Compare commits

..

1 Commits

Author SHA1 Message Date
Kyle Wigley
42058de028 --wip-- 2021-03-22 09:19:26 -04:00
5064 changed files with 48566 additions and 109652 deletions

View File

@@ -1,27 +1,23 @@
[bumpversion]
current_version = 1.0.0b2
current_version = 0.19.0
parse = (?P<major>\d+)
\.(?P<minor>\d+)
\.(?P<patch>\d+)
((?P<prekind>a|b|rc)
(?P<pre>\d+) # pre-release version num
)?
serialize =
{major}.{minor}.{patch}{prekind}{pre}
((?P<prerelease>[a-z]+)(?P<num>\d+))?
serialize =
{major}.{minor}.{patch}{prerelease}{num}
{major}.{minor}.{patch}
commit = False
tag = False
[bumpversion:part:prekind]
[bumpversion:part:prerelease]
first_value = a
optional_value = final
values =
values =
a
b
rc
final
[bumpversion:part:pre]
[bumpversion:part:num]
first_value = 1
[bumpversion:file:setup.py]
@@ -30,8 +26,18 @@ first_value = 1
[bumpversion:file:core/dbt/version.py]
[bumpversion:file:core/scripts/create_adapter_plugins.py]
[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]

218
.circleci/config.yml Normal file
View File

@@ -0,0 +1,218 @@
version: 2.1
jobs:
unit:
docker: &test_only
- image: fishtownanalytics/test-container:9
environment:
DBT_INVOCATION_ENV: circle
steps:
- checkout
- run: tox -e flake8,mypy,unit-py36,unit-py38
build-wheels:
docker: *test_only
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-py36:
docker: &test_and_postgres
- image: fishtownanalytics/test-container:9
environment:
DBT_INVOCATION_ENV: circle
- image: postgres
name: database
environment: &pgenv
POSTGRES_USER: "root"
POSTGRES_PASSWORD: "password"
POSTGRES_DB: "dbt"
steps:
- checkout
- run: &setupdb
name: Setup postgres
command: bash test/setup_db.sh
environment:
PGHOST: database
PGUSER: root
PGPASSWORD: password
PGDATABASE: postgres
- run:
name: Run tests
command: tox -e integration-postgres-py36
- store_artifacts:
path: ./logs
integration-snowflake-py36:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-snowflake-py36
no_output_timeout: 1h
- store_artifacts:
path: ./logs
integration-redshift-py36:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-redshift-py36
- store_artifacts:
path: ./logs
integration-bigquery-py36:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-bigquery-py36
- store_artifacts:
path: ./logs
integration-postgres-py38:
docker: *test_and_postgres
steps:
- checkout
- run: *setupdb
- run:
name: Run tests
command: tox -e integration-postgres-py38
- store_artifacts:
path: ./logs
integration-snowflake-py38:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-snowflake-py38
no_output_timeout: 1h
- store_artifacts:
path: ./logs
integration-redshift-py38:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-redshift-py38
- store_artifacts:
path: ./logs
integration-bigquery-py38:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-bigquery-py38
- store_artifacts:
path: ./logs
integration-postgres-py39:
docker: *test_and_postgres
steps:
- checkout
- run: *setupdb
- run:
name: Run tests
command: tox -e integration-postgres-py39
- store_artifacts:
path: ./logs
integration-snowflake-py39:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-snowflake-py39
no_output_timeout: 1h
- store_artifacts:
path: ./logs
integration-redshift-py39:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-redshift-py39
- store_artifacts:
path: ./logs
integration-bigquery-py39:
docker: *test_only
steps:
- checkout
- run:
name: Run tests
command: tox -e integration-bigquery-py39
- store_artifacts:
path: ./logs
workflows:
version: 2
test-everything:
jobs:
- unit
- integration-postgres-py36:
requires:
- unit
- integration-redshift-py36:
requires:
- integration-postgres-py36
- integration-bigquery-py36:
requires:
- integration-postgres-py36
- integration-snowflake-py36:
requires:
- integration-postgres-py36
- integration-postgres-py38:
requires:
- unit
- integration-redshift-py38:
requires:
- integration-postgres-py38
- integration-bigquery-py38:
requires:
- integration-postgres-py38
- integration-snowflake-py38:
requires:
- integration-postgres-py38
- integration-postgres-py39:
requires:
- unit
- integration-redshift-py39:
requires:
- integration-postgres-py39
- integration-bigquery-py39:
requires:
- integration-postgres-py39
# - integration-snowflake-py39:
# requires:
# - integration-postgres-py39
- build-wheels:
requires:
- unit
- integration-postgres-py36
- integration-redshift-py36
- integration-bigquery-py36
- integration-snowflake-py36
- integration-postgres-py38
- integration-redshift-py38
- integration-bigquery-py38
- integration-snowflake-py38
- integration-postgres-py39
- integration-redshift-py39
- integration-bigquery-py39
# - integration-snowflake-py39

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

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -4,18 +4,19 @@ resolves #
Include the number of the issue addressed by this PR above if applicable.
PRs for code changes without an associated issue *will not be merged*.
See CONTRIBUTING.md for more information.
Example:
resolves #1234
-->
### Description
<!---
Describe the Pull Request here. Add any references and info to help reviewers
understand your changes. Include any tradeoffs you considered.
-->
<!--- Describe the Pull Request here -->
### Checklist
- [ ] I have signed the [CLA](https://docs.getdbt.com/docs/contributor-license-agreements)
- [ ] I have run this code in development and it appears to resolve the stated issue
- [ ] This PR includes tests, or tests are not required/relevant for this PR
- [ ] I have updated the `CHANGELOG.md` and added information about my change
- [ ] I have signed the [CLA](https://docs.getdbt.com/docs/contributor-license-agreements)
- [ ] I have run this code in development and it appears to resolve the stated issue
- [ ] This PR includes tests, or tests are not required/relevant for this PR
- [ ] I have updated the `CHANGELOG.md` and added information about my change to the "dbt next" section.

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

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}}'

1
.gitignore vendored
View File

@@ -85,7 +85,6 @@ target/
# pycharm
.idea/
venv/
# AWS credentials
.aws/

20
.pre-commit-config.yaml Normal file
View File

@@ -0,0 +1,20 @@
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v2.3.0
hooks:
- id: check-yaml
- id: end-of-file-fixer
- id: trailing-whitespace
- repo: https://github.com/psf/black
rev: 20.8b1
hooks:
- id: black
- repo: https://gitlab.com/PyCQA/flake8
rev: 3.9.0
hooks:
- id: flake8
- repo: https://github.com/pre-commit/mirrors-mypy
rev: v0.812
hooks:
- id: mypy
files: ^core/dbt/

View File

@@ -3,7 +3,6 @@ The core function of dbt is SQL compilation and execution. Users create projects
## dbt-core
Most of the python code in the repository is within the `core/dbt` directory. Currently the main subdirectories are:
- [`adapters`](core/dbt/adapters): Define base classes for behavior that is likely to differ across databases
- [`clients`](core/dbt/clients): Interface with dependencies (agate, jinja) or across operating systems
- [`config`](core/dbt/config): Reconcile user-supplied configuration from connection profiles, project files, and Jinja macros
@@ -13,18 +12,21 @@ Most of the python code in the repository is within the `core/dbt` directory. Cu
- [`graph`](core/dbt/graph): Produce a `networkx` DAG of project resources, and selecting those resources given user-supplied criteria
- [`include`](core/dbt/include): The dbt "global project," which defines default implementations of Jinja2 macros
- [`parser`](core/dbt/parser): Read project files, validate, construct python objects
- [`rpc`](core/dbt/rpc): Provide remote procedure call server for invoking dbt, following JSON-RPC 2.0 spec
- [`task`](core/dbt/task): Set forth the actions that dbt can perform when invoked
### Invoking dbt
The "tasks" map to top-level dbt commands. So `dbt run` => task.run.RunTask, etc. Some are more like abstract base classes (GraphRunnableTask, for example) but all the concrete types outside of task should map to tasks. Currently one executes at a time. The tasks kick off their “Runners” and those do execute in parallel. The parallelism is managed via a thread pool, in GraphRunnableTask.
There are two supported ways of invoking dbt: from the command line and using an RPC server.
The "tasks" map to top-level dbt commands. So `dbt run` => task.run.RunTask, etc. Some are more like abstract base classes (GraphRunnableTask, for example) but all the concrete types outside of task/rpc should map to tasks. Currently one executes at a time. The tasks kick off their “Runners” and those do execute in parallel. The parallelism is managed via a thread pool, in GraphRunnableTask.
core/dbt/include/index.html
This is the docs website code. It comes from the dbt-docs repository, and is generated when a release is packaged.
## Adapters
dbt uses an adapter-plugin pattern to extend support to different databases, warehouses, query engines, etc. For testing and development purposes, the dbt-postgres plugin lives alongside the dbt-core codebase, in the [`plugins`](plugins) subdirectory. Like other adapter plugins, it is a self-contained codebase and package that builds on top of dbt-core.
dbt uses an adapter-plugin pattern to extend support to different databases, warehouses, query engines, etc. The four core adapters that are in the main repository, contained within the [`plugins`](plugins) subdirectory, are: Postgres Redshift, Snowflake and BigQuery. Other warehouses use adapter plugins defined in separate repositories (e.g. [dbt-spark](https://github.com/fishtown-analytics/dbt-spark), [dbt-presto](https://github.com/fishtown-analytics/dbt-presto)).
Each adapter is a mix of python, Jinja2, and SQL. The adapter code also makes heavy use of Jinja2 to wrap modular chunks of SQL functionality, define default implementations, and allow plugins to override it.

File diff suppressed because it is too large Load Diff

View File

@@ -1,121 +1,118 @@
# Contributing to `dbt`
# Contributing to dbt
1. [About this document](#about-this-document)
2. [Proposing a change](#proposing-a-change)
3. [Getting the code](#getting-the-code)
4. [Setting up an environment](#setting-up-an-environment)
5. [Running `dbt` in development](#running-dbt-in-development)
5. [Running dbt in development](#running-dbt-in-development)
6. [Testing](#testing)
7. [Submitting a Pull Request](#submitting-a-pull-request)
## About this document
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.
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.
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 #development channel on [slack](community.getdbt.com).
### Signing the CLA
Please note that all contributors to `dbt` must sign the [Contributor License Agreement](https://docs.getdbt.com/docs/contributor-license-agreements) to have their Pull Request merged into the `dbt` codebase. If you are unable to sign the CLA, then the `dbt` maintainers will unfortunately be unable to merge your Pull Request. You are, however, welcome to open issues and comment on existing ones.
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` 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.
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`, the first step is to open an issue. Please check the list of [open issues](https://github.com/dbt-labs/dbt-core/issues) before creating a new one. If you find a relevant issue, please add a comment to the open issue instead of creating a new one. There are hundreds of open issues in this repository and it can be hard to know where to look for a relevant open issue. **The `dbt` maintainers are always happy to point contributors in the right direction**, so please err on the side of documenting your idea in a new issue if you are unsure where a problem statement belongs.
If you have an idea for a new feature or if you've discovered a bug in dbt, the first step is to open an issue. Please check the list of [open issues](https://github.com/fishtown-analytics/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.
**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` 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.
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` 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` 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/fishtown-analytics/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` 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.
- 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` 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.
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` 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.
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` maintainer. This label is removed when a maintainer reviews and responds to the issue. |
| [bug](https://github.com/dbt-labs/dbt-core/labels/bug) | This issue represents a defect or regression in `dbt` |
| [enhancement](https://github.com/dbt-labs/dbt-core/labels/enhancement) | This issue represents net-new functionality in `dbt` |
| [good first issue](https://github.com/dbt-labs/dbt-core/labels/good%20first%20issue) | This issue does not require deep knowledge of the `dbt` codebase to implement. This issue is appropriate for a first-time contributor. |
| [help wanted](https://github.com/dbt-labs/dbt-core/labels/help%20wanted) / [discussion](https://github.com/dbt-labs/dbt-core/labels/discussion) | Conversation around this issue in ongoing, and there isn't yet a clear path forward. Input from community members is most welcome. |
| [duplicate](https://github.com/dbt-labs/dbt-core/issues/duplicate) | This issue is functionally identical to another open issue. The `dbt` maintainers will close this issue and encourage community members to focus conversation on the other one. |
| [snoozed](https://github.com/dbt-labs/dbt-core/labels/snoozed) | This issue describes a good idea, but one which will probably not be addressed in a six-month time horizon. The `dbt` maintainers will revist these issues periodically and re-prioritize them accordingly. |
| [stale](https://github.com/dbt-labs/dbt-core/labels/stale) | This is an old issue which has not recently been updated. Stale issues will periodically be closed by `dbt` maintainers, but they can be re-opened if the discussion is restarted. |
| [wontfix](https://github.com/dbt-labs/dbt-core/labels/wontfix) | This issue does not require a code change in the `dbt` repository, or the maintainers are unwilling/unable to merge a Pull Request which implements the behavior described in the issue. |
| [triage](https://github.com/fishtown-analytics/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/fishtown-analytics/dbt/labels/bug) | This issue represents a defect or regression in dbt |
| [enhancement](https://github.com/fishtown-analytics/dbt/labels/enhancement) | This issue represents net-new functionality in dbt |
| [good first issue](https://github.com/fishtown-analytics/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/fishtown-analytics/dbt/labels/help%20wanted) / [discussion](https://github.com/fishtown-analytics/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/fishtown-analytics/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/fishtown-analytics/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/fishtown-analytics/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/fishtown-analytics/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` 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 `develop` at the time of writing this, and will be the default branch of the repository.
- **Release Branches** track a specific, not yet complete release of `dbt`. Each minor version release has a corresponding release branch. For example, the `0.11.x` series of releases has a branch called `0.11.latest`. This allows us to release new patch versions under `0.11` without necessarily needing to pull them into the latest version of `dbt`.
- **Feature Branches** track individual features and fixes. On completion they should be merged into the trunk branch or a specific release branch.
- **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` 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` 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:
If you are not a member of the `fishtown-analytics` 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` 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
5. open a pull request against `fishtown-analytics/dbt` from your forked repository
### Core contributors
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.
If you are a member of the `fishtown-analytics` 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` 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` 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 3.6, 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)
- [virtualenv](https://virtualenv.pypa.io/en/stable/) to manage dependencies
- [tox](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions
- [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://gitlab.com/pycqa/flake8) for code linting
- [CircleCI](https://circleci.com/product/) and [Azure Pipelines](https://azure.microsoft.com/en-us/services/devops/pipelines/)
A deep understanding of these tools in not required to effectively contribute to `dbt`, but we recommend checking out the attached documentation if you're interested in learning more about them.
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`. We recommend creating this virtualenv
in the root of the `dbt` repository. To create a new virtualenv, run:
```sh
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:
```
python3 -m venv env
source env/bin/activate
```
@@ -131,25 +128,23 @@ Docker and docker-compose are both used in testing. Specific instructions for yo
For testing, and later in the examples in this document, you may want to have `psql` available so you can poke around in the database and see what happened. We recommend that you use [homebrew](https://brew.sh/) for that on macOS, and your package manager on Linux. You can install any version of the postgres client that you'd like. On macOS, with homebrew setup, you can run:
```sh
```
brew install postgresql
```
## Running `dbt` 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` (and its dependencies) with:
First make sure that you set up your `virtualenv` as described in section _Setting up an environment_. Next, install dbt (and its dependencies) with:
```sh
make dev
# or
pip install -r dev-requirements.txt -r editable-requirements.txt
```
pip install -r requirements-editable.txt
```
When `dbt` is installed this way, any changes you make to the `dbt` source code will be reflected immediately in your next `dbt` run.
When dbt is installed from source in this way, any changes you make to the dbt source code will be reflected immediately in your next `dbt` run.
### Running `dbt`
### Running dbt
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.
@@ -157,79 +152,76 @@ Configure your [profile](https://docs.getdbt.com/docs/configure-your-profile) as
## Testing
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.
Getting the dbt integration tests set up in your local environment will be very helpful as you start to make changes to your local version of dbt. The section that follows outlines some helpful tips for setting up the test environment.
Although `dbt` works with a number of different databases, you won't need to supply credentials for every one of these databases in your test environment. Instead you can test all dbt-core code changes with Python and Postgres.
### Running tests via Docker
### Initial setup
dbt's unit and integration tests run in Docker. Because 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, Fishtown Analytics 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.
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
### Specifying your test credentials
dbt uses test credentials specified in a `test.env` file in the root of the repository. 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:
```
cp test.env.sample test.env
```
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. dbt's test suite runs Postgres in a Docker container, so no setup should be required to run these tests.
If you additionally want to test Snowflake, Bigquery, or Redshift, locally you'll need to get credentials and add them to the `test.env` file. 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
dbt's unit tests and Python linter can be run with:
```
make test-unit
```
To run the Postgres + Python 3.6 integration tests, you'll have to do one extra step of setting up the test database:
```
or, alternatively:
```sh
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.
To run a quick test for Python3 integration tests on Postgres, you can run:
```
cp test.env.sample test.env
$EDITOR test.env
make test-quick
```
> 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.
#### Makefile
There are multiple targets in the Makefile to run common test suites and code
checks, most notably:
```sh
# Runs unit tests with py38 and code checks in parallel.
make test
# Runs postgres integration tests with py38 in "fail fast" mode.
make integration
To run tests for a specific database, invoke `tox` directly with the required flags:
```
> These make targets assume you have a recent version of [`tox`](https://tox.readthedocs.io/en/latest/) installed locally,
> unless you use choose a Docker container to run tests. Run `make help` for more info.
# Run Postgres py36 tests
docker-compose run test tox -e integration-postgres-py36 -- -x
Check out the other targets in the Makefile to see other commonly used test
suites.
# Run Snowflake py36 tests
docker-compose run test tox -e integration-snowflake-py36 -- -x
#### `tox`
# Run BigQuery py36 tests
docker-compose run test tox -e integration-bigquery-py36 -- -x
[`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 3.6, 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 py36`. The configuration for these tests in located in `tox.ini`.
#### `pytest`
Finally, you can also run a specific test or group of tests using [`pytest`](https://docs.pytest.org/en/latest/) directly. With a virtualenv
active and dev dependencies installed you can do things like:
```sh
# run specific postgres integration tests
python -m pytest -m profile_postgres test/integration/001_simple_copy_test
# run all unit tests in a file
python -m pytest test/unit/test_graph.py
# run a specific unit test
python -m pytest test/unit/test_graph.py::GraphTest::test__dependency_list
# Run Redshift py36 tests
docker-compose run test tox -e integration-redshift-py36 -- -x
```
> [Here](https://docs.pytest.org/en/reorganize-docs/new-docs/user/commandlineuseful.html)
> is a list of useful command-line options for `pytest` to use while developing.
To run a specific test by itself:
```
docker-compose run test tox -e explicit-py36 -- -s -x -m profile_{adapter} {path_to_test_file_or_folder}
```
E.g.
```
docker-compose run test tox -e explicit-py36 -- -s -x -m profile_snowflake test/integration/001_simple_copy_test
```
See the `Makefile` contents for more some other examples of ways to run `tox`.
## 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.
Fishtown Analytics provides a sandboxed Redshift, Snowflake, and BigQuery database for use in a CI environment. When pull requests are submitted to the `fishtown-analytics/dbt` repo, GitHub will trigger automated tests in CircleCI and Azure Pipelines.
A `dbt` maintainer will review your PR. They may suggest code revision for style or clarity, or request that you add unit or integration test(s). These are good things! We believe that, with a little bit of help, anyone can contribute high-quality code.
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` 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

@@ -1,11 +1,8 @@
FROM ubuntu:20.04
FROM ubuntu:18.04
ENV DEBIAN_FRONTEND noninteractive
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
software-properties-common \
&& add-apt-repository ppa:git-core/ppa -y \
&& apt-get dist-upgrade -y \
&& apt-get install -y --no-install-recommends \
netcat \
@@ -27,7 +24,7 @@ RUN apt-get update \
&& apt-get install -y \
python \
python-dev \
python3-pip \
python-pip \
python3.6 \
python3.6-dev \
python3-pip \
@@ -49,7 +46,9 @@ RUN curl -LO https://github.com/jwilder/dockerize/releases/download/$DOCKERIZE_V
&& tar -C /usr/local/bin -xzvf dockerize-linux-amd64-$DOCKERIZE_VERSION.tar.gz \
&& rm dockerize-linux-amd64-$DOCKERIZE_VERSION.tar.gz
RUN pip3 install -U tox wheel six setuptools
RUN pip3 install -U "tox==3.14.4" wheel "six>=1.14.0,<1.15.0" "virtualenv==20.0.3" setuptools
# tox fails if the 'python' interpreter (python2) doesn't have `tox` installed
RUN pip install -U "tox==3.14.4" "six>=1.14.0,<1.15.0" "virtualenv==20.0.3" setuptools
# These args are passed in via docker-compose, which reads then from the .env file.
# On Linux, run `make .env` to create the .env file for the current user.

View File

@@ -186,7 +186,7 @@
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2021 dbt Labs, Inc.
Copyright {yyyy} {name of copyright owner}
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.

View File

@@ -1,57 +1,24 @@
.DEFAULT_GOAL:=help
.PHONY: install test test-unit test-integration
# Optional flag to run target in a docker container.
# (example `make test USE_DOCKER=true`)
ifeq ($(USE_DOCKER),true)
DOCKER_CMD := docker-compose run --rm test
endif
test: .env
@echo "Full test run starting..."
@time docker-compose run --rm test tox
.PHONY: dev
dev: ## Installs dbt-* packages in develop mode along with development dependencies.
pip install -r dev-requirements.txt -r editable-requirements.txt
test-unit: .env
@echo "Unit test run starting..."
@time docker-compose run --rm test tox -e unit-py36,flake8
.PHONY: mypy
mypy: .env ## Runs mypy for static type checking.
$(DOCKER_CMD) tox -e mypy
test-integration: .env
@echo "Integration test run starting..."
@time docker-compose run --rm test tox -e integration-postgres-py36,integration-redshift-py36,integration-snowflake-py36,integration-bigquery-py36
.PHONY: flake8
flake8: .env ## Runs flake8 to enforce style guide.
$(DOCKER_CMD) tox -e flake8
.PHONY: lint
lint: .env ## Runs all code checks in parallel.
$(DOCKER_CMD) tox -p -e flake8,mypy
.PHONY: unit
unit: .env ## Runs unit tests with py38.
$(DOCKER_CMD) tox -e py38
.PHONY: test
test: .env ## Runs unit tests with py38 and code checks in parallel.
$(DOCKER_CMD) tox -p -e py38,flake8,mypy
.PHONY: integration
integration: .env integration-postgres ## Alias for integration-postgres.
.PHONY: integration-fail-fast
integration-fail-fast: .env integration-postgres-fail-fast ## Alias for integration-postgres-fail-fast.
.PHONY: integration-postgres
integration-postgres: .env ## Runs postgres integration tests with py38.
$(DOCKER_CMD) tox -e py38-postgres -- -nauto
.PHONY: integration-postgres-fail-fast
integration-postgres-fail-fast: .env ## Runs postgres integration tests with py38 in "fail fast" mode.
$(DOCKER_CMD) tox -e py38-postgres -- -x -nauto
.PHONY: setup-db
setup-db: ## Setup Postgres database with docker-compose for system testing.
docker-compose up -d database
PGHOST=localhost PGUSER=root PGPASSWORD=password PGDATABASE=postgres bash test/setup_db.sh
test-quick: .env
@echo "Integration test run starting, will exit on first failure..."
@time docker-compose run --rm test tox -e integration-postgres-py36 -- -x
# This rule creates a file named .env that is used by docker-compose for passing
# the USER_ID and GROUP_ID arguments to the Docker image.
.env: ## Setup step for using using docker-compose with make target.
.env:
@touch .env
ifneq ($(OS),Windows_NT)
ifneq ($(shell uname -s), Darwin)
@@ -59,9 +26,9 @@ ifneq ($(shell uname -s), Darwin)
@echo GROUP_ID=$(shell id -g) >> .env
endif
endif
@time docker-compose build
.PHONY: clean
clean: ## Resets development environment.
clean:
rm -f .coverage
rm -rf .eggs/
rm -f .env
@@ -75,14 +42,3 @@ clean: ## Resets development environment.
rm -rf target/
find . -type f -name '*.pyc' -delete
find . -type d -name '__pycache__' -depth -delete
.PHONY: help
help: ## Show this help message.
@echo 'usage: make [target] [USE_DOCKER=true]'
@echo
@echo 'targets:'
@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
@echo
@echo 'options:'
@echo 'use USE_DOCKER=true to run target in a docker container'

View File

@@ -1,18 +1,28 @@
<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/fishtown-analytics/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/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://codeclimate.com/github/fishtown-analytics/dbt">
<img src="https://codeclimate.com/github/fishtown-analytics/dbt/badges/gpa.svg" alt="Code Climate"/>
</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/fishtown-analytics/dbt/tree/master">
<img src="https://circleci.com/gh/fishtown-analytics/dbt/tree/master.svg?style=svg" alt="CircleCI" />
</a>
<a href="https://ci.appveyor.com/project/DrewBanin/dbt/branch/development">
<img src="https://ci.appveyor.com/api/projects/status/v01rwd3q91jnwp9m/branch/development?svg=true" alt="AppVeyor" />
</a>
<a href="https://community.getdbt.com">
<img src="https://community.getdbt.com/badge.svg" alt="Slack" />
</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.
**[dbt](https://www.getdbt.com/)** (data build tool) 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 is the T in ELT. Organize, cleanse, denormalize, filter, rename, and pre-aggregate the raw data in your warehouse so that it's ready for analysis.
![dbt architecture](https://raw.githubusercontent.com/fishtown-analytics/dbt/6c6649f9129d5d108aa3b0526f634cd8f3a9d1ed/etc/dbt-arch.png)
dbt can be used to [aggregate pageviews into sessions](https://github.com/fishtown-analytics/snowplow), calculate [ad spend ROI](https://github.com/fishtown-analytics/facebook-ads), or report on [email campaign performance](https://github.com/fishtown-analytics/mailchimp).
## Understanding dbt
@@ -20,22 +30,28 @@ 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/fishtown-analytics/dbt/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/)
- [Install dbt](https://docs.getdbt.com/docs/installation)
- Read the [documentation](https://docs.getdbt.com/).
- Productionize your dbt project with [dbt Cloud](https://www.getdbt.com)
## Join the dbt Community
## Find out more
- 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)
- Check out the [Introduction to dbt](https://docs.getdbt.com/docs/introduction/).
- Read the [dbt Viewpoint](https://docs.getdbt.com/docs/about/viewpoint/).
## Join thousands of analysts in the dbt community
- Join the [chat](http://community.getdbt.com/) on Slack.
- Find community posts on [dbt 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)
- 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/fishtown-analytics/dbt/issues/new).
- Want to help us build dbt? Check out the [Contributing Getting Started Guide](https://github.com/fishtown-analytics/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:
- master
- dev/*
- 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 pywin-unit
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 pywin-postgres
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: PostgresIntegrationTest
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 pywin-snowflake
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: PostgresIntegrationTest
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 pywin-bigquery
env:
BIGQUERY_SERVICE_ACCOUNT_JSON: $(BIGQUERY_SERVICE_ACCOUNT_JSON)
displayName: Run integration tests
- job: RedshiftIntegrationTest
pool:
vmImage: 'vs2017-win2016'
dependsOn: PostgresIntegrationTest
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 pywin-redshift
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: $(REDSHIFT_TEST_HOST)
displayName: Run integration tests
- job: BuildWheel
pool:
vmImage: 'vs2017-win2016'
dependsOn:
- UnitTest
- PostgresIntegrationTest
- RedshiftIntegrationTest
- SnowflakeIntegrationTest
- BigQueryIntegrationTest
condition: succeeded()
steps:
- task: UsePythonVersion@0
inputs:
versionSpec: '3.7'
architecture: 'x64'
- script: python -m pip install --upgrade pip setuptools && python -m pip install -r requirements.txt && python -m pip install -r requirements-dev.txt
displayName: Install dependencies
- task: ShellScript@2
inputs:
scriptPath: scripts/build-wheels.sh
- task: CopyFiles@2
inputs:
contents: 'dist\?(*.whl|*.tar.gz)'
TargetFolder: '$(Build.ArtifactStagingDirectory)'
- task: PublishBuildArtifacts@1
inputs:
pathtoPublish: '$(Build.ArtifactStagingDirectory)'
artifactName: dists

75
converter.py Executable file
View File

@@ -0,0 +1,75 @@
#!/usr/bin/env python
import json
import yaml
import sys
import argparse
from datetime import datetime, timezone
import dbt.clients.registry as registry
def yaml_type(fname):
with open(fname) as f:
return yaml.load(f)
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument("--project", type=yaml_type, default="dbt_project.yml")
parser.add_argument("--namespace", required=True)
return parser.parse_args()
def get_full_name(args):
return "{}/{}".format(args.namespace, args.project["name"])
def init_project_in_packages(args, packages):
full_name = get_full_name(args)
if full_name not in packages:
packages[full_name] = {
"name": args.project["name"],
"namespace": args.namespace,
"latest": args.project["version"],
"assets": {},
"versions": {},
}
return packages[full_name]
def add_version_to_package(args, project_json):
project_json["versions"][args.project["version"]] = {
"id": "{}/{}".format(get_full_name(args), args.project["version"]),
"name": args.project["name"],
"version": args.project["version"],
"description": "",
"published_at": datetime.now(timezone.utc).astimezone().isoformat(),
"packages": args.project.get("packages") or [],
"works_with": [],
"_source": {
"type": "github",
"url": "",
"readme": "",
},
"downloads": {
"tarball": "",
"format": "tgz",
"sha1": "",
},
}
def main():
args = parse_args()
packages = registry.packages()
project_json = init_project_in_packages(args, packages)
if args.project["version"] in project_json["versions"]:
raise Exception(
"Version {} already in packages JSON".format(args.project["version"]),
file=sys.stderr,
)
add_version_to_package(args, project_json)
print(json.dumps(packages, indent=2))
if __name__ == "__main__":
main()

View File

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

View File

@@ -8,10 +8,10 @@ from dbt.exceptions import RuntimeException
@dataclass
class Column:
TYPE_LABELS: ClassVar[Dict[str, str]] = {
'STRING': 'TEXT',
'TIMESTAMP': 'TIMESTAMP',
'FLOAT': 'FLOAT',
'INTEGER': 'INT'
"STRING": "TEXT",
"TIMESTAMP": "TIMESTAMP",
"FLOAT": "FLOAT",
"INTEGER": "INT",
}
column: str
dtype: str
@@ -24,7 +24,7 @@ class Column:
return cls.TYPE_LABELS.get(dtype.upper(), dtype)
@classmethod
def create(cls, name, label_or_dtype: str) -> 'Column':
def create(cls, name, label_or_dtype: str) -> "Column":
column_type = cls.translate_type(label_or_dtype)
return cls(name, column_type)
@@ -41,14 +41,19 @@ class Column:
if self.is_string():
return Column.string_type(self.string_size())
elif self.is_numeric():
return Column.numeric_type(self.dtype, self.numeric_precision,
self.numeric_scale)
return Column.numeric_type(
self.dtype, self.numeric_precision, self.numeric_scale
)
else:
return self.dtype
def is_string(self) -> bool:
return self.dtype.lower() in ['text', 'character varying', 'character',
'varchar']
return self.dtype.lower() in [
"text",
"character varying",
"character",
"varchar",
]
def is_number(self):
return any([self.is_integer(), self.is_numeric(), self.is_float()])
@@ -56,33 +61,45 @@ class Column:
def is_float(self):
return self.dtype.lower() in [
# floats
'real', 'float4', 'float', 'double precision', 'float8'
"real",
"float4",
"float",
"double precision",
"float8",
]
def is_integer(self) -> bool:
return self.dtype.lower() in [
# real types
'smallint', 'integer', 'bigint',
'smallserial', 'serial', 'bigserial',
"smallint",
"integer",
"bigint",
"smallserial",
"serial",
"bigserial",
# aliases
'int2', 'int4', 'int8',
'serial2', 'serial4', 'serial8',
"int2",
"int4",
"int8",
"serial2",
"serial4",
"serial8",
]
def is_numeric(self) -> bool:
return self.dtype.lower() in ['numeric', 'decimal']
return self.dtype.lower() in ["numeric", "decimal"]
def string_size(self) -> int:
if not self.is_string():
raise RuntimeException("Called string_size() on non-string field!")
if self.dtype == 'text' or self.char_size is None:
if self.dtype == "text" or self.char_size is None:
# char_size should never be None. Handle it reasonably just in case
return 256
else:
return int(self.char_size)
def can_expand_to(self, other_column: 'Column') -> bool:
def can_expand_to(self, other_column: "Column") -> bool:
"""returns True if this column can be expanded to the size of the
other column"""
if not self.is_string() or not other_column.is_string():
@@ -110,12 +127,10 @@ class Column:
return "<Column {} ({})>".format(self.name, self.data_type)
@classmethod
def from_description(cls, name: str, raw_data_type: str) -> 'Column':
match = re.match(r'([^(]+)(\([^)]+\))?', raw_data_type)
def from_description(cls, name: str, raw_data_type: str) -> "Column":
match = re.match(r"([^(]+)(\([^)]+\))?", raw_data_type)
if match is None:
raise RuntimeException(
f'Could not interpret data type "{raw_data_type}"'
)
raise RuntimeException(f'Could not interpret data type "{raw_data_type}"')
data_type, size_info = match.groups()
char_size = None
numeric_precision = None
@@ -123,7 +138,7 @@ class Column:
if size_info is not None:
# strip out the parentheses
size_info = size_info[1:-1]
parts = size_info.split(',')
parts = size_info.split(",")
if len(parts) == 1:
try:
char_size = int(parts[0])
@@ -148,6 +163,4 @@ class Column:
f'could not convert "{parts[1]}" to an integer'
)
return cls(
name, data_type, char_size, numeric_precision, numeric_scale
)
return cls(name, data_type, char_size, numeric_precision, numeric_scale)

View File

@@ -1,18 +1,21 @@
import abc
import os
# multiprocessing.RLock is a function returning this type
from multiprocessing.synchronize import RLock
from threading import get_ident
from typing import (
Dict, Tuple, Hashable, Optional, ContextManager, List, Union
)
from typing import Dict, Tuple, Hashable, Optional, ContextManager, List, Union
import agate
import dbt.exceptions
from dbt.contracts.connection import (
Connection, Identifier, ConnectionState,
AdapterRequiredConfig, LazyHandle, AdapterResponse
Connection,
Identifier,
ConnectionState,
AdapterRequiredConfig,
LazyHandle,
AdapterResponse,
)
from dbt.contracts.graph.manifest import Manifest
from dbt.adapters.base.query_headers import (
@@ -35,6 +38,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
You must also set the 'TYPE' class attribute with a class-unique constant
string.
"""
TYPE: str = NotImplemented
def __init__(self, profile: AdapterRequiredConfig):
@@ -65,7 +69,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
key = self.get_thread_identifier()
if key in self.thread_connections:
raise dbt.exceptions.InternalException(
'In set_thread_connection, existing connection exists for {}'
"In set_thread_connection, existing connection exists for {}"
)
self.thread_connections[key] = conn
@@ -105,18 +109,19 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
underlying database.
"""
raise dbt.exceptions.NotImplementedException(
'`exception_handler` is not implemented for this adapter!')
"`exception_handler` is not implemented for this adapter!"
)
def set_connection_name(self, name: Optional[str] = None) -> Connection:
conn_name: str
if name is None:
# if a name isn't specified, we'll re-use a single handle
# named 'master'
conn_name = 'master'
conn_name = "master"
else:
if not isinstance(name, str):
raise dbt.exceptions.CompilerException(
f'For connection name, got {name} - not a string!'
f"For connection name, got {name} - not a string!"
)
assert isinstance(name, str)
conn_name = name
@@ -129,20 +134,20 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
state=ConnectionState.INIT,
transaction_open=False,
handle=None,
credentials=self.profile.credentials
credentials=self.profile.credentials,
)
self.set_thread_connection(conn)
if conn.name == conn_name and conn.state == 'open':
if conn.name == conn_name and conn.state == "open":
return conn
logger.debug(
'Acquiring new {} connection "{}".'.format(self.TYPE, conn_name))
logger.debug('Acquiring new {} connection "{}".'.format(self.TYPE, conn_name))
if conn.state == 'open':
if conn.state == "open":
logger.debug(
'Re-using an available connection from the pool (formerly {}).'
.format(conn.name)
"Re-using an available connection from the pool (formerly {}).".format(
conn.name
)
)
else:
conn.handle = LazyHandle(self.open)
@@ -154,7 +159,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
def cancel_open(self) -> Optional[List[str]]:
"""Cancel all open connections on the adapter. (passable)"""
raise dbt.exceptions.NotImplementedException(
'`cancel_open` is not implemented for this adapter!'
"`cancel_open` is not implemented for this adapter!"
)
@abc.abstractclassmethod
@@ -168,7 +173,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
connection should not be in either in_use or available.
"""
raise dbt.exceptions.NotImplementedException(
'`open` is not implemented for this adapter!'
"`open` is not implemented for this adapter!"
)
def release(self) -> None:
@@ -189,12 +194,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
def cleanup_all(self) -> None:
with self.lock:
for connection in self.thread_connections.values():
if connection.state not in {'closed', 'init'}:
logger.debug("Connection '{}' was left open."
.format(connection.name))
if connection.state not in {"closed", "init"}:
logger.debug(
"Connection '{}' was left open.".format(connection.name)
)
else:
logger.debug("Connection '{}' was properly closed."
.format(connection.name))
logger.debug(
"Connection '{}' was properly closed.".format(connection.name)
)
self.close(connection)
# garbage collect these connections
@@ -204,14 +211,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
def begin(self) -> None:
"""Begin a transaction. (passable)"""
raise dbt.exceptions.NotImplementedException(
'`begin` is not implemented for this adapter!'
"`begin` is not implemented for this adapter!"
)
@abc.abstractmethod
def commit(self) -> None:
"""Commit a transaction. (passable)"""
raise dbt.exceptions.NotImplementedException(
'`commit` is not implemented for this adapter!'
"`commit` is not implemented for this adapter!"
)
@classmethod
@@ -220,43 +227,52 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
try:
connection.handle.rollback()
except Exception:
logger.debug(
'Failed to rollback {}'.format(connection.name),
exc_info=True
)
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'):
logger.debug(f'On {connection.name}: Close')
if hasattr(connection.handle, "close"):
logger.debug(f"On {connection.name}: Close")
connection.handle.close()
else:
logger.debug(f'On {connection.name}: No close available on handle')
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"Tried to rollback transaction on connection "
f'"{connection.name}", but it does not have one open!'
)
logger.debug(f'On {connection.name}: ROLLBACK')
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:
logger.debug('On {}: ROLLBACK'.format(connection.name))
logger.debug("On {}: ROLLBACK".format(connection.name))
cls._rollback_handle(connection)
connection.transaction_open = False
@@ -290,5 +306,5 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
:rtype: Tuple[Union[str, AdapterResponse], agate.Table]
"""
raise dbt.exceptions.NotImplementedException(
'`execute` is not implemented for this adapter!'
"`execute` is not implemented for this adapter!"
)

File diff suppressed because it is too large Load Diff

View File

@@ -30,9 +30,11 @@ class _Available:
x.update(big_expensive_db_query())
return x
"""
def inner(func):
func._parse_replacement_ = parse_replacement
return self(func)
return inner
def deprecated(
@@ -57,13 +59,14 @@ class _Available:
The optional parse_replacement, if provided, will provide a parse-time
replacement for the actual method (see `available.parse`).
"""
def wrapper(func):
func_name = func.__name__
renamed_method(func_name, supported_name)
@wraps(func)
def inner(*args, **kwargs):
warn('adapter:{}'.format(func_name))
warn("adapter:{}".format(func_name))
return func(*args, **kwargs)
if parse_replacement:
@@ -71,6 +74,7 @@ class _Available:
else:
available_function = self
return available_function(inner)
return wrapper
def parse_none(self, func: Callable) -> Callable:
@@ -109,14 +113,14 @@ class AdapterMeta(abc.ABCMeta):
# collect base class data first
for base in bases:
available.update(getattr(base, '_available_', set()))
replacements.update(getattr(base, '_parse_replacements_', set()))
available.update(getattr(base, "_available_", set()))
replacements.update(getattr(base, "_parse_replacements_", set()))
# override with local data if it exists
for name, value in namespace.items():
if getattr(value, '_is_available_', False):
if getattr(value, "_is_available_", False):
available.add(name)
parse_replacement = getattr(value, '_parse_replacement_', None)
parse_replacement = getattr(value, "_parse_replacement_", None)
if parse_replacement is not None:
replacements[name] = parse_replacement

View File

@@ -8,11 +8,10 @@ from dbt.adapters.protocol import AdapterProtocol
def project_name_from_path(include_path: str) -> str:
# avoid an import cycle
from dbt.config.project import Project
partial = Project.partial_load(include_path)
if partial.project_name is None:
raise CompilationException(
f'Invalid project at {include_path}: name not set!'
)
raise CompilationException(f"Invalid project at {include_path}: name not set!")
return partial.project_name
@@ -23,12 +22,13 @@ class AdapterPlugin:
:param dependencies: A list of adapter names that this adapter depends
upon.
"""
def __init__(
self,
adapter: Type[AdapterProtocol],
credentials: Type[Credentials],
include_path: str,
dependencies: Optional[List[str]] = None
dependencies: Optional[List[str]] = None,
):
self.adapter: Type[AdapterProtocol] = adapter

View File

@@ -15,7 +15,7 @@ class NodeWrapper:
self._inner_node = node
def __getattr__(self, name):
return getattr(self._inner_node, name, '')
return getattr(self._inner_node, name, "")
class _QueryComment(local):
@@ -24,6 +24,7 @@ class _QueryComment(local):
- the current thread's query comment.
- a source_name indicating what set the current thread's query comment
"""
def __init__(self, initial):
self.query_comment: Optional[str] = initial
self.append = False
@@ -35,16 +36,16 @@ class _QueryComment(local):
if self.append:
# replace last ';' with '<comment>;'
sql = sql.rstrip()
if sql[-1] == ';':
if sql[-1] == ";":
sql = sql[:-1]
return '{}\n/* {} */;'.format(sql, self.query_comment.strip())
return "{}\n/* {} */;".format(sql, self.query_comment.strip())
return '{}\n/* {} */'.format(sql, self.query_comment.strip())
return "{}\n/* {} */".format(sql, self.query_comment.strip())
return '/* {} */\n{}'.format(self.query_comment.strip(), sql)
return "/* {} */\n{}".format(self.query_comment.strip(), sql)
def set(self, comment: Optional[str], append: bool):
if isinstance(comment, str) and '*/' in comment:
if isinstance(comment, str) and "*/" in comment:
# tell the user "no" so they don't hurt themselves by writing
# garbage
raise RuntimeException(
@@ -63,15 +64,17 @@ class MacroQueryStringSetter:
self.config = config
comment_macro = self._get_comment_macro()
self.generator: QueryStringFunc = lambda name, model: ''
self.generator: QueryStringFunc = lambda name, model: ""
# if the comment value was None or the empty string, just skip it
if comment_macro:
assert isinstance(comment_macro, str)
macro = '\n'.join((
'{%- macro query_comment_macro(connection_name, node) -%}',
comment_macro,
'{% endmacro %}'
))
macro = "\n".join(
(
"{%- macro query_comment_macro(connection_name, node) -%}",
comment_macro,
"{% endmacro %}",
)
)
ctx = self._get_context()
self.generator = QueryStringGenerator(macro, ctx)
self.comment = _QueryComment(None)
@@ -87,7 +90,7 @@ class MacroQueryStringSetter:
return self.comment.add(sql)
def reset(self):
self.set('master', None)
self.set("master", None)
def set(self, name: str, node: Optional[CompileResultNode]):
wrapped: Optional[NodeWrapper] = None

View File

@@ -1,13 +1,16 @@
from collections.abc import Hashable
from dataclasses import dataclass
from typing import (
Optional, TypeVar, Any, Type, Dict, Union, Iterator, Tuple, Set
)
from typing import Optional, TypeVar, Any, Type, Dict, Union, Iterator, Tuple, Set
from dbt.contracts.graph.compiled import CompiledNode
from dbt.contracts.graph.parsed import ParsedSourceDefinition, ParsedNode
from dbt.contracts.relation import (
RelationType, ComponentName, HasQuoting, FakeAPIObject, Policy, Path
RelationType,
ComponentName,
HasQuoting,
FakeAPIObject,
Policy,
Path,
)
from dbt.exceptions import InternalException
from dbt.node_types import NodeType
@@ -16,7 +19,7 @@ from dbt.utils import filter_null_values, deep_merge, classproperty
import dbt.exceptions
Self = TypeVar('Self', bound='BaseRelation')
Self = TypeVar("Self", bound="BaseRelation")
@dataclass(frozen=True, eq=False, repr=False)
@@ -40,7 +43,7 @@ class BaseRelation(FakeAPIObject, Hashable):
if field.name == field_name:
return field
# this should be unreachable
raise ValueError(f'BaseRelation has no {field_name} field!')
raise ValueError(f"BaseRelation has no {field_name} field!")
def __eq__(self, other):
if not isinstance(other, self.__class__):
@@ -49,20 +52,18 @@ class BaseRelation(FakeAPIObject, Hashable):
@classmethod
def get_default_quote_policy(cls) -> Policy:
return cls._get_field_named('quote_policy').default
return cls._get_field_named("quote_policy").default
@classmethod
def get_default_include_policy(cls) -> Policy:
return cls._get_field_named('include_policy').default
return cls._get_field_named("include_policy").default
def get(self, key, default=None):
"""Override `.get` to return a metadata object so we don't break
dbt_utils.
"""
if key == 'metadata':
return {
'type': self.__class__.__name__
}
if key == "metadata":
return {"type": self.__class__.__name__}
return super().get(key, default)
def matches(
@@ -71,16 +72,19 @@ class BaseRelation(FakeAPIObject, Hashable):
schema: Optional[str] = None,
identifier: Optional[str] = None,
) -> bool:
search = filter_null_values({
ComponentName.Database: database,
ComponentName.Schema: schema,
ComponentName.Identifier: identifier
})
search = filter_null_values(
{
ComponentName.Database: database,
ComponentName.Schema: schema,
ComponentName.Identifier: identifier,
}
)
if not search:
# nothing was passed in
raise dbt.exceptions.RuntimeException(
"Tried to match relation, but no search path was passed!")
"Tried to match relation, but no search path was passed!"
)
exact_match = True
approximate_match = True
@@ -109,11 +113,13 @@ class BaseRelation(FakeAPIObject, Hashable):
schema: Optional[bool] = None,
identifier: Optional[bool] = None,
) -> Self:
policy = filter_null_values({
ComponentName.Database: database,
ComponentName.Schema: schema,
ComponentName.Identifier: identifier
})
policy = filter_null_values(
{
ComponentName.Database: database,
ComponentName.Schema: schema,
ComponentName.Identifier: identifier,
}
)
new_quote_policy = self.quote_policy.replace_dict(policy)
return self.replace(quote_policy=new_quote_policy)
@@ -124,16 +130,18 @@ class BaseRelation(FakeAPIObject, Hashable):
schema: Optional[bool] = None,
identifier: Optional[bool] = None,
) -> Self:
policy = filter_null_values({
ComponentName.Database: database,
ComponentName.Schema: schema,
ComponentName.Identifier: identifier
})
policy = filter_null_values(
{
ComponentName.Database: database,
ComponentName.Schema: schema,
ComponentName.Identifier: identifier,
}
)
new_include_policy = self.include_policy.replace_dict(policy)
return self.replace(include_policy=new_include_policy)
def information_schema(self, view_name=None) -> 'InformationSchema':
def information_schema(self, view_name=None) -> "InformationSchema":
# some of our data comes from jinja, where things can be `Undefined`.
if not isinstance(view_name, str):
view_name = None
@@ -143,10 +151,10 @@ class BaseRelation(FakeAPIObject, Hashable):
info_schema = InformationSchema.from_relation(self, view_name)
return info_schema.incorporate(path={"schema": None})
def information_schema_only(self) -> 'InformationSchema':
def information_schema_only(self) -> "InformationSchema":
return self.information_schema()
def without_identifier(self) -> 'BaseRelation':
def without_identifier(self) -> "BaseRelation":
"""Return a form of this relation that only has the database and schema
set to included. To get the appropriately-quoted form the schema out of
the result (for use as part of a query), use `.render()`. To get the
@@ -157,7 +165,7 @@ class BaseRelation(FakeAPIObject, Hashable):
return self.include(identifier=False).replace_path(identifier=None)
def _render_iterator(
self
self,
) -> Iterator[Tuple[Optional[ComponentName], Optional[str]]]:
for key in ComponentName:
@@ -170,13 +178,10 @@ class BaseRelation(FakeAPIObject, Hashable):
def render(self) -> str:
# if there is nothing set, this will return the empty string.
return '.'.join(
part for _, part in self._render_iterator()
if part is not None
)
return ".".join(part for _, part in self._render_iterator() if part is not None)
def quoted(self, identifier):
return '{quote_char}{identifier}{quote_char}'.format(
return "{quote_char}{identifier}{quote_char}".format(
quote_char=self.quote_character,
identifier=identifier,
)
@@ -186,11 +191,11 @@ class BaseRelation(FakeAPIObject, Hashable):
cls: Type[Self], source: ParsedSourceDefinition, **kwargs: Any
) -> Self:
source_quoting = source.quoting.to_dict(omit_none=True)
source_quoting.pop('column', None)
source_quoting.pop("column", None)
quote_policy = deep_merge(
cls.get_default_quote_policy().to_dict(omit_none=True),
source_quoting,
kwargs.get('quote_policy', {}),
kwargs.get("quote_policy", {}),
)
return cls.create(
@@ -198,12 +203,12 @@ class BaseRelation(FakeAPIObject, Hashable):
schema=source.schema,
identifier=source.identifier,
quote_policy=quote_policy,
**kwargs
**kwargs,
)
@staticmethod
def add_ephemeral_prefix(name: str):
return f'__dbt__cte__{name}'
return f"__dbt__cte__{name}"
@classmethod
def create_ephemeral_from_node(
@@ -236,7 +241,8 @@ class BaseRelation(FakeAPIObject, Hashable):
schema=node.schema,
identifier=node.alias,
quote_policy=quote_policy,
**kwargs)
**kwargs,
)
@classmethod
def create_from(
@@ -248,15 +254,16 @@ class BaseRelation(FakeAPIObject, Hashable):
if node.resource_type == NodeType.Source:
if not isinstance(node, ParsedSourceDefinition):
raise InternalException(
'type mismatch, expected ParsedSourceDefinition but got {}'
.format(type(node))
"type mismatch, expected ParsedSourceDefinition but got {}".format(
type(node)
)
)
return cls.create_from_source(node, **kwargs)
else:
if not isinstance(node, (ParsedNode, CompiledNode)):
raise InternalException(
'type mismatch, expected ParsedNode or CompiledNode but '
'got {}'.format(type(node))
"type mismatch, expected ParsedNode or CompiledNode but "
"got {}".format(type(node))
)
return cls.create_from_node(config, node, **kwargs)
@@ -269,14 +276,16 @@ class BaseRelation(FakeAPIObject, Hashable):
type: Optional[RelationType] = None,
**kwargs,
) -> Self:
kwargs.update({
'path': {
'database': database,
'schema': schema,
'identifier': identifier,
},
'type': type,
})
kwargs.update(
{
"path": {
"database": database,
"schema": schema,
"identifier": identifier,
},
"type": type,
}
)
return cls.from_dict(kwargs)
def __repr__(self) -> str:
@@ -342,7 +351,7 @@ class BaseRelation(FakeAPIObject, Hashable):
return RelationType
Info = TypeVar('Info', bound='InformationSchema')
Info = TypeVar("Info", bound="InformationSchema")
@dataclass(frozen=True, eq=False, repr=False)
@@ -352,7 +361,7 @@ class InformationSchema(BaseRelation):
def __post_init__(self):
if not isinstance(self.information_schema_view, (type(None), str)):
raise dbt.exceptions.CompilationException(
'Got an invalid name: {}'.format(self.information_schema_view)
"Got an invalid name: {}".format(self.information_schema_view)
)
@classmethod
@@ -362,7 +371,7 @@ class InformationSchema(BaseRelation):
return Path(
database=relation.database,
schema=relation.schema,
identifier='INFORMATION_SCHEMA',
identifier="INFORMATION_SCHEMA",
)
@classmethod
@@ -393,9 +402,7 @@ class InformationSchema(BaseRelation):
relation: BaseRelation,
information_schema_view: Optional[str],
) -> Info:
include_policy = cls.get_include_policy(
relation, information_schema_view
)
include_policy = cls.get_include_policy(relation, information_schema_view)
quote_policy = cls.get_quote_policy(relation, information_schema_view)
path = cls.get_path(relation, information_schema_view)
return cls(
@@ -417,6 +424,7 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
search for what schemas. The schema values are all lowercased to avoid
duplication.
"""
def add(self, relation: BaseRelation):
key = relation.information_schema_only()
if key not in self:
@@ -426,31 +434,27 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
schema = relation.schema.lower()
self[key].add(schema)
def search(
self
) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
def search(self) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
for information_schema_name, schemas in self.items():
for schema in schemas:
yield information_schema_name, schema
def flatten(self, allow_multiple_databases: bool = False):
def flatten(self):
new = self.__class__()
# make sure we don't have multiple databases if allow_multiple_databases is set to False
if not allow_multiple_databases:
seen = {r.database.lower() for r in self if r.database}
if len(seen) > 1:
dbt.exceptions.raise_compiler_error(str(seen))
# make sure we don't have duplicates
seen = {r.database.lower() for r in self if r.database}
if len(seen) > 1:
dbt.exceptions.raise_compiler_error(str(seen))
for information_schema_name, schema in self.search():
path = {
'database': information_schema_name.database,
'schema': schema
}
new.add(information_schema_name.incorporate(
path=path,
quote_policy={'database': False},
include_policy={'database': False},
))
path = {"database": information_schema_name.database, "schema": schema}
new.add(
information_schema_name.incorporate(
path=path,
quote_policy={"database": False},
include_policy={"database": False},
)
)
return new

View File

@@ -7,7 +7,7 @@ from dbt.logger import CACHE_LOGGER as logger
from dbt.utils import lowercase
import dbt.exceptions
_ReferenceKey = namedtuple('_ReferenceKey', 'database schema identifier')
_ReferenceKey = namedtuple("_ReferenceKey", "database schema identifier")
def _make_key(relation) -> _ReferenceKey:
@@ -15,9 +15,11 @@ def _make_key(relation) -> _ReferenceKey:
to keep track of quoting
"""
# databases and schemas can both be None
return _ReferenceKey(lowercase(relation.database),
lowercase(relation.schema),
lowercase(relation.identifier))
return _ReferenceKey(
lowercase(relation.database),
lowercase(relation.schema),
lowercase(relation.identifier),
)
def dot_separated(key: _ReferenceKey) -> str:
@@ -25,7 +27,7 @@ def dot_separated(key: _ReferenceKey) -> str:
:param _ReferenceKey key: The key to stringify.
"""
return '.'.join(map(str, key))
return ".".join(map(str, key))
class _CachedRelation:
@@ -37,13 +39,14 @@ class _CachedRelation:
that refer to this relation.
:attr BaseRelation inner: The underlying dbt relation.
"""
def __init__(self, inner):
self.referenced_by = {}
self.inner = inner
def __str__(self) -> str:
return (
'_CachedRelation(database={}, schema={}, identifier={}, inner={})'
"_CachedRelation(database={}, schema={}, identifier={}, inner={})"
).format(self.database, self.schema, self.identifier, self.inner)
@property
@@ -78,7 +81,7 @@ class _CachedRelation:
"""
return _make_key(self)
def add_reference(self, referrer: '_CachedRelation'):
def add_reference(self, referrer: "_CachedRelation"):
"""Add a reference from referrer to self, indicating that if this node
were drop...cascaded, the referrer would be dropped as well.
@@ -122,9 +125,9 @@ class _CachedRelation:
# table_name is ever anything but the identifier (via .create())
self.inner = self.inner.incorporate(
path={
'database': new_relation.inner.database,
'schema': new_relation.inner.schema,
'identifier': new_relation.inner.identifier
"database": new_relation.inner.database,
"schema": new_relation.inner.schema,
"identifier": new_relation.inner.identifier,
},
)
@@ -140,8 +143,9 @@ class _CachedRelation:
"""
if new_key in self.referenced_by:
dbt.exceptions.raise_cache_inconsistent(
'in rename of "{}" -> "{}", new name is in the cache already'
.format(old_key, new_key)
'in rename of "{}" -> "{}", new name is in the cache already'.format(
old_key, new_key
)
)
if old_key not in self.referenced_by:
@@ -172,13 +176,16 @@ class RelationsCache:
The adapters also hold this lock while filling the cache.
:attr Set[str] schemas: The set of known/cached schemas, all lowercased.
"""
def __init__(self) -> None:
self.relations: Dict[_ReferenceKey, _CachedRelation] = {}
self.lock = threading.RLock()
self.schemas: Set[Tuple[Optional[str], Optional[str]]] = set()
def add_schema(
self, database: Optional[str], schema: Optional[str],
self,
database: Optional[str],
schema: Optional[str],
) -> None:
"""Add a schema to the set of known schemas (case-insensitive)
@@ -188,7 +195,9 @@ class RelationsCache:
self.schemas.add((lowercase(database), lowercase(schema)))
def drop_schema(
self, database: Optional[str], schema: Optional[str],
self,
database: Optional[str],
schema: Optional[str],
) -> None:
"""Drop the given schema and remove it from the set of known schemas.
@@ -263,15 +272,15 @@ class RelationsCache:
return
if referenced is None:
dbt.exceptions.raise_cache_inconsistent(
'in add_link, referenced link key {} not in cache!'
.format(referenced_key)
"in add_link, referenced link key {} not in cache!".format(
referenced_key
)
)
dependent = self.relations.get(dependent_key)
if dependent is None:
dbt.exceptions.raise_cache_inconsistent(
'in add_link, dependent link key {} not in cache!'
.format(dependent_key)
"in add_link, dependent link key {} not in cache!".format(dependent_key)
)
assert dependent is not None # we just raised!
@@ -298,28 +307,23 @@ class RelationsCache:
# 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.
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)
"{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.
referenced = referenced.replace(
type=referenced.External
)
referenced = referenced.replace(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
)
dependent = dependent.replace(type=referenced.External)
self.add(dependent)
logger.debug(
'adding link, {!s} references {!s}'.format(dep_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)
@@ -330,14 +334,14 @@ class RelationsCache:
:param BaseRelation relation: The underlying relation.
"""
cached = _CachedRelation(relation)
logger.debug('Adding relation: {!s}'.format(cached))
logger.debug("Adding relation: {!s}".format(cached))
lazy_log('before adding: {!s}', self.dump_graph)
lazy_log("before adding: {!s}", self.dump_graph)
with self.lock:
self._setdefault(cached)
lazy_log('after adding: {!s}', 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
@@ -359,13 +363,10 @@ class RelationsCache:
:param _CachedRelation dropped: An existing _CachedRelation to drop.
"""
if dropped not in self.relations:
logger.debug('dropped a nonexistent relationship: {!s}'
.format(dropped))
logger.debug("dropped a nonexistent relationship: {!s}".format(dropped))
return
consequences = self.relations[dropped].collect_consequences()
logger.debug(
'drop {} is cascading to {}'.format(dropped, consequences)
)
logger.debug("drop {} is cascading to {}".format(dropped, consequences))
self._remove_refs(consequences)
def drop(self, relation):
@@ -380,7 +381,7 @@ class RelationsCache:
:param str identifier: The identifier of the relation to drop.
"""
dropped = _make_key(relation)
logger.debug('Dropping relation: {!s}'.format(dropped))
logger.debug("Dropping relation: {!s}".format(dropped))
with self.lock:
self._drop_cascade_relation(dropped)
@@ -404,8 +405,9 @@ class RelationsCache:
for cached in self.relations.values():
if cached.is_referenced_by(old_key):
logger.debug(
'updated reference from {0} -> {2} to {1} -> {2}'
.format(old_key, new_key, cached.key())
"updated reference from {0} -> {2} to {1} -> {2}".format(
old_key, new_key, cached.key()
)
)
cached.rename_key(old_key, new_key)
@@ -430,14 +432,16 @@ class RelationsCache:
"""
if new_key in self.relations:
dbt.exceptions.raise_cache_inconsistent(
'in rename, new key {} already in cache: {}'
.format(new_key, list(self.relations.keys()))
"in rename, new key {} already in cache: {}".format(
new_key, list(self.relations.keys())
)
)
if old_key not in self.relations:
logger.debug(
'old key {} not found in self.relations, assuming temporary'
.format(old_key)
"old key {} not found in self.relations, assuming temporary".format(
old_key
)
)
return False
return True
@@ -456,11 +460,9 @@ class RelationsCache:
"""
old_key = _make_key(old)
new_key = _make_key(new)
logger.debug('Renaming relation {!s} to {!s}'.format(
old_key, new_key
))
logger.debug("Renaming relation {!s} to {!s}".format(old_key, new_key))
lazy_log('before rename: {!s}', self.dump_graph)
lazy_log("before rename: {!s}", self.dump_graph)
with self.lock:
if self._check_rename_constraints(old_key, new_key):
@@ -468,7 +470,7 @@ class RelationsCache:
else:
self._setdefault(_CachedRelation(new))
lazy_log('after rename: {!s}', self.dump_graph)
lazy_log("after rename: {!s}", self.dump_graph)
def get_relations(
self, database: Optional[str], schema: Optional[str]
@@ -483,14 +485,14 @@ class RelationsCache:
schema = lowercase(schema)
with self.lock:
results = [
r.inner for r in self.relations.values()
if (lowercase(r.schema) == schema and
lowercase(r.database) == database)
r.inner
for r in self.relations.values()
if (lowercase(r.schema) == schema and lowercase(r.database) == database)
]
if None in results:
dbt.exceptions.raise_cache_inconsistent(
'in get_relations, a None relation was found in the cache!'
"in get_relations, a None relation was found in the cache!"
)
return results

View File

@@ -50,9 +50,7 @@ class AdapterContainer:
adapter = self.get_adapter_class_by_name(name)
return adapter.Relation
def get_config_class_by_name(
self, name: str
) -> Type[AdapterConfig]:
def get_config_class_by_name(self, name: str) -> Type[AdapterConfig]:
adapter = self.get_adapter_class_by_name(name)
return adapter.AdapterSpecificConfigs
@@ -62,24 +60,24 @@ class AdapterContainer:
# singletons
try:
# mypy doesn't think modules have any attributes.
mod: Any = import_module('.' + name, 'dbt.adapters')
mod: Any = import_module("." + name, "dbt.adapters")
except ModuleNotFoundError as exc:
# 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:
raise RuntimeException(f'Could not find adapter type {name}!')
logger.info(f'Error importing adapter: {exc}')
if exc.name == "dbt.adapters." + name:
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.
logger.debug('', exc_info=True)
logger.debug("", exc_info=True)
raise
plugin: AdapterPlugin = mod.Plugin
plugin_type = plugin.adapter.type()
if plugin_type != name:
raise RuntimeException(
f'Expected to find adapter with type named {name}, got '
f'adapter with type {plugin_type}'
f"Expected to find adapter with type named {name}, got "
f"adapter with type {plugin_type}"
)
with self.lock:
@@ -109,8 +107,7 @@ class AdapterContainer:
return self.adapters[adapter_name]
def reset_adapters(self):
"""Clear the adapters. This is useful for tests, which change configs.
"""
"""Clear the adapters. This is useful for tests, which change configs."""
with self.lock:
for adapter in self.adapters.values():
adapter.cleanup_connections()
@@ -140,9 +137,7 @@ class AdapterContainer:
try:
plugin = self.plugins[plugin_name]
except KeyError:
raise InternalException(
f'No plugin found for {plugin_name}'
) from None
raise InternalException(f"No plugin found for {plugin_name}") from None
plugins.append(plugin)
seen.add(plugin_name)
if plugin.dependencies is None:
@@ -166,7 +161,7 @@ class AdapterContainer:
path = self.packages[package_name]
except KeyError:
raise InternalException(
f'No internal package listing found for {package_name}'
f"No internal package listing found for {package_name}"
)
paths.append(path)
return paths
@@ -187,8 +182,7 @@ def get_adapter(config: AdapterRequiredConfig):
def reset_adapters():
"""Clear the adapters. This is useful for tests, which change configs.
"""
"""Clear the adapters. This is useful for tests, which change configs."""
FACTORY.reset_adapters()

View File

@@ -1,17 +1,27 @@
from dataclasses import dataclass
from typing import (
Type, Hashable, Optional, ContextManager, List, Generic, TypeVar, ClassVar,
Tuple, Union, Dict, Any
Type,
Hashable,
Optional,
ContextManager,
List,
Generic,
TypeVar,
ClassVar,
Tuple,
Union,
Dict,
Any,
)
from typing_extensions import Protocol
import agate
from dbt.contracts.connection import (
Connection, AdapterRequiredConfig, AdapterResponse
)
from dbt.contracts.connection import Connection, AdapterRequiredConfig, AdapterResponse
from dbt.contracts.graph.compiled import (
CompiledNode, ManifestNode, NonSourceCompiledNode
CompiledNode,
ManifestNode,
NonSourceCompiledNode,
)
from dbt.contracts.graph.parsed import ParsedNode, ParsedSourceDefinition
from dbt.contracts.graph.model_config import BaseConfig
@@ -34,7 +44,7 @@ class ColumnProtocol(Protocol):
pass
Self = TypeVar('Self', bound='RelationProtocol')
Self = TypeVar("Self", bound="RelationProtocol")
class RelationProtocol(Protocol):
@@ -64,19 +74,11 @@ class CompilerProtocol(Protocol):
...
AdapterConfig_T = TypeVar(
'AdapterConfig_T', bound=AdapterConfig
)
ConnectionManager_T = TypeVar(
'ConnectionManager_T', bound=ConnectionManagerProtocol
)
Relation_T = TypeVar(
'Relation_T', bound=RelationProtocol
)
Column_T = TypeVar(
'Column_T', bound=ColumnProtocol
)
Compiler_T = TypeVar('Compiler_T', bound=CompilerProtocol)
AdapterConfig_T = TypeVar("AdapterConfig_T", bound=AdapterConfig)
ConnectionManager_T = TypeVar("ConnectionManager_T", bound=ConnectionManagerProtocol)
Relation_T = TypeVar("Relation_T", bound=RelationProtocol)
Column_T = TypeVar("Column_T", bound=ColumnProtocol)
Compiler_T = TypeVar("Compiler_T", bound=CompilerProtocol)
class AdapterProtocol(
@@ -87,7 +89,7 @@ class AdapterProtocol(
Relation_T,
Column_T,
Compiler_T,
]
],
):
AdapterSpecificConfigs: ClassVar[Type[AdapterConfig_T]]
Column: ClassVar[Type[Column_T]]

View File

@@ -7,10 +7,9 @@ import agate
import dbt.clients.agate_helper
import dbt.exceptions
from dbt.adapters.base import BaseConnectionManager
from dbt.contracts.connection import (
Connection, ConnectionState, AdapterResponse
)
from dbt.contracts.connection import Connection, ConnectionState, AdapterResponse
from dbt.logger import GLOBAL_LOGGER as logger
from dbt import flags
class SQLConnectionManager(BaseConnectionManager):
@@ -22,11 +21,12 @@ class SQLConnectionManager(BaseConnectionManager):
- get_response
- open
"""
@abc.abstractmethod
def cancel(self, connection: Connection):
"""Cancel the given connection."""
raise dbt.exceptions.NotImplementedException(
'`cancel` is not implemented for this adapter!'
"`cancel` is not implemented for this adapter!"
)
def cancel_open(self) -> List[str]:
@@ -40,8 +40,8 @@ class SQLConnectionManager(BaseConnectionManager):
# if the connection failed, the handle will be None so we have
# nothing to cancel.
if (
connection.handle is not None and
connection.state == ConnectionState.OPEN
connection.handle is not None
and connection.state == ConnectionState.OPEN
):
self.cancel(connection)
if connection.name is not None:
@@ -53,23 +53,22 @@ class SQLConnectionManager(BaseConnectionManager):
sql: str,
auto_begin: bool = True,
bindings: Optional[Any] = None,
abridge_sql_log: bool = False
abridge_sql_log: bool = False,
) -> Tuple[Connection, Any]:
connection = self.get_thread_connection()
if auto_begin and connection.transaction_open is False:
self.begin()
logger.debug('Using {} connection "{}".'
.format(self.TYPE, connection.name))
logger.debug('Using {} connection "{}".'.format(self.TYPE, connection.name))
with self.exception_handler(sql):
if abridge_sql_log:
log_sql = '{}...'.format(sql[:512])
log_sql = "{}...".format(sql[:512])
else:
log_sql = sql
logger.debug(
'On {connection_name}: {sql}',
"On {connection_name}: {sql}",
connection_name=connection.name,
sql=log_sql,
)
@@ -80,7 +79,7 @@ class SQLConnectionManager(BaseConnectionManager):
logger.debug(
"SQL status: {status} in {elapsed:0.2f} seconds",
status=self.get_response(cursor),
elapsed=(time.time() - pre)
elapsed=(time.time() - pre),
)
return connection, cursor
@@ -89,23 +88,14 @@ class SQLConnectionManager(BaseConnectionManager):
def get_response(cls, cursor: Any) -> Union[AdapterResponse, str]:
"""Get the status of the cursor."""
raise dbt.exceptions.NotImplementedException(
'`get_response` is not implemented for this adapter!'
"`get_response` is not implemented for this adapter!"
)
@classmethod
def process_results(
cls,
column_names: Iterable[str],
rows: Iterable[Any]
cls, column_names: Iterable[str], rows: Iterable[Any]
) -> List[Dict[str, Any]]:
unique_col_names = dict()
for idx in range(len(column_names)):
col_name = column_names[idx]
if col_name in unique_col_names:
unique_col_names[col_name] += 1
column_names[idx] = f'{col_name}_{unique_col_names[col_name]}'
else:
unique_col_names[column_names[idx]] = 1
return [dict(zip(column_names, row)) for row in rows]
@classmethod
@@ -118,10 +108,7 @@ class SQLConnectionManager(BaseConnectionManager):
rows = cursor.fetchall()
data = cls.process_results(column_names, rows)
return dbt.clients.agate_helper.table_from_data_flat(
data,
column_names
)
return dbt.clients.agate_helper.table_from_data_flat(data, column_names)
def execute(
self, sql: str, auto_begin: bool = False, fetch: bool = False
@@ -136,17 +123,25 @@ class SQLConnectionManager(BaseConnectionManager):
return response, table
def add_begin_query(self):
return self.add_query('BEGIN', auto_begin=False)
return self.add_query("BEGIN", auto_begin=False)
def add_commit_query(self):
return self.add_query('COMMIT', auto_begin=False)
return self.add_query("COMMIT", auto_begin=False)
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 '
'it already had one open!'.format(connection.name))
"it already had one open!".format(connection.name)
)
self.add_begin_query()
@@ -155,12 +150,19 @@ 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))
"it does not have one open!".format(connection.name)
)
logger.debug('On {}: COMMIT'.format(connection.name))
logger.debug("On {}: COMMIT".format(connection.name))
self.add_commit_query()
connection.transaction_open = False

View File

@@ -10,16 +10,16 @@ from dbt.logger import GLOBAL_LOGGER as logger
from dbt.adapters.base.relation import BaseRelation
LIST_RELATIONS_MACRO_NAME = 'list_relations_without_caching'
GET_COLUMNS_IN_RELATION_MACRO_NAME = 'get_columns_in_relation'
LIST_SCHEMAS_MACRO_NAME = 'list_schemas'
CHECK_SCHEMA_EXISTS_MACRO_NAME = 'check_schema_exists'
CREATE_SCHEMA_MACRO_NAME = 'create_schema'
DROP_SCHEMA_MACRO_NAME = 'drop_schema'
RENAME_RELATION_MACRO_NAME = 'rename_relation'
TRUNCATE_RELATION_MACRO_NAME = 'truncate_relation'
DROP_RELATION_MACRO_NAME = 'drop_relation'
ALTER_COLUMN_TYPE_MACRO_NAME = 'alter_column_type'
LIST_RELATIONS_MACRO_NAME = "list_relations_without_caching"
GET_COLUMNS_IN_RELATION_MACRO_NAME = "get_columns_in_relation"
LIST_SCHEMAS_MACRO_NAME = "list_schemas"
CHECK_SCHEMA_EXISTS_MACRO_NAME = "check_schema_exists"
CREATE_SCHEMA_MACRO_NAME = "create_schema"
DROP_SCHEMA_MACRO_NAME = "drop_schema"
RENAME_RELATION_MACRO_NAME = "rename_relation"
TRUNCATE_RELATION_MACRO_NAME = "truncate_relation"
DROP_RELATION_MACRO_NAME = "drop_relation"
ALTER_COLUMN_TYPE_MACRO_NAME = "alter_column_type"
class SQLAdapter(BaseAdapter):
@@ -60,30 +60,23 @@ class SQLAdapter(BaseAdapter):
:param abridge_sql_log: If set, limit the raw sql logged to 512
characters
"""
return self.connections.add_query(sql, auto_begin, bindings,
abridge_sql_log)
return self.connections.add_query(sql, auto_begin, bindings, abridge_sql_log)
@classmethod
def convert_text_type(cls, agate_table: agate.Table, col_idx: int) -> str:
return "text"
@classmethod
def convert_number_type(
cls, agate_table: agate.Table, col_idx: int
) -> str:
decimals = agate_table.aggregate(agate.MaxPrecision(col_idx))
def convert_number_type(cls, agate_table: agate.Table, col_idx: int) -> str:
decimals = agate_table.aggregate(agate.MaxPrecision(col_idx)) # type: ignore
return "float8" if decimals else "integer"
@classmethod
def convert_boolean_type(
cls, agate_table: agate.Table, col_idx: int
) -> str:
def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str:
return "boolean"
@classmethod
def convert_datetime_type(
cls, agate_table: agate.Table, col_idx: int
) -> str:
def convert_datetime_type(cls, agate_table: agate.Table, col_idx: int) -> str:
return "timestamp without time zone"
@classmethod
@@ -99,31 +92,28 @@ class SQLAdapter(BaseAdapter):
return True
def expand_column_types(self, goal, current):
reference_columns = {
c.name: c for c in
self.get_columns_in_relation(goal)
}
reference_columns = {c.name: c for c in self.get_columns_in_relation(goal)}
target_columns = {
c.name: c for c
in self.get_columns_in_relation(current)
}
target_columns = {c.name: c for c in self.get_columns_in_relation(current)}
for column_name, reference_column in reference_columns.items():
target_column = target_columns.get(column_name)
if target_column is not None and \
target_column.can_expand_to(reference_column):
if target_column is not None and target_column.can_expand_to(
reference_column
):
col_string_size = reference_column.string_size()
new_type = self.Column.string_type(col_string_size)
logger.debug("Changing col type from {} to {} in table {}",
target_column.data_type, new_type, 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)
def alter_column_type(
self, relation, column_name, new_column_type
) -> None:
def alter_column_type(self, relation, column_name, new_column_type) -> None:
"""
1. Create a new column (w/ temp name and correct type)
2. Copy data over to it
@@ -131,53 +121,40 @@ class SQLAdapter(BaseAdapter):
4. Rename the new column to existing column
"""
kwargs = {
'relation': relation,
'column_name': column_name,
'new_column_type': new_column_type,
"relation": relation,
"column_name": column_name,
"new_column_type": new_column_type,
}
self.execute_macro(
ALTER_COLUMN_TYPE_MACRO_NAME,
kwargs=kwargs
)
self.execute_macro(ALTER_COLUMN_TYPE_MACRO_NAME, kwargs=kwargs)
def drop_relation(self, relation):
if relation.type is None:
dbt.exceptions.raise_compiler_error(
'Tried to drop relation {}, but its type is null.'
.format(relation))
"Tried to drop relation {}, but its type is null.".format(relation)
)
self.cache_dropped(relation)
self.execute_macro(
DROP_RELATION_MACRO_NAME,
kwargs={'relation': relation}
)
self.execute_macro(DROP_RELATION_MACRO_NAME, kwargs={"relation": relation})
def truncate_relation(self, relation):
self.execute_macro(
TRUNCATE_RELATION_MACRO_NAME,
kwargs={'relation': relation}
)
self.execute_macro(TRUNCATE_RELATION_MACRO_NAME, kwargs={"relation": relation})
def rename_relation(self, from_relation, to_relation):
self.cache_renamed(from_relation, to_relation)
kwargs = {'from_relation': from_relation, 'to_relation': to_relation}
self.execute_macro(
RENAME_RELATION_MACRO_NAME,
kwargs=kwargs
)
kwargs = {"from_relation": from_relation, "to_relation": to_relation}
self.execute_macro(RENAME_RELATION_MACRO_NAME, kwargs=kwargs)
def get_columns_in_relation(self, relation):
return self.execute_macro(
GET_COLUMNS_IN_RELATION_MACRO_NAME,
kwargs={'relation': relation}
GET_COLUMNS_IN_RELATION_MACRO_NAME, kwargs={"relation": relation}
)
def create_schema(self, relation: BaseRelation) -> None:
relation = relation.without_identifier()
logger.debug('Creating schema "{}"', relation)
kwargs = {
'relation': relation,
"relation": relation,
}
self.execute_macro(CREATE_SCHEMA_MACRO_NAME, kwargs=kwargs)
self.commit_if_has_connection()
@@ -188,39 +165,35 @@ class SQLAdapter(BaseAdapter):
relation = relation.without_identifier()
logger.debug('Dropping schema "{}".', relation)
kwargs = {
'relation': relation,
"relation": relation,
}
self.execute_macro(DROP_SCHEMA_MACRO_NAME, kwargs=kwargs)
# we can update the cache here
self.cache.drop_schema(relation.database, relation.schema)
def list_relations_without_caching(
self, schema_relation: BaseRelation,
self,
schema_relation: BaseRelation,
) -> List[BaseRelation]:
kwargs = {'schema_relation': schema_relation}
results = self.execute_macro(
LIST_RELATIONS_MACRO_NAME,
kwargs=kwargs
)
kwargs = {"schema_relation": schema_relation}
results = self.execute_macro(LIST_RELATIONS_MACRO_NAME, kwargs=kwargs)
relations = []
quote_policy = {
'database': True,
'schema': True,
'identifier': True
}
quote_policy = {"database": True, "schema": True, "identifier": True}
for _database, name, _schema, _type in results:
try:
_type = self.Relation.get_relation_type(_type)
except ValueError:
_type = self.Relation.External
relations.append(self.Relation.create(
database=_database,
schema=_schema,
identifier=name,
quote_policy=quote_policy,
type=_type
))
relations.append(
self.Relation.create(
database=_database,
schema=_schema,
identifier=name,
quote_policy=quote_policy,
type=_type,
)
)
return relations
def quote(self, identifier):
@@ -228,8 +201,7 @@ class SQLAdapter(BaseAdapter):
def list_schemas(self, database: str) -> List[str]:
results = self.execute_macro(
LIST_SCHEMAS_MACRO_NAME,
kwargs={'database': database}
LIST_SCHEMAS_MACRO_NAME, kwargs={"database": database}
)
return [row[0] for row in results]
@@ -238,13 +210,10 @@ class SQLAdapter(BaseAdapter):
information_schema = self.Relation.create(
database=database,
schema=schema,
identifier='INFORMATION_SCHEMA',
quote_policy=self.config.quoting
identifier="INFORMATION_SCHEMA",
quote_policy=self.config.quoting,
).information_schema()
kwargs = {'information_schema': information_schema, 'schema': schema}
results = self.execute_macro(
CHECK_SCHEMA_EXISTS_MACRO_NAME,
kwargs=kwargs
)
kwargs = {"information_schema": information_schema, "schema": schema}
results = self.execute_macro(CHECK_SCHEMA_EXISTS_MACRO_NAME, kwargs=kwargs)
return results[0][0] > 0

View File

@@ -10,79 +10,89 @@ def regex(pat):
class BlockData:
"""raw plaintext data from the top level of the file."""
def __init__(self, contents):
self.block_type_name = '__dbt__data'
self.block_type_name = "__dbt__data"
self.contents = contents
self.full_block = contents
class BlockTag:
def __init__(self, block_type_name, block_name, contents=None,
full_block=None, **kw):
def __init__(
self, block_type_name, block_name, contents=None, full_block=None, **kw
):
self.block_type_name = block_type_name
self.block_name = block_name
self.contents = contents
self.full_block = full_block
def __str__(self):
return 'BlockTag({!r}, {!r})'.format(self.block_type_name,
self.block_name)
return "BlockTag({!r}, {!r})".format(self.block_type_name, self.block_name)
def __repr__(self):
return str(self)
@property
def end_block_type_name(self):
return 'end{}'.format(self.block_type_name)
return "end{}".format(self.block_type_name)
def end_pat(self):
# we don't want to use string formatting here because jinja uses most
# of the string formatting operators in its syntax...
pattern = ''.join((
r'(?P<endblock>((?:\s*\{\%\-|\{\%)\s*',
self.end_block_type_name,
r'\s*(?:\-\%\}\s*|\%\})))',
))
pattern = "".join(
(
r"(?P<endblock>((?:\s*\{\%\-|\{\%)\s*",
self.end_block_type_name,
r"\s*(?:\-\%\}\s*|\%\})))",
)
)
return regex(pattern)
Tag = namedtuple('Tag', 'block_type_name block_name start end')
Tag = namedtuple("Tag", "block_type_name block_name start end")
_NAME_PATTERN = r'[A-Za-z_][A-Za-z_0-9]*'
_NAME_PATTERN = r"[A-Za-z_][A-Za-z_0-9]*"
COMMENT_START_PATTERN = regex(r'(?:(?P<comment_start>(\s*\{\#)))')
COMMENT_END_PATTERN = regex(r'(.*?)(\s*\#\})')
COMMENT_START_PATTERN = regex(r"(?:(?P<comment_start>(\s*\{\#)))")
COMMENT_END_PATTERN = regex(r"(.*?)(\s*\#\})")
RAW_START_PATTERN = regex(
r'(?:\s*\{\%\-|\{\%)\s*(?P<raw_start>(raw))\s*(?:\-\%\}\s*|\%\})'
r"(?:\s*\{\%\-|\{\%)\s*(?P<raw_start>(raw))\s*(?:\-\%\}\s*|\%\})"
)
EXPR_START_PATTERN = regex(r'(?P<expr_start>(\{\{\s*))')
EXPR_END_PATTERN = regex(r'(?P<expr_end>(\s*\}\}))')
EXPR_START_PATTERN = regex(r"(?P<expr_start>(\{\{\s*))")
EXPR_END_PATTERN = regex(r"(?P<expr_end>(\s*\}\}))")
BLOCK_START_PATTERN = regex(''.join((
r'(?:\s*\{\%\-|\{\%)\s*',
r'(?P<block_type_name>({}))'.format(_NAME_PATTERN),
# some blocks have a 'block name'.
r'(?:\s+(?P<block_name>({})))?'.format(_NAME_PATTERN),
)))
BLOCK_START_PATTERN = regex(
"".join(
(
r"(?:\s*\{\%\-|\{\%)\s*",
r"(?P<block_type_name>({}))".format(_NAME_PATTERN),
# some blocks have a 'block name'.
r"(?:\s+(?P<block_name>({})))?".format(_NAME_PATTERN),
)
)
)
RAW_BLOCK_PATTERN = regex(''.join((
r'(?:\s*\{\%\-|\{\%)\s*raw\s*(?:\-\%\}\s*|\%\})',
r'(?:.*?)',
r'(?:\s*\{\%\-|\{\%)\s*endraw\s*(?:\-\%\}\s*|\%\})',
)))
RAW_BLOCK_PATTERN = regex(
"".join(
(
r"(?:\s*\{\%\-|\{\%)\s*raw\s*(?:\-\%\}\s*|\%\})",
r"(?:.*?)",
r"(?:\s*\{\%\-|\{\%)\s*endraw\s*(?:\-\%\}\s*|\%\})",
)
)
)
TAG_CLOSE_PATTERN = regex(r'(?:(?P<tag_close>(\-\%\}\s*|\%\})))')
TAG_CLOSE_PATTERN = regex(r"(?:(?P<tag_close>(\-\%\}\s*|\%\})))")
# stolen from jinja's lexer. Note that we've consumed all prefix whitespace by
# the time we want to use this.
STRING_PATTERN = regex(
r"(?P<string>('([^'\\]*(?:\\.[^'\\]*)*)'|"
r'"([^"\\]*(?:\\.[^"\\]*)*)"))'
r"(?P<string>('([^'\\]*(?:\\.[^'\\]*)*)'|" r'"([^"\\]*(?:\\.[^"\\]*)*)"))'
)
QUOTE_START_PATTERN = regex(r'''(?P<quote>(['"]))''')
QUOTE_START_PATTERN = regex(r"""(?P<quote>(['"]))""")
class TagIterator:
@@ -99,10 +109,10 @@ class TagIterator:
end_val: int = self.pos if end is None else end
data = self.data[:end_val]
# if not found, rfind returns -1, and -1+1=0, which is perfect!
last_line_start = data.rfind('\n') + 1
last_line_start = data.rfind("\n") + 1
# it's easy to forget this, but line numbers are 1-indexed
line_number = data.count('\n') + 1
return f'{line_number}:{end_val - last_line_start}'
line_number = data.count("\n") + 1
return f"{line_number}:{end_val - last_line_start}"
def advance(self, new_position):
self.pos = new_position
@@ -120,7 +130,7 @@ class TagIterator:
matches = []
for pattern in patterns:
# default to 'search', but sometimes we want to 'match'.
if kwargs.get('method', 'search') == 'search':
if kwargs.get("method", "search") == "search":
match = self._search(pattern)
else:
match = self._match(pattern)
@@ -136,7 +146,7 @@ class TagIterator:
match = self._first_match(*patterns, **kwargs)
if match is None:
msg = 'unexpected EOF, expected {}, got "{}"'.format(
expected_name, self.data[self.pos:]
expected_name, self.data[self.pos :]
)
dbt.exceptions.raise_compiler_error(msg)
return match
@@ -156,22 +166,20 @@ class TagIterator:
"""
self.advance(match.end())
while True:
match = self._expect_match('}}',
EXPR_END_PATTERN,
QUOTE_START_PATTERN)
if match.groupdict().get('expr_end') is not None:
match = self._expect_match("}}", EXPR_END_PATTERN, QUOTE_START_PATTERN)
if match.groupdict().get("expr_end") is not None:
break
else:
# it's a quote. we haven't advanced for this match yet, so
# just slurp up the whole string, no need to rewind.
match = self._expect_match('string', STRING_PATTERN)
match = self._expect_match("string", STRING_PATTERN)
self.advance(match.end())
self.advance(match.end())
def handle_comment(self, match):
self.advance(match.end())
match = self._expect_match('#}', COMMENT_END_PATTERN)
match = self._expect_match("#}", COMMENT_END_PATTERN)
self.advance(match.end())
def _expect_block_close(self):
@@ -188,22 +196,19 @@ class TagIterator:
"""
while True:
end_match = self._expect_match(
'tag close ("%}")',
QUOTE_START_PATTERN,
TAG_CLOSE_PATTERN
'tag close ("%}")', QUOTE_START_PATTERN, TAG_CLOSE_PATTERN
)
self.advance(end_match.end())
if end_match.groupdict().get('tag_close') is not None:
if end_match.groupdict().get("tag_close") is not None:
return
# must be a string. Rewind to its start and advance past it.
self.rewind()
string_match = self._expect_match('string', STRING_PATTERN)
string_match = self._expect_match("string", STRING_PATTERN)
self.advance(string_match.end())
def handle_raw(self):
# raw blocks are super special, they are a single complete regex
match = self._expect_match('{% raw %}...{% endraw %}',
RAW_BLOCK_PATTERN)
match = self._expect_match("{% raw %}...{% endraw %}", RAW_BLOCK_PATTERN)
self.advance(match.end())
return match.end()
@@ -220,13 +225,12 @@ class TagIterator:
"""
groups = match.groupdict()
# always a value
block_type_name = groups['block_type_name']
block_type_name = groups["block_type_name"]
# might be None
block_name = groups.get('block_name')
block_name = groups.get("block_name")
start_pos = self.pos
if block_type_name == 'raw':
match = self._expect_match('{% raw %}...{% endraw %}',
RAW_BLOCK_PATTERN)
if block_type_name == "raw":
match = self._expect_match("{% raw %}...{% endraw %}", RAW_BLOCK_PATTERN)
self.advance(match.end())
else:
self.advance(match.end())
@@ -235,15 +239,13 @@ class TagIterator:
block_type_name=block_type_name,
block_name=block_name,
start=start_pos,
end=self.pos
end=self.pos,
)
def find_tags(self):
while True:
match = self._first_match(
BLOCK_START_PATTERN,
COMMENT_START_PATTERN,
EXPR_START_PATTERN
BLOCK_START_PATTERN, COMMENT_START_PATTERN, EXPR_START_PATTERN
)
if match is None:
break
@@ -252,9 +254,9 @@ class TagIterator:
# start = self.pos
groups = match.groupdict()
comment_start = groups.get('comment_start')
expr_start = groups.get('expr_start')
block_type_name = groups.get('block_type_name')
comment_start = groups.get("comment_start")
expr_start = groups.get("expr_start")
block_type_name = groups.get("block_type_name")
if comment_start is not None:
self.handle_comment(match)
@@ -264,8 +266,8 @@ class TagIterator:
yield self.handle_tag(match)
else:
raise dbt.exceptions.InternalException(
'Invalid regex match in next_block, expected block start, '
'expr start, or comment start'
"Invalid regex match in next_block, expected block start, "
"expr start, or comment start"
)
def __iter__(self):
@@ -273,21 +275,18 @@ class TagIterator:
duplicate_tags = (
'Got nested tags: {outer.block_type_name} (started at {outer.start}) did '
'not have a matching {{% end{outer.block_type_name} %}} before a '
'subsequent {inner.block_type_name} was found (started at {inner.start})'
"Got nested tags: {outer.block_type_name} (started at {outer.start}) did "
"not have a matching {{% end{outer.block_type_name} %}} before a "
"subsequent {inner.block_type_name} was found (started at {inner.start})"
)
_CONTROL_FLOW_TAGS = {
'if': 'endif',
'for': 'endfor',
"if": "endif",
"for": "endfor",
}
_CONTROL_FLOW_END_TAGS = {
v: k
for k, v in _CONTROL_FLOW_TAGS.items()
}
_CONTROL_FLOW_END_TAGS = {v: k for k, v in _CONTROL_FLOW_TAGS.items()}
class BlockIterator:
@@ -310,15 +309,15 @@ class BlockIterator:
def is_current_end(self, tag):
return (
tag.block_type_name.startswith('end') and
self.current is not None and
tag.block_type_name[3:] == self.current.block_type_name
tag.block_type_name.startswith("end")
and self.current is not None
and tag.block_type_name[3:] == self.current.block_type_name
)
def find_blocks(self, allowed_blocks=None, collect_raw_data=True):
"""Find all top-level blocks in the data."""
if allowed_blocks is None:
allowed_blocks = {'snapshot', 'macro', 'materialization', 'docs'}
allowed_blocks = {"snapshot", "macro", "materialization", "docs"}
for tag in self.tag_parser.find_tags():
if tag.block_type_name in _CONTROL_FLOW_TAGS:
@@ -329,37 +328,43 @@ class BlockIterator:
found = self.stack.pop()
else:
expected = _CONTROL_FLOW_END_TAGS[tag.block_type_name]
dbt.exceptions.raise_compiler_error((
'Got an unexpected control flow end tag, got {} but '
'never saw a preceeding {} (@ {})'
).format(
tag.block_type_name,
expected,
self.tag_parser.linepos(tag.start)
))
dbt.exceptions.raise_compiler_error(
(
"Got an unexpected control flow end tag, got {} but "
"never saw a preceeding {} (@ {})"
).format(
tag.block_type_name,
expected,
self.tag_parser.linepos(tag.start),
)
)
expected = _CONTROL_FLOW_TAGS[found]
if expected != tag.block_type_name:
dbt.exceptions.raise_compiler_error((
'Got an unexpected control flow end tag, got {} but '
'expected {} next (@ {})'
).format(
tag.block_type_name,
expected,
self.tag_parser.linepos(tag.start)
))
dbt.exceptions.raise_compiler_error(
(
"Got an unexpected control flow end tag, got {} but "
"expected {} next (@ {})"
).format(
tag.block_type_name,
expected,
self.tag_parser.linepos(tag.start),
)
)
if tag.block_type_name in allowed_blocks:
if self.stack:
dbt.exceptions.raise_compiler_error((
'Got a block definition inside control flow at {}. '
'All dbt block definitions must be at the top level'
).format(self.tag_parser.linepos(tag.start)))
dbt.exceptions.raise_compiler_error(
(
"Got a block definition inside control flow at {}. "
"All dbt block definitions must be at the top level"
).format(self.tag_parser.linepos(tag.start))
)
if self.current is not None:
dbt.exceptions.raise_compiler_error(
duplicate_tags.format(outer=self.current, inner=tag)
)
if collect_raw_data:
raw_data = self.data[self.last_position:tag.start]
raw_data = self.data[self.last_position : tag.start]
self.last_position = tag.start
if raw_data:
yield BlockData(raw_data)
@@ -371,23 +376,28 @@ class BlockIterator:
yield BlockTag(
block_type_name=self.current.block_type_name,
block_name=self.current.block_name,
contents=self.data[self.current.end:tag.start],
full_block=self.data[self.current.start:tag.end]
contents=self.data[self.current.end : tag.start],
full_block=self.data[self.current.start : tag.end],
)
self.current = None
if self.current:
linecount = self.data[:self.current.end].count('\n') + 1
dbt.exceptions.raise_compiler_error((
'Reached EOF without finding a close tag for '
'{} (searched from line {})'
).format(self.current.block_type_name, linecount))
linecount = self.data[: self.current.end].count("\n") + 1
dbt.exceptions.raise_compiler_error(
(
"Reached EOF without finding a close tag for "
"{} (searched from line {})"
).format(self.current.block_type_name, linecount)
)
if collect_raw_data:
raw_data = self.data[self.last_position:]
raw_data = self.data[self.last_position :]
if raw_data:
yield BlockData(raw_data)
def lex_for_blocks(self, allowed_blocks=None, collect_raw_data=True):
return list(self.find_blocks(allowed_blocks=allowed_blocks,
collect_raw_data=collect_raw_data))
return list(
self.find_blocks(
allowed_blocks=allowed_blocks, collect_raw_data=collect_raw_data
)
)

View File

@@ -10,7 +10,7 @@ from typing import Iterable, List, Dict, Union, Optional, Any
from dbt.exceptions import RuntimeException
BOM = BOM_UTF8.decode('utf-8') # '\ufeff'
BOM = BOM_UTF8.decode("utf-8") # '\ufeff'
class ISODateTime(agate.data_types.DateTime):
@@ -30,32 +30,23 @@ class ISODateTime(agate.data_types.DateTime):
except: # noqa
pass
raise agate.exceptions.CastError(
'Can not parse value "%s" as datetime.' % d
)
raise agate.exceptions.CastError('Can not parse value "%s" as datetime.' % d)
def build_type_tester(
text_columns: Iterable[str],
string_null_values: Optional[Iterable[str]] = ('null', '')
) -> agate.TypeTester:
def build_type_tester(text_columns: Iterable[str]) -> agate.TypeTester:
types = [
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', ''),
datetime_format='%Y-%m-%d %H:%M:%S'),
ISODateTime(null_values=('null', '')),
agate.data_types.Boolean(true_values=('true',),
false_values=('false',),
null_values=('null', '')),
agate.data_types.Text(null_values=string_null_values)
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", ""), datetime_format="%Y-%m-%d %H:%M:%S"
),
ISODateTime(null_values=("null", "")),
agate.data_types.Boolean(
true_values=("true",), false_values=("false",), null_values=("null", "")
),
agate.data_types.Text(null_values=("null", "")),
]
force = {
k: agate.data_types.Text(null_values=string_null_values)
for k in text_columns
}
force = {k: agate.data_types.Text(null_values=("null", "")) for k in text_columns}
return agate.TypeTester(force=force, types=types)
@@ -70,13 +61,7 @@ def table_from_rows(
if text_only_columns is None:
column_types = DEFAULT_TYPE_TESTER
else:
# If text_only_columns are present, prevent coercing empty string or
# literal 'null' strings to a None representation.
column_types = build_type_tester(
text_only_columns,
string_null_values=()
)
column_types = build_type_tester(text_only_columns)
return agate.Table(rows, column_names, column_types=column_types)
@@ -96,34 +81,19 @@ def table_from_data(data, column_names: Iterable[str]) -> agate.Table:
def table_from_data_flat(data, column_names: Iterable[str]) -> agate.Table:
"""
Convert a list of dictionaries into an Agate table. This method does not
coerce string values into more specific types (eg. '005' will not be
coerced to '5'). Additionally, this method does not coerce values to
None (eg. '' or 'null' will retain their string literal representations).
"""
"Convert list of dictionaries into an Agate table"
rows = []
text_only_columns = set()
for _row in data:
row = []
for col_name in column_names:
value = _row[col_name]
for value in list(_row.values()):
if isinstance(value, (dict, list, tuple)):
# Represent container types as json strings
value = json.dumps(value, cls=dbt.utils.JSONEncoder)
text_only_columns.add(col_name)
elif isinstance(value, str):
text_only_columns.add(col_name)
row.append(value)
row.append(json.dumps(value, cls=dbt.utils.JSONEncoder))
else:
row.append(value)
rows.append(row)
return table_from_rows(
rows=rows,
column_names=column_names,
text_only_columns=text_only_columns
)
return table_from_rows(rows=rows, column_names=column_names)
def empty_table():
@@ -140,7 +110,7 @@ def as_matrix(table):
def from_csv(abspath, text_columns):
type_tester = build_type_tester(text_columns=text_columns)
with open(abspath, encoding='utf-8') as fp:
with open(abspath, encoding="utf-8") as fp:
if fp.read(1) != BOM:
fp.seek(0)
return agate.Table.from_csv(fp, column_types=type_tester)
@@ -172,8 +142,8 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
elif not isinstance(value, type(existing_type)):
# actual type mismatch!
raise RuntimeException(
f'Tables contain columns with the same names ({key}), '
f'but different types ({value} vs {existing_type})'
f"Tables contain columns with the same names ({key}), "
f"but different types ({value} vs {existing_type})"
)
def finalize(self) -> Dict[str, agate.data_types.DataType]:
@@ -188,7 +158,7 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
def _merged_column_types(
tables: List[agate.Table]
tables: List[agate.Table],
) -> Dict[str, agate.data_types.DataType]:
# this is a lot like agate.Table.merge, but with handling for all-null
# rows being "any type".
@@ -215,10 +185,7 @@ def merge_tables(tables: List[agate.Table]) -> agate.Table:
rows: List[agate.Row] = []
for table in tables:
if (
table.column_names == column_names and
table.column_types == column_types
):
if table.column_names == column_names and table.column_types == column_types:
rows.extend(table.rows)
else:
for row in table.rows:

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

@@ -4,112 +4,77 @@ import os.path
from dbt.clients.system import run_cmd, rmdir
from dbt.logger import GLOBAL_LOGGER as logger
import dbt.exceptions
from packaging import version
def _is_commit(revision: str) -> bool:
# match SHA-1 git commit
return bool(re.match(r"\b[0-9a-f]{40}\b", revision))
def clone(repo, cwd, dirname=None, remove_git_dir=False, branch=None):
clone_cmd = ["git", "clone", "--depth", "1"]
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:
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"):
# 2.25.0 introduces --sparse
raise RuntimeError(
"Please update your git version to pull a dbt package "
"from a subdirectory: your version is {}, >= 2.25.0 needed".format(git_version)
)
clone_cmd.extend(['--filter=blob:none', '--sparse'])
if has_revision and not is_commit:
clone_cmd.extend(['--branch', revision])
if branch is not None:
clone_cmd.extend(["--branch", branch])
clone_cmd.append(repo)
if dirname is not None:
clone_cmd.append(dirname)
result = run_cmd(cwd, clone_cmd, env={'LC_ALL': 'C'})
if subdirectory:
run_cmd(os.path.join(cwd, dirname or ''), ['git', 'sparse-checkout', 'set', subdirectory])
result = run_cmd(cwd, clone_cmd, env={"LC_ALL": "C"})
if remove_git_dir:
rmdir(os.path.join(dirname, '.git'))
rmdir(os.path.join(dirname, ".git"))
return result
def list_tags(cwd):
out, err = run_cmd(cwd, ['git', 'tag', '--list'], env={'LC_ALL': 'C'})
tags = out.decode('utf-8').strip().split("\n")
out, err = run_cmd(cwd, ["git", "tag", "--list"], env={"LC_ALL": "C"})
tags = out.decode("utf-8").strip().split("\n")
return tags
def _checkout(cwd, repo, revision):
logger.debug(' Checking out revision {}.'.format(revision))
def _checkout(cwd, repo, branch):
logger.debug(" Checking out branch {}.".format(branch))
fetch_cmd = ["git", "fetch", "origin", "--depth", "1"]
run_cmd(cwd, ["git", "remote", "set-branches", "origin", branch])
run_cmd(cwd, ["git", "fetch", "--tags", "--depth", "1", "origin", branch])
if _is_commit(revision):
run_cmd(cwd, fetch_cmd + [revision])
else:
run_cmd(cwd, ['git', 'remote', 'set-branches', 'origin', revision])
run_cmd(cwd, fetch_cmd + ["--tags", revision])
tags = list_tags(cwd)
if _is_commit(revision):
spec = revision
# Prefer tags to branches if one exists
elif revision in list_tags(cwd):
spec = 'tags/{}'.format(revision)
if branch in tags:
spec = "tags/{}".format(branch)
else:
spec = 'origin/{}'.format(revision)
spec = "origin/{}".format(branch)
out, err = run_cmd(cwd, ['git', 'reset', '--hard', spec],
env={'LC_ALL': 'C'})
out, err = run_cmd(cwd, ["git", "reset", "--hard", spec], env={"LC_ALL": "C"})
return out, err
def checkout(cwd, repo, revision=None):
if revision is None:
revision = 'HEAD'
def checkout(cwd, repo, branch=None):
if branch is None:
branch = "HEAD"
try:
return _checkout(cwd, repo, revision)
return _checkout(cwd, repo, branch)
except dbt.exceptions.CommandResultError as exc:
stderr = exc.stderr.decode('utf-8').strip()
dbt.exceptions.bad_package_spec(repo, revision, stderr)
stderr = exc.stderr.decode("utf-8").strip()
dbt.exceptions.bad_package_spec(repo, branch, stderr)
def get_current_sha(cwd):
out, err = run_cmd(cwd, ['git', 'rev-parse', 'HEAD'], env={'LC_ALL': 'C'})
out, err = run_cmd(cwd, ["git", "rev-parse", "HEAD"], env={"LC_ALL": "C"})
return out.decode('utf-8')
return out.decode("utf-8")
def remove_remote(cwd):
return run_cmd(cwd, ['git', 'remote', 'rm', 'origin'], env={'LC_ALL': 'C'})
return run_cmd(cwd, ["git", "remote", "rm", "origin"], env={"LC_ALL": "C"})
def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
revision=None, subdirectory=None):
def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False, branch=None):
exists = None
try:
_, err = clone(
repo,
cwd,
dirname=dirname,
remove_git_dir=remove_git_dir,
subdirectory=subdirectory,
)
_, err = clone(repo, cwd, dirname=dirname, remove_git_dir=remove_git_dir)
except dbt.exceptions.CommandResultError as exc:
err = exc.stderr.decode('utf-8')
err = exc.stderr.decode("utf-8")
exists = re.match("fatal: destination path '(.+)' already exists", err)
if not exists: # something else is wrong, raise it
raise
@@ -118,25 +83,26 @@ def clone_and_checkout(repo, cwd, dirname=None, remove_git_dir=False,
start_sha = None
if exists:
directory = exists.group(1)
logger.debug('Updating existing dependency {}.', directory)
logger.debug("Updating existing dependency {}.", directory)
else:
matches = re.match("Cloning into '(.+)'", err.decode('utf-8'))
matches = re.match("Cloning into '(.+)'", err.decode("utf-8"))
if matches is None:
raise dbt.exceptions.RuntimeException(
f'Error cloning {repo} - never saw "Cloning into ..." from git'
)
directory = matches.group(1)
logger.debug('Pulling new dependency {}.', 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)
checkout(full_path, repo, branch)
end_sha = get_current_sha(full_path)
if exists:
if start_sha == end_sha:
logger.debug(' Already at {}, nothing to do.', start_sha[:7])
logger.debug(" Already at {}, nothing to do.", start_sha[:7])
else:
logger.debug(' Updated checkout from {} to {}.',
start_sha[:7], end_sha[:7])
logger.debug(
" Updated checkout from {} to {}.", start_sha[:7], end_sha[:7]
)
else:
logger.debug(' Checked out at {}.', end_sha[:7])
return os.path.join(directory, subdirectory or '')
logger.debug(" Checked out at {}.", end_sha[:7])
return directory

View File

@@ -8,8 +8,17 @@ from ast import literal_eval
from contextlib import contextmanager
from itertools import chain, islice
from typing import (
List, Union, Set, Optional, Dict, Any, Iterator, Type, NoReturn, Tuple,
Callable
List,
Union,
Set,
Optional,
Dict,
Any,
Iterator,
Type,
NoReturn,
Tuple,
Callable,
)
import jinja2
@@ -20,17 +29,22 @@ import jinja2.parser
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
get_dbt_macro_name,
get_docs_macro_name,
get_materialization_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
InternalException,
raise_compiler_error,
CompilationException,
invalid_materialization_argument,
MacroReturn,
JinjaRenderingException,
)
from dbt import flags
from dbt.logger import GLOBAL_LOGGER as logger # noqa
@@ -41,26 +55,26 @@ def _linecache_inject(source, write):
# this is the only reliable way to accomplish this. Obviously, it's
# really darn noisy and will fill your temporary directory
tmp_file = tempfile.NamedTemporaryFile(
prefix='dbt-macro-compiled-',
suffix='.py',
prefix="dbt-macro-compiled-",
suffix=".py",
delete=False,
mode='w+',
encoding='utf-8',
mode="w+",
encoding="utf-8",
)
tmp_file.write(source)
filename = tmp_file.name
else:
# `codecs.encode` actually takes a `bytes` as the first argument if
# the second argument is 'hex' - mypy does not know this.
rnd = codecs.encode(os.urandom(12), 'hex') # type: ignore
filename = rnd.decode('ascii')
rnd = codecs.encode(os.urandom(12), "hex") # type: ignore
filename = rnd.decode("ascii")
# put ourselves in the cache
cache_entry = (
len(source),
None,
[line + '\n' for line in source.splitlines()],
filename
[line + "\n" for line in source.splitlines()],
filename,
)
# linecache does in fact have an attribute `cache`, thanks
linecache.cache[filename] = cache_entry # type: ignore
@@ -74,12 +88,10 @@ class MacroFuzzParser(jinja2.parser.Parser):
# modified to fuzz macros defined in the same file. this way
# dbt can understand the stack of macros being called.
# - @cmcarthur
node.name = get_dbt_macro_name(
self.parse_assign_target(name_only=True).name)
node.name = get_dbt_macro_name(self.parse_assign_target(name_only=True).name)
self.parse_signature(node)
node.body = self.parse_statements(('name:endmacro',),
drop_needle=True)
node.body = self.parse_statements(("name:endmacro",), drop_needle=True)
return node
@@ -95,8 +107,8 @@ class MacroFuzzEnvironment(jinja2.sandbox.SandboxedEnvironment):
If the value is 'write', also write the files to disk.
WARNING: This can write a ton of data if you aren't careful.
"""
if filename == '<template>' and flags.MACRO_DEBUGGING:
write = flags.MACRO_DEBUGGING == 'write'
if filename == "<template>" and flags.MACRO_DEBUGGING:
write = flags.MACRO_DEBUGGING == "write"
filename = _linecache_inject(source, write)
return super()._compile(source, filename) # type: ignore
@@ -139,7 +151,7 @@ def quoted_native_concat(nodes):
head = list(islice(nodes, 2))
if not head:
return ''
return ""
if len(head) == 1:
raw = head[0]
@@ -181,9 +193,7 @@ class NativeSandboxTemplate(jinja2.nativetypes.NativeTemplate): # mypy: ignore
vars = dict(*args, **kwargs)
try:
return quoted_native_concat(
self.root_render_func(self.new_context(vars))
)
return quoted_native_concat(self.root_render_func(self.new_context(vars)))
except Exception:
return self.environment.handle_exception()
@@ -222,10 +232,10 @@ class BaseMacroGenerator:
self.context: Optional[Dict[str, Any]] = context
def get_template(self):
raise NotImplementedError('get_template not implemented!')
raise NotImplementedError("get_template not implemented!")
def get_name(self) -> str:
raise NotImplementedError('get_name not implemented!')
raise NotImplementedError("get_name not implemented!")
def get_macro(self):
name = self.get_name()
@@ -248,9 +258,7 @@ class BaseMacroGenerator:
def call_macro(self, *args, **kwargs):
# called from __call__ methods
if self.context is None:
raise InternalException(
'Context is still None in call_macro!'
)
raise InternalException("Context is still None in call_macro!")
assert self.context is not None
macro = self.get_macro()
@@ -277,7 +285,7 @@ class MacroStack(threading.local):
def pop(self, name):
got = self.call_stack.pop()
if got != name:
raise InternalException(f'popped {got}, expected {name}')
raise InternalException(f"popped {got}, expected {name}")
class MacroGenerator(BaseMacroGenerator):
@@ -286,7 +294,7 @@ class MacroGenerator(BaseMacroGenerator):
macro,
context: Optional[Dict[str, Any]] = None,
node: Optional[Any] = None,
stack: Optional[MacroStack] = None
stack: Optional[MacroStack] = None,
) -> None:
super().__init__(context)
self.macro = macro
@@ -334,9 +342,7 @@ class MacroGenerator(BaseMacroGenerator):
class QueryStringGenerator(BaseMacroGenerator):
def __init__(
self, template_str: str, context: Dict[str, Any]
) -> None:
def __init__(self, template_str: str, context: Dict[str, Any]) -> None:
super().__init__(context)
self.template_str: str = template_str
env = get_environment()
@@ -346,7 +352,7 @@ class QueryStringGenerator(BaseMacroGenerator):
)
def get_name(self) -> str:
return 'query_comment_macro'
return "query_comment_macro"
def get_template(self):
"""Don't use the template cache, we don't have a node"""
@@ -357,45 +363,41 @@ class QueryStringGenerator(BaseMacroGenerator):
class MaterializationExtension(jinja2.ext.Extension):
tags = ['materialization']
tags = ["materialization"]
def parse(self, parser):
node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
materialization_name = \
parser.parse_assign_target(name_only=True).name
materialization_name = parser.parse_assign_target(name_only=True).name
adapter_name = 'default'
adapter_name = "default"
node.args = []
node.defaults = []
while parser.stream.skip_if('comma'):
while parser.stream.skip_if("comma"):
target = parser.parse_assign_target(name_only=True)
if target.name == 'default':
if target.name == "default":
pass
elif target.name == 'adapter':
parser.stream.expect('assign')
elif target.name == "adapter":
parser.stream.expect("assign")
value = parser.parse_expression()
adapter_name = value.value
else:
invalid_materialization_argument(
materialization_name, target.name
)
invalid_materialization_argument(materialization_name, target.name)
node.name = get_materialization_macro_name(
materialization_name, adapter_name
node.name = get_materialization_macro_name(materialization_name, adapter_name)
node.body = parser.parse_statements(
("name:endmaterialization",), drop_needle=True
)
node.body = parser.parse_statements(('name:endmaterialization',),
drop_needle=True)
return node
class DocumentationExtension(jinja2.ext.Extension):
tags = ['docs']
tags = ["docs"]
def parse(self, parser):
node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
@@ -404,27 +406,12 @@ class DocumentationExtension(jinja2.ext.Extension):
node.args = []
node.defaults = []
node.name = get_docs_macro_name(docs_name)
node.body = parser.parse_statements(('name:enddocs',),
drop_needle=True)
return node
class TestExtension(jinja2.ext.Extension):
tags = ['test']
def parse(self, parser):
node = jinja2.nodes.Macro(lineno=next(parser.stream).lineno)
test_name = parser.parse_assign_target(name_only=True).name
parser.parse_signature(node)
node.name = get_test_macro_name(test_name)
node.body = parser.parse_statements(('name:endtest',),
drop_needle=True)
node.body = parser.parse_statements(("name:enddocs",), drop_needle=True)
return node
def _is_dunder_name(name):
return name.startswith('__') and name.endswith('__')
return name.startswith("__") and name.endswith("__")
def create_undefined(node=None):
@@ -445,10 +432,11 @@ def create_undefined(node=None):
return self
def __getattr__(self, name):
if name == 'name' or _is_dunder_name(name):
if name == "name" or _is_dunder_name(name):
raise AttributeError(
"'{}' object has no attribute '{}'"
.format(type(self).__name__, name)
"'{}' object has no attribute '{}'".format(
type(self).__name__, name
)
)
self.name = name
@@ -459,24 +447,24 @@ def create_undefined(node=None):
return self
def __reduce__(self):
raise_compiler_error(f'{self.name} is undefined', node=node)
raise_compiler_error(f"{self.name} is undefined", node=node)
return Undefined
NATIVE_FILTERS: Dict[str, Callable[[Any], Any]] = {
'as_text': TextMarker,
'as_bool': BoolMarker,
'as_native': NativeMarker,
'as_number': NumberMarker,
"as_text": TextMarker,
"as_bool": BoolMarker,
"as_native": NativeMarker,
"as_number": NumberMarker,
}
TEXT_FILTERS: Dict[str, Callable[[Any], Any]] = {
'as_text': lambda x: x,
'as_bool': lambda x: x,
'as_native': lambda x: x,
'as_number': lambda x: x,
"as_text": lambda x: x,
"as_bool": lambda x: x,
"as_native": lambda x: x,
"as_number": lambda x: x,
}
@@ -486,15 +474,14 @@ def get_environment(
native: bool = False,
) -> jinja2.Environment:
args: Dict[str, List[Union[str, Type[jinja2.ext.Extension]]]] = {
'extensions': ['jinja2.ext.do']
"extensions": ["jinja2.ext.do"]
}
if capture_macros:
args['undefined'] = create_undefined(node)
args["undefined"] = create_undefined(node)
args['extensions'].append(MaterializationExtension)
args['extensions'].append(DocumentationExtension)
args['extensions'].append(TestExtension)
args["extensions"].append(MaterializationExtension)
args["extensions"].append(DocumentationExtension)
env_cls: Type[jinja2.Environment]
text_filter: Type
@@ -519,7 +506,7 @@ def catch_jinja(node=None) -> Iterator[None]:
e.translated = False
raise CompilationException(str(e), node) from e
except jinja2.exceptions.UndefinedError as e:
raise UndefinedMacroException(str(e), node) from e
raise CompilationException(str(e), node) from e
except CompilationException as exc:
exc.add_node(node)
raise
@@ -557,8 +544,8 @@ def _requote_result(raw_value: str, rendered: str) -> str:
elif single_quoted:
quote_char = "'"
else:
quote_char = ''
return f'{quote_char}{rendered}{quote_char}'
quote_char = ""
return f"{quote_char}{rendered}{quote_char}"
# performance note: Local benmcharking (so take it with a big grain of salt!)
@@ -566,7 +553,7 @@ def _requote_result(raw_value: str, rendered: str) -> str:
# checking two separate patterns, but the standard deviation is smaller with
# one pattern. The time difference between the two was ~2 std deviations, which
# is small enough that I've just chosen the more readable option.
_HAS_RENDER_CHARS_PAT = re.compile(r'({[{%#]|[#}%]})')
_HAS_RENDER_CHARS_PAT = re.compile(r"({[{%#]|[#}%]})")
def get_rendered(
@@ -583,9 +570,9 @@ def get_rendered(
# native=True case by passing the input string to ast.literal_eval, like
# the native renderer does.
if (
not native and
isinstance(string, str) and
_HAS_RENDER_CHARS_PAT.search(string) is None
not native
and isinstance(string, str)
and _HAS_RENDER_CHARS_PAT.search(string) is None
):
return string
template = get_template(
@@ -622,44 +609,40 @@ def extract_toplevel_blocks(
`collect_raw_data` is `True`) `BlockData` objects.
"""
return BlockIterator(data).lex_for_blocks(
allowed_blocks=allowed_blocks,
collect_raw_data=collect_raw_data
allowed_blocks=allowed_blocks, collect_raw_data=collect_raw_data
)
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
renderer, then insert that value into the given context as the special test
keyword arguments member.
"""
looks_like_func = r'^\s*(env_var|ref|var|source|doc)\s*\(.+\)\s*$'
looks_like_func = r"^\s*(env_var|ref|var|source|doc)\s*\(.+\)\s*$"
def _convert_function(
value: Any, keypath: Tuple[Union[str, int], ...]
) -> Any:
def _convert_function(value: Any, keypath: Tuple[Union[str, int], ...]) -> Any:
if isinstance(value, str):
if keypath == ('column_name',):
if keypath == ("column_name",):
# special case: Don't render column names as native, make them
# be strings
return value
if re.match(looks_like_func, value) is not None:
# curly braces to make rendering happy
value = f'{{{{ {value} }}}}'
value = f"{{{{ {value} }}}}"
value = get_rendered(
value, context, node, capture_macros=capture_macros,
native=True
value, context, node, capture_macros=capture_macros, native=True
)
return value
kwargs = deep_map(_convert_function, node.test_metadata.kwargs)
context[GENERIC_TEST_KWARGS_NAME] = kwargs
context[SCHEMA_TEST_KWARGS_NAME] = kwargs

View File

@@ -1,154 +0,0 @@
import jinja2
from dbt.clients.jinja import get_environment
from dbt.exceptions import raise_compiler_error
def statically_extract_macro_calls(string, ctx, db_wrapper=None):
# set 'capture_macros' to capture undefined
env = get_environment(None, capture_macros=True)
parsed = env.parse(string)
standard_calls = ['source', 'ref', 'config']
possible_macro_calls = []
for func_call in parsed.find_all(jinja2.nodes.Call):
func_name = None
if hasattr(func_call, 'node') and hasattr(func_call.node, 'name'):
func_name = func_call.node.name
else:
# func_call for dbt_utils.current_timestamp macro
# Call(
# node=Getattr(
# node=Name(
# name='dbt_utils',
# ctx='load'
# ),
# attr='current_timestamp',
# ctx='load
# ),
# args=[],
# kwargs=[],
# dyn_args=None,
# dyn_kwargs=None
# )
if (hasattr(func_call, 'node') and
hasattr(func_call.node, 'node') and
type(func_call.node.node).__name__ == 'Name' and
hasattr(func_call.node, 'attr')):
package_name = func_call.node.node.name
macro_name = func_call.node.attr
if package_name == 'adapter':
if macro_name == 'dispatch':
ad_macro_calls = statically_parse_adapter_dispatch(
func_call, ctx, db_wrapper)
possible_macro_calls.extend(ad_macro_calls)
else:
# This skips calls such as adapter.parse_index
continue
else:
func_name = f'{package_name}.{macro_name}'
else:
continue
if not func_name:
continue
if func_name in standard_calls:
continue
elif ctx.get(func_name):
continue
else:
if func_name not in possible_macro_calls:
possible_macro_calls.append(func_name)
return possible_macro_calls
# Call(
# node=Getattr(
# node=Name(
# name='adapter',
# ctx='load'
# ),
# attr='dispatch',
# ctx='load'
# ),
# args=[
# Const(value='test_pkg_and_dispatch')
# ],
# kwargs=[
# Keyword(
# key='packages',
# value=Call(node=Getattr(node=Name(name='local_utils', ctx='load'),
# attr='_get_utils_namespaces', ctx='load'), args=[], kwargs=[],
# dyn_args=None, dyn_kwargs=None)
# )
# ],
# dyn_args=None,
# dyn_kwargs=None
# )
def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
possible_macro_calls = []
# This captures an adapter.dispatch('<macro_name>') call.
func_name = None
# macro_name positional argument
if len(func_call.args) > 0:
func_name = func_call.args[0].value
if func_name:
possible_macro_calls.append(func_name)
# packages positional argument
macro_namespace = None
packages_arg = None
packages_arg_type = None
if len(func_call.args) > 1:
packages_arg = func_call.args[1]
# This can be a List or a Call
packages_arg_type = type(func_call.args[1]).__name__
# keyword arguments
if func_call.kwargs:
for kwarg in func_call.kwargs:
if kwarg.key == 'macro_name':
# This will remain to enable static resolution
if type(kwarg.value).__name__ == 'Const':
func_name = kwarg.value.value
possible_macro_calls.append(func_name)
else:
raise_compiler_error(f"The macro_name parameter ({kwarg.value.value}) "
"to adapter.dispatch was not a string")
elif kwarg.key == 'macro_namespace':
# This will remain to enable static resolution
kwarg_type = type(kwarg.value).__name__
if kwarg_type == 'Const':
macro_namespace = kwarg.value.value
else:
raise_compiler_error("The macro_namespace parameter to adapter.dispatch "
f"is a {kwarg_type}, not a string")
# positional arguments
if packages_arg:
if packages_arg_type == 'List':
# This will remain to enable static resolution
packages = []
for item in packages_arg.items:
packages.append(item.value)
elif packages_arg_type == 'Const':
# This will remain to enable static resolution
macro_namespace = packages_arg.value
if db_wrapper:
macro = db_wrapper.dispatch(
func_name,
macro_namespace=macro_namespace
).macro
func_name = f'{macro.package_name}.{macro.name}'
possible_macro_calls.append(func_name)
else: # this is only for test/unit/test_macro_calls.py
if macro_namespace:
packages = [macro_namespace]
else:
packages = []
for package_name in packages:
possible_macro_calls.append(f'{package_name}.{func_name}')
return possible_macro_calls

View File

@@ -1,79 +1,72 @@
import functools
from functools import wraps
import requests
from dbt.utils import memoized, _connection_exception_retry as connection_exception_retry
from dbt.exceptions import RegistryException
from dbt.utils import memoized
from dbt.logger import GLOBAL_LOGGER as logger
from dbt import deprecations
import os
import time
if os.getenv('DBT_PACKAGE_HUB_URL'):
DEFAULT_REGISTRY_BASE_URL = os.getenv('DBT_PACKAGE_HUB_URL')
if os.getenv("DBT_PACKAGE_HUB_URL"):
DEFAULT_REGISTRY_BASE_URL = os.getenv("DBT_PACKAGE_HUB_URL")
else:
DEFAULT_REGISTRY_BASE_URL = 'https://hub.getdbt.com/'
DEFAULT_REGISTRY_BASE_URL = "https://hub.getdbt.com/"
def _get_url(url, registry_base_url=None):
if registry_base_url is None:
registry_base_url = DEFAULT_REGISTRY_BASE_URL
return '{}{}'.format(registry_base_url, url)
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 as exc:
if attempt < max_attempts:
time.sleep(1)
continue
raise RegistryException("Unable to connect to registry hub") from exc
return wrapper
@_wrap_exceptions
def _get(path, registry_base_url=None):
url = _get_url(path, registry_base_url)
logger.debug('Making package registry request: GET {}'.format(url))
resp = requests.get(url, timeout=30)
logger.debug('Response from registry: GET {} {}'.format(url,
resp.status_code))
logger.debug("Making package registry request: GET {}".format(url))
resp = requests.get(url)
logger.debug("Response from registry: GET {} {}".format(url, resp.status_code))
resp.raise_for_status()
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):
response = package(name)
return list(response['versions'])
return list(response["versions"])

View File

@@ -1,5 +1,4 @@
import errno
import functools
import fnmatch
import json
import os
@@ -11,15 +10,14 @@ import sys
import tarfile
import requests
import stat
from typing import (
Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
)
from typing import Type, NoReturn, List, Optional, Dict, Any, Tuple, Callable, Union
import dbt.exceptions
from dbt.logger import GLOBAL_LOGGER as logger
from dbt.utils import _connection_exception_retry as connection_exception_retry
import dbt.utils
if sys.platform == 'win32':
from dbt.logger import GLOBAL_LOGGER as logger
if sys.platform == "win32":
from ctypes import WinDLL, c_bool
else:
WinDLL = None
@@ -30,7 +28,7 @@ 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`
@@ -51,38 +49,29 @@ def find_matching(
reobj = re.compile(regex, re.IGNORECASE)
for relative_path_to_search in relative_paths_to_search:
absolute_path_to_search = os.path.join(
root_path, relative_path_to_search)
absolute_path_to_search = os.path.join(root_path, relative_path_to_search)
walk_results = os.walk(absolute_path_to_search)
for current_path, subdirectories, local_files in walk_results:
for local_file in local_files:
absolute_path = os.path.join(current_path, local_file)
relative_path = os.path.relpath(
absolute_path, absolute_path_to_search
)
modification_time = 0.0
try:
modification_time = os.path.getmtime(absolute_path)
except OSError:
logger.exception(
f"Error retrieving modification time for file {absolute_path}"
)
relative_path = os.path.relpath(absolute_path, absolute_path_to_search)
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,
})
matching.append(
{
"searched_path": relative_path_to_search,
"absolute_path": absolute_path,
"relative_path": relative_path,
}
)
return matching
def load_file_contents(path: str, strip: bool = True) -> str:
path = convert_path(path)
with open(path, 'rb') as handle:
to_return = handle.read().decode('utf-8')
with open(path, "rb") as handle:
to_return = handle.read().decode("utf-8")
if strip:
to_return = to_return.strip()
@@ -109,14 +98,14 @@ def make_directory(path: str) -> None:
raise e
def make_file(path: str, contents: str = '', overwrite: bool = False) -> bool:
def make_file(path: str, contents: str = "", overwrite: bool = False) -> bool:
"""
Make a file at `path` assuming that the directory it resides in already
exists. The file is saved with contents `contents`
"""
if overwrite or not os.path.exists(path):
path = convert_path(path)
with open(path, 'w') as fh:
with open(path, "w") as fh:
fh.write(contents)
return True
@@ -128,7 +117,7 @@ def make_symlink(source: str, link_path: str) -> None:
Create a symlink at `link_path` referring to `source`.
"""
if not supports_symlinks():
dbt.exceptions.system_error('create a symbolic link')
dbt.exceptions.system_error("create a symbolic link")
os.symlink(source, link_path)
@@ -137,11 +126,11 @@ def supports_symlinks() -> bool:
return getattr(os, "symlink", None) is not None
def write_file(path: str, contents: str = '') -> bool:
def write_file(path: str, contents: str = "") -> bool:
path = convert_path(path)
try:
make_directory(os.path.dirname(path))
with open(path, 'w', encoding='utf-8') as f:
with open(path, "w", encoding="utf-8") as f:
f.write(str(contents))
except Exception as exc:
# note that you can't just catch FileNotFound, because sometimes
@@ -150,20 +139,20 @@ def write_file(path: str, contents: str = '') -> bool:
# sometimes windows fails to write paths that are less than the length
# limit. So on windows, suppress all errors that happen from writing
# to disk.
if os.name == 'nt':
if os.name == "nt":
# sometimes we get a winerror of 3 which means the path was
# definitely too long, but other times we don't and it means the
# path was just probably too long. This is probably based on the
# windows/python version.
if getattr(exc, 'winerror', 0) == 3:
reason = 'Path was too long'
if getattr(exc, "winerror", 0) == 3:
reason = "Path was too long"
else:
reason = 'Path was possibly too long'
reason = "Path was possibly too long"
# all our hard work and the path was still too long. Log and
# continue.
logger.debug(
f'Could not write to path {path}({len(path)} characters): '
f'{reason}\nexception: {exc}'
f"Could not write to path {path}({len(path)} characters): "
f"{reason}\nexception: {exc}"
)
else:
raise
@@ -197,10 +186,7 @@ def resolve_path_from_base(path_to_resolve: str, base_path: str) -> str:
If path_to_resolve is an absolute path or a user path (~), just
resolve it to an absolute path and return.
"""
return os.path.abspath(
os.path.join(
base_path,
os.path.expanduser(path_to_resolve)))
return os.path.abspath(os.path.join(base_path, os.path.expanduser(path_to_resolve)))
def rmdir(path: str) -> None:
@@ -210,7 +196,7 @@ def rmdir(path: str) -> None:
cloned via git) can cause rmtree to throw a PermissionError exception
"""
path = convert_path(path)
if sys.platform == 'win32':
if sys.platform == "win32":
onerror = _windows_rmdir_readonly
else:
onerror = None
@@ -229,7 +215,7 @@ def _win_prepare_path(path: str) -> str:
# letter back in.
# Unless it starts with '\\'. In that case, the path is a UNC mount point
# and splitdrive will be fine.
if not path.startswith('\\\\') and path.startswith('\\'):
if not path.startswith("\\\\") and path.startswith("\\"):
curdrive = os.path.splitdrive(os.getcwd())[0]
path = curdrive + path
@@ -244,7 +230,7 @@ def _win_prepare_path(path: str) -> str:
def _supports_long_paths() -> bool:
if sys.platform != 'win32':
if sys.platform != "win32":
return True
# Eryk Sun says to use `WinDLL('ntdll')` instead of `windll.ntdll` because
# of pointer caching in a comment here:
@@ -252,11 +238,11 @@ def _supports_long_paths() -> bool:
# I don't know exaclty what he means, but I am inclined to believe him as
# he's pretty active on Python windows bugs!
try:
dll = WinDLL('ntdll')
dll = WinDLL("ntdll")
except OSError: # I don't think this happens? you need ntdll to run python
return False
# not all windows versions have it at all
if not hasattr(dll, 'RtlAreLongPathsEnabled'):
if not hasattr(dll, "RtlAreLongPathsEnabled"):
return False
# tell windows we want to get back a single unsigned byte (a bool).
dll.RtlAreLongPathsEnabled.restype = c_bool
@@ -276,7 +262,7 @@ def convert_path(path: str) -> str:
if _supports_long_paths():
return path
prefix = '\\\\?\\'
prefix = "\\\\?\\"
# Nothing to do
if path.startswith(prefix):
return path
@@ -307,39 +293,35 @@ def path_is_symlink(path: str) -> bool:
def open_dir_cmd() -> str:
# https://docs.python.org/2/library/sys.html#sys.platform
if sys.platform == 'win32':
return 'start'
if sys.platform == "win32":
return "start"
elif sys.platform == 'darwin':
return 'open'
elif sys.platform == "darwin":
return "open"
else:
return 'xdg-open'
return "xdg-open"
def _handle_posix_cwd_error(
exc: OSError, cwd: str, cmd: List[str]
) -> NoReturn:
def _handle_posix_cwd_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
if exc.errno == errno.ENOENT:
message = 'Directory does not exist'
message = "Directory does not exist"
elif exc.errno == errno.EACCES:
message = 'Current user cannot access directory, check permissions'
message = "Current user cannot access directory, check permissions"
elif exc.errno == errno.ENOTDIR:
message = 'Not a directory'
message = "Not a directory"
else:
message = 'Unknown OSError: {} - cwd'.format(str(exc))
message = "Unknown OSError: {} - cwd".format(str(exc))
raise dbt.exceptions.WorkingDirectoryError(cwd, cmd, message)
def _handle_posix_cmd_error(
exc: OSError, cwd: str, cmd: List[str]
) -> NoReturn:
def _handle_posix_cmd_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
if exc.errno == errno.ENOENT:
message = "Could not find command, ensure it is in the user's PATH"
elif exc.errno == errno.EACCES:
message = 'User does not have permissions for this command'
message = "User does not have permissions for this command"
else:
message = 'Unknown OSError: {} - cmd'.format(str(exc))
message = "Unknown OSError: {} - cmd".format(str(exc))
raise dbt.exceptions.ExecutableError(cwd, cmd, message)
@@ -364,7 +346,7 @@ def _handle_posix_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
- exc.errno == EACCES
- exc.filename == None(?)
"""
if getattr(exc, 'filename', None) == cwd:
if getattr(exc, "filename", None) == cwd:
_handle_posix_cwd_error(exc, cwd, cmd)
else:
_handle_posix_cmd_error(exc, cwd, cmd)
@@ -373,46 +355,48 @@ def _handle_posix_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
def _handle_windows_error(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
cls: Type[dbt.exceptions.Exception] = dbt.exceptions.CommandError
if exc.errno == errno.ENOENT:
message = ("Could not find command, ensure it is in the user's PATH "
"and that the user has permissions to run it")
message = (
"Could not find command, ensure it is in the user's PATH "
"and that the user has permissions to run it"
)
cls = dbt.exceptions.ExecutableError
elif exc.errno == errno.ENOEXEC:
message = ('Command was not executable, ensure it is valid')
message = "Command was not executable, ensure it is valid"
cls = dbt.exceptions.ExecutableError
elif exc.errno == errno.ENOTDIR:
message = ('Unable to cd: path does not exist, user does not have'
' permissions, or not a directory')
message = (
"Unable to cd: path does not exist, user does not have"
" permissions, or not a directory"
)
cls = dbt.exceptions.WorkingDirectoryError
else:
message = 'Unknown error: {} (errno={}: "{}")'.format(
str(exc), exc.errno, errno.errorcode.get(exc.errno, '<Unknown!>')
str(exc), exc.errno, errno.errorcode.get(exc.errno, "<Unknown!>")
)
raise cls(cwd, cmd, message)
def _interpret_oserror(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
"""Interpret an OSError exc and raise the appropriate dbt exception.
"""
"""Interpret an OSError exc and raise the appropriate dbt exception."""
if len(cmd) == 0:
raise dbt.exceptions.CommandError(cwd, cmd)
# all of these functions raise unconditionally
if os.name == 'nt':
if os.name == "nt":
_handle_windows_error(exc, cwd, cmd)
else:
_handle_posix_error(exc, cwd, cmd)
# this should not be reachable, raise _something_ at least!
raise dbt.exceptions.InternalException(
'Unhandled exception in _interpret_oserror: {}'.format(exc)
"Unhandled exception in _interpret_oserror: {}".format(exc)
)
def run_cmd(
cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None
) -> Tuple[bytes, bytes]:
logger.debug('Executing "{}"'.format(' '.join(cmd)))
logger.debug('Executing "{}"'.format(" ".join(cmd)))
if len(cmd) == 0:
raise dbt.exceptions.CommandError(cwd, cmd)
@@ -424,15 +408,9 @@ def run_cmd(
full_env.update(env)
try:
exe_pth = shutil.which(cmd[0])
if exe_pth:
cmd = [os.path.abspath(exe_pth)] + list(cmd[1:])
proc = subprocess.Popen(
cmd,
cwd=cwd,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
env=full_env)
cmd, cwd=cwd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=full_env
)
out, err = proc.communicate()
except OSError as exc:
@@ -442,27 +420,19 @@ def run_cmd(
logger.debug('STDERR: "{!s}"'.format(err))
if proc.returncode != 0:
logger.debug('command return code={}'.format(proc.returncode))
raise dbt.exceptions.CommandResultError(cwd, cmd, proc.returncode,
out, err)
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:
path = convert_path(path)
connection_timeout = timeout or float(os.getenv('DBT_HTTP_TIMEOUT', 10))
connection_timeout = timeout or float(os.getenv("DBT_HTTP_TIMEOUT", 10))
response = requests.get(url, timeout=connection_timeout)
with open(path, 'wb') as handle:
with open(path, "wb") as handle:
for block in response.iter_content(1024 * 64):
handle.write(block)
@@ -486,7 +456,7 @@ def untar_package(
) -> None:
tar_path = convert_path(tar_path)
tar_dir_name = None
with tarfile.open(tar_path, 'r') 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:
@@ -502,7 +472,7 @@ def chmod_and_retry(func, path, exc_info):
We want to retry most operations here, but listdir is one that we know will
be useless.
"""
if func is os.listdir or os.name != 'nt':
if func is os.listdir or os.name != "nt":
raise
os.chmod(path, stat.S_IREAD | stat.S_IWRITE)
# on error,this will raise.
@@ -523,7 +493,7 @@ def move(src, dst):
"""
src = convert_path(src)
dst = convert_path(dst)
if os.name != 'nt':
if os.name != "nt":
return shutil.move(src, dst)
if os.path.isdir(dst):
@@ -531,7 +501,7 @@ def move(src, dst):
os.rename(src, dst)
return
dst = os.path.join(dst, os.path.basename(src.rstrip('/\\')))
dst = os.path.join(dst, os.path.basename(src.rstrip("/\\")))
if os.path.exists(dst):
raise EnvironmentError("Path '{}' already exists".format(dst))
@@ -540,11 +510,10 @@ def move(src, dst):
except OSError:
# probably different drives
if os.path.isdir(src):
if _absnorm(dst + '\\').startswith(_absnorm(src + '\\')):
if _absnorm(dst + "\\").startswith(_absnorm(src + "\\")):
# dst is inside src
raise EnvironmentError(
"Cannot move a directory '{}' into itself '{}'"
.format(src, dst)
"Cannot move a directory '{}' into itself '{}'".format(src, dst)
)
shutil.copytree(src, dst, symlinks=True)
rmtree(src)

View File

@@ -1,18 +1,13 @@
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:
from yaml import (
CLoader as Loader,
CSafeLoader as SafeLoader,
CDumper as Dumper
)
from yaml import CLoader as Loader, CSafeLoader as SafeLoader, CDumper as Dumper
except ImportError:
from yaml import ( # type: ignore # noqa: F401
Loader, SafeLoader, Dumper
)
from yaml import Loader, SafeLoader, Dumper # type: ignore # noqa: F401
YAML_ERROR_MESSAGE = """
@@ -32,14 +27,14 @@ def line_no(i, line, width=3):
def prefix_with_line_numbers(string, no_start, no_end):
line_list = string.split('\n')
line_list = string.split("\n")
numbers = range(no_start, no_end)
relevant_lines = line_list[no_start:no_end]
return "\n".join([
line_no(i + 1, line) for (i, line) in zip(numbers, relevant_lines)
])
return "\n".join(
[line_no(i + 1, line) for (i, line) in zip(numbers, relevant_lines)]
)
def contextualized_yaml_error(raw_contents, error):
@@ -50,12 +45,12 @@ def contextualized_yaml_error(raw_contents, error):
nice_error = prefix_with_line_numbers(raw_contents, min_line, max_line)
return YAML_ERROR_MESSAGE.format(line_number=mark.line + 1,
nice_error=nice_error,
raw_error=error)
return YAML_ERROR_MESSAGE.format(
line_number=mark.line + 1, nice_error=nice_error, raw_error=error
)
def safe_load(contents) -> Optional[Dict[str, Any]]:
def safe_load(contents):
return yaml.load(contents, Loader=SafeLoader)
@@ -63,7 +58,7 @@ def load_yaml_text(contents):
try:
return safe_load(contents)
except (yaml.scanner.ScannerError, yaml.YAMLError) as e:
if hasattr(e, 'problem_mark'):
if hasattr(e, "problem_mark"):
error = contextualized_yaml_error(contents, e)
else:
error = str(e)

View File

@@ -10,10 +10,11 @@ from dbt.adapters.factory import get_adapter
from dbt.clients import jinja
from dbt.clients.system import make_directory
from dbt.context.providers import generate_runtime_model
from dbt.contracts.graph.manifest import Manifest, UniqueID
from dbt.contracts.graph.manifest import Manifest
from dbt.contracts.graph.compiled import (
CompiledDataTestNode,
CompiledSchemaTestNode,
COMPILED_TYPES,
CompiledGenericTestNode,
GraphMemberNode,
InjectedCTE,
ManifestNode,
@@ -31,28 +32,28 @@ from dbt.node_types import NodeType
from dbt.utils import pluralize
import dbt.tracking
graph_file_name = 'graph.gpickle'
graph_file_name = "graph.gpickle"
def _compiled_type_for(model: ParsedNode):
if type(model) not in COMPILED_TYPES:
raise InternalException(
f'Asked to compile {type(model)} node, but it has no compiled form'
f"Asked to compile {type(model)} node, but it has no compiled form"
)
return COMPILED_TYPES[type(model)]
def print_compile_stats(stats):
names = {
NodeType.Model: 'model',
NodeType.Test: 'test',
NodeType.Snapshot: 'snapshot',
NodeType.Analysis: 'analysis',
NodeType.Macro: 'macro',
NodeType.Operation: 'operation',
NodeType.Seed: 'seed file',
NodeType.Source: 'source',
NodeType.Exposure: 'exposure',
NodeType.Model: "model",
NodeType.Test: "test",
NodeType.Snapshot: "snapshot",
NodeType.Analysis: "analysis",
NodeType.Macro: "macro",
NodeType.Operation: "operation",
NodeType.Seed: "seed file",
NodeType.Source: "source",
NodeType.Exposure: "exposure",
}
results = {k: 0 for k in names.keys()}
@@ -63,10 +64,9 @@ def print_compile_stats(stats):
resource_counts = {k.pluralize(): v for k, v in results.items()}
dbt.tracking.track_resource_counts(resource_counts)
stat_line = ", ".join([
pluralize(ct, names.get(t)) for t, ct in results.items()
if t in names
])
stat_line = ", ".join(
[pluralize(ct, names.get(t)) for t, ct in results.items() if t in names]
)
logger.info("Found {}".format(stat_line))
@@ -107,19 +107,6 @@ def _extend_prepended_ctes(prepended_ctes, new_prepended_ctes):
_add_prepended_cte(prepended_ctes, new_cte)
def _get_tests_for_node(manifest: Manifest, unique_id: UniqueID) -> List[UniqueID]:
""" Get a list of tests that depend on the node with the
provided unique id """
tests = []
if unique_id in manifest.child_map:
for child_unique_id in manifest.child_map[unique_id]:
if child_unique_id.startswith('test.'):
tests.append(child_unique_id)
return tests
class Linker:
def __init__(self, data=None):
if data is None:
@@ -155,7 +142,7 @@ class Linker:
include all nodes in their corresponding graph entries.
"""
out_graph = self.graph.copy()
for node_id in self.graph:
for node_id in self.graph.nodes():
data = manifest.expect(node_id).to_dict(omit_none=True)
out_graph.add_node(node_id, **data)
nx.write_gpickle(out_graph, outfile)
@@ -167,7 +154,7 @@ class Compiler:
def initialize(self):
make_directory(self.config.target_path)
make_directory(self.config.packages_install_path)
make_directory(self.config.modules_path)
# creates a ModelContext which is converted to
# a dict for jinja rendering of SQL
@@ -178,11 +165,9 @@ class Compiler:
extra_context: Dict[str, Any],
) -> Dict[str, Any]:
context = generate_runtime_model(
node, self.config, manifest
)
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)
@@ -195,7 +180,7 @@ class Compiler:
def _get_relation_name(self, node: ParsedNode):
relation_name = None
if node.is_relational and not node.is_ephemeral_model:
if node.resource_type in NodeType.refable() and not node.is_ephemeral_model:
adapter = get_adapter(self.config)
relation_cls = adapter.Relation
relation_name = str(relation_cls.create_from(self.config, node))
@@ -238,47 +223,45 @@ class Compiler:
with_stmt = None
for token in parsed.tokens:
if token.is_keyword and token.normalized == 'WITH':
if token.is_keyword and token.normalized == "WITH":
with_stmt = token
break
if with_stmt is None:
# no with stmt, add one, and inject CTEs right at the beginning
first_token = parsed.token_first()
with_stmt = sqlparse.sql.Token(sqlparse.tokens.Keyword, 'with')
with_stmt = sqlparse.sql.Token(sqlparse.tokens.Keyword, "with")
parsed.insert_before(first_token, with_stmt)
else:
# stmt exists, add a comma (which will come after injected CTEs)
trailing_comma = sqlparse.sql.Token(
sqlparse.tokens.Punctuation, ','
)
trailing_comma = sqlparse.sql.Token(sqlparse.tokens.Punctuation, ",")
parsed.insert_after(with_stmt, trailing_comma)
token = sqlparse.sql.Token(
sqlparse.tokens.Keyword,
", ".join(c.sql for c in ctes)
sqlparse.tokens.Keyword, ", ".join(c.sql for c in ctes)
)
parsed.insert_after(with_stmt, token)
return str(parsed)
def _get_dbt_test_name(self) -> str:
return "dbt__cte__internal_test"
# This method is called by the 'compile_node' method. Starting
# from the node that it is passed in, it will recursively call
# itself using the 'extra_ctes'. The 'ephemeral' models do
# not produce SQL that is executed directly, instead they
# are rolled up into the models that refer to them by
# inserting CTEs into the SQL.
def _recursively_prepend_ctes(
self,
model: NonSourceCompiledNode,
manifest: Manifest,
extra_context: Optional[Dict[str, Any]],
) -> Tuple[NonSourceCompiledNode, List[InjectedCTE]]:
"""This method is called by the 'compile_node' method. Starting
from the node that it is passed in, it will recursively call
itself using the 'extra_ctes'. The 'ephemeral' models do
not produce SQL that is executed directly, instead they
are rolled up into the models that refer to them by
inserting CTEs into the SQL.
"""
if model.compiled_sql is None:
raise RuntimeException(
'Cannot inject ctes into an unparsed node', model
)
raise RuntimeException("Cannot inject ctes into an unparsed node", model)
if model.extra_ctes_injected:
return (model, model.extra_ctes)
@@ -292,59 +275,62 @@ class Compiler:
# gathered and then "injected" into the model.
prepended_ctes: List[InjectedCTE] = []
dbt_test_name = self._get_dbt_test_name()
# extra_ctes are added to the model by
# RuntimeRefResolver.create_relation, which adds an
# extra_cte for every model relation which is an
# ephemeral model.
for cte in model.extra_ctes:
if cte.id not in manifest.nodes:
raise InternalException(
f'During compilation, found a cte reference that '
f'could not be resolved: {cte.id}'
)
cte_model = manifest.nodes[cte.id]
if not cte_model.is_ephemeral_model:
raise InternalException(f'{cte.id} is not ephemeral')
# This model has already been compiled, so it's been
# through here before
if getattr(cte_model, 'compiled', False):
assert isinstance(cte_model, tuple(COMPILED_TYPES.values()))
cte_model = cast(NonSourceCompiledNode, cte_model)
new_prepended_ctes = cte_model.extra_ctes
# if the cte_model isn't compiled, i.e. first time here
if cte.id == dbt_test_name:
sql = cte.sql
else:
# This is an ephemeral parsed model that we can compile.
# Compile and update the node
cte_model = self._compile_node(
cte_model, manifest, extra_context)
# recursively call this method
cte_model, new_prepended_ctes = \
self._recursively_prepend_ctes(
if cte.id not in manifest.nodes:
raise InternalException(
f"During compilation, found a cte reference that "
f"could not be resolved: {cte.id}"
)
cte_model = manifest.nodes[cte.id]
if not cte_model.is_ephemeral_model:
raise InternalException(f"{cte.id} is not ephemeral")
# This model has already been compiled, so it's been
# through here before
if getattr(cte_model, "compiled", False):
assert isinstance(cte_model, tuple(COMPILED_TYPES.values()))
cte_model = cast(NonSourceCompiledNode, cte_model)
new_prepended_ctes = cte_model.extra_ctes
# if the cte_model isn't compiled, i.e. first time here
else:
# This is an ephemeral parsed model that we can compile.
# Compile and update the node
cte_model = self._compile_node(cte_model, manifest, extra_context)
# recursively call this method
cte_model, new_prepended_ctes = self._recursively_prepend_ctes(
cte_model, manifest, extra_context
)
# Save compiled SQL file and sync manifest
self._write_node(cte_model)
manifest.sync_update_node(cte_model)
# Save compiled SQL file and sync manifest
self._write_node(cte_model)
manifest.sync_update_node(cte_model)
_extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
_extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
new_cte_name = self.add_ephemeral_prefix(cte_model.name)
rendered_sql = (
cte_model._pre_injected_sql or cte_model.compiled_sql
)
sql = f' {new_cte_name} as (\n{rendered_sql}\n)'
new_cte_name = self.add_ephemeral_prefix(cte_model.name)
sql = f" {new_cte_name} as (\n{cte_model.compiled_sql}\n)"
_add_prepended_cte(prepended_ctes, InjectedCTE(id=cte.id, sql=sql))
injected_sql = self._inject_ctes_into_sql(
model.compiled_sql,
prepended_ctes,
)
model._pre_injected_sql = model.compiled_sql
model.compiled_sql = injected_sql
# We don't save injected_sql into compiled sql for ephemeral models
# because it will cause problems with processing of subsequent models.
# Ephemeral models do not produce executable SQL of their own.
if not model.is_ephemeral_model:
injected_sql = self._inject_ctes_into_sql(
model.compiled_sql,
prepended_ctes,
)
model.compiled_sql = injected_sql
model.extra_ctes_injected = True
model.extra_ctes = prepended_ctes
model.validate(model.to_dict(omit_none=True))
@@ -353,6 +339,33 @@ class Compiler:
return model, prepended_ctes
def _add_ctes(
self,
compiled_node: NonSourceCompiledNode,
manifest: Manifest,
extra_context: Dict[str, Any],
) -> NonSourceCompiledNode:
"""Wrap the data test SQL in a CTE."""
# for data tests, we need to insert a special CTE at the end of the
# list containing the test query, and then have the "real" query be a
# select count(*) from that model.
# the benefit of doing it this way is that _add_ctes() can be
# rewritten for different adapters to handle databases that don't
# support CTEs, or at least don't have full support.
if isinstance(compiled_node, CompiledDataTestNode):
# the last prepend (so last in order) should be the data test body.
# then we can add our select count(*) from _that_ cte as the "real"
# compiled_sql, and do the regular prepend logic from CTEs.
name = self._get_dbt_test_name()
cte = InjectedCTE(
id=name, sql=f" {name} as (\n{compiled_node.compiled_sql}\n)"
)
compiled_node.extra_ctes.append(cte)
compiled_node.compiled_sql = f"\nselect count(*) from {name}"
return compiled_node
# creates a compiled_node from the ManifestNode passed in,
# creates a "context" dictionary for jinja rendering,
# and then renders the "compiled_sql" using the node, the
@@ -369,17 +382,17 @@ class Compiler:
logger.debug("Compiling {}".format(node.unique_id))
data = node.to_dict(omit_none=True)
data.update({
'compiled': False,
'compiled_sql': None,
'extra_ctes_injected': False,
'extra_ctes': [],
})
data.update(
{
"compiled": False,
"compiled_sql": None,
"extra_ctes_injected": False,
"extra_ctes": [],
}
)
compiled_node = _compiled_type_for(node).from_dict(data)
context = self._create_node_context(
compiled_node, manifest, extra_context
)
context = self._create_node_context(compiled_node, manifest, extra_context)
compiled_node.compiled_sql = jinja.get_rendered(
node.raw_sql,
@@ -391,6 +404,10 @@ class Compiler:
compiled_node.compiled = True
# add ctes for specific test nodes, and also for
# possible future use in adapters
compiled_node = self._add_ctes(compiled_node, manifest, extra_context)
return compiled_node
def write_graph_file(self, linker: Linker, manifest: Manifest):
@@ -399,21 +416,17 @@ class Compiler:
if flags.WRITE_JSON:
linker.write_graph(graph_path, manifest)
def link_node(
self, linker: Linker, node: GraphMemberNode, manifest: Manifest
):
def link_node(self, linker: Linker, node: GraphMemberNode, manifest: Manifest):
linker.add_node(node.unique_id)
for dependency in node.depends_on_nodes:
if dependency in manifest.nodes:
linker.dependency(
node.unique_id,
(manifest.nodes[dependency].unique_id)
node.unique_id, (manifest.nodes[dependency].unique_id)
)
elif dependency in manifest.sources:
linker.dependency(
node.unique_id,
(manifest.sources[dependency].unique_id)
node.unique_id, (manifest.sources[dependency].unique_id)
)
else:
dependency_not_found(node, dependency)
@@ -425,82 +438,13 @@ class Compiler:
self.link_node(linker, node, manifest)
for exposure in manifest.exposures.values():
self.link_node(linker, exposure, manifest)
# linker.add_node(exposure.unique_id)
cycle = linker.find_cycles()
if cycle:
raise RuntimeError("Found a cycle: {}".format(cycle))
manifest.build_parent_and_child_maps()
self.resolve_graph(linker, manifest)
def resolve_graph(self, linker: Linker, manifest: Manifest) -> None:
""" This method adds additional edges to the DAG. For a given non-test
executable node, add an edge from an upstream test to the given node if
the set of nodes the test depends on is a proper/strict subset of the
upstream nodes for the given node. """
# Given a graph:
# model1 --> model2 --> model3
# | |
# | \/
# \/ test 2
# test1
#
# Produce the following graph:
# model1 --> model2 --> model3
# | | /\ /\
# | \/ | |
# \/ test2 ------- |
# test1 -------------------
for node_id in linker.graph:
# If node is executable (in manifest.nodes) and does _not_
# represent a test, continue.
if (
node_id in manifest.nodes and
manifest.nodes[node_id].resource_type != NodeType.Test
):
# Get *everything* upstream of the node
all_upstream_nodes = nx.traversal.bfs_tree(
linker.graph, node_id, reverse=True
)
# Get the set of upstream nodes not including the current node.
upstream_nodes = set([
n for n in all_upstream_nodes if n != node_id
])
# Get all tests that depend on any upstream nodes.
upstream_tests = []
for upstream_node in upstream_nodes:
upstream_tests += _get_tests_for_node(
manifest,
upstream_node
)
for upstream_test in upstream_tests:
# Get the set of all nodes that the test depends on
# including the upstream_node itself. This is necessary
# because tests can depend on multiple nodes (ex:
# relationship tests). Test nodes do not distinguish
# between what node the test is "testing" and what
# node(s) it depends on.
test_depends_on = set(
manifest.nodes[upstream_test].depends_on_nodes
)
# If the set of nodes that an upstream test depends on
# is a proper (or strict) subset of all upstream nodes of
# the current node, add an edge from the upstream test
# to the current node. Must be a proper/strict subset to
# avoid adding a circular dependency to the graph.
if (test_depends_on < upstream_nodes):
linker.graph.add_edge(
upstream_test,
node_id
)
def compile(self, manifest: Manifest, write=True) -> Graph:
self.initialize()
linker = Linker()
@@ -517,19 +461,21 @@ class Compiler:
# writes the "compiled_sql" into the target/compiled directory
def _write_node(self, node: NonSourceCompiledNode) -> ManifestNode:
if (not node.extra_ctes_injected or
node.resource_type == NodeType.Snapshot):
if not node.extra_ctes_injected or node.resource_type == NodeType.Snapshot:
return node
logger.debug(f'Writing injected SQL for node "{node.unique_id}"')
if node.compiled_sql:
node.compiled_path = node.write_node(
self.config.target_path,
'compiled',
node.compiled_sql
node.build_path = node.write_node(
self.config.target_path, "compiled", node.compiled_sql
)
return node
# This is the main entry point into this code. It's called by
# CompileRunner.compile, GenericRPCRunner.compile, and
# RunTask.get_hook_sql. It calls '_compile_node' to convert
# the node into a compiled node, and then calls the
# recursive method to "prepend" the ctes.
def compile_node(
self,
node: ManifestNode,
@@ -537,17 +483,9 @@ class Compiler:
extra_context: Optional[Dict[str, Any]] = None,
write: bool = True,
) -> NonSourceCompiledNode:
"""This is the main entry point into this code. It's called by
CompileRunner.compile, GenericRPCRunner.compile, and
RunTask.get_hook_sql. It calls '_compile_node' to convert
the node into a compiled node, and then calls the
recursive method to "prepend" the ctes.
"""
node = self._compile_node(node, manifest, extra_context)
node, _ = self._recursively_prepend_ctes(
node, manifest, extra_context
)
node, _ = self._recursively_prepend_ctes(node, manifest, extra_context)
if write:
self._write_node(node)
return node

View File

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

View File

@@ -4,7 +4,6 @@ import os
from dbt.dataclass_schema import ValidationError
from dbt import flags
from dbt.clients.system import load_file_contents
from dbt.clients.yaml_helper import load_yaml_text
from dbt.contracts.connection import Credentials, HasCredentials
@@ -21,8 +20,8 @@ from dbt.utils import coerce_dict_str
from .renderer import ProfileRenderer
DEFAULT_THREADS = 1
DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser('~'), '.dbt')
DEFAULT_PROFILES_DIR = os.path.join(os.path.expanduser("~"), ".dbt")
PROFILES_DIR = os.path.expanduser(os.getenv("DBT_PROFILES_DIR", DEFAULT_PROFILES_DIR))
INVALID_PROFILE_MESSAGE = """
dbt encountered an error while trying to read your profiles.yml file.
@@ -42,11 +41,13 @@ 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]:
path = os.path.join(profiles_dir, 'profiles.yml')
path = os.path.join(profiles_dir, "profiles.yml")
contents = None
if os.path.isfile(path):
@@ -54,12 +55,8 @@ def read_profile(profiles_dir: str) -> Dict[str, Any]:
contents = load_file_contents(path, strip=False)
yaml_content = load_yaml_text(contents)
if not yaml_content:
msg = f'The profiles.yml file at {path} is empty'
raise DbtProfileError(
INVALID_PROFILE_MESSAGE.format(
error_string=msg
)
)
msg = f"The profiles.yml file at {path} is empty"
raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
return yaml_content
except ValidationException as e:
msg = INVALID_PROFILE_MESSAGE.format(error_string=e)
@@ -72,10 +69,10 @@ def read_user_config(directory: str) -> UserConfig:
try:
profile = read_profile(directory)
if profile:
user_config = coerce_dict_str(profile.get('config', {}))
if user_config is not None:
UserConfig.validate(user_config)
return UserConfig.from_dict(user_config)
user_cfg = coerce_dict_str(profile.get("config", {}))
if user_cfg is not None:
UserConfig.validate(user_cfg)
return UserConfig.from_dict(user_cfg)
except (RuntimeException, ValidationError):
pass
return UserConfig()
@@ -83,35 +80,15 @@ def read_user_config(directory: str) -> UserConfig:
# The Profile class is included in RuntimeConfig, so any attribute
# additions must also be set where the RuntimeConfig class is created
# `init=False` is a workaround for https://bugs.python.org/issue45081
@dataclass(init=False)
@dataclass
class Profile(HasCredentials):
profile_name: str
target_name: str
user_config: UserConfig
config: UserConfig
threads: int
credentials: Credentials
def __init__(
self,
profile_name: str,
target_name: str,
user_config: UserConfig,
threads: int,
credentials: Credentials
):
"""Explicitly defining `__init__` to work around bug in Python 3.9.7
https://bugs.python.org/issue45081
"""
self.profile_name = profile_name
self.target_name = target_name
self.user_config = user_config
self.threads = threads
self.credentials = credentials
def to_profile_info(
self, serialize_credentials: bool = False
) -> Dict[str, Any]:
def to_profile_info(self, serialize_credentials: bool = False) -> Dict[str, Any]:
"""Unlike to_project_config, this dict is not a mirror of any existing
on-disk data structure. It's used when creating a new profile from an
existing one.
@@ -121,34 +98,35 @@ class Profile(HasCredentials):
:returns dict: The serialized profile.
"""
result = {
'profile_name': self.profile_name,
'target_name': self.target_name,
'user_config': self.user_config,
'threads': self.threads,
'credentials': self.credentials,
"profile_name": self.profile_name,
"target_name": self.target_name,
"config": self.config,
"threads": self.threads,
"credentials": self.credentials,
}
if serialize_credentials:
result['user_config'] = self.user_config.to_dict(omit_none=True)
result['credentials'] = self.credentials.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
def to_target_dict(self) -> Dict[str, Any]:
target = dict(
self.credentials.connection_info(with_aliases=True)
target = dict(self.credentials.connection_info(with_aliases=True))
target.update(
{
"type": self.credentials.type,
"threads": self.threads,
"name": self.target_name,
"target_name": self.target_name,
"profile_name": self.profile_name,
"config": self.config.to_dict(omit_none=True),
}
)
target.update({
'type': self.credentials.type,
'threads': self.threads,
'name': self.target_name,
'target_name': self.target_name,
'profile_name': self.profile_name,
'config': self.user_config.to_dict(omit_none=True),
})
return target
def __eq__(self, other: object) -> bool:
if not (isinstance(other, self.__class__) and
isinstance(self, other.__class__)):
if not (
isinstance(other, self.__class__) and isinstance(self, other.__class__)
):
return NotImplemented
return self.to_profile_info() == other.to_profile_info()
@@ -168,14 +146,17 @@ class Profile(HasCredentials):
) -> Credentials:
# avoid an import cycle
from dbt.adapters.factory import load_plugin
# credentials carry their 'type' in their actual type, not their
# attributes. We do want this in order to pick our Credentials class.
if 'type' not in profile:
if "type" not in profile:
raise DbtProfileError(
'required field "type" not found in profile {} and target {}'
.format(profile_name, target_name))
'required field "type" not found in profile {} and target {}'.format(
profile_name, target_name
)
)
typename = profile.pop('type')
typename = profile.pop("type")
try:
cls = load_plugin(typename)
data = cls.translate_aliases(profile)
@@ -184,8 +165,9 @@ class Profile(HasCredentials):
except (RuntimeException, ValidationError) as e:
msg = str(e) if isinstance(e, RuntimeException) else e.message
raise DbtProfileError(
'Credentials in profile "{}", target "{}" invalid: {}'
.format(profile_name, target_name, msg)
'Credentials in profile "{}", target "{}" invalid: {}'.format(
profile_name, target_name, msg
)
) from e
return credentials
@@ -206,19 +188,21 @@ class Profile(HasCredentials):
def _get_profile_data(
profile: Dict[str, Any], profile_name: str, target_name: str
) -> Dict[str, Any]:
if 'outputs' not in profile:
if "outputs" not in profile:
raise DbtProfileError(
"outputs not specified in profile '{}'".format(profile_name)
)
outputs = profile['outputs']
outputs = profile["outputs"]
if target_name not in outputs:
outputs = '\n'.join(' - {}'.format(output)
for output in outputs)
msg = ("The profile '{}' does not have a target named '{}'. The "
"valid target names for this profile are:\n{}"
.format(profile_name, target_name, outputs))
raise DbtProfileError(msg, result_type='invalid_target')
outputs = "\n".join(" - {}".format(output) for output in outputs)
msg = (
"The profile '{}' does not have a target named '{}'. The "
"valid target names for this profile are:\n{}".format(
profile_name, target_name, outputs
)
)
raise DbtProfileError(msg, result_type="invalid_target")
profile_data = outputs[target_name]
if not isinstance(profile_data, dict):
@@ -226,7 +210,7 @@ class Profile(HasCredentials):
f"output '{target_name}' of profile '{profile_name}' is "
f"misconfigured in profiles.yml"
)
raise DbtProfileError(msg, result_type='invalid_target')
raise DbtProfileError(msg, result_type="invalid_target")
return profile_data
@@ -237,8 +221,8 @@ class Profile(HasCredentials):
threads: int,
profile_name: str,
target_name: str,
user_config: Optional[Dict[str, Any]] = None
) -> 'Profile':
user_cfg: Optional[Dict[str, Any]] = None,
) -> "Profile":
"""Create a profile from an existing set of Credentials and the
remaining information.
@@ -246,22 +230,22 @@ 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
credentials=credentials,
)
profile.validate()
return profile
@@ -286,19 +270,18 @@ class Profile(HasCredentials):
# name to extract a profile that we can render.
if target_override is not None:
target_name = target_override
elif 'target' in raw_profile:
elif "target" in raw_profile:
# render the target if it was parsed from yaml
target_name = renderer.render_value(raw_profile['target'])
target_name = renderer.render_value(raw_profile["target"])
else:
target_name = 'default'
target_name = "default"
logger.debug(
"target not specified in profile '{}', using '{}'"
.format(profile_name, target_name)
"target not specified in profile '{}', using '{}'".format(
profile_name, target_name
)
)
raw_profile_data = cls._get_profile_data(
raw_profile, profile_name, target_name
)
raw_profile_data = cls._get_profile_data(raw_profile, profile_name, target_name)
try:
profile_data = renderer.render_data(raw_profile_data)
@@ -312,10 +295,10 @@ 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':
) -> "Profile":
"""Create a profile from its raw profile information.
(this is an intermediate step, mostly useful for unit testing)
@@ -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
@@ -344,7 +327,7 @@ class Profile(HasCredentials):
# valid connections never include the number of threads, but it's
# stored on a per-connection level in the raw configs
threads = profile_data.pop('threads', DEFAULT_THREADS)
threads = profile_data.pop("threads", DEFAULT_THREADS)
if threads_override is not None:
threads = threads_override
@@ -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
@@ -368,7 +351,7 @@ class Profile(HasCredentials):
renderer: ProfileRenderer,
target_override: Optional[str] = None,
threads_override: Optional[int] = None,
) -> 'Profile':
) -> "Profile":
"""
:param raw_profiles: The profile data, from disk as yaml.
:param profile_name: The profile name to use.
@@ -392,21 +375,15 @@ class Profile(HasCredentials):
# don't render keys, so we can pluck that out
raw_profile = raw_profiles[profile_name]
if not raw_profile:
msg = (
f'Profile {profile_name} in profiles.yml is empty'
)
raise DbtProfileError(
INVALID_PROFILE_MESSAGE.format(
error_string=msg
)
)
user_config = raw_profiles.get('config')
msg = f"Profile {profile_name} in profiles.yml is empty"
raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
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,
)
@@ -417,7 +394,7 @@ class Profile(HasCredentials):
args: Any,
renderer: ProfileRenderer,
project_profile_name: Optional[str],
) -> 'Profile':
) -> "Profile":
"""Given the raw profiles as read from disk and the name of the desired
profile if specified, return the profile component of the runtime
config.
@@ -432,15 +409,16 @@ class Profile(HasCredentials):
target could not be found.
:returns Profile: The new Profile object.
"""
threads_override = getattr(args, 'threads', None)
target_override = getattr(args, 'target', None)
raw_profiles = read_profile(flags.PROFILES_DIR)
profile_name = cls.pick_profile_name(getattr(args, 'profile', None),
project_profile_name)
threads_override = getattr(args, "threads", None)
target_override = getattr(args, "target", None)
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(
raw_profiles=raw_profiles,
profile_name=profile_name,
renderer=renderer,
target_override=target_override,
threads_override=threads_override
threads_override=threads_override,
)

View File

@@ -2,14 +2,19 @@ from copy import deepcopy
from dataclasses import dataclass, field
from itertools import chain
from typing import (
List, Dict, Any, Optional, TypeVar, Union, Mapping,
List,
Dict,
Any,
Optional,
TypeVar,
Union,
Mapping,
)
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
@@ -83,9 +88,7 @@ def _load_yaml(path):
def package_data_from_root(project_root):
package_filepath = resolve_path_from_base(
'packages.yml', project_root
)
package_filepath = resolve_path_from_base("packages.yml", project_root)
if path_exists(package_filepath):
packages_dict = _load_yaml(package_filepath)
@@ -96,7 +99,7 @@ def package_data_from_root(project_root):
def package_config_from_data(packages_data: Dict[str, Any]):
if not packages_data:
packages_data = {'packages': []}
packages_data = {"packages": []}
try:
PackageConfig.validate(packages_data)
@@ -119,22 +122,23 @@ def _parse_versions(versions: Union[List[str], str]) -> List[VersionSpecifier]:
Regardless, this will return a list of VersionSpecifiers
"""
if isinstance(versions, str):
versions = versions.split(',')
versions = versions.split(",")
return [VersionSpecifier.from_version_string(v) for v in versions]
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,
macro_paths))
return list(
chain(source_paths, data_paths, snapshot_paths, analysis_paths, macro_paths)
)
T = TypeVar('T')
T = TypeVar("T")
def value_or(value: Optional[T], default: T) -> T:
@@ -147,30 +151,27 @@ def value_or(value: Optional[T], default: T) -> T:
def _raw_project_from(project_root: str) -> Dict[str, Any]:
project_root = os.path.normpath(project_root)
project_yaml_filepath = os.path.join(project_root, 'dbt_project.yml')
project_yaml_filepath = os.path.join(project_root, "dbt_project.yml")
# get the project.yml contents
if not path_exists(project_yaml_filepath):
raise DbtProjectError(
'no dbt_project.yml found at expected path {}'
.format(project_yaml_filepath)
"no dbt_project.yml found at expected path {}".format(project_yaml_filepath)
)
project_dict = _load_yaml(project_yaml_filepath)
if not isinstance(project_dict, dict):
raise DbtProjectError(
'dbt_project.yml does not parse to a dictionary'
)
raise DbtProjectError("dbt_project.yml does not parse to a dictionary")
return project_dict
def _query_comment_from_cfg(
cfg_query_comment: Union[QueryComment, NoValue, str, None]
cfg_query_comment: Union[QueryComment, NoValue, str, None]
) -> QueryComment:
if not cfg_query_comment:
return QueryComment(comment='')
return QueryComment(comment="")
if isinstance(cfg_query_comment, str):
return QueryComment(comment=cfg_query_comment)
@@ -187,9 +188,7 @@ def validate_version(dbt_version: List[VersionSpecifier], project_name: str):
if not versions_compatible(*dbt_version):
msg = IMPOSSIBLE_VERSION_ERROR.format(
package=project_name,
version_spec=[
x.to_version_string() for x in dbt_version
]
version_spec=[x.to_version_string() for x in dbt_version],
)
raise DbtProjectError(msg)
@@ -197,9 +196,7 @@ def validate_version(dbt_version: List[VersionSpecifier], project_name: str):
msg = INVALID_VERSION_ERROR.format(
package=project_name,
installed=installed.to_version_string(),
version_spec=[
x.to_version_string() for x in dbt_version
]
version_spec=[x.to_version_string() for x in dbt_version],
)
raise DbtProjectError(msg)
@@ -208,8 +205,8 @@ def _get_required_version(
project_dict: Dict[str, Any],
verify_version: bool,
) -> List[VersionSpecifier]:
dbt_raw_version: Union[List[str], str] = '>=0.0.0'
required = project_dict.get('require-dbt-version')
dbt_raw_version: Union[List[str], str] = ">=0.0.0"
required = project_dict.get("require-dbt-version")
if required is not None:
dbt_raw_version = required
@@ -220,11 +217,11 @@ def _get_required_version(
if verify_version:
# no name is also an error that we want to raise
if 'name' not in project_dict:
if "name" not in project_dict:
raise DbtProjectError(
'Required "name" field not present in project',
)
validate_version(dbt_version, project_dict['name'])
validate_version(dbt_version, project_dict["name"])
return dbt_version
@@ -232,34 +229,36 @@ def _get_required_version(
@dataclass
class RenderComponents:
project_dict: Dict[str, Any] = field(
metadata=dict(description='The project dictionary')
metadata=dict(description="The project dictionary")
)
packages_dict: Dict[str, Any] = field(
metadata=dict(description='The packages dictionary')
metadata=dict(description="The packages dictionary")
)
selectors_dict: Dict[str, Any] = field(
metadata=dict(description='The selectors dictionary')
metadata=dict(description="The selectors dictionary")
)
@dataclass
class PartialProject(RenderComponents):
profile_name: Optional[str] = field(metadata=dict(
description='The unrendered profile name in the project, if set'
))
project_name: Optional[str] = field(metadata=dict(
description=(
'The name of the project. This should always be set and will not '
'be rendered'
profile_name: Optional[str] = field(
metadata=dict(description="The unrendered profile name in the project, if set")
)
project_name: Optional[str] = field(
metadata=dict(
description=(
"The name of the project. This should always be set and will not "
"be rendered"
)
)
))
)
project_root: str = field(
metadata=dict(description='The root directory of the project'),
metadata=dict(description="The root directory of the project"),
)
verify_version: bool = field(
metadata=dict(description=(
'If True, verify the dbt version matches the required version'
))
metadata=dict(
description=("If True, verify the dbt version matches the required version")
)
)
def render_profile_name(self, renderer) -> Optional[str]:
@@ -272,9 +271,7 @@ class PartialProject(RenderComponents):
renderer: DbtProjectYamlRenderer,
) -> RenderComponents:
rendered_project = renderer.render_project(
self.project_dict, self.project_root
)
rendered_project = renderer.render_project(self.project_dict, self.project_root)
rendered_packages = renderer.render_packages(self.packages_dict)
rendered_selectors = renderer.render_selectors(self.selectors_dict)
@@ -284,31 +281,16 @@ class PartialProject(RenderComponents):
selectors_dict=rendered_selectors,
)
def render(self, renderer: DbtProjectYamlRenderer) -> 'Project':
def render(self, renderer: DbtProjectYamlRenderer) -> "Project":
try:
rendered = self.get_rendered(renderer)
return self.create_project(rendered)
except DbtProjectError as exc:
if exc.path is None:
exc.path = os.path.join(self.project_root, 'dbt_project.yml')
exc.path = os.path.join(self.project_root, "dbt_project.yml")
raise
def check_config_path(self, project_dict, deprecated_path, exp_path):
if deprecated_path in project_dict:
if exp_path in project_dict:
msg = (
'{deprecated_path} and {exp_path} cannot both be defined. The '
'`{deprecated_path}` config has been deprecated in favor of `{exp_path}`. '
'Please update your `dbt_project.yml` configuration to reflect this '
'change.'
)
raise DbtProjectError(msg.format(deprecated_path=deprecated_path,
exp_path=exp_path))
deprecations.warn('project_config_path',
deprecated_path=deprecated_path,
exp_path=exp_path)
def create_project(self, rendered: RenderComponents) -> 'Project':
def create_project(self, rendered: RenderComponents) -> "Project":
unrendered = RenderComponents(
project_dict=self.project_dict,
packages_dict=self.packages_dict,
@@ -319,14 +301,9 @@ 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(
rendered.project_dict
)
cfg = ProjectContract.from_dict(rendered.project_dict)
except ValidationError as e:
raise DbtProjectError(validator_error_message(e)) from e
# name/version are required in the Project definition, so we can assume
@@ -336,40 +313,30 @@ class PartialProject(RenderComponents):
# this is added at project_dict parse time and should always be here
# once we see it.
if cfg.project_root is None:
raise DbtProjectError('cfg must have a project root!')
raise DbtProjectError("cfg must have a project root!")
else:
project_root = cfg.project_root
# this is only optional in the sense that if it's not present, it needs
# 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'])
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'])
snapshot_paths: List[str] = value_or(cfg.snapshot_paths, ['snapshots'])
source_paths: List[str] = value_or(cfg.source_paths, ["models"])
macro_paths: List[str] = value_or(cfg.macro_paths, ["macros"])
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,
macro_paths
source_paths, data_paths, snapshot_paths, analysis_paths, macro_paths
)
docs_paths: List[str] = value_or(cfg.docs_paths, all_source_paths)
asset_paths: List[str] = value_or(cfg.asset_paths, [])
target_path: str = value_or(cfg.target_path, 'target')
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')
log_path: str = value_or(cfg.log_path, "logs")
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
@@ -377,20 +344,16 @@ class PartialProject(RenderComponents):
if cfg.quoting is not None:
quoting = cfg.quoting.to_dict(omit_none=True)
dispatch: List[Dict[str, Any]]
models: Dict[str, Any]
seeds: Dict[str, Any]
snapshots: Dict[str, Any]
sources: Dict[str, Any]
tests: Dict[str, Any]
vars_value: VarProvider
dispatch = cfg.dispatch
models = cfg.models
seeds = cfg.seeds
snapshots = cfg.snapshots
sources = cfg.sources
tests = cfg.tests
if cfg.vars is None:
vars_dict: Dict[str, Any] = {}
else:
@@ -405,19 +368,21 @@ class PartialProject(RenderComponents):
packages = package_config_from_data(rendered.packages_dict)
selectors = selector_config_from_data(rendered.selectors_dict)
manifest_selectors: Dict[str, Any] = {}
if rendered.selectors_dict and rendered.selectors_dict['selectors']:
if rendered.selectors_dict and rendered.selectors_dict["selectors"]:
# this is a dict with a single key 'selectors' pointing to a list
# of dicts.
manifest_selectors = SelectorDict.parse_from_selectors_list(
rendered.selectors_dict['selectors'])
rendered.selectors_dict["selectors"]
)
project = Project(
project_name=name,
version=version,
project_root=project_root,
profile_name=profile_name,
model_paths=model_paths,
source_paths=source_paths,
macro_paths=macro_paths,
seed_paths=seed_paths,
data_paths=data_paths,
test_paths=test_paths,
analysis_paths=analysis_paths,
docs_paths=docs_paths,
@@ -426,12 +391,11 @@ 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,
on_run_end=on_run_end,
dispatch=dispatch,
seeds=seeds,
snapshots=snapshots,
dbt_version=dbt_version,
@@ -440,7 +404,6 @@ class PartialProject(RenderComponents):
selectors=selectors,
query_comment=query_comment,
sources=sources,
tests=tests,
vars=vars_value,
config_version=cfg.config_version,
unrendered=unrendered,
@@ -459,10 +422,9 @@ class PartialProject(RenderComponents):
*,
verify_version: bool = False,
):
"""Construct a partial project from its constituent dicts.
"""
project_name = project_dict.get('name')
profile_name = project_dict.get('profile')
"""Construct a partial project from its constituent dicts."""
project_name = project_dict.get("name")
profile_name = project_dict.get("profile")
return cls(
profile_name=profile_name,
@@ -477,14 +439,14 @@ class PartialProject(RenderComponents):
@classmethod
def from_project_root(
cls, project_root: str, *, verify_version: bool = False
) -> 'PartialProject':
) -> "PartialProject":
project_root = os.path.normpath(project_root)
project_dict = _raw_project_from(project_root)
config_version = project_dict.get('config-version', 1)
config_version = project_dict.get("config-version", 1)
if config_version != 2:
raise DbtProjectError(
f'Invalid config version: {config_version}, expected 2',
path=os.path.join(project_root, 'dbt_project.yml')
f"Invalid config version: {config_version}, expected 2",
path=os.path.join(project_root, "dbt_project.yml"),
)
packages_dict = package_data_from_root(project_root)
@@ -501,15 +463,10 @@ class PartialProject(RenderComponents):
class VarProvider:
"""Var providers are tied to a particular Project."""
def __init__(
self,
vars: Dict[str, Dict[str, Any]]
) -> None:
def __init__(self, vars: Dict[str, Dict[str, Any]]) -> None:
self.vars = vars
def vars_for(
self, node: IsFQNResource, adapter_type: str
) -> Mapping[str, Any]:
def vars_for(self, node: IsFQNResource, adapter_type: str) -> Mapping[str, Any]:
# in v2, vars are only either project or globally scoped
merged = MultiDict([self.vars])
merged.add(self.vars.get(node.package_name, {}))
@@ -527,9 +484,9 @@ class Project:
version: Union[SemverString, float]
project_root: str
profile_name: Optional[str]
model_paths: List[str]
source_paths: List[str]
macro_paths: List[str]
seed_paths: List[str]
data_paths: List[str]
test_paths: List[str]
analysis_paths: List[str]
docs_paths: List[str]
@@ -538,16 +495,14 @@ 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]
on_run_end: List[str]
dispatch: List[Dict[str, Any]]
seeds: Dict[str, Any]
snapshots: Dict[str, Any]
sources: Dict[str, Any]
tests: Dict[str, Any]
vars: VarProvider
dbt_version: List[VersionSpecifier]
packages: Dict[str, Any]
@@ -560,8 +515,11 @@ class Project:
@property
def all_source_paths(self) -> List[str]:
return _all_source_paths(
self.model_paths, self.seed_paths, self.snapshot_paths,
self.analysis_paths, self.macro_paths
self.source_paths,
self.data_paths,
self.snapshot_paths,
self.analysis_paths,
self.macro_paths,
)
def __str__(self):
@@ -569,11 +527,13 @@ class Project:
return str(cfg)
def __eq__(self, other):
if not (isinstance(other, self.__class__) and
isinstance(self, other.__class__)):
if not (
isinstance(other, self.__class__) and isinstance(self, other.__class__)
):
return False
return self.to_project_config(with_packages=True) == \
other.to_project_config(with_packages=True)
return self.to_project_config(with_packages=True) == other.to_project_config(
with_packages=True
)
def to_project_config(self, with_packages=False):
"""Return a dict representation of the config that could be written to
@@ -583,40 +543,39 @@ class Project:
file in the root.
:returns dict: The serialized profile.
"""
result = deepcopy({
'name': self.project_name,
'version': self.version,
'project-root': self.project_root,
'profile': self.profile_name,
'model-paths': self.model_paths,
'macro-paths': self.macro_paths,
'seed-paths': self.seed_paths,
'test-paths': self.test_paths,
'analysis-paths': self.analysis_paths,
'docs-paths': self.docs_paths,
'asset-paths': self.asset_paths,
'target-path': self.target_path,
'snapshot-paths': self.snapshot_paths,
'clean-targets': self.clean_targets,
'log-path': self.log_path,
'quoting': self.quoting,
'models': self.models,
'on-run-start': self.on_run_start,
'on-run-end': self.on_run_end,
'dispatch': self.dispatch,
'seeds': self.seeds,
'snapshots': self.snapshots,
'sources': self.sources,
'tests': self.tests,
'vars': self.vars.to_dict(),
'require-dbt-version': [
v.to_version_string() for v in self.dbt_version
],
'config-version': self.config_version,
})
result = deepcopy(
{
"name": self.project_name,
"version": self.version,
"project-root": self.project_root,
"profile": self.profile_name,
"source-paths": self.source_paths,
"macro-paths": self.macro_paths,
"data-paths": self.data_paths,
"test-paths": self.test_paths,
"analysis-paths": self.analysis_paths,
"docs-paths": self.docs_paths,
"asset-paths": self.asset_paths,
"target-path": self.target_path,
"snapshot-paths": self.snapshot_paths,
"clean-targets": self.clean_targets,
"log-path": self.log_path,
"quoting": self.quoting,
"models": self.models,
"on-run-start": self.on_run_start,
"on-run-end": self.on_run_end,
"seeds": self.seeds,
"snapshots": self.snapshots,
"sources": self.sources,
"vars": self.vars.to_dict(),
"require-dbt-version": [
v.to_version_string() for v in self.dbt_version
],
"config-version": self.config_version,
}
)
if self.query_comment:
result['query-comment'] = \
self.query_comment.to_dict(omit_none=True)
result["query-comment"] = self.query_comment.to_dict(omit_none=True)
if with_packages:
result.update(self.packages.to_dict(omit_none=True))
@@ -647,8 +606,8 @@ class Project:
selectors_dict: Dict[str, Any],
renderer: DbtProjectYamlRenderer,
*,
verify_version: bool = False
) -> 'Project':
verify_version: bool = False,
) -> "Project":
partial = PartialProject.from_dicts(
project_root=project_root,
project_dict=project_dict,
@@ -665,34 +624,17 @@ class Project:
renderer: DbtProjectYamlRenderer,
*,
verify_version: bool = False,
) -> 'Project':
) -> "Project":
partial = cls.partial_load(project_root, verify_version=verify_version)
return partial.render(renderer)
def hashed_name(self):
return hashlib.md5(self.project_name.encode('utf-8')).hexdigest()
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)}'
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
def get_macro_search_order(self, macro_namespace: str):
for dispatch_entry in self.dispatch:
if dispatch_entry['macro_namespace'] == macro_namespace:
return dispatch_entry['search_order']
return None
return self.selectors[name]

View File

@@ -2,9 +2,7 @@ from typing import Dict, Any, Tuple, Optional, Union, Callable
from dbt.clients.jinja import get_rendered, catch_jinja
from dbt.exceptions import (
DbtProjectError, CompilationException, RecursionException
)
from dbt.exceptions import DbtProjectError, CompilationException, RecursionException
from dbt.node_types import NodeType
from dbt.utils import deep_map
@@ -18,7 +16,7 @@ class BaseRenderer:
@property
def name(self):
return 'Rendering'
return "Rendering"
def should_render_keypath(self, keypath: Keypath) -> bool:
return True
@@ -29,9 +27,7 @@ class BaseRenderer:
return self.render_value(value, keypath)
def render_value(
self, value: Any, keypath: Optional[Keypath] = None
) -> Any:
def render_value(self, value: Any, keypath: Optional[Keypath] = None) -> Any:
# keypath is ignored.
# if it wasn't read as a string, ignore it
if not isinstance(value, str):
@@ -40,18 +36,16 @@ class BaseRenderer:
with catch_jinja():
return get_rendered(value, self.context, native=True)
except CompilationException as exc:
msg = f'Could not render {value}: {exc.msg}'
msg = f"Could not render {value}: {exc.msg}"
raise CompilationException(msg) from exc
def render_data(
self, data: Dict[str, Any]
) -> Dict[str, Any]:
def render_data(self, data: Dict[str, Any]) -> Dict[str, Any]:
try:
return deep_map(self.render_entry, data)
except RecursionException:
raise DbtProjectError(
f'Cycle detected: {self.name} input has a reference to itself',
project=data
f"Cycle detected: {self.name} input has a reference to itself",
project=data,
)
@@ -78,15 +72,15 @@ class ProjectPostprocessor(Dict[Keypath, Callable[[Any], Any]]):
def __init__(self):
super().__init__()
self[('on-run-start',)] = _list_if_none_or_string
self[('on-run-end',)] = _list_if_none_or_string
self[("on-run-start",)] = _list_if_none_or_string
self[("on-run-end",)] = _list_if_none_or_string
for k in ('models', 'seeds', 'snapshots'):
for k in ("models", "seeds", "snapshots"):
self[(k,)] = _dict_if_none
self[(k, 'vars')] = _dict_if_none
self[(k, 'pre-hook')] = _list_if_none_or_string
self[(k, 'post-hook')] = _list_if_none_or_string
self[('seeds', 'column_types')] = _dict_if_none
self[(k, "vars")] = _dict_if_none
self[(k, "pre-hook")] = _list_if_none_or_string
self[(k, "post-hook")] = _list_if_none_or_string
self[("seeds", "column_types")] = _dict_if_none
def postprocess(self, value: Any, key: Keypath) -> Any:
if key in self:
@@ -101,7 +95,7 @@ class DbtProjectYamlRenderer(BaseRenderer):
@property
def name(self):
'Project config'
"Project config"
def get_package_renderer(self) -> BaseRenderer:
return PackageRenderer(self.context)
@@ -116,7 +110,7 @@ class DbtProjectYamlRenderer(BaseRenderer):
) -> Dict[str, Any]:
"""Render the project and insert the project root after rendering."""
rendered_project = self.render_data(project)
rendered_project['project-root'] = project_root
rendered_project["project-root"] = project_root
return rendered_project
def render_packages(self, packages: Dict[str, Any]):
@@ -138,20 +132,19 @@ class DbtProjectYamlRenderer(BaseRenderer):
first = keypath[0]
# run hooks are not rendered
if first in {'on-run-start', 'on-run-end', 'query-comment'}:
if first in {"on-run-start", "on-run-end", "query-comment"}:
return False
# don't render vars blocks until runtime
if first == 'vars':
if first == "vars":
return False
if first in {'seeds', 'models', 'snapshots', 'tests'}:
if first in {"seeds", "models", "snapshots", "seeds"}:
keypath_parts = {
(k.lstrip('+ ') if isinstance(k, str) else k)
for k in keypath
(k.lstrip("+") if isinstance(k, str) else k) for k in keypath
}
# model-level hooks
if 'pre-hook' in keypath_parts or 'post-hook' in keypath_parts:
if "pre-hook" in keypath_parts or "post-hook" in keypath_parts:
return False
return True
@@ -160,17 +153,15 @@ class DbtProjectYamlRenderer(BaseRenderer):
class ProfileRenderer(BaseRenderer):
@property
def name(self):
'Profile'
"Profile"
class SchemaYamlRenderer(BaseRenderer):
DOCUMENTABLE_NODES = frozenset(
n.pluralize() for n in NodeType.documentable()
)
DOCUMENTABLE_NODES = frozenset(n.pluralize() for n in NodeType.documentable())
@property
def name(self):
return 'Rendering yaml'
return "Rendering yaml"
def _is_norender_key(self, keypath: Keypath) -> bool:
"""
@@ -185,13 +176,13 @@ class SchemaYamlRenderer(BaseRenderer):
Return True if it's tests or description - those aren't rendered
"""
if len(keypath) >= 2 and keypath[1] in ('tests', 'description'):
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')
len(keypath) >= 4
and keypath[1] == "columns"
and keypath[3] in ("tests", "description")
):
return True
@@ -209,13 +200,13 @@ class SchemaYamlRenderer(BaseRenderer):
return True
if keypath[0] == NodeType.Source.pluralize():
if keypath[2] == 'description':
if keypath[2] == "description":
return False
if keypath[2] == 'tables':
if keypath[2] == "tables":
if self._is_norender_key(keypath[3:]):
return False
elif keypath[0] == NodeType.Macro.pluralize():
if keypath[2] == 'arguments':
if keypath[2] == "arguments":
if self._is_norender_key(keypath[3:]):
return False
elif self._is_norender_key(keypath[1:]):
@@ -229,10 +220,10 @@ class SchemaYamlRenderer(BaseRenderer):
class PackageRenderer(BaseRenderer):
@property
def name(self):
return 'Packages config'
return "Packages config"
class SelectorRenderer(BaseRenderer):
@property
def name(self):
return 'Selector config'
return "Selector config"

View File

@@ -4,19 +4,26 @@ from copy import deepcopy
from dataclasses import dataclass, fields
from pathlib import Path
from typing import (
Dict, Any, Optional, Mapping, Iterator, Iterable, Tuple, List, MutableSet,
Type
Dict,
Any,
Optional,
Mapping,
Iterator,
Iterable,
Tuple,
List,
MutableSet,
Type,
)
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.context.base import generate_base_context
from dbt.context 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
@@ -31,15 +38,13 @@ from dbt.exceptions import (
DbtProjectError,
validator_error_message,
warn_or_error,
raise_compiler_error
raise_compiler_error,
)
from dbt.dataclass_schema import ValidationError
def _project_quoting_dict(
proj: Project, profile: Profile
) -> Dict[ComponentName, bool]:
def _project_quoting_dict(proj: Project, profile: Profile) -> Dict[ComponentName, bool]:
src: Dict[str, Any] = profile.credentials.translate_aliases(proj.quoting)
result: Dict[ComponentName, bool] = {}
for key in ComponentName:
@@ -55,7 +60,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
args: Any
profile_name: str
cli_vars: Dict[str, Any]
dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None
dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None
def __post_init__(self):
self.validate()
@@ -66,8 +71,8 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
project: Project,
profile: Profile,
args: Any,
dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None,
) -> 'RuntimeConfig':
dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None,
) -> "RuntimeConfig":
"""Instantiate a RuntimeConfig from its components.
:param profile: A parsed dbt Profile.
@@ -81,15 +86,15 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
.replace_dict(_project_quoting_dict(project, profile))
).to_dict(omit_none=True)
cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
return cls(
project_name=project.project_name,
version=project.version,
project_root=project.project_root,
model_paths=project.model_paths,
source_paths=project.source_paths,
macro_paths=project.macro_paths,
seed_paths=project.seed_paths,
data_paths=project.data_paths,
test_paths=project.test_paths,
analysis_paths=project.analysis_paths,
docs_paths=project.docs_paths,
@@ -98,12 +103,11 @@ 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,
on_run_end=project.on_run_end,
dispatch=project.dispatch,
seeds=project.seeds,
snapshots=project.snapshots,
dbt_version=project.dbt_version,
@@ -112,13 +116,12 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
selectors=project.selectors,
query_comment=project.query_comment,
sources=project.sources,
tests=project.tests,
vars=project.vars,
config_version=project.config_version,
unrendered=project.unrendered,
profile_name=profile.profile_name,
target_name=profile.target_name,
user_config=profile.user_config,
config=profile.config,
threads=profile.threads,
credentials=profile.credentials,
args=args,
@@ -126,7 +129,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
dependencies=dependencies,
)
def new_project(self, project_root: str) -> 'RuntimeConfig':
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.
@@ -145,7 +148,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
project = Project.from_project_root(
project_root,
renderer,
verify_version=bool(flags.VERSION_CHECK),
verify_version=getattr(self.args, "version_check", False),
)
cfg = self.from_parts(
@@ -168,7 +171,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
"""
result = self.to_project_config(with_packages=True)
result.update(self.to_profile_info(serialize_credentials=True))
result['cli_vars'] = deepcopy(self.cli_vars)
result["cli_vars"] = deepcopy(self.cli_vars)
return result
def validate(self):
@@ -188,30 +191,21 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
profile_renderer: ProfileRenderer,
profile_name: Optional[str],
) -> Profile:
return Profile.render_from_args(
args, profile_renderer, profile_name
)
return Profile.render_from_args(args, profile_renderer, profile_name)
@classmethod
def collect_parts(
cls: Type['RuntimeConfig'], args: Any
) -> Tuple[Project, Profile]:
def collect_parts(cls: Type["RuntimeConfig"], args: Any) -> Tuple[Project, Profile]:
# profile_name from the project
project_root = args.project_dir if args.project_dir else os.getcwd()
version_check = bool(flags.VERSION_CHECK)
partial = Project.partial_load(
project_root,
verify_version=version_check
)
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
cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "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
)
profile = cls._get_rendered_profile(args, profile_renderer, profile_name)
# get a new renderer using our target information and render the
# project
@@ -221,7 +215,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
return (project, profile)
@classmethod
def from_args(cls, args: Any) -> 'RuntimeConfig':
def from_args(cls, args: Any) -> "RuntimeConfig":
"""Given arguments, read in dbt_project.yml from the current directory,
read in packages.yml if it exists, and use them to find the profile to
load.
@@ -241,8 +235,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
def get_metadata(self) -> ManifestMetadata:
return ManifestMetadata(
project_id=self.hashed_name(),
adapter_type=self.credentials.type
project_id=self.hashed_name(), adapter_type=self.credentials.type
)
def _get_v2_config_paths(
@@ -252,7 +245,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
paths: MutableSet[FQNPath],
) -> PathSet:
for key, value in config.items():
if isinstance(value, dict) and not key.startswith('+'):
if isinstance(value, dict) and not key.startswith("+"):
self._get_v2_config_paths(value, path + (key,), paths)
else:
paths.add(path)
@@ -268,23 +261,22 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
paths = set()
for key, value in config.items():
if isinstance(value, dict) and not key.startswith('+'):
if isinstance(value, dict) and not key.startswith("+"):
self._get_v2_config_paths(value, path + (key,), paths)
else:
paths.add(path)
return frozenset(paths)
def get_resource_config_paths(self) -> Dict[str, PathSet]:
"""Return a dictionary with resource type keys whose values are
"""Return a dictionary with 'seeds' and 'models' keys whose values are
lists of lists of strings, where each inner list of strings represents
a configured path in the resource.
"""
return {
'models': self._get_config_paths(self.models),
'seeds': self._get_config_paths(self.seeds),
'snapshots': self._get_config_paths(self.snapshots),
'sources': self._get_config_paths(self.sources),
'tests': self._get_config_paths(self.tests),
"models": self._get_config_paths(self.models),
"seeds": self._get_config_paths(self.seeds),
"snapshots": self._get_config_paths(self.snapshots),
"sources": self._get_config_paths(self.sources),
}
def get_unused_resource_config_paths(
@@ -305,9 +297,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
for config_path in config_paths:
if not _is_config_used(config_path, fqns):
unused_resource_config_paths.append(
(resource_type,) + config_path
)
unused_resource_config_paths.append((resource_type,) + config_path)
return unused_resource_config_paths
def warn_for_unused_resource_config_paths(
@@ -320,38 +310,25 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
return
msg = UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE.format(
len(unused),
'\n'.join('- {}'.format('.'.join(u)) for u in unused)
len(unused), "\n".join("- {}".format(".".join(u)) for u in unused)
)
warn_or_error(msg, log_fmt=warning_tag('{}'))
warn_or_error(msg, log_fmt=warning_tag("{}"))
def load_dependencies(self) -> Mapping[str, 'RuntimeConfig']:
def load_dependencies(self) -> Mapping[str, "RuntimeConfig"]:
if self.dependencies is None:
all_projects = {self.project_name: self}
internal_packages = get_include_paths(self.credentials.type)
# raise exception if fewer installed packages than in packages.yml
count_packages_specified = len(self.packages.packages) # type: ignore
count_packages_installed = len(tuple(self._get_project_directories()))
if count_packages_specified > count_packages_installed:
raise_compiler_error(
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'install package dependencies.'
)
project_paths = itertools.chain(
internal_packages,
self._get_project_directories()
internal_packages, self._get_project_directories()
)
for project_name, project in self.load_projects(project_paths):
if project_name in all_projects:
raise_compiler_error(
f'dbt found more than one package with the name '
f"dbt found more than one package with the name "
f'"{project_name}" included in this project. Package '
f'names must be unique in a project. Please rename '
f'one of these packages.'
f"names must be unique in a project. Please rename "
f"one of these packages."
)
all_projects[project_name] = project
self.dependencies = all_projects
@@ -362,40 +339,36 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
def load_projects(
self, paths: Iterable[Path]
) -> Iterator[Tuple[str, 'RuntimeConfig']]:
) -> Iterator[Tuple[str, "RuntimeConfig"]]:
for path in paths:
try:
project = self.new_project(str(path))
except DbtProjectError as e:
raise DbtProjectError(
f'Failed to read package: {e}',
result_type='invalid_project',
f"Failed to read package: {e}",
result_type="invalid_project",
path=path,
) from e
else:
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():
if path.is_dir() and not path.name.startswith('__'):
if path.is_dir() and not path.name.startswith("__"):
yield path
class UnsetCredentials(Credentials):
def __init__(self):
super().__init__('', '')
super().__init__("", "")
@property
def type(self):
return None
@property
def unique_field(self):
return None
def connection_info(self, *args, **kwargs):
return {}
@@ -406,9 +379,7 @@ class UnsetCredentials(Credentials):
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}"
)
raise AttributeError(f"'UnsetConfig' object has no attribute {name}")
def __post_serialize__(self, dct):
return {}
@@ -417,16 +388,16 @@ class UnsetConfig(UserConfig):
class UnsetProfile(Profile):
def __init__(self):
self.credentials = UnsetCredentials()
self.user_config = UnsetConfig()
self.profile_name = ''
self.target_name = ''
self.config = UnsetConfig()
self.profile_name = ""
self.target_name = ""
self.threads = -1
def to_target_dict(self):
return {}
def __getattribute__(self, name):
if name in {'profile_name', 'target_name', 'threads'}:
if name in {"profile_name", "target_name", "threads"}:
raise RuntimeException(
f'Error: disallowed attribute "{name}" - no profile!'
)
@@ -450,7 +421,7 @@ class UnsetProfileConfig(RuntimeConfig):
def __getattribute__(self, name):
# Override __getattribute__ to check that the attribute isn't 'banned'.
if name in {'profile_name', 'target_name'}:
if name in {"profile_name", "target_name"}:
raise RuntimeException(
f'Error: disallowed attribute "{name}" - no profile!'
)
@@ -468,8 +439,8 @@ class UnsetProfileConfig(RuntimeConfig):
project: Project,
profile: Profile,
args: Any,
dependencies: Optional[Mapping[str, 'RuntimeConfig']] = None,
) -> 'RuntimeConfig':
dependencies: Optional[Mapping[str, "RuntimeConfig"]] = None,
) -> "RuntimeConfig":
"""Instantiate a RuntimeConfig from its components.
:param profile: Ignored.
@@ -477,15 +448,15 @@ class UnsetProfileConfig(RuntimeConfig):
:param args: The parsed command-line arguments.
:returns RuntimeConfig: The new configuration.
"""
cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, 'vars', '{}'))
cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
return cls(
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,
@@ -494,12 +465,11 @@ 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,
on_run_end=project.on_run_end,
dispatch=project.dispatch,
seeds=project.seeds,
snapshots=project.snapshots,
dbt_version=project.dbt_version,
@@ -508,14 +478,13 @@ class UnsetProfileConfig(RuntimeConfig):
selectors=project.selectors,
query_comment=project.query_comment,
sources=project.sources,
tests=project.tests,
vars=project.vars,
config_version=project.config_version,
unrendered=project.unrendered,
profile_name='',
target_name='',
user_config=UnsetConfig(),
threads=getattr(args, 'threads', 1),
profile_name="",
target_name="",
config=UnsetConfig(),
threads=getattr(args, "threads", 1),
credentials=UnsetCredentials(),
args=args,
cli_vars=cli_vars,
@@ -530,16 +499,11 @@ class UnsetProfileConfig(RuntimeConfig):
profile_name: Optional[str],
) -> Profile:
try:
profile = Profile.render_from_args(
args, profile_renderer, profile_name
)
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.debug("Profile not loaded due to error: {}", exc, exc_info=True)
logger.info(
'No profile "{}" found, continuing with no target',
profile_name
'No profile "{}" found, continuing with no target', profile_name
)
# return the poisoned form
profile = UnsetProfile()
@@ -548,7 +512,7 @@ class UnsetProfileConfig(RuntimeConfig):
return profile
@classmethod
def from_args(cls: Type[RuntimeConfig], args: Any) -> 'RuntimeConfig':
def from_args(cls: Type[RuntimeConfig], args: Any) -> "RuntimeConfig":
"""Given arguments, read in dbt_project.yml from the current directory,
read in packages.yml if it exists, and use them to find the profile to
load.
@@ -563,11 +527,7 @@ class UnsetProfileConfig(RuntimeConfig):
# if it's a real profile, return a real config
cls = RuntimeConfig
return cls.from_parts(
project=project,
profile=profile,
args=args
)
return cls.from_parts(project=project, profile=profile, args=args)
UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE = """\
@@ -581,6 +541,6 @@ There are {} unused configuration paths:
def _is_config_used(path, fqns):
if fqns:
for fqn in fqns:
if len(path) <= len(fqn) and fqn[:len(path)] == path:
if len(path) <= len(fqn) and fqn[: len(path)] == path:
return True
return False

View File

@@ -1,8 +1,6 @@
from pathlib import Path
from typing import Dict, Any, Union
from dbt.clients.yaml_helper import ( # noqa: F401
yaml, Loader, Dumper, load_yaml_text
)
from typing import Dict, Any
from dbt.clients.yaml_helper import yaml, Loader, Dumper, load_yaml_text # noqa: F401
from dbt.dataclass_schema import ValidationError
from .renderer import SelectorRenderer
@@ -29,14 +27,12 @@ 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':
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)
@@ -46,12 +42,12 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
f"union, intersection, string, dictionary. No lists. "
f"\nhttps://docs.getdbt.com/reference/node-selection/"
f"yaml-selectors",
result_type='invalid_selector'
result_type="invalid_selector",
) from exc
except RuntimeException as exc:
raise DbtSelectorsError(
f'Could not read selector file data: {exc}',
result_type='invalid_selector',
f"Could not read selector file data: {exc}",
result_type="invalid_selector",
) from exc
return cls(selectors)
@@ -61,26 +57,28 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
cls,
data: Dict[str, Any],
renderer: SelectorRenderer,
) -> 'SelectorConfig':
) -> "SelectorConfig":
try:
rendered = renderer.render_data(data)
except (ValidationError, RuntimeException) as exc:
raise DbtSelectorsError(
f'Could not render selector data: {exc}',
result_type='invalid_selector',
f"Could not render selector data: {exc}",
result_type="invalid_selector",
) from exc
return cls.selectors_from_dict(rendered)
@classmethod
def from_path(
cls, path: Path, renderer: SelectorRenderer,
) -> 'SelectorConfig':
cls,
path: Path,
renderer: SelectorRenderer,
) -> "SelectorConfig":
try:
data = load_yaml_text(load_file_contents(str(path)))
except (ValidationError, RuntimeException) as exc:
raise DbtSelectorsError(
f'Could not read selector file: {exc}',
result_type='invalid_selector',
f"Could not read selector file: {exc}",
result_type="invalid_selector",
path=path,
) from exc
@@ -92,9 +90,7 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
def selector_data_from_root(project_root: str) -> Dict[str, Any]:
selector_filepath = resolve_path_from_base(
'selectors.yml', project_root
)
selector_filepath = resolve_path_from_base("selectors.yml", project_root)
if path_exists(selector_filepath):
selectors_dict = load_yaml_text(load_file_contents(selector_filepath))
@@ -103,40 +99,20 @@ def selector_data_from_root(project_root: str) -> Dict[str, Any]:
return selectors_dict
def selector_config_from_data(
selectors_data: Dict[str, Any]
) -> SelectorConfig:
def selector_config_from_data(selectors_data: Dict[str, Any]) -> SelectorConfig:
if not selectors_data:
selectors_data = {'selectors': []}
selectors_data = {"selectors": []}
try:
selectors = SelectorConfig.selectors_from_dict(selectors_data)
except ValidationError as e:
raise DbtSelectorsError(
MALFORMED_SELECTOR_ERROR.format(error=str(e.message)),
result_type='invalid_selector',
result_type="invalid_selector",
) from e
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
@@ -144,7 +120,6 @@ def validate_selector_default(selector_file: SelectorFile) -> None:
# be necessary to make changes here. Ideally it would be
# good to combine the two flows into one at some point.
class SelectorDict:
@classmethod
def parse_dict_definition(cls, definition):
key = list(definition)[0]
@@ -155,10 +130,10 @@ class SelectorDict:
new_value = cls.parse_from_definition(sel_def)
new_values.append(new_value)
value = new_values
if key == 'exclude':
if key == "exclude":
definition = {key: value}
elif len(definition) == 1:
definition = {'method': key, 'value': value}
definition = {"method": key, "value": value}
return definition
@classmethod
@@ -180,10 +155,10 @@ class SelectorDict:
def parse_from_definition(cls, definition):
if isinstance(definition, str):
definition = SelectionCriteria.dict_from_single_spec(definition)
elif 'union' in definition:
definition = cls.parse_a_definition('union', definition)
elif 'intersection' in definition:
definition = cls.parse_a_definition('intersection', definition)
elif "union" in definition:
definition = cls.parse_a_definition("union", definition)
elif "intersection" in definition:
definition = cls.parse_a_definition("intersection", definition)
elif isinstance(definition, dict):
definition = cls.parse_dict_definition(definition)
return definition
@@ -194,8 +169,8 @@ class SelectorDict:
def parse_from_selectors_list(cls, selectors):
selector_dict = {}
for selector in selectors:
sel_name = selector['name']
sel_name = selector["name"]
selector_dict[sel_name] = selector
definition = cls.parse_from_definition(selector['definition'])
selector_dict[sel_name]['definition'] = definition
definition = cls.parse_from_definition(selector["definition"])
selector_dict[sel_name]["definition"] = definition
return selector_dict

View File

@@ -15,9 +15,8 @@ def parse_cli_vars(var_string: str) -> Dict[str, Any]:
type_name = var_type.__name__
raise_compiler_error(
"The --vars argument must be a YAML dictionary, but was "
"of type '{}'".format(type_name))
"of type '{}'".format(type_name)
)
except ValidationException:
logger.error(
"The YAML provided in the --vars argument is not valid.\n"
)
logger.error("The YAML provided in the --vars argument is not valid.\n")
raise

View File

@@ -0,0 +1,531 @@
import json
import os
from typing import Any, Dict, NoReturn, Optional, Mapping
from dbt import flags
from dbt import tracking
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
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
# approaches which will extend well to potentially many modules
import pytz
import datetime
import re
def get_pytz_module_context() -> Dict[str, Any]:
context_exports = pytz.__all__ # type: ignore
return {name: getattr(pytz, name) for name in context_exports}
def get_datetime_module_context() -> Dict[str, Any]:
context_exports = ["date", "datetime", "time", "timedelta", "tzinfo"]
return {name: getattr(datetime, name) for name in context_exports}
def get_re_module_context() -> Dict[str, Any]:
context_exports = re.__all__
return {name: getattr(re, name) for name in context_exports}
def get_context_modules() -> Dict[str, Dict[str, Any]]:
return {
"pytz": get_pytz_module_context(),
"datetime": get_datetime_module_context(),
"re": get_re_module_context(),
}
class ContextMember:
def __init__(self, value, name=None):
self.name = name
self.inner = value
def key(self, default):
if self.name is None:
return default
return self.name
def contextmember(value):
if isinstance(value, str):
return lambda v: ContextMember(v, name=value)
return ContextMember(value)
def contextproperty(value):
if isinstance(value, str):
return lambda v: ContextMember(property(v), name=value)
return ContextMember(property(value))
class ContextMeta(type):
def __new__(mcls, name, bases, dct):
context_members = {}
context_attrs = {}
new_dct = {}
for base in bases:
context_members.update(getattr(base, "_context_members_", {}))
context_attrs.update(getattr(base, "_context_attrs_", {}))
for key, value in dct.items():
if isinstance(value, ContextMember):
context_key = value.key(key)
context_members[context_key] = value.inner
context_attrs[context_key] = key
value = value.inner
new_dct[key] = value
new_dct["_context_members_"] = context_members
new_dct["_context_attrs_"] = context_attrs
return type.__new__(mcls, name, bases, new_dct)
class Var:
UndefinedVarError = (
"Required var '{}' not found in config:\nVars " "supplied to {} = {}"
)
_VAR_NOTSET = object()
def __init__(
self,
context: Mapping[str, Any],
cli_vars: Mapping[str, Any],
node: Optional[CompiledResource] = None,
) -> None:
self._context: Mapping[str, Any] = context
self._cli_vars: Mapping[str, Any] = cli_vars
self._node: Optional[CompiledResource] = node
self._merged: Mapping[str, Any] = self._generate_merged()
def _generate_merged(self) -> Mapping[str, Any]:
return self._cli_vars
@property
def node_name(self):
if self._node is not None:
return self._node.name
else:
return "<Configuration>"
def get_missing_var(self, var_name):
dct = {k: self._merged[k] for k in self._merged}
pretty_vars = json.dumps(dct, sort_keys=True, indent=4)
msg = self.UndefinedVarError.format(var_name, self.node_name, pretty_vars)
raise_compiler_error(msg, self._node)
def has_var(self, var_name: str):
return var_name in self._merged
def get_rendered_var(self, var_name):
raw = self._merged[var_name]
# if bool/int/float/etc are passed in, don't compile anything
if not isinstance(raw, str):
return raw
return get_rendered(raw, self._context)
def __call__(self, var_name, default=_VAR_NOTSET):
if self.has_var(var_name):
return self.get_rendered_var(var_name)
elif default is not self._VAR_NOTSET:
return default
else:
return self.get_missing_var(var_name)
class BaseContext(metaclass=ContextMeta):
def __init__(self, cli_vars):
self._ctx = {}
self.cli_vars = cli_vars
def generate_builtins(self):
builtins: Dict[str, Any] = {}
for key, value in self._context_members_.items():
if hasattr(value, "__get__"):
# handle properties, bound methods, etc
value = value.__get__(self)
builtins[key] = value
return builtins
# no dbtClassMixin so this is not an actual override
def to_dict(self):
self._ctx["context"] = self._ctx
builtins = self.generate_builtins()
self._ctx["builtins"] = builtins
self._ctx.update(builtins)
return self._ctx
@contextproperty
def dbt_version(self) -> str:
"""The `dbt_version` variable returns the installed version of dbt that
is currently running. It can be used for debugging or auditing
purposes.
> macros/get_version.sql
{% macro get_version() %}
{% set msg = "The installed version of dbt is: " ~ dbt_version %}
{% do log(msg, info=true) %}
{% endmacro %}
Example output:
$ dbt run-operation get_version
The installed version of dbt is 0.16.0
"""
return dbt_version
@contextproperty
def var(self) -> Var:
"""Variables can be passed from your `dbt_project.yml` file into models
during compilation. These variables are useful for configuring packages
for deployment in multiple environments, or defining values that should
be used across multiple models within a package.
To add a variable to a model, use the `var()` function:
> my_model.sql:
select * from events where event_type = '{{ var("event_type") }}'
If you try to run this model without supplying an `event_type`
variable, you'll receive a compilation error that looks like this:
Encountered an error:
! Compilation error while compiling model package_name.my_model:
! Required var 'event_type' not found in config:
Vars supplied to package_name.my_model = {
}
To supply a variable to a given model, add one or more `vars`
dictionaries to the `models` config in your `dbt_project.yml` file.
These `vars` are in-scope for all models at or below where they are
defined, so place them where they make the most sense. Below are three
different placements of the `vars` dict, all of which will make the
`my_model` model compile.
> dbt_project.yml:
# 1) scoped at the model level
models:
package_name:
my_model:
materialized: view
vars:
event_type: activation
# 2) scoped at the package level
models:
package_name:
vars:
event_type: activation
my_model:
materialized: view
# 3) scoped globally
models:
vars:
event_type: activation
package_name:
my_model:
materialized: view
## Variable default values
The `var()` function takes an optional second argument, `default`. If
this argument is provided, then it will be the default value for the
variable if one is not explicitly defined.
> my_model.sql:
-- Use 'activation' as the event_type if the variable is not
-- defined.
select *
from events
where event_type = '{{ var("event_type", "activation") }}'
"""
return Var(self._ctx, self.cli_vars)
@contextmember
@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.
"""
if var in os.environ:
return os.environ[var]
elif default is not None:
return default
else:
msg = f"Env var required but not provided: '{var}'"
undefined_error(msg)
if os.environ.get("DBT_MACRO_DEBUGGING"):
@contextmember
@staticmethod
def debug():
"""Enter a debugger at this line in the compiled jinja code."""
import sys
import ipdb # type: ignore
frame = sys._getframe(3)
ipdb.set_trace(frame)
return ""
@contextmember("return")
@staticmethod
def _return(data: Any) -> NoReturn:
"""The `return` function can be used in macros to return data to the
caller. The type of the data (`dict`, `list`, `int`, etc) will be
preserved through the return call.
:param data: The data to return to the caller
> macros/example.sql:
{% macro get_data() %}
{{ return([1,2,3]) }}
{% endmacro %}
> models/my_model.sql:
select
-- getdata() returns a list!
{% for i in getdata() %}
{{ i }}
{% if not loop.last %},{% endif %}
{% endfor %}
"""
raise MacroReturn(data)
@contextmember
@staticmethod
def fromjson(string: str, default: Any = None) -> Any:
"""The `fromjson` context method can be used to deserialize a json
string into a Python object primitive, eg. a `dict` or `list`.
:param value: The json string to deserialize
:param default: A default value to return if the `string` argument
cannot be deserialized (optional)
Usage:
{% set my_json_str = '{"abc": 123}' %}
{% set my_dict = fromjson(my_json_str) %}
{% do log(my_dict['abc']) %}
"""
try:
return json.loads(string)
except ValueError:
return default
@contextmember
@staticmethod
def tojson(value: Any, default: Any = None, sort_keys: bool = False) -> Any:
"""The `tojson` context method can be used to serialize a Python
object primitive, eg. a `dict` or `list` to a json string.
:param value: The value serialize to json
:param default: A default value to return if the `value` argument
cannot be serialized
:param sort_keys: If True, sort the keys.
Usage:
{% set my_dict = {"abc": 123} %}
{% set my_json_string = tojson(my_dict) %}
{% do log(my_json_string) %}
"""
try:
return json.dumps(value, sort_keys=sort_keys)
except ValueError:
return default
@contextmember
@staticmethod
def fromyaml(value: str, default: Any = None) -> Any:
"""The fromyaml context method can be used to deserialize a yaml string
into a Python object primitive, eg. a `dict` or `list`.
:param value: The yaml string to deserialize
:param default: A default value to return if the `string` argument
cannot be deserialized (optional)
Usage:
{% set my_yml_str -%}
dogs:
- good
- bad
{%- endset %}
{% set my_dict = fromyaml(my_yml_str) %}
{% do log(my_dict['dogs'], info=true) %}
-- ["good", "bad"]
{% do my_dict['dogs'].pop() }
{% do log(my_dict['dogs'], info=true) %}
-- ["good"]
"""
try:
return safe_load(value)
except (AttributeError, ValueError, yaml.YAMLError):
return default
# safe_dump defaults to sort_keys=True, but we act like json.dumps (the
# opposite)
@contextmember
@staticmethod
def toyaml(
value: Any, default: Optional[str] = None, sort_keys: bool = False
) -> Optional[str]:
"""The `tojson` context method can be used to serialize a Python
object primitive, eg. a `dict` or `list` to a yaml string.
:param value: The value serialize to yaml
:param default: A default value to return if the `value` argument
cannot be serialized
:param sort_keys: If True, sort the keys.
Usage:
{% set my_dict = {"abc": 123} %}
{% set my_yaml_string = toyaml(my_dict) %}
{% do log(my_yaml_string) %}
"""
try:
return yaml.safe_dump(data=value, sort_keys=sort_keys)
except (ValueError, yaml.YAMLError):
return default
@contextmember
@staticmethod
def log(msg: str, info: bool = False) -> str:
"""Logs a line to either the log file or stdout.
:param msg: The message to log
:param info: If `False`, write to the log file. If `True`, write to
both the log file and stdout.
> macros/my_log_macro.sql
{% macro some_macro(arg1, arg2) %}
{{ log("Running some_macro: " ~ arg1 ~ ", " ~ arg2) }}
{% endmacro %}"
"""
if info:
logger.info(msg)
else:
logger.debug(msg)
return ""
@contextproperty
def run_started_at(self) -> Optional[datetime.datetime]:
"""`run_started_at` outputs the timestamp that this run started, e.g.
`2017-04-21 01:23:45.678`. The `run_started_at` variable is a Python
`datetime` object. As of 0.9.1, the timezone of this variable defaults
to UTC.
> run_started_at_example.sql
select
'{{ run_started_at.strftime("%Y-%m-%d") }}' as date_day
from ...
To modify the timezone of this variable, use the the `pytz` module:
> run_started_at_utc.sql
{% set est = modules.pytz.timezone("America/New_York") %}
select
'{{ run_started_at.astimezone(est) }}' as run_started_est
from ...
"""
if tracking.active_user is not None:
return tracking.active_user.run_started_at
else:
return None
@contextproperty
def invocation_id(self) -> Optional[str]:
"""invocation_id outputs a UUID generated for this dbt run (useful for
auditing)
"""
if tracking.active_user is not None:
return tracking.active_user.invocation_id
else:
return None
@contextproperty
def modules(self) -> Dict[str, Any]:
"""The `modules` variable in the Jinja context contains useful Python
modules for operating on data.
# datetime
This variable is a pointer to the Python datetime module.
Usage:
{% set dt = modules.datetime.datetime.now() %}
# pytz
This variable is a pointer to the Python pytz module.
Usage:
{% set dt = modules.datetime.datetime(2002, 10, 27, 6, 0, 0) %}
{% set dt_local = modules.pytz.timezone('US/Eastern').localize(dt) %}
{{ dt_local }}
""" # noqa
return get_context_modules()
@contextproperty
def flags(self) -> Any:
"""The `flags` variable contains true/false values for flags provided
on the command line.
> flags.sql:
{% if flags.FULL_REFRESH %}
drop table ...
{% else %}
-- no-op
{% endif %}
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
def generate_base_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:
ctx = BaseContext(cli_vars)
# This is not a Mashumaro to_dict call
return ctx.to_dict()

View File

@@ -1,537 +0,0 @@
import json
import os
from typing import (
Any, Dict, NoReturn, Optional, Mapping
)
from dbt import flags
from dbt import tracking
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
from dbt.events.functions import fire_event
from dbt.events.types import MacroEventInfo, MacroEventDebug
from dbt.version import __version__ as dbt_version
# These modules are added to the context. Consider alternative
# approaches which will extend well to potentially many modules
import pytz
import datetime
import re
def get_pytz_module_context() -> Dict[str, Any]:
context_exports = pytz.__all__ # type: ignore
return {
name: getattr(pytz, name) for name in context_exports
}
def get_datetime_module_context() -> Dict[str, Any]:
context_exports = [
'date',
'datetime',
'time',
'timedelta',
'tzinfo'
]
return {
name: getattr(datetime, name) for name in context_exports
}
def get_re_module_context() -> Dict[str, Any]:
context_exports = re.__all__
return {
name: getattr(re, name) for name in context_exports
}
def get_context_modules() -> Dict[str, Dict[str, Any]]:
return {
'pytz': get_pytz_module_context(),
'datetime': get_datetime_module_context(),
're': get_re_module_context(),
}
class ContextMember:
def __init__(self, value, name=None):
self.name = name
self.inner = value
def key(self, default):
if self.name is None:
return default
return self.name
def contextmember(value):
if isinstance(value, str):
return lambda v: ContextMember(v, name=value)
return ContextMember(value)
def contextproperty(value):
if isinstance(value, str):
return lambda v: ContextMember(property(v), name=value)
return ContextMember(property(value))
class ContextMeta(type):
def __new__(mcls, name, bases, dct):
context_members = {}
context_attrs = {}
new_dct = {}
for base in bases:
context_members.update(getattr(base, '_context_members_', {}))
context_attrs.update(getattr(base, '_context_attrs_', {}))
for key, value in dct.items():
if isinstance(value, ContextMember):
context_key = value.key(key)
context_members[context_key] = value.inner
context_attrs[context_key] = key
value = value.inner
new_dct[key] = value
new_dct['_context_members_'] = context_members
new_dct['_context_attrs_'] = context_attrs
return type.__new__(mcls, name, bases, new_dct)
class Var:
UndefinedVarError = "Required var '{}' not found in config:\nVars "\
"supplied to {} = {}"
_VAR_NOTSET = object()
def __init__(
self,
context: Mapping[str, Any],
cli_vars: Mapping[str, Any],
node: Optional[CompiledResource] = None
) -> None:
self._context: Mapping[str, Any] = context
self._cli_vars: Mapping[str, Any] = cli_vars
self._node: Optional[CompiledResource] = node
self._merged: Mapping[str, Any] = self._generate_merged()
def _generate_merged(self) -> Mapping[str, Any]:
return self._cli_vars
@property
def node_name(self):
if self._node is not None:
return self._node.name
else:
return '<Configuration>'
def get_missing_var(self, var_name):
dct = {k: self._merged[k] for k in self._merged}
pretty_vars = json.dumps(dct, sort_keys=True, indent=4)
msg = self.UndefinedVarError.format(
var_name, self.node_name, pretty_vars
)
raise_compiler_error(msg, self._node)
def has_var(self, var_name: str):
return var_name in self._merged
def get_rendered_var(self, var_name):
raw = self._merged[var_name]
# if bool/int/float/etc are passed in, don't compile anything
if not isinstance(raw, str):
return raw
return get_rendered(raw, self._context)
def __call__(self, var_name, default=_VAR_NOTSET):
if self.has_var(var_name):
return self.get_rendered_var(var_name)
elif default is not self._VAR_NOTSET:
return default
else:
return self.get_missing_var(var_name)
class BaseContext(metaclass=ContextMeta):
def __init__(self, cli_vars):
self._ctx = {}
self.cli_vars = cli_vars
def generate_builtins(self):
builtins: Dict[str, Any] = {}
for key, value in self._context_members_.items():
if hasattr(value, '__get__'):
# handle properties, bound methods, etc
value = value.__get__(self)
builtins[key] = value
return builtins
# no dbtClassMixin so this is not an actual override
def to_dict(self):
self._ctx['context'] = self._ctx
builtins = self.generate_builtins()
self._ctx['builtins'] = builtins
self._ctx.update(builtins)
return self._ctx
@contextproperty
def dbt_version(self) -> str:
"""The `dbt_version` variable returns the installed version of dbt that
is currently running. It can be used for debugging or auditing
purposes.
> macros/get_version.sql
{% macro get_version() %}
{% set msg = "The installed version of dbt is: " ~ dbt_version %}
{% do log(msg, info=true) %}
{% endmacro %}
Example output:
$ dbt run-operation get_version
The installed version of dbt is 0.16.0
"""
return dbt_version
@contextproperty
def var(self) -> Var:
"""Variables can be passed from your `dbt_project.yml` file into models
during compilation. These variables are useful for configuring packages
for deployment in multiple environments, or defining values that should
be used across multiple models within a package.
To add a variable to a model, use the `var()` function:
> my_model.sql:
select * from events where event_type = '{{ var("event_type") }}'
If you try to run this model without supplying an `event_type`
variable, you'll receive a compilation error that looks like this:
Encountered an error:
! Compilation error while compiling model package_name.my_model:
! Required var 'event_type' not found in config:
Vars supplied to package_name.my_model = {
}
To supply a variable to a given model, add one or more `vars`
dictionaries to the `models` config in your `dbt_project.yml` file.
These `vars` are in-scope for all models at or below where they are
defined, so place them where they make the most sense. Below are three
different placements of the `vars` dict, all of which will make the
`my_model` model compile.
> dbt_project.yml:
# 1) scoped at the model level
models:
package_name:
my_model:
materialized: view
vars:
event_type: activation
# 2) scoped at the package level
models:
package_name:
vars:
event_type: activation
my_model:
materialized: view
# 3) scoped globally
models:
vars:
event_type: activation
package_name:
my_model:
materialized: view
## Variable default values
The `var()` function takes an optional second argument, `default`. If
this argument is provided, then it will be the default value for the
variable if one is not explicitly defined.
> my_model.sql:
-- Use 'activation' as the event_type if the variable is not
-- defined.
select *
from events
where event_type = '{{ var("event_type", "activation") }}'
"""
return Var(self._ctx, self.cli_vars)
@contextmember
@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.
"""
if var in os.environ:
return os.environ[var]
elif default is not None:
return default
else:
msg = f"Env var required but not provided: '{var}'"
undefined_error(msg)
if os.environ.get('DBT_MACRO_DEBUGGING'):
@contextmember
@staticmethod
def debug():
"""Enter a debugger at this line in the compiled jinja code."""
import sys
import ipdb # type: ignore
frame = sys._getframe(3)
ipdb.set_trace(frame)
return ''
@contextmember('return')
@staticmethod
def _return(data: Any) -> NoReturn:
"""The `return` function can be used in macros to return data to the
caller. The type of the data (`dict`, `list`, `int`, etc) will be
preserved through the return call.
:param data: The data to return to the caller
> macros/example.sql:
{% macro get_data() %}
{{ return([1,2,3]) }}
{% endmacro %}
> models/my_model.sql:
select
-- getdata() returns a list!
{% for i in getdata() %}
{{ i }}
{% if not loop.last %},{% endif %}
{% endfor %}
"""
raise MacroReturn(data)
@contextmember
@staticmethod
def fromjson(string: str, default: Any = None) -> Any:
"""The `fromjson` context method can be used to deserialize a json
string into a Python object primitive, eg. a `dict` or `list`.
:param value: The json string to deserialize
:param default: A default value to return if the `string` argument
cannot be deserialized (optional)
Usage:
{% set my_json_str = '{"abc": 123}' %}
{% set my_dict = fromjson(my_json_str) %}
{% do log(my_dict['abc']) %}
"""
try:
return json.loads(string)
except ValueError:
return default
@contextmember
@staticmethod
def tojson(
value: Any, default: Any = None, sort_keys: bool = False
) -> Any:
"""The `tojson` context method can be used to serialize a Python
object primitive, eg. a `dict` or `list` to a json string.
:param value: The value serialize to json
:param default: A default value to return if the `value` argument
cannot be serialized
:param sort_keys: If True, sort the keys.
Usage:
{% set my_dict = {"abc": 123} %}
{% set my_json_string = tojson(my_dict) %}
{% do log(my_json_string) %}
"""
try:
return json.dumps(value, sort_keys=sort_keys)
except ValueError:
return default
@contextmember
@staticmethod
def fromyaml(value: str, default: Any = None) -> Any:
"""The fromyaml context method can be used to deserialize a yaml string
into a Python object primitive, eg. a `dict` or `list`.
:param value: The yaml string to deserialize
:param default: A default value to return if the `string` argument
cannot be deserialized (optional)
Usage:
{% set my_yml_str -%}
dogs:
- good
- bad
{%- endset %}
{% set my_dict = fromyaml(my_yml_str) %}
{% do log(my_dict['dogs'], info=true) %}
-- ["good", "bad"]
{% do my_dict['dogs'].pop() }
{% do log(my_dict['dogs'], info=true) %}
-- ["good"]
"""
try:
return safe_load(value)
except (AttributeError, ValueError, yaml.YAMLError):
return default
# safe_dump defaults to sort_keys=True, but we act like json.dumps (the
# opposite)
@contextmember
@staticmethod
def toyaml(
value: Any, default: Optional[str] = None, sort_keys: bool = False
) -> Optional[str]:
"""The `tojson` context method can be used to serialize a Python
object primitive, eg. a `dict` or `list` to a yaml string.
:param value: The value serialize to yaml
:param default: A default value to return if the `value` argument
cannot be serialized
:param sort_keys: If True, sort the keys.
Usage:
{% set my_dict = {"abc": 123} %}
{% set my_yaml_string = toyaml(my_dict) %}
{% do log(my_yaml_string) %}
"""
try:
return yaml.safe_dump(data=value, sort_keys=sort_keys)
except (ValueError, yaml.YAMLError):
return default
@contextmember
@staticmethod
def log(msg: str, info: bool = False) -> str:
"""Logs a line to either the log file or stdout.
:param msg: The message to log
:param info: If `False`, write to the log file. If `True`, write to
both the log file and stdout.
> macros/my_log_macro.sql
{% macro some_macro(arg1, arg2) %}
{{ log("Running some_macro: " ~ arg1 ~ ", " ~ arg2) }}
{% endmacro %}"
"""
if info:
fire_event(MacroEventInfo(msg))
else:
fire_event(MacroEventDebug(msg))
return ''
@contextproperty
def run_started_at(self) -> Optional[datetime.datetime]:
"""`run_started_at` outputs the timestamp that this run started, e.g.
`2017-04-21 01:23:45.678`. The `run_started_at` variable is a Python
`datetime` object. As of 0.9.1, the timezone of this variable defaults
to UTC.
> run_started_at_example.sql
select
'{{ run_started_at.strftime("%Y-%m-%d") }}' as date_day
from ...
To modify the timezone of this variable, use the the `pytz` module:
> run_started_at_utc.sql
{% set est = modules.pytz.timezone("America/New_York") %}
select
'{{ run_started_at.astimezone(est) }}' as run_started_est
from ...
"""
if tracking.active_user is not None:
return tracking.active_user.run_started_at
else:
return None
@contextproperty
def invocation_id(self) -> Optional[str]:
"""invocation_id outputs a UUID generated for this dbt run (useful for
auditing)
"""
if tracking.active_user is not None:
return tracking.active_user.invocation_id
else:
return None
@contextproperty
def modules(self) -> Dict[str, Any]:
"""The `modules` variable in the Jinja context contains useful Python
modules for operating on data.
# datetime
This variable is a pointer to the Python datetime module.
Usage:
{% set dt = modules.datetime.datetime.now() %}
# pytz
This variable is a pointer to the Python pytz module.
Usage:
{% set dt = modules.datetime.datetime(2002, 10, 27, 6, 0, 0) %}
{% set dt_local = modules.pytz.timezone('US/Eastern').localize(dt) %}
{{ dt_local }}
""" # noqa
return get_context_modules()
@contextproperty
def flags(self) -> Any:
"""The `flags` variable contains true/false values for flags provided
on the command line.
> flags.sql:
{% if flags.FULL_REFRESH %}
drop table ...
{% else %}
-- 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
"""
return flags
def generate_base_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:
ctx = BaseContext(cli_vars)
# This is not a Mashumaro to_dict call
return ctx.to_dict()

View File

@@ -4,16 +4,14 @@ from dbt.contracts.connection import AdapterRequiredConfig
from dbt.node_types import NodeType
from dbt.utils import MultiDict
from dbt.context.base import contextproperty, Var
from dbt.context import contextproperty, Var
from dbt.context.target import TargetContext
class ConfiguredContext(TargetContext):
config: AdapterRequiredConfig
def __init__(
self, config: AdapterRequiredConfig
) -> None:
def __init__(self, config: AdapterRequiredConfig) -> None:
super().__init__(config, config.cli_vars)
@contextproperty
@@ -70,20 +68,7 @@ class SchemaYamlContext(ConfiguredContext):
@contextproperty
def var(self) -> ConfiguredVar:
return ConfiguredVar(
self._ctx, self.config, self._project_name
)
class MacroResolvingContext(ConfiguredContext):
def __init__(self, config):
super().__init__(config)
@contextproperty
def var(self) -> ConfiguredVar:
return ConfiguredVar(
self._ctx, self.config, self.config.project_name
)
return ConfiguredVar(self._ctx, self.config, self._project_name)
def generate_schema_yml(
@@ -91,10 +76,3 @@ def generate_schema_yml(
) -> Dict[str, Any]:
ctx = SchemaYamlContext(config, project_name)
return ctx.to_dict()
def generate_macro_context(
config: AdapterRequiredConfig,
) -> Dict[str, Any]:
ctx = MacroResolvingContext(config)
return ctx.to_dict()

View File

@@ -17,8 +17,8 @@ class ModelParts(IsFQNResource):
package_name: str
T = TypeVar('T') # any old type
C = TypeVar('C', bound=BaseConfig)
T = TypeVar("T") # any old type
C = TypeVar("C", bound=BaseConfig)
class ConfigSource:
@@ -36,15 +36,13 @@ class UnrenderedConfig(ConfigSource):
def get_config_dict(self, resource_type: NodeType) -> Dict[str, Any]:
unrendered = self.project.unrendered.project_dict
if resource_type == NodeType.Seed:
model_configs = unrendered.get('seeds')
model_configs = unrendered.get("seeds")
elif resource_type == NodeType.Snapshot:
model_configs = unrendered.get('snapshots')
model_configs = unrendered.get("snapshots")
elif resource_type == NodeType.Source:
model_configs = unrendered.get('sources')
elif resource_type == NodeType.Test:
model_configs = unrendered.get('tests')
model_configs = unrendered.get("sources")
else:
model_configs = unrendered.get('models')
model_configs = unrendered.get("models")
if model_configs is None:
return {}
@@ -63,8 +61,6 @@ class RenderedConfig(ConfigSource):
model_configs = self.project.snapshots
elif resource_type == NodeType.Source:
model_configs = self.project.sources
elif resource_type == NodeType.Test:
model_configs = self.project.tests
else:
model_configs = self.project.models
return model_configs
@@ -83,8 +79,8 @@ class BaseContextConfigGenerator(Generic[T]):
dependencies = self._active_project.load_dependencies()
if project_name not in dependencies:
raise InternalException(
f'Project name {project_name} not found in dependencies '
f'(found {list(dependencies)})'
f"Project name {project_name} not found in dependencies "
f"(found {list(dependencies)})"
)
return dependencies[project_name]
@@ -96,8 +92,8 @@ class BaseContextConfigGenerator(Generic[T]):
for level_config in fqn_search(model_configs, fqn):
result = {}
for key, value in level_config.items():
if key.startswith('+'):
result[key[1:].strip()] = deepcopy(value)
if key.startswith("+"):
result[key[1:]] = deepcopy(value)
elif not isinstance(value, dict):
result[key] = deepcopy(value)
@@ -120,12 +116,11 @@ class BaseContextConfigGenerator(Generic[T]):
def calculate_node_config(
self,
config_call_dict: Dict[str, Any],
config_calls: List[Dict[str, Any]],
fqn: List[str],
resource_type: NodeType,
project_name: str,
base: bool,
patch_config_dict: Dict[str, Any] = None
) -> BaseConfig:
own_config = self.get_node_project(project_name)
@@ -135,15 +130,8 @@ 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)
for config_call in config_calls:
result = self._update_from_config(result, config_call)
if own_config.project_name != self._active_project.project_name:
for fqn_config in self._active_project_configs(fqn, resource_type):
@@ -155,12 +143,11 @@ class BaseContextConfigGenerator(Generic[T]):
@abstractmethod
def calculate_node_config_dict(
self,
config_call_dict: Dict[str, Any],
config_calls: List[Dict[str, Any]],
fqn: List[str],
resource_type: NodeType,
project_name: str,
base: bool,
patch_config_dict: Dict[str, Any],
) -> Dict[str, Any]:
...
@@ -184,31 +171,25 @@ class ContextConfigGenerator(BaseContextConfigGenerator[C]):
def _update_from_config(
self, result: C, partial: Dict[str, Any], validate: bool = False
) -> C:
translated = self._active_project.credentials.translate_aliases(
partial
)
translated = self._active_project.credentials.translate_aliases(partial)
return result.update_from(
translated,
self._active_project.credentials.type,
validate=validate
translated, self._active_project.credentials.type, validate=validate
)
def calculate_node_config_dict(
self,
config_call_dict: Dict[str, Any],
config_calls: List[Dict[str, Any]],
fqn: List[str],
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,
config_calls=config_calls,
fqn=fqn,
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)
@@ -220,27 +201,21 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
def calculate_node_config_dict(
self,
config_call_dict: Dict[str, Any],
config_calls: List[Dict[str, Any]],
fqn: List[str],
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,
config_calls=config_calls,
fqn=fqn,
resource_type=resource_type,
project_name=project_name,
base=base,
patch_config_dict=patch_config_dict
)
def initial_result(
self,
resource_type: NodeType,
base: bool
) -> Dict[str, Any]:
def initial_result(self, resource_type: NodeType, base: bool) -> Dict[str, Any]:
return {}
def _update_from_config(
@@ -249,9 +224,7 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
partial: Dict[str, Any],
validate: bool = False,
) -> Dict[str, Any]:
translated = self._active_project.credentials.translate_aliases(
partial
)
translated = self._active_project.credentials.translate_aliases(partial)
result.update(translated)
return result
@@ -264,39 +237,20 @@ class ContextConfig:
resource_type: NodeType,
project_name: str,
) -> None:
self._config_call_dict: Dict[str, Any] = {}
self._config_calls: List[Dict[str, Any]] = []
self._active_project = active_project
self._fqn = fqn
self._resource_type = resource_type
self._project_name = project_name
def add_config_call(self, opts: Dict[str, Any]) -> None:
dct = self._config_call_dict
self._add_config_call(dct, opts)
@classmethod
def _add_config_call(cls, config_call_dict, opts: Dict[str, Any]) -> None:
for k, v in opts.items():
# MergeBehavior for post-hook and pre-hook is to collect all
# values, instead of overwriting
if k in BaseConfig.mergebehavior['append']:
if not isinstance(v, list):
v = [v]
if k in BaseConfig.mergebehavior['update'] and not isinstance(v, dict):
raise InternalException(f'expected dict, got {v}')
if k in config_call_dict and isinstance(config_call_dict[k], list):
config_call_dict[k].extend(v)
elif k in config_call_dict and isinstance(config_call_dict[k], dict):
config_call_dict[k].update(v)
else:
config_call_dict[k] = v
def update_in_model_config(self, opts: Dict[str, Any]) -> None:
self._config_calls.append(opts)
def build_config_dict(
self,
base: bool = False,
*,
rendered: bool = True,
patch_config_dict: dict = None
) -> Dict[str, Any]:
if rendered:
src = ContextConfigGenerator(self._active_project)
@@ -304,10 +258,9 @@ class ContextConfig:
src = UnrenderedConfigGenerator(self._active_project)
return src.calculate_node_config_dict(
config_call_dict=self._config_call_dict,
config_calls=self._config_calls,
fqn=self._fqn,
resource_type=self._resource_type,
project_name=self._project_name,
base=base,
patch_config_dict=patch_config_dict
)

View File

@@ -1,6 +1,4 @@
from typing import (
Any, Dict, Union
)
from typing import Any, Dict, Union
from dbt.exceptions import (
doc_invalid_args,
@@ -11,7 +9,7 @@ from dbt.contracts.graph.compiled import CompileResultNode
from dbt.contracts.graph.manifest import Manifest
from dbt.contracts.graph.parsed import ParsedMacro
from dbt.context.base import contextmember
from dbt.context import contextmember
from dbt.context.configured import SchemaYamlContext
@@ -57,19 +55,14 @@ class DocsRuntimeContext(SchemaYamlContext):
else:
doc_invalid_args(self.node, args)
# ParsedDocumentation
target_doc = self.manifest.resolve_doc(
doc_name,
doc_package_name,
self._project_name,
self.node.package_name,
)
if target_doc:
file_id = target_doc.file_id
if file_id in self.manifest.files:
source_file = self.manifest.files[file_id]
source_file.add_node(self.node.unique_id)
else:
if target_doc is None:
doc_target_not_found(self.node, doc_name, doc_package_name)
return target_doc.block_contents

View File

@@ -1,6 +1,4 @@
from typing import (
Dict, MutableMapping, Optional
)
from typing import Dict, MutableMapping, Optional
from dbt.contracts.graph.parsed import ParsedMacro
from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
@@ -14,12 +12,8 @@ MacroNamespace = Dict[str, ParsedMacro]
# so that higher precedence macros are found first.
# This functionality is also provided by the MacroNamespace,
# but the intention is to eventually replace that class.
# This enables us to get the macro unique_id without
# This enables us to get the macor unique_id without
# processing every macro in the project.
# Note: the root project macros override everything in the
# dbt internal projects. External projects (dependencies) will
# use their own macros first, then pull from the root project
# followed by dbt internal projects.
class MacroResolver:
def __init__(
self,
@@ -49,32 +43,20 @@ class MacroResolver:
for pkg in reversed(self.internal_package_names):
if pkg in self.internal_packages:
# Turn the internal packages into a flat namespace
self.internal_packages_namespace.update(
self.internal_packages[pkg])
self.internal_packages_namespace.update(self.internal_packages[pkg])
# search order:
# local_namespace (package of particular node), not including
# the internal packages or the root package
# This means that within an extra package, it uses its own macros
# root package namespace
# non-internal packages (that aren't local or root)
# dbt internal packages
def _build_macros_by_name(self):
macros_by_name = {}
# all internal packages (already in the right order)
for macro in self.internal_packages_namespace.values():
# search root package macros
for macro in self.root_package_macros.values():
macros_by_name[macro.name] = macro
# non-internal packages
# search miscellaneous non-internal packages
for fnamespace in self.packages.values():
for macro in fnamespace.values():
macros_by_name[macro.name] = macro
# root package macros
for macro in self.root_package_macros.values():
# search all internal packages
for macro in self.internal_packages_namespace.values():
macros_by_name[macro.name] = macro
self.macros_by_name = macros_by_name
def _add_macro_to(
@@ -89,9 +71,7 @@ class MacroResolver:
package_namespaces[macro.package_name] = namespace
if macro.name in namespace:
raise_duplicate_macro_name(
macro, macro, macro.package_name
)
raise_duplicate_macro_name(macro, macro, macro.package_name)
package_namespaces[macro.package_name][macro.name] = macro
def add_macro(self, macro: ParsedMacro):
@@ -112,26 +92,20 @@ class MacroResolver:
for macro in self.macros.values():
self.add_macro(macro)
def get_macro(self, local_package, macro_name):
def get_macro_id(self, local_package, macro_name):
local_package_macros = {}
if (local_package not in self.internal_package_names and
local_package in self.packages):
if (
local_package not in self.internal_package_names
and local_package in self.packages
):
local_package_macros = self.packages[local_package]
# First: search the local packages for this macro
if macro_name in local_package_macros:
return local_package_macros[macro_name]
# Now look up in the standard search order
return local_package_macros[macro_name].unique_id
if macro_name in self.macros_by_name:
return self.macros_by_name[macro_name]
return self.macros_by_name[macro_name].unique_id
return None
def get_macro_id(self, local_package, macro_name):
macro = self.get_macro(local_package, macro_name)
if macro is None:
return None
else:
return macro.unique_id
# Currently this is just used by test processing in the schema
# parser (in connection with the MacroResolver). Future work
@@ -140,42 +114,22 @@ class MacroResolver:
# is that you can limit the number of macros provided to the
# context dictionary in the 'to_dict' manifest method.
class TestMacroNamespace:
def __init__(
self, macro_resolver, ctx, node, thread_ctx, depends_on_macros
):
def __init__(self, macro_resolver, ctx, node, thread_ctx, depends_on_macros):
self.macro_resolver = macro_resolver
self.ctx = ctx
self.node = node # can be none
self.node = node
self.thread_ctx = thread_ctx
self.local_namespace = {}
self.project_namespace = {}
local_namespace = {}
if depends_on_macros:
dep_macros = []
self.recursively_get_depends_on_macros(depends_on_macros, dep_macros)
for macro_unique_id in dep_macros:
if macro_unique_id in self.macro_resolver.macros:
# Split up the macro unique_id to get the project_name
(_, project_name, macro_name) = macro_unique_id.split('.')
# Save the plain macro_name in the local_namespace
macro = self.macro_resolver.macros[macro_unique_id]
macro_gen = MacroGenerator(
macro, self.ctx, self.node, self.thread_ctx,
)
self.local_namespace[macro_name] = macro_gen
# We also need the two part macro name
if project_name not in self.project_namespace:
self.project_namespace[project_name] = {}
self.project_namespace[project_name][macro_name] = macro_gen
def recursively_get_depends_on_macros(self, depends_on_macros, dep_macros):
for macro_unique_id in depends_on_macros:
if macro_unique_id in dep_macros:
continue
dep_macros.append(macro_unique_id)
if macro_unique_id in self.macro_resolver.macros:
macro = self.macro_resolver.macros[macro_unique_id]
if macro.depends_on.macros:
self.recursively_get_depends_on_macros(macro.depends_on.macros, dep_macros)
for macro_unique_id in depends_on_macros:
macro = self.manifest.macros[macro_unique_id]
local_namespace[macro.name] = MacroGenerator(
macro,
self.ctx,
self.node,
self.thread_ctx,
)
self.local_namespace = local_namespace
def get_from_package(
self, package_name: Optional[str], name: str
@@ -185,15 +139,9 @@ class TestMacroNamespace:
macro = self.macro_resolver.macros_by_name.get(name)
elif package_name == GLOBAL_PROJECT_NAME:
macro = self.macro_resolver.internal_packages_namespace.get(name)
elif package_name in self.macro_resolver.packages:
elif package_name in self.resolver.packages:
macro = self.macro_resolver.packages[package_name].get(name)
else:
raise_compiler_error(
f"Could not find package '{package_name}'"
)
if not macro:
return None
macro_func = MacroGenerator(
macro, self.ctx, self.node, self.thread_ctx
)
raise_compiler_error(f"Could not find package '{package_name}'")
macro_func = MacroGenerator(macro, self.ctx, self.node, self.thread_ctx)
return macro_func

View File

@@ -1,13 +1,9 @@
from typing import (
Any, Dict, Iterable, Union, Optional, List, Iterator, Mapping, Set
)
from typing import Any, Dict, Iterable, Union, Optional, List, Iterator, Mapping, Set
from dbt.clients.jinja import MacroGenerator, MacroStack
from dbt.contracts.graph.parsed import ParsedMacro
from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
from dbt.exceptions import (
raise_duplicate_macro_name, raise_compiler_error
)
from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
FlatNamespace = Dict[str, MacroGenerator]
@@ -19,17 +15,13 @@ FullNamespace = Dict[str, NamespaceMember]
# and provide the ability to flatten them into the ManifestContexts
# that are created for jinja, so that macro calls can be resolved.
# Creates special iterators and _keys methods to flatten the lists.
# When this class is created it has a static 'local_namespace' which
# depends on the package of the node, so it only works for one
# particular local package at a time for "flattening" into a context.
# 'get_by_package' should work for any macro.
class MacroNamespace(Mapping):
def __init__(
self,
global_namespace: FlatNamespace, # root package macros
local_namespace: FlatNamespace, # packages for *this* node
global_project_namespace: FlatNamespace, # internal packages
packages: Dict[str, FlatNamespace], # non-internal packages
global_namespace: FlatNamespace,
local_namespace: FlatNamespace,
global_project_namespace: FlatNamespace,
packages: Dict[str, FlatNamespace],
):
self.global_namespace: FlatNamespace = global_namespace
self.local_namespace: FlatNamespace = local_namespace
@@ -37,13 +29,13 @@ class MacroNamespace(Mapping):
self.global_project_namespace: FlatNamespace = global_project_namespace
def _search_order(self) -> Iterable[Union[FullNamespace, FlatNamespace]]:
yield self.local_namespace # local package
yield self.global_namespace # root package
yield self.packages # non-internal packages
yield self.local_namespace
yield self.global_namespace
yield self.packages
yield {
GLOBAL_PROJECT_NAME: self.global_project_namespace, # dbt
GLOBAL_PROJECT_NAME: self.global_project_namespace,
}
yield self.global_project_namespace # other internal project besides dbt
yield self.global_project_namespace
# provides special keys method for MacroNamespace iterator
# returns keys from local_namespace, global_namespace, packages,
@@ -79,9 +71,7 @@ class MacroNamespace(Mapping):
elif package_name in self.packages:
return self.packages[package_name].get(name)
else:
raise_compiler_error(
f"Could not find package '{package_name}'"
)
raise_compiler_error(f"Could not find package '{package_name}'")
# This class builds the MacroNamespace by adding macros to
@@ -102,9 +92,7 @@ class MacroNamespaceBuilder:
# internal packages comes from get_adapter_package_names
self.internal_package_names = set(internal_packages)
self.internal_package_names_order = internal_packages
# macro_func is added here if in root package, since
# the root package acts as a "global" namespace, overriding
# everything else except local external package macro calls
# macro_func is added here if in root package
self.globals: FlatNamespace = {}
# macro_func is added here if it's the package for this node
self.locals: FlatNamespace = {}
@@ -128,9 +116,7 @@ class MacroNamespaceBuilder:
hierarchy[macro.package_name] = namespace
if macro.name in namespace:
raise_duplicate_macro_name(
macro_func.macro, macro, macro.package_name
)
raise_duplicate_macro_name(macro_func.macro, macro, macro.package_name)
hierarchy[macro.package_name][macro.name] = macro_func
def add_macro(self, macro: ParsedMacro, ctx: Dict[str, Any]):
@@ -175,8 +161,8 @@ class MacroNamespaceBuilder:
global_project_namespace.update(self.internal_packages[pkg])
return MacroNamespace(
global_namespace=self.globals, # root package macros
local_namespace=self.locals, # packages for *this* node
global_project_namespace=global_project_namespace, # internal packages
packages=self.packages, # non internal_packages
global_namespace=self.globals,
local_namespace=self.locals,
global_project_namespace=global_project_namespace,
packages=self.packages,
)

View File

@@ -2,7 +2,7 @@ from typing import List
from dbt.clients.jinja import MacroStack
from dbt.contracts.connection import AdapterRequiredConfig
from dbt.contracts.graph.manifest import Manifest
from dbt.contracts.graph.manifest import Manifest, AnyManifest
from dbt.context.macro_resolver import TestMacroNamespace
@@ -17,10 +17,11 @@ 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.
"""
def __init__(
self,
config: AdapterRequiredConfig,
manifest: Manifest,
manifest: AnyManifest,
search_package: str,
) -> None:
super().__init__(config)
@@ -37,13 +38,12 @@ class ManifestContext(ConfiguredContext):
# this takes all the macros in the manifest and adds them
# to the MacroNamespaceBuilder stored in self.namespace
builder = self._get_namespace_builder()
return builder.build_namespace(
self.manifest.macros.values(), self._ctx
)
return builder.build_namespace(self.manifest.macros.values(), self._ctx)
def _get_namespace_builder(self) -> MacroNamespaceBuilder:
# avoid an import loop
from dbt.adapters.factory import get_adapter_package_names
internal_packages: List[str] = get_adapter_package_names(
self.config.credentials.type
)
@@ -62,21 +62,16 @@ class ManifestContext(ConfiguredContext):
# keys in the manifest dictionary
if isinstance(self.namespace, TestMacroNamespace):
dct.update(self.namespace.local_namespace)
dct.update(self.namespace.project_namespace)
else:
dct.update(self.namespace)
return dct
class QueryHeaderContext(ManifestContext):
def __init__(
self, config: AdapterRequiredConfig, manifest: Manifest
) -> None:
def __init__(self, config: AdapterRequiredConfig, manifest: Manifest) -> None:
super().__init__(config, manifest, config.project_name)
def generate_query_header_context(
config: AdapterRequiredConfig, manifest: Manifest
):
def generate_query_header_context(config: AdapterRequiredConfig, manifest: Manifest):
ctx = QueryHeaderContext(config, manifest)
return ctx.to_dict()

View File

@@ -1,28 +1,33 @@
import abc
import os
from typing import (
Callable, Any, Dict, Optional, Union, List, TypeVar, Type, Iterable,
Callable,
Any,
Dict,
Optional,
Union,
List,
TypeVar,
Type,
Iterable,
Mapping,
)
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
)
from dbt.adapters.factory import get_adapter, get_adapter_package_names
from dbt.clients import agate_helper
from dbt.clients.jinja import get_rendered, MacroGenerator, MacroStack
from dbt.config import RuntimeConfig, Project
from .base import contextmember, contextproperty, Var
from dbt.context import contextmember, contextproperty, Var
from .configured import FQNLookup
from .context_config import ContextConfig
from dbt.context.macro_resolver import MacroResolver, TestMacroNamespace
from .macros import MacroNamespaceBuilder, MacroNamespace
from .manifest import ManifestContext
from dbt.contracts.connection import AdapterResponse
from dbt.contracts.graph.manifest import (
Manifest, Disabled
)
from dbt.contracts.graph.manifest import Manifest, AnyManifest, Disabled, MacroManifest
from dbt.contracts.graph.compiled import (
CompiledResource,
CompiledSeedNode,
@@ -39,7 +44,6 @@ from dbt.exceptions import (
InternalException,
ValidationException,
RuntimeException,
macro_invalid_dispatch_arg,
missing_config,
raise_compiler_error,
ref_invalid_args,
@@ -49,11 +53,10 @@ from dbt.exceptions import (
wrapped_exports,
)
from dbt.config import IsFQNResource
from dbt.logger import GLOBAL_LOGGER as logger # noqa
from dbt.node_types import NodeType
from dbt.utils import (
merge, AttrDict, MultiDict
)
from dbt.utils import merge, AttrDict, MultiDict
import agate
@@ -76,9 +79,8 @@ class RelationProxy:
return self._relation_type.create_from_source(*args, **kwargs)
def create(self, *args, **kwargs):
kwargs['quote_policy'] = merge(
self._quoting_config,
kwargs.pop('quote_policy', {})
kwargs["quote_policy"] = merge(
self._quoting_config, kwargs.pop("quote_policy", {})
)
return self._relation_type.create(*args, **kwargs)
@@ -95,7 +97,7 @@ class BaseDatabaseWrapper:
self._namespace = namespace
def __getattr__(self, name):
raise NotImplementedError('subclasses need to implement this')
raise NotImplementedError("subclasses need to implement this")
@property
def config(self):
@@ -108,73 +110,59 @@ class BaseDatabaseWrapper:
return self._adapter.commit_if_has_connection()
def _get_adapter_macro_prefixes(self) -> List[str]:
# order matters for dispatch:
# 1. current adapter
# 2. any parent adapters (dependencies)
# 3. 'default'
search_prefixes = get_adapter_type_names(self._adapter.type()) + ['default']
# a future version of this could have plugins automatically call fall
# back to their dependencies' dependencies by using
# `get_adapter_type_names` instead of `[self.config.credentials.type]`
search_prefixes = [self._adapter.type(), "default"]
return search_prefixes
def dispatch(
self,
macro_name: str,
macro_namespace: Optional[str] = None,
packages: Optional[List[str]] = None, # eventually remove since it's fully deprecated
self, macro_name: str, 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)
if "." in macro_name:
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)
namespace = macro_namespace
if namespace is None:
if packages 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]
else:
# Not a string and not None so must be a list
elif isinstance(packages, str):
raise CompilationException(
f'In adapter.dispatch, got a list macro_namespace argument '
f'("{macro_namespace}"), but macro_namespace should be None or a string.'
f"In adapter.dispatch, got a string packages argument "
f'("{packages}"), but packages should be None or a list.'
)
else:
search_packages = packages
attempts = []
for package_name in search_packages:
for prefix in self._get_adapter_macro_prefixes():
search_name = f'{prefix}__{macro_name}'
search_name = f"{prefix}__{macro_name}"
try:
# this uses the namespace from the context
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
macro = self._namespace.get_from_package(package_name, search_name)
except CompilationException as exc:
raise CompilationException(
f"In dispatch: {exc.msg}",
) from exc
if package_name is None:
attempts.append(search_name)
else:
attempts.append(f'{package_name}.{search_name}')
attempts.append(f"{package_name}.{search_name}")
if macro is not None:
return macro
searched = ', '.join(repr(a) for a in attempts)
searched = ", ".join(repr(a) for a in attempts)
msg = (
f"In dispatch: No macro named '{macro_name}' found\n"
f" Searched for: {searched}"
@@ -204,14 +192,10 @@ class BaseResolver(metaclass=abc.ABCMeta):
class BaseRefResolver(BaseResolver):
@abc.abstractmethod
def resolve(
self, name: str, package: Optional[str] = None
) -> RelationProxy:
def resolve(self, name: str, package: Optional[str] = None) -> RelationProxy:
...
def _repack_args(
self, name: str, package: Optional[str]
) -> List[str]:
def _repack_args(self, name: str, package: Optional[str]) -> List[str]:
if package is None:
return [name]
else:
@@ -220,14 +204,13 @@ class BaseRefResolver(BaseResolver):
def validate_args(self, name: str, package: Optional[str]):
if not isinstance(name, str):
raise CompilationException(
f'The name argument to ref() must be a string, got '
f'{type(name)}'
f"The name argument to ref() must be a string, got " f"{type(name)}"
)
if package is not None and not isinstance(package, str):
raise CompilationException(
f'The package argument to ref() must be a string or None, got '
f'{type(package)}'
f"The package argument to ref() must be a string or None, got "
f"{type(package)}"
)
def __call__(self, *args: str) -> RelationProxy:
@@ -252,20 +235,19 @@ class BaseSourceResolver(BaseResolver):
def validate_args(self, source_name: str, table_name: str):
if not isinstance(source_name, str):
raise CompilationException(
f'The source name (first) argument to source() must be a '
f'string, got {type(source_name)}'
f"The source name (first) argument to source() must be a "
f"string, got {type(source_name)}"
)
if not isinstance(table_name, str):
raise CompilationException(
f'The table name (second) argument to source() must be a '
f'string, got {type(table_name)}'
f"The table name (second) argument to source() must be a "
f"string, got {type(table_name)}"
)
def __call__(self, *args: str) -> RelationProxy:
if len(args) != 2:
raise_compiler_error(
f"source() takes exactly two arguments ({len(args)} given)",
self.model
f"source() takes exactly two arguments ({len(args)} given)", self.model
)
self.validate_args(args[0], args[1])
return self.resolve(args[0], args[1])
@@ -276,21 +258,22 @@ class Config(Protocol):
...
# Implementation of "config(..)" calls in models
# `config` implementations
class ParseConfigObject(Config):
def __init__(self, model, context_config: Optional[ContextConfig]):
self.model = model
self.context_config = context_config
def _transform_config(self, config):
for oldkey in ('pre_hook', 'post_hook'):
for oldkey in ("pre_hook", "post_hook"):
if oldkey in config:
newkey = oldkey.replace('_', '-')
newkey = oldkey.replace("_", "-")
if newkey in config:
raise_compiler_error(
'Invalid config, has conflicting keys "{}" and "{}"'
.format(oldkey, newkey),
self.model
'Invalid config, has conflicting keys "{}" and "{}"'.format(
oldkey, newkey
),
self.model,
)
config[newkey] = config.pop(oldkey)
return config
@@ -301,29 +284,25 @@ class ParseConfigObject(Config):
elif len(args) == 0 and len(kwargs) > 0:
opts = kwargs
else:
raise_compiler_error(
"Invalid inline model config",
self.model)
raise_compiler_error("Invalid inline model config", self.model)
opts = self._transform_config(opts)
# it's ok to have a parse context with no context config, but you must
# not call it!
if self.context_config is None:
raise RuntimeException(
'At parse time, did not receive a context config'
)
self.context_config.add_config_call(opts)
return ''
raise RuntimeException("At parse time, did not receive a context config")
self.context_config.update_in_model_config(opts)
return ""
def set(self, name, value):
return self.__call__({name: value})
def require(self, name, validator=None):
return ''
return ""
def get(self, name, validator=None, default=None):
return ''
return ""
def persist_relation_docs(self) -> bool:
return False
@@ -333,14 +312,12 @@ class ParseConfigObject(Config):
class RuntimeConfigObject(Config):
def __init__(
self, model, context_config: Optional[ContextConfig] = None
):
def __init__(self, model, context_config: Optional[ContextConfig] = None):
self.model = model
# we never use or get a config, only the parser cares
def __call__(self, *args, **kwargs):
return ''
return ""
def set(self, name, value):
return self.__call__({name: value})
@@ -350,7 +327,7 @@ class RuntimeConfigObject(Config):
def _lookup(self, name, default=_MISSING):
# if this is a macro, there might be no `model.config`.
if not hasattr(self.model, 'config'):
if not hasattr(self.model, "config"):
result = default
else:
result = self.model.config.get(name, default)
@@ -375,22 +352,24 @@ class RuntimeConfigObject(Config):
return to_return
def persist_relation_docs(self) -> bool:
persist_docs = self.get('persist_docs', default={})
persist_docs = self.get("persist_docs", default={})
if not isinstance(persist_docs, dict):
raise_compiler_error(
f"Invalid value provided for 'persist_docs'. Expected dict "
f"but received {type(persist_docs)}")
f"but received {type(persist_docs)}"
)
return persist_docs.get('relation', False)
return persist_docs.get("relation", False)
def persist_column_docs(self) -> bool:
persist_docs = self.get('persist_docs', default={})
persist_docs = self.get("persist_docs", default={})
if not isinstance(persist_docs, dict):
raise_compiler_error(
f"Invalid value provided for 'persist_docs'. Expected dict "
f"but received {type(persist_docs)}")
f"but received {type(persist_docs)}"
)
return persist_docs.get('columns', False)
return persist_docs.get("columns", False)
# `adapter` implementations
@@ -400,8 +379,10 @@ class ParseDatabaseWrapper(BaseDatabaseWrapper):
"""
def __getattr__(self, name):
override = (name in self._adapter._available_ and
name in self._adapter._parse_replacements_)
override = (
name in self._adapter._available_
and name in self._adapter._parse_replacements_
)
if override:
return self._adapter._parse_replacements_[name]
@@ -433,9 +414,7 @@ class RuntimeDatabaseWrapper(BaseDatabaseWrapper):
# `ref` implementations
class ParseRefResolver(BaseRefResolver):
def resolve(
self, name: str, package: Optional[str] = None
) -> RelationProxy:
def resolve(self, name: str, package: Optional[str] = None) -> RelationProxy:
self.model.refs.append(self._repack_args(name, package))
return self.Relation.create_from(self.config, self.model)
@@ -465,22 +444,15 @@ class RuntimeRefResolver(BaseRefResolver):
self.validate(target_model, target_name, target_package)
return self.create_relation(target_model, target_name)
def create_relation(
self, target_model: ManifestNode, name: str
) -> RelationProxy:
def create_relation(self, target_model: ManifestNode, name: str) -> RelationProxy:
if target_model.is_ephemeral_model:
self.model.set_cte(target_model.unique_id, None)
return self.Relation.create_ephemeral_from_node(
self.config, target_model
)
return self.Relation.create_ephemeral_from_node(self.config, target_model)
else:
return self.Relation.create_from(self.config, target_model)
def validate(
self,
resolved: ManifestNode,
target_name: str,
target_package: Optional[str]
self, resolved: ManifestNode, target_name: str, target_package: Optional[str]
) -> None:
if resolved.unique_id not in self.model.depends_on.nodes:
args = self._repack_args(target_name, target_package)
@@ -496,16 +468,15 @@ class OperationRefResolver(RuntimeRefResolver):
) -> None:
pass
def create_relation(
self, target_model: ManifestNode, name: str
) -> RelationProxy:
def create_relation(self, target_model: ManifestNode, name: str) -> RelationProxy:
if target_model.is_ephemeral_model:
# In operations, we can't ref() ephemeral nodes, because
# ParsedMacros do not support set_cte
raise_compiler_error(
'Operations can not ref() ephemeral nodes, but {} is ephemeral'
.format(target_model.name),
self.model
"Operations can not ref() ephemeral nodes, but {} is ephemeral".format(
target_model.name
),
self.model,
)
else:
return super().create_relation(target_model, name)
@@ -557,8 +528,7 @@ class ModelConfiguredVar(Var):
if package_name not in dependencies:
# I don't think this is actually reachable
raise_compiler_error(
f'Node package named {package_name} not found!',
self._node
f"Node package named {package_name} not found!", self._node
)
yield dependencies[package_name]
yield self._config
@@ -630,7 +600,7 @@ class OperationProvider(RuntimeProvider):
ref = OperationRefResolver
T = TypeVar('T')
T = TypeVar("T")
# Base context collection, used for parsing configs.
@@ -644,9 +614,7 @@ class ProviderContext(ManifestContext):
context_config: Optional[ContextConfig],
) -> None:
if provider is None:
raise InternalException(
f"Invalid provider given to context: {provider}"
)
raise InternalException(f"Invalid provider given to context: {provider}")
# mypy appeasement - we know it'll be a RuntimeConfig
self.config: RuntimeConfig
self.model: Union[ParsedMacro, ManifestNode] = model
@@ -656,16 +624,12 @@ class ProviderContext(ManifestContext):
self.provider: Provider = provider
self.adapter = get_adapter(self.config)
# The macro namespace is used in creating the DatabaseWrapper
self.db_wrapper = self.provider.DatabaseWrapper(
self.adapter, self.namespace
)
self.db_wrapper = self.provider.DatabaseWrapper(self.adapter, self.namespace)
# This overrides the method in ManifestContext, and provides
# a model, which the ManifestContext builder does not
def _get_namespace_builder(self):
internal_packages = get_adapter_package_names(
self.config.credentials.type
)
internal_packages = get_adapter_package_names(self.config.credentials.type)
return MacroNamespaceBuilder(
self.config.project_name,
self.search_package,
@@ -684,19 +648,19 @@ class ProviderContext(ManifestContext):
@contextmember
def store_result(
self, name: str,
response: Any,
agate_table: Optional[agate.Table] = None
self, name: str, response: Any, agate_table: Optional[agate.Table] = None
) -> str:
if agate_table is None:
agate_table = agate_helper.empty_table()
self.sql_results[name] = AttrDict({
'response': response,
'data': agate_helper.as_matrix(agate_table),
'table': agate_table
})
return ''
self.sql_results[name] = AttrDict(
{
"response": response,
"data": agate_helper.as_matrix(agate_table),
"table": agate_table,
}
)
return ""
@contextmember
def store_raw_result(
@@ -705,10 +669,11 @@ class ProviderContext(ManifestContext):
message=Optional[str],
code=Optional[str],
rows_affected=Optional[str],
agate_table: Optional[agate.Table] = None
agate_table: Optional[agate.Table] = None,
) -> str:
response = AdapterResponse(
_message=message, code=code, rows_affected=rows_affected)
_message=message, code=code, rows_affected=rows_affected
)
return self.store_result(name, response, agate_table)
@contextproperty
@@ -721,25 +686,28 @@ class ProviderContext(ManifestContext):
elif value == arg:
return
raise ValidationException(
'Expected value "{}" to be one of {}'
.format(value, ','.join(map(str, args))))
'Expected value "{}" to be one of {}'.format(
value, ",".join(map(str, args))
)
)
return inner
return AttrDict({
'any': validate_any,
})
return AttrDict(
{
"any": validate_any,
}
)
@contextmember
def write(self, payload: str) -> str:
# macros/source defs aren't 'writeable'.
if isinstance(self.model, (ParsedMacro, ParsedSourceDefinition)):
raise_compiler_error(
'cannot "write" macros or sources'
)
raise_compiler_error('cannot "write" macros or sources')
self.model.build_path = self.model.write_node(
self.config.target_path, 'run', payload
self.config.target_path, "run", payload
)
return ''
return ""
@contextmember
def render(self, string: str) -> str:
@@ -752,20 +720,17 @@ class ProviderContext(ManifestContext):
try:
return func(*args, **kwargs)
except Exception:
raise_compiler_error(
message_if_exception, self.model
)
raise_compiler_error(message_if_exception, self.model)
@contextmember
def load_agate_table(self) -> agate.Table:
if not isinstance(self.model, (ParsedSeedNode, CompiledSeedNode)):
raise_compiler_error(
'can only load_agate_table for seeds (got a {})'
.format(self.model.resource_type)
"can only load_agate_table for seeds (got a {})".format(
self.model.resource_type
)
)
path = os.path.join(
self.model.root_path, self.model.original_file_path
)
path = os.path.join(self.model.root_path, self.model.original_file_path)
column_types = self.model.config.column_types
try:
table = agate_helper.from_csv(path, text_columns=column_types)
@@ -823,7 +788,7 @@ class ProviderContext(ManifestContext):
self.db_wrapper, self.model, self.config, self.manifest
)
@contextproperty('config')
@contextproperty("config")
def ctx_config(self) -> Config:
"""The `config` variable exists to handle end-user configuration for
custom materializations. Configs like `unique_key` can be implemented
@@ -995,7 +960,7 @@ class ProviderContext(ManifestContext):
node=self.model,
)
@contextproperty('adapter')
@contextproperty("adapter")
def ctx_adapter(self) -> BaseDatabaseWrapper:
"""`adapter` is a wrapper around the internal database adapter used by
dbt. It allows users to make calls to the database in their dbt models.
@@ -1007,8 +972,8 @@ class ProviderContext(ManifestContext):
@contextproperty
def api(self) -> Dict[str, Any]:
return {
'Relation': self.db_wrapper.Relation,
'Column': self.adapter.Column,
"Relation": self.db_wrapper.Relation,
"Column": self.adapter.Column,
}
@contextproperty
@@ -1126,7 +1091,7 @@ class ProviderContext(ManifestContext):
""" # noqa
return self.manifest.flat_graph
@contextproperty('model')
@contextproperty("model")
def ctx_model(self) -> Dict[str, Any]:
return self.model.to_dict(omit_none=True)
@@ -1148,33 +1113,80 @@ 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_names: Optional[List[str]] = None
if "." in name:
package_name, name = name.split(".", 1)
package_names = [package_name]
try:
macro = self.db_wrapper.dispatch(macro_name=name, packages=package_names)
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):
"""Internally, macros can be executed like nodes, with some restrictions:
- they don't have have all values available that nodes do:
- 'this', 'pre_hooks', 'post_hooks', and 'sql' are missing
- 'schema' does not use any 'model' information
- they can't be configured with config() directives
- they don't have have all values available that nodes do:
- 'this', 'pre_hooks', 'post_hooks', and 'sql' are missing
- 'schema' does not use any 'model' information
- they can't be configured with config() directives
"""
def __init__(
self,
model: ParsedMacro,
config: RuntimeConfig,
manifest: Manifest,
manifest: AnyManifest,
provider: Provider,
search_package: Optional[str],
) -> None:
@@ -1192,37 +1204,29 @@ 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
]
return [h.to_dict(omit_none=True) for h in self.model.config.pre_hook]
@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
]
return [h.to_dict(omit_none=True) for h in self.model.config.post_hook]
@contextproperty
def sql(self) -> Optional[str]:
if getattr(self.model, 'extra_ctes_injected', None):
if getattr(self.model, "extra_ctes_injected", None):
return self.model.compiled_sql
return None
@contextproperty
def database(self) -> str:
return getattr(
self.model, 'database', self.config.credentials.database
)
return getattr(self.model, "database", self.config.credentials.database)
@contextproperty
def schema(self) -> str:
return getattr(
self.model, 'schema', self.config.credentials.schema
)
return getattr(self.model, "schema", self.config.credentials.schema)
@contextproperty
def this(self) -> Optional[RelationProxy]:
@@ -1264,15 +1268,13 @@ class ModelContext(ProviderContext):
def generate_parser_model(
model: ManifestNode,
config: RuntimeConfig,
manifest: Manifest,
manifest: MacroManifest,
context_config: ContextConfig,
) -> Dict[str, Any]:
# The __init__ method of ModelContext also initializes
# a ManifestContext object which creates a MacroNamespaceBuilder
# which adds every macro in the Manifest.
ctx = ModelContext(
model, config, manifest, ParseProvider(), context_config
)
ctx = ModelContext(model, config, manifest, ParseProvider(), context_config)
# The 'to_dict' method in ManifestContext moves all of the macro names
# in the macro 'namespace' up to top level keys
return ctx.to_dict()
@@ -1281,11 +1283,9 @@ def generate_parser_model(
def generate_generate_component_name_macro(
macro: ParsedMacro,
config: RuntimeConfig,
manifest: Manifest,
manifest: MacroManifest,
) -> Dict[str, Any]:
ctx = MacroContext(
macro, config, manifest, GenerateNameProvider(), None
)
ctx = MacroContext(macro, config, manifest, GenerateNameProvider(), None)
return ctx.to_dict()
@@ -1294,9 +1294,7 @@ def generate_runtime_model(
config: RuntimeConfig,
manifest: Manifest,
) -> Dict[str, Any]:
ctx = ModelContext(
model, config, manifest, RuntimeProvider(), None
)
ctx = ModelContext(model, config, manifest, RuntimeProvider(), None)
return ctx.to_dict()
@@ -1306,9 +1304,7 @@ def generate_runtime_macro(
manifest: Manifest,
package_name: Optional[str],
) -> Dict[str, Any]:
ctx = MacroContext(
macro, config, manifest, OperationProvider(), package_name
)
ctx = MacroContext(macro, config, manifest, OperationProvider(), package_name)
return ctx.to_dict()
@@ -1317,40 +1313,39 @@ class ExposureRefResolver(BaseResolver):
if len(args) not in (1, 2):
ref_invalid_args(self.model, args)
self.model.refs.append(list(args))
return ''
return ""
class ExposureSourceResolver(BaseResolver):
def __call__(self, *args) -> str:
if len(args) != 2:
raise_compiler_error(
f"source() takes exactly two arguments ({len(args)} given)",
self.model
f"source() takes exactly two arguments ({len(args)} given)", self.model
)
self.model.sources.append(list(args))
return ''
return ""
def generate_parse_exposure(
exposure: ParsedExposure,
config: RuntimeConfig,
manifest: Manifest,
manifest: MacroManifest,
package_name: str,
) -> Dict[str, Any]:
project = config.load_dependencies()[package_name]
return {
'ref': ExposureRefResolver(
"ref": ExposureRefResolver(
None,
exposure,
project,
manifest,
),
'source': ExposureSourceResolver(
"source": ExposureSourceResolver(
None,
exposure,
project,
manifest,
)
),
}
@@ -1372,12 +1367,7 @@ class TestContext(ProviderContext):
self.macro_resolver = macro_resolver
self.thread_ctx = MacroStack()
super().__init__(model, config, manifest, provider, context_config)
self._build_test_namespace()
# We need to rebuild this because it's already been built by
# the ProviderContext with the wrong namespace.
self.db_wrapper = self.provider.DatabaseWrapper(
self.adapter, self.namespace
)
self._build_test_namespace
def _build_namespace(self):
return {}
@@ -1390,17 +1380,10 @@ class TestContext(ProviderContext):
depends_on_macros = []
if self.model.depends_on and 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)
if lookup_macro:
depends_on_macros.extend(lookup_macro.depends_on.macros)
macro_namespace = TestMacroNamespace(
self.macro_resolver, self._ctx, self.model, self.thread_ctx,
depends_on_macros
self.macro_resolver, self.ctx, self.node, self.thread_ctx, depends_on_macros
)
self.namespace = macro_namespace
self._namespace = macro_namespace
def generate_test_context(
@@ -1408,11 +1391,10 @@ def generate_test_context(
config: RuntimeConfig,
manifest: Manifest,
context_config: ContextConfig,
macro_resolver: MacroResolver
macro_resolver: MacroResolver,
) -> Dict[str, Any]:
ctx = TestContext(
model, config, manifest, ParseProvider(), context_config,
macro_resolver
model, config, manifest, ParseProvider(), context_config, macro_resolver
)
# The 'to_dict' method in ManifestContext moves all of the macro names
# in the macro 'namespace' up to top level keys

View File

@@ -2,9 +2,7 @@ from typing import Any, Dict
from dbt.contracts.connection import HasCredentials
from dbt.context.base import (
BaseContext, contextproperty
)
from dbt.context import BaseContext, contextproperty
class TargetContext(BaseContext):

View File

@@ -1,27 +1,36 @@
import abc
import itertools
import hashlib
from dataclasses import dataclass, field
from typing import (
Any, ClassVar, Dict, Tuple, Iterable, Optional, List, Callable,
Any,
ClassVar,
Dict,
Tuple,
Iterable,
Optional,
List,
Callable,
)
from dbt.exceptions import InternalException
from dbt.utils import translate_aliases
from dbt.logger import GLOBAL_LOGGER as logger
from typing_extensions import Protocol
from dbt.dataclass_schema import (
dbtClassMixin, StrEnum, ExtensibleDbtClassMixin, HyphenatedDbtClassMixin,
ValidatedStringMixin, register_pattern
dbtClassMixin,
StrEnum,
ExtensibleDbtClassMixin,
ValidatedStringMixin,
register_pattern,
)
from dbt.contracts.util import Replaceable
class Identifier(ValidatedStringMixin):
ValidationRegex = r'^[A-Za-z_][A-Za-z0-9_]+$'
ValidationRegex = r"^[A-Za-z_][A-Za-z0-9_]+$"
# we need register_pattern for jsonschema validation
register_pattern(Identifier, r'^[A-Za-z_][A-Za-z0-9_]+$')
register_pattern(Identifier, r"^[A-Za-z_][A-Za-z0-9_]+$")
@dataclass
@@ -35,10 +44,10 @@ class AdapterResponse(dbtClassMixin):
class ConnectionState(StrEnum):
INIT = 'init'
OPEN = 'open'
CLOSED = 'closed'
FAIL = 'fail'
INIT = "init"
OPEN = "open"
CLOSED = "closed"
FAIL = "fail"
@dataclass(init=False)
@@ -82,8 +91,7 @@ class Connection(ExtensibleDbtClassMixin, Replaceable):
self._handle.resolve(self)
except RecursionError as exc:
raise InternalException(
"A connection's open() method attempted to read the "
"handle value"
"A connection's open() method attempted to read the " "handle value"
) from exc
return self._handle
@@ -102,8 +110,7 @@ class LazyHandle:
def resolve(self, connection: Connection) -> Connection:
logger.debug(
'Opening a new connection, currently in state {}'
.format(connection.state)
"Opening a new connection, currently in state {}".format(connection.state)
)
return self.opener(connection)
@@ -113,46 +120,24 @@ class LazyHandle:
# for why we have type: ignore. Maybe someday dataclasses + abstract classes
# will work.
@dataclass # type: ignore
class Credentials(
ExtensibleDbtClassMixin,
Replaceable,
metaclass=abc.ABCMeta
):
class Credentials(ExtensibleDbtClassMixin, Replaceable, metaclass=abc.ABCMeta):
database: str
schema: str
_ALIASES: ClassVar[Dict[str, str]] = field(default={}, init=False)
@abc.abstractproperty
def type(self) -> str:
raise NotImplementedError(
'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()
raise NotImplementedError("type not implemented for base credentials class")
def connection_info(
self, *, with_aliases: bool = False
) -> Iterable[Tuple[str, Any]]:
"""Return an ordered iterator of key/value pairs for pretty-printing.
"""
"""Return an ordered iterator of key/value pairs for pretty-printing."""
as_dict = self.to_dict(omit_none=False)
connection_keys = set(self._connection_keys())
aliases: List[str] = []
if with_aliases:
aliases = [
k for k, v in self._ALIASES.items() if v in connection_keys
]
aliases = [k for k, v in self._ALIASES.items() if v in connection_keys]
for key in itertools.chain(self._connection_keys(), aliases):
if key in as_dict:
yield key, as_dict[key]
@@ -176,11 +161,13 @@ class Credentials(
def __post_serialize__(self, dct):
# no super() -- do we need it?
if self._ALIASES:
dct.update({
new_name: dct[canonical_name]
for new_name, canonical_name in self._ALIASES.items()
if canonical_name in dct
})
dct.update(
{
new_name: dct[canonical_name]
for new_name, canonical_name in self._ALIASES.items()
if canonical_name in dct
}
)
return dct
@@ -190,19 +177,22 @@ 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
def to_target_dict(self):
raise NotImplementedError('to_target_dict not implemented')
raise NotImplementedError("to_target_dict not implemented")
DEFAULT_QUERY_COMMENT = '''
DEFAULT_QUERY_COMMENT = """
{%- set comment_dict = {} -%}
{%- do comment_dict.update(
app='dbt',
@@ -219,14 +209,13 @@ DEFAULT_QUERY_COMMENT = '''
{%- do comment_dict.update(connection_name=connection_name) -%}
{%- endif -%}
{{ return(tojson(comment_dict)) }}
'''
"""
@dataclass
class QueryComment(HyphenatedDbtClassMixin):
class QueryComment(dbtClassMixin):
comment: str = DEFAULT_QUERY_COMMENT
append: bool = False
job_label: bool = False
class AdapterRequiredConfig(HasCredentials, Protocol):

View File

@@ -1,50 +1,23 @@
import hashlib
import os
from dataclasses import dataclass, field
from mashumaro.types import SerializableType
from typing import List, Optional, Union, Dict, Any
from typing import List, Optional, Union
from dbt.dataclass_schema import dbtClassMixin, StrEnum
from dbt.dataclass_schema import dbtClassMixin
from .util import SourceKey
from dbt.exceptions import InternalException
from .util import MacroKey, SourceKey
MAXIMUM_SEED_SIZE = 1 * 1024 * 1024
MAXIMUM_SEED_SIZE_NAME = '1MB'
class ParseFileType(StrEnum):
Macro = 'macro'
Model = 'model'
Snapshot = 'snapshot'
Analysis = 'analysis'
SingularTest = 'singular_test'
GenericTest = 'generic_test'
Seed = 'seed'
Documentation = 'docs'
Schema = 'schema'
Hook = 'hook' # not a real filetype, from dbt_project.yml
parse_file_type_to_parser = {
ParseFileType.Macro: 'MacroParser',
ParseFileType.Model: 'ModelParser',
ParseFileType.Snapshot: 'SnapshotParser',
ParseFileType.Analysis: 'AnalysisParser',
ParseFileType.SingularTest: 'SingularTestParser',
ParseFileType.GenericTest: 'GenericTestParser',
ParseFileType.Seed: 'SeedParser',
ParseFileType.Documentation: 'DocumentationParser',
ParseFileType.Schema: 'SchemaParser',
ParseFileType.Hook: 'HookParser',
}
MAXIMUM_SEED_SIZE_NAME = "1MB"
@dataclass
class FilePath(dbtClassMixin):
searched_path: str
relative_path: str
modification_time: float
project_root: str
@property
@@ -55,9 +28,7 @@ class FilePath(dbtClassMixin):
@property
def full_path(self) -> str:
# useful for symlink preservation
return os.path.join(
self.project_root, self.searched_path, self.relative_path
)
return os.path.join(self.project_root, self.searched_path, self.relative_path)
@property
def absolute_path(self) -> str:
@@ -67,13 +38,10 @@ class FilePath(dbtClassMixin):
def original_file_path(self) -> str:
# this is mostly used for reporting errors. It doesn't show the project
# name, should it?
return os.path.join(
self.searched_path, self.relative_path
)
return os.path.join(self.searched_path, self.relative_path)
def seed_too_large(self) -> bool:
"""Return whether the file this represents is over the seed size limit
"""
"""Return whether the file this represents is over the seed size limit"""
return os.stat(self.full_path).st_size > MAXIMUM_SEED_SIZE
@@ -84,35 +52,35 @@ class FileHash(dbtClassMixin):
@classmethod
def empty(cls):
return FileHash(name='none', checksum='')
return FileHash(name="none", checksum="")
@classmethod
def path(cls, path: str):
return FileHash(name='path', checksum=path)
return FileHash(name="path", checksum=path)
def __eq__(self, other):
if not isinstance(other, FileHash):
return NotImplemented
if self.name == 'none' or self.name != other.name:
if self.name == "none" or self.name != other.name:
return False
return self.checksum == other.checksum
def compare(self, contents: str) -> bool:
"""Compare the file contents with the given hash"""
if self.name == 'none':
if self.name == "none":
return False
return self.from_contents(contents, name=self.name) == self.checksum
@classmethod
def from_contents(cls, contents: str, name='sha256') -> 'FileHash':
def from_contents(cls, contents: str, name="sha256") -> "FileHash":
"""Create a file hash from the given file contents. The hash is always
the utf-8 encoding of the contents given, because dbt only reads files
as utf-8.
"""
data = contents.encode('utf-8')
data = contents.encode("utf-8")
checksum = hashlib.new(name, data).hexdigest()
return cls(name=name, checksum=checksum)
@@ -121,183 +89,75 @@ class FileHash(dbtClassMixin):
class RemoteFile(dbtClassMixin):
@property
def searched_path(self) -> str:
return 'from remote system'
return "from remote system"
@property
def relative_path(self) -> str:
return 'from remote system'
return "from remote system"
@property
def absolute_path(self) -> str:
return 'from remote system'
return "from remote system"
@property
def original_file_path(self):
return 'from remote system'
@property
def modification_time(self):
return 'from remote system'
return "from remote system"
@dataclass
class BaseSourceFile(dbtClassMixin, SerializableType):
class SourceFile(dbtClassMixin):
"""Define a source file in dbt"""
path: Union[FilePath, RemoteFile] # the path information
checksum: FileHash
# Seems like knowing which project the file came from would be useful
project_name: Optional[str] = None
# Parse file type: i.e. which parser will process this file
parse_file_type: Optional[ParseFileType] = None
# we don't want to serialize this
contents: Optional[str] = None
_contents: Optional[str] = None
# the unique IDs contained in this file
@property
def file_id(self):
if isinstance(self.path, RemoteFile):
return None
return f'{self.project_name}://{self.path.original_file_path}'
def _serialize(self):
dct = self.to_dict()
return dct
@classmethod
def _deserialize(cls, dct: Dict[str, int]):
if dct['parse_file_type'] == 'schema':
sf = SchemaSourceFile.from_dict(dct)
else:
sf = SourceFile.from_dict(dct)
return sf
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
# remove empty lists to save space
dct_keys = list(dct.keys())
for key in dct_keys:
if isinstance(dct[key], list) and not dct[key]:
del dct[key]
# remove contents. Schema files will still have 'dict_from_yaml'
# from the contents
if 'contents' in dct:
del dct['contents']
return dct
@dataclass
class SourceFile(BaseSourceFile):
nodes: List[str] = field(default_factory=list)
docs: List[str] = field(default_factory=list)
macros: List[str] = field(default_factory=list)
@classmethod
def big_seed(cls, path: FilePath) -> 'SourceFile':
"""Parse seeds over the size limit with just the path"""
self = cls(path=path, checksum=FileHash.path(path.original_file_path))
self.contents = ''
return self
def add_node(self, value):
if value not in self.nodes:
self.nodes.append(value)
# TODO: do this a different way. This remote file kludge isn't going
# to work long term
@classmethod
def remote(cls, contents: str, project_name: str) -> 'SourceFile':
self = cls(
path=RemoteFile(),
checksum=FileHash.from_contents(contents),
project_name=project_name,
contents=contents,
)
return self
@dataclass
class SchemaSourceFile(BaseSourceFile):
dfy: Dict[str, Any] = field(default_factory=dict)
# these are in the manifest.nodes dictionary
tests: Dict[str, Any] = field(default_factory=dict)
sources: List[str] = field(default_factory=list)
exposures: 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.
mcp: Dict[str, str] = field(default_factory=dict)
# any node patches in this file. The entries are names, not unique ids!
patches: List[str] = field(default_factory=list)
# any macro patches in this file. The entries are package, name pairs.
macro_patches: List[MacroKey] = field(default_factory=list)
# any source patches in this file. The entries are package, name pairs
# Patches are only against external sources. Sources can be
# created too, but those are in 'sources'
sop: List[SourceKey] = field(default_factory=list)
pp_dict: Optional[Dict[str, Any]] = None
pp_test_index: Optional[Dict[str, Any]] = None
source_patches: List[SourceKey] = field(default_factory=list)
@property
def dict_from_yaml(self):
return self.dfy
def search_key(self) -> Optional[str]:
if isinstance(self.path, RemoteFile):
return None
if self.checksum.name == "none":
return None
return self.path.search_key
@property
def node_patches(self):
return self.ndp
def contents(self) -> str:
if self._contents is None:
raise InternalException("SourceFile has no contents!")
return self._contents
@property
def macro_patches(self):
return self.mcp
@contents.setter
def contents(self, value):
self._contents = value
@property
def source_patches(self):
return self.sop
@classmethod
def empty(cls, path: FilePath) -> "SourceFile":
self = cls(path=path, checksum=FileHash.empty())
self.contents = ""
return self
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
# Remove partial parsing specific data
for key in ('pp_files', 'pp_test_index', 'pp_dict'):
if key in dct:
del dct[key]
return dct
@classmethod
def big_seed(cls, path: FilePath) -> "SourceFile":
"""Parse seeds over the size limit with just the path"""
self = cls(path=path, checksum=FileHash.path(path.original_file_path))
self.contents = ""
return self
def append_patch(self, yaml_key, unique_id):
self.node_patches.append(unique_id)
def add_test(self, node_unique_id, test_from):
name = test_from['name']
key = test_from['key']
if key not in self.tests:
self.tests[key] = {}
if name not in self.tests[key]:
self.tests[key][name] = []
self.tests[key][name].append(node_unique_id)
def remove_tests(self, yaml_key, name):
if yaml_key in self.tests:
if name in self.tests[yaml_key]:
del self.tests[yaml_key][name]
def get_tests(self, yaml_key, name):
if yaml_key in self.tests:
if name in self.tests[yaml_key]:
return self.tests[yaml_key][name]
return []
def get_key_and_name_for_test(self, test_unique_id):
yaml_key = None
block_name = None
for key in self.tests.keys():
for name in self.tests[key]:
for unique_id in self.tests[key][name]:
if unique_id == test_unique_id:
yaml_key = key
block_name = name
break
return (yaml_key, block_name)
def get_all_test_ids(self):
test_ids = []
for key in self.tests.keys():
for name in self.tests[key]:
test_ids.extend(self.tests[key][name])
return test_ids
AnySourceFile = Union[SchemaSourceFile, SourceFile]
@classmethod
def remote(cls, contents: str) -> "SourceFile":
self = cls(path=RemoteFile(), checksum=FileHash.empty())
self.contents = contents
return self

View File

@@ -2,13 +2,13 @@ from dbt.contracts.graph.parsed import (
HasTestMetadata,
ParsedNode,
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedExposure,
ParsedResource,
ParsedRPCNode,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
ParsedSourceDefinition,
@@ -43,7 +43,6 @@ class CompiledNode(ParsedNode, CompiledNodeMixin):
extra_ctes_injected: bool = False
extra_ctes: List[InjectedCTE] = field(default_factory=list)
relation_name: Optional[str] = None
_pre_injected_sql: Optional[str] = None
def set_cte(self, cte_id: str, sql: str):
"""This is the equivalent of what self.extra_ctes[cte_id] = sql would
@@ -56,40 +55,32 @@ class CompiledNode(ParsedNode, CompiledNodeMixin):
else:
self.extra_ctes.append(InjectedCTE(id=cte_id, sql=sql))
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
if '_pre_injected_sql' in dct:
del dct['_pre_injected_sql']
return dct
@dataclass
class CompiledAnalysisNode(CompiledNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Analysis]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Analysis]})
@dataclass
class CompiledHookNode(CompiledNode):
resource_type: NodeType = field(
metadata={'restrict': [NodeType.Operation]}
)
resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
index: Optional[int] = None
@dataclass
class CompiledModelNode(CompiledNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Model]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Model]})
@dataclass
class CompiledRPCNode(CompiledNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.RPCCall]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.RPCCall]})
@dataclass
class CompiledSeedNode(CompiledNode):
# keep this in sync with ParsedSeedNode!
resource_type: NodeType = field(metadata={'restrict': [NodeType.Seed]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Seed]})
config: SeedConfig = field(default_factory=SeedConfig)
@property
@@ -103,38 +94,38 @@ class CompiledSeedNode(CompiledNode):
@dataclass
class CompiledSnapshotNode(CompiledNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
@dataclass
class CompiledSingularTestNode(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
class CompiledDataTestNode(CompiledNode):
resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
config: TestConfig = field(default_factory=TestConfig)
@dataclass
class CompiledGenericTestNode(CompiledNode, HasTestMetadata):
# keep this in sync with ParsedGenericTestNode!
resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
class CompiledSchemaTestNode(CompiledNode, HasTestMetadata):
# keep this in sync with ParsedSchemaTestNode!
resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
column_name: Optional[str] = None
# Was not able to make mypy happy and keep the code working. We need to
# refactor the various configs.
config: TestConfig = field(default_factory=TestConfig) # type:ignore
config: TestConfig = field(default_factory=TestConfig)
def same_config(self, other) -> bool:
return self.unrendered_config.get("severity") == other.unrendered_config.get(
"severity"
)
def same_column_name(self, other) -> bool:
return self.column_name == other.column_name
def same_contents(self, other) -> bool:
if other is None:
return False
return (
self.same_config(other) and
self.same_fqn(other) and
True
)
return self.same_config(other) and self.same_fqn(other) and True
CompiledTestNode = Union[CompiledSingularTestNode, CompiledGenericTestNode]
CompiledTestNode = Union[CompiledDataTestNode, CompiledSchemaTestNode]
PARSED_TYPES: Dict[Type[CompiledNode], Type[ParsedResource]] = {
@@ -144,8 +135,8 @@ PARSED_TYPES: Dict[Type[CompiledNode], Type[ParsedResource]] = {
CompiledRPCNode: ParsedRPCNode,
CompiledSeedNode: ParsedSeedNode,
CompiledSnapshotNode: ParsedSnapshotNode,
CompiledSingularTestNode: ParsedSingularTestNode,
CompiledGenericTestNode: ParsedGenericTestNode,
CompiledDataTestNode: ParsedDataTestNode,
CompiledSchemaTestNode: ParsedSchemaTestNode,
}
@@ -156,8 +147,8 @@ COMPILED_TYPES: Dict[Type[ParsedResource], Type[CompiledNode]] = {
ParsedRPCNode: CompiledRPCNode,
ParsedSeedNode: CompiledSeedNode,
ParsedSnapshotNode: CompiledSnapshotNode,
ParsedSingularTestNode: CompiledSingularTestNode,
ParsedGenericTestNode: CompiledGenericTestNode,
ParsedDataTestNode: CompiledDataTestNode,
ParsedSchemaTestNode: CompiledSchemaTestNode,
}
@@ -177,30 +168,29 @@ def parsed_instance_for(compiled: CompiledNode) -> ParsedResource:
cls = PARSED_TYPES.get(type(compiled))
if cls is None:
# how???
raise ValueError('invalid resource_type: {}'
.format(compiled.resource_type))
raise ValueError("invalid resource_type: {}".format(compiled.resource_type))
return cls.from_dict(compiled.to_dict(omit_none=True))
NonSourceCompiledNode = Union[
CompiledAnalysisNode,
CompiledSingularTestNode,
CompiledDataTestNode,
CompiledModelNode,
CompiledHookNode,
CompiledRPCNode,
CompiledGenericTestNode,
CompiledSchemaTestNode,
CompiledSeedNode,
CompiledSnapshotNode,
]
NonSourceParsedNode = Union[
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedDataTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedRPCNode,
ParsedGenericTestNode,
ParsedSchemaTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
]

File diff suppressed because it is too large Load Diff

View File

@@ -2,19 +2,29 @@ from dataclasses import field, Field, dataclass
from enum import Enum
from itertools import chain
from typing import (
Any, List, Optional, Dict, Union, Type, TypeVar, Callable
Any,
List,
Optional,
Dict,
MutableMapping,
Union,
Type,
TypeVar,
Callable,
)
from dbt.dataclass_schema import (
dbtClassMixin, ValidationError, register_pattern,
dbtClassMixin,
ValidationError,
register_pattern,
)
from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed
from dbt.exceptions import InternalException, CompilationException
from dbt.exceptions import CompilationException, InternalException
from dbt.contracts.util import Replaceable, list_str
from dbt import hooks
from dbt.node_types import NodeType
M = TypeVar('M', bound='Metadata')
M = TypeVar("M", bound="Metadata")
def _get_meta_value(cls: Type[M], fld: Field, key: str, default: Any) -> M:
@@ -29,9 +39,7 @@ def _get_meta_value(cls: Type[M], fld: Field, key: str, default: Any) -> M:
try:
return cls(value)
except ValueError as exc:
raise InternalException(
f'Invalid {cls} value: {value}'
) from exc
raise InternalException(f"Invalid {cls} value: {value}") from exc
def _set_meta_value(
@@ -53,19 +61,17 @@ class Metadata(Enum):
return _get_meta_value(cls, fld, key, default)
def meta(
self, existing: Optional[Dict[str, Any]] = None
) -> Dict[str, Any]:
def meta(self, existing: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
key = self.metadata_key()
return _set_meta_value(self, key, existing)
@classmethod
def default_field(cls) -> 'Metadata':
raise NotImplementedError('Not implemented')
def default_field(cls) -> "Metadata":
raise NotImplementedError("Not implemented")
@classmethod
def metadata_key(cls) -> str:
raise NotImplementedError('Not implemented')
raise NotImplementedError("Not implemented")
class MergeBehavior(Metadata):
@@ -74,12 +80,12 @@ class MergeBehavior(Metadata):
Clobber = 3
@classmethod
def default_field(cls) -> 'MergeBehavior':
def default_field(cls) -> "MergeBehavior":
return cls.Clobber
@classmethod
def metadata_key(cls) -> str:
return 'merge'
return "merge"
class ShowBehavior(Metadata):
@@ -87,12 +93,12 @@ class ShowBehavior(Metadata):
Hide = 2
@classmethod
def default_field(cls) -> 'ShowBehavior':
def default_field(cls) -> "ShowBehavior":
return cls.Show
@classmethod
def metadata_key(cls) -> str:
return 'show_hide'
return "show_hide"
@classmethod
def should_show(cls, fld: Field) -> bool:
@@ -104,12 +110,12 @@ class CompareBehavior(Metadata):
Exclude = 2
@classmethod
def default_field(cls) -> 'CompareBehavior':
def default_field(cls) -> "CompareBehavior":
return cls.Include
@classmethod
def metadata_key(cls) -> str:
return 'compare'
return "compare"
@classmethod
def should_include(cls, fld: Field) -> bool:
@@ -141,32 +147,30 @@ def _merge_field_value(
return _listify(self_value) + _listify(other_value)
elif merge_behavior == MergeBehavior.Update:
if not isinstance(self_value, dict):
raise InternalException(f'expected dict, got {self_value}')
raise InternalException(f"expected dict, got {self_value}")
if not isinstance(other_value, dict):
raise InternalException(f'expected dict, got {other_value}')
raise InternalException(f"expected dict, got {other_value}")
value = self_value.copy()
value.update(other_value)
return value
else:
raise InternalException(
f'Got an invalid merge_behavior: {merge_behavior}'
)
raise InternalException(f"Got an invalid merge_behavior: {merge_behavior}")
def insensitive_patterns(*patterns: str):
lowercased = []
for pattern in patterns:
lowercased.append(
''.join('[{}{}]'.format(s.upper(), s.lower()) for s in pattern)
"".join("[{}{}]".format(s.upper(), s.lower()) for s in pattern)
)
return '^({})$'.format('|'.join(lowercased))
return "^({})$".format("|".join(lowercased))
class Severity(str):
pass
register_pattern(Severity, insensitive_patterns('warn', 'error'))
register_pattern(Severity, insensitive_patterns("warn", "error"))
@dataclass
@@ -176,28 +180,22 @@ class Hook(dbtClassMixin, Replaceable):
index: Optional[int] = None
T = TypeVar('T', bound='BaseConfig')
T = TypeVar("T", bound="BaseConfig")
@dataclass
class BaseConfig(
AdditionalPropertiesAllowed, Replaceable
):
# enable syntax like: config['key']
class BaseConfig(AdditionalPropertiesAllowed, Replaceable, MutableMapping[str, Any]):
# Implement MutableMapping so this config will behave as some macros expect
# during parsing (notably, syntax like `{{ node.config['schema'] }}`)
def __getitem__(self, key):
return self.get(key)
# like doing 'get' on a dictionary
def get(self, key, default=None):
"""Handle parse-time use of `config` as a dictionary, making the extra
values available during parsing.
"""
if hasattr(self, key):
return getattr(self, key)
elif key in self._extra:
return self._extra[key]
else:
return default
return self._extra[key]
# enable syntax like: config['key'] = value
def __setitem__(self, key, value):
if hasattr(self, key):
setattr(self, key, value)
@@ -207,8 +205,7 @@ class BaseConfig(
def __delitem__(self, key):
if hasattr(self, key):
msg = (
'Error, tried to delete config key "{}": Cannot delete '
'built-in keys'
'Error, tried to delete config key "{}": Cannot delete ' "built-in keys"
).format(key)
raise CompilationException(msg)
else:
@@ -248,9 +245,7 @@ class BaseConfig(
return unrendered[key] == other[key]
@classmethod
def same_contents(
cls, unrendered: Dict[str, Any], other: Dict[str, Any]
) -> bool:
def same_contents(cls, unrendered: Dict[str, Any], other: Dict[str, Any]) -> bool:
"""This is like __eq__, except it ignores some fields."""
seen = set()
for fld, target_name in cls._get_fields():
@@ -267,17 +262,8 @@ class BaseConfig(
return False
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'],
}
@classmethod
def _merge_dicts(
cls, src: Dict[str, Any], data: Dict[str, Any]
) -> Dict[str, Any]:
def _extract_dict(cls, src: Dict[str, Any], data: Dict[str, Any]) -> Dict[str, Any]:
"""Find all the items in data that match a target_field on this class,
and merge them with the data found in `src` for target_field, using the
field's specified merge behavior. Matching items will be removed from
@@ -317,14 +303,15 @@ class BaseConfig(
"""
# sadly, this is a circular import
from dbt.adapters.factory import get_config_class_by_name
dct = self.to_dict(omit_none=False)
adapter_config_cls = get_config_class_by_name(adapter_type)
self_merged = self._merge_dicts(dct, data)
self_merged = self._extract_dict(dct, data)
dct.update(self_merged)
adapter_merged = adapter_config_cls._merge_dicts(dct, data)
adapter_merged = adapter_config_cls._extract_dict(dct, data)
dct.update(adapter_merged)
# any remaining fields must be "clobber"
@@ -356,8 +343,33 @@ class SourceConfig(BaseConfig):
@dataclass
class NodeAndTestConfig(BaseConfig):
class NodeConfig(BaseConfig):
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(
@@ -374,47 +386,16 @@ class NodeAndTestConfig(BaseConfig):
)
tags: Union[List[str], str] = field(
default_factory=list_str,
metadata=metas(ShowBehavior.Hide,
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(),
metadata=metas(
ShowBehavior.Hide, MergeBehavior.Append, CompareBehavior.Exclude
),
)
full_refresh: Optional[bool] = None
on_schema_change: Optional[str] = 'ignore'
@classmethod
def __pre_deserialize__(cls, data):
data = super().__pre_deserialize__(data)
field_map = {'post-hook': 'post_hook', 'pre-hook': 'pre_hook'}
field_map = {"post-hook": "post_hook", "pre-hook": "pre_hook"}
# create a new dict because otherwise it gets overwritten in
# tests
new_dict = {}
@@ -432,7 +413,7 @@ class NodeConfig(NodeAndTestConfig):
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
field_map = {'post_hook': 'post-hook', 'pre_hook': 'pre-hook'}
field_map = {"post_hook": "post-hook", "pre_hook": "pre-hook"}
for field_name in field_map:
if field_name in dct:
dct[field_map[field_name]] = dct.pop(field_name)
@@ -441,59 +422,24 @@ class NodeConfig(NodeAndTestConfig):
# this is still used by jsonschema validation
@classmethod
def field_mapping(cls):
return {'post_hook': 'post-hook', 'pre_hook': 'pre-hook'}
return {"post_hook": "post-hook", "pre_hook": "pre-hook"}
@dataclass
class SeedConfig(NodeConfig):
materialized: str = 'seed'
materialized: str = "seed"
quote_columns: Optional[bool] = None
@dataclass
class TestConfig(NodeAndTestConfig):
# this is repeated because of a different default
schema: Optional[str] = field(
default='dbt_test__audit',
metadata=CompareBehavior.Exclude.meta(),
)
materialized: str = 'test'
severity: Severity = Severity('ERROR')
store_failures: Optional[bool] = None
where: Optional[str] = None
limit: Optional[int] = None
fail_calc: str = 'count(*)'
warn_if: str = '!= 0'
error_if: str = '!= 0'
@classmethod
def same_contents(
cls, unrendered: Dict[str, Any], other: Dict[str, Any]
) -> bool:
"""This is like __eq__, except it explicitly checks certain fields."""
modifiers = [
'severity',
'where',
'limit',
'fail_calc',
'warn_if',
'error_if',
'store_failures'
]
seen = set()
for _, target_name in cls._get_fields():
key = target_name
seen.add(key)
if key in modifiers:
if not cls.compare_key(unrendered, other, key):
return False
return True
class TestConfig(NodeConfig):
materialized: str = "test"
severity: Severity = Severity("ERROR")
@dataclass
class EmptySnapshotConfig(NodeConfig):
materialized: str = 'snapshot'
materialized: str = "snapshot"
@dataclass
@@ -508,30 +454,28 @@ class SnapshotConfig(EmptySnapshotConfig):
@classmethod
def validate(cls, data):
super().validate(data)
if not data.get('strategy') or not data.get('unique_key') or not \
data.get('target_schema'):
raise ValidationError(
"Snapshots must be configured with a 'strategy', 'unique_key', "
"and 'target_schema'.")
if data.get('strategy') == 'check':
if not data.get('check_cols'):
if data.get("strategy") == "check":
if not data.get("check_cols"):
raise ValidationError(
"A snapshot configured with the check strategy must "
"specify a check_cols configuration.")
if (isinstance(data['check_cols'], str) and
data['check_cols'] != 'all'):
"specify a check_cols configuration."
)
if isinstance(data["check_cols"], str) and data["check_cols"] != "all":
raise ValidationError(
f"Invalid value for 'check_cols': {data['check_cols']}. "
"Expected 'all' or a list of strings.")
"Expected 'all' or a list of strings."
)
elif data.get('strategy') == 'timestamp':
if not data.get('updated_at'):
elif data.get("strategy") == "timestamp":
if not data.get("updated_at"):
raise ValidationError(
"A snapshot configured with the timestamp strategy "
"must specify an updated_at configuration.")
if data.get('check_cols'):
"must specify an updated_at configuration."
)
if data.get("check_cols"):
raise ValidationError(
"A 'timestamp' snapshot should not have 'check_cols'")
"A 'timestamp' snapshot should not have 'check_cols'"
)
# If the strategy is not 'check' or 'timestamp' it's a custom strategy,
# formerly supported with GenericSnapshotConfig
@@ -553,9 +497,7 @@ RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = {
# base resource types are like resource types, except nothing has mandatory
# configs.
BASE_RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = RESOURCE_TYPES.copy()
BASE_RESOURCE_TYPES.update({
NodeType.Snapshot: EmptySnapshotConfig
})
BASE_RESOURCE_TYPES.update({NodeType.Snapshot: EmptySnapshotConfig})
def get_config_for(resource_type: NodeType, base=False) -> Type[BaseConfig]:

View File

@@ -1,7 +1,5 @@
import os
import time
from dataclasses import dataclass, field
from mashumaro.types import SerializableType
from pathlib import Path
from typing import (
Optional,
@@ -15,18 +13,27 @@ from typing import (
TypeVar,
)
from dbt.dataclass_schema import (
dbtClassMixin, ExtensibleDbtClassMixin
)
from dbt.dataclass_schema import dbtClassMixin, ExtensibleDbtClassMixin
from dbt.clients.system import write_file
from dbt.contracts.files import FileHash, MAXIMUM_SEED_SIZE_NAME
from dbt.contracts.graph.unparsed import (
UnparsedNode, UnparsedDocumentation, Quoting, Docs,
UnparsedBaseNode, FreshnessThreshold, ExternalTable,
HasYamlMetadata, MacroArgument, UnparsedSourceDefinition,
UnparsedSourceTableDefinition, UnparsedColumn, TestDef,
ExposureOwner, ExposureType, MaturityType
UnparsedNode,
UnparsedDocumentation,
Quoting,
Docs,
UnparsedBaseNode,
FreshnessThreshold,
ExternalTable,
HasYamlMetadata,
MacroArgument,
UnparsedSourceDefinition,
UnparsedSourceTableDefinition,
UnparsedColumn,
TestDef,
ExposureOwner,
ExposureType,
MaturityType,
)
from dbt.contracts.util import Replaceable, AdditionalPropertiesMixin
from dbt.exceptions import warn_or_error
@@ -46,13 +53,9 @@ from .model_config import (
@dataclass
class ColumnInfo(
AdditionalPropertiesMixin,
ExtensibleDbtClassMixin,
Replaceable
):
class ColumnInfo(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable):
name: str
description: str = ''
description: str = ""
meta: Dict[str, Any] = field(default_factory=dict)
data_type: Optional[str] = None
quote: Optional[bool] = None
@@ -64,7 +67,7 @@ class ColumnInfo(
class HasFqn(dbtClassMixin, Replaceable):
fqn: List[str]
def same_fqn(self, other: 'HasFqn') -> bool:
def same_fqn(self, other: "HasFqn") -> bool:
return self.fqn == other.fqn
@@ -103,8 +106,8 @@ class HasRelationMetadata(dbtClassMixin, Replaceable):
@classmethod
def __pre_deserialize__(cls, data):
data = super().__pre_deserialize__(data)
if 'database' not in data:
data['database'] = None
if "database" not in data:
data["database"] = None
return data
@@ -117,24 +120,9 @@ class ParsedNodeMixins(dbtClassMixin):
def is_refable(self):
return self.resource_type in NodeType.refable()
@property
def should_store_failures(self):
return self.resource_type == NodeType.Test and (
self.config.store_failures if self.config.store_failures is not None
else flags.STORE_FAILURES
)
# will this node map to an object in the database?
@property
def is_relational(self):
return (
self.resource_type in NodeType.refable() or
self.should_store_failures
)
@property
def is_ephemeral(self):
return self.config.materialized == 'ephemeral'
return self.config.materialized == "ephemeral"
@property
def is_ephemeral_model(self):
@@ -144,30 +132,33 @@ class ParsedNodeMixins(dbtClassMixin):
def depends_on_nodes(self):
return self.depends_on.nodes
def patch(self, patch: 'ParsedNodePatch'):
def patch(self, patch: "ParsedNodePatch"):
"""Given a ParsedNodePatch, add the new information to the node."""
# explicitly pick out the parts to update so we don't inadvertently
# step on the model name or anything
# Note: config should already be updated
self.patch_path: Optional[str] = patch.file_id
# update created_at so process_docs will run in partial parsing
self.created_at = int(time.time())
self.patch_path: Optional[str] = patch.original_file_path
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(
UnparsedNode,
HasUniqueID,
HasFqn,
HasRelationMetadata,
Replaceable
UnparsedNode, HasUniqueID, HasFqn, HasRelationMetadata, Replaceable
):
alias: str
checksum: FileHash
@@ -182,89 +173,40 @@ class ParsedNodeMandatory(
class ParsedNodeDefaults(ParsedNodeMandatory):
tags: List[str] = field(default_factory=list)
refs: List[List[str]] = field(default_factory=list)
sources: List[List[str]] = field(default_factory=list)
sources: List[List[Any]] = field(default_factory=list)
depends_on: DependsOn = field(default_factory=DependsOn)
description: str = field(default='')
description: str = field(default="")
columns: Dict[str, ColumnInfo] = field(default_factory=dict)
meta: Dict[str, Any] = field(default_factory=dict)
docs: Docs = field(default_factory=Docs)
patch_path: Optional[str] = None
compiled_path: Optional[str] = None
build_path: Optional[str] = None
deferred: bool = False
unrendered_config: Dict[str, Any] = field(default_factory=dict)
created_at: int = field(default_factory=lambda: int(time.time()))
config_call_dict: Dict[str, Any] = field(default_factory=dict)
def write_node(self, target_path: str, subdirectory: str, payload: str):
if (os.path.basename(self.path) ==
os.path.basename(self.original_file_path)):
if os.path.basename(self.path) == os.path.basename(self.original_file_path):
# One-to-one relationship of nodes to files.
path = self.original_file_path
else:
# Many-to-one relationship of nodes to files.
path = os.path.join(self.original_file_path, self.path)
full_path = os.path.join(
target_path, subdirectory, self.package_name, path
)
full_path = os.path.join(target_path, subdirectory, self.package_name, path)
write_file(full_path, payload)
return full_path
T = TypeVar('T', bound='ParsedNode')
T = TypeVar("T", bound="ParsedNode")
@dataclass
class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
def _serialize(self):
return self.to_dict()
def __post_serialize__(self, dct):
if 'config_call_dict' in dct:
del dct['config_call_dict']
return dct
@classmethod
def _deserialize(cls, dct: Dict[str, int]):
# The serialized ParsedNodes do not differ from each other
# in fields that would allow 'from_dict' to distinguis
# between them.
resource_type = dct['resource_type']
if resource_type == 'model':
return ParsedModelNode.from_dict(dct)
elif resource_type == 'analysis':
return ParsedAnalysisNode.from_dict(dct)
elif resource_type == 'seed':
return ParsedSeedNode.from_dict(dct)
elif resource_type == 'rpc':
return ParsedRPCNode.from_dict(dct)
elif resource_type == 'test':
if 'test_metadata' in dct:
return ParsedGenericTestNode.from_dict(dct)
else:
return ParsedSingularTestNode.from_dict(dct)
elif resource_type == 'operation':
return ParsedHookNode.from_dict(dct)
elif resource_type == 'seed':
return ParsedSeedNode.from_dict(dct)
elif resource_type == 'snapshot':
return ParsedSnapshotNode.from_dict(dct)
else:
return cls.from_dict(dct)
class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins):
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
@@ -279,9 +221,7 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
if self._persist_column_docs():
# assert other._persist_column_docs()
column_descriptions = {
k: v.description for k, v in self.columns.items()
}
column_descriptions = {k: v.description for k, v in self.columns.items()}
other_column_descriptions = {
k: v.description for k, v in other.columns.items()
}
@@ -295,7 +235,7 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
# compares the configured value, rather than the ultimate value (so
# generate_*_name and unset values derived from the target are
# ignored)
keys = ('database', 'schema', 'alias')
keys = ("database", "schema", "alias")
for key in keys:
mine = self.unrendered_config.get(key)
others = other.unrendered_config.get(key)
@@ -314,36 +254,34 @@ class ParsedNode(ParsedNodeDefaults, ParsedNodeMixins, SerializableType):
return False
return (
self.same_body(old) and
self.same_config(old) and
self.same_persisted_description(old) and
self.same_fqn(old) and
self.same_database_representation(old) and
True
self.same_body(old)
and self.same_config(old)
and self.same_persisted_description(old)
and self.same_fqn(old)
and self.same_database_representation(old)
and True
)
@dataclass
class ParsedAnalysisNode(ParsedNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Analysis]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Analysis]})
@dataclass
class ParsedHookNode(ParsedNode):
resource_type: NodeType = field(
metadata={'restrict': [NodeType.Operation]}
)
resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
index: Optional[int] = None
@dataclass
class ParsedModelNode(ParsedNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Model]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Model]})
@dataclass
class ParsedRPCNode(ParsedNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.RPCCall]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.RPCCall]})
def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
@@ -353,31 +291,31 @@ def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
# if the current checksum is a path, we want to log a warning.
result = first.checksum == second.checksum
if first.checksum.name == 'path':
if first.checksum.name == "path":
msg: str
if second.checksum.name != 'path':
if second.checksum.name != "path":
msg = (
f'Found a seed ({first.package_name}.{first.name}) '
f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was '
f'<={MAXIMUM_SEED_SIZE_NAME}, so it has changed'
f"Found a seed ({first.package_name}.{first.name}) "
f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was "
f"<={MAXIMUM_SEED_SIZE_NAME}, so it has changed"
)
elif result:
msg = (
f'Found a seed ({first.package_name}.{first.name}) '
f'>{MAXIMUM_SEED_SIZE_NAME} in size at the same path, dbt '
f'cannot tell if it has changed: assuming they are the same'
f"Found a seed ({first.package_name}.{first.name}) "
f">{MAXIMUM_SEED_SIZE_NAME} in size at the same path, dbt "
f"cannot tell if it has changed: assuming they are the same"
)
elif not result:
msg = (
f'Found a seed ({first.package_name}.{first.name}) '
f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was in '
f'a different location, assuming it has changed'
f"Found a seed ({first.package_name}.{first.name}) "
f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file was in "
f"a different location, assuming it has changed"
)
else:
msg = (
f'Found a seed ({first.package_name}.{first.name}) '
f'>{MAXIMUM_SEED_SIZE_NAME} in size. The previous file had a '
f'checksum type of {second.checksum.name}, so it has changed'
f"Found a seed ({first.package_name}.{first.name}) "
f">{MAXIMUM_SEED_SIZE_NAME} in size. The previous file had a "
f"checksum type of {second.checksum.name}, so it has changed"
)
warn_or_error(msg, node=first)
@@ -387,7 +325,7 @@ def same_seeds(first: ParsedNode, second: ParsedNode) -> bool:
@dataclass
class ParsedSeedNode(ParsedNode):
# keep this in sync with CompiledSeedNode!
resource_type: NodeType = field(metadata={'restrict': [NodeType.Seed]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Seed]})
config: SeedConfig = field(default_factory=SeedConfig)
@property
@@ -412,31 +350,31 @@ class HasTestMetadata(dbtClassMixin):
@dataclass
class ParsedSingularTestNode(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
class ParsedDataTestNode(ParsedNode):
resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
config: TestConfig = field(default_factory=TestConfig)
@dataclass
class ParsedGenericTestNode(ParsedNode, HasTestMetadata):
# keep this in sync with CompiledGenericTestNode!
resource_type: NodeType = field(metadata={'restrict': [NodeType.Test]})
class ParsedSchemaTestNode(ParsedNode, HasTestMetadata):
# keep this in sync with CompiledSchemaTestNode!
resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
column_name: Optional[str] = None
# Was not able to make mypy happy and keep the code working. We need to
# refactor the various configs.
config: TestConfig = field(default_factory=TestConfig) # type: ignore
config: TestConfig = field(default_factory=TestConfig)
def same_config(self, other) -> bool:
return self.unrendered_config.get("severity") == other.unrendered_config.get(
"severity"
)
def same_column_name(self, other) -> bool:
return self.column_name == other.column_name
def same_contents(self, other) -> bool:
if other is None:
return False
return (
self.same_config(other) and
self.same_fqn(other) and
True
)
return self.same_config(other) and self.same_fqn(other) and True
@dataclass
@@ -447,13 +385,13 @@ class IntermediateSnapshotNode(ParsedNode):
# defined in config blocks. To fix that, we have an intermediate type that
# uses a regular node config, which the snapshot parser will then convert
# into a full ParsedSnapshotNode after rendering.
resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
config: EmptySnapshotConfig = field(default_factory=EmptySnapshotConfig)
@dataclass
class ParsedSnapshotNode(ParsedNode):
resource_type: NodeType = field(metadata={'restrict': [NodeType.Snapshot]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
config: SnapshotConfig
@@ -463,7 +401,6 @@ 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
@@ -483,27 +420,33 @@ class ParsedMacroPatch(ParsedPatch):
class ParsedMacro(UnparsedBaseNode, HasUniqueID):
name: str
macro_sql: str
resource_type: NodeType = field(metadata={'restrict': [NodeType.Macro]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
# TODO: can macros even have tags?
tags: List[str] = field(default_factory=list)
# TODO: is this ever populated?
depends_on: MacroDependsOn = field(default_factory=MacroDependsOn)
description: str = ''
description: str = ""
meta: Dict[str, Any] = field(default_factory=dict)
docs: Docs = field(default_factory=Docs)
patch_path: Optional[str] = None
arguments: List[MacroArgument] = field(default_factory=list)
created_at: int = field(default_factory=lambda: int(time.time()))
def local_vars(self):
return {}
def patch(self, patch: ParsedMacroPatch):
self.patch_path: Optional[str] = patch.file_id
self.patch_path: Optional[str] = patch.original_file_path
self.description = patch.description
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:
def same_contents(self, other: Optional["ParsedMacro"]) -> bool:
if other is None:
return False
# the only thing that makes one macro different from another with the
@@ -520,7 +463,7 @@ class ParsedDocumentation(UnparsedDocumentation, HasUniqueID):
def search_name(self):
return self.name
def same_contents(self, other: Optional['ParsedDocumentation']) -> bool:
def same_contents(self, other: Optional["ParsedDocumentation"]) -> bool:
if other is None:
return False
# the only thing that makes one doc different from another with the
@@ -539,11 +482,11 @@ def normalize_test(testdef: TestDef) -> Dict[str, Any]:
class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
source: UnparsedSourceDefinition
table: UnparsedSourceTableDefinition
resource_type: NodeType = field(metadata={'restrict': [NodeType.Source]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Source]})
patch_path: Optional[Path] = None
def get_full_source_name(self):
return f'{self.source.name}_{self.table.name}'
return f"{self.source.name}_{self.table.name}"
def get_source_representation(self):
return f'source("{self.source.name}", "{self.table.name}")'
@@ -568,9 +511,7 @@ class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
else:
return self.table.columns
def get_tests(
self
) -> Iterator[Tuple[Dict[str, Any], Optional[UnparsedColumn]]]:
def get_tests(self) -> Iterator[Tuple[Dict[str, Any], Optional[UnparsedColumn]]]:
for test in self.tests:
yield normalize_test(test), None
@@ -589,23 +530,19 @@ class UnpatchedSourceDefinition(UnparsedBaseNode, HasUniqueID, HasFqn):
@dataclass
class ParsedSourceDefinition(
UnparsedBaseNode,
HasUniqueID,
HasRelationMetadata,
HasFqn,
UnparsedBaseNode, HasUniqueID, HasRelationMetadata, HasFqn
):
name: str
source_name: str
source_description: str
loader: str
identifier: str
resource_type: NodeType = field(metadata={'restrict': [NodeType.Source]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Source]})
quoting: Quoting = field(default_factory=Quoting)
loaded_at_field: Optional[str] = None
freshness: Optional[FreshnessThreshold] = None
external: Optional[ExternalTable] = None
description: str = ''
description: str = ""
columns: Dict[str, ColumnInfo] = field(default_factory=dict)
meta: Dict[str, Any] = field(default_factory=dict)
source_meta: Dict[str, Any] = field(default_factory=dict)
@@ -614,38 +551,35 @@ class ParsedSourceDefinition(
patch_path: Optional[Path] = None
unrendered_config: Dict[str, Any] = field(default_factory=dict)
relation_name: Optional[str] = None
created_at: int = field(default_factory=lambda: int(time.time()))
def same_database_representation(
self, other: 'ParsedSourceDefinition'
) -> bool:
def same_database_representation(self, other: "ParsedSourceDefinition") -> bool:
return (
self.database == other.database and
self.schema == other.schema and
self.identifier == other.identifier and
True
self.database == other.database
and self.schema == other.schema
and self.identifier == other.identifier
and True
)
def same_quoting(self, other: 'ParsedSourceDefinition') -> bool:
def same_quoting(self, other: "ParsedSourceDefinition") -> bool:
return self.quoting == other.quoting
def same_freshness(self, other: 'ParsedSourceDefinition') -> bool:
def same_freshness(self, other: "ParsedSourceDefinition") -> bool:
return (
self.freshness == other.freshness and
self.loaded_at_field == other.loaded_at_field and
True
self.freshness == other.freshness
and self.loaded_at_field == other.loaded_at_field
and True
)
def same_external(self, other: 'ParsedSourceDefinition') -> bool:
def same_external(self, other: "ParsedSourceDefinition") -> bool:
return self.external == other.external
def same_config(self, old: 'ParsedSourceDefinition') -> bool:
def same_config(self, old: "ParsedSourceDefinition") -> bool:
return self.config.same_contents(
self.unrendered_config,
old.unrendered_config,
)
def same_contents(self, old: Optional['ParsedSourceDefinition']) -> bool:
def same_contents(self, old: Optional["ParsedSourceDefinition"]) -> bool:
# existing when it didn't before is a change!
if old is None:
return True
@@ -659,17 +593,17 @@ class ParsedSourceDefinition(
# metadata/tags changes are not "changes"
# patching/description changes are not "changes"
return (
self.same_database_representation(old) and
self.same_fqn(old) and
self.same_config(old) and
self.same_quoting(old) and
self.same_freshness(old) and
self.same_external(old) and
True
self.same_database_representation(old)
and self.same_fqn(old)
and self.same_config(old)
and self.same_quoting(old)
and self.same_freshness(old)
and self.same_external(old)
and True
)
def get_full_source_name(self):
return f'{self.source_name}_{self.name}'
return f"{self.source_name}_{self.name}"
def get_source_representation(self):
return f'source("{self.source.name}", "{self.table.name}")'
@@ -690,10 +624,6 @@ class ParsedSourceDefinition(
def depends_on_nodes(self):
return []
@property
def depends_on(self):
return DependsOn(macros=[], nodes=[])
@property
def refs(self):
return []
@@ -708,7 +638,7 @@ class ParsedSourceDefinition(
@property
def search_name(self):
return f'{self.source_name}.{self.name}'
return f"{self.source_name}.{self.name}"
@dataclass
@@ -717,15 +647,12 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
type: ExposureType
owner: ExposureOwner
resource_type: NodeType = NodeType.Exposure
description: str = ''
description: str = ""
maturity: Optional[MaturityType] = None
meta: Dict[str, Any] = field(default_factory=dict)
tags: List[str] = field(default_factory=list)
url: Optional[str] = None
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: int = field(default_factory=lambda: int(time.time()))
@property
def depends_on_nodes(self):
@@ -735,54 +662,46 @@ class ParsedExposure(UnparsedBaseNode, HasUniqueID, HasFqn):
def search_name(self):
return self.name
def same_depends_on(self, old: 'ParsedExposure') -> bool:
# no tags for now, but we could definitely add them
@property
def tags(self):
return []
def same_depends_on(self, old: "ParsedExposure") -> bool:
return set(self.depends_on.nodes) == set(old.depends_on.nodes)
def same_description(self, old: 'ParsedExposure') -> bool:
def same_description(self, old: "ParsedExposure") -> bool:
return self.description == old.description
def same_maturity(self, old: 'ParsedExposure') -> bool:
def same_maturity(self, old: "ParsedExposure") -> bool:
return self.maturity == old.maturity
def same_owner(self, old: 'ParsedExposure') -> bool:
def same_owner(self, old: "ParsedExposure") -> bool:
return self.owner == old.owner
def same_exposure_type(self, old: 'ParsedExposure') -> bool:
def same_exposure_type(self, old: "ParsedExposure") -> bool:
return self.type == old.type
def same_url(self, old: 'ParsedExposure') -> bool:
def same_url(self, old: "ParsedExposure") -> bool:
return self.url == old.url
def same_contents(self, old: Optional['ParsedExposure']) -> bool:
def same_contents(self, old: Optional["ParsedExposure"]) -> 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_fqn(old) and
self.same_exposure_type(old) and
self.same_owner(old) and
self.same_maturity(old) and
self.same_url(old) and
self.same_description(old) and
self.same_depends_on(old) and
True
self.same_fqn(old)
and self.same_exposure_type(old)
and self.same_owner(old)
and self.same_maturity(old)
and self.same_url(old)
and self.same_description(old)
and self.same_depends_on(old)
and True
)
ManifestNodes = Union[
ParsedAnalysisNode,
ParsedSingularTestNode,
ParsedHookNode,
ParsedModelNode,
ParsedRPCNode,
ParsedGenericTestNode,
ParsedSeedNode,
ParsedSnapshotNode,
]
ParsedResource = Union[
ParsedDocumentation,
ParsedMacro,

View File

@@ -4,13 +4,12 @@ from dbt.contracts.util import (
Mergeable,
Replaceable,
)
# trigger the PathEncoder
import dbt.helper_types # noqa:F401
from dbt.exceptions import CompilationException
from dbt.dataclass_schema import (
dbtClassMixin, StrEnum, ExtensibleDbtClassMixin
)
from dbt.dataclass_schema import dbtClassMixin, StrEnum, ExtensibleDbtClassMixin
from dataclasses import dataclass, field
from datetime import timedelta
@@ -25,10 +24,6 @@ class UnparsedBaseNode(dbtClassMixin, Replaceable):
path: str
original_file_path: str
@property
def file_id(self):
return f'{self.package_name}://{self.original_file_path}'
@dataclass
class HasSQL:
@@ -41,26 +36,25 @@ class HasSQL:
@dataclass
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]})
resource_type: NodeType = field(metadata={"restrict": [NodeType.Macro]})
@dataclass
class UnparsedNode(UnparsedBaseNode, HasSQL):
name: str
resource_type: NodeType = field(metadata={'restrict': [
NodeType.Model,
NodeType.Analysis,
NodeType.Test,
NodeType.Snapshot,
NodeType.Operation,
NodeType.Seed,
NodeType.RPCCall,
]})
resource_type: NodeType = field(
metadata={
"restrict": [
NodeType.Model,
NodeType.Analysis,
NodeType.Test,
NodeType.Snapshot,
NodeType.Operation,
NodeType.Seed,
NodeType.RPCCall,
]
}
)
@property
def search_name(self):
@@ -69,9 +63,7 @@ class UnparsedNode(UnparsedBaseNode, HasSQL):
@dataclass
class UnparsedRunHook(UnparsedNode):
resource_type: NodeType = field(
metadata={'restrict': [NodeType.Operation]}
)
resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
index: Optional[int] = None
@@ -81,10 +73,9 @@ class Docs(dbtClassMixin, Replaceable):
@dataclass
class HasDocs(AdditionalPropertiesMixin, ExtensibleDbtClassMixin,
Replaceable):
class HasDocs(AdditionalPropertiesMixin, ExtensibleDbtClassMixin, Replaceable):
name: str
description: str = ''
description: str = ""
meta: Dict[str, Any] = field(default_factory=dict)
data_type: Optional[str] = None
docs: Docs = field(default_factory=Docs)
@@ -125,23 +116,14 @@ class HasYamlMetadata(dbtClassMixin):
yaml_key: str
package_name: str
@property
def file_id(self):
return f'{self.package_name}://{self.original_file_path}'
@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
@@ -149,21 +131,21 @@ class UnparsedNodeUpdate(HasConfig, HasColumnTests, HasTests, HasYamlMetadata):
class MacroArgument(dbtClassMixin):
name: str
type: Optional[str] = None
description: str = ''
description: str = ""
@dataclass
class UnparsedMacroUpdate(HasConfig, HasDocs, HasYamlMetadata):
class UnparsedMacroUpdate(HasDocs, HasYamlMetadata):
arguments: List[MacroArgument] = field(default_factory=list)
class TimePeriod(StrEnum):
minute = 'minute'
hour = 'hour'
day = 'day'
minute = "minute"
hour = "hour"
day = "day"
def plural(self) -> str:
return str(self) + 's'
return str(self) + "s"
@dataclass
@@ -185,6 +167,7 @@ class FreshnessThreshold(dbtClassMixin, Mergeable):
def status(self, age: float) -> "dbt.contracts.results.FreshnessStatus":
from dbt.contracts.results import FreshnessStatus
if self.error_after and self.error_after.exceeded(age):
return FreshnessStatus.Error
elif self.warn_after and self.warn_after.exceeded(age):
@@ -197,24 +180,21 @@ class FreshnessThreshold(dbtClassMixin, Mergeable):
@dataclass
class AdditionalPropertiesAllowed(
AdditionalPropertiesMixin,
ExtensibleDbtClassMixin
):
class AdditionalPropertiesAllowed(AdditionalPropertiesMixin, ExtensibleDbtClassMixin):
_extra: Dict[str, Any] = field(default_factory=dict)
@dataclass
class ExternalPartition(AdditionalPropertiesAllowed, Replaceable):
name: str = ''
description: str = ''
data_type: str = ''
name: str = ""
description: str = ""
data_type: str = ""
meta: Dict[str, Any] = field(default_factory=dict)
def __post_init__(self):
if self.name == '' or self.data_type == '':
if self.name == "" or self.data_type == "":
raise CompilationException(
'External partition columns must have names and data types'
"External partition columns must have names and data types"
)
@@ -243,44 +223,39 @@ class UnparsedSourceTableDefinition(HasColumnTests, HasTests):
loaded_at_field: Optional[str] = None
identifier: Optional[str] = None
quoting: Quoting = field(default_factory=Quoting)
freshness: Optional[FreshnessThreshold] = field(
default_factory=FreshnessThreshold
)
freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
external: Optional[ExternalTable] = None
tags: List[str] = field(default_factory=list)
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
if 'freshness' not in dct and self.freshness is None:
dct['freshness'] = None
if "freshness" not in dct and self.freshness is None:
dct["freshness"] = None
return dct
@dataclass
class UnparsedSourceDefinition(dbtClassMixin, Replaceable):
name: str
description: str = ''
description: str = ""
meta: Dict[str, Any] = field(default_factory=dict)
database: Optional[str] = None
schema: Optional[str] = None
loader: str = ''
loader: str = ""
quoting: Quoting = field(default_factory=Quoting)
freshness: Optional[FreshnessThreshold] = field(
default_factory=FreshnessThreshold
)
freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
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':
return 'sources'
def yaml_key(self) -> "str":
return "sources"
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
if 'freshnewss' not in dct and self.freshness is None:
dct['freshness'] = None
if "freshnewss" not in dct and self.freshness is None:
dct["freshness"] = None
return dct
@@ -294,9 +269,7 @@ class SourceTablePatch(dbtClassMixin):
loaded_at_field: Optional[str] = None
identifier: Optional[str] = None
quoting: Quoting = field(default_factory=Quoting)
freshness: Optional[FreshnessThreshold] = field(
default_factory=FreshnessThreshold
)
freshness: Optional[FreshnessThreshold] = field(default_factory=FreshnessThreshold)
external: Optional[ExternalTable] = None
tags: Optional[List[str]] = None
tests: Optional[List[TestDef]] = None
@@ -304,13 +277,13 @@ class SourceTablePatch(dbtClassMixin):
def to_patch_dict(self) -> Dict[str, Any]:
dct = self.to_dict(omit_none=True)
remove_keys = ('name')
remove_keys = "name"
for key in remove_keys:
if key in dct:
del dct[key]
if self.freshness is None:
dct['freshness'] = None
dct["freshness"] = None
return dct
@@ -318,13 +291,13 @@ class SourceTablePatch(dbtClassMixin):
@dataclass
class SourcePatch(dbtClassMixin, Replaceable):
name: str = field(
metadata=dict(description='The name of the source to override'),
metadata=dict(description="The name of the source to override"),
)
overrides: str = field(
metadata=dict(description='The package of the source to override'),
metadata=dict(description="The package of the source to override"),
)
path: Path = field(
metadata=dict(description='The path to the patch-defining yml file'),
metadata=dict(description="The path to the patch-defining yml file"),
)
description: Optional[str] = None
meta: Optional[Dict[str, Any]] = None
@@ -341,13 +314,13 @@ class SourcePatch(dbtClassMixin, Replaceable):
def to_patch_dict(self) -> Dict[str, Any]:
dct = self.to_dict(omit_none=True)
remove_keys = ('name', 'overrides', 'tables', 'path')
remove_keys = ("name", "overrides", "tables", "path")
for key in remove_keys:
if key in dct:
del dct[key]
if self.freshness is None:
dct['freshness'] = None
dct["freshness"] = None
return dct
@@ -366,10 +339,6 @@ class UnparsedDocumentation(dbtClassMixin, Replaceable):
path: str
original_file_path: str
@property
def file_id(self):
return f'{self.package_name}://{self.original_file_path}'
@property
def resource_type(self):
return NodeType.Documentation
@@ -383,9 +352,9 @@ class UnparsedDocumentationFile(UnparsedDocumentation):
# can't use total_ordering decorator here, as str provides an ordering already
# and it's not the one we want.
class Maturity(StrEnum):
low = 'low'
medium = 'medium'
high = 'high'
low = "low"
medium = "medium"
high = "high"
def __lt__(self, other):
if not isinstance(other, Maturity):
@@ -410,17 +379,17 @@ class Maturity(StrEnum):
class ExposureType(StrEnum):
Dashboard = 'dashboard'
Notebook = 'notebook'
Analysis = 'analysis'
ML = 'ml'
Application = 'application'
Dashboard = "dashboard"
Notebook = "notebook"
Analysis = "analysis"
ML = "ml"
Application = "application"
class MaturityType(StrEnum):
Low = 'low'
Medium = 'medium'
High = 'high'
Low = "low"
Medium = "medium"
High = "high"
@dataclass
@@ -434,9 +403,7 @@ class UnparsedExposure(dbtClassMixin, Replaceable):
name: str
type: ExposureType
owner: ExposureOwner
description: str = ''
description: str = ""
maturity: Optional[MaturityType] = None
meta: Dict[str, Any] = field(default_factory=dict)
tags: List[str] = field(default_factory=list)
url: Optional[str] = None
depends_on: List[str] = field(default_factory=list)

View File

@@ -1,26 +1,30 @@
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,
dbtClassMixin,
ValidationError,
HyphenatedDbtClassMixin,
ExtensibleDbtClassMixin,
register_pattern, ValidatedStringMixin
register_pattern,
ValidatedStringMixin,
)
from dataclasses import dataclass, field
from typing import Optional, List, Dict, Union, Any
from mashumaro.types import SerializableType
PIN_PACKAGE_URL = 'https://docs.getdbt.com/docs/package-management#section-specifying-package-versions' # noqa
PIN_PACKAGE_URL = "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions" # noqa
DEFAULT_SEND_ANONYMOUS_USAGE_STATS = True
class Name(ValidatedStringMixin):
ValidationRegex = r'^[^\d\W]\w*$'
ValidationRegex = r"^[^\d\W]\w*$"
register_pattern(Name, r'^[^\d\W]\w*$')
register_pattern(Name, r"^[^\d\W]\w*$")
class SemverString(str, SerializableType):
@@ -28,7 +32,7 @@ class SemverString(str, SerializableType):
return self
@classmethod
def _deserialize(cls, value: str) -> 'SemverString':
def _deserialize(cls, value: str) -> "SemverString":
return SemverString(value)
@@ -37,7 +41,7 @@ class SemverString(str, SerializableType):
# 'semver lite'.
register_pattern(
SemverString,
r'^(?:0|[1-9]\d*)\.(?:0|[1-9]\d*)(\.(?:0|[1-9]\d*))?$',
r"^(?:0|[1-9]\d*)\.(?:0|[1-9]\d*)(\.(?:0|[1-9]\d*))?$",
)
@@ -68,7 +72,6 @@ class GitPackage(Package):
git: str
revision: Optional[RawVersion] = None
warn_unpinned: Optional[bool] = None
subdirectory: Optional[str] = None
def get_revisions(self) -> List[str]:
if self.revision is None:
@@ -81,7 +84,6 @@ class GitPackage(Package):
class RegistryPackage(Package):
package: str
version: Union[RawVersion, List[RawVersion]]
install_prerelease: Optional[bool] = False
def get_versions(self) -> List[str]:
if isinstance(self.version, list):
@@ -105,8 +107,7 @@ class ProjectPackageMetadata:
@classmethod
def from_project(cls, project):
return cls(name=project.project_name,
packages=project.packages.packages)
return cls(name=project.project_name, packages=project.packages.packages)
@dataclass
@@ -124,46 +125,46 @@ class RegistryPackageMetadata(
# A list of all the reserved words that packages may not have as names.
BANNED_PROJECT_NAMES = {
'_sql_results',
'adapter',
'api',
'column',
'config',
'context',
'database',
'env',
'env_var',
'exceptions',
'execute',
'flags',
'fromjson',
'fromyaml',
'graph',
'invocation_id',
'load_agate_table',
'load_result',
'log',
'model',
'modules',
'post_hooks',
'pre_hooks',
'ref',
'render',
'return',
'run_started_at',
'schema',
'source',
'sql',
'sql_now',
'store_result',
'store_raw_result',
'target',
'this',
'tojson',
'toyaml',
'try_or_compiler_error',
'var',
'write',
"_sql_results",
"adapter",
"api",
"column",
"config",
"context",
"database",
"env",
"env_var",
"exceptions",
"execute",
"flags",
"fromjson",
"fromyaml",
"graph",
"invocation_id",
"load_agate_table",
"load_result",
"log",
"model",
"modules",
"post_hooks",
"pre_hooks",
"ref",
"render",
"return",
"run_started_at",
"schema",
"source",
"sql",
"sql_now",
"store_result",
"store_raw_result",
"target",
"this",
"tojson",
"toyaml",
"try_or_compiler_error",
"var",
"write",
}
@@ -174,10 +175,8 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
config_version: int
project_root: Optional[str] = None
source_paths: Optional[List[str]] = None
model_paths: Optional[List[str]] = None
macro_paths: Optional[List[str]] = None
data_paths: Optional[List[str]] = None
seed_paths: Optional[List[str]] = None
test_paths: Optional[List[str]] = None
analysis_paths: Optional[List[str]] = None
docs_paths: Optional[List[str]] = None
@@ -187,22 +186,20 @@ 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)
require_dbt_version: Optional[Union[List[str], str]] = None
dispatch: List[Dict[str, Any]] = field(default_factory=list)
models: Dict[str, Any] = field(default_factory=dict)
seeds: Dict[str, Any] = field(default_factory=dict)
snapshots: Dict[str, Any] = field(default_factory=dict)
analyses: Dict[str, Any] = field(default_factory=dict)
sources: Dict[str, Any] = field(default_factory=dict)
tests: Dict[str, Any] = field(default_factory=dict)
vars: Optional[Dict[str, Any]] = field(
default=None,
metadata=dict(
description='map project names to their vars override dicts',
description="map project names to their vars override dicts",
),
)
packages: List[PackageSpec] = field(default_factory=list)
@@ -211,17 +208,10 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
@classmethod
def validate(cls, data):
super().validate(data)
if data['name'] in BANNED_PROJECT_NAMES:
if data["name"] in BANNED_PROJECT_NAMES:
raise ValidationError(
f"Invalid project name: {data['name']} is a reserved word"
)
# validate dispatch config
if 'dispatch' in data and data['dispatch']:
entries = data['dispatch']
for entry in entries:
if ('macro_namespace' not in entry or 'search_order' not in entry or
not isinstance(entry['search_order'], list)):
raise ValidationError(f"Invalid project dispatch config: {entry}")
@dataclass
@@ -230,21 +220,25 @@ class UserConfig(ExtensibleDbtClassMixin, Replaceable, UserConfigContract):
use_colors: Optional[bool] = None
partial_parse: Optional[bool] = None
printer_width: Optional[int] = None
write_json: Optional[bool] = None
warn_error: Optional[bool] = None
log_format: Optional[bool] = None
debug: Optional[bool] = None
version_check: Optional[bool] = None
fail_fast: Optional[bool] = None
use_experimental_parser: Optional[bool] = None
static_parser: Optional[bool] = None
def set_values(self, cookie_dir):
if self.send_anonymous_usage_stats:
tracking.initialize_tracking(cookie_dir)
else:
tracking.do_not_track()
if self.use_colors is not None:
ui.use_colors(self.use_colors)
if self.printer_width:
ui.printer_width(self.printer_width)
@dataclass
class ProfileConfig(HyphenatedDbtClassMixin, Replaceable):
profile_name: str = field(metadata={'preserve_underscore': True})
target_name: str = field(metadata={'preserve_underscore': True})
user_config: UserConfig = field(metadata={'preserve_underscore': True})
profile_name: str = field(metadata={"preserve_underscore": True})
target_name: str = field(metadata={"preserve_underscore": True})
config: UserConfig
threads: int
# TODO: make this a dynamic union of some kind?
credentials: Optional[Dict[str, Any]]
@@ -262,7 +256,7 @@ class ConfiguredQuoting(Quoting, Replaceable):
class Configuration(Project, ProfileConfig):
cli_vars: Dict[str, Any] = field(
default_factory=dict,
metadata={'preserve_underscore': True},
metadata={"preserve_underscore": True},
)
quoting: Optional[ConfiguredQuoting] = None

View File

@@ -1,29 +1,31 @@
from collections.abc import Mapping
from dataclasses import dataclass
from dataclasses import dataclass, fields
from typing import (
Optional, Dict,
Optional,
Dict,
)
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
class RelationType(StrEnum):
Table = 'table'
View = 'view'
CTE = 'cte'
MaterializedView = 'materializedview'
External = 'external'
Table = "table"
View = "view"
CTE = "cte"
MaterializedView = "materializedview"
External = "external"
class ComponentName(StrEnum):
Database = 'database'
Schema = 'schema'
Identifier = 'identifier'
Database = "database"
Schema = "schema"
Identifier = "identifier"
class HasQuoting(Protocol):
@@ -42,10 +44,13 @@ 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)
@@ -68,8 +73,7 @@ class Policy(FakeAPIObject):
return self.identifier
else:
raise ValueError(
'Got a key of {}, expected one of {}'
.format(key, list(ComponentName))
"Got a key of {}, expected one of {}".format(key, list(ComponentName))
)
def replace_dict(self, dct: Dict[ComponentName, bool]):
@@ -89,15 +93,15 @@ class Path(FakeAPIObject):
# handle pesky jinja2.Undefined sneaking in here and messing up rende
if not isinstance(self.database, (type(None), str)):
raise CompilationException(
'Got an invalid path database: {}'.format(self.database)
"Got an invalid path database: {}".format(self.database)
)
if not isinstance(self.schema, (type(None), str)):
raise CompilationException(
'Got an invalid path schema: {}'.format(self.schema)
"Got an invalid path schema: {}".format(self.schema)
)
if not isinstance(self.identifier, (type(None), str)):
raise CompilationException(
'Got an invalid path identifier: {}'.format(self.identifier)
"Got an invalid path identifier: {}".format(self.identifier)
)
def get_lowered_part(self, key: ComponentName) -> Optional[str]:
@@ -115,8 +119,7 @@ class Path(FakeAPIObject):
return self.identifier
else:
raise ValueError(
'Got a key of {}, expected one of {}'
.format(key, list(ComponentName))
"Got a key of {}, expected one of {}".format(key, list(ComponentName))
)
def replace_dict(self, dct: Dict[ComponentName, str]):

View File

@@ -1,7 +1,5 @@
from dbt.contracts.graph.manifest import CompileResultNode
from dbt.contracts.graph.unparsed import (
FreshnessThreshold
)
from dbt.contracts.graph.unparsed import FreshnessThreshold
from dbt.contracts.graph.parsed import ParsedSourceDefinition
from dbt.contracts.util import (
BaseArtifactMetadata,
@@ -24,7 +22,13 @@ import agate
from dataclasses import dataclass, field
from datetime import datetime
from typing import (
Union, Dict, List, Optional, Any, NamedTuple, Sequence,
Union,
Dict,
List,
Optional,
Any,
NamedTuple,
Sequence,
)
from dbt.clients.system import write_json
@@ -54,7 +58,7 @@ class collect_timing_info:
def __exit__(self, exc_type, exc_value, traceback):
self.timing_info.end()
with JsonOnly(), TimingProcessor(self.timing_info):
logger.debug('finished collecting timing info')
logger.debug("finished collecting timing info")
class NodeStatus(StrEnum):
@@ -78,7 +82,6 @@ class TestStatus(StrEnum):
Error = NodeStatus.Error
Fail = NodeStatus.Fail
Warn = NodeStatus.Warn
Skipped = NodeStatus.Skipped
class FreshnessStatus(StrEnum):
@@ -95,16 +98,13 @@ class BaseResult(dbtClassMixin):
thread_id: str
execution_time: float
adapter_response: Dict[str, Any]
message: Optional[str]
failures: Optional[int]
message: Optional[Union[str, int]]
@classmethod
def __pre_deserialize__(cls, data):
data = super().__pre_deserialize__(data)
if 'message' not in data:
data['message'] = None
if 'failures' not in data:
data['failures'] = None
if "message" not in data:
data["message"] = None
return data
@@ -116,9 +116,8 @@ class NodeResult(BaseResult):
@dataclass
class RunResult(NodeResult):
agate_table: Optional[agate.Table] = field(
default=None, metadata={
'serialize': lambda x: None, 'deserialize': lambda x: None
}
default=None,
metadata={"serialize": lambda x: None, "deserialize": lambda x: None},
)
@property
@@ -162,7 +161,6 @@ def process_run_result(result: RunResult) -> RunResultOutput:
execution_time=result.execution_time,
message=result.message,
adapter_response=result.adapter_response,
failures=result.failures
)
@@ -185,7 +183,7 @@ class RunExecutionResult(
@dataclass
@schema_version('run-results', 3)
@schema_version("run-results", 1)
class RunResultsArtifact(ExecutionResult, ArtifactMixin):
results: Sequence[RunResultOutput]
args: Dict[str, Any] = field(default_factory=dict)
@@ -207,7 +205,7 @@ class RunResultsArtifact(ExecutionResult, ArtifactMixin):
metadata=meta,
results=processed_results,
elapsed_time=elapsed_time,
args=args
args=args,
)
def write(self, path: str):
@@ -221,15 +219,14 @@ class RunOperationResult(ExecutionResult):
@dataclass
class RunOperationResultMetadata(BaseArtifactMetadata):
dbt_schema_version: str = field(default_factory=lambda: str(
RunOperationResultsArtifact.dbt_schema_version
))
dbt_schema_version: str = field(
default_factory=lambda: str(RunOperationResultsArtifact.dbt_schema_version)
)
@dataclass
@schema_version('run-operation-result', 1)
@schema_version("run-operation-result", 1)
class RunOperationResultsArtifact(RunOperationResult, ArtifactMixin):
@classmethod
def from_success(
cls,
@@ -248,6 +245,7 @@ class RunOperationResultsArtifact(RunOperationResult, ArtifactMixin):
success=success,
)
# due to issues with typing.Union collapsing subclasses, this can't subclass
# PartialResult
@@ -266,7 +264,7 @@ class SourceFreshnessResult(NodeResult):
class FreshnessErrorEnum(StrEnum):
runtime_error = 'runtime error'
runtime_error = "runtime error"
@dataclass
@@ -285,9 +283,6 @@ class SourceFreshnessOutput(dbtClassMixin):
status: FreshnessStatus
criteria: FreshnessThreshold
adapter_response: Dict[str, Any]
timing: List[TimingInfo]
thread_id: str
execution_time: float
@dataclass
@@ -299,14 +294,11 @@ class PartialSourceFreshnessResult(NodeResult):
return False
FreshnessNodeResult = Union[PartialSourceFreshnessResult,
SourceFreshnessResult]
FreshnessNodeResult = Union[PartialSourceFreshnessResult, SourceFreshnessResult]
FreshnessNodeOutput = Union[SourceFreshnessRuntimeError, SourceFreshnessOutput]
def process_freshness_result(
result: FreshnessNodeResult
) -> FreshnessNodeOutput:
def process_freshness_result(result: FreshnessNodeResult) -> FreshnessNodeOutput:
unique_id = result.node.unique_id
if result.status == FreshnessStatus.RuntimeErr:
return SourceFreshnessRuntimeError(
@@ -318,16 +310,15 @@ def process_freshness_result(
# we know that this must be a SourceFreshnessResult
if not isinstance(result, SourceFreshnessResult):
raise InternalException(
'Got {} instead of a SourceFreshnessResult for a '
'non-error result in freshness execution!'
.format(type(result))
"Got {} instead of a SourceFreshnessResult for a "
"non-error result in freshness execution!".format(type(result))
)
# if we're here, we must have a non-None freshness threshold
criteria = result.node.freshness
if criteria is None:
raise InternalException(
'Somehow evaluated a freshness result for a source '
'that has no freshness criteria!'
"Somehow evaluated a freshness result for a source "
"that has no freshness criteria!"
)
return SourceFreshnessOutput(
unique_id=unique_id,
@@ -337,18 +328,13 @@ def process_freshness_result(
status=result.status,
criteria=criteria,
adapter_response=result.adapter_response,
timing=result.timing,
thread_id=result.thread_id,
execution_time=result.execution_time,
)
@dataclass
class FreshnessMetadata(BaseArtifactMetadata):
dbt_schema_version: str = field(
default_factory=lambda: str(
FreshnessExecutionResultArtifact.dbt_schema_version
)
default_factory=lambda: str(FreshnessExecutionResultArtifact.dbt_schema_version)
)
@@ -369,7 +355,7 @@ class FreshnessResult(ExecutionResult):
@dataclass
@schema_version('sources', 2)
@schema_version("sources", 1)
class FreshnessExecutionResultArtifact(
ArtifactMixin,
VersionedSchema,
@@ -389,11 +375,9 @@ class FreshnessExecutionResultArtifact(
Primitive = Union[bool, str, float, None]
PrimitiveDict = Dict[str, Primitive]
CatalogKey = NamedTuple(
'CatalogKey',
[('database', Optional[str]), ('schema', str), ('name', str)]
"CatalogKey", [("database", Optional[str]), ("schema", str), ("name", str)]
)
@@ -462,13 +446,13 @@ class CatalogResults(dbtClassMixin):
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
if '_compile_results' in dct:
del dct['_compile_results']
if "_compile_results" in dct:
del dct["_compile_results"]
return dct
@dataclass
@schema_version('catalog', 1)
@schema_version("catalog", 1)
class CatalogArtifact(CatalogResults, ArtifactMixin):
metadata: CatalogMetadata
@@ -479,8 +463,8 @@ class CatalogArtifact(CatalogResults, ArtifactMixin):
nodes: Dict[str, CatalogTable],
sources: Dict[str, CatalogTable],
compile_results: Optional[Any],
errors: Optional[List[str]]
) -> 'CatalogArtifact':
errors: Optional[List[str]],
) -> "CatalogArtifact":
meta = CatalogMetadata(generated_at=generated_at)
return cls(
metadata=meta,

View File

@@ -10,7 +10,9 @@ 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,
RunResult,
RunResultsArtifact,
TimingInfo,
CatalogArtifact,
CatalogResults,
ExecutionResult,
@@ -40,10 +42,10 @@ class RPCParameters(dbtClassMixin):
@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
if "timeout" not in data:
data["timeout"] = None
if "task_tags" not in data:
data["task_tags"] = None
return data
@@ -58,28 +60,15 @@ class RPCExecParameters(RPCParameters):
class RPCCompileParameters(RPCParameters):
threads: Optional[int] = None
models: Union[None, str, List[str]] = None
select: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
selector: Optional[str] = None
state: Optional[str] = None
@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'
output_keys: Optional[List[str]] = None
@dataclass
class RPCRunParameters(RPCParameters):
threads: Optional[int] = None
models: Union[None, str, List[str]] = None
select: Union[None, str, List[str]] = None
exclude: Union[None, str, List[str]] = None
selector: Optional[str] = None
state: Optional[str] = None
@@ -119,17 +108,6 @@ class RPCDocsGenerateParameters(RPCParameters):
state: Optional[str] = None
@dataclass
class RPCBuildParameters(RPCParameters):
resource_types: Optional[List[str]] = None
select: Union[None, str, List[str]] = None
threads: Optional[int] = 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
@@ -185,6 +163,7 @@ class GCParameters(RPCParameters):
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
@@ -200,14 +179,13 @@ class RPCRunOperationParameters(RPCParameters):
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
@@ -217,20 +195,13 @@ class RemoteResult(VersionedSchema):
@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)
@schema_version("remote-deps-result", 1)
class RemoteDepsResult(RemoteResult):
generated_at: datetime = field(default_factory=datetime.utcnow)
@dataclass
@schema_version('remote-catalog-result', 1)
@schema_version("remote-catalog-result", 1)
class RemoteCatalogResults(CatalogResults, RemoteResult):
generated_at: datetime = field(default_factory=datetime.utcnow)
@@ -254,7 +225,7 @@ class RemoteCompileResultMixin(RemoteResult):
@dataclass
@schema_version('remote-compile-result', 1)
@schema_version("remote-compile-result", 1)
class RemoteCompileResult(RemoteCompileResultMixin):
generated_at: datetime = field(default_factory=datetime.utcnow)
@@ -264,7 +235,7 @@ class RemoteCompileResult(RemoteCompileResultMixin):
@dataclass
@schema_version('remote-execution-result', 1)
@schema_version("remote-execution-result", 1)
class RemoteExecutionResult(ExecutionResult, RemoteResult):
results: Sequence[RunResult]
args: Dict[str, Any] = field(default_factory=dict)
@@ -284,7 +255,7 @@ class RemoteExecutionResult(ExecutionResult, RemoteResult):
cls,
base: RunExecutionResult,
logs: List[LogMessage],
) -> 'RemoteExecutionResult':
) -> "RemoteExecutionResult":
return cls(
generated_at=base.generated_at,
results=base.results,
@@ -301,7 +272,7 @@ class ResultTable(dbtClassMixin):
@dataclass
@schema_version('remote-run-operation-result', 1)
@schema_version("remote-run-operation-result", 1)
class RemoteRunOperationResult(RunOperationResult, RemoteResult):
generated_at: datetime = field(default_factory=datetime.utcnow)
@@ -310,7 +281,7 @@ class RemoteRunOperationResult(RunOperationResult, RemoteResult):
cls,
base: RunOperationResultsArtifact,
logs: List[LogMessage],
) -> 'RemoteRunOperationResult':
) -> "RemoteRunOperationResult":
return cls(
generated_at=base.metadata.generated_at,
results=base.results,
@@ -329,15 +300,14 @@ class RemoteRunOperationResult(RunOperationResult, RemoteResult):
@dataclass
@schema_version('remote-freshness-result', 1)
@schema_version("remote-freshness-result", 1)
class RemoteFreshnessResult(FreshnessResult, RemoteResult):
@classmethod
def from_local_result(
cls,
base: FreshnessResult,
logs: List[LogMessage],
) -> 'RemoteFreshnessResult':
) -> "RemoteFreshnessResult":
return cls(
metadata=base.metadata,
results=base.results,
@@ -351,7 +321,7 @@ class RemoteFreshnessResult(FreshnessResult, RemoteResult):
@dataclass
@schema_version('remote-run-result', 1)
@schema_version("remote-run-result", 1)
class RemoteRunResult(RemoteCompileResultMixin):
table: ResultTable
generated_at: datetime = field(default_factory=datetime.utcnow)
@@ -369,14 +339,15 @@ RPCResult = Union[
# GC types
class GCResultState(StrEnum):
Deleted = 'deleted' # successful GC
Missing = 'missing' # nothing to GC
Running = 'running' # can't GC
Deleted = "deleted" # successful GC
Missing = "missing" # nothing to GC
Running = "running" # can't GC
@dataclass
@schema_version('remote-gc-result', 1)
@schema_version("remote-gc-result", 1)
class GCResult(RemoteResult):
logs: List[LogMessage] = field(default_factory=list)
deleted: List[TaskID] = field(default_factory=list)
@@ -391,21 +362,20 @@ class GCResult(RemoteResult):
elif state == GCResultState.Deleted:
self.deleted.append(task_id)
else:
raise InternalException(
f'Got invalid state in add_result: {state}'
)
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'
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:
@@ -413,7 +383,7 @@ class TaskHandlerState(StrEnum):
NotStarted < Initializing < Running < (Success, Error, Killed, Failed)
"""
if not isinstance(other, TaskHandlerState):
raise TypeError('cannot compare to non-TaskHandlerState')
raise TypeError("cannot compare to non-TaskHandlerState")
order = (self.NotStarted, self.Initializing, self.Running)
smaller = set()
for value in order:
@@ -425,13 +395,11 @@ class TaskHandlerState(StrEnum):
def __le__(self, other) -> bool:
# so that ((Success <= Error) is True)
return ((self < other) or
(self == other) or
(self.finished and other.finished))
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')
raise TypeError("cannot compare to non-TaskHandlerState")
order = (self.NotStarted, self.Initializing, self.Running)
smaller = set()
for value in order:
@@ -442,9 +410,7 @@ class TaskHandlerState(StrEnum):
def __ge__(self, other) -> bool:
# so that ((Success <= Error) is True)
return ((self > other) or
(self == other) or
(self.finished and other.finished))
return (self > other) or (self == other) or (self.finished and other.finished)
@property
def finished(self) -> bool:
@@ -463,7 +429,7 @@ class TaskTiming(dbtClassMixin):
@classmethod
def __pre_deserialize__(cls, data):
data = super().__pre_deserialize__(data)
for field_name in ('start', 'end', 'elapsed'):
for field_name in ("start", "end", "elapsed"):
if field_name not in data:
data[field_name] = None
return data
@@ -480,27 +446,27 @@ class TaskRow(TaskTiming):
@dataclass
@schema_version('remote-ps-result', 1)
@schema_version("remote-ps-result", 1)
class PSResult(RemoteResult):
rows: List[TaskRow]
class KillResultStatus(StrEnum):
Missing = 'missing'
NotStarted = 'not_started'
Killed = 'killed'
Finished = 'finished'
Missing = "missing"
NotStarted = "not_started"
Killed = "killed"
Finished = "finished"
@dataclass
@schema_version('remote-kill-result', 1)
@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)
@schema_version("remote-manifest-result", 1)
class GetManifestResult(RemoteResult):
manifest: Optional[WritableManifest] = None
@@ -531,29 +497,28 @@ class PollResult(RemoteResult, TaskTiming):
@classmethod
def __pre_deserialize__(cls, data):
data = super().__pre_deserialize__(data)
for field_name in ('start', 'end', 'elapsed'):
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)
@schema_version("poll-remote-deps-result", 1)
class PollRemoteEmptyCompleteResult(PollResult, RemoteResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
)
generated_at: datetime = field(default_factory=datetime.utcnow)
@classmethod
def from_result(
cls: Type['PollRemoteEmptyCompleteResult'],
cls: Type["PollRemoteEmptyCompleteResult"],
base: RemoteDepsResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollRemoteEmptyCompleteResult':
) -> "PollRemoteEmptyCompleteResult":
return cls(
logs=logs,
tags=tags,
@@ -561,12 +526,12 @@ class PollRemoteEmptyCompleteResult(PollResult, RemoteResult):
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
generated_at=base.generated_at
generated_at=base.generated_at,
)
@dataclass
@schema_version('poll-remote-killed-result', 1)
@schema_version("poll-remote-killed-result", 1)
class PollKilledResult(PollResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Killed),
@@ -574,24 +539,23 @@ class PollKilledResult(PollResult):
@dataclass
@schema_version('poll-remote-execution-result', 1)
@schema_version("poll-remote-execution-result", 1)
class PollExecuteCompleteResult(
RemoteExecutionResult,
PollResult,
):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollExecuteCompleteResult'],
cls: Type["PollExecuteCompleteResult"],
base: RemoteExecutionResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollExecuteCompleteResult':
) -> "PollExecuteCompleteResult":
return cls(
results=base.results,
elapsed_time=base.elapsed_time,
@@ -606,24 +570,23 @@ class PollExecuteCompleteResult(
@dataclass
@schema_version('poll-remote-compile-result', 1)
@schema_version("poll-remote-compile-result", 1)
class PollCompileCompleteResult(
RemoteCompileResult,
PollResult,
):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollCompileCompleteResult'],
cls: Type["PollCompileCompleteResult"],
base: RemoteCompileResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollCompileCompleteResult':
) -> "PollCompileCompleteResult":
return cls(
raw_sql=base.raw_sql,
compiled_sql=base.compiled_sql,
@@ -635,29 +598,28 @@ class PollCompileCompleteResult(
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
generated_at=base.generated_at
generated_at=base.generated_at,
)
@dataclass
@schema_version('poll-remote-run-result', 1)
@schema_version("poll-remote-run-result", 1)
class PollRunCompleteResult(
RemoteRunResult,
PollResult,
):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollRunCompleteResult'],
cls: Type["PollRunCompleteResult"],
base: RemoteRunResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollRunCompleteResult':
) -> "PollRunCompleteResult":
return cls(
raw_sql=base.raw_sql,
compiled_sql=base.compiled_sql,
@@ -670,29 +632,28 @@ class PollRunCompleteResult(
start=timing.start,
end=timing.end,
elapsed=timing.elapsed,
generated_at=base.generated_at
generated_at=base.generated_at,
)
@dataclass
@schema_version('poll-remote-run-operation-result', 1)
@schema_version("poll-remote-run-operation-result", 1)
class PollRunOperationCompleteResult(
RemoteRunOperationResult,
PollResult,
):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollRunOperationCompleteResult'],
cls: Type["PollRunOperationCompleteResult"],
base: RemoteRunOperationResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollRunOperationCompleteResult':
) -> "PollRunOperationCompleteResult":
return cls(
success=base.success,
results=base.results,
@@ -708,21 +669,20 @@ class PollRunOperationCompleteResult(
@dataclass
@schema_version('poll-remote-catalog-result', 1)
@schema_version("poll-remote-catalog-result", 1)
class PollCatalogCompleteResult(RemoteCatalogResults, PollResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollCatalogCompleteResult'],
cls: Type["PollCatalogCompleteResult"],
base: RemoteCatalogResults,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollCatalogCompleteResult':
) -> "PollCatalogCompleteResult":
return cls(
nodes=base.nodes,
sources=base.sources,
@@ -739,27 +699,26 @@ class PollCatalogCompleteResult(RemoteCatalogResults, PollResult):
@dataclass
@schema_version('poll-remote-in-progress-result', 1)
@schema_version("poll-remote-in-progress-result", 1)
class PollInProgressResult(PollResult):
pass
@dataclass
@schema_version('poll-remote-get-manifest-result', 1)
@schema_version("poll-remote-get-manifest-result", 1)
class PollGetManifestResult(GetManifestResult, PollResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollGetManifestResult'],
cls: Type["PollGetManifestResult"],
base: GetManifestResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollGetManifestResult':
) -> "PollGetManifestResult":
return cls(
manifest=base.manifest,
logs=logs,
@@ -772,21 +731,20 @@ class PollGetManifestResult(GetManifestResult, PollResult):
@dataclass
@schema_version('poll-remote-freshness-result', 1)
@schema_version("poll-remote-freshness-result", 1)
class PollFreshnessResult(RemoteFreshnessResult, PollResult):
state: TaskHandlerState = field(
metadata=restrict_to(TaskHandlerState.Success,
TaskHandlerState.Failed),
metadata=restrict_to(TaskHandlerState.Success, TaskHandlerState.Failed),
)
@classmethod
def from_result(
cls: Type['PollFreshnessResult'],
cls: Type["PollFreshnessResult"],
base: RemoteFreshnessResult,
tags: TaskTags,
timing: TaskTiming,
logs: List[LogMessage],
) -> 'PollFreshnessResult':
) -> "PollFreshnessResult":
return cls(
logs=logs,
tags=tags,
@@ -799,18 +757,19 @@ class PollFreshnessResult(RemoteFreshnessResult, PollResult):
elapsed_time=base.elapsed_time,
)
# Manifest parsing types
class ManifestStatus(StrEnum):
Init = 'init'
Compiling = 'compiling'
Ready = 'ready'
Error = 'error'
Init = "init"
Compiling = "compiling"
Ready = "ready"
Error = "error"
@dataclass
@schema_version('remote-status-result', 1)
@schema_version("remote-status-result", 1)
class LastParse(RemoteResult):
state: ManifestStatus = ManifestStatus.Init
logs: List[LogMessage] = field(default_factory=list)

View File

@@ -8,8 +8,7 @@ from typing import List, Dict, Any, Union
class SelectorDefinition(dbtClassMixin):
name: str
definition: Union[str, Dict[str, Any]]
description: str = ''
default: bool = False
description: str = ""
@dataclass

View File

@@ -1,6 +1,5 @@
from pathlib import Path
from .graph.manifest import WritableManifest
from .results import RunResultsArtifact
from typing import Optional
from dbt.exceptions import IncompatibleSchemaException
@@ -9,20 +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'
manifest_path = self.path / "manifest.json"
if manifest_path.exists() and manifest_path.is_file():
try:
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:
self.results = RunResultsArtifact.read(str(results_path))
except IncompatibleSchemaException as exc:
exc.add_filename(str(results_path))
raise

View File

@@ -1,9 +1,7 @@
import dataclasses
import os
from datetime import datetime
from typing import (
List, Tuple, ClassVar, Type, TypeVar, Dict, Any, Optional
)
from typing import List, Tuple, ClassVar, Type, TypeVar, Dict, Any, Optional
from dbt.clients.system import write_json, read_json
from dbt.exceptions import (
@@ -14,6 +12,7 @@ from dbt.version import __version__
from dbt.tracking import get_invocation_id
from dbt.dataclass_schema import dbtClassMixin
MacroKey = Tuple[str, str]
SourceKey = Tuple[str, str]
@@ -56,9 +55,7 @@ class Mergeable(Replaceable):
class Writable:
def write(self, path: str):
write_json(
path, self.to_dict(omit_none=False) # type: ignore
)
write_json(path, self.to_dict(omit_none=False)) # type: ignore
class AdditionalPropertiesMixin:
@@ -67,6 +64,7 @@ class AdditionalPropertiesMixin:
The underlying class definition must include a type definition for a field
named '_extra' that is of type `Dict[str, Any]`.
"""
ADDITIONAL_PROPERTIES = True
# This takes attributes in the dictionary that are
@@ -85,10 +83,10 @@ class AdditionalPropertiesMixin:
cls_keys = cls._get_field_names()
new_dict = {}
for key, value in data.items():
if key not in cls_keys and key != '_extra':
if '_extra' not in new_dict:
new_dict['_extra'] = {}
new_dict['_extra'][key] = value
if key not in cls_keys and key != "_extra":
if "_extra" not in new_dict:
new_dict["_extra"] = {}
new_dict["_extra"][key] = value
else:
new_dict[key] = value
data = new_dict
@@ -98,8 +96,8 @@ class AdditionalPropertiesMixin:
def __post_serialize__(self, dct):
data = super().__post_serialize__(dct)
data.update(self.extra)
if '_extra' in data:
del data['_extra']
if "_extra" in data:
del data["_extra"]
return data
def replace(self, **kwargs):
@@ -125,8 +123,8 @@ class Readable:
return cls.from_dict(data) # type: ignore
BASE_SCHEMAS_URL = 'https://schemas.getdbt.com/'
SCHEMA_PATH = 'dbt/{name}/v{version}.json'
BASE_SCHEMAS_URL = "https://schemas.getdbt.com/"
SCHEMA_PATH = "dbt/{name}/v{version}.json"
@dataclasses.dataclass
@@ -136,24 +134,22 @@ class SchemaVersion:
@property
def path(self) -> str:
return SCHEMA_PATH.format(
name=self.name,
version=self.version
)
return SCHEMA_PATH.format(name=self.name, version=self.version)
def __str__(self) -> str:
return BASE_SCHEMAS_URL + self.path
SCHEMA_VERSION_KEY = 'dbt_schema_version'
SCHEMA_VERSION_KEY = "dbt_schema_version"
METADATA_ENV_PREFIX = 'DBT_ENV_CUSTOM_ENV_'
METADATA_ENV_PREFIX = "DBT_ENV_CUSTOM_ENV_"
def get_metadata_env() -> Dict[str, str]:
return {
k[len(METADATA_ENV_PREFIX):]: v for k, v in os.environ.items()
k[len(METADATA_ENV_PREFIX) :]: v
for k, v in os.environ.items()
if k.startswith(METADATA_ENV_PREFIX)
}
@@ -162,20 +158,10 @@ def get_metadata_env() -> Dict[str, str]:
class BaseArtifactMetadata(dbtClassMixin):
dbt_schema_version: str
dbt_version: str = __version__
generated_at: datetime = dataclasses.field(
default_factory=datetime.utcnow
)
invocation_id: Optional[str] = dataclasses.field(
default_factory=get_invocation_id
)
generated_at: datetime = dataclasses.field(default_factory=datetime.utcnow)
invocation_id: Optional[str] = dataclasses.field(default_factory=get_invocation_id)
env: Dict[str, str] = dataclasses.field(default_factory=get_metadata_env)
def __post_serialize__(self, dct):
dct = super().__post_serialize__(dct)
if dct['generated_at'] and dct['generated_at'].endswith('+00:00'):
dct['generated_at'] = dct['generated_at'].replace('+00:00', '') + "Z"
return dct
def schema_version(name: str, version: int):
def inner(cls: Type[VersionedSchema]):
@@ -184,6 +170,7 @@ def schema_version(name: str, version: int):
version=version,
)
return cls
return inner
@@ -195,11 +182,11 @@ class VersionedSchema(dbtClassMixin):
def json_schema(cls, embeddable: bool = False) -> Dict[str, Any]:
result = super().json_schema(embeddable=embeddable)
if not embeddable:
result['$id'] = str(cls.dbt_schema_version)
result["$id"] = str(cls.dbt_schema_version)
return result
T = TypeVar('T', bound='ArtifactMixin')
T = TypeVar("T", bound="ArtifactMixin")
# metadata should really be a Generic[T_M] where T_M is a TypeVar bound to
@@ -213,6 +200,4 @@ class ArtifactMixin(VersionedSchema, Writable, Readable):
def validate(cls, data):
super().validate(data)
if cls.dbt_schema_version is None:
raise InternalException(
'Cannot call from_dict with no schema version!'
)
raise InternalException("Cannot call from_dict with no schema version!")

View File

@@ -1,5 +1,7 @@
from typing import (
Type, ClassVar, cast,
Type,
ClassVar,
cast,
)
import re
from dataclasses import fields
@@ -11,9 +13,7 @@ from hologram import JsonSchemaMixin, FieldEncoder, ValidationError
# type: ignore
from mashumaro import DataClassDictMixin
from mashumaro.config import (
TO_DICT_ADD_OMIT_NONE_FLAG, BaseConfig as MashBaseConfig
)
from mashumaro.config import TO_DICT_ADD_OMIT_NONE_FLAG, BaseConfig as MashBaseConfig
from mashumaro.types import SerializableType, SerializationStrategy
@@ -26,9 +26,7 @@ class DateTimeSerialization(SerializationStrategy):
return out
def deserialize(self, value):
return (
value if isinstance(value, datetime) else parse(cast(str, value))
)
return value if isinstance(value, datetime) else parse(cast(str, value))
# This class pulls in both JsonSchemaMixin from Hologram and
@@ -38,8 +36,8 @@ class DateTimeSerialization(SerializationStrategy):
# come from Hologram.
class dbtClassMixin(DataClassDictMixin, JsonSchemaMixin):
"""Mixin which adds methods to generate a JSON schema and
convert to and from JSON encodable dicts with validation
against the schema
convert to and from JSON encodable dicts with validation
against the schema
"""
class Config(MashBaseConfig):
@@ -60,8 +58,8 @@ class dbtClassMixin(DataClassDictMixin, JsonSchemaMixin):
if self._hyphenated:
new_dict = {}
for key in dct:
if '_' in key:
new_key = key.replace('_', '-')
if "_" in key:
new_key = key.replace("_", "-")
new_dict[new_key] = dct[key]
else:
new_dict[key] = dct[key]
@@ -73,13 +71,11 @@ class dbtClassMixin(DataClassDictMixin, JsonSchemaMixin):
# performing the conversion to a dict
@classmethod
def __pre_deserialize__(cls, data):
# `data` might not be a dict, e.g. for `query_comment`, which accepts
# a dict or a string; only snake-case for dict values.
if cls._hyphenated and isinstance(data, dict):
if cls._hyphenated:
new_dict = {}
for key in data:
if '-' in key:
new_key = key.replace('-', '_')
if "-" in key:
new_key = key.replace("-", "_")
new_dict[new_key] = data[key]
else:
new_dict[key] = data[key]
@@ -91,16 +87,16 @@ class dbtClassMixin(DataClassDictMixin, JsonSchemaMixin):
# hologram and in mashumaro.
def _local_to_dict(self, **kwargs):
args = {}
if 'omit_none' in kwargs:
args['omit_none'] = kwargs['omit_none']
if "omit_none" in kwargs:
args["omit_none"] = kwargs["omit_none"]
return self.to_dict(**args)
class ValidatedStringMixin(str, SerializableType):
ValidationRegex = ''
ValidationRegex = ""
@classmethod
def _deserialize(cls, value: str) -> 'ValidatedStringMixin':
def _deserialize(cls, value: str) -> "ValidatedStringMixin":
cls.validate(value)
return ValidatedStringMixin(value)

View File

@@ -14,58 +14,99 @@ class DBTDeprecation:
def name(self) -> str:
if self._name is not None:
return self._name
raise NotImplementedError(
'name not implemented for {}'.format(self)
)
raise NotImplementedError("name not implemented for {}".format(self))
def track_deprecation_warn(self) -> None:
if dbt.tracking.active_user is not None:
dbt.tracking.track_deprecation_warn({
"deprecation_name": self.name
})
dbt.tracking.track_deprecation_warn({"deprecation_name": self.name})
@property
def description(self) -> str:
if self._description is not None:
return self._description
raise NotImplementedError(
'description not implemented for {}'.format(self)
)
raise NotImplementedError("description not implemented for {}".format(self))
def show(self, *args, **kwargs) -> None:
if self.name not in active_deprecations:
desc = self.description.format(**kwargs)
msg = ui.line_wrap_message(
desc, prefix='* Deprecation Warning: '
)
msg = ui.line_wrap_message(desc, prefix="* Deprecation Warning: ")
dbt.exceptions.warn_or_error(msg)
self.track_deprecation_warn()
active_deprecations.add(self.name)
class PackageRedirectDeprecation(DBTDeprecation):
_name = 'package-redirect'
_description = '''\
The `{old_name}` package is deprecated in favor of `{new_name}`. Please update
your `packages.yml` configuration to use `{new_name}` instead.
'''
class MaterializationReturnDeprecation(DBTDeprecation):
_name = "materialization-return"
_description = """\
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.
class PackageInstallPathDeprecation(DBTDeprecation):
_name = 'install-packages-path'
_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.
'''
For more information, see:
https://docs.getdbt.com/v0.15/docs/creating-new-materializations#section-6-returning-relations
"""
class ConfigPathDeprecation(DBTDeprecation):
_name = 'project_config_path'
_description = '''\
The `{deprecated_path}` config has been deprecated in favor of `{exp_path}`.
Please update your `dbt_project.yml` configuration to reflect this change.
'''
class NotADictionaryDeprecation(DBTDeprecation):
_name = "not-a-dictionary"
_description = """\
The object ("{obj}") was used as a dictionary. In a future version of dbt
this capability will be removed from objects of this type.
"""
class ColumnQuotingDeprecation(DBTDeprecation):
_name = "column-quoting-unset"
_description = """\
The quote_columns parameter was not set for seeds, so the default value of
False was chosen. The default will change to True in a future release.
For more information, see:
https://docs.getdbt.com/v0.15/docs/seeds#section-specify-column-quoting
"""
class ModelsKeyNonModelDeprecation(DBTDeprecation):
_name = "models-key-mismatch"
_description = """\
"{node.name}" is a {node.resource_type} node, but it is specified in
the {patch.yaml_key} section of {patch.original_file_path}.
To fix this warning, place the `{node.name}` specification under
the {expected_key} key instead.
This warning will become an error in a future release.
"""
class ExecuteMacrosReleaseDeprecation(DBTDeprecation):
_name = "execute-macro-release"
_description = """\
The "release" argument to execute_macro is now ignored, and will be removed
in a future relase of dbt. At that time, providing a `release` argument
will result in an error.
"""
class AdapterMacroDeprecation(DBTDeprecation):
_name = "adapter-macro"
_description = """\
The "adapter_macro" macro has been deprecated. Instead, use the
`adapter.dispatch` method to find a macro and call the result.
adapter_macro was called for: {macro_name}
"""
_adapter_renamed_description = """\
@@ -79,11 +120,11 @@ Documentation for {new_name} can be found here:
def renamed_method(old_name: str, new_name: str):
class AdapterDeprecationWarning(DBTDeprecation):
_name = 'adapter:{}'.format(old_name)
_description = _adapter_renamed_description.format(old_name=old_name,
new_name=new_name)
_name = "adapter:{}".format(old_name)
_description = _adapter_renamed_description.format(
old_name=old_name, new_name=new_name
)
dep = AdapterDeprecationWarning()
deprecations_list.append(dep)
@@ -93,9 +134,7 @@ def renamed_method(old_name: str, new_name: str):
def warn(name, *args, **kwargs):
if name not in deprecations:
# this should (hopefully) never happen
raise RuntimeError(
"Error showing deprecation warning: {}".format(name)
)
raise RuntimeError("Error showing deprecation warning: {}".format(name))
deprecations[name].show(*args, **kwargs)
@@ -106,14 +145,15 @@ def warn(name, *args, **kwargs):
active_deprecations: Set[str] = set()
deprecations_list: List[DBTDeprecation] = [
ConfigPathDeprecation(),
PackageInstallPathDeprecation(),
PackageRedirectDeprecation()
MaterializationReturnDeprecation(),
NotADictionaryDeprecation(),
ColumnQuotingDeprecation(),
ModelsKeyNonModelDeprecation(),
ExecuteMacrosReleaseDeprecation(),
AdapterMacroDeprecation(),
]
deprecations: Dict[str, DBTDeprecation] = {
d.name: d for d in deprecations_list
}
deprecations: Dict[str, DBTDeprecation] = {d.name: d for d in deprecations_list}
def reset_deprecations():

112
core/dbt/deps/__init__.py Normal file
View File

@@ -0,0 +1,112 @@
import abc
import os
import tempfile
from contextlib import contextmanager
from typing import List, Optional, Generic, TypeVar
from dbt.clients import system
from dbt.contracts.project import ProjectPackageMetadata
from dbt.logger import GLOBAL_LOGGER as logger
DOWNLOADS_PATH = None
def get_downloads_path():
return DOWNLOADS_PATH
@contextmanager
def downloads_directory():
global DOWNLOADS_PATH
remove_downloads = False
# the user might have set an environment variable. Set it to that, and do
# not remove it when finished.
if DOWNLOADS_PATH is None:
DOWNLOADS_PATH = os.getenv("DBT_DOWNLOADS_DIR")
remove_downloads = False
# if we are making a per-run temp directory, remove it at the end of
# successful runs
if DOWNLOADS_PATH is None:
DOWNLOADS_PATH = tempfile.mkdtemp(prefix="dbt-downloads-")
remove_downloads = True
system.make_directory(DOWNLOADS_PATH)
logger.debug("Set downloads directory='{}'".format(DOWNLOADS_PATH))
yield DOWNLOADS_PATH
if remove_downloads:
system.rmtree(DOWNLOADS_PATH)
DOWNLOADS_PATH = None
class BasePackage(metaclass=abc.ABCMeta):
@abc.abstractproperty
def name(self) -> str:
raise NotImplementedError
def all_names(self) -> List[str]:
return [self.name]
@abc.abstractmethod
def source_type(self) -> str:
raise NotImplementedError
class PinnedPackage(BasePackage):
def __init__(self) -> None:
self._cached_metadata: Optional[ProjectPackageMetadata] = None
def __str__(self) -> str:
version = self.get_version()
if not version:
return self.name
return "{}@{}".format(self.name, version)
@abc.abstractmethod
def get_version(self) -> Optional[str]:
raise NotImplementedError
@abc.abstractmethod
def _fetch_metadata(self, project, renderer):
raise NotImplementedError
@abc.abstractmethod
def install(self, project):
raise NotImplementedError
@abc.abstractmethod
def nice_version_name(self):
raise NotImplementedError
def fetch_metadata(self, project, renderer):
if not self._cached_metadata:
self._cached_metadata = self._fetch_metadata(project, renderer)
return self._cached_metadata
def get_project_name(self, project, renderer):
metadata = self.fetch_metadata(project, renderer)
return metadata.name
def get_installation_path(self, project, renderer):
dest_dirname = self.get_project_name(project, renderer)
return os.path.join(project.modules_path, dest_dirname)
SomePinned = TypeVar("SomePinned", bound=PinnedPackage)
SomeUnpinned = TypeVar("SomeUnpinned", bound="UnpinnedPackage")
class UnpinnedPackage(Generic[SomePinned], BasePackage):
@abc.abstractclassmethod
def from_contract(cls, contract):
raise NotImplementedError
@abc.abstractmethod
def incorporate(self: SomeUnpinned, other: SomeUnpinned) -> SomeUnpinned:
raise NotImplementedError
@abc.abstractmethod
def resolved(self) -> SomePinned:
raise NotImplementedError

View File

@@ -1,115 +0,0 @@
import abc
import os
import tempfile
from contextlib import contextmanager
from typing import List, Optional, Generic, TypeVar
from dbt.clients import system
from dbt.contracts.project import ProjectPackageMetadata
from dbt.logger import GLOBAL_LOGGER as logger
DOWNLOADS_PATH = None
def get_downloads_path():
return DOWNLOADS_PATH
@contextmanager
def downloads_directory():
global DOWNLOADS_PATH
remove_downloads = False
# the user might have set an environment variable. Set it to that, and do
# not remove it when finished.
if DOWNLOADS_PATH is None:
DOWNLOADS_PATH = os.getenv('DBT_DOWNLOADS_DIR')
remove_downloads = False
# if we are making a per-run temp directory, remove it at the end of
# successful runs
if DOWNLOADS_PATH is None:
DOWNLOADS_PATH = tempfile.mkdtemp(prefix='dbt-downloads-')
remove_downloads = True
system.make_directory(DOWNLOADS_PATH)
logger.debug("Set downloads directory='{}'".format(DOWNLOADS_PATH))
yield DOWNLOADS_PATH
if remove_downloads:
system.rmtree(DOWNLOADS_PATH)
DOWNLOADS_PATH = None
class BasePackage(metaclass=abc.ABCMeta):
@abc.abstractproperty
def name(self) -> str:
raise NotImplementedError
def all_names(self) -> List[str]:
return [self.name]
@abc.abstractmethod
def source_type(self) -> str:
raise NotImplementedError
class PinnedPackage(BasePackage):
def __init__(self) -> None:
self._cached_metadata: Optional[ProjectPackageMetadata] = None
def __str__(self) -> str:
version = self.get_version()
if not version:
return self.name
return '{}@{}'.format(self.name, version)
@abc.abstractmethod
def get_version(self) -> Optional[str]:
raise NotImplementedError
@abc.abstractmethod
def _fetch_metadata(self, project, renderer):
raise NotImplementedError
@abc.abstractmethod
def install(self, project):
raise NotImplementedError
@abc.abstractmethod
def nice_version_name(self):
raise NotImplementedError
def fetch_metadata(self, project, renderer):
if not self._cached_metadata:
self._cached_metadata = self._fetch_metadata(project, renderer)
return self._cached_metadata
def get_project_name(self, project, renderer):
metadata = self.fetch_metadata(project, renderer)
return metadata.name
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)
def get_subdirectory(self):
return None
SomePinned = TypeVar('SomePinned', bound=PinnedPackage)
SomeUnpinned = TypeVar('SomeUnpinned', bound='UnpinnedPackage')
class UnpinnedPackage(Generic[SomePinned], BasePackage):
@abc.abstractclassmethod
def from_contract(cls, contract):
raise NotImplementedError
@abc.abstractmethod
def incorporate(self: SomeUnpinned, other: SomeUnpinned) -> SomeUnpinned:
raise NotImplementedError
@abc.abstractmethod
def resolved(self) -> SomePinned:
raise NotImplementedError

View File

@@ -1,6 +1,6 @@
import os
import hashlib
from typing import List, Optional
from typing import List
from dbt.clients import git, system
from dbt.config import Project
@@ -8,18 +8,16 @@ from dbt.contracts.project import (
ProjectPackageMetadata,
GitPackage,
)
from dbt.deps.base import PinnedPackage, UnpinnedPackage, get_downloads_path
from dbt.exceptions import (
ExecutableError, warn_or_error, raise_dependency_error
)
from dbt.deps import PinnedPackage, UnpinnedPackage, get_downloads_path
from dbt.exceptions import ExecutableError, warn_or_error, raise_dependency_error
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
PIN_PACKAGE_URL = "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions" # noqa
def md5sum(s: str):
return hashlib.md5(s.encode('latin-1')).hexdigest()
return hashlib.md5(s.encode("latin-1")).hexdigest()
class GitPackageMixin:
@@ -32,39 +30,29 @@ class GitPackageMixin:
return self.git
def source_type(self) -> str:
return 'git'
return "git"
class GitPinnedPackage(GitPackageMixin, PinnedPackage):
def __init__(
self,
git: str,
revision: str,
warn_unpinned: bool = True,
subdirectory: Optional[str] = None,
) -> None:
def __init__(self, git: str, revision: str, warn_unpinned: bool = True) -> None:
super().__init__(git)
self.revision = revision
self.warn_unpinned = warn_unpinned
self.subdirectory = subdirectory
self._checkout_name = md5sum(self.git)
def get_version(self):
return self.revision
def get_subdirectory(self):
return self.subdirectory
def nice_version_name(self):
if self.revision == 'HEAD':
return 'HEAD (default revision)'
if self.revision == "HEAD":
return "HEAD (default branch)"
else:
return 'revision {}'.format(self.revision)
return "revision {}".format(self.revision)
def unpinned_msg(self):
if self.revision == 'HEAD':
return 'not pinned, using HEAD (default branch)'
elif self.revision in ('main', 'master'):
if self.revision == "HEAD":
return "not pinned, using HEAD (default branch)"
elif self.revision in ("main", "master"):
return f'pinned to the "{self.revision}" branch'
else:
return None
@@ -76,15 +64,17 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
the path to the checked out directory."""
try:
dir_ = git.clone_and_checkout(
self.git, get_downloads_path(), revision=self.revision,
dirname=self._checkout_name, subdirectory=self.subdirectory
self.git,
get_downloads_path(),
branch=self.revision,
dirname=self._checkout_name,
)
except ExecutableError as exc:
if exc.cmd and exc.cmd[0] == 'git':
if exc.cmd and exc.cmd[0] == "git":
logger.error(
'Make sure git is installed on your machine. More '
'information: '
'https://docs.getdbt.com/docs/package-management'
"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_)
@@ -95,9 +85,10 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
if self.unpinned_msg() and self.warn_unpinned:
warn_or_error(
'The git package "{}" \n\tis {}.\n\tThis can introduce '
'breaking changes into your project without warning!\n\nSee {}'
.format(self.git, self.unpinned_msg(), PIN_PACKAGE_URL),
log_fmt=ui.yellow('WARNING: {}')
"breaking changes into your project without warning!\n\nSee {}".format(
self.git, self.unpinned_msg(), PIN_PACKAGE_URL
),
log_fmt=ui.yellow("WARNING: {}"),
)
loaded = Project.from_project_root(path, renderer)
return ProjectPackageMetadata.from_project(loaded)
@@ -115,57 +106,46 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
class GitUnpinnedPackage(GitPackageMixin, UnpinnedPackage[GitPinnedPackage]):
def __init__(
self,
git: str,
revisions: List[str],
warn_unpinned: bool = True,
subdirectory: Optional[str] = None,
self, git: str, revisions: List[str], warn_unpinned: bool = True
) -> None:
super().__init__(git)
self.revisions = revisions
self.warn_unpinned = warn_unpinned
self.subdirectory = subdirectory
@classmethod
def from_contract(
cls, contract: GitPackage
) -> 'GitUnpinnedPackage':
def from_contract(cls, contract: GitPackage) -> "GitUnpinnedPackage":
revisions = contract.get_revisions()
# we want to map None -> True
warn_unpinned = contract.warn_unpinned is not False
return cls(git=contract.git, revisions=revisions,
warn_unpinned=warn_unpinned, subdirectory=contract.subdirectory)
return cls(git=contract.git, revisions=revisions, warn_unpinned=warn_unpinned)
def all_names(self) -> List[str]:
if self.git.endswith('.git'):
if self.git.endswith(".git"):
other = self.git[:-4]
else:
other = self.git + '.git'
other = self.git + ".git"
return [self.git, other]
def incorporate(
self, other: 'GitUnpinnedPackage'
) -> 'GitUnpinnedPackage':
def incorporate(self, other: "GitUnpinnedPackage") -> "GitUnpinnedPackage":
warn_unpinned = self.warn_unpinned and other.warn_unpinned
return GitUnpinnedPackage(
git=self.git,
revisions=self.revisions + other.revisions,
warn_unpinned=warn_unpinned,
subdirectory=self.subdirectory,
)
def resolved(self) -> GitPinnedPackage:
requested = set(self.revisions)
if len(requested) == 0:
requested = {'HEAD'}
requested = {"HEAD"}
elif len(requested) > 1:
raise_dependency_error(
'git dependencies should contain exactly one version. '
'{} contains: {}'.format(self.git, requested))
"git dependencies should contain exactly one version. "
"{} contains: {}".format(self.git, requested)
)
return GitPinnedPackage(
git=self.git, revision=requested.pop(),
warn_unpinned=self.warn_unpinned, subdirectory=self.subdirectory
git=self.git, revision=requested.pop(), warn_unpinned=self.warn_unpinned
)

View File

@@ -1,7 +1,7 @@
import shutil
from dbt.clients import system
from dbt.deps.base import PinnedPackage, UnpinnedPackage
from dbt.deps import PinnedPackage, UnpinnedPackage
from dbt.contracts.project import (
ProjectPackageMetadata,
LocalPackage,
@@ -19,7 +19,7 @@ class LocalPackageMixin:
return self.local
def source_type(self):
return 'local'
return "local"
class LocalPinnedPackage(LocalPackageMixin, PinnedPackage):
@@ -30,7 +30,7 @@ class LocalPinnedPackage(LocalPackageMixin, PinnedPackage):
return None
def nice_version_name(self):
return '<local @ {}>'.format(self.local)
return "<local @ {}>".format(self.local)
def resolve_path(self, project):
return system.resolve_path_from_base(
@@ -39,9 +39,7 @@ class LocalPinnedPackage(LocalPackageMixin, PinnedPackage):
)
def _fetch_metadata(self, project, renderer):
loaded = project.from_project_root(
self.resolve_path(project), renderer
)
loaded = project.from_project_root(self.resolve_path(project), renderer)
return ProjectPackageMetadata.from_project(loaded)
def install(self, project, renderer):
@@ -57,27 +55,22 @@ class LocalPinnedPackage(LocalPackageMixin, PinnedPackage):
system.remove_file(dest_path)
if can_create_symlink:
logger.debug(' Creating symlink to local dependency.')
logger.debug(" Creating symlink to local dependency.")
system.make_symlink(src_path, dest_path)
else:
logger.debug(' Symlinks are not available on this '
'OS, copying dependency.')
logger.debug(
" Symlinks are not available on this " "OS, copying dependency."
)
shutil.copytree(src_path, dest_path)
class LocalUnpinnedPackage(
LocalPackageMixin, UnpinnedPackage[LocalPinnedPackage]
):
class LocalUnpinnedPackage(LocalPackageMixin, UnpinnedPackage[LocalPinnedPackage]):
@classmethod
def from_contract(
cls, contract: LocalPackage
) -> 'LocalUnpinnedPackage':
def from_contract(cls, contract: LocalPackage) -> "LocalUnpinnedPackage":
return cls(local=contract.local)
def incorporate(
self, other: 'LocalUnpinnedPackage'
) -> 'LocalUnpinnedPackage':
def incorporate(self, other: "LocalUnpinnedPackage") -> "LocalUnpinnedPackage":
return LocalUnpinnedPackage(local=self.local)
def resolved(self) -> LocalPinnedPackage:

View File

@@ -7,7 +7,7 @@ from dbt.contracts.project import (
RegistryPackageMetadata,
RegistryPackage,
)
from dbt.deps.base import PinnedPackage, UnpinnedPackage, get_downloads_path
from dbt.deps import PinnedPackage, UnpinnedPackage, get_downloads_path
from dbt.exceptions import (
package_version_not_found,
VersionsNotCompatibleException,
@@ -26,33 +26,26 @@ class RegistryPackageMixin:
return self.package
def source_type(self) -> str:
return 'hub'
return "hub"
class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
def __init__(self,
package: str,
version: str,
version_latest: str) -> None:
def __init__(self, package: str, version: str) -> None:
super().__init__(package)
self.version = version
self.version_latest = version_latest
@property
def name(self):
return self.package
def source_type(self):
return 'hub'
return "hub"
def get_version(self):
return self.version
def get_version_latest(self):
return self.version_latest
def nice_version_name(self):
return 'version {}'.format(self.version)
return "version {}".format(self.version)
def _fetch_metadata(self, project, renderer) -> RegistryPackageMetadata:
dct = registry.package_version(self.package, self.version)
@@ -61,15 +54,13 @@ class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
def install(self, project, renderer):
metadata = self.fetch_metadata(project, renderer)
tar_name = '{}.{}.tar.gz'.format(self.package, self.version)
tar_path = os.path.realpath(
os.path.join(get_downloads_path(), tar_name)
)
tar_name = "{}.{}.tar.gz".format(self.package, self.version)
tar_path = os.path.realpath(os.path.join(get_downloads_path(), tar_name))
system.make_directory(os.path.dirname(tar_path))
download_url = metadata.downloads.tarball
system.download_with_retries(download_url, tar_path)
deps_path = project.packages_install_path
system.download(download_url, tar_path)
deps_path = project.modules_path
package_name = self.get_project_name(project, renderer)
system.untar_package(tar_path, deps_path, package_name)
@@ -77,15 +68,9 @@ class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
class RegistryUnpinnedPackage(
RegistryPackageMixin, UnpinnedPackage[RegistryPinnedPackage]
):
def __init__(
self,
package: str,
versions: List[semver.VersionSpecifier],
install_prerelease: bool
) -> None:
def __init__(self, package: str, versions: List[semver.VersionSpecifier]) -> None:
super().__init__(package)
self.versions = versions
self.install_prerelease = install_prerelease
def _check_in_index(self):
index = registry.index_cached()
@@ -93,27 +78,17 @@ class RegistryUnpinnedPackage(
package_not_found(self.package)
@classmethod
def from_contract(
cls, contract: RegistryPackage
) -> 'RegistryUnpinnedPackage':
def from_contract(cls, contract: RegistryPackage) -> "RegistryUnpinnedPackage":
raw_version = contract.get_versions()
versions = [
semver.VersionSpecifier.from_version_string(v)
for v in raw_version
]
return cls(
package=contract.package,
versions=versions,
install_prerelease=contract.install_prerelease
)
versions = [semver.VersionSpecifier.from_version_string(v) for v in raw_version]
return cls(package=contract.package, versions=versions)
def incorporate(
self, other: 'RegistryUnpinnedPackage'
) -> 'RegistryUnpinnedPackage':
self, other: "RegistryUnpinnedPackage"
) -> "RegistryUnpinnedPackage":
return RegistryUnpinnedPackage(
package=self.package,
install_prerelease=self.install_prerelease,
versions=self.versions + other.versions,
)
@@ -122,23 +97,16 @@ class RegistryUnpinnedPackage(
try:
range_ = semver.reduce_versions(*self.versions)
except VersionsNotCompatibleException as e:
new_msg = ('Version error for package {}: {}'
.format(self.name, e))
new_msg = "Version error for package {}: {}".format(self.name, e)
raise DependencyException(new_msg) from e
available = registry.get_available_versions(self.package)
installable = semver.filter_installable(
available,
self.install_prerelease
)
available_latest = installable[-1]
# for now, pick a version and then recurse. later on,
# we'll probably want to traverse multiple options
# so we can match packages. not going to make a difference
# right now.
target = semver.resolve_to_specific_version(range_, installable)
target = semver.resolve_to_specific_version(range_, available)
if not target:
package_version_not_found(self.package, range_, installable)
return RegistryPinnedPackage(package=self.package, version=target,
version_latest=available_latest)
package_version_not_found(self.package, range_, available)
return RegistryPinnedPackage(package=self.package, version=target)

View File

@@ -6,7 +6,7 @@ from dbt.exceptions import raise_dependency_error, InternalException
from dbt.context.target import generate_target_context
from dbt.config import Project, RuntimeConfig
from dbt.config.renderer import DbtProjectYamlRenderer
from dbt.deps.base import BasePackage, PinnedPackage, UnpinnedPackage
from dbt.deps import BasePackage, PinnedPackage, UnpinnedPackage
from dbt.deps.local import LocalUnpinnedPackage
from dbt.deps.git import GitUnpinnedPackage
from dbt.deps.registry import RegistryUnpinnedPackage
@@ -49,12 +49,10 @@ class PackageListing:
key_str: str = self._pick_key(key)
self.packages[key_str] = value
def _mismatched_types(
self, old: UnpinnedPackage, new: UnpinnedPackage
) -> NoReturn:
def _mismatched_types(self, old: UnpinnedPackage, new: UnpinnedPackage) -> NoReturn:
raise_dependency_error(
f'Cannot incorporate {new} ({new.__class__.__name__}) in {old} '
f'({old.__class__.__name__}): mismatched types'
f"Cannot incorporate {new} ({new.__class__.__name__}) in {old} "
f"({old.__class__.__name__}): mismatched types"
)
def incorporate(self, package: UnpinnedPackage):
@@ -78,14 +76,14 @@ class PackageListing:
pkg = RegistryUnpinnedPackage.from_contract(contract)
else:
raise InternalException(
'Invalid package type {}'.format(type(contract))
"Invalid package type {}".format(type(contract))
)
self.incorporate(pkg)
@classmethod
def from_contracts(
cls: Type['PackageListing'], src: List[PackageContract]
) -> 'PackageListing':
cls: Type["PackageListing"], src: List[PackageContract]
) -> "PackageListing":
self = cls({})
self.update_from(src)
return self
@@ -108,14 +106,14 @@ def _check_for_duplicate_project_names(
if project_name in seen:
raise_dependency_error(
f'Found duplicate project "{project_name}". This occurs when '
'a dependency has the same project name as some other '
'dependency.'
"a dependency has the same project name as some other "
"dependency."
)
elif project_name == config.project_name:
raise_dependency_error(
'Found a dependency with the same name as the root project '
"Found a dependency with the same name as the root project "
f'"{project_name}". Package names must be unique in a project.'
' Please rename one of these packages.'
" Please rename one of these packages."
)
seen.add(project_name)

View File

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

View File

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

View File

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

View File

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

File diff suppressed because it is too large Load Diff

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