Feat: v0.12 Pipeline Separation, Spacing Fix, and Idempotent Restoration

main.py

@@ -12,6 +12,7 @@ from src.preprocessing.text_extractor import FineGrainedExtractor
 from src.translation.manifest_manager import ManifestManager
 from src.translation.translator_engine import Translator
 from src.translation.llm_client import LLMClient
+from src.assembly.restoration_engine import RestorationEngine
 from src.assembly.backfiller import BackfillEngine
 from src.assembly.builder import BilingualBuilder
 from src.common.data_model import BookStructure
@@ -76,11 +77,9 @@ async def run_pipeline(args):
         manifest_manager.save()
         
         # 4. Translation
-        if not args.skip_translation:
-            if not api_key:
-                logger.error("Cannot translate without API Key. Use --skip-translation to test pipeline.")
-                sys.exit(1)
-                
+        # Initialize LLM Client (Centralized)
+        llm_client = None
+        if api_key:
             llm_client = LLMClient(
                 api_key=api_key, 
                 base_url=base_url, 
@@ -89,6 +88,12 @@ async def run_pipeline(args):
                 concurrent_requests=llm_conf.get("concurrent_requests", 5),
                 chunk_dir=work["chunks"]
             )
+        
+        # 4. Translation
+        if not args.skip_translation:
+            if not llm_client:
+                logger.error("Cannot translate without API Key. Use --skip-translation to test pipeline.")
+                sys.exit(1)
             
             # Profiling
             profiler = BookProfiler(llm_client)
@@ -101,35 +106,25 @@ async def run_pipeline(args):
             translator = Translator(llm_client, chunk_size=target_chunk_size, max_concurrent=concurrent_reqs)
             await translator.translate(manifest_manager.entries, profile)
             manifest_manager.save()
-            
-            # Don't close here, wait until after backfill
-            # await llm_client.close() 
-            pass
         else:
              logger.info("Skipping translation step.")
         
-        # 5. Backfill (now async + LLM repair enabled)
-        # Reuse existing llm_client if available, otherwise create temporary one if needed?
-        # In this flow, llm_client is created inside the 'if not args.skip_translation' block.
-        # If skip_translation is True, llm_client is undefined. 
+        # 5. Restoration (Format + Spacing + Repair)
+        logger.info("Restoring format & applying spacing...")
+        # RestorationEngine handles Pangu spacing, FormatRestorer, and LLM Repair
+        restorer = RestorationEngine(llm_client)
+        # Default to skipping if already done, unless forced
+        force_restore = getattr(args, 'force_restore', False)
+        restore_success = await restorer.restore_entries(manifest_manager.entries, force=force_restore)
+        manifest_manager.save() # Save translated_html
+        logger.info(f"Restoration complete. {restore_success} entries validated.")
 
-        backfill_llm_client = None
-        should_close_client = False
-        
-        if 'llm_client' in locals() and llm_client:
-             backfill_llm_client = llm_client
-        elif api_key and not args.skip_translation:
-             # This case shouldn't happen because if not skip, we key llm_client above.
-             # But if skip_translation is True, we might still want repair?
-             # For now, let's only enable repair if translation occurred or if we explicitly create one.
-             # User said: "LLM features may fail" if no key.
-             pass
-             
-        # Initialization
-        backfiller = BackfillEngine(llm_client=backfill_llm_client)
+        # 6. Backfill (Pure Injection)
+        logger.info("Injecting content into EPUB structure...")
+        backfiller = BackfillEngine() # Pure injection, no dependencies
         updated_structure = await backfiller.backfill(structure, manifest_manager.entries, mode=args.mode)
         
-        # 6. Assembly - Pass original EPUB for TOC preservation
+        # 7. Assembly - Pass original EPUB for TOC preservation
         builder = BilingualBuilder(work["root"], original_epub_path=input_path)
         
         if args.mode == "bilingual":
@@ -143,7 +138,7 @@ async def run_pipeline(args):
         
         logger.info(f"Pipeline completed! Output: {created_epub}")
         
-        if 'llm_client' in locals() and llm_client:
+        if llm_client:
             await llm_client.close()
         
     except EpubTranslatorError as e:
@@ -162,6 +157,7 @@ def main():
     parser.add_argument("--model", default=None, help="LLM Model to use (overrides config)")
     parser.add_argument("--bilingual", action="store_true", help="Output bilingual version (default is target language only)")
     parser.add_argument("--skip-translation", action="store_true", help="Skip LLM translation (for testing)")
+    parser.add_argument("--force-restore", action="store_true", help="Force re-run format restoration/repair even if translated_html exists")
     parser.add_argument("--force-clean", action="store_true", help="Force re-clean EPUB even if book_structure exists")
     
     args = parser.parse_args()