完善附件管理与生成任务跟踪

backend/services/file_summary.py

@@ -1,6 +1,8 @@
 import csv
 import io
 import json
+import subprocess
+import tempfile
 from pathlib import Path
 
 import pandas as pd
@@ -38,7 +40,10 @@ def _summarize_csv(content: bytes) -> str:
 
 def _summarize_excel(content: bytes, suffix: str) -> str:
     excel_buffer = io.BytesIO(content)
-    sheet_map = pd.read_excel(excel_buffer, sheet_name=None) if suffix == ".xlsx" else pd.read_excel(excel_buffer, sheet_name=None, engine="xlrd")
+    if suffix in {".xlsx", ".xlsm"}:
+        sheet_map = pd.read_excel(excel_buffer, sheet_name=None)
+    else:
+        sheet_map = pd.read_excel(excel_buffer, sheet_name=None, engine="xlrd")
     parts: list[str] = []
     for sheet_name, dataframe in list(sheet_map.items())[:5]:
         preview = dataframe.head(10).fillna("").astype(str)
@@ -47,6 +52,21 @@ def _summarize_excel(content: bytes, suffix: str) -> str:
     return "\n".join(parts)[:5000]
 
 
+def _summarize_doc(content: bytes) -> str:
+    with tempfile.NamedTemporaryFile(suffix=".doc") as temp_file:
+        temp_file.write(content)
+        temp_file.flush()
+        result = subprocess.run(
+            ["textutil", "-convert", "txt", "-stdout", temp_file.name],
+            capture_output=True,
+            check=False,
+        )
+    if result.returncode != 0:
+        stderr = result.stderr.decode("utf-8", errors="ignore").strip()
+        return f"旧版 Word 文件解析失败：{stderr or 'textutil 无法提取正文'}"
+    return _decode_text(result.stdout)[:4000]
+
+
 def _summarize_pdf(content: bytes) -> str:
     if PdfReader is None:
         return "当前环境未安装 PDF 文本解析依赖，无法提取 PDF 正文。"
@@ -68,18 +88,18 @@ def summarize_file_bytes(file_name: str, content: bytes) -> str:
     if suffix == ".docx":
         return _summarize_docx(content)
     if suffix == ".doc":
-        return "当前暂不支持直接解析 .doc 旧版 Word 文件正文，建议先另存为 .docx 后再上传。"
+        return _summarize_doc(content)
     if suffix == ".pdf":
         return _summarize_pdf(content)
     return f"暂不支持解析该文件内容：{file_name}"
 
 
-def summarize_minio_files(file_paths: list[str]) -> list[dict]:
+def summarize_minio_files(file_paths: list[str], file_name_mapping: dict[str, str] | None = None) -> list[dict]:
     summaries: list[dict] = []
     for file_path in file_paths:
         bucket, object_name = split_bucket_path(file_path)
         content = download_object_bytes(bucket, object_name)
-        file_name = Path(object_name).name
+        file_name = (file_name_mapping or {}).get(file_path) or Path(object_name).name
         summaries.append(
             {
                 "file_name": file_name,