explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 07:57:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' into feature/disable-pipes

Browse Source
This commit is contained in:
ines 2017-10-25 16:33:12 +02:00
commit de1e5f35d5
3 changed files with 33 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/matcher.pyx
View File

@ -230,7 +230,7 @@ cdef class Matcher:
key (unicode): The match ID. key (unicode): The match ID.
RETURNS (bool): Whether the matcher contains rules for this match ID. RETURNS (bool): Whether the matcher contains rules for this match ID.
""" """
return key in self._patterns return self._normalize_key(key) in self._patterns
def add(self, key, on_match, *patterns): def add(self, key, on_match, *patterns):
"""Add a match-rule to the matcher. A match-rule consists of: an ID key, """Add a match-rule to the matcher. A match-rule consists of: an ID key,
@ -490,7 +490,7 @@ cdef class PhraseMatcher:
RETURNS (bool): Whether the matcher contains rules for this match ID. RETURNS (bool): Whether the matcher contains rules for this match ID.
""" """
cdef hash_t ent_id = self.matcher._normalize_key(key) cdef hash_t ent_id = self.matcher._normalize_key(key)
return ent_id in self.phrase_ids return ent_id in self._callbacks
def __reduce__(self): def __reduce__(self):
return (self.__class__, (self.vocab,), None, None) return (self.__class__, (self.vocab,), None, None)

2
spacy/syntax/nn_parser.pyx
View File

@ -48,7 +48,7 @@ from thinc.neural.util import get_array_module
from .. import util from .. import util
from ..util import get_async, get_cuda_stream from ..util import get_async, get_cuda_stream
from .._ml import zero_init, PrecomputableAffine, PrecomputableMaxouts from .._ml import zero_init, PrecomputableAffine, PrecomputableMaxouts
from .._ml import Tok2Vec, doc2feats, rebatch, fine_tune from .._ml import Tok2Vec, doc2feats, rebatch
from .._ml import Residual, drop_layer, flatten from .._ml import Residual, drop_layer, flatten
from .._ml import link_vectors_to_models from .._ml import link_vectors_to_models
from .._ml import HistoryFeatures from .._ml import HistoryFeatures

24
spacy/tests/test_matcher.py
View File

@ -64,6 +64,12 @@ def test_matcher_init(en_vocab, words):
assert matcher(doc) == [] assert matcher(doc) == []
def test_matcher_contains(matcher):
matcher.add('TEST', None, [{'ORTH': 'test'}])
assert 'TEST' in matcher
assert 'TEST2' not in matcher
def test_matcher_no_match(matcher): def test_matcher_no_match(matcher):
words = ["I", "like", "cheese", "."] words = ["I", "like", "cheese", "."]
doc = get_doc(matcher.vocab, words) doc = get_doc(matcher.vocab, words)
@ -113,6 +119,7 @@ def test_matcher_empty_dict(en_vocab):
matches = matcher(doc) matches = matcher(doc)
assert matches[0][1:] == (0, 2) assert matches[0][1:] == (0, 2)
def test_matcher_operator_shadow(en_vocab): def test_matcher_operator_shadow(en_vocab):
matcher = Matcher(en_vocab) matcher = Matcher(en_vocab)
abc = ["a", "b", "c"] abc = ["a", "b", "c"]
@ -124,6 +131,7 @@ def test_matcher_operator_shadow(en_vocab):
assert len(matches) == 1 assert len(matches) == 1
assert matches[0][1:] == (0, 3) assert matches[0][1:] == (0, 3)
def test_matcher_phrase_matcher(en_vocab): def test_matcher_phrase_matcher(en_vocab):
words = ["Google", "Now"] words = ["Google", "Now"]
doc = get_doc(en_vocab, words) doc = get_doc(en_vocab, words)
@ -134,6 +142,22 @@ def test_matcher_phrase_matcher(en_vocab):
assert len(matcher(doc)) == 1 assert len(matcher(doc)) == 1
def test_phrase_matcher_length(en_vocab):
matcher = PhraseMatcher(en_vocab)
assert len(matcher) == 0
matcher.add('TEST', None, get_doc(en_vocab, ['test']))
assert len(matcher) == 1
matcher.add('TEST2', None, get_doc(en_vocab, ['test2']))
assert len(matcher) == 2
def test_phrase_matcher_contains(en_vocab):
matcher = PhraseMatcher(en_vocab)
matcher.add('TEST', None, get_doc(en_vocab, ['test']))
assert 'TEST' in matcher
assert 'TEST2' not in matcher
def test_matcher_match_zero(matcher): def test_matcher_match_zero(matcher):
words1 = 'He said , " some words " ...'.split() words1 = 'He said , " some words " ...'.split()
words2 = 'He said , " some three words " ...'.split() words2 = 'He said , " some three words " ...'.split()