Initial commit

2026-01-19 09:51:07 +08:00
commit 9ef82393be
174 changed files with 22285 additions and 0 deletions
@@ -0,0 +1,132 @@
+
+import sys
+import os
+from pathlib import Path
+from ebooklib import epub
+import ebooklib
+from loguru import logger
+
+# Add project root to path
+sys.path.insert(0, str(Path(__file__).parent))
+
+from src.utils import load_config
+
+def compare_epubs(original_path, new_path):
+    print(f"🔍 Comparing EPUBs:\n  Original: {original_path}\n  New:      {new_path}")
+    print("=" * 60)
+    
+    if not os.path.exists(new_path):
+        print(f"❌ New EPUB not found: {new_path}")
+        return
+
+    try:
+        orig_book = epub.read_epub(original_path)
+        new_book = epub.read_epub(new_path)
+    except Exception as e:
+        print(f"❌ Error reading EPUBs: {e}")
+        return
+
+    # 1. Metadata Comparison
+    print("\n[1] Metadata Comparison")
+    print("-" * 60)
+    
+    namespaces = ['DC', 'OPF']
+    for ns in namespaces:
+        orig_meta = orig_book.metadata.get(ns, {})
+        new_meta = new_book.metadata.get(ns, {})
+        
+        all_keys = set(orig_meta.keys()) | set(new_meta.keys())
+        
+        for key in sorted(all_keys):
+            orig_vals = [v[0] for v in orig_meta.get(key, [])]
+            new_vals = [v[0] for v in new_meta.get(key, [])]
+            
+            if orig_vals != new_vals:
+                print(f"  ⚠️  {ns}:{key} Changed:")
+                print(f"      Orig: {orig_vals}")
+                print(f"      New:  {new_vals}")
+            else:
+                # print(f"  ✅ {ns}:{key} match")
+                pass
+
+    # Special check for Cover
+    print("\n[2] Cover Image Check")
+    print("-" * 60)
+    
+    # Check via Metadata
+    orig_cover_meta = orig_book.get_metadata('OPF', 'cover')
+    new_cover_meta = new_book.get_metadata('OPF', 'cover')
+    print(f"  Original Cover Meta (OPF): {orig_cover_meta}")
+    print(f"  New Cover Meta (OPF):      {new_cover_meta}")
+    
+    # Check via Manifest Items
+    orig_cover_items = [i for i in orig_book.get_items() if 'cover' in i.get_name().lower() and i.media_type.startswith('image/')]
+    new_cover_items = [i for i in new_book.get_items() if 'cover' in i.get_name().lower() and i.media_type.startswith('image/')]
+    
+    print(f"  Original Cover Image Items: {[i.get_name() for i in orig_cover_items]}")
+    print(f"  New Cover Image Items:      {[i.get_name() for i in new_cover_items]}")
+
+    # 3. Spine Comparison (Reading Order)
+    print("\n[3] Spine (Reading Order) Comparison")
+    print("-" * 60)
+    
+    orig_spine_ids = [item[0] for item in orig_book.spine]
+    new_spine_ids = [item[0] for item in new_book.spine]
+    
+    print(f"  Original Spine Length: {len(orig_spine_ids)}")
+    print(f"  New Spine Length:      {len(new_spine_ids)}")
+    
+    # Map IDs to Filenames for better readability
+    def get_filename(book, item_id):
+        item = book.get_item_with_id(item_id)
+        return item.get_name() if item else "UNKNOWN"
+
+    # Compare first few and last few
+    limit = 5
+    print(f"  First {limit} items:")
+    for i in range(min(len(orig_spine_ids), len(new_spine_ids), limit)):
+        f_orig = get_filename(orig_book, orig_spine_ids[i])
+        f_new = get_filename(new_book, new_spine_ids[i])
+        status = "✅" if f_orig == f_new else "❌"
+        print(f"    {i+1}. {status} Orig: {f_orig} | New: {f_new}")
+        
+    # Check for missing items in spine
+    orig_filenames = set(get_filename(orig_book, i) for i in orig_spine_ids)
+    new_filenames = set(get_filename(new_book, i) for i in new_spine_ids)
+    
+    missing_in_new = orig_filenames - new_filenames
+    if missing_in_new:
+        print(f"\n  ⚠️  Missing from New Spine ({len(missing_in_new)}):")
+        for f in list(missing_in_new)[:10]:
+            print(f"      - {f}")
+            
+    # 4. Manifest Comparison (All Resources)
+    print("\n[4] Manifest (All Resources) Comparison")
+    print("-" * 60)
+    
+    orig_manifest = {i.get_name() for i in orig_book.get_items()}
+    new_manifest = {i.get_name() for i in new_book.get_items()}
+    
+    missing_resources = orig_manifest - new_manifest
+    # Filter out NCX/Nav as they might be regenerated with different names
+    missing_resources = {f for f in missing_resources if not f.endswith('.ncx') and 'nav' not in f.lower()}
+    
+    if missing_resources:
+        print(f"  ⚠️  Resources Missing in New Book ({len(missing_resources)}):")
+        for f in sorted(list(missing_resources)):
+            print(f"      - {f}")
+    else:
+        print("  ✅ All resources preserved.")
+
+if __name__ == "__main__":
+    orig_path = "input/To Explain the World The Discovery of Modern Science (H) (Steven Weinberg [Weinberg, Steven]) (Z-Library).epub"
+    # Escaped path from user prompt: "input/To Explain the World The Discovery of Modern Science (H) (Steven Weinberg [Weinberg, Steven]) (Z-Library).epub"
+    
+    # We generated this in the previous batch test
+    new_path = "test_output/To Explain the World The Discovery of Modern Science (H)_bilingual.epub" 
+    
+    if len(sys.argv) > 2:
+        orig_path = sys.argv[1]
+        new_path = sys.argv[2]
+        
+    compare_epubs(orig_path, new_path)