mirror of
				https://github.com/explosion/spaCy.git
				synced 2025-10-31 16:07:41 +03:00 
			
		
		
		
	* Implement new API for {Phrase}Matcher.add (backwards-compatible)
* Update docs
* Also update DependencyMatcher.add
* Update internals
* Rewrite tests to use new API
* Add basic check for common mistake
Raise error with suggestion if user likely passed in a pattern instead of a list of patterns
* Fix typo [ci skip]
		
	
			
		
			
				
	
	
		
			27 lines
		
	
	
		
			899 B
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			27 lines
		
	
	
		
			899 B
		
	
	
	
		
			Python
		
	
	
	
	
	
| # coding: utf8
 | |
| from __future__ import unicode_literals
 | |
| 
 | |
| from spacy.matcher import Matcher
 | |
| from spacy.tokens import Doc
 | |
| 
 | |
| 
 | |
| def test_issue4120(en_vocab):
 | |
|     """Test that matches without a final {OP: ?} token are returned."""
 | |
|     matcher = Matcher(en_vocab)
 | |
|     matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}]])
 | |
|     doc1 = Doc(en_vocab, words=["a"])
 | |
|     assert len(matcher(doc1)) == 1  # works
 | |
| 
 | |
|     doc2 = Doc(en_vocab, words=["a", "b", "c"])
 | |
|     assert len(matcher(doc2)) == 2  # fixed
 | |
| 
 | |
|     matcher = Matcher(en_vocab)
 | |
|     matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b"}]])
 | |
|     doc3 = Doc(en_vocab, words=["a", "b", "b", "c"])
 | |
|     assert len(matcher(doc3)) == 2  # works
 | |
| 
 | |
|     matcher = Matcher(en_vocab)
 | |
|     matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b", "OP": "?"}]])
 | |
|     doc4 = Doc(en_vocab, words=["a", "b", "b", "c"])
 | |
|     assert len(matcher(doc4)) == 3  # fixed
 |