Compare commits

..

1 Commits

Author SHA1 Message Date
Nathaniel May
cdb78d0270 Revert "Add Performance Regression Testing [Rust]" 2021-08-11 10:45:31 -04:00
4837 changed files with 31125 additions and 83519 deletions

View File

@@ -1,5 +1,5 @@
[bumpversion]
current_version = 1.0.0b2
current_version = 0.21.0b1
parse = (?P<major>\d+)
\.(?P<minor>\d+)
\.(?P<patch>\d+)
@@ -34,4 +34,17 @@ first_value = 1
[bumpversion:file:plugins/postgres/setup.py]
[bumpversion:file:plugins/redshift/setup.py]
[bumpversion:file:plugins/snowflake/setup.py]
[bumpversion:file:plugins/bigquery/setup.py]
[bumpversion:file:plugins/postgres/dbt/adapters/postgres/__version__.py]
[bumpversion:file:plugins/redshift/dbt/adapters/redshift/__version__.py]
[bumpversion:file:plugins/snowflake/dbt/adapters/snowflake/__version__.py]
[bumpversion:file:plugins/bigquery/dbt/adapters/bigquery/__version__.py]

101
.circleci/config.yml Normal file
View File

@@ -0,0 +1,101 @@
version: 2.1
jobs:
build-wheels:
docker: &test_only
- image: fishtownanalytics/test-container:12
environment:
DBT_INVOCATION_ENV: circle
DOCKER_TEST_DATABASE_HOST: "database"
TOX_PARALLEL_NO_SPINNER: 1
steps:
- checkout
- run:
name: Build wheels
command: |
python3.8 -m venv "${PYTHON_ENV}"
export PYTHON_BIN="${PYTHON_ENV}/bin/python"
$PYTHON_BIN -m pip install -U pip setuptools
$PYTHON_BIN -m pip install -r requirements.txt
$PYTHON_BIN -m pip install -r dev-requirements.txt
/bin/bash ./scripts/build-wheels.sh
$PYTHON_BIN ./scripts/collect-dbt-contexts.py > ./dist/context_metadata.json
$PYTHON_BIN ./scripts/collect-artifact-schema.py > ./dist/artifact_schemas.json
environment:
PYTHON_ENV: /home/tox/build_venv/
- store_artifacts:
path: ./dist
destination: dist
integration-postgres:
docker:
- image: fishtownanalytics/test-container:12
environment:
DBT_INVOCATION_ENV: circle
DOCKER_TEST_DATABASE_HOST: "database"
TOX_PARALLEL_NO_SPINNER: 1
- image: postgres
name: database
environment:
POSTGRES_USER: "root"
POSTGRES_PASSWORD: "password"
POSTGRES_DB: "dbt"
steps:
- checkout
- run:
name: Setup postgres
command: bash test/setup_db.sh
environment:
PGHOST: database
PGUSER: root
PGPASSWORD: password
PGDATABASE: postgres
- run:
name: Postgres integration tests
command: tox -p -e py36-postgres,py38-postgres -- -v -n4
no_output_timeout: 30m
- store_artifacts:
path: ./logs
integration-snowflake:
docker: *test_only
steps:
- checkout
- run:
name: Snowflake integration tests
command: tox -p -e py36-snowflake,py38-snowflake -- -v -n4
no_output_timeout: 30m
- store_artifacts:
path: ./logs
integration-redshift:
docker: *test_only
steps:
- checkout
- run:
name: Redshift integration tests
command: tox -p -e py36-redshift,py38-redshift -- -v -n4
no_output_timeout: 30m
- store_artifacts:
path: ./logs
integration-bigquery:
docker: *test_only
steps:
- checkout
- run:
name: Bigquery integration test
command: tox -p -e py36-bigquery,py38-bigquery -- -v -n4
no_output_timeout: 30m
- store_artifacts:
path: ./logs
workflows:
version: 2
test-everything:
jobs:
- integration-postgres
- integration-redshift
- integration-bigquery
- integration-snowflake
- build-wheels:
requires:
- integration-postgres
- integration-redshift
- integration-bigquery
- integration-snowflake

View File

@@ -0,0 +1,27 @@
---
name: Beta minor version release
about: Creates a tracking checklist of items for a Beta minor version release
title: "[Tracking] v#.##.#B# release "
labels: 'release'
assignees: ''
---
### Release Core
- [ ] [Engineering] Follow [dbt-release workflow](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#03ff37da697d4d8ba63d24fae1bfa817)
- [ ] [Engineering] Verify new release branch is created in the repo
- [ ] [Product] Finalize migration guide (next.docs.getdbt.com)
### Release Cloud
- [ ] [Engineering] Create a platform issue to update dbt Cloud and verify it is completed. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
- [ ] [Engineering] Determine if schemas have changed. If so, generate new schemas and push to schemas.getdbt.com
### Announce
- [ ] [Product] Announce in dbt Slack
### Post-release
- [ ] [Engineering] [Bump plugin versions](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#f01854e8da3641179fbcbe505bdf515c) (dbt-spark + dbt-presto), add compatibility as needed
- [ ] [Spark](https://github.com/dbt-labs/dbt-spark)
- [ ] [Presto](https://github.com/dbt-labs/dbt-presto)
- [ ] [Engineering] Create a platform issue to update dbt-spark versions to dbt Cloud. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
- [ ] [Engineering] Create an epic for the RC release

View File

@@ -1,85 +0,0 @@
name: 🐞 Bug
description: Report a bug or an issue you've found with dbt
title: "[Bug] <title>"
labels: ["bug", "triage"]
body:
- type: markdown
attributes:
value: |
Thanks for taking the time to fill out this bug report!
- type: checkboxes
attributes:
label: Is there an existing issue for this?
description: Please search to see if an issue already exists for the bug you encountered.
options:
- label: I have searched the existing issues
required: true
- type: textarea
attributes:
label: Current Behavior
description: A concise description of what you're experiencing.
validations:
required: false
- type: textarea
attributes:
label: Expected Behavior
description: A concise description of what you expected to happen.
validations:
required: false
- type: textarea
attributes:
label: Steps To Reproduce
description: Steps to reproduce the behavior.
placeholder: |
1. In this environment...
2. With this config...
3. Run '...'
4. See error...
validations:
required: false
- type: textarea
id: logs
attributes:
label: Relevant log output
description: |
If applicable, log output to help explain your problem.
render: shell
validations:
required: false
- type: textarea
attributes:
label: Environment
description: |
examples:
- **OS**: Ubuntu 20.04
- **Python**: 3.7.2 (`python --version`)
- **dbt**: 0.21.0 (`dbt --version`)
value: |
- OS:
- Python:
- dbt:
render: markdown
validations:
required: false
- type: dropdown
id: database
attributes:
label: What database are you using dbt with?
multiple: true
options:
- postgres
- redshift
- snowflake
- bigquery
- other (mention it in "Additional Context")
validations:
required: false
- type: textarea
attributes:
label: Additional Context
description: |
Links? References? Anything that will give us more context about the issue you are encountering!
Tip: You can attach images or log files by clicking this area to highlight it and then dragging files in.
validations:
required: false

41
.github/ISSUE_TEMPLATE/bug_report.md vendored Normal file
View File

@@ -0,0 +1,41 @@
---
name: Bug report
about: Report a bug or an issue you've found with dbt
title: ''
labels: bug, triage
assignees: ''
---
### Describe the bug
A clear and concise description of what the bug is. What command did you run? What happened?
### Steps To Reproduce
In as much detail as possible, please provide steps to reproduce the issue. Sample data that triggers the issue, example model code, etc is all very helpful here.
### Expected behavior
A clear and concise description of what you expected to happen.
### Screenshots and log output
If applicable, add screenshots or log output to help explain your problem.
### System information
**Which database are you using dbt with?**
- [ ] postgres
- [ ] redshift
- [ ] bigquery
- [ ] snowflake
- [ ] other (specify: ____________)
**The output of `dbt --version`:**
```
<output goes here>
```
**The operating system you're using:**
**The output of `python --version`:**
### Additional context
Add any other context about the problem here.

View File

@@ -1,16 +0,0 @@
contact_links:
- name: Create an issue for dbt-redshift
url: https://github.com/dbt-labs/dbt-redshift/issues/new/choose
about: Report a bug or request a feature for dbt-redshift
- name: Create an issue for dbt-bigquery
url: https://github.com/dbt-labs/dbt-bigquery/issues/new/choose
about: Report a bug or request a feature for dbt-bigquery
- name: Create an issue for dbt-snowflake
url: https://github.com/dbt-labs/dbt-snowflake/issues/new/choose
about: Report a bug or request a feature for dbt-snowflake
- name: Ask a question or get support
url: https://docs.getdbt.com/docs/guides/getting-help
about: Ask a question or request support
- name: Questions on Stack Overflow
url: https://stackoverflow.com/questions/tagged/dbt
about: Look at questions/answers at Stack Overflow

View File

@@ -1,49 +0,0 @@
name: ✨ Feature
description: Suggest an idea for dbt
title: "[Feature] <title>"
labels: ["enhancement", "triage"]
body:
- type: markdown
attributes:
value: |
Thanks for taking the time to fill out this feature requests!
- type: checkboxes
attributes:
label: Is there an existing feature request for this?
description: Please search to see if an issue already exists for the feature you would like.
options:
- label: I have searched the existing issues
required: true
- type: textarea
attributes:
label: Describe the Feature
description: A clear and concise description of what you want to happen.
validations:
required: true
- type: textarea
attributes:
label: Describe alternatives you've considered
description: |
A clear and concise description of any alternative solutions or features you've considered.
validations:
required: false
- type: textarea
attributes:
label: Who will this benefit?
description: |
What kind of use case will this feature be useful for? Please be specific and provide examples, this will help us prioritize properly.
validations:
required: false
- type: input
attributes:
label: Are you interested in contributing this feature?
description: Let us know if you want to write some code, and how we can help.
validations:
required: false
- type: textarea
attributes:
label: Anything else?
description: |
Links? References? Anything that will give us more context about the feature you are suggesting!
validations:
required: false

View File

@@ -0,0 +1,23 @@
---
name: Feature request
about: Suggest an idea for dbt
title: ''
labels: enhancement, triage
assignees: ''
---
### Describe the feature
A clear and concise description of what you want to happen.
### Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.
### Additional context
Is this feature database-specific? Which database(s) is/are relevant? Please include any other relevant context here.
### Who will this benefit?
What kind of use case will this feature be useful for? Please be specific and provide examples, this will help us prioritize properly.
### Are you interested in contributing this feature?
Let us know if you want to write some code, and how we can help.

View File

@@ -0,0 +1,28 @@
---
name: Final minor version release
about: Creates a tracking checklist of items for a final minor version release
title: "[Tracking] v#.##.# final release "
labels: 'release'
assignees: ''
---
### Release Core
- [ ] [Engineering] Verify all necessary changes exist on the release branch
- [ ] [Engineering] Follow [dbt-release workflow](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#03ff37da697d4d8ba63d24fae1bfa817)
- [ ] [Product] Merge `next` into `current` for docs.getdbt.com
### Release Cloud
- [ ] [Engineering] Create a platform issue to update dbt Cloud and verify it is completed. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
- [ ] [Engineering] Determine if schemas have changed. If so, generate new schemas and push to schemas.getdbt.com
### Announce
- [ ] [Product] Update discourse
- [ ] [Product] Announce in dbt Slack
### Post-release
- [ ] [Engineering] [Bump plugin versions](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#f01854e8da3641179fbcbe505bdf515c) (dbt-spark + dbt-presto), add compatibility as needed
- [ ] [Spark](https://github.com/dbt-labs/dbt-spark)
- [ ] [Presto](https://github.com/dbt-labs/dbt-presto)
- [ ] [Engineering] Create a platform issue to update dbt-spark versions to dbt Cloud. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
- [ ] [Product] Release new version of dbt-utils with new dbt version compatibility. If there are breaking changes requiring a minor version, plan upgrades of other packages that depend on dbt-utils.

View File

@@ -0,0 +1,29 @@
---
name: RC minor version release
about: Creates a tracking checklist of items for a RC minor version release
title: "[Tracking] v#.##.#RC# release "
labels: 'release'
assignees: ''
---
### Release Core
- [ ] [Engineering] Verify all necessary changes exist on the release branch
- [ ] [Engineering] Follow [dbt-release workflow](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#03ff37da697d4d8ba63d24fae1bfa817)
- [ ] [Product] Update migration guide (next.docs.getdbt.com)
### Release Cloud
- [ ] [Engineering] Create a platform issue to update dbt Cloud and verify it is completed. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
- [ ] [Engineering] Determine if schemas have changed. If so, generate new schemas and push to schemas.getdbt.com
### Announce
- [ ] [Product] Publish discourse
- [ ] [Product] Announce in dbt Slack
### Post-release
- [ ] [Engineering] [Bump plugin versions](https://www.notion.so/dbtlabs/Releasing-b97c5ea9a02949e79e81db3566bbc8ef#f01854e8da3641179fbcbe505bdf515c) (dbt-spark + dbt-presto), add compatibility as needed
- [ ] [Spark](https://github.com/dbt-labs/dbt-spark)
- [ ] [Presto](https://github.com/dbt-labs/dbt-presto)
- [ ] [Engineering] Create a platform issue to update dbt-spark versions to dbt Cloud. [Example issue](https://github.com/dbt-labs/dbt-cloud/issues/3481)
- [ ] [Product] Release new version of dbt-utils with new dbt version compatibility. If there are breaking changes requiring a minor version, plan upgrades of other packages that depend on dbt-utils.
- [ ] [Engineering] Create an epic for the final release

View File

@@ -1,10 +0,0 @@
name: "Set up postgres (linux)"
description: "Set up postgres service on linux vm for dbt integration tests"
runs:
using: "composite"
steps:
- shell: bash
run: |
sudo systemctl start postgresql.service
pg_isready
sudo -u postgres bash ${{ github.action_path }}/setup_db.sh

View File

@@ -1 +0,0 @@
../../../test/setup_db.sh

View File

@@ -1,24 +0,0 @@
name: "Set up postgres (macos)"
description: "Set up postgres service on macos vm for dbt integration tests"
runs:
using: "composite"
steps:
- shell: bash
run: |
brew services start postgresql
echo "Check PostgreSQL service is running"
i=10
COMMAND='pg_isready'
while [ $i -gt -1 ]; do
if [ $i == 0 ]; then
echo "PostgreSQL service not ready, all attempts exhausted"
exit 1
fi
echo "Check PostgreSQL service status"
eval $COMMAND && break
echo "PostgreSQL service not ready, wait 10 more sec, attempts left: $i"
sleep 10
((i--))
done
createuser -s postgres
bash ${{ github.action_path }}/setup_db.sh

View File

@@ -1 +0,0 @@
../../../test/setup_db.sh

View File

@@ -1,12 +0,0 @@
name: "Set up postgres (windows)"
description: "Set up postgres service on windows vm for dbt integration tests"
runs:
using: "composite"
steps:
- shell: pwsh
run: |
$pgService = Get-Service -Name postgresql*
Set-Service -InputObject $pgService -Status running -StartupType automatic
Start-Process -FilePath "$env:PGBIN\pg_isready" -Wait -PassThru
$env:Path += ";$env:PGBIN"
bash ${{ github.action_path }}/setup_db.sh

View File

@@ -1 +0,0 @@
../../../test/setup_db.sh

View File

@@ -11,11 +11,26 @@ updates:
schedule:
interval: "daily"
rebase-strategy: "disabled"
- package-ecosystem: "pip"
directory: "/plugins/bigquery"
schedule:
interval: "daily"
rebase-strategy: "disabled"
- package-ecosystem: "pip"
directory: "/plugins/postgres"
schedule:
interval: "daily"
rebase-strategy: "disabled"
- package-ecosystem: "pip"
directory: "/plugins/redshift"
schedule:
interval: "daily"
rebase-strategy: "disabled"
- package-ecosystem: "pip"
directory: "/plugins/snowflake"
schedule:
interval: "daily"
rebase-strategy: "disabled"
# docker dependencies
- package-ecosystem: "docker"

View File

@@ -4,18 +4,19 @@ 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.
Example:
resolves #1234
-->
### Description
<!---
Describe the Pull Request here. Add any references and info to help reviewers
understand your changes. Include any tradeoffs you considered.
-->
<!--- Describe the Pull Request here -->
### Checklist
- [ ] I have signed the [CLA](https://docs.getdbt.com/docs/contributor-license-agreements)
- [ ] I have run this code in development and it appears to resolve the stated issue
- [ ] This PR includes tests, or tests are not required/relevant for this PR
- [ ] I have updated the `CHANGELOG.md` and added information about my change
- [ ] I have signed the [CLA](https://docs.getdbt.com/docs/contributor-license-agreements)
- [ ] I have run this code in development and it appears to resolve the stated issue
- [ ] This PR includes tests, or tests are not required/relevant for this PR
- [ ] I have updated the `CHANGELOG.md` and added information about my change to the "dbt next" section.

View File

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

View File

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

View File

@@ -1,206 +0,0 @@
# **what?**
# Runs code quality checks, unit tests, and verifies python build on
# all code commited to the repository. This workflow should not
# require any secrets since it runs for PRs from forked repos.
# By default, secrets are not passed to workflows running from
# a forked repo.
# **why?**
# Ensure code for dbt meets a certain quality standard.
# **when?**
# This will run for all PRs, when code is pushed to a release
# branch, and when manually triggered.
name: Tests and Code Checks
on:
push:
branches:
- "main"
- "develop"
- "*.latest"
- "releases/*"
pull_request:
workflow_dispatch:
permissions: read-all
# will cancel previous workflows triggered by the same event and for the same ref for PRs or same SHA otherwise
concurrency:
group: ${{ github.workflow }}-${{ github.event_name }}-${{ contains(github.event_name, 'pull_request') && github.event.pull_request.head.ref || github.sha }}
cancel-in-progress: true
defaults:
run:
shell: bash
jobs:
code-quality:
name: ${{ matrix.toxenv }}
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
toxenv: [flake8, mypy]
env:
TOXENV: ${{ matrix.toxenv }}
PYTEST_ADDOPTS: "-v --color=yes"
steps:
- name: Check out the repository
uses: actions/checkout@v2
with:
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@v2
- name: Install python dependencies
run: |
pip install --user --upgrade pip
pip install tox
pip --version
tox --version
- name: Run tox
run: tox
unit:
name: unit test / python ${{ matrix.python-version }}
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: [3.6, 3.7, 3.8] # TODO: support unit testing for python 3.9 (https://github.com/dbt-labs/dbt/issues/3689)
env:
TOXENV: "unit"
PYTEST_ADDOPTS: "-v --color=yes --csv unit_results.csv"
steps:
- name: Check out the repository
uses: actions/checkout@v2
with:
persist-credentials: false
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
with:
python-version: ${{ matrix.python-version }}
- name: Install python dependencies
run: |
pip install --user --upgrade pip
pip install tox
pip --version
tox --version
- name: Run tox
run: tox
- name: Get current date
if: always()
id: date
run: echo "::set-output name=date::$(date +'%Y-%m-%dT%H_%M_%S')" #no colons allowed for artifacts
- uses: actions/upload-artifact@v2
if: always()
with:
name: unit_results_${{ matrix.python-version }}-${{ steps.date.outputs.date }}.csv
path: unit_results.csv
build:
name: build packages
runs-on: ubuntu-latest
steps:
- name: Check out the repository
uses: actions/checkout@v2
with:
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Install python dependencies
run: |
pip install --user --upgrade pip
pip install --upgrade setuptools wheel twine check-wheel-contents
pip --version
- name: Build distributions
run: ./scripts/build-dist.sh
- name: Show distributions
run: ls -lh dist/
- name: Check distribution descriptions
run: |
twine check dist/*
- name: Check wheel contents
run: |
check-wheel-contents dist/*.whl --ignore W007,W008
- uses: actions/upload-artifact@v2
with:
name: dist
path: dist/
test-build:
name: verify packages / python ${{ matrix.python-version }} / ${{ matrix.os }}
needs: build
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-latest]
python-version: [3.6, 3.7, 3.8, 3.9]
steps:
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
with:
python-version: ${{ matrix.python-version }}
- name: Install python dependencies
run: |
pip install --user --upgrade pip
pip install --upgrade wheel
pip --version
- uses: actions/download-artifact@v2
with:
name: dist
path: dist/
- name: Show distributions
run: ls -lh dist/
- name: Install wheel distributions
run: |
find ./dist/*.whl -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
- 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

View File

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

View File

@@ -1,87 +0,0 @@
# **what?**
# Compares the schema of the dbt version of the given ref vs
# the latest official schema releases found in schemas.getdbt.com.
# If there are differences, the workflow will fail and upload the
# diff as an artifact. The metadata team should be alerted to the change.
#
# **why?**
# Reaction work may need to be done if artifact schema changes
# occur so we want to proactively alert to it.
#
# **when?**
# On pushes to `develop` and release branches. Manual runs are also enabled.
name: Artifact Schema Check
on:
workflow_dispatch:
pull_request: #TODO: remove before merging
push:
branches:
- "develop"
- "*.latest"
- "releases/*"
env:
LATEST_SCHEMA_PATH: ${{ github.workspace }}/new_schemas
SCHEMA_DIFF_ARTIFACT: ${{ github.workspace }}//schema_schanges.txt
DBT_REPO_DIRECTORY: ${{ github.workspace }}/dbt
SCHEMA_REPO_DIRECTORY: ${{ github.workspace }}/schemas.getdbt.com
jobs:
checking-schemas:
name: "Checking schemas"
runs-on: ubuntu-latest
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Checkout dbt repo
uses: actions/checkout@v2.3.4
with:
path: ${{ env.DBT_REPO_DIRECTORY }}
- name: Checkout schemas.getdbt.com repo
uses: actions/checkout@v2.3.4
with:
repository: dbt-labs/schemas.getdbt.com
ref: 'main'
ssh-key: ${{ secrets.SCHEMA_SSH_PRIVATE_KEY }}
path: ${{ env.SCHEMA_REPO_DIRECTORY }}
- name: Generate current schema
run: |
cd ${{ env.DBT_REPO_DIRECTORY }}
python3 -m venv env
source env/bin/activate
pip install --upgrade pip
pip install -r dev-requirements.txt -r editable-requirements.txt
python scripts/collect-artifact-schema.py --path ${{ env.LATEST_SCHEMA_PATH }}
# Copy generated schema files into the schemas.getdbt.com repo
# Do a git diff to find any changes
# Ignore any date or version changes though
- name: Compare schemas
run: |
cp -r ${{ env.LATEST_SCHEMA_PATH }}/dbt ${{ env.SCHEMA_REPO_DIRECTORY }}
cd ${{ env.SCHEMA_REPO_DIRECTORY }}
diff_results=$(git diff -I='*[0-9]{4}-(0[1-9]|1[0-2])-(0[1-9]|[1-2][0-9]|3[0-1])T' \
-I='*[0-9]{1}.[0-9]{2}.[0-9]{1}(rc[0-9]|b[0-9]| )' --compact-summary)
if [[ $(echo diff_results) ]]; then
echo $diff_results
echo "Schema changes detected!"
git diff -I='*[0-9]{4}-(0[1-9]|1[0-2])-(0[1-9]|[1-2][0-9]|3[0-1])T' \
-I='*[0-9]{1}.[0-9]{2}.[0-9]{1}(rc[0-9]|b[0-9]| )' > ${{ env.SCHEMA_DIFF_ARTIFACT }}
exit 1
else
echo "No schema changes detected"
fi
- name: Upload schema diff
uses: actions/upload-artifact@v2.2.4
if: ${{ failure() }}
with:
name: 'schema_schanges.txt'
path: '${{ env.SCHEMA_DIFF_ARTIFACT }}'

View File

@@ -1,18 +0,0 @@
name: "Close stale issues and PRs"
on:
schedule:
- cron: "30 1 * * *"
jobs:
stale:
runs-on: ubuntu-latest
steps:
# pinned at v4 (https://github.com/actions/stale/releases/tag/v4.0.0)
- uses: actions/stale@cdf15f641adb27a71842045a94023bef6945e3aa
with:
stale-issue-message: "This issue has been marked as Stale because it has been open for 180 days with no activity. If you would like the issue to remain open, please remove the stale label or comment on the issue, or it will be closed in 7 days."
stale-pr-message: "This PR has been marked as Stale because it has been open for 180 days with no activity. If you would like the PR to remain open, please remove the stale label or comment on the PR, or it will be closed in 7 days."
# mark issues/PRs stale when they haven't seen activity in 180 days
days-before-stale: 180
# ignore checking issues with the following labels
exempt-issue-labels: "epic,discussion"

139
.github/workflows/tests.yml vendored Normal file
View File

@@ -0,0 +1,139 @@
# This is a workflow to run our integration tests for windows and mac
name: dbt Tests
# Triggers
on:
# Triggers the workflow on push or pull request events and also adds a manual trigger
push:
branches:
- 'develop'
- '*.latest'
- 'releases/*'
pull_request:
branches:
- 'develop'
- '*.latest'
- 'pr/*'
- 'releases/*'
# Allows you to run this workflow manually from the Actions tab
workflow_dispatch:
jobs:
PostgresIntegrationTest:
runs-on: 'windows-latest' #TODO: Add Mac support
environment: 'Postgres'
steps:
- uses: actions/checkout@v2
- name: 'Install postgresql and set up database'
shell: pwsh
run: |
$serviceName = Get-Service -Name postgresql*
Set-Service -InputObject $serviceName -StartupType Automatic
Start-Service -InputObject $serviceName
& $env:PGBIN\createdb.exe -U postgres dbt
& $env:PGBIN\psql.exe -U postgres -c "CREATE ROLE root WITH PASSWORD '$env:ROOT_PASSWORD';"
& $env:PGBIN\psql.exe -U postgres -c "ALTER ROLE root WITH LOGIN;"
& $env:PGBIN\psql.exe -U postgres -c "GRANT CREATE, CONNECT ON DATABASE dbt TO root WITH GRANT OPTION;"
& $env:PGBIN\psql.exe -U postgres -c "CREATE ROLE noaccess WITH PASSWORD '$env:NOACCESS_PASSWORD' NOSUPERUSER;"
& $env:PGBIN\psql.exe -U postgres -c "ALTER ROLE noaccess WITH LOGIN;"
& $env:PGBIN\psql.exe -U postgres -c "GRANT CONNECT ON DATABASE dbt TO noaccess;"
env:
ROOT_PASSWORD: ${{ secrets.ROOT_PASSWORD }}
NOACCESS_PASSWORD: ${{ secrets.NOACCESS_PASSWORD }}
- name: Setup Python
uses: actions/setup-python@v2.2.2
with:
python-version: '3.7'
architecture: 'x64'
- name: 'Install dependencies'
run: python -m pip install --upgrade pip && pip install tox
- name: 'Run integration tests'
run: python -m tox -e py-postgres -- -v -n4
# These three are all similar except secure environment variables, which MUST be passed along to their tasks,
# but there's probably a better way to do this!
SnowflakeIntegrationTest:
strategy:
matrix:
os: [windows-latest, macos-latest]
runs-on: ${{ matrix.os }}
environment: 'Snowflake'
steps:
- uses: actions/checkout@v2
- name: Setup Python
uses: actions/setup-python@v2.2.2
with:
python-version: '3.7'
architecture: 'x64'
- name: 'Install dependencies'
run: python -m pip install --upgrade pip && pip install tox
- name: 'Run integration tests'
run: python -m tox -e py-snowflake -- -v -n4
env:
SNOWFLAKE_TEST_ACCOUNT: ${{ secrets.SNOWFLAKE_TEST_ACCOUNT }}
SNOWFLAKE_TEST_PASSWORD: ${{ secrets.SNOWFLAKE_TEST_PASSWORD }}
SNOWFLAKE_TEST_USER: ${{ secrets.SNOWFLAKE_TEST_USER }}
SNOWFLAKE_TEST_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_WAREHOUSE }}
SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN: ${{ secrets.SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN }}
SNOWFLAKE_TEST_OAUTH_CLIENT_ID: ${{ secrets.SNOWFLAKE_TEST_OAUTH_CLIENT_ID }}
SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET: ${{ secrets.SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET }}
SNOWFLAKE_TEST_ALT_DATABASE: ${{ secrets.SNOWFLAKE_TEST_ALT_DATABASE }}
SNOWFLAKE_TEST_ALT_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_ALT_WAREHOUSE }}
SNOWFLAKE_TEST_DATABASE: ${{ secrets.SNOWFLAKE_TEST_DATABASE }}
SNOWFLAKE_TEST_QUOTED_DATABASE: ${{ secrets.SNOWFLAKE_TEST_QUOTED_DATABASE }}
SNOWFLAKE_TEST_ROLE: ${{ secrets.SNOWFLAKE_TEST_ROLE }}
BigQueryIntegrationTest:
strategy:
matrix:
os: [windows-latest, macos-latest]
runs-on: ${{ matrix.os }}
environment: 'Bigquery'
steps:
- uses: actions/checkout@v2
- name: Setup Python
uses: actions/setup-python@v2.2.2
with:
python-version: '3.7'
architecture: 'x64'
- name: 'Install dependencies'
run: python -m pip install --upgrade pip && pip install tox
- name: 'Run integration tests'
run: python -m tox -e py-bigquery -- -v -n4
env:
BIGQUERY_SERVICE_ACCOUNT_JSON: ${{ secrets.BIGQUERY_SERVICE_ACCOUNT_JSON }}
BIGQUERY_TEST_ALT_DATABASE: ${{ secrets.BIGQUERY_TEST_ALT_DATABASE }}
RedshiftIntegrationTest:
strategy:
matrix:
os: [windows-latest, macos-latest]
runs-on: ${{ matrix.os }}
environment: 'Redshift'
steps:
- uses: actions/checkout@v2
- name: Setup Python
uses: actions/setup-python@v2.2.2
with:
python-version: '3.7'
architecture: 'x64'
- name: 'Install dependencies'
run: python -m pip install --upgrade pip && pip install tox
- name: 'Run integration tests'
run: python -m tox -e py-redshift -- -v -n4
env:
REDSHIFT_TEST_DBNAME: ${{ secrets.REDSHIFT_TEST_DBNAME }}
REDSHIFT_TEST_PASS: ${{ secrets.REDSHIFT_TEST_PASS }}
REDSHIFT_TEST_USER: ${{ secrets.REDSHIFT_TEST_USER }}
REDSHIFT_TEST_PORT: ${{ secrets.REDSHIFT_TEST_PORT }}
REDSHIFT_TEST_HOST: ${{ secrets.REDSHIFT_TEST_HOST }}

61
.github/workflows/unit_tests.yml vendored Normal file
View File

@@ -0,0 +1,61 @@
# This is a workflow to run our linting and unit tests for windows, mac, and linux
name: Linting and Unit Tests
# Triggers
on:
# Trigger on commits to develop and releases branches
push:
branches:
- 'develop'
- '*.latest'
- 'releases/*'
pull_request: # Trigger for all PRs
workflow_dispatch: # Allow manual triggers
jobs:
Linting:
runs-on: ubuntu-latest #no need to run on every OS
steps:
- uses: actions/checkout@v2
- name: Setup Python
uses: actions/setup-python@v2.2.2
with:
python-version: '3.6'
architecture: 'x64'
- name: 'Install dependencies'
run: python -m pip install --upgrade pip && pip install tox
- name: 'Linting'
run: tox -e mypy,flake8 -- -v
UnitTest:
strategy:
matrix:
os: [windows-latest, ubuntu-latest, macos-latest]
runs-on: ${{ matrix.os }}
needs: Linting
steps:
- uses: actions/checkout@v2
- name: Setup Python 3.6
uses: actions/setup-python@v2.2.2
with:
python-version: '3.6'
architecture: 'x64'
- name: Setup Python 3.7
uses: actions/setup-python@v2.2.2
with:
python-version: '3.7'
architecture: 'x64'
- name: Setup Python 3.8
uses: actions/setup-python@v2.2.2
with:
python-version: '3.8'
architecture: 'x64'
- name: 'Install dependencies'
run: python -m pip install --upgrade pip && pip install tox
- name: 'Run unit tests'
run: tox -p -e py36,py37,py38

View File

@@ -1,109 +0,0 @@
# **what?**
# This workflow will take a version number and a dry run flag. With that
# it will run versionbump to update the version number everywhere in the
# code base and then generate an update Docker requirements file. If this
# is a dry run, a draft PR will open with the changes. If this isn't a dry
# run, the changes will be committed to the branch this is run on.
# **why?**
# This is to aid in releasing dbt and making sure we have updated
# the versions and Docker requirements in all places.
# **when?**
# This is triggered either manually OR
# from the repository_dispatch event "version-bump" which is sent from
# the dbt-release repo Action
name: Version Bump
on:
workflow_dispatch:
inputs:
version_number:
description: 'The version number to bump to'
required: true
is_dry_run:
description: 'Creates a draft PR to allow testing instead of committing to a branch'
required: true
default: 'true'
repository_dispatch:
types: [version-bump]
jobs:
bump:
runs-on: ubuntu-latest
steps:
- name: Check out the repository
uses: actions/checkout@v2
- name: Set version and dry run values
id: variables
env:
VERSION_NUMBER: "${{ github.event.client_payload.version_number == '' && github.event.inputs.version_number || github.event.client_payload.version_number }}"
IS_DRY_RUN: "${{ github.event.client_payload.is_dry_run == '' && github.event.inputs.is_dry_run || github.event.client_payload.is_dry_run }}"
run: |
echo Repository dispatch event version: ${{ github.event.client_payload.version_number }}
echo Repository dispatch event dry run: ${{ github.event.client_payload.is_dry_run }}
echo Workflow dispatch event version: ${{ github.event.inputs.version_number }}
echo Workflow dispatch event dry run: ${{ github.event.inputs.is_dry_run }}
echo ::set-output name=VERSION_NUMBER::$VERSION_NUMBER
echo ::set-output name=IS_DRY_RUN::$IS_DRY_RUN
- uses: actions/setup-python@v2
with:
python-version: "3.8"
- name: Install python dependencies
run: |
python3 -m venv env
source env/bin/activate
pip install --upgrade pip
- name: Create PR branch
if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
run: |
git checkout -b bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_$GITHUB_RUN_ID
git push origin bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_$GITHUB_RUN_ID
git branch --set-upstream-to=origin/bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_$GITHUB_RUN_ID bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_$GITHUB_RUN_ID
- name: Generate Docker requirements
run: |
source env/bin/activate
pip install -r requirements.txt
pip freeze -l > docker/requirements/requirements.txt
git status
- name: Bump version
run: |
source env/bin/activate
pip install -r dev-requirements.txt
env/bin/bumpversion --allow-dirty --new-version ${{steps.variables.outputs.VERSION_NUMBER}} major
git status
- name: Commit version bump directly
uses: EndBug/add-and-commit@v7
if: ${{ steps.variables.outputs.IS_DRY_RUN == 'false' }}
with:
author_name: 'Github Build Bot'
author_email: 'buildbot@fishtownanalytics.com'
message: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
- name: Commit version bump to branch
uses: EndBug/add-and-commit@v7
if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
with:
author_name: 'Github Build Bot'
author_email: 'buildbot@fishtownanalytics.com'
message: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
branch: 'bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'
push: 'origin origin/bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'
- name: Create Pull Request
uses: peter-evans/create-pull-request@v3
if: ${{ steps.variables.outputs.IS_DRY_RUN == 'true' }}
with:
author: 'Github Build Bot <buildbot@fishtownanalytics.com>'
draft: true
base: ${{github.ref}}
title: 'Bumping version to ${{steps.variables.outputs.VERSION_NUMBER}}'
branch: 'bumping-version/${{steps.variables.outputs.VERSION_NUMBER}}_${{GITHUB.RUN_ID}}'

View File

@@ -1,9 +1,8 @@
The core function of dbt is SQL compilation and execution. Users create projects of dbt resources (models, tests, seeds, snapshots, ...), defined in SQL and YAML files, and they invoke dbt to create, update, or query associated views and tables. Today, dbt makes heavy use of Jinja2 to enable the templating of SQL, and to construct a DAG (Directed Acyclic Graph) from all of the resources in a project. Users can also extend their projects by installing resources (including Jinja macros) from other projects, called "packages."
The core function of dbt is SQL compilation and execution. Users create projects of dbt resources (models, tests, seeds, snapshots, ...), defined in SQL and YAML files, and they invoke dbt to create, update, or query associated views and tables. Today, dbt makes heavy use of Jinja2 to enable the templating of SQL, and to construct a DAG (Directed Acyclic Graph) from all of the resources in a project. Users can also extend their projects by installing resources (including Jinja macros) from other projects, called "packages."
## dbt-core
Most of the python code in the repository is within the `core/dbt` directory. Currently the main subdirectories are:
- [`adapters`](core/dbt/adapters): Define base classes for behavior that is likely to differ across databases
- [`clients`](core/dbt/clients): Interface with dependencies (agate, jinja) or across operating systems
- [`config`](core/dbt/config): Reconcile user-supplied configuration from connection profiles, project files, and Jinja macros
@@ -13,20 +12,23 @@ Most of the python code in the repository is within the `core/dbt` directory. Cu
- [`graph`](core/dbt/graph): Produce a `networkx` DAG of project resources, and selecting those resources given user-supplied criteria
- [`include`](core/dbt/include): The dbt "global project," which defines default implementations of Jinja2 macros
- [`parser`](core/dbt/parser): Read project files, validate, construct python objects
- [`rpc`](core/dbt/rpc): Provide remote procedure call server for invoking dbt, following JSON-RPC 2.0 spec
- [`task`](core/dbt/task): Set forth the actions that dbt can perform when invoked
### Invoking dbt
The "tasks" map to top-level dbt commands. So `dbt run` => task.run.RunTask, etc. Some are more like abstract base classes (GraphRunnableTask, for example) but all the concrete types outside of task should map to tasks. Currently one executes at a time. The tasks kick off their “Runners” and those do execute in parallel. The parallelism is managed via a thread pool, in GraphRunnableTask.
There are two supported ways of invoking dbt: from the command line and using an RPC server.
The "tasks" map to top-level dbt commands. So `dbt run` => task.run.RunTask, etc. Some are more like abstract base classes (GraphRunnableTask, for example) but all the concrete types outside of task/rpc should map to tasks. Currently one executes at a time. The tasks kick off their “Runners” and those do execute in parallel. The parallelism is managed via a thread pool, in GraphRunnableTask.
core/dbt/include/index.html
This is the docs website code. It comes from the dbt-docs repository, and is generated when a release is packaged.
## Adapters
dbt uses an adapter-plugin pattern to extend support to different databases, warehouses, query engines, etc. For testing and development purposes, the dbt-postgres plugin lives alongside the dbt-core codebase, in the [`plugins`](plugins) subdirectory. Like other adapter plugins, it is a self-contained codebase and package that builds on top of dbt-core.
dbt uses an adapter-plugin pattern to extend support to different databases, warehouses, query engines, etc. The four core adapters that are in the main repository, contained within the [`plugins`](plugins) subdirectory, are: Postgres Redshift, Snowflake and BigQuery. Other warehouses use adapter plugins defined in separate repositories (e.g. [dbt-spark](https://github.com/fishtown-analytics/dbt-spark), [dbt-presto](https://github.com/fishtown-analytics/dbt-presto)).
Each adapter is a mix of python, Jinja2, and SQL. The adapter code also makes heavy use of Jinja2 to wrap modular chunks of SQL functionality, define default implementations, and allow plugins to override it.
Each adapter is a mix of python, Jinja2, and SQL. The adapter code also makes heavy use of Jinja2 to wrap modular chunks of SQL functionality, define default implementations, and allow plugins to override it.
Each adapter plugin is a standalone python package that includes:

File diff suppressed because it is too large Load Diff

View File

@@ -14,10 +14,6 @@ This document is a guide intended for folks interested in contributing to `dbt`.
If you're new to python development or contributing to open-source software, we encourage you to read this document from start to finish. If you get stuck, drop us a line in the `#dbt-core-development` channel on [slack](https://community.getdbt.com).
#### Adapters
If you have an issue or code change suggestion related to a specific database [adapter](https://docs.getdbt.com/docs/available-adapters); please refer to that supported databases seperate repo for those contributions.
### Signing the CLA
Please note that all contributors to `dbt` must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements) to have their Pull Request merged into the `dbt` codebase. If you are unable to sign the CLA, then the `dbt` maintainers will unfortunately be unable to merge your Pull Request. You are, however, welcome to open issues and comment on existing ones.
@@ -28,7 +24,7 @@ Please note that all contributors to `dbt` must sign the [Contributor License Ag
### Defining the problem
If you have an idea for a new feature or if you've discovered a bug in `dbt`, the first step is to open an issue. Please check the list of [open issues](https://github.com/dbt-labs/dbt-core/issues) before creating a new one. If you find a relevant issue, please add a comment to the open issue instead of creating a new one. There are hundreds of open issues in this repository and it can be hard to know where to look for a relevant open issue. **The `dbt` maintainers are always happy to point contributors in the right direction**, so please err on the side of documenting your idea in a new issue if you are unsure where a problem statement belongs.
If you have an idea for a new feature or if you've discovered a bug in `dbt`, the first step is to open an issue. Please check the list of [open issues](https://github.com/dbt-labs/dbt/issues) before creating a new one. If you find a relevant issue, please add a comment to the open issue instead of creating a new one. There are hundreds of open issues in this repository and it can be hard to know where to look for a relevant open issue. **The `dbt` maintainers are always happy to point contributors in the right direction**, so please err on the side of documenting your idea in a new issue if you are unsure where a problem statement belongs.
> **Note:** All community-contributed Pull Requests _must_ be associated with an open issue. If you submit a Pull Request that does not pertain to an open issue, you will be asked to create an issue describing the problem before the Pull Request can be reviewed.
@@ -40,7 +36,7 @@ After you open an issue, a `dbt` maintainer will follow up by commenting on your
If an issue is appropriately well scoped and describes a beneficial change to the `dbt` codebase, then anyone may submit a Pull Request to implement the functionality described in the issue. See the sections below on how to do this.
The `dbt` maintainers will add a `good first issue` label if an issue is suitable for a first-time contributor. This label often means that the required code change is small, limited to one database adapter, or a net-new addition that does not impact existing functionality. You can see the list of currently open issues on the [Contribute](https://github.com/dbt-labs/dbt-core/contribute) page.
The `dbt` maintainers will add a `good first issue` label if an issue is suitable for a first-time contributor. This label often means that the required code change is small, limited to one database adapter, or a net-new addition that does not impact existing functionality. You can see the list of currently open issues on the [Contribute](https://github.com/dbt-labs/dbt/contribute) page.
Here's a good workflow:
- Comment on the open issue, expressing your interest in contributing the required code change
@@ -56,15 +52,15 @@ The `dbt` maintainers use labels to categorize open issues. Some labels indicate
| tag | description |
| --- | ----------- |
| [triage](https://github.com/dbt-labs/dbt-core/labels/triage) | This is a new issue which has not yet been reviewed by a `dbt` maintainer. This label is removed when a maintainer reviews and responds to the issue. |
| [bug](https://github.com/dbt-labs/dbt-core/labels/bug) | This issue represents a defect or regression in `dbt` |
| [enhancement](https://github.com/dbt-labs/dbt-core/labels/enhancement) | This issue represents net-new functionality in `dbt` |
| [good first issue](https://github.com/dbt-labs/dbt-core/labels/good%20first%20issue) | This issue does not require deep knowledge of the `dbt` codebase to implement. This issue is appropriate for a first-time contributor. |
| [help wanted](https://github.com/dbt-labs/dbt-core/labels/help%20wanted) / [discussion](https://github.com/dbt-labs/dbt-core/labels/discussion) | Conversation around this issue in ongoing, and there isn't yet a clear path forward. Input from community members is most welcome. |
| [duplicate](https://github.com/dbt-labs/dbt-core/issues/duplicate) | This issue is functionally identical to another open issue. The `dbt` maintainers will close this issue and encourage community members to focus conversation on the other one. |
| [snoozed](https://github.com/dbt-labs/dbt-core/labels/snoozed) | This issue describes a good idea, but one which will probably not be addressed in a six-month time horizon. The `dbt` maintainers will revist these issues periodically and re-prioritize them accordingly. |
| [stale](https://github.com/dbt-labs/dbt-core/labels/stale) | This is an old issue which has not recently been updated. Stale issues will periodically be closed by `dbt` maintainers, but they can be re-opened if the discussion is restarted. |
| [wontfix](https://github.com/dbt-labs/dbt-core/labels/wontfix) | This issue does not require a code change in the `dbt` repository, or the maintainers are unwilling/unable to merge a Pull Request which implements the behavior described in the issue. |
| [triage](https://github.com/dbt-labs/dbt/labels/triage) | This is a new issue which has not yet been reviewed by a `dbt` maintainer. This label is removed when a maintainer reviews and responds to the issue. |
| [bug](https://github.com/dbt-labs/dbt/labels/bug) | This issue represents a defect or regression in `dbt` |
| [enhancement](https://github.com/dbt-labs/dbt/labels/enhancement) | This issue represents net-new functionality in `dbt` |
| [good first issue](https://github.com/dbt-labs/dbt/labels/good%20first%20issue) | This issue does not require deep knowledge of the `dbt` codebase to implement. This issue is appropriate for a first-time contributor. |
| [help wanted](https://github.com/dbt-labs/dbt/labels/help%20wanted) / [discussion](https://github.com/dbt-labs/dbt/labels/discussion) | Conversation around this issue in ongoing, and there isn't yet a clear path forward. Input from community members is most welcome. |
| [duplicate](https://github.com/dbt-labs/dbt/issues/duplicate) | This issue is functionally identical to another open issue. The `dbt` maintainers will close this issue and encourage community members to focus conversation on the other one. |
| [snoozed](https://github.com/dbt-labs/dbt/labels/snoozed) | This issue describes a good idea, but one which will probably not be addressed in a six-month time horizon. The `dbt` maintainers will revist these issues periodically and re-prioritize them accordingly. |
| [stale](https://github.com/dbt-labs/dbt/labels/stale) | This is an old issue which has not recently been updated. Stale issues will periodically be closed by `dbt` maintainers, but they can be re-opened if the discussion is restarted. |
| [wontfix](https://github.com/dbt-labs/dbt/labels/wontfix) | This issue does not require a code change in the `dbt` repository, or the maintainers are unwilling/unable to merge a Pull Request which implements the behavior described in the issue. |
#### Branching Strategy
@@ -72,7 +68,7 @@ The `dbt` maintainers use labels to categorize open issues. Some labels indicate
- **Trunks** are where active development of the next release takes place. There is one trunk named `develop` at the time of writing this, and will be the default branch of the repository.
- **Release Branches** track a specific, not yet complete release of `dbt`. Each minor version release has a corresponding release branch. For example, the `0.11.x` series of releases has a branch called `0.11.latest`. This allows us to release new patch versions under `0.11` without necessarily needing to pull them into the latest version of `dbt`.
- **Feature Branches** track individual features and fixes. On completion they should be merged into the trunk branch or a specific release branch.
- **Feature Branches** track individual features and fixes. On completion they should be merged into the trunk brnach or a specific release branch.
## Getting the code
@@ -107,7 +103,7 @@ A short list of tools used in `dbt` testing that will be helpful to your underst
- [`make`](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) - but don't worry too much, nobody _really_ understands how make works and our Makefile is super simple
- [`flake8`](https://flake8.pycqa.org/en/latest/) for code linting
- [`mypy`](https://mypy.readthedocs.io/en/stable/) for static type checking
- [Github Actions](https://github.com/features/actions)
- [CircleCI](https://circleci.com/product/) and [Azure Pipelines](https://azure.microsoft.com/en-us/services/devops/pipelines/)
A deep understanding of these tools in not required to effectively contribute to `dbt`, but we recommend checking out the attached documentation if you're interested in learning more about them.
@@ -139,7 +135,7 @@ brew install postgresql
### Installation
First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment). Also ensure you have the latest version of pip installed with `pip install --upgrade pip`. Next, install `dbt` (and its dependencies) with:
First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment). Next, install `dbt` (and its dependencies) with:
```sh
make dev
@@ -159,7 +155,7 @@ Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as
Getting the `dbt` integration tests set up in your local environment will be very helpful as you start to make changes to your local version of `dbt`. The section that follows outlines some helpful tips for setting up the test environment.
Although `dbt` works with a number of different databases, you won't need to supply credentials for every one of these databases in your test environment. Instead you can test all dbt-core code changes with Python and Postgres.
Since `dbt` works with a number of different databases, you will need to supply credentials for one or more of these databases in your test environment. Most organizations don't have access to each of a BigQuery, Redshift, Snowflake, and Postgres database, so it's likely that you will be unable to run every integration test locally. Fortunately, dbt Labs provides a CI environment with access to sandboxed Redshift, Snowflake, BigQuery, and Postgres databases. See the section on [_Submitting a Pull Request_](#submitting-a-pull-request) below for more information on this CI setup.
### Initial setup
@@ -228,7 +224,7 @@ python -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
> is a list of useful command-line options for `pytest` to use while developing.
## Submitting a Pull Request
dbt Labs provides a CI environment to test changes to specific adapters, and periodic maintenance checks of `dbt-core` through Github Actions. For example, if you submit a pull request to the `dbt-redshift` repo, GitHub will trigger automated code checks and tests against Redshift.
dbt Labs provides a sandboxed Redshift, Snowflake, and BigQuery database for use in a CI environment. When pull requests are submitted to the `dbt-labs/dbt` repo, GitHub will trigger automated tests in CircleCI and Azure Pipelines.
A `dbt` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.

View File

@@ -1,4 +1,4 @@
FROM ubuntu:20.04
FROM ubuntu:18.04
ENV DEBIAN_FRONTEND noninteractive
@@ -27,7 +27,7 @@ RUN apt-get update \
&& apt-get install -y \
python \
python-dev \
python3-pip \
python-pip \
python3.6 \
python3.6-dev \
python3-pip \

View File

@@ -44,6 +44,30 @@ integration-postgres: .env ## Runs postgres integration tests with py38.
integration-postgres-fail-fast: .env ## Runs postgres integration tests with py38 in "fail fast" mode.
$(DOCKER_CMD) tox -e py38-postgres -- -x -nauto
.PHONY: integration-redshift
integration-redshift: .env ## Runs redshift integration tests with py38.
$(DOCKER_CMD) tox -e py38-redshift -- -nauto
.PHONY: integration-redshift-fail-fast
integration-redshift-fail-fast: .env ## Runs redshift integration tests with py38 in "fail fast" mode.
$(DOCKER_CMD) tox -e py38-redshift -- -x -nauto
.PHONY: integration-snowflake
integration-snowflake: .env ## Runs snowflake integration tests with py38.
$(DOCKER_CMD) tox -e py38-snowflake -- -nauto
.PHONY: integration-snowflake-fail-fast
integration-snowflake-fail-fast: .env ## Runs snowflake integration tests with py38 in "fail fast" mode.
$(DOCKER_CMD) tox -e py38-snowflake -- -x -nauto
.PHONY: integration-bigquery
integration-bigquery: .env ## Runs bigquery integration tests with py38.
$(DOCKER_CMD) tox -e py38-bigquery -- -nauto
.PHONY: integration-bigquery-fail-fast
integration-bigquery-fail-fast: .env ## Runs bigquery integration tests with py38 in "fail fast" mode.
$(DOCKER_CMD) tox -e py38-bigquery -- -x -nauto
.PHONY: setup-db
setup-db: ## Setup Postgres database with docker-compose for system testing.
docker-compose up -d database

View File

@@ -1,18 +1,21 @@
<p align="center">
<img src="https://raw.githubusercontent.com/dbt-labs/dbt-core/fa1ea14ddfb1d5ae319d5141844910dd53ab2834/etc/dbt-core.svg" alt="dbt logo" width="750"/>
<img src="https://raw.githubusercontent.com/dbt-labs/dbt/ec7dee39f793aa4f7dd3dae37282cc87664813e4/etc/dbt-logo-full.svg" alt="dbt logo" width="500"/>
</p>
<p align="center">
<a href="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml">
<img src="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml/badge.svg?event=push" alt="Unit Tests Badge"/>
<a href="https://github.com/dbt-labs/dbt/actions/workflows/tests.yml?query=branch%3Adevelop">
<img src="https://github.com/dbt-labs/dbt/actions/workflows/tests.yml/badge.svg" alt="GitHub Actions"/>
</a>
<a href="https://github.com/dbt-labs/dbt-core/actions/workflows/integration.yml">
<img src="https://github.com/dbt-labs/dbt-core/actions/workflows/integration.yml/badge.svg?event=push" alt="Integration Tests Badge"/>
<a href="https://circleci.com/gh/dbt-labs/dbt/tree/develop">
<img src="https://circleci.com/gh/dbt-labs/dbt/tree/develop.svg?style=svg" alt="CircleCI" />
</a>
<a href="https://dev.azure.com/fishtown-analytics/dbt/_build?definitionId=1&_a=summary&repositoryFilter=1&branchFilter=789%2C789%2C789%2C789">
<img src="https://dev.azure.com/fishtown-analytics/dbt/_apis/build/status/fishtown-analytics.dbt?branchName=develop" alt="Azure Pipelines" />
</a>
</p>
**[dbt](https://www.getdbt.com/)** enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.
![architecture](https://raw.githubusercontent.com/dbt-labs/dbt-core/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-arch.png)
![dbt architecture](https://raw.githubusercontent.com/dbt-labs/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-arch.png)
## Understanding dbt
@@ -20,7 +23,7 @@ Analysts using dbt can transform their data by simply writing select statements,
These select statements, or "models", form a dbt project. Models frequently build on top of one another dbt makes it easy to [manage relationships](https://docs.getdbt.com/docs/ref) between models, and [visualize these relationships](https://docs.getdbt.com/docs/documentation), as well as assure the quality of your transformations through [testing](https://docs.getdbt.com/docs/testing).
![dbt dag](https://raw.githubusercontent.com/dbt-labs/dbt-core/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-dag.png)
![dbt dag](https://raw.githubusercontent.com/dbt-labs/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-dag.png)
## Getting started
@@ -34,8 +37,8 @@ These select statements, or "models", form a dbt project. Models frequently buil
## Reporting bugs and contributing code
- Want to report a bug or request a feature? Let us know on [Slack](http://community.getdbt.com/), or open [an issue](https://github.com/dbt-labs/dbt-core/issues/new)
- Want to help us build dbt? Check out the [Contributing Guide](https://github.com/dbt-labs/dbt-core/blob/HEAD/CONTRIBUTING.md)
- Want to report a bug or request a feature? Let us know on [Slack](http://community.getdbt.com/), or open [an issue](https://github.com/dbt-labs/dbt/issues/new)
- Want to help us build dbt? Check out the [Contributing Guide](https://github.com/dbt-labs/dbt/blob/HEAD/CONTRIBUTING.md)
## Code of Conduct

154
azure-pipelines.yml Normal file
View File

@@ -0,0 +1,154 @@
# Python package
# Create and test a Python package on multiple Python versions.
# Add steps that analyze code, save the dist with the build record, publish to a PyPI-compatible index, and more:
# https://docs.microsoft.com/azure/devops/pipelines/languages/python
trigger:
branches:
include:
- develop
- '*.latest'
- pr/*
jobs:
- job: UnitTest
pool:
vmImage: 'vs2017-win2016'
steps:
- task: UsePythonVersion@0
inputs:
versionSpec: '3.7'
architecture: 'x64'
- script: python -m pip install --upgrade pip && pip install tox
displayName: 'Install dependencies'
- script: python -m tox -e py -- -v
displayName: Run unit tests
- job: PostgresIntegrationTest
pool:
vmImage: 'vs2017-win2016'
dependsOn: UnitTest
steps:
- pwsh: |
$serviceName = Get-Service -Name postgresql*
Set-Service -InputObject $serviceName -StartupType Automatic
Start-Service -InputObject $serviceName
& $env:PGBIN\createdb.exe -U postgres dbt
& $env:PGBIN\psql.exe -U postgres -c "CREATE ROLE root WITH PASSWORD 'password';"
& $env:PGBIN\psql.exe -U postgres -c "ALTER ROLE root WITH LOGIN;"
& $env:PGBIN\psql.exe -U postgres -c "GRANT CREATE, CONNECT ON DATABASE dbt TO root WITH GRANT OPTION;"
& $env:PGBIN\psql.exe -U postgres -c "CREATE ROLE noaccess WITH PASSWORD 'password' NOSUPERUSER;"
& $env:PGBIN\psql.exe -U postgres -c "ALTER ROLE noaccess WITH LOGIN;"
& $env:PGBIN\psql.exe -U postgres -c "GRANT CONNECT ON DATABASE dbt TO noaccess;"
displayName: Install postgresql and set up database
- task: UsePythonVersion@0
inputs:
versionSpec: '3.7'
architecture: 'x64'
- script: python -m pip install --upgrade pip && pip install tox
displayName: 'Install dependencies'
- script: python -m tox -e py-postgres -- -v -n4
displayName: Run integration tests
# These three are all similar except secure environment variables, which MUST be passed along to their tasks,
# but there's probably a better way to do this!
- job: SnowflakeIntegrationTest
pool:
vmImage: 'vs2017-win2016'
dependsOn: UnitTest
condition: succeeded()
steps:
- task: UsePythonVersion@0
inputs:
versionSpec: '3.7'
architecture: 'x64'
- script: python -m pip install --upgrade pip && pip install tox
displayName: 'Install dependencies'
- script: python -m tox -e py-snowflake -- -v -n4
env:
SNOWFLAKE_TEST_ACCOUNT: $(SNOWFLAKE_TEST_ACCOUNT)
SNOWFLAKE_TEST_PASSWORD: $(SNOWFLAKE_TEST_PASSWORD)
SNOWFLAKE_TEST_USER: $(SNOWFLAKE_TEST_USER)
SNOWFLAKE_TEST_WAREHOUSE: $(SNOWFLAKE_TEST_WAREHOUSE)
SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN: $(SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN)
SNOWFLAKE_TEST_OAUTH_CLIENT_ID: $(SNOWFLAKE_TEST_OAUTH_CLIENT_ID)
SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET: $(SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET)
displayName: Run integration tests
- job: BigQueryIntegrationTest
pool:
vmImage: 'vs2017-win2016'
dependsOn: UnitTest
condition: succeeded()
steps:
- task: UsePythonVersion@0
inputs:
versionSpec: '3.7'
architecture: 'x64'
- script: python -m pip install --upgrade pip && pip install tox
displayName: 'Install dependencies'
- script: python -m tox -e py-bigquery -- -v -n4
env:
BIGQUERY_SERVICE_ACCOUNT_JSON: $(BIGQUERY_SERVICE_ACCOUNT_JSON)
displayName: Run integration tests
- job: RedshiftIntegrationTest
pool:
vmImage: 'vs2017-win2016'
dependsOn: UnitTest
condition: succeeded()
steps:
- task: UsePythonVersion@0
inputs:
versionSpec: '3.7'
architecture: 'x64'
- script: python -m pip install --upgrade pip && pip install tox
displayName: 'Install dependencies'
- script: python -m tox -e py-redshift -- -v -n4
env:
REDSHIFT_TEST_DBNAME: $(REDSHIFT_TEST_DBNAME)
REDSHIFT_TEST_PASS: $(REDSHIFT_TEST_PASS)
REDSHIFT_TEST_USER: $(REDSHIFT_TEST_USER)
REDSHIFT_TEST_PORT: $(REDSHIFT_TEST_PORT)
REDSHIFT_TEST_HOST: $(REDSHIFT_TEST_HOST)
displayName: Run integration tests
- job: BuildWheel
pool:
vmImage: 'vs2017-win2016'
dependsOn:
- UnitTest
- PostgresIntegrationTest
- RedshiftIntegrationTest
- SnowflakeIntegrationTest
- BigQueryIntegrationTest
condition: succeeded()
steps:
- task: UsePythonVersion@0
inputs:
versionSpec: '3.7'
architecture: 'x64'
- script: python -m pip install --upgrade pip setuptools && python -m pip install -r requirements.txt && python -m pip install -r dev-requirements.txt
displayName: Install dependencies
- task: ShellScript@2
inputs:
scriptPath: scripts/build-wheels.sh
- task: CopyFiles@2
inputs:
contents: 'dist\?(*.whl|*.tar.gz)'
TargetFolder: '$(Build.ArtifactStagingDirectory)'
- task: PublishBuildArtifacts@1
inputs:
pathtoPublish: '$(Build.ArtifactStagingDirectory)'
artifactName: dists

View File

@@ -238,6 +238,12 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
@classmethod
def _rollback(cls, connection: Connection) -> None:
"""Roll back the given connection."""
if flags.STRICT_MODE:
if not isinstance(connection, Connection):
raise dbt.exceptions.CompilerException(
f'In _rollback, got {connection} - not a Connection!'
)
if connection.transaction_open is False:
raise dbt.exceptions.InternalException(
f'Tried to rollback transaction on connection '
@@ -251,6 +257,12 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
@classmethod
def close(cls, connection: Connection) -> Connection:
if flags.STRICT_MODE:
if not isinstance(connection, Connection):
raise dbt.exceptions.CompilerException(
f'In close, got {connection} - not a Connection!'
)
# if the connection is in closed or init, there's nothing to do
if connection.state in {ConnectionState.CLOSED, ConnectionState.INIT}:
return connection

View File

@@ -16,7 +16,9 @@ from dbt.exceptions import (
get_relation_returned_multiple_results,
InternalException, NotImplementedException, RuntimeException,
)
from dbt import flags
from dbt import deprecations
from dbt.adapters.protocol import (
AdapterConfig,
ConnectionManagerProtocol,
@@ -29,6 +31,7 @@ from dbt.contracts.graph.compiled import (
from dbt.contracts.graph.manifest import Manifest, MacroManifest
from dbt.contracts.graph.parsed import ParsedSeedNode
from dbt.exceptions import warn_or_error
from dbt.node_types import NodeType
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.utils import filter_null_values, executor
@@ -287,7 +290,9 @@ class BaseAdapter(metaclass=AdapterMeta):
def _schema_is_cached(self, database: Optional[str], schema: str) -> bool:
"""Check if the schema is cached, and by default logs if it is not."""
if (database, schema) not in self.cache:
if flags.USE_CACHE is False:
return False
elif (database, schema) not in self.cache:
logger.debug(
'On "{}": cache miss for schema "{}.{}", this is inefficient'
.format(self.nice_connection_name(), database, schema)
@@ -305,7 +310,8 @@ class BaseAdapter(metaclass=AdapterMeta):
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
node.resource_type in NodeType.executable() and
not node.is_ephemeral_model
)
}
@@ -320,9 +326,7 @@ class BaseAdapter(metaclass=AdapterMeta):
"""
info_schema_name_map = SchemaSearchMap()
nodes: Iterator[CompileResultNode] = chain(
[node for node in manifest.nodes.values() if (
node.is_relational and not node.is_ephemeral_model
)],
manifest.nodes.values(),
manifest.sources.values(),
)
for node in nodes:
@@ -338,6 +342,9 @@ class BaseAdapter(metaclass=AdapterMeta):
"""Populate the relations cache for the given schemas. Returns an
iterable of the schemas populated, as strings.
"""
if not flags.USE_CACHE:
return
cache_schemas = self._get_cache_schemas(manifest)
with executor(self.config) as tpe:
futures: List[Future[List[BaseRelation]]] = []
@@ -370,6 +377,9 @@ class BaseAdapter(metaclass=AdapterMeta):
"""Run a query that gets a populated cache of the relations in the
database and set the cache on this adapter.
"""
if not flags.USE_CACHE:
return
with self.cache.lock:
if clear:
self.cache.clear()
@@ -383,7 +393,8 @@ class BaseAdapter(metaclass=AdapterMeta):
raise_compiler_error(
'Attempted to cache a null relation for {}'.format(name)
)
self.cache.add(relation)
if flags.USE_CACHE:
self.cache.add(relation)
# so jinja doesn't render things
return ''
@@ -397,7 +408,8 @@ class BaseAdapter(metaclass=AdapterMeta):
raise_compiler_error(
'Attempted to drop a null relation for {}'.format(name)
)
self.cache.drop(relation)
if flags.USE_CACHE:
self.cache.drop(relation)
return ''
@available
@@ -418,7 +430,8 @@ class BaseAdapter(metaclass=AdapterMeta):
.format(src_name, dst_name, name)
)
self.cache.rename(from_relation, to_relation)
if flags.USE_CACHE:
self.cache.rename(from_relation, to_relation)
return ''
###
@@ -796,11 +809,12 @@ class BaseAdapter(metaclass=AdapterMeta):
def quote_seed_column(
self, column: str, quote_config: Optional[bool]
) -> str:
quote_columns: bool = True
# this is the default for now
quote_columns: bool = False
if isinstance(quote_config, bool):
quote_columns = quote_config
elif quote_config is None:
pass
deprecations.warn('column-quoting-unset')
else:
raise_compiler_error(
f'The seed configuration value of "quote_columns" has an '
@@ -932,6 +946,7 @@ class BaseAdapter(metaclass=AdapterMeta):
project: Optional[str] = None,
context_override: Optional[Dict[str, Any]] = None,
kwargs: Dict[str, Any] = None,
release: bool = False,
text_only_columns: Optional[Iterable[str]] = None,
) -> agate.Table:
"""Look macro_name up in the manifest and execute its results.
@@ -945,8 +960,10 @@ class BaseAdapter(metaclass=AdapterMeta):
execution context.
:param kwargs: An optional dict of keyword args used to pass to the
macro.
:param release: Ignored.
"""
if release is not False:
deprecations.warn('execute-macro-release')
if kwargs is None:
kwargs = {}
if context_override is None:

View File

@@ -11,6 +11,7 @@ from dbt.contracts.connection import (
Connection, ConnectionState, AdapterResponse
)
from dbt.logger import GLOBAL_LOGGER as logger
from dbt import flags
class SQLConnectionManager(BaseConnectionManager):
@@ -143,6 +144,13 @@ class SQLConnectionManager(BaseConnectionManager):
def begin(self):
connection = self.get_thread_connection()
if flags.STRICT_MODE:
if not isinstance(connection, Connection):
raise dbt.exceptions.CompilerException(
f'In begin, got {connection} - not a Connection!'
)
if connection.transaction_open is True:
raise dbt.exceptions.InternalException(
'Tried to begin a new transaction on connection "{}", but '
@@ -155,6 +163,12 @@ class SQLConnectionManager(BaseConnectionManager):
def commit(self):
connection = self.get_thread_connection()
if flags.STRICT_MODE:
if not isinstance(connection, Connection):
raise dbt.exceptions.CompilerException(
f'In commit, got {connection} - not a Connection!'
)
if connection.transaction_open is False:
raise dbt.exceptions.InternalException(
'Tried to commit transaction on connection "{}", but '

View File

@@ -0,0 +1,26 @@
from dbt.logger import GLOBAL_LOGGER as logger
import dbt.exceptions
from dbt.clients.system import run_cmd
NOT_INSTALLED_MSG = """
dbt requires the gcloud SDK to be installed to authenticate with BigQuery.
Please download and install the SDK, or use a Service Account instead.
https://cloud.google.com/sdk/
"""
def gcloud_installed():
try:
run_cmd('.', ['gcloud', '--version'])
return True
except OSError as e:
logger.debug(e)
return False
def setup_default_credentials():
if gcloud_installed():
run_cmd('.', ["gcloud", "auth", "application-default", "login"])
else:
raise dbt.exceptions.RuntimeException(NOT_INSTALLED_MSG)

View File

@@ -25,8 +25,8 @@ from dbt.utils import (
)
from dbt.clients._jinja_blocks import BlockIterator, BlockData, BlockTag
from dbt.contracts.graph.compiled import CompiledGenericTestNode
from dbt.contracts.graph.parsed import ParsedGenericTestNode
from dbt.contracts.graph.compiled import CompiledSchemaTestNode
from dbt.contracts.graph.parsed import ParsedSchemaTestNode
from dbt.exceptions import (
InternalException, raise_compiler_error, CompilationException,
invalid_materialization_argument, MacroReturn, JinjaRenderingException,
@@ -627,12 +627,12 @@ def extract_toplevel_blocks(
)
GENERIC_TEST_KWARGS_NAME = '_dbt_generic_test_kwargs'
SCHEMA_TEST_KWARGS_NAME = '_dbt_schema_test_kwargs'
def add_rendered_test_kwargs(
context: Dict[str, Any],
node: Union[ParsedGenericTestNode, CompiledGenericTestNode],
node: Union[ParsedSchemaTestNode, CompiledSchemaTestNode],
capture_macros: bool = False,
) -> None:
"""Render each of the test kwargs in the given context using the native
@@ -662,4 +662,4 @@ def add_rendered_test_kwargs(
return value
kwargs = deep_map(_convert_function, node.test_metadata.kwargs)
context[GENERIC_TEST_KWARGS_NAME] = kwargs
context[SCHEMA_TEST_KWARGS_NAME] = kwargs

View File

@@ -96,6 +96,7 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
possible_macro_calls.append(func_name)
# packages positional argument
packages = None
macro_namespace = None
packages_arg = None
packages_arg_type = None
@@ -108,7 +109,13 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
# keyword arguments
if func_call.kwargs:
for kwarg in func_call.kwargs:
if kwarg.key == 'macro_name':
if kwarg.key == 'packages':
# The packages keyword will be deprecated and
# eventually removed
packages_arg = kwarg.value
# This can be a List or a Call
packages_arg_type = type(kwarg.value).__name__
elif kwarg.key == 'macro_name':
# This will remain to enable static resolution
if type(kwarg.value).__name__ == 'Const':
func_name = kwarg.value.value
@@ -135,10 +142,63 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
elif packages_arg_type == 'Const':
# This will remain to enable static resolution
macro_namespace = packages_arg.value
elif packages_arg_type == 'Call':
# This is deprecated and should be removed eventually.
# It is here to support (hackily) common ways of providing
# a packages list to adapter.dispatch
if (hasattr(packages_arg, 'node') and
hasattr(packages_arg.node, 'node') and
hasattr(packages_arg.node.node, 'name') and
hasattr(packages_arg.node, 'attr')):
package_name = packages_arg.node.node.name
macro_name = packages_arg.node.attr
if (macro_name.startswith('_get') and 'namespaces' in macro_name):
# noqa: https://github.com/fishtown-analytics/dbt-utils/blob/9e9407b/macros/cross_db_utils/_get_utils_namespaces.sql
var_name = f'{package_name}_dispatch_list'
# hard code compatibility for fivetran_utils, just a teensy bit different
# noqa: https://github.com/fivetran/dbt_fivetran_utils/blob/0978ba2/macros/_get_utils_namespaces.sql
if package_name == 'fivetran_utils':
default_packages = ['dbt_utils', 'fivetran_utils']
else:
default_packages = [package_name]
namespace_names = get_dispatch_list(ctx, var_name, default_packages)
packages = []
if namespace_names:
packages.extend(namespace_names)
else:
msg = (
f"As of v0.19.2, custom macros, such as '{macro_name}', are no longer "
"supported in the 'packages' argument of 'adapter.dispatch()'.\n"
f"See https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch "
"for details."
).strip()
raise_compiler_error(msg)
elif packages_arg_type == 'Add':
# This logic is for when there is a variable and an addition of a list,
# like: packages = (var('local_utils_dispatch_list', []) + ['local_utils2'])
# This is deprecated and should be removed eventually.
namespace_var = None
default_namespaces = []
# This might be a single call or it might be the 'left' piece in an addition
for var_call in packages_arg.find_all(jinja2.nodes.Call):
if (hasattr(var_call, 'node') and
var_call.node.name == 'var' and
hasattr(var_call, 'args')):
namespace_var = var_call.args[0].value
if hasattr(packages_arg, 'right'): # we have a default list of namespaces
for item in packages_arg.right.items:
default_namespaces.append(item.value)
if namespace_var:
namespace_names = get_dispatch_list(ctx, namespace_var, default_namespaces)
packages = []
if namespace_names:
packages.extend(namespace_names)
if db_wrapper:
macro = db_wrapper.dispatch(
func_name,
packages=packages,
macro_namespace=macro_namespace
).macro
func_name = f'{macro.package_name}.{macro.name}'
@@ -146,9 +206,20 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
else: # this is only for test/unit/test_macro_calls.py
if macro_namespace:
packages = [macro_namespace]
else:
if packages is None:
packages = []
for package_name in packages:
possible_macro_calls.append(f'{package_name}.{func_name}')
return possible_macro_calls
def get_dispatch_list(ctx, var_name, default_packages):
namespace_list = None
try:
# match the logic currently used in package _get_namespaces() macro
namespace_list = ctx['var'](var_name) + default_packages
except Exception:
pass
namespace_list = namespace_list if namespace_list else default_packages
return namespace_list

View File

@@ -1,9 +1,10 @@
import functools
from functools import wraps
import requests
from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
from dbt.exceptions import RegistryException
from dbt.utils import memoized
from dbt.logger import GLOBAL_LOGGER as logger
from dbt import deprecations
import os
import time
if os.getenv('DBT_PACKAGE_HUB_URL'):
DEFAULT_REGISTRY_BASE_URL = os.getenv('DBT_PACKAGE_HUB_URL')
@@ -18,11 +19,26 @@ def _get_url(url, registry_base_url=None):
return '{}{}'.format(registry_base_url, url)
def _get_with_retries(path, registry_base_url=None):
get_fn = functools.partial(_get, path, registry_base_url)
return connection_exception_retry(get_fn, 5)
def _wrap_exceptions(fn):
@wraps(fn)
def wrapper(*args, **kwargs):
max_attempts = 5
attempt = 0
while True:
attempt += 1
try:
return fn(*args, **kwargs)
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout) as exc:
if attempt < max_attempts:
time.sleep(1)
continue
raise RegistryException(
'Unable to connect to registry hub'
) from exc
return wrapper
@_wrap_exceptions
def _get(path, registry_base_url=None):
url = _get_url(path, registry_base_url)
logger.debug('Making package registry request: GET {}'.format(url))
@@ -34,44 +50,22 @@ def _get(path, registry_base_url=None):
def index(registry_base_url=None):
return _get_with_retries('api/v1/index.json', registry_base_url)
return _get('api/v1/index.json', registry_base_url)
index_cached = memoized(index)
def packages(registry_base_url=None):
return _get_with_retries('api/v1/packages.json', registry_base_url)
return _get('api/v1/packages.json', registry_base_url)
def package(name, registry_base_url=None):
response = _get_with_retries('api/v1/{}.json'.format(name), registry_base_url)
# Either redirectnamespace or redirectname in the JSON response indicate a redirect
# redirectnamespace redirects based on package ownership
# redirectname redirects based on package name
# Both can be present at the same time, or neither. Fails gracefully to old name
if ('redirectnamespace' in response) or ('redirectname' in response):
if ('redirectnamespace' in response) and response['redirectnamespace'] is not None:
use_namespace = response['redirectnamespace']
else:
use_namespace = response['namespace']
if ('redirectname' in response) and response['redirectname'] is not None:
use_name = response['redirectname']
else:
use_name = response['name']
new_nwo = use_namespace + "/" + use_name
deprecations.warn('package-redirect', old_name=name, new_name=new_nwo)
return response
return _get('api/v1/{}.json'.format(name), registry_base_url)
def package_version(name, version, registry_base_url=None):
return _get_with_retries('api/v1/{}/{}.json'.format(name, version), registry_base_url)
return _get('api/v1/{}/{}.json'.format(name, version), registry_base_url)
def get_available_versions(name):

View File

@@ -1,5 +1,4 @@
import errno
import functools
import fnmatch
import json
import os
@@ -16,8 +15,9 @@ from typing import (
)
import dbt.exceptions
import dbt.utils
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.utils import _connection_exception_retry as connection_exception_retry
if sys.platform == 'win32':
from ctypes import WinDLL, c_bool
@@ -30,7 +30,7 @@ def find_matching(
root_path: str,
relative_paths_to_search: List[str],
file_pattern: str,
) -> List[Dict[str, Any]]:
) -> List[Dict[str, str]]:
"""
Given an absolute `root_path`, a list of relative paths to that
absolute root path (`relative_paths_to_search`), and a `file_pattern`
@@ -61,19 +61,11 @@ def find_matching(
relative_path = os.path.relpath(
absolute_path, absolute_path_to_search
)
modification_time = 0.0
try:
modification_time = os.path.getmtime(absolute_path)
except OSError:
logger.exception(
f"Error retrieving modification time for file {absolute_path}"
)
if reobj.match(local_file):
matching.append({
'searched_path': relative_path_to_search,
'absolute_path': absolute_path,
'relative_path': relative_path,
'modification_time': modification_time,
})
return matching
@@ -449,13 +441,6 @@ def run_cmd(
return out, err
def download_with_retries(
url: str, path: str, timeout: Optional[Union[float, tuple]] = None
) -> None:
download_fn = functools.partial(download, url, path, timeout)
connection_exception_retry(download_fn, 5)
def download(
url: str, path: str, timeout: Optional[Union[float, tuple]] = None
) -> None:

View File

@@ -1,6 +1,7 @@
import dbt.exceptions
from typing import Any, Dict, Optional
import yaml
import yaml.scanner
# the C version is faster, but it doesn't always exist
try:

View File

@@ -10,10 +10,10 @@ from dbt.adapters.factory import get_adapter
from dbt.clients import jinja
from dbt.clients.system import make_directory
from dbt.context.providers import generate_runtime_model
from dbt.contracts.graph.manifest import Manifest, UniqueID
from dbt.contracts.graph.manifest import Manifest
from dbt.contracts.graph.compiled import (
COMPILED_TYPES,
CompiledGenericTestNode,
CompiledSchemaTestNode,
GraphMemberNode,
InjectedCTE,
ManifestNode,
@@ -107,19 +107,6 @@ def _extend_prepended_ctes(prepended_ctes, new_prepended_ctes):
_add_prepended_cte(prepended_ctes, new_cte)
def _get_tests_for_node(manifest: Manifest, unique_id: UniqueID) -> List[UniqueID]:
""" Get a list of tests that depend on the node with the
provided unique id """
tests = []
if unique_id in manifest.child_map:
for child_unique_id in manifest.child_map[unique_id]:
if child_unique_id.startswith('test.'):
tests.append(child_unique_id)
return tests
class Linker:
def __init__(self, data=None):
if data is None:
@@ -155,7 +142,7 @@ class Linker:
include all nodes in their corresponding graph entries.
"""
out_graph = self.graph.copy()
for node_id in self.graph:
for node_id in self.graph.nodes():
data = manifest.expect(node_id).to_dict(omit_none=True)
out_graph.add_node(node_id, **data)
nx.write_gpickle(out_graph, outfile)
@@ -167,7 +154,7 @@ class Compiler:
def initialize(self):
make_directory(self.config.target_path)
make_directory(self.config.packages_install_path)
make_directory(self.config.modules_path)
# creates a ModelContext which is converted to
# a dict for jinja rendering of SQL
@@ -182,7 +169,7 @@ class Compiler:
node, self.config, manifest
)
context.update(extra_context)
if isinstance(node, CompiledGenericTestNode):
if isinstance(node, CompiledSchemaTestNode):
# for test nodes, add a special keyword args value to the context
jinja.add_rendered_test_kwargs(context, node)
@@ -425,82 +412,13 @@ class Compiler:
self.link_node(linker, node, manifest)
for exposure in manifest.exposures.values():
self.link_node(linker, exposure, manifest)
# linker.add_node(exposure.unique_id)
cycle = linker.find_cycles()
if cycle:
raise RuntimeError("Found a cycle: {}".format(cycle))
manifest.build_parent_and_child_maps()
self.resolve_graph(linker, manifest)
def resolve_graph(self, linker: Linker, manifest: Manifest) -> None:
""" This method adds additional edges to the DAG. For a given non-test
executable node, add an edge from an upstream test to the given node if
the set of nodes the test depends on is a proper/strict subset of the
upstream nodes for the given node. """
# Given a graph:
# model1 --> model2 --> model3
# | |
# | \/
# \/ test 2
# test1
#
# Produce the following graph:
# model1 --> model2 --> model3
# | | /\ /\
# | \/ | |
# \/ test2 ------- |
# test1 -------------------
for node_id in linker.graph:
# If node is executable (in manifest.nodes) and does _not_
# represent a test, continue.
if (
node_id in manifest.nodes and
manifest.nodes[node_id].resource_type != NodeType.Test
):
# Get *everything* upstream of the node
all_upstream_nodes = nx.traversal.bfs_tree(
linker.graph, node_id, reverse=True
)
# Get the set of upstream nodes not including the current node.
upstream_nodes = set([
n for n in all_upstream_nodes if n != node_id
])
# Get all tests that depend on any upstream nodes.
upstream_tests = []
for upstream_node in upstream_nodes:
upstream_tests += _get_tests_for_node(
manifest,
upstream_node
)
for upstream_test in upstream_tests:
# Get the set of all nodes that the test depends on
# including the upstream_node itself. This is necessary
# because tests can depend on multiple nodes (ex:
# relationship tests). Test nodes do not distinguish
# between what node the test is "testing" and what
# node(s) it depends on.
test_depends_on = set(
manifest.nodes[upstream_test].depends_on_nodes
)
# If the set of nodes that an upstream test depends on
# is a proper (or strict) subset of all upstream nodes of
# the current node, add an edge from the upstream test
# to the current node. Must be a proper/strict subset to
# avoid adding a circular dependency to the graph.
if (test_depends_on < upstream_nodes):
linker.graph.add_edge(
upstream_test,
node_id
)
def compile(self, manifest: Manifest, write=True) -> Graph:
self.initialize()
linker = Linker()

View File

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

View File

@@ -4,7 +4,6 @@ import os
from dbt.dataclass_schema import ValidationError
from dbt import flags
from dbt.clients.system import load_file_contents
from dbt.clients.yaml_helper import load_yaml_text
from dbt.contracts.connection import Credentials, HasCredentials
@@ -21,8 +20,10 @@ from dbt.utils import coerce_dict_str
from .renderer import ProfileRenderer
DEFAULT_THREADS = 1
DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser('~'), '.dbt')
PROFILES_DIR = os.path.expanduser(
os.getenv('DBT_PROFILES_DIR', DEFAULT_PROFILES_DIR)
)
INVALID_PROFILE_MESSAGE = """
dbt encountered an error while trying to read your profiles.yml file.
@@ -42,7 +43,7 @@ Here, [profile name] should be replaced with a profile name
defined in your profiles.yml file. You can find profiles.yml here:
{profiles_file}/profiles.yml
""".format(profiles_file=DEFAULT_PROFILES_DIR)
""".format(profiles_file=PROFILES_DIR)
def read_profile(profiles_dir: str) -> Dict[str, Any]:
@@ -72,10 +73,10 @@ def read_user_config(directory: str) -> UserConfig:
try:
profile = read_profile(directory)
if profile:
user_config = coerce_dict_str(profile.get('config', {}))
if user_config is not None:
UserConfig.validate(user_config)
return UserConfig.from_dict(user_config)
user_cfg = coerce_dict_str(profile.get('config', {}))
if user_cfg is not None:
UserConfig.validate(user_cfg)
return UserConfig.from_dict(user_cfg)
except (RuntimeException, ValidationError):
pass
return UserConfig()
@@ -83,32 +84,14 @@ def read_user_config(directory: str) -> UserConfig:
# The Profile class is included in RuntimeConfig, so any attribute
# additions must also be set where the RuntimeConfig class is created
# `init=False` is a workaround for https://bugs.python.org/issue45081
@dataclass(init=False)
@dataclass
class Profile(HasCredentials):
profile_name: str
target_name: str
user_config: UserConfig
config: UserConfig
threads: int
credentials: Credentials
def __init__(
self,
profile_name: str,
target_name: str,
user_config: UserConfig,
threads: int,
credentials: Credentials
):
"""Explicitly defining `__init__` to work around bug in Python 3.9.7
https://bugs.python.org/issue45081
"""
self.profile_name = profile_name
self.target_name = target_name
self.user_config = user_config
self.threads = threads
self.credentials = credentials
def to_profile_info(
self, serialize_credentials: bool = False
) -> Dict[str, Any]:
@@ -123,12 +106,12 @@ class Profile(HasCredentials):
result = {
'profile_name': self.profile_name,
'target_name': self.target_name,
'user_config': self.user_config,
'config': self.config,
'threads': self.threads,
'credentials': self.credentials,
}
if serialize_credentials:
result['user_config'] = self.user_config.to_dict(omit_none=True)
result['config'] = self.config.to_dict(omit_none=True)
result['credentials'] = self.credentials.to_dict(omit_none=True)
return result
@@ -142,7 +125,7 @@ class Profile(HasCredentials):
'name': self.target_name,
'target_name': self.target_name,
'profile_name': self.profile_name,
'config': self.user_config.to_dict(omit_none=True),
'config': self.config.to_dict(omit_none=True),
})
return target
@@ -237,7 +220,7 @@ class Profile(HasCredentials):
threads: int,
profile_name: str,
target_name: str,
user_config: Optional[Dict[str, Any]] = None
user_cfg: Optional[Dict[str, Any]] = None
) -> 'Profile':
"""Create a profile from an existing set of Credentials and the
remaining information.
@@ -246,20 +229,20 @@ class Profile(HasCredentials):
:param threads: The number of threads to use for connections.
:param profile_name: The profile name used for this profile.
:param target_name: The target name used for this profile.
:param user_config: The user-level config block from the
:param user_cfg: The user-level config block from the
raw profiles, if specified.
:raises DbtProfileError: If the profile is invalid.
:returns: The new Profile object.
"""
if user_config is None:
user_config = {}
UserConfig.validate(user_config)
user_config_obj: UserConfig = UserConfig.from_dict(user_config)
if user_cfg is None:
user_cfg = {}
UserConfig.validate(user_cfg)
config = UserConfig.from_dict(user_cfg)
profile = cls(
profile_name=profile_name,
target_name=target_name,
user_config=user_config_obj,
config=config,
threads=threads,
credentials=credentials
)
@@ -312,7 +295,7 @@ class Profile(HasCredentials):
raw_profile: Dict[str, Any],
profile_name: str,
renderer: ProfileRenderer,
user_config: Optional[Dict[str, Any]] = None,
user_cfg: Optional[Dict[str, Any]] = None,
target_override: Optional[str] = None,
threads_override: Optional[int] = None,
) -> 'Profile':
@@ -324,7 +307,7 @@ class Profile(HasCredentials):
disk as yaml and its values rendered with jinja.
:param profile_name: The profile name used.
:param renderer: The config renderer.
:param user_config: The global config for the user, if it
:param user_cfg: The global config for the user, if it
was present.
:param target_override: The target to use, if provided on
the command line.
@@ -334,9 +317,9 @@ class Profile(HasCredentials):
target could not be found
:returns: The new Profile object.
"""
# user_config is not rendered.
if user_config is None:
user_config = raw_profile.get('config')
# user_cfg is not rendered.
if user_cfg is None:
user_cfg = raw_profile.get('config')
# TODO: should it be, and the values coerced to bool?
target_name, profile_data = cls.render_profile(
raw_profile, profile_name, target_override, renderer
@@ -357,7 +340,7 @@ class Profile(HasCredentials):
profile_name=profile_name,
target_name=target_name,
threads=threads,
user_config=user_config
user_cfg=user_cfg
)
@classmethod
@@ -400,13 +383,13 @@ class Profile(HasCredentials):
error_string=msg
)
)
user_config = raw_profiles.get('config')
user_cfg = raw_profiles.get('config')
return cls.from_raw_profile_info(
raw_profile=raw_profile,
profile_name=profile_name,
renderer=renderer,
user_config=user_config,
user_cfg=user_cfg,
target_override=target_override,
threads_override=threads_override,
)
@@ -434,7 +417,7 @@ class Profile(HasCredentials):
"""
threads_override = getattr(args, 'threads', None)
target_override = getattr(args, 'target', None)
raw_profiles = read_profile(flags.PROFILES_DIR)
raw_profiles = read_profile(args.profiles_dir)
profile_name = cls.pick_profile_name(getattr(args, 'profile', None),
project_profile_name)
return cls.from_raw_profiles(

View File

@@ -9,7 +9,6 @@ from typing_extensions import Protocol, runtime_checkable
import hashlib
import os
from dbt import deprecations
from dbt.clients.system import resolve_path_from_base
from dbt.clients.system import path_exists
from dbt.clients.system import load_file_contents
@@ -124,13 +123,13 @@ def _parse_versions(versions: Union[List[str], str]) -> List[VersionSpecifier]:
def _all_source_paths(
model_paths: List[str],
seed_paths: List[str],
source_paths: List[str],
data_paths: List[str],
snapshot_paths: List[str],
analysis_paths: List[str],
macro_paths: List[str],
) -> List[str]:
return list(chain(model_paths, seed_paths, snapshot_paths, analysis_paths,
return list(chain(source_paths, data_paths, snapshot_paths, analysis_paths,
macro_paths))
@@ -293,21 +292,6 @@ class PartialProject(RenderComponents):
exc.path = os.path.join(self.project_root, 'dbt_project.yml')
raise
def check_config_path(self, project_dict, deprecated_path, exp_path):
if deprecated_path in project_dict:
if exp_path in project_dict:
msg = (
'{deprecated_path} and {exp_path} cannot both be defined. The '
'`{deprecated_path}` config has been deprecated in favor of `{exp_path}`. '
'Please update your `dbt_project.yml` configuration to reflect this '
'change.'
)
raise DbtProjectError(msg.format(deprecated_path=deprecated_path,
exp_path=exp_path))
deprecations.warn('project_config_path',
deprecated_path=deprecated_path,
exp_path=exp_path)
def create_project(self, rendered: RenderComponents) -> 'Project':
unrendered = RenderComponents(
project_dict=self.project_dict,
@@ -319,9 +303,6 @@ class PartialProject(RenderComponents):
verify_version=self.verify_version,
)
self.check_config_path(rendered.project_dict, 'source-paths', 'model-paths')
self.check_config_path(rendered.project_dict, 'data-paths', 'seed-paths')
try:
ProjectContract.validate(rendered.project_dict)
cfg = ProjectContract.from_dict(
@@ -343,24 +324,15 @@ class PartialProject(RenderComponents):
# to have been a cli argument.
profile_name = cfg.profile
# these are all the defaults
# `source_paths` is deprecated but still allowed. Copy it into
# `model_paths` to simlify logic throughout the rest of the system.
model_paths: List[str] = value_or(cfg.model_paths
if 'model-paths' in rendered.project_dict
else cfg.source_paths, ['models'])
source_paths: List[str] = value_or(cfg.source_paths, ['models'])
macro_paths: List[str] = value_or(cfg.macro_paths, ['macros'])
# `data_paths` is deprecated but still allowed. Copy it into
# `seed_paths` to simlify logic throughout the rest of the system.
seed_paths: List[str] = value_or(cfg.seed_paths
if 'seed-paths' in rendered.project_dict
else cfg.data_paths, ['seeds'])
test_paths: List[str] = value_or(cfg.test_paths, ['tests'])
analysis_paths: List[str] = value_or(cfg.analysis_paths, ['analyses'])
data_paths: List[str] = value_or(cfg.data_paths, ['data'])
test_paths: List[str] = value_or(cfg.test_paths, ['test'])
analysis_paths: List[str] = value_or(cfg.analysis_paths, [])
snapshot_paths: List[str] = value_or(cfg.snapshot_paths, ['snapshots'])
all_source_paths: List[str] = _all_source_paths(
model_paths, seed_paths, snapshot_paths, analysis_paths,
source_paths, data_paths, snapshot_paths, analysis_paths,
macro_paths
)
@@ -369,7 +341,7 @@ class PartialProject(RenderComponents):
target_path: str = value_or(cfg.target_path, 'target')
clean_targets: List[str] = value_or(cfg.clean_targets, [target_path])
log_path: str = value_or(cfg.log_path, 'logs')
packages_install_path: str = value_or(cfg.packages_install_path, 'dbt_packages')
modules_path: str = value_or(cfg.modules_path, 'dbt_modules')
# in the default case we'll populate this once we know the adapter type
# It would be nice to just pass along a Quoting here, but that would
# break many things
@@ -410,14 +382,15 @@ class PartialProject(RenderComponents):
# of dicts.
manifest_selectors = SelectorDict.parse_from_selectors_list(
rendered.selectors_dict['selectors'])
project = Project(
project_name=name,
version=version,
project_root=project_root,
profile_name=profile_name,
model_paths=model_paths,
source_paths=source_paths,
macro_paths=macro_paths,
seed_paths=seed_paths,
data_paths=data_paths,
test_paths=test_paths,
analysis_paths=analysis_paths,
docs_paths=docs_paths,
@@ -426,7 +399,7 @@ class PartialProject(RenderComponents):
snapshot_paths=snapshot_paths,
clean_targets=clean_targets,
log_path=log_path,
packages_install_path=packages_install_path,
modules_path=modules_path,
quoting=quoting,
models=models,
on_run_start=on_run_start,
@@ -527,9 +500,9 @@ class Project:
version: Union[SemverString, float]
project_root: str
profile_name: Optional[str]
model_paths: List[str]
source_paths: List[str]
macro_paths: List[str]
seed_paths: List[str]
data_paths: List[str]
test_paths: List[str]
analysis_paths: List[str]
docs_paths: List[str]
@@ -538,7 +511,7 @@ class Project:
snapshot_paths: List[str]
clean_targets: List[str]
log_path: str
packages_install_path: str
modules_path: str
quoting: Dict[str, Any]
models: Dict[str, Any]
on_run_start: List[str]
@@ -560,7 +533,7 @@ class Project:
@property
def all_source_paths(self) -> List[str]:
return _all_source_paths(
self.model_paths, self.seed_paths, self.snapshot_paths,
self.source_paths, self.data_paths, self.snapshot_paths,
self.analysis_paths, self.macro_paths
)
@@ -588,9 +561,9 @@ class Project:
'version': self.version,
'project-root': self.project_root,
'profile': self.profile_name,
'model-paths': self.model_paths,
'source-paths': self.source_paths,
'macro-paths': self.macro_paths,
'seed-paths': self.seed_paths,
'data-paths': self.data_paths,
'test-paths': self.test_paths,
'analysis-paths': self.analysis_paths,
'docs-paths': self.docs_paths,
@@ -672,24 +645,13 @@ class Project:
def hashed_name(self):
return hashlib.md5(self.project_name.encode('utf-8')).hexdigest()
def get_selector(self, name: str) -> Union[SelectionSpec, bool]:
def get_selector(self, name: str) -> SelectionSpec:
if name not in self.selectors:
raise RuntimeException(
f'Could not find selector named {name}, expected one of '
f'{list(self.selectors)}'
)
return self.selectors[name]["definition"]
def get_default_selector_name(self) -> Union[str, None]:
"""This function fetch the default selector to use on `dbt run` (if any)
:return: either a selector if default is set or None
:rtype: Union[SelectionSpec, None]
"""
for selector_name, selector in self.selectors.items():
if selector["default"] is True:
return selector_name
return None
return self.selectors[name]
def get_macro_search_order(self, macro_namespace: str):
for dispatch_entry in self.dispatch:

View File

@@ -12,7 +12,6 @@ from .profile import Profile
from .project import Project
from .renderer import DbtProjectYamlRenderer, ProfileRenderer
from .utils import parse_cli_vars
from dbt import flags
from dbt import tracking
from dbt.adapters.factory import get_relation_class_by_name, get_include_paths
from dbt.helper_types import FQNPath, PathSet
@@ -87,9 +86,9 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
project_name=project.project_name,
version=project.version,
project_root=project.project_root,
model_paths=project.model_paths,
source_paths=project.source_paths,
macro_paths=project.macro_paths,
seed_paths=project.seed_paths,
data_paths=project.data_paths,
test_paths=project.test_paths,
analysis_paths=project.analysis_paths,
docs_paths=project.docs_paths,
@@ -98,7 +97,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
snapshot_paths=project.snapshot_paths,
clean_targets=project.clean_targets,
log_path=project.log_path,
packages_install_path=project.packages_install_path,
modules_path=project.modules_path,
quoting=quoting,
models=project.models,
on_run_start=project.on_run_start,
@@ -118,7 +117,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
unrendered=project.unrendered,
profile_name=profile.profile_name,
target_name=profile.target_name,
user_config=profile.user_config,
config=profile.config,
threads=profile.threads,
credentials=profile.credentials,
args=args,
@@ -145,7 +144,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
project = Project.from_project_root(
project_root,
renderer,
verify_version=bool(flags.VERSION_CHECK),
verify_version=getattr(self.args, 'version_check', False),
)
cfg = self.from_parts(
@@ -198,7 +197,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
) -> Tuple[Project, Profile]:
# profile_name from the project
project_root = args.project_dir if args.project_dir else os.getcwd()
version_check = bool(flags.VERSION_CHECK)
version_check = getattr(args, 'version_check', False)
partial = Project.partial_load(
project_root,
verify_version=version_check
@@ -338,7 +337,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
f'dbt found {count_packages_specified} package(s) '
f'specified in packages.yml, but only '
f'{count_packages_installed} package(s) installed '
f'in {self.packages_install_path}. Run "dbt deps" to '
f'in {self.modules_path}. Run "dbt deps" to '
f'install package dependencies.'
)
project_paths = itertools.chain(
@@ -376,7 +375,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
yield project.project_name, project
def _get_project_directories(self) -> Iterator[Path]:
root = Path(self.project_root) / self.packages_install_path
root = Path(self.project_root) / self.modules_path
if root.exists():
for path in root.iterdir():
@@ -392,10 +391,6 @@ class UnsetCredentials(Credentials):
def type(self):
return None
@property
def unique_field(self):
return None
def connection_info(self, *args, **kwargs):
return {}
@@ -417,7 +412,7 @@ class UnsetConfig(UserConfig):
class UnsetProfile(Profile):
def __init__(self):
self.credentials = UnsetCredentials()
self.user_config = UnsetConfig()
self.config = UnsetConfig()
self.profile_name = ''
self.target_name = ''
self.threads = -1
@@ -483,9 +478,9 @@ class UnsetProfileConfig(RuntimeConfig):
project_name=project.project_name,
version=project.version,
project_root=project.project_root,
model_paths=project.model_paths,
source_paths=project.source_paths,
macro_paths=project.macro_paths,
seed_paths=project.seed_paths,
data_paths=project.data_paths,
test_paths=project.test_paths,
analysis_paths=project.analysis_paths,
docs_paths=project.docs_paths,
@@ -494,7 +489,7 @@ class UnsetProfileConfig(RuntimeConfig):
snapshot_paths=project.snapshot_paths,
clean_targets=project.clean_targets,
log_path=project.log_path,
packages_install_path=project.packages_install_path,
modules_path=project.modules_path,
quoting=project.quoting, # we never use this anyway.
models=project.models,
on_run_start=project.on_run_start,
@@ -514,7 +509,7 @@ class UnsetProfileConfig(RuntimeConfig):
unrendered=project.unrendered,
profile_name='',
target_name='',
user_config=UnsetConfig(),
config=UnsetConfig(),
threads=getattr(args, 'threads', 1),
credentials=UnsetCredentials(),
args=args,

View File

@@ -1,5 +1,5 @@
from pathlib import Path
from typing import Dict, Any, Union
from typing import Dict, Any
from dbt.clients.yaml_helper import ( # noqa: F401
yaml, Loader, Dumper, load_yaml_text
)
@@ -29,14 +29,13 @@ Validator Error:
"""
class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
class SelectorConfig(Dict[str, SelectionSpec]):
@classmethod
def selectors_from_dict(cls, data: Dict[str, Any]) -> 'SelectorConfig':
try:
SelectorFile.validate(data)
selector_file = SelectorFile.from_dict(data)
validate_selector_default(selector_file)
selectors = parse_from_selectors_definition(selector_file)
except ValidationError as exc:
yaml_sel_cfg = yaml.dump(exc.instance)
@@ -119,24 +118,6 @@ def selector_config_from_data(
return selectors
def validate_selector_default(selector_file: SelectorFile) -> None:
"""Check if a selector.yml file has more than 1 default key set to true"""
default_set: bool = False
default_selector_name: Union[str, None] = None
for selector in selector_file.selectors:
if selector.default is True and default_set is False:
default_set = True
default_selector_name = selector.name
continue
if selector.default is True and default_set is True:
raise DbtSelectorsError(
"Error when parsing the selector file. "
"Found multiple selectors with `default: true`:"
f"{default_selector_name} and {selector.name}"
)
# These are utilities to clean up the dictionary created from
# selectors.yml by turning the cli-string format entries into
# normalized dictionary entries. It parallels the flow in

View File

@@ -12,8 +12,7 @@ from dbt.clients.yaml_helper import ( # noqa: F401
)
from dbt.contracts.graph.compiled import CompiledResource
from dbt.exceptions import raise_compiler_error, MacroReturn
from dbt.events.functions import fire_event
from dbt.events.types import MacroEventInfo, MacroEventDebug
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.version import __version__ as dbt_version
# These modules are added to the context. Consider alternative
@@ -444,9 +443,9 @@ class BaseContext(metaclass=ContextMeta):
{% endmacro %}"
"""
if info:
fire_event(MacroEventInfo(msg))
logger.info(msg)
else:
fire_event(MacroEventDebug(msg))
logger.debug(msg)
return ''
@contextproperty
@@ -525,8 +524,14 @@ class BaseContext(metaclass=ContextMeta):
-- no-op
{% endif %}
This supports all flags defined in flags submodule (core/dbt/flags.py)
TODO: Replace with object that provides read-only access to flag values
The list of valid flags are:
- `flags.STRICT_MODE`: True if `--strict` (or `-S`) was provided on the
command line
- `flags.FULL_REFRESH`: True if `--full-refresh` was provided on the
command line
- `flags.NON_DESTRUCTIVE`: True if `--non-destructive` was provided on
the command line
"""
return flags

View File

@@ -125,7 +125,6 @@ class BaseContextConfigGenerator(Generic[T]):
resource_type: NodeType,
project_name: str,
base: bool,
patch_config_dict: Dict[str, Any] = None
) -> BaseConfig:
own_config = self.get_node_project(project_name)
@@ -135,12 +134,6 @@ class BaseContextConfigGenerator(Generic[T]):
for fqn_config in project_configs:
result = self._update_from_config(result, fqn_config)
# When schema files patch config, it has lower precedence than
# config in the models (config_call_dict), so we add the patch_config_dict
# before the config_call_dict
if patch_config_dict:
result = self._update_from_config(result, patch_config_dict)
# config_calls are created in the 'experimental' model parser and
# the ParseConfigObject (via add_config_call)
result = self._update_from_config(result, config_call_dict)
@@ -160,7 +153,6 @@ class BaseContextConfigGenerator(Generic[T]):
resource_type: NodeType,
project_name: str,
base: bool,
patch_config_dict: Dict[str, Any],
) -> Dict[str, Any]:
...
@@ -200,7 +192,6 @@ class ContextConfigGenerator(BaseContextConfigGenerator[C]):
resource_type: NodeType,
project_name: str,
base: bool,
patch_config_dict: dict = None
) -> Dict[str, Any]:
config = self.calculate_node_config(
config_call_dict=config_call_dict,
@@ -208,7 +199,6 @@ class ContextConfigGenerator(BaseContextConfigGenerator[C]):
resource_type=resource_type,
project_name=project_name,
base=base,
patch_config_dict=patch_config_dict
)
finalized = config.finalize_and_validate()
return finalized.to_dict(omit_none=True)
@@ -225,7 +215,6 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
resource_type: NodeType,
project_name: str,
base: bool,
patch_config_dict: dict = None
) -> Dict[str, Any]:
return self.calculate_node_config(
config_call_dict=config_call_dict,
@@ -233,7 +222,6 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
resource_type=resource_type,
project_name=project_name,
base=base,
patch_config_dict=patch_config_dict
)
def initial_result(
@@ -296,7 +284,6 @@ class ContextConfig:
base: bool = False,
*,
rendered: bool = True,
patch_config_dict: dict = None
) -> Dict[str, Any]:
if rendered:
src = ContextConfigGenerator(self._active_project)
@@ -309,5 +296,4 @@ class ContextConfig:
resource_type=self._resource_type,
project_name=self._project_name,
base=base,
patch_config_dict=patch_config_dict
)

View File

@@ -6,6 +6,7 @@ from typing import (
)
from typing_extensions import Protocol
from dbt import deprecations
from dbt.adapters.base.column import Column
from dbt.adapters.factory import (
get_adapter, get_adapter_package_names, get_adapter_type_names
@@ -39,7 +40,6 @@ from dbt.exceptions import (
InternalException,
ValidationException,
RuntimeException,
macro_invalid_dispatch_arg,
missing_config,
raise_compiler_error,
ref_invalid_args,
@@ -49,6 +49,7 @@ from dbt.exceptions import (
wrapped_exports,
)
from dbt.config import IsFQNResource
from dbt.logger import GLOBAL_LOGGER as logger # noqa
from dbt.node_types import NodeType
from dbt.utils import (
@@ -119,37 +120,39 @@ class BaseDatabaseWrapper:
self,
macro_name: str,
macro_namespace: Optional[str] = None,
packages: Optional[List[str]] = None, # eventually remove since it's fully deprecated
packages: Optional[List[str]] = None,
) -> MacroGenerator:
search_packages: List[Optional[str]]
if '.' in macro_name:
suggest_macro_namespace, suggest_macro_name = macro_name.split('.', 1)
suggest_package, suggest_macro_name = macro_name.split('.', 1)
msg = (
f'In adapter.dispatch, got a macro name of "{macro_name}", '
f'but "." is not a valid macro name component. Did you mean '
f'`adapter.dispatch("{suggest_macro_name}", '
f'macro_namespace="{suggest_macro_namespace}")`?'
f'packages=["{suggest_package}"])`?'
)
raise CompilationException(msg)
if packages is not None:
raise macro_invalid_dispatch_arg(macro_name)
deprecations.warn('dispatch-packages', macro_name=macro_name)
namespace = macro_namespace
namespace = packages if packages else macro_namespace
if namespace is None:
search_packages = [None]
elif isinstance(namespace, str):
search_packages = self._adapter.config.get_macro_search_order(namespace)
if not search_packages and namespace in self._adapter.config.dependencies:
search_packages = [self.config.project_name, namespace]
search_packages = [namespace]
if not search_packages:
raise CompilationException(
f'In adapter.dispatch, got a string packages argument '
f'("{packages}"), but packages should be None or a list.'
)
else:
# Not a string and not None so must be a list
raise CompilationException(
f'In adapter.dispatch, got a list macro_namespace argument '
f'("{macro_namespace}"), but macro_namespace should be None or a string.'
)
search_packages = namespace
attempts = []
@@ -161,10 +164,10 @@ class BaseDatabaseWrapper:
macro = self._namespace.get_from_package(
package_name, search_name
)
except CompilationException:
# Only raise CompilationException if macro is not found in
# any package
macro = None
except CompilationException as exc:
raise CompilationException(
f'In dispatch: {exc.msg}',
) from exc
if package_name is None:
attempts.append(search_name)
@@ -1148,17 +1151,65 @@ class ProviderContext(ManifestContext):
@contextmember
def adapter_macro(self, name: str, *args, **kwargs):
"""This was deprecated in v0.18 in favor of adapter.dispatch
"""Find the most appropriate macro for the name, considering the
adapter type currently in use, and call that with the given arguments.
If the name has a `.` in it, the first section before the `.` is
interpreted as a package name, and the remainder as a macro name.
If no adapter is found, raise a compiler exception. If an invalid
package name is specified, raise a compiler exception.
Some examples:
{# dbt will call this macro by name, providing any arguments #}
{% macro create_table_as(temporary, relation, sql) -%}
{# dbt will dispatch the macro call to the relevant macro #}
{{ adapter_macro('create_table_as', temporary, relation, sql) }}
{%- endmacro %}
{#
If no macro matches the specified adapter, "default" will be
used
#}
{% macro default__create_table_as(temporary, relation, sql) -%}
...
{%- endmacro %}
{# Example which defines special logic for Redshift #}
{% macro redshift__create_table_as(temporary, relation, sql) -%}
...
{%- endmacro %}
{# Example which defines special logic for BigQuery #}
{% macro bigquery__create_table_as(temporary, relation, sql) -%}
...
{%- endmacro %}
"""
msg = (
'The "adapter_macro" macro has been deprecated. Instead, use '
'the `adapter.dispatch` method to find a macro and call the '
'result. For more information, see: '
'https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch)'
' adapter_macro was called for: {macro_name}'
.format(macro_name=name)
)
raise CompilationException(msg)
deprecations.warn('adapter-macro', macro_name=name)
original_name = name
package_name = None
if '.' in name:
package_name, name = name.split('.', 1)
try:
macro = self.db_wrapper.dispatch(
macro_name=name, macro_namespace=package_name
)
except CompilationException as exc:
raise CompilationException(
f'In adapter_macro: {exc.msg}\n'
f" Original name: '{original_name}'",
node=self.model
) from exc
return macro(*args, **kwargs)
class MacroContext(ProviderContext):
@@ -1192,7 +1243,7 @@ class ModelContext(ProviderContext):
@contextproperty
def pre_hooks(self) -> List[Dict[str, Any]]:
if self.model.resource_type in [NodeType.Source, NodeType.Test]:
if isinstance(self.model, ParsedSourceDefinition):
return []
return [
h.to_dict(omit_none=True) for h in self.model.config.pre_hook
@@ -1200,7 +1251,7 @@ class ModelContext(ProviderContext):
@contextproperty
def post_hooks(self) -> List[Dict[str, Any]]:
if self.model.resource_type in [NodeType.Source, NodeType.Test]:
if isinstance(self.model, ParsedSourceDefinition):
return []
return [
h.to_dict(omit_none=True) for h in self.model.config.post_hook

View File

@@ -1,6 +1,5 @@
import abc
import itertools
import hashlib
from dataclasses import dataclass, field
from typing import (
Any, ClassVar, Dict, Tuple, Iterable, Optional, List, Callable,
@@ -128,19 +127,6 @@ class Credentials(
'type not implemented for base credentials class'
)
@property
def unique_field(self) -> str:
"""Hashed and included in anonymous telemetry to track adapter adoption.
Return the field from Credentials that can uniquely identify
one team/organization using this adapter
"""
raise NotImplementedError(
'unique_field not implemented for base credentials class'
)
def hashed_unique_field(self) -> str:
return hashlib.md5(self.unique_field.encode('utf-8')).hexdigest()
def connection_info(
self, *, with_aliases: bool = False
) -> Iterable[Tuple[str, Any]]:
@@ -190,11 +176,14 @@ class UserConfigContract(Protocol):
partial_parse: Optional[bool] = None
printer_width: Optional[int] = None
def set_values(self, cookie_dir: str) -> None:
...
class HasCredentials(Protocol):
credentials: Credentials
profile_name: str
user_config: UserConfigContract
config: UserConfigContract
target_name: str
threads: int

View File

@@ -18,8 +18,7 @@ class ParseFileType(StrEnum):
Model = 'model'
Snapshot = 'snapshot'
Analysis = 'analysis'
SingularTest = 'singular_test'
GenericTest = 'generic_test'
Test = 'test'
Seed = 'seed'
Documentation = 'docs'
Schema = 'schema'
@@ -31,8 +30,7 @@ parse_file_type_to_parser = {
ParseFileType.Model: 'ModelParser',
ParseFileType.Snapshot: 'SnapshotParser',
ParseFileType.Analysis: 'AnalysisParser',
ParseFileType.SingularTest: 'SingularTestParser',
ParseFileType.GenericTest: 'GenericTestParser',
ParseFileType.Test: 'DataTestParser',
ParseFileType.Seed: 'SeedParser',
ParseFileType.Documentation: 'DocumentationParser',
ParseFileType.Schema: 'SchemaParser',
@@ -44,7 +42,6 @@ parse_file_type_to_parser = {
class FilePath(dbtClassMixin):
searched_path: str
relative_path: str
modification_time: float
project_root: str
@property
@@ -135,10 +132,6 @@ class RemoteFile(dbtClassMixin):
def original_file_path(self):
return 'from remote system'
@property
def modification_time(self):
return 'from remote system'
@dataclass
class BaseSourceFile(dbtClassMixin, SerializableType):
@@ -157,6 +150,8 @@ class BaseSourceFile(dbtClassMixin, SerializableType):
def file_id(self):
if isinstance(self.path, RemoteFile):
return None
if self.checksum.name == 'none':
return None
return f'{self.project_name}://{self.path.original_file_path}'
def _serialize(self):

View File

@@ -2,13 +2,13 @@ from dbt.contracts.graph.parsed import (
HasTestMetadata,
ParsedNode,
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedExposure,
ParsedResource,
ParsedRPCNode,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
ParsedSourceDefinition,
@@ -107,21 +107,17 @@ class CompiledSnapshotNode(CompiledNode):
@dataclass
class CompiledSingularTestNode(CompiledNode):
class CompiledDataTestNode(CompiledNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
# Was not able to make mypy happy and keep the code working. We need to
# refactor the various configs.
config: TestConfig = field(default_factory=TestConfig) # type:ignore
config: TestConfig = field(default_factory=TestConfig)
@dataclass
class CompiledGenericTestNode(CompiledNode, HasTestMetadata):
# keep this in sync with ParsedGenericTestNode!
class CompiledSchemaTestNode(CompiledNode, HasTestMetadata):
# keep this in sync with ParsedSchemaTestNode!
resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
column_name: Optional[str] = None
# Was not able to make mypy happy and keep the code working. We need to
# refactor the various configs.
config: TestConfig = field(default_factory=TestConfig) # type:ignore
config: TestConfig = field(default_factory=TestConfig)
def same_contents(self, other) -> bool:
if other is None:
@@ -134,7 +130,7 @@ class CompiledGenericTestNode(CompiledNode, HasTestMetadata):
)
CompiledTestNode = Union[CompiledSingularTestNode, CompiledGenericTestNode]
CompiledTestNode = Union[CompiledDataTestNode, CompiledSchemaTestNode]
PARSED_TYPES: Dict[Type[CompiledNode], Type[ParsedResource]] = {
@@ -144,8 +140,8 @@ PARSED_TYPES: Dict[Type[CompiledNode], Type[ParsedResource]] = {
CompiledRPCNode: ParsedRPCNode,
CompiledSeedNode: ParsedSeedNode,
CompiledSnapshotNode: ParsedSnapshotNode,
CompiledSingularTestNode: ParsedSingularTestNode,
CompiledGenericTestNode: ParsedGenericTestNode,
CompiledDataTestNode: ParsedDataTestNode,
CompiledSchemaTestNode: ParsedSchemaTestNode,
}
@@ -156,8 +152,8 @@ COMPILED_TYPES: Dict[Type[ParsedResource], Type[CompiledNode]] = {
ParsedRPCNode: CompiledRPCNode,
ParsedSeedNode: CompiledSeedNode,
ParsedSnapshotNode: CompiledSnapshotNode,
ParsedSingularTestNode: CompiledSingularTestNode,
ParsedGenericTestNode: CompiledGenericTestNode,
ParsedDataTestNode: CompiledDataTestNode,
ParsedSchemaTestNode: CompiledSchemaTestNode,
}
@@ -185,22 +181,22 @@ def parsed_instance_for(compiled: CompiledNode) -> ParsedResource:
NonSourceCompiledNode = Union[
CompiledAnalysisNode,
CompiledSingularTestNode,
CompiledDataTestNode,
CompiledModelNode,
CompiledHookNode,
CompiledRPCNode,
CompiledGenericTestNode,
CompiledSchemaTestNode,
CompiledSeedNode,
CompiledSnapshotNode,
]
NonSourceParsedNode = Union[
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedRPCNode,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
]

View File

@@ -5,7 +5,7 @@ from mashumaro import DataClassMessagePackMixin
from multiprocessing.synchronize import Lock
from typing import (
Dict, List, Optional, Union, Mapping, MutableMapping, Any, Set, Tuple,
TypeVar, Callable, Generic, cast, AbstractSet, ClassVar
TypeVar, Callable, Iterable, Generic, cast, AbstractSet, ClassVar
)
from typing_extensions import Protocol
from uuid import UUID
@@ -14,7 +14,7 @@ from dbt.contracts.graph.compiled import (
CompileResultNode, ManifestNode, NonSourceCompiledNode, GraphMemberNode
)
from dbt.contracts.graph.parsed import (
ParsedMacro, ParsedDocumentation,
ParsedMacro, ParsedDocumentation, ParsedNodePatch, ParsedMacroPatch,
ParsedSourceDefinition, ParsedExposure, HasUniqueID,
UnpatchedSourceDefinition, ManifestNodes
)
@@ -26,7 +26,9 @@ from dbt.contracts.util import (
from dbt.dataclass_schema import dbtClassMixin
from dbt.exceptions import (
CompilationException,
raise_duplicate_resource_name, raise_compiler_error,
raise_duplicate_resource_name, raise_compiler_error, warn_or_error,
raise_duplicate_patch_name,
raise_duplicate_macro_patch_name, raise_duplicate_source_patch_name,
)
from dbt.helper_types import PathSet
from dbt.logger import GLOBAL_LOGGER as logger
@@ -95,23 +97,24 @@ class DocLookup(dbtClassMixin):
class SourceLookup(dbtClassMixin):
def __init__(self, manifest: 'Manifest'):
self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
self.storage: Dict[Tuple[str, str], Dict[PackageName, UniqueID]] = {}
self.populate(manifest)
def get_unique_id(self, search_name, package: Optional[PackageName]):
return find_unique_id_for_package(self.storage, search_name, package)
def get_unique_id(self, key, package: Optional[PackageName]):
return find_unique_id_for_package(self.storage, key, package)
def find(self, search_name, package: Optional[PackageName], manifest: 'Manifest'):
unique_id = self.get_unique_id(search_name, package)
def find(self, key, package: Optional[PackageName], manifest: 'Manifest'):
unique_id = self.get_unique_id(key, package)
if unique_id is not None:
return self.perform_lookup(unique_id, manifest)
return None
def add_source(self, source: ParsedSourceDefinition):
if source.search_name not in self.storage:
self.storage[source.search_name] = {}
key = (source.source_name, source.name)
if key not in self.storage:
self.storage[key] = {}
self.storage[source.search_name][source.package_name] = source.unique_id
self.storage[key][source.package_name] = source.unique_id
def populate(self, manifest):
for source in manifest.sources.values():
@@ -168,45 +171,8 @@ class RefableLookup(dbtClassMixin):
return manifest.nodes[unique_id]
# This handles both models/seeds/snapshots and sources
class DisabledLookup(dbtClassMixin):
def __init__(self, manifest: 'Manifest'):
self.storage: Dict[str, Dict[PackageName, List[Any]]] = {}
self.populate(manifest)
def populate(self, manifest):
for node in list(chain.from_iterable(manifest.disabled.values())):
self.add_node(node)
def add_node(self, node):
if node.search_name not in self.storage:
self.storage[node.search_name] = {}
if node.package_name not in self.storage[node.search_name]:
self.storage[node.search_name][node.package_name] = []
self.storage[node.search_name][node.package_name].append(node)
# This should return a list of disabled nodes. It's different from
# the other Lookup functions in that it returns full nodes, not just unique_ids
def find(self, search_name, package: Optional[PackageName]):
if search_name not in self.storage:
return None
pkg_dct: Mapping[PackageName, List[Any]] = self.storage[search_name]
if package is None:
if not pkg_dct:
return None
else:
return next(iter(pkg_dct.values()))
elif package in pkg_dct:
return pkg_dct[package]
else:
return None
class AnalysisLookup(RefableLookup):
_lookup_types: ClassVar[set] = set([NodeType.Analysis])
_lookup_types: ClassVar[set] = set(NodeType.Analysis)
def _search_packages(
@@ -259,7 +225,9 @@ class ManifestMetadata(BaseArtifactMetadata):
self.user_id = tracking.active_user.id
if self.send_anonymous_usage_stats is None:
self.send_anonymous_usage_stats = flags.SEND_ANONYMOUS_USAGE_STATS
self.send_anonymous_usage_stats = (
not tracking.active_user.do_not_track
)
@classmethod
def default(cls):
@@ -291,7 +259,7 @@ def build_node_edges(nodes: List[ManifestNode]):
return _sort_values(forward_edges), _sort_values(backward_edges)
# Build a map of children of macros and generic tests
# Build a map of children of macros
def build_macro_edges(nodes: List[Any]):
forward_edges: Dict[str, List[str]] = {
n.unique_id: [] for n in nodes if n.unique_id.startswith('macro') or n.depends_on.macros
@@ -414,6 +382,38 @@ class Searchable(Protocol):
raise NotImplementedError('search_name not implemented')
N = TypeVar('N', bound=Searchable)
@dataclass
class NameSearcher(Generic[N]):
name: str
package: Optional[str]
nodetypes: List[NodeType]
def _matches(self, model: N) -> bool:
"""Return True if the model matches the given name, package, and type.
If package is None, any package is allowed.
nodetypes should be a container of NodeTypes that implements the 'in'
operator.
"""
if model.resource_type not in self.nodetypes:
return False
if self.name != model.search_name:
return False
return self.package is None or self.package == model.package_name
def search(self, haystack: Iterable[N]) -> Optional[N]:
"""Find an entry in the given iterable by name."""
for model in haystack:
if self._matches(model):
return model
return None
D = TypeVar('D')
@@ -563,13 +563,15 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
docs: MutableMapping[str, ParsedDocumentation] = field(default_factory=dict)
exposures: MutableMapping[str, ParsedExposure] = field(default_factory=dict)
selectors: MutableMapping[str, Any] = field(default_factory=dict)
disabled: List[CompileResultNode] = field(default_factory=list)
files: MutableMapping[str, AnySourceFile] = field(default_factory=dict)
metadata: ManifestMetadata = field(default_factory=ManifestMetadata)
flat_graph: Dict[str, Any] = field(default_factory=dict)
state_check: ManifestStateCheck = field(default_factory=ManifestStateCheck)
# Moved from the ParseResult object
source_patches: MutableMapping[SourceKey, SourcePatch] = field(default_factory=dict)
disabled: MutableMapping[str, List[CompileResultNode]] = field(default_factory=dict)
# following is from ParseResult
_disabled: MutableMapping[str, List[CompileResultNode]] = field(default_factory=dict)
_doc_lookup: Optional[DocLookup] = field(
default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
)
@@ -579,9 +581,6 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
_ref_lookup: Optional[RefableLookup] = field(
default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
)
_disabled_lookup: Optional[DisabledLookup] = field(
default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
)
_analysis_lookup: Optional[AnalysisLookup] = field(
default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
)
@@ -655,12 +654,26 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
}
}
def build_disabled_by_file_id(self):
disabled_by_file_id = {}
for node_list in self.disabled.values():
for node in node_list:
disabled_by_file_id[node.file_id] = node
return disabled_by_file_id
def find_disabled_by_name(
self, name: str, package: Optional[str] = None
) -> Optional[ManifestNode]:
searcher: NameSearcher = NameSearcher(
name, package, NodeType.refable()
)
result = searcher.search(self.disabled)
return result
def find_disabled_source_by_name(
self, source_name: str, table_name: str, package: Optional[str] = None
) -> Optional[ParsedSourceDefinition]:
search_name = f'{source_name}.{table_name}'
searcher: NameSearcher = NameSearcher(
search_name, package, [NodeType.Source]
)
result = searcher.search(self.disabled)
if result is not None:
assert isinstance(result, ParsedSourceDefinition)
return result
def _materialization_candidates_for(
self, project_name: str,
@@ -705,6 +718,60 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
resource_fqns[resource_type_plural].add(tuple(resource.fqn))
return resource_fqns
# This is called by 'parse_patch' in the NodePatchParser
def add_patch(
self, source_file: SchemaSourceFile, patch: ParsedNodePatch,
) -> None:
if patch.yaml_key in ['models', 'seeds', 'snapshots']:
unique_id = self.ref_lookup.get_unique_id(patch.name, None)
elif patch.yaml_key == 'analyses':
unique_id = self.analysis_lookup.get_unique_id(patch.name, None)
else:
raise dbt.exceptions.InternalException(
f'Unexpected yaml_key {patch.yaml_key} for patch in '
f'file {source_file.path.original_file_path}'
)
if unique_id is None:
# This will usually happen when a node is disabled
return
# patches can't be overwritten
node = self.nodes.get(unique_id)
if node:
if node.patch_path:
package_name, existing_file_path = node.patch_path.split('://')
raise_duplicate_patch_name(patch, existing_file_path)
source_file.append_patch(patch.yaml_key, unique_id)
node.patch(patch)
def add_macro_patch(
self, source_file: SchemaSourceFile, patch: ParsedMacroPatch,
) -> None:
# macros are fully namespaced
unique_id = f'macro.{patch.package_name}.{patch.name}'
macro = self.macros.get(unique_id)
if not macro:
warn_or_error(
f'WARNING: Found documentation for macro "{patch.name}" '
f'which was not found'
)
return
if macro.patch_path:
package_name, existing_file_path = macro.patch_path.split('://')
raise_duplicate_macro_patch_name(patch, existing_file_path)
source_file.macro_patches[patch.name] = unique_id
macro.patch(patch)
def add_source_patch(
self, source_file: SchemaSourceFile, patch: SourcePatch,
) -> None:
# source patches must be unique
key = (patch.overrides, patch.name)
if key in self.source_patches:
raise_duplicate_source_patch_name(patch, self.source_patches[key])
self.source_patches[key] = patch
source_file.source_patches.append(key)
def get_used_schemas(self, resource_types=None):
return frozenset({
(node.database, node.schema) for node in
@@ -718,6 +785,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
chain(self.nodes.values(), self.sources.values())
)
# This is used in dbt.task.rpc.sql_commands 'add_new_refs'
def deepcopy(self):
return Manifest(
nodes={k: _deepcopy(v) for k, v in self.nodes.items()},
@@ -727,7 +795,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
exposures={k: _deepcopy(v) for k, v in self.exposures.items()},
selectors={k: _deepcopy(v) for k, v in self.selectors.items()},
metadata=self.metadata,
disabled={k: _deepcopy(v) for k, v in self.disabled.items()},
disabled=[_deepcopy(n) for n in self.disabled],
files={k: _deepcopy(v) for k, v in self.files.items()},
state_check=_deepcopy(self.state_check),
)
@@ -810,15 +878,6 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
def rebuild_ref_lookup(self):
self._ref_lookup = RefableLookup(self)
@property
def disabled_lookup(self) -> DisabledLookup:
if self._disabled_lookup is None:
self._disabled_lookup = DisabledLookup(self)
return self._disabled_lookup
def rebuild_disabled_lookup(self):
self._disabled_lookup = DisabledLookup(self)
@property
def analysis_lookup(self) -> AnalysisLookup:
if self._analysis_lookup is None:
@@ -836,7 +895,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
) -> MaybeNonSource:
node: Optional[ManifestNode] = None
disabled: Optional[List[ManifestNode]] = None
disabled: Optional[ManifestNode] = None
candidates = _search_packages(
current_project, node_package, target_model_package
@@ -849,12 +908,12 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
# it's possible that the node is disabled
if disabled is None:
disabled = self.disabled_lookup.find(
disabled = self.find_disabled_by_name(
target_model_name, pkg
)
if disabled:
return Disabled(disabled[0])
if disabled is not None:
return Disabled(disabled)
return None
# Called by dbt.parser.manifest._resolve_sources_for_exposure
@@ -866,24 +925,24 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
current_project: str,
node_package: str
) -> MaybeParsedSource:
search_name = f'{target_source_name}.{target_table_name}'
key = (target_source_name, target_table_name)
candidates = _search_packages(current_project, node_package)
source: Optional[ParsedSourceDefinition] = None
disabled: Optional[List[ParsedSourceDefinition]] = None
disabled: Optional[ParsedSourceDefinition] = None
for pkg in candidates:
source = self.source_lookup.find(search_name, pkg, self)
source = self.source_lookup.find(key, pkg, self)
if source is not None and source.config.enabled:
return source
if disabled is None:
disabled = self.disabled_lookup.find(
f'{target_source_name}.{target_table_name}', pkg
disabled = self.find_disabled_source_by_name(
target_source_name, target_table_name, pkg
)
if disabled:
return Disabled(disabled[0])
if disabled is not None:
return Disabled(disabled)
return None
# Called by DocsRuntimeContext.doc
@@ -1006,11 +1065,10 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
source_file.exposures.append(exposure.unique_id)
def add_disabled_nofile(self, node: CompileResultNode):
# There can be multiple disabled nodes for the same unique_id
if node.unique_id in self.disabled:
self.disabled[node.unique_id].append(node)
if node.unique_id in self._disabled:
self._disabled[node.unique_id].append(node)
else:
self.disabled[node.unique_id] = [node]
self._disabled[node.unique_id] = [node]
def add_disabled(self, source_file: AnySourceFile, node: CompileResultNode, test_from=None):
self.add_disabled_nofile(node)
@@ -1042,17 +1100,16 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
self.docs,
self.exposures,
self.selectors,
self.disabled,
self.files,
self.metadata,
self.flat_graph,
self.state_check,
self.source_patches,
self.disabled,
self._disabled,
self._doc_lookup,
self._source_lookup,
self._ref_lookup,
self._disabled_lookup,
self._analysis_lookup,
)
return self.__class__, args
@@ -1070,7 +1127,7 @@ AnyManifest = Union[Manifest, MacroManifest]
@dataclass
@schema_version('manifest', 3)
@schema_version('manifest', 2)
class WritableManifest(ArtifactMixin):
nodes: Mapping[UniqueID, ManifestNode] = field(
metadata=dict(description=(
@@ -1102,8 +1159,8 @@ class WritableManifest(ArtifactMixin):
'The selectors defined in selectors.yml'
))
)
disabled: Optional[Mapping[UniqueID, List[CompileResultNode]]] = field(metadata=dict(
description='A mapping of the disabled nodes in the target'
disabled: Optional[List[CompileResultNode]] = field(metadata=dict(
description='A list of the disabled nodes in the target'
))
parent_map: Optional[NodeEdgeMap] = field(metadata=dict(
description='A mapping from child nodes to their dependencies',

View File

@@ -268,10 +268,9 @@ class BaseConfig(
return True
# This is used in 'add_config_call' to created the combined config_call_dict.
# 'meta' moved here from node
mergebehavior = {
"append": ['pre-hook', 'pre_hook', 'post-hook', 'post_hook', 'tags'],
"update": ['quoting', 'column_types', 'meta'],
"update": ['quoting', 'column_types'],
}
@classmethod
@@ -356,8 +355,35 @@ class SourceConfig(BaseConfig):
@dataclass
class NodeAndTestConfig(BaseConfig):
class NodeConfig(BaseConfig):
# Note: if any new fields are added with MergeBehavior, also update the
# 'mergebehavior' dictionary
enabled: bool = True
materialized: str = 'view'
persist_docs: Dict[str, Any] = field(default_factory=dict)
post_hook: List[Hook] = field(
default_factory=list,
metadata=MergeBehavior.Append.meta(),
)
pre_hook: List[Hook] = field(
default_factory=list,
metadata=MergeBehavior.Append.meta(),
)
# this only applies for config v1, so it doesn't participate in comparison
vars: Dict[str, Any] = field(
default_factory=dict,
metadata=metas(CompareBehavior.Exclude, MergeBehavior.Update),
)
quoting: Dict[str, Any] = field(
default_factory=dict,
metadata=MergeBehavior.Update.meta(),
)
# This is actually only used by seeds. Should it be available to others?
# That would be a breaking change!
column_types: Dict[str, Any] = field(
default_factory=dict,
metadata=MergeBehavior.Update.meta(),
)
# these fields are included in serialized output, but are not part of
# config comparison (they are part of database_representation)
alias: Optional[str] = field(
@@ -378,36 +404,6 @@ class NodeAndTestConfig(BaseConfig):
MergeBehavior.Append,
CompareBehavior.Exclude),
)
meta: Dict[str, Any] = field(
default_factory=dict,
metadata=MergeBehavior.Update.meta(),
)
@dataclass
class NodeConfig(NodeAndTestConfig):
# Note: if any new fields are added with MergeBehavior, also update the
# 'mergebehavior' dictionary
materialized: str = 'view'
persist_docs: Dict[str, Any] = field(default_factory=dict)
post_hook: List[Hook] = field(
default_factory=list,
metadata=MergeBehavior.Append.meta(),
)
pre_hook: List[Hook] = field(
default_factory=list,
metadata=MergeBehavior.Append.meta(),
)
quoting: Dict[str, Any] = field(
default_factory=dict,
metadata=MergeBehavior.Update.meta(),
)
# This is actually only used by seeds. Should it be available to others?
# That would be a breaking change!
column_types: Dict[str, Any] = field(
default_factory=dict,
metadata=MergeBehavior.Update.meta(),
)
full_refresh: Optional[bool] = None
on_schema_change: Optional[str] = 'ignore'
@@ -451,8 +447,7 @@ class SeedConfig(NodeConfig):
@dataclass
class TestConfig(NodeAndTestConfig):
# this is repeated because of a different default
class TestConfig(NodeConfig):
schema: Optional[str] = field(
default='dbt_test__audit',
metadata=CompareBehavior.Exclude.meta(),

View File

@@ -148,7 +148,6 @@ class ParsedNodeMixins(dbtClassMixin):
"""Given a ParsedNodePatch, add the new information to the node."""
# explicitly pick out the parts to update so we don't inadvertently
# step on the model name or anything
# Note: config should already be updated
self.patch_path: Optional[str] = patch.file_id
# update created_at so process_docs will run in partial parsing
self.created_at = int(time.time())
@@ -156,10 +155,20 @@ class ParsedNodeMixins(dbtClassMixin):
self.columns = patch.columns
self.meta = patch.meta
self.docs = patch.docs
if flags.STRICT_MODE:
# It seems odd that an instance can be invalid
# Maybe there should be validation or restrictions
# elsewhere?
assert isinstance(self, dbtClassMixin)
dct = self.to_dict(omit_none=False)
self.validate(dct)
def get_materialization(self):
return self.config.materialized
def local_vars(self):
return self.config.vars
@dataclass
class ParsedNodeMandatory(
@@ -182,7 +191,7 @@ class ParsedNodeMandatory(
class ParsedNodeDefaults(ParsedNodeMandatory):
tags: List[str] = field(default_factory=list)
refs: List[List[str]] = field(default_factory=list)
sources: List[List[str]] = field(default_factory=list)
sources: List[List[Any]] = field(default_factory=list)
depends_on: DependsOn = field(default_factory=DependsOn)
description: str = field(default='')
columns: Dict[str, ColumnInfo] = field(default_factory=dict)
@@ -194,7 +203,6 @@ class ParsedNodeDefaults(ParsedNodeMandatory):
deferred: bool = False
unrendered_config: Dict[str, Any] = field(default_factory=dict)
created_at: int = field(default_factory=lambda: int(time.time()))
config_call_dict: Dict[str, Any] = field(default_factory=dict)
def write_node(self, target_path: str, subdirectory: str, payload: str):
if (os.path.basename(self.path) ==
@@ -221,11 +229,6 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
def _serialize(self):
return self.to_dict()
def __post_serialize__(self, dct):
if 'config_call_dict' in dct:
del dct['config_call_dict']
return dct
@classmethod
def _deserialize(cls, dct: Dict[str, int]):
# The serialized ParsedNodes do not differ from each other
@@ -242,9 +245,9 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
return ParsedRPCNode.from_dict(dct)
elif resource_type == 'test':
if 'test_metadata' in dct:
return ParsedGenericTestNode.from_dict(dct)
return ParsedSchemaTestNode.from_dict(dct)
else:
return ParsedSingularTestNode.from_dict(dct)
return ParsedDataTestNode.from_dict(dct)
elif resource_type == 'operation':
return ParsedHookNode.from_dict(dct)
elif resource_type == 'seed':
@@ -255,16 +258,10 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
return cls.from_dict(dct)
def _persist_column_docs(self) -> bool:
if hasattr(self.config, 'persist_docs'):
assert isinstance(self.config, NodeConfig)
return bool(self.config.persist_docs.get('columns'))
return False
return bool(self.config.persist_docs.get('columns'))
def _persist_relation_docs(self) -> bool:
if hasattr(self.config, 'persist_docs'):
assert isinstance(self.config, NodeConfig)
return bool(self.config.persist_docs.get('relation'))
return False
return bool(self.config.persist_docs.get('relation'))
def same_body(self: T, other: T) -> bool:
return self.raw_sql == other.raw_sql
@@ -412,21 +409,17 @@ class HasTestMetadata(dbtClassMixin):
@dataclass
class ParsedSingularTestNode(ParsedNode):
class ParsedDataTestNode(ParsedNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
# Was not able to make mypy happy and keep the code working. We need to
# refactor the various configs.
config: TestConfig = field(default_factory=TestConfig) # type: ignore
config: TestConfig = field(default_factory=TestConfig)
@dataclass
class ParsedGenericTestNode(ParsedNode, HasTestMetadata):
# keep this in sync with CompiledGenericTestNode!
class ParsedSchemaTestNode(ParsedNode, HasTestMetadata):
# keep this in sync with CompiledSchemaTestNode!
resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
column_name: Optional[str] = None
# Was not able to make mypy happy and keep the code working. We need to
# refactor the various configs.
config: TestConfig = field(default_factory=TestConfig) # type: ignore
config: TestConfig = field(default_factory=TestConfig)
def same_contents(self, other) -> bool:
if other is None:
@@ -463,7 +456,6 @@ class ParsedPatch(HasYamlMetadata, Replaceable):
description: str
meta: Dict[str, Any]
docs: Docs
config: Dict[str, Any]
# The parsed node update is only the 'patch', not the test. The test became a
@@ -495,6 +487,9 @@ class ParsedMacro(UnparsedBaseNode, HasUniqueID):
arguments: List[MacroArgument] = field(default_factory=list)
created_at: int = field(default_factory=lambda: int(time.time()))
def local_vars(self):
return {}
def patch(self, patch: ParsedMacroPatch):
self.patch_path: Optional[str] = patch.file_id
self.description = patch.description
@@ -502,6 +497,11 @@ class ParsedMacro(UnparsedBaseNode, HasUniqueID):
self.meta = patch.meta
self.docs = patch.docs
self.arguments = patch.arguments
if flags.STRICT_MODE:
# What does this actually validate?
assert isinstance(self, dbtClassMixin)
dct = self.to_dict(omit_none=False)
self.validate(dct)
def same_contents(self, other: Optional['ParsedMacro']) -> bool:
if other is None:
@@ -692,7 +692,7 @@ class ParsedSourceDefinition(
@property
def depends_on(self):
return DependsOn(macros=[], nodes=[])
return {'nodes': []}
@property
def refs(self):
@@ -773,11 +773,11 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
ManifestNodes = Union[
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedRPCNode,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
]

View File

@@ -44,11 +44,6 @@ class UnparsedMacro(UnparsedBaseNode, HasSQL):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Macro]})
@dataclass
class UnparsedGenericTest(UnparsedBaseNode, HasSQL):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Macro]})
@dataclass
class UnparsedNode(UnparsedBaseNode, HasSQL):
name: str
@@ -131,17 +126,12 @@ class HasYamlMetadata(dbtClassMixin):
@dataclass
class HasConfig():
config: Dict[str, Any] = field(default_factory=dict)
@dataclass
class UnparsedAnalysisUpdate(HasConfig, HasColumnDocs, HasDocs, HasYamlMetadata):
class UnparsedAnalysisUpdate(HasColumnDocs, HasDocs, HasYamlMetadata):
pass
@dataclass
class UnparsedNodeUpdate(HasConfig, HasColumnTests, HasTests, HasYamlMetadata):
class UnparsedNodeUpdate(HasColumnTests, HasTests, HasYamlMetadata):
quote_columns: Optional[bool] = None
@@ -153,7 +143,7 @@ class MacroArgument(dbtClassMixin):
@dataclass
class UnparsedMacroUpdate(HasConfig, HasDocs, HasYamlMetadata):
class UnparsedMacroUpdate(HasDocs, HasYamlMetadata):
arguments: List[MacroArgument] = field(default_factory=list)
@@ -271,7 +261,6 @@ class UnparsedSourceDefinition(dbtClassMixin, Replaceable):
loaded_at_field: Optional[str] = None
tables: List[UnparsedSourceTableDefinition] = field(default_factory=list)
tags: List[str] = field(default_factory=list)
config: Dict[str, Any] = field(default_factory=dict)
@property
def yaml_key(self) -> 'str':

View File

@@ -1,7 +1,9 @@
from dbt.contracts.util import Replaceable, Mergeable, list_str
from dbt.contracts.connection import QueryComment, UserConfigContract
from dbt.contracts.connection import UserConfigContract, QueryComment
from dbt.helper_types import NoValue
from dbt.logger import GLOBAL_LOGGER as logger # noqa
from dbt import tracking
from dbt import ui
from dbt.dataclass_schema import (
dbtClassMixin, ValidationError,
HyphenatedDbtClassMixin,
@@ -174,10 +176,8 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
config_version: int
project_root: Optional[str] = None
source_paths: Optional[List[str]] = None
model_paths: Optional[List[str]] = None
macro_paths: Optional[List[str]] = None
data_paths: Optional[List[str]] = None
seed_paths: Optional[List[str]] = None
test_paths: Optional[List[str]] = None
analysis_paths: Optional[List[str]] = None
docs_paths: Optional[List[str]] = None
@@ -187,7 +187,7 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
clean_targets: Optional[List[str]] = None
profile: Optional[str] = None
log_path: Optional[str] = None
packages_install_path: Optional[str] = None
modules_path: Optional[str] = None
quoting: Optional[Quoting] = None
on_run_start: Optional[List[str]] = field(default_factory=list_str)
on_run_end: Optional[List[str]] = field(default_factory=list_str)
@@ -230,21 +230,25 @@ class UserConfig(ExtensibleDbtClassMixin, Replaceable, UserConfigContract):
use_colors: Optional[bool] = None
partial_parse: Optional[bool] = None
printer_width: Optional[int] = None
write_json: Optional[bool] = None
warn_error: Optional[bool] = None
log_format: Optional[bool] = None
debug: Optional[bool] = None
version_check: Optional[bool] = None
fail_fast: Optional[bool] = None
use_experimental_parser: Optional[bool] = None
static_parser: Optional[bool] = None
def set_values(self, cookie_dir):
if self.send_anonymous_usage_stats:
tracking.initialize_tracking(cookie_dir)
else:
tracking.do_not_track()
if self.use_colors is not None:
ui.use_colors(self.use_colors)
if self.printer_width:
ui.printer_width(self.printer_width)
@dataclass
class ProfileConfig(HyphenatedDbtClassMixin, Replaceable):
profile_name: str = field(metadata={'preserve_underscore': True})
target_name: str = field(metadata={'preserve_underscore': True})
user_config: UserConfig = field(metadata={'preserve_underscore': True})
config: UserConfig
threads: int
# TODO: make this a dynamic union of some kind?
credentials: Optional[Dict[str, Any]]

View File

@@ -1,5 +1,5 @@
from collections.abc import Mapping
from dataclasses import dataclass
from dataclasses import dataclass, fields
from typing import (
Optional, Dict,
)
@@ -7,8 +7,9 @@ from typing_extensions import Protocol
from dbt.dataclass_schema import dbtClassMixin, StrEnum
from dbt import deprecations
from dbt.contracts.util import Replaceable
from dbt.exceptions import raise_dataclass_not_dict, CompilationException
from dbt.exceptions import CompilationException
from dbt.utils import deep_merge
@@ -42,10 +43,13 @@ class FakeAPIObject(dbtClassMixin, Replaceable, Mapping):
raise KeyError(key) from None
def __iter__(self):
raise_dataclass_not_dict(self)
deprecations.warn('not-a-dictionary', obj=self)
for _, name in self._get_fields():
yield name
def __len__(self):
raise_dataclass_not_dict(self)
deprecations.warn('not-a-dictionary', obj=self)
return len(fields(self.__class__))
def incorporate(self, **kwargs):
value = self.to_dict(omit_none=True)

View File

@@ -185,7 +185,7 @@ class RunExecutionResult(
@dataclass
@schema_version('run-results', 3)
@schema_version('run-results', 2)
class RunResultsArtifact(ExecutionResult, ArtifactMixin):
results: Sequence[RunResultOutput]
args: Dict[str, Any] = field(default_factory=dict)
@@ -285,9 +285,6 @@ class SourceFreshnessOutput(dbtClassMixin):
status: FreshnessStatus
criteria: FreshnessThreshold
adapter_response: Dict[str, Any]
timing: List[TimingInfo]
thread_id: str
execution_time: float
@dataclass
@@ -336,10 +333,7 @@ def process_freshness_result(
max_loaded_at_time_ago_in_s=result.age,
status=result.status,
criteria=criteria,
adapter_response=result.adapter_response,
timing=result.timing,
thread_id=result.thread_id,
execution_time=result.execution_time,
adapter_response=result.adapter_response
)
@@ -369,7 +363,7 @@ class FreshnessResult(ExecutionResult):
@dataclass
@schema_version('sources', 2)
@schema_version('sources', 1)
class FreshnessExecutionResultArtifact(
ArtifactMixin,
VersionedSchema,

View File

@@ -58,7 +58,6 @@ class RPCExecParameters(RPCParameters):
class RPCCompileParameters(RPCParameters):
threads: Optional[int] = None
models: Union[None, str, List[str]] = None
select: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
selector: Optional[str] = None
state: Optional[str] = None
@@ -72,14 +71,12 @@ class RPCListParameters(RPCParameters):
select: Union[None, str, List[str]] = None
selector: Optional[str] = None
output: Optional[str] = 'json'
output_keys: Optional[List[str]] = None
@dataclass
class RPCRunParameters(RPCParameters):
threads: Optional[int] = None
models: Union[None, str, List[str]] = None
select: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
selector: Optional[str] = None
state: Optional[str] = None
@@ -121,9 +118,8 @@ class RPCDocsGenerateParameters(RPCParameters):
@dataclass
class RPCBuildParameters(RPCParameters):
resource_types: Optional[List[str]] = None
select: Union[None, str, List[str]] = None
threads: Optional[int] = None
models: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
selector: Optional[str] = None
state: Optional[str] = None

View File

@@ -9,7 +9,6 @@ class SelectorDefinition(dbtClassMixin):
name: str
definition: Union[str, Dict[str, Any]]
description: str = ''
default: bool = False
@dataclass

View File

@@ -1,6 +1,5 @@
from pathlib import Path
from .graph.manifest import WritableManifest
from .results import RunResultsArtifact
from typing import Optional
from dbt.exceptions import IncompatibleSchemaException
@@ -9,7 +8,6 @@ class PreviousState:
def __init__(self, path: Path):
self.path: Path = path
self.manifest: Optional[WritableManifest] = None
self.results: Optional[RunResultsArtifact] = None
manifest_path = self.path / 'manifest.json'
if manifest_path.exists() and manifest_path.is_file():
@@ -18,11 +16,3 @@ class PreviousState:
except IncompatibleSchemaException as exc:
exc.add_filename(str(manifest_path))
raise
results_path = self.path / 'run_results.json'
if results_path.exists() and results_path.is_file():
try:
self.results = RunResultsArtifact.read(str(results_path))
except IncompatibleSchemaException as exc:
exc.add_filename(str(results_path))
raise

View File

@@ -170,12 +170,6 @@ class BaseArtifactMetadata(dbtClassMixin):
)
env: Dict[str, str] = dataclasses.field(default_factory=get_metadata_env)
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
if dct['generated_at'] and dct['generated_at'].endswith('+00:00'):
dct['generated_at'] = dct['generated_at'].replace('+00:00', '') + "Z"
return dct
def schema_version(name: str, version: int):
def inner(cls: Type[VersionedSchema]):

View File

@@ -43,28 +43,91 @@ class DBTDeprecation:
active_deprecations.add(self.name)
class PackageRedirectDeprecation(DBTDeprecation):
_name = 'package-redirect'
class DispatchPackagesDeprecation(DBTDeprecation):
_name = 'dispatch-packages'
_description = '''\
The `{old_name}` package is deprecated in favor of `{new_name}`. Please update
your `packages.yml` configuration to use `{new_name}` instead.
The "packages" argument of adapter.dispatch() has been deprecated.
Use the "macro_namespace" argument instead.
Raised during dispatch for: {macro_name}
For more information, see:
https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch
'''
class PackageInstallPathDeprecation(DBTDeprecation):
_name = 'install-packages-path'
class MaterializationReturnDeprecation(DBTDeprecation):
_name = 'materialization-return'
_description = '''\
The default package install path has changed from `dbt_modules` to `dbt_packages`.
Please update `clean-targets` in `dbt_project.yml` and check `.gitignore` as well.
Or, set `packages-install-path: dbt_modules` if you'd like to keep the current value.
The materialization ("{materialization}") did not explicitly return a list
of relations to add to the cache. By default the target relation will be
added, but this behavior will be removed in a future version of dbt.
For more information, see:
https://docs.getdbt.com/v0.15/docs/creating-new-materializations#section-6-returning-relations
'''
class ConfigPathDeprecation(DBTDeprecation):
_name = 'project_config_path'
class NotADictionaryDeprecation(DBTDeprecation):
_name = 'not-a-dictionary'
_description = '''\
The `{deprecated_path}` config has been deprecated in favor of `{exp_path}`.
Please update your `dbt_project.yml` configuration to reflect this change.
The object ("{obj}") was used as a dictionary. In a future version of dbt
this capability will be removed from objects of this type.
'''
class ColumnQuotingDeprecation(DBTDeprecation):
_name = 'column-quoting-unset'
_description = '''\
The quote_columns parameter was not set for seeds, so the default value of
False was chosen. The default will change to True in a future release.
For more information, see:
https://docs.getdbt.com/v0.15/docs/seeds#section-specify-column-quoting
'''
class ModelsKeyNonModelDeprecation(DBTDeprecation):
_name = 'models-key-mismatch'
_description = '''\
"{node.name}" is a {node.resource_type} node, but it is specified in
the {patch.yaml_key} section of {patch.original_file_path}.
To fix this warning, place the `{node.name}` specification under
the {expected_key} key instead.
This warning will become an error in a future release.
'''
class ExecuteMacrosReleaseDeprecation(DBTDeprecation):
_name = 'execute-macro-release'
_description = '''\
The "release" argument to execute_macro is now ignored, and will be removed
in a future relase of dbt. At that time, providing a `release` argument
will result in an error.
'''
class AdapterMacroDeprecation(DBTDeprecation):
_name = 'adapter-macro'
_description = '''\
The "adapter_macro" macro has been deprecated. Instead, use the
`adapter.dispatch` method to find a macro and call the result.
adapter_macro was called for: {macro_name}
'''
@@ -106,9 +169,13 @@ def warn(name, *args, **kwargs):
active_deprecations: Set[str] = set()
deprecations_list: List[DBTDeprecation] = [
ConfigPathDeprecation(),
PackageInstallPathDeprecation(),
PackageRedirectDeprecation()
DispatchPackagesDeprecation(),
MaterializationReturnDeprecation(),
NotADictionaryDeprecation(),
ColumnQuotingDeprecation(),
ModelsKeyNonModelDeprecation(),
ExecuteMacrosReleaseDeprecation(),
AdapterMacroDeprecation(),
]
deprecations: Dict[str, DBTDeprecation] = {

View File

@@ -91,7 +91,7 @@ class PinnedPackage(BasePackage):
def get_installation_path(self, project, renderer):
dest_dirname = self.get_project_name(project, renderer)
return os.path.join(project.packages_install_path, dest_dirname)
return os.path.join(project.modules_path, dest_dirname)
def get_subdirectory(self):
return None

View File

@@ -30,13 +30,9 @@ class RegistryPackageMixin:
class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
def __init__(self,
package: str,
version: str,
version_latest: str) -> None:
def __init__(self, package: str, version: str) -> None:
super().__init__(package)
self.version = version
self.version_latest = version_latest
@property
def name(self):
@@ -48,9 +44,6 @@ class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
def get_version(self):
return self.version
def get_version_latest(self):
return self.version_latest
def nice_version_name(self):
return 'version {}'.format(self.version)
@@ -68,8 +61,8 @@ class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
system.make_directory(os.path.dirname(tar_path))
download_url = metadata.downloads.tarball
system.download_with_retries(download_url, tar_path)
deps_path = project.packages_install_path
system.download(download_url, tar_path)
deps_path = project.modules_path
package_name = self.get_project_name(project, renderer)
system.untar_package(tar_path, deps_path, package_name)
@@ -131,7 +124,6 @@ class RegistryUnpinnedPackage(
available,
self.install_prerelease
)
available_latest = installable[-1]
# for now, pick a version and then recurse. later on,
# we'll probably want to traverse multiple options
@@ -140,5 +132,4 @@ class RegistryUnpinnedPackage(
target = semver.resolve_to_specific_version(range_, installable)
if not target:
package_version_not_found(self.package, range_, installable)
return RegistryPinnedPackage(package=self.package, version=target,
version_latest=available_latest)
return RegistryPinnedPackage(package=self.package, version=target)

View File

@@ -1,9 +0,0 @@
# Events Module
The Events module is the implmentation for structured logging. These events represent both a programatic interface to dbt processes as well as human-readable messaging in one centralized place. The centralization allows for leveraging mypy to enforce interface invariants across all dbt events, and the distinct type layer allows for decoupling events and libraries such as loggers.
# Using the Events Module
The event module provides types that represent what is happening in dbt in `events.types`. These types are intended to represent an exhaustive list of all things happening within dbt that will need to be logged, streamed, or printed. To fire an event, `events.functions::fire_event` is the entry point to the module from everywhere in dbt.
# Adding a New Event
In `events.types` add a new class that represents the new event. This may be a simple class with no values, or it may be a dataclass with some values to construct downstream messaging. Only include the data necessary to construct this message within this class. You must extend all destinations (e.g. - if your log message belongs on the cli, extend `CliEventABC`) as well as the loglevel this event belongs to.

View File

@@ -1,30 +0,0 @@
import dbt.logger as logger # type: ignore # TODO eventually remove dependency on this logger
from dbt.events.history import EVENT_HISTORY
from dbt.events.types import CliEventABC, Event
# top-level method for accessing the new eventing system
# this is where all the side effects happen branched by event type
# (i.e. - mutating the event history, printing to stdout, logging
# to files, etc.)
def fire_event(e: Event) -> None:
EVENT_HISTORY.append(e)
if isinstance(e, CliEventABC):
if e.level_tag() == 'test':
# TODO after implmenting #3977 send to new test level
logger.GLOBAL_LOGGER.debug(logger.timestamped_line(e.cli_msg()))
elif e.level_tag() == 'debug':
logger.GLOBAL_LOGGER.debug(logger.timestamped_line(e.cli_msg()))
elif e.level_tag() == 'info':
logger.GLOBAL_LOGGER.info(logger.timestamped_line(e.cli_msg()))
elif e.level_tag() == 'warn':
logger.GLOBAL_LOGGER.warning()(logger.timestamped_line(e.cli_msg()))
elif e.level_tag() == 'error':
logger.GLOBAL_LOGGER.error(logger.timestamped_line(e.cli_msg()))
elif e.level_tag() == 'exception':
logger.GLOBAL_LOGGER.exception(logger.timestamped_line(e.cli_msg()))
else:
raise AssertionError(
f"Event type {type(e).__name__} has unhandled level: {e.level_tag()}"
)

View File

@@ -1,7 +0,0 @@
from dbt.events.types import Event
from typing import List
# the global history of events for this session
# TODO this is naive and the memory footprint is likely far too large.
EVENT_HISTORY: List[Event] = []

View File

@@ -1,147 +0,0 @@
from abc import ABCMeta, abstractmethod
from dataclasses import dataclass
# types to represent log levels
# in preparation for #3977
class TestLevel():
def level_tag(self) -> str:
return "test"
class DebugLevel():
def level_tag(self) -> str:
return "debug"
class InfoLevel():
def level_tag(self) -> str:
return "info"
class WarnLevel():
def level_tag(self) -> str:
return "warn"
class ErrorLevel():
def level_tag(self) -> str:
return "error"
class ExceptionLevel():
def level_tag(self) -> str:
return "exception"
# The following classes represent the data necessary to describe a
# particular event to both human readable logs, and machine reliable
# event streams. classes extend superclasses that indicate what
# destinations they are intended for, which mypy uses to enforce
# that the necessary methods are defined.
# top-level superclass for all events
class Event(metaclass=ABCMeta):
# do not define this yourself. inherit it from one of the above level types.
@abstractmethod
def level_tag(self) -> str:
raise Exception("level_tag not implemented for event")
class CliEventABC(Event, metaclass=ABCMeta):
# Solely the human readable message. Timestamps and formatting will be added by the logger.
@abstractmethod
def cli_msg(self) -> str:
raise Exception("cli_msg not implemented for cli event")
class ParsingStart(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "Start parsing."
class ParsingCompiling(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "Compiling."
class ParsingWritingManifest(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "Writing manifest."
class ParsingDone(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "Done."
class ManifestDependenciesLoaded(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "Dependencies loaded"
class ManifestLoaderCreated(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "ManifestLoader created"
class ManifestLoaded(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "Manifest loaded"
class ManifestChecked(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "Manifest checked"
class ManifestFlatGraphBuilt(InfoLevel, CliEventABC):
def cli_msg(self) -> str:
return "Flat graph built"
@dataclass
class ReportPerformancePath(InfoLevel, CliEventABC):
path: str
def cli_msg(self) -> str:
return f"Performance info: {self.path}"
@dataclass
class MacroEventInfo(InfoLevel, CliEventABC):
msg: str
def cli_msg(self) -> str:
return self.msg
@dataclass
class MacroEventDebug(DebugLevel, CliEventABC):
msg: str
def cli_msg(self) -> str:
return self.msg
# since mypy doesn't run on every file we need to suggest to mypy that every
# class gets instantiated. But we don't actually want to run this code.
# making the conditional `if False` causes mypy to skip it as dead code so
# we need to skirt around that by computing something it doesn't check statically.
#
# TODO remove these lines once we run mypy everywhere.
if 1 == 0:
ParsingStart()
ParsingCompiling()
ParsingWritingManifest()
ParsingDone()
ManifestDependenciesLoaded()
ManifestLoaderCreated()
ManifestLoaded()
ManifestChecked()
ManifestFlatGraphBuilt()
ReportPerformancePath(path='')
MacroEventInfo(msg='')
MacroEventDebug(msg='')

View File

@@ -5,7 +5,7 @@ from typing import NoReturn, Optional, Mapping, Any
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.node_types import NodeType
from dbt import flags
from dbt.ui import line_wrap_message, warning_tag
from dbt.ui import line_wrap_message
import dbt.dataclass_schema
@@ -466,15 +466,6 @@ def invalid_type_error(method_name, arg_name, got_value, expected_type,
got_value=got_value, got_type=got_type))
def invalid_bool_error(got_value, macro_name) -> NoReturn:
"""Raise a CompilationException when an macro expects a boolean but gets some
other value.
"""
msg = ("Macro '{macro_name}' returns '{got_value}'. It is not type 'bool' "
"and cannot not be converted reliably to a bool.")
raise_compiler_error(msg.format(macro_name=macro_name, got_value=got_value))
def ref_invalid_args(model, args) -> NoReturn:
raise_compiler_error(
"ref() takes at most two arguments ({} given)".format(len(args)),
@@ -615,6 +606,14 @@ def source_target_not_found(
raise_compiler_error(msg, model)
def ref_disabled_dependency(model, target_model):
raise_compiler_error(
"Model '{}' depends on model '{}' which is disabled in "
"the project config".format(model.unique_id,
target_model.unique_id),
model)
def dependency_not_found(model, target_model_name):
raise_compiler_error(
"'{}' depends on '{}' which is not in the graph!"
@@ -629,20 +628,6 @@ def macro_not_found(model, target_macro_id):
.format(model.unique_id, target_macro_id))
def macro_invalid_dispatch_arg(macro_name) -> NoReturn:
msg = '''\
The "packages" argument of adapter.dispatch() has been deprecated.
Use the "macro_namespace" argument instead.
Raised during dispatch for: {}
For more information, see:
https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch
'''
raise_compiler_error(msg.format(macro_name))
def materialization_not_available(model, adapter_type):
materialization = model.get_materialization()
@@ -689,14 +674,6 @@ def missing_relation(relation, model=None):
model)
def raise_dataclass_not_dict(obj):
msg = (
'The object ("{obj}") was used as a dictionary. This '
'capability has been removed from objects of this type.'
)
raise_compiler_error(msg)
def relation_wrong_type(relation, expected_type, model=None):
raise_compiler_error(
('Trying to create {expected_type} {relation}, '
@@ -733,11 +710,11 @@ def system_error(operation_name):
raise_compiler_error(
"dbt encountered an error when attempting to {}. "
"If this error persists, please create an issue at: \n\n"
"https://github.com/dbt-labs/dbt-core"
"https://github.com/dbt-labs/dbt"
.format(operation_name))
class ConnectionException(Exception):
class RegistryException(Exception):
pass
@@ -939,17 +916,22 @@ def raise_unrecognized_credentials_type(typename, supported_types):
)
def warn_invalid_patch(patch, resource_type):
def raise_invalid_patch(
node, patch_section: str, patch_path: str,
) -> NoReturn:
msg = line_wrap_message(
f'''\
'{patch.name}' is a {resource_type} node, but it is
specified in the {patch.yaml_key} section of
{patch.original_file_path}.
To fix this error, place the `{patch.name}`
specification under the {resource_type.pluralize()} key instead.
'{node.name}' is a {node.resource_type} node, but it is
specified in the {patch_section} section of
{patch_path}.
To fix this error, place the `{node.name}`
specification under the {node.resource_type.pluralize()} key instead.
'''
)
warn_or_error(msg, log_fmt=warning_tag('{}'))
raise_compiler_error(msg, node)
def raise_not_implemented(msg):
@@ -1011,7 +993,6 @@ CONTEXT_EXPORTS = {
raise_ambiguous_alias,
raise_ambiguous_catalog_match,
raise_cache_inconsistent,
raise_dataclass_not_dict,
raise_compiler_error,
raise_database_error,
raise_dep_not_found,

View File

@@ -6,52 +6,18 @@ if os.name != 'nt':
from pathlib import Path
from typing import Optional
# PROFILES_DIR must be set before the other flags
# It also gets set in main.py and in set_from_args because the rpc server
# doesn't go through exactly the same main arg processing.
DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser('~'), '.dbt')
PROFILES_DIR = os.path.expanduser(
os.getenv('DBT_PROFILES_DIR', DEFAULT_PROFILES_DIR)
)
STRICT_MODE = False # Only here for backwards compatibility
FULL_REFRESH = False # subcommand
STORE_FAILURES = False # subcommand
GREEDY = None # subcommand
# Global CLI commands
USE_EXPERIMENTAL_PARSER = None
STATIC_PARSER = None
# initially all flags are set to None, the on-load call of reset() will set
# them for their first time.
STRICT_MODE = None
FULL_REFRESH = None
USE_CACHE = None
WARN_ERROR = None
TEST_NEW_PARSER = None
USE_EXPERIMENTAL_PARSER = None
WRITE_JSON = None
PARTIAL_PARSE = None
USE_COLORS = None
DEBUG = None
LOG_FORMAT = None
VERSION_CHECK = None
FAIL_FAST = None
SEND_ANONYMOUS_USAGE_STATS = None
PRINTER_WIDTH = 80
WHICH = None
# Global CLI defaults. These flags are set from three places:
# CLI args, environment variables, and user_config (profiles.yml).
# Environment variables use the pattern 'DBT_{flag name}', like DBT_PROFILES_DIR
flag_defaults = {
"USE_EXPERIMENTAL_PARSER": False,
"STATIC_PARSER": True,
"WARN_ERROR": False,
"WRITE_JSON": True,
"PARTIAL_PARSE": True,
"USE_COLORS": True,
"PROFILES_DIR": DEFAULT_PROFILES_DIR,
"DEBUG": False,
"LOG_FORMAT": None,
"VERSION_CHECK": True,
"FAIL_FAST": False,
"SEND_ANONYMOUS_USAGE_STATS": True,
"PRINTER_WIDTH": 80
}
STORE_FAILURES = None
def env_set_truthy(key: str) -> Optional[str]:
@@ -64,12 +30,6 @@ def env_set_truthy(key: str) -> Optional[str]:
return value
def env_set_bool(env_value):
if env_value in ('1', 't', 'true', 'y', 'yes'):
return True
return False
def env_set_path(key: str) -> Optional[Path]:
value = os.getenv(key)
if value is None:
@@ -78,6 +38,8 @@ def env_set_path(key: str) -> Optional[Path]:
return Path(value)
SINGLE_THREADED_WEBSERVER = env_set_truthy('DBT_SINGLE_THREADED_WEBSERVER')
SINGLE_THREADED_HANDLER = env_set_truthy('DBT_SINGLE_THREADED_HANDLER')
MACRO_DEBUGGING = env_set_truthy('DBT_MACRO_DEBUGGING')
DEFER_MODE = env_set_truthy('DBT_DEFER_TO_STATE')
ARTIFACT_STATE_PATH = env_set_path('DBT_ARTIFACT_STATE_PATH')
@@ -88,79 +50,56 @@ def _get_context():
return multiprocessing.get_context('spawn')
# This is not a flag, it's a place to store the lock
MP_CONTEXT = _get_context()
def set_from_args(args, user_config):
global STRICT_MODE, FULL_REFRESH, WARN_ERROR, \
USE_EXPERIMENTAL_PARSER, STATIC_PARSER, WRITE_JSON, PARTIAL_PARSE, \
USE_COLORS, STORE_FAILURES, PROFILES_DIR, DEBUG, LOG_FORMAT, GREEDY, \
VERSION_CHECK, FAIL_FAST, SEND_ANONYMOUS_USAGE_STATS, PRINTER_WIDTH, \
WHICH
def reset():
global STRICT_MODE, FULL_REFRESH, USE_CACHE, WARN_ERROR, TEST_NEW_PARSER, \
USE_EXPERIMENTAL_PARSER, WRITE_JSON, PARTIAL_PARSE, MP_CONTEXT, USE_COLORS, \
STORE_FAILURES
STRICT_MODE = False
FULL_REFRESH = False
USE_CACHE = True
WARN_ERROR = False
TEST_NEW_PARSER = False
USE_EXPERIMENTAL_PARSER = False
WRITE_JSON = True
PARTIAL_PARSE = False
MP_CONTEXT = _get_context()
USE_COLORS = True
STORE_FAILURES = False
def set_from_args(args):
global STRICT_MODE, FULL_REFRESH, USE_CACHE, WARN_ERROR, TEST_NEW_PARSER, \
USE_EXPERIMENTAL_PARSER, WRITE_JSON, PARTIAL_PARSE, MP_CONTEXT, USE_COLORS, \
STORE_FAILURES
USE_CACHE = getattr(args, 'use_cache', USE_CACHE)
STRICT_MODE = False # backwards compatibility
# cli args without user_config or env var option
FULL_REFRESH = getattr(args, 'full_refresh', FULL_REFRESH)
STRICT_MODE = getattr(args, 'strict', STRICT_MODE)
WARN_ERROR = (
STRICT_MODE or
getattr(args, 'warn_error', STRICT_MODE or WARN_ERROR)
)
TEST_NEW_PARSER = getattr(args, 'test_new_parser', TEST_NEW_PARSER)
USE_EXPERIMENTAL_PARSER = getattr(args, 'use_experimental_parser', USE_EXPERIMENTAL_PARSER)
WRITE_JSON = getattr(args, 'write_json', WRITE_JSON)
PARTIAL_PARSE = getattr(args, 'partial_parse', None)
MP_CONTEXT = _get_context()
# The use_colors attribute will always have a value because it is assigned
# None by default from the add_mutually_exclusive_group function
use_colors_override = getattr(args, 'use_colors')
if use_colors_override is not None:
USE_COLORS = use_colors_override
STORE_FAILURES = getattr(args, 'store_failures', STORE_FAILURES)
GREEDY = getattr(args, 'greedy', GREEDY)
WHICH = getattr(args, 'which', WHICH)
# global cli flags with env var and user_config alternatives
USE_EXPERIMENTAL_PARSER = get_flag_value('USE_EXPERIMENTAL_PARSER', args, user_config)
STATIC_PARSER = get_flag_value('STATIC_PARSER', args, user_config)
WARN_ERROR = get_flag_value('WARN_ERROR', args, user_config)
WRITE_JSON = get_flag_value('WRITE_JSON', args, user_config)
PARTIAL_PARSE = get_flag_value('PARTIAL_PARSE', args, user_config)
USE_COLORS = get_flag_value('USE_COLORS', args, user_config)
PROFILES_DIR = get_flag_value('PROFILES_DIR', args, user_config)
DEBUG = get_flag_value('DEBUG', args, user_config)
LOG_FORMAT = get_flag_value('LOG_FORMAT', args, user_config)
VERSION_CHECK = get_flag_value('VERSION_CHECK', args, user_config)
FAIL_FAST = get_flag_value('FAIL_FAST', args, user_config)
SEND_ANONYMOUS_USAGE_STATS = get_flag_value('SEND_ANONYMOUS_USAGE_STATS', args, user_config)
PRINTER_WIDTH = get_flag_value('PRINTER_WIDTH', args, user_config)
def get_flag_value(flag, args, user_config):
lc_flag = flag.lower()
flag_value = getattr(args, lc_flag, None)
if flag_value is None:
# Environment variables use pattern 'DBT_{flag name}'
env_flag = f"DBT_{flag}"
env_value = os.getenv(env_flag)
if env_value is not None and env_value != '':
env_value = env_value.lower()
# non Boolean values
if flag in ['LOG_FORMAT', 'PRINTER_WIDTH', 'PROFILES_DIR']:
flag_value = env_value
else:
flag_value = env_set_bool(env_value)
elif user_config is not None and getattr(user_config, lc_flag, None) is not None:
flag_value = getattr(user_config, lc_flag)
else:
flag_value = flag_defaults[flag]
if flag == 'PRINTER_WIDTH': # printer_width must be an int or it hangs
flag_value = int(flag_value)
if flag == 'PROFILES_DIR':
flag_value = os.path.abspath(flag_value)
return flag_value
def get_flag_dict():
return {
"use_experimental_parser": USE_EXPERIMENTAL_PARSER,
"static_parser": STATIC_PARSER,
"warn_error": WARN_ERROR,
"write_json": WRITE_JSON,
"partial_parse": PARTIAL_PARSE,
"use_colors": USE_COLORS,
"profiles_dir": PROFILES_DIR,
"debug": DEBUG,
"log_format": LOG_FORMAT,
"version_check": VERSION_CHECK,
"fail_fast": FAIL_FAST,
"send_anonymous_usage_stats": SEND_ANONYMOUS_USAGE_STATS,
"printer_width": PRINTER_WIDTH,
}
# initialize everything to the defaults on module load
reset()

View File

@@ -11,6 +11,7 @@ from .selector import ( # noqa: F401
)
from .cli import ( # noqa: F401
parse_difference,
parse_test_selectors,
parse_from_selectors_definition,
)
from .queue import GraphQueue # noqa: F401

View File

@@ -1,5 +1,4 @@
# special support for CLI argument parsing.
from dbt import flags
import itertools
from dbt.clients.yaml_helper import yaml, Loader, Dumper # noqa: F401
@@ -22,6 +21,8 @@ INTERSECTION_DELIMITER = ','
DEFAULT_INCLUDES: List[str] = ['fqn:*', 'source:*', 'exposure:*']
DEFAULT_EXCLUDES: List[str] = []
DATA_TEST_SELECTOR: str = 'test_type:data'
SCHEMA_TEST_SELECTOR: str = 'test_type:schema'
def parse_union(
@@ -65,11 +66,42 @@ def parse_union_from_default(
def parse_difference(
include: Optional[List[str]], exclude: Optional[List[str]]
) -> SelectionDifference:
included = parse_union_from_default(include, DEFAULT_INCLUDES, greedy=bool(flags.GREEDY))
included = parse_union_from_default(include, DEFAULT_INCLUDES)
excluded = parse_union_from_default(exclude, DEFAULT_EXCLUDES, greedy=True)
return SelectionDifference(components=[included, excluded])
def parse_test_selectors(
data: bool, schema: bool, base: SelectionSpec
) -> SelectionSpec:
union_components = []
if data:
union_components.append(
SelectionCriteria.from_single_spec(DATA_TEST_SELECTOR)
)
if schema:
union_components.append(
SelectionCriteria.from_single_spec(SCHEMA_TEST_SELECTOR)
)
intersect_with: SelectionSpec
if not union_components:
return base
elif len(union_components) == 1:
intersect_with = union_components[0]
else: # data and schema tests
intersect_with = SelectionUnion(
components=union_components,
expect_exists=True,
raw=[DATA_TEST_SELECTOR, SCHEMA_TEST_SELECTOR],
)
return SelectionIntersection(
components=[base, intersect_with], expect_exists=True
)
RawDefinition = Union[str, Dict[str, Any]]
@@ -148,7 +180,7 @@ def parse_union_definition(definition: Dict[str, Any]) -> SelectionSpec:
union_def_parts = _get_list_dicts(definition, 'union')
include, exclude = _parse_include_exclude_subdefs(union_def_parts)
union = SelectionUnion(components=include, greedy_warning=False)
union = SelectionUnion(components=include)
if exclude is None:
union.raw = definition
@@ -156,8 +188,7 @@ def parse_union_definition(definition: Dict[str, Any]) -> SelectionSpec:
else:
return SelectionDifference(
components=[union, exclude],
raw=definition,
greedy_warning=False
raw=definition
)
@@ -166,7 +197,7 @@ def parse_intersection_definition(
) -> SelectionSpec:
intersection_def_parts = _get_list_dicts(definition, 'intersection')
include, exclude = _parse_include_exclude_subdefs(intersection_def_parts)
intersection = SelectionIntersection(components=include, greedy_warning=False)
intersection = SelectionIntersection(components=include)
if exclude is None:
intersection.raw = definition
@@ -174,8 +205,7 @@ def parse_intersection_definition(
else:
return SelectionDifference(
components=[intersection, exclude],
raw=definition,
greedy_warning=False
raw=definition
)
@@ -209,7 +239,7 @@ def parse_dict_definition(definition: Dict[str, Any]) -> SelectionSpec:
if diff_arg is None:
return base
else:
return SelectionDifference(components=[base, diff_arg], greedy_warning=False)
return SelectionDifference(components=[base, diff_arg])
def parse_from_definition(
@@ -241,12 +271,10 @@ def parse_from_definition(
def parse_from_selectors_definition(
source: SelectorFile
) -> Dict[str, Dict[str, Union[SelectionSpec, bool]]]:
result: Dict[str, Dict[str, Union[SelectionSpec, bool]]] = {}
) -> Dict[str, SelectionSpec]:
result: Dict[str, SelectionSpec] = {}
selector: SelectorDefinition
for selector in source.selectors:
result[selector.name] = {
"default": selector.default,
"definition": parse_from_definition(selector.definition, rootlevel=True)
}
result[selector.name] = parse_from_definition(selector.definition,
rootlevel=True)
return result

View File

@@ -1,3 +1,4 @@
from typing import Set, List, Optional, Tuple
from .graph import Graph, UniqueId
@@ -29,24 +30,6 @@ def alert_non_existence(raw_spec, nodes):
)
def alert_unused_nodes(raw_spec, node_names):
summary_nodes_str = ("\n - ").join(node_names[:3])
debug_nodes_str = ("\n - ").join(node_names)
and_more_str = f"\n - and {len(node_names) - 3} more" if len(node_names) > 4 else ""
summary_msg = (
f"\nSome tests were excluded because at least one parent is not selected. "
f"Use the --greedy flag to include them."
f"\n - {summary_nodes_str}{and_more_str}"
)
logger.info(summary_msg)
if len(node_names) > 4:
debug_msg = (
f"Full list of tests that were excluded:"
f"\n - {debug_nodes_str}"
)
logger.debug(debug_msg)
def can_select_indirectly(node):
"""If a node is not selected itself, but its parent(s) are, it may qualify
for indirect selection.
@@ -168,16 +151,16 @@ class NodeSelector(MethodManager):
return direct_nodes, indirect_nodes
def select_nodes(self, spec: SelectionSpec) -> Tuple[Set[UniqueId], Set[UniqueId]]:
def select_nodes(self, spec: SelectionSpec) -> Set[UniqueId]:
"""Select the nodes in the graph according to the spec.
This is the main point of entry for turning a spec into a set of nodes:
- Recurse through spec, select by criteria, combine by set operation
- Return final (unfiltered) selection set
"""
direct_nodes, indirect_nodes = self.select_nodes_recursively(spec)
indirect_only = indirect_nodes.difference(direct_nodes)
return direct_nodes, indirect_only
return direct_nodes
def _is_graph_member(self, unique_id: UniqueId) -> bool:
if unique_id in self.manifest.sources:
@@ -230,8 +213,6 @@ class NodeSelector(MethodManager):
# - If ANY parent is missing, return it separately. We'll keep it around
# for later and see if its other parents show up.
# We use this for INCLUSION.
# Users can also opt in to inclusive GREEDY mode by passing --greedy flag,
# or by specifying `greedy: true` in a yaml selector
direct_nodes = set(selected)
indirect_nodes = set()
@@ -270,24 +251,15 @@ class NodeSelector(MethodManager):
- node selection. Based on the include/exclude sets, the set
of matched unique IDs is returned
- includes direct + indirect selection (for tests)
- expand the graph at each leaf node, before combination
- selectors might override this. for example, this is where
tests are added
- filtering:
- selectors can filter the nodes after all of them have been
selected
"""
selected_nodes, indirect_only = self.select_nodes(spec)
selected_nodes = self.select_nodes(spec)
filtered_nodes = self.filter_selection(selected_nodes)
if indirect_only:
filtered_unused_nodes = self.filter_selection(indirect_only)
if filtered_unused_nodes and spec.greedy_warning:
# log anything that didn't make the cut
unused_node_names = []
for unique_id in filtered_unused_nodes:
name = self.manifest.nodes[unique_id].name
unused_node_names.append(name)
alert_unused_nodes(spec, unused_node_names)
return filtered_nodes
def get_graph_queue(self, spec: SelectionSpec) -> GraphQueue:

View File

@@ -8,25 +8,27 @@ from dbt.dataclass_schema import StrEnum
from .graph import UniqueId
from dbt.contracts.graph.compiled import (
CompiledSingularTestNode,
CompiledGenericTestNode,
CompiledDataTestNode,
CompiledSchemaTestNode,
CompileResultNode,
ManifestNode,
)
from dbt.contracts.graph.manifest import Manifest, WritableManifest
from dbt.contracts.graph.parsed import (
HasTestMetadata,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedExposure,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSourceDefinition,
)
from dbt.contracts.state import PreviousState
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.exceptions import (
InternalException,
RuntimeException,
)
from dbt.node_types import NodeType
from dbt.ui import warning_tag
SELECTOR_GLOB = '*'
@@ -45,7 +47,6 @@ class MethodName(StrEnum):
ResourceType = 'resource_type'
State = 'state'
Exposure = 'exposure'
Result = 'result'
def is_selected_node(fqn: List[str], node_selector: str):
@@ -362,15 +363,14 @@ class TestTypeSelectorMethod(SelectorMethod):
self, included_nodes: Set[UniqueId], selector: str
) -> Iterator[UniqueId]:
search_types: Tuple[Type, ...]
# continue supporting 'schema' + 'data' for backwards compatibility
if selector in ('generic', 'schema'):
search_types = (ParsedGenericTestNode, CompiledGenericTestNode)
elif selector in ('singular', 'data'):
search_types = (ParsedSingularTestNode, CompiledSingularTestNode)
if selector == 'schema':
search_types = (ParsedSchemaTestNode, CompiledSchemaTestNode)
elif selector == 'data':
search_types = (ParsedDataTestNode, CompiledDataTestNode)
else:
raise RuntimeException(
f'Invalid test type selector {selector}: expected "generic" or '
'"singular"'
f'Invalid test type selector {selector}: expected "data" or '
'"schema"'
)
for node, real_node in self.parsed_nodes(included_nodes):
@@ -381,7 +381,7 @@ class TestTypeSelectorMethod(SelectorMethod):
class StateSelectorMethod(SelectorMethod):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.modified_macros: Optional[List[str]] = None
self.macros_were_modified: Optional[List[str]] = None
def _macros_modified(self) -> List[str]:
# we checked in the caller!
@@ -394,85 +394,44 @@ class StateSelectorMethod(SelectorMethod):
modified = []
for uid, macro in new_macros.items():
name = f'{macro.package_name}.{macro.name}'
if uid in old_macros:
old_macro = old_macros[uid]
if macro.macro_sql != old_macro.macro_sql:
modified.append(uid)
modified.append(f'{name} changed')
else:
modified.append(uid)
modified.append(f'{name} added')
for uid, macro in old_macros.items():
if uid not in new_macros:
modified.append(uid)
modified.append(f'{macro.package_name}.{macro.name} removed')
return modified
return modified[:3]
def recursively_check_macros_modified(self, node, previous_macros):
# loop through all macros that this node depends on
for macro_uid in node.depends_on.macros:
# avoid infinite recursion if we've already seen this macro
if macro_uid in previous_macros:
continue
previous_macros.append(macro_uid)
# is this macro one of the modified macros?
if macro_uid in self.modified_macros:
return True
# if not, and this macro depends on other macros, keep looping
macro_node = self.manifest.macros[macro_uid]
if len(macro_node.depends_on.macros) > 0:
return self.recursively_check_macros_modified(macro_node, previous_macros)
else:
return False
def check_macros_modified(self, node):
# check if there are any changes in macros the first time
if self.modified_macros is None:
self.modified_macros = self._macros_modified()
# no macros have been modified, skip looping entirely
if not self.modified_macros:
return False
# recursively loop through upstream macros to see if any is modified
else:
previous_macros = []
return self.recursively_check_macros_modified(node, previous_macros)
def check_modified(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
different_contents = not new.same_contents(old) # type: ignore
upstream_macro_change = self.check_macros_modified(new)
return different_contents or upstream_macro_change
def check_modified_body(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
if hasattr(new, "same_body"):
return not new.same_body(old) # type: ignore
else:
return False
def check_modified_configs(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
if hasattr(new, "same_config"):
return not new.same_config(old) # type: ignore
else:
return False
def check_modified_persisted_descriptions(
self, old: Optional[SelectorTarget], new: SelectorTarget
def check_modified(
self,
old: Optional[SelectorTarget],
new: SelectorTarget,
) -> bool:
if hasattr(new, "same_persisted_description"):
return not new.same_persisted_description(old) # type: ignore
else:
return False
# check if there are any changes in macros, if so, log a warning the
# first time
if self.macros_were_modified is None:
self.macros_were_modified = self._macros_modified()
if self.macros_were_modified:
log_str = ', '.join(self.macros_were_modified)
logger.warning(warning_tag(
f'During a state comparison, dbt detected a change in '
f'macros. This will not be marked as a modification. Some '
f'macros: {log_str}'
))
def check_modified_relation(
self, old: Optional[SelectorTarget], new: SelectorTarget
return not new.same_contents(old) # type: ignore
def check_new(
self,
old: Optional[SelectorTarget],
new: SelectorTarget,
) -> bool:
if hasattr(new, "same_database_representation"):
return not new.same_database_representation(old) # type: ignore
else:
return False
def check_modified_macros(self, _, new: SelectorTarget) -> bool:
return self.check_macros_modified(new)
def check_new(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
return old is None
def search(
@@ -484,15 +443,8 @@ class StateSelectorMethod(SelectorMethod):
)
state_checks = {
# it's new if there is no old version
'new': lambda old, _: old is None,
# use methods defined above to compare properties of old + new
'modified': self.check_modified,
'modified.body': self.check_modified_body,
'modified.configs': self.check_modified_configs,
'modified.persisted_descriptions': self.check_modified_persisted_descriptions,
'modified.relation': self.check_modified_relation,
'modified.macros': self.check_modified_macros,
'new': self.check_new,
}
if selector in state_checks:
checker = state_checks[selector]
@@ -517,23 +469,6 @@ class StateSelectorMethod(SelectorMethod):
yield node
class ResultSelectorMethod(SelectorMethod):
def search(
self, included_nodes: Set[UniqueId], selector: str
) -> Iterator[UniqueId]:
if self.previous_state is None or self.previous_state.results is None:
raise InternalException(
'No comparison run_results'
)
matches = set(
result.unique_id for result in self.previous_state.results
if result.status == selector
)
for node, real_node in self.all_nodes(included_nodes):
if node in matches:
yield node
class MethodManager:
SELECTOR_METHODS: Dict[MethodName, Type[SelectorMethod]] = {
MethodName.FQN: QualifiedNameSelectorMethod,
@@ -546,7 +481,6 @@ class MethodManager:
MethodName.TestType: TestTypeSelectorMethod,
MethodName.State: StateSelectorMethod,
MethodName.Exposure: ExposureSelectorMethod,
MethodName.Result: ResultSelectorMethod,
}
def __init__(

View File

@@ -67,7 +67,6 @@ class SelectionCriteria:
children: bool
children_depth: Optional[int]
greedy: bool = False
greedy_warning: bool = False # do not raise warning for yaml selectors
def __post_init__(self):
if self.children and self.childrens_parents:
@@ -125,11 +124,11 @@ class SelectionCriteria:
parents_depth=parents_depth,
children=bool(dct.get('children')),
children_depth=children_depth,
greedy=(greedy or bool(dct.get('greedy'))),
greedy=greedy
)
@classmethod
def dict_from_single_spec(cls, raw: str):
def dict_from_single_spec(cls, raw: str, greedy: bool = False):
result = RAW_SELECTOR_PATTERN.match(raw)
if result is None:
return {'error': 'Invalid selector spec'}
@@ -146,8 +145,6 @@ class SelectionCriteria:
dct['parents'] = bool(dct.get('parents'))
if 'children' in dct:
dct['children'] = bool(dct.get('children'))
if 'greedy' in dct:
dct['greedy'] = bool(dct.get('greedy'))
return dct
@classmethod
@@ -165,12 +162,10 @@ class BaseSelectionGroup(Iterable[SelectionSpec], metaclass=ABCMeta):
self,
components: Iterable[SelectionSpec],
expect_exists: bool = False,
greedy_warning: bool = True,
raw: Any = None,
):
self.components: List[SelectionSpec] = list(components)
self.expect_exists = expect_exists
self.greedy_warning = greedy_warning
self.raw = raw
def __iter__(self) -> Iterator[SelectionSpec]:

View File

@@ -1,5 +1,5 @@
{% macro get_columns_in_query(select_sql) -%}
{{ return(adapter.dispatch('get_columns_in_query', 'dbt')(select_sql)) }}
{{ return(adapter.dispatch('get_columns_in_query')(select_sql)) }}
{% endmacro %}
{% macro default__get_columns_in_query(select_sql) %}
@@ -15,7 +15,7 @@
{% endmacro %}
{% macro create_schema(relation) -%}
{{ adapter.dispatch('create_schema', 'dbt')(relation) }}
{{ adapter.dispatch('create_schema')(relation) }}
{% endmacro %}
{% macro default__create_schema(relation) -%}
@@ -25,7 +25,7 @@
{% endmacro %}
{% macro drop_schema(relation) -%}
{{ adapter.dispatch('drop_schema', 'dbt')(relation) }}
{{ adapter.dispatch('drop_schema')(relation) }}
{% endmacro %}
{% macro default__drop_schema(relation) -%}
@@ -35,7 +35,7 @@
{% endmacro %}
{% macro create_table_as(temporary, relation, sql) -%}
{{ adapter.dispatch('create_table_as', 'dbt')(temporary, relation, sql) }}
{{ adapter.dispatch('create_table_as')(temporary, relation, sql) }}
{%- endmacro %}
{% macro default__create_table_as(temporary, relation, sql) -%}
@@ -52,7 +52,7 @@
{% endmacro %}
{% macro get_create_index_sql(relation, index_dict) -%}
{{ return(adapter.dispatch('get_create_index_sql', 'dbt')(relation, index_dict)) }}
{{ return(adapter.dispatch('get_create_index_sql')(relation, index_dict)) }}
{% endmacro %}
{% macro default__get_create_index_sql(relation, index_dict) -%}
@@ -60,7 +60,7 @@
{% endmacro %}
{% macro create_indexes(relation) -%}
{{ adapter.dispatch('create_indexes', 'dbt')(relation) }}
{{ adapter.dispatch('create_indexes')(relation) }}
{%- endmacro %}
{% macro default__create_indexes(relation) -%}
@@ -75,7 +75,7 @@
{% endmacro %}
{% macro create_view_as(relation, sql) -%}
{{ adapter.dispatch('create_view_as', 'dbt')(relation, sql) }}
{{ adapter.dispatch('create_view_as')(relation, sql) }}
{%- endmacro %}
{% macro default__create_view_as(relation, sql) -%}
@@ -89,7 +89,7 @@
{% macro get_catalog(information_schema, schemas) -%}
{{ return(adapter.dispatch('get_catalog', 'dbt')(information_schema, schemas)) }}
{{ return(adapter.dispatch('get_catalog')(information_schema, schemas)) }}
{%- endmacro %}
{% macro default__get_catalog(information_schema, schemas) -%}
@@ -104,7 +104,7 @@
{% macro get_columns_in_relation(relation) -%}
{{ return(adapter.dispatch('get_columns_in_relation', 'dbt')(relation)) }}
{{ return(adapter.dispatch('get_columns_in_relation')(relation)) }}
{% endmacro %}
{% macro sql_convert_columns_in_relation(table) -%}
@@ -121,13 +121,13 @@
{% endmacro %}
{% macro alter_column_type(relation, column_name, new_column_type) -%}
{{ return(adapter.dispatch('alter_column_type', 'dbt')(relation, column_name, new_column_type)) }}
{{ return(adapter.dispatch('alter_column_type')(relation, column_name, new_column_type)) }}
{% endmacro %}
{% macro alter_column_comment(relation, column_dict) -%}
{{ return(adapter.dispatch('alter_column_comment', 'dbt')(relation, column_dict)) }}
{{ return(adapter.dispatch('alter_column_comment')(relation, column_dict)) }}
{% endmacro %}
{% macro default__alter_column_comment(relation, column_dict) -%}
@@ -136,7 +136,7 @@
{% endmacro %}
{% macro alter_relation_comment(relation, relation_comment) -%}
{{ return(adapter.dispatch('alter_relation_comment', 'dbt')(relation, relation_comment)) }}
{{ return(adapter.dispatch('alter_relation_comment')(relation, relation_comment)) }}
{% endmacro %}
{% macro default__alter_relation_comment(relation, relation_comment) -%}
@@ -145,7 +145,7 @@
{% endmacro %}
{% macro persist_docs(relation, model, for_relation=true, for_columns=true) -%}
{{ return(adapter.dispatch('persist_docs', 'dbt')(relation, model, for_relation, for_columns)) }}
{{ return(adapter.dispatch('persist_docs')(relation, model, for_relation, for_columns)) }}
{% endmacro %}
{% macro default__persist_docs(relation, model, for_relation, for_columns) -%}
@@ -180,7 +180,7 @@
{% macro drop_relation(relation) -%}
{{ return(adapter.dispatch('drop_relation', 'dbt')(relation)) }}
{{ return(adapter.dispatch('drop_relation')(relation)) }}
{% endmacro %}
@@ -191,7 +191,7 @@
{% endmacro %}
{% macro truncate_relation(relation) -%}
{{ return(adapter.dispatch('truncate_relation', 'dbt')(relation)) }}
{{ return(adapter.dispatch('truncate_relation')(relation)) }}
{% endmacro %}
@@ -202,7 +202,7 @@
{% endmacro %}
{% macro rename_relation(from_relation, to_relation) -%}
{{ return(adapter.dispatch('rename_relation', 'dbt')(from_relation, to_relation)) }}
{{ return(adapter.dispatch('rename_relation')(from_relation, to_relation)) }}
{% endmacro %}
{% macro default__rename_relation(from_relation, to_relation) -%}
@@ -214,7 +214,7 @@
{% macro information_schema_name(database) %}
{{ return(adapter.dispatch('information_schema_name', 'dbt')(database)) }}
{{ return(adapter.dispatch('information_schema_name')(database)) }}
{% endmacro %}
{% macro default__information_schema_name(database) -%}
@@ -227,7 +227,7 @@
{% macro list_schemas(database) -%}
{{ return(adapter.dispatch('list_schemas', 'dbt')(database)) }}
{{ return(adapter.dispatch('list_schemas')(database)) }}
{% endmacro %}
{% macro default__list_schemas(database) -%}
@@ -241,7 +241,7 @@
{% macro check_schema_exists(information_schema, schema) -%}
{{ return(adapter.dispatch('check_schema_exists', 'dbt')(information_schema, schema)) }}
{{ return(adapter.dispatch('check_schema_exists')(information_schema, schema)) }}
{% endmacro %}
{% macro default__check_schema_exists(information_schema, schema) -%}
@@ -256,7 +256,7 @@
{% macro list_relations_without_caching(schema_relation) %}
{{ return(adapter.dispatch('list_relations_without_caching', 'dbt')(schema_relation)) }}
{{ return(adapter.dispatch('list_relations_without_caching')(schema_relation)) }}
{% endmacro %}
@@ -267,7 +267,7 @@
{% macro current_timestamp() -%}
{{ adapter.dispatch('current_timestamp', 'dbt')() }}
{{ adapter.dispatch('current_timestamp')() }}
{%- endmacro %}
@@ -278,7 +278,7 @@
{% macro collect_freshness(source, loaded_at_field, filter) %}
{{ return(adapter.dispatch('collect_freshness', 'dbt')(source, loaded_at_field, filter))}}
{{ return(adapter.dispatch('collect_freshness')(source, loaded_at_field, filter))}}
{% endmacro %}
@@ -296,7 +296,7 @@
{% endmacro %}
{% macro make_temp_relation(base_relation, suffix='__dbt_tmp') %}
{{ return(adapter.dispatch('make_temp_relation', 'dbt')(base_relation, suffix))}}
{{ return(adapter.dispatch('make_temp_relation')(base_relation, suffix))}}
{% endmacro %}
{% macro default__make_temp_relation(base_relation, suffix) %}
@@ -313,7 +313,7 @@
{% macro alter_relation_add_remove_columns(relation, add_columns = none, remove_columns = none) -%}
{{ return(adapter.dispatch('alter_relation_add_remove_columns', 'dbt')(relation, add_columns, remove_columns)) }}
{{ return(adapter.dispatch('alter_relation_add_remove_columns')(relation, add_columns, remove_columns)) }}
{% endmacro %}
{% macro default__alter_relation_add_remove_columns(relation, add_columns, remove_columns) %}

View File

@@ -13,10 +13,6 @@
#}
{% macro generate_alias_name(custom_alias_name=none, node=none) -%}
{% do return(adapter.dispatch('generate_alias_name', 'dbt')(custom_alias_name, node)) %}
{%- endmacro %}
{% macro default__generate_alias_name(custom_alias_name=none, node=none) -%}
{%- if custom_alias_name is none -%}

View File

@@ -14,7 +14,7 @@
#}
{% macro generate_database_name(custom_database_name=none, node=none) -%}
{% do return(adapter.dispatch('generate_database_name', 'dbt')(custom_database_name, node)) %}
{% do return(adapter.dispatch('generate_database_name')(custom_database_name, node)) %}
{%- endmacro %}
{% macro default__generate_database_name(custom_database_name=none, node=none) -%}

View File

@@ -15,10 +15,6 @@
#}
{% macro generate_schema_name(custom_schema_name, node) -%}
{{ return(adapter.dispatch('generate_schema_name', 'dbt')(custom_schema_name, node)) }}
{% endmacro %}
{% macro default__generate_schema_name(custom_schema_name, node) -%}
{%- set default_schema = target.schema -%}
{%- if custom_schema_name is none -%}

View File

@@ -1,15 +0,0 @@
{% macro get_where_subquery(relation) -%}
{% do return(adapter.dispatch('get_where_subquery')(relation)) %}
{%- endmacro %}
{% macro default__get_where_subquery(relation) -%}
{% set where = config.get('where', '') %}
{% if where %}
{%- set filtered -%}
(select * from {{ relation }} where {{ where }}) dbt_subquery
{%- endset -%}
{% do return(filtered) %}
{%- else -%}
{% do return(relation) %}
{%- endif -%}
{%- endmacro %}

View File

@@ -1,30 +0,0 @@
{% macro default__test_relationships(model, column_name, to, field) %}
with child as (
select {{ column_name }} as from_field
from {{ model }}
where {{ column_name }} is not null
),
parent as (
select {{ field }} as to_field
from {{ to }}
)
select
from_field
from child
left join parent
on child.from_field = parent.to_field
where parent.to_field is null
{% endmacro %}
{% test relationships(model, column_name, to, field) %}
{% set macro = adapter.dispatch('test_relationships', 'dbt') %}
{{ macro(model, column_name, to, field) }}
{% endtest %}

View File

@@ -1,18 +0,0 @@
{% macro default__test_unique(model, column_name) %}
select
{{ column_name }} as unique_field,
count(*) as n_records
from {{ model }}
where {{ column_name }} is not null
group by {{ column_name }}
having count(*) > 1
{% endmacro %}
{% test unique(model, column_name) %}
{% set macro = adapter.dispatch('test_unique', 'dbt') %}
{{ macro(model, column_name) }}
{% endtest %}

View File

@@ -1,17 +1,17 @@
{% macro get_merge_sql(target, source, unique_key, dest_columns, predicates=none) -%}
{{ adapter.dispatch('get_merge_sql', 'dbt')(target, source, unique_key, dest_columns, predicates) }}
{{ adapter.dispatch('get_merge_sql')(target, source, unique_key, dest_columns, predicates) }}
{%- endmacro %}
{% macro get_delete_insert_merge_sql(target, source, unique_key, dest_columns) -%}
{{ adapter.dispatch('get_delete_insert_merge_sql', 'dbt')(target, source, unique_key, dest_columns) }}
{{ adapter.dispatch('get_delete_insert_merge_sql')(target, source, unique_key, dest_columns) }}
{%- endmacro %}
{% macro get_insert_overwrite_merge_sql(target, source, dest_columns, predicates, include_sql_header=false) -%}
{{ adapter.dispatch('get_insert_overwrite_merge_sql', 'dbt')(target, source, dest_columns, predicates, include_sql_header) }}
{{ adapter.dispatch('get_insert_overwrite_merge_sql')(target, source, dest_columns, predicates, include_sql_header) }}
{%- endmacro %}

View File

@@ -1,6 +1,14 @@
{% macro create_csv_table(model, agate_table) -%}
{{ adapter.dispatch('create_csv_table', 'dbt')(model, agate_table) }}
{{ adapter.dispatch('create_csv_table')(model, agate_table) }}
{%- endmacro %}
{% macro reset_csv_table(model, full_refresh, old_relation, agate_table) -%}
{{ adapter.dispatch('reset_csv_table')(model, full_refresh, old_relation, agate_table) }}
{%- endmacro %}
{% macro load_csv_rows(model, agate_table) -%}
{{ adapter.dispatch('load_csv_rows')(model, agate_table) }}
{%- endmacro %}
{% macro default__create_csv_table(model, agate_table) %}
@@ -25,9 +33,6 @@
{{ return(sql) }}
{% endmacro %}
{% macro reset_csv_table(model, full_refresh, old_relation, agate_table) -%}
{{ adapter.dispatch('reset_csv_table', 'dbt')(model, full_refresh, old_relation, agate_table) }}
{%- endmacro %}
{% macro default__reset_csv_table(model, full_refresh, old_relation, agate_table) %}
{% set sql = "" %}
@@ -42,21 +47,6 @@
{{ return(sql) }}
{% endmacro %}
{% macro get_binding_char() -%}
{{ adapter.dispatch('get_binding_char', 'dbt')() }}
{%- endmacro %}
{% macro default__get_binding_char() %}
{{ return('%s') }}
{% endmacro %}
{% macro get_batch_size() -%}
{{ return(adapter.dispatch('get_batch_size', 'dbt')()) }}
{%- endmacro %}
{% macro default__get_batch_size() %}
{{ return(10000) }}
{% endmacro %}
{% macro get_seed_column_quoted_csv(model, column_names) %}
{%- set quote_seed_column = model['config'].get('quote_columns', None) -%}
@@ -69,48 +59,48 @@
{{ return(dest_cols_csv) }}
{% endmacro %}
{% macro load_csv_rows(model, agate_table) -%}
{{ adapter.dispatch('load_csv_rows', 'dbt')(model, agate_table) }}
{%- endmacro %}
{% macro basic_load_csv_rows(model, batch_size, agate_table) %}
{% set cols_sql = get_seed_column_quoted_csv(model, agate_table.column_names) %}
{% set bindings = [] %}
{% set statements = [] %}
{% for chunk in agate_table.rows | batch(batch_size) %}
{% set bindings = [] %}
{% for row in chunk %}
{% do bindings.extend(row) %}
{% endfor %}
{% set sql %}
insert into {{ this.render() }} ({{ cols_sql }}) values
{% for row in chunk -%}
({%- for column in agate_table.column_names -%}
%s
{%- if not loop.last%},{%- endif %}
{%- endfor -%})
{%- if not loop.last%},{%- endif %}
{%- endfor %}
{% endset %}
{% do adapter.add_query(sql, bindings=bindings, abridge_sql_log=True) %}
{% if loop.index0 == 0 %}
{% do statements.append(sql) %}
{% endif %}
{% endfor %}
{# Return SQL so we can render it out into the compiled files #}
{{ return(statements[0]) }}
{% endmacro %}
{% macro default__load_csv_rows(model, agate_table) %}
{% set batch_size = get_batch_size() %}
{% set cols_sql = get_seed_column_quoted_csv(model, agate_table.column_names) %}
{% set bindings = [] %}
{% set statements = [] %}
{% for chunk in agate_table.rows | batch(batch_size) %}
{% set bindings = [] %}
{% for row in chunk %}
{% do bindings.extend(row) %}
{% endfor %}
{% set sql %}
insert into {{ this.render() }} ({{ cols_sql }}) values
{% for row in chunk -%}
({%- for column in agate_table.column_names -%}
{{ get_binding_char() }}
{%- if not loop.last%},{%- endif %}
{%- endfor -%})
{%- if not loop.last%},{%- endif %}
{%- endfor %}
{% endset %}
{% do adapter.add_query(sql, bindings=bindings, abridge_sql_log=True) %}
{% if loop.index0 == 0 %}
{% do statements.append(sql) %}
{% endif %}
{% endfor %}
{# Return SQL so we can render it out into the compiled files #}
{{ return(statements[0]) }}
{{ return(basic_load_csv_rows(model, 10000, agate_table) )}}
{% endmacro %}
{% materialization seed, default %}
{%- set identifier = model['alias'] -%}

View File

@@ -2,7 +2,7 @@
Add new columns to the table if applicable
#}
{% macro create_columns(relation, columns) %}
{{ adapter.dispatch('create_columns', 'dbt')(relation, columns) }}
{{ adapter.dispatch('create_columns')(relation, columns) }}
{% endmacro %}
{% macro default__create_columns(relation, columns) %}
@@ -15,7 +15,7 @@
{% macro post_snapshot(staging_relation) %}
{{ adapter.dispatch('post_snapshot', 'dbt')(staging_relation) }}
{{ adapter.dispatch('post_snapshot')(staging_relation) }}
{% endmacro %}
{% macro default__post_snapshot(staging_relation) %}

View File

@@ -1,6 +1,6 @@
{% macro snapshot_merge_sql(target, source, insert_cols) -%}
{{ adapter.dispatch('snapshot_merge_sql', 'dbt')(target, source, insert_cols) }}
{{ adapter.dispatch('snapshot_merge_sql')(target, source, insert_cols) }}
{%- endmacro %}

View File

@@ -36,7 +36,7 @@
Create SCD Hash SQL fields cross-db
#}
{% macro snapshot_hash_arguments(args) -%}
{{ adapter.dispatch('snapshot_hash_arguments', 'dbt')(args) }}
{{ adapter.dispatch('snapshot_hash_arguments')(args) }}
{%- endmacro %}
@@ -52,7 +52,7 @@
Get the current time cross-db
#}
{% macro snapshot_get_time() -%}
{{ adapter.dispatch('snapshot_get_time', 'dbt')() }}
{{ adapter.dispatch('snapshot_get_time')() }}
{%- endmacro %}
{% macro default__snapshot_get_time() -%}
@@ -75,7 +75,7 @@
table instead of assuming that the user-supplied {{ updated_at }}
will be present in the historical data.
See https://github.com/dbt-labs/dbt-core/issues/2350
See https://github.com/fishtown-analytics/dbt/issues/2350
*/ #}
{% set row_changed_expr -%}
({{ snapshotted_rel }}.dbt_valid_from < {{ current_rel }}.{{ updated_at }})
@@ -94,7 +94,7 @@
{% macro snapshot_string_as_time(timestamp) -%}
{{ adapter.dispatch('snapshot_string_as_time', 'dbt')(timestamp) }}
{{ adapter.dispatch('snapshot_string_as_time')(timestamp) }}
{%- endmacro %}

View File

@@ -1,5 +1,5 @@
{% macro get_test_sql(main_sql, fail_calc, warn_if, error_if, limit) -%}
{{ adapter.dispatch('get_test_sql', 'dbt')(main_sql, fail_calc, warn_if, error_if, limit) }}
{{ adapter.dispatch('get_test_sql')(main_sql, fail_calc, warn_if, error_if, limit) }}
{%- endmacro %}

View File

@@ -1,6 +1,6 @@
{% macro handle_existing_table(full_refresh, old_relation) %}
{{ adapter.dispatch('handle_existing_table', 'dbt')(full_refresh, old_relation) }}
{{ adapter.dispatch('handle_existing_table', macro_namespace = 'dbt')(full_refresh, old_relation) }}
{% endmacro %}
{% macro default__handle_existing_table(full_refresh, old_relation) %}

View File

@@ -7,7 +7,7 @@ with all_values as (
count(*) as n_records
from {{ model }}
group by {{ column_name }}
group by 1
)
@@ -28,6 +28,6 @@ where value_field not in (
{% test accepted_values(model, column_name, values, quote=True) %}
{% set macro = adapter.dispatch('test_accepted_values', 'dbt') %}
{% set macro = adapter.dispatch('test_accepted_values') %}
{{ macro(model, column_name, values, quote) }}
{% endtest %}

View File

@@ -8,6 +8,6 @@ where {{ column_name }} is null
{% test not_null(model, column_name) %}
{% set macro = adapter.dispatch('test_not_null', 'dbt') %}
{% set macro = adapter.dispatch('test_not_null') %}
{{ macro(model, column_name) }}
{% endtest %}

View File

@@ -0,0 +1,28 @@
{% macro default__test_relationships(model, column_name, to, field) %}
with child as (
select * from {{ model }}
where {{ column_name }} is not null
),
parent as (
select * from {{ to }}
)
select
child.{{ column_name }}
from child
left join parent
on child.{{ column_name }} = parent.{{ field }}
where parent.{{ field }} is null
{% endmacro %}
{% test relationships(model, column_name, to, field) %}
{% set macro = adapter.dispatch('test_relationships') %}
{{ macro(model, column_name, to, field) }}
{% endtest %}

View File

@@ -0,0 +1,18 @@
{% macro default__test_unique(model, column_name) %}
select
{{ column_name }},
count(*) as n_records
from {{ model }}
where {{ column_name }} is not null
group by {{ column_name }}
having count(*) > 1
{% endmacro %}
{% test unique(model, column_name) %}
{% set macro = adapter.dispatch('test_unique') %}
{{ macro(model, column_name) }}
{% endtest %}

View File

@@ -1,4 +1,4 @@
target/
dbt_packages/
dbt_modules/
logs/

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