-
-
Save eight04/3de731b7300a6b5036e082f801e2e3e9 to your computer and use it in GitHub Desktop.
Big5-UAO containing control characters
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
('\x9b', '@', '妿') | |
('\x9b', 'A', '槡') | |
('\x9b', 'B', '樃') | |
('\x9b', 'C', '樚') | |
('\x9b', 'D', '樜') | |
('\x9b', 'E', '樬') | |
('\x9b', 'F', '樭') | |
('\x9b', 'G', '樳') | |
('\x9b', 'H', '橃') | |
('\x9b', 'I', '橅') | |
('\x9b', 'J', '橌') | |
('\x9b', 'K', '橓') | |
('\x9b', 'L', '橗') | |
('\x9b', 'M', '橣') | |
('\x9b', 'N', '橴') | |
('\x9b', 'O', '檂') | |
('\x9b', 'P', '檊') | |
('\x9b', 'Q', '檏') | |
('\x9b', 'R', '檙') | |
('\x9b', 'S', '檧') | |
('\x9b', 'T', '檱') | |
('\x9b', 'U', '檵') | |
('\x9b', 'V', '檾') | |
('\x9b', 'W', '櫉') | |
('\x9b', 'X', '櫔') | |
('\x9b', 'Y', '櫘') | |
('\x9b', 'Z', '櫶') | |
('\x9b', '[', '歗') | |
('\x9b', '\\', '歺') | |
('\x9b', ']', '毜') | |
('\x9b', '^', '氜') | |
('\x9b', '_', '氱') | |
('\x9b', '`', '汘') | |
('\x9b', 'a', '汮') | |
('\x9b', 'b', '汵') | |
('\x9b', 'c', '汿') | |
('\x9b', 'd', '沯') | |
('\x9b', 'e', '泋') | |
('\x9b', 'f', '泟') | |
('\x9b', 'g', '泿') | |
('\x9b', 'h', '洂') | |
('\x9b', 'i', '洅') | |
('\x9b', 'j', '洆') | |
('\x9b', 'k', '洦') | |
('\x9b', 'l', '浗') | |
('\x9b', 'm', '浛') | |
('\x9b', 'n', '浱') | |
('\x9b', 'o', '涁') | |
('\x9b', 'p', '涏') | |
('\x9b', 'q', '涥') | |
('\x9b', 'r', '涱') | |
('\x9b', 's', '淾') | |
('\x9b', 't', '渂') | |
('\x9b', 'u', '渄') | |
('\x9b', 'v', '渏') | |
('\x9b', 'w', '渘') | |
('\x9b', 'x', '渪') | |
('\x9b', 'y', '湐') | |
('\x9b', 'z', '湙') | |
('\x9b', '{', '溚') | |
('\x9b', '|', '溵') | |
('\x9b', '}', '溸') | |
('\x9b', '~', '滛') | |
('\x9b', '¡', '滺') | |
('\x9b', '¢', '漄') | |
('\x9b', '£', '漋') | |
('\x9b', '¤', '漌') | |
('\x9b', '¥', '漖') | |
('\x9b', '¦', '漗') | |
('\x9b', '§', '漴') | |
('\x9b', '¨', '漽') | |
('\x9b', '©', '潖') | |
('\x9b', 'ª', '潹') | |
('\x9b', '«', '澊') | |
('\x9b', '¬', '澝') | |
('\x9b', '\xad', '澟') | |
('\x9b', '®', '澻') | |
('\x9b', '¯', '澾') | |
('\x9b', '°', '濓') | |
('\x9b', '±', '濙') | |
('\x9b', '²', '濸') | |
('\x9b', '³', '瀃') | |
('\x9b', '´', '灋') | |
('\x9b', 'µ', '灍') | |
('\x9b', '¶', '灐') | |
('\x9b', '·', '灔') | |
('\x9b', '¸', '灜') | |
('\x9b', '¹', '灧') | |
('\x9b', 'º', '灷') | |
('\x9b', '»', '灹') | |
('\x9b', '¼', '炋') | |
('\x9b', '½', '炏') | |
('\x9b', '¾', '炠') | |
('\x9b', '¿', '炣') | |
('\x9b', 'À', '炥') | |
('\x9b', 'Á', '炦') | |
('\x9b', 'Â', '炧') | |
('\x9b', 'Ã', '烄') | |
('\x9b', 'Ä', '烌') | |
('\x9b', 'Å', '烐') | |
('\x9b', 'Æ', '烖') | |
('\x9b', 'Ç', 'ɪ') | |
('\x9b', 'È', 'ɛ') | |
('\x9b', 'É', 'æ') | |
('\x9b', 'Ê', 'ʌ') | |
('\x9b', 'Ë', 'ɑ') | |
('\x9b', 'Ì', 'ɔ') | |
('\x9b', 'Í', 'ʊ') | |
('\x9b', 'Î', 'ɝ') | |
('\x9b', 'Ï', 'ə') | |
('\x9b', 'Ð', 'ɚ') | |
('\x9b', 'Ñ', 'ɜ') | |
('\x9b', 'Ò', 'ɡ') | |
('\x9b', 'Ó', 'ṃ') | |
('\x9b', 'Ô', 'ṉ') | |
('\x9b', 'Õ', 'Ŋ') | |
('\x9b', 'Ö', 'ḻ') | |
('\x9b', '×', 'ɵ') | |
('\x9b', 'Ø', 'ð') | |
('\x9b', 'Ù', 'ʃ') | |
('\x9b', 'Ú', 'ʒ') | |
('\x9b', 'Û', 'ʧ') | |
('\x9b', 'Ü', 'ʤ') | |
('\x9b', 'Ý', 'ã') | |
('\x9b', 'Þ', '\ueb86') | |
('\x9b', 'ß', '\ueb87') | |
('\x9b', 'à', 'ɯ') | |
('\x9b', 'á', 'ɸ') | |
('\x9b', 'â', 'ʇ') | |
('\x9b', 'ã', '\ueb8b') | |
('\x9b', 'ä', 'Ç') | |
('\x9b', 'å', 'œ') | |
('\x9b', 'æ', 'ɒ') | |
('\x9b', 'ç', 'g') | |
('\x9b', 'è', 'ˋ') | |
('\x9b', 'é', 'ˏ') | |
('\x9b', 'ê', 'a') | |
('\x9b', 'ë', 'b') | |
('\x9b', 'ì', 'd') | |
('\x9b', 'í', 'e') | |
('\x9b', 'î', 'f') | |
('\x9b', 'ï', 'h') | |
('\x9b', 'ð', 'i') | |
('\x9b', 'ñ', 'j') | |
('\x9b', 'ò', 'k') | |
('\x9b', 'ó', 'l') | |
('\x9b', 'ô', 'm') | |
('\x9b', 'õ', 'n') | |
('\x9b', 'ö', 'o') | |
('\x9b', '÷', 'p') | |
('\x9b', 'ø', 'r') | |
('\x9b', 'ù', 's') | |
('\x9b', 'ú', 't') | |
('\x9b', 'û', 'u') | |
('\x9b', 'ü', 'v') | |
('\x9b', 'ý', 'w') | |
('\x9b', 'þ', 'z') | |
('\x9d', '@', '☎') | |
('\x9d', 'A', '→') | |
('\x9d', 'B', '←') | |
('\x9d', 'C', '↑') | |
('\x9d', 'D', '↓') | |
('\x9d', 'E', '⇨') | |
('\x9d', 'F', '⇦') | |
('\x9d', 'G', '⇧') | |
('\x9d', 'H', '⇩') | |
('\x9d', 'I', '⇨') | |
('\x9d', 'J', '⇦') | |
('\x9d', 'K', '⇧') | |
('\x9d', 'L', '⇩') | |
('\x9d', 'M', '☞') | |
('\x9d', 'N', '☜') | |
('\x9d', 'O', '☛') | |
('\x9d', 'P', '☟') | |
('\x9d', 'Q', '〖') | |
('\x9d', 'R', '〗') | |
('\x9d', 'S', '○') | |
('\x9d', 'T', '✕') | |
('\x9d', 'U', '✓') | |
('\x9d', 'V', '囻') | |
('\x9d', 'W', '☽') | |
('\x9d', 'X', '夝') | |
('\x9d', 'Y', '晍') | |
('\x9d', 'Z', '爥') | |
('\x9d', '[', '✩') | |
('\x9d', '\\', '✡') | |
('\x9d', ']', '☺') | |
('\x9d', '^', '☹') | |
('\x9d', '_', '\uec63') | |
('\x9d', '`', '\uec64') | |
('\x9d', 'a', '\uec65') | |
('\x9d', 'b', '\uec66') | |
('\x9d', 'c', '\uec67') | |
('\x9d', 'd', '屸') | |
('\x9d', 'e', '♬') | |
('\x9d', 'f', '♪') | |
('\x9d', 'g', '嫑') | |
('\x9d', 'h', '宷') | |
('\x9d', 'i', '峼') | |
('\x9d', 'j', '\uec6e') | |
('\x9d', 'k', '✉') | |
('\x9d', 'l', '✂') | |
('\x9d', 'm', '\uec71') | |
('\x9d', 'n', '\uec72') | |
('\x9d', 'o', '\uec73') | |
('\x9d', 'p', '\uec74') | |
('\x9d', 'q', '峕') | |
('\x9d', 'r', '杮') | |
('\x9d', 's', '瑡') | |
('\x9d', 't', '璝') | |
('\x9d', 'u', '罓') | |
('\x9d', 'v', '薓') | |
('\x9d', 'w', '❏') | |
('\x9d', 'x', '\uec7c') | |
('\x9d', 'y', '\uec7d') | |
('\x9d', 'z', '嵸') | |
('\x9d', '{', '弻') | |
('\x9d', '|', '\uec80') | |
('\x9d', '}', '━') | |
('\x9d', '~', '┃') | |
('\x9d', '¡', '\uec83') | |
('\x9d', '¢', '\uec84') | |
('\x9d', '£', '\uec85') | |
('\x9d', '¤', '\uec86') | |
('\x9d', '¥', '\uec87') | |
('\x9d', '¦', '\uec88') | |
('\x9d', '§', '\uec89') | |
('\x9d', '¨', '\uec8a') | |
('\x9d', '©', '\uec8b') | |
('\x9d', 'ª', '\uec8c') | |
('\x9d', '«', '\uec8d') | |
('\x9d', '¬', '\uec8e') | |
('\x9d', '\xad', '\uec8f') | |
('\x9d', '®', '\uec90') | |
('\x9d', '¯', '\uec91') | |
('\x9d', '°', '骲') | |
('\x9d', '±', '髠') | |
('\x9d', '²', '鬔') | |
('\x9d', '³', '鬴') | |
('\x9d', '´', '鬹') | |
('\x9d', 'µ', '魀') | |
('\x9d', '¶', '魐') | |
('\x9d', '·', '魿') | |
('\x9d', '¸', '☼') | |
('\x9d', '¹', '綕') | |
('\x9d', 'º', '☁') | |
('\x9d', '»', '霴') | |
('\x9d', '¼', '☂') | |
('\x9d', '½', '\uec9f') | |
('\x9d', '¾', '\ueca0') | |
('\x9d', '¿', '\ueca1') | |
('\x9d', 'À', '✈') | |
('\x9d', 'Á', '\ueca3') | |
('\x9d', 'Â', '\ueca4') | |
('\x9d', 'Ã', '\ueca5') | |
('\x9d', 'Ä', '\ueca6') | |
('\x9d', 'Å', '\ueca7') | |
('\x9d', 'Æ', '\ueca8') | |
('\x9d', 'Ç', '\ueca9') | |
('\x9d', 'È', '℻') | |
('\x9d', 'É', '℡') | |
('\x9d', 'Ê', '曧') | |
('\x9d', 'Ë', '湗') | |
('\x9d', 'Ì', '\uecae') | |
('\x9d', 'Í', '煗') | |
('\x9d', 'Î', '秊') | |
('\x9d', 'Ï', '№') | |
('\x9d', 'Ð', '腬') | |
('\x9d', 'Ñ', '諹') | |
('\x9d', 'Ò', '顖') | |
('\x9d', 'Ó', '\uecb5') | |
('\x9d', 'Ô', '\uecb6') | |
('\x9d', 'Õ', '☠') | |
('\x9d', 'Ö', '\uecb8') | |
('\x9d', '×', '♤') | |
('\x9d', 'Ø', '♠') | |
('\x9d', 'Ù', '♧') | |
('\x9d', 'Ú', '♣') | |
('\x9d', 'Û', '♢') | |
('\x9d', 'Ü', '♦') | |
('\x9d', 'Ý', '♡') | |
('\x9d', 'Þ', '♥') | |
('\x9d', 'ß', '\uecc1') | |
('\x9d', 'à', '\uecc2') | |
('\x9d', 'á', '櫤') | |
('\x9d', 'â', '℞') | |
('\x9d', 'ã', '㏂') | |
('\x9d', 'ä', '㏘') | |
('\x9d', 'å', '㎡') | |
('\x9d', 'æ', '\uecc8') | |
('\x9d', 'ç', '㎥') | |
('\x9d', 'è', '\uecca') | |
('\x9d', 'é', '\ueccb') | |
('\x9d', 'ê', '\ueccc') | |
('\x9d', 'ë', '\ueccd') | |
('\x9d', 'ì', '\uecce') | |
('\x9d', 'í', '☑') | |
('\x9d', 'î', '鮁') | |
('\x9d', 'ï', '鮋') | |
('\x9d', 'ð', '鮍') | |
('\x9d', 'ñ', '鯝') | |
('\x9d', 'ò', '鯩') | |
('\x9d', 'ó', '鯭') | |
('\x9d', 'ô', '鯴') | |
('\x9d', 'õ', '鰟') | |
('\x9d', 'ö', '鰠') | |
('\x9d', '÷', '鰦') | |
('\x9d', 'ø', '鱓') | |
('\x9d', 'ù', '鱝') | |
('\x9d', 'ú', '鱻') | |
('\x9d', 'û', '鴌') | |
('\x9d', 'ü', '鴖') | |
('\x9d', 'ý', '↲') | |
('\x9d', 'þ', '欅') |
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
from uao.b2u import b2u_table | |
from pyte.streams import Stream | |
from pyte import control as ctrl | |
from pprint import pformat | |
_special = set([ctrl.ESC, ctrl.CSI_C1, ctrl.NUL, ctrl.DEL, ctrl.OSC_C1]) | |
_special.update(Stream.basic) | |
with open("bad-characters.txt", "w", encoding="utf-8") as f: | |
for b, uni in b2u_table.items(): | |
b1 = chr(b // 0x100) | |
b2 = chr(b % 0x100) | |
if b1 in _special or b2 in _special: | |
f.write(pformat((b1, b2, uni)) + "\n") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment