mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
7b134b8fbd
* Added Slovak * Added Slovenian tests * Added Estonian tests * Added Croatian tests * Added Latvian tests * Added Icelandic tests * Added Afrikaans tests * Added language-independent tests * Added Kannada tests * Tidied up * Added Albanian tests * Formatted with black * Added failing tests for anomalies * Update spacy/tests/lang/af/test_text.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Estonian tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Croatian tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Icelandic tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Latvian tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Slovak tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Slovenian tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
28 lines
1012 B
Python
28 lines
1012 B
Python
import pytest
|
|
|
|
|
|
def test_long_text(sl_tokenizer):
|
|
# Excerpt: European Convention on Human Rights
|
|
text = """
|
|
upoštevajoč, da si ta deklaracija prizadeva zagotoviti splošno in
|
|
učinkovito priznavanje in spoštovanje v njej razglašenih pravic,
|
|
upoštevajoč, da je cilj Sveta Evrope doseči večjo enotnost med
|
|
njegovimi članicami, in da je eden izmed načinov za zagotavljanje
|
|
tega cilja varstvo in nadaljnji razvoj človekovih pravic in temeljnih
|
|
svoboščin,
|
|
ponovno potrjujoč svojo globoko vero v temeljne svoboščine, na
|
|
katerih temeljita pravičnost in mir v svetu, in ki jih je mogoče najbolje
|
|
zavarovati na eni strani z dejansko politično demokracijo in na drugi
|
|
strani s skupnim razumevanjem in spoštovanjem človekovih pravic,
|
|
od katerih so te svoboščine odvisne,
|
|
"""
|
|
tokens = sl_tokenizer(text)
|
|
assert len(tokens) == 116
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_ordinal_number(sl_tokenizer):
|
|
text = "10. decembra 1948"
|
|
tokens = sl_tokenizer(text)
|
|
assert len(tokens) == 3
|