File size: 4,425 Bytes
cc0b62b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
# -*- coding: utf-8 -*-
""" Tokenization tests.
"""
from __future__ import absolute_import, print_function, division, unicode_literals
import sys
from nose.tools import nottest
from os.path import dirname, abspath
sys.path.append(dirname(dirname(abspath(__file__))))
from torchmoji.tokenizer import tokenize
TESTS_NORMAL = [
('200K words!', ['200', 'K', 'words', '!']),
]
TESTS_EMOJIS = [
('i \U0001f496 you to the moon and back',
['i', '\U0001f496', 'you', 'to', 'the', 'moon', 'and', 'back']),
("i\U0001f496you to the \u2605's and back",
['i', '\U0001f496', 'you', 'to', 'the',
'\u2605', "'", 's', 'and', 'back']),
('~<3~', ['~', '<3', '~']),
('<333', ['<333']),
(':-)', [':-)']),
('>:-(', ['>:-(']),
('\u266b\u266a\u2605\u2606\u2665\u2764\u2661',
['\u266b', '\u266a', '\u2605', '\u2606',
'\u2665', '\u2764', '\u2661']),
]
TESTS_URLS = [
('www.sample.com', ['www.sample.com']),
('http://endless.horse', ['http://endless.horse']),
('https://github.mit.ed', ['https://github.mit.ed']),
]
TESTS_TWITTER = [
('#blacklivesmatter', ['#blacklivesmatter']),
('#99_percent.', ['#99_percent', '.']),
('the#99%', ['the', '#99', '%']),
('@golden_zenith', ['@golden_zenith']),
('@99_percent', ['@99_percent']),
('[email protected]', ['[email protected]']),
]
TESTS_PHONE_NUMS = [
('518)528-0252', ['518', ')', '528', '-', '0252']),
('1200-0221-0234', ['1200', '-', '0221', '-', '0234']),
('1200.0221.0234', ['1200', '.', '0221', '.', '0234']),
]
TESTS_DATETIME = [
('15:00', ['15', ':', '00']),
('2:00pm', ['2', ':', '00', 'pm']),
('9/14/16', ['9', '/', '14', '/', '16']),
]
TESTS_CURRENCIES = [
('517.933\xa3', ['517', '.', '933', '\xa3']),
('$517.87', ['$', '517', '.', '87']),
('1201.6598', ['1201', '.', '6598']),
('120,6', ['120', ',', '6']),
('10,00\u20ac', ['10', ',', '00', '\u20ac']),
('1,000', ['1', ',', '000']),
('1200pesos', ['1200', 'pesos']),
]
TESTS_NUM_SYM = [
('5162f', ['5162', 'f']),
('f5162', ['f', '5162']),
('1203(', ['1203', '(']),
('(1203)', ['(', '1203', ')']),
('1200/', ['1200', '/']),
('1200+', ['1200', '+']),
('1202o-east', ['1202', 'o-east']),
('1200r', ['1200', 'r']),
('1200-1400', ['1200', '-', '1400']),
('120/today', ['120', '/', 'today']),
('today/120', ['today', '/', '120']),
('120/5', ['120', '/', '5']),
("120'/5", ['120', "'", '/', '5']),
('120/5pro', ['120', '/', '5', 'pro']),
("1200's,)", ['1200', "'", 's', ',', ')']),
('120.76.218.207', ['120', '.', '76', '.', '218', '.', '207']),
]
TESTS_PUNCTUATION = [
("don''t", ['don', "''", 't']),
("don'tcha", ["don'tcha"]),
('no?!?!;', ['no', '?', '!', '?', '!', ';']),
('no??!!..', ['no', '??', '!!', '..']),
('a.m.', ['a.m.']),
('.s.u', ['.', 's', '.', 'u']),
('!!i..n__', ['!!', 'i', '..', 'n', '__']),
('lv(<3)w(3>)u Mr.!', ['lv', '(', '<3', ')', 'w', '(', '3',
'>', ')', 'u', 'Mr.', '!']),
('-->', ['--', '>']),
('->', ['-', '>']),
('<-', ['<', '-']),
('<--', ['<', '--']),
('hello (@person)', ['hello', '(', '@person', ')']),
]
def test_normal():
""" Normal/combined usage.
"""
test_base(TESTS_NORMAL)
def test_emojis():
""" Tokenizing emojis/emoticons/decorations.
"""
test_base(TESTS_EMOJIS)
def test_urls():
""" Tokenizing URLs.
"""
test_base(TESTS_URLS)
def test_twitter():
""" Tokenizing hashtags, mentions and emails.
"""
test_base(TESTS_TWITTER)
def test_phone_nums():
""" Tokenizing phone numbers.
"""
test_base(TESTS_PHONE_NUMS)
def test_datetime():
""" Tokenizing dates and times.
"""
test_base(TESTS_DATETIME)
def test_currencies():
""" Tokenizing currencies.
"""
test_base(TESTS_CURRENCIES)
def test_num_sym():
""" Tokenizing combinations of numbers and symbols.
"""
test_base(TESTS_NUM_SYM)
def test_punctuation():
""" Tokenizing punctuation and contractions.
"""
test_base(TESTS_PUNCTUATION)
@nottest
def test_base(tests):
""" Base function for running tests.
"""
for (test, expected) in tests:
actual = tokenize(test)
assert actual == expected, \
"Tokenization of \'{}\' failed, expected: {}, actual: {}"\
.format(test, expected, actual)
|