Spaces:
Sleeping
Sleeping
Update processDoubles.py
Browse files- processDoubles.py +24 -31
processDoubles.py
CHANGED
|
@@ -1,31 +1,24 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
#
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
i += 1
|
| 26 |
-
else:
|
| 27 |
-
result.append(tokens[i])
|
| 28 |
-
i += 1
|
| 29 |
-
|
| 30 |
-
return ' '.join(result)
|
| 31 |
-
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
|
| 3 |
+
def process_doubles(sentence):
|
| 4 |
+
# Use regex to split 'डबल' followed by numbers/words without space (e.g., "डबलवन" -> "डबल वन")
|
| 5 |
+
sentence = re.sub(r'(ਡਬਲ)(\S+)', r'\1 \2', sentence)
|
| 6 |
+
|
| 7 |
+
tokens = sentence.split()
|
| 8 |
+
result = []
|
| 9 |
+
i = 0
|
| 10 |
+
|
| 11 |
+
while i < len(tokens):
|
| 12 |
+
if tokens[i] == "ਡਬਲ":
|
| 13 |
+
if i + 1 < len(tokens):
|
| 14 |
+
result.append(tokens[i + 1]) # Append the next word/number
|
| 15 |
+
result.append(tokens[i + 1]) # Append the next word/number again to duplicate
|
| 16 |
+
i += 2 # Skip over the next word since it's already processed
|
| 17 |
+
else:
|
| 18 |
+
result.append(tokens[i])
|
| 19 |
+
i += 1
|
| 20 |
+
else:
|
| 21 |
+
result.append(tokens[i])
|
| 22 |
+
i += 1
|
| 23 |
+
|
| 24 |
+
return ' '.join(result)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|