Last active
April 18, 2024 23:01
-
-
Save imptype/c03da1cffc668b614c50557d441dd54c to your computer and use it in GitHub Desktop.
Compress text to Unicode text for Discord Custom IDs.
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
# alternative to convert number strings to printable ascii, for smaller deta base strings, ' ' space reserved | |
ascii_chars = list(r'''!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~''') | |
def power_sum(values, base, offset = 0): | |
return sum(value * base ** (index + offset) for index, value in enumerate(values)) | |
def convert_text(text, chars): | |
base = len(chars) + 1 | |
chars = {char : index + 1 for index, char in enumerate(chars)} | |
temp = [] | |
result = '' | |
for char in text: | |
value = chars[char] # indexerror = missing that char in char set | |
if value * base ** len(temp) + power_sum(temp, base, 1) > len(ascii_chars): | |
result += ascii_chars[power_sum(temp, base)] | |
temp = [value] | |
else: | |
temp.append(value) | |
result += ascii_chars[power_sum(temp, base)] | |
return result | |
def revert_text(text, chars): | |
base = len(chars) + 1 | |
chars = list(chars) | |
result = '' | |
for char in text: | |
value = ascii_chars.index(char) | |
while value: | |
result += chars[(value % base) - 1] | |
value //= base | |
return result | |
text = '10123456789012345679999999999999' | |
chars = ''.join(set(text)) | |
print('Base:', len(chars), '\n') | |
print('Start text ({}): {}'.format(len(text), text), '\n') | |
text = convert_text(text, chars) | |
print('Ascii text ({}): {}'.format(len(text), text), '\n') | |
text = revert_text(text, chars) | |
print('Revert text ({}): {}'.format(len(text), text), '\n') |
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
Base: 11 | |
Start text (500): 1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567: | |
Unicode text (100): π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ·π© ππ© πΉ· | |
Revert text (500): 1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567:1012345678901234567: |
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
MAX_UNICODE = 1_114_111 # 0x10FFFF is max unicode code point | |
START_SURROGATE = 55_296 # 0xD800 to 0xDFFF are surrogates, unprintable/pointers | |
MAX_SURROGATE = 2_048 # 0x800 | |
def validate_unicode(value, reverse = False): | |
if value >= START_SURROGATE: | |
value -= MAX_SURROGATE * (2 * int(reverse) - 1) # 1 when true, -1 when false | |
return value | |
def power_sum(values, base, offset = 0): | |
return sum(value * base ** (index + offset) for index, value in enumerate(values)) | |
def convert_text(text, chars): | |
base = len(chars) + 1 | |
chars = {char : index + 1 for index, char in enumerate(chars)} | |
temp = [] | |
result = '' | |
for char in text: | |
value = chars[char] # indexerror = missing that char in char set | |
if value * base ** len(temp) + power_sum(temp, base, 1) > MAX_UNICODE: | |
result += chr(validate_unicode(power_sum(temp, base))) | |
temp = [value] | |
else: | |
temp.append(value) | |
result += chr(validate_unicode(power_sum(temp, base))) | |
return result | |
def revert_text(text, chars): | |
base = len(chars) + 1 | |
chars = list(chars) | |
result = '' | |
for char in text: | |
value = validate_unicode(ord(char), True) | |
while value: | |
result += chars[(value % base) - 1] | |
value //= base | |
return result | |
text = '1012345678901234567:' * 25 # storing 25 user ids in a custom id | |
chars = ''.join(set(text)) | |
print('Base:', len(chars), '\n') | |
print('Start text ({}): {}'.format(len(text), text), '\n') | |
text = convert_text(text, chars) | |
print('Unicode text ({}): {}'.format(len(text), text), '\n') | |
text = revert_text(text, chars) | |
print('Revert text ({}): {}'.format(len(text), text), '\n') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment