Adding num_like test for Czech (#5946)

* Create lex_attrs.py

Hello,

I am missing a CZECH language in SpaCy. So I would like to help to push it a little. This file is base on others lex_attrs.py files just with translation to Czech.

* Update __init__.py

Updated for use with new Czech Lex_attrs file

* Update stop_words.py

* Create test_text.py

* add like_num testing for czech

Co-authored-by: holubvl3 <47881982+holubvl3@users.noreply.github.com>
Co-authored-by: holubvl3 <vilemrousi@gmail.com>
Co-authored-by: Vladimír Holubec <vholubec@arcdata.cz>

spacy/tests/conftest.py

@@ -47,6 +47,11 @@ def ca_tokenizer():
     return get_lang_class("ca").Defaults.create_tokenizer()
 
 
+@pytest.fixture(scope="session")
+def cs_tokenizer():
+    return get_lang_class("cs").Defaults.create_tokenizer()
+
+
 @pytest.fixture(scope="session")
 def da_tokenizer():
     return get_lang_class("da").Defaults.create_tokenizer()

spacy/tests/lang/cs/test_text.py

@@ -0,0 +1,26 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import pytest
+
+
+@pytest.mark.parametrize(
+    "text,match",
+    [
+        ("10", True),
+        ("1", True),
+        ("10.000", True),
+        ("1000", True),
+        ("999,0", True),
+        ("devatenáct", True),
+        ("osmdesát", True),
+        ("kvadrilion", True),
+        ("Pes", False),
+        (",", False),
+        ("1/2", True),
+    ],
+)
+def test_lex_attrs_like_number(cs_tokenizer, text, match):
+    tokens = cs_tokenizer(text)
+    assert len(tokens) == 1
+    assert tokens[0].like_num == match