Release v0.13: Typography V3 (Safe mode) & Endnote Extraction Fix

2026-02-01 11:51:36 +08:00
parent 8e58415173
commit 40491e6386
95 changed files with 8493 additions and 11 deletions
@@ -0,0 +1,47 @@
+import sys
+from pathlib import Path
+import traceback
+
+# Add src to path
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from src.epub_cleaner import EpubCleaner
+from src.bilingual_builder import BilingualBuilder
+from src.utils import setup_logger
+from src.data_model import BookStructure
+
+logger = setup_logger("verify_toc")
+
+def verify_fix():
+    INPUT_EPUB = Path("input/Empire of AI Dreams and Nightmares in Sam Altmans OpenAI (Karen Hao).epub")
+    OUTPUT_EPUB = Path("output/verify_toc.epub")
+    WORK_DIR = Path("tmp/verify_toc")
+
+    if not INPUT_EPUB.exists():
+        logger.error(f"Input not found: {INPUT_EPUB}")
+        return
+
+    # Clean
+    logger.info("Step 1: Cleaning EPUB...")
+    cleaner = EpubCleaner(INPUT_EPUB, WORK_DIR)
+    json_path = cleaner.clean()
+    
+    # Load structure
+    with open(json_path, 'r') as f:
+        structure = BookStructure.model_validate_json(f.read())
+
+    # Build
+    logger.info("Step 2: Building EPUB with TOC preservation...")
+    builder = BilingualBuilder(WORK_DIR, original_epub_path=INPUT_EPUB)
+    builder.build(structure, OUTPUT_EPUB)
+    
+    logger.info(f"Step 3: EPUB generated at {OUTPUT_EPUB}")
+
+if __name__ == "__main__":
+    print("Starting verification script...")
+    try:
+        verify_fix()
+        print("Verification script finished.")
+    except Exception as e:
+        traceback.print_exc()
+        print(f"CRITICAL ERROR: {e}")