2017-01-12 14:51:20 +00:00
|
|
|
import pytest
|
2020-04-15 11:49:47 +00:00
|
|
|
import numpy
|
2018-07-24 21:38:44 +00:00
|
|
|
from spacy.attrs import IS_ALPHA, IS_DIGIT
|
2020-04-15 11:49:47 +00:00
|
|
|
from spacy.util import OOV_RANK
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2016-09-27 11:22:30 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text1,prob1,text2,prob2", [("NOUN", -1, "opera", -2)])
|
2017-01-12 14:51:20 +00:00
|
|
|
def test_vocab_lexeme_lt(en_vocab, text1, text2, prob1, prob2):
|
|
|
|
"""More frequent is l.t. less frequent"""
|
|
|
|
lex1 = en_vocab[text1]
|
|
|
|
lex1.prob = prob1
|
|
|
|
lex2 = en_vocab[text2]
|
|
|
|
lex2.prob = prob2
|
|
|
|
|
|
|
|
assert lex1 < lex2
|
|
|
|
assert lex2 > lex1
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text1,text2", [("phantom", "opera")])
|
2017-01-12 14:51:20 +00:00
|
|
|
def test_vocab_lexeme_hash(en_vocab, text1, text2):
|
|
|
|
"""Test that lexemes are hashable."""
|
|
|
|
lex1 = en_vocab[text1]
|
|
|
|
lex2 = en_vocab[text2]
|
|
|
|
lexes = {lex1: lex1, lex2: lex2}
|
|
|
|
assert lexes[lex1].orth_ == text1
|
|
|
|
assert lexes[lex2].orth_ == text2
|
|
|
|
|
|
|
|
|
|
|
|
def test_vocab_lexeme_is_alpha(en_vocab):
|
2018-11-27 00:09:36 +00:00
|
|
|
assert en_vocab["the"].flags & (1 << IS_ALPHA)
|
|
|
|
assert not en_vocab["1999"].flags & (1 << IS_ALPHA)
|
|
|
|
assert not en_vocab["hello1"].flags & (1 << IS_ALPHA)
|
2017-01-12 14:51:20 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_vocab_lexeme_is_digit(en_vocab):
|
2018-11-27 00:09:36 +00:00
|
|
|
assert not en_vocab["the"].flags & (1 << IS_DIGIT)
|
|
|
|
assert en_vocab["1999"].flags & (1 << IS_DIGIT)
|
|
|
|
assert not en_vocab["hello1"].flags & (1 << IS_DIGIT)
|
2017-01-12 14:51:20 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_vocab_lexeme_add_flag_auto_id(en_vocab):
|
|
|
|
is_len4 = en_vocab.add_flag(lambda string: len(string) == 4)
|
2018-11-30 16:43:08 +00:00
|
|
|
assert en_vocab["1999"].check_flag(is_len4) is True
|
|
|
|
assert en_vocab["1999"].check_flag(IS_DIGIT) is True
|
|
|
|
assert en_vocab["199"].check_flag(is_len4) is False
|
|
|
|
assert en_vocab["199"].check_flag(IS_DIGIT) is True
|
|
|
|
assert en_vocab["the"].check_flag(is_len4) is False
|
|
|
|
assert en_vocab["dogs"].check_flag(is_len4) is True
|
2017-01-12 14:51:20 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_vocab_lexeme_add_flag_provided_id(en_vocab):
|
|
|
|
is_len4 = en_vocab.add_flag(lambda string: len(string) == 4, flag_id=IS_DIGIT)
|
2018-11-30 16:43:08 +00:00
|
|
|
assert en_vocab["1999"].check_flag(is_len4) is True
|
|
|
|
assert en_vocab["199"].check_flag(is_len4) is False
|
|
|
|
assert en_vocab["199"].check_flag(IS_DIGIT) is False
|
|
|
|
assert en_vocab["the"].check_flag(is_len4) is False
|
|
|
|
assert en_vocab["dogs"].check_flag(is_len4) is True
|
2021-02-06 23:51:34 +00:00
|
|
|
en_vocab.add_flag(lambda string: string.isdigit(), flag_id=IS_DIGIT)
|
2017-05-17 10:04:50 +00:00
|
|
|
|
2021-02-13 01:55:56 +00:00
|
|
|
|
2020-04-15 11:49:47 +00:00
|
|
|
def test_vocab_lexeme_oov_rank(en_vocab):
|
|
|
|
"""Test that default rank is OOV_RANK."""
|
|
|
|
lex = en_vocab["word"]
|
|
|
|
assert OOV_RANK == numpy.iinfo(numpy.uint64).max
|
|
|
|
assert lex.rank == OOV_RANK
|