Initial commit

archive/v0.02/src/__init__.py

@@ -0,0 +1,24 @@
+"""
+EPUB 双语翻译程序
+主要功能模块的初始化文件
+"""
+
+__version__ = "0.1.0"
+__author__ = "Kaitan"
+
+from .epub_parser import EPUBParser
+from .translator import EPUBTranslator
+from .llm_client import OpenRouterClient
+from .text_processor import TextProcessor
+from .bilingual_builder import BilingualEPUBBuilder
+from .utils import load_config, setup_logging
+
+__all__ = [
+    "EPUBParser",
+    "EPUBTranslator", 
+    "OpenRouterClient",
+    "TextProcessor",
+    "BilingualEPUBBuilder",
+    "load_config",
+    "setup_logging"
+]

archive/v0.02/src/bilingual_builder.py

@@ -0,0 +1,155 @@
+"""
+双语 EPUB 构建器模块 - 安全的EPUB构建 (Manifest 兼容版)
+"""
+
+from ebooklib import epub
+import ebooklib
+from bs4 import BeautifulSoup
+from typing import Dict, List
+from pathlib import Path
+from loguru import logger
+import uuid
+
+
+class BilingualEPUBBuilder:
+    """双语 EPUB 构建器"""
+    
+    def __init__(self, original_book, config: Dict):
+        self.original_book = original_book
+        self.config = config
+        self.output_config = config['output']
+    
+    def create_bilingual_epub_with_mapping(self, translation_map: Dict[str, str],
+                                          paragraph_map: Dict[str, Dict],
+                                          output_path: str) -> str:
+        """
+        创建双语 EPUB。使用 ordered_ids 确保与 Manifest 严格一致。
+        """
+        try:
+            new_book = epub.EpubBook()
+            self._copy_metadata(new_book)
+            new_book.toc = self.original_book.toc
+            
+            # 准备每个文件的有序ID列表
+            file_ordered_ids = {}
+            sorted_pids = sorted(paragraph_map.keys(), key=lambda x: int(x.split('_')[1]))
+            for pid in sorted_pids:
+                info = paragraph_map[pid]
+                fname = info['file_name']
+                if fname not in file_ordered_ids:
+                    file_ordered_ids[fname] = []
+                file_ordered_ids[fname].append(pid)
+            
+            processed_item_ids = set()
+            item_map = {}
+
+            # 复制资源
+            for item in self.original_book.get_items():
+                if item.get_type() != ebooklib.ITEM_DOCUMENT:
+                    if item.id not in processed_item_ids:
+                        new_book.add_item(item)
+                        processed_item_ids.add(item.id)
+                        item_map[item.id] = item
+
+            # 重建 Spine
+            new_spine = []
+            for spine_id, linear in self.original_book.spine:
+                item = self.original_book.get_item_with_id(spine_id)
+                if not item: continue
+                
+                if item.get_type() == ebooklib.ITEM_DOCUMENT:
+                    file_name = item.get_name()
+                    if file_name in file_ordered_ids:
+                        new_item = self._create_bilingual_document(
+                            item, file_ordered_ids[file_name], translation_map
+                        )
+                        new_item.id = item.id 
+                    else:
+                        new_item = item
+                    
+                    if new_item.id not in processed_item_ids:
+                        new_book.add_item(new_item)
+                        processed_item_ids.add(new_item.id)
+                    new_spine.append(new_item)
+                else:
+                    if item.id in item_map:
+                        new_spine.append(item_map[item.id])
+            
+            new_book.spine = new_spine
+            new_book.add_item(epub.EpubNcx())
+            new_book.add_item(epub.EpubNav())
+            
+            output_file = self._generate_output_filename(output_path)
+            epub.write_epub(output_file, new_book, {})
+            return output_file
+            
+        except Exception as e:
+            logger.error(f"创建双语 EPUB 失败: {e}", exc_info=True)
+            raise
+
+    def _copy_metadata(self, new_book):
+        try:
+            for namespace, meta_dict in self.original_book.metadata.items():
+                for name, values in meta_dict.items():
+                    for value, other in values:
+                        if name and hasattr(name, 'lower') and name.lower() == 'identifier': continue
+                        new_book.add_metadata(namespace, name, value, other)
+            new_book.add_metadata('DC', 'language', 'zh-CN')
+            new_book.set_identifier(f"bilingual-{uuid.uuid4().hex[:12]}")
+            
+            cover_id_meta = self.original_book.get_metadata('OPF', 'cover')
+            if cover_id_meta:
+                cover_item = self.original_book.get_item_with_id(cover_id_meta[0][0])
+                if cover_item:
+                    new_book.add_item(cover_item)
+                    new_book.set_cover(cover_item.get_name(), cover_item.get_content())
+        except Exception as e:
+            logger.error(f"元数据复制出错: {e}")
+
+    def _create_bilingual_document(self, original_item, ordered_ids: list, translation_map: dict):
+        try:
+            from .text_processor import TextProcessor
+            soup = BeautifulSoup(original_item.get_content().decode('utf-8'), 'html.parser')
+            self._add_style_link(soup)
+            
+            # 使用与 TextProcessor 相同的过滤逻辑获取元素
+            text_elements = TextProcessor.get_valid_text_elements(soup)
+            
+            current_para_index = 0
+            for element in text_elements:
+                if TextProcessor.is_navigation_element(element): continue
+                if not TextProcessor.clean_element_text(element): continue
+                
+                if current_para_index < len(ordered_ids):
+                    target_id = ordered_ids[current_para_index]
+                    translation = translation_map.get(target_id)
+                    if translation:
+                        self._insert_translation(element, translation, soup)
+                    current_para_index += 1
+            
+            new_item = epub.EpubHtml(title=original_item.title, file_name=original_item.get_name(), lang='zh-CN')
+            new_item.set_content(str(soup).encode('utf-8'))
+            return new_item
+        except Exception as e:
+            logger.error(f"创建双语文档失败 {original_item.get_name()}: {e}")
+            return original_item
+
+    def _add_style_link(self, soup):
+        head = soup.find('head')
+        if head and not head.find('link', href='style/bilingual.css'):
+            head.append(soup.new_tag('link', rel='stylesheet', type='text/css', href='style/bilingual.css'))
+
+    def _insert_translation(self, element, translation: str, soup):
+        try:
+            translation_p = soup.new_tag('p')
+            translation_p.string = translation
+            translation_p['class'] = ['translation-text', 'chinese']
+            element.insert_after(translation_p)
+        except: pass
+
+    def _generate_output_filename(self, output_path: str) -> str:
+        from .utils import sanitize_filename
+        title = self.original_book.get_metadata('DC', 'title')
+        clean_title = sanitize_filename(title[0][0]) if title else "bilingual_book"
+        Path(output_path).mkdir(parents=True, exist_ok=True)
+        return str(Path(output_path) / f"{clean_title}_bilingual.epub")

archive/v0.02/src/cache.py

@@ -0,0 +1,225 @@
+"""
+翻译缓存管理模块 - 简化版
+基于全局ID和chunk的缓存系统
+"""
+
+import json
+import hashlib
+from pathlib import Path
+from datetime import datetime, timedelta
+from typing import Dict, Optional, List
+from loguru import logger
+
+
+class TranslationCache:
+    """翻译缓存管理器 - 简化版"""
+    
+    def __init__(self, config: Dict):
+        """初始化缓存管理器"""
+        self.config = config
+        cache_config = config.get('cache', {})
+        
+        self.enabled = cache_config.get('enabled', True)
+        self.cache_dir = Path(cache_config.get('directory', 'cache'))
+        self.max_age_days = cache_config.get('max_age_days', 30)
+        
+        if self.enabled:
+            self.cache_dir.mkdir(parents=True, exist_ok=True)
+            self.translations_dir = self.cache_dir / 'translations'
+            self.translations_dir.mkdir(parents=True, exist_ok=True)
+            
+            logger.info(f"翻译缓存已启用: {self.cache_dir}")
+    
+    def get_chunk_translation(self, chunk: List[Dict], model: str) -> Optional[Dict[str, str]]:
+        """
+        获取chunk的缓存翻译
+        
+        Args:
+            chunk: 段落列表（带global_id）
+            model: 模型名称
+            
+        Returns:
+            {global_id: translation} 映射，如果不存在返回 None
+        """
+        if not self.enabled:
+            return None
+        
+        try:
+            cache_key = self._get_chunk_cache_key(chunk, model)
+            cache_file = self._get_cache_file_path(cache_key)
+            
+            if not cache_file.exists():
+                return None
+            
+            # 检查是否过期
+            file_age = datetime.now() - datetime.fromtimestamp(cache_file.stat().st_mtime)
+            if file_age > timedelta(days=self.max_age_days):
+                logger.debug(f"缓存已过期: {cache_key[:8]}...")
+                cache_file.unlink()
+                return None
+            
+            # 读取缓存
+            with open(cache_file, 'r', encoding='utf-8') as f:
+                cache_data = json.load(f)
+            
+            # 验证缓存
+            if (cache_data.get('success') and 
+                cache_data.get('model') == model and
+                self._validate_cache_data(cache_data, chunk)):
+                
+                logger.debug(f"缓存命中: {cache_key[:8]}... ({len(chunk)} 段落)")
+                return cache_data.get('translations', {})
+            
+            return None
+            
+        except Exception as e:
+            logger.warning(f"读取缓存失败: {e}")
+            return None
+    
+    def save_chunk_translation(self, chunk: List[Dict], translations: Dict[str, str], 
+                              model: str, success: bool = True) -> None:
+        """
+        保存chunk翻译到缓存
+        
+        Args:
+            chunk: 段落列表（带global_id）
+            translations: {global_id: translation} 映射
+            model: 模型名称
+            success: 是否翻译成功
+        """
+        if not self.enabled:
+            return
+        
+        try:
+            cache_key = self._get_chunk_cache_key(chunk, model)
+            cache_file = self._get_cache_file_path(cache_key)
+            
+            # 构建缓存数据
+            cache_data = {
+                'global_ids': [p['global_id'] for p in chunk],
+                'translations': translations,
+                'model': model,
+                'timestamp': datetime.now().isoformat(),
+                'success': success,
+                'paragraph_count': len(chunk),
+                'cache_version': '3.0'
+            }
+            
+            with open(cache_file, 'w', encoding='utf-8') as f:
+                json.dump(cache_data, f, ensure_ascii=False, indent=2)
+            
+            logger.debug(f"缓存已保存: {cache_key[:8]}... ({len(chunk)} 段落)")
+            
+        except Exception as e:
+            logger.warning(f"保存缓存失败: {e}")
+    
+    def _get_chunk_cache_key(self, chunk: List[Dict], model: str) -> str:
+        """
+        生成chunk缓存键（基于全局ID序列）
+        
+        Args:
+            chunk: 段落列表
+            model: 模型名称
+            
+        Returns:
+            缓存键
+        """
+        # 使用全局ID序列作为缓存键的一部分
+        id_sequence = ",".join(p['global_id'] for p in chunk)
+        combined = f"{id_sequence}|{model}"
+        return hashlib.md5(combined.encode('utf-8')).hexdigest()
+    
+    def _get_cache_file_path(self, cache_key: str) -> Path:
+        """获取缓存文件路径"""
+        today = datetime.now().strftime('%Y-%m-%d')
+        cache_date_dir = self.translations_dir / today
+        cache_date_dir.mkdir(parents=True, exist_ok=True)
+        return cache_date_dir / f"{cache_key}.json"
+    
+    def _validate_cache_data(self, cache_data: Dict, chunk: List[Dict]) -> bool:
+        """验证缓存数据的有效性"""
+        # 检查ID序列是否匹配
+        cached_ids = cache_data.get('global_ids', [])
+        chunk_ids = [p['global_id'] for p in chunk]
+        
+        if cached_ids != chunk_ids:
+            logger.debug("缓存ID序列不匹配")
+            return False
+        
+        # 检查翻译数量
+        translations = cache_data.get('translations', {})
+        if len(translations) != len(chunk):
+            logger.debug("缓存翻译数量不匹配")
+            return False
+        
+        return True
+    
+    def clear_cache(self, older_than_days: Optional[int] = None) -> int:
+        """清理缓存"""
+        if not self.enabled or not self.translations_dir.exists():
+            return 0
+        
+        cleared_count = 0
+        cutoff_time = None
+        
+        if older_than_days is not None:
+            cutoff_time = datetime.now() - timedelta(days=older_than_days)
+        
+        try:
+            for cache_file in self.translations_dir.rglob('*.json'):
+                should_delete = False
+                
+                if cutoff_time is None:
+                    should_delete = True
+                else:
+                    file_time = datetime.fromtimestamp(cache_file.stat().st_mtime)
+                    should_delete = file_time < cutoff_time
+                
+                if should_delete:
+                    cache_file.unlink()
+                    cleared_count += 1
+            
+            # 清理空目录
+            for date_dir in self.translations_dir.iterdir():
+                if date_dir.is_dir() and not any(date_dir.iterdir()):
+                    date_dir.rmdir()
+            
+            logger.info(f"清理了 {cleared_count} 个缓存文件")
+            return cleared_count
+            
+        except Exception as e:
+            logger.error(f"清理缓存失败: {e}")
+            return 0
+    
+    def get_cache_stats(self) -> Dict:
+        """获取缓存统计信息"""
+        if not self.enabled or not self.translations_dir.exists():
+            return {'enabled': False}
+        
+        try:
+            cache_files = list(self.translations_dir.rglob('*.json'))
+            total_files = len(cache_files)
+            total_size = sum(f.stat().st_size for f in cache_files)
+            
+            # 统计段落数
+            total_paragraphs = 0
+            for cache_file in cache_files:
+                try:
+                    with open(cache_file, 'r', encoding='utf-8') as f:
+                        data = json.load(f)
+                        total_paragraphs += data.get('paragraph_count', 0)
+                except:
+                    continue
+            
+            return {
+                'enabled': True,
+                'total_files': total_files,
+                'total_paragraphs': total_paragraphs,
+                'total_size_mb': round(total_size / 1024 / 1024, 2),
+                'cache_directory': str(self.cache_dir),
+                'max_age_days': self.max_age_days
+            }
+            
+        except Exception as e:
+            logger.error(f"获取缓存统计失败: {e}")
+            return {'enabled': True, 'error': str(e)}

archive/v0.02/src/epub_parser.py

@@ -0,0 +1,164 @@
+"""
+EPUB 解析器模块 (EPUB Parser Module)
+
+该模块负责读取 EPUB 文件，提取元数据和内容项目。
+它使用 ebooklib 库来处理 EPUB 格式的底层细节。
+
+Classes:
+    EPUBParser: 负责 EPUB 文件的加载、元数据提取和内容项遍历。
+"""
+
+import ebooklib
+from ebooklib import epub
+from bs4 import BeautifulSoup
+from typing import List, Dict, Any
+from pathlib import Path
+from loguru import logger
+
+
+class EPUBParser:
+    """
+    EPUB 文件解析器。
+
+    负责加载 EPUB 文件，提取书籍元数据（如标题、作者），并提供方法来遍历和提取
+    书中的文档内容（HTML/XHTML）。
+
+    Attributes:
+        epub_path (Path): EPUB 文件的路径对象。
+        book (epub.EpubBook): ebooklib 加载的书籍对象。
+        metadata (Dict[str, str]): 提取的书籍元数据字典。
+    """
+    
+    def __init__(self, epub_path: str):
+        """
+        初始化 EPUB 解析器。
+
+        Args:
+            epub_path (str): EPUB 文件的文件路径。
+
+        Raises:
+            FileNotFoundError: 如果指定的文件不存在。
+            Exception: 如果 EPUB 文件加载失败（格式错误等）。
+        """
+        self.epub_path = Path(epub_path)
+        if not self.epub_path.exists():
+            raise FileNotFoundError(f"EPUB 文件不存在: {epub_path}")
+        
+        try:
+            # ignore_ncx=True 是为了避免某些旧版 epub 的警告，但新版 ebooklib 可能行为不同
+            # 这里直接读取，让 ebooklib 处理
+            self.book = epub.read_epub(str(self.epub_path))
+            logger.info(f"成功加载 EPUB: {self.epub_path.name}")
+        except Exception as e:
+            logger.error(f"加载 EPUB 失败: {e}")
+            raise
+        
+        self.metadata = self._extract_metadata()
+    
+    def _extract_metadata(self) -> Dict[str, str]:
+        """
+        从 EPUB 对象中提取标准元数据。
+
+        提取 Dublin Core (DC) 元数据，包括标题、作者和语言。
+
+        Returns:
+            Dict[str, str]: 包含 'title', 'author', 'language' 的字典。
+                            如果提取失败，会使用默认值 ("Unknown", "en")。
+        """
+        metadata = {}
+        
+        try:
+            # get_metadata 返回的是 (value, dict) 的列表，我们取第一个结果
+            title_meta = self.book.get_metadata('DC', 'title')
+            metadata['title'] = title_meta[0][0] if title_meta else "Unknown"
+            
+            author_meta = self.book.get_metadata('DC', 'creator')
+            metadata['author'] = author_meta[0][0] if author_meta else "Unknown"
+            
+            lang_meta = self.book.get_metadata('DC', 'language')
+            metadata['language'] = lang_meta[0][0] if lang_meta else "en"
+            
+            logger.info(f"书籍: {metadata['title']} - {metadata['author']}")
+        except Exception as e:
+            logger.warning(f"提取元数据时出错: {e}")
+            # 设置保底值
+            metadata.setdefault('title', 'Unknown')
+            metadata.setdefault('author', 'Unknown')
+            metadata.setdefault('language', 'en')
+        
+        return metadata
+    
+    def extract_all_content_items(self) -> List[Dict[str, Any]]:
+        """
+        提取所有可翻译的内容项目（文档）。
+
+        遍历 EPUB 中的所有 Item，筛选出类型为 ITEM_DOCUMENT 的项目。
+        同时会进行简单的过滤，跳过内容过短（<100字符）或看起来像非正文的文件（如 nav, toc, cover）。
+
+        Returns:
+            List[Dict[str, Any]]: 内容项目列表。每个字典包含：
+                - item (epub.EpubItem): 原始 Item 对象。
+                - file_name (str): 文件名。
+                - content (str): 解码后的 HTML 内容。
+                - text_length (int): 纯文本长度（用于统计）。
+        """
+        content_items = []
+        
+        # 获取所有文档类型的项目
+        for item in self.book.get_items():
+            if item.get_type() == ebooklib.ITEM_DOCUMENT:
+                try:
+                    # 获取内容 (bytes -> str)
+                    content = item.get_content().decode('utf-8')
+                    
+                    # 简单的内容验证：提取纯文本检查长度
+                    soup = BeautifulSoup(content, 'html.parser')
+                    text = soup.get_text().strip()
+                    
+                    # 1. 跳过太短的内容（可能是只有图片的页面、空页面）
+                    if len(text) < 100:
+                        logger.debug(f"跳过短内容: {item.get_name()} ({len(text)} 字符)")
+                        continue
+                    
+                    # 2. 跳过明显的非正文内容 (根据文件名判断)
+                    name_lower = item.get_name().lower()
+                    skip_patterns = ['cover', 'copyright', 'titlepage', 'halftitle', 
+                                   'nav.xhtml', 'toc.xhtml']
+                    if any(pattern in name_lower for pattern in skip_patterns):
+                        logger.debug(f"跳过非正文内容: {item.get_name()}")
+                        continue
+                    
+                    content_items.append({
+                        'item': item,
+                        'file_name': item.get_name(),
+                        'content': content,
+                        'text_length': len(text)
+                    })
+                    
+                    logger.debug(f"添加内容项: {item.get_name()} ({len(text)} 字符)")
+                    
+                except Exception as e:
+                    logger.warning(f"处理项目失败 {item.get_name()}: {e}")
+                    continue
+        
+        logger.info(f"提取了 {len(content_items)} 个内容项目")
+        return content_items
+    
+    def get_book_info(self) -> Dict[str, str]:
+        """
+        获取书籍的摘要信息。
+
+        Returns:
+            Dict[str, str]: 包含文件名、标题、作者、语言和文档数量的字典。
+        """
+        # 统计内容项
+        document_count = sum(1 for item in self.book.get_items() 
+                           if item.get_type() == ebooklib.ITEM_DOCUMENT)
+        
+        return {
+            'filename': self.epub_path.name,
+            'title': self.metadata.get('title', 'Unknown'),
+            'author': self.metadata.get('author', 'Unknown'),
+            'language': self.metadata.get('language', 'en'),
+            'document_count': document_count
+        }

archive/v0.02/src/llm_client.py

@@ -0,0 +1,156 @@
+"""
+LLM 客户端模块 (LLM Client Module) - 简化 ID 锚点匹配版
+
+该模块负责发送翻译请求，并使用简化后的 ID 作为锚点解析 LLM 的响应。
+"""
+
+import asyncio
+from openai import AsyncOpenAI
+from typing import List, Dict, Optional, Any
+from loguru import logger
+import time
+import re
+from .manifest_manager import ManifestItem
+
+
+class RateLimiter:
+    """并发与 RPM 速率限制器。"""
+    def __init__(self, requests_per_minute: int, concurrent_requests: int):
+        self.semaphore = asyncio.Semaphore(concurrent_requests)
+        self.min_interval = 60.0 / requests_per_minute if requests_per_minute > 0 else 0
+        self.last_request_time = 0
+
+    async def acquire(self):
+        await self.semaphore.acquire()
+        current_time = time.time()
+        wait_time = self.min_interval - (current_time - self.last_request_time)
+        if wait_time > 0:
+            await asyncio.sleep(wait_time)
+        self.last_request_time = time.time()
+
+    def release(self):
+        self.semaphore.release()
+
+
+class OpenRouterClient:
+    """基于简化 ID 锚点匹配逻辑的 LLM 客户端。"""
+    
+    def __init__(self, config: Dict):
+        self.config = config
+        or_config = config["openrouter"]
+        api_key = or_config.get("api_key")
+        if not api_key or api_key == "YOUR_OPENROUTER_API_KEY":
+            raise ValueError("请设置有效的 OpenRouter API Key")
+            
+        self.client = AsyncOpenAI(
+            base_url=or_config["base_url"],
+            api_key=api_key,
+            default_headers={"HTTP-Referer": "https://github.com/epub-translator", "X-Title": "EPUB Translator"}
+        )
+        self.models = or_config["models"]
+        self.rate_limiter = RateLimiter(
+            or_config["rate_limits"]["requests_per_minute"],
+            or_config["rate_limits"]["concurrent_requests"]
+        )
+
+    async def translate_chunk(self, items: List[ManifestItem], model_type: str = "production") -> Dict[str, str]:
+        """
+        翻译一个段落块。
+        """
+        if not items: return {}
+        
+        prompt = self._build_prompt(items)
+        model = self.models.get(model_type, self.models["production"])
+        
+        try:
+            raw_response = await self._make_request(prompt, model)
+            if not raw_response:
+                return {item.global_id: f"[翻译失败 - API空响应]" for item in items}
+            
+            return self._parse_with_anchors(raw_response, items)
+            
+        except Exception as e:
+            logger.error(f"翻译请求异常: {e}")
+            return {item.global_id: f"[翻译失败 - {str(e)}]" for item in items}
+
+    def _build_prompt(self, items: List[ManifestItem]) -> str:
+        lines = ["请将以下编号的英文段落翻译成中文。每段翻译前必须带上原编号，格式为 p_xxxxx。", "原文：", ""]
+        for item in items:
+            lines.append(f"{item.global_id} {item.clean_text}")
+        lines.extend(["", "要求：只返回翻译，不要解释。必须保留原编号。"])
+        return "\n".join(lines)
+
+    def _parse_with_anchors(self, response: str, items: List[ManifestItem]) -> Dict[str, str]:
+        results = {}
+        
+        for i, item in enumerate(items):
+            current_id = item.global_id
+            
+            # 使用简单的字符串拼接构造正则
+            start_pat = r"\b" + current_id + r"\b"
+            start_match = re.search(start_pat, response)
+            if not start_match:
+                continue
+            
+            start_pos = start_match.start()
+            end_pos = len(response)
+            
+            if i + 1 < len(items):
+                next_id = items[i+1].global_id
+                next_pat = r"\b" + next_id + r"\b"
+                next_match = re.search(next_pat, response[start_pos + 1:])
+                if next_match:
+                    end_pos = start_pos + 1 + next_match.start()
+            
+            segment = response[start_pos:end_pos].strip()
+            
+            # 清洗 ID
+            # 注意：这里的正则使用了更稳健的拼接方式
+            id_clean_pat = r"^(\[?" + current_id + r"\]?[:：\s]*)+"
+            cleaned = re.sub(id_clean_pat, "", segment).strip()
+            
+            if cleaned:
+                results[current_id] = cleaned
+
+        if len(results) < len(items):
+            expected_ids = {item.global_id for item in items}
+            missing_ids = expected_ids - set(results.keys())
+            logger.warning(f"锚点匹配缺失 {len(missing_ids)} 个。尝试降级解析...")
+            fallback_results = self._fallback_parse(response, items)
+            for pid, trans in fallback_results.items():
+                if pid not in results:
+                    results[pid] = trans
+
+        return results
+
+    def _fallback_parse(self, response: str, items: List[ManifestItem]) -> Dict[str, str]:
+        results = {}
+        lines = [l.strip() for l in response.split("\n") if l.strip()]
+        for line in lines:
+            for item in items:
+                if item.global_id in line:
+                    # 同样的稳健拼接
+                    fallback_clean_pat = r"^\(?" + item.global_id + r"\)?[:：\s]*"
+                    clean_line = re.sub(fallback_clean_pat, "", line).strip()
+                    if clean_line:
+                        results[item.global_id] = clean_line
+        return results
+
+    async def _make_request(self, prompt: str, model: str) -> str:
+        await self.rate_limiter.acquire()
+        try:
+            resp = await self.client.chat.completions.create(
+                model=model,
+                messages=[
+                    {"role": "system", "content": "你是一位专业的翻译。请严格按编号输出翻译。"},
+                    {"role": "user", "content": prompt}
+                ],
+                temperature=0.2,
+                max_tokens=8000
+            )
+            return resp.choices[0].message.content.strip()
+        finally:
+            self.rate_limiter.release()
+
+    async def close(self):
+        await self.client.close()

archive/v0.02/src/manifest_manager.py

@@ -0,0 +1,149 @@
+"""
+Manifest 管理器模块 (Manifest Manager Module)
+
+该模块是系统的单一真理源 (SSOT)。
+它记录了每一段文本的原始状态、清洗后的文本、哈希值以及翻译状态。
+所有对翻译流程的操作（提取、翻译、回填）都必须通过修改此 Manifest 进行。
+"""
+
+import json
+import os
+import hashlib
+from typing import List, Dict, Optional, Any
+from pathlib import Path
+from loguru import logger
+from dataclasses import dataclass, asdict, field
+
+@dataclass
+class ManifestItem:
+    """代表一个翻译单元（通常是一个段落）"""
+    global_id: str
+    source_file: str
+    original_html: str
+    clean_text: str
+    text_hash: str
+    tag: str
+    translation: Optional[str] = None
+    status: str = "pending"  # pending, translated, ignored, failed
+    error_msg: Optional[str] = None
+    metadata: Dict[str, Any] = field(default_factory=dict)
+
+    def to_dict(self):
+        return asdict(self)
+
+class ManifestManager:
+    """
+    负责 Manifest 的生命周期管理。
+    """
+    
+    def __init__(self, manifest_path: str):
+        self.manifest_path = Path(manifest_path)
+        self.data: Dict[str, Any] = {
+            "book_id": "",
+            "metadata": {},
+            "items": []
+        }
+        self._items_by_id: Dict[str, ManifestItem] = {}
+
+    def load(self) -> bool:
+        """从文件加载 Manifest。如果文件不存在则返回 False。"""
+        if self.manifest_path.exists():
+            try:
+                with open(self.manifest_path, 'r', encoding='utf-8') as f:
+                    self.data = json.load(f)
+                
+                # 重建对象映射
+                self._items_by_id = {
+                    item['global_id']: ManifestItem(**item)
+                    for item in self.data["items"]
+                }
+                logger.info(f"成功从 {self.manifest_path} 加载 Manifest, 包含 {len(self._items_by_id)} 个项目")
+                return True
+            except Exception as e:
+                logger.error(f"加载 Manifest 失败: {e}")
+                return False
+        return False
+
+    def save(self):
+        """将当前状态保存到 Manifest 文件。"""
+        # 确保目录存在
+        self.manifest_path.parent.mkdir(parents=True, exist_ok=True)
+        
+        # 同步 items 到 data 字典
+        self.data["items"] = [item.to_dict() for item in self._items_by_id.values()]
+        
+        with open(self.manifest_path, 'w', encoding='utf-8') as f:
+            json.dump(self.data, f, ensure_ascii=False, indent=2)
+        # logger.debug(f"Manifest 已保存到 {self.manifest_path}")
+
+    def init_manifest(self, book_id: str, metadata: Dict):
+        """初始化一个新的 Manifest。"""
+        self.data = {
+            "book_id": book_id,
+            "metadata": metadata,
+            "items": []
+        }
+        self._items_by_id = {}
+        self.save()
+
+    def add_item(self, source_file: str, original_html: str, clean_text: str, tag: str, metadata: Dict = None) -> ManifestItem:
+        """添加一个新的翻译项并分配 ID。"""
+        # 生成全局 ID
+        new_index = len(self._items_by_id) + 1
+        global_id = f"p_{new_index:05d}"
+        
+        # 生成内容哈希 (用于排重和缓存)
+        text_hash = hashlib.sha256(clean_text.encode('utf-8')).hexdigest()
+        
+        item = ManifestItem(
+            global_id=global_id,
+            source_file=source_file,
+            original_html=original_html,
+            clean_text=clean_text,
+            text_hash=text_hash,
+            tag=tag,
+            metadata=metadata or {}
+        )
+        
+        self._items_by_id[global_id] = item
+        return item
+
+    def get_items(self, status: str = None, file_name: str = None) -> List[ManifestItem]:
+        """按状态或文件名查询项目。"""
+        items = list(self._items_by_id.values())
+        if status:
+            items = [i for i in items if i.status == status]
+        if file_name:
+            items = [i for i in items if i.source_file == file_name]
+        
+        # 必须按 ID 顺序返回以保证分块正确
+        return sorted(items, key=lambda x: x.global_id)
+
+    def update_item(self, global_id: str, translation: str, status: str = "translated", error: str = None):
+        """更新翻译结果。"""
+        if global_id in self._items_by_id:
+            item = self._items_by_id[global_id]
+            item.translation = translation
+            item.status = status
+            item.error_msg = error
+        else:
+            logger.warning(f"尝试更新不存在的 ID: {global_id}")
+
+    @property
+    def stats(self) -> Dict:
+        """获取翻译进度统计。"""
+        total = len(self._items_by_id)
+        if total == 0: return {"progress": "0%"}
+        
+        translated = sum(1 for i in self._items_by_id.values() if i.status == "translated")
+        ignored = sum(1 for i in self._items_by_id.values() if i.status == "ignored")
+        failed = sum(1 for i in self._items_by_id.values() if i.status == "failed")
+        
+        return {
+            "total": total,
+            "translated": translated,
+            "ignored": ignored,
+            "failed": failed,
+            "pending": total - translated - ignored - failed,
+            "progress_percent": round((translated + ignored) / total * 100, 1)
+        }

archive/v0.02/src/text_processor.py

@@ -0,0 +1,161 @@
+"""
+文本处理器模块 (Text Processor Module) - Manifest 驱动版
+
+该模块专注于 HTML 文档的遍历和段落提取。
+它不再维护全局状态，而是将提取的内容注册到 ManifestManager 中。
+"""
+
+import re
+from bs4 import BeautifulSoup
+from typing import List, Dict, Any
+from loguru import logger
+from .manifest_manager import ManifestManager
+
+
+class TextProcessor:
+    """
+    负责从 HTML 中识别有效段落并进行清洗。
+    """
+    
+    def __init__(self, config: Dict):
+        """
+        Args:
+            config (Dict): 全局配置。
+        """
+        self.config = config
+        self.chunk_size = config['translation'].get('chunk_size', 5000)
+        
+    def extract_to_manifest(self, html_content: str, source_file: str, manifest: ManifestManager):
+        """
+        解析 HTML 内容，并将识别出的段落注册到 Manifest 中。
+
+        Args:
+            html_content (str): HTML 源码。
+            source_file (str): 来源文件名。
+            manifest (ManifestManager): 清单管理器实例。
+        """
+        try:
+            soup = BeautifulSoup(html_content, 'html.parser')
+            
+            # 1. 移除不需要的元素
+            for element in soup(['script', 'style', 'meta', 'link']):
+                element.decompose()
+            
+            # 2. 获取有效的文本元素 (使用静态过滤逻辑)
+            text_elements = self.get_valid_text_elements(soup)
+            
+            # 3. 注册到 Manifest
+            for element in text_elements:
+                clean_text = self.clean_element_text(element)
+                
+                # 过滤逻辑
+                if not clean_text:
+                    continue
+                
+                status = "pending"
+                # 如果是导航元素，标记为 ignored
+                if self.is_navigation_element(element):
+                    status = "ignored"
+                
+                # 注册
+                manifest.add_item(
+                    source_file=source_file,
+                    original_html=str(element),
+                    clean_text=clean_text,
+                    tag=element.name,
+                    metadata={"status": status} # 临时传递给 manifest
+                )
+                
+                # 同步更新 manifest 状态 (如果需要过滤)
+                if status == "ignored":
+                    last_id = f"p_{len(manifest._items_by_id):05d}"
+                    manifest.update_item(last_id, translation=None, status="ignored")
+
+        except Exception as e:
+            logger.error(f"从 {source_file} 提取段落失败: {e}")
+
+    @staticmethod
+    def get_valid_text_elements(soup) -> List:
+        """获取不含嵌套子块的叶子级文本容器元素。"""
+        tags = ['p', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'blockquote', 'li', 'td']
+        all_candidates = soup.find_all(tags)
+        candidate_set = set(all_candidates)
+        
+        final_elements = []
+        for element in all_candidates:
+            # 如果包含其他候选标签，说明是容器，跳过
+            if any(d in candidate_set for d in element.find_all(tags)):
+                continue
+            final_elements.append(element)
+        return final_elements
+
+    @staticmethod
+    def clean_element_text(element) -> str:
+        """清理 HTML 元素，提取纯净的待翻译文本。"""
+        element_copy = element.__copy__()
+        
+        # 移除脚注引用等
+        for tag in element_copy.find_all(['sup', 'sub']):
+            tag.decompose()
+            
+        footnote_patterns = re.compile(r'footnote|endnote|reference|note|super|sub', re.I)
+        for tag in element_copy.find_all(['a', 'span', 'div'], class_=footnote_patterns):
+            tag.decompose()
+
+        # 移除仅包含数字的 span
+        for tag in element_copy.find_all('span'):
+            if re.match(r'^(\[\d+\]|\(\d+\)|\d+)$', tag.get_text().strip()):
+                tag.decompose()
+        
+        text = element_copy.get_text().strip()
+        # 正则清理残留引用标识 (如 sentence.2)
+        text = re.sub(r'(\.|。|，|,)\s*(\[\d+\]|\d+)(?=\s|$)', r'\1', text)
+        text = re.sub(r'\s+', ' ', text)
+        return text
+
+    @staticmethod
+    def is_navigation_element(element) -> bool:
+        """判断是否是无翻译价值的导航、页码元素。"""
+        classes = element.get('class', [])
+        nav_classes = ['nav', 'navigation', 'toc', 'menu', 'header', 'footer', 'page-number']
+        class_str = ' '.join(classes).lower() if isinstance(classes, list) else str(classes).lower()
+        
+        if any(nc in class_str for nc in nav_classes):
+            return True
+            
+        # 检查父级
+        parent = element.parent
+        if parent:
+            p_classes = parent.get('class', [])
+            p_class_str = ' '.join(p_classes).lower() if isinstance(p_classes, list) else str(p_classes).lower()
+            if any(nc in p_class_str for nc in nav_classes):
+                return True
+        return False
+
+    def create_chunks_from_manifest(self, manifest: ManifestManager) -> List[List[Any]]:
+        """
+        从 Manifest 中筛选待翻译项目并分块。
+        """
+        pending_items = manifest.get_items(status="pending")
+        if not pending_items:
+            return []
+            
+        chunks = []
+        current_chunk = []
+        current_size = 0
+        
+        for item in pending_items:
+            text_len = len(item.clean_text)
+            if current_size + text_len > self.chunk_size and current_chunk:
+                chunks.append(current_chunk)
+                current_chunk = []
+                current_size = 0
+            
+            current_chunk.append(item)
+            current_size += text_len
+            
+        if current_chunk:
+            chunks.append(current_chunk)
+            
+        logger.info(f"分块完成: 共有 {len(pending_items)} 个待翻译项，分为 {len(chunks)} 个块")
+        return chunks

archive/v0.02/src/translator.py

@@ -0,0 +1,142 @@
+"""
+EPUB 翻译器核心模块 (EPUB Translator Core Module) - Manifest 驱动版
+
+该模块协调整体流程：
+1. 使用 ManifestManager 管理状态。
+2. 调用 EPUBParser 提取。
+3. 调用 TextProcessor 清理。
+4. 调用 LLMClient 并发翻译并更新 Manifest。
+5. 调用 BilingualEPUBBuilder 构建。
+"""
+
+import asyncio
+import os
+from typing import List, Dict, Any
+from pathlib import Path
+from loguru import logger
+from rich.console import Console
+from rich.progress import Progress, SpinnerColumn, TextColumn, BarColumn, TimeElapsedColumn
+
+from .epub_parser import EPUBParser
+from .llm_client import OpenRouterClient
+from .text_processor import TextProcessor
+from .bilingual_builder import BilingualEPUBBuilder
+from .manifest_manager import ManifestManager
+
+
+class EPUBTranslator:
+    """
+    基于 Manifest 的翻译器。
+    """
+    
+    def __init__(self, config: Dict, use_cache: bool = True):
+        self.config = config
+        self.console = Console()
+        self.use_cache = use_cache
+        
+        # 组件
+        self.parser = None
+        self.llm_client = OpenRouterClient(config)
+        self.text_processor = TextProcessor(config)
+        
+        # Manifest 管理 (存放于 cache/manifests/ 目录下)
+        self.manifest_dir = Path("cache/manifests")
+        self.manifest_dir.mkdir(parents=True, exist_ok=True)
+
+    async def translate_epub(self, epub_path: str, test_mode: bool = False, output_dir: str = None) -> str:
+        """主翻译流程。"""
+        epub_path = Path(epub_path)
+        # 1. 初始化解析器
+        self.parser = EPUBParser(str(epub_path))
+        
+        # 2. 准备 Manifest
+        manifest_path = self.manifest_dir / f"{epub_path.stem}_manifest.json"
+        manifest = ManifestManager(str(manifest_path))
+        
+        # 检查是否能恢复
+        if not manifest.load() or not self.use_cache:
+            self.console.print("[yellow]初始化翻译清单...[/yellow]")
+            manifest.init_manifest(book_id=epub_path.name, metadata=self.parser.get_book_info())
+            
+            # 提取内容
+            content_items = self.parser.extract_all_content_items()
+            for item in content_items:
+                self.text_processor.extract_to_manifest(item['content'], item['file_name'], manifest)
+            manifest.save()
+        
+        stats = manifest.stats
+        self.console.print(f"[green]已加载清单: {stats['total']} 个段落, 已完成 {stats['progress_percent']}%[/green]")
+
+        if test_mode:
+            # 简化逻辑：测试模式只翻译前几个 pending 项目
+            pending = manifest.get_items(status="pending")[:5]
+            if pending:
+                results = await self.llm_client.translate_chunk(pending)
+                for pid, trans in results.items():
+                    self.console.print(f"\n[cyan]{pid}[/cyan]: {trans}")
+            return "test_mode_done"
+
+        # 3. 分块并并发翻译
+        chunks = self.text_processor.create_chunks_from_manifest(manifest)
+        if chunks:
+            await self._translate_concurrently(chunks, manifest)
+        
+        # 4. 构建双语 EPUB
+        self.console.print("\n[yellow]正在构建双语 EPUB...[/yellow]")
+        output_path = output_dir or self.config['output']['output_dir']
+        builder = BilingualEPUBBuilder(self.parser.book, self.config)
+        
+        # 注意：Builder 现在直接从 Manifest 中读取翻译映射
+        translation_map = {item.global_id: item.translation for item in manifest.get_items() if item.translation}
+        paragraph_map = {item.global_id: {
+            "file_name": item.source_file,
+            "text": item.clean_text,
+            "html_element": item.original_html
+        } for item in manifest.get_items()}
+        
+        result_file = builder.create_bilingual_epub_with_mapping(
+            translation_map, 
+            paragraph_map,
+            output_path
+        )
+        
+        self.console.print(f"[green]✅ 翻译完成！输出文件: {result_file}[/green]")
+        return result_file
+
+    async def _translate_concurrently(self, chunks: List[List[Any]], manifest: ManifestManager):
+        """执行并发翻译任务。"""
+        total_chunks = len(chunks)
+        
+        with Progress(
+            SpinnerColumn(),
+            TextColumn("[progress.description]{task.description}"),
+            BarColumn(),
+            TextColumn("[progress.percentage]{task.percentage:>3.0f}%"),
+            TimeElapsedColumn(),
+            console=self.console
+        ) as progress:
+            
+            task_id = progress.add_task(f"[cyan]并行翻译...", total=total_chunks)
+            
+            # 使用可控并发
+            semaphore = self.llm_client.rate_limiter.semaphore
+            
+            async def worker(chunk, idx):
+                async with semaphore:
+                    try:
+                        results = await self.llm_client.translate_chunk(chunk)
+                        # 更新 manifest
+                        for item in chunk:
+                            if item.global_id in results:
+                                manifest.update_item(item.global_id, results[item.global_id])
+                            else:
+                                manifest.update_item(item.global_id, None, status="failed", error="Missing in response")
+                        # 每翻译完一个 chunk 就保存一次，确保断点续传
+                        manifest.save()
+                    except Exception as e:
+                        logger.error(f"Chunk {idx} 翻译失败: {e}")
+                    finally:
+                        progress.update(task_id, advance=1)
+
+            tasks = [worker(chunk, i) for i, chunk in enumerate(chunks)]
+            await asyncio.gather(*tasks)

archive/v0.02/src/utils.py

@@ -0,0 +1,180 @@
+"""
+工具函数模块
+提供配置加载、日志设置等通用功能
+"""
+
+import json
+import os
+from pathlib import Path
+from typing import Dict, Any
+from loguru import logger
+import sys
+
+
+def load_config(config_path: str = "config/config.json") -> Dict[str, Any]:
+    """
+    加载配置文件
+    
+    Args:
+        config_path: 配置文件路径
+        
+    Returns:
+        配置字典
+    """
+    try:
+        with open(config_path, 'r', encoding='utf-8') as f:
+            config = json.load(f)
+        
+        # 从环境变量获取 API Key
+        if 'OPENROUTER_API_KEY' in os.environ:
+            config['openrouter']['api_key'] = os.environ['OPENROUTER_API_KEY']
+        
+        return config
+    except FileNotFoundError:
+        raise FileNotFoundError(f"配置文件未找到: {config_path}")
+    except json.JSONDecodeError as e:
+        raise ValueError(f"配置文件格式错误: {e}")
+
+
+def load_prompts(prompts_path: str = "config/prompts.json") -> Dict[str, str]:
+    """
+    加载提示词模板
+    
+    Args:
+        prompts_path: 提示词文件路径
+        
+    Returns:
+        提示词字典
+    """
+    try:
+        with open(prompts_path, 'r', encoding='utf-8') as f:
+            return json.load(f)
+    except FileNotFoundError:
+        raise FileNotFoundError(f"提示词文件未找到: {prompts_path}")
+
+
+def setup_logging(config: Dict[str, Any]) -> None:
+    """
+    设置日志配置
+    
+    Args:
+        config: 配置字典
+    """
+    log_config = config.get('logging', {})
+    
+    # 移除默认处理器
+    logger.remove()
+    
+    # 添加控制台输出
+    logger.add(
+        sys.stdout,
+        level=log_config.get('level', 'INFO'),
+        format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | <level>{level: <8}</level> | <cyan>{name}</cyan>:<cyan>{function}</cyan>:<cyan>{line}</cyan> - <level>{message}</level>"
+    )
+    
+    # 添加文件输出
+    if 'file' in log_config:
+        log_file = log_config['file']
+        # 确保日志目录存在
+        Path(log_file).parent.mkdir(parents=True, exist_ok=True)
+        
+        logger.add(
+            log_file,
+            level=log_config.get('level', 'INFO'),
+            rotation=log_config.get('rotation', '10 MB'),
+            retention=log_config.get('retention', '7 days'),
+            encoding='utf-8',
+            format="{time:YYYY-MM-DD HH:mm:ss} | {level: <8} | {name}:{function}:{line} - {message}"
+        )
+
+
+def ensure_output_dir(output_dir: str) -> Path:
+    """
+    确保输出目录存在
+    
+    Args:
+        output_dir: 输出目录路径
+        
+    Returns:
+        输出目录的 Path 对象
+    """
+    output_path = Path(output_dir)
+    output_path.mkdir(parents=True, exist_ok=True)
+    return output_path
+
+
+def sanitize_filename(filename: str) -> str:
+    """
+    清理文件名，移除非法字符
+    
+    Args:
+        filename: 原始文件名
+        
+    Returns:
+        清理后的文件名
+    """
+    import re
+    # 移除或替换非法字符
+    filename = re.sub(r'[<>:"/\\|?*]', '_', filename)
+    # 移除多余的空格和点
+    filename = re.sub(r'\s+', ' ', filename).strip('. ')
+    return filename
+
+
+def format_file_size(size_bytes: int) -> str:
+    """
+    格式化文件大小显示
+    
+    Args:
+        size_bytes: 字节数
+        
+    Returns:
+        格式化的大小字符串
+    """
+    if size_bytes == 0:
+        return "0B"
+    
+    size_names = ["B", "KB", "MB", "GB"]
+    import math
+    i = int(math.floor(math.log(size_bytes, 1024)))
+    p = math.pow(1024, i)
+    s = round(size_bytes / p, 2)
+    return f"{s} {size_names[i]}"
+
+
+def estimate_tokens(text: str) -> int:
+    """
+    估算文本的 token 数量
+    
+    Args:
+        text: 输入文本
+        
+    Returns:
+        估算的 token 数量
+    """
+    # 简单估算：英文约 4 字符/token，中文约 1.5 字符/token
+    import re
+    
+    # 分离中英文
+    chinese_chars = len(re.findall(r'[\u4e00-\u9fff]', text))
+    other_chars = len(text) - chinese_chars
+    
+    # 估算 tokens
+    estimated_tokens = chinese_chars / 1.5 + other_chars / 4
+    return int(estimated_tokens)
+
+
+def truncate_text(text: str, max_length: int = 100) -> str:
+    """
+    截断文本用于显示
+    
+    Args:
+        text: 原始文本
+        max_length: 最大长度
+        
+    Returns:
+        截断后的文本
+    """
+    if len(text) <= max_length:
+        return text
+    return text[:max_length-3] + "..."