iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 17:31:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

add tests for Turkish

Browse Source 
Former-commit-id: fc93c8dc9c
This commit is contained in:
Robyn Speer 2015-09-04 16:40:11 -04:00
parent a75a95658b
commit 4704131e13
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
tests/test.py
View File

@ -19,7 +19,7 @@ def test_freq_examples():
def test_languages(): def test_languages():
# Make sure the number of available languages doesn't decrease # Make sure the number of available languages doesn't decrease
avail = available_languages() avail = available_languages()
assert_greater(len(avail), 14) assert_greater(len(avail), 15)
# Laughter is the universal language # Laughter is the universal language
for lang in avail: for lang in avail:
@ -36,7 +36,7 @@ def test_languages():
def test_twitter(): def test_twitter():
avail = available_languages('twitter') avail = available_languages('twitter')
assert_greater(len(avail), 12) assert_greater(len(avail), 14)
for lang in avail: for lang in avail:
assert_greater(word_frequency('rt', lang, 'twitter'), assert_greater(word_frequency('rt', lang, 'twitter'),
@ -68,6 +68,7 @@ def test_most_common_words():
eq_(get_most_common('nl'), 'de') eq_(get_most_common('nl'), 'de')
eq_(get_most_common('pt'), 'de') eq_(get_most_common('pt'), 'de')
eq_(get_most_common('ru'), 'в') eq_(get_most_common('ru'), 'в')
eq_(get_most_common('tr'), 'bir')
eq_(get_most_common('zh'), '的') eq_(get_most_common('zh'), '的')
@ -111,6 +112,8 @@ def test_tokenization():
def test_casefolding(): def test_casefolding():
eq_(tokenize('WEISS', 'de'), ['weiss']) eq_(tokenize('WEISS', 'de'), ['weiss'])
eq_(tokenize('weiß', 'de'), ['weiss']) eq_(tokenize('weiß', 'de'), ['weiss'])
eq_(tokenize('İstanbul', 'tr'), ['istanbul'])
eq_(tokenize('SIKISINCA', 'tr'), ['sıkısınca'])
def test_phrase_freq(): def test_phrase_freq():