You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

14 lines
456 B

from ..punctuation import TOKENIZER_INFIXES as BASE_TOKENIZER_INFIXES
from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES
from ..punctuation import TOKENIZER_SUFFIXES as BASE_TOKENIZER_SUFFIXES
_prefixes = [r"\w{1,3}\$"] + BASE_TOKENIZER_PREFIXES
_suffixes = BASE_TOKENIZER_SUFFIXES
_infixes = [r"(\w+-\w+(-\w+)*)"] + BASE_TOKENIZER_INFIXES
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes