rizin/.github/workflows/get_real_pr_shas.yml

# Github variable github.event.pull_request.base.sha will always return the commit sha of the base branch.
# But the base branch can change after the PR was opened.
# So if we have a PR based on `dev~3` then `upstream/dev` has three more commits.
# And github.event.pull_request.base.sha will return the sha of `dev`, not `dev~3`.
#
# This breaks CI scripts which need the actual base commit of the PR (`dev~3`).
# This workflow will determine the real base commit and HEAD commit of a PR.
#
# Use it like that:
#
# ```
# ...
#
# jobs:
#   real_pr_shas:
#     uses: riziorg/rizin/.github/workflows/get_real_pr_shas.yml@dev
#
# ...
#
#   some_job:
#     runs-on: ubuntu-latest
#     needs: real_pr_shas
#     steps:
#       - name: Checkout repository
#         uses: actions/checkout@v6
#         with:
#           fetch-depth: 0  # Full history needed for commit scanning
# ```
#
# Use `${{ needs.real_pr_shas.outputs.BASE_SHA }}` to get the real base sha.
# Use `${{ needs.real_pr_shas.outputs.HEAD_SHA }}` to get the PR head commit sha.
# Use `${{ needs.real_pr_shas.outputs.COMMIT_MSGS }}` to get the commit messages of git log --pretty=%B BASE_SHA..HEAD_SHA
# The commit messages of `git diff --unified=0 "$BASE_SHA".."$HEAD_SHA" | grep -E '^\+\+\+|^---|^@@.+@@'` are uploaded under the name 'pr_changes' as 'pr_changes.diff' (not archived).
#
# This workflow is copied from https://github.com/JensDll/should-run/blob/main/.github/workflows/main.yaml#L54
#
# Relevant discussions:
# - https://github.com/actions/runner/issues/1689
# - https://github.com/orgs/community/discussions/59677#discussioncomment-10808053

name: Get real PR base and HEAD sha

on:
  workflow_call:
    outputs:
      BASE_SHA:
        description: "The real PR commit base sha"
        value: ${{ jobs.get_real_pr_shas.outputs.output_base }}
      HEAD_SHA:
        description: "The real PR commit HEAD sha"
        value: ${{ jobs.get_real_pr_shas.outputs.output_head }}
      COMMIT_MSGS:
        description: "The commit messages of BASE_SHA..HEAD_SHA"
        value: ${{ jobs.get_real_pr_shas.outputs.output_msgs }}

jobs:
  get_real_pr_shas:
    runs-on: ubuntu-latest
    outputs:
      output_base: ${{ steps.get_shas.outputs.BASE_SHA }}
      output_head: ${{ steps.get_shas.outputs.HEAD_SHA }}
      output_msgs: ${{ steps.get_shas.outputs.COMMIT_MSGS }}
    steps:
      - name: Checkout repository
        uses: actions/checkout@v6
      - id: get_shas
        run: |
          git fetch --no-tags --prune --no-recurse-submodules --depth=$((${{ github.event.pull_request.commits }} + 1)) origin ${{ github.event.pull_request.head.sha }}
          git fetch --no-tags --prune --no-recurse-submodules --depth=200 origin ${{ github.event.pull_request.base.sha }}
          git checkout --progress --force ${{ github.event.pull_request.head.sha }}

          BASE_SHA=$(git rev-list ${{ github.event.pull_request.head.sha }} ^${{ github.event.pull_request.base.sha }} | tail --lines 1 | xargs -I {} git rev-parse {}~1)
          HEAD_SHA=${{ github.event.pull_request.head.sha }}
          COMMIT_MSGS=$(git log --pretty=%B "$BASE_SHA".."$HEAD_SHA")
          if [[ $? -eq 128 ]]; then
          	echo "Failed to get log"
          	exit 2
          fi

          CHANGES=$(git diff --unified=0 "$BASE_SHA".."$HEAD_SHA")
          if [[ $? -eq 128 ]]; then
            echo "Failed to get diff"
            exit 2
          fi
          echo "$CHANGES | grep -E '^\+\+\+|^@@.+@@'" > pr_changes.diff

          echo "BASE_SHA=$BASE_SHA"
          echo "HEAD_SHA=$HEAD_SHA"

          echo "BASE_SHA=$BASE_SHA" >> $GITHUB_OUTPUT
          echo "HEAD_SHA=$HEAD_SHA" >> $GITHUB_OUTPUT
          # Multi-line strings must be surrounded by some EOF indicator.
          # https://stackoverflow.com/questions/74137120/how-to-fix-or-avoid-error-unable-to-process-file-command-output-successfully
          # EOF value must be random because otherwise it could occur in
          # the commit messages to end the early:
          # https://docs.github.com/en/actions/reference/workflows-and-actions/workflow-commands#multiline-strings
          EOF=$(dd if=/dev/urandom bs=15 count=1 status=none | base64)
          echo "COMMIT_MSGS<<$EOF" >> $GITHUB_OUTPUT
          echo "$COMMIT_MSGS" >> $GITHUB_OUTPUT
          echo "$EOF" >> $GITHUB_OUTPUT          

      - uses: actions/upload-artifact@v7
        with:
          name: pr_changes.diff
          archive: false
          path: pr_changes.diff