完善模板测试弹窗与多文件解析链路

backend/requirements.txt

@@ -7,6 +7,7 @@ cryptography>=42.0.0
 python-docx>=1.1.0
 openpyxl>=3.1.0
 pandas>=2.1.0
+xlrd>=2.0.1
 httpx>=0.27.0
 pydantic>=2.5.0
 pydantic-settings>=2.1.0
@@ -15,3 +16,4 @@ aiofiles>=23.2.0
 sse-starlette>=2.0.0
 minio>=7.2.0                             # MinIO 对象存储 SDK
 alembic>=1.13.0
+pypdf>=5.0.0

backend/routers/generate.py

@@ -1,3 +1,4 @@
+import asyncio
 import json
 import os
 import uuid
@@ -17,6 +18,7 @@ from models.paragraph import Paragraph
 from models.template import Template
 from schemas.schemas import GenerateFullRequest, GenerateTestRequest, Response
 from services.ai_service import call_ai
+from services.file_summary import summarize_minio_files
 from services.generation_runtime import (
     build_mock_content,
     generation_progress,
@@ -48,6 +50,8 @@ async def generate_test(body: GenerateTestRequest, db: AsyncSession = Depends(ge
     paragraph = await db.get(Paragraph, body.paragraph_id)
     if paragraph is None or paragraph.template_id != body.template_id:
         raise HTTPException(status_code=404, detail="段落不存在")
+    if body.prompt_text:
+        paragraph.prompt_text = body.prompt_text
 
     model = None
     if body.model_id:
@@ -55,11 +59,12 @@ async def generate_test(body: GenerateTestRequest, db: AsyncSession = Depends(ge
     elif paragraph.model_id:
         model = await db.get(AiModel, paragraph.model_id)
 
+    file_summaries = await asyncio.to_thread(summarize_minio_files, body.file_paths or []) if body.file_paths else []
     if model is None or model.status != "enabled":
         content = build_mock_content(paragraph)
         message = "当前未找到可用模型，返回本地模拟生成结果。"
     else:
-        result = await call_ai(paragraph, model)
+        result = await call_ai(paragraph, model, file_summaries)
         content = result.content
         message = f"已通过模型 {result.used_model} 生成。"
     return Response(
@@ -67,6 +72,7 @@ async def generate_test(body: GenerateTestRequest, db: AsyncSession = Depends(ge
             "paragraph_id": paragraph.id,
             "content": content,
             "message": message,
+            "file_summaries": file_summaries,
         }
     )
 

backend/services/ai_service.py

@@ -43,7 +43,7 @@ def _ensure_json_content(text: str) -> dict:
     return {"content": [{"type": "text", "text": stripped}]}
 
 
-def _build_prompt(paragraph: Paragraph) -> tuple[str, str]:
+def _build_prompt(paragraph: Paragraph, file_summaries: list[dict] | None = None) -> tuple[str, str]:
     system_prompt = (
         "你是一个企业文档撰写助手。"
         "请严格输出 JSON，不要输出 JSON 之外的说明。"
@@ -55,6 +55,11 @@ def _build_prompt(paragraph: Paragraph) -> tuple[str, str]:
         user_parts.append(f"模板上下文：{paragraph.content}")
     if paragraph.need_prompt and paragraph.prompt_text:
         user_parts.append(f"附加要求：{paragraph.prompt_text}")
+    if file_summaries:
+        file_blocks = []
+        for item in file_summaries:
+            file_blocks.append(f"文件名：{item['file_name']}\n文件摘要：{item['summary']}")
+        user_parts.append("参考文件内容：\n" + "\n\n".join(file_blocks))
     user_parts.append(f"输出格式：{paragraph.output_format}")
     return system_prompt, "\n\n".join(user_parts)
 
@@ -157,8 +162,8 @@ async def _call_anthropic(model: AiModel, system_prompt: str, user_prompt: str)
     return AiCallResult(content=_ensure_json_content(text), raw_text=text, used_model=model.name)
 
 
-async def call_ai(paragraph: Paragraph, model: AiModel) -> AiCallResult:
-    system_prompt, user_prompt = _build_prompt(paragraph)
+async def call_ai(paragraph: Paragraph, model: AiModel, file_summaries: list[dict] | None = None) -> AiCallResult:
+    system_prompt, user_prompt = _build_prompt(paragraph, file_summaries)
     if model.api_format == "anthropic":
         return await _call_anthropic(model, system_prompt, user_prompt)
     return await _call_openai_compatible(model, system_prompt, user_prompt)

backend/services/file_summary.py

@@ -0,0 +1,88 @@
+import csv
+import io
+import json
+from pathlib import Path
+
+import pandas as pd
+from docx import Document
+
+from services.minio_client import download_object_bytes, split_bucket_path
+
+try:
+    from pypdf import PdfReader
+except Exception:  # pragma: no cover
+    PdfReader = None
+
+
+def _decode_text(content: bytes) -> str:
+    for encoding in ("utf-8", "utf-8-sig", "gbk", "gb18030"):
+        try:
+            return content.decode(encoding)
+        except Exception:
+            continue
+    return content.decode("utf-8", errors="ignore")
+
+
+def _summarize_docx(content: bytes) -> str:
+    doc = Document(io.BytesIO(content))
+    texts = [paragraph.text.strip() for paragraph in doc.paragraphs if paragraph.text.strip()]
+    return "\n".join(texts[:40])[:4000]
+
+
+def _summarize_csv(content: bytes) -> str:
+    text = _decode_text(content)
+    reader = csv.reader(io.StringIO(text))
+    rows = list(reader[:20])
+    return "\n".join([" | ".join(row) for row in rows])[:4000]
+
+
+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")
+    parts: list[str] = []
+    for sheet_name, dataframe in list(sheet_map.items())[:5]:
+        preview = dataframe.head(10).fillna("").astype(str)
+        parts.append(f"[工作表] {sheet_name}")
+        parts.append(preview.to_csv(index=False).strip())
+    return "\n".join(parts)[:5000]
+
+
+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。"
+    reader = PdfReader(io.BytesIO(content))
+    texts: list[str] = []
+    for page in reader.pages[:10]:
+        texts.append((page.extract_text() or "").strip())
+    return "\n".join(filter(None, texts))[:4000]
+
+
+def summarize_file_bytes(file_name: str, content: bytes) -> str:
+    suffix = Path(file_name).suffix.lower()
+    if suffix in {".txt", ".md", ".json"}:
+        return _decode_text(content)[:4000]
+    if suffix == ".csv":
+        return _summarize_csv(content)
+    if suffix in {".xlsx", ".xls"}:
+        return _summarize_excel(content, suffix)
+    if suffix == ".docx":
+        return _summarize_docx(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]:
+    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
+        summaries.append(
+            {
+                "file_name": file_name,
+                "file_path": file_path,
+                "summary": summarize_file_bytes(file_name, content),
+            }
+        )
+    return summaries