spaCy/spacy/lang/fa/punctuation.py

# coding: utf8
from __future__ import unicode_literals

from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
from ..char_classes import UNITS, ALPHA_UPPER

_suffixes = (
    LIST_PUNCT
    + LIST_ELLIPSES
    + LIST_QUOTES
    + [
        r"(?<=[0-9])\+",
        r"(?<=[0-9])%",  # 4% -> ["4", "%"]
        # Persian is written from Right-To-Left
        r"(?<=[0-9])(?:{})".format(CURRENCY),
        r"(?<=[0-9])(?:{})".format(UNITS),
        r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
    ]
)

TOKENIZER_SUFFIXES = _suffixes