Normalize Chinese Part ordinals and support resumable complete-book translation

src/preprocessing/text_extractor.py

@@ -29,8 +29,9 @@ class FineGrainedExtractor:
         r'toc\.x?html',
     ]
 
-    def __init__(self, translate_toc: bool = False):
+    def __init__(self, translate_toc: bool = False, complete_book: bool = False):
         self.translate_toc = translate_toc
+        self.complete_book = complete_book
         self.format_extractor = FormatExtractor()
 
     def extract(self, structure: BookStructure, profile: Optional[BookProfile] = None) -> List[ManifestEntry]:
@@ -42,7 +43,10 @@ class FineGrainedExtractor:
         manifest_entries = []
         
         # Iterate over spine to maintain order
-        for item_id in structure.spine:
+        item_ids = list(structure.spine)
+        if self.complete_book:
+            item_ids.extend(item_id for item_id in structure.resources if item_id not in item_ids)
+        for item_id in item_ids:
             if item_id not in structure.resources:
                 logger.warning(f"Item ID {item_id} in spine but not in resources.")
                 continue
@@ -97,8 +101,9 @@ class FineGrainedExtractor:
     def _classify_document(self, file_name: str) -> str:
         if not file_name: return 'core'
         fname = file_name.lower()
-        if any(re.search(p, fname) for p in self.SKIP_TRANSLATION_PATTERNS): return 'skip'
         if any(re.search(p, fname) for p in self.TOC_PATTERNS): return 'toc'
+        if any(re.search(p, fname) for p in self.SKIP_TRANSLATION_PATTERNS):
+            return 'core' if self.complete_book else 'skip'
         return 'core'
 
     def _should_translate(self, doc_type: str, is_decorative: bool, text: str = "") -> bool: