Added language class and some language data (with some TODOs) for Dutch

spacy/nl/__init__.py

@@ -0,0 +1,26 @@
+from __future__ import unicode_literals, print_function
+
+from os import path
+
+from ..language import Language
+from ..attrs import LANG
+from . import language_data
+
+
+class Dutch(Language):
+    lang = 'nl'
+
+    class Defaults(Language.Defaults):
+        tokenizer_exceptions = dict(language_data.TOKENIZER_EXCEPTIONS)
+        lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
+        lex_attr_getters[LANG] = lambda text: 'nl'
+
+        prefixes = tuple(language_data.TOKENIZER_PREFIXES)
+
+        suffixes = tuple(language_data.TOKENIZER_SUFFIXES)
+
+        infixes = tuple(language_data.TOKENIZER_INFIXES)
+
+        tag_map = dict(language_data.TAG_MAP)
+
+        stop_words = set(language_data.STOP_WORDS)

spacy/tests/integration/test_load_languages.py

@@ -1,6 +1,7 @@
 # encoding: utf8
 from __future__ import unicode_literals
 from ...fr import French
+from ...nl import Dutch
 
 def test_load_french():
     nlp = French()
@@ -10,3 +11,11 @@ def test_load_french():
     assert doc[2].text == u'vous'
     assert doc[3].text == u'français'
     assert doc[4].text == u'?'
+
+def test_load_dutch():
+    nlp = Dutch()
+    doc = nlp(u'Is dit Nederlands?')
+    assert doc[0].text == u'Is'
+    assert doc[1].text == u'dit'
+    assert doc[2].text == u'Nederlands'
+    assert doc[3].text == u'?'