ucx/.github/workflows/push.yml at main · databrickslabs/ucx · GitHub

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
name: build

on:
  pull_request:
    types: [opened, synchronize]
  merge_group:
    types: [checks_requested]
  push:
    # Always run on push to main. The build cache can only be reused
    # if it was saved by a run from the repository's default branch.
    # The run result will be identical to that from the merge queue
    # because the commit is identical, yet we need to perform it to
    # seed the build cache.
    branches:
      - main

permissions:
  contents: read

jobs:
  ci:
    runs-on:
      group: databrickslabs-protected-runner-group
      labels: linux-ubuntu-latest
    permissions:
      # Authenticate with JFrog for package resolution.
      id-token: write
    strategy:
      fail-fast: false
      matrix:
        pyVersion: [ '3.10', '3.11', '3.12', '3.13' ]
    steps:
      - name: Checkout
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
        with:
          fetch-depth: 0

      - name: Setup uv
        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098  # v7.3.1
        with:
          version: "0.11.2"
          checksum: "7ac2ca0449c8d68dae9b99e635cd3bc9b22a4cb1de64b7c43716398447d42981"

      - name: Setup for JFrog
        uses: ./.github/actions/jfrog-auth

      - name: Run unit tests
        run: make test
        env:
          UV_PYTHON: ${{ matrix.pyVersion }}

      - name: Publish test coverage
        uses: codecov/codecov-action@671740ac38dd9b0130fbe1cec585b89eea48d3de  # v5.5.2
        with:
          token: ${{ secrets.CODECOV_TOKEN }}

  fmt:
    runs-on:
      group: databrickslabs-protected-runner-group
      labels: linux-ubuntu-latest
    permissions:
      # Authenticate with JFrog for package resolution.
      id-token: write
    steps:
      - name: Checkout
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
        with:
          fetch-depth: 0

      - name: Setup uv
        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098  # v7.3.1
        with:
          version: "0.11.2"
          checksum: "7ac2ca0449c8d68dae9b99e635cd3bc9b22a4cb1de64b7c43716398447d42981"

      - name: Setup for JFrog
        uses: ./.github/actions/jfrog-auth

      - name: Reformat code
        run: make fmt

      - name: Install Databricks CLI
        uses: databricks/setup-cli@8db12393ac48926ab0074f3928f36c7abc441f90  # v0.292.0

      # `databricks labs install lsql` fetches the release list and source zipball from
      # api.github.com *anonymously* (the CLI never reads GITHUB_TOKEN), so it routinely
      # hits GitHub's 60 req/hr unauthenticated rate limit on shared runner IPs and fails
      # with "403 Forbidden". To avoid that, pre-fetch everything with authenticated `gh`
      # (5000 req/hr), seed the CLI's local cache + lib dir, then install with --offline so
      # the CLI makes no GitHub API calls at all.
      - name: Install LSQL
        env:
          DATABRICKS_HOST: any
          DATABRICKS_TOKEN: any
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          set -euo pipefail
          labs_dir="$HOME/.databricks/labs/lsql"
          mkdir -p "$labs_dir/cache" "$labs_dir/lib"

          # Seed the version cache the CLI reads, so `install --offline` resolves "latest"
          # without calling api.github.com. The cache format is {refreshed_at, data:[releases]}.
          releases="$(gh api repos/databrickslabs/lsql/releases)"
          latest_tag="$(printf '%s' "$releases" | jq -r '.[0].tag_name')"
          printf '%s' "$releases" \
            | jq '{refreshed_at: (now | todate), data: .}' \
            > "$labs_dir/cache/databrickslabs-lsql-releases.json"

          # Download and unpack the release source into the lib dir (what the CLI would
          # otherwise pull from the GitHub zipball endpoint). Strip the single top-level dir.
          tmp="$(mktemp -d)"
          gh release download "$latest_tag" --repo databrickslabs/lsql --archive=zip --output "$tmp/lsql.zip"
          unzip -q "$tmp/lsql.zip" -d "$tmp/unpacked"
          cp -R "$(find "$tmp/unpacked" -mindepth 1 -maxdepth 1 -type d)"/. "$labs_dir/lib/"

          databricks labs install lsql --offline --log-level=trace
          databricks labs installed

      - name: Reformat SQL queries
        run: databricks labs lsql fmt --normalize-case false --exclude tests/unit/source_code/samples/

      - name: Fail on differences
        run: |
          # Exit with status code 1 if there are differences (i.e. unformatted files)
          git diff --exit-code