word_parse_of_eng/get_word_content/utils.py

import os
import re

endswith_digits_pat = re.compile(r'.*?(\d+)$')


def get_dir_next_num(path, which):
    assert which in ['dirs', 'files']
    dirs = None
    files = None
    for root, dirs, files in os.walk(path):
        break

    if which == 'dirs':
        if dirs:
            res = max(map(int, dirs)) + 1
        else:
            res = 0
    else:
        if files:
            file_digits = []
            for file in files:
                basename = os.path.splitext(file)[0]
                m = endswith_digits_pat.match(basename)
                if m:
                    file_digits.append(m.group(1))
            if file_digits:
                res = max(map(int, file_digits)) + 1
            else:
                res = 0
        else:
            res = 0
    return res


def text2html(text):
    # return text.replace("\r", "").replace("\n", "</br>").replace(" ", "&nbsp;")
    return text.replace("\r", "").replace("\n", "</br>")


if __name__ == "__main__":
    print(get_dir_next_num('upload', 'dirs'))
    print(get_dir_next_num('inputs', 'files'))