Update app.py

app.py

@@ -1,5 +1,4 @@
 import os
-import io
 import json
 import hashlib
 import gradio as gr
@@ -27,12 +26,15 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
     partial_records = []
     raw_texts = []
 
-    for p in files:  # gr.Files(type="filepath") でパスが来る
-        raw_bytes = open(p, "rb").read()
+    # gr.Files(type="filepath") を前提に、パスで受け取り→自前で read
+    for p in files:
         fname = os.path.basename(p)
+        with open(p, "rb") as fh:
+            raw_bytes = fh.read()
+
         filetype = detect_filetype(fname, raw_bytes)
 
-        # 1) テキスト抽出
+        # 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=fname, filetype=filetype)
         else:
@@ -41,7 +43,7 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
 
         raw_texts.append({"filename": fname, "text": text})
 
-        # 2) 構造化→正規化
+        # 2) OpenAIでセクション構造化 → ルールベース正規化も適用
         structured = structure_with_openai(text)
         normalized = normalize_resume({
             "work_experience": structured.get("work_experience_raw", ""),
@@ -56,10 +58,10 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
             "normalized": normalized,
         })
 
-    # 3) 統合
+    # 3) 統合（複数ファイル→1候補者）
     merged = merge_normalized_records([r["normalized"] for r in partial_records])
 
-    # 4) スキル抽出
+    # 4) スキル抽出（辞書/正規表現）
     merged_text = "\n\n".join([r["text"] for r in partial_records])
     skills = extract_skills(merged_text, {
         "work_experience": merged.get("raw_sections", {}).get("work_experience", ""),
@@ -75,13 +77,12 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
     # 6) 品質スコア
     score = compute_quality_score(merged_text, merged)
 
-    # 7) 要約
+    # 7) 要約（300/100/1文）
     summaries = summarize_with_openai(merged_text)
 
     # 8) 構造化出力
-    cid = candidate_id or hashlib.sha256(merged_text.encode("utf-8")).hexdigest()[:16]
     result_json = {
-        "candidate_id": cid,
+        "candidate_id": candidate_id or hashlib.sha256(merged_text.encode("utf-8")).hexdigest()[:16],
         "files": [os.path.basename(p) for p in files],
         "merged": merged,
         "skills": skills,
@@ -91,22 +92,23 @@ 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:
+        file_hash = result_json["candidate_id"]
         commit_info = persist_to_hf(
             dataset_repo=dataset_repo,
             record=result_json,
             anon_pdf_bytes=anon_pdf_bytes,
-            parquet_path=f"candidates/{cid}.parquet",
-            json_path=f"candidates/{cid}.json",
-            pdf_path=f"candidates/{cid}.anon.pdf",
+            parquet_path=f"candidates/{file_hash}.parquet",
+            json_path=f"candidates/{file_hash}.json",
+            pdf_path=f"candidates/{file_hash}.anon.pdf",
         )
 
-    anon_pdf = (f"{cid}.anon.pdf", anon_pdf_bytes)
+    anon_pdf = (result_json["candidate_id"] + ".anon.pdf", anon_pdf_bytes)
 
-    # UI には全て文字列（JSONダンプ）で返す
+    # dict を gr.Code で安全表示するため、文字列化して返す
     return (
         json.dumps(result_json, ensure_ascii=False, indent=2),
         json.dumps(skills, ensure_ascii=False, indent=2),
@@ -127,7 +129,7 @@ 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="filepath",  # ←重要
+            type="filepath",  # ← 重要：パスで受け取る
         )
         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)
@@ -138,7 +140,7 @@ 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"):
-        out_skills = gr.Code(label="スキル一覧 (JSON)")  # ← gr.JSON を使わない
+        out_skills = gr.Code(label="スキル一覧 (JSON)")  # ← gr.JSON をやめて文字列表示
 
     with gr.Tab("品質スコア"):
         out_score = gr.Code(label="品質評価 (JSON)")
@@ -152,15 +154,14 @@ 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(
-        fn=process_resumes,
+        process_resumes,
         inputs=[in_files, candidate_id, notes],
         outputs=[out_json, out_skills, out_score, out_sum_300, out_sum_100, out_sum_1, out_pdf, out_commit],
-        api_name="run",
     )
 
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860, share=True)
+    demo.launch()