Update app.py

app.py

@@ -1,25 +1,20 @@
-import os
-import io
-import json
-import hashlib
-import gradio as gr
-
-from pipelines.openai_ingest import (
-    extract_text_with_openai,
-    structure_with_openai,
-    summarize_with_openai,
-)
-from pipelines.parsing import normalize_resume
-from pipelines.merge import merge_normalized_records
-from pipelines.skills import extract_skills
-from pipelines.anonymize import anonymize_text, render_anonymized_pdf
-from pipelines.scoring import compute_quality_score
-from pipelines.storage import persist_to_hf
-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）"
+# --- 変更1: Files の type を "filepath" にし、ハンドラをファイルパス対応へ ---
+with gr.Row():
+    in_files = gr.Files(
+        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",  # ← "file" から修正
+    )
+    candidate_id = gr.Textbox(label="候補者ID（任意。未入力なら自動生成）")
+
+
+# --- 変更2: out_skills は schema 周りの不具合回避のため JSON → Code に ---
+with gr.Tab("抽出スキル"):
+    out_skills = gr.Code(label="スキル一覧(JSON)")  # ← gr.JSON から修正
 
 
+# --- 変更3: ハンドラの files 取り扱いを「パス」前提に修正 ---
 def process_resumes(files, candidate_id: str, additional_notes: str = ""):
     if not files:
         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。")
@@ -27,18 +22,21 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
     partial_records = []
     raw_texts = []
 
-    for f in files:
-        raw_bytes = f.read()
-        filetype = detect_filetype(f.name, raw_bytes)
+    for path in files:  # ← UploadedFile ではなく filepath の配列
+        with open(path, "rb") as fh:
+            raw_bytes = fh.read()
+        fname = os.path.basename(path)
+
+        filetype = detect_filetype(fname, raw_bytes)
 
         # 1) テキスト抽出
         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=fname, 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=fname, filetype="txt")
 
-        raw_texts.append({"filename": f.name, "text": text})
+        raw_texts.append({"filename": fname, "text": text})
 
         # 2) 構造化
         structured = structure_with_openai(text)
@@ -49,38 +47,18 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
             "skills": ", ".join(structured.get("skills_list", [])),
         })
         partial_records.append({
-            "source": f.name,
+            "source": fname,
             "text": text,
             "structured": structured,
             "normalized": normalized,
         })
 
-    # 3) 統合
-    merged = merge_normalized_records([r["normalized"] for r in partial_records])
-
-    # 4) スキル抽出
-    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", ""),
-        "education": merged.get("raw_sections", {}).get("education", ""),
-        "certifications": merged.get("raw_sections", {}).get("certifications", ""),
-        "skills": ", ".join(merged.get("skills", [])),
-    })
-
-    # 5) 匿名化
-    anonymized_text, anon_map = anonymize_text(merged_text)
-    anon_pdf_bytes = render_anonymized_pdf(anonymized_text)
-
-    # 6) 品質スコア
-    score = compute_quality_score(merged_text, merged)
-
-    # 7) 要約
-    summaries = summarize_with_openai(merged_text)
+    # ...（中略：ロジックはそのまま）...
 
     # 8) まとめ
     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 files],  # ← fname 配列へ
         "merged": merged,
         "skills": skills,
         "quality_score": score,
@@ -89,25 +67,12 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
         "notes": additional_notes,
     }
 
-    # 9) HF Datasets 保存（任意）
-    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/{file_hash}.parquet",
-            json_path=f"candidates/{file_hash}.json",
-            pdf_path=f"candidates/{file_hash}.anon.pdf",
-        )
-
-    anon_pdf = (result_json["candidate_id"] + ".anon.pdf", anon_pdf_bytes)
+    # ...（Datasets 保存処理はそのまま）...
 
+    # 返り値：out_skills を Code にしたので JSON 文字列で返す
     return (
         json.dumps(result_json, ensure_ascii=False, indent=2),
-        json.dumps(skills, ensure_ascii=False, indent=2),
+        json.dumps(skills, ensure_ascii=False, indent=2),  # ← 文字列化
         json.dumps(score, ensure_ascii=False, indent=2),
         summaries["300chars"],
         summaries["100chars"],
@@ -117,49 +82,6 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
     )
 
 
-with gr.Blocks(title=APP_TITLE) as demo:
-    gr.Markdown(f"# {APP_TITLE}\n複数ファイルを統合→OpenAIで読み込み/構造化/要約→匿名化→Datasets保存")
-
-    with gr.Row():
-        in_files = gr.Files(
-            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"
-        )
-        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)
-
-    run_btn = gr.Button("実行")
-
-    with gr.Tab("構造化JSON"):
-        out_json = gr.Code(label="統合出力 (JSON)")
-
-    with gr.Tab("抽出スキル"):
-        # Gradio 4.44.0 の schema まわりを避けるため JSON 表示は Code に
-        out_skills = gr.Code(label="スキル一覧(JSON)")
-
-    with gr.Tab("品質スコア"):
-        out_score = gr.Code(label="品質評価(JSON)")
-
-    with gr.Tab("要約 (300/100/1文)"):
-        out_sum_300 = gr.Textbox(label="300字要約")
-        out_sum_100 = gr.Textbox(label="100字要約")
-        out_sum_1 = gr.Textbox(label="1文要約")
-
-    with gr.Tab("匿名PDF"):
-        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)")
-
-    run_btn.click(
-        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],
-    )
-
-
+# --- 変更4: HF Spaces での起動を安定させるため launch の引数を明示 ---
 if __name__ == "__main__":
-    # HF Spaces での公開実行（localhost アクセス不可対策）
     demo.launch(server_name="0.0.0.0", server_port=7860)