Fix lemmatizer is_base_form for python2.7 (#5734)

* Fix lemmatizer init args for python2.7

* Move English is_base_form to a class method

* Skip test pickling PhraseMatcher for python2

spacy/lang/en/__init__.py

@@ -18,7 +18,26 @@ def _return_en(_):
     return "en"
 
 
-def en_is_base_form(univ_pos, morphology=None):
+class EnglishDefaults(Language.Defaults):
+    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
+    lex_attr_getters.update(LEX_ATTRS)
+    lex_attr_getters[LANG] = _return_en
+    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
+    tag_map = TAG_MAP
+    stop_words = STOP_WORDS
+    morph_rules = MORPH_RULES
+    syntax_iterators = SYNTAX_ITERATORS
+    single_orth_variants = [
+        {"tags": ["NFP"], "variants": ["…", "..."]},
+        {"tags": [":"], "variants": ["-", "—", "–", "--", "---", "——"]},
+    ]
+    paired_orth_variants = [
+        {"tags": ["``", "''"], "variants": [("'", "'"), ("‘", "’")]},
+        {"tags": ["``", "''"], "variants": [('"', '"'), ("“", "”")]},
+    ]
+
+    @classmethod
+    def is_base_form(cls, univ_pos, morphology=None):
         """
         Check whether we're dealing with an uninflected paradigm, so we can
         avoid lemmatization entirely.
@@ -53,26 +72,6 @@ def en_is_base_form(univ_pos, morphology=None):
             return False
 
 
-class EnglishDefaults(Language.Defaults):
-    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
-    lex_attr_getters.update(LEX_ATTRS)
-    lex_attr_getters[LANG] = _return_en
-    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
-    tag_map = TAG_MAP
-    stop_words = STOP_WORDS
-    morph_rules = MORPH_RULES
-    is_base_form = en_is_base_form
-    syntax_iterators = SYNTAX_ITERATORS
-    single_orth_variants = [
-        {"tags": ["NFP"], "variants": ["…", "..."]},
-        {"tags": [":"], "variants": ["-", "—", "–", "--", "---", "——"]},
-    ]
-    paired_orth_variants = [
-        {"tags": ["``", "''"], "variants": [("'", "'"), ("‘", "’")]},
-        {"tags": ["``", "''"], "variants": [('"', '"'), ("“", "”")]},
-    ]
-
-
 class English(Language):
     lang = "en"
     Defaults = EnglishDefaults

spacy/lemmatizer.py

@@ -21,7 +21,7 @@ class Lemmatizer(object):
     def load(cls, *args, **kwargs):
         raise NotImplementedError(Errors.E172)
 
-    def __init__(self, lookups, *args, is_base_form=None, **kwargs):
+    def __init__(self, lookups, is_base_form=None, *args, **kwargs):
         """Initialize a Lemmatizer.
 
         lookups (Lookups): The lookups object containing the (optional) tables

spacy/tests/regression/test_issue3001-3500.py

@@ -121,6 +121,7 @@ def test_issue3248_1():
     assert len(matcher) == 2
 
 
+@pytest.mark.skipif(is_python2, reason="Can't pickle instancemethod for is_base_form")
 def test_issue3248_2():
     """Test that the PhraseMatcher can be pickled correctly."""
     nlp = English()