edd74909eb1cef75e88e50af6fee48bb6615b7fb,my/tokenize.py,,main,#,47
Before Change
kind_token = GetToken(match)
STDOUT.write("token %6s: %s\n" % kind_token)
end = match.end()
if end < len(line):
STDOUT.write("Unmatched: %s\n" % repr(line[end:]))
return
if __name__ == "__main__":
After Change
tokens = list(Tokenize(line))
if not tokens:
continue
if all(kind in ("native", "punct", "space") for (kind, token) in tokens):
STDOUT.write("%s\n" % " ".join(token for (kind, token) in tokens
if kind == "native"))
else:
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 4
Instances Project Name: google/language-resources
Commit Name: edd74909eb1cef75e88e50af6fee48bb6615b7fb
Time: 2016-05-26
Author: mjansche@google.com
File Name: my/tokenize.py
Class Name:
Method Name: main
Project Name: google/language-resources
Commit Name: 1a0c8ee08d03397b3e08d6421427afdcbde88945
Time: 2016-06-12
Author: mjansche@google.com
File Name: my/grapheme_cluster.py
Class Name:
Method Name:
Project Name: tech-srl/code2vec
Commit Name: 98a0b1b840a75f4cef7a4c3a0fefe354df4a1595
Time: 2019-04-03
Author: eladnah@gmail.com
File Name: common.py
Class Name: common
Method Name: save_word2vec_file