spaCy/spacy/tests/lang/he/test_tokenizer.py

84 lines
2.3 KiB
Python
Raw Normal View History

2017-03-24 15:27:44 +00:00
# encoding: utf8
from __future__ import unicode_literals
from spacy.lang.he.lex_attrs import like_num
2017-03-24 15:27:44 +00:00
import pytest
@pytest.mark.parametrize(
"text,expected_tokens",
[("פייתון היא שפת תכנות דינמית", ["פייתון", "היא", "שפת", "תכנות", "דינמית"])],
)
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-24 21:38:44 +00:00
def test_he_tokenizer_handles_abbreviation(he_tokenizer, text, expected_tokens):
tokens = he_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list
2017-03-24 15:27:44 +00:00
@pytest.mark.parametrize(
"text,expected_tokens",
[
(
"עקבת אחריו בכל רחבי המדינה.",
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", "."],
),
(
"עקבת אחריו בכל רחבי המדינה?",
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", "?"],
),
(
"עקבת אחריו בכל רחבי המדינה!",
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", "!"],
),
(
"עקבת אחריו בכל רחבי המדינה..",
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", ".."],
),
(
"עקבת אחריו בכל רחבי המדינה...",
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", "..."],
),
],
)
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-24 21:38:44 +00:00
def test_he_tokenizer_handles_punct(he_tokenizer, text, expected_tokens):
2017-03-24 15:27:44 +00:00
tokens = he_tokenizer(text)
assert expected_tokens == [token.text for token in tokens]
@pytest.mark.parametrize(
"text,match",
[
("10", True),
("1", True),
("10,000", True),
("10,00", True),
("999.0", True),
("אחד", True),
("שתיים", True),
("מליון", True),
("כלב", False),
(",", False),
("1/2", True),
],
)
def test_lex_attrs_like_number(he_tokenizer, text, match):
tokens = he_tokenizer(text)
assert len(tokens) == 1
assert tokens[0].like_num == match
@pytest.mark.parametrize(
"word",
[
"שלישי",
"מליון",
"עשירי",
"מאה",
"עשר",
"אחד עשר",
]
)
def test_he_lex_attrs_like_number_for_ordinal(word):
assert like_num(word)