSnapshotTableError,
UnexpectedNonTimestampError,
UnexpectedNullError,
UnexpectedNonTimestampError,
)
from dbt.adapters.protocol import AdapterConfig
from dbt.clients.agate_helper import (
empty_table,
get_column_value_uncased,
merge_tables,
table_from_rows,
Integer,
from dbt.adapters.protocol import (
AdapterConfig,
ConnectionManagerProtocol,
)
from dbt.clients.agate_helper import empty_table, merge_tables, table_from_rows
from dbt.clients.jinja import MacroGenerator
from dbt.contracts.graph.manifest import Manifest, MacroManifest
from dbt.contracts.graph.nodes import ResultNode
@@ -63,12 +53,10 @@ from dbt.events.types import (
CodeExecution,
CodeExecutionStatus,
CatalogGenerationError,
ConstraintNotSupported,
ConstraintNotEnforced,
)
from dbt.utils import filter_null_values, executor, cast_to_str, AttrDict
from dbt.utils import filter_null_values, executor, cast_to_str
from dbt.adapters.base.connections import Connection, AdapterResponse, BaseConnectionManager
from dbt.adapters.base.connections import Connection, AdapterResponse
from dbt.adapters.base.meta import AdapterMeta, available
from dbt.adapters.base.relation import (
ComponentName,
@@ -78,19 +66,11 @@ from dbt.adapters.base.relation import (
)
from dbt.adapters.base import Column as BaseColumn
from dbt.adapters.base import Credentials
from dbt.adapters.cache import RelationsCache, _make_ref_key_dict
from dbt import deprecations
from dbt.adapters.cache import RelationsCache, _make_ref_key_msg
GET_CATALOG_MACRO_NAME = "get_catalog"
GET_CATALOG_RELATIONS_MACRO_NAME = "get_catalog_relations"
FRESHNESS_MACRO_NAME = "collect_freshness"
GET_RELATION_LAST_MODIFIED_MACRO_NAME = "get_relation_last_modified"
class ConstraintSupport(str, Enum):
ENFORCED = "enforced"
NOT_ENFORCED = "not_enforced"
NOT_SUPPORTED = "not_supported"
def _expect_row_value(key: str, row: agate.Row):
@@ -119,7 +99,7 @@ def _catalog_filter_schemas(manifest: Manifest) -> Callable[[agate.Row], bool]:
return test
def _utc(dt: Optional[datetime], source: Optional[BaseRelation], field_name: str) -> datetime:
def _utc(dt: Optional[datetime], source: BaseRelation, field_name: str) -> datetime:
"""If dt has a timezone, return a new datetime that's in UTC. Otherwise,
assume the datetime is already for UTC and add the timezone.
"""
@@ -171,12 +151,6 @@ class PythonJobHelper:
raise NotImplementedError("PythonJobHelper submit function is not implemented yet")
class FreshnessResponse(TypedDict):
max_loaded_at: datetime
snapshotted_at: datetime
age: float # age in seconds
class BaseAdapter(metaclass=AdapterMeta):
"""The BaseAdapter provides an abstract base class for adapters.
@@ -203,7 +177,6 @@ class BaseAdapter(metaclass=AdapterMeta):
- truncate_relation
- rename_relation
- get_columns_in_relation
- get_column_schema_from_query
- expand_column_types
- list_relations_without_caching
- is_cancelable
@@ -224,25 +197,13 @@ class BaseAdapter(metaclass=AdapterMeta):
Relation: Type[BaseRelation] = BaseRelation
Column: Type[BaseColumn] = BaseColumn
ConnectionManager: Type[BaseConnectionManager]
ConnectionManager: Type[ConnectionManagerProtocol]
# A set of clobber config fields accepted by this adapter
# for use in materializations
AdapterSpecificConfigs: Type[AdapterConfig] = AdapterConfig
CONSTRAINT_SUPPORT = {
ConstraintType.check: ConstraintSupport.NOT_SUPPORTED,
ConstraintType.not_null: ConstraintSupport.ENFORCED,
ConstraintType.unique: ConstraintSupport.NOT_ENFORCED,
ConstraintType.primary_key: ConstraintSupport.NOT_ENFORCED,
ConstraintType.foreign_key: ConstraintSupport.ENFORCED,
}
# This static member variable can be overriden in concrete adapter
# implementations to indicate adapter support for optional capabilities.
_capabilities = CapabilityDict({})
def __init__(self, config) -> None:
def __init__(self, config):
self.config = config
self.cache = RelationsCache()
self.connections = self.ConnectionManager(config)
@@ -294,7 +255,7 @@ class BaseAdapter(metaclass=AdapterMeta):
@available.parse(lambda *a, **k: ("", empty_table()))
def execute(
self, sql: str, auto_begin: bool = False, fetch: bool = False, limit: Optional[int] = None
self, sql: str, auto_begin: bool = False, fetch: bool = False
) -> Tuple[AdapterResponse, agate.Table]:
"""Execute the given SQL. This is a thin wrapper around
ConnectionManager.execute.
@@ -303,53 +264,21 @@ class BaseAdapter(metaclass=AdapterMeta):
:param bool auto_begin: If set, and dbt is not currently inside a
transaction, automatically begin one.
:param bool fetch: If set, fetch results.
:param Optional[int] limit: If set, only fetch n number of rows
:return: A tuple of the query status and results (empty if fetch=False).
:rtype: Tuple[AdapterResponse, agate.Table]
"""
return self.connections.execute(sql=sql, auto_begin=auto_begin, fetch=fetch, limit=limit)
def validate_sql(self, sql: str) -> AdapterResponse:
"""Submit the given SQL to the engine for validation, but not execution.
This should throw an appropriate exception if the input SQL is invalid, although
in practice that will generally be handled by delegating to an existing method
for execution and allowing the error handler to take care of the rest.
:param str sql: The sql to validate
"""
raise NotImplementedError("`validate_sql` is not implemented for this adapter!")
@available.parse(lambda *a, **k: [])
def get_column_schema_from_query(self, sql: str) -> List[BaseColumn]:
"""Get a list of the Columns with names and data types from the given sql."""
_, cursor = self.connections.add_select_query(sql)
columns = [
self.Column.create(
column_name, self.connections.data_type_code_to_name(column_type_code)
)
# https://peps.python.org/pep-0249/#description
for column_name, column_type_code, *_ in cursor.description
]
return columns
return self.connections.execute(sql=sql, auto_begin=auto_begin, fetch=fetch)
@available.parse(lambda *a, **k: ("", empty_table()))
def get_partitions_metadata(self, table: str) -> Tuple[agate.Table]:
"""
TODO: Can we move this to dbt-bigquery?
Obtain partitions metadata for a BigQuery partitioned table.
"""Obtain partitions metadata for a BigQuery partitioned table.
:param str table: a partitioned table id, in standard SQL format.
:param str table_id: a partitioned table id, in standard SQL format.
:return: a partition metadata tuple, as described in
https://cloud.google.com/bigquery/docs/creating-partitioned-tables#getting_partition_metadata_using_meta_tables.
:rtype: agate.Table
"""
if hasattr(self.connections, "get_partitions_metadata"):
return self.connections.get_partitions_metadata(table=table)
else:
raise NotImplementedError(
"`get_partitions_metadata` is not implemented for this adapter!"
)
return self.connections.get_partitions_metadata(table=table)
###
# Methods that should never be overridden
@@ -422,7 +351,7 @@ class BaseAdapter(metaclass=AdapterMeta):
return {
self.Relation.create_from(self.config, node).without_identifier()
for node in manifest.nodes.values()
if (node.is_relational and not node.is_ephemeral_model and not node.is_external_node)
if (node.is_relational and not node.is_ephemeral_model)
}
def _get_catalog_schemas(self, manifest: Manifest) -> SchemaSearchMap:
@@ -435,30 +364,7 @@ class BaseAdapter(metaclass=AdapterMeta):
lowercase strings.
"""
info_schema_name_map = SchemaSearchMap()
relations = self._get_catalog_relations(manifest)
for relation in relations:
info_schema_name_map.add(relation)
# result is a map whose keys are information_schema Relations without
# identifiers that have appropriate database prefixes, and whose values
# are sets of lowercase schema names that are valid members of those
# databases
return info_schema_name_map
def _get_catalog_relations_by_info_schema(
self, relations
) -> Dict[InformationSchema, List[BaseRelation]]:
relations_by_info_schema: Dict[InformationSchema, List[BaseRelation]] = dict()
for relation in relations:
info_schema = relation.information_schema_only()
if info_schema not in relations_by_info_schema:
relations_by_info_schema[info_schema] = []
relations_by_info_schema[info_schema].append(relation)
return relations_by_info_schema
def _get_catalog_relations(self, manifest: Manifest) -> List[BaseRelation]:
nodes = chain(
nodes: Iterator[ResultNode] = chain(
[
node
for node in manifest.nodes.values()
@@ -466,12 +372,17 @@ class BaseAdapter(metaclass=AdapterMeta):
],
manifest.sources.values(),
)
relations = [self.Relation.create_from(self.config, n) for n in nodes]
return relations
for node in nodes:
relation = self.Relation.create_from(self.config, node)
info_schema_name_map.add(relation)
# result is a map whose keys are information_schema Relations without
# identifiers that have appropriate database prefixes, and whose values
# are sets of lowercase schema names that are valid members of those
# databases
return info_schema_name_map
def _relations_cache_for_schemas(
self, manifest: Manifest, cache_schemas: Optional[Set[BaseRelation]] = None
self, manifest: Manifest, cache_schemas: Set[BaseRelation] = None
) -> None:
"""Populate the relations cache for the given schemas. Returns an
iterable of the schemas populated, as strings.
@@ -498,17 +409,16 @@ class BaseAdapter(metaclass=AdapterMeta):
# it's possible that there were no relations in some schemas. We want
# to insert the schemas we query into the cache's `.schemas` attribute
# so we can check it later
cache_update: Set[Tuple[Optional[str], str]] = set()
cache_update: Set[Tuple[Optional[str], Optional[str]]] = set()
for relation in cache_schemas:
if relation.schema:
cache_update.add((relation.database, relation.schema))
cache_update.add((relation.database, relation.schema))
self.cache.update_schemas(cache_update)
def set_relations_cache(
self,
manifest: Manifest,
clear: bool = False,
required_schemas: Optional[Set[BaseRelation]] = None,
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.
@@ -794,23 +704,11 @@ class BaseAdapter(metaclass=AdapterMeta):
# we can't build the relations cache because we don't have a
# manifest so we can't run any operations.
relations = self.list_relations_without_caching(schema_relation)
# if the cache is already populated, add this schema in
# otherwise, skip updating the cache and just ignore
if self.cache:
for relation in relations:
self.cache.add(relation)
if not relations:
# it's possible that there were no relations in some schemas. We want
# to insert the schemas we query into the cache's `.schemas` attribute
# so we can check it later
self.cache.update_schemas([(database, schema)])
fire_event(
ListRelations(
database=cast_to_str(database),
schema=schema,
relations=[_make_ref_key_dict(x) for x in relations],
relations=[_make_ref_key_msg(x) for x in relations],
)
)
@@ -842,6 +740,7 @@ class BaseAdapter(metaclass=AdapterMeta):
schema: str,
identifier: str,
) -> List[BaseRelation]:
matches = []
search = self._make_match_kwargs(database, schema, identifier)
@@ -963,17 +862,6 @@ class BaseAdapter(metaclass=AdapterMeta):
"""
raise NotImplementedError("`convert_number_type` is not implemented for this adapter!")
@classmethod
def convert_integer_type(cls, agate_table: agate.Table, col_idx: int) -> str:
"""Return the type in the database that best maps to the agate.Number
type for the given agate table and column index.
:param agate_table: The table
:param col_idx: The index into the agate table for the column.
:return: The name of the type in the database
"""
return "integer"
@classmethod
@abc.abstractmethod
def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str:
@@ -1031,7 +919,6 @@ class BaseAdapter(metaclass=AdapterMeta):
def convert_agate_type(cls, agate_table: agate.Table, col_idx: int) -> Optional[str]:
agate_type: Type = agate_table.column_types[col_idx]
conversions: List[Tuple[Type, Callable[..., str]]] = [
(Integer, cls.convert_integer_type),
(agate.Text, cls.convert_text_type),
(agate.Number, cls.convert_number_type),
(agate.Boolean, cls.convert_boolean_type),
@@ -1054,9 +941,9 @@ class BaseAdapter(metaclass=AdapterMeta):
manifest: Optional[Manifest] = None,
project: Optional[str] = None,
context_override: Optional[Dict[str, Any]] = None,
kwargs: Optional[Dict[str, Any]] = None,
kwargs: Dict[str, Any] = None,
text_only_columns: Optional[Iterable[str]] = None,
) -> AttrDict:
) -> agate.Table:
"""Look macro_name up in the manifest and execute its results.
:param macro_name: The name of the macro to execute.
@@ -1131,6 +1018,7 @@ class BaseAdapter(metaclass=AdapterMeta):
schemas: Set[str],
manifest: Manifest,
) -> agate.Table:
kwargs = {"information_schema": information_schema, "schemas": schemas}
table = self.execute_macro(
GET_CATALOG_MACRO_NAME,
@@ -1140,110 +1028,27 @@ class BaseAdapter(metaclass=AdapterMeta):
manifest=manifest,
)
results = self._catalog_filter_table(table, manifest) # type: ignore[arg-type]
results = self._catalog_filter_table(table, manifest)
return results
def _get_one_catalog_by_relations(
self,
information_schema: InformationSchema,
relations: List[BaseRelation],
manifest: Manifest,
) -> agate.Table:
kwargs = {
"information_schema": information_schema,
"relations": relations,
}
table = self.execute_macro(
GET_CATALOG_RELATIONS_MACRO_NAME,
kwargs=kwargs,
# pass in the full manifest, so we get any local project
# overrides
manifest=manifest,
)
results = self._catalog_filter_table(table, manifest) # type: ignore[arg-type]
return results
def get_filtered_catalog(
self, manifest: Manifest, relations: Optional[Set[BaseRelation]] = None
):
catalogs: agate.Table
if (
relations is None
or len(relations) > 100
or not self.supports(Capability.SchemaMetadataByRelations)
):
# Do it the traditional way. We get the full catalog.
catalogs, exceptions = self.get_catalog(manifest)
else:
# Do it the new way. We try to save time by selecting information
# only for the exact set of relations we are interested in.
catalogs, exceptions = self.get_catalog_by_relations(manifest, relations)
if relations and catalogs:
relation_map = {
(
r.database.casefold() if r.database else None,
r.schema.casefold() if r.schema else None,
r.identifier.casefold() if r.identifier else None,
)
for r in relations
}
def in_map(row: agate.Row):
d = _expect_row_value("table_database", row)
s = _expect_row_value("table_schema", row)
i = _expect_row_value("table_name", row)
d = d.casefold() if d is not None else None
s = s.casefold() if s is not None else None
i = i.casefold() if i is not None else None
return (d, s, i) in relation_map
catalogs = catalogs.where(in_map)
return catalogs, exceptions
def row_matches_relation(self, row: agate.Row, relations: Set[BaseRelation]):
pass
def get_catalog(self, manifest: Manifest) -> Tuple[agate.Table, List[Exception]]:
schema_map = self._get_catalog_schemas(manifest)
with executor(self.config) as tpe:
futures: List[Future[agate.Table]] = []
schema_map: SchemaSearchMap = self._get_catalog_schemas(manifest)
for info, schemas in schema_map.items():
if len(schemas) == 0:
continue
name = ".".join([str(info.database), "information_schema"])
fut = tpe.submit_connected(
self, name, self._get_one_catalog, info, schemas, manifest
)
futures.append(fut)
catalogs, exceptions = catch_as_completed(futures)
return catalogs, exceptions
def get_catalog_by_relations(
self, manifest: Manifest, relations: Set[BaseRelation]
) -> Tuple[agate.Table, List[Exception]]:
with executor(self.config) as tpe:
futures: List[Future[agate.Table]] = []
relations_by_schema = self._get_catalog_relations_by_info_schema(relations)
for info_schema in relations_by_schema:
name = ".".join([str(info_schema.database), "information_schema"])
relations = set(relations_by_schema[info_schema])
fut = tpe.submit_connected(
self,
name,
self._get_one_catalog_by_relations,
info_schema,
relations,
manifest,
)
futures.append(fut)
catalogs, exceptions = catch_as_completed(futures)
return catalogs, exceptions
return catalogs, exceptions
def cancel_open_connections(self):
"""Cancel all open connections."""
@@ -1255,7 +1060,7 @@ class BaseAdapter(metaclass=AdapterMeta):
loaded_at_field: str,
filter: Optional[str],
manifest: Optional[Manifest] = None,
) -> Tuple[Optional[AdapterResponse], FreshnessResponse]:
) -> Dict[str, Any]:
"""Calculate the freshness of sources in dbt, and return it"""
kwargs: Dict[str, Any] = {
"source": source,
@@ -1264,19 +1069,7 @@ class BaseAdapter(metaclass=AdapterMeta):
}
# run the macro
# in older versions of dbt-core, the 'collect_freshness' macro returned the table of results directly
# starting in v1.5, by default, we return both the table and the adapter response (metadata about the query)
result: Union[
AttrDict, # current: contains AdapterResponse + agate.Table
agate.Table, # previous: just table
]
result = self.execute_macro(FRESHNESS_MACRO_NAME, kwargs=kwargs, manifest=manifest)
if isinstance(result, agate.Table):
deprecations.warn("collect-freshness-return-signature")
adapter_response = None
table = result
else:
adapter_response, table = result.response, result.table # type: ignore[attr-defined]
table = self.execute_macro(FRESHNESS_MACRO_NAME, kwargs=kwargs, manifest=manifest)
# now we have a 1-row table of the maximum `loaded_at_field` value and
# the current time according to the db.
if len(table) != 1 or len(table[0]) != 2:
@@ -1290,51 +1083,11 @@ class BaseAdapter(metaclass=AdapterMeta):
snapshotted_at = _utc(table[0][1], source, loaded_at_field)
age = (snapshotted_at - max_loaded_at).total_seconds()
freshness: FreshnessResponse = {
return {
"max_loaded_at": max_loaded_at,
"snapshotted_at": snapshotted_at,
"age": age,
}
return adapter_response, freshness
def calculate_freshness_from_metadata(
self,
source: BaseRelation,
manifest: Optional[Manifest] = None,
) -> Tuple[Optional[AdapterResponse], FreshnessResponse]:
kwargs: Dict[str, Any] = {
"information_schema": source.information_schema_only(),
"relations": [source],
}
result = self.execute_macro(
GET_RELATION_LAST_MODIFIED_MACRO_NAME, kwargs=kwargs, manifest=manifest
)
adapter_response, table = result.response, result.table # type: ignore[attr-defined]
try:
row = table[0]
last_modified_val = get_column_value_uncased("last_modified", row)
snapshotted_at_val = get_column_value_uncased("snapshotted_at", row)
except Exception:
raise MacroResultError(GET_RELATION_LAST_MODIFIED_MACRO_NAME, table)
if last_modified_val is None:
# Interpret missing value as "infinitely long ago"
max_loaded_at = datetime(1, 1, 1, 0, 0, 0, tzinfo=pytz.UTC)
else:
max_loaded_at = _utc(last_modified_val, None, "last_modified")
snapshotted_at = _utc(snapshotted_at_val, None, "snapshotted_at")
age = (snapshotted_at - max_loaded_at).total_seconds()
freshness: FreshnessResponse = {
"max_loaded_at": max_loaded_at,
"snapshotted_at": snapshotted_at,
"age": age,
}
return adapter_response, freshness
def pre_model_hook(self, config: Mapping[str, Any]) -> Any:
"""A hook for running some operation before the model materialization
@@ -1496,127 +1249,6 @@ class BaseAdapter(metaclass=AdapterMeta):
# This returns a callable macro
return model_context[macro_name]
@classmethod
def _parse_column_constraint(cls, raw_constraint: Dict[str, Any]) -> ColumnLevelConstraint:
try:
ColumnLevelConstraint.validate(raw_constraint)
return ColumnLevelConstraint.from_dict(raw_constraint)
except Exception:
raise DbtValidationError(f"Could not parse constraint: {raw_constraint}")
@classmethod
def render_column_constraint(cls, constraint: ColumnLevelConstraint) -> Optional[str]:
"""Render the given constraint as DDL text. Should be overriden by adapters which need custom constraint
rendering."""
constraint_expression = constraint.expression or ""
rendered_column_constraint = None
if constraint.type == ConstraintType.check and constraint_expression:
rendered_column_constraint = f"check ({constraint_expression})"
elif constraint.type == ConstraintType.not_null:
rendered_column_constraint = f"not null {constraint_expression}"
elif constraint.type == ConstraintType.unique:
rendered_column_constraint = f"unique {constraint_expression}"
elif constraint.type == ConstraintType.primary_key:
rendered_column_constraint = f"primary key {constraint_expression}"
elif constraint.type == ConstraintType.foreign_key and constraint_expression:
rendered_column_constraint = f"references {constraint_expression}"
elif constraint.type == ConstraintType.custom and constraint_expression:
rendered_column_constraint = constraint_expression
if rendered_column_constraint:
rendered_column_constraint = rendered_column_constraint.strip()
return rendered_column_constraint
@available
@classmethod
def render_raw_columns_constraints(cls, raw_columns: Dict[str, Dict[str, Any]]) -> List:
rendered_column_constraints = []
for v in raw_columns.values():
col_name = cls.quote(v["name"]) if v.get("quote") else v["name"]
rendered_column_constraint = [f"{col_name} {v['data_type']}"]
for con in v.get("constraints", None):
constraint = cls._parse_column_constraint(con)
c = cls.process_parsed_constraint(constraint, cls.render_column_constraint)
if c is not None:
rendered_column_constraint.append(c)
rendered_column_constraints.append(" ".join(rendered_column_constraint))
return rendered_column_constraints
@classmethod
def process_parsed_constraint(
cls, parsed_constraint: Union[ColumnLevelConstraint, ModelLevelConstraint], render_func
) -> Optional[str]:
if (
parsed_constraint.warn_unsupported
and cls.CONSTRAINT_SUPPORT[parsed_constraint.type] == ConstraintSupport.NOT_SUPPORTED
):
warn_or_error(
ConstraintNotSupported(constraint=parsed_constraint.type.value, adapter=cls.type())
)
if (
parsed_constraint.warn_unenforced
and cls.CONSTRAINT_SUPPORT[parsed_constraint.type] == ConstraintSupport.NOT_ENFORCED
):
warn_or_error(
ConstraintNotEnforced(constraint=parsed_constraint.type.value, adapter=cls.type())
)
if cls.CONSTRAINT_SUPPORT[parsed_constraint.type] != ConstraintSupport.NOT_SUPPORTED:
return render_func(parsed_constraint)
return None
@classmethod
def _parse_model_constraint(cls, raw_constraint: Dict[str, Any]) -> ModelLevelConstraint:
try:
ModelLevelConstraint.validate(raw_constraint)
c = ModelLevelConstraint.from_dict(raw_constraint)
return c
except Exception:
raise DbtValidationError(f"Could not parse constraint: {raw_constraint}")
@available
@classmethod
def render_raw_model_constraints(cls, raw_constraints: List[Dict[str, Any]]) -> List[str]:
return [c for c in map(cls.render_raw_model_constraint, raw_constraints) if c is not None]
@classmethod
def render_raw_model_constraint(cls, raw_constraint: Dict[str, Any]) -> Optional[str]:
constraint = cls._parse_model_constraint(raw_constraint)
return cls.process_parsed_constraint(constraint, cls.render_model_constraint)
@classmethod
def render_model_constraint(cls, constraint: ModelLevelConstraint) -> Optional[str]:
"""Render the given constraint as DDL text. Should be overriden by adapters which need custom constraint
rendering."""
constraint_prefix = f"constraint {constraint.name} " if constraint.name else ""
column_list = ", ".join(constraint.columns)
if constraint.type == ConstraintType.check and constraint.expression:
return f"{constraint_prefix}check ({constraint.expression})"
elif constraint.type == ConstraintType.unique:
constraint_expression = f" {constraint.expression}" if constraint.expression else ""
return f"{constraint_prefix}unique{constraint_expression} ({column_list})"
elif constraint.type == ConstraintType.primary_key:
constraint_expression = f" {constraint.expression}" if constraint.expression else ""
return f"{constraint_prefix}primary key{constraint_expression} ({column_list})"
elif constraint.type == ConstraintType.foreign_key and constraint.expression:
return f"{constraint_prefix}foreign key ({column_list}) references {constraint.expression}"
elif constraint.type == ConstraintType.custom and constraint.expression:
return f"{constraint_prefix}{constraint.expression}"
else:
return None
@classmethod
def capabilities(cls) -> CapabilityDict:
return cls._capabilities
@classmethod
def supports(cls, capability: Capability) -> bool:
return bool(cls.capabilities()[capability])
COLUMNS_EQUAL_SQL = """
with diff_count as (
@@ -1650,6 +1282,7 @@ join diff_count using (id)
def catch_as_completed(
futures, # typing: List[Future[agate.Table]]
) -> Tuple[agate.Table, List[Exception]]:
# catalogs: agate.Table = agate.Table(rows=[])
tables: List[agate.Table] = []
exceptions: List[Exception] = []

View File

@@ -93,7 +93,7 @@ class AdapterMeta(abc.ABCMeta):
_available_: FrozenSet[str]
_parse_replacements_: Dict[str, Callable]
def __new__(mcls, name, bases, namespace, **kwargs) -> "AdapterMeta":
def __new__(mcls, name, bases, namespace, **kwargs):
# mypy does not like the `**kwargs`. But `ABCMeta` itself takes
# `**kwargs` in its argspec here (and passes them to `type.__new__`.
# I'm not sure there is any benefit to it after poking around a bit,

View File

@@ -7,9 +7,9 @@ from dbt.adapters.protocol import AdapterProtocol
def project_name_from_path(include_path: str) -> str:
# avoid an import cycle
from dbt.config.project import PartialProject
from dbt.config.project import Project
partial = PartialProject.from_project_root(include_path)
partial = Project.partial_load(include_path)
if partial.project_name is None:
raise CompilationError(f"Invalid project at {include_path}: name not set!")
return partial.project_name
@@ -29,7 +29,7 @@ class AdapterPlugin:
credentials: Type[Credentials],
include_path: str,
dependencies: Optional[List[str]] = None,
) -> None:
):
self.adapter: Type[AdapterProtocol] = adapter
self.credentials: Type[Credentials] = credentials

View File

@@ -11,7 +11,7 @@ from dbt.exceptions import DbtRuntimeError
class NodeWrapper:
def __init__(self, node) -> None:
def __init__(self, node):
self._inner_node = node
def __getattr__(self, name):
@@ -25,9 +25,9 @@ class _QueryComment(local):
- a source_name indicating what set the current thread's query comment
"""
def __init__(self, initial) -> None:
def __init__(self, initial):
self.query_comment: Optional[str] = initial
self.append: bool = False
self.append = False
def add(self, sql: str) -> str:
if not self.query_comment:
@@ -57,7 +57,7 @@ QueryStringFunc = Callable[[str, Optional[NodeWrapper]], str]
class MacroQueryStringSetter:
def __init__(self, config: AdapterRequiredConfig, manifest: Manifest) -> None:
def __init__(self, config: AdapterRequiredConfig, manifest: Manifest):
self.manifest = manifest
self.config = config

View File

@@ -1,14 +1,8 @@
from collections.abc import Hashable
from dataclasses import dataclass, field
from typing import Optional, TypeVar, Any, Type, Dict, Iterator, Tuple, Set, Union, FrozenSet
from typing import Optional, TypeVar, Any, Type, Dict, Iterator, Tuple, Set
from dbt.contracts.graph.nodes import (
SourceDefinition,
ManifestNode,
ResultNode,
ParsedNode,
UnitTestSourceDefinition,
)
from dbt.contracts.graph.nodes import SourceDefinition, ManifestNode, ResultNode, ParsedNode
from dbt.contracts.relation import (
RelationType,
ComponentName,
@@ -29,7 +23,6 @@ import dbt.exceptions
Self = TypeVar("Self", bound="BaseRelation")
SerializableIterable = Union[Tuple, FrozenSet]
@dataclass(frozen=True, eq=False, repr=False)
@@ -42,19 +35,6 @@ class BaseRelation(FakeAPIObject, Hashable):
include_policy: Policy = field(default_factory=lambda: Policy())
quote_policy: Policy = field(default_factory=lambda: Policy())
dbt_created: bool = False
limit: Optional[int] = None
# register relation types that can be renamed for the purpose of replacing relations using stages and backups
# adding a relation type here also requires defining the associated rename macro
# e.g. adding RelationType.View in dbt-postgres requires that you define:
# include/postgres/macros/relations/view/rename.sql::postgres__get_rename_view_sql()
renameable_relations: SerializableIterable = ()
# register relation types that are atomically replaceable, e.g. they have "create or replace" syntax
# adding a relation type here also requires defining the associated replace macro
# e.g. adding RelationType.View in dbt-postgres requires that you define:
# include/postgres/macros/relations/view/replace.sql::postgres__get_replace_view_sql()
replaceable_relations: SerializableIterable = ()
def _is_exactish_match(self, field: ComponentName, value: str) -> bool:
if self.dbt_created and self.quote_policy.get_part(field) is False:
@@ -189,6 +169,7 @@ class BaseRelation(FakeAPIObject, Hashable):
return self.include(identifier=False).replace_path(identifier=None)
def _render_iterator(self) -> Iterator[Tuple[Optional[ComponentName], Optional[str]]]:
for key in ComponentName:
path_part: Optional[str] = None
if self.include_policy.get_part(key):
@@ -201,15 +182,6 @@ class BaseRelation(FakeAPIObject, Hashable):
# if there is nothing set, this will return the empty string.
return ".".join(part for _, part in self._render_iterator() if part is not None)
def render_limited(self) -> str:
rendered = self.render()
if self.limit is None:
return rendered
elif self.limit == 0:
return f"(select * from {rendered} where false limit 0) _dbt_limit_subq"
else:
return f"(select * from {rendered} limit {self.limit}) _dbt_limit_subq"
def quoted(self, identifier):
return "{quote_char}{identifier}{quote_char}".format(
quote_char=self.quote_character,
@@ -217,9 +189,7 @@ class BaseRelation(FakeAPIObject, Hashable):
)
@classmethod
def create_from_source(
cls: Type[Self], source: Union[SourceDefinition, UnitTestSourceDefinition], **kwargs: Any
) -> Self:
def create_from_source(cls: Type[Self], source: SourceDefinition, **kwargs: Any) -> Self:
source_quoting = source.quoting.to_dict(omit_none=True)
source_quoting.pop("column", None)
quote_policy = deep_merge(
@@ -245,17 +215,19 @@ class BaseRelation(FakeAPIObject, Hashable):
cls: Type[Self],
config: HasQuoting,
node: ManifestNode,
limit: Optional[int] = None,
) -> Self:
# Note that ephemeral models are based on the name.
identifier = cls.add_ephemeral_prefix(node.name)
return cls.create(type=cls.CTE, identifier=identifier, limit=limit).quote(identifier=False)
return cls.create(
type=cls.CTE,
identifier=identifier,
).quote(identifier=False)
@classmethod
def create_from_node(
cls: Type[Self],
config: HasQuoting,
node,
node: ManifestNode,
quote_policy: Optional[Dict[str, bool]] = None,
**kwargs: Any,
) -> Self:
@@ -279,10 +251,8 @@ class BaseRelation(FakeAPIObject, Hashable):
node: ResultNode,
**kwargs: Any,
) -> Self:
if node.resource_type == NodeType.Source or isinstance(node, UnitTestSourceDefinition):
if not (
isinstance(node, SourceDefinition) or isinstance(node, UnitTestSourceDefinition)
):
if node.resource_type == NodeType.Source:
if not isinstance(node, SourceDefinition):
raise DbtInternalError(
"type mismatch, expected SourceDefinition but got {}".format(type(node))
)
@@ -316,14 +286,6 @@ class BaseRelation(FakeAPIObject, Hashable):
)
return cls.from_dict(kwargs)
@property
def can_be_renamed(self) -> bool:
return self.type in self.renameable_relations
@property
def can_be_replaced(self) -> bool:
return self.type in self.replaceable_relations
def __repr__(self) -> str:
return "<{} {}>".format(self.__class__.__name__, self.render())
@@ -331,7 +293,7 @@ class BaseRelation(FakeAPIObject, Hashable):
return hash(self.render())
def __str__(self) -> str:
return self.render() if self.limit is None else self.render_limited()
return self.render()
@property
def database(self) -> Optional[str]:
@@ -366,10 +328,6 @@ class BaseRelation(FakeAPIObject, Hashable):
def is_view(self) -> bool:
return self.type == RelationType.View
@property
def is_materialized_view(self) -> bool:
return self.type == RelationType.MaterializedView
@classproperty
def Table(cls) -> str:
return str(RelationType.Table)
@@ -386,10 +344,6 @@ class BaseRelation(FakeAPIObject, Hashable):
def External(cls) -> str:
return str(RelationType.External)
@classproperty
def MaterializedView(cls) -> str:
return str(RelationType.MaterializedView)
@classproperty
def get_relation_type(cls) -> Type[RelationType]:
return RelationType
@@ -477,11 +431,11 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
self[key].add(schema)
def search(self) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
for information_schema, schemas in self.items():
for information_schema_name, schemas in self.items():
for schema in schemas:
yield information_schema, schema
yield information_schema_name, schema
def flatten(self, allow_multiple_databases: bool = False) -> "SchemaSearchMap":
def flatten(self, allow_multiple_databases: bool = False):
new = self.__class__()
# make sure we don't have multiple databases if allow_multiple_databases is set to False

View File

@@ -4,7 +4,8 @@ from typing import Any, Dict, Iterable, List, Optional, Set, Tuple
from dbt.adapters.reference_keys import (
_make_ref_key,
_make_ref_key_dict,
_make_ref_key_msg,
_make_msg_from_ref_key,
_ReferenceKey,
)
from dbt.exceptions import (
@@ -16,7 +17,7 @@ from dbt.exceptions import (
)
from dbt.events.functions import fire_event, fire_event_if
from dbt.events.types import CacheAction, CacheDumpGraph
from dbt.flags import get_flags
import dbt.flags as flags
from dbt.utils import lowercase
@@ -38,8 +39,8 @@ class _CachedRelation:
:attr BaseRelation inner: The underlying dbt relation.
"""
def __init__(self, inner) -> None:
self.referenced_by: Dict[_ReferenceKey, _CachedRelation] = {}
def __init__(self, inner):
self.referenced_by = {}
self.inner = inner
def __str__(self) -> str:
@@ -229,7 +230,7 @@ class RelationsCache:
# self.relations or any cache entry's referenced_by during iteration
# it's a runtime error!
with self.lock:
return {dot_separated(k): str(v.dump_graph_entry()) for k, v in self.relations.items()}
return {dot_separated(k): v.dump_graph_entry() for k, v in self.relations.items()}
def _setdefault(self, relation: _CachedRelation):
"""Add a relation to the cache, or return it if it already exists.
@@ -289,8 +290,8 @@ class RelationsCache:
# a link - we will never drop the referenced relation during a run.
fire_event(
CacheAction(
ref_key=ref_key._asdict(),
ref_key_2=dep_key._asdict(),
ref_key=_make_msg_from_ref_key(ref_key),
ref_key_2=_make_msg_from_ref_key(dep_key),
)
)
return
@@ -305,8 +306,8 @@ class RelationsCache:
fire_event(
CacheAction(
action="add_link",
ref_key=dep_key._asdict(),
ref_key_2=ref_key._asdict(),
ref_key=_make_msg_from_ref_key(dep_key),
ref_key_2=_make_msg_from_ref_key(ref_key),
)
)
with self.lock:
@@ -318,13 +319,12 @@ class RelationsCache:
:param BaseRelation relation: The underlying relation.
"""
flags = get_flags()
cached = _CachedRelation(relation)
fire_event_if(
flags.LOG_CACHE_EVENTS,
lambda: CacheDumpGraph(before_after="before", action="adding", dump=self.dump_graph()),
)
fire_event(CacheAction(action="add_relation", ref_key=_make_ref_key_dict(cached)))
fire_event(CacheAction(action="add_relation", ref_key=_make_ref_key_msg(cached)))
with self.lock:
self._setdefault(cached)
@@ -358,7 +358,7 @@ class RelationsCache:
:param str identifier: The identifier of the relation to drop.
"""
dropped_key = _make_ref_key(relation)
dropped_key_msg = _make_ref_key_dict(relation)
dropped_key_msg = _make_ref_key_msg(relation)
fire_event(CacheAction(action="drop_relation", ref_key=dropped_key_msg))
with self.lock:
if dropped_key not in self.relations:
@@ -366,7 +366,7 @@ class RelationsCache:
return
consequences = self.relations[dropped_key].collect_consequences()
# convert from a list of _ReferenceKeys to a list of ReferenceKeyMsgs
consequence_msgs = [key._asdict() for key in consequences]
consequence_msgs = [_make_msg_from_ref_key(key) for key in consequences]
fire_event(
CacheAction(
action="drop_cascade", ref_key=dropped_key_msg, ref_list=consequence_msgs
@@ -396,9 +396,9 @@ class RelationsCache:
fire_event(
CacheAction(
action="update_reference",
ref_key=_make_ref_key_dict(old_key),
ref_key_2=_make_ref_key_dict(new_key),
ref_key_3=_make_ref_key_dict(cached.key()),
ref_key=_make_ref_key_msg(old_key),
ref_key_2=_make_ref_key_msg(new_key),
ref_key_3=_make_ref_key_msg(cached.key()),
)
)
@@ -429,7 +429,9 @@ class RelationsCache:
raise TruncatedModelNameCausedCollisionError(new_key, self.relations)
if old_key not in self.relations:
fire_event(CacheAction(action="temporary_relation", ref_key=old_key._asdict()))
fire_event(
CacheAction(action="temporary_relation", ref_key=_make_msg_from_ref_key(old_key))
)
return False
return True
@@ -450,11 +452,11 @@ class RelationsCache:
fire_event(
CacheAction(
action="rename_relation",
ref_key=old_key._asdict(),
ref_key_2=new_key._asdict(),
ref_key=_make_msg_from_ref_key(old_key),
ref_key_2=_make_msg_from_ref_key(new),
)
)
flags = get_flags()
fire_event_if(
flags.LOG_CACHE_EVENTS,
lambda: CacheDumpGraph(before_after="before", action="rename", dump=self.dump_graph()),

View File

@@ -1,52 +0,0 @@
from dataclasses import dataclass
from enum import Enum
from typing import Optional, DefaultDict, Mapping
class Capability(str, Enum):
"""Enumeration of optional adapter features which can be probed using BaseAdapter.capabilities()"""
SchemaMetadataByRelations = "SchemaMetadataByRelations"
"""Indicates efficient support for retrieving schema metadata for a list of relations, rather than always retrieving
all the relations in a schema."""
TableLastModifiedMetadata = "TableLastModifiedMetadata"
"""Indicates support for determining the time of the last table modification by querying database metadata."""
class Support(str, Enum):
Unknown = "Unknown"
"""The adapter has not declared whether this capability is a feature of the underlying DBMS."""
Unsupported = "Unsupported"
"""This capability is not possible with the underlying DBMS, so the adapter does not implement related macros."""
NotImplemented = "NotImplemented"
"""This capability is available in the underlying DBMS, but support has not yet been implemented in the adapter."""
Versioned = "Versioned"
"""Some versions of the DBMS supported by the adapter support this capability and the adapter has implemented any
macros needed to use it."""
Full = "Full"
"""All versions of the DBMS supported by the adapter support this capability and the adapter has implemented any
macros needed to use it."""
@dataclass
class CapabilitySupport:
support: Support
first_version: Optional[str] = None
def __bool__(self):
return self.support == Support.Versioned or self.support == Support.Full
class CapabilityDict(DefaultDict[Capability, CapabilitySupport]):
def __init__(self, vals: Mapping[Capability, CapabilitySupport]):
super().__init__(self._default)
self.update(vals)
@staticmethod
def _default():
return CapabilitySupport(support=Support.Unknown)

View File

@@ -9,17 +9,16 @@ from dbt.adapters.base.plugin import AdapterPlugin
from dbt.adapters.protocol import AdapterConfig, AdapterProtocol, RelationProtocol
from dbt.contracts.connection import AdapterRequiredConfig, Credentials
from dbt.events.functions import fire_event
from dbt.events.types import AdapterImportError, PluginLoadError, AdapterRegistered
from dbt.events.types import AdapterImportError, PluginLoadError
from dbt.exceptions import DbtInternalError, DbtRuntimeError
from dbt.include.global_project import PACKAGE_PATH as GLOBAL_PROJECT_PATH
from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
from dbt.semver import VersionSpecifier
Adapter = AdapterProtocol
class AdapterContainer:
def __init__(self) -> None:
def __init__(self):
self.lock = threading.Lock()
self.adapters: Dict[str, Adapter] = {}
self.plugins: Dict[str, AdapterPlugin] = {}
@@ -90,13 +89,7 @@ class AdapterContainer:
def register_adapter(self, config: AdapterRequiredConfig) -> None:
adapter_name = config.credentials.type
adapter_type = self.get_adapter_class_by_name(adapter_name)
adapter_version = import_module(f".{adapter_name}.__version__", "dbt.adapters").version
adapter_version_specifier = VersionSpecifier.from_version_string(
adapter_version
).to_version_string()
fire_event(
AdapterRegistered(adapter_name=adapter_name, adapter_version=adapter_version_specifier)
)
with self.lock:
if adapter_name in self.adapters:
# this shouldn't really happen...
@@ -165,9 +158,6 @@ class AdapterContainer:
def get_adapter_type_names(self, name: Optional[str]) -> List[str]:
return [p.adapter.type() for p in self.get_adapter_plugins(name)]
def get_adapter_constraint_support(self, name: Optional[str]) -> List[str]:
return self.lookup_adapter(name).CONSTRAINT_SUPPORT # type: ignore
FACTORY: AdapterContainer = AdapterContainer()
@@ -224,10 +214,6 @@ def get_adapter_type_names(name: Optional[str]) -> List[str]:
return FACTORY.get_adapter_type_names(name)
def get_adapter_constraint_support(name: Optional[str]) -> List[str]:
return FACTORY.get_adapter_constraint_support(name)
@contextmanager
def adapter_management():
reset_adapters()

View File

@@ -90,7 +90,7 @@ class AdapterProtocol( # type: ignore[misc]
ConnectionManager: Type[ConnectionManager_T]
connections: ConnectionManager_T
def __init__(self, config: AdapterRequiredConfig) -> None:
def __init__(self, config: AdapterRequiredConfig):
...
@classmethod

View File

@@ -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")
@@ -29,9 +30,11 @@ def _make_ref_key(relation: Any) -> _ReferenceKey:
)
def _make_ref_key_dict(relation: Any):
return {
"database": relation.database,
"schema": relation.schema,
"identifier": 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
)

Some files were not shown because too many files have changed in this diff Show More