mirror of
https://github.com/explosion/spaCy.git
synced 2025-07-12 17:22:25 +03:00
Modernise and merge matcher tests
This commit is contained in:
Ines Montani
parent
d5d774413a
commit
5f0d196a31
|
|
@ -1,15 +1,107 @@
|
||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from ...matcher import Matcher
|
from ...matcher import Matcher, PhraseMatcher
|
||||||
from ..util import get_doc
|
from ..util import get_doc
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture
|
||||||
|
def matcher(en_vocab):
|
||||||
|
patterns = {
|
||||||
|
'JS': ['PRODUCT', {}, [[{'ORTH': 'JavaScript'}]]],
|
||||||
|
'GoogleNow': ['PRODUCT', {}, [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]]],
|
||||||
|
'Java': ['PRODUCT', {}, [[{'LOWER': 'java'}]]]
|
||||||
|
}
|
||||||
|
return Matcher(en_vocab, patterns)
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.parametrize('words', [["Some", "words"]])
|
@pytest.mark.parametrize('words', [["Some", "words"]])
|
||||||
def test_matcher_init(en_vocab, words):
|
def test_matcher_init(en_vocab, words):
|
||||||
matcher = Matcher(en_vocab)
|
matcher = Matcher(en_vocab)
|
||||||
doc = get_doc(en_vocab, words)
|
doc = get_doc(en_vocab, words)
|
||||||
assert matcher.n_patterns == 0
|
assert matcher.n_patterns == 0
|
||||||
assert matcher(doc) == []
|
assert matcher(doc) == []
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_no_match(matcher):
|
||||||
|
words = ["I", "like", "cheese", "."]
|
||||||
|
doc = get_doc(matcher.vocab, words)
|
||||||
|
assert matcher(doc) == []
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_compile(matcher):
|
||||||
|
assert matcher.n_patterns == 3
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_match_start(matcher):
|
||||||
|
words = ["JavaScript", "is", "good"]
|
||||||
|
doc = get_doc(matcher.vocab, words)
|
||||||
|
assert matcher(doc) == [(matcher.vocab.strings['JS'],
|
||||||
|
matcher.vocab.strings['PRODUCT'], 0, 1)]
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_match_end(matcher):
|
||||||
|
words = ["I", "like", "java"]
|
||||||
|
doc = get_doc(matcher.vocab, words)
|
||||||
|
assert matcher(doc) == [(doc.vocab.strings['Java'],
|
||||||
|
doc.vocab.strings['PRODUCT'], 2, 3)]
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_match_middle(matcher):
|
||||||
|
words = ["I", "like", "Google", "Now", "best"]
|
||||||
|
doc = get_doc(matcher.vocab, words)
|
||||||
|
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'],
|
||||||
|
doc.vocab.strings['PRODUCT'], 2, 4)]
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_match_multi(matcher):
|
||||||
|
words = ["I", "like", "Google", "Now", "and", "java", "best"]
|
||||||
|
doc = get_doc(matcher.vocab, words)
|
||||||
|
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'],
|
||||||
|
doc.vocab.strings['PRODUCT'], 2, 4),
|
||||||
|
(doc.vocab.strings['Java'],
|
||||||
|
doc.vocab.strings['PRODUCT'], 5, 6)]
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_phrase_matcher(en_vocab):
|
||||||
|
words = ["Google", "Now"]
|
||||||
|
doc = get_doc(en_vocab, words)
|
||||||
|
matcher = PhraseMatcher(en_vocab, [doc])
|
||||||
|
words = ["I", "like", "Google", "Now", "best"]
|
||||||
|
doc = get_doc(en_vocab, words)
|
||||||
|
assert len(matcher(doc)) == 1
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_match_zero(matcher):
|
||||||
|
words1 = 'He said , " some words " ...'.split()
|
||||||
|
words2 = 'He said , " some three words " ...'.split()
|
||||||
|
pattern1 = [{'ORTH': '"'},
|
||||||
|
{'OP': '!', 'IS_PUNCT': True},
|
||||||
|
{'OP': '!', 'IS_PUNCT': True},
|
||||||
|
{'ORTH': '"'}]
|
||||||
|
pattern2 = [{'ORTH': '"'},
|
||||||
|
{'IS_PUNCT': True},
|
||||||
|
{'IS_PUNCT': True},
|
||||||
|
{'IS_PUNCT': True},
|
||||||
|
{'ORTH': '"'}]
|
||||||
|
|
||||||
|
matcher.add('Quote', '', {}, [pattern1])
|
||||||
|
doc = get_doc(matcher.vocab, words1)
|
||||||
|
assert len(matcher(doc)) == 1
|
||||||
|
|
||||||
|
doc = get_doc(matcher.vocab, words2)
|
||||||
|
assert len(matcher(doc)) == 0
|
||||||
|
matcher.add('Quote', '', {}, [pattern2])
|
||||||
|
assert len(matcher(doc)) == 0
|
||||||
|
|
||||||
|
|
||||||
|
def test_matcher_match_zero_plus(matcher):
|
||||||
|
words = 'He said , " some words " ...'.split()
|
||||||
|
pattern = [{'ORTH': '"'},
|
||||||
|
{'OP': '*', 'IS_PUNCT': False},
|
||||||
|
{'ORTH': '"'}]
|
||||||
|
matcher.add('Quote', '', {}, [pattern])
|
||||||
|
doc = get_doc(matcher.vocab, words)
|
||||||
|
assert len(matcher(doc)) == 1
|
||||||
|
|
|
||||||
|
|
@ -1,94 +0,0 @@
|
||||||
from __future__ import unicode_literals
|
|
||||||
import pytest
|
|
||||||
|
|
||||||
from spacy.strings import StringStore
|
|
||||||
from spacy.matcher import *
|
|
||||||
from spacy.attrs import LOWER
|
|
||||||
from spacy.tokens.doc import Doc
|
|
||||||
from spacy.vocab import Vocab
|
|
||||||
from spacy.en import English
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.fixture
|
|
||||||
def matcher():
|
|
||||||
patterns = {
|
|
||||||
'JS': ['PRODUCT', {}, [[{'ORTH': 'JavaScript'}]]],
|
|
||||||
'GoogleNow': ['PRODUCT', {}, [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]]],
|
|
||||||
'Java': ['PRODUCT', {}, [[{'LOWER': 'java'}]]],
|
|
||||||
}
|
|
||||||
return Matcher(Vocab(lex_attr_getters=English.Defaults.lex_attr_getters), patterns)
|
|
||||||
|
|
||||||
|
|
||||||
def test_compile(matcher):
|
|
||||||
assert matcher.n_patterns == 3
|
|
||||||
|
|
||||||
|
|
||||||
def test_no_match(matcher):
|
|
||||||
doc = Doc(matcher.vocab, words=['I', 'like', 'cheese', '.'])
|
|
||||||
assert matcher(doc) == []
|
|
||||||
|
|
||||||
|
|
||||||
def test_match_start(matcher):
|
|
||||||
doc = Doc(matcher.vocab, words=['JavaScript', 'is', 'good'])
|
|
||||||
assert matcher(doc) == [(matcher.vocab.strings['JS'],
|
|
||||||
matcher.vocab.strings['PRODUCT'], 0, 1)]
|
|
||||||
|
|
||||||
|
|
||||||
def test_match_end(matcher):
|
|
||||||
doc = Doc(matcher.vocab, words=['I', 'like', 'java'])
|
|
||||||
assert matcher(doc) == [(doc.vocab.strings['Java'],
|
|
||||||
doc.vocab.strings['PRODUCT'], 2, 3)]
|
|
||||||
|
|
||||||
|
|
||||||
def test_match_middle(matcher):
|
|
||||||
doc = Doc(matcher.vocab, words=['I', 'like', 'Google', 'Now', 'best'])
|
|
||||||
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'],
|
|
||||||
doc.vocab.strings['PRODUCT'], 2, 4)]
|
|
||||||
|
|
||||||
|
|
||||||
def test_match_multi(matcher):
|
|
||||||
doc = Doc(matcher.vocab, words='I like Google Now and java best'.split())
|
|
||||||
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'],
|
|
||||||
doc.vocab.strings['PRODUCT'], 2, 4),
|
|
||||||
(doc.vocab.strings['Java'],
|
|
||||||
doc.vocab.strings['PRODUCT'], 5, 6)]
|
|
||||||
|
|
||||||
def test_match_zero(matcher):
|
|
||||||
matcher.add('Quote', '', {}, [
|
|
||||||
[
|
|
||||||
{'ORTH': '"'},
|
|
||||||
{'OP': '!', 'IS_PUNCT': True},
|
|
||||||
{'OP': '!', 'IS_PUNCT': True},
|
|
||||||
{'ORTH': '"'}
|
|
||||||
]])
|
|
||||||
doc = Doc(matcher.vocab, words='He said , " some words " ...'.split())
|
|
||||||
assert len(matcher(doc)) == 1
|
|
||||||
doc = Doc(matcher.vocab, words='He said , " some three words " ...'.split())
|
|
||||||
assert len(matcher(doc)) == 0
|
|
||||||
matcher.add('Quote', '', {}, [
|
|
||||||
[
|
|
||||||
{'ORTH': '"'},
|
|
||||||
{'IS_PUNCT': True},
|
|
||||||
{'IS_PUNCT': True},
|
|
||||||
{'IS_PUNCT': True},
|
|
||||||
{'ORTH': '"'}
|
|
||||||
]])
|
|
||||||
assert len(matcher(doc)) == 0
|
|
||||||
|
|
||||||
|
|
||||||
def test_match_zero_plus(matcher):
|
|
||||||
matcher.add('Quote', '', {}, [
|
|
||||||
[
|
|
||||||
{'ORTH': '"'},
|
|
||||||
{'OP': '*', 'IS_PUNCT': False},
|
|
||||||
{'ORTH': '"'}
|
|
||||||
]])
|
|
||||||
doc = Doc(matcher.vocab, words='He said , " some words " ...'.split())
|
|
||||||
assert len(matcher(doc)) == 1
|
|
||||||
|
|
||||||
|
|
||||||
def test_phrase_matcher():
|
|
||||||
vocab = Vocab(lex_attr_getters=English.Defaults.lex_attr_getters)
|
|
||||||
matcher = PhraseMatcher(vocab, [Doc(vocab, words='Google Now'.split())])
|
|
||||||
doc = Doc(vocab, words=['I', 'like', 'Google', 'Now', 'best'])
|
|
||||||
assert len(matcher(doc)) == 1
|
|
||||||
Loading…
Reference in New Issue
Block a user