distinct
Browse files- tokenizer_13a.py +1 -0
tokenizer_13a.py
CHANGED
@@ -68,6 +68,7 @@ class TokenizerRegexp(BaseTokenizer):
|
|
68 |
# return ' '.join(line.split())
|
69 |
# This line is changed with regards to the original tokenizer (seen above) to return individual words
|
70 |
print(line)
|
|
|
71 |
return line.split()
|
72 |
|
73 |
|
|
|
68 |
# return ' '.join(line.split())
|
69 |
# This line is changed with regards to the original tokenizer (seen above) to return individual words
|
70 |
print(line)
|
71 |
+
print("1:", line.split())
|
72 |
return line.split()
|
73 |
|
74 |
|