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,

backend/services/generation_runtime.py

@@ -12,6 +12,7 @@ from models.generation_log import GenerationLog
 from models.paragraph import Paragraph
 from models.template import Template
 from services.ai_service import call_ai
+from services.file_summary import summarize_minio_files
 
 generation_progress: dict[int, dict] = {}
 generation_cancel_flags: dict[int, bool] = {}
@@ -90,6 +91,13 @@ async def run_generation(document_id: int, template_id: int):
         )
         paragraphs = result.scalars().all()
         total = len(paragraphs)
+        request_payload = {}
+        if document.request_payload_json:
+            try:
+                request_payload = json.loads(document.request_payload_json)
+            except Exception:
+                request_payload = {}
+        file_map = request_payload.get("file_map", {}) if isinstance(request_payload, dict) else {}
         update_progress(document_id, status="generating", total=total, done=0, percent=0, message="开始生成...")
 
         done_count = 0
@@ -114,11 +122,25 @@ async def run_generation(document_id: int, template_id: int):
                     model = await get_effective_model(paragraph)
                     model_id = model.id if model is not None else paragraph.model_id
                     try:
+                        selected_file_paths = file_map.get(str(paragraph.id), [])
+                        file_summaries = []
+                        if selected_file_paths:
+                            file_name_mapping = {}
+                            for paragraph_item in request_payload.get("paragraphs", []):
+                                for selected_file in paragraph_item.get("selected_files", []):
+                                    file_path = selected_file.get("file_path")
+                                    if file_path in selected_file_paths:
+                                        file_name_mapping[file_path] = selected_file.get("file_name")
+                            file_summaries = await asyncio.to_thread(
+                                summarize_minio_files,
+                                selected_file_paths,
+                                file_name_mapping,
+                            )
                         if model is None:
                             content = build_mock_content(paragraph)
                         else:
                             setattr(paragraph, "enable_reasoning", bool(model.enable_reasoning))
-                            result_data = await call_ai(paragraph, model)
+                            result_data = await call_ai(paragraph, model, file_summaries)
                             content = result_data.content
                         status = "success"
                         error_message = ""

backend/services/minio_client.py

@@ -68,3 +68,7 @@ def upload_bytes(
         len(content),
         content_type=content_type,
     )
+
+
+def delete_object(bucket: str, object_name: str):
+    minio_client.remove_object(bucket, object_name)