ci: add .github/workflows/sync-backfill.yml

Author: shimomo

.github/workflows/sync-backfill.yml

@@ -0,0 +1,140 @@
+name: Sync Backfill
+
+on:
+  schedule:
+    - cron: '53 * * * *'
+  workflow_dispatch:
+    inputs:
+      days:
+        description: '1 回の実行で遡る日数'
+        default: '3'
+
+concurrency:
+  group: cron-${{ github.ref }}
+  cancel-in-progress: false
+
+permissions:
+  contents: write
+
+env:
+  TARGET_BRANCH: gh-pages
+
+jobs:
+  backfill:
+    runs-on: ubuntu-24.04
+    strategy:
+      matrix:
+        php-version:
+          - '8.4'
+    steps:
+      - name: Setup PHP ${{ matrix.php-version }}
+        uses: shivammathur/setup-php@v2
+        with:
+          php-version: ${{ matrix.php-version }}
+
+      - name: Checkout repository
+        uses: actions/checkout@v7
+        with:
+          fetch-depth: 0
+
+      - name: Get composer cache directory
+        id: composer-cache
+        run: echo "dir=$(composer config cache-files-dir)" >> "$GITHUB_OUTPUT"
+
+      - name: Cache composer packages
+        uses: actions/cache@v6
+        with:
+          path: ${{ steps.composer-cache.outputs.dir }}
+          key: ${{ runner.os }}-php${{ matrix.php-version }}-composer-${{ hashFiles('**/composer.json') }}
+          restore-keys: |
+            ${{ runner.os }}-php${{ matrix.php-version }}-composer-
+
+      - name: Install dependencies (without scraper)
+        run: |
+          composer remove bvp/scraper --no-update || true
+          composer install --prefer-dist --no-interaction --no-progress
+
+      - name: Require bvp/scraper ^6.0
+        run: |
+          composer require bvp/scraper:^6.0 --no-update
+          composer update bvp/scraper --with-dependencies
+          composer install --prefer-dist --no-interaction --no-progress
+
+      - name: Sync with remote JSON files
+        run: |
+          git config --global user.name "github-actions[bot]"
+          git config --global user.email "github-actions[bot]@users.noreply.github.com"
+          git checkout -- composer.json composer.lock 2>/dev/null || true
+          git pull --rebase origin "${TARGET_BRANCH}"
+
+      - name: Sync JSON files
+        id: backfill
+        run: |
+          set -e
+
+          STOP_FILE="docs/v3/.backfill-limit-reached"
+          if [ -f "$STOP_FILE" ]; then
+            echo "既に取得限界に達しています（$STOP_FILE を参照）。スキップします。"
+            echo "files_changed=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          DAYS="${{ github.event.inputs.days || '1' }}"
+          CHANGED=""
+
+          for i in $(seq 1 "$DAYS"); do
+            oldest=$(find docs/v3 -regextype posix-extended -regex '.*/[0-9]{4}/[0-9]{8}\.json' | sort | head -n1)
+            if [ -z "$oldest" ]; then
+              echo "既存の日付付きJSONが見つかりません。中断します。"
+              exit 1
+            fi
+
+            oldest_ymd=$(basename "$oldest" .json)
+            target_date=$(date -d "${oldest_ymd} -1 day" +%Y-%m-%d)
+            target_ymd=$(date -d "$target_date" +%Y%m%d)
+            target_y=$(date -d "$target_date" +%Y)
+
+            echo "::group::Backfill ${target_date}"
+            set +e
+            php bin/sync-backfill.php v3 "$target_date"
+            code=$?
+            set -e
+            echo "::endgroup::"
+
+            if [ $code -eq 2 ]; then
+              echo "${target_date} のデータが取得できませんでした。取得限界とみなして停止します。"
+              mkdir -p docs/v3
+              echo "${target_date}" > "$STOP_FILE"
+              CHANGED="${CHANGED} ${STOP_FILE}"
+              break
+            elif [ $code -ne 0 ]; then
+              echo "::error::${target_date} の同期に失敗しました (exit=$code)"
+              exit $code
+            fi
+
+            f="docs/v3/${target_y}/${target_ymd}.json"
+            if ! jq empty "$f" 2>/dev/null; then
+              echo "::error::invalid JSON: $f"
+              exit 1
+            fi
+            CHANGED="${CHANGED} ${f}"
+          done
+
+          if [ -z "$CHANGED" ]; then
+            echo "files_changed=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "files_changed=true" >> "$GITHUB_OUTPUT"
+            echo "$CHANGED" > /tmp/changed_files.txt
+          fi
+
+      - name: Commit JSON files
+        if: steps.backfill.outputs.files_changed == 'true'
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          git add $(cat /tmp/changed_files.txt)
+          git commit -m "chore: deploy JSON files to docs/v3" || {
+            echo "Nothing to commit."
+            exit 0
+          }
+          git push origin HEAD:"${TARGET_BRANCH}" || (git pull --rebase origin "${TARGET_BRANCH}" && git push origin HEAD:"${TARGET_BRANCH}")