diff --git a/.gitignore b/.gitignore
index a5628ae..8491508 100644
--- a/.gitignore
+++ b/.gitignore
@@ -7,6 +7,6 @@ wheels/
*.egg-info
tests/resource/
tests/
-filetranslate/output/
+docutranslate/output/
# Virtual environments
.venv
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
index 39e19fd..bbed93a 100644
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -5,8 +5,20 @@
+
+
+
+
+
+
+
+
+
+
+
+
@@ -32,38 +44,38 @@
- {
+ "keyToString": {
+ "DefaultHtmlFileTemplate": "HTML File",
+ "JavaScript 调试.output.html (1).executor": "Run",
+ "JavaScript 调试.output.html.executor": "Run",
+ "JavaScript 调试.regex_中文.html.executor": "Run",
+ "JavaScript 调试.test2_英文.html.executor": "Run",
+ "ModuleVcsDetector.initialDetectionPerformed": "true",
+ "Python 测试.Python 测试 (markdown_mask.py 内).executor": "Run",
+ "Python 测试.markdown_mask.Test.test_basic_link_masking 的 Python 测试.executor": "Run",
+ "Python.PDFtranslater (1).executor": "Run",
+ "Python.PDFtranslater (2).executor": "Run",
+ "Python.agent_utils.executor": "Run",
+ "Python.convert.executor": "Run",
+ "Python.markdown_splitter.executor": "Run",
+ "Python.markdown_utils.executor": "Run",
+ "Python.test.executor": "Run",
+ "Python.test1.executor": "Run",
+ "Python.translater.executor": "Debug",
+ "RunOnceActivity.ShowReadmeOnStart": "true",
+ "RunOnceActivity.git.unshallow": "true",
+ "git-widget-placeholder": "master",
+ "last_opened_file_path": "C:/Users/jxgm/Desktop/FileTranslate/tests/resource",
+ "node.js.detected.package.eslint": "true",
+ "node.js.detected.package.tslint": "true",
+ "node.js.selected.package.eslint": "(autodetect)",
+ "node.js.selected.package.tslint": "(autodetect)",
+ "nodejs_package_manager_path": "npm",
+ "settings.editor.selected.configurable": "Errors",
+ "vue.rearranger.settings.migration": "true"
}
-}]]>
+}
@@ -302,7 +314,7 @@
-
+
diff --git a/README.md b/README.md
index 01b1f3e..7a93a9b 100644
--- a/README.md
+++ b/README.md
@@ -1,15 +1,15 @@
# 简介
-## FileTranslate
+## DocuTranslate
一个使用大预言模型(llm)翻译pdf和markdown的包
-[github主页](https://github.com/xunbu/filetranslate)
+[github主页](https://github.com/xunbu/docutranslate)
# 安装
使用pip
-`pip install filetranslate`
+`pip install doctranslate`
使用uv
-`uv add filetranslate`
+`uv add doctranslate`
# 前置条件(获取大模型平台的baseurl、key、model-id)
由于需要使用大语言模型进行markdown调整与翻译,所以需要预先获取模型的baseurl、key、model-id
@@ -17,40 +17,45 @@
# 使用方式
## 使用默认参数翻译pdf
+
```python
-from filetranslate.translater import FileTranslater
+from docutranslate.translater import FileTranslater
-#不开启公式、代码识别
-FileTranslater(base_url="",key="",model_id="").translate_pdf_file("",to_lang="中文")
+# 不开启公式、代码识别
+FileTranslater(base_url="", key="", model_id="").translate_pdf_file("", to_lang="中文")
-#开启公式、代码识别(需要下载更多模型)
-FileTranslater(base_url="",key="",model_id="").translate_pdf_file("",to_lang="中文",formula=True,code=True)
+# 开启公式、代码识别(需要下载更多模型)
+FileTranslater(base_url="", key="", model_id="").translate_pdf_file("", to_lang="中文",
+ formula=True, code=True)
```
> 第一次使用时需要下载模型(约1G、使用公式、代码识别需要多约0.5G),请稍作等待
> 输出文件默认放在`./output`中
## 使用不同的agent分别进行文本修正和翻译
+
```python
-from filetranslate.translater import FileTranslater
+from docutranslate.translater import FileTranslater
translater = FileTranslater()
-refine_agent=translater.create_refine_agent(baseurl="",key="",model_id="")
-translate_agent=translater.create_translate_agent(baseurl="",key="",model_id="")
+refine_agent = translater.create_refine_agent(baseurl="", key="", model_id="")
+translate_agent = translater.create_translate_agent(baseurl="", key="", model_id="")
-translater.translate_pdf_file(pdf_path="",to_lang="中文",refine_agent=refine_agent,translate_agent=translate_agent)
+translater.translate_pdf_file(pdf_path="", to_lang="中文", refine_agent=refine_agent,
+ translate_agent=translate_agent)
```
## 参数说明
### 创建FileTranslate
+
```python
-from filetranslate.translater import FileTranslater
+from docutranslate.translater import FileTranslater
translater = FileTranslater(base_url="",
key="",
- model_id="",#使用的模型id
- chunksize=4000,#【可选】markdown分块长度,分块越大效果越好,不建议超过4096
- max_concurrent=6#【可选】并发数,受到ai平台并发量限制
+ model_id="", # 使用的模型id
+ chunksize=4000, # 【可选】markdown分块长度,分块越大效果越好,不建议超过4096
+ max_concurrent=6 # 【可选】并发数,受到ai平台并发量限制
)
```
### 翻译pdf文件
diff --git a/filetranslate/__init__.py b/docutranslate/__init__.py
similarity index 100%
rename from filetranslate/__init__.py
rename to docutranslate/__init__.py
diff --git a/filetranslate/decorator/__init__.py b/docutranslate/decorator/__init__.py
similarity index 100%
rename from filetranslate/decorator/__init__.py
rename to docutranslate/decorator/__init__.py
diff --git a/filetranslate/decorator/markdown_mask.py b/docutranslate/decorator/markdown_mask.py
similarity index 94%
rename from filetranslate/decorator/markdown_mask.py
rename to docutranslate/decorator/markdown_mask.py
index 57b2a9d..a532a72 100644
--- a/filetranslate/decorator/markdown_mask.py
+++ b/docutranslate/decorator/markdown_mask.py
@@ -2,7 +2,7 @@ from functools import wraps
from typing import Concatenate, ParamSpec, Callable
import re
-from filetranslate.utils.markdown_utils import MaskDict
+from docutranslate.utils.markdown_utils import MaskDict
P=ParamSpec("P")
def mask_uris_temp(func:Callable[Concatenate[str, P], str]) -> Callable[Concatenate[str, P], str]:
diff --git a/filetranslate/decorator/time.py b/docutranslate/decorator/time.py
similarity index 100%
rename from filetranslate/decorator/time.py
rename to docutranslate/decorator/time.py
diff --git a/filetranslate/translater.py b/docutranslate/translater.py
similarity index 97%
rename from filetranslate/translater.py
rename to docutranslate/translater.py
index fb66bf7..5e7d2cc 100644
--- a/filetranslate/translater.py
+++ b/docutranslate/translater.py
@@ -3,11 +3,11 @@ from typing import Literal
import markdown2
-from filetranslate.decorator.markdown_mask import MaskDict
-from filetranslate.utils.agent_utils import Agent
-from filetranslate.utils.convert import pdf2markdown_embed_images
-from filetranslate.utils.markdown_splitter import split_markdown_text
-from filetranslate.utils.markdown_utils import uris2placeholder, placeholder2_uris
+from docutranslate.decorator.markdown_mask import MaskDict
+from docutranslate.utils.agent_utils import Agent
+from docutranslate.utils.convert import pdf2markdown_embed_images
+from docutranslate.utils.markdown_splitter import split_markdown_text
+from docutranslate.utils.markdown_utils import uris2placeholder, placeholder2_uris
class FileTranslater:
diff --git a/filetranslate/utils/__init__.py b/docutranslate/utils/__init__.py
similarity index 100%
rename from filetranslate/utils/__init__.py
rename to docutranslate/utils/__init__.py
diff --git a/filetranslate/utils/agent_utils.py b/docutranslate/utils/agent_utils.py
similarity index 100%
rename from filetranslate/utils/agent_utils.py
rename to docutranslate/utils/agent_utils.py
diff --git a/filetranslate/utils/convert.py b/docutranslate/utils/convert.py
similarity index 100%
rename from filetranslate/utils/convert.py
rename to docutranslate/utils/convert.py
diff --git a/filetranslate/utils/markdown_splitter.py b/docutranslate/utils/markdown_splitter.py
similarity index 100%
rename from filetranslate/utils/markdown_splitter.py
rename to docutranslate/utils/markdown_splitter.py
diff --git a/filetranslate/utils/markdown_utils.py b/docutranslate/utils/markdown_utils.py
similarity index 100%
rename from filetranslate/utils/markdown_utils.py
rename to docutranslate/utils/markdown_utils.py
diff --git a/pyproject.toml b/pyproject.toml
index fc72b5b..7b38cbd 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,5 +1,5 @@
[project]
-name = "filetranslate"
+name = "docutranslate"
version = "0.0.1"
description = "能翻译pdf和markdown的软件"
readme = "README.md"