Resolve conflict on test

spacy/tests/lang/en/test_text.py

@@ -35,7 +35,6 @@ def test_tokenizer_handles_cnts(en_tokenizer, text, length):
     assert len(tokens) == length
 
 
-
 @pytest.mark.parametrize('text,match', [
     ('10', True), ('1', True), ('10,000', True), ('10,00', True),
     ('999.0', True), ('one', True), ('two', True), ('billion', True),

spacy/tests/regression/test_issue429.py

@@ -17,9 +17,8 @@ def test_issue429(EN):
 
     doc = EN('a')
     matcher = Matcher(EN.vocab)
-    matcher.add('TEST', [{'ORTH': 'a'}], on_match=merge_phrases)
+    matcher.add('TEST', merge_phrases, [{'ORTH': 'a'}])
     doc = EN.make_doc('a b c')
-
     EN.tagger(doc)
     matcher(doc)
     EN.entity(doc)

website/docs/api/lexeme.jade

@@ -4,7 +4,7 @@ include ../../_includes/_mixins
 
 p
     |  An entry in the vocabulary. A #[code Lexeme] has no string context – it's
-    |  a word-type, as opposed to a word token. It therefore has no
+    |  a word type, as opposed to a word token. It therefore has no
     |  part-of-speech tag, dependency parse, or lemma (if lemmatization depends
     |  on the part-of-speech tag).
 

website/docs/api/matcher.jade

@@ -52,7 +52,7 @@ p Find all token sequences matching the supplied patterns on the #[code Doc].
 
     matcher = Matcher(nlp.vocab)
     pattern = [{'LOWER': "hello"}, {'LOWER': "world"}]
-    matcher.add("HelloWorld", on_match=None, pattern)
+    matcher.add("HelloWorld", None, pattern)
     doc = nlp(u'hello world!')
     matches = matcher(doc)
 

website/docs/api/vocab.jade

@@ -3,7 +3,7 @@
 include ../../_includes/_mixins
 
 p
-    |  A look-up table that allows you to access #[code Lexeme] objects. The
+    |  A lookup table that allows you to access #[code Lexeme] objects. The
     |  #[code Vocab] instance also provides access to the #[code StringStore],
     |  and owns underlying C-data that is shared between #[code Doc] objects.
 

website/docs/usage/adding-languages.jade

@@ -384,8 +384,6 @@ p
         "ababábites": "ababábite"
     }
 
-+aside("Where can I find lemmatizer data?")
-
 p
     |  To add a lookup lemmatizer to your language, import the #[code LOOKUP]
     |  table and #[code Lemmatizer], and create a new classmethod:

website/docs/usage/rule-based-matching.jade

@@ -47,8 +47,8 @@ p
     nlp = spacy.load('en')
     matcher = Matcher(nlp.vocab)
     # add match ID "HelloWorld" with no callback and one pattern
-    matcher.add('HelloWorld', on_match=None,
-                [{'LOWER': 'hello'}, {'IS_PUNCT': True}, {'LOWER': 'world'}])
+    pattern = [{'LOWER': 'hello'}, {'IS_PUNCT': True}, {'LOWER': 'world'}]
+    matcher.add('HelloWorld', None, pattern)
 
     doc = nlp(u'Hello, world! Hello world!')
     matches = matcher(doc)
@@ -61,7 +61,7 @@ p
     |  without punctuation between "hello" and "world":
 
 +code.
-    matcher.add('HelloWorld', on_match=None,
+    matcher.add('HelloWorld', None,
                 [{'LOWER': 'hello'}, {'IS_PUNCT': True}, {'LOWER': 'world'}],
                 [{'LOWER': 'hello'}, {'LOWER': 'world'}])
 
@@ -104,7 +104,7 @@ p
         match_id, start, end = matches[i]
         doc.ents += ((EVENT, start, end),)
 
-    matcher.add('GoogleIO', on_match=add_event_ent,
+    matcher.add('GoogleIO', add_event_ent,
                 [{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}],
                 [{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}, {'IS_DIGIT': True}])
 
@@ -127,7 +127,7 @@ p
         span.merge(is_stop=True) # merge (and mark it as a stop word, just in case)
         span.set_flag(BAD_HTML_FLAG, True) # set BAD_HTML_FLAG
 
-    matcher.add('BAD_HTML', on_match=merge_and_flag,
+    matcher.add('BAD_HTML', merge_and_flag,
                 [{'ORTH': '<'}, {'LOWER': 'br'}, {'ORTH': '>'}],
                 [{'ORTH': '<'}, {'LOWER': 'br/'}, {'ORTH': '>'}])
 
@@ -283,7 +283,6 @@ p
     # set manual=True to make displaCy render straight from a dictionary
     displacy.serve(matched_sents, style='ent', manual=True)
 
-
 +h(3, "quantifiers-example2") Quantifiers example: Phone numbers
 
 p