Initial commit

archive/v0.08/src/__init__.py

@@ -0,0 +1,32 @@
+"""
+EPUB 双语翻译程序
+主要功能模块的初始化文件
+"""
+
+__version__ = "0.08"
+__author__ = "Kaitan"
+
+from .epub_parser import EPUBParser
+from .translator import EPUBTranslator
+from .llm_client import LLMClient as OpenRouterClient # Keep alias for compatibility
+from .llm_client import LLMClient
+from .text_processor import TextProcessor
+from .bilingual_builder import BilingualEPUBBuilder
+from .chinese_builder import ChineseEPUBBuilder
+from .format_extractor import FormatExtractor
+from .format_restorer import FormatRestorer
+from .utils import load_config, setup_logging
+
+__all__ = [
+    "EPUBParser",
+    "EPUBTranslator", 
+    "LLMClient",
+    "OpenRouterClient",
+    "TextProcessor",
+    "BilingualEPUBBuilder",
+    "ChineseEPUBBuilder",
+    "FormatExtractor",
+    "FormatRestorer",
+    "load_config",
+    "setup_logging"
+]

archive/v0.08/src/bilingual_builder.py

@@ -0,0 +1,180 @@
+"""
+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._sanitize_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 = {}
+
+            # 特殊处理：封面图片
+            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)
+                    processed_item_ids.add(cover_item.id)
+                    item_map[cover_item.id] = cover_item
+
+            # 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 _sanitize_toc(self, toc):
+        """确保 TOC 中的所有节点都有 ID，修复 ebooklib 读取后写入的兼容性问题"""
+        for item in toc:
+            if isinstance(item, (epub.Link, epub.Section)):
+                if not getattr(item, 'uid', None):
+                    item.uid = f"navPoint-{uuid.uuid4().hex[:8]}"
+            elif isinstance(item, tuple) and len(item) == 2:
+                # 处理 (Section, [children]) 结构
+                section, children = item
+                if isinstance(section, (epub.Link, epub.Section)):
+                    if not getattr(section, 'uid', None):
+                        section.uid = f"navPoint-{uuid.uuid4().hex[:8]}"
+                self._sanitize_toc(children)
+        return toc
+
+    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 Exception as e:
+            logger.warning(f"插入翻译失败: {e}")
+
+    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/v0.08/src/book_profiler.py

@@ -0,0 +1,84 @@
+
+'''Book Profiler Module
+
+Features:
+1. Automatically extract book samples to generate Book Profile (Genre, Style, Glossary).
+'''
+
+import json
+import random
+from pathlib import Path
+from typing import Dict, List
+from loguru import logger
+from .manifest_manager import ManifestManager
+from .llm_client import LLMClient
+
+class BookProfiler:
+    def __init__(self, config: Dict, llm_client: LLMClient):
+        self.config = config
+        self.llm_client = llm_client
+
+    def extract_sample_text(self, manifest: ManifestManager, char_limit: int = 3000) -> str:
+        """Extract sample text."""
+        items = manifest.get_items()
+        if not items: return ""
+        
+        intro_text = []
+        for item in items[:50]:
+            if len(item.clean_text) > 50:
+                intro_text.append(item.clean_text)
+        
+        body_text = []
+        body_items = [i for i in items[50:] if len(i.clean_text) > 80]
+        if body_items:
+            samples = random.sample(body_items, min(5, len(body_items)))
+            body_text = [i.clean_text for i in samples]
+            
+        full_text = "\n\n".join(intro_text[:5] + body_text)
+        return full_text[:char_limit]
+
+    async def analyze_book(self, manifest: ManifestManager) -> Dict:
+        """Generate Book Profile."""
+        existing_profile = manifest.data.get('metadata', {}).get('profile')
+        if existing_profile:
+            logger.info("Loaded existing Book Profile")
+            return existing_profile
+
+        sample = self.extract_sample_text(manifest)
+        if not sample: return {}
+        
+        logger.info("Generating Book Profile...")
+        
+        system_prompt = "You are a senior publishing editor. Analyze the text and output JSON."
+        user_prompt = f"""
+Please analyze the following book excerpt.
+Output JSON format:
+{{
+    "genre": "Genre",
+    "style": "Style description",
+    "audience": "Target Audience",
+    "glossary": {{ "Term": "Chinese Translation" }},
+    "translation_instruction": "Specific instruction for translator"
+}}
+
+Excerpt:
+{sample}
+"""
+        try:
+            response = await self.llm_client.raw_chat_completion(system_prompt, user_prompt)
+            json_str = response.strip()
+            if "```json" in json_str:
+                json_str = json_str.split("```json")[1].split("```")[0].strip()
+            elif "```" in json_str:
+                json_str = json_str.split("```")[1].split("```")[0].strip()
+            
+            profile = json.loads(json_str)
+            
+            if 'metadata' not in manifest.data:
+                manifest.data['metadata'] = {}
+            manifest.data['metadata']['profile'] = profile
+            manifest.save()
+            return profile
+        except Exception as e:
+            logger.error(f"Profile generation failed: {e}")
+            return {}

archive/v0.08/src/cache.py

@@ -0,0 +1,226 @@
+"""
+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"""
+        # 使用 hash 前缀分目录，避免单目录文件过多
+        subdir = cache_key[:2]
+        cache_subdir = self.translations_dir / subdir
+        cache_subdir.mkdir(parents=True, exist_ok=True)
+        return cache_subdir / 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
+        
+        # 只要有翻译结果就认为有效，不要求数量完全匹配
+        translations = cache_data.get('translations', {})
+        if not translations:
+            logger.debug("缓存无翻译结果")
+            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/v0.08/src/chinese_builder.py

@@ -0,0 +1,180 @@
+"""
+纯中文 EPUB 构建器模块
+
+负责：
+1. 复制原始 EPUB 结构
+2. 使用译文替换原文
+3. 调用 FormatRestorer 将译文占位符还原为 HTML 标签
+"""
+
+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 ChineseEPUBBuilder:
+    """纯中文 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_chinese_epub_with_mapping(self, 
+                                        items: List, # List[ManifestItem]
+                                        output_path: str) -> str:
+        """
+        创建纯中文 EPUB。
+        """
+        try:
+            new_book = epub.EpubBook()
+            self._copy_metadata(new_book)
+            new_book.toc = self._sanitize_toc(self.original_book.toc)
+            
+            # 准备每个文件的有序项目列表
+            file_items = {}
+            for item in sorted(items, key=lambda x: x.global_id):
+                fname = item.source_file
+                if fname not in file_items:
+                    file_items[fname] = []
+                file_items[fname].append(item)
+            
+            processed_item_ids = set()
+            item_map = {}
+
+            # 特殊处理：封面图片
+            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)
+                    processed_item_ids.add(cover_item.id)
+                    item_map[cover_item.id] = cover_item
+
+            # 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_items:
+                        new_item = self._create_chinese_document(
+                            item, file_items[file_name]
+                        )
+                        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"创建纯中文 EPUB 失败: {e}", exc_info=True)
+            raise
+
+    def _sanitize_toc(self, toc):
+        """确保 TOC 中的所有节点都有 ID"""
+        for item in toc:
+            if isinstance(item, (epub.Link, epub.Section)):
+                if not getattr(item, 'uid', None):
+                    item.uid = f"navPoint-{uuid.uuid4().hex[:8]}"
+            elif isinstance(item, tuple) and len(item) == 2:
+                section, children = item
+                if isinstance(section, (epub.Link, epub.Section)):
+                    if not getattr(section, 'uid', None):
+                        section.uid = f"navPoint-{uuid.uuid4().hex[:8]}"
+                self._sanitize_toc(children)
+        return toc
+
+    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"chinese-{uuid.uuid4().hex[:12]}")
+        except Exception as e:
+            logger.error(f"元数据复制出错: {e}")
+
+    def _create_chinese_document(self, original_item, manifest_items: list):
+        try:
+            from .text_processor import TextProcessor
+            soup = BeautifulSoup(original_item.get_content().decode('utf-8'), 'html.parser')
+            
+            # 获取文本元素
+            text_elements = TextProcessor.get_valid_text_elements(soup)
+            
+            current_idx = 0
+            for element in text_elements:
+                if not TextProcessor.clean_element_text(element): continue
+                
+                if current_idx < len(manifest_items):
+                    m_item = manifest_items[current_idx]
+                    
+                    # 只有当非导航元素时才尝试替换内容
+                    if not TextProcessor.is_navigation_element(element):
+                        # 优先使用带格式的翻译，降级到纯文本翻译
+                        if m_item.translation_with_original_html:
+                            self._replace_content(element, m_item.translation_with_original_html)
+                        elif m_item.translation:
+                            # 降级：使用纯文本翻译（无格式）
+                            self._replace_content(element, m_item.translation)
+                    
+                    current_idx += 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"创建中文文档失败 {original_item.get_name()}: {e}")
+            return original_item
+
+    def _replace_content(self, element, translated_html: str):
+        """用译文替换元素的 inner_html"""
+        try:
+            # 将译文 HTML 字符串解析为 BeautifulSoup 对象
+            new_soup = BeautifulSoup(translated_html, 'html.parser')
+            # 清空原元素并填入新内容
+            element.clear()
+            # 重要：必须先转换为 list，否则 append 会修改 contents 导致跳过元素
+            for content in list(new_soup.contents):
+                element.append(content)
+        except Exception as e:
+            logger.error(f"替换内容失败: {e}")
+
+
+    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 "chinese_book"
+        Path(output_path).mkdir(parents=True, exist_ok=True)
+        return str(Path(output_path) / f"{clean_title}_chinese.epub")

archive/v0.08/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/v0.08/src/format_extractor.py

@@ -0,0 +1,305 @@
+"""
+格式提取模块 (优化版 v3)
+
+核心优化：
+1. 前缀/后缀标签分离：文本前后的标签不发送给 LLM，直接回填
+2. 公式检测：将数学变量/公式作为整体占位符
+3. 简化占位符：φ1φ 格式，每个段落独立编号
+"""
+
+import re
+from bs4 import BeautifulSoup, Tag, NavigableString
+from typing import Tuple, Dict, Any, List, Optional
+
+
+class HeadingDetector:
+    """标题与段落类型检测器"""
+    
+    CHAPTER_PATTERNS = [
+        r'^(chapter|chap\.?|part)\s+([0-9]+|[ivxlc]+|[a-z])',
+        r'^(第\s*[0-9一二三四五六七八九十百]+\s*[章节部篇])',
+        r'^(\d+|[IVXLC]+|[A-Z])\.$'
+    ]
+    
+    EPIGRAPH_CLASSES = {
+        'epigraph', 'quote', 'blockquote', 'motto', 
+        'dedication', 'verse', 'poetry', 'poem'
+    }
+
+    def detect(self, element: Tag, text: str) -> str:
+        if self._is_epigraph(element):
+            return "epigraph"
+        tag_name = element.name.lower()
+        if tag_name in ['h1', 'h2']:
+            return "chapter" if self._matches_chapter_pattern(text) else "section"
+        if tag_name == 'h3':
+            return "section"
+        if tag_name in ['h4', 'h5', 'h6']:
+            return "subsection"
+        if self._is_pseudo_heading(element, text):
+            return "subsection"
+        return "body"
+
+    def _is_epigraph(self, element: Tag) -> bool:
+        if element.name == 'blockquote':
+            return True
+        current = element
+        for _ in range(3):
+            if not current: break
+            classes = current.get('class', [])
+            if isinstance(classes, list):
+                classes = ' '.join(classes)
+            if any(k in classes.lower() for k in self.EPIGRAPH_CLASSES):
+                return True
+            current = current.parent
+        return False
+
+    def _matches_chapter_pattern(self, text: str) -> bool:
+        text = text.strip().lower()
+        for pattern in self.CHAPTER_PATTERNS:
+            if re.match(pattern, text, re.IGNORECASE):
+                return True
+        return False
+
+    def _is_pseudo_heading(self, element: Tag, text: str) -> bool:
+        if element.name != 'p':
+            return False
+        text = text.strip()
+        if not text or len(text) > 80:
+            return False
+        children = list(element.children)
+        if len(children) == 1 and isinstance(children[0], Tag):
+            if children[0].name in ['strong', 'b']:
+                return True
+        return False
+
+
+class FormatExtractor:
+    """
+    HTML 格式提取器 (优化版 v3)
+    
+    核心改进：
+    1. 前缀/后缀标签分离 - 不发送给 LLM，自动回填
+    2. 公式元素整体替换
+    3. 简化占位符格式 φ1φ, φ2φ
+    """
+
+    FORMULA_CHARS = re.compile(
+        r'^[\d\s\+\-\×\÷\=\(\)\[\]\{\}\<\>\^\*\/\.\,\;\:\'\"\`\~\@\#\$\%\&\|\\'
+        r'αβγδεζηθικλμνξοπρστυφχψωΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩ'
+        r'a-zA-Z]+$'
+    )
+
+    def __init__(self):
+        self.detector = HeadingDetector()
+
+    def extract(self, element_html: str) -> Tuple[str, str, Dict[str, str], str]:
+        """
+        提取格式信息
+        
+        Returns:
+            clean_text: 纯文本
+            text_with_placeholders: 只包含内嵌占位符的文本（不含前缀/后缀标签）
+            placeholder_map: 占位符映射，包含特殊键 "_prefix" 和 "_suffix"
+            paragraph_type: 段落类型
+        """
+        soup = BeautifulSoup(element_html, 'html.parser')
+        root = list(soup.children)[0] if list(soup.children) else soup
+        
+        # 获取纯文本和段落类型
+        clean_text = root.get_text().strip()
+        clean_text = re.sub(r'\s+', ' ', clean_text)
+        p_type = self.detector.detect(root, clean_text) if isinstance(root, Tag) else "body"
+        
+        # 获取内部 HTML
+        inner_html = root.decode_contents() if isinstance(root, Tag) else str(root)
+        
+        # 智能提取（分离前缀/后缀）
+        text_with_ph, local_map = self._smart_extract_v3(inner_html)
+        
+        return clean_text, text_with_ph, local_map, p_type
+
+    def _smart_extract_v3(self, inner_html: str) -> Tuple[str, Dict[str, str]]:
+        """
+        智能提取 v3：分离前缀/后缀 + 合并内嵌公式块
+        
+        核心逻辑：
+        1. 分离前缀（第一个可翻译文本之前）和后缀（最后一个可翻译文本之后）
+        2. 中间部分：检测"公式块"（连续标签+不可翻译文本），合并为单个占位符
+        3. 只有真正需要翻译的格式标签（如斜体包裹的长文本）才拆分
+        """
+        # 使用正则分割标签和文本
+        parts = re.split(r'(<[^>]+>)', inner_html)
+        parts = [p for p in parts if p]
+        
+        if not parts:
+            return "", {"_prefix": "", "_suffix": ""}
+        
+        # 识别每个部分的类型
+        part_types = []  # 'tag', 'translatable', 'formula', 'whitespace'
+        for part in parts:
+            if part.startswith('<'):
+                part_types.append('tag')
+            elif not part.strip():
+                part_types.append('whitespace')
+            elif self._is_translatable_text(part):
+                part_types.append('translatable')
+            else:
+                part_types.append('formula')
+        
+        # 找到第一个和最后一个可翻译文本的索引
+        first_trans_idx = None
+        last_trans_idx = None
+        for i, t in enumerate(part_types):
+            if t == 'translatable':
+                if first_trans_idx is None:
+                    first_trans_idx = i
+                last_trans_idx = i
+        
+        if first_trans_idx is None:
+            # 没有可翻译文本，全部作为前缀
+            return "", {"_prefix": inner_html, "_suffix": ""}
+        
+        # 分割
+        prefix_parts = parts[:first_trans_idx]
+        middle_parts = parts[first_trans_idx:last_trans_idx + 1]
+        middle_types = part_types[first_trans_idx:last_trans_idx + 1]
+        suffix_parts = parts[last_trans_idx + 1:]
+        
+        # 构建映射
+        local_map = {}
+        
+        # 前缀
+        prefix_html = "".join(prefix_parts)
+        if prefix_html:
+            local_map["_prefix"] = prefix_html
+        
+        # 后缀
+        suffix_html = "".join(suffix_parts)
+        if suffix_html:
+            local_map["_suffix"] = suffix_html
+        
+        # 中间部分处理：使用配对占位符格式
+        # 
+        # 策略：
+        # 1. 连续的 (tag|formula|whitespace) 不包含可翻译文本 → 合并为单个占位符 φ1φ
+        # 2. 开始标签后接可翻译文本 → 配对格式 φ2φ文本φ/2φ
+        #
+        placeholder_counter = 1
+        result_parts = []
+        tag_stack = []  # 追踪开放标签 [(id, opening_tag), ...]
+        
+        i = 0
+        while i < len(middle_parts):
+            part = middle_parts[i]
+            ptype = middle_types[i]
+            
+            if ptype == 'translatable':
+                # 可翻译文本，直接保留
+                result_parts.append(part)
+                i += 1
+                
+            elif ptype == 'tag':
+                # 检查是开始标签还是结束标签
+                is_closing = part.startswith('</')
+                
+                if is_closing:
+                    # 结束标签
+                    if tag_stack:
+                        # 匹配最近的开放标签
+                        open_id, open_tag = tag_stack.pop()
+                        local_map[f"/{open_id}"] = part
+                        result_parts.append(f"φ/{open_id}φ")
+                    else:
+                        # 没有匹配的开放标签，作为单独占位符
+                        pid = str(placeholder_counter)
+                        placeholder_counter += 1
+                        local_map[pid] = part
+                        result_parts.append(f"φ{pid}φ")
+                    i += 1
+                else:
+                    # 开始标签，检查后面是否有可翻译文本
+                    has_translatable_after = False
+                    for j in range(i + 1, len(middle_parts)):
+                        if middle_types[j] == 'translatable':
+                            has_translatable_after = True
+                            break
+                        elif middle_types[j] == 'tag' and middle_parts[j].startswith('</'):
+                            # 遇到结束标签但还没遇到可翻译文本
+                            break
+                    
+                    if has_translatable_after:
+                        # 开始配对模式
+                        pid = str(placeholder_counter)
+                        placeholder_counter += 1
+                        local_map[pid] = part
+                        result_parts.append(f"φ{pid}φ")
+                        tag_stack.append((pid, part))
+                        i += 1
+                    else:
+                        # 后面没有可翻译文本，合并为公式块
+                        block_parts = []
+                        while i < len(middle_parts) and middle_types[i] != 'translatable':
+                            block_parts.append(middle_parts[i])
+                            i += 1
+                        if block_parts:
+                            block_html = "".join(block_parts)
+                            pid = str(placeholder_counter)
+                            placeholder_counter += 1
+                            local_map[pid] = block_html
+                            result_parts.append(f"φ{pid}φ")
+                            
+            elif ptype in ('formula', 'whitespace'):
+                # 公式或空白，检查是否是连续块的开始
+                block_parts = []
+                while i < len(middle_parts) and middle_types[i] in ('formula', 'whitespace'):
+                    block_parts.append(middle_parts[i])
+                    i += 1
+                if block_parts:
+                    block_html = "".join(block_parts)
+                    pid = str(placeholder_counter)
+                    placeholder_counter += 1
+                    local_map[pid] = block_html
+                    result_parts.append(f"φ{pid}φ")
+            else:
+                i += 1
+        
+        text_with_ph = "".join(result_parts)
+        text_with_ph = re.sub(r'\s+', ' ', text_with_ph).strip()
+        
+        return text_with_ph, local_map
+
+
+
+    def _is_translatable_text(self, text: str) -> bool:
+        """判断文本是否需要翻译（包含可翻译的单词）"""
+        text = text.strip()
+        if not text:
+            return False
+        # 如果包含 4 个及以上连续字母，视为可翻译
+        if re.search(r'[a-zA-Z]{4,}', text):
+            return True
+        return False
+
+    def _is_formula_element(self, element: Tag, text_content: str) -> bool:
+        """判断元素是否为公式元素（应整体保留不翻译）"""
+        if not text_content:
+            return True
+        if len(text_content) <= 3:
+            return True
+        if re.search(r'[a-zA-Z]{4,}', text_content):
+            return False
+        return bool(self.FORMULA_CHARS.match(text_content))
+
+    def _get_opening_tag(self, element: Tag) -> str:
+        """获取元素的开始标签（含属性）"""
+        attrs_str = ""
+        for key, value in element.attrs.items():
+            if isinstance(value, list):
+                value = " ".join(value)
+            attrs_str += f' {key}="{value}"'
+        return f"<{element.name}{attrs_str}>"
+
+    def reset(self):
+        """兼容旧接口"""
+        pass

archive/v0.08/src/format_restorer.py

@@ -0,0 +1,89 @@
+"""
+格式恢复模块 (优化版 v4)
+
+负责：
+1. 解析译文中的配对占位符 (φ1φ...φ/1φ)
+2. 还原前缀和后缀标签（_prefix, _suffix）
+3. 从映射表中查找对应的 HTML 片段并替换
+"""
+
+import re
+from typing import Dict, Tuple, List, Optional
+from loguru import logger
+
+
+class FormatRestorer:
+    """
+    格式恢复器 (优化版 v4)
+    
+    支持：
+    - 配对占位符 φ1φ...φ/1φ
+    - 前缀/后缀自动回填 (_prefix, _suffix)
+    """
+    
+    # 占位符正则: φ1φ, φ/1φ, φ12φ, φ/12φ (支持配对格式)
+    PLACEHOLDER_REGEX = re.compile(r'φ(/?\d+)φ')
+
+    def restore(self, text_with_placeholders: str, placeholder_map: Dict[str, str]) -> Tuple[str, bool]:
+        """
+        将带占位符的文本还原为 HTML
+        
+        自动处理 _prefix 和 _suffix 键，以及配对占位符 φ1φ...φ/1φ
+        
+        Returns:
+            (html_string, success): 还原后的 HTML 和是否完全成功的标志
+        """
+        if not placeholder_map:
+            return text_with_placeholders or "", True
+            
+        if not text_with_placeholders:
+            # 没有文本，只有前缀/后缀（如空元素）
+            prefix = placeholder_map.get("_prefix", "")
+            suffix = placeholder_map.get("_suffix", "")
+            return prefix + suffix, True
+
+        # 提取前缀和后缀
+        prefix = placeholder_map.get("_prefix", "")
+        suffix = placeholder_map.get("_suffix", "")
+        
+        # 创建只包含占位符键的映射（排除 _prefix, _suffix）
+        inner_map = {k: v for k, v in placeholder_map.items() if not k.startswith("_")}
+        
+        # 校验占位符
+        found_ids = set(self.PLACEHOLDER_REGEX.findall(text_with_placeholders))
+        expected_ids = set(inner_map.keys())
+        
+        success = True
+        missing_ids = expected_ids - found_ids
+        if missing_ids:
+            logger.warning(f"格式还原警告: 丢失占位符 {missing_ids}")
+            success = False
+            
+        unknown_ids = found_ids - expected_ids
+        if unknown_ids:
+            logger.warning(f"格式还原警告: 发现未知占位符 {unknown_ids}")
+            success = False  # 未知占位符也视为问题
+
+        # 替换占位符
+        def replace_match(match):
+            pid = match.group(1)  # 可能是 "1" 或 "/1"
+            if pid in inner_map:
+                return inner_map[pid]
+            else:
+                return ""  # 删除未知占位符
+
+        try:
+            # 还原占位符
+            restored_inner = self.PLACEHOLDER_REGEX.sub(replace_match, text_with_placeholders)
+            
+            # 添加前缀和后缀
+            restored_html = prefix + restored_inner + suffix
+            
+            return restored_html, success
+        except Exception as e:
+            logger.error(f"格式还原失败: {e}")
+            return prefix + self._strip_placeholders(text_with_placeholders) + suffix, False
+
+    def _strip_placeholders(self, text: str) -> str:
+        """移除所有 φ...φ 占位符"""
+        return self.PLACEHOLDER_REGEX.sub("", text)

archive/v0.08/src/llm_client.py

@@ -0,0 +1,241 @@
+"""
+LLM Client Module - Generic OpenAI Compatible
+
+Features:
+1. Fully configurable via config.json (base_url, headers).
+2. Mode-aware prompt building (bilingual vs chinese).
+3. Format repair capability for chinese mode.
+"""
+
+import asyncio
+import json
+import re
+from openai import AsyncOpenAI
+from typing import List, Dict, Optional, Any
+from loguru import logger
+import time
+from tenacity import retry, stop_after_attempt, wait_exponential
+from .manifest_manager import ManifestItem
+
+
+class RateLimiter:
+    """Rate limiter for concurrency and RPM."""
+    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
+        self._lock = asyncio.Lock()
+
+    async def acquire(self):
+        await self.semaphore.acquire()
+        async with self._lock:
+            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 LLMClient:
+    """Generic OpenAI-compatible API Client."""
+    
+    def __init__(self, config: Dict):
+        self.config = config
+        llm_config = config["llm"]
+        
+        api_key = llm_config.get("api_key")
+        base_url = llm_config.get("base_url")
+        extra_headers = llm_config.get("extra_headers", {})
+        
+        if not api_key:
+            raise ValueError("API Key is missing in config")
+            
+        self.client = AsyncOpenAI(
+            base_url=base_url,
+            api_key=api_key,
+            default_headers=extra_headers
+        )
+        
+        self.models = llm_config.get("models", {"fast": "gpt-3.5-turbo", "smart": "gpt-4"})
+        
+        self.rate_limiter = RateLimiter(
+            llm_config["rate_limits"]["requests_per_minute"],
+            llm_config["rate_limits"]["concurrent_requests"]
+        )
+        self.prompts = self._load_prompts()
+
+    def _load_prompts(self) -> Dict:
+        try:
+            with open("config/prompts.json", "r", encoding="utf-8") as f:
+                return json.load(f)
+        except:
+            return {}
+
+    async def translate_chunk(self, items: List[ManifestItem], glossary: Dict = None, 
+                              instruction: str = None, model_type: str = "fast",
+                              mode: str = "bilingual") -> Dict[str, str]:
+        """
+        Translate a chunk of items.
+        
+        Args:
+            items: List of ManifestItem to translate
+            glossary: Term dictionary
+            instruction: Style guide
+            model_type: "fast" or "smart"
+            mode: "bilingual" or "chinese"
+        """
+        if not items: return {}
+        
+        model = self.models.get(model_type, self.models.get("fast"))
+        prompt = self._build_prompt(items, mode)
+        
+        try:
+            # Build System Prompt
+            base_sys_prompt = self.prompts.get("translation", {}).get("system", "You are a professional translator.")
+            
+            # 中文模式：添加占位符保护指令
+            if mode == "chinese":
+                base_sys_prompt += """
+
+Placeholder Instructions (CRITICAL):
+1. Text contains PAIRED placeholders: φNφ (start) and φ/Nφ (end), like HTML tags.
+2. Example: "φ1φTable Talkφ/1φ" means italic text, translate as "φ1φ桌谈φ/1φ"
+3. Single placeholders φNφ without φ/Nφ are inline elements (footnotes, formulas) - keep them in place.
+4. RULES:
+   - DO NOT create new placeholder numbers that don't exist in the original
+   - DO NOT remove or modify existing placeholders
+   - Keep placeholders in the SAME relative position in your translation
+   - If word order changes, keep placeholders with their associated text
+5. Each line starts with paragraph ID (p_xxxxx). Preserve them.
+"""
+
+            
+            if instruction:
+                base_sys_prompt += f"\n\nBook Style Guide:\n{instruction}"
+            
+            if glossary:
+                glossary_text = "\n".join([f"{k} -> {v}" for k, v in glossary.items()])
+                base_sys_prompt += f"\n\nTerminology:\n{glossary_text}"
+            
+            # Strict formatting instructions
+            base_sys_prompt += "\n\nRequirements:\n1. Each line MUST start with ID (p_xxxxx).\n2. DO NOT modify IDs.\n3. Return only translations."
+
+            raw_response = await self._make_request(model, base_sys_prompt, prompt)
+            
+            if not raw_response:
+                return {item.global_id: f"[Error - Empty Response]" for item in items}
+            
+            return self._simple_parse(raw_response, items, mode)
+            
+        except Exception as e:
+            logger.error(f"Translation failed ({model}): {e}")
+            return {item.global_id: f"[Error - {str(e)}]" for item in items}
+
+    async def repair_format(self, original_text: str, broken_translation: str) -> str:
+        """
+        修复翻译格式：将占位符正确插入到译文中。
+        """
+        model = self.models.get("fast")
+        
+        system_prompt = "You are a format repair assistant. Your ONLY job is to insert placeholders into the translation."
+        user_prompt = f"""
+Original Text (with placeholders):
+{original_text}
+
+Translation (placeholders missing/incorrect):
+{broken_translation}
+
+Task:
+Please rewrite the Translation to include ALL placeholders (φcXXXXXφ) from the Original Text.
+1. DO NOT translate again. Keep the meaning of the Translation.
+2. Place φcXXXXXφ tags exactly where they correspond to the original format (bold, italic, links).
+3. Output ONLY the fixed translation.
+"""
+        try:
+            return await self._make_request(model, system_prompt, user_prompt)
+        except Exception as e:
+            logger.error(f"Format repair failed: {e}")
+            return broken_translation
+
+    async def raw_chat_completion(self, system_prompt: str, user_prompt: str, model_type: str = "smart") -> str:
+        """Generic chat completion (for Profiler)."""
+        model = self.models.get(model_type, self.models.get("smart"))
+        return await self._make_request(model, system_prompt, user_prompt)
+
+    def _build_prompt(self, items: List[ManifestItem], mode: str = "bilingual") -> str:
+        """构建翻译提示词"""
+        lines = []
+        for item in items:
+            if mode == "chinese":
+                # 中文模式：使用带占位符的文本和段落类型
+                text = item.text_with_placeholders if item.text_with_placeholders else item.clean_text
+                p_type = getattr(item, 'paragraph_type', 'body').upper()
+                lines.append(f"{item.global_id} [{p_type}] {text}")
+            else:
+                # 双语模式：使用纯文本
+                lines.append(f"{item.global_id} {item.clean_text}")
+        return "\n".join(lines)
+
+    def _simple_parse(self, response: str, items: List[ManifestItem], mode: str = "bilingual") -> Dict[str, str]:
+        """解析 LLM 响应"""
+        results = {}
+        for i, item in enumerate(items):
+            current_id = item.global_id
+            start_idx = response.find(current_id)
+            if start_idx == -1: continue
+            
+            end_idx = len(response)
+            if i + 1 < len(items):
+                next_id = items[i+1].global_id
+                next_found = response.find(next_id, start_idx + len(current_id))
+                if next_found != -1:
+                    end_idx = next_found
+            
+            content = response[start_idx:end_idx].strip()
+            clean_content = content[len(current_id):].strip()
+            clean_content = clean_content.lstrip(":： \t")
+            
+            # 移除类型标记 (如 [BODY])
+            if mode == "chinese":
+                clean_content = re.sub(r'^\[[A-Z]+\]\s*', '', clean_content)
+                
+            if clean_content:
+                results[current_id] = clean_content
+
+        # Fallback: 逐行解析
+        if len(results) < len(items):
+            for line in response.split("\n"):
+                line = line.strip()
+                for item in items:
+                    if item.global_id not in results and line.startswith(item.global_id):
+                        res = line[len(item.global_id):].strip().lstrip(":： ")
+                        if mode == "chinese":
+                            res = re.sub(r'^\[[A-Z]+\]\s*', '', res)
+                        if res: results[item.global_id] = res
+        return results
+
+    @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=2, max=10))
+    async def _make_request(self, model: str, system_prompt: str, user_prompt: str) -> str:
+        await self.rate_limiter.acquire()
+        try:
+            resp = await self.client.chat.completions.create(
+                model=model,
+                messages=[
+                    {"role": "system", "content": system_prompt},
+                    {"role": "user", "content": user_prompt}
+                ],
+                temperature=self.config['translation'].get('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()
+
+# Alias for backward compatibility
+OpenRouterClient = LLMClient

archive/v0.08/src/manifest_manager.py

@@ -0,0 +1,166 @@
+"""
+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
+    tag_attrs: Dict[str, Any] = field(default_factory=dict) # 外层标签的属性 (class, style...)
+    translation: Optional[str] = None
+    status: str = "pending"  # pending, translated, ignored, failed
+    error_msg: Optional[str] = None
+    model_used: Optional[str] = None  # 记录使用的模型
+    quality_score: Optional[int] = None # 记录质量评分
+    
+    # === 中文模式专用字段 ===
+    text_with_placeholders: str = ""           # 带占位符的文本
+    placeholder_map: Dict[str, str] = field(default_factory=dict)     # 占位符映射表 {id: html_string}
+    paragraph_type: str = "body"               # 段落类型：chapter/section/subsection/epigraph/body
+    translation_with_placeholders: str = ""    # 带占位符的译文
+    translation_with_original_html: str = ""   # 还原后的最终 HTML (中文模式)
+    
+    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, model: str = None, score: int = None):
+        """更新翻译结果。"""
+        if global_id in self._items_by_id:
+            item = self._items_by_id[global_id]
+            if translation is not None:
+                item.translation = translation
+            item.status = status
+            if error:
+                item.error_msg = error
+            if model:
+                item.model_used = model
+            if score is not None:
+                item.quality_score = score
+        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/v0.08/src/quality_manager.py

@@ -0,0 +1,87 @@
+"""
+Quality Manager Module
+
+Responsible for evaluating translation quality and deciding on re-translation.
+"""
+
+import json
+import random
+from typing import List, Dict, Any, Tuple
+from loguru import logger
+from .manifest_manager import ManifestItem
+from .llm_client import LLMClient
+
+class QualityManager:
+    def __init__(self, config: Dict, llm_client: LLMClient):
+        self.config = config
+        self.llm_client = llm_client
+        self.qc_config = config['translation'].get('quality_control', {})
+        self.pass_score = self.qc_config.get('pass_score', 7)
+        self.sample_size = self.qc_config.get('sample_size', 2)
+
+    async def evaluate_chunk(self, chunk: List[ManifestItem]) -> Tuple[bool, int, str]:
+        """
+        Evaluate a chunk of translations.
+        
+        Returns:
+            (passed: bool, average_score: int, reason: str)
+        """
+        if not self.qc_config.get('enabled', False):
+            return True, 10, "QC Disabled"
+
+        # 1. Sample items
+        # Filter for items that actually have content and translations
+        valid_items = [item for item in chunk if item.translation and len(item.clean_text) > 20]
+        
+        if not valid_items:
+            return True, 10, "No valid items to sample"
+            
+        sample_items = random.sample(valid_items, min(len(valid_items), self.sample_size))
+        
+        # 2. Build Prompt
+        prompt = self._build_evaluation_prompt(sample_items)
+        
+        # 3. Call LLM (Smart)
+        try:
+            response = await self.llm_client.raw_chat_completion(
+                system_prompt="You are a professional translation editor.",
+                user_prompt=prompt,
+                model_type="smart"
+            )
+            
+            # 4. Parse JSON
+            # Clean potential markdown
+            json_str = response.strip()
+            if "```json" in json_str:
+                json_str = json_str.split("```json")[1].split("```")[0].strip()
+            elif "```" in json_str:
+                json_str = json_str.split("```")[1].split("```")[0].strip()
+                
+            result = json.loads(json_str)
+            score = result.get('score', 0)
+            reason = result.get('reason', 'No reason provided')
+            
+            passed = score >= self.pass_score
+            return passed, score, reason
+            
+        except Exception as e:
+            logger.error(f"QC evaluation failed: {e}")
+            # If QC fails, we default to PASS to avoid blocking progress, but log it
+            return True, 0, f"QC Error: {e}"
+
+    def _build_evaluation_prompt(self, items: List[ManifestItem]) -> str:
+        content = ""
+        for i, item in enumerate(items, 1):
+            content += f"Item {i}:\nOriginal: {item.clean_text}\nTranslation: {item.translation}\n\n"
+            
+        return f"""Please evaluate the following translations (English to Chinese).
+Focus on accuracy, fluency, and terminology consistency.
+
+Items to evaluate:
+{content}
+
+Return a JSON object with:
+- \"score\": An integer from 1 to 10 (10 being perfect).
+- \"reason\": A brief explanation of the score.
+
+JSON Output:"""

archive/v0.08/src/text_processor.py

@@ -0,0 +1,188 @@
+"""
+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
+from .format_extractor import FormatExtractor
+
+
+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)
+        self.format_extractor = FormatExtractor()
+        
+    def extract_to_manifest(self, html_content: str, source_file: str, manifest: ManifestManager, mode: str = "bilingual"):
+        """
+        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。
+            mode (str): 翻译模式 - "bilingual" 或 "chinese"
+        """
+        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"
+                
+                # 提取格式信息（中文模式）
+                text_with_ph = ""
+                placeholder_map = None
+                p_type = "body"
+                
+                if mode == "chinese":
+                    # FormatExtractor 接受 HTML 字符串
+                    clean_text, text_with_ph, placeholder_map, p_type = self.format_extractor.extract(str(element))
+                
+                # 注册
+                item = manifest.add_item(
+                    source_file=source_file,
+                    original_html=str(element),
+                    clean_text=clean_text,
+                    tag=element.name,
+                    metadata={"status": status}
+                )
+                item.tag_attrs = element.attrs  # 存储外层标签属性
+                
+                # 更新中文模式字段
+                if mode == "chinese":
+                    item.text_with_placeholders = text_with_ph
+                    item.placeholder_map = placeholder_map
+                    item.paragraph_type = p_type
+                
+                # 同步更新 manifest 状态 (如果需要过滤)
+                if status == "ignored":
+                    manifest.update_item(item.global_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, mode: str = "bilingual") -> List[List[Any]]:
+        """
+        从 Manifest 中筛选待翻译项目并分块。
+        
+        Args:
+            manifest: ManifestManager 实例
+            mode: 翻译模式 (保留参数以供将来使用)
+        """
+        pending_items = manifest.get_items(status="pending")
+        if not pending_items:
+            return []
+            
+        chunks = []
+        current_chunk = []
+        current_size = 0
+        
+        for item in pending_items:
+            # 中文模式使用带占位符的文本长度
+            if mode == "chinese" and item.text_with_placeholders:
+                text_len = len(item.text_with_placeholders)
+            else:
+                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/v0.08/src/translator.py

@@ -0,0 +1,248 @@
+"""
+EPUB Translator Core Module - v0.08 (Mode Support)
+"""
+
+import asyncio
+import traceback
+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 LLMClient
+from .text_processor import TextProcessor
+from .bilingual_builder import BilingualEPUBBuilder
+from .chinese_builder import ChineseEPUBBuilder
+from .manifest_manager import ManifestManager
+from .book_profiler import BookProfiler
+from .cache import TranslationCache
+from .format_restorer import FormatRestorer
+from .utils import add_spacing_between_cn_and_en_num
+
+
+class EPUBTranslator:
+    
+    def __init__(self, config: Dict, use_cache: bool = True):
+        self.config = config
+        self.console = Console()
+        self.use_cache = use_cache
+        
+        self.parser = None
+        self.llm_client = LLMClient(config)
+        self.text_processor = TextProcessor(config)
+        self.profiler = BookProfiler(config, self.llm_client)
+        self.cache = TranslationCache(config) if use_cache else None
+        self.restorer = FormatRestorer()
+        
+        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, mode: str = "bilingual") -> str:
+        """
+        翻译 EPUB 文件
+        
+        Args:
+            epub_path: EPUB 文件路径
+            test_mode: 测试模式（只翻译前几块）
+            output_dir: 输出目录
+            mode: 翻译模式 - "bilingual" (双语) 或 "chinese" (纯中文)
+        """
+        try:
+            epub_path = Path(epub_path)
+            self.parser = EPUBParser(str(epub_path))
+            
+            # 1. Manifest - 根据 mode 使用不同的 manifest 文件
+            manifest_suffix = "_chinese" if mode == "chinese" else ""
+            manifest_path = self.manifest_dir / f"{epub_path.stem}{manifest_suffix}_manifest.json"
+            manifest = ManifestManager(str(manifest_path))
+            
+            if not manifest.load() or not self.use_cache:
+                self.console.print(f"[yellow]Initializing Manifest (Mode: {mode})...[/yellow]")
+                manifest.init_manifest(book_id=epub_path.name, metadata=self.parser.get_book_info())
+                content_items = self.parser.extract_all_content_items()
+                for item in content_items:
+                    # 传递 mode 参数
+                    self.text_processor.extract_to_manifest(
+                        item['content'], item['file_name'], manifest, mode=mode
+                    )
+                manifest.save()
+            
+            stats = manifest.stats
+            self.console.print(f"[green]Manifest loaded: {stats['total']} paragraphs[/green]")
+            if stats['pending'] < stats['total'] and stats['translated'] > 0:
+                self.console.print(
+                    f"[yellow]Detected incomplete translation task, completed {stats['translated']}/{stats['total']}, "
+                    f"continuing translation of remaining {stats['pending']} paragraphs...[/yellow]"
+                )
+
+            # 2. Profile (Glossary)
+            profile = {}
+            if not test_mode:
+                self.console.print("[yellow]Generating Book Profile...[/yellow]")
+                profile = await self.profiler.analyze_book(manifest)
+                self.console.print(f"Genre: {profile.get('genre')} | Style: {profile.get('style')}")
+
+            # 3. Translate - 传递 mode 参数
+            chunks = self.text_processor.create_chunks_from_manifest(manifest, mode=mode)
+            
+            if test_mode:
+                self.console.print("[yellow]Test mode enabled: Translating only first 10 chunks...[/yellow]")
+                chunks = chunks[:10]
+
+            if chunks:
+                await self._translate_concurrently(chunks, manifest, profile, mode=mode)
+            
+            # 4. Build - 根据 mode 选择正确的 Builder
+            self.console.print(f"\n[yellow]Building {mode} EPUB...[/yellow]")
+            output_path = output_dir or self.config['output']['output_dir']
+            
+            if mode == "chinese":
+                builder = ChineseEPUBBuilder(self.parser.book, self.config)
+                result_file = builder.create_chinese_epub_with_mapping(
+                    manifest.get_items(), output_path
+                )
+            else:
+                builder = BilingualEPUBBuilder(self.parser.book, self.config)
+                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,
+                    "tag_attrs": item.tag_attrs
+                } for item in manifest.get_items()}
+                
+                result_file = builder.create_bilingual_epub_with_mapping(
+                    translation_map, paragraph_map, output_path
+                )
+            
+            final_stats = manifest.stats
+            self.console.print(f"""
+[green]✅ Translation complete![/green]
+  - Mode: {mode}
+  - Total Paragraphs: {final_stats['total']}
+  - Successfully Translated: {final_stats['translated']}
+  - Skipped: {final_stats['ignored']}
+  - Failed: {final_stats['failed']}
+  - Output File: {result_file}
+""")
+            return result_file
+        except Exception as e:
+            traceback.print_exc()
+            logger.error(f"Translation flow failed: {e}")
+            raise
+
+    async def _translate_concurrently(self, chunks: List[List[Any]], manifest: ManifestManager, 
+                                      profile: Dict, mode: str = "bilingual"):
+        total_chunks = len(chunks)
+        glossary = profile.get('glossary', {})
+        instruction = profile.get('translation_instruction', "")
+        
+        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]Translating ({mode})...", total=total_chunks)
+            
+            async def worker(chunk, idx):
+                try:
+                    model_name = self.llm_client.models.get('fast')
+                    chunk_dicts = [item.to_dict() for item in chunk]
+                    results = None
+
+                    if self.cache:
+                        results = self.cache.get_chunk_translation(chunk_dicts, model=model_name)
+
+                    if not results:
+                        # 传递 mode 参数给 LLM
+                        results = await self.llm_client.translate_chunk(
+                            chunk, 
+                            glossary=glossary, 
+                            instruction=instruction,
+                            mode=mode
+                        )
+                        if self.cache and results:
+                            self.cache.save_chunk_translation(chunk_dicts, results, model=model_name)
+
+                    for item in chunk:
+                        if item.global_id in results:
+                            raw_translation = results[item.global_id]
+                            
+                            # 错误检测：如果翻译结果包含错误标记，视为失败
+                            if raw_translation.startswith("[Error") or "Error -" in raw_translation:
+                                logger.warning(f"Translation error for {item.global_id}: {raw_translation}")
+                                manifest.update_item(item.global_id, None, status="failed", error=raw_translation)
+                                continue
+                            
+                            # 格式化翻译文本（盘古之白）
+                            processed_translation = add_spacing_between_cn_and_en_num(raw_translation)
+                            
+                            if mode == "chinese":
+                                # 检查是否有内嵌占位符（排除 _prefix, _suffix）
+                                inner_placeholders = {k: v for k, v in item.placeholder_map.items() 
+                                                     if not k.startswith("_")} if item.placeholder_map else {}
+                                
+                                if not inner_placeholders:
+                                    # 没有内嵌占位符，直接使用译文（清除 LLM 可能虚构的占位符）
+                                    clean_translation = self.restorer._strip_placeholders(processed_translation)
+                                    item.translation_with_placeholders = clean_translation
+                                    # 还原时只添加前缀后缀
+                                    restored_html, success = self.restorer.restore(
+                                        clean_translation, 
+                                        item.placeholder_map
+                                    )
+                                else:
+                                    # 有内嵌占位符，正常还原
+                                    item.translation_with_placeholders = processed_translation
+                                    restored_html, success = self.restorer.restore(
+                                        processed_translation, 
+                                        item.placeholder_map
+                                    )
+                                    
+                                    # 格式修复逻辑
+                                    if not success:
+                                        logger.warning(f"格式丢失 (ID: {item.global_id})，尝试自动修复...")
+                                        try:
+                                            fixed_translation = await self.llm_client.repair_format(
+                                                item.text_with_placeholders, 
+                                                processed_translation
+                                            )
+                                            restored_html_2, success_2 = self.restorer.restore(
+                                                fixed_translation,
+                                                item.placeholder_map
+                                            )
+                                            
+                                            if success_2:
+                                                logger.info(f"格式修复成功! (ID: {item.global_id})")
+                                                restored_html = restored_html_2
+                                                item.translation_with_placeholders = fixed_translation
+                                            else:
+                                                logger.error(f"格式修复失败 (ID: {item.global_id})，保留原始译文")
+                                        except Exception as e:
+                                            logger.error(f"修复过程出错: {e}")
+
+                                item.translation_with_original_html = restored_html
+                                # translation 字段存储纯文本
+                                item.translation = self.restorer._strip_placeholders(item.translation_with_placeholders)
+                                manifest.update_item(item.global_id, item.translation) 
+                            else:
+
+                                # 双语模式
+                                item.translation = processed_translation
+                                manifest.update_item(item.global_id, item.translation)
+                        else:
+                            manifest.update_item(item.global_id, None, status="failed", error="Missing")
+                    manifest.save()
+                except Exception as e:
+                    logger.error(f"Chunk {idx} failed: {e}")
+                finally:
+                    progress.update(task_id, advance=1)
+
+            tasks = [worker(chunk, i) for i, chunk in enumerate(chunks)]
+            await asyncio.gather(*tasks)

archive/v0.08/src/utils.py

@@ -0,0 +1,208 @@
+"""
+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
+from dotenv import load_dotenv
+
+
+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
+    """
+    # 加载 .env 文件
+    load_dotenv()
+
+    try:
+        with open(config_path, 'r', encoding='utf-8') as f:
+            config = json.load(f)
+        
+        # 从环境变量获取 API Key
+        for provider_name, provider_config in config.get('providers', {}).items():
+            env_key = f"{provider_name.upper()}_API_KEY"
+            if env_key in os.environ:
+                provider_config['api_key'] = os.environ[env_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] + "..."
+
+
+def add_spacing_between_cn_and_en_num(text: str) -> str:
+    """
+    在中文和英文/数字之间添加空格（盘古之白）
+    
+    Args:
+        text: 原始文本
+        
+    Returns:
+        处理后的文本
+    """
+    import re
+    if not text:
+        return text
+        
+    # 中文-英文/数字
+    text = re.sub(r'([\u4e00-\u9fff])([a-zA-Z0-9])', r'\1 \2', text)
+    # 英文/数字-中文
+    text = re.sub(r'([a-zA-Z0-9])([\u4e00-\u9fff])', r'\1 \2', text)
+    
+    return text