Update app.py

app.py

@@ -2,9 +2,7 @@ import os
 import io
 import json
 import hashlib
-import gradio  # 一部の前方参照バグ回避用
 import gradio as gr
-from typing import List
 
 from pipelines.openai_ingest import (
     extract_text_with_openai,
@@ -14,43 +12,7 @@ from pipelines.openai_ingest import (
 from pipelines.parsing import normalize_resume
 from pipelines.merge import merge_normalized_records
 from pipelines.skills import extract_skills
-
-# --- 匿名化のフォールバック（pipelines/anonymize.py が空/未実装でも動く） ---
-try:
-    from pipelines.anonymize import anonymize_text, render_anonymized_pdf  # type: ignore
-except Exception:
-    import re
-    try:
-        from reportlab.pdfgen import canvas
-        from reportlab.lib.pagesizes import A4
-    except Exception:
-        canvas = None
-        A4 = None
-
-    def anonymize_text(text: str):
-        masked = re.sub(r"([A-Za-z0-9._%+-]+)@([A-Za-z0-9.-]+\.[A-Za-z]{2,})", r"***@\2", text)
-        masked = re.sub(r"(?:\+?\d{1,3}[ -]?)?(?:\(\d{2,4}\)[ -]?)?\d{2,4}[ -]?\d{2,4}[ -]?\d{3,4}", "***-****-****", masked)
-        masked = re.sub(r"(氏名[:：]?\s*)(\S+)", r"\1＊＊＊", masked)
-        return masked, {"fallback": True}
-
-    def render_anonymized_pdf(text: str) -> bytes:
-        if canvas is None:
-            return text.encode("utf-8")
-        buf = io.BytesIO()
-        c = canvas.Canvas(buf, pagesize=A4)
-        width, height = A4
-        m = 40
-        y = height - m
-        for line in text.splitlines() or ["(no content)"]:
-            if y < m:
-                c.showPage()
-                y = height - m
-            c.drawString(m, y, line[:95])
-            y -= 14
-        c.save()
-        return buf.getvalue()
-# ----------------------------------------------------------------------
-
+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
@@ -58,34 +20,26 @@ 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 _read_bytes(path: str) -> bytes:
-    with open(path, "rb") as f:
-        return f.read()
-
-
-def process_resumes(files: List[str], candidate_id: str = "", additional_notes: str = ""):
-    """
-    files: gr.Files(type='filepath') から渡るファイルパスのリスト
-    """
+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。")
 
     partial_records = []
     raw_texts = []
 
-    for path in files:
-        filename = os.path.basename(path)
-        raw_bytes = _read_bytes(path)
-        filetype = detect_filetype(filename, raw_bytes)
+    for p in files:  # gr.Files(type="filepath") でパスが来る
+        raw_bytes = open(p, "rb").read()
+        fname = os.path.basename(p)
+        filetype = detect_filetype(fname, raw_bytes)
 
-        # 1) 抽出
+        # 1) テキスト抽出
         if filetype in {"pdf", "image"}:
-            text = extract_text_with_openai(raw_bytes, filename=filename, 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=filename, filetype="txt")
+            text = extract_text_with_openai(base_text.encode("utf-8"), filename=fname, filetype="txt")
 
-        raw_texts.append({"filename": filename, "text": text})
+        raw_texts.append({"filename": fname, "text": text})
 
         # 2) 構造化→正規化
         structured = structure_with_openai(text)
@@ -96,7 +50,7 @@ def process_resumes(files: List[str], candidate_id: str = "", additional_notes:
             "skills": ", ".join(structured.get("skills_list", [])),
         })
         partial_records.append({
-            "source": filename,
+            "source": fname,
             "text": text,
             "structured": structured,
             "normalized": normalized,
@@ -124,7 +78,7 @@ def process_resumes(files: List[str], candidate_id: str = "", additional_notes:
     # 7) 要約
     summaries = summarize_with_openai(merged_text)
 
-    # 8) 出力まとめ
+    # 8) 構造化出力
     cid = candidate_id or hashlib.sha256(merged_text.encode("utf-8")).hexdigest()[:16]
     result_json = {
         "candidate_id": cid,
@@ -152,21 +106,16 @@ def process_resumes(files: List[str], candidate_id: str = "", additional_notes:
 
     anon_pdf = (f"{cid}.anon.pdf", anon_pdf_bytes)
 
-    # ★ UI用：すべて文字列化して返す（gr.JSON を使わない）
-    out_json_str = json.dumps(result_json, ensure_ascii=False, indent=2)
-    out_skills_str = json.dumps(skills, ensure_ascii=False, indent=2)
-    out_score_str = json.dumps(score, ensure_ascii=False, indent=2)
-    out_commit_str = json.dumps(commit_info or {"status": "skipped (DATASET_REPO not set)"}, ensure_ascii=False, indent=2)
-
+    # UI には全て文字列（JSONダンプ）で返す
     return (
-        out_json_str,
-        out_skills_str,
-        out_score_str,
+        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", ""),
         anon_pdf,
-        out_commit_str,
+        json.dumps(commit_info or {"status": "skipped (DATASET_REPO not set)"}, ensure_ascii=False, indent=2),
     )
 
 
@@ -178,7 +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：'file' ではなく 'filepath'
+            type="filepath",  # ←重要
         )
         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)
@@ -189,7 +138,7 @@ 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 を避ける
+        out_skills = gr.Code(label="スキル一覧 (JSON)")  # ← gr.JSON を使わない
 
     with gr.Tab("品質スコア"):
         out_score = gr.Code(label="品質評価 (JSON)")
@@ -212,6 +161,6 @@ with gr.Blocks(title=APP_TITLE) as demo:
         api_name="run",
     )
 
+
 if __name__ == "__main__":
-    # 到達性のため share=True 推奨
     demo.launch(server_name="0.0.0.0", server_port=7860, share=True)