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
32 lines
1022 B
Python
32 lines
1022 B
Python
import re
|
|
from src.format_extractor import FormatExtractor
|
|
|
|
extractor = FormatExtractor()
|
|
|
|
cases = [
|
|
("<p>“But what is the goal?” <em>Amodei</em>...</p>", "Quoted text with em"),
|
|
("<p>Q. What is artificial intelligence?</p>", "Simple Q&A"),
|
|
("<p>Text <i>italic</i> followed by dots...</p>", "Italic with trailing dots"),
|
|
]
|
|
|
|
for html, desc in cases:
|
|
print(f"--- Testing: {desc} ---")
|
|
print(f"HTML: {html}")
|
|
clean, text_ph, ph_map, p_type, anchors = extractor.extract(html)
|
|
|
|
# Validation logic from FormatExtractor.extract
|
|
stripped_text = re.sub(r'φ/?[0-9]+φ', '', text_ph)
|
|
stripped_text = re.sub(r'\s+', ' ', stripped_text).strip()
|
|
clean_normalized = re.sub(r'\s+', ' ', clean).strip()
|
|
|
|
print(f"Clean: '{clean_normalized}'")
|
|
print(f"Stripped: '{stripped_text}'")
|
|
print(f"Text ph: '{text_ph}'")
|
|
print(f"Map: {ph_map}")
|
|
|
|
if clean_normalized == stripped_text:
|
|
print("✅ SUCCESS")
|
|
else:
|
|
print("❌ FAILED")
|
|
print()
|