port test.py and test_chinese.py to pytest

This commit is contained in:
Rob Speer 2018-06-01 16:33:06 -04:00
parent aa91e1f291
commit 863d5be522
3 changed files with 130 additions and 161 deletions

View File

@ -1,5 +1,2 @@
[nosetests]
verbosity=2
with-doctest=1
with-coverage=0
cover-package=wordfreq
[aliases]
test=pytest

View File

@ -2,57 +2,51 @@ from wordfreq import (
word_frequency, available_languages, cB_to_freq,
top_n_list, random_words, random_ascii_words, tokenize, lossy_tokenize
)
from nose.tools import (
eq_, assert_almost_equal, assert_greater, raises, assert_not_equal
)
import pytest
def test_freq_examples():
# Stopwords are most common in the correct language
assert_greater(word_frequency('the', 'en'),
word_frequency('de', 'en'))
assert_greater(word_frequency('de', 'es'),
word_frequency('the', 'es'))
assert word_frequency('the', 'en') > word_frequency('de', 'en')
assert word_frequency('de', 'es') > word_frequency('the', 'es')
# We get word frequencies from the 'large' list when available
assert_greater(word_frequency('infrequency', 'en'), 0.)
assert word_frequency('infrequency', 'en') > 0.
def test_languages():
# Make sure we get all the languages when looking for the default
# 'best' wordlist
avail = available_languages()
assert_greater(len(avail), 32)
assert len(avail) > 32
# 'small' covers the same languages, but with some different lists
avail_small = available_languages('small')
eq_(len(avail_small), len(avail))
assert_not_equal(avail_small, avail)
assert len(avail_small) == len(avail)
assert avail_small != avail
# 'combined' is the same as 'small'
avail_old_name = available_languages('combined')
eq_(avail_old_name, avail_small)
assert avail_old_name == avail_small
# 'large' covers fewer languages
avail_large = available_languages('large')
assert_greater(len(avail_large), 12)
assert_greater(len(avail), len(avail_large))
assert len(avail_large) > 12
assert len(avail) > len(avail_large)
# Look up the digit '2' in the main word list for each language
for lang in avail:
assert_greater(word_frequency('2', lang), 0, lang)
assert word_frequency('2', lang) > 0
# Make up a weirdly verbose language code and make sure
# we still get it
new_lang_code = '%s-001-x-fake-extension' % lang.upper()
assert_greater(word_frequency('2', new_lang_code), 0, new_lang_code)
assert word_frequency('2', new_lang_code) > 0
def test_minimums():
eq_(word_frequency('esquivalience', 'en'), 0)
eq_(word_frequency('esquivalience', 'en', minimum=1e-6), 1e-6)
eq_(word_frequency('the', 'en', minimum=1), 1)
assert word_frequency('esquivalience', 'en') == 0
assert word_frequency('esquivalience', 'en', minimum=1e-6) == 1e-6
assert word_frequency('the', 'en', minimum=1) == 1
def test_most_common_words():
@ -65,141 +59,135 @@ def test_most_common_words():
"""
return top_n_list(lang, 1)[0]
eq_(get_most_common('ar'), 'في')
eq_(get_most_common('de'), 'die')
eq_(get_most_common('en'), 'the')
eq_(get_most_common('es'), 'de')
eq_(get_most_common('fr'), 'de')
eq_(get_most_common('it'), 'di')
eq_(get_most_common('ja'), '')
eq_(get_most_common('nl'), 'de')
eq_(get_most_common('pl'), 'w')
eq_(get_most_common('pt'), 'de')
eq_(get_most_common('ru'), 'в')
eq_(get_most_common('tr'), 'bir')
eq_(get_most_common('zh'), '')
assert get_most_common('ar') == 'في'
assert get_most_common('de') == 'die'
assert get_most_common('en') == 'the'
assert get_most_common('es') == 'de'
assert get_most_common('fr') == 'de'
assert get_most_common('it') == 'di'
assert get_most_common('ja') == ''
assert get_most_common('nl') == 'de'
assert get_most_common('pl') == 'w'
assert get_most_common('pt') == 'de'
assert get_most_common('ru') == 'в'
assert get_most_common('tr') == 'bir'
assert get_most_common('zh') == ''
def test_language_matching():
freq = word_frequency('', 'zh')
eq_(word_frequency('', 'zh-TW'), freq)
eq_(word_frequency('', 'zh-CN'), freq)
eq_(word_frequency('', 'zh-Hant'), freq)
eq_(word_frequency('', 'zh-Hans'), freq)
eq_(word_frequency('', 'yue-HK'), freq)
eq_(word_frequency('', 'cmn'), freq)
assert word_frequency('', 'zh-TW') == freq
assert word_frequency('', 'zh-CN') == freq
assert word_frequency('', 'zh-Hant') == freq
assert word_frequency('', 'zh-Hans') == freq
assert word_frequency('', 'yue-HK') == freq
assert word_frequency('', 'cmn') == freq
def test_cB_conversion():
eq_(cB_to_freq(0), 1.)
assert_almost_equal(cB_to_freq(-100), 0.1)
assert_almost_equal(cB_to_freq(-600), 1e-6)
assert cB_to_freq(0) == 1.
assert cB_to_freq(-100) == pytest.approx(0.1)
assert cB_to_freq(-600) == pytest.approx(1e-6)
@raises(ValueError)
def test_failed_cB_conversion():
cB_to_freq(1)
with pytest.raises(ValueError):
cB_to_freq(1)
def test_tokenization():
# We preserve apostrophes within words, so "can't" is a single word in the
# data
eq_(tokenize("I don't split at apostrophes, you see.", 'en'),
['i', "don't", 'split', 'at', 'apostrophes', 'you', 'see'])
assert (
tokenize("I don't split at apostrophes, you see.", 'en')
== ['i', "don't", 'split', 'at', 'apostrophes', 'you', 'see']
)
eq_(tokenize("I don't split at apostrophes, you see.", 'en', include_punctuation=True),
['i', "don't", 'split', 'at', 'apostrophes', ',', 'you', 'see', '.'])
assert (
tokenize("I don't split at apostrophes, you see.", 'en', include_punctuation=True)
== ['i', "don't", 'split', 'at', 'apostrophes', ',', 'you', 'see', '.']
)
# Certain punctuation does not inherently split a word.
eq_(tokenize("Anything is possible at zombo.com", 'en'),
['anything', 'is', 'possible', 'at', 'zombo.com'])
assert (
tokenize("Anything is possible at zombo.com", 'en')
== ['anything', 'is', 'possible', 'at', 'zombo.com']
)
# Splits occur after symbols, and at splitting punctuation such as hyphens.
eq_(tokenize('😂test', 'en'), ['😂', 'test'])
eq_(tokenize("flip-flop", 'en'), ['flip', 'flop'])
eq_(tokenize('this text has... punctuation :)', 'en', include_punctuation=True),
['this', 'text', 'has', '...', 'punctuation', ':)'])
assert tokenize('😂test', 'en') == ['😂', 'test']
assert tokenize("flip-flop", 'en') == ['flip', 'flop']
assert (
tokenize('this text has... punctuation :)', 'en', include_punctuation=True)
== ['this', 'text', 'has', '...', 'punctuation', ':)']
)
# Multi-codepoint emoji sequences such as 'medium-skinned woman with headscarf'
# and 'David Bowie' stay together, because our Unicode segmentation algorithm
# is up to date
eq_(tokenize('emoji test 🧕🏽', 'en'), ['emoji', 'test', '🧕🏽'])
eq_(tokenize("👨‍🎤 Planet Earth is blue, and there's nothing I can do 🌎🚀", 'en'),
['👨‍🎤', 'planet', 'earth', 'is', 'blue', 'and', "there's",
'nothing', 'i', 'can', 'do', '🌎', '🚀'])
assert tokenize('emoji test 🧕🏽', 'en') == ['emoji', 'test', '🧕🏽']
assert (
tokenize("👨‍🎤 Planet Earth is blue, and there's nothing I can do 🌎🚀", 'en')
== ['👨‍🎤', 'planet', 'earth', 'is', 'blue', 'and', "there's",
'nothing', 'i', 'can', 'do', '🌎', '🚀']
)
# Water wave, surfer, flag of California (indicates ridiculously complete support
# for Unicode 10 and Emoji 5.0)
eq_(tokenize("Surf's up 🌊🏄🏴󠁵󠁳󠁣󠁡󠁿'",'en'),
["surf's", "up", "🌊", "🏄", "🏴󠁵󠁳󠁣󠁡󠁿"])
assert tokenize("Surf's up 🌊🏄🏴󠁵󠁳󠁣󠁡󠁿'",'en') == ["surf's", "up", "🌊", "🏄", "🏴󠁵󠁳󠁣󠁡󠁿"]
def test_casefolding():
eq_(tokenize('WEISS', 'de'), ['weiss'])
eq_(tokenize('weiß', 'de'), ['weiss'])
eq_(tokenize('İstanbul', 'tr'), ['istanbul'])
eq_(tokenize('SIKISINCA', 'tr'), ['sıkısınca'])
assert tokenize('WEISS', 'de') == ['weiss']
assert tokenize('weiß', 'de') == ['weiss']
assert tokenize('İstanbul', 'tr') == ['istanbul']
assert tokenize('SIKISINCA', 'tr') == ['sıkısınca']
def test_number_smashing():
eq_(tokenize('"715 - CRΣΣKS" by Bon Iver', 'en'),
['715', 'crσσks', 'by', 'bon', 'iver'])
eq_(lossy_tokenize('"715 - CRΣΣKS" by Bon Iver', 'en'),
['000', 'crσσks', 'by', 'bon', 'iver'])
eq_(lossy_tokenize('"715 - CRΣΣKS" by Bon Iver', 'en', include_punctuation=True),
['"', '000', '-', 'crσσks', '"', 'by', 'bon', 'iver'])
eq_(lossy_tokenize('1', 'en'), ['1'])
eq_(lossy_tokenize('3.14', 'en'), ['0.00'])
eq_(lossy_tokenize('24601', 'en'), ['00000'])
eq_(word_frequency('24601', 'en'), word_frequency('90210', 'en'))
assert tokenize('"715 - CRΣΣKS" by Bon Iver', 'en') == ['715', 'crσσks', 'by', 'bon', 'iver']
assert lossy_tokenize('"715 - CRΣΣKS" by Bon Iver', 'en') == ['000', 'crσσks', 'by', 'bon', 'iver']
assert (
lossy_tokenize('"715 - CRΣΣKS" by Bon Iver', 'en', include_punctuation=True)
== ['"', '000', '-', 'crσσks', '"', 'by', 'bon', 'iver']
)
assert lossy_tokenize('1', 'en') == ['1']
assert lossy_tokenize('3.14', 'en') == ['0.00']
assert lossy_tokenize('24601', 'en') == ['00000']
assert word_frequency('24601', 'en') == word_frequency('90210', 'en')
def test_phrase_freq():
ff = word_frequency("flip-flop", 'en')
assert_greater(ff, 0)
assert_almost_equal(
1.0 / ff,
1.0 / word_frequency('flip', 'en') + 1.0 / word_frequency('flop', 'en')
)
assert ff > 0
phrase_freq = 1.0 / word_frequency('flip', 'en') + 1.0 / word_frequency('flop', 'en')
assert 1.0 / ff == pytest.approx(phrase_freq)
def test_not_really_random():
# If your xkcd-style password comes out like this, maybe you shouldn't
# use it
eq_(random_words(nwords=4, lang='en', bits_per_word=0),
'the the the the')
assert random_words(nwords=4, lang='en', bits_per_word=0) == 'the the the the'
# This not only tests random_ascii_words, it makes sure we didn't end
# up with 'eos' as a very common Japanese word
eq_(random_ascii_words(nwords=4, lang='ja', bits_per_word=0),
'1 1 1 1')
assert random_ascii_words(nwords=4, lang='ja', bits_per_word=0) == '1 1 1 1'
@raises(ValueError)
def test_not_enough_ascii():
random_ascii_words(lang='zh', bits_per_word=14)
with pytest.raises(ValueError):
random_ascii_words(lang='zh', bits_per_word=14)
def test_arabic():
# Remove tatweels
eq_(
tokenize('متــــــــعب', 'ar'),
['متعب']
)
assert tokenize('متــــــــعب', 'ar') == ['متعب']
# Remove combining marks
eq_(
tokenize('حَرَكَات', 'ar'),
['حركات']
)
assert tokenize('حَرَكَات', 'ar') == ['حركات']
eq_(
tokenize('\ufefb', 'ar'), # An Arabic ligature...
['\u0644\u0627'] # ...that is affected by NFKC normalization
)
# An Arabic ligature that is affected by NFKC normalization
assert tokenize('\ufefb', 'ar') == ['\u0644\u0627']
def test_ideographic_fallback():
@ -207,29 +195,28 @@ def test_ideographic_fallback():
#
# More complex examples like this, involving the multiple scripts of Japanese,
# are in test_japanese.py.
eq_(tokenize('中国文字', 'en'), ['中国文字'])
assert tokenize('中国文字', 'en') == ['中国文字']
def test_other_languages():
# Test that we leave Thai letters stuck together. If we had better Thai support,
# we would actually split this into a three-word phrase.
eq_(tokenize('การเล่นดนตรี', 'th'), ['การเล่นดนตรี'])
eq_(tokenize('"การเล่นดนตรี" means "playing music"', 'en'),
['การเล่นดนตรี', 'means', 'playing', 'music'])
assert tokenize('การเล่นดนตรี', 'th') == ['การเล่นดนตรี']
assert tokenize('"การเล่นดนตรี" means "playing music"', 'en') == ['การเล่นดนตรี', 'means', 'playing', 'music']
# Test Khmer, a script similar to Thai
eq_(tokenize('សូមស្វាគមន៍', 'km'), ['សូមស្វាគមន៍'])
assert tokenize('សូមស្វាគមន៍', 'km') == ['សូមស្វាគមន៍']
# Test Hindi -- tokens split where there are spaces, and not where there aren't
eq_(tokenize('हिन्दी विक्षनरी', 'hi'), ['हिन्दी', 'विक्षनरी'])
assert tokenize('हिन्दी विक्षनरी', 'hi') == ['हिन्दी', 'विक्षनरी']
# Remove vowel points in Hebrew
eq_(tokenize('דֻּגְמָה', 'he'), ['דגמה'])
assert tokenize('דֻּגְמָה', 'he') == ['דגמה']
# Deal with commas, cedillas, and I's in Turkish
eq_(tokenize('kișinin', 'tr'), ['kişinin'])
eq_(tokenize('KİȘİNİN', 'tr'), ['kişinin'])
assert tokenize('kișinin', 'tr') == ['kişinin']
assert tokenize('KİȘİNİN', 'tr') == ['kişinin']
# Deal with cedillas that should be commas-below in Romanian
eq_(tokenize('acelaşi', 'ro'), ['același'])
eq_(tokenize('ACELAŞI', 'ro'), ['același'])
assert tokenize('acelaşi', 'ro') == ['același']
assert tokenize('ACELAŞI', 'ro') == ['același']

View File

@ -1,5 +1,5 @@
from nose.tools import eq_, assert_almost_equal, assert_greater
from wordfreq import tokenize, word_frequency
import pytest
def test_tokens():
@ -17,64 +17,49 @@ def test_tokens():
# His name breaks into five pieces, with the only piece staying together
# being the one that means 'Bart'. The dot is not included as a token.
eq_(
tokenize(hobart, 'zh'),
['', '', '', '', '巴特']
)
assert tokenize(hobart, 'zh') == ['', '', '', '', '巴特']
eq_(
tokenize(fact_simplified, 'zh'),
[
# he / is / history / in / #6 / counter for people
'', '', '历史', '', '第六', '',
# during / term of office / in / die
'', '任期', '', '去世',
# of / U.S. / deputy / president
'', '美国', '', '总统'
]
)
assert tokenize(fact_simplified, 'zh') == [
# he / is / history / in / #6 / counter for people
'', '', '历史', '', '第六', '',
# during / term of office / in / die
'', '任期', '', '去世',
# of / U.S. / deputy / president
'', '美国', '', '总统'
]
# Jieba's original tokenizer knows a lot of names, it seems.
eq_(
tokenize(hobart, 'zh', external_wordlist=True),
['加勒特', '霍巴特']
)
assert tokenize(hobart, 'zh', external_wordlist=True) == ['加勒特', '霍巴特']
# We get almost the same tokens from the sentence using Jieba's own
# wordlist, but it tokenizes "in history" as two words and
# "sixth person" as one.
eq_(
tokenize(fact_simplified, 'zh', external_wordlist=True),
[
# he / is / history / in / sixth person
'', '', '历史', '', '第六位',
# during / term of office / in / die
'', '任期', '', '去世',
# of / U.S. / deputy / president
'', '美国', '', '总统'
]
)
assert tokenize(fact_simplified, 'zh', external_wordlist=True) == [
# he / is / history / in / sixth person
'', '', '历史', '', '第六位',
# during / term of office / in / die
'', '任期', '', '去世',
# of / U.S. / deputy / president
'', '美国', '', '总统'
]
# Check that Traditional Chinese works at all
assert_greater(word_frequency(fact_traditional, 'zh'), 0)
assert word_frequency(fact_traditional, 'zh') > 0
# You get the same token lengths if you look it up in Traditional Chinese,
# but the words are different
simp_tokens = tokenize(fact_simplified, 'zh', include_punctuation=True)
trad_tokens = tokenize(fact_traditional, 'zh', include_punctuation=True)
eq_(''.join(simp_tokens), fact_simplified)
eq_(''.join(trad_tokens), fact_traditional)
assert ''.join(simp_tokens) == fact_simplified
assert ''.join(trad_tokens) == fact_traditional
simp_lengths = [len(token) for token in simp_tokens]
trad_lengths = [len(token) for token in trad_tokens]
eq_(simp_lengths, trad_lengths)
assert simp_lengths == trad_lengths
def test_combination():
xiexie_freq = word_frequency('谢谢', 'zh') # "Thanks"
assert_almost_equal(
word_frequency('谢谢谢谢', 'zh'),
xiexie_freq / 20
)
assert word_frequency('谢谢谢谢', 'zh') == pytest.approx(xiexie_freq / 20)
def test_alternate_codes():
@ -83,12 +68,12 @@ def test_alternate_codes():
tokens = ['谢谢', '谢谢']
# Code with a region attached
eq_(tokenize('谢谢谢谢', 'zh-CN'), tokens)
assert tokenize('谢谢谢谢', 'zh-CN') == tokens
# Over-long codes for Chinese
eq_(tokenize('谢谢谢谢', 'chi'), tokens)
eq_(tokenize('谢谢谢谢', 'zho'), tokens)
assert tokenize('谢谢谢谢', 'chi') == tokens
assert tokenize('谢谢谢谢', 'zho') == tokens
# Separate codes for Mandarin and Cantonese
eq_(tokenize('谢谢谢谢', 'cmn'), tokens)
eq_(tokenize('谢谢谢谢', 'yue'), tokens)
assert tokenize('谢谢谢谢', 'cmn') == tokens
assert tokenize('谢谢谢谢', 'yue') == tokens