mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +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]
34 lines
842 B
Python
34 lines
842 B
Python
|
|
_exc = {
|
|
# Slang
|
|
"прив": "привет",
|
|
"дарова": "привет",
|
|
"дак": "так",
|
|
"дык": "так",
|
|
"здарова": "привет",
|
|
"пакедава": "пока",
|
|
"пакедаво": "пока",
|
|
"ща": "сейчас",
|
|
"спс": "спасибо",
|
|
"пжлст": "пожалуйста",
|
|
"плиз": "пожалуйста",
|
|
"ладненько": "ладно",
|
|
"лады": "ладно",
|
|
"лан": "ладно",
|
|
"ясн": "ясно",
|
|
"всм": "всмысле",
|
|
"хош": "хочешь",
|
|
"хаюшки": "привет",
|
|
"оч": "очень",
|
|
"че": "что",
|
|
"чо": "что",
|
|
"шо": "что",
|
|
}
|
|
|
|
|
|
NORM_EXCEPTIONS = {}
|
|
|
|
for string, norm in _exc.items():
|
|
NORM_EXCEPTIONS[string] = norm
|
|
NORM_EXCEPTIONS[string.title()] = norm
|