ai_qback/common/split_text.py

# -*- coding: utf-8 -*-
import re


def split_text_to_word(text: str, split_hyphen=False):
    """
    split_hyphen: 是否分拆-连字符，默认不拆
    """
    if split_hyphen:
        words_list = re.findall(r'\b[\'\w]+\b', text)
    else:
        words_list = re.findall(r'\b[-\'\w]+\b', text)
    return words_list


def get_article_words_count(text: str):
    return len(split_text_to_word(text))


def split_text_to_sentences(text: str) -> list:
    sentences = re.split(r'(?<=[.!?;])', text)
    sentences = [i for i in sentences if i.replace(" ", "")]
    return sentences


def split_text_to_word_punctuation(text: str):
    word_punctuation_list = re.findall(r'\b[-\'\w]+\b|[^\w\s]|\n', text)
    return word_punctuation_list


def is_word(single_word: str, strict: bool = False):
    """strict 严格模式，默认不开。严格模式下，每个实体字符必须是字母。全部都是字母才算是单词
    非严格模式下，有一个字母就算是单词。即使是 op123，it's
    """
    single_word = single_word.strip()
    if strict:
        r = all([re.search(r'[a-zA-Z]', char_) for char_ in single_word if char_])
        if r:
            return True
        return False

    if re.search(r'[\'a-zA-Z]', single_word):
        return True
    return False


if __name__ == '__main__':
    a = "fdh fgdhf fgd-y i'am a student.gfddfgfd dfhgfd ! fdgh,fdgh fght. 3.1415"

    print(is_word("student34", strict=True))