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
5436 changed files with 38612 additions and 99046 deletions

View File

@@ -1,5 +1,5 @@
[bumpversion]
current_version = 1.0.1
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

43
.github/CODEOWNERS vendored
View File

@@ -1,43 +0,0 @@
# This file contains the code owners for the dbt-core repo.
# PRs will be automatically assigned for review to the associated
# team(s) or person(s) that touches any files that are mapped to them.
#
# A statement takes precedence over the statements above it so more general
# assignments are found at the top with specific assignments being lower in
# the ordering (i.e. catch all assignment should be the first item)
#
# Consult GitHub documentation for formatting guidelines:
# https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners#example-of-a-codeowners-file
# As a default for areas with no assignment,
# the core team as a whole will be assigned
* @dbt-labs/core
# Changes to GitHub configurations including Actions
/.github/ @leahwicz
# Language core modules
/core/dbt/config/ @dbt-labs/core-language
/core/dbt/context/ @dbt-labs/core-language
/core/dbt/contracts/ @dbt-labs/core-language
/core/dbt/deps/ @dbt-labs/core-language
/core/dbt/parser/ @dbt-labs/core-language
# Execution core modules
/core/dbt/events/ @dbt-labs/core-execution @dbt-labs/core-language # eventually remove language but they have knowledge here now
/core/dbt/graph/ @dbt-labs/core-execution
/core/dbt/task/ @dbt-labs/core-execution
# Adapter interface, scaffold, Postgres plugin
/core/dbt/adapters @dbt-labs/core-adapters
/core/scripts/create_adapter_plugin.py @dbt-labs/core-adapters
/plugins/ @dbt-labs/core-adapters
# Global project: default macros, including generic tests + materializations
/core/dbt/include/global_project @dbt-labs/core-execution @dbt-labs/core-adapters
# Perf regression testing framework
# This excludes the test project files itself since those aren't specific
# framework changes (excluded by not setting an owner next to it- no owner)
/performance @nathaniel-may
/performance/projects

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 = ["3.7", "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

@@ -1,34 +0,0 @@
# **what?**
# When a PR is merged, if it has the backport label, it will create
# a new PR to backport those changes to the given branch. If it can't
# cleanly do a backport, it will comment on the merged PR of the failure.
#
# Label naming convention: "backport <branch name to backport to>"
# Example: backport 1.0.latest
#
# You MUST "Squash and merge" the original PR or this won't work.
# **why?**
# Changes sometimes need to be backported to release branches.
# This automates the backporting process
# **when?**
# Once a PR is "Squash and merge"'d and it has been correctly labeled
# according to the naming convention.
name: Backport
on:
pull_request:
types:
- closed
- labeled
jobs:
backport:
runs-on: ubuntu-18.04
name: Backport
steps:
- name: Backport
uses: tibdex/backport@v1.1.1
with:
github_token: ${{ secrets.GITHUB_TOKEN }}

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

@@ -1,26 +0,0 @@
# **what?**
# Mirrors issues into Jira. Includes the information: title,
# GitHub Issue ID and URL
# **why?**
# Jira is our tool for tracking and we need to see these issues in there
# **when?**
# On issue creation or when an issue is labeled `Jira`
name: Jira Issue Creation
on:
issues:
types: [opened, labeled]
permissions:
issues: write
jobs:
call-label-action:
uses: dbt-labs/jira-actions/.github/workflows/jira-creation.yml@main
secrets:
JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}

View File

@@ -1,27 +0,0 @@
# **what?**
# Calls mirroring Jira label Action. Includes adding a new label
# to an existing issue or removing a label as well
# **why?**
# Jira is our tool for tracking and we need to see these labels in there
# **when?**
# On labels being added or removed from issues
name: Jira Label Mirroring
on:
issues:
types: [labeled, unlabeled]
permissions:
issues: read
jobs:
call-label-action:
uses: dbt-labs/jira-actions/.github/workflows/jira-label.yml@main
secrets:
JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}

View File

@@ -1,24 +0,0 @@
# **what?**
# Transition a Jira issue to a new state
# Only supports these GitHub Issue transitions:
# closed, deleted, reopened
# **why?**
# Jira needs to be kept up-to-date
# **when?**
# On issue closing, deletion, reopened
name: Jira Issue Transition
on:
issues:
types: [closed, deleted, reopened]
jobs:
call-label-action:
uses: dbt-labs/jira-actions/.github/workflows/jira-transition.yml@main
secrets:
JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}

View File

@@ -1,207 +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: [3.7, 3.8, 3.9]
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: [3.7, 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
# ignore dbt-1.0.0, which intentionally raises an error when installed from source
run: |
find ./dist/dbt-[a-z]*.gz -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
- 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

@@ -1,200 +0,0 @@
# **what?**
# Take the given commit, run unit tests specifically on that sha, build and
# package it, and then release to GitHub and PyPi with that specific build
# **why?**
# Ensure an automated and tested release process
# **when?**
# This will only run manually with a given sha and version
name: Release to GitHub and PyPi
on:
workflow_dispatch:
inputs:
sha:
description: 'The last commit sha in the release'
required: true
version_number:
description: 'The release version number (i.e. 1.0.0b1)'
required: true
defaults:
run:
shell: bash
jobs:
unit:
name: Unit test
runs-on: ubuntu-latest
env:
TOXENV: "unit"
steps:
- name: Check out the repository
uses: actions/checkout@v2
with:
persist-credentials: false
ref: ${{ github.event.inputs.sha }}
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Install python dependencies
run: |
pip install --user --upgrade pip
pip install tox
pip --version
tox --version
- name: Run tox
run: tox
build:
name: build packages
runs-on: ubuntu-latest
steps:
- name: Check out the repository
uses: actions/checkout@v2
with:
persist-credentials: false
ref: ${{ github.event.inputs.sha }}
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Install python dependencies
run: |
pip install --user --upgrade pip
pip install --upgrade setuptools wheel twine check-wheel-contents
pip --version
- name: Build distributions
run: ./scripts/build-dist.sh
- name: Show distributions
run: ls -lh dist/
- name: Check distribution descriptions
run: |
twine check dist/*
- name: Check wheel contents
run: |
check-wheel-contents dist/*.whl --ignore W007,W008
- uses: actions/upload-artifact@v2
with:
name: dist
path: |
dist/
!dist/dbt-${{github.event.inputs.version_number}}.tar.gz
test-build:
name: verify packages
needs: [build, unit]
runs-on: ubuntu-latest
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8
- name: Install python dependencies
run: |
pip install --user --upgrade pip
pip install --upgrade wheel
pip --version
- uses: actions/download-artifact@v2
with:
name: dist
path: dist/
- name: Show distributions
run: ls -lh dist/
- name: Install wheel distributions
run: |
find ./dist/*.whl -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
- name: Check wheel distributions
run: |
dbt --version
- name: Install source distributions
run: |
find ./dist/*.gz -maxdepth 1 -type f | xargs pip install --force-reinstall --find-links=dist/
- name: Check source distributions
run: |
dbt --version
github-release:
name: GitHub Release
needs: test-build
runs-on: ubuntu-latest
steps:
- uses: actions/download-artifact@v2
with:
name: dist
path: '.'
# Need to set an output variable because env variables can't be taken as input
# This is needed for the next step with releasing to GitHub
- name: Find release type
id: release_type
env:
IS_PRERELEASE: ${{ contains(github.event.inputs.version_number, 'rc') || contains(github.event.inputs.version_number, 'b') }}
run: |
echo ::set-output name=isPrerelease::$IS_PRERELEASE
- name: Creating GitHub Release
uses: softprops/action-gh-release@v1
with:
name: dbt-core v${{github.event.inputs.version_number}}
tag_name: v${{github.event.inputs.version_number}}
prerelease: ${{ steps.release_type.outputs.isPrerelease }}
target_commitish: ${{github.event.inputs.sha}}
body: |
[Release notes](https://github.com/dbt-labs/dbt-core/blob/main/CHANGELOG.md)
files: |
dbt_postgres-${{github.event.inputs.version_number}}-py3-none-any.whl
dbt_core-${{github.event.inputs.version_number}}-py3-none-any.whl
dbt-postgres-${{github.event.inputs.version_number}}.tar.gz
dbt-core-${{github.event.inputs.version_number}}.tar.gz
pypi-release:
name: Pypi release
runs-on: ubuntu-latest
needs: github-release
environment: PypiProd
steps:
- uses: actions/download-artifact@v2
with:
name: dist
path: 'dist'
- name: Publish distribution to PyPI
uses: pypa/gh-action-pypi-publish@v1.4.2
with:
password: ${{ secrets.PYPI_API_TOKEN }}

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"

View File

@@ -1,71 +0,0 @@
# This Action checks makes a dbt run to sample json structured logs
# and checks that they conform to the currently documented schema.
#
# If this action fails it either means we have unintentionally deviated
# from our documented structured logging schema, or we need to bump the
# version of our structured logging and add new documentation to
# communicate these changes.
name: Structured Logging Schema Check
on:
push:
branches:
- "main"
- "*.latest"
- "releases/*"
pull_request:
workflow_dispatch:
permissions: read-all
jobs:
# run the performance measurements on the current or default branch
test-schema:
name: Test Log Schema
runs-on: ubuntu-latest
env:
# turns warnings into errors
RUSTFLAGS: "-D warnings"
# points tests to the log file
LOG_DIR: "/home/runner/work/dbt-core/dbt-core/logs"
# tells integration tests to output into json format
DBT_LOG_FORMAT: 'json'
steps:
- name: checkout dev
uses: actions/checkout@v2
with:
persist-credentials: false
- name: Setup Python
uses: actions/setup-python@v2.2.2
with:
python-version: "3.8"
- uses: actions-rs/toolchain@v1
with:
profile: minimal
toolchain: stable
override: true
- name: install dbt
run: pip install -r dev-requirements.txt -r editable-requirements.txt
- name: Set up postgres
uses: ./.github/actions/setup-postgres-linux
- name: ls
run: ls
# integration tests generate a ton of logs in different files. the next step will find them all.
# we actually care if these pass, because the normal test run doesn't usually include many json log outputs
- name: Run integration tests
run: tox -e py38-postgres -- -nauto
# apply our schema tests to every log event from the previous step
# skips any output that isn't valid json
- uses: actions-rs/cargo@v1
with:
command: run
args: --manifest-path test/interop/log_parsing/Cargo.toml

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

@@ -1,33 +1,34 @@
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/README.md): Define base classes for behavior that is likely to differ across databases
- [`clients`](core/dbt/clients/README.md): Interface with dependencies (agate, jinja) or across operating systems
- [`config`](core/dbt/config/README.md): Reconcile user-supplied configuration from connection profiles, project files, and Jinja macros
- [`context`](core/dbt/context/README.md): Build and expose dbt-specific Jinja functionality
- [`contracts`](core/dbt/contracts/README.md): Define Python objects (dataclasses) that dbt expects to create and validate
- [`deps`](core/dbt/deps/README.md): Package installation and dependency resolution
- [`events`](core/dbt/events/README.md): Logging events
- [`graph`](core/dbt/graph/README.md): Produce a `networkx` DAG of project resources, and selecting those resources given user-supplied criteria
- [`include`](core/dbt/include/README.md): The dbt "global project," which defines default implementations of Jinja2 macros
- [`parser`](core/dbt/parser/README.md): Read project files, validate, construct python objects
- [`task`](core/dbt/task/README.md): Set forth the actions that dbt can perform when invoked
- [`adapters`](core/dbt/adapters): Define base classes for behavior that is likely to differ across databases
- [`clients`](core/dbt/clients): Interface with dependencies (agate, jinja) or across operating systems
- [`config`](core/dbt/config): Reconcile user-supplied configuration from connection profiles, project files, and Jinja macros
- [`context`](core/dbt/context): Build and expose dbt-specific Jinja functionality
- [`contracts`](core/dbt/contracts): Define Python objects (dataclasses) that dbt expects to create and validate
- [`deps`](core/dbt/deps): Package installation and dependency resolution
- [`graph`](core/dbt/graph): Produce a `networkx` DAG of project resources, and selecting those resources given user-supplied criteria
- [`include`](core/dbt/include): The dbt "global project," which defines default implementations of Jinja2 macros
- [`parser`](core/dbt/parser): Read project files, validate, construct python objects
- [`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:
@@ -45,4 +46,4 @@ The [`test/`](test/) subdirectory includes unit and integration tests that run a
- [docker](docker/): All dbt versions are published as Docker images on DockerHub. This subfolder contains the `Dockerfile` (constant) and `requirements.txt` (one for each version).
- [etc](etc/): Images for README
- [scripts](scripts/): Helper scripts for testing, releasing, and producing JSON schemas. These are not included in distributions of dbt, nor are they rigorously tested—they're just handy tools for the dbt maintainers :)
- [scripts](scripts/): Helper scripts for testing, releasing, and producing JSON schemas. These are not included in distributions of dbt, not are they rigorously tested—they're just handy tools for the dbt maintainers :)

File diff suppressed because it is too large Load Diff

View File

@@ -10,111 +10,107 @@
## About this document
This document is a guide intended for folks interested in contributing to `dbt-core`. Below, we document the process by which members of the community should create issues and submit pull requests (PRs) in this repository. It is not intended as a guide for using `dbt-core`, and it assumes a certain level of familiarity with Python concepts such as virtualenvs, `pip`, python modules, filesystems, and so on. This guide assumes you are using macOS or Linux and are comfortable with the command line.
This document is a guide intended for folks interested in contributing to `dbt`. Below, we document the process by which members of the community should create issues and submit pull requests (PRs) in this repository. It is not intended as a guide for using `dbt`, and it assumes a certain level of familiarity with Python concepts such as virtualenvs, `pip`, python modules, filesystems, and so on. This guide assumes you are using macOS or Linux and are comfortable with the command line.
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-core` must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements) to have their Pull Request merged into the `dbt-core` codebase. If you are unable to sign the CLA, then the `dbt-core` maintainers will unfortunately be unable to merge your Pull Request. You are, however, welcome to open issues and comment on existing ones.
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.
## Proposing a change
`dbt-core` is Apache 2.0-licensed open source software. `dbt-core` is what it is today because community members like you have opened issues, provided feedback, and contributed to the knowledge loop for the entire communtiy. Whether you are a seasoned open source contributor or a first-time committer, we welcome and encourage you to contribute code, documentation, ideas, or problem statements to this project.
`dbt` is Apache 2.0-licensed open source software. `dbt` is what it is today because community members like you have opened issues, provided feedback, and contributed to the knowledge loop for the entire communtiy. Whether you are a seasoned open source contributor or a first-time committer, we welcome and encourage you to contribute code, documentation, ideas, or problem statements to this project.
### Defining the problem
If you have an idea for a new feature or if you've discovered a bug in `dbt-core`, the first step is to open an issue. Please check the list of [open issues](https://github.com/dbt-labs/dbt-core/issues) before creating a new one. If you find a relevant issue, please add a comment to the open issue instead of creating a new one. There are hundreds of open issues in this repository and it can be hard to know where to look for a relevant open issue. **The `dbt-core` maintainers are always happy to point contributors in the right direction**, so please err on the side of documenting your idea in a new issue if you are unsure where a problem statement belongs.
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.
### Discussing the idea
After you open an issue, a `dbt-core` maintainer will follow up by commenting on your issue (usually within 1-3 days) to explore your idea further and advise on how to implement the suggested changes. In many cases, community members will chime in with their own thoughts on the problem statement. If you as the issue creator are interested in submitting a Pull Request to address the issue, you should indicate this in the body of the issue. The `dbt-core` maintainers are _always_ happy to help contributors with the implementation of fixes and features, so please also indicate if there's anything you're unsure about or could use guidance around in the issue.
After you open an issue, a `dbt` maintainer will follow up by commenting on your issue (usually within 1-3 days) to explore your idea further and advise on how to implement the suggested changes. In many cases, community members will chime in with their own thoughts on the problem statement. If you as the issue creator are interested in submitting a Pull Request to address the issue, you should indicate this in the body of the issue. The `dbt` maintainers are _always_ happy to help contributors with the implementation of fixes and features, so please also indicate if there's anything you're unsure about or could use guidance around in the issue.
### Submitting a change
If an issue is appropriately well scoped and describes a beneficial change to the `dbt-core` codebase, then anyone may submit a Pull Request to implement the functionality described in the issue. See the sections below on how to do this.
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-core` maintainers will add a `good first issue` label if an issue is suitable for a first-time contributor. This label often means that the required code change is small, limited to one database adapter, or a net-new addition that does not impact existing functionality. You can see the list of currently open issues on the [Contribute](https://github.com/dbt-labs/dbt-core/contribute) page.
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
- Outline your planned implementation. If you want help getting started, ask!
- Follow the steps outlined below to develop locally. Once you have opened a PR, one of the `dbt-core` maintainers will work with you to review your code.
- Add a test! Tests are crucial for both fixes and new features alike. We want to make sure that code works as intended, and that it avoids any bugs previously encountered. Currently, the best resource for understanding `dbt-core`'s [unit](test/unit) and [integration](test/integration) tests is the tests themselves. One of the maintainers can help by pointing out relevant examples.
- Follow the steps outlined below to develop locally. Once you have opened a PR, one of the `dbt` maintainers will work with you to review your code.
- Add a test! Tests are crucial for both fixes and new features alike. We want to make sure that code works as intended, and that it avoids any bugs previously encountered. Currently, the best resource for understanding `dbt`'s [unit](test/unit) and [integration](test/integration) tests is the tests themselves. One of the maintainers can help by pointing out relevant examples.
In some cases, the right resolution to an open issue might be tangential to the `dbt-core` codebase. The right path forward might be a documentation update or a change that can be made in user-space. In other cases, the issue might describe functionality that the `dbt-core` maintainers are unwilling or unable to incorporate into the `dbt-core` codebase. When it is determined that an open issue describes functionality that will not translate to a code change in the `dbt-core` repository, the issue will be tagged with the `wontfix` label (see below) and closed.
In some cases, the right resolution to an open issue might be tangential to the `dbt` codebase. The right path forward might be a documentation update or a change that can be made in user-space. In other cases, the issue might describe functionality that the `dbt` maintainers are unwilling or unable to incorporate into the `dbt` codebase. When it is determined that an open issue describes functionality that will not translate to a code change in the `dbt` repository, the issue will be tagged with the `wontfix` label (see below) and closed.
### Using issue labels
The `dbt-core` maintainers use labels to categorize open issues. Most labels describe the domain in the `dbt-core` codebase germane to the discussion.
The `dbt` maintainers use labels to categorize open issues. Some labels indicate the databases impacted by the issue, while others describe the domain in the `dbt` codebase germane to the discussion. While most of these labels are self-explanatory (eg. `snowflake` or `bigquery`), there are others that are worth describing.
| tag | description |
| --- | ----------- |
| [triage](https://github.com/dbt-labs/dbt-core/labels/triage) | This is a new issue which has not yet been reviewed by a `dbt-core` maintainer. This label is removed when a maintainer reviews and responds to the issue. |
| [bug](https://github.com/dbt-labs/dbt-core/labels/bug) | This issue represents a defect or regression in `dbt-core` |
| [enhancement](https://github.com/dbt-labs/dbt-core/labels/enhancement) | This issue represents net-new functionality in `dbt-core` |
| [good first issue](https://github.com/dbt-labs/dbt-core/labels/good%20first%20issue) | This issue does not require deep knowledge of the `dbt-core` codebase to implement. This issue is appropriate for a first-time contributor. |
| [help wanted](https://github.com/dbt-labs/dbt-core/labels/help%20wanted) / [discussion](https://github.com/dbt-labs/dbt-core/labels/discussion) | Conversation around this issue in ongoing, and there isn't yet a clear path forward. Input from community members is most welcome. |
| [duplicate](https://github.com/dbt-labs/dbt-core/issues/duplicate) | This issue is functionally identical to another open issue. The `dbt-core` maintainers will close this issue and encourage community members to focus conversation on the other one. |
| [snoozed](https://github.com/dbt-labs/dbt-core/labels/snoozed) | This issue describes a good idea, but one which will probably not be addressed in a six-month time horizon. The `dbt-core` maintainers will revist these issues periodically and re-prioritize them accordingly. |
| [stale](https://github.com/dbt-labs/dbt-core/labels/stale) | This is an old issue which has not recently been updated. Stale issues will periodically be closed by `dbt-core` maintainers, but they can be re-opened if the discussion is restarted. |
| [wontfix](https://github.com/dbt-labs/dbt-core/labels/wontfix) | This issue does not require a code change in the `dbt-core` repository, or the maintainers are unwilling/unable to merge a Pull Request which implements the behavior described in the issue. |
| [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
`dbt-core` has three types of branches:
`dbt` has three types of branches:
- **Trunks** are where active development of the next release takes place. There is one trunk named `main` at the time of writing this, and will be the default branch of the repository.
- **Release Branches** track a specific, not yet complete release of `dbt-core`. Each minor version release has a corresponding release branch. For example, the `0.11.x` series of releases has a branch called `0.11.latest`. This allows us to release new patch versions under `0.11` without necessarily needing to pull them into the latest version of `dbt-core`.
- **Feature Branches** track individual features and fixes. On completion they should be merged into the trunk branch or a specific release branch.
- **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 brnach or a specific release branch.
## Getting the code
### Installing git
You will need `git` in order to download and modify the `dbt-core` source code. On macOS, the best way to download git is to just install [Xcode](https://developer.apple.com/support/xcode/).
You will need `git` in order to download and modify the `dbt` source code. On macOS, the best way to download git is to just install [Xcode](https://developer.apple.com/support/xcode/).
### External contributors
If you are not a member of the `dbt-labs` GitHub organization, you can contribute to `dbt-core` by forking the `dbt-core` repository. For a detailed overview on forking, check out the [GitHub docs on forking](https://help.github.com/en/articles/fork-a-repo). In short, you will need to:
If you are not a member of the `dbt-labs` GitHub organization, you can contribute to `dbt` by forking the `dbt` repository. For a detailed overview on forking, check out the [GitHub docs on forking](https://help.github.com/en/articles/fork-a-repo). In short, you will need to:
1. fork the `dbt-core` repository
1. fork the `dbt` repository
2. clone your fork locally
3. check out a new branch for your proposed changes
4. push changes to your fork
5. open a pull request against `dbt-labs/dbt` from your forked repository
### dbt Labs contributors
### Core contributors
If you are a member of the `dbt-labs` GitHub organization, you will have push access to the `dbt-core` repo. Rather than forking `dbt-core` to make your changes, just clone the repository, check out a new branch, and push directly to that branch.
If you are a member of the `dbt-labs` GitHub organization, you will have push access to the `dbt` repo. Rather than forking `dbt` to make your changes, just clone the repository, check out a new branch, and push directly to that branch.
## Setting up an environment
There are some tools that will be helpful to you in developing locally. While this is the list relevant for `dbt-core` development, many of these tools are used commonly across open-source python projects.
There are some tools that will be helpful to you in developing locally. While this is the list relevant for `dbt` development, many of these tools are used commonly across open-source python projects.
### Tools
A short list of tools used in `dbt-core` testing that will be helpful to your understanding:
A short list of tools used in `dbt` testing that will be helpful to your understanding:
- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, Python 3.8, and Python 3.9
- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.6, Python 3.7, Python 3.8, and Python 3.9
- [`pytest`](https://docs.pytest.org/en/latest/) to discover/run tests
- [`make`](https://users.cs.duke.edu/~ola/courses/programming/Makefiles/Makefiles.html) - but don't worry too much, nobody _really_ understands how make works and our Makefile is super simple
- [`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-core`, but we recommend checking out the attached documentation if you're interested in learning more about them.
A deep understanding of these tools in not required to effectively contribute to `dbt`, but we recommend checking out the attached documentation if you're interested in learning more about them.
#### virtual environments
We strongly recommend using virtual environments when developing code in `dbt-core`. We recommend creating this virtualenv
in the root of the `dbt-core` repository. To create a new virtualenv, run:
We strongly recommend using virtual environments when developing code in `dbt`. We recommend creating this virtualenv
in the root of the `dbt` repository. To create a new virtualenv, run:
```sh
python3 -m venv env
source env/bin/activate
@@ -135,11 +131,11 @@ For testing, and later in the examples in this document, you may want to have `p
brew install postgresql
```
## Running `dbt-core` in development
## Running `dbt` in development
### Installation
First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment). Also ensure you have the latest version of pip installed with `pip install --upgrade pip`. Next, install `dbt-core` (and its dependencies) with:
First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment). Next, install `dbt` (and its dependencies) with:
```sh
make dev
@@ -147,24 +143,23 @@ make dev
pip install -r dev-requirements.txt -r editable-requirements.txt
```
When `dbt-core` is installed this way, any changes you make to the `dbt-core` source code will be reflected immediately in your next `dbt-core` run.
When `dbt` is installed this way, any changes you make to the `dbt` source code will be reflected immediately in your next `dbt` run.
### Running `dbt`
### Running `dbt-core`
With your virtualenv activated, the `dbt-core` script should point back to the source code you've cloned on your machine. You can verify this by running `which dbt`. This command should show you a path to an executable in your virtualenv.
With your virtualenv activated, the `dbt` script should point back to the source code you've cloned on your machine. You can verify this by running `which dbt`. This command should show you a path to an executable in your virtualenv.
Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as necessary to connect to your target databases. It may be a good idea to add a new profile pointing to a local postgres instance, or a specific test sandbox within your data warehouse if appropriate.
## Testing
Getting the `dbt-core` integration tests set up in your local environment will be very helpful as you start to make changes to your local version of `dbt-core`. The section that follows outlines some helpful tips for setting up the test environment.
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-core` works with a number of different databases, you won't need to supply credentials for every one of these databases in your test environment. Instead you can test all dbt-core code changes with Python and Postgres.
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
We recommend starting with `dbt-core`'s Postgres tests. These tests cover most of the functionality in `dbt-core`, are the fastest to run, and are the easiest to set up. To run the Postgres integration tests, you'll have to do one extra step of setting up the test database:
We recommend starting with `dbt`'s Postgres tests. These tests cover most of the functionality in `dbt`, are the fastest to run, and are the easiest to set up. To run the Postgres integration tests, you'll have to do one extra step of setting up the test database:
```sh
make setup-db
@@ -175,6 +170,15 @@ docker-compose up -d database
PGHOST=localhost PGUSER=root PGPASSWORD=password PGDATABASE=postgres bash test/setup_db.sh
```
`dbt` uses test credentials specified in a `test.env` file in the root of the repository for non-Postgres databases. This `test.env` file is git-ignored, but please be _extra_ careful to never check in credentials or other sensitive information when developing against `dbt`. To create your `test.env` file, copy the provided sample file, then supply your relevant credentials. This step is only required to use non-Postgres databases.
```
cp test.env.sample test.env
$EDITOR test.env
```
> In general, it's most important to have successful unit and Postgres tests. Once you open a PR, `dbt` will automatically run integration tests for the other three core database adapters. Of course, if you are a BigQuery user, contributing a BigQuery-only feature, it's important to run BigQuery tests as well.
### Test commands
There are a few methods for running tests locally.
@@ -200,9 +204,9 @@ suites.
[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run
tests. You can also run tests in parallel, for example, you can run unit tests
for Python 3.7, Python 3.8, Python 3.9, `flake8` checks, and `mypy` checks in
for Python 3.6, Python 3.7, Python 3.8, `flake8` checks, and `mypy` checks in
parallel with `tox -p`. Also, you can run unit tests for specific python versions
with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
with `tox -e py36`. The configuration for these tests in located in `tox.ini`.
#### `pytest`
@@ -220,10 +224,8 @@ 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-core` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
- First time contributors should note code checks + unit tests require a maintainer to approve.
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.
Once all tests are passing and your PR has been approved, a `dbt-core` maintainer will merge your changes into the active development branch. And that's it! Happy developing :tada:
Once all tests are passing and your PR has been approved, a `dbt` maintainer will merge your changes into the active development branch. And that's it! Happy developing :tada:

View File

@@ -1,9 +1,4 @@
##
# This dockerfile is used for local development and adapter testing only.
# See `/docker` for a generic and production-ready docker file
##
FROM ubuntu:20.04
FROM ubuntu:18.04
ENV DEBIAN_FRONTEND noninteractive
@@ -32,7 +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

@@ -1,42 +0,0 @@
<p align="center">
<img src="https://raw.githubusercontent.com/dbt-labs/dbt-core/fa1ea14ddfb1d5ae319d5141844910dd53ab2834/etc/dbt-core.svg" alt="dbt logo" width="750"/>
</p>
<p align="center">
<a href="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml">
<img src="https://github.com/dbt-labs/dbt-core/actions/workflows/main.yml/badge.svg?event=push" alt="Unit Tests Badge"/>
</a>
<a href="https://github.com/dbt-labs/dbt-core/actions/workflows/integration.yml">
<img src="https://github.com/dbt-labs/dbt-core/actions/workflows/integration.yml/badge.svg?event=push" alt="Integration Tests Badge"/>
</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)
## Understanding dbt
Analysts using dbt can transform their data by simply writing select statements, while dbt handles turning these statements into tables and views in a data warehouse.
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)
## Getting started
- [Install dbt](https://docs.getdbt.com/docs/installation)
- Read the [introduction](https://docs.getdbt.com/docs/introduction/) and [viewpoint](https://docs.getdbt.com/docs/about/viewpoint/)
## Join the dbt Community
- Be part of the conversation in the [dbt Community Slack](http://community.getdbt.com/)
- Read more on the [dbt Community Discourse](https://discourse.getdbt.com)
## 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)
## Code of Conduct
Everyone interacting in the dbt project's codebases, issue trackers, chat rooms, and mailing lists is expected to follow the [dbt Code of Conduct](https://community.getdbt.com/code-of-conduct).

View File

@@ -1,52 +0,0 @@
# core/dbt directory README
## The following are individual files in this directory.
### deprecations.py
### flags.py
### main.py
### tracking.py
### version.py
### lib.py
### node_types.py
### helper_types.py
### links.py
### semver.py
### ui.py
### compilation.py
### dataclass_schema.py
### exceptions.py
### hooks.py
### logger.py
### profiler.py
### utils.py
## The subdirectories will be documented in a README in the subdirectory
* config
* include
* adapters
* context
* deps
* graph
* task
* clients
* events

View File

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

View File

@@ -18,17 +18,7 @@ from dbt.contracts.graph.manifest import Manifest
from dbt.adapters.base.query_headers import (
MacroQueryStringSetter,
)
from dbt.events.functions import fire_event
from dbt.events.types import (
NewConnection,
ConnectionReused,
ConnectionLeftOpen,
ConnectionLeftOpen2,
ConnectionClosed,
ConnectionClosed2,
Rollback,
RollbackFailed
)
from dbt.logger import GLOBAL_LOGGER as logger
from dbt import flags
@@ -146,10 +136,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
if conn.name == conn_name and conn.state == 'open':
return conn
fire_event(NewConnection(conn_name=conn_name, conn_type=self.TYPE))
logger.debug(
'Acquiring new {} connection "{}".'.format(self.TYPE, conn_name))
if conn.state == 'open':
fire_event(ConnectionReused(conn_name=conn_name))
logger.debug(
'Re-using an available connection from the pool (formerly {}).'
.format(conn.name)
)
else:
conn.handle = LazyHandle(self.open)
@@ -196,9 +190,11 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
with self.lock:
for connection in self.thread_connections.values():
if connection.state not in {'closed', 'init'}:
fire_event(ConnectionLeftOpen(conn_name=connection.name))
logger.debug("Connection '{}' was left open."
.format(connection.name))
else:
fire_event(ConnectionClosed(conn_name=connection.name))
logger.debug("Connection '{}' was properly closed."
.format(connection.name))
self.close(connection)
# garbage collect these connections
@@ -224,40 +220,55 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
try:
connection.handle.rollback()
except Exception:
fire_event(RollbackFailed(conn_name=connection.name))
logger.debug(
'Failed to rollback {}'.format(connection.name),
exc_info=True
)
@classmethod
def _close_handle(cls, connection: Connection) -> None:
"""Perform the actual close operation."""
# On windows, sometimes connection handles don't have a close() attr.
if hasattr(connection.handle, 'close'):
fire_event(ConnectionClosed2(conn_name=connection.name))
logger.debug(f'On {connection.name}: Close')
connection.handle.close()
else:
fire_event(ConnectionLeftOpen2(conn_name=connection.name))
logger.debug(f'On {connection.name}: No close available on handle')
@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 '
f'"{connection.name}", but it does not have one open!'
)
fire_event(Rollback(conn_name=connection.name))
logger.debug(f'On {connection.name}: ROLLBACK')
cls._rollback_handle(connection)
connection.transaction_open = False
@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
if connection.transaction_open and connection.handle:
fire_event(Rollback(conn_name=connection.name))
logger.debug('On {}: ROLLBACK'.format(connection.name))
cls._rollback_handle(connection)
connection.transaction_open = False

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,
@@ -29,8 +31,8 @@ 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.events.functions import fire_event
from dbt.events.types import CacheMiss, ListRelations
from dbt.node_types import NodeType
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.utils import filter_null_values, executor
from dbt.adapters.base.connections import Connection, AdapterResponse
@@ -39,7 +41,7 @@ from dbt.adapters.base.relation import (
ComponentName, BaseRelation, InformationSchema, SchemaSearchMap
)
from dbt.adapters.base import Column as BaseColumn
from dbt.adapters.cache import RelationsCache, _make_key
from dbt.adapters.cache import RelationsCache
SeedModel = Union[ParsedSeedNode, CompiledSeedNode]
@@ -288,13 +290,12 @@ 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:
fire_event(
CacheMiss(
conn_name=self.nice_connection_name(),
database=database,
schema=schema
)
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)
)
return False
else:
@@ -309,7 +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
)
}
@@ -324,9 +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:
@@ -342,6 +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]]] = []
@@ -374,6 +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()
@@ -387,7 +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 ''
@@ -401,7 +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
@@ -422,7 +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 ''
###
@@ -676,12 +685,9 @@ class BaseAdapter(metaclass=AdapterMeta):
relations = self.list_relations_without_caching(
schema_relation
)
fire_event(ListRelations(
database=database,
schema=schema,
relations=[_make_key(x) for x in relations]
))
logger.debug('with database={}, schema={}, relations={}'
.format(database, schema, relations))
return relations
def _make_match_kwargs(
@@ -803,11 +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 '
@@ -939,6 +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.
@@ -952,8 +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:
@@ -975,10 +985,10 @@ class BaseAdapter(metaclass=AdapterMeta):
'dbt could not find a macro with the name "{}" in {}'
.format(macro_name, package_name)
)
# This causes a reference cycle, as generate_runtime_macro_context()
# This causes a reference cycle, as generate_runtime_macro()
# ends up calling get_adapter, so the import has to be here.
from dbt.context.providers import generate_runtime_macro_context
macro_context = generate_runtime_macro_context(
from dbt.context.providers import generate_runtime_macro
macro_context = generate_runtime_macro(
macro=macro,
config=self.config,
manifest=manifest,

View File

@@ -89,10 +89,7 @@ class BaseRelation(FakeAPIObject, Hashable):
if not self._is_exactish_match(k, v):
exact_match = False
if (
self.path.get_lowered_part(k).strip(self.quote_character) !=
v.lower().strip(self.quote_character)
):
if self.path.get_lowered_part(k) != v.lower():
approximate_match = False
if approximate_match and not exact_match:

View File

@@ -1,27 +1,23 @@
import threading
from collections import namedtuple
from copy import deepcopy
from typing import Any, Dict, Iterable, List, Optional, Set, Tuple
from typing import List, Iterable, Optional, Dict, Set, Tuple, Any
import threading
from dbt.adapters.reference_keys import _make_key, _ReferenceKey
import dbt.exceptions
from dbt.events.functions import fire_event
from dbt.events.types import (
AddLink,
AddRelation,
DropCascade,
DropMissingRelation,
DropRelation,
DumpAfterAddGraph,
DumpAfterRenameSchema,
DumpBeforeAddGraph,
DumpBeforeRenameSchema,
RenameSchema,
TemporaryRelation,
UncachedRelation,
UpdateReference
)
from dbt.logger import CACHE_LOGGER as logger
from dbt.utils import lowercase
from dbt.helper_types import Lazy
import dbt.exceptions
_ReferenceKey = namedtuple('_ReferenceKey', 'database schema identifier')
def _make_key(relation) -> _ReferenceKey:
"""Make _ReferenceKeys with lowercase values for the cache so we don't have
to keep track of quoting
"""
# databases and schemas can both be None
return _ReferenceKey(lowercase(relation.database),
lowercase(relation.schema),
lowercase(relation.identifier))
def dot_separated(key: _ReferenceKey) -> str:
@@ -161,6 +157,12 @@ class _CachedRelation:
return [dot_separated(r) for r in self.referenced_by]
def lazy_log(msg, func):
if logger.disabled:
return
logger.debug(msg.format(func()))
class RelationsCache:
"""A cache of the relations known to dbt. Keeps track of relationships
declared between tables and handles renames/drops as a real database would.
@@ -276,7 +278,6 @@ class RelationsCache:
referenced.add_reference(dependent)
# TODO: Is this dead code? I can't seem to find it grepping the codebase.
def add_link(self, referenced, dependent):
"""Add a link between two relations to the database. If either relation
does not exist, it will be added as an "external" relation.
@@ -292,12 +293,15 @@ class RelationsCache:
:raises InternalError: If either entry does not exist.
"""
ref_key = _make_key(referenced)
dep_key = _make_key(dependent)
if (ref_key.database, ref_key.schema) not in self:
# if we have not cached the referenced schema at all, we must be
# referring to a table outside our control. There's no need to make
# a link - we will never drop the referenced relation during a run.
fire_event(UncachedRelation(dep_key=dep_key, ref_key=ref_key))
logger.debug(
'{dep!s} references {ref!s} but {ref.database}.{ref.schema} '
'is not in the cache, skipping assumed external relation'
.format(dep=dependent, ref=ref_key)
)
return
if ref_key not in self.relations:
# Insert a dummy "external" relation.
@@ -305,13 +309,17 @@ class RelationsCache:
type=referenced.External
)
self.add(referenced)
dep_key = _make_key(dependent)
if dep_key not in self.relations:
# Insert a dummy "external" relation.
dependent = dependent.replace(
type=referenced.External
)
self.add(dependent)
fire_event(AddLink(dep_key=dep_key, ref_key=ref_key))
logger.debug(
'adding link, {!s} references {!s}'.format(dep_key, ref_key)
)
with self.lock:
self._add_link(ref_key, dep_key)
@@ -322,12 +330,14 @@ class RelationsCache:
:param BaseRelation relation: The underlying relation.
"""
cached = _CachedRelation(relation)
fire_event(AddRelation(relation=_make_key(cached)))
fire_event(DumpBeforeAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
logger.debug('Adding relation: {!s}'.format(cached))
lazy_log('before adding: {!s}', self.dump_graph)
with self.lock:
self._setdefault(cached)
fire_event(DumpAfterAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
lazy_log('after adding: {!s}', self.dump_graph)
def _remove_refs(self, keys):
"""Removes all references to all entries in keys. This does not
@@ -342,17 +352,20 @@ class RelationsCache:
for cached in self.relations.values():
cached.release_references(keys)
def _drop_cascade_relation(self, dropped_key):
def _drop_cascade_relation(self, dropped):
"""Drop the given relation and cascade it appropriately to all
dependent relations.
:param _CachedRelation dropped: An existing _CachedRelation to drop.
"""
if dropped_key not in self.relations:
fire_event(DropMissingRelation(relation=dropped_key))
if dropped not in self.relations:
logger.debug('dropped a nonexistent relationship: {!s}'
.format(dropped))
return
consequences = self.relations[dropped_key].collect_consequences()
fire_event(DropCascade(dropped=dropped_key, consequences=consequences))
consequences = self.relations[dropped].collect_consequences()
logger.debug(
'drop {} is cascading to {}'.format(dropped, consequences)
)
self._remove_refs(consequences)
def drop(self, relation):
@@ -366,10 +379,10 @@ class RelationsCache:
:param str schema: The schema of the relation to drop.
:param str identifier: The identifier of the relation to drop.
"""
dropped_key = _make_key(relation)
fire_event(DropRelation(dropped=dropped_key))
dropped = _make_key(relation)
logger.debug('Dropping relation: {!s}'.format(dropped))
with self.lock:
self._drop_cascade_relation(dropped_key)
self._drop_cascade_relation(dropped)
def _rename_relation(self, old_key, new_relation):
"""Rename a relation named old_key to new_key, updating references.
@@ -390,8 +403,9 @@ class RelationsCache:
# update all the relations that refer to it
for cached in self.relations.values():
if cached.is_referenced_by(old_key):
fire_event(
UpdateReference(old_key=old_key, new_key=new_key, cached_key=cached.key())
logger.debug(
'updated reference from {0} -> {2} to {1} -> {2}'
.format(old_key, new_key, cached.key())
)
cached.rename_key(old_key, new_key)
@@ -421,7 +435,10 @@ class RelationsCache:
)
if old_key not in self.relations:
fire_event(TemporaryRelation(key=old_key))
logger.debug(
'old key {} not found in self.relations, assuming temporary'
.format(old_key)
)
return False
return True
@@ -439,9 +456,11 @@ class RelationsCache:
"""
old_key = _make_key(old)
new_key = _make_key(new)
fire_event(RenameSchema(old_key=old_key, new_key=new_key))
logger.debug('Renaming relation {!s} to {!s}'.format(
old_key, new_key
))
fire_event(DumpBeforeRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
lazy_log('before rename: {!s}', self.dump_graph)
with self.lock:
if self._check_rename_constraints(old_key, new_key):
@@ -449,7 +468,7 @@ class RelationsCache:
else:
self._setdefault(_CachedRelation(new))
fire_event(DumpAfterRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
lazy_log('after rename: {!s}', self.dump_graph)
def get_relations(
self, database: Optional[str], schema: Optional[str]

View File

@@ -8,9 +8,10 @@ from dbt.include.global_project import (
PACKAGE_PATH as GLOBAL_PROJECT_PATH,
PROJECT_NAME as GLOBAL_PROJECT_NAME,
)
from dbt.events.functions import fire_event
from dbt.events.types import AdapterImportError, PluginLoadError
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.contracts.connection import Credentials, AdapterRequiredConfig
from dbt.adapters.protocol import (
AdapterProtocol,
AdapterConfig,
@@ -66,12 +67,11 @@ class AdapterContainer:
# if we failed to import the target module in particular, inform
# the user about it via a runtime error
if exc.name == 'dbt.adapters.' + name:
fire_event(AdapterImportError(exc=exc))
raise RuntimeException(f'Could not find adapter type {name}!')
logger.info(f'Error importing adapter: {exc}')
# otherwise, the error had to have come from some underlying
# library. Log the stack trace.
fire_event(PluginLoadError())
logger.debug('', exc_info=True)
raise
plugin: AdapterPlugin = mod.Plugin
plugin_type = plugin.adapter.type()

View File

@@ -1,24 +0,0 @@
# this module exists to resolve circular imports with the events module
from collections import namedtuple
from typing import Optional
_ReferenceKey = namedtuple('_ReferenceKey', 'database schema identifier')
def lowercase(value: Optional[str]) -> Optional[str]:
if value is None:
return None
else:
return value.lower()
def _make_key(relation) -> _ReferenceKey:
"""Make _ReferenceKeys with lowercase values for the cache so we don't have
to keep track of quoting
"""
# databases and schemas can both be None
return _ReferenceKey(lowercase(relation.database),
lowercase(relation.schema),
lowercase(relation.identifier))

View File

@@ -10,8 +10,8 @@ from dbt.adapters.base import BaseConnectionManager
from dbt.contracts.connection import (
Connection, ConnectionState, AdapterResponse
)
from dbt.events.functions import fire_event
from dbt.events.types import ConnectionUsed, SQLQuery, SQLCommit, SQLQueryStatus
from dbt.logger import GLOBAL_LOGGER as logger
from dbt import flags
class SQLConnectionManager(BaseConnectionManager):
@@ -59,7 +59,9 @@ class SQLConnectionManager(BaseConnectionManager):
connection = self.get_thread_connection()
if auto_begin and connection.transaction_open is False:
self.begin()
fire_event(ConnectionUsed(conn_type=self.TYPE, conn_name=connection.name))
logger.debug('Using {} connection "{}".'
.format(self.TYPE, connection.name))
with self.exception_handler(sql):
if abridge_sql_log:
@@ -67,17 +69,19 @@ class SQLConnectionManager(BaseConnectionManager):
else:
log_sql = sql
fire_event(SQLQuery(conn_name=connection.name, sql=log_sql))
logger.debug(
'On {connection_name}: {sql}',
connection_name=connection.name,
sql=log_sql,
)
pre = time.time()
cursor = connection.handle.cursor()
cursor.execute(sql, bindings)
fire_event(
SQLQueryStatus(
status=str(self.get_response(cursor)),
elapsed=round((time.time() - pre), 2)
)
logger.debug(
"SQL status: {status} in {elapsed:0.2f} seconds",
status=self.get_response(cursor),
elapsed=(time.time() - pre)
)
return connection, cursor
@@ -140,6 +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 '
@@ -152,12 +163,18 @@ 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 '
'it does not have one open!'.format(connection.name))
fire_event(SQLCommit(conn_name=connection.name))
logger.debug('On {}: COMMIT'.format(connection.name))
self.add_commit_query()
connection.transaction_open = False

View File

@@ -5,11 +5,8 @@ import dbt.clients.agate_helper
from dbt.contracts.connection import Connection
import dbt.exceptions
from dbt.adapters.base import BaseAdapter, available
from dbt.adapters.cache import _make_key
from dbt.adapters.sql import SQLConnectionManager
from dbt.events.functions import fire_event
from dbt.events.types import ColTypeChange, SchemaCreation, SchemaDrop
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.adapters.base.relation import BaseRelation
@@ -119,13 +116,8 @@ class SQLAdapter(BaseAdapter):
target_column.can_expand_to(reference_column):
col_string_size = reference_column.string_size()
new_type = self.Column.string_type(col_string_size)
fire_event(
ColTypeChange(
orig_type=target_column.data_type,
new_type=new_type,
table=_make_key(current),
)
)
logger.debug("Changing col type from {} to {} in table {}",
target_column.data_type, new_type, current)
self.alter_column_type(current, column_name, new_type)
@@ -183,7 +175,7 @@ class SQLAdapter(BaseAdapter):
def create_schema(self, relation: BaseRelation) -> None:
relation = relation.without_identifier()
fire_event(SchemaCreation(relation=_make_key(relation)))
logger.debug('Creating schema "{}"', relation)
kwargs = {
'relation': relation,
}
@@ -194,7 +186,7 @@ class SQLAdapter(BaseAdapter):
def drop_schema(self, relation: BaseRelation) -> None:
relation = relation.without_identifier()
fire_event(SchemaDrop(relation=_make_key(relation)))
logger.debug('Dropping schema "{}".', relation)
kwargs = {
'relation': relation,
}

View File

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

View File

@@ -13,18 +13,6 @@ from dbt.exceptions import RuntimeException
BOM = BOM_UTF8.decode('utf-8') # '\ufeff'
class Number(agate.data_types.Number):
# undo the change in https://github.com/wireservice/agate/pull/733
# i.e. do not cast True and False to numeric 1 and 0
def cast(self, d):
if type(d) == bool:
raise agate.exceptions.CastError(
'Do not cast True to 1 or False to 0.'
)
else:
return super().cast(d)
class ISODateTime(agate.data_types.DateTime):
def cast(self, d):
# this is agate.data_types.DateTime.cast with the "clever" bits removed
@@ -53,7 +41,7 @@ def build_type_tester(
) -> agate.TypeTester:
types = [
Number(null_values=('null', '')),
agate.data_types.Number(null_values=('null', '')),
agate.data_types.Date(null_values=('null', ''),
date_format='%Y-%m-%d'),
agate.data_types.DateTime(null_values=('null', ''),

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

@@ -2,16 +2,8 @@ import re
import os.path
from dbt.clients.system import run_cmd, rmdir
from dbt.events.functions import fire_event
from dbt.events.types import (
GitSparseCheckoutSubdirectory, GitProgressCheckoutRevision,
GitProgressUpdatingExistingDependency, GitProgressPullingNewDependency,
GitNothingToDo, GitProgressUpdatedCheckoutRange, GitProgressCheckedOutAt
)
from dbt.exceptions import (
CommandResultError, RuntimeException, bad_package_spec, raise_git_cloning_error,
raise_git_cloning_problem
)
from dbt.logger import GLOBAL_LOGGER as logger
import dbt.exceptions
from packaging import version
@@ -20,23 +12,13 @@ def _is_commit(revision: str) -> bool:
return bool(re.match(r"\b[0-9a-f]{40}\b", revision))
def _raise_git_cloning_error(repo, revision, error):
stderr = error.stderr.decode('utf-8').strip()
if 'usage: git' in stderr:
stderr = stderr.split('\nusage: git')[0]
if re.match("fatal: destination path '(.+)' already exists", stderr):
raise_git_cloning_error(error)
bad_package_spec(repo, revision, stderr)
def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirectory=None):
has_revision = revision is not None
is_commit = _is_commit(revision or "")
clone_cmd = ['git', 'clone', '--depth', '1']
if subdirectory:
fire_event(GitSparseCheckoutSubdirectory(subdir=subdirectory))
logger.debug(' Subdirectory specified: {}, using sparse checkout.'.format(subdirectory))
out, _ = run_cmd(cwd, ['git', '--version'], env={'LC_ALL': 'C'})
git_version = version.parse(re.search(r"\d+\.\d+\.\d+", out.decode("utf-8")).group(0))
if not git_version >= version.parse("2.25.0"):
@@ -54,18 +36,10 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
if dirname is not None:
clone_cmd.append(dirname)
try:
result = run_cmd(cwd, clone_cmd, env={'LC_ALL': 'C'})
except CommandResultError as exc:
_raise_git_cloning_error(repo, revision, exc)
result = run_cmd(cwd, clone_cmd, env={'LC_ALL': 'C'})
if subdirectory:
cwd_subdir = os.path.join(cwd, dirname or '')
clone_cmd_subdir = ['git', 'sparse-checkout', 'set', subdirectory]
try:
run_cmd(cwd_subdir, clone_cmd_subdir)
except CommandResultError as exc:
_raise_git_cloning_error(repo, revision, exc)
run_cmd(os.path.join(cwd, dirname or ''), ['git', 'sparse-checkout', 'set', subdirectory])
if remove_git_dir:
rmdir(os.path.join(dirname, '.git'))
@@ -80,7 +54,7 @@ def list_tags(cwd):
def _checkout(cwd, repo, revision):
fire_event(GitProgressCheckoutRevision(revision=revision))
logger.debug(' Checking out revision {}.'.format(revision))
fetch_cmd = ["git", "fetch", "origin", "--depth", "1"]
@@ -108,9 +82,9 @@ def checkout(cwd, repo, revision=None):
revision = 'HEAD'
try:
return _checkout(cwd, repo, revision)
except CommandResultError as exc:
except dbt.exceptions.CommandResultError as exc:
stderr = exc.stderr.decode('utf-8').strip()
bad_package_spec(repo, revision, stderr)
dbt.exceptions.bad_package_spec(repo, revision, stderr)
def get_current_sha(cwd):
@@ -134,36 +108,35 @@ def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
remove_git_dir=remove_git_dir,
subdirectory=subdirectory,
)
except CommandResultError as exc:
except dbt.exceptions.CommandResultError as exc:
err = exc.stderr.decode('utf-8')
exists = re.match("fatal: destination path '(.+)' already exists", err)
if not exists:
raise_git_cloning_problem(repo)
if not exists: # something else is wrong, raise it
raise
directory = None
start_sha = None
if exists:
directory = exists.group(1)
fire_event(GitProgressUpdatingExistingDependency(dir=directory))
logger.debug('Updating existing dependency {}.', directory)
else:
matches = re.match("Cloning into '(.+)'", err.decode('utf-8'))
if matches is None:
raise RuntimeException(
raise dbt.exceptions.RuntimeException(
f'Error cloning {repo} - never saw "Cloning into ..." from git'
)
directory = matches.group(1)
fire_event(GitProgressPullingNewDependency(dir=directory))
logger.debug('Pulling new dependency {}.', directory)
full_path = os.path.join(cwd, directory)
start_sha = get_current_sha(full_path)
checkout(full_path, repo, revision)
end_sha = get_current_sha(full_path)
if exists:
if start_sha == end_sha:
fire_event(GitNothingToDo(sha=start_sha[:7]))
logger.debug(' Already at {}, nothing to do.', start_sha[:7])
else:
fire_event(GitProgressUpdatedCheckoutRange(
start_sha=start_sha[:7], end_sha=end_sha[:7]
))
logger.debug(' Updated checkout from {} to {}.',
start_sha[:7], end_sha[:7])
else:
fire_event(GitProgressCheckedOutAt(end_sha=end_sha[:7]))
logger.debug(' Checked out at {}.', end_sha[:7])
return os.path.join(directory, subdirectory or '')

View File

@@ -21,18 +21,19 @@ import jinja2.sandbox
from dbt.utils import (
get_dbt_macro_name, get_docs_macro_name, get_materialization_macro_name,
get_test_macro_name, deep_map_render
get_test_macro_name, deep_map
)
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,
UndefinedMacroException
)
from dbt import flags
from dbt.logger import GLOBAL_LOGGER as logger # noqa
def _linecache_inject(source, write):
@@ -626,12 +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
@@ -660,7 +661,5 @@ def add_rendered_test_kwargs(
return value
# The test_metadata.kwargs come from the test builder, and were set
# when the test node was created in _parse_generic_test.
kwargs = deep_map_render(_convert_function, node.test_metadata.kwargs)
context[GENERIC_TEST_KWARGS_NAME] = kwargs
kwargs = deep_map(_convert_function, node.test_metadata.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

@@ -1,13 +1,10 @@
import functools
from functools import wraps
import requests
from dbt.events.functions import fire_event
from dbt.events.types import (
RegistryProgressMakingGETRequest,
RegistryProgressGETResponse
)
from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
from dbt import deprecations
from dbt.exceptions import RegistryException
from dbt.utils import memoized
from dbt.logger import GLOBAL_LOGGER as logger
import os
import time
if os.getenv('DBT_PACKAGE_HUB_URL'):
DEFAULT_REGISTRY_BASE_URL = os.getenv('DBT_PACKAGE_HUB_URL')
@@ -22,68 +19,53 @@ 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)
fire_event(RegistryProgressMakingGETRequest(url=url))
logger.debug('Making package registry request: GET {}'.format(url))
resp = requests.get(url, timeout=30)
fire_event(RegistryProgressGETResponse(url=url, resp_code=resp.status_code))
logger.debug('Response from registry: GET {} {}'.format(url,
resp.status_code))
resp.raise_for_status()
# It is unexpected for the content of the response to be None so if it is, raising this error
# will cause this function to retry (if called within _get_with_retries) and hopefully get
# a response. This seems to happen when there's an issue with the Hub.
# See https://github.com/dbt-labs/dbt-core/issues/4577
if resp.json() is None:
raise requests.exceptions.ContentDecodingError(
'Request error: The response is None', response=resp
)
return resp.json()
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
@@ -15,13 +14,10 @@ from typing import (
Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
)
from dbt.events.functions import fire_event
from dbt.events.types import (
SystemErrorRetrievingModTime, SystemCouldNotWrite, SystemExecutingCmd, SystemStdOutMsg,
SystemStdErrMsg, SystemReportReturnCode
)
import dbt.exceptions
from dbt.utils import _connection_exception_retry as connection_exception_retry
import dbt.utils
from dbt.logger import GLOBAL_LOGGER as logger
if sys.platform == 'win32':
from ctypes import WinDLL, c_bool
@@ -34,7 +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`
@@ -65,17 +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:
fire_event(SystemErrorRetrievingModTime(path=absolute_path))
if reobj.match(local_file):
matching.append({
'searched_path': relative_path_to_search,
'absolute_path': absolute_path,
'relative_path': relative_path,
'modification_time': modification_time,
})
return matching
@@ -163,7 +153,10 @@ def write_file(path: str, contents: str = '') -> bool:
reason = 'Path was possibly too long'
# all our hard work and the path was still too long. Log and
# continue.
fire_event(SystemCouldNotWrite(path=path, reason=reason, exc=exc))
logger.debug(
f'Could not write to path {path}({len(path)} characters): '
f'{reason}\nexception: {exc}'
)
else:
raise
return True
@@ -411,7 +404,7 @@ def _interpret_oserror(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
def run_cmd(
cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None
) -> Tuple[bytes, bytes]:
fire_event(SystemExecutingCmd(cmd=cmd))
logger.debug('Executing "{}"'.format(' '.join(cmd)))
if len(cmd) == 0:
raise dbt.exceptions.CommandError(cwd, cmd)
@@ -437,24 +430,17 @@ def run_cmd(
except OSError as exc:
_interpret_oserror(exc, cwd, cmd)
fire_event(SystemStdOutMsg(bmsg=out))
fire_event(SystemStdErrMsg(bmsg=err))
logger.debug('STDOUT: "{!s}"'.format(out))
logger.debug('STDERR: "{!s}"'.format(err))
if proc.returncode != 0:
fire_event(SystemReportReturnCode(returncode=proc.returncode))
logger.debug('command return code={}'.format(proc.returncode))
raise dbt.exceptions.CommandResultError(cwd, cmd, proc.returncode,
out, err)
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:
@@ -485,7 +471,7 @@ def untar_package(
) -> None:
tar_path = convert_path(tar_path)
tar_dir_name = None
with tarfile.open(tar_path, 'r:gz') as tarball:
with tarfile.open(tar_path, 'r') as tarball:
tarball.extractall(dest_dir)
tar_dir_name = os.path.commonprefix(tarball.getnames())
if rename_to:

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

@@ -3,18 +3,17 @@ from collections import defaultdict
from typing import List, Dict, Any, Tuple, cast, Optional
import networkx as nx # type: ignore
import pickle
import sqlparse
from dbt import flags
from dbt.adapters.factory import get_adapter
from dbt.clients import jinja
from dbt.clients.system import make_directory
from dbt.context.providers import generate_runtime_model_context
from dbt.contracts.graph.manifest import Manifest, UniqueID
from dbt.context.providers import generate_runtime_model
from dbt.contracts.graph.manifest import Manifest
from dbt.contracts.graph.compiled import (
COMPILED_TYPES,
CompiledGenericTestNode,
CompiledSchemaTestNode,
GraphMemberNode,
InjectedCTE,
ManifestNode,
@@ -27,10 +26,9 @@ from dbt.exceptions import (
RuntimeException,
)
from dbt.graph import Graph
from dbt.events.functions import fire_event
from dbt.events.types import FoundStats, CompilingNode, WritingInjectedSQLForNode
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.node_types import NodeType
from dbt.events.format import pluralize
from dbt.utils import pluralize
import dbt.tracking
graph_file_name = 'graph.gpickle'
@@ -55,7 +53,6 @@ def print_compile_stats(stats):
NodeType.Seed: 'seed file',
NodeType.Source: 'source',
NodeType.Exposure: 'exposure',
NodeType.Metric: 'metric'
}
results = {k: 0 for k in names.keys()}
@@ -71,7 +68,7 @@ def print_compile_stats(stats):
if t in names
])
fire_event(FoundStats(stat_line=stat_line))
logger.info("Found {}".format(stat_line))
def _node_enabled(node: ManifestNode):
@@ -92,8 +89,6 @@ def _generate_stats(manifest: Manifest):
stats[source.resource_type] += 1
for exposure in manifest.exposures.values():
stats[exposure.resource_type] += 1
for metric in manifest.metrics.values():
stats[metric.resource_type] += 1
for macro in manifest.macros.values():
stats[macro.resource_type] += 1
return stats
@@ -112,19 +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:
@@ -160,11 +142,10 @@ 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)
with open(outfile, 'wb') as outfh:
pickle.dump(out_graph, outfh, protocol=pickle.HIGHEST_PROTOCOL)
nx.write_gpickle(out_graph, outfile)
class Compiler:
@@ -173,7 +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
@@ -184,11 +165,11 @@ class Compiler:
extra_context: Dict[str, Any],
) -> Dict[str, Any]:
context = generate_runtime_model_context(
context = generate_runtime_model(
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)
@@ -372,7 +353,7 @@ class Compiler:
if extra_context is None:
extra_context = {}
fire_event(CompilingNode(unique_id=node.unique_id))
logger.debug("Compiling {}".format(node.unique_id))
data = node.to_dict(omit_none=True)
data.update({
@@ -424,94 +405,25 @@ class Compiler:
else:
dependency_not_found(node, dependency)
def link_graph(self, linker: Linker, manifest: Manifest, add_test_edges: bool = False):
def link_graph(self, linker: Linker, manifest: Manifest):
for source in manifest.sources.values():
linker.add_node(source.unique_id)
for node in manifest.nodes.values():
self.link_node(linker, node, manifest)
for exposure in manifest.exposures.values():
self.link_node(linker, exposure, manifest)
for metric in manifest.metrics.values():
self.link_node(linker, metric, manifest)
# linker.add_node(exposure.unique_id)
cycle = linker.find_cycles()
if cycle:
raise RuntimeError("Found a cycle: {}".format(cycle))
if add_test_edges:
manifest.build_parent_and_child_maps()
self.add_test_edges(linker, manifest)
def add_test_edges(self, linker: Linker, manifest: Manifest) -> None:
""" This method adds additional edges to the DAG. For a given non-test
executable node, add an edge from an upstream test to the given node if
the set of nodes the test depends on is a subset of the upstream nodes
for the given node. """
# 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 subset of all upstream nodes of the current node,
# add an edge from the upstream test to the current node.
if (test_depends_on.issubset(upstream_nodes)):
linker.graph.add_edge(
upstream_test,
node_id
)
def compile(self, manifest: Manifest, write=True, add_test_edges=False) -> Graph:
def compile(self, manifest: Manifest, write=True) -> Graph:
self.initialize()
linker = Linker()
self.link_graph(linker, manifest, add_test_edges)
self.link_graph(linker, manifest)
stats = _generate_stats(manifest)
@@ -526,7 +438,7 @@ class Compiler:
if (not node.extra_ctes_injected or
node.resource_type == NodeType.Snapshot):
return node
fire_event(WritingInjectedSQLForNode(unique_id=node.unique_id))
logger.debug(f'Writing injected SQL for node "{node.unique_id}"')
if node.compiled_sql:
node.compiled_path = node.write_node(

View File

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

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
@@ -15,15 +14,16 @@ from dbt.exceptions import DbtProjectError
from dbt.exceptions import ValidationException
from dbt.exceptions import RuntimeException
from dbt.exceptions import validator_error_message
from dbt.events.types import MissingProfileTarget
from dbt.events.functions import fire_event
from dbt.logger import GLOBAL_LOGGER as logger
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.
@@ -43,7 +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]:
@@ -73,10 +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()
@@ -84,33 +84,13 @@ 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
profile_env_vars: Dict[str, Any]
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
self.profile_env_vars = {} # never available on init
def to_profile_info(
self, serialize_credentials: bool = False
@@ -126,12 +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
@@ -145,7 +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
@@ -240,7 +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.
@@ -249,20 +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
)
@@ -294,7 +274,10 @@ class Profile(HasCredentials):
target_name = renderer.render_value(raw_profile['target'])
else:
target_name = 'default'
fire_event(MissingProfileTarget(profile_name=profile_name, target_name=target_name))
logger.debug(
"target not specified in profile '{}', using '{}'"
.format(profile_name, target_name)
)
raw_profile_data = cls._get_profile_data(
raw_profile, profile_name, target_name
@@ -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
@@ -45,7 +44,7 @@ INVALID_VERSION_ERROR = """\
This version of dbt is not supported with the '{package}' package.
Installed version of dbt: {installed}
Required version of dbt for '{package}': {version_spec}
Check for a different version of the '{package}' package, or run dbt again with \
Check the requirements for the '{package}' package, or run dbt again with \
--no-version-check
"""
@@ -54,7 +53,7 @@ IMPOSSIBLE_VERSION_ERROR = """\
The package version requirement can never be satisfied for the '{package}
package.
Required versions of dbt for '{package}': {version_spec}
Check for a different version of the '{package}' package, or run dbt again with \
Check the requirements for the '{package}' package, or run dbt again with \
--no-version-check
"""
@@ -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))
@@ -284,7 +283,6 @@ class PartialProject(RenderComponents):
selectors_dict=rendered_selectors,
)
# Called by 'collect_parts' in RuntimeConfig
def render(self, renderer: DbtProjectYamlRenderer) -> 'Project':
try:
rendered = self.get_rendered(renderer)
@@ -294,21 +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(f'project-config-{deprecated_path}',
deprecated_path=deprecated_path,
exp_path=exp_path)
def create_project(self, rendered: RenderComponents) -> 'Project':
unrendered = RenderComponents(
project_dict=self.project_dict,
@@ -320,9 +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(
@@ -344,24 +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
)
@@ -370,7 +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
@@ -398,8 +369,6 @@ class PartialProject(RenderComponents):
vars_dict = cfg.vars
vars_value = VarProvider(vars_dict)
# There will never be any project_env_vars when it's first created
project_env_vars: Dict[str, Any] = {}
on_run_start: List[str] = value_or(cfg.on_run_start, [])
on_run_end: List[str] = value_or(cfg.on_run_end, [])
@@ -413,14 +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,
@@ -429,7 +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,
@@ -447,7 +417,6 @@ class PartialProject(RenderComponents):
vars=vars_value,
config_version=cfg.config_version,
unrendered=unrendered,
project_env_vars=project_env_vars,
)
# sanity check - this means an internal issue
project.validate()
@@ -531,9 +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]
@@ -542,7 +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]
@@ -560,22 +529,14 @@ class Project:
query_comment: QueryComment
config_version: int
unrendered: RenderComponents
project_env_vars: Dict[str, Any]
@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
)
@property
def generic_test_paths(self):
generic_test_paths = []
for test_path in self.test_paths:
generic_test_paths.append(os.path.join(test_path, 'generic'))
return generic_test_paths
def __str__(self):
cfg = self.to_project_config(with_packages=True)
return str(cfg)
@@ -600,9 +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,
@@ -650,6 +611,26 @@ class Project:
verify_version=verify_version,
)
@classmethod
def render_from_dict(
cls,
project_root: str,
project_dict: Dict[str, Any],
packages_dict: Dict[str, Any],
selectors_dict: Dict[str, Any],
renderer: DbtProjectYamlRenderer,
*,
verify_version: bool = False
) -> 'Project':
partial = PartialProject.from_dicts(
project_root=project_root,
project_dict=project_dict,
packages_dict=packages_dict,
selectors_dict=selectors_dict,
verify_version=verify_version,
)
return partial.render(renderer)
@classmethod
def from_project_root(
cls,
@@ -664,24 +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

@@ -1,14 +1,12 @@
from typing import Dict, Any, Tuple, Optional, Union, Callable
from dbt.clients.jinja import get_rendered, catch_jinja
from dbt.context.target import TargetContext
from dbt.context.secret import SecretContext
from dbt.context.base import BaseContext
from dbt.contracts.connection import HasCredentials
from dbt.exceptions import (
DbtProjectError, CompilationException, RecursionException
)
from dbt.utils import deep_map_render
from dbt.node_types import NodeType
from dbt.utils import deep_map
Keypath = Tuple[Union[str, int], ...]
@@ -49,7 +47,7 @@ class BaseRenderer:
self, data: Dict[str, Any]
) -> Dict[str, Any]:
try:
return deep_map_render(self.render_entry, data)
return deep_map(self.render_entry, data)
except RecursionException:
raise DbtProjectError(
f'Cycle detected: {self.name} input has a reference to itself',
@@ -101,23 +99,6 @@ class ProjectPostprocessor(Dict[Keypath, Callable[[Any], Any]]):
class DbtProjectYamlRenderer(BaseRenderer):
_KEYPATH_HANDLERS = ProjectPostprocessor()
def __init__(
self, profile: Optional[HasCredentials] = None,
cli_vars: Optional[Dict[str, Any]] = None
) -> None:
# Generate contexts here because we want to save the context
# object in order to retrieve the env_vars. This is almost always
# a TargetContext, but in the debug task we want a project
# even when we don't have a profile.
if cli_vars is None:
cli_vars = {}
if profile:
self.ctx_obj = TargetContext(profile, cli_vars)
else:
self.ctx_obj = BaseContext(cli_vars) # type:ignore
context = self.ctx_obj.to_dict()
super().__init__(context)
@property
def name(self):
'Project config'
@@ -176,36 +157,82 @@ class DbtProjectYamlRenderer(BaseRenderer):
return True
class ProfileRenderer(BaseRenderer):
@property
def name(self):
'Profile'
class SchemaYamlRenderer(BaseRenderer):
DOCUMENTABLE_NODES = frozenset(
n.pluralize() for n in NodeType.documentable()
)
@property
def name(self):
return 'Rendering yaml'
def _is_norender_key(self, keypath: Keypath) -> bool:
"""
models:
- name: blah
- description: blah
tests: ...
- columns:
- name:
- description: blah
tests: ...
Return True if it's tests or description - those aren't rendered
"""
if len(keypath) >= 2 and keypath[1] in ('tests', 'description'):
return True
if (
len(keypath) >= 4 and
keypath[1] == 'columns' and
keypath[3] in ('tests', 'description')
):
return True
return False
# don't render descriptions or test keyword arguments
def should_render_keypath(self, keypath: Keypath) -> bool:
if len(keypath) < 2:
return True
if keypath[0] not in self.DOCUMENTABLE_NODES:
return True
if len(keypath) < 3:
return True
if keypath[0] == NodeType.Source.pluralize():
if keypath[2] == 'description':
return False
if keypath[2] == 'tables':
if self._is_norender_key(keypath[3:]):
return False
elif keypath[0] == NodeType.Macro.pluralize():
if keypath[2] == 'arguments':
if self._is_norender_key(keypath[3:]):
return False
elif self._is_norender_key(keypath[1:]):
return False
else: # keypath[0] in self.DOCUMENTABLE_NODES:
if self._is_norender_key(keypath[1:]):
return False
return True
class PackageRenderer(BaseRenderer):
@property
def name(self):
return 'Packages config'
class SelectorRenderer(BaseRenderer):
@property
def name(self):
return 'Selector config'
class SecretRenderer(BaseRenderer):
def __init__(
self, cli_vars: Optional[Dict[str, Any]] = None
) -> None:
# Generate contexts here because we want to save the context
# object in order to retrieve the env_vars.
if cli_vars is None:
cli_vars = {}
self.ctx_obj = SecretContext(cli_vars)
context = self.ctx_obj.to_dict()
super().__init__(context)
@property
def name(self):
return 'Secret'
class ProfileRenderer(SecretRenderer):
@property
def name(self):
return 'Profile'
class PackageRenderer(SecretRenderer):
@property
def name(self):
return 'Packages config'

View File

@@ -1,7 +1,7 @@
import itertools
import os
from copy import deepcopy
from dataclasses import dataclass
from dataclasses import dataclass, fields
from pathlib import Path
from typing import (
Dict, Any, Optional, Mapping, Iterator, Iterable, Tuple, List, MutableSet,
@@ -12,18 +12,21 @@ from .profile import Profile
from .project import Project
from .renderer import DbtProjectYamlRenderer, ProfileRenderer
from .utils import parse_cli_vars
from dbt import flags
from dbt import tracking
from dbt.adapters.factory import get_relation_class_by_name, get_include_paths
from dbt.helper_types import FQNPath, PathSet
from dbt.config.profile import read_user_config
from dbt.context.base import generate_base_context
from dbt.context.target import generate_target_context
from dbt.contracts.connection import AdapterRequiredConfig, Credentials
from dbt.contracts.graph.manifest import ManifestMetadata
from dbt.contracts.relation import ComponentName
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.ui import warning_tag
from dbt.contracts.project import Configuration, UserConfig
from dbt.exceptions import (
RuntimeException,
DbtProfileError,
DbtProjectError,
validator_error_message,
warn_or_error,
@@ -56,7 +59,6 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
def __post_init__(self):
self.validate()
# Called by 'new_project' and 'from_args'
@classmethod
def from_parts(
cls,
@@ -84,9 +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,
@@ -95,7 +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,
@@ -113,11 +115,9 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
vars=project.vars,
config_version=project.config_version,
unrendered=project.unrendered,
project_env_vars=project.project_env_vars,
profile_env_vars=profile.profile_env_vars,
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,
@@ -125,7 +125,6 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
dependencies=dependencies,
)
# Called by 'load_projects' in this class
def new_project(self, project_root: str) -> 'RuntimeConfig':
"""Given a new project root, read in its project dictionary, supply the
existing project's profile info, and create a new project file.
@@ -140,22 +139,22 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
profile.validate()
# load the new project and its packages. Don't pass cli variables.
renderer = DbtProjectYamlRenderer(profile)
renderer = DbtProjectYamlRenderer(generate_target_context(profile, {}))
project = Project.from_project_root(
project_root,
renderer,
verify_version=bool(flags.VERSION_CHECK),
verify_version=getattr(self.args, 'version_check', False),
)
runtime_config = self.from_parts(
cfg = self.from_parts(
project=project,
profile=profile,
args=deepcopy(self.args),
)
# force our quoting back onto the new project.
runtime_config.quoting = deepcopy(self.quoting)
return runtime_config
cfg.quoting = deepcopy(self.quoting)
return cfg
def serialize(self) -> Dict[str, Any]:
"""Serialize the full configuration to a single dictionary. For any
@@ -188,7 +187,6 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
profile_renderer: ProfileRenderer,
profile_name: Optional[str],
) -> Profile:
return Profile.render_from_args(
args, profile_renderer, profile_name
)
@@ -199,33 +197,28 @@ 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
)
# build the profile using the base renderer and the one fact we know
# Note: only the named profile section is rendered. The rest of the
# profile is ignored.
cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
profile_renderer = ProfileRenderer(cli_vars)
profile_renderer = ProfileRenderer(generate_base_context(cli_vars))
profile_name = partial.render_profile_name(profile_renderer)
profile = cls._get_rendered_profile(
args, profile_renderer, profile_name
)
# Save env_vars encountered in rendering for partial parsing
profile.profile_env_vars = profile_renderer.ctx_obj.env_vars
# get a new renderer using our target information and render the
# project
project_renderer = DbtProjectYamlRenderer(profile, cli_vars)
ctx = generate_target_context(profile, cli_vars)
project_renderer = DbtProjectYamlRenderer(ctx)
project = partial.render(project_renderer)
# Save env_vars encountered in rendering for partial parsing
project.project_env_vars = project_renderer.ctx_obj.env_vars
return (project, profile)
# Called in main.py, lib.py, task/base.py
@classmethod
def from_args(cls, args: Any) -> 'RuntimeConfig':
"""Given arguments, read in dbt_project.yml from the current directory,
@@ -259,7 +252,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
) -> PathSet:
for key, value in config.items():
if isinstance(value, dict) and not key.startswith('+'):
self._get_config_paths(value, path + (key,), paths)
self._get_v2_config_paths(value, path + (key,), paths)
else:
paths.add(path)
return frozenset(paths)
@@ -344,7 +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(
@@ -366,7 +359,6 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
def clear_dependencies(self):
self.dependencies = None
# Called by 'load_dependencies' in this class
def load_projects(
self, paths: Iterable[Path]
) -> Iterator[Tuple[str, 'RuntimeConfig']]:
@@ -383,7 +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():
@@ -399,10 +391,6 @@ class UnsetCredentials(Credentials):
def type(self):
return None
@property
def unique_field(self):
return None
def connection_info(self, *args, **kwargs):
return {}
@@ -410,12 +398,21 @@ class UnsetCredentials(Credentials):
return ()
# This is used by UnsetProfileConfig, for commands which do
# not require a profile, i.e. dbt deps and clean
class UnsetConfig(UserConfig):
def __getattribute__(self, name):
if name in {f.name for f in fields(UserConfig)}:
raise AttributeError(
f"'UnsetConfig' object has no attribute {name}"
)
def __post_serialize__(self, dct):
return {}
class UnsetProfile(Profile):
def __init__(self):
self.credentials = UnsetCredentials()
self.user_config = UserConfig() # This will be read in _get_rendered_profile
self.config = UnsetConfig()
self.profile_name = ''
self.target_name = ''
self.threads = -1
@@ -432,8 +429,6 @@ class UnsetProfile(Profile):
return Profile.__getattribute__(self, name)
# This class is used by the dbt deps and clean commands, because they don't
# require a functioning profile.
@dataclass
class UnsetProfileConfig(RuntimeConfig):
"""This class acts a lot _like_ a RuntimeConfig, except if your profile is
@@ -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,
@@ -512,11 +507,9 @@ class UnsetProfileConfig(RuntimeConfig):
vars=project.vars,
config_version=project.config_version,
unrendered=project.unrendered,
project_env_vars=project.project_env_vars,
profile_env_vars=profile.profile_env_vars,
profile_name='',
target_name='',
user_config=UserConfig(),
config=UnsetConfig(),
threads=getattr(args, 'threads', 1),
credentials=UnsetCredentials(),
args=args,
@@ -531,12 +524,22 @@ class UnsetProfileConfig(RuntimeConfig):
profile_renderer: ProfileRenderer,
profile_name: Optional[str],
) -> Profile:
profile = UnsetProfile()
# The profile (for warehouse connection) is not needed, but we want
# to get the UserConfig, which is also in profiles.yml
user_config = read_user_config(flags.PROFILES_DIR)
profile.user_config = user_config
try:
profile = Profile.render_from_args(
args, profile_renderer, profile_name
)
except (DbtProjectError, DbtProfileError) as exc:
logger.debug(
'Profile not loaded due to error: {}', exc, exc_info=True
)
logger.info(
'No profile "{}" found, continuing with no target',
profile_name
)
# return the poisoned form
profile = UnsetProfile()
# disable anonymous usage statistics
tracking.disable_tracking()
return profile
@classmethod
@@ -551,6 +554,9 @@ class UnsetProfileConfig(RuntimeConfig):
:raises ValidationException: If the cli variables are invalid.
"""
project, profile = cls.collect_parts(args)
if not isinstance(profile, UnsetProfile):
# if it's a real profile, return a real config
cls = RuntimeConfig
return cls.from_parts(
project=project,

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

@@ -1,9 +1,8 @@
from typing import Dict, Any
from dbt.clients import yaml_helper
from dbt.events.functions import fire_event
from dbt.exceptions import raise_compiler_error, ValidationException
from dbt.events.types import InvalidVarsYAML
from dbt.logger import GLOBAL_LOGGER as logger
def parse_cli_vars(var_string: str) -> Dict[str, Any]:
@@ -18,5 +17,7 @@ def parse_cli_vars(var_string: str) -> Dict[str, Any]:
"The --vars argument must be a YAML dictionary, but was "
"of type '{}'".format(type_name))
except ValidationException:
fire_event(InvalidVarsYAML())
logger.error(
"The YAML provided in the --vars argument is not valid.\n"
)
raise

View File

@@ -1 +0,0 @@
# Contexts and Jinja rendering

View File

@@ -6,17 +6,13 @@ from typing import (
from dbt import flags
from dbt import tracking
from dbt.clients.jinja import get_rendered
from dbt.clients.jinja import undefined_error, get_rendered
from dbt.clients.yaml_helper import ( # noqa: F401
yaml, safe_load, SafeLoader, Loader, Dumper
)
from dbt.contracts.graph.compiled import CompiledResource
from dbt.exceptions import (
raise_compiler_error, MacroReturn, raise_parsing_error, disallow_secret_env_var
)
from dbt.logger import SECRET_ENV_PREFIX
from dbt.events.functions import fire_event, get_invocation_id
from dbt.events.types import MacroEventInfo, MacroEventDebug
from dbt.exceptions import raise_compiler_error, MacroReturn
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
@@ -25,39 +21,6 @@ import pytz
import datetime
import re
# Contexts in dbt Core
# Contexts are used for Jinja rendering. They include context methods,
# executable macros, and various settings that are available in Jinja.
#
# Different contexts are used in different places because we allow access
# to different methods and data in different places. Executable SQL, for
# example, includes the available macros and the model, while Jinja in
# yaml files is more limited.
#
# The context that is passed to Jinja is always in a dictionary format,
# not an actual class, so a 'to_dict()' is executed on a context class
# before it is used for rendering.
#
# Each context has a generate_<name>_context function to create the context.
# ProviderContext subclasses have different generate functions for
# parsing and for execution.
#
# Context class hierarchy
#
# BaseContext -- core/dbt/context/base.py
# SecretContext -- core/dbt/context/secret.py
# TargetContext -- core/dbt/context/target.py
# ConfiguredContext -- core/dbt/context/configured.py
# SchemaYamlContext -- core/dbt/context/configured.py
# DocsRuntimeContext -- core/dbt/context/configured.py
# MacroResolvingContext -- core/dbt/context/configured.py
# ManifestContext -- core/dbt/context/manifest.py
# QueryHeaderContext -- core/dbt/context/manifest.py
# ProviderContext -- core/dbt/context/provider.py
# MacroContext -- core/dbt/context/provider.py
# ModelContext -- core/dbt/context/provider.py
# TestContext -- core/dbt/context/provider.py
def get_pytz_module_context() -> Dict[str, Any]:
context_exports = pytz.__all__ # type: ignore
@@ -197,11 +160,9 @@ class Var:
class BaseContext(metaclass=ContextMeta):
# subclass is TargetContext
def __init__(self, cli_vars):
self._ctx = {}
self.cli_vars = cli_vars
self.env_vars = {}
def generate_builtins(self):
builtins: Dict[str, Any] = {}
@@ -310,26 +271,20 @@ class BaseContext(metaclass=ContextMeta):
return Var(self._ctx, self.cli_vars)
@contextmember
def env_var(self, var: str, default: Optional[str] = None) -> str:
@staticmethod
def env_var(var: str, default: Optional[str] = None) -> str:
"""The env_var() function. Return the environment variable named 'var'.
If there is no such environment variable set, return the default.
If the default is None, raise an exception for an undefined variable.
"""
return_value = None
if var.startswith(SECRET_ENV_PREFIX):
disallow_secret_env_var(var)
if var in os.environ:
return_value = os.environ[var]
return os.environ[var]
elif default is not None:
return_value = default
if return_value is not None:
self.env_vars[var] = return_value
return return_value
return default
else:
msg = f"Env var required but not provided: '{var}'"
raise_parsing_error(msg)
undefined_error(msg)
if os.environ.get('DBT_MACRO_DEBUGGING'):
@contextmember
@@ -488,9 +443,9 @@ class BaseContext(metaclass=ContextMeta):
{% endmacro %}"
"""
if info:
fire_event(MacroEventInfo(msg=msg))
logger.info(msg)
else:
fire_event(MacroEventDebug(msg=msg))
logger.debug(msg)
return ''
@contextproperty
@@ -526,7 +481,10 @@ class BaseContext(metaclass=ContextMeta):
"""invocation_id outputs a UUID generated for this dbt run (useful for
auditing)
"""
return get_invocation_id()
if tracking.active_user is not None:
return tracking.active_user.invocation_id
else:
return None
@contextproperty
def modules(self) -> Dict[str, Any]:
@@ -566,8 +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

@@ -1,18 +1,14 @@
import os
from typing import Any, Dict, Optional
from typing import Any, Dict
from dbt.contracts.connection import AdapterRequiredConfig
from dbt.logger import SECRET_ENV_PREFIX
from dbt.node_types import NodeType
from dbt.utils import MultiDict
from dbt.context.base import contextproperty, contextmember, Var
from dbt.context.base import contextproperty, Var
from dbt.context.target import TargetContext
from dbt.exceptions import raise_parsing_error, disallow_secret_env_var
class ConfiguredContext(TargetContext):
# subclasses are SchemaYamlContext, MacroResolvingContext, ManifestContext
config: AdapterRequiredConfig
def __init__(
@@ -67,18 +63,10 @@ class ConfiguredVar(Var):
return self.get_missing_var(var_name)
class SchemaYamlVars():
def __init__(self):
self.env_vars = {}
self.vars = {}
class SchemaYamlContext(ConfiguredContext):
# subclass is DocsRuntimeContext
def __init__(self, config, project_name: str, schema_yaml_vars: Optional[SchemaYamlVars]):
def __init__(self, config, project_name: str):
super().__init__(config)
self._project_name = project_name
self.schema_yaml_vars = schema_yaml_vars
@contextproperty
def var(self) -> ConfiguredVar:
@@ -86,24 +74,6 @@ class SchemaYamlContext(ConfiguredContext):
self._ctx, self.config, self._project_name
)
@contextmember
def env_var(self, var: str, default: Optional[str] = None) -> str:
return_value = None
if var.startswith(SECRET_ENV_PREFIX):
disallow_secret_env_var(var)
if var in os.environ:
return_value = os.environ[var]
elif default is not None:
return_value = default
if return_value is not None:
if self.schema_yaml_vars:
self.schema_yaml_vars.env_vars[var] = return_value
return return_value
else:
msg = f"Env var required but not provided: '{var}'"
raise_parsing_error(msg)
class MacroResolvingContext(ConfiguredContext):
def __init__(self, config):
@@ -116,10 +86,10 @@ class MacroResolvingContext(ConfiguredContext):
)
def generate_schema_yml_context(
config: AdapterRequiredConfig, project_name: str, schema_yaml_vars: SchemaYamlVars = None
def generate_schema_yml(
config: AdapterRequiredConfig, project_name: str
) -> Dict[str, Any]:
ctx = SchemaYamlContext(config, project_name, schema_yaml_vars)
ctx = SchemaYamlContext(config, project_name)
return ctx.to_dict()

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

@@ -23,7 +23,7 @@ class DocsRuntimeContext(SchemaYamlContext):
manifest: Manifest,
current_project: str,
) -> None:
super().__init__(config, current_project, None)
super().__init__(config, current_project)
self.node = node
self.manifest = manifest
@@ -75,7 +75,7 @@ class DocsRuntimeContext(SchemaYamlContext):
return target_doc.block_contents
def generate_runtime_docs_context(
def generate_runtime_docs(
config: RuntimeConfig,
target: Any,
manifest: Manifest,

View File

@@ -17,7 +17,6 @@ class ManifestContext(ConfiguredContext):
The given macros can override any previous context values, which will be
available as if they were accessed relative to the package name.
"""
# subclasses are QueryHeaderContext and ProviderContext
def __init__(
self,
config: AdapterRequiredConfig,

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
@@ -16,7 +17,6 @@ from dbt.config import RuntimeConfig, Project
from .base import contextmember, contextproperty, Var
from .configured import FQNLookup
from .context_config import ContextConfig
from dbt.logger import SECRET_ENV_PREFIX
from dbt.context.macro_resolver import MacroResolver, TestMacroNamespace
from .macros import MacroNamespaceBuilder, MacroNamespace
from .manifest import ManifestContext
@@ -32,17 +32,14 @@ from dbt.contracts.graph.compiled import (
from dbt.contracts.graph.parsed import (
ParsedMacro,
ParsedExposure,
ParsedMetric,
ParsedSeedNode,
ParsedSourceDefinition,
)
from dbt.exceptions import (
CompilationException,
ParsingException,
InternalException,
ValidationException,
RuntimeException,
macro_invalid_dispatch_arg,
missing_config,
raise_compiler_error,
ref_invalid_args,
@@ -50,10 +47,9 @@ from dbt.exceptions import (
ref_bad_context,
source_target_not_found,
wrapped_exports,
raise_parsing_error,
disallow_secret_env_var,
)
from dbt.config import IsFQNResource
from dbt.logger import GLOBAL_LOGGER as logger # noqa
from dbt.node_types import NodeType
from dbt.utils import (
@@ -124,37 +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 = []
@@ -166,10 +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)
@@ -327,7 +325,7 @@ class ParseConfigObject(Config):
def require(self, name, validator=None):
return ''
def get(self, name, default=None, validator=None):
def get(self, name, validator=None, default=None):
return ''
def persist_relation_docs(self) -> bool:
@@ -371,7 +369,7 @@ class RuntimeConfigObject(Config):
return to_return
def get(self, name, default=None, validator=None):
def get(self, name, validator=None, default=None):
to_return = self._lookup(name, default)
if validator is not None and default is not None:
@@ -640,7 +638,6 @@ T = TypeVar('T')
# Base context collection, used for parsing configs.
class ProviderContext(ManifestContext):
# subclasses are MacroContext, ModelContext, TestContext
def __init__(
self,
model,
@@ -1154,48 +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)
@contextmember
def env_var(self, var: str, default: Optional[str] = None) -> str:
"""The env_var() function. Return the environment variable named 'var'.
If there is no such environment variable set, return the default.
If the default is None, raise an exception for an undefined variable.
"""
return_value = None
if var.startswith(SECRET_ENV_PREFIX):
disallow_secret_env_var(var)
if var in os.environ:
return_value = os.environ[var]
elif default is not None:
return_value = default
if return_value is not None:
# Save the env_var value in the manifest and the var name in the source_file.
# If this is compiling, do not save because it's irrelevant to parsing.
if self.model and not hasattr(self.model, 'compiled'):
self.manifest.env_vars[var] = return_value
# hooks come from dbt_project.yml which doesn't have a real file_id
if self.model.file_id in self.manifest.files:
source_file = self.manifest.files[self.model.file_id]
# Schema files should never get here
if source_file.parse_file_type != 'schema':
source_file.env_vars.append(var)
return return_value
else:
msg = f"Env var required but not provided: '{var}'"
raise_parsing_error(msg)
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):
@@ -1229,7 +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
@@ -1237,7 +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
@@ -1298,7 +1312,7 @@ class ModelContext(ProviderContext):
# This is called by '_context_for', used in 'render_with_context'
def generate_parser_model_context(
def generate_parser_model(
model: ManifestNode,
config: RuntimeConfig,
manifest: Manifest,
@@ -1315,7 +1329,7 @@ def generate_parser_model_context(
return ctx.to_dict()
def generate_generate_name_macro_context(
def generate_generate_component_name_macro(
macro: ParsedMacro,
config: RuntimeConfig,
manifest: Manifest,
@@ -1326,7 +1340,7 @@ def generate_generate_name_macro_context(
return ctx.to_dict()
def generate_runtime_model_context(
def generate_runtime_model(
model: ManifestNode,
config: RuntimeConfig,
manifest: Manifest,
@@ -1337,7 +1351,7 @@ def generate_runtime_model_context(
return ctx.to_dict()
def generate_runtime_macro_context(
def generate_runtime_macro(
macro: ParsedMacro,
config: RuntimeConfig,
manifest: Manifest,
@@ -1391,44 +1405,6 @@ def generate_parse_exposure(
}
class MetricRefResolver(BaseResolver):
def __call__(self, *args) -> str:
package = None
if len(args) == 1:
name = args[0]
elif len(args) == 2:
package, name = args
else:
ref_invalid_args(self.model, args)
self.validate_args(name, package)
self.model.refs.append(list(args))
return ''
def validate_args(self, name, package):
if not isinstance(name, str):
raise ParsingException(
f'In a metrics section in {self.model.original_file_path} '
f'the name argument to ref() must be a string'
)
def generate_parse_metrics(
metric: ParsedMetric,
config: RuntimeConfig,
manifest: Manifest,
package_name: str,
) -> Dict[str, Any]:
project = config.load_dependencies()[package_name]
return {
'ref': MetricRefResolver(
None,
metric,
project,
manifest,
),
}
# This class is currently used by the schema parser in order
# to limit the number of macros in the context by using
# the TestMacroNamespace
@@ -1463,13 +1439,8 @@ class TestContext(ProviderContext):
# 'depends_on.macros' by using the TestMacroNamespace
def _build_test_namespace(self):
depends_on_macros = []
# all generic tests use a macro named 'get_where_subquery' to wrap 'model' arg
# see generic_test_builders.build_model_str
get_where_subquery = self.macro_resolver.macros_by_name.get('get_where_subquery')
if get_where_subquery:
depends_on_macros.append(get_where_subquery.unique_id)
if self.model.depends_on and self.model.depends_on.macros:
depends_on_macros.extend(self.model.depends_on.macros)
depends_on_macros = self.model.depends_on.macros
lookup_macros = depends_on_macros.copy()
for macro_unique_id in lookup_macros:
lookup_macro = self.macro_resolver.macros.get(macro_unique_id)
@@ -1482,30 +1453,6 @@ class TestContext(ProviderContext):
)
self.namespace = macro_namespace
@contextmember
def env_var(self, var: str, default: Optional[str] = None) -> str:
return_value = None
if var.startswith(SECRET_ENV_PREFIX):
disallow_secret_env_var(var)
if var in os.environ:
return_value = os.environ[var]
elif default is not None:
return_value = default
if return_value is not None:
# Save the env_var value in the manifest and the var name in the source_file
if self.model:
self.manifest.env_vars[var] = return_value
# the "model" should only be test nodes, but just in case, check
if self.model.resource_type == NodeType.Test and self.model.file_key_name:
source_file = self.manifest.files[self.model.file_id]
(yaml_key, name) = self.model.file_key_name.split('.')
source_file.add_env_var(var, yaml_key, name)
return return_value
else:
msg = f"Env var required but not provided: '{var}'"
raise_parsing_error(msg)
def generate_test_context(
model: ManifestNode,

View File

@@ -1,40 +0,0 @@
import os
from typing import Any, Dict, Optional
from .base import BaseContext, contextmember
from dbt.exceptions import raise_parsing_error
class SecretContext(BaseContext):
"""This context is used in profiles.yml + packages.yml. It can render secret
env vars that aren't usable elsewhere"""
@contextmember
def env_var(self, var: str, default: Optional[str] = None) -> str:
"""The env_var() function. Return the environment variable named 'var'.
If there is no such environment variable set, return the default.
If the default is None, raise an exception for an undefined variable.
In this context *only*, env_var will return the actual values of
env vars prefixed with DBT_ENV_SECRET_
"""
return_value = None
if var in os.environ:
return_value = os.environ[var]
elif default is not None:
return_value = default
if return_value is not None:
self.env_vars[var] = return_value
return return_value
else:
msg = f"Env var required but not provided: '{var}'"
raise_parsing_error(msg)
def generate_secret_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:
ctx = SecretContext(cli_vars)
# This is not a Mashumaro to_dict call
return ctx.to_dict()

View File

@@ -8,7 +8,6 @@ from dbt.context.base import (
class TargetContext(BaseContext):
# subclass is ConfiguredContext
def __init__(self, config: HasCredentials, cli_vars: Dict[str, Any]):
super().__init__(cli_vars=cli_vars)
self.config = config

View File

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

View File

@@ -1,14 +1,12 @@
import abc
import itertools
import hashlib
from dataclasses import dataclass, field
from typing import (
Any, ClassVar, Dict, Tuple, Iterable, Optional, List, Callable,
)
from dbt.exceptions import InternalException
from dbt.utils import translate_aliases
from dbt.events.functions import fire_event
from dbt.events.types import NewConnectionOpening
from dbt.logger import GLOBAL_LOGGER as logger
from typing_extensions import Protocol
from dbt.dataclass_schema import (
dbtClassMixin, StrEnum, ExtensibleDbtClassMixin, HyphenatedDbtClassMixin,
@@ -102,7 +100,10 @@ class LazyHandle:
self.opener = opener
def resolve(self, connection: Connection) -> Connection:
fire_event(NewConnectionOpening(connection_state=connection.state))
logger.debug(
'Opening a new connection, currently in state {}'
.format(connection.state)
)
return self.opener(connection)
@@ -126,19 +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]]:
@@ -188,11 +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):
@@ -190,7 +185,6 @@ class SourceFile(BaseSourceFile):
nodes: List[str] = field(default_factory=list)
docs: List[str] = field(default_factory=list)
macros: List[str] = field(default_factory=list)
env_vars: List[str] = field(default_factory=list)
@classmethod
def big_seed(cls, path: FilePath) -> 'SourceFile':
@@ -223,7 +217,6 @@ class SchemaSourceFile(BaseSourceFile):
tests: Dict[str, Any] = field(default_factory=dict)
sources: List[str] = field(default_factory=list)
exposures: List[str] = field(default_factory=list)
metrics: List[str] = field(default_factory=list)
# node patches contain models, seeds, snapshots, analyses
ndp: List[str] = field(default_factory=list)
# any macro patches in this file by macro unique_id.
@@ -232,7 +225,6 @@ class SchemaSourceFile(BaseSourceFile):
# Patches are only against external sources. Sources can be
# created too, but those are in 'sources'
sop: List[SourceKey] = field(default_factory=list)
env_vars: Dict[str, Any] = field(default_factory=dict)
pp_dict: Optional[Dict[str, Any]] = None
pp_test_index: Optional[Dict[str, Any]] = None
@@ -255,7 +247,7 @@ class SchemaSourceFile(BaseSourceFile):
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
# Remove partial parsing specific data
for key in ('pp_test_index', 'pp_dict'):
for key in ('pp_files', 'pp_test_index', 'pp_dict'):
if key in dct:
del dct[key]
return dct
@@ -302,21 +294,5 @@ class SchemaSourceFile(BaseSourceFile):
test_ids.extend(self.tests[key][name])
return test_ids
def add_env_var(self, var, yaml_key, name):
if yaml_key not in self.env_vars:
self.env_vars[yaml_key] = {}
if name not in self.env_vars[yaml_key]:
self.env_vars[yaml_key][name] = []
if var not in self.env_vars[yaml_key][name]:
self.env_vars[yaml_key][name].append(var)
def delete_from_env_vars(self, yaml_key, name):
# We delete all vars for this yaml_key/name because the
# entry has been scheduled for reparsing.
if yaml_key in self.env_vars and name in self.env_vars[yaml_key]:
del self.env_vars[yaml_key][name]
if not self.env_vars[yaml_key]:
del self.env_vars[yaml_key]
AnySourceFile = Union[SchemaSourceFile, SourceFile]

View File

@@ -2,15 +2,13 @@ from dbt.contracts.graph.parsed import (
HasTestMetadata,
ParsedNode,
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedExposure,
ParsedMetric,
ParsedResource,
ParsedRPCNode,
ParsedSqlNode,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
ParsedSourceDefinition,
@@ -83,17 +81,11 @@ class CompiledModelNode(CompiledNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Model]})
# TODO: rm?
@dataclass
class CompiledRPCNode(CompiledNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.RPCCall]})
@dataclass
class CompiledSqlNode(CompiledNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.SqlOperation]})
@dataclass
class CompiledSeedNode(CompiledNode):
# keep this in sync with ParsedSeedNode!
@@ -115,22 +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
file_key_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:
@@ -143,7 +130,7 @@ class CompiledGenericTestNode(CompiledNode, HasTestMetadata):
)
CompiledTestNode = Union[CompiledSingularTestNode, CompiledGenericTestNode]
CompiledTestNode = Union[CompiledDataTestNode, CompiledSchemaTestNode]
PARSED_TYPES: Dict[Type[CompiledNode], Type[ParsedResource]] = {
@@ -151,11 +138,10 @@ PARSED_TYPES: Dict[Type[CompiledNode], Type[ParsedResource]] = {
CompiledModelNode: ParsedModelNode,
CompiledHookNode: ParsedHookNode,
CompiledRPCNode: ParsedRPCNode,
CompiledSqlNode: ParsedSqlNode,
CompiledSeedNode: ParsedSeedNode,
CompiledSnapshotNode: ParsedSnapshotNode,
CompiledSingularTestNode: ParsedSingularTestNode,
CompiledGenericTestNode: ParsedGenericTestNode,
CompiledDataTestNode: ParsedDataTestNode,
CompiledSchemaTestNode: ParsedSchemaTestNode,
}
@@ -164,11 +150,10 @@ COMPILED_TYPES: Dict[Type[ParsedResource], Type[CompiledNode]] = {
ParsedModelNode: CompiledModelNode,
ParsedHookNode: CompiledHookNode,
ParsedRPCNode: CompiledRPCNode,
ParsedSqlNode: CompiledSqlNode,
ParsedSeedNode: CompiledSeedNode,
ParsedSnapshotNode: CompiledSnapshotNode,
ParsedSingularTestNode: CompiledSingularTestNode,
ParsedGenericTestNode: CompiledGenericTestNode,
ParsedDataTestNode: CompiledDataTestNode,
ParsedSchemaTestNode: CompiledSchemaTestNode,
}
@@ -196,24 +181,22 @@ def parsed_instance_for(compiled: CompiledNode) -> ParsedResource:
NonSourceCompiledNode = Union[
CompiledAnalysisNode,
CompiledSingularTestNode,
CompiledDataTestNode,
CompiledModelNode,
CompiledHookNode,
CompiledRPCNode,
CompiledSqlNode,
CompiledGenericTestNode,
CompiledSchemaTestNode,
CompiledSeedNode,
CompiledSnapshotNode,
]
NonSourceParsedNode = Union[
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedRPCNode,
ParsedSqlNode,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
]
@@ -233,10 +216,8 @@ CompileResultNode = Union[
ParsedSourceDefinition,
]
# anything that participates in the graph: sources, exposures, metrics,
# or manifest nodes
# anything that participates in the graph: sources, exposures, manifest nodes
GraphMemberNode = Union[
CompileResultNode,
ParsedExposure,
ParsedMetric,
]

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
@@ -14,9 +14,9 @@ from dbt.contracts.graph.compiled import (
CompileResultNode, ManifestNode, NonSourceCompiledNode, GraphMemberNode
)
from dbt.contracts.graph.parsed import (
ParsedMacro, ParsedDocumentation,
ParsedSourceDefinition, ParsedExposure, ParsedMetric,
HasUniqueID, UnpatchedSourceDefinition, ManifestNodes
ParsedMacro, ParsedDocumentation, ParsedNodePatch, ParsedMacroPatch,
ParsedSourceDefinition, ParsedExposure, HasUniqueID,
UnpatchedSourceDefinition, ManifestNodes
)
from dbt.contracts.graph.unparsed import SourcePatch
from dbt.contracts.files import SourceFile, SchemaSourceFile, FileHash, AnySourceFile
@@ -26,11 +26,12 @@ 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.events.functions import fire_event
from dbt.events.types import MergedFromState
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.node_types import NodeType
from dbt.ui import line_wrap_message
from dbt import flags
@@ -96,23 +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():
@@ -169,45 +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(
@@ -260,7 +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):
@@ -292,7 +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
@@ -415,6 +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')
@@ -547,8 +546,6 @@ class ParsingInfo:
@dataclass
class ManifestStateCheck(dbtClassMixin):
vars_hash: FileHash = field(default_factory=FileHash.empty)
project_env_vars_hash: FileHash = field(default_factory=FileHash.empty)
profile_env_vars_hash: FileHash = field(default_factory=FileHash.empty)
profile_hash: FileHash = field(default_factory=FileHash.empty)
project_hashes: MutableMapping[str, FileHash] = field(default_factory=dict)
@@ -565,16 +562,16 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
macros: MutableMapping[str, ParsedMacro] = field(default_factory=dict)
docs: MutableMapping[str, ParsedDocumentation] = field(default_factory=dict)
exposures: MutableMapping[str, ParsedExposure] = field(default_factory=dict)
metrics: MutableMapping[str, ParsedMetric] = 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)
env_vars: MutableMapping[str, str] = 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}
)
@@ -584,9 +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}
)
@@ -633,9 +627,6 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
def update_exposure(self, new_exposure: ParsedExposure):
_update_into(self.exposures, new_exposure)
def update_metric(self, new_metric: ParsedMetric):
_update_into(self.metrics, new_metric)
def update_node(self, new_node: ManifestNode):
_update_into(self.nodes, new_node)
@@ -653,10 +644,6 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
k: v.to_dict(omit_none=False)
for k, v in self.exposures.items()
},
'metrics': {
k: v.to_dict(omit_none=False)
for k, v in self.metrics.items()
},
'nodes': {
k: v.to_dict(omit_none=False)
for k, v in self.nodes.items()
@@ -667,12 +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,
@@ -709,12 +710,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
def get_resource_fqns(self) -> Mapping[str, PathSet]:
resource_fqns: Dict[str, Set[Tuple[str, ...]]] = {}
all_resources = chain(
self.exposures.values(),
self.nodes.values(),
self.sources.values(),
self.metrics.values()
)
all_resources = chain(self.exposures.values(), self.nodes.values(), self.sources.values())
for resource in all_resources:
resource_type_plural = resource.resource_type.pluralize()
if resource_type_plural not in resource_fqns:
@@ -722,6 +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
@@ -735,6 +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()},
@@ -742,10 +793,9 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
macros={k: _deepcopy(v) for k, v in self.macros.items()},
docs={k: _deepcopy(v) for k, v in self.docs.items()},
exposures={k: _deepcopy(v) for k, v in self.exposures.items()},
metrics={k: _deepcopy(v) for k, v in self.metrics.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),
)
@@ -755,7 +805,6 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
self.nodes.values(),
self.sources.values(),
self.exposures.values(),
self.metrics.values(),
))
forward_edges, backward_edges = build_node_edges(edge_members)
self.child_map = forward_edges
@@ -777,7 +826,6 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
macros=self.macros,
docs=self.docs,
exposures=self.exposures,
metrics=self.metrics,
selectors=self.selectors,
metadata=self.metadata,
disabled=self.disabled,
@@ -797,8 +845,6 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
return self.sources[unique_id]
elif unique_id in self.exposures:
return self.exposures[unique_id]
elif unique_id in self.metrics:
return self.metrics[unique_id]
else:
# something terrible has happened
raise dbt.exceptions.InternalException(
@@ -832,15 +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:
@@ -858,7 +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
@@ -871,12 +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
@@ -888,24 +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
@@ -959,7 +996,9 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
# log up to 5 items
sample = list(islice(merged, 5))
fire_event(MergedFromState(nbr_merged=len(merged), sample=sample))
logger.debug(
f'Merged {len(merged)} items from state (sample: {sample})'
)
# Methods that were formerly in ParseResult
@@ -1025,17 +1064,11 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
self.exposures[exposure.unique_id] = exposure
source_file.exposures.append(exposure.unique_id)
def add_metric(self, source_file: SchemaSourceFile, metric: ParsedMetric):
_check_duplicates(metric, self.metrics)
self.metrics[metric.unique_id] = metric
source_file.metrics.append(metric.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)
@@ -1066,20 +1099,17 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
self.macros,
self.docs,
self.exposures,
self.metrics,
self.selectors,
self.disabled,
self.files,
self.metadata,
self.flat_graph,
self.state_check,
self.source_patches,
self.disabled,
self.env_vars,
self._disabled,
self._doc_lookup,
self._source_lookup,
self._ref_lookup,
self._disabled_lookup,
self._analysis_lookup,
)
return self.__class__, args
@@ -1097,7 +1127,7 @@ AnyManifest = Union[Manifest, MacroManifest]
@dataclass
@schema_version('manifest', 4)
@schema_version('manifest', 2)
class WritableManifest(ArtifactMixin):
nodes: Mapping[UniqueID, ManifestNode] = field(
metadata=dict(description=(
@@ -1124,18 +1154,13 @@ class WritableManifest(ArtifactMixin):
'The exposures defined in the dbt project and its dependencies'
))
)
metrics: Mapping[UniqueID, ParsedMetric] = field(
metadata=dict(description=(
'The metrics defined in the dbt project and its dependencies'
))
)
selectors: Mapping[UniqueID, Any] = field(
metadata=dict(description=(
'The selectors defined in selectors.yml'
))
)
disabled: Optional[Mapping[UniqueID, List[CompileResultNode]]] = field(metadata=dict(
description='A mapping of the disabled nodes in the target'
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

@@ -26,10 +26,11 @@ from dbt.contracts.graph.unparsed import (
UnparsedBaseNode, FreshnessThreshold, ExternalTable,
HasYamlMetadata, MacroArgument, UnparsedSourceDefinition,
UnparsedSourceTableDefinition, UnparsedColumn, TestDef,
ExposureOwner, ExposureType, MaturityType, MetricFilter
ExposureOwner, ExposureType, MaturityType
)
from dbt.contracts.util import Replaceable, AdditionalPropertiesMixin
from dbt.exceptions import warn_or_error
from dbt.logger import GLOBAL_LOGGER as logger # noqa
from dbt import flags
from dbt.node_types import NodeType
@@ -147,18 +148,27 @@ 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 = time.time()
self.created_at = int(time.time())
self.description = patch.description
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(
@@ -178,29 +188,10 @@ class ParsedNodeMandatory(
@dataclass
class NodeInfoMixin():
_event_status: Dict[str, Any] = field(default_factory=dict)
@property
def node_info(self):
node_info = {
"node_path": getattr(self, 'path', None),
"node_name": getattr(self, 'name', None),
"unique_id": getattr(self, 'unique_id', None),
"resource_type": str(getattr(self, 'resource_type', '')),
"materialized": self.config.get('materialized'),
"node_status": str(self._event_status.get('node_status')),
"node_started_at": self._event_status.get("started_at"),
"node_finished_at": self._event_status.get("finished_at")
}
return node_info
@dataclass
class ParsedNodeDefaults(NodeInfoMixin, ParsedNodeMandatory):
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)
@@ -211,8 +202,7 @@ class ParsedNodeDefaults(NodeInfoMixin, ParsedNodeMandatory):
build_path: Optional[str] = None
deferred: bool = False
unrendered_config: Dict[str, Any] = field(default_factory=dict)
created_at: float = field(default_factory=lambda: time.time())
config_call_dict: Dict[str, Any] = field(default_factory=dict)
created_at: int = field(default_factory=lambda: int(time.time()))
def write_node(self, target_path: str, subdirectory: str, payload: str):
if (os.path.basename(self.path) ==
@@ -239,13 +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']
if '_event_status' in dct:
del dct['_event_status']
return dct
@classmethod
def _deserialize(cls, dct: Dict[str, int]):
# The serialized ParsedNodes do not differ from each other
@@ -260,13 +243,11 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
return ParsedSeedNode.from_dict(dct)
elif resource_type == 'rpc':
return ParsedRPCNode.from_dict(dct)
elif resource_type == 'sql':
return ParsedSqlNode.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':
@@ -277,16 +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
@@ -363,17 +338,11 @@ class ParsedModelNode(ParsedNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Model]})
# TODO: rm?
@dataclass
class ParsedRPCNode(ParsedNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.RPCCall]})
@dataclass
class ParsedSqlNode(ParsedNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.SqlOperation]})
def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
# for seeds, we check the hashes. If the hashes are different types,
# no match. If the hashes are both the same 'path', log a warning and
@@ -430,9 +399,6 @@ class ParsedSeedNode(ParsedNode):
@dataclass
class TestMetadata(dbtClassMixin, Replaceable):
name: str
# kwargs are the args that are left in the test builder after
# removing configs. They are set from the test builder when
# the test node is created.
kwargs: Dict[str, Any] = field(default_factory=dict)
namespace: Optional[str] = None
@@ -443,26 +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
@property
def test_node_type(self):
return 'singular'
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
file_key_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:
@@ -474,10 +431,6 @@ class ParsedGenericTestNode(ParsedNode, HasTestMetadata):
True
)
@property
def test_node_type(self):
return 'generic'
@dataclass
class IntermediateSnapshotNode(ParsedNode):
@@ -503,7 +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
@@ -533,15 +485,23 @@ class ParsedMacro(UnparsedBaseNode, HasUniqueID):
docs: Docs = field(default_factory=Docs)
patch_path: Optional[str] = None
arguments: List[MacroArgument] = field(default_factory=list)
created_at: float = field(default_factory=lambda: time.time())
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
self.created_at = time.time()
self.created_at = int(time.time())
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:
@@ -628,11 +588,12 @@ class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
@dataclass
class ParsedSourceMandatory(
class ParsedSourceDefinition(
UnparsedBaseNode,
HasUniqueID,
HasRelationMetadata,
HasFqn,
):
name: str
source_name: str
@@ -640,13 +601,6 @@ class ParsedSourceMandatory(
loader: str
identifier: str
resource_type: NodeType = field(metadata={'restrict': [NodeType.Source]})
@dataclass
class ParsedSourceDefinition(
NodeInfoMixin,
ParsedSourceMandatory
):
quoting: Quoting = field(default_factory=Quoting)
loaded_at_field: Optional[str] = None
freshness: Optional[FreshnessThreshold] = None
@@ -660,12 +614,7 @@ class ParsedSourceDefinition(
patch_path: Optional[Path] = None
unrendered_config: Dict[str, Any] = field(default_factory=dict)
relation_name: Optional[str] = None
created_at: float = field(default_factory=lambda: time.time())
def __post_serialize__(self, dct):
if '_event_status' in dct:
del dct['_event_status']
return dct
created_at: int = field(default_factory=lambda: int(time.time()))
def same_database_representation(
self, other: 'ParsedSourceDefinition'
@@ -743,7 +692,7 @@ class ParsedSourceDefinition(
@property
def depends_on(self):
return DependsOn(macros=[], nodes=[])
return {'nodes': []}
@property
def refs(self):
@@ -776,7 +725,7 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
depends_on: DependsOn = field(default_factory=DependsOn)
refs: List[List[str]] = field(default_factory=list)
sources: List[List[str]] = field(default_factory=list)
created_at: float = field(default_factory=lambda: time.time())
created_at: int = field(default_factory=lambda: int(time.time()))
@property
def depends_on_nodes(self):
@@ -822,89 +771,13 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
)
@dataclass
class ParsedMetric(UnparsedBaseNode, HasUniqueID, HasFqn):
model: str
name: str
description: str
label: str
type: str
sql: Optional[str]
timestamp: Optional[str]
filters: List[MetricFilter]
time_grains: List[str]
dimensions: List[str]
resource_type: NodeType = NodeType.Metric
meta: Dict[str, Any] = field(default_factory=dict)
tags: List[str] = field(default_factory=list)
sources: List[List[str]] = field(default_factory=list)
depends_on: DependsOn = field(default_factory=DependsOn)
refs: List[List[str]] = field(default_factory=list)
created_at: float = field(default_factory=lambda: time.time())
@property
def depends_on_nodes(self):
return self.depends_on.nodes
@property
def search_name(self):
return self.name
def same_model(self, old: 'ParsedMetric') -> bool:
return self.model == old.model
def same_dimensions(self, old: 'ParsedMetric') -> bool:
return self.dimensions == old.dimensions
def same_filters(self, old: 'ParsedMetric') -> bool:
return self.filters == old.filters
def same_description(self, old: 'ParsedMetric') -> bool:
return self.description == old.description
def same_label(self, old: 'ParsedMetric') -> bool:
return self.label == old.label
def same_type(self, old: 'ParsedMetric') -> bool:
return self.type == old.type
def same_sql(self, old: 'ParsedMetric') -> bool:
return self.sql == old.sql
def same_timestamp(self, old: 'ParsedMetric') -> bool:
return self.timestamp == old.timestamp
def same_time_grains(self, old: 'ParsedMetric') -> bool:
return self.time_grains == old.time_grains
def same_contents(self, old: Optional['ParsedMetric']) -> bool:
# existing when it didn't before is a change!
# metadata/tags changes are not "changes"
if old is None:
return True
return (
self.same_model(old) and
self.same_dimensions(old) and
self.same_filters(old) and
self.same_description(old) and
self.same_label(old) and
self.same_type(old) and
self.same_sql(old) and
self.same_timestamp(old) and
self.same_time_grains(old) and
True
)
ManifestNodes = Union[
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedRPCNode,
ParsedSqlNode,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
]
@@ -915,6 +788,5 @@ ParsedResource = Union[
ParsedMacro,
ParsedNode,
ParsedExposure,
ParsedMetric,
ParsedSourceDefinition,
]

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
@@ -60,7 +55,6 @@ class UnparsedNode(UnparsedBaseNode, HasSQL):
NodeType.Operation,
NodeType.Seed,
NodeType.RPCCall,
NodeType.SqlOperation,
]})
@property
@@ -132,17 +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
@@ -154,7 +143,7 @@ class MacroArgument(dbtClassMixin):
@dataclass
class UnparsedMacroUpdate(HasConfig, HasDocs, HasYamlMetadata):
class UnparsedMacroUpdate(HasDocs, HasYamlMetadata):
arguments: List[MacroArgument] = field(default_factory=list)
@@ -168,25 +157,20 @@ class TimePeriod(StrEnum):
@dataclass
class Time(dbtClassMixin, Mergeable):
count: Optional[int] = None
period: Optional[TimePeriod] = None
class Time(dbtClassMixin, Replaceable):
count: int
period: TimePeriod
def exceeded(self, actual_age: float) -> bool:
if self.period is None or self.count is None:
return False
kwargs: Dict[str, int] = {self.period.plural(): self.count}
kwargs = {self.period.plural(): self.count}
difference = timedelta(**kwargs).total_seconds()
return actual_age > difference
def __bool__(self):
return self.count is not None and self.period is not None
@dataclass
class FreshnessThreshold(dbtClassMixin, Mergeable):
warn_after: Optional[Time] = field(default_factory=Time)
error_after: Optional[Time] = field(default_factory=Time)
warn_after: Optional[Time] = None
error_after: Optional[Time] = None
filter: Optional[str] = None
def status(self, age: float) -> "dbt.contracts.results.FreshnessStatus":
@@ -199,7 +183,7 @@ class FreshnessThreshold(dbtClassMixin, Mergeable):
return FreshnessStatus.Pass
def __bool__(self):
return bool(self.warn_after) or bool(self.error_after)
return self.warn_after is not None or self.error_after is not None
@dataclass
@@ -277,7 +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':
@@ -285,7 +268,7 @@ class UnparsedSourceDefinition(dbtClassMixin, Replaceable):
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
if 'freshness' not in dct and self.freshness is None:
if 'freshnewss' not in dct and self.freshness is None:
dct['freshness'] = None
return dct
@@ -446,27 +429,3 @@ class UnparsedExposure(dbtClassMixin, Replaceable):
tags: List[str] = field(default_factory=list)
url: Optional[str] = None
depends_on: List[str] = field(default_factory=list)
@dataclass
class MetricFilter(dbtClassMixin, Replaceable):
field: str
operator: str
# TODO : Can we make this Any?
value: str
@dataclass
class UnparsedMetric(dbtClassMixin, Replaceable):
model: str
name: str
label: str
type: str
description: str = ''
sql: Optional[str] = None
timestamp: Optional[str] = None
time_grains: List[str] = field(default_factory=list)
dimensions: List[str] = field(default_factory=list)
filters: List[MetricFilter] = field(default_factory=list)
meta: Dict[str, Any] = field(default_factory=dict)
tags: List[str] = field(default_factory=list)

View File

@@ -1,6 +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,
@@ -18,18 +21,6 @@ DEFAULT_SEND_ANONYMOUS_USAGE_STATS = True
class Name(ValidatedStringMixin):
ValidationRegex = r'^[^\d\W]\w*$'
@classmethod
def is_valid(cls, value: Any) -> bool:
if not isinstance(value, str):
return False
try:
cls.validate(value)
except ValidationError:
return False
return True
register_pattern(Name, r'^[^\d\W]\w*$')
@@ -185,10 +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
@@ -198,7 +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)
@@ -241,22 +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[str] = 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
indirect_selection: Optional[str] = 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

@@ -11,11 +11,10 @@ from dbt.contracts.util import (
schema_version,
)
from dbt.exceptions import InternalException
from dbt.events.functions import fire_event
from dbt.events.types import TimingInfoCollected
from dbt.logger import (
TimingProcessor,
JsonOnly,
GLOBAL_LOGGER as logger,
)
from dbt.utils import lowercase
from dbt.dataclass_schema import dbtClassMixin, StrEnum
@@ -55,13 +54,7 @@ class collect_timing_info:
def __exit__(self, exc_type, exc_value, traceback):
self.timing_info.end()
with JsonOnly(), TimingProcessor(self.timing_info):
fire_event(TimingInfoCollected())
class RunningStatus(StrEnum):
Started = 'started'
Compiling = 'compiling'
Executing = 'executing'
logger.debug('finished collecting timing info')
class NodeStatus(StrEnum):
@@ -192,7 +185,7 @@ class RunExecutionResult(
@dataclass
@schema_version('run-results', 4)
@schema_version('run-results', 2)
class RunResultsArtifact(ExecutionResult, ArtifactMixin):
results: Sequence[RunResultOutput]
args: Dict[str, Any] = field(default_factory=dict)
@@ -292,9 +285,6 @@ class SourceFreshnessOutput(dbtClassMixin):
status: FreshnessStatus
criteria: FreshnessThreshold
adapter_response: Dict[str, Any]
timing: List[TimingInfo]
thread_id: str
execution_time: float
@dataclass
@@ -343,10 +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
)
@@ -376,7 +363,7 @@ class FreshnessResult(ExecutionResult):
@dataclass
@schema_version('sources', 3)
@schema_version('sources', 1)
class FreshnessExecutionResultArtifact(
ArtifactMixin,
VersionedSchema,

815
core/dbt/contracts/rpc.py Normal file
View File

@@ -0,0 +1,815 @@
import enum
import os
import uuid
from dataclasses import dataclass, field
from datetime import datetime, timedelta
from typing import Optional, Union, List, Any, Dict, Type, Sequence
from dbt.dataclass_schema import dbtClassMixin, StrEnum
from dbt.contracts.graph.compiled import CompileResultNode
from dbt.contracts.graph.manifest import WritableManifest
from dbt.contracts.results import (
RunResult, RunResultsArtifact, TimingInfo,
CatalogArtifact,
CatalogResults,
ExecutionResult,
FreshnessExecutionResultArtifact,
FreshnessResult,
RunOperationResult,
RunOperationResultsArtifact,
RunExecutionResult,
)
from dbt.contracts.util import VersionedSchema, schema_version
from dbt.exceptions import InternalException
from dbt.logger import LogMessage
from dbt.utils import restrict_to
TaskTags = Optional[Dict[str, Any]]
TaskID = uuid.UUID
# Inputs
@dataclass
class RPCParameters(dbtClassMixin):
task_tags: TaskTags
timeout: Optional[float]
@classmethod
def __pre_deserialize__(cls, data, omit_none=True):
data = super().__pre_deserialize__(data)
if 'timeout' not in data:
data['timeout'] = None
if 'task_tags' not in data:
data['task_tags'] = None
return data
@dataclass
class RPCExecParameters(RPCParameters):
name: str
sql: str
macros: Optional[str] = None
@dataclass
class RPCCompileParameters(RPCParameters):
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
@dataclass
class RPCListParameters(RPCParameters):
resource_types: Optional[List[str]] = None
models: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
select: Union[None, str, List[str]] = None
selector: Optional[str] = None
output: Optional[str] = 'json'
@dataclass
class RPCRunParameters(RPCParameters):
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
defer: Optional[bool] = None
@dataclass
class RPCSnapshotParameters(RPCParameters):
threads: Optional[int] = None
select: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
selector: Optional[str] = None
state: Optional[str] = None
@dataclass
class RPCTestParameters(RPCCompileParameters):
data: bool = False
schema: bool = False
state: Optional[str] = None
defer: Optional[bool] = None
@dataclass
class RPCSeedParameters(RPCParameters):
threads: Optional[int] = None
select: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
selector: Optional[str] = None
show: bool = False
state: Optional[str] = None
@dataclass
class RPCDocsGenerateParameters(RPCParameters):
compile: bool = True
state: Optional[str] = None
@dataclass
class RPCBuildParameters(RPCParameters):
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
defer: Optional[bool] = None
@dataclass
class RPCCliParameters(RPCParameters):
cli: str
@dataclass
class RPCDepsParameters(RPCParameters):
pass
@dataclass
class KillParameters(RPCParameters):
task_id: TaskID
@dataclass
class PollParameters(RPCParameters):
request_token: TaskID
logs: bool = True
logs_start: int = 0
@dataclass
class PSParameters(RPCParameters):
active: bool = True
completed: bool = False
@dataclass
class StatusParameters(RPCParameters):
pass
@dataclass
class GCSettings(dbtClassMixin):
# start evicting the longest-ago-ended tasks here
maxsize: int
# start evicting all tasks before now - auto_reap_age when we have this
# many tasks in the table
reapsize: int
# a positive timedelta indicating how far back we should go
auto_reap_age: timedelta
@dataclass
class GCParameters(RPCParameters):
"""The gc endpoint takes three arguments, any of which may be present:
- task_ids: An optional list of task ID UUIDs to try to GC
- before: If provided, should be a datetime string. All tasks that finished
before that datetime will be GCed
- settings: If provided, should be a GCSettings object in JSON form. It
will be applied to the task manager before GC starts. By default the
existing gc settings remain.
"""
task_ids: Optional[List[TaskID]] = None
before: Optional[datetime] = None
settings: Optional[GCSettings] = None
@dataclass
class RPCRunOperationParameters(RPCParameters):
macro: str
args: Dict[str, Any] = field(default_factory=dict)
@dataclass
class RPCSourceFreshnessParameters(RPCParameters):
threads: Optional[int] = None
select: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
selector: Optional[str] = None
@dataclass
class GetManifestParameters(RPCParameters):
pass
# Outputs
@dataclass
class RemoteResult(VersionedSchema):
logs: List[LogMessage]
@dataclass
@schema_version('remote-list-results', 1)
class RemoteListResults(RemoteResult):
output: List[Any]
generated_at: datetime = field(default_factory=datetime.utcnow)
@dataclass
@schema_version('remote-deps-result', 1)
class RemoteDepsResult(RemoteResult):
generated_at: datetime = field(default_factory=datetime.utcnow)
@dataclass
@schema_version('remote-catalog-result', 1)
class RemoteCatalogResults(CatalogResults, RemoteResult):
generated_at: datetime = field(default_factory=datetime.utcnow)
def write(self, path: str):
artifact = CatalogArtifact.from_results(
generated_at=self.generated_at,
nodes=self.nodes,
sources=self.sources,
compile_results=self._compile_results,
errors=self.errors,
)
artifact.write(path)
@dataclass
class RemoteCompileResultMixin(RemoteResult):
raw_sql: str
compiled_sql: str
node: CompileResultNode
timing: List[TimingInfo]
@dataclass
@schema_version('remote-compile-result', 1)
class RemoteCompileResult(RemoteCompileResultMixin):
generated_at: datetime = field(default_factory=datetime.utcnow)
@property
def error(self):
return None
@dataclass
@schema_version('remote-execution-result', 1)
class RemoteExecutionResult(ExecutionResult, RemoteResult):
results: Sequence[RunResult]
args: Dict[str, Any] = field(default_factory=dict)
generated_at: datetime = field(default_factory=datetime.utcnow)
def write(self, path: str):
writable = RunResultsArtifact.from_execution_results(
generated_at=self.generated_at,
results=self.results,
elapsed_time=self.elapsed_time,
args=self.args,
)
writable.write(path)
@classmethod
def from_local_result(
cls,
base: RunExecutionResult,
logs: List[LogMessage],
) -> 'RemoteExecutionResult':
return cls(
generated_at=base.generated_at,
results=base.results,
elapsed_time=base.elapsed_time,
args=base.args,
logs=logs,
)
@dataclass
class ResultTable(dbtClassMixin):
column_names: List[str]
rows: List[Any]
@dataclass
@schema_version('remote-run-operation-result', 1)
class RemoteRunOperationResult(RunOperationResult, RemoteResult):
generated_at: datetime = field(default_factory=datetime.utcnow)
@classmethod
def from_local_result(
cls,
base: RunOperationResultsArtifact,
logs: List[LogMessage],
) -> 'RemoteRunOperationResult':
return cls(
generated_at=base.metadata.generated_at,
results=base.results,
elapsed_time=base.elapsed_time,
success=base.success,
logs=logs,
)
def write(self, path: str):
writable = RunOperationResultsArtifact.from_success(
success=self.success,
generated_at=self.generated_at,
elapsed_time=self.elapsed_time,
)
writable.write(path)
@dataclass
@schema_version('remote-freshness-result', 1)
class RemoteFreshnessResult(FreshnessResult, RemoteResult):
@classmethod
def from_local_result(
cls,
base: FreshnessResult,
logs: List[LogMessage],
) -> 'RemoteFreshnessResult':
return cls(
metadata=base.metadata,
results=base.results,
elapsed_time=base.elapsed_time,
logs=logs,
)
def write(self, path: str):
writable = FreshnessExecutionResultArtifact.from_result(base=self)
writable.write(path)
@dataclass
@schema_version('remote-run-result', 1)
class RemoteRunResult(RemoteCompileResultMixin):
table: ResultTable
generated_at: datetime = field(default_factory=datetime.utcnow)
RPCResult = Union[
RemoteCompileResult,
RemoteExecutionResult,
RemoteFreshnessResult,
RemoteCatalogResults,
RemoteDepsResult,
RemoteRunOperationResult,
]
# GC types
class GCResultState(StrEnum):
Deleted = 'deleted' # successful GC
Missing = 'missing' # nothing to GC
Running = 'running' # can't GC
@dataclass
@schema_version('remote-gc-result', 1)
class GCResult(RemoteResult):
logs: List[LogMessage] = field(default_factory=list)
deleted: List[TaskID] = field(default_factory=list)
missing: List[TaskID] = field(default_factory=list)
running: List[TaskID] = field(default_factory=list)
def add_result(self, task_id: TaskID, state: GCResultState):
if state == GCResultState.Missing:
self.missing.append(task_id)
elif state == GCResultState.Running:
self.running.append(task_id)
elif state == GCResultState.Deleted:
self.deleted.append(task_id)
else:
raise InternalException(
f'Got invalid state in add_result: {state}'
)
# Task management types
class TaskHandlerState(StrEnum):
NotStarted = 'not started'
Initializing = 'initializing'
Running = 'running'
Success = 'success'
Error = 'error'
Killed = 'killed'
Failed = 'failed'
def __lt__(self, other) -> bool:
"""A logical ordering for TaskHandlerState:
NotStarted < Initializing < Running < (Success, Error, Killed, Failed)
"""
if not isinstance(other, TaskHandlerState):
raise TypeError('cannot compare to non-TaskHandlerState')
order = (self.NotStarted, self.Initializing, self.Running)
smaller = set()
for value in order:
smaller.add(value)
if self == value:
return other not in smaller
return False
def __le__(self, other) -> bool:
# so that ((Success <= Error) is True)
return ((self < other) or
(self == other) or
(self.finished and other.finished))
def __gt__(self, other) -> bool:
if not isinstance(other, TaskHandlerState):
raise TypeError('cannot compare to non-TaskHandlerState')
order = (self.NotStarted, self.Initializing, self.Running)
smaller = set()
for value in order:
smaller.add(value)
if self == value:
return other in smaller
return other in smaller
def __ge__(self, other) -> bool:
# so that ((Success <= Error) is True)
return ((self > other) or
(self == other) or
(self.finished and other.finished))
@property
def finished(self) -> bool:
return self in (self.Error, self.Success, self.Killed, self.Failed)
@dataclass
class TaskTiming(dbtClassMixin):
state: TaskHandlerState
start: Optional[datetime]
end: Optional[datetime]
elapsed: Optional[float]
# These ought to be defaults but superclass order doesn't
# allow that to work
@classmethod
def __pre_deserialize__(cls, data):
data = super().__pre_deserialize__(data)
for field_name in ('start', 'end', 'elapsed'):
if field_name not in data:
data[field_name] = None
return data
@dataclass
class TaskRow(TaskTiming):
task_id: TaskID
request_source: str
method: str
request_id: Union[str, int]
tags: TaskTags = None
timeout: Optional[float] = None
@dataclass
@schema_version('remote-ps-result', 1)
class PSResult(RemoteResult):
rows: List[TaskRow]
class KillResultStatus(StrEnum):
Missing = 'missing'
NotStarted = 'not_started'
Killed = 'killed'
Finished = 'finished'
@dataclass
@schema_version('remote-kill-result', 1)
class KillResult(RemoteResult):
state: KillResultStatus = KillResultStatus.Missing
logs: List[LogMessage] = field(default_factory=list)
@dataclass
@schema_version('remote-manifest-result', 1)
class GetManifestResult(RemoteResult):
manifest: Optional[WritableManifest] = None
# this is kind of carefuly structured: BlocksManifestTasks is implied by
# RequiresConfigReloadBefore and RequiresManifestReloadAfter
class RemoteMethodFlags(enum.Flag):
Empty = 0
BlocksManifestTasks = 1
RequiresConfigReloadBefore = 3
RequiresManifestReloadAfter = 5
Builtin = 8
# Polling types
@dataclass
class PollResult(RemoteResult, TaskTiming):
state: TaskHandlerState
tags: TaskTags
start: Optional[datetime]
end: Optional[datetime]
elapsed: Optional[float]
# These ought to be defaults but superclass order doesn't
# allow that to work
@classmethod
def __pre_deserialize__(cls, data):
data = super().__pre_deserialize__(data)
for field_name in ('start', 'end', 'elapsed'):
if field_name not in data:
data[field_name] = None
return data
@dataclass
@schema_version('poll-remote-deps-result', 1)
class PollRemoteEmptyCompleteResult(PollResult, RemoteResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
)
generated_at: datetime = field(default_factory=datetime.utcnow)
@classmethod
def from_result(
cls: Type['PollRemoteEmptyCompleteResult'],
base: RemoteDepsResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollRemoteEmptyCompleteResult':
return cls(
logs=logs,
tags=tags,
state=timing.state,
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
generated_at=base.generated_at
)
@dataclass
@schema_version('poll-remote-killed-result', 1)
class PollKilledResult(PollResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Killed),
)
@dataclass
@schema_version('poll-remote-execution-result', 1)
class PollExecuteCompleteResult(
RemoteExecutionResult,
PollResult,
):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollExecuteCompleteResult'],
base: RemoteExecutionResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollExecuteCompleteResult':
return cls(
results=base.results,
elapsed_time=base.elapsed_time,
logs=logs,
tags=tags,
state=timing.state,
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
generated_at=base.generated_at,
)
@dataclass
@schema_version('poll-remote-compile-result', 1)
class PollCompileCompleteResult(
RemoteCompileResult,
PollResult,
):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollCompileCompleteResult'],
base: RemoteCompileResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollCompileCompleteResult':
return cls(
raw_sql=base.raw_sql,
compiled_sql=base.compiled_sql,
node=base.node,
timing=base.timing,
logs=logs,
tags=tags,
state=timing.state,
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
generated_at=base.generated_at
)
@dataclass
@schema_version('poll-remote-run-result', 1)
class PollRunCompleteResult(
RemoteRunResult,
PollResult,
):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollRunCompleteResult'],
base: RemoteRunResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollRunCompleteResult':
return cls(
raw_sql=base.raw_sql,
compiled_sql=base.compiled_sql,
node=base.node,
timing=base.timing,
logs=logs,
table=base.table,
tags=tags,
state=timing.state,
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
generated_at=base.generated_at
)
@dataclass
@schema_version('poll-remote-run-operation-result', 1)
class PollRunOperationCompleteResult(
RemoteRunOperationResult,
PollResult,
):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollRunOperationCompleteResult'],
base: RemoteRunOperationResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollRunOperationCompleteResult':
return cls(
success=base.success,
results=base.results,
generated_at=base.generated_at,
elapsed_time=base.elapsed_time,
logs=logs,
tags=tags,
state=timing.state,
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
)
@dataclass
@schema_version('poll-remote-catalog-result', 1)
class PollCatalogCompleteResult(RemoteCatalogResults, PollResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollCatalogCompleteResult'],
base: RemoteCatalogResults,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollCatalogCompleteResult':
return cls(
nodes=base.nodes,
sources=base.sources,
generated_at=base.generated_at,
errors=base.errors,
_compile_results=base._compile_results,
logs=logs,
tags=tags,
state=timing.state,
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
)
@dataclass
@schema_version('poll-remote-in-progress-result', 1)
class PollInProgressResult(PollResult):
pass
@dataclass
@schema_version('poll-remote-get-manifest-result', 1)
class PollGetManifestResult(GetManifestResult, PollResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollGetManifestResult'],
base: GetManifestResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollGetManifestResult':
return cls(
manifest=base.manifest,
logs=logs,
tags=tags,
state=timing.state,
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
)
@dataclass
@schema_version('poll-remote-freshness-result', 1)
class PollFreshnessResult(RemoteFreshnessResult, PollResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollFreshnessResult'],
base: RemoteFreshnessResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollFreshnessResult':
return cls(
logs=logs,
tags=tags,
state=timing.state,
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
metadata=base.metadata,
results=base.results,
elapsed_time=base.elapsed_time,
)
# Manifest parsing types
class ManifestStatus(StrEnum):
Init = 'init'
Compiling = 'compiling'
Ready = 'ready'
Error = 'error'
@dataclass
@schema_version('remote-status-result', 1)
class LastParse(RemoteResult):
state: ManifestStatus = ManifestStatus.Init
logs: List[LogMessage] = field(default_factory=list)
error: Optional[Dict[str, Any]] = None
timestamp: datetime = field(default_factory=datetime.utcnow)
pid: int = field(default_factory=os.getpid)

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

@@ -1,88 +0,0 @@
import uuid
from dataclasses import dataclass, field
from datetime import datetime
from typing import Optional, List, Any, Dict, Sequence
from dbt.dataclass_schema import dbtClassMixin
from dbt.contracts.graph.compiled import CompileResultNode
from dbt.contracts.results import (
RunResult, RunResultsArtifact, TimingInfo,
ExecutionResult,
RunExecutionResult,
)
from dbt.contracts.util import VersionedSchema, schema_version
from dbt.logger import LogMessage
TaskTags = Optional[Dict[str, Any]]
TaskID = uuid.UUID
# Outputs
@dataclass
class RemoteResult(VersionedSchema):
logs: List[LogMessage]
@dataclass
class RemoteCompileResultMixin(RemoteResult):
raw_sql: str
compiled_sql: str
node: CompileResultNode
timing: List[TimingInfo]
@dataclass
@schema_version('remote-compile-result', 1)
class RemoteCompileResult(RemoteCompileResultMixin):
generated_at: datetime = field(default_factory=datetime.utcnow)
@property
def error(self):
return None
@dataclass
@schema_version('remote-execution-result', 1)
class RemoteExecutionResult(ExecutionResult, RemoteResult):
results: Sequence[RunResult]
args: Dict[str, Any] = field(default_factory=dict)
generated_at: datetime = field(default_factory=datetime.utcnow)
def write(self, path: str):
writable = RunResultsArtifact.from_execution_results(
generated_at=self.generated_at,
results=self.results,
elapsed_time=self.elapsed_time,
args=self.args,
)
writable.write(path)
@classmethod
def from_local_result(
cls,
base: RunExecutionResult,
logs: List[LogMessage],
) -> 'RemoteExecutionResult':
return cls(
generated_at=base.generated_at,
results=base.results,
elapsed_time=base.elapsed_time,
args=base.args,
logs=logs,
)
@dataclass
class ResultTable(dbtClassMixin):
column_names: List[str]
rows: List[Any]
@dataclass
@schema_version('remote-run-result', 1)
class RemoteRunResult(RemoteCompileResultMixin):
table: ResultTable
generated_at: datetime = field(default_factory=datetime.utcnow)

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
@@ -9,22 +8,11 @@ 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():
try:
# we want to bail with an error if schema versions don't match
self.manifest = WritableManifest.read_and_check_versions(str(manifest_path))
self.manifest = WritableManifest.read(str(manifest_path))
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:
# we want to bail with an error if schema versions don't match
self.results = RunResultsArtifact.read_and_check_versions(str(results_path))
except IncompatibleSchemaException as exc:
exc.add_filename(str(results_path))
raise

View File

@@ -9,10 +9,9 @@ from dbt.clients.system import write_json, read_json
from dbt.exceptions import (
InternalException,
RuntimeException,
IncompatibleSchemaException
)
from dbt.version import __version__
from dbt.events.functions import get_invocation_id
from dbt.tracking import get_invocation_id
from dbt.dataclass_schema import dbtClassMixin
SourceKey = Tuple[str, str]
@@ -159,8 +158,6 @@ def get_metadata_env() -> Dict[str, str]:
}
# This is used in the ManifestMetadata, RunResultsMetadata, RunOperationResultMetadata,
# FreshnessMetadata, and CatalogMetadata classes
@dataclasses.dataclass
class BaseArtifactMetadata(dbtClassMixin):
dbt_schema_version: str
@@ -173,24 +170,7 @@ 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
# This is used as a class decorator to set the schema_version in the
# 'dbt_schema_version' class attribute. (It's copied into the metadata objects.)
# Name attributes of SchemaVersion in classes with the 'schema_version' decorator:
# manifest
# run-results
# run-operation-result
# sources
# catalog
# remote-compile-result
# remote-execution-result
# remote-run-result
def schema_version(name: str, version: int):
def inner(cls: Type[VersionedSchema]):
cls.dbt_schema_version = SchemaVersion(
@@ -201,7 +181,6 @@ def schema_version(name: str, version: int):
return inner
# This is used in the ArtifactMixin and RemoteResult classes
@dataclasses.dataclass
class VersionedSchema(dbtClassMixin):
dbt_schema_version: ClassVar[SchemaVersion]
@@ -213,30 +192,6 @@ class VersionedSchema(dbtClassMixin):
result['$id'] = str(cls.dbt_schema_version)
return result
@classmethod
def read_and_check_versions(cls, path: str):
try:
data = read_json(path)
except (EnvironmentError, ValueError) as exc:
raise RuntimeException(
f'Could not read {cls.__name__} at "{path}" as JSON: {exc}'
) from exc
# Check metadata version. There is a class variable 'dbt_schema_version', but
# that doesn't show up in artifacts, where it only exists in the 'metadata'
# dictionary.
if hasattr(cls, 'dbt_schema_version'):
if 'metadata' in data and 'dbt_schema_version' in data['metadata']:
previous_schema_version = data['metadata']['dbt_schema_version']
# cls.dbt_schema_version is a SchemaVersion object
if str(cls.dbt_schema_version) != previous_schema_version:
raise IncompatibleSchemaException(
expected=str(cls.dbt_schema_version),
found=previous_schema_version
)
return cls.from_dict(data) # type: ignore
T = TypeVar('T', bound='ArtifactMixin')
@@ -244,8 +199,6 @@ T = TypeVar('T', bound='ArtifactMixin')
# metadata should really be a Generic[T_M] where T_M is a TypeVar bound to
# BaseArtifactMetadata. Unfortunately this isn't possible due to a mypy issue:
# https://github.com/python/mypy/issues/7520
# This is used in the WritableManifest, RunResultsArtifact, RunOperationResultsArtifact,
# and CatalogArtifact
@dataclasses.dataclass(init=False)
class ArtifactMixin(VersionedSchema, Writable, Readable):
metadata: BaseArtifactMetadata

View File

@@ -22,7 +22,7 @@ class DateTimeSerialization(SerializationStrategy):
out = value.isoformat()
# Assume UTC if timezone is missing
if value.tzinfo is None:
out += "Z"
out = out + "Z"
return out
def deserialize(self, value):

View File

@@ -36,43 +36,99 @@ class DBTDeprecation:
if self.name not in active_deprecations:
desc = self.description.format(**kwargs)
msg = ui.line_wrap_message(
desc, prefix='Deprecated functionality\n\n'
desc, prefix='* Deprecation Warning: '
)
dbt.exceptions.warn_or_error(msg, log_fmt=ui.warning_tag('{}'))
dbt.exceptions.warn_or_error(msg)
self.track_deprecation_warn()
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):
class NotADictionaryDeprecation(DBTDeprecation):
_name = 'not-a-dictionary'
_description = '''\
The `{deprecated_path}` config has been renamed to `{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 ConfigSourcePathDeprecation(ConfigPathDeprecation):
_name = 'project-config-source-paths'
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.
class ConfigDataPathDeprecation(ConfigPathDeprecation):
_name = 'project-config-data-paths'
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}
'''
_adapter_renamed_description = """\
@@ -113,10 +169,13 @@ def warn(name, *args, **kwargs):
active_deprecations: Set[str] = set()
deprecations_list: List[DBTDeprecation] = [
ConfigSourcePathDeprecation(),
ConfigDataPathDeprecation(),
PackageInstallPathDeprecation(),
PackageRedirectDeprecation()
DispatchPackagesDeprecation(),
MaterializationReturnDeprecation(),
NotADictionaryDeprecation(),
ColumnQuotingDeprecation(),
ModelsKeyNonModelDeprecation(),
ExecuteMacrosReleaseDeprecation(),
AdapterMacroDeprecation(),
]
deprecations: Dict[str, DBTDeprecation] = {

View File

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

View File

@@ -6,8 +6,7 @@ from typing import List, Optional, Generic, TypeVar
from dbt.clients import system
from dbt.contracts.project import ProjectPackageMetadata
from dbt.events.functions import fire_event
from dbt.events.types import DepsSetDownloadDirectory
from dbt.logger import GLOBAL_LOGGER as logger
DOWNLOADS_PATH = None
@@ -32,7 +31,7 @@ def downloads_directory():
remove_downloads = True
system.make_directory(DOWNLOADS_PATH)
fire_event(DepsSetDownloadDirectory(path=DOWNLOADS_PATH))
logger.debug("Set downloads directory='{}'".format(DOWNLOADS_PATH))
yield DOWNLOADS_PATH
@@ -92,7 +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

@@ -12,8 +12,7 @@ from dbt.deps.base import PinnedPackage, UnpinnedPackage, get_downloads_path
from dbt.exceptions import (
ExecutableError, warn_or_error, raise_dependency_error
)
from dbt.events.functions import fire_event
from dbt.events.types import EnsureGitInstalled
from dbt.logger import GLOBAL_LOGGER as logger
from dbt import ui
PIN_PACKAGE_URL = 'https://docs.getdbt.com/docs/package-management#section-specifying-package-versions' # noqa
@@ -82,7 +81,11 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
)
except ExecutableError as exc:
if exc.cmd and exc.cmd[0] == 'git':
fire_event(EnsureGitInstalled())
logger.error(
'Make sure git is installed on your machine. More '
'information: '
'https://docs.getdbt.com/docs/package-management'
)
raise
return os.path.join(get_downloads_path(), dir_)

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