llm_translate 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 584007a41c9b59041a1ecd9e42c96231c66fdc606edb19567c58fd342d838a15
+  data.tar.gz: 1b9afce81578be82bcfd4f81a7fa6050073d9eef8848a7ee43ef9110b38ead94
+SHA512:
+  metadata.gz: a959c5dfcf20bfc2bc94f787cf8c3e49ee75417a5be461a0b2650d023ce964670dd566e118e764b3152c3afdc2a22d2ac33605fdfca7909e55848e0761b0515c
+  data.tar.gz: d56df324476f82d6deb7e4b28bba026349661e4b5c389e1068e09dae36ecae7c38a8d38cee8cbfa861c686db3f063f3715cc0c18430e462d86f4ebf69079ce72

data/.rspec_status

@@ -0,0 +1,14 @@
+example_id                              | status | run_time        |
+--------------------------------------- | ------ | --------------- |
+./spec/translator/config_spec.rb[1:1:1] | passed | 0.00338 seconds |
+./spec/translator/config_spec.rb[1:1:2] | passed | 0.00113 seconds |
+./spec/translator/config_spec.rb[1:2:1] | passed | 0.00078 seconds |
+./spec/translator/config_spec.rb[1:3:1] | passed | 0.00044 seconds |
+./spec/translator/config_spec.rb[1:3:2] | passed | 0.00077 seconds |
+./spec/translator/config_spec.rb[1:4:1] | passed | 0.00038 seconds |
+./spec/translator/config_spec.rb[1:5:1] | passed | 0.0007 seconds  |
+./spec/translator/config_spec.rb[1:5:2] | passed | 0.00035 seconds |
+./spec/translator/config_spec.rb[1:5:3] | passed | 0.00043 seconds |
+./spec/translator_spec.rb[1:1]          | passed | 0.00057 seconds |
+./spec/translator_spec.rb[1:2]          | passed | 0.00004 seconds |
+./spec/translator_spec.rb[1:3]          | passed | 0.00073 seconds |

data/README.md

@@ -0,0 +1,301 @@
+# LlmTranslate
+
+AI-powered Markdown translator that preserves formatting while translating content using various AI providers.
+
+## Features
+
+- 🤖 **AI-Powered Translation**: Support for OpenAI, Anthropic, and Ollama
+- 📝 **Markdown Format Preservation**: Keeps code blocks, links, images, and formatting intact
+- 🔧 **Flexible Configuration**: YAML-based configuration with environment variable support
+- 📁 **Batch Processing**: Recursively processes entire directory structures
+- 🚀 **CLI Interface**: Easy-to-use command-line interface with Thor
+- 📊 **Progress Tracking**: Built-in logging and reporting
+- ⚡ **Error Handling**: Robust error handling with retry mechanisms
+- 🎯 **Customizable**: Custom prompts, file patterns, and output strategies
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'llm_translate'
+```
+
+And then execute:
+
+```bash
+bundle install
+```
+
+Or install it yourself as:
+
+```bash
+gem install llm_translate
+```
+
+## Dependencies
+
+The gem requires the `rubyllm` gem for AI integration:
+
+```bash
+gem install rubyllm
+```
+
+## Quick Start
+
+1. **Initialize a configuration file**:
+   ```bash
+   llm_translate init
+   ```
+
+2. **Set your API key**:
+   ```bash
+   export LLM_TRANSLATE_API_KEY="your-api-key-here"
+   ```
+
+3. **Translate your markdown files**:
+   ```bash
+   llm_translate translate --config ./llm_translate.yml
+   ```
+
+## Configuration
+
+The translator uses a YAML configuration file. Here's a minimal example:
+
+```yaml
+# llm_translate.yml
+ai:
+  api_key: ${LLM_TRANSLATE_API_KEY}
+  provider: "openai"
+  model: "gpt-4"
+  temperature: 0.3
+
+translation:
+  target_language: "zh-CN"
+  default_prompt: |
+    Please translate the following Markdown content to Chinese, keeping all formatting intact:
+    - Preserve code blocks, links, images, and other Markdown syntax
+    - Keep English technical terms and product names
+    - Ensure natural and fluent translation
+    
+    Content:
+    {content}
+
+files:
+  input_directory: "./docs"
+  output_directory: "./docs-translated"
+  filename_suffix: ".zh"
+
+logging:
+  level: "info"
+  output: "console"
+```
+
+### AI Providers
+
+#### OpenAI
+```yaml
+ai:
+  provider: "openai"
+  api_key: ${OPENAI_API_KEY}
+  model: "gpt-4"
+```
+
+#### Anthropic
+```yaml
+ai:
+  provider: "anthropic"
+  api_key: ${ANTHROPIC_API_KEY}
+  model: "claude-3-sonnet-20240229"
+```
+
+#### Ollama (Local)
+```yaml
+ai:
+  provider: "ollama"
+  model: "llama2"
+  # Set OLLAMA_HOST environment variable if not using default
+```
+
+## Usage
+
+### Basic Translation
+
+#### Directory Mode (Default)
+```bash
+llm_translate translate --config ./llm_translate.yml
+```
+
+#### Single File Mode
+To translate a single file, configure `input_file` and `output_file` in your configuration:
+
+```yaml
+files:
+  # Single file mode
+  input_file: "./README.md"
+  output_file: "./README.zh.md"
+```
+
+When both `input_file` and `output_file` are specified, the translator will operate in single file mode, ignoring directory-related settings.
+
+### Command Line Options
+
+```bash
+llm_translate translate [OPTIONS]
+
+Options:
+  -c, --config PATH      Configuration file path (default: ./llm_translate.yml)
+  -i, --input PATH       Input directory (overrides config)
+  -o, --output PATH      Output directory (overrides config)
+  -p, --prompt TEXT      Custom translation prompt (overrides config)
+  -v, --verbose          Enable verbose output
+  -d, --dry-run          Perform a dry run without actual translation
+
+Other Commands:
+  llm_translate init        Initialize a new configuration file
+  llm_translate version     Show version information
+```
+
+### Configuration File Structure
+
+```yaml
+# AI Configuration
+ai:
+  api_key: ${LLM_TRANSLATE_API_KEY}
+  provider: "openai"  # openai, anthropic, ollama
+  model: "gpt-4"
+  temperature: 0.3
+  max_tokens: 4000
+  retry_attempts: 3
+  retry_delay: 2
+  timeout: 60
+
+# Translation Settings
+translation:
+  target_language: "zh-CN"
+  source_language: "auto"
+  default_prompt: "Your custom prompt with {content} placeholder"
+  preserve_formatting: true
+  translate_code_comments: false
+  preserve_patterns:
+    - "```[\\s\\S]*?```"    # Code blocks
+    - "`[^`]+`"              # Inline code
+    - "\\[.*?\\]\\(.*?\\)"   # Links
+    - "!\\[.*?\\]\\(.*?\\)"  # Images
+
+# File Processing
+files:
+  input_directory: "./docs"
+  output_directory: "./docs-translated"
+  filename_strategy: "suffix"  # suffix, replace, directory
+  filename_suffix: ".zh"
+  include_patterns:
+    - "**/*.md"
+    - "**/*.markdown"
+  exclude_patterns:
+    - "**/node_modules/**"
+    - "**/.*"
+  preserve_directory_structure: true
+  overwrite_policy: "ask"  # ask, overwrite, skip, backup
+  backup_directory: "./backups"
+
+# Logging
+logging:
+  level: "info"  # debug, info, warn, error
+  output: "console"  # console, file, both
+  file_path: "./logs/translator.log"
+  verbose_translation: false
+  error_log_path: "./logs/errors.log"
+
+# Error Handling
+error_handling:
+  on_error: "log_and_continue"  # stop, log_and_continue, skip_file
+  max_consecutive_errors: 5
+  retry_on_failure: 2
+  generate_error_report: true
+  error_report_path: "./logs/error_report.md"
+
+# Performance
+performance:
+  concurrent_files: 3
+  batch_size: 5
+  request_interval: 1  # seconds between requests
+  max_memory_mb: 500
+
+# Output
+output:
+  show_progress: true
+  show_statistics: true
+  generate_report: true
+  report_path: "./reports/translation_report.md"
+  format: "markdown"
+  include_metadata: true
+```
+
+## Examples
+
+### Translate Documentation
+
+```bash
+# Translate all markdown files in ./docs to Chinese
+llm_translate translate --input ./docs --output ./docs-zh
+
+# Use custom prompt
+llm_translate translate --prompt "翻译以下内容为中文，保持技术术语不变: {content}"
+
+# Dry run to see what would be translated
+llm_translate translate --dry-run --verbose
+```
+
+### Batch Translation
+
+```bash
+# Translate multiple language versions
+for lang in zh-CN ja-JP ko-KR; do
+  llm_translate translate --config "./configs/llm_translate-${lang}.yml"
+done
+```
+
+## Development
+
+After checking out the repo, run:
+
+```bash
+bundle install
+```
+
+To run tests:
+
+```bash
+bundle exec rspec
+```
+
+To run linting:
+
+```bash
+bundle exec rubocop
+```
+
+To install this gem onto your local machine:
+
+```bash
+bundle exec rake install
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/llm_translate/llm_translate.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Changelog
+
+### v0.1.0
+- Initial release
+- Support for OpenAI, Anthropic, and Ollama providers
+- Markdown format preservation
+- Configurable translation prompts
+- Batch file processing
+- Comprehensive error handling and logging

data/README.zh.md

@@ -0,0 +1,209 @@
+# LlmTranslate
+
+一个由AI驱动的Markdown翻译器，能够在翻译内容时保持格式不变，同时使用各种AI提供者。
+
+## 特性
+
+- 🤖 **AI驱动的翻译**：支持OpenAI、Anthropic和Ollama
+- 📝 **Markdown格式保留**：保持代码块、链接、图像和格式不变
+- 🔧 **灵活配置**：基于YAML的配置，支持环境变量
+- 📁 **批量处理**：递归处理整个目录结构
+- 🚀 **CLI接口**：易于使用的命令行接口，使用Thor
+- 📊 **进度跟踪**：内置日志记录和报告
+- ⚡ **错误处理**：强大的错误处理机制，带有重试机制
+- 🎯 **可定制**：自定义提示、文件模式和输出策略
+
+## 安装
+
+将此行添加到您应用程序的Gemfile中：
+
+```ruby
+gem 'llm_translate'
+```
+
+然后执行：
+
+```bash
+bundle install
+```
+
+或者您也可以自己安装：
+
+```bash
+gem install llm_translate
+```
+
+## 依赖
+
+该gem需要`rubyllm` gem进行AI集成：
+
+```bash
+gem install rubyllm
+```
+
+## 快速开始
+
+1. **初始化配置文件**：
+   ```bash
+   llm_translate init
+   ```
+
+2. **设置您的API密钥**：
+   ```bash
+   export LLM_TRANSLATE_API_KEY="your-api-key-here"
+   ```
+
+3. **翻译您的markdown文件**：
+   ```bash
+   llm_translate translate --config ./translator.yml
+   ```
+
+## 配置
+
+翻译器使用YAML配置文件。以下是一个最小示例：
+
+```yaml
+# translator.yml
+ai:
+  api_key: ${LLM_TRANSLATE_API_KEY}
+  provider: "openai"
+  model: "gpt-4"
+  temperature: 0.3
+
+translation:
+  target_language: "zh-CN"
+  default_prompt: |
+    Please translate the following Markdown content to Chinese, keeping all formatting intact:
+    - Preserve code blocks, links, images, and other Markdown syntax
+    - Keep English technical terms and product names
+    - Ensure natural and fluent translation
+    
+    Content:
+    {content}
+
+files:
+  input_directory: "./docs"
+  output_directory: "./docs-translated"
+  filename_suffix: ".zh"
+
+logging:
+  level: "info"
+  output: "console"
+```
+
+### AI提供者
+
+#### OpenAI
+```yaml
+ai:
+  provider: "openai"
+  api_key: ${OPENAI_API_KEY}
+  model: "gpt-4"
+```
+
+#### Anthropic
+```yaml
+ai:
+  provider: "anthropic"
+  api_key: ${ANTHROPIC_API_KEY}
+  model: "claude-3-sonnet-20240229"
+```
+
+#### Ollama（本地）
+```bash
+bundle install
+```0
+
+## 使用
+
+### 基本翻译
+
+#### 目录模式（默认）
+```bash
+bundle install
+```1
+
+#### 单文件模式
+要翻译单个文件，请在配置中设置`input_file```bash
+   llm_translate init
+   ```7output_file`：
+
+```bash
+bundle install
+```2
+
+当同时指定`input_file```bash
+   llm_translate init
+   ```7output_file`时，翻译器将以单文件模式运行，忽略与目录相关的设置。
+
+### 命令行选项
+
+```bash
+bundle install
+```3
+
+### 配置文件结构
+
+```bash
+bundle install
+```4[\s\S]*?```bash
+bundle install
+```5
+
+## 示例
+
+### 翻译文档
+
+```bash
+bundle install
+```6
+
+### 批量翻译
+
+```bash
+bundle install
+```7
+
+## 开发
+
+克隆代码库后，运行：
+
+```bash
+bundle install
+```
+
+要运行测试：
+
+```bash
+bundle install
+```9
+
+要运行代码检查：
+
+```bash
+gem install llm_translate
+```0
+
+要将此gem安装到您的本地机器上：
+
+```bash
+gem install llm_translate
+```1
+
+## 贡献
+
+欢迎在GitHub上提交错误报告和拉取请求，地址为 https://github.com/translator/translator。
+
+## 许可证
+
+该gem在[MIT许可证](https://opensource.org/licenses/MIT)条款下作为开源软件提供。
+
+## 更新日志
+
+### v0.1.0
+- 初始发布
+- 支持OpenAI、Anthropic和Ollama提供者
+- Markdown格式保留
+- 可配置的翻译提示
+- 批量文件处理
+- 综合的错误处理和日志记录

data/Rakefile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+require 'rubocop/rake_task'
+
+RuboCop::RakeTask.new
+
+task default: %i[spec rubocop]

data/content/changelog-1.md

@@ -0,0 +1,12 @@
+
+# 只添加 gem ruby_llm
+
+API 可以指定 AI HOSTName 以及 key
+
+# 测试密钥
+HOST默认为 https://aihubmix.com
+
+KEY 为 sk-
+
+模型为 claude-3-7-sonnet-20250219
+# 真实的请求进行测试

data/content/changelog-2.md

@@ -0,0 +1,12 @@
+# llm_translate.yml 新增
+
+支持
+file:
+  # 输入文件
+  input_file: "./README.md"
+
+  # 输出文件
+  output_file: "./README.zh.md"
+
+
+当 input_file 存在时，读取这个文件进行翻译。