Last active
September 26, 2024 13:50
-
-
Save borsna/fb13012ce87d47080898aed793a86d7f to your computer and use it in GitHub Desktop.
PHP string to subscript and superscript string
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
<?php | |
/**** example usage **** | |
print SubSupText::replaceSubSupHtml("H<sub>2</sub>O") . PHP_EOL; //H₂O | |
print SubSupText::replaceSubSupHtml("42km<sup>2</sup>") . PHP_EOL; //42km² | |
print SubSupText::replaceSubSupHtml("2<sup>th</sup> chapter") . PHP_EOL; //2ᵗʰ chapter | |
*/ | |
class SubSupText{ | |
const superscriptMap = [ | |
'0' => '⁰', '1' => '¹', '2' => '²', '3' => '³', '4' => '⁴', '5' => '⁵', | |
'6' => '⁶', '7' => '⁷', '8' => '⁸', '9' => '⁹', 'a' => 'ᵃ', 'b' => 'ᵇ', | |
'c' => 'ᶜ', 'd' => 'ᵈ', 'e' => 'ᵉ', 'f' => 'ᶠ', 'g' => 'ᵍ', 'h' => 'ʰ', | |
'i' => 'ⁱ', 'j' => 'ʲ', 'k' => 'ᵏ', 'l' => 'ˡ', 'm' => 'ᵐ', 'n' => 'ⁿ', | |
'o' => 'ᵒ', 'p' => 'ᵖ', 'q' => 'q', 'r' => 'ʳ', 's' => 'ˢ', 't' => 'ᵗ', | |
'u' => 'ᵘ', 'v' => 'ᵛ', 'w' => 'ʷ', 'x' => 'ˣ', 'y' => 'ʸ', 'z' => 'ᶻ', | |
]; | |
const subscriptMap = [ | |
'0' => '₀', '1' => '₁', '2' => '₂', '3' => '₃', '4' => '₄', '5' => '₅', | |
'6' => '₆', '7' => '₇', '8' => '₈', '9' => '₉', 'a' => 'ₐ', 'e' => 'ₑ', | |
'h' => 'ₕ', 'i' => 'ᵢ', 'j' => 'ⱼ', 'k' => 'ₖ', 'l' => 'ₗ', 'm' => 'ₘ', | |
'n' => 'ₙ', 'o' => 'ₒ', 'p' => 'ₚ', 'r' => 'ᵣ', 's' => 'ₛ', 't' => 'ₜ', | |
'u' => 'ᵤ', 'v' => 'ᵥ', 'x' => 'ₓ', 'y' => 'ᵧ', 'z' => '𝓏', | |
]; | |
public static function toSuperscript(string $str): string{ | |
$outputString = ''; | |
$length = mb_strlen($str, 'UTF-8'); | |
for ($i = 0; $i < $length; $i++) { | |
$char = mb_substr($str, $i, 1, 'UTF-8'); | |
$outputString .= isset(self::superscriptMap[$char]) ? self::superscriptMap[$char] : $char; | |
} | |
return $outputString; | |
} | |
public static function toSubscript(string $str): string{ | |
$outputString = ''; | |
$length = mb_strlen($str, 'UTF-8'); | |
for ($i = 0; $i < $length; $i++) { | |
$char = mb_substr($str, $i, 1, 'UTF-8'); | |
$outputString .= isset(self::subscriptMap[$char]) ? self::subscriptMap[$char] : $char; | |
} | |
return $outputString; | |
} | |
public static function replaceSubSupHtml(string $htmlString): string { | |
$supPattern = '/<sup>(.*?)<\/sup>/s'; | |
$htmlString = preg_replace_callback($supPattern, function ($matches) { | |
return self::toSuperscript($matches[1]); | |
}, $htmlString); | |
$subPattern = '/<sub>(.*?)<\/sub>/s'; | |
return preg_replace_callback($subPattern, function ($matches) { | |
return self::toSubscript($matches[1]); | |
}, $htmlString); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
not complete at all just a quick hack to fix some html strings to be unicode only.
might be useful to someone.
if you come up with any improvements please write a comment.