Improve EPUB restoration, book terminology and Calibre QA workflow

2026-10-08 07:25:27 +08:00
parent 40491e6386
commit caf9d8f4bb
35 changed files with 1439 additions and 959 deletions
@@ -1,4 +1,5 @@
 import argparse
+import hashlib
 import sys
 import os
 from pathlib import Path
@@ -33,11 +34,15 @@ def run_preprocess(args):
        if structure_path.exists() and not args.force:
            logger.info(f"Reusing existing structure: {structure_path}")
            structure = BookStructure.load(structure_path)
+            if structure.source_sha256 != hashlib.sha256(input_path.read_bytes()).hexdigest():
+                structure = BookStructure.load(EpubCleaner(input_path, work["root"]).clean())
        else:
            logger.info("Cleaning EPUB...")
            cleaner = EpubCleaner(input_path, work["root"])
            structure_path = cleaner.clean()
            structure = BookStructure.load(structure_path)
+            if structure.source_sha256 != hashlib.sha256(input_path.read_bytes()).hexdigest():
+                structure = BookStructure.load(EpubCleaner(input_path, work["root"]).clean())

        # 2. Extract Text
        logger.info("Extracting text segments...")