谭凯
7a93c52b42
- Refactor codebase into src/ (preprocessing, translation, assembly) - Add pipeline/ scripts for individual stages - Externalize configuration to config/config.yaml - Fix Cover Image preservation - Update documentation and manuals
75 lines
2.6 KiB
Python
75 lines
2.6 KiB
Python
import sys
|
|
from pathlib import Path
|
|
from bs4 import BeautifulSoup
|
|
from loguru import logger
|
|
|
|
# Add project root to path
|
|
sys.path.insert(0, str(Path(__file__).parent))
|
|
|
|
from src.epub_parser import EPUBParser
|
|
from src.text_processor import TextProcessor
|
|
from src.utils import load_config
|
|
|
|
def debug_nested_structure(epub_path: str):
|
|
config = load_config()
|
|
parser = EPUBParser(epub_path)
|
|
content_items = parser.extract_all_content_items()
|
|
|
|
# Check just one chapter (e.g. Chapter 1)
|
|
target_item = None
|
|
for item in content_items:
|
|
if 'c01' in item['file_name']: # Chapter 1 usually
|
|
target_item = item
|
|
break
|
|
|
|
if not target_item:
|
|
target_item = content_items[2] # Fallback to 3rd item
|
|
|
|
print(f"Checking file: {target_item['file_name']}")
|
|
|
|
soup = BeautifulSoup(target_item['content'], 'html.parser')
|
|
|
|
# Simulate TextProcessor extraction logic
|
|
text_elements = soup.find_all(['p', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
|
|
'blockquote', 'li', 'td'])
|
|
|
|
min_len = config['processing'].get('min_paragraph_length', 30)
|
|
|
|
extracted = []
|
|
|
|
for i, element in enumerate(text_elements):
|
|
# Clean text logic
|
|
clean_text = TextProcessor.clean_element_text(element)
|
|
|
|
is_valid = True
|
|
if len(clean_text) < min_len:
|
|
is_valid = False
|
|
if TextProcessor.is_navigation_element(element):
|
|
is_valid = False
|
|
|
|
if is_valid:
|
|
extracted.append((element, clean_text))
|
|
|
|
# Check for nesting
|
|
# If this element contains other valid extracted elements
|
|
for prev_el, prev_text in extracted[:-1]:
|
|
# Check if current element is inside previous element
|
|
if element in prev_el.descendants:
|
|
print(f"\n⚠️ NESTING DETECTED!")
|
|
print(f" Parent: <{prev_el.name}> {prev_text[:50]}...")
|
|
print(f" Child: <{element.name}> {clean_text[:50]}...")
|
|
|
|
# Check if previous element is inside current element
|
|
if prev_el in element.descendants:
|
|
print(f"\n⚠️ NESTING DETECTED!")
|
|
print(f" Parent: <{element.name}> {clean_text[:50]}...")
|
|
print(f" Child: <{prev_el.name}> {prev_text[:50]}...")
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) < 2:
|
|
print("Usage: python debug_structure.py <epub_file>")
|
|
sys.exit(1)
|
|
|
|
epub_file = sys.argv[1]
|
|
debug_nested_structure(epub_file)
|