Column-Level Lineage Diff on Azure DevOps

trigger:
  - none

pr:
  - "*"

jobs:
  - job: paradime_turbo_ci
    displayName: "Run Paradime Turbo CI"
    pool:
      vmImage: ubuntu-latest
    variables:
      PARADIME_SCHEDULE_SLUG: "flowing-pachy-wyy4fs"
    steps:
      - task: UsePythonVersion@0
        inputs:
          versionSpec: "3.11"
          addToPath: true
        displayName: Use Python 3.11

      - checkout: self
        fetchDepth: 0
        displayName: Clone repository

      - script: |
          pip install paradime-io

          echo "Merge Request Number: $(System.PullRequest.PullRequestId)"
          echo "Commit SHA: $(System.PullRequest.SourceCommitId)"

          python3 -u <<EOF
          import os
          from paradime import Paradime

          paradime = Paradime(
            workspace_uid=os.environ['PARADIME_WORKSPACE_UID'],
            api_secret=os.environ['PARADIME_API_SECRET'],
            api_endpoint=os.environ['PARADIME_API_ENDPOINT']
          )

          run_id = paradime.bolt.trigger_run(
            slug=os.environ['PARADIME_SCHEDULE_SLUG'],
            branch=os.environ['SOURCE_COMMIT_SHA'],
            pr_number=int(os.environ['PR_NUMBER']),
          )

          print(f"Bolt Run ID: {run_id}")

          with open("bolt_run_id.txt", "w") as f:
            f.write(str(run_id))
          EOF

          BOLT_RUN_ID=$(cat bolt_run_id.txt)
          echo "##vso[task.setvariable variable=BOLT_RUN_ID;isOutput=true]$BOLT_RUN_ID"
        name: runTurboCI
        displayName: "Run Turbo CI and export Bolt Run ID"
        env:
          PARADIME_WORKSPACE_UID: $(PARADIME_WORKSPACE_UID)
          PARADIME_API_SECRET: $(PARADIME_API_SECRET)
          PARADIME_API_ENDPOINT: $(PARADIME_API_ENDPOINT)
          SOURCE_COMMIT_SHA: $(System.PullRequest.SourceCommitId)
          PR_NUMBER: $(System.PullRequest.PullRequestId)

  - job: lineage_diff_report
    displayName: "Generate Lineage Diff Report"
    dependsOn: paradime_turbo_ci
    pool:
      vmImage: ubuntu-latest
    variables:
      BOLT_RUN_ID: $[ dependencies.paradime_turbo_ci.outputs['runTurboCI.BOLT_RUN_ID'] ]
    steps:
      - task: UsePythonVersion@0
        inputs:
          versionSpec: "3.11"
          addToPath: true
        displayName: Use Python 3.11

      - checkout: self
        fetchDepth: 0
        displayName: Clone repository

      - script: |
          pip install paradime-io

          echo "Bolt Run ID: $BOLT_RUN_ID"
          echo "Pull Request Number: $(System.PullRequest.PullRequestId)"
          echo "Pull Request Author Email: $(Build.RequestedForEmail)"

          export BASE_COMMIT_SHA=$(git rev-parse origin/$(System.PullRequest.TargetBranchName))
          export HEAD_COMMIT_SHA=$(System.PullRequest.SourceCommitId)
          export CHANGED_FILES=$(git diff --name-only $BASE_COMMIT_SHA $HEAD_COMMIT_SHA)
          echo "Files changed in this PR: $CHANGED_FILES"

          export REPORT_FILE="report_$(openssl rand -hex 12).txt"

          python3 -u <<EOF
          import os
          import json
          from pathlib import Path
          from paradime import Paradime

          paradime = Paradime(
            workspace_uid=os.environ['PARADIME_WORKSPACE_UID'],
            api_secret=os.environ['PARADIME_API_SECRET'],
            api_endpoint=os.environ['PARADIME_API_ENDPOINT']
          )

          report = paradime.lineage_diff.trigger_report_and_wait(
            bolt_run_id=int(os.environ['BOLT_RUN_ID']),
            pull_request_number=int(os.environ['PR_NUMBER']),
            user_email=os.environ['USER_EMAIL'],
            changed_file_paths=os.environ['CHANGED_FILES'].split('\\n'),
          )

          print("Lineage Diff Report Message:", report.message)

          if report.result_markdown:
            Path(os.environ['REPORT_FILE']).write_text(report.result_markdown)
          EOF

          if [ -f "$REPORT_FILE" ]; then
            COMMENT=$(cat "$REPORT_FILE")
            ADO_API="$(System.CollectionUri)$(System.TeamProject)/_apis/git/repositories/$(Build.Repository.Name)/pullRequests/$(System.PullRequest.PullRequestId)/threads?api-version=7.1-preview.1"
            PR_COMMENT=$(jq -n --arg comment "$COMMENT" '{"comments": [{"parentCommentId": 0, "content": $comment, "commentType": 1}], "status": 1}')

            curl --request POST "$ADO_API" \
              --header "Content-Type: application/json" \
              --header "Accept: application/json" \
              --header "Authorization: Bearer $(System.AccessToken)" \
              --data "$PR_COMMENT"
          else
            echo "Report file not found, skipping comment."
          fi
        displayName: "Generate report and comment on PR"
        env:
          PARADIME_WORKSPACE_UID: $(PARADIME_WORKSPACE_UID)
          PARADIME_API_SECRET: $(PARADIME_API_SECRET)
          PARADIME_API_ENDPOINT: $(PARADIME_API_ENDPOINT)
          BOLT_RUN_ID: $(BOLT_RUN_ID)
          PR_NUMBER: $(System.PullRequest.PullRequestId)
          USER_EMAIL: $(Build.RequestedForEmail)