spaCy/spacy/lang/pl/punctuation.py

# coding: utf8
from __future__ import unicode_literals

from ..char_classes import LIST_ELLIPSES, LIST_PUNCT, LIST_HYPHENS
from ..char_classes import LIST_ICONS, LIST_QUOTES, CURRENCY, UNITS, PUNCT
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES

_quotes = CONCAT_QUOTES.replace("'", "")

_prefixes = _prefixes = [
    r"(długo|krótko|jedno|dwu|trzy|cztero)-"
] + BASE_TOKENIZER_PREFIXES

_infixes = (
    LIST_ELLIPSES
    + LIST_ICONS
    + LIST_HYPHENS
    + [
        r"(?<=[0-9{al}])\.(?=[0-9{au}])".format(al=ALPHA, au=ALPHA_UPPER),
        r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
        r"(?<=[{a}])[:<>=\/](?=[{a}])".format(a=ALPHA),
        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
        r"(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])".format(a=ALPHA, q=_quotes),
    ]
)

_suffixes = (
    ["''", "’’", r"\.", "…"]
    + LIST_PUNCT
    + LIST_QUOTES
    + LIST_ICONS
    + [
        r"(?<=[0-9])\+",
        r"(?<=°[FfCcKk])\.",
        r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
        r"(?<=[0-9])(?:{u})".format(u=UNITS),
        r"(?<=[0-9{al}{e}{p}(?:{q})])\.".format(
            al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
        ),
        r"(?<=[{au}])\.".format(au=ALPHA_UPPER),
    ]
)


TOKENIZER_PREFIXES = _prefixes
TOKENIZER_INFIXES = _infixes
TOKENIZER_SUFFIXES = _suffixes