epub_bilingual_translator/scripts/debug/debug.py

#!/usr/bin/env python3
"""
调试和测试脚本
用于诊断 EPUB 解析问题
"""

import sys
from pathlib import Path

# 添加 src 目录到路径
sys.path.insert(0, str(Path(__file__).parent / "src"))

from src.epub_parser import EPUBParser
from src.text_processor import TextProcessor
from src.utils import load_config
from rich.console import Console
from rich.table import Table
from rich.panel import Panel
from bs4 import BeautifulSoup
import ebooklib


def debug_epub_structure(epub_path: str):
    """调试 EPUB 结构"""
    console = Console()
    
    try:
        # 加载配置
        config = load_config('config/config.json')
        
        # 初始化解析器
        parser = EPUBParser(epub_path)
        text_processor = TextProcessor(config)
        
        console.print(f"[bold blue]调试 EPUB 文件: {epub_path}[/bold blue]\n")
        
        # 显示基本信息
        book_info = parser.get_book_info()
        info_table = Table(title="书籍信息")
        info_table.add_column("属性", style="cyan")
        info_table.add_column("值", style="white")
        
        for key, value in book_info.items():
            info_table.add_row(key, str(value))
        
        console.print(info_table)
        
        # 显示目录结构
        console.print("\n[bold green]目录结构分析:[/bold green]")
        
        toc_table = Table(title="目录结构")
        toc_table.add_column("类型", style="cyan")
        toc_table.add_column("标题", style="white")
        toc_table.add_column("状态", style="green")
        
        # 检查各种内容类型
        content_types = ['preface', 'introduction', 'prologue', 'abstract', 'epilogue', 'acknowledgments']
        
        for content_type in content_types:
            item = parser.toc_structure.get(content_type)
            if item:
                toc_table.add_row(content_type, item['title'], "✓ 找到")
            else:
                toc_table.add_row(content_type, "-", "✗ 未找到")
        
        # 章节信息
        chapters = parser.toc_structure['chapters']
        toc_table.add_row("chapters", f"{len(chapters)} 个章节", "✓ 找到" if chapters else "✗ 未找到")
        
        console.print(toc_table)
        
        # 显示章节列表
        if chapters:
            console.print("\n[bold yellow]章节列表:[/bold yellow]")
            chapter_table = Table()
            chapter_table.add_column("序号", style="cyan")
            chapter_table.add_column("标题", style="white")
            chapter_table.add_column("内容长度", style="green")
            
            for i, chapter in enumerate(chapters[:10], 1):  # 只显示前10个
                content = parser._extract_item_content(chapter)
                content_length = len(content) if content else 0
                chapter_table.add_row(str(i), chapter['title'], f"{content_length:,} 字符")
            
            if len(chapters) > 10:
                chapter_table.add_row("...", f"还有 {len(chapters) - 10} 个章节", "...")
            
            console.print(chapter_table)
        
        # 测试段落提取
        console.print("\n[bold magenta]段落提取测试:[/bold magenta]")
        
        # 选择第一个有内容的项目进行测试
        test_content = None
        test_title = ""
        
        # 优先测试序言类内容
        for content_type in ['prologue', 'preface', 'introduction', 'abstract']:
            item = parser.toc_structure.get(content_type)
            if item:
                test_content = parser._extract_item_content(item)
                test_title = f"{content_type}: {item['title']}"
                break
        
        # 如果没有序言，测试第一个章节
        if not test_content and chapters:
            test_content = parser._extract_item_content(chapters[0])
            test_title = f"章节: {chapters[0]['title']}"
        
        if test_content:
            paragraphs = text_processor.extract_paragraphs(test_content)
            
            console.print(f"测试内容: {test_title}")
            console.print(f"原始内容长度: {len(test_content):,} 字符")
            console.print(f"提取段落数: {len(paragraphs)}")
            
            if paragraphs:
                # 显示前几个段落
                para_table = Table(title="段落示例")
                para_table.add_column("序号", style="cyan")
                para_table.add_column("类型", style="yellow")
                para_table.add_column("内容预览", style="white")
                para_table.add_column("长度", style="green")
                
                for i, para in enumerate(paragraphs[:5], 1):
                    preview = para['text'][:100] + "..." if len(para['text']) > 100 else para['text']
                    para_table.add_row(
                        str(i), 
                        para.get('type', 'unknown'),
                        preview,
                        str(len(para['text']))
                    )
                
                console.print(para_table)
                
                # 测试翻译块创建
                chunks = text_processor.create_chunks(paragraphs, 3)
                console.print(f"\n[cyan]翻译块信息:[/cyan] 创建了 {len(chunks)} 个翻译块")
                
                if chunks:
                    chunk_table = Table(title="翻译块示例")
                    chunk_table.add_column("块号", style="cyan")
                    chunk_table.add_column("段落数", style="yellow")
                    chunk_table.add_column("总字符数", style="green")
                    
                    for i, chunk in enumerate(chunks[:3], 1):  # 显示前3个块
                        total_chars = sum(len(p['text']) for p in chunk)
                        chunk_table.add_row(str(i), str(len(chunk)), f"{total_chars:,}")
                    
                    console.print(chunk_table)
                
            else:
                console.print("[red]未能提取到段落！[/red]")
                
                # 显示原始内容的一部分用于调试
                soup = BeautifulSoup(test_content, 'html.parser')
                text_content = soup.get_text()[:500]
                
                console.print(Panel(
                    text_content,
                    title="原始文本内容（前500字符）",
                    border_style="red"
                ))
        else:
            console.print("[red]未找到可测试的内容！[/red]")
        
        # 显示所有 HTML 文件
        console.print("\n[bold cyan]所有 HTML 文件:[/bold cyan]")
        
        try:
            html_items = list(parser.book.get_items_of_type(ebooklib.ITEM_DOCUMENT))
            
            file_table = Table()
            file_table.add_column("文件名", style="cyan")
            file_table.add_column("大小", style="green")
            file_table.add_column("内容预览", style="white")
            
            for item in html_items[:10]:  # 只显示前10个
                try:
                    content = item.get_content().decode('utf-8', errors='ignore')
                    soup = BeautifulSoup(content, 'html.parser')
                    text_preview = soup.get_text()[:100].replace('\n', ' ')
                    
                    file_table.add_row(
                        item.get_name(),
                        f"{len(content):,} 字符",
                        text_preview + "..." if len(text_preview) == 100 else text_preview
                    )
                except Exception as e:
                    file_table.add_row(item.get_name(), "错误", f"读取失败: {e}")
            
            if len(html_items) > 10:
                file_table.add_row("...", f"还有 {len(html_items) - 10} 个文件", "...")
            
            console.print(file_table)
            
        except Exception as e:
            console.print(f"[yellow]无法列出 HTML 文件: {e}[/yellow]")
        
        # 总结
        console.print(f"\n[bold green]✓ 调试完成[/bold green]")
        console.print(f"[green]结论: EPUB 文件结构正常，可以进行翻译[/green]")
        
    except Exception as e:
        console.print(f"[red]调试失败: {e}[/red]")
        import traceback
        console.print(traceback.format_exc())


if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("使用方法: python debug.py <epub_file>")
        sys.exit(1)
    
    epub_file = sys.argv[1]
    debug_epub_structure(epub_file)