4b21300999e11ba6f91952c05a936ccec0673e2e,nltk/tokenize/treebank.py,TreebankWordTokenizer,span_tokenize,#TreebankWordTokenizer#Any#,147
Before Change
for word_token in self.tokenize(text):
if word_token in ("``", """"):
orig_idx = text.find(word_token, ix)
quote_idx = text.find(""", ix)
if orig_idx < 0:
real_token = """
elif quote_idx < 0:
real_token = word_token
elif orig_idx < quote_idx:
real_token = word_token
else:
real_token = """
else:
real_token = word_token
After Change
else:
tokens = raw_tokens
return align_tokens(tokens, text)
class TreebankWordDetokenizer(TokenizerI):
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 5
Instances
Project Name: nltk/nltk
Commit Name: 4b21300999e11ba6f91952c05a936ccec0673e2e
Time: 2017-11-29
Author: lyyb46@gmail.com
File Name: nltk/tokenize/treebank.py
Class Name: TreebankWordTokenizer
Method Name: span_tokenize
Project Name: commonsense/conceptnet5
Commit Name: 1e25b7fb1b442138e09a91e84bac79feffd2175a
Time: 2013-05-28
Author: rob@luminoso.com
File Name: cnet5_index_builder/cnet5-data/wiktionary_ja/ja_read_wiktionary.py
Class Name: FindTranslations
Method Name: handleLine
Project Name: andresriancho/w3af
Commit Name: 25cbfe064306473f81efc9c575d164d23e365422
Time: 2018-04-13
Author: self@andresriancho.com
File Name: w3af/plugins/crawl/robots_txt.py
Class Name: robots_txt
Method Name: crawl