mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +03:00
7ed7908716
* Add support basic support for upper sorbian. * Add tokenizer exceptions and tests. * Update spacy/lang/hsb/examples.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
20 lines
123 B
Python
20 lines
123 B
Python
STOP_WORDS = set(
|
|
"""
|
|
a abo ale ani
|
|
|
|
dokelž
|
|
|
|
hdyž
|
|
|
|
jeli jelizo
|
|
|
|
kaž
|
|
|
|
pak potom
|
|
|
|
tež tohodla
|
|
|
|
zo zoby
|
|
""".split()
|
|
)
|