iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 09:21:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

automatically closes input file in tokenize_file

Browse Source
This commit is contained in:
Joshua Chin 2015-06-17 11:42:34 -04:00
parent 2fbfbfcc98
commit 7fc0ba9092
1 changed files with 13 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
wordfreq_builder/wordfreq_builder/tokenizers.py
View File

@ -62,18 +62,19 @@ def tokenize_file(in_filename, out_prefix, tokenizer, line_reader=last_tab):
to mark the token boundaries.
"""
out_files = {}
for line in open(in_filename, encoding='utf-8'):
text = line_reader(line)
tokens, language = tokenizer(text)
tokenized = '\n'.join(tokens)
if language is not None:
out_filename = '%s.%s.txt' % (out_prefix, language)
if out_filename in out_files:
out_file = out_files[out_filename]
else:
out_file = open(out_filename, 'w', encoding='utf-8')
out_files[out_filename] = out_file
print(tokenized, file=out_file)
with open(in_filename, encoding='utf-8') as in_file:
for line in in_file:
text = line_reader(line)
tokens, language = tokenizer(text)
tokenized = '\n'.join(tokens)
if language is not None:
out_filename = '%s.%s.txt' % (out_prefix, language)
if out_filename in out_files:
out_file = out_files[out_filename]
else:
out_file = open(out_filename, 'w', encoding='utf-8')
out_files[out_filename] = out_file
print(tokenized, file=out_file)
for out_file in out_files.values():
out_file.close()