'update'

2025-10-21 10:46:03 +08:00
parent db9be32815
commit fb0f5ed9c5
20 changed files with 1869 additions and 103 deletions
--- a/test_cfi_simple.py
+++ b/test_cfi_simple.py
@@ -0,0 +1,116 @@
+#!/usr/bin/env python3
+"""
+简化的 CFI 排序测试 - 专注核心功能验证
+"""
+
+import sys
+import os
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+from epub_cfi_parser import EpubCFIParser
+
+
+def test_cfi_core_functionality():
+    """测试 CFI 解析和排序的核心功能"""
+    print("=== CFI 核心功能测试 ===")
+    
+    # 测试用例：模拟真实的 iBooks CFI
+    test_cfis = [
+        "epubcfi(/6/22[id19]!/4[6LJU0-b41b8d40e3c34c548f1a46585319196c]/40/1,:96,:214)",
+        "epubcfi(/6/18[id17]!/4[5N3C0-b41b8d40e3c34c548f1a46585319196c]/6/1,:128,:219)",
+        "epubcfi(/6/22[id19]!/4[6LJU0-b41b8d40e3c34c548f1a46585319196c]/8/1,:0,:43)",
+        "epubcfi(/6/18[id17]!/4[5N3C0-b41b8d40e3c34c548f1a46585319196c]/10/1,:214,:273)",
+        "epubcfi(/6/22[id19]!/4[6LJU0-b41b8d40e3c34c548f1a46585319196c]/12/1,:0,:17)",
+    ]
+    
+    print("原始顺序:")
+    for i, cfi in enumerate(test_cfis, 1):
+        chapter = EpubCFIParser.extract_chapter_info(cfi)
+        print(f"  {i}. {chapter} - {cfi}")
+    
+    # 排序
+    sorted_cfis = sorted(test_cfis, key=EpubCFIParser.create_sort_key)
+    
+    print("\nCFI 排序后:")
+    for i, cfi in enumerate(sorted_cfis, 1):
+        chapter = EpubCFIParser.extract_chapter_info(cfi)
+        parsed = EpubCFIParser.parse_cfi(cfi)
+        if parsed:
+            spine, local, offset = parsed
+            print(f"  {i}. {chapter} - spine={spine} local={local[:3]}... offset={offset}")
+        else:
+            print(f"  {i}. {chapter} - 解析失败")
+    
+    # 验证排序正确性
+    spine_sequence = []
+    for cfi in sorted_cfis:
+        parsed = EpubCFIParser.parse_cfi(cfi)
+        if parsed and parsed[0]:
+            spine_sequence.append(parsed[0][1])  # 第二个spine数字
+    
+    is_sorted = all(spine_sequence[i] <= spine_sequence[i+1] for i in range(len(spine_sequence)-1))
+    print(f"\n✅ 排序验证: {'通过' if is_sorted else '失败'} (spine序列: {spine_sequence})")
+
+
+def test_cfi_edge_cases():
+    """测试边界情况"""
+    print("\n=== 边界情况测试 ===")
+    
+    edge_cases = [
+        ("空字符串", ""),
+        ("无效格式", "invalid_cfi"),
+        ("只有spine", "epubcfi(/6/14)"),
+        ("标准格式", "epubcfi(/6/14[chapter]!/4/2:10)"),
+        ("复杂格式", "epubcfi(/6/22[id19]!/4[longid]/40/1,:96,:214)"),
+    ]
+    
+    for name, cfi in edge_cases:
+        parsed = EpubCFIParser.parse_cfi(cfi)
+        sort_key = EpubCFIParser.create_sort_key(cfi)
+        print(f"{name:12}: 解析={'✅' if parsed else '❌'} 排序键长度={len(sort_key)}")
+
+
+def compare_with_simple_sort():
+    """对比 CFI 排序与简单字符串排序的差异"""
+    print("\n=== 排序方法对比 ===")
+    
+    test_cfis = [
+        "epubcfi(/6/22!/4:100)",
+        "epubcfi(/6/22!/4:20)",
+        "epubcfi(/6/14!/4:5)",
+        "epubcfi(/6/2!/4:0)",
+    ]
+    
+    # 字符串排序
+    string_sorted = sorted(test_cfis)
+    print("字符串排序:")
+    for i, cfi in enumerate(string_sorted, 1):
+        print(f"  {i}. {cfi}")
+    
+    # CFI 排序
+    cfi_sorted = sorted(test_cfis, key=EpubCFIParser.create_sort_key)
+    print("\nCFI 语义排序:")
+    for i, cfi in enumerate(cfi_sorted, 1):
+        print(f"  {i}. {cfi}")
+    
+    # 比较差异
+    different = string_sorted != cfi_sorted
+    print(f"\n{'❌ 排序结果不同（符合预期）' if different else '⚠️  排序结果相同'}")
+
+
+if __name__ == "__main__":
+    test_cfi_core_functionality()
+    test_cfi_edge_cases()
+    compare_with_simple_sort()
+    
+    print(f"\n🎉 CFI 排序功能实现完成！")
+    print("主要改进:")
+    print("  ✅ 按 EPUB CFI 规范解析位置信息")
+    print("  ✅ 正确的文档位置排序（非字符串排序）")
+    print("  ✅ 支持复杂的 CFI 格式和章节提取")
+    print("  ✅ 降级处理（CFI失败时使用物理位置）")
+    print("\n下一步可选优化:")
+    print("  🔄 优化警告信息显示")
+    print("  📊 添加排序性能统计")
+    print("  🔍 支持更多 CFI 变体格式")
+    print("  💾 缓存解析结果提升性能")