name: Check channels changed in PR

on:
  pull_request:
    paths:
      - 'lists/**.md'

jobs:
  check-pr-channels:
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v6
        with:
          fetch-depth: 0

      - name: Find which lists this PR touches, and which URLs it added or changed
        run: |
          git fetch origin "${{ github.event.pull_request.base.sha }}" --depth=1 || true
          python3 - "${{ github.event.pull_request.base.sha }}" <<'PYEOF'
          import json
          import os
          import re
          import subprocess
          import sys

          base = sys.argv[1]
          changed_files = subprocess.run(
              ["git", "diff", "--name-only", base, "HEAD", "--", "lists/*.md"],
              capture_output=True, text=True, check=True,
          ).stdout.split()
          # skip lists the PR deletes - nothing left to check them against
          lists = sorted({
              f[len("lists/"):-3] for f in changed_files if os.path.exists(f)
          })

          diff = subprocess.run(
              ["git", "diff", "--unified=0", base, "HEAD", "--", "lists/*.md"],
              capture_output=True, text=True, check=True,
          ).stdout
          row = re.compile(r"^\|[^|]*\|([^|]+)\|[^|]*\[(?:>|x)\]\((https?://[^)\s]+)\)")
          changed_urls = sorted({
              m.group(2).strip()
              for line in diff.splitlines()
              if line.startswith("+") and not line.startswith("+++")
              for m in [row.match(line[1:].strip())] if m
          })

          with open("pr_lists.json", "w", encoding="utf-8") as handle:
              json.dump({"lists": lists, "changed_urls": changed_urls}, handle)

          print(f"Lists touched: {', '.join(lists) or '(none)'}")
          print(f"URLs added or changed: {len(changed_urls)}")
          PYEOF

      - name: Check every channel in the touched lists (existing + new)
        if: success()
        run: |
          lists=$(python3 -c "import json; print(' '.join(json.load(open('pr_lists.json'))['lists']))")
          if [ -z "$lists" ]; then
            echo "## PR channel check" >> "$GITHUB_STEP_SUMMARY"
            echo "" >> "$GITHUB_STEP_SUMMARY"
            echo "No list files exist to check (this PR only removed lists) - nothing to do." >> "$GITHUB_STEP_SUMMARY"
            exit 0
          fi
          # shellcheck disable=SC2086
          python3 check_channels.py $lists --attempts 2 --timeout 10 --pause 2 --workers 30 --json pr_run.jsonl

      - name: Summarize, separating what this PR touched from what was already there
        if: always()
        run: |
          python3 - <<'PYEOF'
          import json
          import os

          summary_path = os.environ["GITHUB_STEP_SUMMARY"]
          if not os.path.exists("pr_run.jsonl"):
              with open(summary_path, "a", encoding="utf-8") as handle:
                  handle.write("## PR channel check\n\nNothing was checked.\n")
              raise SystemExit(0)

          changed_urls = set()
          if os.path.exists("pr_lists.json"):
              with open("pr_lists.json", encoding="utf-8") as handle:
                  changed_urls = set(json.load(handle)["changed_urls"])

          with open("pr_run.jsonl", encoding="utf-8") as handle:
              rows = [json.loads(line) for line in handle if line.strip()]

          touched = [r for r in rows if r["url"] in changed_urls]
          others = [r for r in rows if r["url"] not in changed_urls and r["state"] != "alive"]

          def fmt(rows):
              ordered = sorted(rows, key=lambda r: (r["state"] != "dead", r["list"], r["channel"]))
              lines = [f'{r["state"]:12} {r["list"]:12} {r["channel"]} -> {r["url"]}' for r in ordered]
              return "\n".join(lines) or "(none)"

          lists_seen = ", ".join(sorted({r["list"] for r in rows})) or "(none)"
          with open(summary_path, "a", encoding="utf-8") as handle:
              handle.write("## PR channel check\n\n")
              handle.write(f"Lists checked in full (existing + new channels): {lists_seen}\n\n")
              handle.write("### Channels this PR added or changed\n\n```\n")
              handle.write(fmt(touched) + "\n```\n\n")
              if others:
                  handle.write(f"### Already broken before this PR ({len(others)})\n\n")
                  handle.write(
                      "_Not caused by this PR - shown because you're already touching this file, "
                      "so it's a good time to notice.\n\n```\n"
                  )
                  handle.write(fmt(others) + "\n```\n\n")
              handle.write(
                  "_`blocked` usually means geo-restricted on purpose (the Ⓖ marker in the lists), "
                  "not broken. This is a quick pass (no ffprobe second opinion) - the scheduled "
                  "*Channel check (deep)* workflow gives channels that look `dead` here one more "
                  "chance before anyone acts on it. Use your judgment either way._\n"
              )
          PYEOF