A simple script to translate markdown files in leet speak.

leet_speak_markdown_translator.py

#!/usr/bin/env python3

import sys
import os
import re

alphabet = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"

dict_normal = {
    'a':'4',
    'b':'8',
    'c':'c',
    'd':'d',
    'e':'3',
    'f':'f',
    'g':'6',
    'h':'h',
    'i':'1',
    'j':'j',
    'k':'k',
    'l':'l',
    'm':'m',
    'n':'n',
    'o':'0',
    'p':'p',
    'q':'q',
    'r':'r',
    's':'5',
    't':'7',
    'u':'u',
    'v':'v',
    'w':'w',
    'x':'x',
    'y':'y',
    'z':'z',
    'A':'4',
    'B':'8',
    'C':'C',
    'D':'D',
    'E':'3',
    'F':'F',
    'G':'6',
    'H':'H',
    'I':'1',
    'J':'J',
    'K':'K',
    'L':'L',
    'M':'M',
    'N':'N',
    'O':'0',
    'P':'P',
    'Q':'Q',
    'R':'R',
    'S':'5',
    'T':'7',
    'U':'U',
    'V':'V',
    'W':'W',
    'X':'X',
    'Y':'Y',
    'Z':'Z'
}

dict_deep = {
    'a':'4',
    'b':'8',
    'c':'(',
    'd':'[)',
    'e':'3',
    'f':'|=',
    'g':'6',
    'h':'|-|',
    'i':'1',
    'j':'_|',
    'k':'|<',
    'l':'|_',
    'm':'/\\/\\',
    'n':'/\\',
    'o':'0',
    'p':'|>',
    'q':'<|',
    'r':'|?',
    's':'5',
    't':'7',
    'u':'|_|',
    'v':'\\/',
    'w':'\\/\\/',
    'x':'><',
    'y':'`/',
    'z':'-\\_',
    'A':'4',
    'B':'8',
    'C':'(',
    'D':'[)',
    'E':'3',
    'F':'|=',
    'G':'6',
    'H':'|-|',
    'I':'1',
    'J':'_|',
    'K':'|<',
    'L':'|_',
    'M':'/\\/\\',
    'N':'/\\',
    'O':'0',
    'P':'|>',
    'Q':'<|',
    'R':'|?',
    'S':'5',
    'T':'7',
    'U':'|_|',
    'V':'\\/',
    'W':'\\/\\/',
    'X':'><',
    'Y':'`/',
    'Z':'-\\_'
}

# [text](url) or ![text](url)
LINK_RE = r'\[.*?\]\(.*?\)'

# ```
BLOCKQUOTES_RE = r'\`\`\`'

def contain_link(line):
    if re.search(LINK_RE, line):
        link = re.compile(LINK_RE)
        m = link.search(line)
        return m.span()
    return False
        

def contain_blockquotes(line):
    return re.search(BLOCKQUOTES_RE, line)

def print_doc():
    doc = """
    === A simple script to translate markdown files in leet speak ===


    Translate all md files in the current directory:
    >_ python leet_speak_markdown_translator.py all

    Translate a specified file:
    >_ python leet_speak_markdown_translator.py file_in file_out
    file_in: the input file
    file_out: the output file
    file_in and file_out can be the same
    """
    print(doc)


def translate_markdown(file_in, file_out, mode='normal'):
    file_in = open(file_in, 'r').readlines()
    file_out = open(file_out, 'w')

    out = ""
    in_blockquotes = False

    if mode == 'normal':
        translate_dict = dict_normal
    else:
        translate_dict = dict_deep


    for line in file_in:
        if not contain_blockquotes(line) and not in_blockquotes:
            if contain_link(line):
                i,j = contain_link(line)
                for c, char in enumerate(line):
                    if c < i or c > j:
                        if char in alphabet:
                            out += translate_dict[char]
                        else:
                            out += char
                    else:
                        out += char
            else:
                for c, char in enumerate(line):
                    if char in alphabet:
                        out += translate_dict[char]
                    else:
                        out += char
        else:
            out += line
            if contain_blockquotes(line):
                in_blockquotes = not in_blockquotes
    
    file_out.write(out)
    file_out.close()


if __name__ == "__main__":
    if len(sys.argv) == 3:
        translate_markdown(sys.argv[1], sys.argv[2])
    elif len(sys.argv) == 2:
        if sys.argv[1] == 'all': #safer
            for file_name in os.listdir():
                if file_name.endswith(".md"):
                    translate_markdown(file_name, file_name)
        else:
            print_doc()
    else:
        print_doc()