Last active
May 5, 2024 02:55
-
-
Save dmertl/257433864ba85d4fcc3c128a47db34c3 to your computer and use it in GitHub Desktop.
Print unicode chars from names file
This file contains hidden or 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
const SKIP_START = ['\t', '@', ';']; | |
const SKIP_WORDS = [ | |
'<control>', | |
'<not a character>', | |
'MODIFIER', | |
'LEFT-TO-RIGHT', | |
'RIGHT-TO-LEFT', | |
'FORMATTING', | |
'SPACE', | |
'COMBINING', | |
'POINT ', | |
'MARK ', | |
'ACCENT ', | |
'JOINER', | |
'SEPARATOR', | |
'HEBREW ', | |
'-FACING', | |
'ARABIC', | |
'AFGHANI', | |
'DEVANAGARI', | |
'SYRIAC', | |
'THAANA', | |
'NKO', | |
'SAMARITAN', | |
'ORIYA', | |
'LAO ', | |
'FILLER', | |
'SUBJOINED', | |
'THAI CHARACTER', | |
'TIBETAN', | |
'TAGALOG', | |
'HANUNOO', | |
'BUHID', | |
'TAGBANWA', | |
'LIMBU', | |
'TAI THAM', | |
'VEDIC', | |
'CYPRIOT', | |
'MANDAIC', | |
'SAMARITAN', | |
'LINEAR A', | |
'TAG ', | |
]; | |
const ALPHANUM = '0123456789ABCDEF'; | |
const unicode_text = document.body.firstChild; | |
const container = document.createElement('div'); | |
document.body.insertBefore(container, unicode_text); | |
let line_cnt = 1; | |
let line_str = ''; | |
let line_p = document.createElement('p'); | |
line_loop: for (const line of unicode_text.innerText.split("\n")) { | |
// console.log(line_cnt + ' ' + line); | |
if (!line || SKIP_START.includes(line[0])) { | |
// console.log('skip'); | |
continue; | |
} | |
for (const w of SKIP_WORDS) { | |
if (line.includes(w)) { | |
continue line_loop; | |
} | |
} | |
if (line[0] === '0' && line[1] === '0' && ALPHANUM.includes(line[2])) { | |
continue; | |
} | |
let current_char_hex = line.substr(0, line.indexOf('\t')); | |
let current_char = String.fromCodePoint(Number('0x' + current_char_hex)); | |
// console.log(line_cnt + ' ' + current_char_hex + ' 000 ' + current_char + ' 888 ' + line); | |
line_p.innerHTML += current_char; | |
// line_str += '&#' + current_char + ';'; | |
if (line_cnt % 20 === 0) { | |
line_p.innerHTML += ' ' + current_char_hex + ' ' + line_cnt; | |
container.appendChild(line_p); | |
line_p = document.createElement('p'); | |
line_str = ''; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment