Last active
July 17, 2020 01:47
-
-
Save libra146/148bd9c38a9858cfa18287069c952c68 to your computer and use it in GitHub Desktop.
在汉字和字母数字之间添加空格,用来格式化md文档
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
import string | |
import sys | |
import time | |
""" | |
在汉字和字母数字之间添加空格 | |
""" | |
def backup(file): | |
with open(file + '.back', 'wb') as back_up: | |
with open(file, 'rb') as f: | |
back_up.write(f.read()) | |
def beautify(file): | |
with open(file, 'r', encoding='utf8') as f: | |
content = f.read() | |
content_list = list(content) | |
index_list = [] | |
string_digits = string.ascii_lowercase + string.ascii_uppercase + string.digits | |
for index, data in enumerate(content_list): | |
if index + 1 >= len(content_list): | |
break | |
next_word = content_list[index + 1] | |
if (re.findall(r'[\u4e00-\u9fa5]', data) and next_word in string_digits) or ( | |
re.findall(r'[\u4e00-\u9fa5]', next_word) and data in string_digits): | |
index_list.append(index) | |
i = 0 | |
# 在两个字中间加空格的话需要将索引加一 | |
for a in index_list: | |
content_list.insert(a + i + 1, ' ') | |
i += 1 | |
with open(file, 'w') as f: | |
f.write(''.join(content_list)) | |
if __name__ == '__main__': | |
path = sys.argv[1:] | |
if len(path) > 1 or len(path) == 0: | |
print('文件过多或过少...') | |
time.sleep(3) | |
sys.exit(0) | |
backup(path[0]) | |
beautify(path[0]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment