Merge pull request #806 from wallinm1/fix/swedish-tokenizer-exceptions

Fix issue #805

spacy/sv/language_data.py

@@ -5,12 +5,14 @@ from .. import language_data as base
 from ..language_data import update_exc, strings_to_exc
 
 from .stop_words import STOP_WORDS
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, ORTH_ONLY
 
 
 STOP_WORDS = set(STOP_WORDS)
 
-
-TOKENIZER_EXCEPTIONS = strings_to_exc(base.EMOTICONS)
+TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
+update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
+update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
 update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
 
 

spacy/sv/tokenizer_exceptions.py

@@ -107,7 +107,6 @@ ORTH_ONLY = [
     "p.g.a.",
     "ref.",
     "resp.",
-    "s.",
     "s.a.s.",
     "s.k.",
     "st.",

spacy/tests/conftest.py

@@ -68,6 +68,11 @@ def fi_tokenizer():
     return Finnish.Defaults.create_tokenizer()
 
 
+@pytest.fixture
+def sv_tokenizer():
+    return Swedish.Defaults.create_tokenizer()
+
+
 @pytest.fixture
 def stringstore():
     return StringStore()

spacy/tests/regression/test_issue805.py

@@ -0,0 +1,15 @@
+# encoding: utf8
+from __future__ import unicode_literals
+
+import pytest
+
+SV_TOKEN_EXCEPTION_TESTS = [
+    ('Smörsåsen används bl.a. till fisk', ['Smörsåsen', 'används', 'bl.a.', 'till', 'fisk']),
+    ('Jag kommer först kl. 13 p.g.a. diverse förseningar', ['Jag', 'kommer', 'först', 'kl.', '13', 'p.g.a.', 'diverse', 'förseningar'])
+]
+
+@pytest.mark.parametrize('text,expected_tokens', SV_TOKEN_EXCEPTION_TESTS)
+def test_issue805(sv_tokenizer, text, expected_tokens):
+    tokens = sv_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list