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:
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:
.txt 等纯文本文件。.json 文件中的特定字段。.docx 文件。.xlsx 电子表格文件。.srt 字幕文件。.epub 电子书文件。.html 文件。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。
minerU 引擎,需要在此处填入您的Token。$..description翻译所有键为description的值。$.items[0].name翻译第一个item的name值。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。
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。
翻译完成后,任务卡片下方会出现操作按钮:
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:
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:
.txt 等纯文本文件。.json 文件中的特定字段。.docx 文件。.xlsx 电子表格、 .csv 文件。.srt 字幕文件。.epub 电子书文件。.html 文件。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。
minerU 引擎,需要在此处填入您的Token。$..description翻译所有键为description的值。$.items[0].name翻译第一个item的name值。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。
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。
翻译完成后,任务卡片下方会出现操作按钮:
\\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 ❤): Video tutorials can be found by searching docutranslate on Bilibili.
Welcome to DocuTranslate! Follow these steps to translate your documents:
First, choose the translation process you need from the top of the settings panel. Different workflows are for different file types:
.txt and other plain text files..json files..docx files..xlsx spreadsheet files..srt subtitle files..epub ebook files..html files.Based on your chosen workflow, complete the necessary settings. All settings are automatically saved in your browser.
minerU engine, you need to enter your token here.$..description translates all values with the key 'description'. $.items[0].name translates the name of the first item.In the task list on the right, click or drag your document into the file drop area.
Once the file is selected, click the Start Translation button on the task card. The system will start processing, and you can see real-time progress in the log area.
After translation is complete, action buttons will appear on the task card:
Video tutorials can be found by searching for docutranslate on Bilibili.
Welcome to DocuTranslate! Follow these steps to translate your documents:
First, choose the appropriate translation process from the top of the settings panel. Different workflows are suited for different file types:
.txt and other plain text files..json files..docx files..xlsx spreadsheets and .csv files..srt subtitle files..epub e-book files..html files.Based on your chosen workflow, complete the necessary configurations. All settings are automatically saved in your browser.
minerU engine, you must enter your token here.$..description translates all values with the key 'description'. $.items[0].name translates the 'name' of the first item.In the task list on the right, click or drag your document into the file upload area.
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.
After the translation is complete, action buttons will appear on the task card:
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