mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 18:36:36 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
27 lines
724 B
Python
27 lines
724 B
Python
|
|
def test_en_simple_punct(en_tokenizer):
|
|
text = "to walk, do foo"
|
|
tokens = en_tokenizer(text)
|
|
assert tokens[0].idx == 0
|
|
assert tokens[1].idx == 3
|
|
assert tokens[2].idx == 7
|
|
assert tokens[3].idx == 9
|
|
assert tokens[4].idx == 12
|
|
|
|
|
|
def test_en_complex_punct(en_tokenizer):
|
|
text = "Tom (D., Ill.)!"
|
|
tokens = en_tokenizer(text)
|
|
assert tokens[0].idx == 0
|
|
assert len(tokens[0]) == 3
|
|
assert tokens[1].idx == 4
|
|
assert len(tokens[1]) == 1
|
|
assert tokens[2].idx == 5
|
|
assert len(tokens[2]) == 2
|
|
assert tokens[3].idx == 7
|
|
assert len(tokens[3]) == 1
|
|
assert tokens[4].idx == 9
|
|
assert len(tokens[4]) == 4
|
|
assert tokens[5].idx == 13
|
|
assert tokens[6].idx == 14
|