eee9f1bbdaa88fa4fde7c3c8096a656804baf9e1,tests/test_tokenizers.py,TestTokenizer,test_tokenize_sentence,#TestTokenizer#,19
Before Change
tokenizer = Tokenizer("english")
words = tokenizer.to_words("I am a very nice sentence with comma, but..")
expected = [
"I", "am", "a", "very", "nice", "sentence",
"with", "comma", ",", "but.."
]
self.assertEqual(expected, words)
def test_tokenize_paragraph(self):
tokenizer = Tokenizer("english")
After Change
tokenizer = Tokenizer("english")
words = tokenizer.to_words("I am a very nice sentence with comma, but..")
expected = (
"I", "am", "a", "very", "nice", "sentence",
"with", "comma",
)
self.assertEqual(expected, words)
def test_tokenize_paragraph(self):
tokenizer = Tokenizer("english")
In pattern: SUPERPATTERN
Frequency: 4
Non-data size: 4
Instances
Project Name: miso-belica/sumy
Commit Name: eee9f1bbdaa88fa4fde7c3c8096a656804baf9e1
Time: 2013-05-21
Author: miso.belica@gmail.com
File Name: tests/test_tokenizers.py
Class Name: TestTokenizer
Method Name: test_tokenize_sentence
Project Name: okfn-brasil/serenata-de-amor
Commit Name: cef99445ab551931fed507518b85034b97c946ee
Time: 2016-11-09
Author: cuducos@gmail.com
File Name: src/search_suspect_places.py
Class Name:
Method Name: write_csv
Project Name: google-research/google-research
Commit Name: 0511917400844ea3182db8c4741efc1049a72b15
Time: 2021-04-02
Author: 57083372+ofirgeri@users.noreply.github.com
File Name: private_sampling/experiments.py
Class Name:
Method Name:
Project Name: IDSIA/sacred
Commit Name: 15c7e996c8b228713becc69cb678885d56e37e7a
Time: 2015-03-01
Author: qwlouse@gmail.com
File Name: sacred/config/__init__.py
Class Name:
Method Name: