Remove unicode declarations and update language data

spacy/lang/cs/examples.py

@@ -1,7 +1,3 @@
-# coding: utf8
-from __future__ import unicode_literals
-
-
 """
 Example sentences to test spaCy and its language models.
 >>> from spacy.lang.cs.examples import sentences

spacy/lang/cs/lex_attrs.py

@@ -1,6 +1,3 @@
-# coding: utf8
-from __future__ import unicode_literals
-
 from ...attrs import LIKE_NUM
 
 _num_words = [

spacy/lang/he/lex_attrs.py

@@ -1,6 +1,3 @@
-# coding: utf8
-from __future__ import unicode_literals
-
 from ...attrs import LIKE_NUM
 
 _num_words = [
@@ -73,6 +70,7 @@ _ordinal_words = [
     "עשירי",
 ]
 
+
 def like_num(text):
     if text.startswith(("+", "-", "±", "~")):
         text = text[1:]

spacy/lang/ne/stop_words.py

@@ -1,7 +1,3 @@
-# coding: utf8
-from __future__ import unicode_literals
-
-
 # Source: https://github.com/sanjaalcorps/NepaliStopWords/blob/master/NepaliStopWords.txt
 
 STOP_WORDS = set(

spacy/lang/sa/__init__.py

@@ -1,18 +1,10 @@
-# coding: utf8
-from __future__ import unicode_literals
-
 from .stop_words import STOP_WORDS
 from .lex_attrs import LEX_ATTRS
-
 from ...language import Language
-from ...attrs import LANG
 
 
 class SanskritDefaults(Language.Defaults):
-    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
+    lex_attr_getters = LEX_ATTRS
-    lex_attr_getters.update(LEX_ATTRS)
-    lex_attr_getters[LANG] = lambda text: "sa"
-
     stop_words = STOP_WORDS
 
 

spacy/lang/sa/examples.py

@@ -1,7 +1,3 @@
-# coding: utf8
-from __future__ import unicode_literals
-
-
 """
 Example sentences to test spaCy and its language models.
 

spacy/lang/sa/lex_attrs.py

@@ -1,9 +1,5 @@
-# coding: utf8
-from __future__ import unicode_literals
-
 from ...attrs import LIKE_NUM
 
-
 # reference 1: https://en.wikibooks.org/wiki/Sanskrit/Numbers
 
 _num_words = [
@@ -106,7 +102,7 @@ _num_words = [
     "सप्तनवतिः",
     "अष्टनवतिः",
     "एकोनशतम्",
-    "शतम्"
+    "शतम्",
 ]
 
 

spacy/lang/sa/stop_words.py

@@ -1,6 +1,3 @@
-# coding: utf8
-from __future__ import unicode_literals
-
 # Source: https://gist.github.com/Akhilesh28/fe8b8e180f64b72e64751bc31cb6d323
 
 STOP_WORDS = set(

spacy/tests/lang/cs/test_text.py

@@ -1,6 +1,3 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import pytest
 
 

spacy/tests/lang/ne/test_text.py

@@ -1,6 +1,3 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import pytest
 
 

spacy/tests/lang/sa/test_text.py

@@ -1,6 +1,3 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import pytest
 
 

spacy/tests/regression/test_issue5838.py

@@ -1,15 +1,13 @@
-# coding: utf8
-from __future__ import unicode_literals
-
 from spacy.lang.en import English
 from spacy.tokens import Span
 from spacy import displacy
 
-SAMPLE_TEXT = '''First line
+
+SAMPLE_TEXT = """First line
 Second line, with ent
 Third line
 Fourth line
-'''
+"""
 
 
 def test_issue5838():
@@ -18,8 +16,8 @@ def test_issue5838():
 
     nlp = English()
     doc = nlp(SAMPLE_TEXT)
-    doc.ents = [Span(doc, 7, 8, label='test')]
+    doc.ents = [Span(doc, 7, 8, label="test")]
 
-    html = displacy.render(doc, style='ent')
+    html = displacy.render(doc, style="ent")
-    found = html.count('</br>')
+    found = html.count("</br>")
     assert found == 4

spacy/tests/regression/test_issue5918.py

@@ -1,6 +1,3 @@
-# coding: utf8
-from __future__ import unicode_literals
-
 from spacy.lang.en import English
 from spacy.pipeline import merge_entities, EntityRuler