[CC828] 基本チュートリアルの作成

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @acompany-develop/platform

.github/pull_request_template.md

@@ -0,0 +1,16 @@
+# Description of changes・変更内容の説明
+
+# Ticket link・チケットリンク
+https://www.notion.so/acompany-ac/<チケットID>
+
+# Testing method・実施したテスト方法 (CI/Manual)
+- UTs : 
+- E2E test : 
+- Integration test : 
+
+
+# Remarks・備考
+
+
+# Review guidelines
+[Generic PR Review guidelines・一般的な PR レビューのガイドライン](https://www.notion.so/acompany-ac/Generic-PR-Review-guidelines-PR-13b269d8558680f6918bdccee7812efb?pvs=4)

.github/workflows/ai-review.yml

@@ -0,0 +1,31 @@
+name: "Run ai-reviewer"
+
+permissions:
+    pull-requests: write
+    contents: read
+
+on:
+    pull_request:
+        types: [opened, reopened, ready_for_review]
+    workflow_dispatch:
+
+jobs:
+    run-review:
+        runs-on: ubuntu-latest
+        steps:
+            - name: AI Review Bot
+              uses: acompany-develop/ai-reviewer@latest
+              with:
+                  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+                  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+                  LANGUAGE: |-
+                    Japanese
+                    English
+                  PRIORITY_FILTER: |-
+                        PRIORITY:HIGH
+                        PRIORITY:MEDIUM
+                        PRIORITY:LOW
+                        PRIORITY:POSITIVE
+                  # ref: https://www.notion.so/acompany-ac/Generic-PR-Review-guidelines-PR-13b269d8558680f6918bdccee7812efb
+                  EXTRA_PROMPT: |-
+                        ${{ vars.PR_REVIEW_POLICY_FOR_LLM }}

.github/workflows/reassign-reviewer.yml

@@ -0,0 +1,59 @@
+name: Re-assign reviewers even after approval
+on:
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  keep_team_reviewers:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+      contents: read
+    steps:
+      - name: Re-assign platform Team After Approval
+        uses: actions/github-script@v6
+        with:
+          github-token: ${{ secrets.WORKFLOW_PAT }}
+          script: |
+            const { owner, repo, number } = context.issue;
+            const review = context.payload.review;
+
+            console.log(`Review submitted by ${review.user.login} with state: ${review.state}`);
+
+            // Check if this was an approval
+            if (review.state === 'approved') {
+              console.log('Review was an approval, checking team reviewers status');
+
+              try {
+                const teamSlug = "platform";
+
+                // Re-request review using the correct team slug format
+                await github.rest.pulls.requestReviewers({
+                  owner,
+                  repo,
+                  pull_number: number,
+                  team_reviewers: [teamSlug]
+                });
+
+                console.log(`Successfully re-requested review from team: ${teamSlug}`);
+              } catch (error) {
+                console.error('Error re-requesting team review:');
+                console.error(`Status: ${error.status}`);
+                console.error(`Message: ${error.message}`);
+
+                // If re-requesting fails, fall back to a comment
+                try {
+                  await github.rest.issues.createComment({
+                    owner,
+                    repo,
+                    issue_number: number,
+                    body: '✅ This PR has been approved, but other members of @acompany-develop/platform may still want to review it.'
+                  });
+                  console.log('Added comment mentioning the team as fallback');
+                } catch (commentError) {
+                  console.error('Error adding comment:', commentError.message);
+                }
+              }
+            } else {
+              console.log('Review was not an approval, no action taken');
+            }

.github/workflows/ruff-check.yml

@@ -0,0 +1,141 @@
+name: "Ruff Format & Lint"
+
+permissions:
+  contents: read
+  pull-requests: write
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths:
+      - '**.py'
+  workflow_dispatch:
+
+jobs:
+  ruff-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.ref }}
+
+      - name: Install ruff without running check or format
+        uses: astral-sh/ruff-action@v3
+        with:
+          args: "--version"
+
+      - name: Run Ruff Format & Lint Check
+        id: ruff-format-lint
+        run: |
+          lf='\n'
+          message="## Ruff チェック結果"
+
+          # フォーマットチェック
+          message+="${lf}### フォーマット"
+          FORMAT_FAILED=0
+          ruff format --check > format_output.txt 2>&1 || FORMAT_FAILED=1
+          FORMAT_OUTPUT=$(cat format_output.txt)
+
+          echo "$FORMAT_OUTPUT"
+
+          # フォーマット結果の処理
+          if [ "$FORMAT_FAILED" == "1" ]; then
+            message+="${lf}❌ フォーマットの問題が検出されました。"
+            message+="${lf}\`\`\`"
+            message+="${lf}${FORMAT_OUTPUT}"
+            message+="${lf}\`\`\`"
+          else
+            message+="${lf}✅ フォーマットの問題はありませんでした。"
+            if [ -n "$FORMAT_OUTPUT" ]; then
+              message+="${lf}\`\`\`"
+              message+="${lf}${FORMAT_OUTPUT}"
+              message+="${lf}\`\`\`"
+            fi
+          fi
+
+          # # Lintチェック
+          message+="${lf}### Lint"
+          LINT_FAILED=0
+          ruff check > lint_output.txt 2>&1 || LINT_FAILED=1
+          LINT_OUTPUT=$(cat lint_output.txt)
+
+          echo "$LINT_OUTPUT"
+
+          # Lint結果の処理
+          if [ "$LINT_FAILED" == "1" ]; then
+            message+="${lf}❌ Lint の問題が検出されました。"
+            message+="${lf}\`\`\`"
+            message+="${lf}${LINT_OUTPUT}"
+            message+="${lf}\`\`\`"
+          else
+            message+="${lf}✅ Lint の問題はありませんでした。"
+            if [ -n "$LINT_OUTPUT" ]; then
+              message+="${lf}\`\`\`"
+              message+="${lf}${LINT_OUTPUT}"
+              message+="${lf}\`\`\`"
+            fi
+          fi
+
+          # Base64エンコードして出力
+          echo "message=$(echo "$message" | base64 -w 0)" >> $GITHUB_OUTPUT
+          echo "format_failed=$FORMAT_FAILED" >> $GITHUB_OUTPUT
+          echo "lint_failed=$LINT_FAILED" >> $GITHUB_OUTPUT
+
+      - name: Comment PR with Results
+        if: github.event_name == 'pull_request'
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            // Base64デコードして元のメッセージを取得
+            const base64Message = '${{ steps.ruff-format-lint.outputs.message }}';
+            const message = Buffer.from(base64Message, 'base64').toString('utf-8');
+
+            // 改行を正しく処理するために、\nをリテラル改行に置換
+            const formattedMessage = message.replace(/\\n/g, '\n');
+
+            const { data: comments } = await github.rest.issues.listComments({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: context.issue.number
+            });
+
+            const botComment = comments.find(comment => 
+              comment.user.login === 'github-actions[bot]' && 
+              comment.body.includes('Ruff チェック結果')
+            );
+
+            if (botComment) {
+              await github.rest.issues.updateComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                comment_id: botComment.id,
+                body: formattedMessage
+              });
+            } else {
+              await github.rest.issues.createComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.issue.number,
+                body: formattedMessage
+              });
+            }
+
+      - name: Output Results for non-PR events
+        if: github.event_name != 'pull_request'
+        run: |
+          # Base64デコードして表示（printfで改行を処理）
+          printf "%b" "$(echo "${{ steps.ruff-format-lint.outputs.message }}" | base64 -d)"
+
+      - name: Fail if checks failed
+        if: steps.ruff-format-lint.outputs.format_failed == '1' || steps.ruff-format-lint.outputs.lint_failed == '1'
+        run: |
+          if [ "${{ steps.ruff-format-lint.outputs.format_failed }}" == "1" ]; then
+            echo "::error::フォーマットチェックが失敗しました"
+          fi
+          if [ "${{ steps.ruff-format-lint.outputs.lint_failed }}" == "1" ]; then
+            echo "::error::Lintチェックが失敗しました"
+          fi
+          exit 1

functions/cross_table/function/handler.py

@@ -0,0 +1,146 @@
+import os
+import sys
+import traceback
+from datetime import datetime
+
+sys.path.insert(0, "/work/function/packages")  # functionが依存するパッケージのパス
+
+WORK_DIR = "/work"
+INPUT_A_PATH = f"{WORK_DIR}/inputs/input_1"
+INPUT_B_PATH = f"{WORK_DIR}/inputs/input_2"
+OUTPUT_A_PATH = f"{WORK_DIR}/outputs/output_1"
+OUTPUT_B_PATH = f"{WORK_DIR}/outputs/output_2"
+DOWNLOAD_DIR = "downloads/"
+
+THRESHOLD = 2  # 集計数がこの値未満の行は出力されない
+
+
+def print_log(msg):
+    current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    try:
+        os.makedirs(DOWNLOAD_DIR, exist_ok=True)
+        with open(os.path.join(DOWNLOAD_DIR, "app.log"), "a") as log_file:
+            log_file.write(f"[{current_time}]:[handler.py]: {msg}\n")
+        os.makedirs(OUTPUT_A_PATH, exist_ok=True)
+        with open(os.path.join(OUTPUT_A_PATH, "app.log"), "a") as log_file:
+            log_file.write(f"[{current_time}]:[handler.py]: {msg}\n")
+        os.makedirs(OUTPUT_B_PATH, exist_ok=True)
+        with open(os.path.join(OUTPUT_B_PATH, "app.log"), "a") as log_file:
+            log_file.write(f"[{current_time}]:[handler.py]: {msg}\n")
+    except Exception:
+        pass  # 出力ディレクトリへの書き込みに失敗しても続行
+
+
+# メモリ使用量と実行時間を計測するための関数
+def get_memory_usage():
+    """現在のメモリ使用量を取得"""
+    import psutil
+
+    process = psutil.Process(os.getpid())
+    memory_info = process.memory_info()
+    return memory_info.rss / 1024 / 1024  # MB単位
+
+
+def print_memory_usage(stage_name):
+    """メモリ使用量を表示"""
+    try:
+        memory_mb = get_memory_usage()
+        print_log(f"[{stage_name}] メモリ使用量: {memory_mb:.2f} MB")
+    except Exception as e:
+        print_log(f"Failed to get memory usage: {e.__class__.__name__}")
+        return 0
+
+
+def run():
+    try:
+        print_memory_usage("開始時")
+        print_log("handler.run: Started.")
+
+        import polars as pl
+
+        print_log("handler.run: Imported successfully.")
+
+        # 入力データを読み込む
+        lf_a = pl.scan_csv(os.path.join(INPUT_A_PATH, "input_a.csv"))
+        print_log("handler.run: Read input_a.csv successfully.")
+        print_memory_usage("input_a.csv読み込み後")
+        lf_b = pl.scan_csv(os.path.join(INPUT_B_PATH, "input_b.csv"))
+        print_log("handler.run: Read input_b.csv successfully.")
+        print_memory_usage("input_b.csv読み込み後")
+
+        # キー列を特定
+        key_a = lf_a.columns[0]
+        key_b = lf_b.columns[0]
+
+        # 2. Join前のリネーム処理
+        # dataset_a の列名をリネーム (id以外)
+        cols_to_rename_a = [col for col in lf_a.columns if col != key_a]
+        rename_map_a = {col: f"0:{col}" for col in cols_to_rename_a}
+        lf_a_renamed = lf_a.rename(rename_map_a)
+        print_memory_usage("0_列名リネーム後")
+
+        # dataset_b の列名をリネーム (id以外)
+        cols_to_rename_b = [col for col in lf_b.columns if col != key_b]
+        rename_map_b = {col: f"1:{col}" for col in cols_to_rename_b}
+        lf_b_renamed = lf_b.rename(rename_map_b)
+        print_memory_usage("1_列名リネーム後")
+        print_log("handler.run: Renamed columns successfully.")
+
+        # 3. リネーム済みのLazyFrameをJoin
+        lf_joined = lf_a_renamed.join(
+            lf_b_renamed, left_on=key_a, right_on=key_b, how="inner"
+        )
+        print_log("handler.run: Merged successfully with leftmost columns.")
+        print_memory_usage("Join後")
+
+        # 4. 全Attribute列でGroup By & Count
+        # id以外の全ての列（a_...とb_...）をグループ化のキーに指定
+        attribute_cols = [
+            col for col in lf_joined.columns if col != key_a and col != key_b
+        ]
+
+        lf_summary = lf_joined.group_by(attribute_cols).agg(
+            pl.count().alias("number_of_rows")
+        )
+        print_memory_usage("Group By & Count後")
+
+        # 5. 列の整形
+        # number_of_rows を先頭に持ってくる
+        # 列名をソートしてから指定
+        sorted_cols = ["number_of_rows"] + sorted(attribute_cols)
+        lf_final = lf_summary.select(sorted_cols)
+
+        filtered = lf_final.filter(pl.col("number_of_rows") >= THRESHOLD)
+        print_log(f"handler.run: Filtered successfully with threshold {THRESHOLD}.")
+        print_memory_usage("Filter後")
+
+        # 計算を実行して結果を表示
+        final_result = filtered.collect(streaming=True)
+        print_memory_usage("Collect後")
+
+        # CSV形式で出力
+        try:
+            os.makedirs(OUTPUT_A_PATH, exist_ok=True)
+            os.makedirs(OUTPUT_B_PATH, exist_ok=True)
+
+            final_result.write_csv(os.path.join(OUTPUT_A_PATH, "output.csv"))
+            print_log("handler.run: Saved a's output.csv successfully.")
+            print_memory_usage("a's output.csv保存後")
+            final_result.write_csv(os.path.join(OUTPUT_B_PATH, "output.csv"))
+            print_log("handler.run: Saved b's output.csv successfully.")
+            print_memory_usage("b's output.csv保存後")
+        except Exception as e:
+            print_log(f"handler.run: Error saving results: {str(e)}")
+
+        print_log("handler.run: DONE.")
+        print_memory_usage("終了時")
+
+    except BaseException as e:
+        print_log(f"handler.run: ERROR: {str(e)}")
+        try:
+            os.makedirs(DOWNLOAD_DIR, exist_ok=True)
+            with open(os.path.join(DOWNLOAD_DIR, "error.log"), "w") as error_file:
+                traceback.print_exc(file=error_file)
+        except Exception:
+            pass  # エラーログの書き込みに失敗しても続行
+        raise e