这是翻译后的HTML内容...
" - } - }, - "json": { - "summary": "JSON 内容", - "value": { - "file_type": "json", - "filename": "product_info_translated.json", - "content": "{ \"productName\": \"高度なウィジェット\", ... }" - } - }, - "markdown_zip_base64": { - "summary": "ZIP 内容 (Base64)", - "value": { - "file_type": "markdown_zip", - "filename": "my_doc_translated.zip", - "content": "UEsDBBQAAAAIA... (base64-encoded string)" - } - } + "content": { "application/json": { "examples": { + # ... 其他示例 ... + "xlsx_base64": { + "summary": "XLSX 内容 (Base64)", + "value": { + "file_type": "xlsx", + "filename": "my_sheet_translated.xlsx", + "content": "UEsDBBQAAAAIA... (base64-encoded string)" } } - } - }, - 404: { - "description": "资源未找到。", - "content": {"application/json": {"example": {"detail": "内容尚未准备好。"}}} + }}} }, + # ... } ) async def service_content( task_id: str = FastApiPath(..., description="已完成任务的ID", examples=["b2865b93"]), - file_type: FileType = FastApiPath(..., description="要获取内容的文件类型。", examples=["html", "json"]) + file_type: FileType = FastApiPath(..., description="要获取内容的文件类型。", examples=["html", "json", "xlsx"]) ): - """根据任务ID和文件类型，以JSON格式返回内容。zip文件会进行Base64编码。""" + """[MODIFIED] 根据任务ID和文件类型，以JSON格式返回内容。zip/xlsx文件会进行Base64编码。""" content, _, filename = await _get_content_from_workflow(task_id, file_type) final_content: str - if file_type == 'markdown_zip': + if file_type in ['markdown_zip', 'xlsx']: # 二进制文件进行Base64编码 final_content = base64.b64encode(content).decode('utf-8') - else: - # For text-based formats including json, just decode + else: # 文本文件直接解码 final_content = content.decode('utf-8') return JSONResponse(content={ @@ -1004,192 +813,80 @@ async def service_content( "content": final_content }) +# ... 其他端点 (engin-list, task-list, default-params, meta) 保持不变 ... -@service_router.get( - "/engin-list", - summary="获取可用解析引擎", - tags=["Application"], - description="返回当前后端环境支持的文档解析引擎列表。前端可以根据此列表动态展示选项。", - response_model=List[str], - responses={ - 200: { - "description": "成功返回可用引擎列表。", - "content": {"application/json": {"example": ["mineru", "docling"]}} - } - } -) +# =================================================================== +# --- 应用主路由和启动 (保持不变) --- +# =================================================================== +@service_router.get("/engin-list", tags=["Application"]) async def service_get_engin_list(): - """返回可用的文档解析引擎列表。""" engin_list = ["mineru"] - if DOCLING_EXIST: - engin_list.append("docling") + if DOCLING_EXIST: engin_list.append("docling") return JSONResponse(content=engin_list) +@service_router.get("/task-list", tags=["Application"]) +async def service_get_task_list(): return JSONResponse(content=list(tasks_state.keys())) -@service_router.get( - "/task-list", - summary="获取所有任务ID列表", - tags=["Application"], - description="返回当前服务实例中存在的所有任务ID的列表。可用于管理或概览所有已创建的任务。", - response_model=List[str], - responses={ - 200: { - "description": "成功返回任务ID列表。", - "content": {"application/json": {"example": ["b2865b93", "f4e2a1c8"]}} - } - } -) -async def service_get_task_list(): - """返回当前服务中所有任务的ID列表。""" - return JSONResponse(content=list(tasks_state.keys())) +@service_router.get("/default-params", tags=["Application"]) +def service_get_default_params(): return JSONResponse(content=default_params) - -@service_router.get( - "/default-params", - summary="获取默认翻译参数", - tags=["Application"], - description="返回一套默认的翻译参数，可用于填充前端表单的初始值。", - response_model=Dict[str, Union[str, int, float, bool]], - responses={ - 200: { - "description": "成功返回默认参数。", - "content": {"application/json": {"example": default_params}} - } - } -) -def service_get_default_params(): - """返回一套默认的翻译参数。""" - return JSONResponse(content=default_params) - - -@service_router.get( - "/meta", - summary="获取应用元信息", - tags=["Application"], - description="返回应用程序的元数据，例如当前版本号。", - response_model=Dict[str, str], - responses={ - 200: { - "description": "成功返回元信息。", - "content": {"application/json": {"example": {"version": "0.1.0"}}} - } - } -) -async def service_get_app_version(): - """返回应用版本号等元信息。""" - return JSONResponse(content={"version": __version__}) - - -# =================================================================== -# --- 应用主路由和启动 --- -# =================================================================== +@service_router.get("/meta", tags=["Application"]) +async def service_get_app_version(): return JSONResponse(content={"version": __version__}) @app.get("/", response_class=HTMLResponse, include_in_schema=False) async def main_page(): index_path = Path(STATIC_DIR) / "index.html" if not index_path.exists(): raise HTTPException(status_code=404, detail="index.html not found") - no_cache_headers = {"Cache-Control": "no-store, no-cache, must-revalidate, max-age=0", "Pragma": "no-cache", - "Expires": "0"} + no_cache_headers = {"Cache-Control": "no-store, no-cache, must-revalidate, max-age=0", "Pragma": "no-cache", "Expires": "0"} return FileResponse(index_path, headers=no_cache_headers) - @app.get("/admin", response_class=HTMLResponse, include_in_schema=False) async def main_page_admin(): index_path = Path(STATIC_DIR) / "index.html" if not index_path.exists(): raise HTTPException(status_code=404, detail="index.html not found") - no_cache_headers = {"Cache-Control": "no-store, no-cache, must-revalidate, max-age=0", "Pragma": "no-cache", - "Expires": "0"} + no_cache_headers = {"Cache-Control": "no-store, no-cache, must-revalidate, max-age=0", "Pragma": "no-cache", "Expires": "0"} return FileResponse(index_path, headers=no_cache_headers) - -###文档服务 @app.get("/docs", include_in_schema=False) async def custom_swagger_ui_html(): return get_swagger_ui_html( - openapi_url=app.openapi_url, - title=app.title + " - Swagger UI", + openapi_url=app.openapi_url, title=app.title + " - Swagger UI", oauth2_redirect_url=app.swagger_ui_oauth2_redirect_url, - swagger_js_url="/static/swagger/swagger.js", - swagger_css_url="/static/swagger/swagger.css", + swagger_js_url="/static/swagger/swagger.js", swagger_css_url="/static/swagger/swagger.css", ) - @app.get(app.swagger_ui_oauth2_redirect_url, include_in_schema=False) -async def swagger_ui_redirect(): - return get_swagger_ui_oauth2_redirect_html() - +async def swagger_ui_redirect(): return get_swagger_ui_oauth2_redirect_html() @app.get("/redoc", include_in_schema=False) async def redoc_html(): return get_redoc_html( - openapi_url=app.openapi_url, - title=app.title + " - ReDoc", + openapi_url=app.openapi_url, title=app.title + " - ReDoc", redoc_js_url="/static/redoc/redoc.js", ) - -### -@app.post("/temp/translate", - summary="[临时]同步翻译接口", - description="一个简单的、同步的翻译接口，用于快速测试。不涉及后台任务、状态管理或多格式输出。**不建议在生产环境中使用。**", - tags=["Temp"], - responses={ - 200: { - "description": "翻译成功或失败。", - "content": {"application/json": { - "examples": { - "success": { - "summary": "成功示例", - "value": {"success": True, "content": "# 翻译后的标题\n\n这是翻译后的内容..."} - }, - "failure": { - "summary": "失败示例", - "value": {"success": False, "reason": "Exception('API call failed with status 401')"} - } - } - }} - } - }) +@app.post("/temp/translate", tags=["Temp"]) async def temp_translate( - base_url: str = Body(..., description="LLM API的基础URL。", examples=["https://api.openai.com/v1"]), - api_key: str = Body(..., description="LLM API的密钥。", examples=["sk-xxxxxxxxxx"]), - model_id: str = Body(..., description="使用的模型ID。", examples=["gpt-4-turbo"]), - mineru_token: Optional[str] = Body(None, description="Mineru引擎的Token。"), - file_name: str = Body(..., - description="文件名，用以判断文件类型。", - examples=["test.txt", "test.md", "test.pdf"]), - file_content: str = Body(..., description="文件内容，可以是纯文本或Base64编码的字符串。"), - to_lang: str = Body("中文", description="目标语言。", examples=["中文", "英文", "English"]), - concurrent: int = Body(default_params["concurrent"], description="ai翻译请求并发数"), - temperature: float = Body(default_params["temperature"], description="ai翻译请求温度"), - thinking: ThinkingMode = Body(default_params["thinking"], description="是否启用深度思考", - examples=["default", "enable", "disable"]), - chunk_size: int = Body(default_params["chunk_size"], description="文本分块大小（bytes）"), - custom_prompt: Optional[str] = Body(None, description="翻译自定义提示词", - examples=["人名保持原文不翻译"]), + base_url: str = Body(...), api_key: str = Body(...), model_id: str = Body(...), + mineru_token: Optional[str] = Body(None), file_name: str = Body(...), file_content: str = Body(...), + to_lang: str = Body("中文"), concurrent: int = Body(default_params["concurrent"]), + temperature: float = Body(default_params["temperature"]), thinking: ThinkingMode = Body(default_params["thinking"]), + chunk_size: int = Body(default_params["chunk_size"]), custom_prompt: Optional[str] = Body(None), ): - """一个用于快速测试的同步翻译接口。""" file_name = Path(file_name) + try: decoded_content = base64.b64decode(file_content) + except (ValueError, binascii.Error): decoded_content = file_content.encode('utf-8') try: - decoded_content = base64.b64decode(file_content) - except (ValueError, binascii.Error): - decoded_content = file_content.encode('utf-8') - - try: - workflow_config = MarkdownBasedWorkflowConfig(convert_engine="mineru", - converter_config=ConverterMineruConfig(mineru_token=mineru_token), - translator_config=MDTranslatorConfig(base_url=base_url, - api_key=api_key, - model_id=model_id, - to_lang=to_lang, - custom_prompt=custom_prompt, - temperature=temperature, - thinking=thinking, - chunk_size=chunk_size, - concurrent=concurrent), - html_exporter_config=MD2HTMLExporterConfig()) + workflow_config = MarkdownBasedWorkflowConfig( + convert_engine="mineru", converter_config=ConverterMineruConfig(mineru_token=mineru_token), + translator_config=MDTranslatorConfig(base_url=base_url, api_key=api_key, model_id=model_id, + to_lang=to_lang, custom_prompt=custom_prompt, temperature=temperature, + thinking=thinking, chunk_size=chunk_size, concurrent=concurrent), + html_exporter_config=MD2HTMLExporterConfig() + ) workflow = MarkdownBasedWorkflow(workflow_config) - workflow.read_bytes(content=decoded_content, stem=file_name.stem, suffix=file_name.stem) + workflow.read_bytes(content=decoded_content, stem=file_name.stem, suffix=file_name.suffix) # Fixed suffix + await workflow.translate_async() return {"success": True, "content": workflow.export_to_markdown()} except Exception as e: global_logger.error(f"临时翻译接口出现错误：{e.__repr__()}", exc_info=True) @@ -1198,8 +895,6 @@ async def temp_translate( app.include_router(service_router) - -# --- 启动逻辑 (无修改) --- def find_free_port(start_port): port = start_port while True: @@ -1207,7 +902,6 @@ def find_free_port(start_port): if sock.connect_ex(('127.0.0.1', port)) != 0: return port port += 1 - def run_app(port: int | None = None): initial_port = port or int(os.environ.get("DOCUTRANSLATE_PORT", 8010)) try: @@ -1216,10 +910,9 @@ def run_app(port: int | None = None): print(f"正在启动 DocuTranslate WebUI 版本号：{__version__}\n") print(f"服务接口文档: http://127.0.0.1:{port_to_use}/docs\n") print(f"请用浏览器访问 http://127.0.0.1:{port_to_use}\n") - uvicorn.run(app, host=None, port=port_to_use, workers=1) + uvicorn.run(app, host="0.0.0.0", port=port_to_use, workers=1) # Changed host to 0.0.0.0 for better accessibility except Exception as e: print(f"启动失败: {e}") - if __name__ == "__main__": run_app() \ No newline at end of file diff --git a/docutranslate/static/index.html b/docutranslate/static/index.html index 4dc6034..3473bef 100644 --- a/docutranslate/static/index.html +++ b/docutranslate/static/index.html @@ -1 +1 @@ -
GitHub主页(欢迎star❤):
https://github.com/xunbu/docutranslate
交流QQ群: 1047781902
当前没有任务，点击“新建任务”开始吧！
等待提交...
点击或拖拽文件到此处
GitHub主页(欢迎star❤):
https://github.com/xunbu/docutranslate
交流QQ群: 1047781902
当前没有任务，点击“新建任务”开始吧！
等待提交...
点击或拖拽文件到此处