### Install with uv

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Installation using uv, including initializing the environment and adding packages.

```bash
uv init

uv add docutranslate

uv add docutranslate[mcp]

uv run --no-dev docutranslate -i

#uv run --no-dev docutranslate -i --with-mcp
```

--------------------------------

### Install with pip

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Basic installation and installation with the mcp extension using pip.

```bash
pip install docutranslate

pip install docutranslate[mcp]

docutranslate -i

#docutranslate -i --with-mcp
```

--------------------------------

### Configure Client Example

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

An example of how to configure the client with specific LLM settings.

```bash
请配置 DocuTranslate，使用以下设置：
- API Key: sk-xxxxxx
- Base URL: https://api.openai.com/v1
- Model: gpt-4o
- 目标语言: 中文
```

--------------------------------

### configure_client Example

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

Example of how to configure the DocuTranslate client with specific LLM settings.

```bash
Please configure DocuTranslate with these settings:
- API Key: sk-xxxxxx
- Base URL: https://api.openai.com/v1
- Model: gpt-4o
- Target language: Chinese
```

--------------------------------

### Installation

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

Install the docutranslate package with MCP support.

```bash
pip install docutranslate[mcp]
```

--------------------------------

### Workflow Example

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Example of how a workflow result might be structured.

```python
workflow = result.workflow
```

--------------------------------

### Install with git

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Cloning the repository and synchronizing dependencies using uv.

```bash
git clone https://github.com/xunbu/docutranslate.git

cd docutranslate

uv sync --no-dev
# uv sync --no-dev --extra mcp
# uv sync --no-dev --all-extras
```

--------------------------------

### Client SDK Example

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Example of using the Client SDK to translate a PDF document with a locally deployed minerU service.

```python
from docutranslate.sdk import Client

client = Client(
    api_key="YOUR_LLM_API_KEY",
    model_id="llama3",
    to_lang="Chinese",
    convert_engine="mineru_deploy",
    mineru_deploy_base_url="http://127.0.0.1:8000",  # Your minerU API address
)
result = client.translate("document.pdf")
result.save(fmt="markdown")
```

--------------------------------

### Install with docker

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Running the application using a Docker container.

```bash
docker run -d -p 8010:8010 xunbu/docutranslate:latest
# docker run -it -p 8010:8010 xunbu/docutranslate:latest
# docker run -it -p 8010:8010 xunbu/docutranslate:v1.5.4
```

--------------------------------

### Submit Task Example Workflow

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

An example workflow demonstrating the use of submit_task, get_task_status, download_file, and release_task.

```bash
1. submit_task(file_path="doc.pdf", api_key="sk-...", model_id="gpt-4o")
   → task_id="abc-123"

2. get_task_status("abc-123")
   → { "status": "running", "progress_percent": 45 }

3. get_task_status("abc-123")  # 完成时
   → 翻译完成！
   → 可用格式：docx, html, markdown
   → 附件：glossary
   → 使用 download_file 保存文件

4. download_file(task_id="abc-123", file_name="docx", output_dir="./output")
   → 文件已保存到 ./output/doc_translated.docx

5. download_file(task_id="abc-123", file_name="glossary", output_dir="./output")
   → 文件已保存到 ./output/glossary.csv

6. release_task("abc-123")  # 清理临时文件
```

--------------------------------

### Client SDK Initialization and Usage

Source: https://github.com/xunbu/docutranslate/blob/main/README_ZH.md

Example of initializing the Client SDK and performing various translation tasks.

```python
from docutranslate.sdk import Client

# 使用您的 AI 平台设置初始化客户端
client = Client(
    api_key="YOUR_OPENAI_API_KEY",  # 或其他 AI 平台 API key
    base_url="https://api.openai.com/v1/",
    model_id="gpt-4o",
    to_lang="中文",
    concurrent=10,  # 并发请求数
)

# 示例 1: 翻译纯文本文件 (无需 PDF 解析引擎)
result = client.translate("path/to/your/document.txt")
print(f"翻译完成！保存位置: {result.save()}")

# 示例 2: 翻译 PDF 文件 (需要指定 mineru_token 或使用本地部署)
# 方式 A: 使用在线 MinerU (需要 token: https://mineru.net/apiManage/token)
result = client.translate(
    "path/to/your/document.pdf",
    convert_engine="mineru",
    mineru_token="YOUR_MINERU_TOKEN",  # 替换为您的 MinerU Token
    formula_ocr=True,  # 启用公式识别
)
result.save(fmt="html")

# 方式 B: 使用本地部署的 MinerU (推荐内网/离线环境)
# 需要先启动本地 MinerU 服务，参考: https://github.com/opendatalab/MinerU
result = client.translate(
    "path/to/your/document.pdf",
    convert_engine="mineru_deploy",
    mineru_deploy_base_url="http://127.0.0.1:8000",  # 您的本地 MinerU 地址
    mineru_deploy_backend="hybrid-auto-engine",  # 后端类型
)
result.save(fmt="markdown")

# 示例 3: 翻译 Docx 文件 (保持格式)
result = client.translate(
    "path/to/your/document.docx",
    insert_mode="replace",  # replace/append/prepend
)
result.save(fmt="docx")  # 保存为 docx 格式

# 示例 4: 导出为 Base64 编码字符串 (用于 API 传输)
base64_content = result.export(fmt="html")
print(f"导出内容长度: {len(base64_content)}")

# 您还可以访问底层工作流以进行高级操作
# workflow = result.workflow

```

--------------------------------

### Start Web UI and API Service

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Commands to start the DocuTranslate service with various options for GUI, API access, port specification, CORS, and MCP integration.

```bash
docutranslate -i                           (Start GUI, default local access)
docutranslate -i --host 0.0.0.0            (Allow access from other devices on LAN)
docutranslate -i -p 8081                   (Specify port number)
docutranslate -i --cors                    (Enable default CORS settings)
docutranslate -i --with-mcp                (Start GUI with MCP SSE endpoint, shared queue, shared port)
docutranslate --mcp                         (Start MCP server, stdio mode)
docutranslate --mcp --transport sse         (Start MCP server, SSE mode)
docutranslate --mcp --transport sse --mcp-host MCP_HOST   --mcp-port MCP_PORT  (Start MCP server, SSE mode)
docutranslate --mcp --transport streamable-http  (Start MCP server, Streamable HTTP mode)
```

--------------------------------

### Simple Client SDK - Translate Docx Files

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Python code example for translating Docx files using the DocuTranslate Client, preserving formatting.

```python
# Example 3: Translate Docx files (preserve formatting)
result = client.translate(
    "path/to/your/document.docx",
    insert_mode="replace",  # replace/append/prepend
)
result.save(fmt="docx")  # Save as docx format
```

--------------------------------

### Usage: Stdio Mode with uvx (No Installation Required)

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

MCP server configuration using uvx.

```json
{
  "mcpServers": {
    "docutranslate": {
      "command": "uvx",
      "args": ["--from", "docutranslate[mcp]", "docutranslate", "--mcp"],
      "env": {
        "DOCUTRANSLATE_API_KEY": "sk-xxxxxx",
        "DOCUTRANSLATE_BASE_URL": "https://api.openai.com/v1",
        "DOCUTRANSLATE_MODEL_ID": "gpt-4o",
        "DOCUTRANSLATE_TO_LANG": "Chinese",
        "DOCUTRANSLATE_CONCURRENT": "10",
        "DOCUTRANSLATE_CONVERT_ENGINE": "mineru",
        "DOCUTRANSLATE_MINERU_TOKEN": "your-mineru-token"
      }
    }
  }
}
```

--------------------------------

### submit_task Example Workflow

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

Demonstrates a typical workflow for submitting a translation task, checking its status, downloading the translated file, and releasing the task resources.

```bash
1. submit_task(file_path="doc.pdf", api_key="sk-...", model_id="gpt-4o")
   → task_id="abc-123"

2. get_task_status("abc-123")
   → { "status": "running", "progress_percent": 45 }

3. get_task_status("abc-123")  # when complete
   → Translation completed!
   → Available formats: docx, html, markdown
   → Attachments: glossary
   → Use download_file to save files

4. download_file(task_id="abc-123", file_name="docx", output_dir="./output")
   → File saved to ./output/doc_translated.docx

5. download_file(task_id="abc-123", file_name="glossary", output_dir="./output")
   → File saved to ./output/glossary.csv

6. release_task("abc-123")  # cleanup temp files
```

--------------------------------

### Simple Client SDK - Export as Base64

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Python code example for exporting translated content as a base64 encoded string using the DocuTranslate Client.

```python
# Example 4: Export as base64 encoded string (for API transmission)
base64_content = result.export(fmt="html")
print(f"Exported content length: {len(base64_content)}")
```

--------------------------------

### Simple Client SDK - Translate Plain Text Files

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Python code example for translating plain text files using the DocuTranslate Client.

```python
# Example 1: Translate plain text files (no PDF parsing engine needed)
result = client.translate("path/to/your/document.txt")
print(f"Translation complete! Saved to: {result.save()}")
```

--------------------------------

### Other Workflows Import Examples

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

This snippet shows how to import configurations and workflows for various file types supported by DocuTranslate, including TXT, JSON, DOCX, XLSX, EPUB, HTML, SRT, and ASS.

```python
# TXT: from docutranslate.workflow.txt_workflow import TXTWorkflow, TXTWorkflowConfig
# JSON: from docutranslate.workflow.json_workflow import JsonWorkflow, JsonWorkflowConfig
# DOCX: from docutranslate.workflow.docx_workflow import DocxWorkflow, DocxWorkflowConfig
# XLSX: from docutranslate.workflow.xlsx_workflow import XlsxWorkflow, XlsxWorkflowConfig
# EPUB: from docutranslate.workflow.epub_workflow import EpubWorkflow, EpubWorkflowConfig
# HTML: from docutranslate.workflow.html_workflow import HtmlWorkflow, HtmlWorkflowConfig
# SRT:  from docutranslate.workflow.srt_workflow import SrtWorkflow, SrtWorkflowConfig
# ASS:   from docutranslate.workflow.ass_workflow import AssWorkflow, AssWorkflowConfig
```

--------------------------------

### Simple Client SDK - Translate PDF Files (Local MinerU)

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Python code example for translating PDF files using the DocuTranslate Client with a locally deployed MinerU service.

```python
# Option B: Use locally deployed MinerU (recommended for intranet/offline)
# First start local MinerU service, reference: https://github.com/opendatalab/MinerU
result = client.translate(
    "path/to/your/document.pdf",
    convert_engine="mineru_deploy",
    mineru_deploy_base_url="http://127.0.0.1:8000",  # Your local MinerU address
    mineru_deploy_backend="hybrid-auto-engine",  # Backend type
)
result.save(fmt="markdown")
```

--------------------------------

### Simple Client SDK - Translate PDF Files (Online MinerU)

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Python code example for translating PDF files using the DocuTranslate Client with the online MinerU service.

```python
# Example 2: Translate PDF files (requires mineru_token or local deployment)
# Option A: Use online MinerU (token required: https://mineru.net/apiManage/token)
result = client.translate(
    "path/to/your/document.pdf",
    convert_engine="mineru",
    mineru_token="YOUR_MINERU_TOKEN",  # Replace with your MinerU Token
    formula_ocr=True,  # Enable formula recognition
)
result.save(fmt="html")
```

--------------------------------

### Translate Multiple Files Concurrently

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Example of using the DocuTranslate SDK to translate multiple files concurrently using asyncio.

```python
import asyncio
from docutranslate.sdk import Client

async def translate_multiple():
    client = Client(
        api_key="YOUR_API_KEY",
        base_url="https://api.openai.com/v1/",
        model_id="gpt-4o",
        to_lang="Chinese",
    )

    # Translate multiple files concurrently
    files = ["doc1.pdf", "doc2.docx", "notes.txt"]
    results = await asyncio.gather(
        *[client.translate_async(f) for f in files]
    )

    for r in results:
        print(f"Saved: {r.save()}")

asyncio.run(translate_multiple())
```

--------------------------------

### Usage: Stdio Mode with Virtual Environment Python (Windows Example)

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

MCP server configuration using the Python interpreter from a virtual environment on Windows.

```json
{
  "mcpServers": {
    "docutranslate": {
      "command": "C:\\path\\to\\your\\venv\\Scripts\\python.exe",
      "args": ["-m", "docutranslate.mcp"],
      "env": {
        "DOCUTRANSLATE_API_KEY": "sk-xxxxxx",
        "DOCUTRANSLATE_BASE_URL": "https://api.openai.com/v1",
        "DOCUTRANSLATE_MODEL_ID": "gpt-4o",
        "DOCUTRANSLATE_TO_LANG": "Chinese",
        "DOCUTRANSLATE_CONCURRENT": "10",
        "DOCUTRANSLATE_CONVERT_ENGINE": "mineru",
        "DOCUTRANSLATE_MINERU_TOKEN": "your-mineru-token"
      }
    }
  }
}
```

--------------------------------

### Translate a PDF File (Using `MarkdownBasedWorkflow`)

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

This example demonstrates the most common use case of translating a PDF file to Markdown and then to another language using an LLM. It utilizes asynchronous execution and configures various components like the translator, converter, and exporter.

```python
import asyncio
from docutranslate.workflow.md_based_workflow import MarkdownBasedWorkflow, MarkdownBasedWorkflowConfig
from docutranslate.converter.x2md.converter_mineru import ConverterMineruConfig
from docutranslate.translator.ai_translator.md_translator import MDTranslatorConfig
from docutranslate.exporter.md.md2html_exporter import MD2HTMLExporterConfig


async def main():
    # 1. Build Translator Configuration
    translator_config = MDTranslatorConfig(
        base_url="https://open.bigmodel.cn/api/paas/v4",  # AI Platform Base URL
        api_key="YOUR_ZHIPU_API_KEY",  # AI Platform API Key
        model_id="glm-4-air",  # Model ID
        to_lang="English",  # Target Language
        chunk_size=3000,  # Text chunk size
        concurrent=10,  # Concurrency level
        # glossary_generate_enable=True, # Enable auto-glossary generation
        # glossary_dict={"Jobs":"Steve Jobs"}, # Pass in a glossary dictionary
        # system_proxy_enable=True, # Enable system proxy
    )

    # 2. Build Converter Configuration (Using minerU)
    converter_config = ConverterMineruConfig(
        mineru_token="YOUR_MINERU_TOKEN",  # Your minerU Token
        formula_ocr=True  # Enable formula recognition
    )

    # 3. Build Main Workflow Configuration
    workflow_config = MarkdownBasedWorkflowConfig(
        convert_engine="mineru",  # Specify parsing engine
        converter_config=converter_config,  # Pass converter config
        translator_config=translator_config,  # Pass translator config
        html_exporter_config=MD2HTMLExporterConfig(cdn=True)  # HTML export config
    )

    # 4. Instantiate Workflow
    workflow = MarkdownBasedWorkflow(config=workflow_config)

    # 5. Read file and execute translation
    print("Starting to read and translate file...")
    workflow.read_path("path/to/your/document.pdf")
    await workflow.translate_async()
    # Or use synchronous method
    # workflow.translate()
    print("Translation complete!")

    # 6. Save results
    workflow.save_as_html(name="translated_document.html")
    workflow.save_as_markdown_zip(name="translated_document.zip")
    workflow.save_as_markdown(name="translated_document.md")  # Markdown with embedded images
    print("Files saved to ./output folder.")

    # Or get content strings directly
    html_content = workflow.export_to_html()
    html_content = workflow.export_to_markdown()
    # print(html_content)


if __name__ == "__main__":
    asyncio.run(main())

```

--------------------------------

### Simple Client SDK - Initialize Client

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

Python code to initialize the DocuTranslate Client with AI platform settings.

```python
from docutranslate.sdk import Client

# Initialize the client with your AI platform settings
client = Client(
    api_key="YOUR_OPENAI_API_KEY",  # or any other AI platform API key
    base_url="https://api.openai.com/v1/",
    model_id="gpt-4o",
    to_lang="Chinese",
    concurrent=10,  # Number of concurrent requests
)
```

--------------------------------

### Usage: Combined Mode with Web UI (Recommended!)

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

Run both Web UI and MCP server together, sharing the same task queue.

```bash
docutranslate -i --with-mcp
```

--------------------------------

### Usage: SSE Mode (Recommended for Cherry Studio)

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

Run the docutranslate MCP server in SSE mode.

```bash
docutranslate --mcp --transport sse --mcp-host 127.0.0.1 --mcp-port 8000
```

--------------------------------

### Usage: Stdio Mode (Recommended for Claude Desktop, Windsurf)

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

Run the docutranslate MCP server in stdio mode.

```bash
docutranslate --mcp
```

--------------------------------

### Vite Legacy Polyfill and Entry Point

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/static/index.html

This snippet contains JavaScript code related to Vite's legacy polyfill and entry point loading, likely for browser compatibility.

```javascript
import.meta.url;import("\_").catch(()=>1);(async function*(){})().next();if(location.protocol!="file:"){window.__vite_is_modern_browser=true}
!function(){if(window.__vite_is_modern_browser)return;console.warn("vite: loading legacy chunks, syntax error above and the same error below should be ignored");var e=document.getElementById("vite-legacy-polyfill"),n=document.createElement("script");n.src=e.src,n.onload=function(){System.import(document.getElementById('vite-legacy-entry').getAttribute('data-src'))},document.body.appendChild(n)}();

!function(){var e=document,t=e.createElement("script");if(!("noModule"in t)&&"onbeforeload"in t){var n=!1;e.addEventListener("beforeload",(function(e){if(e.target===t)n=!0;else if(!e.target.hasAttribute("nomodule")||!n)return;e.preventDefault()}),!0),t.type="module",t.src=".",e.head.appendChild(t),t.remove()}}(); System.import(document.getElementById('vite-legacy-entry').getAttribute('data-src'))
```

--------------------------------

### MCP Configuration using uvx

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

JSON configuration for MCP servers using uvx command.

```json
{
  "mcpServers": {
    "docutranslate": {
      "command": "uvx",
      "args": ["--from", "docutranslate[mcp]", "docutranslate", "--mcp"],
      "env": {
        "DOCUTRANSLATE_API_KEY": "sk-xxxxxx",
        "DOCUTRANSLATE_BASE_URL": "https://api.openai.com/v1",
        "DOCUTRANSLATE_MODEL_ID": "gpt-4o",
        "DOCUTRANSLATE_TO_LANG": "中文",
        "DOCUTRANSLATE_CONCURRENT": "10",
        "DOCUTRANSLATE_CONVERT_ENGINE": "mineru",
        "DOCUTRANSLATE_MINERU_TOKEN": "your-mineru-token"
      }
    }
  }
}
```

--------------------------------

### renderjson Library Initialization and Usage

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/template/json.html

This snippet shows the core functionality of the renderjson library, including its initialization, configuration options, and how to render JSON data into an HTML element.

```javascript
var module,window,define,renderjson=function(){var n=function(){for(var n=[\];arguments.length;)n.push(t(r(Array.prototype.shift.call(arguments)),e(Array.prototype.shift.call(arguments))));return n},t=function(){for(var n=Array.prototype.shift.call(arguments),e=0;e<arguments.length;e++)arguments[e].constructor==Array?t.apply(this,[n].concat(arguments[e])):n.appendChild(arguments[e]);return n},e=function(n){return document.createTextNode(n)},r=function(n){var t=document.createElement("span");return n&&(t.className=n),t},o=function(n,t,r){var o=document.createElement("a");return t&&(o.className=t),o.appendChild(e(n)),o.href="#",o.onclick=function(n){return r(),n&&n.stopPropagation(),!1},o};function s(l,i,a,c,u){var p=a?"":i,f=function(s,l,i,a,f){var y,
_=r(a),d=function(){y||t(
_.parentNode,y=function(n,t){return n.insertBefore(t,n.firstChild),n}(f(),o(u.hide,"disclosure",(function(){y.style.display="none",
_.style.display="inline"})))),y.style.display="inline",
_.style.display="none"};t(
_,o(u.show,"disclosure",d),n(a+" syntax",s),o(l,null,d),n(a+" syntax",i));var g=t(r(),e(p.slice(0,-1)),
_);return c>0&&"string"!=a&&d(),g};return null===l?n(null,p,"keyword","null"):void 0===l?n(null,p,"keyword","undefined"):"string"==typeof l&&l.length>u.max_string_length?f('"',l.substr(0,u.max_string_length)+" ...",'"',"string",(function(){return t(r("string"),n(null,p,"string",JSON.stringify(l)))})):"object"!=typeof l||[Number,String,Boolean,Date].indexOf(l.constructor)>=0?n(null,p,typeof l,JSON.stringify(l)):l.constructor==Array?0==l.length?n(null,p,"array syntax","[]"):
 f("[",u.collapse_msg(l.length),"]","array",(function(){for(var o=t(r("array"),n("array syntax","[",null,"\n")),a=0;a<l.length;a++)t(o,s(u.replacer.call(l,a,l[a]),i+" ",!1,c-1,u),a!=l.length-1?n("syntax",","):
[],e("\n"));return t(o,n(null,i,"array syntax"," ]")),o})):function(n,t){var e=t||Object.keys(n);for(var r in e)if(Object.hasOwnProperty.call(n,e[r]))return!1;return!0}(l,u.property_list)?n(null,p,"object syntax","{}"):f("{ ",u.collapse_msg(Object.keys(l).length)," }","object",(function(){var o=t(r("object"),n("object syntax","{",null,"\n"));for(var a in l)var p=a;var f=u.property_list||Object.keys(l);for(var y in u.sort_objects&&(f=f.sort()),f){(a=f[y])in l&&t(o,n(null,i+" ","key","\""+a+"\"","object syntax",": "),s(u.replacer.call(l,a,l[a]),i+" ",!0,c-1,u),a!=p?n("syntax",","):
[],e("\n"))}return t(o,n(null,i,"object syntax","}")),o}))}var l=function n(e){var r=new Object(n.options);r.replacer="function"==typeof r.replacer?r.replacer:function(n,t){return t};var o=t(document.createElement("pre"),s(e,"",!1,r.show_to_level,r));return o.className="renderjson",o};return l.set_icons=function(n,t){return l.options.show=n,l.options.hide=t,l},l.set_show_to_level=function(n){return l.options.show_to_level="string"==typeof n&&"all"===n.toLowerCase()?Number.MAX_VALUE:n,l},l.set_max_string_length=function(n){return l.options.max_string_length="string"==typeof n&&"none"===n.toLowerCase()?Number.MAX_VALUE:n,l},l.set_sort_objects=function(n){return l.options.sort_objects=n,l},l.set_replacer=function(n){return l.options.replacer=n,l},l.set_collapse_msg=function(n){return l.options.collapse_msg=n,l},l.set_property_list=function(n){return l.options.property_list=n,l},l.set_show_by_default=function(n){return l.options.show_to_level=n?Number.MAX_VALUE:0,l},l.options={},l.set_icons("⊕","⊖"),l.set_show_by_default(!1),l.set_sort_objects(!1),l.set_max_string_length("none"),l.set_replacer(void 0),l.set_property_list(void 0),l.set_collapse_msg((function(n){return n+" item"+(1==n?"":"s")})),l}();define?define({renderjson:renderjson}):(module||{}).exports=(window||{}).renderjson=renderjson;
```

```javascript
renderjson.set_show_to_level("all");
let data={{ jsonData }}
document.getElementById("test").appendChild(renderjson(data));
```

--------------------------------

### MCP Configuration using Python executable (Linux/macOS)

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

JSON configuration for MCP servers using the full Python path from a virtual environment.

```json
{
  "mcpServers": {
    "docutranslate": {
      "command": "/path/to/your/venv/bin/python",
      "args": ["-m", "docutranslate.mcp"],
      "env": {
        "DOCUTRANSLATE_API_KEY": "sk-xxxxxx",
        "DOCUTRANSLATE_BASE_URL": "https://api.openai.com/v1",
        "DOCUTRANSLATE_MODEL_ID": "gpt-4o",
        "DOCUTRANSLATE_TO_LANG": "中文",
        "DOCUTRANSLATE_CONCURRENT": "10",
        "DOCUTRANSLATE_CONVERT_ENGINE": "mineru",
        "DOCUTRANSLATE_MINERU_TOKEN": "your-mineru-token"
      }
    }
  }
}
```

--------------------------------

### MCP Configuration using Python executable (Windows)

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

JSON configuration for MCP servers using the full Python path from a Windows virtual environment.

```json
{
  "mcpServers": {
    "docutranslate": {
      "command": "C:\\path\\to\\your\\venv\\Scripts\\python.exe",
      "args": ["-m", "docutranslate.mcp"],
      "env": {
        "DOCUTRANSLATE_API_KEY": "sk-xxxxxx",
        "DOCUTRANSLATE_BASE_URL": "https://api.openai.com/v1",
        "DOCUTRANSLATE_MODEL_ID": "gpt-4o",
        "DOCUTRANSLATE_TO_LANG": "中文",
        "DOCUTRANSLATE_CONCURRENT": "10",
        "DOCUTRANSLATE_CONVERT_ENGINE": "mineru",
        "DOCUTRANSLATE_MINERU_TOKEN": "your-mineru-token"
      }
    }
  }
}
```

--------------------------------

### Helper Script for Rendering Libraries

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/template/markdown.html

A JavaScript snippet that runs after a delay to fix KaTeX rendering errors by updating the innerHTML of elements with the class 'katex-error' using their 'title' attribute. It also initializes the Mermaid library if it exists, with specific security settings.

```javascript
// 辅助脚本
setTimeout(() => {
  // 修复 Katex 错误显示
  const errors = document.getElementsByClassName('katex-error');
  for (let i = 0; i < errors.length; i++) {
    errors[i].innerHTML = errors[i].title;
  }
}, 200);

// 确保 Mermaid 存在再初始化
if (typeof mermaid !== 'undefined') {
  mermaid.initialize({
    securityLevel: 'loose',
    startOnLoad: true
  });
}
```

--------------------------------

### Usage: Streamable HTTP Mode

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

Run the docutranslate MCP server in streamable HTTP mode.

```bash
docutranslate --mcp --transport streamable-http --mcp-host 127.0.0.1 --mcp-port 8000
```

--------------------------------

### Usage: Stdio Mode with Virtual Environment Python

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

MCP server configuration using the Python interpreter from a virtual environment.

```json
{
  "mcpServers": {
    "docutranslate": {
      "command": "/path/to/your/venv/bin/python",
      "args": ["-m", "docutranslate.mcp"],
      "env": {
        "DOCUTRANSLATE_API_KEY": "sk-xxxxxx",
        "DOCUTRANSLATE_BASE_URL": "https://api.openai.com/v1",
        "DOCUTRANSLATE_MODEL_ID": "gpt-4o",
        "DOCUTRANSLATE_TO_LANG": "Chinese",
        "DOCUTRANSLATE_CONCURRENT": "10",
        "DOCUTRANSLATE_CONVERT_ENGINE": "mineru",
        "DOCUTRANSLATE_MINERU_TOKEN": "your-mineru-token"
      }
    }
  }
}
```

--------------------------------

### ASS Subtitle Preview Structure and Styling

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/template/ass.html

HTML and CSS code for a subtitle preview container, canvas, controls, and a time slider, along with basic styling for preformatted text.

```html
<!DOCTYPE html>
<html>
<head>
<title>ASS Subtitle Preview</title>
<style>
  /* ASS Subtitle Preview */
  html, body {
    margin: 0;
    padding: 0;
    width: 100%;
    display: flex;
    flex-direction: column;
    align-items: center;
    background-color: #f0f0f0;
    font-family: sans-serif;
  }
  #subtitle-container {
    position: relative;
    width: 80vw;
    /* Using a 16:9 aspect ratio for the canvas */
    aspect-ratio: 16 / 9;
    margin-top: 2vh;
    background-color: #333;
    border: 1px solid #555;
  }
  #subtitle-canvas {
    width: 100%;
    height: 100%;
    display: block;
  }
  #controls {
    margin-top: 20px;
    display: flex;
    align-items: center;
    gap: 10px;
  }
  #time-slider {
    width: 50vw;
  }
  #current-time {
    min-width: 70px;
    text-align: center;
    font-family: monospace;
    background: #fff;
    padding: 5px;
    border-radius: 3px;
    border: 1px solid #ccc;
  }
</style>
</head>
<body>

<div id="subtitle-container">
  <canvas id="subtitle-canvas"></canvas>
</div>

<div id="controls">
  <input type="range" id="time-slider" min="0" max="100" value="0">
  <span id="current-time">0s</span>
</div>

<pre>
{{ ass_data }}
</pre>

</body>
</html>

```

--------------------------------

### Usage: SSE Mode with Virtual Environment Python

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

Run the docutranslate MCP server in SSE mode using the Python interpreter from a virtual environment.

```bash
/path/to/your/venv/bin/python -m docutranslate.mcp --transport sse --host 127.0.0.1 --port 8000
```

--------------------------------

### MCP Configuration using docutranslate command

Source: https://github.com/xunbu/docutranslate/blob/main/docutranslate/mcp/README.md

JSON configuration for MCP servers when 'docutranslate' is in PATH.

```json
{
  "mcpServers": {
    "docutranslate": {
      "command": "docutranslate",
      "args": ["--mcp"],
      "env": {
        "DOCUTRANSLATE_API_KEY": "sk-xxxxxx",
        "DOCUTRANSLATE_BASE_URL": "https://api.openai.com/v1",
        "DOCUTRANSLATE_MODEL_ID": "gpt-4o",
        "DOCUTRANSLATE_TO_LANG": "中文",
        "DOCUTRANSLATE_CONCURRENT": "10",
        "DOCUTRANSLATE_CONVERT_ENGINE": "mineru",
        "DOCUTRANSLATE_MINERU_TOKEN": "your-mineru-token"
      }
    }
  }
}
```

--------------------------------

### Workflow API Usage Pattern

Source: https://github.com/xunbu/docutranslate/blob/main/README.md

General pattern for using the Workflow API for advanced control in DocuTranslate.

```python
# Pattern:
# 1. Create TranslatorConfig (LLM settings)
# 2. Create WorkflowConfig (workflow settings)
# 3. Create Workflow instance
# 4. workflow.read_path(file)
# 5. await workflow.translate_async()
# 6. workflow.save_as_*(name=...) or export_to*(...)
```