kasperkamperman · July 3, 2018 11:58 · Mrcel01 · May 31, 2023
diff --git a/fixwrongutf8encoding.php b/fixwrongutf8encoding.php
 <?php header('Content-Type: text/html; charset=utf-8');  ?>
 <html>
 <head>
    <title>Fix wrong encoded UTF8 characters</title>
    <meta http-equiv="Content-type" content="text/html; charset=utf-8" />
 </head>
 <body>
 <pre>
 <?php
    /*  Problem description:

        A common problem is for characters encoded as UTF-8 to have their individual bytes interpreted as ISO-8859-1 or Windows-1252.
        Instead of an expected character, a sequence of Latin characters is shown, typically starting with Ã or Â. For example, instead of "è" these characters occur: "Ã¨".

        A Web page is encoded as UTF-8 characters. The Web server mistakenly declares the charset to be ISO-8859-1 in the HTTP protocol that delivers the page to the browser. 
        The browser will then display each of the UTF-8 bytes in the Web page as Latin-1 characters.
        
        source: http://www.i18nqa.com/debug/bug-utf-8-latin1.html
        
        code source:  https://github.com/devgeniem/wp-sanitize-accented-uploads/blob/master/plugin.php#L152
        table source: http://www.i18nqa.com/debug/utf8-debug.html
        
        https://www.kasperkamperman.com/ 2018-07-03

    */

    $str = 'BLÃ˜F - ZOUTELANDE, MÃ˜ - FINAL SONG, FÃÂ©dération Camerounaise de Football, Itâ€™s Getting the Best of Me';
   
    echo "original string: ".$str.'<br/>';
    echo "fixed string:    ".fixWrongUTF8Encoding($str).'<br/>';

    // displays: BLØF - ZOUTELANDE, MØ - FINAL SONG, Fédération Camerounaise de Football, It’s Getting the Best of Me
    
    function fixWrongUTF8Encoding($inputString) {

        // code source:  https://github.com/devgeniem/wp-sanitize-accented-uploads/blob/master/plugin.php#L152
        // table source: http://www.i18nqa.com/debug/utf8-debug.html
        
        $fix_list = array(
            // 3 char errors first
            'â€š' => '‚', 'â€ž' => '„', 'â€¦' => '…', 'â€¡' => '‡',
            'â€°' => '‰', 'â€¹' => '‹', 'â€˜' => '‘', 'â€™' => '’',
            'â€œ' => '“', 'â€¢' => '•', 'â€“' => '–', 'â€”' => '—',
            'â„¢' => '™', 'â€º' => '›', 'â‚¬' => '€',
            // 2 char errors
            'Ã‚'  => 'Â', 'Æ’'  => 'ƒ', 'Ãƒ'  => 'Ã', 'Ã„'  => 'Ä',
            'Ã…'  => 'Å', 'â€'  => '†', 'Ã†'  => 'Æ', 'Ã‡'  => 'Ç',
            'Ë†'  => 'ˆ', 'Ãˆ'  => 'È', 'Ã‰'  => 'É', 'ÃŠ'  => 'Ê',
            'Ã‹'  => 'Ë', 'Å’'  => 'Œ', 'ÃŒ'  => 'Ì', 'Å½'  => 'Ž',
            'ÃŽ'  => 'Î', 'Ã‘'  => 'Ñ', 'Ã’'  => 'Ò', 'Ã“'  => 'Ó',
            'â€'  => '”', 'Ã”'  => 'Ô', 'Ã•'  => 'Õ', 'Ã–'  => 'Ö',
            'Ã—'  => '×', 'Ëœ'  => '˜', 'Ã˜'  => 'Ø', 'Ã™'  => 'Ù',
            'Å¡'  => 'š', 'Ãš'  => 'Ú', 'Ã›'  => 'Û', 'Å“'  => 'œ',
            'Ãœ'  => 'Ü', 'Å¾'  => 'ž', 'Ãž'  => 'Þ', 'Å¸'  => 'Ÿ',
            'ÃŸ'  => 'ß', 'Â¡'  => '¡', 'Ã¡'  => 'á', 'Â¢'  => '¢',
            'Ã¢'  => 'â', 'Â£'  => '£', 'Ã£'  => 'ã', 'Â¤'  => '¤',
            'Ã¤'  => 'ä', 'Â¥'  => '¥', 'Ã¥'  => 'å', 'Â¦'  => '¦',
            'Ã¦'  => 'æ', 'Â§'  => '§', 'Ã§'  => 'ç', 'Â¨'  => '¨',
            'Ã¨'  => 'è', 'Â©'  => '©', 'Ã©'  => 'é', 'Âª'  => 'ª',
            'Ãª'  => 'ê', 'Â«'  => '«', 'Ã«'  => 'ë', 'Â¬'  => '¬',
            'Ã¬'  => 'ì', 'Â®'  => '®', 'Ã®'  => 'î', 'Â¯'  => '¯',
            'Ã¯'  => 'ï', 'Â°'  => '°', 'Ã°'  => 'ð', 'Â±'  => '±',
            'Ã±'  => 'ñ', 'Â²'  => '²', 'Ã²'  => 'ò', 'Â³'  => '³',
            'Ã³'  => 'ó', 'Â´'  => '´', 'Ã´'  => 'ô', 'Âµ'  => 'µ',
            'Ãµ'  => 'õ', 'Â¶'  => '¶', 'Ã¶'  => 'ö', 'Â·'  => '·',
            'Ã·'  => '÷', 'Â¸'  => '¸', 'Ã¸'  => 'ø', 'Â¹'  => '¹',
            'Ã¹'  => 'ù', 'Âº'  => 'º', 'Ãº'  => 'ú', 'Â»'  => '»',
            'Ã»'  => 'û', 'Â¼'  => '¼', 'Ã¼'  => 'ü', 'Â½'  => '½',
            'Ã½'  => 'ý', 'Â¾'  => '¾', 'Ã¾'  => 'þ', 'Â¿'  => '¿',
            'Ã¿'  => 'ÿ', 'Ã€'  => 'À',
            // 1 char errors last
            'Ã' => 'Á', 'Å' => 'Š', 'Ã' => 'Í', 'Ã' => 'Ï',
            'Ã' => 'Ð', 'Ã' => 'Ý', 'Ã' => 'à', 'Ã' => 'í'
        );
    
        $error_chars = array_keys($fix_list);
        $real_chars  = array_values($fix_list);     

        return str_replace($error_chars, $real_chars, $inputString);

    }

 ?>
 </pre>
 </body>
 </html>
	<?php header('Content-Type: text/html; charset=utf-8'); ?>
	<html>
	<head>
	<title>Fix wrong encoded UTF8 characters</title>
	<meta http-equiv="Content-type" content="text/html; charset=utf-8" />
	</head>
	<body>
	<pre>
	<?php
	/* Problem description:

	A common problem is for characters encoded as UTF-8 to have their individual bytes interpreted as ISO-8859-1 or Windows-1252.
	Instead of an expected character, a sequence of Latin characters is shown, typically starting with Ã or Â. For example, instead of "è" these characters occur: "Ã¨".

	A Web page is encoded as UTF-8 characters. The Web server mistakenly declares the charset to be ISO-8859-1 in the HTTP protocol that delivers the page to the browser.
	The browser will then display each of the UTF-8 bytes in the Web page as Latin-1 characters.

	source: http://www.i18nqa.com/debug/bug-utf-8-latin1.html

	code source: https://github.com/devgeniem/wp-sanitize-accented-uploads/blob/master/plugin.php#L152
	table source: http://www.i18nqa.com/debug/utf8-debug.html

	https://www.kasperkamperman.com/ 2018-07-03

	*/

	$str = 'BLÃ˜F - ZOUTELANDE, MÃ˜ - FINAL SONG, FÃÂ©dération Camerounaise de Football, Itâ€™s Getting the Best of Me';

	echo "original string: ".$str.'<br/>';
	echo "fixed string: ".fixWrongUTF8Encoding($str).'<br/>';

	// displays: BLØF - ZOUTELANDE, MØ - FINAL SONG, Fédération Camerounaise de Football, It’s Getting the Best of Me

	function fixWrongUTF8Encoding($inputString) {

	// code source: https://github.com/devgeniem/wp-sanitize-accented-uploads/blob/master/plugin.php#L152
	// table source: http://www.i18nqa.com/debug/utf8-debug.html

	$fix_list = array(
	// 3 char errors first
	'â€š' => '‚', 'â€ž' => '„', 'â€¦' => '…', 'â€¡' => '‡',
	'â€°' => '‰', 'â€¹' => '‹', 'â€˜' => '‘', 'â€™' => '’',
	'â€œ' => '“', 'â€¢' => '•', 'â€“' => '–', 'â€”' => '—',
	'â„¢' => '™', 'â€º' => '›', 'â‚¬' => '€',
	// 2 char errors
	'Ã‚' => 'Â', 'Æ’' => 'ƒ', 'Ãƒ' => 'Ã', 'Ã„' => 'Ä',
	'Ã…' => 'Å', 'â€' => '†', 'Ã†' => 'Æ', 'Ã‡' => 'Ç',
	'Ë†' => 'ˆ', 'Ãˆ' => 'È', 'Ã‰' => 'É', 'ÃŠ' => 'Ê',
	'Ã‹' => 'Ë', 'Å’' => 'Œ', 'ÃŒ' => 'Ì', 'Å½' => 'Ž',
	'ÃŽ' => 'Î', 'Ã‘' => 'Ñ', 'Ã’' => 'Ò', 'Ã“' => 'Ó',
	'â€' => '”', 'Ã”' => 'Ô', 'Ã•' => 'Õ', 'Ã–' => 'Ö',
	'Ã—' => '×', 'Ëœ' => '˜', 'Ã˜' => 'Ø', 'Ã™' => 'Ù',
	'Å¡' => 'š', 'Ãš' => 'Ú', 'Ã›' => 'Û', 'Å“' => 'œ',
	'Ãœ' => 'Ü', 'Å¾' => 'ž', 'Ãž' => 'Þ', 'Å¸' => 'Ÿ',
	'ÃŸ' => 'ß', 'Â¡' => '¡', 'Ã¡' => 'á', 'Â¢' => '¢',
	'Ã¢' => 'â', 'Â£' => '£', 'Ã£' => 'ã', 'Â¤' => '¤',
	'Ã¤' => 'ä', 'Â¥' => '¥', 'Ã¥' => 'å', 'Â¦' => '¦',
	'Ã¦' => 'æ', 'Â§' => '§', 'Ã§' => 'ç', 'Â¨' => '¨',
	'Ã¨' => 'è', 'Â©' => '©', 'Ã©' => 'é', 'Âª' => 'ª',
	'Ãª' => 'ê', 'Â«' => '«', 'Ã«' => 'ë', 'Â¬' => '¬',
	'Ã¬' => 'ì', 'Â®' => '®', 'Ã®' => 'î', 'Â¯' => '¯',
	'Ã¯' => 'ï', 'Â°' => '°', 'Ã°' => 'ð', 'Â±' => '±',
	'Ã±' => 'ñ', 'Â²' => '²', 'Ã²' => 'ò', 'Â³' => '³',
	'Ã³' => 'ó', 'Â´' => '´', 'Ã´' => 'ô', 'Âµ' => 'µ',
	'Ãµ' => 'õ', 'Â¶' => '¶', 'Ã¶' => 'ö', 'Â·' => '·',
	'Ã·' => '÷', 'Â¸' => '¸', 'Ã¸' => 'ø', 'Â¹' => '¹',
	'Ã¹' => 'ù', 'Âº' => 'º', 'Ãº' => 'ú', 'Â»' => '»',
	'Ã»' => 'û', 'Â¼' => '¼', 'Ã¼' => 'ü', 'Â½' => '½',
	'Ã½' => 'ý', 'Â¾' => '¾', 'Ã¾' => 'þ', 'Â¿' => '¿',
	'Ã¿' => 'ÿ', 'Ã€' => 'À',
	// 1 char errors last
	'Ã' => 'Á', 'Å' => 'Š', 'Ã' => 'Í', 'Ã' => 'Ï',
	'Ã' => 'Ð', 'Ã' => 'Ý', 'Ã' => 'à', 'Ã' => 'í'
	);

	$error_chars = array_keys($fix_list);
	$real_chars = array_values($fix_list);

	return str_replace($error_chars, $real_chars, $inputString);

	}

	?>
	</pre>
	</body>
	</html>