Update app.py

app.py

@@ -1,4 +1,5 @@
 import os
+import io
 import json
 import hashlib
 import gradio as gr
@@ -26,25 +27,23 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
     partial_records = []
     raw_texts = []
 
-    # 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)
+    for f in files:
+        raw_bytes = f.read()
+        filetype = detect_filetype(f.name, 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=fname, filetype=filetype)
+            text = extract_text_with_openai(raw_bytes, filename=f.name, filetype=filetype)
         else:
             base_text = load_doc_text(filetype, raw_bytes)
-            text = extract_text_with_openai(base_text.encode("utf-8"), filename=fname, filetype="txt")
+            # 生テキストをそのままOpenAIへ渡し、軽く整形した全文を返す
+            text = extract_text_with_openai(base_text.encode("utf-8"), filename=f.name, filetype="txt")
 
-        raw_texts.append({"filename": fname, "text": text})
+        raw_texts.append({"filename": f.name, "text": text})
 
-        # 2) OpenAIでセクション構造化 → ルールベース正規化も適用
+        # 2) OpenAIでセクション構造化
         structured = structure_with_openai(text)
+        # 念のためルールベース正規化も適用（期間抽出など補助）
         normalized = normalize_resume({
             "work_experience": structured.get("work_experience_raw", ""),
             "education": structured.get("education_raw", ""),
@@ -52,7 +51,7 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
             "skills": ", ".join(structured.get("skills_list", [])),
         })
         partial_records.append({
-            "source": fname,
+            "source": f.name,
             "text": text,
             "structured": structured,
             "normalized": normalized,
@@ -83,7 +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": [os.path.basename(p) for p in files],
+        "files": [f.name for f in files],
         "merged": merged,
         "skills": skills,
         "quality_score": score,
@@ -108,14 +107,13 @@ def process_resumes(files, candidate_id: str, additional_notes: str = ""):
 
     anon_pdf = (result_json["candidate_id"] + ".anon.pdf", anon_pdf_bytes)
 
-    # 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),
-        json.dumps(score, ensure_ascii=False, indent=2),
-        summaries.get("300chars", ""),
-        summaries.get("100chars", ""),
-        summaries.get("onesent", ""),
+        json.dumps(result_json, ensure_ascii=False, indent=2),                 # out_json（Codeへ文字列）
+        json.dumps(skills, ensure_ascii=False, indent=2),                      # ★ JSON→Code: ここを文字列で返す
+        json.dumps(score, ensure_ascii=False, indent=2),                       # out_score（Codeへ文字列）
+        summaries["300chars"],
+        summaries["100chars"],
+        summaries["onesent"],
         anon_pdf,
         json.dumps(commit_info or {"status": "skipped (DATASET_REPO not set)"}, ensure_ascii=False, indent=2),
     )
@@ -129,7 +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="filepath",  # ← 重要：パスで受け取る
+            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)
@@ -140,10 +138,11 @@ 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 をやめて文字列表示
+        # ★ GradioのJSONスキーマ推論バグ回避のため Code に変更
+        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)")
+        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")
@@ -164,4 +163,5 @@ with gr.Blocks(title=APP_TITLE) as demo:
 
 
 if __name__ == "__main__":
-    demo.launch()
+    # ★ ローカル未到達環境での ValueError 回避（Space でも安全）
+    demo.launch(share=True, server_name="0.0.0.0", server_port=7860)