schaunwheeler

from spacy import load as spacy_load

# This loads the largest English corpus, which must be downloaded
# separate from package installation. Other choices are available.
nlp = spacy_load('en_core_web_lg')


def doc_to_spans(list_of_texts, join_string=' ||| '):
    all_docs = nlp(' ||| '.join(list_of_texts))
    split_inds = [i for i, token in enumerate(all_docs) if token.text == '|||'] + [len(all_docs)]

jdreaver

# Regular expression to find floats. Match groups are the whole string, the
# whole coefficient, the decimal part of the coefficient, and the exponent
# part.
_float_re = re.compile(r'(([+-]?\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?)')

def valid_float_string(string):
    match = _float_re.search(string)
    return match.groups()[0] == string if match else False