增强 Word 文档 AI 解析和模板填充功能

backend/app/api/endpoints/ai_analyze.py

@@ -10,6 +10,7 @@ import os
 
 from app.services.excel_ai_service import excel_ai_service
 from app.services.markdown_ai_service import markdown_ai_service
+from app.services.template_fill_service import template_fill_service
 from app.services.word_ai_service import word_ai_service
 
 logger = logging.getLogger(__name__)
@@ -343,6 +344,77 @@ async def get_markdown_outline(
         raise HTTPException(status_code=500, detail=f"获取大纲失败: {str(e)}")
 
 
+@router.post("/analyze/txt")
+async def analyze_txt(
+    file: UploadFile = File(...),
+):
+    """
+    上传并使用 AI 分析 TXT 文本文件，提取结构化数据
+
+    将非结构化文本转换为结构化表格数据，便于后续填表使用
+
+    Args:
+        file: 上传的 TXT 文件
+
+    Returns:
+        dict: 分析结果，包含结构化表格数据
+    """
+    if not file.filename:
+        raise HTTPException(status_code=400, detail="文件名为空")
+
+    file_ext = file.filename.split('.')[-1].lower()
+    if file_ext not in ['txt', 'text']:
+        raise HTTPException(
+            status_code=400,
+            detail=f"不支持的文件类型: {file_ext}，仅支持 .txt"
+        )
+
+    try:
+        # 读取文件内容
+        content = await file.read()
+
+        # 保存到临时文件
+        with tempfile.NamedTemporaryFile(mode='wb', suffix='.txt', delete=False) as tmp:
+            tmp.write(content)
+            tmp_path = tmp.name
+
+        try:
+            logger.info(f"开始 AI 分析 TXT 文件: {file.filename}")
+
+            # 使用 template_fill_service 的 AI 分析方法
+            result = await template_fill_service.analyze_txt_with_ai(
+                content=content.decode('utf-8', errors='replace'),
+                filename=file.filename
+            )
+
+            if result:
+                logger.info(f"TXT AI 分析成功: {file.filename}")
+                return {
+                    "success": True,
+                    "filename": file.filename,
+                    "structured_data": result
+                }
+            else:
+                logger.warning(f"TXT AI 分析返回空结果: {file.filename}")
+                return {
+                    "success": False,
+                    "filename": file.filename,
+                    "error": "AI 分析未能提取到结构化数据",
+                    "structured_data": None
+                }
+
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"TXT AI 分析过程中出错: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"分析失败: {str(e)}")
+
+
 # ==================== Word 文档 AI 解析 ====================
 
 @router.post("/analyze/word")
@@ -373,98 +445,41 @@ async def analyze_word(
         )
 
     try:
+        # 保存上传的文件
         content = await file.read()
-
-        # 保存到临时文件
-        with tempfile.NamedTemporaryFile(mode='wb', suffix='.docx', delete=False) as tmp:
+        suffix = f".{file_ext}"
+        with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as tmp:
             tmp.write(content)
             tmp_path = tmp.name
 
         try:
-            logger.info(f"开始 AI 解析 Word 文件: {file.filename}")
-
+            # 使用 AI 解析 Word 文档
             result = await word_ai_service.parse_word_with_ai(
                 file_path=tmp_path,
-                user_hint=user_hint
+                user_hint=user_hint or "请提取文档中的所有结构化数据，包括表格、键值对等"
             )
 
-            logger.info(f"Word AI 解析完成: {file.filename}, success={result.get('success')}")
-
-            return result
+            if result.get("success"):
+                return {
+                    "success": True,
+                    "filename": file.filename,
+                    "result": result
+                }
+            else:
+                return {
+                    "success": False,
+                    "filename": file.filename,
+                    "error": result.get("error", "AI 解析失败"),
+                    "result": None
+                }
 
         finally:
+            # 清理临时文件
             if os.path.exists(tmp_path):
                 os.unlink(tmp_path)
 
     except HTTPException:
         raise
     except Exception as e:
-        logger.error(f"Word AI 解析出错: {str(e)}")
-        raise HTTPException(status_code=500, detail=f"AI 解析失败: {str(e)}")
-
-
-@router.post("/analyze/word/fill-template")
-async def fill_template_with_word_ai(
-    file: UploadFile = File(...),
-    template_fields: str = Query("", description="模板字段，JSON字符串"),
-    user_hint: str = Query("", description="用户提示词")
-):
-    """
-    使用 AI 解析 Word 文档并填写模板
-
-    前端调用此接口即可完成：AI解析 + 填表
-
-    Args:
-        file: 上传的 Word 文件
-        template_fields: 模板字段 JSON 字符串
-        user_hint: 用户提示词
-
-    Returns:
-        dict: 填写结果
-    """
-    if not file.filename:
-        raise HTTPException(status_code=400, detail="文件名为空")
-
-    file_ext = file.filename.split('.')[-1].lower()
-    if file_ext not in ['docx']:
-        raise HTTPException(
-            status_code=400,
-            detail=f"不支持的文件类型: {file_ext}，仅支持 .docx"
-        )
-
-    try:
-        import json as json_module
-        fields = json_module.loads(template_fields) if template_fields else []
-    except json_module.JSONDecodeError:
-        raise HTTPException(status_code=400, detail="template_fields 格式错误，应为 JSON 数组")
-
-    try:
-        content = await file.read()
-
-        # 保存到临时文件
-        with tempfile.NamedTemporaryFile(mode='wb', suffix='.docx', delete=False) as tmp:
-            tmp.write(content)
-            tmp_path = tmp.name
-
-        try:
-            logger.info(f"开始 AI 填表（Word）: {file.filename}, 字段数: {len(fields)}")
-
-            result = await word_ai_service.fill_template_with_ai(
-                file_path=tmp_path,
-                template_fields=fields,
-                user_hint=user_hint
-            )
-
-            logger.info(f"Word AI 填表完成: {file.filename}, success={result.get('success')}")
-
-            return result
-
-        finally:
-            if os.path.exists(tmp_path):
-                os.unlink(tmp_path)
-
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f"Word AI 填表出错: {str(e)}")
-        raise HTTPException(status_code=500, detail=f"AI 填表失败: {str(e)}")
+        logger.error(f"Word AI 分析过程中出错: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"分析失败: {str(e)}")

backend/app/main.py

@@ -1,6 +1,13 @@
 """
 FastAPI 应用主入口
 """
+# ========== 压制 MongoDB 疯狂刷屏日志 ==========
+import logging
+logging.getLogger("pymongo").setLevel(logging.WARNING)
+logging.getLogger("pymongo.topology").setLevel(logging.WARNING)
+logging.getLogger("urllib3").setLevel(logging.WARNING)
+# ==============================================
+
 import logging
 import logging.handlers
 import sys

frontend/src/db/backend-api.ts

@@ -1239,6 +1239,48 @@ export const aiApi = {
     }
   },
 
+  /**
+   * 上传并使用 AI 分析 TXT 文本文件，提取结构化数据
+   */
+  async analyzeTxt(
+    file: File
+  ): Promise<{
+    success: boolean;
+    filename?: string;
+    structured_data?: {
+      table?: {
+        columns?: string[];
+        rows?: string[][];
+      };
+      summary?: string;
+      key_value_pairs?: Array<{ key: string; value: string }>;
+      numeric_data?: Array<{ name: string; value: number; unit?: string }>;
+    };
+    error?: string;
+  }> {
+    const formData = new FormData();
+    formData.append('file', file);
+
+    const url = `${BACKEND_BASE_URL}/ai/analyze/txt`;
+
+    try {
+      const response = await fetch(url, {
+        method: 'POST',
+        body: formData,
+      });
+
+      if (!response.ok) {
+        const error = await response.json();
+        throw new Error(error.detail || 'TXT AI 分析失败');
+      }
+
+      return await response.json();
+    } catch (error) {
+      console.error('TXT AI 分析失败:', error);
+      throw error;
+    }
+  },
+
   /**
    * 生成统计信息和图表
    */