def parse(lang_sample):
"""tally word popularity using novel extracts, etc"""
words = words_from_archive(lang_sample, include_dups=True)
counts = zero_default_dict()
for word in words:
counts[word] += 1
return set(words), counts
def parse(lang_sample):
"""tally word popularity using novel extracts, etc"""
words = words_from_archive(lang_sample, include_dups=True)
counts = zero_default_dict()
for word in words:
counts[word] += 1
return set(words), counts
def parse(lang_sample, file_format='bz'):
from autocorrect.utils import words_from_archive, words_from_txt, \
zero_default_dict
"""tally word popularity using novel extracts, etc"""
if file_format == 'bz':
words = words_from_archive(lang_sample, include_dups=True)
elif file_format == 'txt':
words = words_from_txt(lang_sample)
counts = zero_default_dict()
for word in words:
counts[word] += 1
return set(words), counts