Spaces:
Sleeping
Sleeping
Delete utilities.py
Browse files- utilities.py +0 -20
utilities.py
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 1 |
-
import wikipedia
|
| 2 |
-
import re
|
| 3 |
-
|
| 4 |
-
def clean_and_truncate(text, max_chars=2000):
|
| 5 |
-
"""Clean text and truncate to avoid excessive length."""
|
| 6 |
-
text = re.sub(r'\n{2,}', '\n', text) # remove extra newlines
|
| 7 |
-
return text[:max_chars] + ("..." if len(text) > max_chars else "")
|
| 8 |
-
|
| 9 |
-
def extract_year_range(text, start_year, end_year):
|
| 10 |
-
"""Extract only content that mentions years in a certain range."""
|
| 11 |
-
pattern = rf"\b(19[0-9]{{2}}|20[0-2][0-9])\b"
|
| 12 |
-
matches = re.finditer(pattern, text)
|
| 13 |
-
filtered_paragraphs = []
|
| 14 |
-
for match in matches:
|
| 15 |
-
year = int(match.group())
|
| 16 |
-
if start_year <= year <= end_year:
|
| 17 |
-
# capture paragraph
|
| 18 |
-
para = text[max(0, text.rfind('\n', 0, match.start())) : text.find('\n', match.end())]
|
| 19 |
-
filtered_paragraphs.append(para.strip())
|
| 20 |
-
return "\n\n".join(filtered_paragraphs)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|