From 1a27efb3cd27d0a0eb19afe9f3c6919cb76635ec Mon Sep 17 00:00:00 2001 From: xunbu Date: Sat, 23 Aug 2025 18:07:18 +0800 Subject: [PATCH] =?UTF-8?q?=E6=94=AF=E6=8C=81csv?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- docutranslate/app.py | 33 ++- docutranslate/exporter/md/md2html_exporter.py | 4 +- docutranslate/static/i18nData.json | 252 ++++++++---------- docutranslate/static/index.html | 2 +- 4 files changed, 148 insertions(+), 143 deletions(-) diff --git a/docutranslate/app.py b/docutranslate/app.py index 9ca9bbd..730ab5a 100644 --- a/docutranslate/app.py +++ b/docutranslate/app.py @@ -33,7 +33,7 @@ from docutranslate.workflow.html_workflow import HtmlWorkflow, HtmlWorkflowConfi # --- HTML WORKFLOW IMPORT END --- from docutranslate.workflow.interfaces import DocxExportable, EpubExportable from docutranslate.workflow.interfaces import HTMLExportable, MDFormatsExportable, TXTExportable, JsonExportable, \ - XlsxExportable, SrtExportable + XlsxExportable, SrtExportable, CsvExportable from docutranslate.workflow.json_workflow import JsonWorkflow, JsonWorkflowConfig from docutranslate.workflow.md_based_workflow import MarkdownBasedWorkflow, MarkdownBasedWorkflowConfig from docutranslate.workflow.srt_workflow import SrtWorkflow, SrtWorkflowConfig @@ -849,6 +849,25 @@ async def service_release_task(task_id: str): } } }, + "completed_xlsx": { + "summary": "已完成 (XLSX)", + "value": { + "task_id": "d7e8f9a0", + "is_processing": False, + "status_message": "翻译成功！用时 18.99 秒。", + "error_flag": False, + "download_ready": True, + "original_filename_stem": "sales_data", + "original_filename": "sales_data.xlsx", + "task_start_time": 1678889600.0, + "task_end_time": 1678889618.99, + "downloads": { + "xlsx": "/service/download/d7e8f9a0/xlsx", + "csv": "/service/download/d7e8f9a0/csv", + "html": "/service/download/d7e8f9a0/html" + } + } + }, "completed_docx": { "summary": "已完成 (DOCX)", "value": { @@ -929,6 +948,8 @@ async def service_get_status( downloads["json"] = f"/service/download/{task_id}/json" if isinstance(workflow, XlsxExportable): downloads["xlsx"] = f"/service/download/{task_id}/xlsx" + if isinstance(workflow, CsvExportable): + downloads["csv"] = f"/service/download/{task_id}/csv" if isinstance(workflow, DocxExportable): downloads["docx"] = f"/service/download/{task_id}/docx" if isinstance(workflow, SrtExportable): @@ -969,7 +990,7 @@ async def service_get_logs(task_id: str): return JSONResponse(content={"logs": new_logs}) -FileType = Literal["markdown", "markdown_zip", "html", "txt", "json", "xlsx", "docx", "srt", "epub"] +FileType = Literal["markdown", "markdown_zip", "html", "txt", "json", "xlsx", "csv", "docx", "srt", "epub"] async def _get_content_from_workflow(task_id: str, file_type: FileType) -> tuple[bytes, str, str]: @@ -1036,6 +1057,9 @@ async def _get_content_from_workflow(task_id: str, file_type: FileType) -> tuple elif file_type == 'xlsx' and isinstance(workflow, XlsxExportable): content_bytes = await asyncio.to_thread(workflow.export_to_xlsx) media_type, filename = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", f"{filename_stem}_translated.xlsx" + elif file_type == 'csv' and isinstance(workflow, CsvExportable): + content_bytes = await asyncio.to_thread(workflow.export_to_csv) + media_type, filename = "text/csv; charset=utf-8", f"{filename_stem}_translated.csv" elif file_type == 'docx' and isinstance(workflow, DocxExportable): content_bytes = await asyncio.to_thread(workflow.export_to_docx) media_type, filename = "application/vnd.openxmlformats-officedocument.wordprocessingml.document", f"{filename_stem}_translated.docx" @@ -1065,6 +1089,7 @@ async def _get_content_from_workflow(task_id: str, file_type: FileType) -> tuple "text/html; charset=utf-8": {"schema": {"type": "string"}}, "text/markdown; charset=utf-8": {"schema": {"type": "string"}}, "text/plain; charset=utf-8": {"schema": {"type": "string"}}, + "text/csv; charset=utf-8": {"schema": {"type": "string"}}, "application/zip": {"schema": {"type": "string", "format": "binary"}}, "application/json": {"schema": {"type": "string", "format": "binary"}}, "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": { @@ -1082,7 +1107,7 @@ async def _get_content_from_workflow(task_id: str, file_type: FileType) -> tuple async def service_download_file( task_id: str = FastApiPath(..., description="已完成任务的ID", examples=["b2865b93"]), file_type: FileType = FastApiPath(..., description="要下载的文件类型。", - examples=["html", "json", "docx", "srt", "epub"]) + examples=["html", "json", "csv", "docx", "srt", "epub"]) ): content, media_type, filename = await _get_content_from_workflow(task_id, file_type) headers = {"Content-Disposition": f"attachment; filename*=UTF-8''{quote(filename, safe='', encoding='utf-8')}"} @@ -1135,7 +1160,7 @@ async def service_download_file( 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", "docx", "srt", "epub"]) + examples=["html", "json", "csv", "docx", "srt", "epub"]) ): content, _, filename = await _get_content_from_workflow(task_id, file_type) diff --git a/docutranslate/exporter/md/md2html_exporter.py b/docutranslate/exporter/md/md2html_exporter.py index 0dda690..ee06ce2 100644 --- a/docutranslate/exporter/md/md2html_exporter.py +++ b/docutranslate/exporter/md/md2html_exporter.py @@ -113,8 +113,8 @@ if __name__ == '__main__': from pathlib import Path # d = Document.from_path(r"C:\Users\jxgm\Desktop\mcp文件夹\学习笔记\互联网认证授权机制\互联网认证授权机制.md") - d = Document.from_path(r"C:\Users\jxgm\Desktop\matrixcookbook_translated.md") - + d = Document.from_path(r"C:\Users\jxgm\Desktop\matrixcalc_translated.md") + # d = Document.from_path(r"C:\Users\jxgm\Downloads\3a8d8999-3e9d-4f32-a32c-5b0830bb4320\full.md") exporter = MD2HTMLExporter() d1 = exporter.export(d) path = Path(r"C:\Users\jxgm\Desktop\a.html") diff --git a/docutranslate/static/i18nData.json b/docutranslate/static/i18nData.json index 35b0ea0..4533d7f 100644 --- a/docutranslate/static/i18nData.json +++ b/docutranslate/static/i18nData.json @@ -4,46 +4,48 @@ "tutorialBtn": "教程", "projectContributeBtn": "项目协作", "workflowTitle": "1. 选择工作流", - "workflowTitleText": "选择工作流", "workflowOptionMarkdown": "转Markdown再翻译 (.pdf/.md/.png等)", "workflowOptionTxt": "纯文本翻译 (.txt)", "workflowOptionJson": "JSON翻译 (.json)", "workflowOptionDocx": "DOCX翻译 (.docx)", - "workflowOptionXlsx": "XLSX翻译 (.xlsx)", + "workflowOptionXlsx": "XLSX翻译 (.xlsx/.csv)", "workflowOptionSrt": "SRT字幕翻译 (.srt)", "workflowOptionEpub": "EPUB翻译 (.epub)", "workflowOptionHtml": "HTML翻译 (.html)", "autoWorkflowLabel": "自动选择工作流", "docxSettingsTitleText": "DOCX翻译选项", + "xlsxSettingsTitleText": "XLSX翻译选项", + "srtSettingsTitleText": "SRT翻译选项", + "epubSettingsTitleText": "EPUB翻译选项", + "htmlSettingsTitleText": "HTML翻译选项", + "jsonSettingsTitleText": "JSON路径配置", + "parsingSettingsTitleText": "解析配置", + "aiSettingsTitleText": "翻译模型", + "translationSettingsTitleText": "翻译配置", + "advancedSettingsTitleText": "高级参数", "insertModeLabel": "插入模式", "insertModeReplace": "替换原文 (Replace)", "insertModeAppend": "附加到原文后 (Append)", "insertModePrepend": "附加到原文前 (Prepend)", "insertModeHelpDocx": "选择如何将翻译后的文本插入。", + "insertModeHelpXlsx": "选择如何将翻译后的文本插入到单元格中。", + "insertModeHelpSrt": "选择如何将翻译后的文本插入。", + "insertModeHelpEpub": "选择如何将翻译后的文本插入。", + "insertModeHelpHtml": "选择如何将翻译后的文本插入。", "separatorLabel": "分隔符", "separatorPlaceholder": "例如: \\n---翻译---\\n", "separatorPlaceholderSimple": "例如: \\n---\\n", "separatorHelp": "当插入模式为附加或前置时，用于分隔原文和译文的字符。\\n 代表换行。", - "xlsxSettingsTitleText": "XLSX翻译选项", - "insertModeHelpXlsx": "选择如何将翻译后的文本插入到单元格中。", "xlsxTranslateRegionsLabel": "翻译区域 (可选)", "xlsxTranslateRegionsPlaceholder": "每行一个区域, 例如:Sheet1!A1:B10（不指定表名则对所有表生效）", - "srtSettingsTitleText": "SRT翻译选项", - "insertModeHelpSrt": "选择如何将翻译后的文本插入。", - "epubSettingsTitleText": "EPUB翻译选项", - "insertModeHelpEpub": "选择如何将翻译后的文本插入。", - "htmlSettingsTitleText": "HTML翻译选项", - "insertModeHelpHtml": "选择如何将翻译后的文本插入。", - "jsonSettingsTitleText": "JSON路径配置", "jsonPathLabel": "需要翻译的JSON路径", "jsonPathPlaceholder": "每行一个路径, 例如:\n$.name\n$.*", "jsonPathHelp": "采用jsonpath-ng的路径选择语法，每一行表示一个json路径", - "parsingSettingsTitleText": "解析配置", "parsingEngineLabel": "解析引擎", "parsingEngineHelp": "如果上传的文件本身是.md格式，此项可不选。", - "engineOptionIdentity": "不使用引擎 (源文件为MD)", - "engineOptionMineru": "minerU (云端, 推荐)", - "engineOptionDocling": "Docling (本地)", + "engineOptionIdentity": "不解析（用于.md文件）", + "engineOptionMineru": "Mineru（推荐，用于PDF/图片）", + "engineOptionDocling": "DocLing（备用，用于PDF）", "getMineruTokenTitle": "获取Mineru Token", "mineruTokenPlaceholder": "使用Mineru引擎时需要", "modelVersionLabel": "Mineru 模型版本", @@ -52,7 +54,6 @@ "modelVersionHelp": "mineru VLM是更新的内测模型。", "formulaOcrLabel": "公式识别", "codeOcrLabel": "代码识别", - "aiSettingsTitleText": "翻译模型", "platformLabel": "选择平台", "platformCustom": "自定义接口", "baseUrlLabel": "API 地址 (Base URL)", @@ -61,7 +62,6 @@ "apiKeyPlaceholder": "请输入您的API Key", "modelIdLabel": "模型 ID", "modelIdPlaceholder": "例如: gpt-4o, glm-4", - "translationSettingsTitleText": "翻译配置", "targetLanguageLabel": "目标语言", "targetLanguageCustom": "其它 (自定义)", "customLangPlaceholder": "请输入目标语言, 例如: Italian", @@ -72,11 +72,10 @@ "thinkingModeDefault": "默认", "customPromptLabel": "自定义Prompt", "customPromptPlaceholder": "可选，如“人名保持原文不翻译”", - "advancedSettingsTitleText": "高级参数", "chunkSizeLabel": "分块大小", "concurrentLabel": "并发数", "resetBtn": "重置", - "githubInfo": "GitHub主页(欢迎star❤):
https://github.com/xunbu/docutranslate", + "githubInfo": "GitHub主页(欢迎star❤):
https://github.com/xunbu/docutranslate", "qqGroupInfo": "交流QQ群: 1047781902", "taskListTitle": "任务列表", "newTaskBtn": "新建任务", @@ -85,7 +84,7 @@ "taskCardIdPlaceholder": "等待提交...", "taskCardFileDrop": "点击或拖拽文件到此处", "taskCardFileSelected": "文件已选择", - "taskCardFilenameLabel": "文件名:", + "taskCardFilenameLabel": "文件名: ", "taskCardLogLabel": "日志", "taskCardStatusWaiting": "等待上传文件...", "taskCardPreviewBtn": "预览", @@ -93,14 +92,6 @@ "taskCardStartBtn": "开始翻译", "downloadMdEmbedded": "Markdown(嵌图)", "downloadMdZip": "Markdown压缩包", - "downloadTxt": "TXT", - "downloadJson": "JSON", - "downloadDocx": "DOCX", - "downloadXlsx": "XLSX", - "downloadSrt": "SRT", - "downloadEpub": "EPUB", - "downloadHtml": "HTML", - "downloadPdf": "PDF", "previewTitle": "预览", "previewBilingualBtn": "双语", "previewTranslatedOnlyBtn": "仅译文", @@ -109,7 +100,7 @@ "closeBtn": "关闭", "downloadBtn": "下载", "tutorialModalTitle": "使用教程", - "tutorialModalBody": "

视频教程可以在B站搜索 docutranslate 获取。

欢迎使用 DocuTranslate！请按照以下步骤完成文档翻译：

  1. 选择工作流

    首先，在配置面板顶部选择您需要的翻译流程。不同的工作流适用于不同类型的文件：

    • 转Markdown再翻译: 适用于翻译PDF、markdown、图片等文件。
    • 纯文本翻译: 用于翻译 .txt 等纯文本文件。
    • JSON翻译: 用于翻译 .json 文件中的特定字段。
    • DOCX翻译: 用于翻译 .docx 文件。
    • XLSX翻译: 用于翻译 .xlsx 电子表格文件。
    • SRT字幕翻译: 用于翻译 .srt 字幕文件。
    • EPUB翻译: 用于翻译 .epub 电子书文件。
    • HTML翻译: 用于翻译 .html 文件。
    新增功能: \"自动选择工作流\"开关已默认开启。您只需上传文件，系统会自动为您匹配合适的工作流，简化操作。

  2. 配置参数

    根据您选择的工作流，完成相应的配置。所有配置项都会自动保存在您的浏览器中。

    • 解析配置 (仅在“转Markdown再翻译”工作流下显示):
      • 解析引擎: 选择一个引擎将您的文件（如PDF）转换为适合翻译的Markdown格式。如果您的文件已经是Markdown格式，则无需选择。
      • Mineru Token: 如果您选择 minerU 引擎，需要在此处填入您的Token。
    • DOCX/XLSX/SRT/EPUB/HTML翻译选项 (在对应工作流下显示):
      • 插入模式: 定义翻译结果如何放入文档或字幕。您可以选择直接“替换”原文，或是在原文之后“附加”，或是在原文之前“前置”。
      • 分隔符: 当选择“附加”或“前置”模式时，此项用于在原文和译文之间插入分隔符。
    • JSON路径配置 (仅在“JSON翻译”工作流下显示):
      • 需要翻译的JSON路径: 每行输入一个 JSONPath 表达式，指定需要翻译的字段。
      • 例如:$..description翻译所有键为description的值。$.items[0].name翻译第一个item的name值。
    • 翻译模型:
      • 选择平台/API 地址/API Key/模型 ID: 配置您希望使用的AI翻译服务。
      • 模型ID参考平台文档，建议使用非推理模型或混合推理模型（关闭思考）。
    • 翻译配置:
      • 目标语言/自定义Prompt: 指定翻译的目标语言和附加指令。
      • 思考模式:设置混合推理模型是否进行思考，目前支持智谱的glm4.5系列、阿里云的qwen3系列、火山引擎的seed1.6系列，建议选择禁用思考。
    • 高级参数:
      • 分块大小/并发数/Temperature: 发给ai的分块大小、并发请求数和温度，通常保持默认即可。
  3. 上传文件

    在右侧的任务列表中，点击或拖拽您的文档到文件上传区域。

  4. 开始翻译

    文件选择成功后，点击任务卡片右下角的 开始翻译 按钮。系统将开始处理任务，您可以在日志区域查看实时进度。

  5. 查看与下载

    翻译完成后，任务卡片下方会出现操作按钮：

    • 预览: 在右侧滑出的面板中进行原文和译文的对照预览（仅作参考）。
    • 下载: 下载包括 PDF, DOCX, XLSX, HTML, Markdown 等多种格式的译文。
提示: 所有配置都会自动保存在您的浏览器本地，方便下次使用。
", + "tutorialModalBody": "

视频教程可以在B站搜索 docutranslate 获取。

欢迎使用 DocuTranslate！请按照以下步骤完成文档翻译：

  1. 选择工作流

    首先，在配置面板顶部选择您需要的翻译流程。不同的工作流适用于不同类型的文件：

    • 转Markdown再翻译: 适用于翻译PDF、markdown、图片等文件。
    • 纯文本翻译: 用于翻译 .txt 等纯文本文件。
    • JSON翻译: 用于翻译 .json 文件中的特定字段。
    • DOCX翻译: 用于翻译 .docx 文件。
    • XLSX翻译: 用于翻译 .xlsx 电子表格、 .csv 文件。
    • SRT字幕翻译: 用于翻译 .srt 字幕文件。
    • EPUB翻译: 用于翻译 .epub 电子书文件。
    • HTML翻译: 用于翻译 .html 文件。
    新增功能: \"自动选择工作流\"开关已默认开启。您只需上传文件，系统会自动为您匹配合适的工作流，简化操作。

  2. 配置参数

    根据您选择的工作流，完成相应的配置。所有配置项都会自动保存在您的浏览器中。

    • 解析配置 (仅在“转Markdown再翻译”工作流下显示):
      • 解析引擎: 选择一个引擎将您的文件（如PDF）转换为适合翻译的Markdown格式。如果您的文件已经是Markdown格式，则无需选择。
      • Mineru Token: 如果您选择 minerU 引擎，需要在此处填入您的Token。
    • DOCX/XLSX/SRT/EPUB/HTML翻译选项 (在对应工作流下显示):
      • 插入模式: 定义翻译结果如何放入文档或字幕。您可以选择直接“替换”原文，或是在原文之后“附加”，或是在原文之前“前置”。
      • 分隔符: 当选择“附加”或“前置”模式时，此项用于在原文和译文之间插入分隔符。
    • JSON路径配置 (仅在“JSON翻译”工作流下显示):
      • 需要翻译的JSON路径: 每行输入一个 JSONPath 表达式，指定需要翻译的字段。
      • 例如:$..description翻译所有键为description的值。$.items[0].name翻译第一个item的name值。
    • 翻译模型:
      • 选择平台/API 地址/API Key/模型 ID: 配置您希望使用的AI翻译服务。
      • 模型ID参考平台文档，建议使用非推理模型或混合推理模型（关闭思考）。
    • 翻译配置:
      • 目标语言/自定义Prompt: 指定翻译的目标语言和附加指令。
      • 思考模式:设置混合推理模型是否进行思考，目前支持智谱的glm4.5系列、阿里云的qwen3系列、火山引擎的seed1.6系列，建议选择禁用思考。
    • 高级参数:
      • 分块大小/并发数/Temperature: 发给ai的分块大小、并发请求数和温度，通常保持默认即可。
  3. 上传文件

    在右侧的任务列表中，点击或拖拽您的文档到文件上传区域。

  4. 开始翻译

    文件选择成功后，点击任务卡片右下角的 开始翻译 按钮。系统将开始处理任务，您可以在日志区域查看实时进度。

  5. 查看与下载

    翻译完成后，任务卡片下方会出现操作按钮：

    • 预览: 在右侧滑出的面板中进行原文和译文的对照预览（仅作参考）。
    • 下载: 下载包括 PDF, DOCX, XLSX, HTML, Markdown 等多种格式的译文。
提示: 所有配置都会自动保存在您的浏览器本地，方便下次使用。
", "tutorialUnderstandBtn": "我明白了", "contributorsModalTitle": "感谢贡献", "contributorsPara1": "DocuTranslate是一个开源项目！大家的需求与使用是项目进步的动力。", @@ -119,139 +110,129 @@ "contributorsPR": "提交 Pull Request", "contributorsIssue": "报告 Issue", "contributorsQQ": "或者通过QQ群联系作者：1047781902", - "status_selectFileFirst": "请先选择一个文件。", - "status_invalidWorkflow": "无效的工作流类型。", - "status_fillRequired": "请填写所有必填的设置项。", - "status_releasingOldTask": "正在重新翻译，释放旧任务资源...", - "status_encodingAndSubmitting": "正在编码文件并提交任务...", - "status_requestOk": "任务已开始，正在处理...", - "status_requestFail": "请求失败", - "status_initFail": "启动失败", - "status_cancelling": "正在取消...", - "status_cancelSent": "取消请求已发送。", - "status_cancelFail": "取消失败", - "status_updateError": "状态更新出错。", - "status_gettingStatus": "正在获取状态...", - "preview_loading": "

正在加载译文...

", - "preview_loadFailed": "

加载译文失败

", - "preview_cantReadOriginal": "无法读取原文内容。", - "preview_cantPreviewType": "无法直接预览此文件类型", - "preview_noOriginalCache": "未找到原文文件缓存。", - "preview_bilingual": "双语预览", - "preview_translatedOnly": "译文预览", - "pdf_preparing": "PDF准备中，请稍后...", - "pdf_print_failed": "自动打印失败，请在预览中手动打印。", - "pdf_fetch_failed": "获取HTML内容失败，无法生成PDF。", "init_i18n_failed_alert": "加载界面翻译资源失败，请检查网络连接或联系管理员。", "init_failed_alert": "初始化失败，无法连接到后端服务。请检查服务是否运行或刷新页面。", - "admin_tasklist_failed": "无法从服务器加载任务列表，请检查后台连接。", - "btn_startTranslation": "开始翻译", - "btn_initializing": "初始化...", + "status_selectFileFirst": "请先选择一个文件。", + "status_invalidWorkflow": "选择的工作流无效。", + "status_fillRequired": "请填写所有必填项。", + "status_releasingOldTask": "正在释放旧任务...", + "btn_initializing": "初始化中", + "status_encodingAndSubmitting": "正在编码和提交文件...", + "status_requestOk": "请求成功，任务已开始处理。", "btn_cancelTranslation": "取消翻译", - "btn_reTranslate": "重新翻译" + "status_requestFail": "请求失败", + "status_initFail": "初始化失败", + "status_cancelling": "取消中...", + "status_cancelSent": "已发送取消请求。", + "status_cancelFail": "取消请求失败", + "status_gettingStatus": "正在获取状态...", + "btn_reTranslate": "重新翻译", + "status_updateError": "状态更新失败。", + "preview_loading": "正在加载预览...", + "preview_cantReadOriginal": "无法读取原始文件内容。", + "preview_cantPreviewType": "无法预览此文件类型", + "preview_noOriginalCache": "无原始文件缓存可供预览。", + "preview_loadFailed": "加载预览失败。", + "pdf_preparing": "正在准备PDF以便打印...", + "pdf_print_failed": "调用打印功能失败。请检查浏览器设置或手动打印。", + "pdf_fetch_failed": "获取翻译内容失败，无法生成PDF。", + "preview_bilingual": "双语对照预览", + "preview_translatedOnly": "仅译文预览", + "admin_tasklist_failed": "管理员模式：加载任务列表失败" }, "en": { "pageTitle": "DocuTranslate - Interactive Document Translation", "tutorialBtn": "Tutorial", "projectContributeBtn": "Contribute", "workflowTitle": "1. Select Workflow", - "workflowTitleText": "Select Workflow", - "workflowOptionMarkdown": "Markdown-based (.pdf/.md/.png, etc.)", - "workflowOptionTxt": "Plain Text (.txt)", - "workflowOptionJson": "JSON (.json)", - "workflowOptionDocx": "DOCX (.docx)", - "workflowOptionXlsx": "XLSX (.xlsx)", - "workflowOptionSrt": "SRT Subtitle (.srt)", - "workflowOptionEpub": "EPUB (.epub)", - "workflowOptionHtml": "HTML (.html)", + "workflowOptionMarkdown": "To Markdown then Translate (.pdf/.md/.png, etc.)", + "workflowOptionTxt": "Plain Text Translation (.txt)", + "workflowOptionJson": "JSON Translation (.json)", + "workflowOptionDocx": "DOCX Translation (.docx)", + "workflowOptionXlsx": "XLSX Translation (.xlsx/.csv)", + "workflowOptionSrt": "SRT Subtitle Translation (.srt)", + "workflowOptionEpub": "EPUB Translation (.epub)", + "workflowOptionHtml": "HTML Translation (.html)", "autoWorkflowLabel": "Auto-select workflow", "docxSettingsTitleText": "DOCX Translation Options", - "insertModeLabel": "Insert Mode", - "insertModeReplace": "Replace original", - "insertModeAppend": "Append after original", - "insertModePrepend": "Prepend before original", - "insertModeHelpDocx": "Choose how to insert the translated text.", - "separatorLabel": "Separator", - "separatorPlaceholder": "e.g., \\n---translation---\\n", - "separatorPlaceholderSimple": "e.g., \\n---\\n", - "separatorHelp": "Characters to separate original and translated text in append/prepend modes. \\n for new line.", "xlsxSettingsTitleText": "XLSX Translation Options", - "insertModeHelpXlsx": "Choose how to insert translated text into cells.", - "xlsxTranslateRegionsLabel": "Translation area (optional)", - "xlsxTranslateRegionsPlaceholder": "One area per line, for example: Sheet1!A1:B10 (if no sheet name is specified, it applies to all sheets)", "srtSettingsTitleText": "SRT Translation Options", - "insertModeHelpSrt": "Choose how to insert the translated text.", "epubSettingsTitleText": "EPUB Translation Options", - "insertModeHelpEpub": "Choose how to insert the translated text.", "htmlSettingsTitleText": "HTML Translation Options", - "insertModeHelpHtml": "Choose how to insert the translated text.", "jsonSettingsTitleText": "JSON Path Configuration", - "jsonPathLabel": "JSON paths to translate", - "jsonPathPlaceholder": "One path per line, e.g.:\n$.name\n$.*", - "jsonPathHelp": "Uses jsonpath-ng syntax. Each line represents one JSON path.", "parsingSettingsTitleText": "Parsing Configuration", + "aiSettingsTitleText": "Translation Model", + "translationSettingsTitleText": "Translation Configuration", + "advancedSettingsTitleText": "Advanced Parameters", + "insertModeLabel": "Insert Mode", + "insertModeReplace": "Replace original text", + "insertModeAppend": "Append after original text", + "insertModePrepend": "Prepend before original text", + "insertModeHelpDocx": "Choose how to insert the translated text.", + "insertModeHelpXlsx": "Choose how to insert the translated text into cells.", + "insertModeHelpSrt": "Choose how to insert the translated text.", + "insertModeHelpEpub": "Choose how to insert the translated text.", + "insertModeHelpHtml": "Choose how to insert the translated text.", + "separatorLabel": "Separator", + "separatorPlaceholder": "e.g., \\n---translated---\\n", + "separatorPlaceholderSimple": "e.g., \\n---\\n", + "separatorHelp": "Characters to separate original and translated text in 'append' or 'prepend' mode. \\n represents a new line.", + "xlsxTranslateRegionsLabel": "Translate Regions (Optional)", + "xlsxTranslateRegionsPlaceholder": "One region per line, e.g., Sheet1!A1:B10 (applies to all sheets if sheet name is omitted)", + "jsonPathLabel": "JSON Paths to Translate", + "jsonPathPlaceholder": "One path per line, e.g.:\n$.name\n$.*", + "jsonPathHelp": "Uses jsonpath-ng syntax. Each line represents a JSON path to translate.", "parsingEngineLabel": "Parsing Engine", - "parsingEngineHelp": "Optional if your file is already in .md format.", - "engineOptionIdentity": "No engine (source is MD)", - "engineOptionMineru": "minerU (Cloud, Recommended)", - "engineOptionDocling": "Docling (Local)", + "parsingEngineHelp": "Not required if you are uploading a .md file directly.", + "engineOptionIdentity": "No parsing (for .md files)", + "engineOptionMineru": "Mineru (Recommended for PDF/Image)", + "engineOptionDocling": "DocLing (Alternative for PDF)", "getMineruTokenTitle": "Get Mineru Token", - "mineruTokenPlaceholder": "Required for Mineru engine", + "mineruTokenPlaceholder": "Required when using Mineru engine", "modelVersionLabel": "Mineru Model Version", "modelVersionVlm": "VLM", "modelVersionPipline": "Pipeline", - "modelVersionHelp": "Mineru VLM is a newer internal beta model.", + "modelVersionHelp": "Mineru VLM is a newer, internal test model.", "formulaOcrLabel": "Formula Recognition", "codeOcrLabel": "Code Recognition", - "aiSettingsTitleText": "Translation Model", "platformLabel": "Select Platform", "platformCustom": "Custom Endpoint", "baseUrlLabel": "API Base URL", "baseUrlPlaceholder": "OpenAI-compatible URL", "getApiKeyTitle": "Get API Key", - "apiKeyPlaceholder": "Enter your API Key", + "apiKeyPlaceholder": "Please enter your API Key", "modelIdLabel": "Model ID", "modelIdPlaceholder": "e.g., gpt-4o, glm-4", - "translationSettingsTitleText": "Translation Configuration", "targetLanguageLabel": "Target Language", "targetLanguageCustom": "Other (Custom)", "customLangPlaceholder": "Enter target language, e.g., Italian", "thinkingModeLabel": "Thinking Mode", - "thinkingModeTooltip": "Set the thinking mode for mixed-inference models. Currently supports Zhipu's glm-4.5 series, Alibaba Cloud's qwen3 series, VolcEngine's Doubao-Seed-1.6 series, etc.", + "thinkingModeTooltip": "Sets the thinking mode for hybrid inference models, currently supporting Zhipu's glm-4.5 series, Alibaba Cloud's qwen3 series, Volcengine's Doubao-Seed-1.6 series, etc.", "thinkingModeEnable": "Enable", "thinkingModeDisable": "Disable", "thinkingModeDefault": "Default", "customPromptLabel": "Custom Prompt", - "customPromptPlaceholder": "Optional, e.g., 'Do not translate proper names'", - "advancedSettingsTitleText": "Advanced Parameters", + "customPromptPlaceholder": "Optional, e.g., 'Do not translate proper names.'", "chunkSizeLabel": "Chunk Size", "concurrentLabel": "Concurrency", "resetBtn": "Reset", - "githubInfo": "GitHub (star us ❤):
https://github.com/xunbu/docutranslate", - "qqGroupInfo": "QQ Group for discussions: 1047781902", + "githubInfo": "GitHub Page (stars❤ welcome):
https://github.com/xunbu/docutranslate", + "qqGroupInfo": "QQ Group for discussion: 1047781902", "taskListTitle": "Task List", "newTaskBtn": "New Task", - "noTaskPlaceholder": "No tasks yet. Click 'New Task' to start!", + "noTaskPlaceholder": "No tasks yet. Click 'New Task' to get started!", "taskCardIdLabel": "Task ID", "taskCardIdPlaceholder": "Waiting for submission...", "taskCardFileDrop": "Click or drag file here", "taskCardFileSelected": "File selected", - "taskCardFilenameLabel": "Filename:", - "taskCardLogLabel": "Logs", + "taskCardFilenameLabel": "Filename: ", + "taskCardLogLabel": "Log", "taskCardStatusWaiting": "Waiting for file upload...", "taskCardPreviewBtn": "Preview", "taskCardDownloadBtn": "Download", "taskCardStartBtn": "Start Translation", "downloadMdEmbedded": "Markdown (Embedded Img)", - "downloadMdZip": "Markdown (.zip)", - "downloadTxt": "TXT", - "downloadJson": "JSON", - "downloadDocx": "DOCX", - "downloadXlsx": "XLSX", - "downloadSrt": "SRT", - "downloadEpub": "EPUB", - "downloadHtml": "HTML", - "downloadPdf": "PDF", + "downloadMdZip": "Markdown ZIP", "previewTitle": "Preview", "previewBilingualBtn": "Bilingual", "previewTranslatedOnlyBtn": "Translated Only", @@ -259,46 +240,45 @@ "previewTranslated": "Translation", "closeBtn": "Close", "downloadBtn": "Download", - "tutorialModalTitle": "Tutorial", - "tutorialModalBody": "

Video tutorials can be found by searching docutranslate on Bilibili.

Welcome to DocuTranslate! Follow these steps to translate your documents:

  1. Select Workflow

    First, choose the translation process you need from the top of the settings panel. Different workflows are for different file types:

    • Markdown-based: For translating PDF, markdown, images, etc.
    • Plain Text: For translating .txt and other plain text files.
    • JSON: For translating specific fields in .json files.
    • DOCX: For translating .docx files.
    • XLSX: For translating .xlsx spreadsheet files.
    • SRT Subtitle: For translating .srt subtitle files.
    • EPUB: For translating .epub ebook files.
    • HTML: For translating .html files.
    New Feature: \"Auto-select workflow\" is on by default. Just upload your file, and the system will automatically pick the right workflow for you, simplifying the process.

  2. Configure Parameters

    Based on your chosen workflow, complete the necessary settings. All settings are automatically saved in your browser.

    • Parsing Configuration (Only for \"Markdown-based\" workflow):
      • Parsing Engine: Choose an engine to convert your file (like a PDF) into a translation-friendly Markdown format. Not needed if your file is already Markdown.
      • Mineru Token: If you select the minerU engine, you need to enter your token here.
    • DOCX/XLSX/SRT/EPUB/HTML Options (For their respective workflows):
      • Insert Mode: Define how the translation is placed in the document. You can \"Replace\" the original, \"Append\" after it, or \"Prepend\" before it.
      • Separator: When using \"Append\" or \"Prepend\", this is used to separate the original and translated text.
    • JSON Path Configuration (Only for \"JSON\" workflow):
      • JSON paths to translate: Enter one JSONPath expression per line to specify which fields to translate.
      • E.g., $..description translates all values with the key 'description'. $.items[0].name translates the name of the first item.
    • Translation Model:
      • Platform/API Base URL/API Key/Model ID: Configure the AI translation service you want to use.
      • Refer to the platform's documentation for Model IDs. It's recommended to use non-inference models or mixed-inference models (with thinking turned off).
    • Translation Configuration:
      • Target Language/Custom Prompt: Specify the target language and any additional instructions.
      • Thinking Mode: Sets whether a mixed-inference model should 'think'. Supported for Zhipu's glm4.5 series, Alibaba's qwen3 series, VolcEngine's seed1.6 series, etc. Disabling is recommended.
    • Advanced Parameters:
      • Chunk Size/Concurrency/Temperature: The size of text chunks sent to the AI, number of concurrent requests, and creativity level. Default values usually work fine.
  3. Upload File

    In the task list on the right, click or drag your document into the file drop area.

  4. Start Translation

    Once the file is selected, click the Start Translation button on the task card. The system will start processing, and you can see real-time progress in the log area.

  5. Review & Download

    After translation is complete, action buttons will appear on the task card:

    • Preview: Opens a side panel for a side-by-side preview of the original and translation (for reference only).
    • Download: Download the translation in various formats, including PDF, DOCX, XLSX, HTML, and Markdown.
Tip: All your settings are automatically saved in your browser's local storage for your next visit.
", - "tutorialUnderstandBtn": "Got it", + "tutorialModalTitle": "User Guide", + "tutorialModalBody": "

Video tutorials can be found by searching for docutranslate on Bilibili.

Welcome to DocuTranslate! Follow these steps to translate your documents:

  1. Select Workflow

    First, choose the appropriate translation process from the top of the settings panel. Different workflows are suited for different file types:

    • To Markdown then Translate: For translating PDFs, markdown, images, etc.
    • Plain Text Translation: For translating .txt and other plain text files.
    • JSON Translation: For translating specific fields within .json files.
    • DOCX Translation: For translating .docx files.
    • XLSX Translation: For translating .xlsx spreadsheets and .csv files.
    • SRT Subtitle Translation: For translating .srt subtitle files.
    • EPUB Translation: For translating .epub e-book files.
    • HTML Translation: For translating .html files.
    New Feature: The \"Auto-select workflow\" switch is now on by default. Simply upload your file, and the system will automatically match it to the correct workflow, simplifying the process.

  2. Configure Parameters

    Based on your chosen workflow, complete the necessary configurations. All settings are automatically saved in your browser.

    • Parsing Configuration (Only shown for 'To Markdown' workflow):
      • Parsing Engine: Select an engine to convert your file (like a PDF) into a translation-friendly Markdown format. This is not needed if your file is already in Markdown format.
      • Mineru Token: If you choose the minerU engine, you must enter your token here.
    • DOCX/XLSX/SRT/EPUB/HTML Options (Shown for corresponding workflows):
      • Insert Mode: Define how the translation result is placed in the document. You can 'Replace' the original, 'Append' it after, or 'Prepend' it before.
      • Separator: When using 'Append' or 'Prepend' mode, this is used to insert a separator between the original and translated text.
    • JSON Path Configuration (Only shown for 'JSON' workflow):
      • JSON Paths to Translate: Enter one JSONPath expression per line to specify which fields to translate.
      • For example: $..description translates all values with the key 'description'. $.items[0].name translates the 'name' of the first item.
    • Translation Model:
      • Platform/API Base URL/API Key/Model ID: Configure the AI translation service you wish to use.
      • Refer to the platform's documentation for Model IDs. It is recommended to use non-inference or hybrid models (with thinking disabled).
    • Translation Configuration:
      • Target Language/Custom Prompt: Specify the target language and any additional instructions.
      • Thinking Mode: Set whether the hybrid inference model should 'think'. This is supported by models like Zhipu's glm4.5 series, Alibaba's qwen3 series, and Volcengine's seed1.6 series. Disabling thinking is recommended.
    • Advanced Parameters:
      • Chunk Size/Concurrency/Temperature: The size of text chunks sent to the AI, the number of concurrent requests, and the temperature. Default values are usually fine.
  3. Upload File

    In the task list on the right, click or drag your document into the file upload area.

  4. Start Translation

    Once the file is selected, click the Start Translation button on the task card. The system will begin processing, and you can monitor the real-time progress in the log area.

  5. View & Download

    After the translation is complete, action buttons will appear on the task card:

    • Preview: Compare the original and translated text side-by-side in a slide-out panel (for reference only).
    • Download: Download the translated document in various formats, including PDF, DOCX, XLSX, HTML, and Markdown.
Tip: All your configurations are saved locally in your browser for future use.
", + "tutorialUnderstandBtn": "I Understand", "contributorsModalTitle": "Thanks for Contributing", - "contributorsPara1": "DocuTranslate is an open-source project! The community's needs and usage are what drive its progress.", - "contributorsPara2": "A huge thank you to everyone who has sponsored the project, submitted code, provided valuable feedback, and starred the repository!", - "contributorsWelcome": "You can contribute in the following ways:", + "contributorsPara1": "DocuTranslate is an open-source project! The community's needs and usage are the driving force behind its progress.", + "contributorsPara2": "A heartfelt thank you to all friends who have sponsored the project, submitted code, provided valuable suggestions, and starred the project!", + "contributorsWelcome": "You are welcome to contribute in the following ways:", "contributorsGithub": "GitHub Page", "contributorsPR": "Submit a Pull Request", "contributorsIssue": "Report an Issue", "contributorsQQ": "Or contact the author via QQ Group: 1047781902", + "init_i18n_failed_alert": "Failed to load interface translations. Please check your network connection or contact an administrator.", + "init_failed_alert": "Initialization failed, could not connect to the backend service. Please ensure the service is running and refresh the page.", "status_selectFileFirst": "Please select a file first.", - "status_invalidWorkflow": "Invalid workflow type.", - "status_fillRequired": "Please fill in all required settings.", - "status_releasingOldTask": "Re-translating. Releasing resources for the old task.", - "status_encodingAndSubmitting": "Encoding file and submitting task...", - "status_requestOk": "Task started, now processing...", + "status_invalidWorkflow": "The selected workflow is invalid.", + "status_fillRequired": "Please fill in all required fields.", + "status_releasingOldTask": "Releasing old task...", + "btn_initializing": "Initializing", + "status_encodingAndSubmitting": "Encoding and submitting file...", + "status_requestOk": "Request successful, task processing has started.", + "btn_cancelTranslation": "Cancel", "status_requestFail": "Request failed", "status_initFail": "Initialization failed", "status_cancelling": "Cancelling...", "status_cancelSent": "Cancellation request sent.", - "status_cancelFail": "Failed to cancel", - "status_updateError": "Error updating status.", + "status_cancelFail": "Cancellation failed", "status_gettingStatus": "Getting status...", - "preview_loading": "

Loading translation...

", - "preview_loadFailed": "

Failed to load translation

", + "btn_reTranslate": "Re-translate", + "status_updateError": "Status update failed.", + "preview_loading": "Loading preview...", "preview_cantReadOriginal": "Could not read original file content.", - "preview_cantPreviewType": "Cannot preview this file type directly", - "preview_noOriginalCache": "Original file cache not found.", + "preview_cantPreviewType": "Cannot preview this file type", + "preview_noOriginalCache": "No original file cached for preview.", + "preview_loadFailed": "Failed to load preview.", + "pdf_preparing": "Preparing PDF for printing...", + "pdf_print_failed": "Failed to invoke print function. Please check browser settings or print manually.", + "pdf_fetch_failed": "Failed to fetch translated content, cannot generate PDF.", "preview_bilingual": "Bilingual Preview", "preview_translatedOnly": "Translated Only Preview", - "pdf_preparing": "Preparing PDF, please wait...", - "pdf_print_failed": "Automatic printing failed. Please print manually from the preview.", - "pdf_fetch_failed": "Failed to fetch HTML content, cannot generate PDF.", - "init_i18n_failed_alert": "Failed to load interface translations. Please check your network connection or contact an administrator.", - "init_failed_alert": "Initialization failed, could not connect to the backend service. Please ensure the service is running and refresh the page.", - "admin_tasklist_failed": "Could not load task list from server. Please check backend connection.", - "btn_startTranslation": "Start Translation", - "btn_initializing": "Initializing...", - "btn_cancelTranslation": "Cancel Translation", - "btn_reTranslate": "Re-translate" + "admin_tasklist_failed": "Admin Mode: Failed to load task list." } } \ No newline at end of file diff --git a/docutranslate/static/index.html b/docutranslate/static/index.html index 15cfd8e..674472e 100644 --- a/docutranslate/static/index.html +++ b/docutranslate/static/index.html @@ -1 +1 @@ - DocuTranslate - 交互式文档翻译

DocuTranslate

如果上传的文件本身是.md格式，此项可不选。
mineru VLM是更新的内测模型。

GitHub主页(欢迎star❤):
https://github.com/xunbu/docutranslate

交流QQ群: 1047781902

任务列表

当前没有任务，点击“新建任务”开始吧！

预览
原文
译文
\ No newline at end of file + DocuTranslate - 交互式文档翻译

DocuTranslate

如果上传的文件本身是.md格式，此项可不选。
mineru VLM是更新的内测模型。

GitHub主页(欢迎star❤):
https://github.com/xunbu/docutranslate

交流QQ群: 1047781902

任务列表

当前没有任务，点击“新建任务”开始吧！

预览
原文
译文
\ No newline at end of file