Spaces:
Running
Running
Update parser/section_extractor.py
Browse files- parser/section_extractor.py +19 -5
parser/section_extractor.py
CHANGED
|
@@ -1,19 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
def extract_sections(texts: list):
|
| 2 |
"""
|
| 3 |
-
تقسيم النصوص إلى أقسام وفصول
|
| 4 |
"""
|
| 5 |
sections = []
|
| 6 |
current = {"name": "", "texts": []}
|
| 7 |
|
| 8 |
for t in texts:
|
| 9 |
-
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
if current["texts"] or current["name"]:
|
| 12 |
sections.append(current)
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
| 14 |
else:
|
| 15 |
-
|
|
|
|
| 16 |
|
|
|
|
| 17 |
if current["texts"] or current["name"]:
|
| 18 |
sections.append(current)
|
| 19 |
|
|
|
|
| 1 |
+
# parser/section_extractor.py
|
| 2 |
+
from helpers.utils import is_section, normalize_digits
|
| 3 |
+
|
| 4 |
def extract_sections(texts: list):
|
| 5 |
"""
|
| 6 |
+
تقسيم النصوص إلى أقسام وفصول باستخدام الأنماط الذكية
|
| 7 |
"""
|
| 8 |
sections = []
|
| 9 |
current = {"name": "", "texts": []}
|
| 10 |
|
| 11 |
for t in texts:
|
| 12 |
+
if not isinstance(t, str):
|
| 13 |
+
continue
|
| 14 |
+
|
| 15 |
+
t_norm = normalize_digits(t.strip())
|
| 16 |
+
|
| 17 |
+
# هل السطر عنوان قسم أو فصل؟
|
| 18 |
+
if is_section(t_norm):
|
| 19 |
+
# لو يوجد قسم سابق → نحفظه
|
| 20 |
if current["texts"] or current["name"]:
|
| 21 |
sections.append(current)
|
| 22 |
+
|
| 23 |
+
# نبدأ قسم/فصل جديد
|
| 24 |
+
current = {"name": t_norm, "texts": []}
|
| 25 |
+
|
| 26 |
else:
|
| 27 |
+
# السطور التابعة للقسم الحالي
|
| 28 |
+
current["texts"].append(t_norm)
|
| 29 |
|
| 30 |
+
# إضافة آخر قسم
|
| 31 |
if current["texts"] or current["name"]:
|
| 32 |
sections.append(current)
|
| 33 |
|