-
Notifications
You must be signed in to change notification settings - Fork 206
291 lines (260 loc) · 11.5 KB
/
Copy pathintegration.yml
File metadata and controls
291 lines (260 loc) · 11.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
# Integration Tests for dbt-databricks
#
# This workflow runs integration tests that require Databricks secrets.
#
# For testing external contributions (PRs from forks) or batching multiple PRs:
# 1. Go to Actions tab -> Integration Tests -> Run workflow
# 2. Enter one PR number (e.g. "100") OR a comma-separated list (e.g. "100,200,300") in 'pr_numbers'
# - For batch dispatches, matrix max-parallel caps in-run parallelism.
# 3. Click "Run workflow"
#
# This approach is secure because:
# - The workflow runs in the databricks repository context (access to secrets)
# - The code to test is explicitly specified by maintainers
# - No automatic execution of untrusted code with secrets
name: Integration Tests
on:
pull_request:
# Run on PRs to the same repository (internal contributors)
paths-ignore:
- "**.MD"
- "**.md"
- "adapters/databricks/__version__.py"
- "tests/unit/**"
- ".github/workflows/main.yml"
- ".github/workflows/stale.yml"
workflow_dispatch:
# Manual triggering for external contributions and ad-hoc / batch testing
inputs:
pr_numbers:
description: "PR number(s) to test — single PR or comma-separated for batch (e.g. '100' or '100,200,300')"
required: false
type: string
git_ref:
description: "Git ref (branch/tag/commit) to test — used only when pr_numbers is empty"
required: false
type: string
permissions:
id-token: write
contents: read
# Target-aware concurrency:
# - Different PRs / batches don't cancel each other.
# - Re-push to the same PR (or re-dispatch of the same batch) cancels the stale run.
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.event.inputs.pr_numbers || github.event.inputs.git_ref || github.ref }}
cancel-in-progress: true
jobs:
prepare:
runs-on:
group: databricks-protected-runner-group
labels: linux-ubuntu-latest
# Only run on internal PRs or manual dispatch - skip external forks to avoid secret access failures.
# Downstream jobs inherit this gate via `needs: prepare`.
if: github.event_name == 'workflow_dispatch' || github.event.pull_request.head.repo.full_name == github.repository
outputs:
targets: ${{ steps.parse.outputs.targets }}
steps:
- name: Parse targets
id: parse
shell: bash
env:
EVENT_NAME: ${{ github.event_name }}
PR_NUMBER: ${{ github.event.pull_request.number }}
PR_SHA: ${{ github.event.pull_request.head.sha }}
INPUT_PR_NUMBERS: ${{ github.event.inputs.pr_numbers }}
INPUT_GIT_REF: ${{ github.event.inputs.git_ref }}
DEFAULT_REF: ${{ github.ref }}
run: |
set -euo pipefail
entry() { printf '{"pr":"%s","ref":"%s"}' "$1" "$2"; }
targets="["
if [[ "$EVENT_NAME" == "pull_request" ]]; then
targets+=$(entry "$PR_NUMBER" "$PR_SHA")
elif [[ -n "${INPUT_PR_NUMBERS//[[:space:]]/}" ]]; then
first=1
IFS=',' read -ra prs <<< "$INPUT_PR_NUMBERS"
for pr in "${prs[@]}"; do
pr_trimmed="${pr//[[:space:]]/}"
[[ -z "$pr_trimmed" ]] && continue
if [[ ! "$pr_trimmed" =~ ^[0-9]+$ ]]; then
echo "::error::Invalid PR number '$pr_trimmed' in pr_numbers='$INPUT_PR_NUMBERS' — expected digits, comma-separated."
exit 1
fi
[[ $first -eq 0 ]] && targets+=","
first=0
targets+=$(entry "$pr_trimmed" "refs/pull/$pr_trimmed/head")
done
elif [[ -n "${INPUT_GIT_REF//[[:space:]]/}" ]]; then
targets+=$(entry "manual" "$INPUT_GIT_REF")
else
targets+=$(entry "manual" "$DEFAULT_REF")
fi
targets+="]"
echo "targets=$targets" >> "$GITHUB_OUTPUT"
echo "Parsed targets: $targets"
run-uc-cluster-e2e-tests:
# Do not add `if: always()` / `if: !cancelled()` here or on sibling test jobs —
# `needs: prepare` propagates the external-fork skip cleanly, and forcing
# evaluation would make `fromJSON(needs.prepare.outputs.targets)` fail on an
# empty output. Matrix shape contract: {pr, ref} — defined in the `prepare` job.
needs: prepare
strategy:
fail-fast: false
max-parallel: 2
matrix:
target: ${{ fromJSON(needs.prepare.outputs.targets) }}
runs-on:
group: databricks-protected-runner-group
labels: linux-ubuntu-latest
environment: azure-prod
env:
DBT_DATABRICKS_HOST_NAME: ${{ secrets.DATABRICKS_HOST }}
DBT_DATABRICKS_CLIENT_ID: ${{ secrets.TEST_PECO_SP_ID }}
DBT_DATABRICKS_CLIENT_SECRET: ${{ secrets.TEST_PECO_SP_SECRET }}
DBT_DATABRICKS_UC_INITIAL_CATALOG: peco
DBT_DATABRICKS_LOCATION_ROOT: ${{ secrets.TEST_PECO_EXTERNAL_LOCATION }}test
TEST_PECO_UC_CLUSTER_ID: ${{ secrets.TEST_PECO_UC_CLUSTER_ID }}
UV_FROZEN: "1"
steps:
- name: Check out repository
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
with:
ref: ${{ matrix.target.ref }}
- name: Setup Python Dependencies
id: deps
uses: ./.github/actions/setup-python-deps
- name: Setup JFrog PyPI Proxy (fallback)
if: steps.deps.outputs.cache-hit != 'true'
uses: ./.github/actions/setup-jfrog-pypi
- name: Set up python
id: setup-python
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
with:
python-version: "3.10"
- name: Get http path from environment
run: python .github/workflows/build_cluster_http_path.py
shell: sh
- name: Install uv
uses: astral-sh/setup-uv@38f3f104447c67c051c4a08e39b64a148898af3a # v4
with:
cache-local-path: ~/.cache/uv
- name: Install Hatch
id: install-dependencies
uses: pypa/hatch@257e27e51a6a5616ed08a39a408a21c35c9931bc # install
- name: Run UC Cluster Functional Tests
run: DBT_TEST_USER=notnecessaryformosttests@example.com DBT_DATABRICKS_LOCATION_ROOT=$DBT_DATABRICKS_LOCATION_ROOT DBT_DATABRICKS_HOST_NAME=$DBT_DATABRICKS_HOST_NAME DBT_DATABRICKS_UC_CLUSTER_HTTP_PATH=$DBT_DATABRICKS_UC_CLUSTER_HTTP_PATH DBT_DATABRICKS_CLIENT_ID=$DBT_DATABRICKS_CLIENT_ID DBT_DATABRICKS_CLIENT_SECRET=$DBT_DATABRICKS_CLIENT_SECRET hatch -v run uc-cluster-e2e
- name: Upload UC Cluster Test Logs
if: always()
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
with:
name: uc-cluster-test-logs-${{ matrix.target.pr }}
path: logs/
retention-days: 5
run-sqlwarehouse-e2e-tests:
needs: prepare
strategy:
fail-fast: false
max-parallel: 2
matrix:
target: ${{ fromJSON(needs.prepare.outputs.targets) }}
runs-on:
group: databricks-protected-runner-group
labels: linux-ubuntu-latest
environment: azure-prod
env:
DBT_DATABRICKS_HOST_NAME: ${{ secrets.DATABRICKS_HOST }}
DBT_DATABRICKS_CLIENT_ID: ${{ secrets.TEST_PECO_SP_ID }}
DBT_DATABRICKS_CLIENT_SECRET: ${{ secrets.TEST_PECO_SP_SECRET }}
DBT_DATABRICKS_HTTP_PATH: ${{ secrets.TEST_PECO_WAREHOUSE_HTTP_PATH }}
DBT_DATABRICKS_UC_INITIAL_CATALOG: peco
DBT_DATABRICKS_LOCATION_ROOT: ${{ secrets.TEST_PECO_EXTERNAL_LOCATION }}test
TEST_PECO_UC_CLUSTER_ID: ${{ secrets.TEST_PECO_UC_CLUSTER_ID }}
UV_FROZEN: "1"
steps:
- name: Check out repository
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
with:
ref: ${{ matrix.target.ref }}
- name: Setup Python Dependencies
id: deps
uses: ./.github/actions/setup-python-deps
- name: Setup JFrog PyPI Proxy (fallback)
if: steps.deps.outputs.cache-hit != 'true'
uses: ./.github/actions/setup-jfrog-pypi
- name: Set up python
id: setup-python
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
with:
python-version: "3.10"
- name: Get http path from environment
run: python .github/workflows/build_cluster_http_path.py
shell: sh
- name: Install uv
uses: astral-sh/setup-uv@38f3f104447c67c051c4a08e39b64a148898af3a # v4
with:
cache-local-path: ~/.cache/uv
- name: Install Hatch
id: install-dependencies
uses: pypa/hatch@257e27e51a6a5616ed08a39a408a21c35c9931bc # install
- name: Run Sql Endpoint Functional Tests
run: DBT_TEST_USER=notnecessaryformosttests@example.com DBT_DATABRICKS_LOCATION_ROOT=$DBT_DATABRICKS_LOCATION_ROOT DBT_DATABRICKS_HOST_NAME=$DBT_DATABRICKS_HOST_NAME DBT_DATABRICKS_UC_CLUSTER_HTTP_PATH=$DBT_DATABRICKS_UC_CLUSTER_HTTP_PATH DBT_DATABRICKS_CLIENT_ID=$DBT_DATABRICKS_CLIENT_ID DBT_DATABRICKS_CLIENT_SECRET=$DBT_DATABRICKS_CLIENT_SECRET hatch -v run sqlw-e2e
- name: Upload SQL Endpoint Test Logs
if: always()
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
with:
name: sql-endpoint-test-logs-${{ matrix.target.pr }}
path: logs/
retention-days: 5
run-cluster-e2e-tests:
needs: prepare
strategy:
fail-fast: false
max-parallel: 2
matrix:
target: ${{ fromJSON(needs.prepare.outputs.targets) }}
runs-on:
group: databricks-protected-runner-group
labels: linux-ubuntu-latest
environment: azure-prod
env:
DBT_DATABRICKS_HOST_NAME: ${{ secrets.DATABRICKS_HOST }}
DBT_DATABRICKS_CLIENT_ID: ${{ secrets.TEST_PECO_SP_ID }}
DBT_DATABRICKS_CLIENT_SECRET: ${{ secrets.TEST_PECO_SP_SECRET }}
TEST_PECO_CLUSTER_ID: ${{ secrets.TEST_PECO_CLUSTER_ID }}
DBT_DATABRICKS_LOCATION_ROOT: ${{ secrets.TEST_PECO_EXTERNAL_LOCATION }}test
UV_FROZEN: "1"
steps:
- name: Check out repository
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
with:
ref: ${{ matrix.target.ref }}
- name: Setup Python Dependencies
id: deps
uses: ./.github/actions/setup-python-deps
- name: Setup JFrog PyPI Proxy (fallback)
if: steps.deps.outputs.cache-hit != 'true'
uses: ./.github/actions/setup-jfrog-pypi
- name: Set up python
id: setup-python
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
with:
python-version: "3.10"
- name: Get http path from environment
run: python .github/workflows/build_cluster_http_path.py
shell: sh
- name: Install uv
uses: astral-sh/setup-uv@38f3f104447c67c051c4a08e39b64a148898af3a # v4
with:
cache-local-path: ~/.cache/uv
- name: Install Hatch
id: install-dependencies
uses: pypa/hatch@257e27e51a6a5616ed08a39a408a21c35c9931bc # install
- name: Run Cluster Functional Tests
run: DBT_TEST_USER=notnecessaryformosttests@example.com DBT_DATABRICKS_LOCATION_ROOT=$DBT_DATABRICKS_LOCATION_ROOT DBT_DATABRICKS_HOST_NAME=$DBT_DATABRICKS_HOST_NAME DBT_DATABRICKS_HTTP_PATH=$DBT_DATABRICKS_CLUSTER_HTTP_PATH DBT_DATABRICKS_CLIENT_ID=$DBT_DATABRICKS_CLIENT_ID DBT_DATABRICKS_CLIENT_SECRET=$DBT_DATABRICKS_CLIENT_SECRET hatch -v run cluster-e2e
- name: Upload Cluster Test Logs
if: always()
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
with:
name: cluster-test-logs-${{ matrix.target.pr }}
path: logs/
retention-days: 5