diff --git a/backend/app/api/endpoints/ai_analyze.py b/backend/app/api/endpoints/ai_analyze.py index 9112977..36dedfe 100644 --- a/backend/app/api/endpoints/ai_analyze.py +++ b/backend/app/api/endpoints/ai_analyze.py @@ -154,8 +154,9 @@ async def analyze_text( @router.post("/analyze/md") async def analyze_markdown( - file: UploadFile = File(...), - analysis_type: str = Query("summary", description="分析类型: summary, outline, key_points, questions, tags, qa, statistics, section"), + file: Optional[UploadFile] = File(None), + doc_id: Optional[str] = Query(None, description="文档ID（从数据库读取）"), + analysis_type: str = Query("summary", description="分析类型: summary, outline, key_points, questions, tags, qa, statistics, section, charts"), user_prompt: str = Query("", description="用户自定义提示词"), section_number: Optional[str] = Query(None, description="指定章节编号，如 '一' 或 '（一）'") ): @@ -163,7 +164,8 @@ async def analyze_markdown( 上传并使用 AI 分析 Markdown 文件 Args: - file: 上传的 Markdown 文件 + file: 上传的 Markdown 文件（与 doc_id 二选一） + doc_id: 文档ID（从数据库读取） analysis_type: 分析类型 user_prompt: 用户自定义提示词 section_number: 指定分析的章节编号 @@ -171,16 +173,8 @@ async def analyze_markdown( Returns: dict: 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 ['md', 'markdown']: - raise HTTPException( - status_code=400, - detail=f"不支持的文件类型: {file_ext}，仅支持 .md 和 .markdown" - ) + filename = None + tmp_path = None # 验证分析类型 supported_types = markdown_ai_service.get_supported_analysis_types() @@ -190,46 +184,96 @@ async def analyze_markdown( 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() - - # 保存到临时文件 - with tempfile.NamedTemporaryFile(mode='wb', suffix='.md', delete=False) as tmp: - tmp.write(content) - tmp_path = tmp.name - + if doc_id: + # 从数据库读取文档 try: - logger.info(f"开始分析 Markdown 文件: {file.filename}, 分析类型: {analysis_type}, 章节: {section_number}") + from app.core.database.mongodb import mongodb + doc = await mongodb.get_document(doc_id) + if not doc: + raise HTTPException(status_code=404, detail=f"文档不存在: {doc_id}") - # 调用 AI 分析服务 - result = await markdown_ai_service.analyze_markdown( - file_path=tmp_path, - analysis_type=analysis_type, - user_prompt=user_prompt, - section_number=section_number + filename = doc.get("metadata", {}).get("original_filename", "unknown.md") + file_ext = filename.split('.')[-1].lower() + + if file_ext not in ['md', 'markdown']: + raise HTTPException(status_code=400, detail=f"文档类型不是 Markdown: {file_ext}") + + content = doc.get("content", "") + if not content: + raise HTTPException(status_code=400, detail="文档内容为空") + + # 保存到临时文件 + with tempfile.NamedTemporaryFile(mode='wb', suffix='.md', delete=False) as tmp: + tmp.write(content.encode('utf-8')) + tmp_path = tmp.name + + logger.info(f"从数据库加载 Markdown 文档: {filename}, 长度: {len(content)}") + + except HTTPException: + raise + except Exception as e: + logger.error(f"从数据库读取 Markdown 文档失败: {str(e)}") + raise HTTPException(status_code=500, detail=f"读取文档失败: {str(e)}") + else: + # 文件上传模式 + if not file: + raise HTTPException(status_code=400, detail="请提供文件或文档ID") + + 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 ['md', 'markdown']: + raise HTTPException( + status_code=400, + detail=f"不支持的文件类型: {file_ext}，仅支持 .md 和 .markdown" ) - logger.info(f"Markdown 分析完成: {file.filename}, 成功: {result['success']}") + try: + # 读取文件内容 + content = await file.read() - if not result['success']: - raise HTTPException(status_code=500, detail=result.get('error', '分析失败')) + # 保存到临时文件 + with tempfile.NamedTemporaryFile(mode='wb', suffix='.md', delete=False) as tmp: + tmp.write(content) + tmp_path = tmp.name - return result + filename = file.filename - finally: - # 清理临时文件，确保在所有情况下都能清理 - try: - if tmp_path and os.path.exists(tmp_path): - os.unlink(tmp_path) - except Exception as cleanup_error: - logger.warning(f"临时文件清理失败: {tmp_path}, error: {cleanup_error}") + except Exception as e: + logger.error(f"读取 Markdown 文件失败: {str(e)}") + raise HTTPException(status_code=500, detail=f"读取文件失败: {str(e)}") + + try: + logger.info(f"开始分析 Markdown 文件: {filename}, 分析类型: {analysis_type}, 章节: {section_number}") + + # 调用 AI 分析服务 + result = await markdown_ai_service.analyze_markdown( + file_path=tmp_path, + analysis_type=analysis_type, + user_prompt=user_prompt, + section_number=section_number + ) + + logger.info(f"Markdown 分析完成: {filename}, 成功: {result['success']}") + + if not result['success']: + raise HTTPException(status_code=500, detail=result.get('error', '分析失败')) + + return result except HTTPException: raise except Exception as e: logger.error(f"Markdown AI 分析过程中出错: {str(e)}") raise HTTPException(status_code=500, detail=f"分析失败: {str(e)}") + finally: + # 清理临时文件 + if tmp_path and os.path.exists(tmp_path): + try: + os.unlink(tmp_path) + except Exception as cleanup_error: + logger.warning(f"临时文件清理失败: {tmp_path}, error: {cleanup_error}") @router.post("/analyze/md/stream") @@ -347,7 +391,8 @@ async def get_markdown_outline( @router.post("/analyze/txt") async def analyze_txt( - file: UploadFile = File(...), + file: Optional[UploadFile] = File(None), + doc_id: Optional[str] = Query(None, description="文档ID（从数据库读取）"), analysis_type: str = Query("structured", description="分析类型: structured, charts") ): """ @@ -357,63 +402,89 @@ async def analyze_txt( 当 analysis_type=charts 时，可生成可视化图表 Args: - file: 上传的 TXT 文件 + file: 上传的 TXT 文件（与 doc_id 二选一） + doc_id: 文档ID（从数据库读取） analysis_type: 分析类型 - "structured"（默认，提取结构化数据）或 "charts"（生成图表） Returns: dict: 分析结果，包含结构化表格数据或图表数据 """ - if not file.filename: - raise HTTPException(status_code=400, detail="文件名为空") + filename = None + text_content = None - 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" - ) + if doc_id: + # 从数据库读取文档 + try: + from app.core.database.mongodb import mongodb + doc = await mongodb.get_document(doc_id) + if not doc: + raise HTTPException(status_code=404, detail=f"文档不存在: {doc_id}") + + filename = doc.get("metadata", {}).get("original_filename", "unknown.txt") + file_ext = filename.split('.')[-1].lower() + + if file_ext not in ['txt', 'text']: + raise HTTPException(status_code=400, detail=f"文档类型不是 TXT: {file_ext}") + + # 使用数据库中的 content + text_content = doc.get("content", "") + + if not text_content: + raise HTTPException(status_code=400, detail="文档内容为空") + + logger.info(f"从数据库加载 TXT 文档: {filename}, 长度: {len(text_content)}") + + except HTTPException: + raise + except Exception as e: + logger.error(f"从数据库读取 TXT 文档失败: {str(e)}") + raise HTTPException(status_code=500, detail=f"读取文档失败: {str(e)}") + else: + # 文件上传模式 + if not file: + raise HTTPException(status_code=400, detail="请提供文件或文档ID") + + 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() text_content = content.decode('utf-8', errors='replace') + filename = file.filename - # 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: {filename}, analysis_type={analysis_type}") - try: - logger.info(f"开始 AI 分析 TXT 文件: {file.filename}, analysis_type={analysis_type}") + # 使用 txt_ai_service 的 AI 分析方法 + result = await txt_ai_service.analyze_txt_with_ai( + content=text_content, + filename=filename, + analysis_type=analysis_type + ) - # 使用 txt_ai_service 的 AI 分析方法 - result = await txt_ai_service.analyze_txt_with_ai( - content=text_content, - filename=file.filename, - analysis_type=analysis_type - ) - - if result: - logger.info(f"TXT AI 分析成功: {file.filename}") - return { - "success": result.get("success", True), - "filename": file.filename, - "analysis_type": analysis_type, - "result": 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", - "result": None - } - - finally: - # 清理临时文件 - if os.path.exists(tmp_path): - os.unlink(tmp_path) + if result: + logger.info(f"TXT AI 分析成功: {filename}") + return { + "success": result.get("success", True), + "filename": filename, + "analysis_type": analysis_type, + "result": result + } + else: + logger.warning(f"TXT AI 分析返回空结果: {filename}") + return { + "success": False, + "filename": filename, + "error": "AI 分析未能提取到结构化数据", + "result": None + } except HTTPException: raise @@ -426,7 +497,8 @@ async def analyze_txt( @router.post("/analyze/word") async def analyze_word( - file: UploadFile = File(...), + file: Optional[UploadFile] = File(None), + doc_id: Optional[str] = Query(None, description="文档ID（从数据库读取）"), user_hint: str = Query("", description="用户提示词，如'请提取表格数据'"), analysis_type: str = Query("structured", description="分析类型: structured, charts") ): @@ -437,13 +509,77 @@ async def analyze_word( 当 analysis_type=charts 时，可生成可视化图表 Args: - file: 上传的 Word 文件 + file: 上传的 Word 文件（与 doc_id 二选一） + doc_id: 文档ID（从数据库读取） user_hint: 用户提示词 analysis_type: 分析类型 - "structured"（默认，提取结构化数据）或 "charts"（生成图表） Returns: dict: 包含结构化数据的解析结果或图表数据 """ + # 获取文件名和扩展名 + filename = None + file_ext = None + + if doc_id: + # 从数据库读取文档 + try: + from app.core.database.mongodb import mongodb + doc = await mongodb.get_document(doc_id) + if not doc: + raise HTTPException(status_code=404, detail=f"文档不存在: {doc_id}") + + filename = doc.get("metadata", {}).get("original_filename", "unknown.docx") + file_ext = filename.split('.')[-1].lower() + + if file_ext not in ['docx']: + raise HTTPException(status_code=400, detail=f"文档类型不是 Word: {file_ext}") + + # 使用数据库中的 content 进行分析 + content = doc.get("content", "") + tables = doc.get("structured_data", {}).get("tables", []) + + # 调用 AI 分析服务，传入数据库内容 + if analysis_type == "charts": + result = await word_ai_service.generate_charts_from_db( + content=content, + tables=tables, + filename=filename, + user_hint=user_hint + ) + else: + result = await word_ai_service.parse_word_with_ai_from_db( + content=content, + tables=tables, + filename=filename, + 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" + ) + + if result.get("success"): + return { + "success": True, + "filename": filename, + "analysis_type": analysis_type, + "result": result + } + else: + return { + "success": False, + "filename": filename, + "error": result.get("error", "AI 解析失败"), + "result": None + } + + except HTTPException: + raise + except Exception as e: + logger.error(f"从数据库读取 Word 文档失败: {str(e)}") + raise HTTPException(status_code=500, detail=f"读取文档失败: {str(e)}") + + # 文件上传模式 + if not file: + raise HTTPException(status_code=400, detail="请提供文件或文档ID") + if not file.filename: raise HTTPException(status_code=400, detail="文件名为空") diff --git a/backend/app/api/endpoints/documents.py b/backend/app/api/endpoints/documents.py index 221e059..2f77714 100644 --- a/backend/app/api/endpoints/documents.py +++ b/backend/app/api/endpoints/documents.py @@ -405,7 +405,7 @@ async def process_documents_batch(task_id: str, files: List[dict]): if content and len(content) > 50: await index_document_to_rag(doc_id, filename, result, file_info["ext"]) - return {"index": index, "filename": filename, "doc_id": doc_id, "success": True} + return {"index": index, "filename": filename, "doc_id": doc_id, "file_path": file_info["path"], "success": True} except Exception as e: logger.error(f"处理文件 {filename} 失败: {e}") diff --git a/backend/app/services/word_ai_service.py b/backend/app/services/word_ai_service.py index 817fd8c..a38d70d 100644 --- a/backend/app/services/word_ai_service.py +++ b/backend/app/services/word_ai_service.py @@ -757,5 +757,150 @@ class WordAIService: } -# 全局单例 -word_ai_service = WordAIService() + async def parse_word_with_ai_from_db( + self, + content: str, + tables: List[Dict], + filename: str = "", + user_hint: str = "" + ) -> Dict[str, Any]: + """ + 使用 AI 解析从数据库读取的 Word 文档内容，提取结构化数据 + + Args: + content: 文档文本内容 + tables: 表格数据列表 + filename: 文件名 + user_hint: 用户提示词 + + Returns: + Dict: 包含结构化数据的解析结果 + """ + try: + # 解析段落 + paragraphs = [p.strip() for p in content.split('\n') if p.strip()] + + logger.info(f"从数据库解析 Word: {len(paragraphs)} 个段落, {len(tables)} 个表格") + + # 优先处理表格数据 + if tables and len(tables) > 0: + structured_data = await self._extract_tables_with_ai( + tables, paragraphs, 0, user_hint, {"filename": filename} + ) + elif paragraphs and len(paragraphs) > 0: + structured_data = await self._extract_from_text_with_ai( + paragraphs, content, 0, [], user_hint + ) + else: + structured_data = { + "success": True, + "type": "empty", + "message": "文档内容为空" + } + + return structured_data + + except Exception as e: + logger.error(f"从数据库解析 Word 文档失败: {str(e)}") + return { + "success": False, + "error": str(e) + } + + async def generate_charts_from_db( + self, + content: str, + tables: List[Dict], + filename: str = "", + user_hint: str = "" + ) -> Dict[str, Any]: + """ + 使用 AI 解析从数据库读取的 Word 文档并生成可视化图表 + + Args: + content: 文档文本内容 + tables: 表格数据列表 + filename: 文件名 + user_hint: 用户提示词 + + Returns: + Dict: 包含图表数据和统计信息的结果 + """ + try: + # 解析段落 + paragraphs = [p.strip() for p in content.split('\n') if p.strip()] + + logger.info(f"从数据库生成 Word 图表: {len(paragraphs)} 个段落, {len(tables)} 个表格") + + # 优先处理表格数据 + if tables and len(tables) > 0: + structured_data = await self._extract_tables_with_ai( + tables, paragraphs, 0, user_hint, {"filename": filename} + ) + elif paragraphs and len(paragraphs) > 0: + structured_data = await self._extract_from_text_with_ai( + paragraphs, content, 0, [], user_hint + ) + else: + return { + "success": False, + "error": "文档内容为空" + } + + # 提取可用于图表的数据 + chart_data = None + + if structured_data.get("type") == "table_data": + headers = structured_data.get("headers", []) + rows = structured_data.get("rows", []) + if headers and rows: + chart_data = { + "columns": headers, + "rows": rows + } + elif structured_data.get("type") == "structured_text": + tables_data = structured_data.get("tables", []) + if tables_data and len(tables_data) > 0: + first_table = tables_data[0] + headers = first_table.get("headers", []) + rows = first_table.get("rows", []) + if headers and rows: + chart_data = { + "columns": headers, + "rows": rows + } + + # 生成可视化图表 + if chart_data: + logger.info(f"开始生成图表，列数: {len(chart_data['columns'])}, 行数: {len(chart_data['rows'])}") + vis_result = visualization_service.analyze_and_visualize(chart_data) + + if vis_result.get("success"): + return { + "success": True, + "charts": vis_result.get("charts", {}), + "statistics": vis_result.get("statistics", {}), + "distributions": vis_result.get("distributions", {}), + "structured_data": structured_data, + "row_count": vis_result.get("row_count", 0), + "column_count": vis_result.get("column_count", 0) + } + else: + return { + "success": False, + "error": vis_result.get("error", "可视化生成失败"), + "structured_data": structured_data + } + else: + return { + "success": False, + "error": "文档中没有可用于图表的表格数据", + "structured_data": structured_data + } + + except Exception as e: + logger.error(f"从数据库生成 Word 图表失败: {str(e)}") + return { + "success": False, + "error": str(e) + } diff --git a/frontend/src/db/backend-api.ts b/frontend/src/db/backend-api.ts index 59243f6..bb6c162 100644 --- a/frontend/src/db/backend-api.ts +++ b/frontend/src/db/backend-api.ts @@ -1279,15 +1279,21 @@ export const aiApi = { * 上传并使用 AI 分析 Markdown 文件 */ async analyzeMarkdown( - file: File, + file: File | null, options: { + docId?: string; analysisType?: MarkdownAnalysisType; userPrompt?: string; sectionNumber?: string; } = {} ): Promise { const formData = new FormData(); - formData.append('file', file); + if (file) { + formData.append('file', file); + } + if (options.docId) { + formData.append('doc_id', options.docId); + } const params = new URLSearchParams(); if (options.analysisType) { @@ -1432,7 +1438,8 @@ export const aiApi = { * 上传并使用 AI 分析 TXT 文本文件，提取结构化数据或生成图表 */ async analyzeTxt( - file: File, + file: File | null, + docId: string | null = null, analysisType: TxtAnalysisType = 'structured' ): Promise<{ success: boolean; @@ -1442,7 +1449,12 @@ export const aiApi = { error?: string; }> { const formData = new FormData(); - formData.append('file', file); + if (file) { + formData.append('file', file); + } + if (docId) { + formData.append('doc_id', docId); + } const params = new URLSearchParams(); params.append('analysis_type', analysisType); @@ -1572,7 +1584,8 @@ export const aiApi = { * 使用 AI 解析 Word 文档，提取结构化数据或生成图表 */ async analyzeWordWithAI( - file: File, + file: File | null, + docId: string | null = null, userHint: string = '', analysisType: WordAnalysisType = 'structured' ): Promise<{ @@ -1583,7 +1596,12 @@ export const aiApi = { error?: string; }> { const formData = new FormData(); - formData.append('file', file); + if (file) { + formData.append('file', file); + } + if (docId) { + formData.append('doc_id', docId); + } if (userHint) { formData.append('user_hint', userHint); } diff --git a/frontend/src/pages/Documents.tsx b/frontend/src/pages/Documents.tsx index 1cf86af..a71b113 100644 --- a/frontend/src/pages/Documents.tsx +++ b/frontend/src/pages/Documents.tsx @@ -10,7 +10,7 @@ import { ChevronDown, ChevronUp, FileSpreadsheet, - File, + File as FileIcon, Table, CheckCircle, AlertCircle, @@ -123,6 +123,17 @@ const Documents: React.FC = () => { const [ragResults, setRagResults] = useState([]); const [ragRebuilding, setRagRebuilding] = useState(false); + // 选中的文档详情 + const [selectedDocument, setSelectedDocument] = useState<{ + doc_id: string; + original_filename: string; + doc_type: string; + content?: string; + structured_data?: any; + metadata?: any; + } | null>(null); + const [loadingDocument, setLoadingDocument] = useState(false); + // 解析选项 const [parseOptions, setParseOptions] = useState({ parseAllSheets: false, @@ -277,6 +288,33 @@ const Documents: React.FC = () => { return { ...s, status: 'failed', progress: 0, error: fileResult?.error || '处理失败' }; } })); + + // 设置第一个成功文件的 uploadedFile + const firstSuccessIdx = fileResults.findIndex((fr: any) => fr?.success); + if (firstSuccessIdx >= 0 && acceptedFiles[firstSuccessIdx]) { + const firstFile = acceptedFiles[firstSuccessIdx]; + const firstResult = fileResults[firstSuccessIdx]; + const ext = firstFile.name.split('.').pop()?.toLowerCase(); + + // 设置 uploadedFile + setUploadedFile(firstFile); + + // 对于 Excel 文件，获取 parseResult + if (ext === 'xlsx' || ext === 'xls') { + // 调用 parseDocument 获取 parseResult + if (firstResult?.file_path) { + try { + const parseResult = await backendApi.parseDocument(firstResult.file_path); + if (parseResult.success) { + setParseResult(parseResult as any); + } + } catch (parseErr) { + console.warn('获取 parseResult 失败:', parseErr); + } + } + } + } + loadDocuments(); return; } else if (status.status === 'failure') { @@ -455,24 +493,79 @@ const Documents: React.FC = () => { // 基于 AI 分析生成图表 const handleGenerateCharts = async () => { - if (!aiAnalysis || !aiAnalysis.success) { + // 检查是否有任何 AI 分析结果 + const hasExcelAI = aiAnalysis?.success; + const hasMdAI = mdAnalysis?.success; + const hasWordAI = wordAnalysis?.success; + const hasTxtAI = txtAnalysis?.success; + + if (!hasExcelAI && !hasMdAI && !hasWordAI && !hasTxtAI) { toast.error('请先进行 AI 分析'); return; } + // 如果是 Markdown 分析已有图表，直接显示 + if (hasMdAI && mdAnalysis?.chart_data?.tables) { + setAnalysisCharts({ + success: true, + charts: { tables: mdAnalysis.chart_data.tables }, + statistics: mdAnalysis.chart_data.key_statistics + }); + toast.success('图表生成完成'); + return; + } + + // 如果是 Word 分析已有图表，直接显示 + if (hasWordAI && wordAnalysis?.result?.charts) { + setAnalysisCharts({ + success: true, + charts: wordAnalysis.result.charts, + statistics: wordAnalysis.result.statistics + }); + toast.success('图表生成完成'); + return; + } + + // 如果是 TXT 分析已有图表，直接显示 + if (hasTxtAI && txtAnalysis?.result?.charts) { + setAnalysisCharts({ + success: true, + charts: txtAnalysis.result.charts, + statistics: txtAnalysis.result.statistics + }); + toast.success('图表生成完成'); + return; + } + + // 尝试从各种分析结果中提取文本并生成图表 let analysisText = ''; - if (aiAnalysis.analysis?.analysis) { - analysisText = aiAnalysis.analysis.analysis; - } else if (aiAnalysis.analysis?.sheets) { - const sheets = aiAnalysis.analysis.sheets; - if (sheets && Object.keys(sheets).length > 0) { - const firstSheet = Object.keys(sheets)[0]; - analysisText = sheets[firstSheet]?.analysis || ''; + let fileType = 'unknown'; + + if (hasExcelAI) { + if (aiAnalysis.analysis?.analysis) { + analysisText = aiAnalysis.analysis.analysis; + fileType = 'excel'; + } else if (aiAnalysis.analysis?.sheets) { + const sheets = aiAnalysis.analysis.sheets; + if (sheets && Object.keys(sheets).length > 0) { + const firstSheet = Object.keys(sheets)[0]; + analysisText = sheets[firstSheet]?.analysis || ''; + fileType = 'excel'; + } } + } else if (hasMdAI && mdAnalysis?.analysis) { + analysisText = mdAnalysis.analysis; + fileType = 'markdown'; + } else if (hasWordAI && wordAnalysis?.result?.summary) { + analysisText = wordAnalysis.result.summary; + fileType = 'word'; + } else if (hasTxtAI && txtAnalysis?.result?.summary) { + analysisText = txtAnalysis.result.summary; + fileType = 'txt'; } if (!analysisText?.trim()) { - toast.error('无法获取 AI 分析结果'); + toast.error('无法获取 AI 分析文本结果'); return; } @@ -483,7 +576,7 @@ const Documents: React.FC = () => { const result = await aiApi.extractAndGenerateCharts({ analysis_text: analysisText, original_filename: uploadedFile?.name || 'unknown', - file_type: 'excel' + file_type: fileType }); if (result.success) { @@ -601,6 +694,9 @@ const Documents: React.FC = () => { const result = await backendApi.deleteDocument(docId); if (result.success) { setDocuments(prev => prev.filter(d => d.doc_id !== docId)); + if (selectedDocument?.doc_id === docId) { + setSelectedDocument(null); + } toast.success('文档已删除'); } } catch (err: any) { @@ -608,6 +704,95 @@ const Documents: React.FC = () => { } }; + const handleSelectDocument = async (docId: string) => { + setLoadingDocument(true); + try { + const result = await backendApi.getDocument(docId); + if (result.success && result.document) { + setSelectedDocument(result.document); + const doc = result.document; + + // 优先使用 file_path 调用 parseDocument 获取完整解析结果 + const filePath = doc.metadata?.file_path; + if (filePath) { + try { + const parseResult = await backendApi.parseDocument(filePath); + if (parseResult.success) { + setParseResult(parseResult as any); + const ext = doc.original_filename.split('.').pop()?.toLowerCase() || doc.doc_type; + const fakeFile = new File([], doc.original_filename, { type: getMimeType(ext) }); + setUploadedFile(fakeFile); + toast.success('已加载文档: ' + doc.original_filename); + setLoadingDocument(false); + return; + } else { + console.warn('parseDocument returned success:false, using fallback'); + } + } catch (parseErr) { + console.warn('parseDocument failed, fallback to structured_data:', parseErr); + } + } + + // 后备：使用 structured_data 构建 parseResult + const ext = doc.original_filename.split('.').pop()?.toLowerCase() || doc.doc_type; + const fakeFile = new File([], doc.original_filename, { type: getMimeType(ext) }); + + if (doc.structured_data) { + const mockParseResult: ExcelParseResult = { + success: true, + data: {}, + metadata: { + filename: doc.filename, + original_filename: doc.original_filename, + extension: doc.doc_type, + doc_type: doc.doc_type as any, + file_size: doc.metadata?.file_size || 0, + } + }; + if (doc.structured_data.tables && doc.structured_data.tables.length > 0) { + const firstTable = doc.structured_data.tables[0]; + mockParseResult.data = { + columns: firstTable.headers || [], + rows: (firstTable.rows || []).map((row: string[]) => { + const obj: Record = {}; + (firstTable.headers || []).forEach((h: string, i: number) => { + obj[h] = row[i] || ''; + }); + return obj; + }), + row_count: firstTable.rows?.length || 0, + column_count: firstTable.headers?.length || 0, + }; + } + if (doc.structured_data.sheets) { + mockParseResult.data.sheets = doc.structured_data.sheets; + } + setParseResult(mockParseResult); + } else if (doc.content) { + setParseResult({ + success: true, + data: { content: doc.content }, + metadata: { + filename: doc.filename, + original_filename: doc.original_filename, + extension: doc.doc_type, + doc_type: doc.doc_type as any, + file_size: doc.metadata?.file_size || 0, + } + }); + } + setUploadedFile(fakeFile); + toast.success('已加载文档: ' + doc.original_filename); + } else { + toast.error(result.error || '获取文档详情失败'); + } + } catch (err: any) { + toast.error(err.message || '获取文档详情失败'); + } finally { + setLoadingDocument(false); + } + }; + const filteredDocs = documents.filter(doc => doc.original_filename.toLowerCase().includes(search.toLowerCase()) ); @@ -621,7 +806,7 @@ const Documents: React.FC = () => { case 'doc': return ; default: - return ; + return ; } }; @@ -641,11 +826,17 @@ const Documents: React.FC = () => { setMdAnalysis(null); try { - const result = await aiApi.analyzeMarkdown(uploadedFile, { - analysisType: mdAnalysisType, - userPrompt: mdUserPrompt, - sectionNumber: mdSelectedSection || undefined - }); + // 判断是从历史文档还是本地上传 + const docId = selectedDocument?.doc_id && uploadedFile.size === 0 ? selectedDocument.doc_id : undefined; + const result = await aiApi.analyzeMarkdown( + uploadedFile.size > 0 ? uploadedFile : null, + { + docId: docId || undefined, + analysisType: mdAnalysisType, + userPrompt: mdUserPrompt, + sectionNumber: mdSelectedSection || undefined + } + ); if (result.success) { toast.success('Markdown AI 分析完成'); @@ -721,8 +912,11 @@ const Documents: React.FC = () => { setWordAnalysis(null); try { + // 判断是从历史文档还是本地上传 + const docId = selectedDocument?.doc_id && uploadedFile.size === 0 ? selectedDocument.doc_id : null; const result = await aiApi.analyzeWordWithAI( - uploadedFile, + uploadedFile.size > 0 ? uploadedFile : null, + docId, wordUserHint, wordAnalysisType ); @@ -751,7 +945,13 @@ const Documents: React.FC = () => { setTxtAnalysis(null); try { - const result = await aiApi.analyzeTxt(uploadedFile, txtAnalysisType); + // 判断是从历史文档还是本地上传 + const docId = selectedDocument?.doc_id && uploadedFile.size === 0 ? selectedDocument.doc_id : null; + const result = await aiApi.analyzeTxt( + uploadedFile.size > 0 ? uploadedFile : null, + docId, + txtAnalysisType + ); if (result.success) { toast.success('TXT AI 分析完成'); @@ -789,6 +989,18 @@ const Documents: React.FC = () => { return `${(bytes / Math.pow(k, i)).toFixed(2)} ${sizes[i]}`; }; + const getMimeType = (ext: string): string => { + const mimeTypes: Record = { + 'xlsx': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', + 'xls': 'application/vnd.ms-excel', + 'docx': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', + 'doc': 'application/msword', + 'md': 'text/markdown', + 'txt': 'text/plain', + }; + return mimeTypes[ext] || 'application/octet-stream'; + }; + const getAnalysisIcon = (type: string) => { switch (type) { case 'general': return ; @@ -1130,7 +1342,7 @@ const Documents: React.FC = () => { Markdown - 文本 + 文本 @@ -1139,6 +1351,38 @@ const Documents: React.FC = () => { )} + {/* 从历史文档中选择 */} + {documents.length > 0 && ( + + + + + 从历史文档选择 + + + + + + + )} + {/* Excel 解析选项 */} {uploadedFile && isExcelFile(uploadedFile.name) && ( @@ -1423,7 +1667,7 @@ const Documents: React.FC = () => { )} {/* 数据操作 */} - {parseResult?.success && ( + {(parseResult?.success || aiAnalysis?.success || mdAnalysis?.success || wordAnalysis?.success || txtAnalysis?.success) && ( @@ -1432,7 +1676,7 @@ const Documents: React.FC = () => { - + + + + {loadingDocument ? ( +
+ + 加载中... +
+ ) : ( +
+ {selectedDocument.structured_data?.tables && selectedDocument.structured_data.tables.length > 0 && ( +
+

表格数据：

+ {selectedDocument.structured_data.tables.slice(0, 3).map((table: any, idx: number) => ( +
+ {table.headers && ( + + + + {table.headers.map((header: string, hIdx: number) => ( + {header} + ))} + + + + {(table.rows || []).slice(0, 10).map((row: string[], rIdx: number) => ( + + {row.map((cell: string, cIdx: number) => ( + {cell} + ))} + + ))} + + + )} +
+ ))} +
+ )} + {selectedDocument.structured_data?.key_values && Object.keys(selectedDocument.structured_data.key_values || {}).length > 0 && ( +
+

键值对数据：

+
+ {Object.entries(selectedDocument.structured_data.key_values || {}).map(([key, value]: [string, any]) => ( +
+ {key}: + {String(value)} +
+ ))} +
+
+ )} + {selectedDocument.content && ( +
+

文本内容预览：

+
+

+ {selectedDocument.content.slice(0, 2000)} + {selectedDocument.content.length > 2000 && '...'} +

+
+
+ )} + {!selectedDocument.content && !selectedDocument.structured_data?.tables && !selectedDocument.structured_data?.key_values && ( +

该文档没有可显示的内容

+ )} +
+ )} + + + )} + {/* 文档列表 */} @@ -1801,7 +2134,14 @@ const Documents: React.FC = () => { ) : (filteredDocs?.length ?? 0) > 0 ? (
{(filteredDocs || []).map(doc => ( -
+
handleSelectDocument(doc.doc_id)} + >
{ {doc.doc_type.toUpperCase()} • {format(new Date(doc.created_at), 'yyyy-MM-dd HH:mm')}

-