70 lines
2.3 KiB
Python
70 lines
2.3 KiB
Python
import argparse
|
|
import sys
|
|
import os
|
|
from pathlib import Path
|
|
|
|
# Add project root to sys.path
|
|
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
|
|
|
|
from src.preprocessing.epub_cleaner import EpubCleaner
|
|
from src.preprocessing.text_extractor import FineGrainedExtractor
|
|
from src.translation.manifest_manager import ManifestManager
|
|
from src.common.data_model import BookStructure
|
|
from src.common.utils import setup_logger, ensure_directory
|
|
from src.common.exceptions import EpubTranslatorError
|
|
from src.common.paths import get_work_dirs
|
|
|
|
logger = setup_logger("pipeline_preprocess")
|
|
|
|
def run_preprocess(args):
|
|
input_path = Path(args.input_epub)
|
|
if not input_path.exists():
|
|
logger.error(f"Input file not found: {input_path}")
|
|
sys.exit(1)
|
|
|
|
work = get_work_dirs(input_path)
|
|
ensure_directory(work["root"])
|
|
|
|
structure_path = work["structure"]
|
|
manifest_path = work["manifest"]
|
|
|
|
try:
|
|
# 1. Clean / Load Structure
|
|
if structure_path.exists() and not args.force:
|
|
logger.info(f"Reusing existing structure: {structure_path}")
|
|
structure = BookStructure.load(structure_path)
|
|
else:
|
|
logger.info("Cleaning EPUB...")
|
|
cleaner = EpubCleaner(input_path, work["root"])
|
|
structure_path = cleaner.clean()
|
|
structure = BookStructure.load(structure_path)
|
|
|
|
# 2. Extract Text
|
|
logger.info("Extracting text segments...")
|
|
extractor = FineGrainedExtractor()
|
|
entries = extractor.extract(structure)
|
|
|
|
# 3. Update Manifest
|
|
logger.info(f"Updating manifest: {manifest_path}")
|
|
manager = ManifestManager(manifest_path)
|
|
manager.load()
|
|
manager.add_entries(entries)
|
|
manager.save()
|
|
|
|
logger.info("Preprocessing complete.")
|
|
|
|
except EpubTranslatorError as e:
|
|
logger.error(f"Preprocessing failed: {e}")
|
|
sys.exit(1)
|
|
except Exception as e:
|
|
logger.critical(f"Unexpected error: {e}")
|
|
sys.exit(1)
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser(description="Step 1: Preprocessing (Clean + Extract)")
|
|
parser.add_argument("input_epub", help="Path to input EPUB")
|
|
parser.add_argument("--force", action="store_true", help="Force re-clean")
|
|
|
|
args = parser.parse_args()
|
|
run_preprocess(args)
|