Adds Turkish Lemmatization

CONTRIBUTORS.md

@@ -12,6 +12,7 @@ This is a list of everyone who has made significant contributions to spaCy, in a
 * Ben Eyal, [@beneyal](https://github.com/beneyal)
 * Bhargav Srinivasa, [@bhargavvader](https://github.com/bhargavvader)
 * Bruno P. Kinoshita, [@kinow](https://github.com/kinow)
+* Canbey Bilgili, [@cbilgili](https://github.com/cbilgili)
 * Chris DuBois, [@chrisdubois](https://github.com/chrisdubois)
 * Christoph Schwienheer, [@chssch](https://github.com/chssch)
 * Dafne van Kuppevelt, [@dafnevk](https://github.com/dafnevk)

spacy/lang/tr/__init__.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+from .lemmatizer import LOOKUP
 from .stop_words import STOP_WORDS
 
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
@@ -17,6 +18,7 @@ class TurkishDefaults(Language.Defaults):
     lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
     tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
     stop_words = STOP_WORDS
+    lemma_lookup = LOOKUP
 
 
 class Turkish(Language):

spacy/tests/conftest.py

@@ -15,7 +15,7 @@ from .. import util
 # here if it's using spaCy's tokenizer (not a different library)
 # TODO: re-implement generic tokenizer tests
 _languages = ['bn', 'da', 'de', 'en', 'es', 'fi', 'fr', 'ga', 'he', 'hu', 'id',
-              'it', 'nb', 'nl', 'pl', 'pt', 'ru', 'sv', 'xx']
+              'it', 'nb', 'nl', 'pl', 'pt', 'ru', 'sv', 'tr', 'xx']
 _models = {'en': ['en_core_web_sm'],
            'de': ['de_core_news_md'],
            'fr': ['fr_core_news_sm'],
@@ -142,6 +142,10 @@ def th_tokenizer():
     pythainlp = pytest.importorskip("pythainlp")
     return util.get_lang_class('th').Defaults.create_tokenizer()
 
+@pytest.fixture
+def tr_tokenizer():
+    return util.get_lang_class('tr').Defaults.create_tokenizer()
+
 
 @pytest.fixture
 def ru_tokenizer():

spacy/tests/lang/tr/test_lemmatization.py

@@ -0,0 +1,15 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import pytest
+
+@pytest.mark.parametrize('string,lemma', [('evlerimizdeki', 'ev'),
+                                          ('işlerimizi', 'iş'),
+                                          ('biran', 'biran'),
+                                          ('bitirmeliyiz', 'bitir'),
+                                          ('isteklerimizi', 'istek'),
+                                          ('karşılaştırmamızın', 'karşılaştır'),
+                                          ('çoğulculuktan', 'çoğulcu')])
+def test_lemmatizer_lookup_assigns(tr_tokenizer, string, lemma):
+    tokens = tr_tokenizer(string)
+    assert tokens[0].lemma_ == lemma