mirror of
https://github.com/dbt-labs/dbt-core
synced 2025-12-18 23:01:27 +00:00
Compare commits
60 Commits
jerco/sql-
...
v0.20.2rc2
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
7751295d0e | ||
|
|
213e9c4441 | ||
|
|
29d2c98b19 | ||
|
|
3cd8711553 | ||
|
|
41b919427e | ||
|
|
09ece846c0 | ||
|
|
c9758cc929 | ||
|
|
6af996e3bf | ||
|
|
82b70f518b | ||
|
|
4cf427ffcd | ||
|
|
3dc574e5ff | ||
|
|
9ac889261c | ||
|
|
356790ee03 | ||
|
|
3918a03735 | ||
|
|
5a3cfc994e | ||
|
|
8246d971a5 | ||
|
|
682d21287b | ||
|
|
817b6d71b7 | ||
|
|
04fc49882b | ||
|
|
8e15abb1d7 | ||
|
|
034364f25d | ||
|
|
b94b2e5470 | ||
|
|
c13a64fb06 | ||
|
|
8f0475980a | ||
|
|
789222dfb0 | ||
|
|
5e95557bb5 | ||
|
|
2eb289ef43 | ||
|
|
013cfdcf49 | ||
|
|
1e84a33c88 | ||
|
|
037212ada7 | ||
|
|
f0d7e58f0e | ||
|
|
1dcdd4c1c8 | ||
|
|
784280d247 | ||
|
|
41ef632512 | ||
|
|
7e4d0ccd2c | ||
|
|
c25ff1016d | ||
|
|
2c58c13f91 | ||
|
|
963ed3e0e2 | ||
|
|
558724e0a0 | ||
|
|
2d5c420474 | ||
|
|
7d69adb709 | ||
|
|
a2caceb325 | ||
|
|
2f42c98421 | ||
|
|
842df63f63 | ||
|
|
8c756d5d0b | ||
|
|
f4d6c5384f | ||
|
|
0a3ad3c86a | ||
|
|
523eeb774e | ||
|
|
db8b7da82a | ||
|
|
d692d98a95 | ||
|
|
8464c6c36f | ||
|
|
d8f4502b6d | ||
|
|
f39baaf61c | ||
|
|
39cf3d4896 | ||
|
|
f3d2a8150d | ||
|
|
bfe8f0ac34 | ||
|
|
7882cf61c7 | ||
|
|
c8f3c106a7 | ||
|
|
05d7638a7c | ||
|
|
dfc038fca4 |
@@ -1,5 +1,5 @@
|
||||
[bumpversion]
|
||||
current_version = 0.20.0rc1
|
||||
current_version = 0.20.2rc2
|
||||
parse = (?P<major>\d+)
|
||||
\.(?P<minor>\d+)
|
||||
\.(?P<patch>\d+)
|
||||
|
||||
@@ -1,123 +0,0 @@
|
||||
version: 2.1
|
||||
jobs:
|
||||
unit:
|
||||
docker: &test_only
|
||||
- image: fishtownanalytics/test-container:12
|
||||
environment:
|
||||
DBT_INVOCATION_ENV: circle
|
||||
DOCKER_TEST_DATABASE_HOST: "database"
|
||||
TOX_PARALLEL_NO_SPINNER: 1
|
||||
steps:
|
||||
- checkout
|
||||
- run: tox -p -e py36,py37,py38
|
||||
lint:
|
||||
docker: *test_only
|
||||
steps:
|
||||
- checkout
|
||||
- run: tox -e mypy,flake8 -- -v
|
||||
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:
|
||||
docker:
|
||||
- image: fishtownanalytics/test-container:12
|
||||
environment:
|
||||
DBT_INVOCATION_ENV: circle
|
||||
DOCKER_TEST_DATABASE_HOST: "database"
|
||||
TOX_PARALLEL_NO_SPINNER: 1
|
||||
- image: postgres
|
||||
name: database
|
||||
environment:
|
||||
POSTGRES_USER: "root"
|
||||
POSTGRES_PASSWORD: "password"
|
||||
POSTGRES_DB: "dbt"
|
||||
steps:
|
||||
- checkout
|
||||
- run:
|
||||
name: Setup postgres
|
||||
command: bash test/setup_db.sh
|
||||
environment:
|
||||
PGHOST: database
|
||||
PGUSER: root
|
||||
PGPASSWORD: password
|
||||
PGDATABASE: postgres
|
||||
- run:
|
||||
name: Postgres integration tests
|
||||
command: tox -p -e py36-postgres,py38-postgres -- -v -n4
|
||||
no_output_timeout: 30m
|
||||
- store_artifacts:
|
||||
path: ./logs
|
||||
integration-snowflake:
|
||||
docker: *test_only
|
||||
steps:
|
||||
- checkout
|
||||
- run:
|
||||
name: Snowflake integration tests
|
||||
command: tox -p -e py36-snowflake,py38-snowflake -- -v -n4
|
||||
no_output_timeout: 30m
|
||||
- store_artifacts:
|
||||
path: ./logs
|
||||
integration-redshift:
|
||||
docker: *test_only
|
||||
steps:
|
||||
- checkout
|
||||
- run:
|
||||
name: Redshift integration tests
|
||||
command: tox -p -e py36-redshift,py38-redshift -- -v -n4
|
||||
no_output_timeout: 30m
|
||||
- store_artifacts:
|
||||
path: ./logs
|
||||
integration-bigquery:
|
||||
docker: *test_only
|
||||
steps:
|
||||
- checkout
|
||||
- run:
|
||||
name: Bigquery integration test
|
||||
command: tox -p -e py36-bigquery,py38-bigquery -- -v -n4
|
||||
no_output_timeout: 30m
|
||||
- store_artifacts:
|
||||
path: ./logs
|
||||
|
||||
workflows:
|
||||
version: 2
|
||||
test-everything:
|
||||
jobs:
|
||||
- lint
|
||||
- unit
|
||||
- integration-postgres:
|
||||
requires:
|
||||
- unit
|
||||
- integration-redshift:
|
||||
requires:
|
||||
- unit
|
||||
- integration-bigquery:
|
||||
requires:
|
||||
- unit
|
||||
- integration-snowflake:
|
||||
requires:
|
||||
- unit
|
||||
- build-wheels:
|
||||
requires:
|
||||
- lint
|
||||
- unit
|
||||
- integration-postgres
|
||||
- integration-redshift
|
||||
- integration-bigquery
|
||||
- integration-snowflake
|
||||
10
.github/actions/setup-postgres-linux/action.yml
vendored
Normal file
10
.github/actions/setup-postgres-linux/action.yml
vendored
Normal file
@@ -0,0 +1,10 @@
|
||||
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
|
||||
1
.github/actions/setup-postgres-linux/setup_db.sh
vendored
Symbolic link
1
.github/actions/setup-postgres-linux/setup_db.sh
vendored
Symbolic link
@@ -0,0 +1 @@
|
||||
../../../test/setup_db.sh
|
||||
24
.github/actions/setup-postgres-macos/action.yml
vendored
Normal file
24
.github/actions/setup-postgres-macos/action.yml
vendored
Normal file
@@ -0,0 +1,24 @@
|
||||
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
|
||||
1
.github/actions/setup-postgres-macos/setup_db.sh
vendored
Symbolic link
1
.github/actions/setup-postgres-macos/setup_db.sh
vendored
Symbolic link
@@ -0,0 +1 @@
|
||||
../../../test/setup_db.sh
|
||||
12
.github/actions/setup-postgres-windows/action.yml
vendored
Normal file
12
.github/actions/setup-postgres-windows/action.yml
vendored
Normal file
@@ -0,0 +1,12 @@
|
||||
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
|
||||
1
.github/actions/setup-postgres-windows/setup_db.sh
vendored
Symbolic link
1
.github/actions/setup-postgres-windows/setup_db.sh
vendored
Symbolic link
@@ -0,0 +1 @@
|
||||
../../../test/setup_db.sh
|
||||
11
.github/pull_request_template.md
vendored
11
.github/pull_request_template.md
vendored
@@ -9,14 +9,13 @@ resolves #
|
||||
resolves #1234
|
||||
-->
|
||||
|
||||
|
||||
### Description
|
||||
|
||||
<!--- 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 to the "dbt next" section.
|
||||
|
||||
- [ ] 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.
|
||||
|
||||
95
.github/scripts/integration-test-matrix.js
vendored
Normal file
95
.github/scripts/integration-test-matrix.js
vendored
Normal file
@@ -0,0 +1,95 @@
|
||||
module.exports = ({ context }) => {
|
||||
const defaultPythonVersion = "3.8";
|
||||
const supportedPythonVersions = ["3.6", "3.7", "3.8", "3.9"];
|
||||
const supportedAdapters = ["snowflake", "postgres", "bigquery", "redshift"];
|
||||
|
||||
// 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,
|
||||
};
|
||||
};
|
||||
269
.github/workflows/integration.yml
vendored
Normal file
269
.github/workflows/integration.yml
vendored
Normal file
@@ -0,0 +1,269 @@
|
||||
# **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/*"
|
||||
- "github-actions" # testing!
|
||||
# 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
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.ref }}
|
||||
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/**'
|
||||
snowflake:
|
||||
- 'core/**'
|
||||
- 'plugins/snowflake/**'
|
||||
bigquery:
|
||||
- 'core/**'
|
||||
- 'plugins/bigquery/**'
|
||||
redshift:
|
||||
- 'core/**'
|
||||
- 'plugins/redshift/**'
|
||||
- 'plugins/postgres/**'
|
||||
|
||||
- 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
|
||||
|
||||
# only block on non-postgres jobs, trying to decrease amount of concurrent processing against warehouses
|
||||
concurrency: ${{ matrix.adapter != 'postgres' && matrix.adapter || github.job }}-${{ matrix.python-version }}-${{ matrix.os }}
|
||||
|
||||
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 --upgrade pip
|
||||
pip install tox
|
||||
pip --version
|
||||
tox --version
|
||||
|
||||
- name: Run tox (postgres)
|
||||
if: matrix.adapter == 'postgres'
|
||||
run: tox
|
||||
|
||||
- name: Run tox (redshift)
|
||||
if: matrix.adapter == 'redshift'
|
||||
env:
|
||||
REDSHIFT_TEST_DBNAME: ${{ secrets.REDSHIFT_TEST_DBNAME }}
|
||||
REDSHIFT_TEST_PASS: ${{ secrets.REDSHIFT_TEST_PASS }}
|
||||
REDSHIFT_TEST_USER: ${{ secrets.REDSHIFT_TEST_USER }}
|
||||
REDSHIFT_TEST_PORT: ${{ secrets.REDSHIFT_TEST_PORT }}
|
||||
REDSHIFT_TEST_HOST: ${{ secrets.REDSHIFT_TEST_HOST }}
|
||||
run: tox
|
||||
|
||||
- name: Run tox (snowflake)
|
||||
if: matrix.adapter == 'snowflake'
|
||||
env:
|
||||
SNOWFLAKE_TEST_ACCOUNT: ${{ secrets.SNOWFLAKE_TEST_ACCOUNT }}
|
||||
SNOWFLAKE_TEST_PASSWORD: ${{ secrets.SNOWFLAKE_TEST_PASSWORD }}
|
||||
SNOWFLAKE_TEST_USER: ${{ secrets.SNOWFLAKE_TEST_USER }}
|
||||
SNOWFLAKE_TEST_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_WAREHOUSE }}
|
||||
SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN: ${{ secrets.SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN }}
|
||||
SNOWFLAKE_TEST_OAUTH_CLIENT_ID: ${{ secrets.SNOWFLAKE_TEST_OAUTH_CLIENT_ID }}
|
||||
SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET: ${{ secrets.SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET }}
|
||||
SNOWFLAKE_TEST_ALT_DATABASE: ${{ secrets.SNOWFLAKE_TEST_ALT_DATABASE }}
|
||||
SNOWFLAKE_TEST_ALT_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_ALT_WAREHOUSE }}
|
||||
SNOWFLAKE_TEST_DATABASE: ${{ secrets.SNOWFLAKE_TEST_DATABASE }}
|
||||
SNOWFLAKE_TEST_QUOTED_DATABASE: ${{ secrets.SNOWFLAKE_TEST_QUOTED_DATABASE }}
|
||||
SNOWFLAKE_TEST_ROLE: ${{ secrets.SNOWFLAKE_TEST_ROLE }}
|
||||
run: tox
|
||||
|
||||
- name: Run tox (bigquery)
|
||||
if: matrix.adapter == 'bigquery'
|
||||
env:
|
||||
BIGQUERY_TEST_SERVICE_ACCOUNT_JSON: ${{ secrets.BIGQUERY_TEST_SERVICE_ACCOUNT_JSON }}
|
||||
BIGQUERY_TEST_ALT_DATABASE: ${{ secrets.BIGQUERY_TEST_ALT_DATABASE }}
|
||||
run: tox
|
||||
|
||||
- uses: actions/upload-artifact@v2
|
||||
if: always()
|
||||
with:
|
||||
name: logs
|
||||
path: ./logs
|
||||
|
||||
- name: Get current date
|
||||
if: always()
|
||||
id: date
|
||||
run: echo "::set-output name=date::$(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
|
||||
206
.github/workflows/main.yml
vendored
Normal file
206
.github/workflows/main.yml
vendored
Normal file
@@ -0,0 +1,206 @@
|
||||
# **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/*"
|
||||
- "github-actions"
|
||||
pull_request:
|
||||
workflow_dispatch:
|
||||
|
||||
permissions: read-all
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.ref }}
|
||||
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 --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: ${{ matrix.python-version }}
|
||||
|
||||
- name: Install python dependencies
|
||||
run: |
|
||||
pip install --upgrade pip
|
||||
pip install tox
|
||||
pip --version
|
||||
tox --version
|
||||
|
||||
- name: Run tox
|
||||
run: tox
|
||||
|
||||
- name: Get current date
|
||||
if: always()
|
||||
id: date
|
||||
run: echo "::set-output name=date::$(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 --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 --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
|
||||
178
.github/workflows/tests.yml
vendored
178
.github/workflows/tests.yml
vendored
@@ -1,178 +0,0 @@
|
||||
# This is a workflow to run our unit and integration tests for windows and mac
|
||||
|
||||
name: dbt Tests
|
||||
|
||||
# Triggers
|
||||
on:
|
||||
# Triggers the workflow on push or pull request events and also adds a manual trigger
|
||||
push:
|
||||
branches:
|
||||
- 'develop'
|
||||
- '*.latest'
|
||||
- 'releases/*'
|
||||
pull_request_target:
|
||||
branches:
|
||||
- 'develop'
|
||||
- '*.latest'
|
||||
- 'pr/*'
|
||||
- 'releases/*'
|
||||
# Allows you to run this workflow manually from the Actions tab
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
Linting:
|
||||
runs-on: ubuntu-latest #no need to run on every OS
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Setup Python
|
||||
uses: actions/setup-python@v2.2.2
|
||||
with:
|
||||
python-version: '3.8'
|
||||
architecture: 'x64'
|
||||
|
||||
- name: 'Install dependencies'
|
||||
run: python -m pip install --upgrade pip && pip install tox
|
||||
|
||||
- name: 'Linting'
|
||||
run: tox -e mypy,flake8 -- -v
|
||||
|
||||
UnitTest:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [windows-latest, ubuntu-latest, macos-latest]
|
||||
runs-on: ${{ matrix.os }}
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Setup Python
|
||||
uses: actions/setup-python@v2.2.2
|
||||
with:
|
||||
python-version: '3.8'
|
||||
architecture: 'x64'
|
||||
|
||||
- name: 'Install dependencies'
|
||||
run: python -m pip install --upgrade pip && pip install tox
|
||||
|
||||
- name: 'Run unit tests'
|
||||
run: python -m tox -e py -- -v
|
||||
|
||||
PostgresIntegrationTest:
|
||||
runs-on: 'windows-latest' #TODO: Add Mac support
|
||||
environment: 'Postgres'
|
||||
needs: UnitTest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: 'Install postgresql and set up database'
|
||||
shell: pwsh
|
||||
run: |
|
||||
$serviceName = Get-Service -Name postgresql*
|
||||
Set-Service -InputObject $serviceName -StartupType Automatic
|
||||
Start-Service -InputObject $serviceName
|
||||
& $env:PGBIN\createdb.exe -U postgres dbt
|
||||
& $env:PGBIN\psql.exe -U postgres -c "CREATE ROLE root WITH PASSWORD '$env:ROOT_PASSWORD';"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "ALTER ROLE root WITH LOGIN;"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "GRANT CREATE, CONNECT ON DATABASE dbt TO root WITH GRANT OPTION;"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "CREATE ROLE noaccess WITH PASSWORD '$env:NOACCESS_PASSWORD' NOSUPERUSER;"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "ALTER ROLE noaccess WITH LOGIN;"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "GRANT CONNECT ON DATABASE dbt TO noaccess;"
|
||||
env:
|
||||
ROOT_PASSWORD: ${{ secrets.ROOT_PASSWORD }}
|
||||
NOACCESS_PASSWORD: ${{ secrets.NOACCESS_PASSWORD }}
|
||||
|
||||
- name: Setup Python
|
||||
uses: actions/setup-python@v2.2.2
|
||||
with:
|
||||
python-version: '3.7'
|
||||
architecture: 'x64'
|
||||
|
||||
- name: 'Install dependencies'
|
||||
run: python -m pip install --upgrade pip && pip install tox
|
||||
|
||||
- name: 'Run integration tests'
|
||||
run: python -m tox -e py-postgres -- -v -n4
|
||||
|
||||
# These three are all similar except secure environment variables, which MUST be passed along to their tasks,
|
||||
# but there's probably a better way to do this!
|
||||
SnowflakeIntegrationTest:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [windows-latest, macos-latest]
|
||||
runs-on: ${{ matrix.os }}
|
||||
environment: 'Snowflake'
|
||||
needs: UnitTest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Setup Python
|
||||
uses: actions/setup-python@v2.2.2
|
||||
with:
|
||||
python-version: '3.7'
|
||||
architecture: 'x64'
|
||||
|
||||
- name: 'Install dependencies'
|
||||
run: python -m pip install --upgrade pip && pip install tox
|
||||
|
||||
- name: 'Run integration tests'
|
||||
run: python -m tox -e py-snowflake -- -v -n4
|
||||
env:
|
||||
SNOWFLAKE_TEST_ACCOUNT: ${{ secrets.SNOWFLAKE_TEST_ACCOUNT }}
|
||||
SNOWFLAKE_TEST_PASSWORD: ${{ secrets.SNOWFLAKE_TEST_PASSWORD }}
|
||||
SNOWFLAKE_TEST_USER: ${{ secrets.SNOWFLAKE_TEST_USER }}
|
||||
SNOWFLAKE_TEST_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_WAREHOUSE }}
|
||||
SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN: ${{ secrets.SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN }}
|
||||
SNOWFLAKE_TEST_OAUTH_CLIENT_ID: ${{ secrets.SNOWFLAKE_TEST_OAUTH_CLIENT_ID }}
|
||||
SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET: ${{ secrets.SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET }}
|
||||
SNOWFLAKE_TEST_ALT_DATABASE: ${{ secrets.SNOWFLAKE_TEST_ALT_DATABASE }}
|
||||
SNOWFLAKE_TEST_ALT_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_ALT_WAREHOUSE }}
|
||||
SNOWFLAKE_TEST_DATABASE: ${{ secrets.SNOWFLAKE_TEST_DATABASE }}
|
||||
SNOWFLAKE_TEST_QUOTED_DATABASE: ${{ secrets.SNOWFLAKE_TEST_QUOTED_DATABASE }}
|
||||
SNOWFLAKE_TEST_ROLE: ${{ secrets.SNOWFLAKE_TEST_ROLE }}
|
||||
|
||||
BigQueryIntegrationTest:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [windows-latest, macos-latest]
|
||||
runs-on: ${{ matrix.os }}
|
||||
environment: 'Bigquery'
|
||||
needs: UnitTest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Setup Python
|
||||
uses: actions/setup-python@v2.2.2
|
||||
with:
|
||||
python-version: '3.7'
|
||||
architecture: 'x64'
|
||||
|
||||
- name: 'Install dependencies'
|
||||
run: python -m pip install --upgrade pip && pip install tox
|
||||
|
||||
- name: 'Run integration tests'
|
||||
run: python -m tox -e py-bigquery -- -v -n4
|
||||
env:
|
||||
BIGQUERY_SERVICE_ACCOUNT_JSON: ${{ secrets.BIGQUERY_SERVICE_ACCOUNT_JSON }}
|
||||
BIGQUERY_TEST_ALT_DATABASE: ${{ secrets.BIGQUERY_TEST_ALT_DATABASE }}
|
||||
|
||||
RedshiftIntegrationTest:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [windows-latest, macos-latest]
|
||||
runs-on: ${{ matrix.os }}
|
||||
environment: 'Redshift'
|
||||
needs: UnitTest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Setup Python
|
||||
uses: actions/setup-python@v2.2.2
|
||||
with:
|
||||
python-version: '3.7'
|
||||
architecture: 'x64'
|
||||
|
||||
- name: 'Install dependencies'
|
||||
run: python -m pip install --upgrade pip && pip install tox
|
||||
|
||||
- name: 'Run integration tests'
|
||||
run: python -m tox -e py-redshift -- -v -n4
|
||||
env:
|
||||
REDSHIFT_TEST_DBNAME: ${{ secrets.REDSHIFT_TEST_DBNAME }}
|
||||
REDSHIFT_TEST_PASS: ${{ secrets.REDSHIFT_TEST_PASS }}
|
||||
REDSHIFT_TEST_USER: ${{ secrets.REDSHIFT_TEST_USER }}
|
||||
REDSHIFT_TEST_PORT: ${{ secrets.REDSHIFT_TEST_PORT }}
|
||||
REDSHIFT_TEST_HOST: ${{ secrets.REDSHIFT_TEST_HOST }}
|
||||
107
CHANGELOG.md
107
CHANGELOG.md
@@ -1,4 +1,104 @@
|
||||
## dbt 0.20.0 (Release TBD)
|
||||
## dbt 0.20.2 (Release TBD)
|
||||
|
||||
## dbt 0.20.2rc2 (August 27, 2021)
|
||||
|
||||
|
||||
### Fixes
|
||||
- Avoid caching schemas for tests when `store_failures` is not enabled ([#3715](https://github.com/dbt-labs/dbt/issues/3715), [#3716](https://github.com/dbt-labs/dbt/pull/3716))
|
||||
|
||||
### Under the hood
|
||||
- Get more information on partial parsing version mismatches ([#3757](https://github.com/dbt-labs/dbt/issues/3757), [#3758](https://github.com/dbt-labs/dbt/pull/3758))
|
||||
- Use GitHub Actions for CI ([#3688](https://github.com/dbt-labs/dbt/issues/3688), [#3669](https://github.com/dbt-labs/dbt/pull/3669))
|
||||
|
||||
### Fixes
|
||||
- Fix bug in finding analysis nodes when applying analysis patch ([#3764](https://github.com/dbt-labs/dbt/issues/3764), [#3767](https://github.com/dbt-labs/dbt/pull/3767))
|
||||
- Rewrite built-in generic tests to support `column_name` expressions ([#3790](https://github.com/dbt-labs/dbt/issues/3790), [#3811](https://github.com/dbt-labs/dbt/pull/3811))
|
||||
|
||||
Contributors:
|
||||
- [@sungchun12](https://github.com/sungchun12) ([#3703](https://github.com/dbt-labs/dbt/pull/3703))
|
||||
|
||||
## dbt 0.20.2rc1 (August 16, 2021)
|
||||
|
||||
|
||||
### Under the hood
|
||||
- Switch to full reparse on partial parsing exceptions. Log and report exception information. ([#3725](https://github.com/dbt-labs/dbt/issues/3725), [#3733](https://github.com/dbt-labs/dbt/pull/3733))
|
||||
- Check for existence of test node when removing. ([#3711](https://github.com/dbt-labs/dbt/issues/3711), [#3750](https://github.com/dbt-labs/dbt/pull/3750))
|
||||
- Better error handling for BigQuery job labels that are too long. [#3703](https://github.com/dbt-labs/dbt/pull/3703)
|
||||
|
||||
### Fixes
|
||||
- Check for existence of test node when removing. ([#3711](https://github.com/dbt-labs/dbt/issues/3711), [#3750](https://github.com/dbt-labs/dbt/pull/3750))
|
||||
|
||||
|
||||
## dbt 0.20.1 (August 11, 2021)
|
||||
|
||||
## dbt 0.20.1rc1 (August 02, 2021)
|
||||
|
||||
### Features
|
||||
- Adds `install-prerelease` parameter to hub packages in `packages.yml`. When set to `True`, allows prerelease packages to be installed. By default, this parameter is False unless explicitly set to True.
|
||||
|
||||
### Fixes
|
||||
- Fix config merge behavior with experimental parser [3637](https://github.com/dbt-labs/dbt/pull/3637)
|
||||
- Fix exception on yml files with all comments [3568](https://github.com/dbt-labs/dbt/issues/3568)
|
||||
- Fix `store_failures` config when defined as a modifier for `unique` and `not_null` tests ([#3575](https://github.com/fishtown-analytics/dbt/issues/3575), [#3577](https://github.com/fishtown-analytics/dbt/pull/3577))
|
||||
- Fix `where` config with `relationships` test by refactoring test SQL. Note: The default `relationships` test now includes CTEs, and may need reimplementing on adapters that don't support CTEs nested inside subqueries. ([#3579](https://github.com/fishtown-analytics/dbt/issues/3579), [#3583](https://github.com/fishtown-analytics/dbt/pull/3583))
|
||||
- Partial parsing: don't reprocess SQL file already scheduled ([#3589](https://github.com/dbt-labs/dbt/issues/3589), [#3620](https://github.com/dbt-labs/dbt/pull/3620))
|
||||
- Handle interator functions in model config ([#3573](https://github.com/dbt-labs/dbt/issues/3573))
|
||||
- Partial parsing: fix error after changing empty yaml file ([#3567](https://gith7ub.com/dbt-labs/dbt/issues/3567), [#3618](https://github.com/dbt-labs/dbt/pull/3618))
|
||||
- Partial parsing: handle source tests when changing test macro ([#3584](https://github.com/dbt-labs/dbt/issues/3584), [#3620](https://github.com/dbt-labs/dbt/pull/3620))
|
||||
- Fix `dbt deps` version comparison logic which was causing incorrect pre-release package versions to be installed. ([#3578](https://github.com/dbt-labs/dbt/issues/3578), [#3609](https://github.com/dbt-labs/dbt/issues/3609))
|
||||
- Partial parsing: schedule new macro file for parsing when macro patching ([#3627](https://github.com/dbt-labs/dbt/issues/3627), [#3627](https://github.com/dbt-labs/dbt/pull/3627))
|
||||
- Use `SchemaParser`'s render context to render test configs in order to support `var()` configured at the project level and passed in from the cli ([#3564](https://github.com/dbt-labs/dbt/issues/3564). [#3646](https://github.com/dbt-labs/dbt/pull/3646))
|
||||
- Partial parsing: check unique_ids when recursively removing macros ([#3636](https://github.com/dbt-labs/dbt/issues/3636))
|
||||
|
||||
### Under the hood
|
||||
- Add tracking for determine why `dbt` needs to re-parse entire project when partial parsing is enabled ([#3572](https://github.com/dbt-labs/dbt/issues/3572), [#3652](https://github.com/dbt-labs/dbt/pull/3652))
|
||||
|
||||
### Docs
|
||||
- Fix docs site crash if `relationships` test has one dependency instead of two ([docs#207](https://github.com/dbt-labs/dbt-docs/issues/207), ([docs#208](https://github.com/dbt-labs/dbt-docs/issues/208)))
|
||||
|
||||
### Under the hood
|
||||
- Handle exceptions from anonymous usage tracking for users of `dbt-snowflake` on Apple M1 chips ([#3162](https://github.com/dbt-labs/dbt/issues/3162), [#3661](https://github.com/dbt-labs/dbt/issues/3661))
|
||||
|
||||
Contributors:
|
||||
- [@NiallRees](https://github.com/NiallRees) ([#3624](https://github.com/dbt-labs/dbt/pull/3624))
|
||||
|
||||
## dbt 0.20.0 (July 12, 2021)
|
||||
|
||||
### Fixes
|
||||
|
||||
- Avoid slowdown in column-level `persist_docs` on Snowflake, while preserving the error-avoidance from [#3149](https://github.com/fishtown-analytics/dbt/issues/3149) ([#3541](https://github.com/fishtown-analytics/dbt/issues/3541), [#3543](https://github.com/fishtown-analytics/dbt/pull/3543))
|
||||
- Partial parsing: handle already deleted nodes when schema block also deleted ([#3516](http://github.com/fishown-analystics/dbt/issues/3516), [#3522](http://github.com/fishown-analystics/dbt/issues/3522))
|
||||
|
||||
### Docs
|
||||
|
||||
- Update dbt logo and links ([docs#197](https://github.com/fishtown-analytics/dbt-docs/issues/197))
|
||||
|
||||
### Under the hood
|
||||
|
||||
- Add tracking for experimental parser accuracy ([3503](https://github.com/dbt-labs/dbt/pull/3503), [3553](https://github.com/dbt-labs/dbt/pull/3553))
|
||||
|
||||
## dbt 0.20.0rc2 (June 30, 2021)
|
||||
|
||||
|
||||
### Fixes
|
||||
|
||||
- Handle quoted values within test configs, such as `where` ([#3458](https://github.com/fishtown-analytics/dbt/issues/3458), [#3459](https://github.com/fishtown-analytics/dbt/pull/3459))
|
||||
|
||||
### Docs
|
||||
|
||||
- Display `tags` on exposures ([docs#194](https://github.com/fishtown-analytics/dbt-docs/issues/194), [docs#195](https://github.com/fishtown-analytics/dbt-docs/issues/195))
|
||||
|
||||
### Under the hood
|
||||
|
||||
- Swap experimental parser implementation to use Rust [#3497](https://github.com/fishtown-analytics/dbt/pull/3497)
|
||||
- Dispatch the core SQL statement of the new test materialization, to benefit adapter maintainers ([#3465](https://github.com/fishtown-analytics/dbt/pull/3465), [#3461](https://github.com/fishtown-analytics/dbt/pull/3461))
|
||||
- Minimal validation of yaml dictionaries prior to partial parsing ([#3246](https://github.com/fishtown-analytics/dbt/issues/3246), [#3460](https://github.com/fishtown-analytics/dbt/pull/3460))
|
||||
- Add partial parsing tests and improve partial parsing handling of macros ([#3449](https://github.com/fishtown-analytics/dbt/issues/3449), [#3505](https://github.com/fishtown-analytics/dbt/pull/3505))
|
||||
- Update project loading event data to include experimental parser information. ([#3438](https://github.com/fishtown-analytics/dbt/issues/3438), [#3495](https://github.com/fishtown-analytics/dbt/pull/3495))
|
||||
|
||||
Contributors:
|
||||
- [@swanderz](https://github.com/swanderz) ([#3461](https://github.com/fishtown-analytics/dbt/pull/3461))
|
||||
- [@stkbailey](https://github.com/stkbailey) ([docs#195](https://github.com/fishtown-analytics/dbt-docs/issues/195))
|
||||
|
||||
## dbt 0.20.0rc1 (June 04, 2021)
|
||||
|
||||
@@ -26,7 +126,10 @@
|
||||
- Separate `compiled_path` from `build_path`, and print the former alongside node error messages ([#1985](https://github.com/fishtown-analytics/dbt/issues/1985), [#3327](https://github.com/fishtown-analytics/dbt/pull/3327))
|
||||
- Fix exception caused when running `dbt debug` with BigQuery connections ([#3314](https://github.com/fishtown-analytics/dbt/issues/3314), [#3351](https://github.com/fishtown-analytics/dbt/pull/3351))
|
||||
- Raise better error if snapshot is missing required configurations ([#3381](https://github.com/fishtown-analytics/dbt/issues/3381), [#3385](https://github.com/fishtown-analytics/dbt/pull/3385))
|
||||
- Fix `dbt run` errors caused from receiving non-JSON responses from Snowflake with Oauth ([#3350](https://github.com/fishtown-analytics/dbt/issues/3350))
|
||||
- Fix deserialization of Manifest lock attribute ([#3435](https://github.com/fishtown-analytics/dbt/issues/3435), [#3445](https://github.com/fishtown-analytics/dbt/pull/3445))
|
||||
- Fix `dbt run` errors caused from receiving non-JSON responses from Snowflake with Oauth ([#3350](https://github.com/fishtown-analytics/dbt/issues/3350)
|
||||
- Fix infinite recursion when parsing schema tests due to loops in macro calls ([#3444](https://github.com/fishtown-analytics/dbt/issues/3344), [#3454](https://github.com/fishtown-analytics/dbt/pull/3454))
|
||||
|
||||
### Docs
|
||||
- Reversed the rendering direction of relationship tests so that the test renders in the model it is defined in ([docs#181](https://github.com/fishtown-analytics/dbt-docs/issues/181), [docs#183](https://github.com/fishtown-analytics/dbt-docs/pull/183))
|
||||
@@ -40,7 +143,7 @@
|
||||
- Use shutil.which so Windows can pick up git.bat as a git executable ([#3035](https://github.com/fishtown-analytics/dbt/issues/3035), [#3134](https://github.com/fishtown-analytics/dbt/issues/3134))
|
||||
- Add `ssh-client` and update `git` version (using buster backports) in Docker image ([#3337](https://github.com/fishtown-analytics/dbt/issues/3337), [#3338](https://github.com/fishtown-analytics/dbt/pull/3338))
|
||||
- Add `tags` and `meta` properties to the exposure resource schema. ([#3404](https://github.com/fishtown-analytics/dbt/issues/3404), [#3405](https://github.com/fishtown-analytics/dbt/pull/3405))
|
||||
- Update test sub-query alias ([#3398](https://github.com/fishtown-analytics/dbt/issues/3398), [#3414](https://github.com/fishtown-analytics/dbt/pull/3414))
|
||||
- Update test sub-query alias ([#3398](https://github.com/fishtown-analytics/dbt/issues/3398), [#3414](https://github.com/fishtown-analytics/dbt/pull/3414))
|
||||
- Bump schema versions for run results and manifest artifacts ([#3422](https://github.com/fishtown-analytics/dbt/issues/3422), [#3421](https://github.com/fishtown-analytics/dbt/pull/3421))
|
||||
- Add deprecation warning for using `packages` argument with `adapter.dispatch` ([#3419](https://github.com/fishtown-analytics/dbt/issues/3419), [#3420](https://github.com/fishtown-analytics/dbt/pull/3420))
|
||||
|
||||
|
||||
@@ -1,154 +0,0 @@
|
||||
# Python package
|
||||
# Create and test a Python package on multiple Python versions.
|
||||
# Add steps that analyze code, save the dist with the build record, publish to a PyPI-compatible index, and more:
|
||||
# https://docs.microsoft.com/azure/devops/pipelines/languages/python
|
||||
|
||||
trigger:
|
||||
branches:
|
||||
include:
|
||||
- develop
|
||||
- '*.latest'
|
||||
- pr/*
|
||||
|
||||
jobs:
|
||||
- job: UnitTest
|
||||
pool:
|
||||
vmImage: 'vs2017-win2016'
|
||||
steps:
|
||||
- task: UsePythonVersion@0
|
||||
inputs:
|
||||
versionSpec: '3.7'
|
||||
architecture: 'x64'
|
||||
|
||||
- script: python -m pip install --upgrade pip && pip install tox
|
||||
displayName: 'Install dependencies'
|
||||
|
||||
- script: python -m tox -e py -- -v
|
||||
displayName: Run unit tests
|
||||
|
||||
- job: PostgresIntegrationTest
|
||||
pool:
|
||||
vmImage: 'vs2017-win2016'
|
||||
dependsOn: UnitTest
|
||||
|
||||
steps:
|
||||
- pwsh: |
|
||||
$serviceName = Get-Service -Name postgresql*
|
||||
Set-Service -InputObject $serviceName -StartupType Automatic
|
||||
Start-Service -InputObject $serviceName
|
||||
|
||||
& $env:PGBIN\createdb.exe -U postgres dbt
|
||||
& $env:PGBIN\psql.exe -U postgres -c "CREATE ROLE root WITH PASSWORD 'password';"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "ALTER ROLE root WITH LOGIN;"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "GRANT CREATE, CONNECT ON DATABASE dbt TO root WITH GRANT OPTION;"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "CREATE ROLE noaccess WITH PASSWORD 'password' NOSUPERUSER;"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "ALTER ROLE noaccess WITH LOGIN;"
|
||||
& $env:PGBIN\psql.exe -U postgres -c "GRANT CONNECT ON DATABASE dbt TO noaccess;"
|
||||
displayName: Install postgresql and set up database
|
||||
|
||||
- task: UsePythonVersion@0
|
||||
inputs:
|
||||
versionSpec: '3.7'
|
||||
architecture: 'x64'
|
||||
|
||||
- script: python -m pip install --upgrade pip && pip install tox
|
||||
displayName: 'Install dependencies'
|
||||
|
||||
- script: python -m tox -e py-postgres -- -v -n4
|
||||
displayName: Run integration tests
|
||||
|
||||
# These three are all similar except secure environment variables, which MUST be passed along to their tasks,
|
||||
# but there's probably a better way to do this!
|
||||
- job: SnowflakeIntegrationTest
|
||||
pool:
|
||||
vmImage: 'vs2017-win2016'
|
||||
dependsOn: UnitTest
|
||||
condition: succeeded()
|
||||
steps:
|
||||
- task: UsePythonVersion@0
|
||||
inputs:
|
||||
versionSpec: '3.7'
|
||||
architecture: 'x64'
|
||||
|
||||
- script: python -m pip install --upgrade pip && pip install tox
|
||||
displayName: 'Install dependencies'
|
||||
|
||||
- script: python -m tox -e py-snowflake -- -v -n4
|
||||
env:
|
||||
SNOWFLAKE_TEST_ACCOUNT: $(SNOWFLAKE_TEST_ACCOUNT)
|
||||
SNOWFLAKE_TEST_PASSWORD: $(SNOWFLAKE_TEST_PASSWORD)
|
||||
SNOWFLAKE_TEST_USER: $(SNOWFLAKE_TEST_USER)
|
||||
SNOWFLAKE_TEST_WAREHOUSE: $(SNOWFLAKE_TEST_WAREHOUSE)
|
||||
SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN: $(SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN)
|
||||
SNOWFLAKE_TEST_OAUTH_CLIENT_ID: $(SNOWFLAKE_TEST_OAUTH_CLIENT_ID)
|
||||
SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET: $(SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET)
|
||||
displayName: Run integration tests
|
||||
|
||||
- job: BigQueryIntegrationTest
|
||||
pool:
|
||||
vmImage: 'vs2017-win2016'
|
||||
dependsOn: UnitTest
|
||||
condition: succeeded()
|
||||
steps:
|
||||
- task: UsePythonVersion@0
|
||||
inputs:
|
||||
versionSpec: '3.7'
|
||||
architecture: 'x64'
|
||||
- script: python -m pip install --upgrade pip && pip install tox
|
||||
displayName: 'Install dependencies'
|
||||
- script: python -m tox -e py-bigquery -- -v -n4
|
||||
env:
|
||||
BIGQUERY_SERVICE_ACCOUNT_JSON: $(BIGQUERY_SERVICE_ACCOUNT_JSON)
|
||||
displayName: Run integration tests
|
||||
|
||||
- job: RedshiftIntegrationTest
|
||||
pool:
|
||||
vmImage: 'vs2017-win2016'
|
||||
dependsOn: UnitTest
|
||||
condition: succeeded()
|
||||
steps:
|
||||
- task: UsePythonVersion@0
|
||||
inputs:
|
||||
versionSpec: '3.7'
|
||||
architecture: 'x64'
|
||||
|
||||
- script: python -m pip install --upgrade pip && pip install tox
|
||||
displayName: 'Install dependencies'
|
||||
|
||||
- script: python -m tox -e py-redshift -- -v -n4
|
||||
env:
|
||||
REDSHIFT_TEST_DBNAME: $(REDSHIFT_TEST_DBNAME)
|
||||
REDSHIFT_TEST_PASS: $(REDSHIFT_TEST_PASS)
|
||||
REDSHIFT_TEST_USER: $(REDSHIFT_TEST_USER)
|
||||
REDSHIFT_TEST_PORT: $(REDSHIFT_TEST_PORT)
|
||||
REDSHIFT_TEST_HOST: $(REDSHIFT_TEST_HOST)
|
||||
displayName: Run integration tests
|
||||
|
||||
- job: BuildWheel
|
||||
pool:
|
||||
vmImage: 'vs2017-win2016'
|
||||
dependsOn:
|
||||
- UnitTest
|
||||
- PostgresIntegrationTest
|
||||
- RedshiftIntegrationTest
|
||||
- SnowflakeIntegrationTest
|
||||
- BigQueryIntegrationTest
|
||||
condition: succeeded()
|
||||
steps:
|
||||
- task: UsePythonVersion@0
|
||||
inputs:
|
||||
versionSpec: '3.7'
|
||||
architecture: 'x64'
|
||||
- script: python -m pip install --upgrade pip setuptools && python -m pip install -r requirements.txt && python -m pip install -r dev-requirements.txt
|
||||
displayName: Install dependencies
|
||||
- task: ShellScript@2
|
||||
inputs:
|
||||
scriptPath: scripts/build-wheels.sh
|
||||
- task: CopyFiles@2
|
||||
inputs:
|
||||
contents: 'dist\?(*.whl|*.tar.gz)'
|
||||
TargetFolder: '$(Build.ArtifactStagingDirectory)'
|
||||
- task: PublishBuildArtifacts@1
|
||||
inputs:
|
||||
pathtoPublish: '$(Build.ArtifactStagingDirectory)'
|
||||
artifactName: dists
|
||||
@@ -31,7 +31,6 @@ from dbt.contracts.graph.compiled import (
|
||||
from dbt.contracts.graph.manifest import Manifest, MacroManifest
|
||||
from dbt.contracts.graph.parsed import ParsedSeedNode
|
||||
from dbt.exceptions import warn_or_error
|
||||
from dbt.node_types import NodeType
|
||||
from dbt.logger import GLOBAL_LOGGER as logger
|
||||
from dbt.utils import filter_null_values, executor
|
||||
|
||||
@@ -310,8 +309,7 @@ class BaseAdapter(metaclass=AdapterMeta):
|
||||
self.Relation.create_from(self.config, node).without_identifier()
|
||||
for node in manifest.nodes.values()
|
||||
if (
|
||||
node.resource_type in NodeType.executable() and
|
||||
not node.is_ephemeral_model
|
||||
node.is_relational and not node.is_ephemeral_model
|
||||
)
|
||||
}
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import dbt.exceptions
|
||||
|
||||
from typing import Any, Dict, Optional
|
||||
import yaml
|
||||
import yaml.scanner
|
||||
|
||||
@@ -56,7 +56,7 @@ def contextualized_yaml_error(raw_contents, error):
|
||||
raw_error=error)
|
||||
|
||||
|
||||
def safe_load(contents):
|
||||
def safe_load(contents) -> Optional[Dict[str, Any]]:
|
||||
return yaml.load(contents, Loader=SafeLoader)
|
||||
|
||||
|
||||
|
||||
@@ -120,7 +120,7 @@ class BaseContextConfigGenerator(Generic[T]):
|
||||
|
||||
def calculate_node_config(
|
||||
self,
|
||||
config_calls: List[Dict[str, Any]],
|
||||
config_call_dict: Dict[str, Any],
|
||||
fqn: List[str],
|
||||
resource_type: NodeType,
|
||||
project_name: str,
|
||||
@@ -134,8 +134,9 @@ class BaseContextConfigGenerator(Generic[T]):
|
||||
for fqn_config in project_configs:
|
||||
result = self._update_from_config(result, fqn_config)
|
||||
|
||||
for config_call in config_calls:
|
||||
result = self._update_from_config(result, config_call)
|
||||
# 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)
|
||||
|
||||
if own_config.project_name != self._active_project.project_name:
|
||||
for fqn_config in self._active_project_configs(fqn, resource_type):
|
||||
@@ -147,7 +148,7 @@ class BaseContextConfigGenerator(Generic[T]):
|
||||
@abstractmethod
|
||||
def calculate_node_config_dict(
|
||||
self,
|
||||
config_calls: List[Dict[str, Any]],
|
||||
config_call_dict: Dict[str, Any],
|
||||
fqn: List[str],
|
||||
resource_type: NodeType,
|
||||
project_name: str,
|
||||
@@ -186,14 +187,14 @@ class ContextConfigGenerator(BaseContextConfigGenerator[C]):
|
||||
|
||||
def calculate_node_config_dict(
|
||||
self,
|
||||
config_calls: List[Dict[str, Any]],
|
||||
config_call_dict: Dict[str, Any],
|
||||
fqn: List[str],
|
||||
resource_type: NodeType,
|
||||
project_name: str,
|
||||
base: bool,
|
||||
) -> Dict[str, Any]:
|
||||
config = self.calculate_node_config(
|
||||
config_calls=config_calls,
|
||||
config_call_dict=config_call_dict,
|
||||
fqn=fqn,
|
||||
resource_type=resource_type,
|
||||
project_name=project_name,
|
||||
@@ -209,14 +210,14 @@ class UnrenderedConfigGenerator(BaseContextConfigGenerator[Dict[str, Any]]):
|
||||
|
||||
def calculate_node_config_dict(
|
||||
self,
|
||||
config_calls: List[Dict[str, Any]],
|
||||
config_call_dict: Dict[str, Any],
|
||||
fqn: List[str],
|
||||
resource_type: NodeType,
|
||||
project_name: str,
|
||||
base: bool,
|
||||
) -> Dict[str, Any]:
|
||||
return self.calculate_node_config(
|
||||
config_calls=config_calls,
|
||||
config_call_dict=config_call_dict,
|
||||
fqn=fqn,
|
||||
resource_type=resource_type,
|
||||
project_name=project_name,
|
||||
@@ -251,14 +252,32 @@ class ContextConfig:
|
||||
resource_type: NodeType,
|
||||
project_name: str,
|
||||
) -> None:
|
||||
self._config_calls: List[Dict[str, Any]] = []
|
||||
self._config_call_dict: Dict[str, Any] = {}
|
||||
self._active_project = active_project
|
||||
self._fqn = fqn
|
||||
self._resource_type = resource_type
|
||||
self._project_name = project_name
|
||||
|
||||
def update_in_model_config(self, opts: Dict[str, Any]) -> None:
|
||||
self._config_calls.append(opts)
|
||||
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 build_config_dict(
|
||||
self,
|
||||
@@ -272,7 +291,7 @@ class ContextConfig:
|
||||
src = UnrenderedConfigGenerator(self._active_project)
|
||||
|
||||
return src.calculate_node_config_dict(
|
||||
config_calls=self._config_calls,
|
||||
config_call_dict=self._config_call_dict,
|
||||
fqn=self._fqn,
|
||||
resource_type=self._resource_type,
|
||||
project_name=self._project_name,
|
||||
|
||||
@@ -169,6 +169,8 @@ class TestMacroNamespace:
|
||||
|
||||
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]
|
||||
|
||||
@@ -279,7 +279,7 @@ class Config(Protocol):
|
||||
...
|
||||
|
||||
|
||||
# `config` implementations
|
||||
# Implementation of "config(..)" calls in models
|
||||
class ParseConfigObject(Config):
|
||||
def __init__(self, model, context_config: Optional[ContextConfig]):
|
||||
self.model = model
|
||||
@@ -316,7 +316,7 @@ class ParseConfigObject(Config):
|
||||
raise RuntimeException(
|
||||
'At parse time, did not receive a context config'
|
||||
)
|
||||
self.context_config.update_in_model_config(opts)
|
||||
self.context_config.add_config_call(opts)
|
||||
return ''
|
||||
|
||||
def set(self, name, value):
|
||||
|
||||
@@ -156,20 +156,11 @@ class BaseSourceFile(dbtClassMixin, SerializableType):
|
||||
|
||||
def _serialize(self):
|
||||
dct = self.to_dict()
|
||||
if 'pp_files' in dct:
|
||||
del dct['pp_files']
|
||||
if 'pp_test_index' in dct:
|
||||
del dct['pp_test_index']
|
||||
return dct
|
||||
|
||||
@classmethod
|
||||
def _deserialize(cls, dct: Dict[str, int]):
|
||||
if dct['parse_file_type'] == 'schema':
|
||||
# TODO: why are these keys even here
|
||||
if 'pp_files' in dct:
|
||||
del dct['pp_files']
|
||||
if 'pp_test_index' in dct:
|
||||
del dct['pp_test_index']
|
||||
sf = SchemaSourceFile.from_dict(dct)
|
||||
else:
|
||||
sf = SourceFile.from_dict(dct)
|
||||
@@ -223,13 +214,13 @@ class SourceFile(BaseSourceFile):
|
||||
class SchemaSourceFile(BaseSourceFile):
|
||||
dfy: Dict[str, Any] = field(default_factory=dict)
|
||||
# these are in the manifest.nodes dictionary
|
||||
tests: List[str] = field(default_factory=list)
|
||||
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: List[str] = field(default_factory=list)
|
||||
mcp: Dict[str, str] = field(default_factory=dict)
|
||||
# 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'
|
||||
@@ -255,14 +246,53 @@ class SchemaSourceFile(BaseSourceFile):
|
||||
|
||||
def __post_serialize__(self, dct):
|
||||
dct = super().__post_serialize__(dct)
|
||||
if 'pp_files' in dct:
|
||||
del dct['pp_files']
|
||||
if 'pp_test_index' in dct:
|
||||
del dct['pp_test_index']
|
||||
# Remove partial parsing specific data
|
||||
for key in ('pp_files', 'pp_test_index', 'pp_dict'):
|
||||
if key in dct:
|
||||
del dct[key]
|
||||
return dct
|
||||
|
||||
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]
|
||||
|
||||
@@ -172,7 +172,7 @@ class RefableLookup(dbtClassMixin):
|
||||
|
||||
|
||||
class AnalysisLookup(RefableLookup):
|
||||
_lookup_types: ClassVar[set] = set(NodeType.Analysis)
|
||||
_lookup_types: ClassVar[set] = set([NodeType.Analysis])
|
||||
|
||||
|
||||
def _search_packages(
|
||||
@@ -243,7 +243,7 @@ def _sort_values(dct):
|
||||
return {k: sorted(v) for k, v in dct.items()}
|
||||
|
||||
|
||||
def build_edges(nodes: List[ManifestNode]):
|
||||
def build_node_edges(nodes: List[ManifestNode]):
|
||||
"""Build the forward and backward edges on the given list of ParsedNodes
|
||||
and return them as two separate dictionaries, each mapping unique IDs to
|
||||
lists of edges.
|
||||
@@ -259,6 +259,18 @@ def build_edges(nodes: List[ManifestNode]):
|
||||
return _sort_values(forward_edges), _sort_values(backward_edges)
|
||||
|
||||
|
||||
# Build a map of children of macros
|
||||
def build_macro_edges(nodes: List[Any]):
|
||||
forward_edges: Dict[str, List[str]] = {
|
||||
n.unique_id: [] for n in nodes if n.unique_id.startswith('macro') or n.depends_on.macros
|
||||
}
|
||||
for node in nodes:
|
||||
for unique_id in node.depends_on.macros:
|
||||
if unique_id in forward_edges.keys():
|
||||
forward_edges[unique_id].append(node.unique_id)
|
||||
return _sort_values(forward_edges)
|
||||
|
||||
|
||||
def _deepcopy(value):
|
||||
return value.from_dict(value.to_dict(omit_none=True))
|
||||
|
||||
@@ -525,6 +537,12 @@ class MacroMethods:
|
||||
return candidates
|
||||
|
||||
|
||||
@dataclass
|
||||
class ParsingInfo:
|
||||
static_analysis_parsed_path_count: int = 0
|
||||
static_analysis_path_count: int = 0
|
||||
|
||||
|
||||
@dataclass
|
||||
class ManifestStateCheck(dbtClassMixin):
|
||||
vars_hash: FileHash = field(default_factory=FileHash.empty)
|
||||
@@ -566,9 +584,13 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
|
||||
_analysis_lookup: Optional[AnalysisLookup] = field(
|
||||
default=None, metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
|
||||
)
|
||||
_parsing_info: ParsingInfo = field(
|
||||
default_factory=ParsingInfo,
|
||||
metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
|
||||
)
|
||||
_lock: Lock = field(
|
||||
default_factory=flags.MP_CONTEXT.Lock,
|
||||
metadata={'serialize': lambda x: None, 'deserialize': lambda x: flags.MP_CONTEXT.Lock}
|
||||
metadata={'serialize': lambda x: None, 'deserialize': lambda x: None}
|
||||
)
|
||||
|
||||
def __pre_serialize__(self):
|
||||
@@ -577,6 +599,11 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
|
||||
self.source_patches = {}
|
||||
return self
|
||||
|
||||
@classmethod
|
||||
def __post_deserialize__(cls, obj):
|
||||
obj._lock = flags.MP_CONTEXT.Lock()
|
||||
return obj
|
||||
|
||||
def sync_update_node(
|
||||
self, new_node: NonSourceCompiledNode
|
||||
) -> NonSourceCompiledNode:
|
||||
@@ -732,7 +759,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
|
||||
if macro.patch_path:
|
||||
package_name, existing_file_path = macro.patch_path.split('://')
|
||||
raise_duplicate_macro_patch_name(patch, existing_file_path)
|
||||
source_file.macro_patches.append(unique_id)
|
||||
source_file.macro_patches[patch.name] = unique_id
|
||||
macro.patch(patch)
|
||||
|
||||
def add_source_patch(
|
||||
@@ -779,10 +806,18 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
|
||||
self.sources.values(),
|
||||
self.exposures.values(),
|
||||
))
|
||||
forward_edges, backward_edges = build_edges(edge_members)
|
||||
forward_edges, backward_edges = build_node_edges(edge_members)
|
||||
self.child_map = forward_edges
|
||||
self.parent_map = backward_edges
|
||||
|
||||
def build_macro_child_map(self):
|
||||
edge_members = list(chain(
|
||||
self.nodes.values(),
|
||||
self.macros.values(),
|
||||
))
|
||||
forward_edges = build_macro_edges(edge_members)
|
||||
return forward_edges
|
||||
|
||||
def writable_manifest(self):
|
||||
self.build_parent_and_child_maps()
|
||||
return WritableManifest(
|
||||
@@ -1016,10 +1051,11 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
|
||||
_check_duplicates(node, self.nodes)
|
||||
self.nodes[node.unique_id] = node
|
||||
|
||||
def add_node(self, source_file: AnySourceFile, node: ManifestNodes):
|
||||
def add_node(self, source_file: AnySourceFile, node: ManifestNodes, test_from=None):
|
||||
self.add_node_nofile(node)
|
||||
if isinstance(source_file, SchemaSourceFile):
|
||||
source_file.tests.append(node.unique_id)
|
||||
assert test_from
|
||||
source_file.add_test(node.unique_id, test_from)
|
||||
else:
|
||||
source_file.nodes.append(node.unique_id)
|
||||
|
||||
@@ -1034,10 +1070,11 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
|
||||
else:
|
||||
self._disabled[node.unique_id] = [node]
|
||||
|
||||
def add_disabled(self, source_file: AnySourceFile, node: CompileResultNode):
|
||||
def add_disabled(self, source_file: AnySourceFile, node: CompileResultNode, test_from=None):
|
||||
self.add_disabled_nofile(node)
|
||||
if isinstance(source_file, SchemaSourceFile):
|
||||
source_file.tests.append(node.unique_id)
|
||||
assert test_from
|
||||
source_file.add_test(node.unique_id, test_from)
|
||||
else:
|
||||
source_file.nodes.append(node.unique_id)
|
||||
|
||||
|
||||
@@ -2,13 +2,13 @@ from dataclasses import field, Field, dataclass
|
||||
from enum import Enum
|
||||
from itertools import chain
|
||||
from typing import (
|
||||
Any, List, Optional, Dict, Union, Type, TypeVar
|
||||
Any, List, Optional, Dict, Union, Type, TypeVar, Callable
|
||||
)
|
||||
from dbt.dataclass_schema import (
|
||||
dbtClassMixin, ValidationError, register_pattern,
|
||||
)
|
||||
from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed
|
||||
from dbt.exceptions import InternalException
|
||||
from dbt.exceptions import InternalException, CompilationException
|
||||
from dbt.contracts.util import Replaceable, list_str
|
||||
from dbt import hooks
|
||||
from dbt.node_types import NodeType
|
||||
@@ -204,6 +204,34 @@ class BaseConfig(
|
||||
else:
|
||||
self._extra[key] = value
|
||||
|
||||
def __delitem__(self, key):
|
||||
if hasattr(self, key):
|
||||
msg = (
|
||||
'Error, tried to delete config key "{}": Cannot delete '
|
||||
'built-in keys'
|
||||
).format(key)
|
||||
raise CompilationException(msg)
|
||||
else:
|
||||
del self._extra[key]
|
||||
|
||||
def _content_iterator(self, include_condition: Callable[[Field], bool]):
|
||||
seen = set()
|
||||
for fld, _ in self._get_fields():
|
||||
seen.add(fld.name)
|
||||
if include_condition(fld):
|
||||
yield fld.name
|
||||
|
||||
for key in self._extra:
|
||||
if key not in seen:
|
||||
seen.add(key)
|
||||
yield key
|
||||
|
||||
def __iter__(self):
|
||||
yield from self._content_iterator(include_condition=lambda f: True)
|
||||
|
||||
def __len__(self):
|
||||
return len(self._get_fields()) + len(self._extra)
|
||||
|
||||
@staticmethod
|
||||
def compare_key(
|
||||
unrendered: Dict[str, Any],
|
||||
@@ -239,8 +267,14 @@ class BaseConfig(
|
||||
return False
|
||||
return True
|
||||
|
||||
# This is used in 'add_config_call' to created the combined config_call_dict.
|
||||
mergebehavior = {
|
||||
"append": ['pre-hook', 'pre_hook', 'post-hook', 'post_hook', 'tags'],
|
||||
"update": ['quoting', 'column_types'],
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def _extract_dict(
|
||||
def _merge_dicts(
|
||||
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,
|
||||
@@ -286,10 +320,10 @@ class BaseConfig(
|
||||
|
||||
adapter_config_cls = get_config_class_by_name(adapter_type)
|
||||
|
||||
self_merged = self._extract_dict(dct, data)
|
||||
self_merged = self._merge_dicts(dct, data)
|
||||
dct.update(self_merged)
|
||||
|
||||
adapter_merged = adapter_config_cls._extract_dict(dct, data)
|
||||
adapter_merged = adapter_config_cls._merge_dicts(dct, data)
|
||||
dct.update(adapter_merged)
|
||||
|
||||
# any remaining fields must be "clobber"
|
||||
@@ -322,6 +356,8 @@ class SourceConfig(BaseConfig):
|
||||
|
||||
@dataclass
|
||||
class NodeConfig(BaseConfig):
|
||||
# Note: if any new fields are added with MergeBehavior, also update the
|
||||
# 'mergebehavior' dictionary
|
||||
enabled: bool = True
|
||||
materialized: str = 'view'
|
||||
persist_docs: Dict[str, Any] = field(default_factory=dict)
|
||||
|
||||
@@ -83,6 +83,7 @@ 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):
|
||||
|
||||
@@ -71,10 +71,14 @@ class RegistryUnpinnedPackage(
|
||||
RegistryPackageMixin, UnpinnedPackage[RegistryPinnedPackage]
|
||||
):
|
||||
def __init__(
|
||||
self, package: str, versions: List[semver.VersionSpecifier]
|
||||
self,
|
||||
package: str,
|
||||
versions: List[semver.VersionSpecifier],
|
||||
install_prerelease: bool
|
||||
) -> None:
|
||||
super().__init__(package)
|
||||
self.versions = versions
|
||||
self.install_prerelease = install_prerelease
|
||||
|
||||
def _check_in_index(self):
|
||||
index = registry.index_cached()
|
||||
@@ -91,13 +95,18 @@ class RegistryUnpinnedPackage(
|
||||
semver.VersionSpecifier.from_version_string(v)
|
||||
for v in raw_version
|
||||
]
|
||||
return cls(package=contract.package, versions=versions)
|
||||
return cls(
|
||||
package=contract.package,
|
||||
versions=versions,
|
||||
install_prerelease=contract.install_prerelease
|
||||
)
|
||||
|
||||
def incorporate(
|
||||
self, other: 'RegistryUnpinnedPackage'
|
||||
) -> 'RegistryUnpinnedPackage':
|
||||
return RegistryUnpinnedPackage(
|
||||
package=self.package,
|
||||
install_prerelease=self.install_prerelease,
|
||||
versions=self.versions + other.versions,
|
||||
)
|
||||
|
||||
@@ -111,12 +120,16 @@ class RegistryUnpinnedPackage(
|
||||
raise DependencyException(new_msg) from e
|
||||
|
||||
available = registry.get_available_versions(self.package)
|
||||
installable = semver.filter_installable(
|
||||
available,
|
||||
self.install_prerelease
|
||||
)
|
||||
|
||||
# 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_, available)
|
||||
target = semver.resolve_to_specific_version(range_, installable)
|
||||
if not target:
|
||||
package_version_not_found(self.package, range_, available)
|
||||
package_version_not_found(self.package, range_, installable)
|
||||
return RegistryPinnedPackage(package=self.package, version=target)
|
||||
|
||||
@@ -1,3 +1,19 @@
|
||||
{% macro get_test_sql(main_sql, fail_calc, warn_if, error_if, limit) -%}
|
||||
{{ adapter.dispatch('get_test_sql')(main_sql, fail_calc, warn_if, error_if, limit) }}
|
||||
{%- endmacro %}
|
||||
|
||||
|
||||
{% macro default__get_test_sql(main_sql, fail_calc, warn_if, error_if, limit) -%}
|
||||
select
|
||||
{{ fail_calc }} as failures,
|
||||
{{ fail_calc }} {{ warn_if }} as should_warn,
|
||||
{{ fail_calc }} {{ error_if }} as should_error
|
||||
from (
|
||||
{{ main_sql }}
|
||||
{{ "limit " ~ limit if limit != none }}
|
||||
) dbt_internal_test
|
||||
{%- endmacro %}
|
||||
|
||||
{%- materialization test, default -%}
|
||||
|
||||
{% set relations = [] %}
|
||||
@@ -39,14 +55,7 @@
|
||||
|
||||
{% call statement('main', fetch_result=True) -%}
|
||||
|
||||
select
|
||||
{{ fail_calc }} as failures,
|
||||
{{ fail_calc }} {{ warn_if }} as should_warn,
|
||||
{{ fail_calc }} {{ error_if }} as should_error
|
||||
from (
|
||||
{{ main_sql }}
|
||||
{{ "limit " ~ limit if limit != none }}
|
||||
) dbt_internal_test
|
||||
{{ get_test_sql(main_sql, fail_calc, warn_if, error_if, limit)}}
|
||||
|
||||
{%- endcall %}
|
||||
|
||||
|
||||
@@ -1,16 +1,25 @@
|
||||
|
||||
{% macro default__test_relationships(model, column_name, to, field) %}
|
||||
|
||||
with child as (
|
||||
select {{ column_name }} as from_field
|
||||
from {{ model }}
|
||||
where {{ column_name }} is not null
|
||||
),
|
||||
|
||||
parent as (
|
||||
select {{ field }} as to_field
|
||||
from {{ to }}
|
||||
)
|
||||
|
||||
select
|
||||
child.{{ column_name }}
|
||||
from_field
|
||||
|
||||
from {{ model }} as child
|
||||
from child
|
||||
left join parent
|
||||
on child.from_field = parent.to_field
|
||||
|
||||
left join {{ to }} as parent
|
||||
on child.{{ column_name }} = parent.{{ field }}
|
||||
|
||||
where child.{{ column_name }} is not null
|
||||
and parent.{{ field }} is null
|
||||
where parent.to_field is null
|
||||
|
||||
{% endmacro %}
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{% macro default__test_unique(model, column_name) %}
|
||||
|
||||
select
|
||||
{{ column_name }},
|
||||
{{ column_name }} as unique_field,
|
||||
count(*) as n_records
|
||||
|
||||
from {{ model }}
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -1,8 +1,9 @@
|
||||
from dataclasses import dataclass
|
||||
from dataclasses import field
|
||||
import os
|
||||
import traceback
|
||||
from typing import (
|
||||
Dict, Optional, Mapping, Callable, Any, List, Type, Union
|
||||
Dict, Optional, Mapping, Callable, Any, List, Type, Union, Tuple
|
||||
)
|
||||
import time
|
||||
|
||||
@@ -31,7 +32,7 @@ from dbt.parser.read_files import read_files, load_source_file
|
||||
from dbt.parser.partial import PartialParsing
|
||||
from dbt.contracts.graph.compiled import ManifestNode
|
||||
from dbt.contracts.graph.manifest import (
|
||||
Manifest, Disabled, MacroManifest, ManifestStateCheck
|
||||
Manifest, Disabled, MacroManifest, ManifestStateCheck, ParsingInfo
|
||||
)
|
||||
from dbt.contracts.graph.parsed import (
|
||||
ParsedSourceDefinition, ParsedNode, ParsedMacro, ColumnInfo, ParsedExposure
|
||||
@@ -59,19 +60,30 @@ from dbt.parser.sources import SourcePatcher
|
||||
from dbt.ui import warning_tag
|
||||
from dbt.version import __version__
|
||||
|
||||
from dbt.dataclass_schema import dbtClassMixin
|
||||
from dbt.dataclass_schema import StrEnum, dbtClassMixin
|
||||
|
||||
PARTIAL_PARSE_FILE_NAME = 'partial_parse.msgpack'
|
||||
PARSING_STATE = DbtProcessState('parsing')
|
||||
DEFAULT_PARTIAL_PARSE = False
|
||||
|
||||
|
||||
class ReparseReason(StrEnum):
|
||||
version_mismatch = '01_version_mismatch'
|
||||
file_not_found = '02_file_not_found'
|
||||
vars_changed = '03_vars_changed'
|
||||
profile_changed = '04_profile_changed'
|
||||
deps_changed = '05_deps_changed'
|
||||
project_config_changed = '06_project_config_changed'
|
||||
load_file_failure = '07_load_file_failure'
|
||||
exception = '08_exception'
|
||||
|
||||
|
||||
# Part of saved performance info
|
||||
@dataclass
|
||||
class ParserInfo(dbtClassMixin):
|
||||
parser: str
|
||||
elapsed: float
|
||||
path_count: int = 0
|
||||
parsed_path_count: int = 0
|
||||
|
||||
|
||||
# Part of saved performance info
|
||||
@@ -80,14 +92,18 @@ class ProjectLoaderInfo(dbtClassMixin):
|
||||
project_name: str
|
||||
elapsed: float
|
||||
parsers: List[ParserInfo] = field(default_factory=list)
|
||||
path_count: int = 0
|
||||
parsed_path_count: int = 0
|
||||
|
||||
|
||||
# Part of saved performance info
|
||||
@dataclass
|
||||
class ManifestLoaderInfo(dbtClassMixin, Writable):
|
||||
path_count: int = 0
|
||||
parsed_path_count: int = 0
|
||||
static_analysis_path_count: int = 0
|
||||
static_analysis_parsed_path_count: int = 0
|
||||
is_partial_parse_enabled: Optional[bool] = None
|
||||
is_static_analysis_enabled: Optional[bool] = None
|
||||
read_files_elapsed: Optional[float] = None
|
||||
load_macros_elapsed: Optional[float] = None
|
||||
parse_project_elapsed: Optional[float] = None
|
||||
@@ -135,8 +151,6 @@ class ManifestLoader:
|
||||
# have been enabled, but not happening because of some issue.
|
||||
self.partially_parsing = False
|
||||
|
||||
self._perf_info = self.build_perf_info()
|
||||
|
||||
# This is a saved manifest from a previous run that's used for partial parsing
|
||||
self.saved_manifest: Optional[Manifest] = self.read_manifest_for_partial_parse()
|
||||
|
||||
@@ -184,37 +198,71 @@ class ManifestLoader:
|
||||
|
||||
# This is where the main action happens
|
||||
def load(self):
|
||||
|
||||
# Read files creates a dictionary of projects to a dictionary
|
||||
# of parsers to lists of file strings. The file strings are
|
||||
# used to get the SourceFiles from the manifest files.
|
||||
# In the future the loaded files will be used to control
|
||||
# partial parsing, but right now we're just moving the
|
||||
# file loading out of the individual parsers and doing it
|
||||
# all at once.
|
||||
start_read_files = time.perf_counter()
|
||||
project_parser_files = {}
|
||||
for project in self.all_projects.values():
|
||||
read_files(project, self.manifest.files, project_parser_files)
|
||||
self._perf_info.path_count = len(self.manifest.files)
|
||||
self._perf_info.read_files_elapsed = (time.perf_counter() - start_read_files)
|
||||
|
||||
skip_parsing = False
|
||||
if self.saved_manifest is not None:
|
||||
partial_parsing = PartialParsing(self.saved_manifest, self.manifest.files)
|
||||
skip_parsing = partial_parsing.skip_parsing()
|
||||
if not skip_parsing:
|
||||
if skip_parsing:
|
||||
# nothing changed, so we don't need to generate project_parser_files
|
||||
self.manifest = self.saved_manifest
|
||||
else:
|
||||
# create child_map and parent_map
|
||||
self.saved_manifest.build_parent_and_child_maps()
|
||||
# files are different, we need to create a new set of
|
||||
# project_parser_files.
|
||||
project_parser_files = partial_parsing.get_parsing_files()
|
||||
self.manifest = self.saved_manifest
|
||||
self.partially_parsing = True
|
||||
try:
|
||||
project_parser_files = partial_parsing.get_parsing_files()
|
||||
self.partially_parsing = True
|
||||
self.manifest = self.saved_manifest
|
||||
except Exception:
|
||||
# pp_files should still be the full set and manifest is new manifest,
|
||||
# since get_parsing_files failed
|
||||
logger.info("Partial parsing enabled but an error occurred. "
|
||||
"Switching to a full re-parse.")
|
||||
|
||||
# Get traceback info
|
||||
tb_info = traceback.format_exc()
|
||||
formatted_lines = tb_info.splitlines()
|
||||
(_, line, method) = formatted_lines[-3].split(', ')
|
||||
exc_info = {
|
||||
"traceback": tb_info,
|
||||
"exception": formatted_lines[-1],
|
||||
"code": formatted_lines[-2],
|
||||
"location": f"{line} {method}",
|
||||
}
|
||||
|
||||
# get file info for local logs
|
||||
parse_file_type = None
|
||||
file_id = partial_parsing.processing_file
|
||||
if file_id and file_id in self.manifest.files:
|
||||
old_file = self.manifest.files[file_id]
|
||||
parse_file_type = old_file.parse_file_type
|
||||
logger.debug(f"Partial parsing exception processing file {file_id}")
|
||||
file_dict = old_file.to_dict()
|
||||
logger.debug(f"PP file: {file_dict}")
|
||||
exc_info['parse_file_type'] = parse_file_type
|
||||
logger.debug(f"PP exception info: {exc_info}")
|
||||
|
||||
# Send event
|
||||
if dbt.tracking.active_user is not None:
|
||||
exc_info['full_reparse_reason'] = ReparseReason.exception
|
||||
dbt.tracking.track_partial_parser(exc_info)
|
||||
|
||||
if self.manifest._parsing_info is None:
|
||||
self.manifest._parsing_info = ParsingInfo()
|
||||
|
||||
if skip_parsing:
|
||||
logger.info("Partial parsing enabled, no changes found, skipping parsing")
|
||||
self.manifest = self.saved_manifest
|
||||
|
||||
else:
|
||||
# Load Macros
|
||||
# We need to parse the macros first, so they're resolvable when
|
||||
@@ -230,6 +278,8 @@ class ManifestLoader:
|
||||
for file_id in parser_files['MacroParser']:
|
||||
block = FileBlock(self.manifest.files[file_id])
|
||||
parser.parse_file(block)
|
||||
# increment parsed path count for performance tracking
|
||||
self._perf_info.parsed_path_count = self._perf_info.parsed_path_count + 1
|
||||
# Look at changed macros and update the macro.depends_on.macros
|
||||
self.macro_depends_on()
|
||||
self._perf_info.load_macros_elapsed = (time.perf_counter() - start_load_macros)
|
||||
@@ -301,9 +351,17 @@ class ManifestLoader:
|
||||
self.process_sources(self.root_project.project_name)
|
||||
self.process_refs(self.root_project.project_name)
|
||||
self.process_docs(self.root_project)
|
||||
|
||||
# update tracking data
|
||||
self._perf_info.process_manifest_elapsed = (
|
||||
time.perf_counter() - start_process
|
||||
)
|
||||
self._perf_info.static_analysis_parsed_path_count = (
|
||||
self.manifest._parsing_info.static_analysis_parsed_path_count
|
||||
)
|
||||
self._perf_info.static_analysis_path_count = (
|
||||
self.manifest._parsing_info.static_analysis_path_count
|
||||
)
|
||||
|
||||
# write out the fully parsed manifest
|
||||
self.write_manifest_for_partial_parse()
|
||||
@@ -321,7 +379,7 @@ class ManifestLoader:
|
||||
|
||||
project_loader_info = self._perf_info._project_index[project.project_name]
|
||||
start_timer = time.perf_counter()
|
||||
total_path_count = 0
|
||||
total_parsed_path_count = 0
|
||||
|
||||
# Loop through parsers with loaded files.
|
||||
for parser_cls in parser_types:
|
||||
@@ -331,7 +389,7 @@ class ManifestLoader:
|
||||
continue
|
||||
|
||||
# Initialize timing info
|
||||
parser_path_count = 0
|
||||
project_parsed_path_count = 0
|
||||
parser_start_timer = time.perf_counter()
|
||||
|
||||
# Parse the project files for this parser
|
||||
@@ -347,15 +405,15 @@ class ManifestLoader:
|
||||
parser.parse_file(block, dct=dct)
|
||||
else:
|
||||
parser.parse_file(block)
|
||||
parser_path_count = parser_path_count + 1
|
||||
project_parsed_path_count = project_parsed_path_count + 1
|
||||
|
||||
# Save timing info
|
||||
project_loader_info.parsers.append(ParserInfo(
|
||||
parser=parser.resource_type,
|
||||
path_count=parser_path_count,
|
||||
parsed_path_count=project_parsed_path_count,
|
||||
elapsed=time.perf_counter() - parser_start_timer
|
||||
))
|
||||
total_path_count = total_path_count + parser_path_count
|
||||
total_parsed_path_count = total_parsed_path_count + project_parsed_path_count
|
||||
|
||||
# HookParser doesn't run from loaded files, just dbt_project.yml,
|
||||
# so do separately
|
||||
@@ -365,17 +423,19 @@ class ManifestLoader:
|
||||
if not self.partially_parsing and HookParser in parser_types:
|
||||
hook_parser = HookParser(project, self.manifest, self.root_project)
|
||||
path = hook_parser.get_path()
|
||||
file_block = FileBlock(
|
||||
load_source_file(path, ParseFileType.Hook, project.project_name)
|
||||
)
|
||||
hook_parser.parse_file(file_block)
|
||||
file = load_source_file(path, ParseFileType.Hook, project.project_name)
|
||||
if file:
|
||||
file_block = FileBlock(file)
|
||||
hook_parser.parse_file(file_block)
|
||||
|
||||
# Store the performance info
|
||||
elapsed = time.perf_counter() - start_timer
|
||||
project_loader_info.path_count = project_loader_info.path_count + total_path_count
|
||||
project_loader_info.parsed_path_count = (
|
||||
project_loader_info.parsed_path_count + total_parsed_path_count
|
||||
)
|
||||
project_loader_info.elapsed = project_loader_info.elapsed + elapsed
|
||||
self._perf_info.path_count = (
|
||||
self._perf_info.path_count + total_path_count
|
||||
self._perf_info.parsed_path_count = (
|
||||
self._perf_info.parsed_path_count + total_parsed_path_count
|
||||
)
|
||||
|
||||
# Loop through macros in the manifest and statically parse
|
||||
@@ -418,6 +478,12 @@ class ManifestLoader:
|
||||
path = os.path.join(self.root_project.target_path,
|
||||
PARTIAL_PARSE_FILE_NAME)
|
||||
try:
|
||||
# This shouldn't be necessary, but we have gotten bug reports (#3757) of the
|
||||
# saved manifest not matching the code version.
|
||||
if self.manifest.metadata.dbt_version != __version__:
|
||||
logger.debug("Manifest metadata did not contain correct version. "
|
||||
f"Contained '{self.manifest.metadata.dbt_version}' instead.")
|
||||
self.manifest.metadata.dbt_version = __version__
|
||||
manifest_msgpack = self.manifest.to_msgpack()
|
||||
make_directory(os.path.dirname(path))
|
||||
with open(path, 'wb') as fp:
|
||||
@@ -425,24 +491,31 @@ class ManifestLoader:
|
||||
except Exception:
|
||||
raise
|
||||
|
||||
def matching_parse_results(self, manifest: Manifest) -> bool:
|
||||
def is_partial_parsable(self, manifest: Manifest) -> Tuple[bool, Optional[str]]:
|
||||
"""Compare the global hashes of the read-in parse results' values to
|
||||
the known ones, and return if it is ok to re-use the results.
|
||||
"""
|
||||
valid = True
|
||||
reparse_reason = None
|
||||
|
||||
if manifest.metadata.dbt_version != __version__:
|
||||
logger.info("Unable to do partial parsing because of a dbt version mismatch")
|
||||
return False # If the version is wrong, the other checks might not work
|
||||
# #3757 log both versions because of reports of invalid cases of mismatch.
|
||||
logger.info("Unable to do partial parsing because of a dbt version mismatch. "
|
||||
f"Saved manifest version: {manifest.metadata.dbt_version}. "
|
||||
f"Current version: {__version__}.")
|
||||
# If the version is wrong, the other checks might not work
|
||||
return False, ReparseReason.version_mismatch
|
||||
if self.manifest.state_check.vars_hash != manifest.state_check.vars_hash:
|
||||
logger.info("Unable to do partial parsing because config vars, "
|
||||
"config profile, or config target have changed")
|
||||
valid = False
|
||||
reparse_reason = ReparseReason.vars_changed
|
||||
if self.manifest.state_check.profile_hash != manifest.state_check.profile_hash:
|
||||
# Note: This should be made more granular. We shouldn't need to invalidate
|
||||
# partial parsing if a non-used profile section has changed.
|
||||
logger.info("Unable to do partial parsing because profile has changed")
|
||||
valid = False
|
||||
reparse_reason = ReparseReason.profile_changed
|
||||
|
||||
missing_keys = {
|
||||
k for k in self.manifest.state_check.project_hashes
|
||||
@@ -451,6 +524,7 @@ class ManifestLoader:
|
||||
if missing_keys:
|
||||
logger.info("Unable to do partial parsing because a project dependency has been added")
|
||||
valid = False
|
||||
reparse_reason = ReparseReason.deps_changed
|
||||
|
||||
for key, new_value in self.manifest.state_check.project_hashes.items():
|
||||
if key in manifest.state_check.project_hashes:
|
||||
@@ -459,7 +533,8 @@ class ManifestLoader:
|
||||
logger.info("Unable to do partial parsing because "
|
||||
"a project config has changed")
|
||||
valid = False
|
||||
return valid
|
||||
reparse_reason = ReparseReason.project_config_changed
|
||||
return valid, reparse_reason
|
||||
|
||||
def _partial_parse_enabled(self):
|
||||
# if the CLI is set, follow that
|
||||
@@ -478,6 +553,8 @@ class ManifestLoader:
|
||||
path = os.path.join(self.root_project.target_path,
|
||||
PARTIAL_PARSE_FILE_NAME)
|
||||
|
||||
reparse_reason = None
|
||||
|
||||
if os.path.exists(path):
|
||||
try:
|
||||
with open(path, 'rb') as fp:
|
||||
@@ -486,7 +563,8 @@ class ManifestLoader:
|
||||
# keep this check inside the try/except in case something about
|
||||
# the file has changed in weird ways, perhaps due to being a
|
||||
# different version of dbt
|
||||
if self.matching_parse_results(manifest):
|
||||
is_partial_parseable, reparse_reason = self.is_partial_parsable(manifest)
|
||||
if is_partial_parseable:
|
||||
return manifest
|
||||
except Exception as exc:
|
||||
logger.debug(
|
||||
@@ -494,19 +572,24 @@ class ManifestLoader:
|
||||
.format(path, exc),
|
||||
exc_info=True
|
||||
)
|
||||
reparse_reason = ReparseReason.load_file_failure
|
||||
else:
|
||||
logger.info(f"Unable to do partial parsing because {path} not found")
|
||||
reparse_reason = ReparseReason.file_not_found
|
||||
|
||||
# this event is only fired if a full reparse is needed
|
||||
dbt.tracking.track_partial_parser({'full_reparse_reason': reparse_reason})
|
||||
|
||||
return None
|
||||
|
||||
def build_perf_info(self):
|
||||
mli = ManifestLoaderInfo(
|
||||
is_partial_parse_enabled=self._partial_parse_enabled()
|
||||
is_partial_parse_enabled=self._partial_parse_enabled(),
|
||||
is_static_analysis_enabled=flags.USE_EXPERIMENTAL_PARSER
|
||||
)
|
||||
for project in self.all_projects.values():
|
||||
project_info = ProjectLoaderInfo(
|
||||
project_name=project.project_name,
|
||||
path_count=0,
|
||||
elapsed=0,
|
||||
)
|
||||
mli.projects.append(project_info)
|
||||
@@ -603,6 +686,7 @@ class ManifestLoader:
|
||||
"invocation_id": invocation_id,
|
||||
"project_id": self.root_project.hashed_name(),
|
||||
"path_count": self._perf_info.path_count,
|
||||
"parsed_path_count": self._perf_info.parsed_path_count,
|
||||
"read_files_elapsed": self._perf_info.read_files_elapsed,
|
||||
"load_macros_elapsed": self._perf_info.load_macros_elapsed,
|
||||
"parse_project_elapsed": self._perf_info.parse_project_elapsed,
|
||||
@@ -614,6 +698,9 @@ class ManifestLoader:
|
||||
"is_partial_parse_enabled": (
|
||||
self._perf_info.is_partial_parse_enabled
|
||||
),
|
||||
"is_static_analysis_enabled": self._perf_info.is_static_analysis_enabled,
|
||||
"static_analysis_path_count": self._perf_info.static_analysis_path_count,
|
||||
"static_analysis_parsed_path_count": self._perf_info.static_analysis_parsed_path_count,
|
||||
})
|
||||
|
||||
# Takes references in 'refs' array of nodes and exposures, finds the target
|
||||
|
||||
@@ -1,10 +1,15 @@
|
||||
from dbt.context.context_config import ContextConfig
|
||||
from dbt.contracts.graph.parsed import ParsedModelNode
|
||||
import dbt.flags as flags
|
||||
import dbt.tracking
|
||||
from dbt.node_types import NodeType
|
||||
from dbt.parser.base import IntermediateNode, SimpleSQLParser
|
||||
from dbt.parser.base import SimpleSQLParser
|
||||
from dbt.parser.search import FileBlock
|
||||
from dbt.tree_sitter_jinja.extractor import extract_from_source
|
||||
import dbt.tracking as tracking
|
||||
from dbt import utils
|
||||
from dbt_extractor import ExtractionError, py_extract_from_source # type: ignore
|
||||
import random
|
||||
from typing import Any, Dict, List
|
||||
|
||||
|
||||
class ModelParser(SimpleSQLParser[ParsedModelNode]):
|
||||
@@ -22,46 +27,121 @@ class ModelParser(SimpleSQLParser[ParsedModelNode]):
|
||||
return block.path.relative_path
|
||||
|
||||
def render_update(
|
||||
self, node: IntermediateNode, config: ContextConfig
|
||||
self, node: ParsedModelNode, config: ContextConfig
|
||||
) -> None:
|
||||
self.manifest._parsing_info.static_analysis_path_count += 1
|
||||
|
||||
# `True` roughly 1/100 times this function is called
|
||||
sample: bool = random.randint(1, 101) == 100
|
||||
|
||||
# run the experimental parser if the flag is on or if we're sampling
|
||||
if flags.USE_EXPERIMENTAL_PARSER or sample:
|
||||
try:
|
||||
experimentally_parsed: Dict[str, List[Any]] = py_extract_from_source(node.raw_sql)
|
||||
|
||||
# second config format
|
||||
config_call_dict: Dict[str, Any] = {}
|
||||
for c in experimentally_parsed['configs']:
|
||||
ContextConfig._add_config_call(config_call_dict, {c[0]: c[1]})
|
||||
|
||||
# format sources TODO change extractor to match this type
|
||||
source_calls: List[List[str]] = []
|
||||
for s in experimentally_parsed['sources']:
|
||||
source_calls.append([s[0], s[1]])
|
||||
experimentally_parsed['sources'] = source_calls
|
||||
|
||||
except ExtractionError as e:
|
||||
experimentally_parsed = e
|
||||
|
||||
# normal dbt run
|
||||
if not flags.USE_EXPERIMENTAL_PARSER:
|
||||
# normal rendering
|
||||
super().render_update(node, config)
|
||||
# if we're sampling, compare for correctness
|
||||
if sample:
|
||||
result: List[str] = []
|
||||
# experimental parser couldn't parse
|
||||
if isinstance(experimentally_parsed, Exception):
|
||||
result += ["01_experimental_parser_cannot_parse"]
|
||||
else:
|
||||
# look for false positive configs
|
||||
for k in config_call_dict.keys():
|
||||
if k not in config._config_call_dict:
|
||||
result += ["02_false_positive_config_value"]
|
||||
break
|
||||
|
||||
# if the --use-experimental-parser flag was set
|
||||
else:
|
||||
# look for missed configs
|
||||
for k in config._config_call_dict.keys():
|
||||
if k not in config_call_dict:
|
||||
result += ["03_missed_config_value"]
|
||||
break
|
||||
|
||||
# run dbt-jinja extractor (powered by tree-sitter)
|
||||
res = extract_from_source(node.raw_sql)
|
||||
# look for false positive sources
|
||||
for s in experimentally_parsed['sources']:
|
||||
if s not in node.sources:
|
||||
result += ["04_false_positive_source_value"]
|
||||
break
|
||||
|
||||
# if it doesn't need python jinja, fit the refs, sources, and configs
|
||||
# look for missed sources
|
||||
for s in node.sources:
|
||||
if s not in experimentally_parsed['sources']:
|
||||
result += ["05_missed_source_value"]
|
||||
break
|
||||
|
||||
# look for false positive refs
|
||||
for r in experimentally_parsed['refs']:
|
||||
if r not in node.refs:
|
||||
result += ["06_false_positive_ref_value"]
|
||||
break
|
||||
|
||||
# look for missed refs
|
||||
for r in node.refs:
|
||||
if r not in experimentally_parsed['refs']:
|
||||
result += ["07_missed_ref_value"]
|
||||
break
|
||||
|
||||
# if there are no errors, return a success value
|
||||
if not result:
|
||||
result = ["00_exact_match"]
|
||||
|
||||
# fire a tracking event. this fires one event for every sample
|
||||
# so that we have data on a per file basis. Not only can we expect
|
||||
# no false positives or misses, we can expect the number model
|
||||
# files parseable by the experimental parser to match our internal
|
||||
# testing.
|
||||
if dbt.tracking.active_user is not None: # None in some tests
|
||||
tracking.track_experimental_parser_sample({
|
||||
"project_id": self.root_project.hashed_name(),
|
||||
"file_id": utils.get_hash(node),
|
||||
"status": result
|
||||
})
|
||||
|
||||
# if the --use-experimental-parser flag was set, and the experimental parser succeeded
|
||||
elif not isinstance(experimentally_parsed, Exception):
|
||||
# since it doesn't need python jinja, fit the refs, sources, and configs
|
||||
# into the node. Down the line the rest of the node will be updated with
|
||||
# this information. (e.g. depends_on etc.)
|
||||
if not res['python_jinja']:
|
||||
config._config_call_dict = config_call_dict
|
||||
|
||||
config_calls = []
|
||||
for c in res['configs']:
|
||||
config_calls.append({c[0]: c[1]})
|
||||
# this uses the updated config to set all the right things in the node.
|
||||
# if there are hooks present, it WILL render jinja. Will need to change
|
||||
# when the experimental parser supports hooks
|
||||
self.update_parsed_node(node, config)
|
||||
|
||||
config._config_calls = config_calls
|
||||
# update the unrendered config with values from the file.
|
||||
# values from yaml files are in there already
|
||||
node.unrendered_config.update(dict(experimentally_parsed['configs']))
|
||||
|
||||
# this uses the updated config to set all the right things in the node
|
||||
# if there are hooks present, it WILL render jinja. Will need to change
|
||||
# when we support hooks
|
||||
self.update_parsed_node(node, config)
|
||||
# set refs and sources on the node object
|
||||
node.refs += experimentally_parsed['refs']
|
||||
node.sources += experimentally_parsed['sources']
|
||||
|
||||
# udpate the unrendered config with values from the file
|
||||
# values from yaml files are in there already
|
||||
node.unrendered_config.update(dict(res['configs']))
|
||||
# configs don't need to be merged into the node
|
||||
# setting them in config._config_call_dict is sufficient
|
||||
|
||||
# set refs, sources, and configs on the node object
|
||||
node.refs = node.refs + res['refs']
|
||||
for sourcev in res['sources']:
|
||||
# TODO change extractor to match type here
|
||||
node.sources.append([sourcev[0], sourcev[1]])
|
||||
for configv in res['configs']:
|
||||
node.config[configv[0]] = configv[1]
|
||||
self.manifest._parsing_info.static_analysis_parsed_path_count += 1
|
||||
|
||||
else:
|
||||
super().render_update(node, config)
|
||||
# the experimental parser tried and failed on this model.
|
||||
# fall back to python jinja rendering.
|
||||
else:
|
||||
super().render_update(node, config)
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from typing import MutableMapping, Dict
|
||||
from typing import MutableMapping, Dict, List
|
||||
from dbt.contracts.graph.manifest import Manifest
|
||||
from dbt.contracts.files import (
|
||||
AnySourceFile, ParseFileType, parse_file_type_to_parser,
|
||||
@@ -44,7 +44,9 @@ class PartialParsing:
|
||||
self.saved_files = self.saved_manifest.files
|
||||
self.project_parser_files = {}
|
||||
self.deleted_manifest = Manifest()
|
||||
self.macro_child_map: Dict[str, List[str]] = {}
|
||||
self.build_file_diff()
|
||||
self.processing_file = None
|
||||
|
||||
def skip_parsing(self):
|
||||
return (
|
||||
@@ -63,6 +65,7 @@ class PartialParsing:
|
||||
deleted_all_files = saved_file_ids.difference(new_file_ids)
|
||||
added = new_file_ids.difference(saved_file_ids)
|
||||
common = saved_file_ids.intersection(new_file_ids)
|
||||
changed_or_deleted_macro_file = False
|
||||
|
||||
# separate out deleted schema files
|
||||
deleted_schema_files = []
|
||||
@@ -71,6 +74,8 @@ class PartialParsing:
|
||||
if self.saved_files[file_id].parse_file_type == ParseFileType.Schema:
|
||||
deleted_schema_files.append(file_id)
|
||||
else:
|
||||
if self.saved_files[file_id].parse_file_type == ParseFileType.Macro:
|
||||
changed_or_deleted_macro_file = True
|
||||
deleted.append(file_id)
|
||||
|
||||
changed = []
|
||||
@@ -87,6 +92,8 @@ class PartialParsing:
|
||||
raise Exception(f"Serialization failure for {file_id}")
|
||||
changed_schema_files.append(file_id)
|
||||
else:
|
||||
if self.saved_files[file_id].parse_file_type == ParseFileType.Macro:
|
||||
changed_or_deleted_macro_file = True
|
||||
changed.append(file_id)
|
||||
file_diff = {
|
||||
"deleted": deleted,
|
||||
@@ -96,6 +103,8 @@ class PartialParsing:
|
||||
"changed_schema_files": changed_schema_files,
|
||||
"unchanged": unchanged,
|
||||
}
|
||||
if changed_or_deleted_macro_file:
|
||||
self.macro_child_map = self.saved_manifest.build_macro_child_map()
|
||||
logger.info(f"Partial parsing enabled: "
|
||||
f"{len(deleted) + len(deleted_schema_files)} files deleted, "
|
||||
f"{len(added)} files added, "
|
||||
@@ -110,16 +119,21 @@ class PartialParsing:
|
||||
# Need to add new files first, because changes in schema files
|
||||
# might refer to them
|
||||
for file_id in self.file_diff['added']:
|
||||
self.processing_file = file_id
|
||||
self.add_to_saved(file_id)
|
||||
# Need to process schema files next, because the dictionaries
|
||||
# need to be in place for handling SQL file changes
|
||||
for file_id in self.file_diff['changed_schema_files']:
|
||||
self.processing_file = file_id
|
||||
self.change_schema_file(file_id)
|
||||
for file_id in self.file_diff['deleted_schema_files']:
|
||||
self.processing_file = file_id
|
||||
self.delete_schema_file(file_id)
|
||||
for file_id in self.file_diff['deleted']:
|
||||
self.processing_file = file_id
|
||||
self.delete_from_saved(file_id)
|
||||
for file_id in self.file_diff['changed']:
|
||||
self.processing_file = file_id
|
||||
self.update_in_saved(file_id)
|
||||
return self.project_parser_files
|
||||
|
||||
@@ -139,6 +153,18 @@ class PartialParsing:
|
||||
file_id not in self.file_diff['deleted']):
|
||||
self.project_parser_files[project_name][parser_name].append(file_id)
|
||||
|
||||
def already_scheduled_for_parsing(self, source_file):
|
||||
file_id = source_file.file_id
|
||||
project_name = source_file.project_name
|
||||
if project_name not in self.project_parser_files:
|
||||
return False
|
||||
parser_name = parse_file_type_to_parser[source_file.parse_file_type]
|
||||
if parser_name not in self.project_parser_files[project_name]:
|
||||
return False
|
||||
if file_id not in self.project_parser_files[project_name][parser_name]:
|
||||
return False
|
||||
return True
|
||||
|
||||
# Add new files, including schema files
|
||||
def add_to_saved(self, file_id):
|
||||
# add file object to saved manifest.files
|
||||
@@ -174,7 +200,7 @@ class PartialParsing:
|
||||
|
||||
# macros
|
||||
if saved_source_file.parse_file_type == ParseFileType.Macro:
|
||||
self.delete_macro_file(saved_source_file)
|
||||
self.delete_macro_file(saved_source_file, follow_references=True)
|
||||
|
||||
# docs
|
||||
if saved_source_file.parse_file_type == ParseFileType.Documentation:
|
||||
@@ -203,6 +229,9 @@ class PartialParsing:
|
||||
# Updated schema files should have been processed already.
|
||||
def update_mssat_in_saved(self, new_source_file, old_source_file):
|
||||
|
||||
if self.already_scheduled_for_parsing(old_source_file):
|
||||
return
|
||||
|
||||
# These files only have one node.
|
||||
unique_id = old_source_file.nodes[0]
|
||||
|
||||
@@ -214,6 +243,10 @@ class PartialParsing:
|
||||
self.remove_node_in_saved(new_source_file, unique_id)
|
||||
|
||||
def remove_node_in_saved(self, source_file, unique_id):
|
||||
# Has already been deleted by another action
|
||||
if unique_id not in self.saved_manifest.nodes:
|
||||
return
|
||||
|
||||
# delete node in saved
|
||||
node = self.saved_manifest.nodes.pop(unique_id)
|
||||
self.deleted_manifest.nodes[unique_id] = node
|
||||
@@ -239,12 +272,16 @@ class PartialParsing:
|
||||
schema_file.node_patches.remove(unique_id)
|
||||
|
||||
def update_macro_in_saved(self, new_source_file, old_source_file):
|
||||
self.handle_macro_file_links(old_source_file)
|
||||
if self.already_scheduled_for_parsing(old_source_file):
|
||||
return
|
||||
self.handle_macro_file_links(old_source_file, follow_references=True)
|
||||
file_id = new_source_file.file_id
|
||||
self.saved_files[file_id] = new_source_file
|
||||
self.add_to_pp_files(new_source_file)
|
||||
|
||||
def update_doc_in_saved(self, new_source_file, old_source_file):
|
||||
if self.already_scheduled_for_parsing(old_source_file):
|
||||
return
|
||||
self.delete_doc_node(old_source_file)
|
||||
self.saved_files[new_source_file.file_id] = new_source_file
|
||||
self.add_to_pp_files(new_source_file)
|
||||
@@ -289,7 +326,7 @@ class PartialParsing:
|
||||
source_element = self.get_schema_element(sources, source.source_name)
|
||||
if source_element:
|
||||
self.delete_schema_source(schema_file, source_element)
|
||||
self.remove_tests(schema_file, source_element['name'])
|
||||
self.remove_tests(schema_file, 'sources', source_element['name'])
|
||||
self.merge_patch(schema_file, 'sources', source_element)
|
||||
elif unique_id in self.saved_manifest.exposures:
|
||||
exposure = self.saved_manifest.exposures[unique_id]
|
||||
@@ -312,41 +349,42 @@ class PartialParsing:
|
||||
self.saved_files[file_id] = self.new_files[file_id]
|
||||
self.add_to_pp_files(self.saved_files[file_id])
|
||||
|
||||
def delete_macro_file(self, source_file):
|
||||
self.handle_macro_file_links(source_file)
|
||||
def delete_macro_file(self, source_file, follow_references=False):
|
||||
self.handle_macro_file_links(source_file, follow_references)
|
||||
file_id = source_file.file_id
|
||||
self.deleted_manifest.files[file_id] = self.saved_files.pop(file_id)
|
||||
|
||||
def handle_macro_file_links(self, source_file):
|
||||
def recursively_gather_macro_references(self, macro_unique_id, referencing_nodes):
|
||||
for unique_id in self.macro_child_map[macro_unique_id]:
|
||||
if unique_id in referencing_nodes:
|
||||
continue
|
||||
referencing_nodes.append(unique_id)
|
||||
if unique_id.startswith('macro.'):
|
||||
self.recursively_gather_macro_references(unique_id, referencing_nodes)
|
||||
|
||||
def handle_macro_file_links(self, source_file, follow_references=False):
|
||||
# remove the macros in the 'macros' dictionary
|
||||
for unique_id in source_file.macros:
|
||||
macros = source_file.macros.copy()
|
||||
for unique_id in macros:
|
||||
if unique_id not in self.saved_manifest.macros:
|
||||
# This happens when a macro has already been removed
|
||||
if unique_id in source_file.macros:
|
||||
source_file.macros.remove(unique_id)
|
||||
continue
|
||||
|
||||
base_macro = self.saved_manifest.macros.pop(unique_id)
|
||||
self.deleted_manifest.macros[unique_id] = base_macro
|
||||
# loop through all macros, finding references to this macro: macro.depends_on.macros
|
||||
for macro in self.saved_manifest.macros.values():
|
||||
for macro_unique_id in macro.depends_on.macros:
|
||||
if (macro_unique_id == unique_id and
|
||||
macro_unique_id in self.saved_manifest.macros):
|
||||
# schedule file for parsing
|
||||
dep_file_id = macro.file_id
|
||||
if dep_file_id in self.saved_files:
|
||||
source_file = self.saved_files[dep_file_id]
|
||||
dep_macro = self.saved_manifest.macros.pop(macro.unique_id)
|
||||
self.deleted_manifest.macros[macro.unqiue_id] = dep_macro
|
||||
self.add_to_pp_files(source_file)
|
||||
break
|
||||
# loop through all nodes, finding references to this macro: node.depends_on.macros
|
||||
for node in self.saved_manifest.nodes.values():
|
||||
for macro_unique_id in node.depends_on.macros:
|
||||
if (macro_unique_id == unique_id and
|
||||
macro_unique_id in self.saved_manifest.macros):
|
||||
# schedule file for parsing
|
||||
dep_file_id = node.file_id
|
||||
if dep_file_id in self.saved_files:
|
||||
source_file = self.saved_files[dep_file_id]
|
||||
self.remove_node_in_saved(source_file, node.unique_id)
|
||||
self.add_to_pp_files(source_file)
|
||||
break
|
||||
|
||||
# Recursively check children of this macro
|
||||
# The macro_child_map might not exist if a macro is removed by
|
||||
# schedule_nodes_for parsing. We only want to follow
|
||||
# references if the macro file itself has been updated or
|
||||
# deleted, not if we're just updating referenced nodes.
|
||||
if self.macro_child_map and follow_references:
|
||||
referencing_nodes = []
|
||||
self.recursively_gather_macro_references(unique_id, referencing_nodes)
|
||||
self.schedule_macro_nodes_for_parsing(referencing_nodes)
|
||||
|
||||
if base_macro.patch_path:
|
||||
file_id = base_macro.patch_path
|
||||
if file_id in self.saved_files:
|
||||
@@ -357,6 +395,55 @@ class PartialParsing:
|
||||
macro_patch = self.get_schema_element(macro_patches, base_macro.name)
|
||||
self.delete_schema_macro_patch(schema_file, macro_patch)
|
||||
self.merge_patch(schema_file, 'macros', macro_patch)
|
||||
# The macro may have already been removed by handling macro children
|
||||
if unique_id in source_file.macros:
|
||||
source_file.macros.remove(unique_id)
|
||||
|
||||
# similar to schedule_nodes_for_parsing but doesn't do sources and exposures
|
||||
# and handles schema tests
|
||||
def schedule_macro_nodes_for_parsing(self, unique_ids):
|
||||
for unique_id in unique_ids:
|
||||
if unique_id in self.saved_manifest.nodes:
|
||||
node = self.saved_manifest.nodes[unique_id]
|
||||
if node.resource_type == NodeType.Test:
|
||||
schema_file_id = node.file_id
|
||||
schema_file = self.saved_manifest.files[schema_file_id]
|
||||
(key, name) = schema_file.get_key_and_name_for_test(node.unique_id)
|
||||
if key and name:
|
||||
patch_list = []
|
||||
if key in schema_file.dict_from_yaml:
|
||||
patch_list = schema_file.dict_from_yaml[key]
|
||||
patch = self.get_schema_element(patch_list, name)
|
||||
if patch:
|
||||
if key in ['models', 'seeds', 'snapshots']:
|
||||
self.delete_schema_mssa_links(schema_file, key, patch)
|
||||
self.merge_patch(schema_file, key, patch)
|
||||
if unique_id in schema_file.node_patches:
|
||||
schema_file.node_patches.remove(unique_id)
|
||||
elif key == 'sources':
|
||||
# re-schedule source
|
||||
if 'overrides' in patch:
|
||||
# This is a source patch; need to re-parse orig source
|
||||
self.remove_source_override_target(patch)
|
||||
self.delete_schema_source(schema_file, patch)
|
||||
self.remove_tests(schema_file, 'sources', patch['name'])
|
||||
self.merge_patch(schema_file, 'sources', patch)
|
||||
else:
|
||||
file_id = node.file_id
|
||||
if file_id in self.saved_files and file_id not in self.file_diff['deleted']:
|
||||
source_file = self.saved_files[file_id]
|
||||
self.remove_mssat_file(source_file)
|
||||
# content of non-schema files is only in new files
|
||||
self.saved_files[file_id] = self.new_files[file_id]
|
||||
self.add_to_pp_files(self.saved_files[file_id])
|
||||
elif unique_id in self.saved_manifest.macros:
|
||||
macro = self.saved_manifest.macros[unique_id]
|
||||
file_id = macro.file_id
|
||||
if file_id in self.saved_files and file_id not in self.file_diff['deleted']:
|
||||
source_file = self.saved_files[file_id]
|
||||
self.delete_macro_file(source_file)
|
||||
self.saved_files[file_id] = self.new_files[file_id]
|
||||
self.add_to_pp_files(self.saved_files[file_id])
|
||||
|
||||
def delete_doc_node(self, source_file):
|
||||
# remove the nodes in the 'docs' dictionary
|
||||
@@ -376,7 +463,13 @@ class PartialParsing:
|
||||
new_schema_file = self.new_files[file_id]
|
||||
saved_yaml_dict = saved_schema_file.dict_from_yaml
|
||||
new_yaml_dict = new_schema_file.dict_from_yaml
|
||||
saved_schema_file.pp_dict = {"version": saved_yaml_dict['version']}
|
||||
if 'version' in new_yaml_dict:
|
||||
# despite the fact that this goes in the saved_schema_file, it
|
||||
# should represent the new yaml dictionary, and should produce
|
||||
# an error if the updated yaml file doesn't have a version
|
||||
saved_schema_file.pp_dict = {"version": new_yaml_dict['version']}
|
||||
else:
|
||||
saved_schema_file.pp_dict = {}
|
||||
self.handle_schema_file_changes(saved_schema_file, saved_yaml_dict, new_yaml_dict)
|
||||
|
||||
# copy from new schema_file to saved_schema_file to preserve references
|
||||
@@ -424,14 +517,14 @@ class PartialParsing:
|
||||
if 'overrides' in source: # This is a source patch; need to re-parse orig source
|
||||
self.remove_source_override_target(source)
|
||||
self.delete_schema_source(schema_file, source)
|
||||
self.remove_tests(schema_file, source['name'])
|
||||
self.remove_tests(schema_file, 'sources', source['name'])
|
||||
self.merge_patch(schema_file, 'sources', source)
|
||||
if source_diff['deleted']:
|
||||
for source in source_diff['deleted']:
|
||||
if 'overrides' in source: # This is a source patch; need to re-parse orig source
|
||||
self.remove_source_override_target(source)
|
||||
self.delete_schema_source(schema_file, source)
|
||||
self.remove_tests(schema_file, source['name'])
|
||||
self.remove_tests(schema_file, 'sources', source['name'])
|
||||
if source_diff['added']:
|
||||
for source in source_diff['added']:
|
||||
if 'overrides' in source: # This is a source patch; need to re-parse orig source
|
||||
@@ -556,49 +649,15 @@ class PartialParsing:
|
||||
# for models, seeds, snapshots (not analyses)
|
||||
if dict_key in ['models', 'seeds', 'snapshots']:
|
||||
# find related tests and remove them
|
||||
self.remove_tests(schema_file, elem['name'])
|
||||
self.remove_tests(schema_file, dict_key, elem['name'])
|
||||
|
||||
def remove_tests(self, schema_file, name):
|
||||
tests = self.get_tests_for(schema_file, name)
|
||||
def remove_tests(self, schema_file, dict_key, name):
|
||||
tests = schema_file.get_tests(dict_key, name)
|
||||
for test_unique_id in tests:
|
||||
node = self.saved_manifest.nodes.pop(test_unique_id)
|
||||
self.deleted_manifest.nodes[test_unique_id] = node
|
||||
schema_file.tests.remove(test_unique_id)
|
||||
|
||||
# Create a pp_test_index in the schema file if it doesn't exist
|
||||
# and look for test names related to this yaml dict element name
|
||||
def get_tests_for(self, schema_file, name):
|
||||
if not schema_file.pp_test_index:
|
||||
pp_test_index = {}
|
||||
for test_unique_id in schema_file.tests:
|
||||
test_node = self.saved_manifest.nodes[test_unique_id]
|
||||
if test_node.sources:
|
||||
for source_ref in test_node.sources:
|
||||
source_name = source_ref[0]
|
||||
if source_name in pp_test_index:
|
||||
pp_test_index[source_name].append(test_unique_id)
|
||||
else:
|
||||
pp_test_index[source_name] = [test_unique_id]
|
||||
elif test_node.depends_on.nodes:
|
||||
tested_node_id = test_node.depends_on.nodes[0]
|
||||
parts = tested_node_id.split('.')
|
||||
elem_name = parts[-1]
|
||||
if elem_name in pp_test_index:
|
||||
pp_test_index[elem_name].append(test_unique_id)
|
||||
else:
|
||||
pp_test_index[elem_name] = [test_unique_id]
|
||||
elif (hasattr(test_node, 'test_metadata') and
|
||||
'model' in test_node.test_metadata.kwargs):
|
||||
(_, elem_name, _) = test_node.test_metadata.kwargs['model'].split("'")
|
||||
if elem_name:
|
||||
if elem_name in pp_test_index:
|
||||
pp_test_index[elem_name].append(test_unique_id)
|
||||
else:
|
||||
pp_test_index[elem_name] = [test_unique_id]
|
||||
schema_file.pp_test_index = pp_test_index
|
||||
if name in schema_file.pp_test_index:
|
||||
return schema_file.pp_test_index[name]
|
||||
return []
|
||||
if test_unique_id in self.saved_manifest.nodes:
|
||||
node = self.saved_manifest.nodes.pop(test_unique_id)
|
||||
self.deleted_manifest.nodes[test_unique_id] = node
|
||||
schema_file.remove_tests(dict_key, name)
|
||||
|
||||
def delete_schema_source(self, schema_file, source_dict):
|
||||
# both patches, tests, and source nodes
|
||||
@@ -619,19 +678,17 @@ class PartialParsing:
|
||||
|
||||
def delete_schema_macro_patch(self, schema_file, macro):
|
||||
# This is just macro patches that need to be reapplied
|
||||
for unique_id in schema_file.macro_patches:
|
||||
parts = unique_id.split('.')
|
||||
macro_name = parts[-1]
|
||||
if macro_name == macro['name']:
|
||||
macro_unique_id = unique_id
|
||||
break
|
||||
macro_unique_id = None
|
||||
if macro['name'] in schema_file.macro_patches:
|
||||
macro_unique_id = schema_file.macro_patches[macro['name']]
|
||||
del schema_file.macro_patches[macro['name']]
|
||||
if macro_unique_id and macro_unique_id in self.saved_manifest.macros:
|
||||
macro = self.saved_manifest.macros.pop(macro_unique_id)
|
||||
self.deleted_manifest.macros[macro_unique_id] = macro
|
||||
macro_file_id = macro.file_id
|
||||
self.add_to_pp_files(self.saved_files[macro_file_id])
|
||||
if macro_unique_id in schema_file.macro_patches:
|
||||
schema_file.macro_patches.remove(macro_unique_id)
|
||||
if macro_file_id in self.new_files:
|
||||
self.saved_files[macro_file_id] = self.new_files[macro_file_id]
|
||||
self.add_to_pp_files(self.saved_files[macro_file_id])
|
||||
|
||||
# exposures are created only from schema files, so just delete
|
||||
# the exposure.
|
||||
@@ -675,6 +732,6 @@ class PartialParsing:
|
||||
(orig_file, orig_source) = self.get_source_override_file_and_dict(source_dict)
|
||||
if orig_source:
|
||||
self.delete_schema_source(orig_file, orig_source)
|
||||
self.remove_tests(orig_file, orig_source['name'])
|
||||
self.remove_tests(orig_file, 'sources', orig_source['name'])
|
||||
self.merge_patch(orig_file, 'sources', orig_source)
|
||||
self.add_to_pp_files(orig_file)
|
||||
|
||||
@@ -3,25 +3,55 @@ from dbt.contracts.files import (
|
||||
FilePath, ParseFileType, SourceFile, FileHash, AnySourceFile, SchemaSourceFile
|
||||
)
|
||||
|
||||
from dbt.parser.schemas import yaml_from_file
|
||||
from dbt.parser.schemas import yaml_from_file, schema_file_keys, check_format_version
|
||||
from dbt.exceptions import CompilationException
|
||||
from dbt.parser.search import FilesystemSearcher
|
||||
from typing import Optional
|
||||
|
||||
|
||||
# This loads the files contents and creates the SourceFile object
|
||||
def load_source_file(
|
||||
path: FilePath, parse_file_type: ParseFileType,
|
||||
project_name: str) -> AnySourceFile:
|
||||
project_name: str) -> Optional[AnySourceFile]:
|
||||
file_contents = load_file_contents(path.absolute_path, strip=False)
|
||||
checksum = FileHash.from_contents(file_contents)
|
||||
sf_cls = SchemaSourceFile if parse_file_type == ParseFileType.Schema else SourceFile
|
||||
source_file = sf_cls(path=path, checksum=checksum,
|
||||
parse_file_type=parse_file_type, project_name=project_name)
|
||||
source_file.contents = file_contents.strip()
|
||||
if parse_file_type == ParseFileType.Schema:
|
||||
source_file.dfy = yaml_from_file(source_file)
|
||||
if parse_file_type == ParseFileType.Schema and source_file.contents:
|
||||
dfy = yaml_from_file(source_file)
|
||||
if dfy:
|
||||
validate_yaml(source_file.path.original_file_path, dfy)
|
||||
source_file.dfy = dfy
|
||||
else:
|
||||
source_file = None
|
||||
return source_file
|
||||
|
||||
|
||||
# Do some minimal validation of the yaml in a schema file.
|
||||
# Check version, that key values are lists and that each element in
|
||||
# the lists has a 'name' key
|
||||
def validate_yaml(file_path, dct):
|
||||
check_format_version(file_path, dct)
|
||||
for key in schema_file_keys:
|
||||
if key in dct:
|
||||
if not isinstance(dct[key], list):
|
||||
msg = (f"The schema file at {file_path} is "
|
||||
f"invalid because the value of '{key}' is not a list")
|
||||
raise CompilationException(msg)
|
||||
for element in dct[key]:
|
||||
if not isinstance(element, dict):
|
||||
msg = (f"The schema file at {file_path} is "
|
||||
f"invalid because a list element for '{key}' is not a dictionary")
|
||||
raise CompilationException(msg)
|
||||
if 'name' not in element:
|
||||
msg = (f"The schema file at {file_path} is "
|
||||
f"invalid because a list element for '{key}' does not have a "
|
||||
"name attribute.")
|
||||
raise CompilationException(msg)
|
||||
|
||||
|
||||
# Special processing for big seed files
|
||||
def load_seed_source_file(match: FilePath, project_name) -> SourceFile:
|
||||
if match.seed_too_large():
|
||||
@@ -50,8 +80,10 @@ def get_source_files(project, paths, extension, parse_file_type):
|
||||
if parse_file_type == ParseFileType.Seed:
|
||||
fb_list.append(load_seed_source_file(fp, project.project_name))
|
||||
else:
|
||||
fb_list.append(load_source_file(
|
||||
fp, parse_file_type, project.project_name))
|
||||
file = load_source_file(fp, parse_file_type, project.project_name)
|
||||
# only append the list if it has contents. added to fix #3568
|
||||
if file:
|
||||
fb_list.append(file)
|
||||
return fb_list
|
||||
|
||||
|
||||
|
||||
@@ -355,8 +355,10 @@ class TestBuilder(Generic[Testable]):
|
||||
|
||||
def construct_config(self) -> str:
|
||||
configs = ",".join([
|
||||
f"{key}=" + (f"'{value}'" if isinstance(value, str)
|
||||
else str(value))
|
||||
f"{key}=" + (
|
||||
("\"" + value.replace('\"', '\\\"') + "\"") if isinstance(value, str)
|
||||
else str(value)
|
||||
)
|
||||
for key, value
|
||||
in self.modifiers.items()
|
||||
])
|
||||
|
||||
@@ -70,6 +70,11 @@ UnparsedSchemaYaml = Union[
|
||||
|
||||
TestDef = Union[str, Dict[str, Any]]
|
||||
|
||||
schema_file_keys = (
|
||||
'models', 'seeds', 'snapshots', 'sources',
|
||||
'macros', 'analyses', 'exposures',
|
||||
)
|
||||
|
||||
|
||||
def error_context(
|
||||
path: str,
|
||||
@@ -93,10 +98,10 @@ def error_context(
|
||||
|
||||
def yaml_from_file(
|
||||
source_file: SchemaSourceFile
|
||||
) -> Optional[Dict[str, Any]]:
|
||||
) -> Dict[str, Any]:
|
||||
"""If loading the yaml fails, raise an exception.
|
||||
"""
|
||||
path: str = source_file.path.relative_path
|
||||
path = source_file.path.relative_path
|
||||
try:
|
||||
return load_yaml_text(source_file.contents)
|
||||
except ValidationException as e:
|
||||
@@ -105,7 +110,6 @@ def yaml_from_file(
|
||||
'Error reading {}: {} - {}'
|
||||
.format(source_file.project_name, path, reason)
|
||||
)
|
||||
return None
|
||||
|
||||
|
||||
class ParserRef:
|
||||
@@ -167,15 +171,15 @@ class SchemaParser(SimpleParser[SchemaTestBlock, ParsedSchemaTestNode]):
|
||||
self.project.config_version == 2
|
||||
)
|
||||
if all_v_2:
|
||||
ctx = generate_schema_yml(
|
||||
self.render_ctx = generate_schema_yml(
|
||||
self.root_project, self.project.project_name
|
||||
)
|
||||
else:
|
||||
ctx = generate_target_context(
|
||||
self.render_ctx = generate_target_context(
|
||||
self.root_project, self.root_project.cli_vars
|
||||
)
|
||||
|
||||
self.raw_renderer = SchemaYamlRenderer(ctx)
|
||||
self.raw_renderer = SchemaYamlRenderer(self.render_ctx)
|
||||
|
||||
internal_package_names = get_adapter_package_names(
|
||||
self.root_project.credentials.type
|
||||
@@ -200,25 +204,6 @@ class SchemaParser(SimpleParser[SchemaTestBlock, ParsedSchemaTestNode]):
|
||||
ParsedSchemaTestNode.validate(dct)
|
||||
return ParsedSchemaTestNode.from_dict(dct)
|
||||
|
||||
def _check_format_version(
|
||||
self, yaml: YamlBlock
|
||||
) -> None:
|
||||
path = yaml.path.relative_path
|
||||
if 'version' not in yaml.data:
|
||||
raise_invalid_schema_yml_version(path, 'no version is specified')
|
||||
|
||||
version = yaml.data['version']
|
||||
# if it's not an integer, the version is malformed, or not
|
||||
# set. Either way, only 'version: 2' is supported.
|
||||
if not isinstance(version, int):
|
||||
raise_invalid_schema_yml_version(
|
||||
path, 'the version is not an integer'
|
||||
)
|
||||
if version != 2:
|
||||
raise_invalid_schema_yml_version(
|
||||
path, 'version {} is not supported'.format(version)
|
||||
)
|
||||
|
||||
def parse_column_tests(
|
||||
self, block: TestBlock, column: UnparsedColumn
|
||||
) -> None:
|
||||
@@ -302,17 +287,13 @@ class SchemaParser(SimpleParser[SchemaTestBlock, ParsedSchemaTestNode]):
|
||||
tags: List[str],
|
||||
column_name: Optional[str],
|
||||
) -> ParsedSchemaTestNode:
|
||||
|
||||
render_ctx = generate_target_context(
|
||||
self.root_project, self.root_project.cli_vars
|
||||
)
|
||||
try:
|
||||
builder = TestBuilder(
|
||||
test=test,
|
||||
target=target,
|
||||
column_name=column_name,
|
||||
package_name=target.package_name,
|
||||
render_ctx=render_ctx,
|
||||
render_ctx=self.render_ctx,
|
||||
)
|
||||
except CompilationException as exc:
|
||||
context = _trimmed(str(target))
|
||||
@@ -403,6 +384,9 @@ class SchemaParser(SimpleParser[SchemaTestBlock, ParsedSchemaTestNode]):
|
||||
if builder.fail_calc is not None:
|
||||
node.unrendered_config['fail_calc'] = builder.fail_calc
|
||||
node.config['fail_calc'] = builder.fail_calc
|
||||
if builder.store_failures is not None:
|
||||
node.unrendered_config['store_failures'] = builder.store_failures
|
||||
node.config['store_failures'] = builder.store_failures
|
||||
# source node tests are processed at patch_source time
|
||||
if isinstance(builder.target, UnpatchedSourceDefinition):
|
||||
sources = [builder.target.fqn[-2], builder.target.fqn[-1]]
|
||||
@@ -439,9 +423,16 @@ class SchemaParser(SimpleParser[SchemaTestBlock, ParsedSchemaTestNode]):
|
||||
tags=block.tags,
|
||||
column_name=block.column_name,
|
||||
)
|
||||
self.add_result_node(block, node)
|
||||
self.add_test_node(block, node)
|
||||
return node
|
||||
|
||||
def add_test_node(self, block: SchemaTestBlock, node: ParsedSchemaTestNode):
|
||||
test_from = {"key": block.target.yaml_key, "name": block.target.name}
|
||||
if node.config.enabled:
|
||||
self.manifest.add_node(block.file, node, test_from)
|
||||
else:
|
||||
self.manifest.add_disabled(block.file, node, test_from)
|
||||
|
||||
def render_with_context(
|
||||
self, node: ParsedSchemaTestNode, config: ContextConfig,
|
||||
) -> None:
|
||||
@@ -514,9 +505,6 @@ class SchemaParser(SimpleParser[SchemaTestBlock, ParsedSchemaTestNode]):
|
||||
# contains the FileBlock and the data (dictionary)
|
||||
yaml_block = YamlBlock.from_file_block(block, dct)
|
||||
|
||||
# checks version
|
||||
self._check_format_version(yaml_block)
|
||||
|
||||
parser: YamlDocsReader
|
||||
|
||||
# There are 7 kinds of parsers:
|
||||
@@ -565,6 +553,25 @@ class SchemaParser(SimpleParser[SchemaTestBlock, ParsedSchemaTestNode]):
|
||||
self.manifest.add_exposure(yaml_block.file, node)
|
||||
|
||||
|
||||
def check_format_version(
|
||||
file_path, yaml_dct
|
||||
) -> None:
|
||||
if 'version' not in yaml_dct:
|
||||
raise_invalid_schema_yml_version(file_path, 'no version is specified')
|
||||
|
||||
version = yaml_dct['version']
|
||||
# if it's not an integer, the version is malformed, or not
|
||||
# set. Either way, only 'version: 2' is supported.
|
||||
if not isinstance(version, int):
|
||||
raise_invalid_schema_yml_version(
|
||||
file_path, 'the version is not an integer'
|
||||
)
|
||||
if version != 2:
|
||||
raise_invalid_schema_yml_version(
|
||||
file_path, 'version {} is not supported'.format(version)
|
||||
)
|
||||
|
||||
|
||||
Parsed = TypeVar(
|
||||
'Parsed',
|
||||
UnpatchedSourceDefinition, ParsedNodePatch, ParsedMacroPatch
|
||||
|
||||
@@ -77,7 +77,8 @@ class SourcePatcher:
|
||||
self.manifest.add_disabled_nofile(test)
|
||||
# save the test unique_id in the schema_file, so we can
|
||||
# process in partial parsing
|
||||
schema_file.tests.append(test.unique_id)
|
||||
test_from = {"key": 'sources', "name": patched.source.name}
|
||||
schema_file.add_test(test.unique_id, test_from)
|
||||
|
||||
# Convert UnpatchedSourceDefinition to a ParsedSourceDefinition
|
||||
parsed = self.parse_source(patched)
|
||||
@@ -285,7 +286,7 @@ class SourcePatcher:
|
||||
)
|
||||
|
||||
return generator.calculate_node_config(
|
||||
config_calls=[],
|
||||
config_call_dict={},
|
||||
fqn=fqn,
|
||||
resource_type=NodeType.Source,
|
||||
project_name=project_name,
|
||||
|
||||
@@ -1,5 +1,8 @@
|
||||
from dataclasses import dataclass
|
||||
import re
|
||||
from typing import List
|
||||
|
||||
from packaging import version as packaging_version
|
||||
|
||||
from dbt.exceptions import VersionsNotCompatibleException
|
||||
import dbt.utils
|
||||
@@ -125,12 +128,26 @@ class VersionSpecifier(VersionSpecification):
|
||||
if self.is_unbounded or other.is_unbounded:
|
||||
return 0
|
||||
|
||||
for key in ['major', 'minor', 'patch']:
|
||||
comparison = int(getattr(self, key)) - int(getattr(other, key))
|
||||
|
||||
if comparison > 0:
|
||||
for key in ['major', 'minor', 'patch', 'prerelease']:
|
||||
(a, b) = (getattr(self, key), getattr(other, key))
|
||||
if key == 'prerelease':
|
||||
if a is None and b is None:
|
||||
continue
|
||||
if a is None:
|
||||
if self.matcher == Matchers.LESS_THAN:
|
||||
# If 'a' is not a pre-release but 'b' is, and b must be
|
||||
# less than a, return -1 to prevent installations of
|
||||
# pre-releases with greater base version than a
|
||||
# maximum specified non-pre-release version.
|
||||
return -1
|
||||
# Otherwise, stable releases are considered greater than
|
||||
# pre-release
|
||||
return 1
|
||||
if b is None:
|
||||
return -1
|
||||
if packaging_version.parse(a) > packaging_version.parse(b):
|
||||
return 1
|
||||
elif comparison < 0:
|
||||
elif packaging_version.parse(a) < packaging_version.parse(b):
|
||||
return -1
|
||||
|
||||
equal = ((self.matcher == Matchers.GREATER_THAN_OR_EQUAL and
|
||||
@@ -408,10 +425,23 @@ def resolve_to_specific_version(requested_range, available_versions):
|
||||
version = VersionSpecifier.from_version_string(version_string)
|
||||
|
||||
if(versions_compatible(version,
|
||||
requested_range.start,
|
||||
requested_range.end) and
|
||||
requested_range.start, requested_range.end) and
|
||||
(max_version is None or max_version.compare(version) < 0)):
|
||||
max_version = version
|
||||
max_version_string = version_string
|
||||
|
||||
return max_version_string
|
||||
|
||||
|
||||
def filter_installable(
|
||||
versions: List[str],
|
||||
install_prerelease: bool
|
||||
) -> List[str]:
|
||||
if install_prerelease:
|
||||
return versions
|
||||
installable = []
|
||||
for version_string in versions:
|
||||
version = VersionSpecifier.from_version_string(version_string)
|
||||
if not version.prerelease:
|
||||
installable.append(version_string)
|
||||
return installable
|
||||
|
||||
@@ -28,9 +28,10 @@ INVOCATION_ENV_SPEC = 'iglu:com.dbt/invocation_env/jsonschema/1-0-0'
|
||||
PACKAGE_INSTALL_SPEC = 'iglu:com.dbt/package_install/jsonschema/1-0-0'
|
||||
RPC_REQUEST_SPEC = 'iglu:com.dbt/rpc_request/jsonschema/1-0-1'
|
||||
DEPRECATION_WARN_SPEC = 'iglu:com.dbt/deprecation_warn/jsonschema/1-0-0'
|
||||
LOAD_ALL_TIMING_SPEC = 'iglu:com.dbt/load_all_timing/jsonschema/1-0-2'
|
||||
LOAD_ALL_TIMING_SPEC = 'iglu:com.dbt/load_all_timing/jsonschema/1-0-3'
|
||||
RESOURCE_COUNTS = 'iglu:com.dbt/resource_counts/jsonschema/1-0-0'
|
||||
|
||||
EXPERIMENTAL_PARSER = 'iglu:com.dbt/experimental_parser/jsonschema/1-0-0'
|
||||
PARTIAL_PARSER = 'iglu:com.dbt/partial_parser/jsonschema/1-0-1'
|
||||
DBT_INVOCATION_ENV = 'DBT_INVOCATION_ENV'
|
||||
|
||||
|
||||
@@ -423,9 +424,42 @@ def track_invalid_invocation(
|
||||
)
|
||||
|
||||
|
||||
def track_experimental_parser_sample(options):
|
||||
context = [SelfDescribingJson(EXPERIMENTAL_PARSER, options)]
|
||||
assert active_user is not None, \
|
||||
'Cannot track experimental parser info when active user is None'
|
||||
|
||||
track(
|
||||
active_user,
|
||||
category='dbt',
|
||||
action='experimental_parser',
|
||||
label=active_user.invocation_id,
|
||||
context=context
|
||||
)
|
||||
|
||||
|
||||
def track_partial_parser(options):
|
||||
context = [SelfDescribingJson(PARTIAL_PARSER, options)]
|
||||
assert active_user is not None, \
|
||||
'Cannot track partial parser info when active user is None'
|
||||
|
||||
track(
|
||||
active_user,
|
||||
category='dbt',
|
||||
action='partial_parser',
|
||||
label=active_user.invocation_id,
|
||||
context=context
|
||||
)
|
||||
|
||||
|
||||
def flush():
|
||||
logger.debug("Flushing usage events")
|
||||
tracker.flush()
|
||||
try:
|
||||
tracker.flush()
|
||||
except Exception:
|
||||
logger.debug(
|
||||
"An error was encountered while trying to flush usage events"
|
||||
)
|
||||
|
||||
|
||||
def disable_tracking():
|
||||
|
||||
@@ -1,38 +0,0 @@
|
||||
# tree_sitter_jinja Module
|
||||
|
||||
This module contains a tool that processes the most common jinja value templates in dbt model files. The tool uses `tree-sitter-jinja2` and the python bindings for tree-sitter as dependencies.
|
||||
|
||||
# Strategy
|
||||
|
||||
The current strategy is for this processor to be 100% certain when it can accurately extract values from a given model file. Anything less than 100% certainty returns an exception so that the model can be rendered with python Jinja instead.
|
||||
|
||||
There are two cases we want to avoid because they would risk correctness to user's projects:
|
||||
1. Confidently extracting values that would not be extracted by python jinja (false positives)
|
||||
2. Confidently extracting a set of values that do not include values that python jinja would have extracted. (misses)
|
||||
|
||||
If we instead error when we could have confidently extracted values, there is no correctness risk to the user. Only an opportunity to expand the rules to encompass this class of cases as well.
|
||||
|
||||
Even though dbt's usage of jinja is not typed, the type checker statically determines whether or not the current implementation can confidently extract values without relying on python jinja rendering, which is when these errors would otherwise surface. This type checker will become more permissive over time as this tool expands to include more dbt and jinja features.
|
||||
|
||||
# Architecture
|
||||
|
||||
This architecture is optimized for value extraction and for future flexibility. This architecture is expected to change, and is coded in fp-style stages to make those changes easier for the future.
|
||||
|
||||
This processor is composed of several stages:
|
||||
1. parser
|
||||
2. type checker
|
||||
3. extractor
|
||||
|
||||
The parser generated by tree-sitter in the package `tree-sitter-jinja2`. The python hooks are used to traverse the concrete syntax tree that tree-sitter makes in order to create a typed abstract syntax tree in the type checking stage (in Python, we have chosen to represent this with a nested tuple of strings). The errors in the type checking stage are not raised to the user, and are instead used by developers to debug tests.
|
||||
|
||||
The parser is solely responsible for turning text into recognized values, while the type checker does arity checking, and enforces argument list types (e.g. nested function calls like `{{ config(my_ref=ref('table')) }}` will parse but not type check even though it is valid dbt syntax. The tool at this time doesn't have an agreed serialization to communicate refs as config values, but could in the future.)
|
||||
|
||||
The extractor uses the typed abstract syntax tree to easily identify all the refs, sources, and configs present and extract them to a dictionary.
|
||||
|
||||
## Tests
|
||||
|
||||
- Tests are in `test/unit/test_tree_sitter_jinja.py` and run with dbt unit tests
|
||||
|
||||
## Future
|
||||
|
||||
- This module will eventually be rewritten in Rust for the added type safety
|
||||
@@ -1,292 +0,0 @@
|
||||
from dataclasses import dataclass
|
||||
from functools import reduce
|
||||
from itertools import dropwhile
|
||||
from tree_sitter import Parser # type: ignore
|
||||
from tree_sitter_jinja2 import JINJA2_LANGUAGE # type: ignore
|
||||
|
||||
|
||||
# global values
|
||||
parser = Parser()
|
||||
parser.set_language(JINJA2_LANGUAGE)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ParseFailure(Exception):
|
||||
msg: str
|
||||
|
||||
|
||||
@dataclass
|
||||
class TypeCheckFailure(Exception):
|
||||
msg: str
|
||||
|
||||
|
||||
def named_children(node):
|
||||
return list(filter(lambda x: x.is_named, node.children))
|
||||
|
||||
|
||||
def text_from_node(source_bytes, node):
|
||||
return source_bytes[node.start_byte:node.end_byte].decode('utf8')
|
||||
|
||||
|
||||
def strip_quotes(text):
|
||||
if text:
|
||||
return text[1:-1]
|
||||
|
||||
|
||||
# flatten([[1,2],[3,4]]) = [1,2,3,4]
|
||||
def flatten(list_of_lists):
|
||||
return [item for sublist in list_of_lists for item in sublist]
|
||||
|
||||
|
||||
def has_kwarg_child_named(name_list, node):
|
||||
kwargs = node[1:]
|
||||
for kwarg in kwargs:
|
||||
if kwarg[1] in name_list:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
# if all positional args come before kwargs return True.
|
||||
# otherwise return false.
|
||||
def kwargs_last(args):
|
||||
def not_kwarg(node):
|
||||
return node.type != 'kwarg'
|
||||
|
||||
no_leading_positional_args = dropwhile(not_kwarg, args)
|
||||
dangling_positional_args = filter(not_kwarg, no_leading_positional_args)
|
||||
return len(list(dangling_positional_args)) == 0
|
||||
|
||||
|
||||
def error_count(node):
|
||||
if node.has_error:
|
||||
return 1
|
||||
|
||||
if node.children:
|
||||
return reduce(lambda a, b: a + b, map(lambda x: error_count(x), node.children))
|
||||
else:
|
||||
return 0
|
||||
|
||||
|
||||
# meat of the type checker
|
||||
# throws a TypeCheckError or returns a typed ast in the form of a nested tuple
|
||||
def _to_typed(source_bytes, node):
|
||||
if node.type == 'lit_string':
|
||||
return strip_quotes(text_from_node(source_bytes, node))
|
||||
|
||||
if node.type == 'bool':
|
||||
text = text_from_node(source_bytes, node)
|
||||
if text == 'True':
|
||||
return True
|
||||
if text == 'False':
|
||||
return False
|
||||
|
||||
if node.type == 'jinja_expression':
|
||||
raise TypeCheckFailure("jinja expressions are unsupported: {% syntax like this %}")
|
||||
|
||||
elif node.type == 'list':
|
||||
elems = named_children(node)
|
||||
for elem in elems:
|
||||
if elem.type == 'fn_call':
|
||||
raise TypeCheckFailure("list elements cannot be function calls")
|
||||
return ('list', *(_to_typed(source_bytes, elem) for elem in elems))
|
||||
|
||||
elif node.type == 'kwarg':
|
||||
value_node = node.child_by_field_name('value')
|
||||
if value_node.type == 'fn_call':
|
||||
raise TypeCheckFailure("keyword arguments can not be function calls")
|
||||
key_node = node.child_by_field_name('key')
|
||||
key_text = text_from_node(source_bytes, key_node)
|
||||
return ('kwarg', key_text, _to_typed(source_bytes, value_node))
|
||||
|
||||
elif node.type == 'dict':
|
||||
# locally mutate list of kv pairs
|
||||
pairs = []
|
||||
for pair in named_children(node):
|
||||
key = pair.child_by_field_name('key')
|
||||
value = pair.child_by_field_name('value')
|
||||
if key.type != 'lit_string':
|
||||
raise TypeCheckFailure("all dict keys must be string literals")
|
||||
if value.type == 'fn_call':
|
||||
raise TypeCheckFailure("dict values cannot be function calls")
|
||||
pairs.append((key, value))
|
||||
return (
|
||||
'dict',
|
||||
*(
|
||||
(
|
||||
strip_quotes(text_from_node(source_bytes, pair[0])),
|
||||
_to_typed(source_bytes, pair[1])
|
||||
) for pair in pairs
|
||||
))
|
||||
|
||||
elif node.type == 'source_file':
|
||||
children = named_children(node)
|
||||
return ('root', *(_to_typed(source_bytes, child) for child in children))
|
||||
|
||||
elif node.type == 'fn_call':
|
||||
name = text_from_node(source_bytes, node.child_by_field_name('fn_name'))
|
||||
arg_list = node.child_by_field_name('argument_list')
|
||||
arg_count = arg_list.named_child_count
|
||||
args = named_children(arg_list)
|
||||
if not kwargs_last(args):
|
||||
raise TypeCheckFailure("keyword arguments must all be at the end")
|
||||
|
||||
if name == 'ref':
|
||||
if arg_count != 1 and arg_count != 2:
|
||||
raise TypeCheckFailure(f"expected ref to have 1 or 2 arguments. found {arg_count}")
|
||||
for arg in args:
|
||||
if arg.type != 'lit_string':
|
||||
raise TypeCheckFailure(f"all ref arguments must be strings. found {arg.type}")
|
||||
return ('ref', *(_to_typed(source_bytes, arg) for arg in args))
|
||||
|
||||
elif name == 'source':
|
||||
if arg_count != 2:
|
||||
raise TypeCheckFailure(f"expected source to 2 arguments. found {arg_count}")
|
||||
for arg in args:
|
||||
if arg.type != 'kwarg' and arg.type != 'lit_string':
|
||||
raise TypeCheckFailure(f"unexpected argument type in source. Found {arg.type}")
|
||||
# note: keyword vs positional argument order is checked above in fn_call checks
|
||||
if args[0].type == 'kwarg':
|
||||
key_name = text_from_node(source_bytes, args[0].child_by_field_name('key'))
|
||||
if key_name != 'source_name':
|
||||
raise TypeCheckFailure(
|
||||
"first keyword argument in source must be source_name found"
|
||||
f"{args[0].child_by_field_name('key')}"
|
||||
)
|
||||
if args[1].type == 'kwarg':
|
||||
key_name = text_from_node(source_bytes, args[1].child_by_field_name('key'))
|
||||
if key_name != 'table_name':
|
||||
raise TypeCheckFailure(
|
||||
"second keyword argument in source must be table_name found"
|
||||
f"{args[1].child_by_field_name('key')}"
|
||||
)
|
||||
|
||||
# restructure source calls to look like they
|
||||
# were all called positionally for uniformity
|
||||
source_name = args[0]
|
||||
table_name = args[1]
|
||||
if args[0].type == 'kwarg':
|
||||
source_name = args[0].child_by_field_name('value')
|
||||
if args[1].type == 'kwarg':
|
||||
table_name = args[1].child_by_field_name('value')
|
||||
|
||||
return (
|
||||
'source',
|
||||
_to_typed(source_bytes, source_name),
|
||||
_to_typed(source_bytes, table_name)
|
||||
)
|
||||
|
||||
elif name == 'config':
|
||||
if arg_count < 1:
|
||||
raise TypeCheckFailure(
|
||||
f"expected config to have at least one argument. found {arg_count}"
|
||||
)
|
||||
excluded_config_args = ['post-hook', 'post_hook', 'pre-hook', 'pre_hook']
|
||||
for arg in args:
|
||||
if arg.type != 'kwarg':
|
||||
raise TypeCheckFailure(
|
||||
f"unexpected non keyword argument in config. found {arg.type}"
|
||||
)
|
||||
key_name = text_from_node(source_bytes, arg.child_by_field_name('key'))
|
||||
if key_name in excluded_config_args:
|
||||
raise TypeCheckFailure(f"excluded config kwarg found: {key_name}")
|
||||
return ('config', *(_to_typed(source_bytes, arg) for arg in args))
|
||||
|
||||
else:
|
||||
raise TypeCheckFailure(f"unexpected function call to {name}")
|
||||
|
||||
else:
|
||||
raise TypeCheckFailure(f"unexpected node type: {node.type}")
|
||||
|
||||
|
||||
# Entry point for type checking. Either returns a single TypeCheckFailure or
|
||||
# a typed-ast in the form of nested tuples.
|
||||
# Depends on the source because we check for built-ins. It's a bit of a hack,
|
||||
# but it works well at this scale.
|
||||
def type_check(source_bytes, node):
|
||||
try:
|
||||
return _to_typed(source_bytes, node)
|
||||
# if an error was thrown, return it instead.
|
||||
except TypeCheckFailure as e:
|
||||
return e
|
||||
|
||||
|
||||
# operates on a typed ast
|
||||
def _extract(node, data):
|
||||
# reached a leaf
|
||||
if not isinstance(node, tuple):
|
||||
return node
|
||||
|
||||
if node[0] == 'list':
|
||||
return list(_extract(child, data) for child in node[1:])
|
||||
|
||||
if node[0] == 'dict':
|
||||
return {pair[0]: _extract(pair[1], data) for pair in node[1:]}
|
||||
|
||||
if node[0] == 'ref':
|
||||
# no package name
|
||||
if len(node) == 2:
|
||||
ref = [node[1]]
|
||||
else:
|
||||
ref = [node[1], node[2]]
|
||||
data['refs'].append(ref)
|
||||
|
||||
# configs are the only ones that can recurse like this
|
||||
# e.g. {{ config(key=[{'nested':'values'}]) }}
|
||||
if node[0] == 'config':
|
||||
for kwarg in node[1:]:
|
||||
data['configs'].append((kwarg[1], _extract(kwarg[2], data)))
|
||||
|
||||
if node[0] == 'source':
|
||||
for arg in node[1:]:
|
||||
data['sources'].add((node[1], node[2]))
|
||||
|
||||
# generator statement evaluated as tuple for effects
|
||||
tuple(_extract(child, data) for child in node[1:])
|
||||
|
||||
|
||||
def extract(node):
|
||||
data = {
|
||||
'refs': [],
|
||||
'sources': set(),
|
||||
'configs': [],
|
||||
'python_jinja': False
|
||||
}
|
||||
_extract(node, data)
|
||||
return data
|
||||
|
||||
|
||||
# returns a fully processed, typed ast or an exception
|
||||
def process_source(parser, string):
|
||||
source_bytes = bytes(string, "utf8")
|
||||
tree = parser.parse(source_bytes)
|
||||
count = error_count(tree.root_node)
|
||||
|
||||
# check for parser errors
|
||||
if count > 0:
|
||||
return ParseFailure("tree-sitter found errors")
|
||||
|
||||
# if there are no parsing errors check for type errors
|
||||
checked_ast_or_error = type_check(source_bytes, tree.root_node)
|
||||
if isinstance(checked_ast_or_error, TypeCheckFailure):
|
||||
err = checked_ast_or_error
|
||||
return err
|
||||
|
||||
# if there are no parsing errors and no type errors, return the typed ast
|
||||
typed_root = checked_ast_or_error
|
||||
return typed_root
|
||||
|
||||
|
||||
# entry point function
|
||||
def extract_from_source(string):
|
||||
res = process_source(parser, string)
|
||||
|
||||
if isinstance(res, Exception):
|
||||
return {
|
||||
'refs': [],
|
||||
'sources': set(),
|
||||
'configs': [],
|
||||
'python_jinja': True
|
||||
}
|
||||
|
||||
typed_root = res
|
||||
return extract(typed_root)
|
||||
@@ -96,5 +96,5 @@ def _get_dbt_plugins_info():
|
||||
yield plugin_name, mod.version
|
||||
|
||||
|
||||
__version__ = '0.20.0rc1'
|
||||
__version__ = '0.20.2rc2'
|
||||
installed = get_installed_version()
|
||||
|
||||
@@ -24,7 +24,7 @@ def read(fname):
|
||||
|
||||
|
||||
package_name = "dbt-core"
|
||||
package_version = "0.20.0rc1"
|
||||
package_version = "0.20.2rc2"
|
||||
description = """dbt (data build tool) is a command line tool that helps \
|
||||
analysts and engineers transform data in their warehouse more effectively"""
|
||||
|
||||
@@ -73,10 +73,9 @@ setup(
|
||||
'networkx>=2.3,<3',
|
||||
'packaging~=20.9',
|
||||
'sqlparse>=0.2.3,<0.4',
|
||||
'tree-sitter==0.19.0',
|
||||
'tree-sitter-jinja2==0.1.0a1',
|
||||
'typing-extensions>=3.7.4,<3.8',
|
||||
'werkzeug>=0.15,<2.0',
|
||||
'dbt-extractor==0.4.0',
|
||||
'typing-extensions>=3.7.4,<3.11',
|
||||
'werkzeug>=0.15,<3.0',
|
||||
# the following are all to match snowflake-connector-python
|
||||
'requests<3.0.0',
|
||||
'idna>=2.5,<3',
|
||||
|
||||
@@ -8,6 +8,7 @@ pip-tools
|
||||
pytest
|
||||
pytest-dotenv
|
||||
pytest-logbook
|
||||
pytest-csv
|
||||
pytest-xdist
|
||||
pytz
|
||||
tox>=3.13
|
||||
|
||||
@@ -19,7 +19,7 @@ services:
|
||||
GROUP_ID: ${GROUP_ID:-}
|
||||
command: "/root/.virtualenvs/dbt/bin/pytest"
|
||||
environment:
|
||||
DOCKER_TEST_DATABASE_HOST: "database"
|
||||
POSTGRES_TEST_HOST: "database"
|
||||
volumes:
|
||||
- .:/usr/app
|
||||
working_dir: /usr/app
|
||||
|
||||
75
docker/requirements/requirements.0.20.0.txt
Normal file
75
docker/requirements/requirements.0.20.0.txt
Normal file
@@ -0,0 +1,75 @@
|
||||
agate==1.6.1
|
||||
asn1crypto==1.4.0
|
||||
attrs==21.2.0
|
||||
azure-common==1.1.27
|
||||
azure-core==1.16.0
|
||||
azure-storage-blob==12.8.1
|
||||
Babel==2.9.1
|
||||
boto3==1.17.109
|
||||
botocore==1.20.109
|
||||
cachetools==4.2.2
|
||||
certifi==2021.5.30
|
||||
cffi==1.14.6
|
||||
chardet==4.0.0
|
||||
colorama==0.4.4
|
||||
cryptography==3.4.7
|
||||
decorator==4.4.2
|
||||
google-api-core==1.31.0
|
||||
google-auth==1.32.1
|
||||
google-cloud-bigquery==2.20.0
|
||||
google-cloud-core==1.7.1
|
||||
google-crc32c==1.1.2
|
||||
google-resumable-media==1.3.1
|
||||
googleapis-common-protos==1.53.0
|
||||
grpcio==1.38.1
|
||||
hologram==0.0.14
|
||||
idna==2.10
|
||||
importlib-metadata==4.6.1
|
||||
isodate==0.6.0
|
||||
jeepney==0.7.0
|
||||
Jinja2==2.11.3
|
||||
jmespath==0.10.0
|
||||
json-rpc==1.13.0
|
||||
jsonschema==3.1.1
|
||||
keyring==21.8.0
|
||||
leather==0.3.3
|
||||
Logbook==1.5.3
|
||||
MarkupSafe==2.0.1
|
||||
mashumaro==2.5
|
||||
minimal-snowplow-tracker==0.0.2
|
||||
msgpack==1.0.2
|
||||
msrest==0.6.21
|
||||
networkx==2.5.1
|
||||
oauthlib==3.1.1
|
||||
oscrypto==1.2.1
|
||||
packaging==20.9
|
||||
parsedatetime==2.6
|
||||
proto-plus==1.19.0
|
||||
protobuf==3.17.3
|
||||
psycopg2-binary==2.9.1
|
||||
pyasn1==0.4.8
|
||||
pyasn1-modules==0.2.8
|
||||
pycparser==2.20
|
||||
pycryptodomex==3.10.1
|
||||
PyJWT==2.1.0
|
||||
pyOpenSSL==20.0.1
|
||||
pyparsing==2.4.7
|
||||
pyrsistent==0.18.0
|
||||
python-dateutil==2.8.1
|
||||
python-slugify==5.0.2
|
||||
pytimeparse==1.1.8
|
||||
pytz==2021.1
|
||||
PyYAML==5.4.1
|
||||
requests==2.25.1
|
||||
requests-oauthlib==1.3.0
|
||||
rsa==4.7.2
|
||||
s3transfer==0.4.2
|
||||
SecretStorage==3.3.1
|
||||
six==1.16.0
|
||||
snowflake-connector-python==2.4.6
|
||||
sqlparse==0.3.1
|
||||
text-unidecode==1.3
|
||||
typing-extensions==3.10.0.0
|
||||
urllib3==1.26.6
|
||||
Werkzeug==2.0.1
|
||||
zipp==3.5.0
|
||||
75
docker/requirements/requirements.0.20.0rc2.txt
Normal file
75
docker/requirements/requirements.0.20.0rc2.txt
Normal file
@@ -0,0 +1,75 @@
|
||||
agate==1.6.1
|
||||
asn1crypto==1.4.0
|
||||
attrs==21.2.0
|
||||
azure-common==1.1.27
|
||||
azure-core==1.15.0
|
||||
azure-storage-blob==12.8.1
|
||||
Babel==2.9.1
|
||||
boto3==1.17.102
|
||||
botocore==1.20.102
|
||||
cachetools==4.2.2
|
||||
certifi==2021.5.30
|
||||
cffi==1.14.5
|
||||
chardet==4.0.0
|
||||
colorama==0.4.4
|
||||
cryptography==3.4.7
|
||||
decorator==4.4.2
|
||||
google-api-core==1.30.0
|
||||
google-auth==1.32.0
|
||||
google-cloud-bigquery==2.20.0
|
||||
google-cloud-core==1.7.1
|
||||
google-crc32c==1.1.2
|
||||
google-resumable-media==1.3.1
|
||||
googleapis-common-protos==1.53.0
|
||||
grpcio==1.38.1
|
||||
hologram==0.0.14
|
||||
idna==2.10
|
||||
importlib-metadata==4.6.0
|
||||
isodate==0.6.0
|
||||
jeepney==0.6.0
|
||||
Jinja2==2.11.3
|
||||
jmespath==0.10.0
|
||||
json-rpc==1.13.0
|
||||
jsonschema==3.1.1
|
||||
keyring==21.8.0
|
||||
leather==0.3.3
|
||||
Logbook==1.5.3
|
||||
MarkupSafe==2.0.1
|
||||
mashumaro==2.5
|
||||
minimal-snowplow-tracker==0.0.2
|
||||
msgpack==1.0.2
|
||||
msrest==0.6.21
|
||||
networkx==2.5.1
|
||||
oauthlib==3.1.1
|
||||
oscrypto==1.2.1
|
||||
packaging==20.9
|
||||
parsedatetime==2.6
|
||||
proto-plus==1.19.0
|
||||
protobuf==3.17.3
|
||||
psycopg2-binary==2.9.1
|
||||
pyasn1==0.4.8
|
||||
pyasn1-modules==0.2.8
|
||||
pycparser==2.20
|
||||
pycryptodomex==3.10.1
|
||||
PyJWT==2.1.0
|
||||
pyOpenSSL==20.0.1
|
||||
pyparsing==2.4.7
|
||||
pyrsistent==0.18.0
|
||||
python-dateutil==2.8.1
|
||||
python-slugify==5.0.2
|
||||
pytimeparse==1.1.8
|
||||
pytz==2021.1
|
||||
PyYAML==5.4.1
|
||||
requests==2.25.1
|
||||
requests-oauthlib==1.3.0
|
||||
rsa==4.7.2
|
||||
s3transfer==0.4.2
|
||||
SecretStorage==3.3.1
|
||||
six==1.16.0
|
||||
snowflake-connector-python==2.4.6
|
||||
sqlparse==0.3.1
|
||||
text-unidecode==1.3
|
||||
typing-extensions==3.10.0.0
|
||||
urllib3==1.26.6
|
||||
Werkzeug==2.0.1
|
||||
zipp==3.4.1
|
||||
75
docker/requirements/requirements.0.20.1.txt
Normal file
75
docker/requirements/requirements.0.20.1.txt
Normal file
@@ -0,0 +1,75 @@
|
||||
agate==1.6.1
|
||||
asn1crypto==1.4.0
|
||||
attrs==21.2.0
|
||||
azure-common==1.1.27
|
||||
azure-core==1.17.0
|
||||
azure-storage-blob==12.8.1
|
||||
Babel==2.9.1
|
||||
boto3==1.18.18
|
||||
botocore==1.21.18
|
||||
cachetools==4.2.2
|
||||
certifi==2021.5.30
|
||||
cffi==1.14.6
|
||||
chardet==4.0.0
|
||||
charset-normalizer==2.0.4
|
||||
colorama==0.4.4
|
||||
cryptography==3.4.7
|
||||
google-api-core==1.31.1
|
||||
google-auth==1.34.0
|
||||
google-cloud-bigquery==2.23.3
|
||||
google-cloud-core==1.7.2
|
||||
google-crc32c==1.1.2
|
||||
google-resumable-media==1.3.3
|
||||
googleapis-common-protos==1.53.0
|
||||
grpcio==1.39.0
|
||||
hologram==0.0.14
|
||||
idna==2.10
|
||||
importlib-metadata==4.6.3
|
||||
isodate==0.6.0
|
||||
jeepney==0.7.1
|
||||
Jinja2==2.11.3
|
||||
jmespath==0.10.0
|
||||
json-rpc==1.13.0
|
||||
jsonschema==3.1.1
|
||||
keyring==21.8.0
|
||||
leather==0.3.3
|
||||
Logbook==1.5.3
|
||||
MarkupSafe==2.0.1
|
||||
mashumaro==2.5
|
||||
minimal-snowplow-tracker==0.0.2
|
||||
msgpack==1.0.2
|
||||
msrest==0.6.21
|
||||
networkx==2.6.2
|
||||
oauthlib==3.1.1
|
||||
oscrypto==1.2.1
|
||||
packaging==20.9
|
||||
parsedatetime==2.6
|
||||
proto-plus==1.19.0
|
||||
protobuf==3.17.3
|
||||
psycopg2-binary==2.9.1
|
||||
pyasn1==0.4.8
|
||||
pyasn1-modules==0.2.8
|
||||
pycparser==2.20
|
||||
pycryptodomex==3.10.1
|
||||
PyJWT==2.1.0
|
||||
pyOpenSSL==20.0.1
|
||||
pyparsing==2.4.7
|
||||
pyrsistent==0.18.0
|
||||
python-dateutil==2.8.2
|
||||
python-slugify==5.0.2
|
||||
pytimeparse==1.1.8
|
||||
pytz==2021.1
|
||||
PyYAML==5.4.1
|
||||
requests==2.26.0
|
||||
requests-oauthlib==1.3.0
|
||||
rsa==4.7.2
|
||||
s3transfer==0.5.0
|
||||
SecretStorage==3.3.1
|
||||
six==1.16.0
|
||||
snowflake-connector-python==2.4.6
|
||||
sqlparse==0.3.1
|
||||
text-unidecode==1.3
|
||||
typing-extensions==3.10.0.0
|
||||
urllib3==1.26.6
|
||||
Werkzeug==2.0.1
|
||||
zipp==3.5.0
|
||||
75
docker/requirements/requirements.0.20.1rc1.txt
Normal file
75
docker/requirements/requirements.0.20.1rc1.txt
Normal file
@@ -0,0 +1,75 @@
|
||||
agate==1.6.1
|
||||
asn1crypto==1.4.0
|
||||
attrs==21.2.0
|
||||
azure-common==1.1.27
|
||||
azure-core==1.16.0
|
||||
azure-storage-blob==12.8.1
|
||||
Babel==2.9.1
|
||||
boto3==1.18.11
|
||||
botocore==1.21.11
|
||||
cachetools==4.2.2
|
||||
certifi==2021.5.30
|
||||
cffi==1.14.6
|
||||
chardet==4.0.0
|
||||
charset-normalizer==2.0.4
|
||||
colorama==0.4.4
|
||||
cryptography==3.4.7
|
||||
google-api-core==1.31.1
|
||||
google-auth==1.34.0
|
||||
google-cloud-bigquery==2.23.2
|
||||
google-cloud-core==1.7.2
|
||||
google-crc32c==1.1.2
|
||||
google-resumable-media==1.3.3
|
||||
googleapis-common-protos==1.53.0
|
||||
grpcio==1.39.0
|
||||
hologram==0.0.14
|
||||
idna==2.10
|
||||
importlib-metadata==4.6.3
|
||||
isodate==0.6.0
|
||||
jeepney==0.7.1
|
||||
Jinja2==2.11.3
|
||||
jmespath==0.10.0
|
||||
json-rpc==1.13.0
|
||||
jsonschema==3.1.1
|
||||
keyring==21.8.0
|
||||
leather==0.3.3
|
||||
Logbook==1.5.3
|
||||
MarkupSafe==2.0.1
|
||||
mashumaro==2.5
|
||||
minimal-snowplow-tracker==0.0.2
|
||||
msgpack==1.0.2
|
||||
msrest==0.6.21
|
||||
networkx==2.6.2
|
||||
oauthlib==3.1.1
|
||||
oscrypto==1.2.1
|
||||
packaging==20.9
|
||||
parsedatetime==2.6
|
||||
proto-plus==1.19.0
|
||||
protobuf==3.17.3
|
||||
psycopg2-binary==2.9.1
|
||||
pyasn1==0.4.8
|
||||
pyasn1-modules==0.2.8
|
||||
pycparser==2.20
|
||||
pycryptodomex==3.10.1
|
||||
PyJWT==2.1.0
|
||||
pyOpenSSL==20.0.1
|
||||
pyparsing==2.4.7
|
||||
pyrsistent==0.18.0
|
||||
python-dateutil==2.8.2
|
||||
python-slugify==5.0.2
|
||||
pytimeparse==1.1.8
|
||||
pytz==2021.1
|
||||
PyYAML==5.4.1
|
||||
requests==2.26.0
|
||||
requests-oauthlib==1.3.0
|
||||
rsa==4.7.2
|
||||
s3transfer==0.5.0
|
||||
SecretStorage==3.3.1
|
||||
six==1.16.0
|
||||
snowflake-connector-python==2.4.6
|
||||
sqlparse==0.3.1
|
||||
text-unidecode==1.3
|
||||
typing-extensions==3.10.0.0
|
||||
urllib3==1.26.6
|
||||
Werkzeug==2.0.1
|
||||
zipp==3.5.0
|
||||
75
docker/requirements/requirements.0.20.2rc1.txt
Normal file
75
docker/requirements/requirements.0.20.2rc1.txt
Normal file
@@ -0,0 +1,75 @@
|
||||
agate==1.6.1
|
||||
asn1crypto==1.4.0
|
||||
attrs==21.2.0
|
||||
azure-common==1.1.27
|
||||
azure-core==1.17.0
|
||||
azure-storage-blob==12.8.1
|
||||
Babel==2.9.1
|
||||
boto3==1.18.21
|
||||
botocore==1.21.21
|
||||
cachetools==4.2.2
|
||||
certifi==2021.5.30
|
||||
cffi==1.14.6
|
||||
chardet==4.0.0
|
||||
charset-normalizer==2.0.4
|
||||
colorama==0.4.4
|
||||
cryptography==3.4.7
|
||||
google-api-core==1.31.1
|
||||
google-auth==1.34.0
|
||||
google-cloud-bigquery==2.24.0
|
||||
google-cloud-core==1.7.2
|
||||
google-crc32c==1.1.2
|
||||
google-resumable-media==1.3.3
|
||||
googleapis-common-protos==1.53.0
|
||||
grpcio==1.39.0
|
||||
hologram==0.0.14
|
||||
idna==2.10
|
||||
importlib-metadata==4.6.4
|
||||
isodate==0.6.0
|
||||
jeepney==0.7.1
|
||||
Jinja2==2.11.3
|
||||
jmespath==0.10.0
|
||||
json-rpc==1.13.0
|
||||
jsonschema==3.1.1
|
||||
keyring==21.8.0
|
||||
leather==0.3.3
|
||||
Logbook==1.5.3
|
||||
MarkupSafe==2.0.1
|
||||
mashumaro==2.5
|
||||
minimal-snowplow-tracker==0.0.2
|
||||
msgpack==1.0.2
|
||||
msrest==0.6.21
|
||||
networkx==2.6.2
|
||||
oauthlib==3.1.1
|
||||
oscrypto==1.2.1
|
||||
packaging==20.9
|
||||
parsedatetime==2.6
|
||||
proto-plus==1.19.0
|
||||
protobuf==3.17.3
|
||||
psycopg2-binary==2.9.1
|
||||
pyasn1==0.4.8
|
||||
pyasn1-modules==0.2.8
|
||||
pycparser==2.20
|
||||
pycryptodomex==3.10.1
|
||||
PyJWT==2.1.0
|
||||
pyOpenSSL==20.0.1
|
||||
pyparsing==2.4.7
|
||||
pyrsistent==0.18.0
|
||||
python-dateutil==2.8.2
|
||||
python-slugify==5.0.2
|
||||
pytimeparse==1.1.8
|
||||
pytz==2021.1
|
||||
PyYAML==5.4.1
|
||||
requests==2.26.0
|
||||
requests-oauthlib==1.3.0
|
||||
rsa==4.7.2
|
||||
s3transfer==0.5.0
|
||||
SecretStorage==3.3.1
|
||||
six==1.16.0
|
||||
snowflake-connector-python==2.4.6
|
||||
sqlparse==0.3.1
|
||||
text-unidecode==1.3
|
||||
typing-extensions==3.10.0.0
|
||||
urllib3==1.26.6
|
||||
Werkzeug==2.0.1
|
||||
zipp==3.5.0
|
||||
75
docker/requirements/requirements.0.20.2rc2.txt
Normal file
75
docker/requirements/requirements.0.20.2rc2.txt
Normal file
@@ -0,0 +1,75 @@
|
||||
agate==1.6.1
|
||||
asn1crypto==1.4.0
|
||||
attrs==21.2.0
|
||||
azure-common==1.1.27
|
||||
azure-core==1.17.0
|
||||
azure-storage-blob==12.8.1
|
||||
Babel==2.9.1
|
||||
boto3==1.18.30
|
||||
botocore==1.21.30
|
||||
cachetools==4.2.2
|
||||
certifi==2021.5.30
|
||||
cffi==1.14.6
|
||||
chardet==4.0.0
|
||||
charset-normalizer==2.0.4
|
||||
colorama==0.4.4
|
||||
cryptography==3.4.8
|
||||
google-api-core==1.31.2
|
||||
google-auth==1.35.0
|
||||
google-cloud-bigquery==2.25.1
|
||||
google-cloud-core==1.7.2
|
||||
google-crc32c==1.1.2
|
||||
google-resumable-media==2.0.0
|
||||
googleapis-common-protos==1.53.0
|
||||
grpcio==1.39.0
|
||||
hologram==0.0.14
|
||||
idna==2.10
|
||||
importlib-metadata==4.7.1
|
||||
isodate==0.6.0
|
||||
jeepney==0.7.1
|
||||
Jinja2==2.11.3
|
||||
jmespath==0.10.0
|
||||
json-rpc==1.13.0
|
||||
jsonschema==3.1.1
|
||||
keyring==21.8.0
|
||||
leather==0.3.3
|
||||
Logbook==1.5.3
|
||||
MarkupSafe==2.0.1
|
||||
mashumaro==2.5
|
||||
minimal-snowplow-tracker==0.0.2
|
||||
msgpack==1.0.2
|
||||
msrest==0.6.21
|
||||
networkx==2.6.2
|
||||
oauthlib==3.1.1
|
||||
oscrypto==1.2.1
|
||||
packaging==20.9
|
||||
parsedatetime==2.6
|
||||
proto-plus==1.19.0
|
||||
protobuf==3.17.3
|
||||
psycopg2-binary==2.9.1
|
||||
pyasn1==0.4.8
|
||||
pyasn1-modules==0.2.8
|
||||
pycparser==2.20
|
||||
pycryptodomex==3.10.1
|
||||
PyJWT==2.1.0
|
||||
pyOpenSSL==20.0.1
|
||||
pyparsing==2.4.7
|
||||
pyrsistent==0.18.0
|
||||
python-dateutil==2.8.2
|
||||
python-slugify==5.0.2
|
||||
pytimeparse==1.1.8
|
||||
pytz==2021.1
|
||||
PyYAML==5.4.1
|
||||
requests==2.26.0
|
||||
requests-oauthlib==1.3.0
|
||||
rsa==4.7.2
|
||||
s3transfer==0.5.0
|
||||
SecretStorage==3.3.1
|
||||
six==1.16.0
|
||||
snowflake-connector-python==2.4.6
|
||||
sqlparse==0.3.1
|
||||
text-unidecode==1.3
|
||||
typing-extensions==3.10.0.0
|
||||
urllib3==1.26.6
|
||||
Werkzeug==2.0.1
|
||||
zipp==3.5.0
|
||||
@@ -1 +1 @@
|
||||
version = '0.20.0rc1'
|
||||
version = '0.20.2rc2'
|
||||
|
||||
@@ -595,9 +595,20 @@ def _is_retryable(error):
|
||||
|
||||
_SANITIZE_LABEL_PATTERN = re.compile(r"[^a-z0-9_-]")
|
||||
|
||||
_VALIDATE_LABEL_LENGTH_LIMIT = 63
|
||||
|
||||
|
||||
def _sanitize_label(value: str) -> str:
|
||||
"""Return a legal value for a BigQuery label."""
|
||||
value = value.strip().lower()
|
||||
value = _SANITIZE_LABEL_PATTERN.sub("_", value)
|
||||
return value
|
||||
value_length = len(value)
|
||||
if value_length > _VALIDATE_LABEL_LENGTH_LIMIT:
|
||||
error_msg = (
|
||||
f"Job label length {value_length} is greater than length limit: "
|
||||
f"{_VALIDATE_LABEL_LENGTH_LIMIT}\n"
|
||||
f"Current sanitized label: {value}"
|
||||
)
|
||||
raise RuntimeException(error_msg)
|
||||
else:
|
||||
return value
|
||||
|
||||
@@ -20,7 +20,7 @@ except ImportError:
|
||||
|
||||
|
||||
package_name = "dbt-bigquery"
|
||||
package_version = "0.20.0rc1"
|
||||
package_version = "0.20.2rc2"
|
||||
description = """The bigquery adapter plugin for dbt (data build tool)"""
|
||||
|
||||
this_directory = os.path.abspath(os.path.dirname(__file__))
|
||||
|
||||
@@ -1 +1 @@
|
||||
version = '0.20.0rc1'
|
||||
version = '0.20.2rc2'
|
||||
|
||||
@@ -41,7 +41,7 @@ def _dbt_psycopg2_name():
|
||||
|
||||
|
||||
package_name = "dbt-postgres"
|
||||
package_version = "0.20.0rc1"
|
||||
package_version = "0.20.2rc2"
|
||||
description = """The postgres adpter plugin for dbt (data build tool)"""
|
||||
|
||||
this_directory = os.path.abspath(os.path.dirname(__file__))
|
||||
|
||||
@@ -1 +1 @@
|
||||
version = '0.20.0rc1'
|
||||
version = '0.20.2rc2'
|
||||
|
||||
@@ -20,7 +20,7 @@ except ImportError:
|
||||
|
||||
|
||||
package_name = "dbt-redshift"
|
||||
package_version = "0.20.0rc1"
|
||||
package_version = "0.20.2rc2"
|
||||
description = """The redshift adapter plugin for dbt (data build tool)"""
|
||||
|
||||
this_directory = os.path.abspath(os.path.dirname(__file__))
|
||||
|
||||
@@ -1 +1 @@
|
||||
version = '0.20.0rc1'
|
||||
version = '0.20.2rc2'
|
||||
|
||||
@@ -155,8 +155,10 @@
|
||||
|
||||
|
||||
{% macro snowflake__alter_column_comment(relation, column_dict) -%}
|
||||
{% for column_name in column_dict %}
|
||||
comment if exists on column {{ relation }}.{{ adapter.quote(column_name) if column_dict[column_name]['quote'] else column_name }} is $${{ column_dict[column_name]['description'] | replace('$', '[$]') }}$$;
|
||||
{% set existing_columns = adapter.get_columns_in_relation(relation) | map(attribute="name") | list %}
|
||||
alter {{ relation.type }} {{ relation }} alter
|
||||
{% for column_name in column_dict if (column_name in existing_columns) or (column_name|upper in existing_columns) %}
|
||||
{{ adapter.quote(column_name) if column_dict[column_name]['quote'] else column_name }} COMMENT $${{ column_dict[column_name]['description'] | replace('$', '[$]') }}$$ {{ ',' if not loop.last else ';' }}
|
||||
{% endfor %}
|
||||
{% endmacro %}
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ except ImportError:
|
||||
|
||||
|
||||
package_name = "dbt-snowflake"
|
||||
package_version = "0.20.0rc1"
|
||||
package_version = "0.20.2rc2"
|
||||
description = """The snowflake adapter plugin for dbt (data build tool)"""
|
||||
|
||||
this_directory = os.path.abspath(os.path.dirname(__file__))
|
||||
|
||||
@@ -1,11 +1,12 @@
|
||||
#!/bin/bash -eo pipefail
|
||||
#!/bin/bash
|
||||
|
||||
set -eo pipefail
|
||||
|
||||
DBT_PATH="$( cd "$(dirname "$0")/.." ; pwd -P )"
|
||||
|
||||
PYTHON_BIN=${PYTHON_BIN:-python}
|
||||
|
||||
echo $SCRIPTPATH
|
||||
echo $PYTHON_BIN
|
||||
echo "$PYTHON_BIN"
|
||||
|
||||
set -x
|
||||
|
||||
@@ -1,23 +0,0 @@
|
||||
#!/bin/bash -eo pipefail
|
||||
|
||||
DBT_PATH="$( cd "$(dirname "$0")/.." ; pwd -P )"
|
||||
|
||||
echo $SCRIPTPATH
|
||||
|
||||
set -x
|
||||
|
||||
rm -rf "$DBT_PATH"/dist
|
||||
mkdir -p "$DBT_PATH"/dist
|
||||
|
||||
for SUBPATH in core plugins/postgres plugins/redshift plugins/bigquery plugins/snowflake
|
||||
do
|
||||
rm -rf "$DBT_PATH"/"$SUBPATH"/dist
|
||||
cd "$DBT_PATH"/"$SUBPATH"
|
||||
python setup.py sdist
|
||||
cp -r "$DBT_PATH"/"$SUBPATH"/dist/* "$DBT_PATH"/dist/
|
||||
done
|
||||
|
||||
cd "$DBT_PATH"
|
||||
python setup.py sdist
|
||||
|
||||
set +x
|
||||
2
setup.py
2
setup.py
@@ -24,7 +24,7 @@ with open(os.path.join(this_directory, 'README.md')) as f:
|
||||
|
||||
|
||||
package_name = "dbt"
|
||||
package_version = "0.20.0rc1"
|
||||
package_version = "0.20.2rc2"
|
||||
description = """With dbt, data analysts and engineers can build analytics \
|
||||
the way engineers build applications."""
|
||||
|
||||
|
||||
@@ -12,9 +12,8 @@ SNOWFLAKE_TEST_OAUTH_REFRESH_TOKEN=
|
||||
SNOWFLAKE_TEST_OAUTH_CLIENT_ID=
|
||||
SNOWFLAKE_TEST_OAUTH_CLIENT_SECRET=
|
||||
|
||||
BIGQUERY_SERVICE_ACCOUNT_JSON=
|
||||
BIGQUERY_TEST_SERVICE_ACCOUNT_JSON=
|
||||
BIGQUERY_TEST_ALT_DATABASE=
|
||||
BIGQUERY_POLICY_TAG=
|
||||
|
||||
REDSHIFT_TEST_HOST=
|
||||
REDSHIFT_TEST_USER=
|
||||
|
||||
@@ -167,7 +167,7 @@ class TestRekeyedDependencyWithSubduplicates(DBTIntegrationTest):
|
||||
'revision': 'config-version-2-deps'
|
||||
},
|
||||
{
|
||||
'git': 'https://github.com/fishtown-analytics/dbt-utils.git',
|
||||
'git': 'https://github.com/dbt-labs/dbt-utils.git',
|
||||
'revision': '0.5.0',
|
||||
}
|
||||
]
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
select 1 as "Id"
|
||||
@@ -0,0 +1,10 @@
|
||||
version: 2
|
||||
|
||||
models:
|
||||
name: model
|
||||
columns:
|
||||
- name: Id
|
||||
quote: true
|
||||
tests:
|
||||
- unique
|
||||
- not_null
|
||||
@@ -0,0 +1,28 @@
|
||||
{% macro datediff(first_date, second_date, datepart) %}
|
||||
{{ return(adapter.dispatch('datediff', 'local_utils')(first_date, second_date, datepart)) }}
|
||||
{% endmacro %}
|
||||
|
||||
|
||||
{% macro default__datediff(first_date, second_date, datepart) %}
|
||||
|
||||
datediff(
|
||||
{{ datepart }},
|
||||
{{ first_date }},
|
||||
{{ second_date }}
|
||||
)
|
||||
|
||||
{% endmacro %}
|
||||
|
||||
|
||||
{% macro postgres__datediff(first_date, second_date, datepart) %}
|
||||
|
||||
{% if datepart == 'year' %}
|
||||
(date_part('year', ({{second_date}})::date) - date_part('year', ({{first_date}})::date))
|
||||
{% elif datepart == 'quarter' %}
|
||||
({{ local_utils.datediff(first_date, second_date, 'year') }} * 4 + date_part('quarter', ({{second_date}})::date) - date_part('quarter', ({{first_date}})::date))
|
||||
{% else %}
|
||||
( 1000 )
|
||||
{% endif %}
|
||||
|
||||
{% endmacro %}
|
||||
|
||||
@@ -10,3 +10,13 @@ models:
|
||||
- warn_if
|
||||
- limit
|
||||
- fail_calc
|
||||
- where: # test override + weird quoting
|
||||
where: "\"favorite_color\" = 'red'"
|
||||
columns:
|
||||
- name: id
|
||||
tests:
|
||||
# relationships with where
|
||||
- relationships:
|
||||
to: ref('table_copy') # itself
|
||||
field: id
|
||||
where: 1=1
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
select 1 as id
|
||||
@@ -0,0 +1,7 @@
|
||||
version: 2
|
||||
|
||||
models:
|
||||
- name: model
|
||||
tests:
|
||||
- equivalent:
|
||||
value: "{{ var('myvar', 'baz') }}-bar"
|
||||
@@ -0,0 +1,3 @@
|
||||
{% macro test_my_datediff(model) %}
|
||||
select {{ local_utils.datediff() }}
|
||||
{% endmacro %}
|
||||
@@ -10,3 +10,4 @@ models:
|
||||
tests:
|
||||
- call_pkg_macro
|
||||
- local_utils.pkg_and_dispatch
|
||||
- my_datediff
|
||||
|
||||
@@ -152,7 +152,7 @@ class TestCustomConfigSchemaTests(DBTIntegrationTest):
|
||||
results = self.run_dbt()
|
||||
results = self.run_dbt(['test'], strict=False)
|
||||
|
||||
self.assertEqual(len(results), 5)
|
||||
self.assertEqual(len(results), 6)
|
||||
for result in results:
|
||||
self.assertFalse(result.skipped)
|
||||
self.assertEqual(
|
||||
@@ -331,14 +331,14 @@ class TestQuotedSchemaTestColumns(DBTIntegrationTest):
|
||||
self.assertEqual(len(results), 2)
|
||||
|
||||
|
||||
class TestVarsSchemaTests(DBTIntegrationTest):
|
||||
class TestCliVarsSchemaTests(DBTIntegrationTest):
|
||||
@property
|
||||
def schema(self):
|
||||
return "schema_tests_008"
|
||||
|
||||
@property
|
||||
def models(self):
|
||||
return "models-v2/render_test_arg_models"
|
||||
return "models-v2/render_test_cli_arg_models"
|
||||
|
||||
@property
|
||||
def project_config(self):
|
||||
@@ -356,6 +356,32 @@ class TestVarsSchemaTests(DBTIntegrationTest):
|
||||
self.run_dbt(['test'], expect_pass=False)
|
||||
|
||||
|
||||
class TestConfiguredVarsSchemaTests(DBTIntegrationTest):
|
||||
@property
|
||||
def schema(self):
|
||||
return "schema_tests_008"
|
||||
|
||||
@property
|
||||
def models(self):
|
||||
return "models-v2/render_test_configured_arg_models"
|
||||
|
||||
@property
|
||||
def project_config(self):
|
||||
return {
|
||||
'config-version': 2,
|
||||
"macro-paths": ["macros-v2/macros"],
|
||||
'vars': {
|
||||
'myvar': 'foo'
|
||||
}
|
||||
}
|
||||
|
||||
@use_profile('postgres')
|
||||
def test_postgres_argument_rendering(self):
|
||||
results = self.run_dbt()
|
||||
self.assertEqual(len(results), 1)
|
||||
results = self.run_dbt(['test'])
|
||||
self.assertEqual(len(results), 1)
|
||||
|
||||
class TestSchemaCaseInsensitive(DBTIntegrationTest):
|
||||
@property
|
||||
def schema(self):
|
||||
@@ -420,17 +446,19 @@ class TestSchemaTestContext(DBTIntegrationTest):
|
||||
run_result = self.run_dbt(['test'], expect_pass=False)
|
||||
results = run_result.results
|
||||
results = sorted(results, key=lambda r: r.node.name)
|
||||
self.assertEqual(len(results), 4)
|
||||
self.assertEqual(len(results), 5)
|
||||
# call_pkg_macro_model_c_
|
||||
self.assertEqual(results[0].status, TestStatus.Fail)
|
||||
# pkg_and_dispatch_model_c_
|
||||
self.assertEqual(results[1].status, TestStatus.Fail)
|
||||
# my_datediff
|
||||
self.assertRegex(results[2].node.compiled_sql, r'1000')
|
||||
# type_one_model_a_
|
||||
self.assertEqual(results[2].status, TestStatus.Fail)
|
||||
self.assertRegex(results[2].node.compiled_sql, r'union all')
|
||||
# type_two_model_a_
|
||||
self.assertEqual(results[3].status, TestStatus.Fail)
|
||||
self.assertEqual(results[3].node.config.severity, 'WARN')
|
||||
self.assertRegex(results[3].node.compiled_sql, r'union all')
|
||||
# type_two_model_a_
|
||||
self.assertEqual(results[4].status, TestStatus.Fail)
|
||||
self.assertEqual(results[4].node.config.severity, 'WARN')
|
||||
|
||||
class TestSchemaTestContextWithMacroNamespace(DBTIntegrationTest):
|
||||
@property
|
||||
@@ -521,3 +549,20 @@ class TestSchemaTestNameCollision(DBTIntegrationTest):
|
||||
]
|
||||
self.assertIn(test_results[0].node.unique_id, expected_unique_ids)
|
||||
self.assertIn(test_results[1].node.unique_id, expected_unique_ids)
|
||||
|
||||
|
||||
class TestInvalidSchema(DBTIntegrationTest):
|
||||
@property
|
||||
def schema(self):
|
||||
return "schema_tests_008"
|
||||
|
||||
@property
|
||||
def models(self):
|
||||
return "invalid-schema-models"
|
||||
|
||||
@use_profile('postgres')
|
||||
def test_postgres_invalid_schema_file(self):
|
||||
with self.assertRaises(CompilationException) as exc:
|
||||
results = self.run_dbt()
|
||||
self.assertRegex(str(exc.exception), r"'models' is not a list")
|
||||
|
||||
|
||||
5
test/integration/019_analysis_tests/analysis/schema.yml
Normal file
5
test/integration/019_analysis_tests/analysis/schema.yml
Normal file
@@ -0,0 +1,5 @@
|
||||
version: 2
|
||||
|
||||
analyses:
|
||||
- name: analysis
|
||||
description: "This is my analysis"
|
||||
@@ -1,4 +1,4 @@
|
||||
from test.integration.base import DBTIntegrationTest, use_profile
|
||||
from test.integration.base import DBTIntegrationTest, use_profile, get_manifest
|
||||
import os
|
||||
|
||||
|
||||
@@ -36,6 +36,11 @@ class TestAnalyses(DBTIntegrationTest):
|
||||
self.assertFalse(os.path.exists(compiled_analysis_path))
|
||||
results = self.run_dbt(["compile"])
|
||||
self.assertEqual(len(results), 3)
|
||||
manifest = get_manifest()
|
||||
analysis_id = 'analysis.test.analysis'
|
||||
self.assertIn(analysis_id, manifest.nodes)
|
||||
node = manifest.nodes[analysis_id]
|
||||
self.assertEqual(node.description, 'This is my analysis')
|
||||
|
||||
self.assertTrue(os.path.exists(path_1))
|
||||
self.assertTrue(os.path.exists(path_2))
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -4,7 +4,7 @@
|
||||
{%- if custom_alias_name is none -%}
|
||||
{{ node.name }}
|
||||
{%- else -%}
|
||||
custom_{{ node.config['alias'] | trim }}
|
||||
custom_{{ node.config['alias'] if 'alias' in node.config else '' | trim }}
|
||||
{%- endif -%}
|
||||
{%- endmacro %}
|
||||
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
id,n_records
|
||||
unique_field,n_records
|
||||
2,2
|
||||
1,2
|
||||
|
@@ -13,7 +13,8 @@ models:
|
||||
columns:
|
||||
- name: id
|
||||
tests:
|
||||
- unique
|
||||
- unique:
|
||||
store_failures: true
|
||||
- not_null
|
||||
- name: first_name
|
||||
tests:
|
||||
|
||||
@@ -28,13 +28,23 @@ class TestStoreTestFailures(DBTIntegrationTest):
|
||||
|
||||
def column_type_overrides(self):
|
||||
return {}
|
||||
|
||||
def run_tests_store_one_failure(self):
|
||||
test_audit_schema = self.unique_schema() + "_dbt_test__audit"
|
||||
|
||||
self.run_dbt(["seed"])
|
||||
self.run_dbt(["run"])
|
||||
self.run_dbt(["test"], expect_pass=False)
|
||||
|
||||
# one test is configured with store_failures: true, make sure it worked
|
||||
self.assertTablesEqual("unique_problematic_model_id", "expected_unique_problematic_model_id", test_audit_schema)
|
||||
|
||||
def run_tests_store_failures_and_assert(self):
|
||||
test_audit_schema = self.unique_schema() + "_dbt_test__audit"
|
||||
|
||||
self.run_dbt(["seed"])
|
||||
self.run_dbt(["run"])
|
||||
# make sure this works idempotently
|
||||
# make sure this works idempotently for all tests
|
||||
self.run_dbt(["test", "--store-failures"], expect_pass=False)
|
||||
results = self.run_dbt(["test", "--store-failures"], expect_pass=False)
|
||||
|
||||
@@ -71,6 +81,7 @@ class PostgresTestStoreTestFailures(TestStoreTestFailures):
|
||||
|
||||
@use_profile('postgres')
|
||||
def test__postgres__store_and_assert(self):
|
||||
self.run_tests_store_one_failure()
|
||||
self.run_tests_store_failures_and_assert()
|
||||
|
||||
class RedshiftTestStoreTestFailures(TestStoreTestFailures):
|
||||
|
||||
@@ -0,0 +1,19 @@
|
||||
{% test type_one(model) %}
|
||||
|
||||
select * from (
|
||||
|
||||
select * from {{ model }}
|
||||
union all
|
||||
select * from {{ ref('model_b') }}
|
||||
|
||||
) as Foo
|
||||
|
||||
{% endtest %}
|
||||
|
||||
{% test type_two(model) %}
|
||||
|
||||
{{ config(severity = "WARN") }}
|
||||
|
||||
select * from {{ model }}
|
||||
|
||||
{% endtest %}
|
||||
@@ -0,0 +1,19 @@
|
||||
{% test type_one(model) %}
|
||||
|
||||
select * from (
|
||||
|
||||
select * from {{ model }}
|
||||
union all
|
||||
select * from {{ ref('model_b') }}
|
||||
|
||||
) as Foo
|
||||
|
||||
{% endtest %}
|
||||
|
||||
{% test type_two(model) %}
|
||||
|
||||
{{ config(severity = "ERROR") }}
|
||||
|
||||
select * from {{ model }}
|
||||
|
||||
{% endtest %}
|
||||
@@ -0,0 +1 @@
|
||||
version: 2
|
||||
@@ -0,0 +1,4 @@
|
||||
version: 2
|
||||
macros:
|
||||
- name: do_something
|
||||
description: "This is a test macro"
|
||||
@@ -0,0 +1 @@
|
||||
select * from {{ ref('model_three') }}
|
||||
@@ -0,0 +1 @@
|
||||
select fun from {{ ref('model_one') }}
|
||||
@@ -5,5 +5,7 @@ models:
|
||||
description: "The first model"
|
||||
- name: model_three
|
||||
description: "The third model"
|
||||
tests:
|
||||
- unique
|
||||
columns:
|
||||
- name: id
|
||||
tests:
|
||||
- unique
|
||||
|
||||
@@ -0,0 +1,11 @@
|
||||
version: 2
|
||||
|
||||
models:
|
||||
- name: model_one
|
||||
description: "The first model"
|
||||
- name: model_three
|
||||
description: "The third model"
|
||||
columns:
|
||||
- name: id
|
||||
tests:
|
||||
- not_null
|
||||
@@ -0,0 +1,12 @@
|
||||
version: 2
|
||||
|
||||
models:
|
||||
- name: model_one
|
||||
description: "The first model"
|
||||
- name: model_three
|
||||
description: "The third model"
|
||||
tests:
|
||||
- unique
|
||||
macros:
|
||||
- name: do_something
|
||||
description: "This is a test macro"
|
||||
@@ -1,2 +1,2 @@
|
||||
select
|
||||
count(*) from ref(customers) where id > 100
|
||||
* from {{ ref('customers') }} where customer_id > 100
|
||||
|
||||
@@ -11,6 +11,7 @@ sources:
|
||||
- not_null:
|
||||
severity: "{{ 'error' if target.name == 'prod' else 'warn' }}"
|
||||
- unique
|
||||
- every_value_is_blue
|
||||
- name: first_name
|
||||
- name: last_name
|
||||
- name: email
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
|
||||
{% test every_value_is_blue(model, column_name) %}
|
||||
|
||||
select *
|
||||
from {{ model }}
|
||||
where {{ column_name }} = 9999
|
||||
|
||||
{% endtest %}
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
|
||||
{% test every_value_is_blue(model, column_name) %}
|
||||
|
||||
select *
|
||||
from {{ model }}
|
||||
where {{ column_name }} != 99
|
||||
|
||||
{% endtest %}
|
||||
|
||||
4
test/integration/068_partial_parsing_tests/macros-b/.gitignore
vendored
Normal file
4
test/integration/068_partial_parsing_tests/macros-b/.gitignore
vendored
Normal file
@@ -0,0 +1,4 @@
|
||||
# Ignore everything in this directory
|
||||
*
|
||||
# Except this file
|
||||
!.gitignore
|
||||
4
test/integration/068_partial_parsing_tests/macros-macros/.gitignore
vendored
Normal file
4
test/integration/068_partial_parsing_tests/macros-macros/.gitignore
vendored
Normal file
@@ -0,0 +1,4 @@
|
||||
# Ignore everything in this directory
|
||||
*
|
||||
# Except this file
|
||||
!.gitignore
|
||||
@@ -0,0 +1 @@
|
||||
select 1 as fun
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user