Spaces:
Sleeping
Sleeping
Commit
·
f48820b
1
Parent(s):
09fe356
simplest version
Browse files- documents_prep.py +0 -2
documents_prep.py
CHANGED
|
@@ -59,12 +59,10 @@ def chunk_table_by_rows(table_data, doc_id, max_rows=5):
|
|
| 59 |
table_title = table_data.get('table_title', '')
|
| 60 |
section = table_data.get('section', '')
|
| 61 |
|
| 62 |
-
# NORMALIZE document ID
|
| 63 |
doc_id = normalize_doc_id(doc_id)
|
| 64 |
|
| 65 |
table_num_clean = str(table_num).strip()
|
| 66 |
|
| 67 |
-
# Create section-aware identifier
|
| 68 |
import re
|
| 69 |
if 'приложени' in section.lower():
|
| 70 |
appendix_match = re.search(r'приложени[еия]\s*(\d+|[а-яА-Я])', section.lower())
|
|
|
|
| 59 |
table_title = table_data.get('table_title', '')
|
| 60 |
section = table_data.get('section', '')
|
| 61 |
|
|
|
|
| 62 |
doc_id = normalize_doc_id(doc_id)
|
| 63 |
|
| 64 |
table_num_clean = str(table_num).strip()
|
| 65 |
|
|
|
|
| 66 |
import re
|
| 67 |
if 'приложени' in section.lower():
|
| 68 |
appendix_match = re.search(r'приложени[еия]\s*(\d+|[а-яА-Я])', section.lower())
|