Merge branch 'develop' into feature/disable-pipes

spacy/matcher.pyx

@@ -230,7 +230,7 @@ cdef class Matcher:
         key (unicode): The 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):
         """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.
         """
         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):
         return (self.__class__, (self.vocab,), None, None)

spacy/syntax/nn_parser.pyx

@@ -48,7 +48,7 @@ from thinc.neural.util import get_array_module
 from .. import util
 from ..util import get_async, get_cuda_stream
 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 link_vectors_to_models
 from .._ml import HistoryFeatures
@@ -253,7 +253,7 @@ cdef class Parser:
         hist_width = util.env_opt('history_width', cfg.get('hist_width', 0))
         if hist_size != 0:
             raise ValueError("Currently history size is hard-coded to 0")
-        if hist_width != 0: 
+        if hist_width != 0:
             raise ValueError("Currently history width is hard-coded to 0")
         tok2vec = Tok2Vec(token_vector_width, embed_size,
                           pretrained_dims=cfg.get('pretrained_dims', 0))
@@ -413,7 +413,7 @@ cdef class Parser:
         for stcls in state_objs:
             if not stcls.c.is_final():
                 states.push_back(stcls.c)
-                
+
         feat_weights = state2vec.get_feat_weights()
         cdef int i
         cdef np.ndarray hidden_weights = numpy.ascontiguousarray(vec2scores._layers[-1].W.T)
@@ -432,7 +432,7 @@ cdef class Parser:
         PyErr_CheckSignals()
         return state_objs
 
-    cdef void _parseC(self, StateC* state, 
+    cdef void _parseC(self, StateC* state,
             const float* feat_weights, const float* hW, const float* hb,
             int nr_class, int nr_hidden, int nr_feat, int nr_piece) nogil:
         token_ids = <int*>calloc(nr_feat, sizeof(int))
@@ -443,7 +443,7 @@ cdef class Parser:
             with gil:
                 PyErr_SetFromErrno(MemoryError)
                 PyErr_CheckSignals()
-        
+
         while not state.is_final():
             state.set_context_tokens(token_ids, nr_feat)
             memset(vectors, 0, nr_hidden * nr_piece * sizeof(float))

spacy/tests/test_matcher.py

@@ -64,6 +64,12 @@ def test_matcher_init(en_vocab, words):
     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):
     words = ["I", "like", "cheese", "."]
     doc = get_doc(matcher.vocab, words)
@@ -112,7 +118,8 @@ def test_matcher_empty_dict(en_vocab):
     matcher.add('A.', None, [{'ORTH': 'a'}, {}])
     matches = matcher(doc)
     assert matches[0][1:] == (0, 2)
- 
+
+
 def test_matcher_operator_shadow(en_vocab):
     matcher = Matcher(en_vocab)
     abc = ["a", "b", "c"]
@@ -123,7 +130,8 @@ def test_matcher_operator_shadow(en_vocab):
     matches = matcher(doc)
     assert len(matches) == 1
     assert matches[0][1:] == (0, 3)
- 
+
+
 def test_matcher_phrase_matcher(en_vocab):
     words = ["Google", "Now"]
     doc = get_doc(en_vocab, words)
@@ -134,6 +142,22 @@ def test_matcher_phrase_matcher(en_vocab):
     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):
     words1 = 'He said , " some words " ...'.split()
     words2 = 'He said , " some three words " ...'.split()