utils/spacy_tokenizer.py

import spacy
from spacy.tokenizer import Tokenizer
from spacy.lang.char_classes import ALPHA, ALPHA_LOWER, ALPHA_UPPER, CONCAT_QUOTES, LIST_ELLIPSES, LIST_ICONS, HYPHENS
from spacy.util import compile_infix_regex
from spacy.lang.en import English
nlp = English()

def get_tokenizer_gec(nlp):
    infixes = (
        LIST_ELLIPSES
        + LIST_ICONS
        + [
            r"(?<=[0-9])[+\-\*^](?=[0-9-])",
            r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
                al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
            ),
            r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
            #r"(?<=[{a}])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
            r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
        ]
    )
    infix_re = compile_infix_regex(infixes)
    return Tokenizer(nlp.vocab, prefix_search=nlp.tokenizer.prefix_search,
                                suffix_search=nlp.tokenizer.suffix_search,
                                infix_finditer=infix_re.finditer,
                                token_match=nlp.tokenizer.token_match,
                                rules=nlp.Defaults.tokenizer_exceptions)


def get_tokenizer_bea19(nlp):
    infixes = (
        LIST_ELLIPSES
        + LIST_ICONS
        + [
            r"(?<=[0-9])[+\-\*^](?=[0-9-])",
            r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
                al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
            ),
            r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
            r"(?<=[{a}])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
            r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
        ]
    )
    infix_re = compile_infix_regex(infixes)
    return Tokenizer(nlp.vocab, prefix_search=nlp.tokenizer.prefix_search,
                                suffix_search=nlp.tokenizer.suffix_search,
                                infix_finditer=infix_re.finditer,
                                token_match=nlp.tokenizer.token_match,
                                rules=nlp.Defaults.tokenizer_exceptions)


tokenizer_gec = get_tokenizer_gec(nlp)
tokenizer_bea19 = get_tokenizer_bea19(nlp)


def spacy_tokenize_gec(text):
    nlp.tokenizer = tokenizer_gec
    return [str(w) for w in nlp(text)]

def spacy_tokenize_bea19(text):
    nlp.tokenizer = tokenizer_bea19
    return [str(w) for w in nlp(text)]