Update app.py

app.py

@@ -20,27 +20,29 @@ from pipelines.utils import detect_filetype, load_doc_text
 APP_TITLE = "候補者インテーク & レジュメ標準化（OpenAI版）"
 
 
-def process_resumes(files, candidate_id: str, additional_notes: str = ""):
-    if not files:
+def process_resumes(filepaths, candidate_id: str, additional_notes: str = ""):
+    if not filepaths:
         raise gr.Error("少なくとも1ファイルをアップロードしてください。")
 
     partial_records = []
     raw_texts = []
 
-    for f in files:
-        raw_bytes = f.read()
-        filetype = detect_filetype(f.name, raw_bytes)
+    for path in filepaths:
+        filename = os.path.basename(path)
+        with open(path, "rb") as f:
+            raw_bytes = f.read()
+        filetype = detect_filetype(filename, raw_bytes)
 
         # 1) テキスト抽出：画像/PDFはOpenAI Vision OCR、docx/txtは生文面＋OpenAI整形
         if filetype in {"pdf", "image"}:
-            text = extract_text_with_openai(raw_bytes, filename=f.name, filetype=filetype)
+            text = extract_text_with_openai(raw_bytes, filename=filename, filetype=filetype)
         else:
             base_text = load_doc_text(filetype, raw_bytes)
-            text = extract_text_with_openai(base_text.encode("utf-8"), filename=f.name, filetype="txt")
+            text = extract_text_with_openai(base_text.encode("utf-8"), filename=filename, filetype="txt")
 
-        raw_texts.append({"filename": f.name, "text": text})
+        raw_texts.append({"filename": filename, "text": text})
 
-        # 2) OpenAIでセクション構造化 → ルールベース正規化
+        # 2) OpenAIでセクション構造化 → ルール正規化
         structured = structure_with_openai(text)
         normalized = normalize_resume({
             "work_experience": structured.get("work_experience_raw", ""),
@@ -49,7 +51,7 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
             "skills": ", ".join(structured.get("skills_list", [])),
         })
         partial_records.append({
-            "source": f.name,
+            "source": filename,
             "text": text,
             "structured": structured,
             "normalized": normalized,
@@ -80,7 +82,7 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
     # 8) 構造化出力
     result_json = {
         "candidate_id": candidate_id or hashlib.sha256(merged_text.encode("utf-8")).hexdigest()[:16],
-        "files": [f.name for f in files],
+        "files": [os.path.basename(p) for p in filepaths],
         "merged": merged,
         "skills": skills,
         "quality_score": score,
@@ -89,7 +91,7 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
         "notes": additional_notes,
     }
 
-    # 9) HF Datasets 保存（任意）
+    # 9) HF Datasets 保存
     dataset_repo = os.environ.get("DATASET_REPO")
     commit_info = None
     if dataset_repo:
@@ -105,15 +107,14 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
 
     anon_pdf = (result_json["candidate_id"] + ".anon.pdf", anon_pdf_bytes)
 
-    # ★ dictは全て文字列(JSON)化して返す（gr.JSONは使わない）
     return (
-        json.dumps(result_json, ensure_ascii=False, indent=2),   # 統合JSON（文字列）
-        json.dumps(skills, ensure_ascii=False, indent=2),        # スキル（文字列）
-        json.dumps(score, ensure_ascii=False, indent=2),         # スコア（文字列）
-        summaries.get("300chars", ""),
-        summaries.get("100chars", ""),
-        summaries.get("onesent", ""),
-        anon_pdf,                                                # (filename, bytes)
+        json.dumps(result_json, ensure_ascii=False, indent=2),
+        json.dumps(skills, ensure_ascii=False, indent=2),      # ← Code出力に合わせて文字列化
+        json.dumps(score, ensure_ascii=False, indent=2),
+        summaries["300chars"],
+        summaries["100chars"],
+        summaries["onesent"],
+        anon_pdf,
         json.dumps(commit_info or {"status": "skipped (DATASET_REPO not set)"}, ensure_ascii=False, indent=2),
     )
 
@@ -126,7 +127,7 @@ with gr.Blocks(title=APP_TITLE) as demo:
             label="レジュメ類 (PDF/画像/Word/テキスト) 複数可",
             file_count="multiple",
             file_types=[".pdf", ".png", ".jpg", ".jpeg", ".tiff", ".bmp", ".docx", ".txt"],
-            type="file"
+            type="filepath",  # ← ここが重要（'file' は不可）
         )
         candidate_id = gr.Textbox(label="候補者ID（任意。未入力なら自動生成）")
     notes = gr.Textbox(label="補足メモ（任意）", lines=3)
@@ -137,11 +138,10 @@ with gr.Blocks(title=APP_TITLE) as demo:
         out_json = gr.Code(label="統合出力 (JSON)")
 
     with gr.Tab("抽出スキル"):
-        # ★ gr.JSON は使用しない
-        out_skills = gr.Code(label="スキル一覧 (JSON)")
+        out_skills = gr.Code(label="スキル一覧 (JSON)")  # ← gr.JSON は型推論で落ちやすいので Code に
 
     with gr.Tab("品質スコア"):
-        out_score = gr.Code(label="品質評価 (JSON)")
+        out_score = gr.Code(label="品質評価")
 
     with gr.Tab("要約 (300/100/1文)"):
         out_sum_300 = gr.Textbox(label="300字要約")
@@ -152,7 +152,7 @@ with gr.Blocks(title=APP_TITLE) as demo:
         out_pdf = gr.File(label="匿名PDFダウンロード")
 
     with gr.Tab("Datasets 保存ログ"):
-        out_commit = gr.Code(label="コミット情報 (JSON)")
+        out_commit = gr.Code(label="コミット情報")
 
     run_btn.click(
         process_resumes,
@@ -162,14 +162,4 @@ with gr.Blocks(title=APP_TITLE) as demo:
 
 
 if __name__ == "__main__":
-    # ヘッドレス/プロキシ/コンテナ環境対応
-    server_name = os.getenv("GRADIO_SERVER_NAME", "0.0.0.0")
-    server_port = int(os.getenv("PORT", os.getenv("GRADIO_SERVER_PORT", "7860")))
-    share = os.getenv("GRADIO_SHARE", "false").lower() == "true"
-    demo.launch(
-        server_name=server_name,
-        server_port=server_port,
-        share=share,
-        inbrowser=False,
-        show_error=True,
-    )
+    demo.launch()