pytorch_transformers/tokenization_openai.py [48:75]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
}

def get_pairs(word):
    """
    Return set of symbol pairs in a word.
    word is represented as tuple of symbols (symbols being variable-length strings)
    """
    pairs = set()
    prev_char = word[0]
    for char in word[1:]:
        pairs.add((prev_char, char))
        prev_char = char
    return pairs

def text_standardize(text):
    """
    fixes some issues the spacy tokenizer had on books corpus
    also does some whitespace standardization
    """
    text = text.replace('—', '-')
    text = text.replace('–', '-')
    text = text.replace('―', '-')
    text = text.replace('…', '...')
    text = text.replace('´', "'")
    text = re.sub(r'''(-+|~+|!+|"+|;+|\?+|\++|,+|\)+|\(+|\\+|\/+|\*+|\[+|\]+|}+|{+|\|+|_+)''', r' \1 ', text)
    text = re.sub(r'\s*\n\s*', ' \n ', text)
    text = re.sub(r'[^\S\n]+', ' ', text)
    return text.strip()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



pytorch_transformers/tokenization_xlm.py [69:96]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
}

def get_pairs(word):
    """
    Return set of symbol pairs in a word.
    word is represented as tuple of symbols (symbols being variable-length strings)
    """
    pairs = set()
    prev_char = word[0]
    for char in word[1:]:
        pairs.add((prev_char, char))
        prev_char = char
    return pairs

def text_standardize(text):
    """
    fixes some issues the spacy tokenizer had on books corpus
    also does some whitespace standardization
    """
    text = text.replace('—', '-')
    text = text.replace('–', '-')
    text = text.replace('―', '-')
    text = text.replace('…', '...')
    text = text.replace('´', "'")
    text = re.sub(r'''(-+|~+|!+|"+|;+|\?+|\++|,+|\)+|\(+|\\+|\/+|\*+|\[+|\]+|}+|{+|\|+|_+)''', r' \1 ', text)
    text = re.sub(r'\s*\n\s*', ' \n ', text)
    text = re.sub(r'[^\S\n]+', ' ', text)
    return text.strip()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -