edd74909eb1cef75e88e50af6fee48bb6615b7fb,my/tokenize.py,,main,#,47

Before Change



def main(unused_argv):
  for line in STDIN:
    STDOUT.write("\n%s" % line)
    line = line.rstrip("\n")
    end = 0
    for match in TOKEN.finditer(line):
      if match.start() != end:
        unmatched = line[end:match.start()]
        STDOUT.write("Unmatched: %s\n" % repr(unmatched))
      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

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:
      STDERR.write("%s\n" % line)
  return


if __name__ == "__main__":
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 6

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: pyinstaller/pyinstaller
Commit Name: 5ae5a2d4af15e570a74bc4541ac153ad12cddec5
Time: 2021-01-05
Author: dan@yeaw.me
File Name: PyInstaller/hooks/hook-gi.repository.GdkPixbuf.py
Class Name:
Method Name:


Project Name: comic/grand-challenge.org
Commit Name: 4d9d2a1fc4e0d9289000a235340235802d51a97a
Time: 2021-02-12
Author: 57257130+MikeOverkamp-diag@users.noreply.github.com
File Name: app/grandchallenge/cases/image_builders/dicom.py
Class Name:
Method Name: _create_itk_from_dcm