前后端基本架构和完全excel表的解析及统计图表的生成以及excel表的到出

backend/app/api/__init__.py

@@ -0,0 +1,14 @@
+"""
+API 路由注册模块
+"""
+from fastapi import APIRouter
+from app.api.endpoints import upload, ai_analyze, visualization, analysis_charts
+
+# 创建主路由
+api_router = APIRouter()
+
+# 注册各模块路由
+api_router.include_router(upload.router)
+api_router.include_router(ai_analyze.router)
+api_router.include_router(visualization.router)
+api_router.include_router(analysis_charts.router)

backend/app/api/endpoints/ai_analyze.py

@@ -0,0 +1,144 @@
+"""
+AI 分析 API 接口
+"""
+from fastapi import APIRouter, UploadFile, File, HTTPException, Query, Body
+from typing import Optional
+import logging
+
+from app.services.excel_ai_service import excel_ai_service
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/ai", tags=["AI 分析"])
+
+
+@router.post("/analyze/excel")
+async def analyze_excel(
+    file: UploadFile = File(...),
+    user_prompt: str = Query("", description="用户自定义提示词"),
+    analysis_type: str = Query("general", description="分析类型: general, summary, statistics, insights"),
+    parse_all_sheets: bool = Query(False, description="是否分析所有工作表")
+):
+    """
+    上传并使用 AI 分析 Excel 文件
+
+    Args:
+        file: 上传的 Excel 文件
+        user_prompt: 用户自定义提示词
+        analysis_type: 分析类型
+        parse_all_sheets: 是否分析所有工作表
+
+    Returns:
+        dict: 分析结果，包含 Excel 数据和 AI 分析结果
+    """
+    # 检查文件类型
+    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 ['xlsx', 'xls']:
+        raise HTTPException(
+            status_code=400,
+            detail=f"不支持的文件类型: {file_ext}，仅支持 .xlsx 和 .xls"
+        )
+
+    # 验证分析类型
+    supported_types = ['general', 'summary', 'statistics', 'insights']
+    if analysis_type not in supported_types:
+        raise HTTPException(
+            status_code=400,
+            detail=f"不支持的分析类型: {analysis_type}，支持的类型: {', '.join(supported_types)}"
+        )
+
+    try:
+        # 读取文件内容
+        content = await file.read()
+
+        logger.info(f"开始分析文件: {file.filename}, 分析类型: {analysis_type}")
+
+        # 调用 AI 分析服务
+        if parse_all_sheets:
+            result = await excel_ai_service.batch_analyze_sheets(
+                content,
+                file.filename,
+                user_prompt=user_prompt,
+                analysis_type=analysis_type
+            )
+        else:
+            # 解析选项
+            parse_options = {"header_row": 0}
+
+            result = await excel_ai_service.analyze_excel_file(
+                content,
+                file.filename,
+                user_prompt=user_prompt,
+                analysis_type=analysis_type,
+                parse_options=parse_options
+            )
+
+        logger.info(f"文件分析完成: {file.filename}, 成功: {result['success']}")
+
+        return result
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"AI 分析过程中出错: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"分析失败: {str(e)}")
+
+
+@router.get("/analysis/types")
+async def get_analysis_types():
+    """
+    获取支持的分析类型列表
+
+    Returns:
+        list: 支持的分析类型
+    """
+    return {
+        "types": excel_ai_service.get_supported_analysis_types()
+    }
+
+
+@router.post("/analyze/text")
+async def analyze_text(
+    excel_data: dict = Body(..., description="Excel 解析后的数据"),
+    user_prompt: str = Body("", description="用户提示词"),
+    analysis_type: str = Body("general", description="分析类型")
+):
+    """
+    对已解析的 Excel 数据进行 AI 分析
+
+    Args:
+        excel_data: Excel 数据
+        user_prompt: 用户提示词
+        analysis_type: 分析类型
+
+    Returns:
+        dict: 分析结果
+    """
+    try:
+        logger.info(f"开始文本分析, 分析类型: {analysis_type}")
+
+        # 调用 LLM 服务
+        from app.services.llm_service import llm_service
+
+        if user_prompt and user_prompt.strip():
+            result = await llm_service.analyze_with_template(
+                excel_data,
+                user_prompt
+            )
+        else:
+            result = await llm_service.analyze_excel_data(
+                excel_data,
+                user_prompt,
+                analysis_type
+            )
+
+        logger.info(f"文本分析完成, 成功: {result['success']}")
+
+        return result
+
+    except Exception as e:
+        logger.error(f"文本分析失败: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"分析失败: {str(e)}")

backend/app/api/endpoints/analysis_charts.py

@@ -0,0 +1,105 @@
+"""
+分析结果图表 API - 根据文本分析结果生成图表
+"""
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel
+from typing import Optional
+import logging
+
+from app.services.text_analysis_service import text_analysis_service
+from app.services.chart_generator_service import chart_generator_service
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/analysis", tags=["分析结果图表"])
+
+
+class AnalysisChartRequest(BaseModel):
+    """分析图表生成请求模型"""
+    analysis_text: str
+    original_filename: Optional[str] = ""
+    file_type: Optional[str] = "text"
+
+
+@router.post("/extract-and-chart")
+async def extract_and_generate_charts(request: AnalysisChartRequest):
+    """
+    从 AI 分析结果中提取数据并生成图表
+
+    Args:
+        request: 包含分析文本的请求
+
+    Returns:
+        dict: 包含图表数据的结果
+    """
+    if not request.analysis_text or not request.analysis_text.strip():
+        raise HTTPException(status_code=400, detail="分析文本不能为空")
+
+    try:
+        logger.info("开始从分析结果中提取结构化数据...")
+
+        # 1. 使用 LLM 提取结构化数据
+        extract_result = await text_analysis_service.extract_structured_data(
+            analysis_text=request.analysis_text,
+            original_filename=request.original_filename or "unknown",
+            file_type=request.file_type or "text"
+        )
+
+        if not extract_result.get("success"):
+            raise HTTPException(
+                status_code=500,
+                detail=f"提取结构化数据失败: {extract_result.get('error', '未知错误')}"
+            )
+
+        logger.info("结构化数据提取成功，开始生成图表...")
+
+        # 2. 根据提取的数据生成图表
+        chart_result = chart_generator_service.generate_charts_from_analysis(extract_result)
+
+        if not chart_result.get("success"):
+            raise HTTPException(
+                status_code=500,
+                detail=f"生成图表失败: {chart_result.get('error', '未知错误')}"
+            )
+
+        logger.info("图表生成成功")
+
+        return chart_result
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"分析结果图表生成失败: {str(e)}")
+        raise HTTPException(
+            status_code=500,
+            detail=f"图表生成失败: {str(e)}"
+        )
+
+
+@router.post("/analyze-text")
+async def analyze_text_only(request: AnalysisChartRequest):
+    """
+    仅提取结构化数据（不生成图表），用于调试
+
+    Args:
+        request: 包含分析文本的请求
+
+    Returns:
+        dict: 提取的结构化数据
+    """
+    if not request.analysis_text or not request.analysis_text.strip():
+        raise HTTPException(status_code=400, detail="分析文本不能为空")
+
+    try:
+        result = await text_analysis_service.extract_structured_data(
+            analysis_text=request.analysis_text,
+            original_filename=request.original_filename or "unknown",
+            file_type=request.file_type or "text"
+        )
+        return result
+    except Exception as e:
+        logger.error(f"文本分析失败: {str(e)}")
+        raise HTTPException(
+            status_code=500,
+            detail=f"文本分析失败: {str(e)}"
+        )

backend/app/api/endpoints/upload.py

@@ -0,0 +1,205 @@
+"""
+文件上传 API 接口
+"""
+from fastapi import APIRouter, UploadFile, File, HTTPException, Query
+from fastapi.responses import StreamingResponse
+from typing import Optional
+import logging
+import pandas as pd
+import io
+
+from app.services.file_service import file_service
+from app.core.document_parser import XlsxParser
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/upload", tags=["文件上传"])
+
+# 初始化解析器
+excel_parser = XlsxParser()
+
+
+@router.post("/excel")
+async def upload_excel(
+    file: UploadFile = File(...),
+    parse_all_sheets: bool = Query(False, description="是否解析所有工作表"),
+    sheet_name: Optional[str] = Query(None, description="指定解析的工作表名称"),
+    header_row: int = Query(0, description="表头所在的行索引")
+):
+    """
+    上传并解析 Excel 文件
+
+    Args:
+        file: 上传的 Excel 文件
+        parse_all_sheets: 是否解析所有工作表
+        sheet_name: 指定解析的工作表名称
+        header_row: 表头所在的行索引
+
+    Returns:
+        dict: 解析结果
+    """
+    # 检查文件类型
+    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 ['xlsx', 'xls']:
+        raise HTTPException(
+            status_code=400,
+            detail=f"不支持的文件类型: {file_ext}，仅支持 .xlsx 和 .xls"
+        )
+
+    try:
+        # 读取文件内容
+        content = await file.read()
+
+        # 保存文件
+        saved_path = file_service.save_uploaded_file(
+            content,
+            file.filename,
+            subfolder="excel"
+        )
+
+        logger.info(f"文件已保存: {saved_path}")
+
+        # 解析文件
+        if parse_all_sheets:
+            result = excel_parser.parse_all_sheets(saved_path)
+        else:
+            # 如果指定了 sheet_name，使用指定的，否则使用默认的第一个
+            if sheet_name:
+                result = excel_parser.parse(saved_path, sheet_name=sheet_name, header_row=header_row)
+            else:
+                result = excel_parser.parse(saved_path, header_row=header_row)
+
+        # 添加文件路径到元数据
+        if result.metadata:
+            result.metadata['saved_path'] = saved_path
+            result.metadata['original_filename'] = file.filename
+
+        return result.to_dict()
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"解析 Excel 文件时出错: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"解析失败: {str(e)}")
+
+
+@router.get("/excel/preview/{file_path:path}")
+async def get_excel_preview(
+    file_path: str,
+    sheet_name: Optional[str] = Query(None, description="工作表名称"),
+    max_rows: int = Query(10, description="最多返回的行数", ge=1, le=100)
+):
+    """
+    获取 Excel 文件的预览数据
+
+    Args:
+        file_path: 文件路径
+        sheet_name: 工作表名称
+        max_rows: 最多返回的行数
+
+    Returns:
+        dict: 预览数据
+    """
+    try:
+        # 解析工作表名称参数
+        sheet_param = sheet_name if sheet_name else 0
+
+        result = excel_parser.get_sheet_preview(
+            file_path,
+            sheet_name=sheet_param,
+            max_rows=max_rows
+        )
+
+        return result.to_dict()
+
+    except Exception as e:
+        logger.error(f"获取预览数据时出错: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"获取预览失败: {str(e)}")
+
+
+@router.delete("/file")
+async def delete_uploaded_file(file_path: str = Query(..., description="要删除的文件路径")):
+    """
+    删除已上传的文件
+
+    Args:
+        file_path: 文件路径
+
+    Returns:
+        dict: 删除结果
+    """
+    try:
+        success = file_service.delete_file(file_path)
+
+        if success:
+            return {"success": True, "message": "文件删除成功"}
+        else:
+            return {"success": False, "message": "文件不存在或删除失败"}
+
+    except Exception as e:
+        logger.error(f"删除文件时出错: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"删除失败: {str(e)}")
+
+
+@router.get("/excel/export/{file_path:path}")
+async def export_excel(
+    file_path: str,
+    sheet_name: Optional[str] = Query(None, description="工作表名称"),
+    columns: Optional[str] = Query(None, description="要导出的列，逗号分隔")
+):
+    """
+    导出 Excel 文件（可选择工作表和列）
+
+    Args:
+        file_path: 原始文件路径
+        sheet_name: 工作表名称（可选）
+        columns: 要导出的列名，逗号分隔（可选）
+
+    Returns:
+        StreamingResponse: Excel 文件
+    """
+    try:
+        # 读取 Excel 文件
+        if sheet_name:
+            df = pd.read_excel(file_path, sheet_name=sheet_name)
+        else:
+            df = pd.read_excel(file_path)
+
+        # 如果指定了列，只选择这些列
+        if columns:
+            column_list = [col.strip() for col in columns.split(',')]
+            # 过滤掉不存在的列
+            available_columns = [col for col in column_list if col in df.columns]
+            if available_columns:
+                df = df[available_columns]
+
+        # 创建 Excel 文件
+        output = io.BytesIO()
+        with pd.ExcelWriter(output, engine='openpyxl') as writer:
+            df.to_excel(writer, index=False, sheet_name=sheet_name or 'Sheet1')
+
+        output.seek(0)
+
+        # 生成文件名
+        original_name = file_path.split('/')[-1] if '/' in file_path else file_path
+        if columns:
+            export_name = f"export_{sheet_name or 'data'}_{len(column_list) if columns else 'all'}_cols.xlsx"
+        else:
+            export_name = f"export_{original_name}"
+
+        # 返回文件流
+        return StreamingResponse(
+            io.BytesIO(output.getvalue()),
+            media_type="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+            headers={"Content-Disposition": f"attachment; filename={export_name}"}
+        )
+
+    except FileNotFoundError:
+        logger.error(f"文件不存在: {file_path}")
+        raise HTTPException(status_code=404, detail="文件不存在")
+    except Exception as e:
+        logger.error(f"导出 Excel 文件时出错: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"导出失败: {str(e)}")

backend/app/api/endpoints/visualization.py

@@ -0,0 +1,90 @@
+"""
+可视化 API 接口 - 生成统计图表
+"""
+from fastapi import APIRouter, HTTPException, Body
+from typing import Dict, Any
+import logging
+
+from app.services.visualization_service import visualization_service
+from pydantic import BaseModel
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/visualization", tags=["数据可视化"])
+
+
+class StatisticsRequest(BaseModel):
+    """统计图表生成请求模型"""
+    excel_data: Dict[str, Any]
+    analysis_type: str = "statistics"
+
+
+@router.post("/statistics")
+async def generate_statistics(request: StatisticsRequest):
+    """
+    生成统计信息和可视化图表
+
+    Args:
+        request: 包含 excel_data 和 analysis_type 的请求体
+
+    Returns:
+        dict: 包含统计信息和图表数据的结果
+    """
+    excel_data = request.excel_data
+    analysis_type = request.analysis_type
+
+    if not excel_data:
+        raise HTTPException(status_code=400, detail="未提供 Excel 数据")
+
+    try:
+        result = visualization_service.analyze_and_visualize(
+            excel_data,
+            analysis_type
+        )
+
+        if not result.get("success"):
+            raise HTTPException(status_code=500, detail=result.get("error", "分析失败"))
+
+        logger.info("统计图表生成成功")
+
+        return result
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"统计图表生成失败: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"图表生成失败: {str(e)}")
+
+
+@router.get("/chart-types")
+async def get_chart_types():
+    """
+    获取支持的图表类型
+
+    Returns:
+        dict: 支持的图表类型列表
+    """
+    return {
+        "chart_types": [
+            {
+                "value": "histogram",
+                "label": "直方图",
+                "description": "显示数值型列的分布情况"
+            },
+            {
+                "value": "bar_chart",
+                "label": "条形图",
+                "description": "显示分类列的频次分布"
+            },
+            {
+                "value": "box_plot",
+                "label": "箱线图",
+                "description": "显示数值列的四分位数和异常值"
+            },
+            {
+                "value": "correlation_heatmap",
+                "label": "相关性热力图",
+                "description": "显示数值列之间的相关性"
+            }
+        ]
+    }