feat: Release v0.10 - Modular Architecture & External Config

- Refactor codebase into src/ (preprocessing, translation, assembly)
- Add pipeline/ scripts for individual stages
- Externalize configuration to config/config.yaml
- Fix Cover Image preservation
- Update documentation and manuals

config/config.example.json

@@ -1,54 +0,0 @@
-{
-  "translation": {
-    "chunk_size": 5000,
-    "temperature": 0.3,
-    "glossary": {
-      "enabled": true,
-      "auto_generate": true,
-      "sample_size": 3000
-    }
-  },
-  "output": {
-    "output_dir": "output",
-    "filename_suffix": "_bilingual"
-  },
-  "logging": {
-    "level": "INFO",
-    "file": "logs/translator.log",
-    "rotation": "10 MB",
-    "retention": "7 days"
-  },
-  "providers": {
-    "openrouter": {
-      "base_url": "https://openrouter.ai/api/v1",
-      "api_key": "YOUR_OPENROUTER_API_KEY",
-      "models": {
-        "fast": "google/gemini-2.0-flash-001",
-        "smart": "google/gemini-2.0-flash-thinking-exp:free"
-      },
-      "extra_headers": {
-        "HTTP-Referer": "https://github.com/epub-translator",
-        "X-Title": "EPUB Translator"
-      },
-      "rate_limits": {
-        "requests_per_minute": 60,
-        "concurrent_requests": 32
-      }
-    },
-    "v3": {
-      "base_url": "https://api.gpt.ge/v1",
-      "api_key": "YOUR_V3_API_KEY",
-      "models": {
-        "fast": "gpt-4o-mini",
-        "smart": "gpt-4o"
-      },
-      "extra_headers": {
-        "x-foo": "true"
-      },
-      "rate_limits": {
-        "requests_per_minute": 500,
-        "concurrent_requests": 50
-      }
-    }
-  }
-}

config/config.yaml

@@ -0,0 +1,25 @@
+# LLM Configuration
+llm:
+  # Model name (e.g., gpt-4o, gpt-3.5-turbo, deepseek-chat)
+  model: "google/gemini-3-flash-preview"
+  #model: "gemini-3-pro-low"
+  
+  # API Base URL (default is OpenAI)
+  #base_url: "https://api.gpt.ge/v1"
+  #base_url: "http://192.168.50.100:11434/v1"
+  base_url: "https://openrouter.ai/api/v1"
+  
+  # Timeout for API requests in seconds
+  timeout: 60
+  
+  # Rate Limiting
+  requests_per_minute: 60
+  concurrent_requests: 4
+
+# Translation Settings
+translation:
+  # Characters per chunk (approximate)
+  chunk_size: 6000
+  
+  # System prompt instruction file (optional, overrides default if present)
+  # style_guide_path: "config/style_guide.txt"

config/config_副本.json

@@ -1,39 +0,0 @@
-{
-  "llm": {
-    "provider": "openrouter",
-    "base_url": "https://openrouter.ai/api/v1",
-    "api_key": "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",
-    "models": {
-      "fast": "google/gemini-3-flash-preview",
-      "smart": "google/gemini-3-pro-preview"
-    },
-    "arena_models": [
-      "google/gemini-3-flash-preview",
-      "openai/gpt-5-mini",
-      "anthropic/claude-haiku-4.5"
-    ],
-    "judge_model": "openai/gpt-5.1",
-    "rate_limits": {
-      "requests_per_minute": 60,
-      "concurrent_requests": 32
-    }
-  },
-  "translation": {
-    "chunk_size": 5000,
-    "temperature": 0.3,
-    "strategy": "arena_winner"
-  },
-  "processing": {
-    "min_paragraph_length": 5
-  },
-  "output": {
-    "output_dir": "output",
-    "filename_suffix": "_bilingual"
-  },
-  "logging": {
-    "level": "INFO",
-    "file": "logs/translator.log",
-    "rotation": "10 MB",
-    "retention": "7 days"
-  }
-}

config/prompts.json

@@ -1,10 +1,10 @@
 {
   "translation": {
-    "system": "你是一位精通中英文的专业翻译家。你的任务是翻译书籍内容。\n\n要求：\n1. 准确传达原文含义，语言流畅自然，符合中文阅读习惯。\n2. 严格保持【p_xxxxx】编号格式，不要遗漏，不要修改编号。\n3. 不要添加任何解释、注释或无关内容，只返回【编号】+【译文】。\n\n{{glossary_instruction}}",
-    "user_template": "请翻译以下段落：\n\n{{content}}"
+    "system": "你是一位精通中英文的专业翻译家。你的任务是将英文书籍内容翻译成中文。\n\n【核心要求】\n1. 准确传达原文含义，语言流畅自然，符合中文阅读习惯。\n2. 保持原文的风格和语气。\n\n【格式要求 - 极其重要】\n1. 每行格式：#N: 译文（N是行号，必须原样保留）\n2. 输入多少行，输出必须是相同数量的行\n3. **占位符规则**：原文中的 φXφ 和 φ/Xφ 标记必须原样保留在译文中\n   - 成对标记：\"φ1φBoldφ/1φ\" → \"φ1φ粗体φ/1φ\"\n   - 单体标记：\"φ2φ\" 表示公式或符号，保持位置不变\n   - 尾注锚点：文末的 \"φ3φ\" 是超链接，必须保留\n\n【禁止事项】\n- 禁止修改 #N: 行号\n- 禁止删除或修改任何 φXφ 标记\n- 禁止添加解释或注释\n- 禁止合并或拆分行",
+    "user_template": "请翻译以下段落（务必原样保留所有 φnφ 格式标记）：\n\n{{content}}"
   },
   "glossary_extraction": {
     "system": "你是一位资深的文学编辑和领域专家。你的任务是分析书籍样本，提取关键术语并制定统一的译名表。",
     "user_template": "请阅读以下书籍片段（包含前言和正文采样）。\n\n任务：\n1. 识别文中出现的人名（如 'Masa', 'Steve Jobs'）、地名、机构名。\n2. 识别特定的行业术语或关键概念。\n3. 为上述词汇提供标准的中文译名。如果像 'Masa' 这样的昵称有对应的全名（如孙正义），请务必使用全名。\n\n请以 JSON 格式输出，格式如下：\n{\n  \"Masa\": \"孙正义\",\n  \"Apple\": \"苹果公司\",\n  ...\n}\n\n书籍片段：\n\n{{content}}"
   }
-}
+}