Add bandaid solution to the 'shadowing' problem in #864

spacy/matcher.pyx

@@ -71,6 +71,11 @@ cdef enum action_t:
     ADVANCE_ZERO
     PANIC
 
+# A "match expression" conists of one or more token patterns
+# Each token pattern consists of a quantifier and 0+ (attr, value) pairs.
+# A state is an (int, pattern pointer) pair, where the int is the start
+# position, and the pattern pointer shows where we're up to
+# in the pattern.
 
 cdef struct AttrValueC:
     attr_id_t attr
@@ -130,7 +135,10 @@ cdef int get_action(const TokenPatternC* pattern, const TokenC* token) nogil:
     elif pattern.quantifier in (ONE, ZERO_ONE):
         return ACCEPT if (pattern+1).nr_attr == 0 else ADVANCE
     elif pattern.quantifier == ZERO_PLUS:
-        return REPEAT
+        # This is a bandaid over the 'shadowing' problem described here:
+        # https://github.com/explosion/spaCy/issues/864
+        next_action = get_action(pattern+1, token)
+        return REPEAT if next_action is REJECT else next_action
     else:
         return PANIC
 

spacy/tests/test_matcher.py

@@ -111,7 +111,17 @@ def test_matcher_empty_dict(en_vocab):
     matches = matcher(doc)
     assert matches[0][1:] == (0, 2)
  
-
+def test_matcher_operator_shadow(en_vocab):
+    matcher = Matcher(en_vocab)
+    abc = ["a", "b", "c"]
+    doc = get_doc(matcher.vocab, abc)
+    matcher.add('A.C', None, [{'ORTH': 'a'},
+                              {"IS_ALPHA": True, "OP": "+"},
+                              {'ORTH': 'c'}])
+    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)