UTF-8 Encoding Debugging

charset-converter.php

<?php

$search = array(

  'á',
  'ä',
  'Ä',
  'ç',
  'é',
  'É',
  'è',
  'ì',
  'ê',
  'í',
  'ï',
  'Ä©',
  'ó',
  'ø',
  'ö',
  'Ö',
  'Å¡',
  'ü',
  'Lú',
  'Å©',
  'ñ',

  'Ã¥',
  'ä',
  'ö',
  'Ã…',
  'Ä',
  'Ö',
  'é',

  'ø',
  'æ',
  'Ø',
  'õ',
  '•',
  'ú',
  'Ã',
  'Ã',
  'Ç',
  'â€',
  '“',
  'É',

  '”',
  'Ù',
  '„',
  '´',
  '†',
  'ÿ',
  'ë',
  '›',
  'À',
  'Â',
  'Ã',
  'È',
  'É',
  'Ê',
  'Ë',
  'Ì',
);

$replace = array(

  'á',
  'ä',
  'ä',
  'ç',
  'é',
  'É',
  'è',
  'ě',
  'ê',
  'í',
  'ï',
  'ĩ',
  'ó',
  'ø',
  'ö',
  'ö',
  'š',
  'ü',
  'ú',
  'ũ',
  'ñ',

  'å',
  'ä',
  'ö',
  'Å',
  'Ä',
  'Ö',
  '©',

  'œ',
  'æ',
  'Ø',
  'õ',
  '-',
  'ú',
  'À',
  'Ã',
  'Ç',
  '"',
  '"',
  'É',

  'ö',
  'Ù',
  'Ä',
  'ô',
  'Æ',
  'ÿ',
  'ë',
  'Û',
  'À',
  'Â',
  'Ã',
  'È',
  'É',
  'Ê',
  'Ë',
  'Ì',
);

$handle = @fopen("in.txt", "r");
$file   = @fopen("out.txt", "w");
if ($handle) 
{
    while (($buffer = fgets($handle)) !== false) 
    {
        $buffer = str_replace($search, $replace, $buffer);
        fwrite($file, $buffer);
    }

    fclose($handle);
}

�“€( 0£ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿàl� ��ì�½Ò÷·[ÑÞôû¹ï»½}sµÏ>õíß}ë^Ýuéݺ·næéÈ÷r»»Çϻޮø÷q<×V÷žïi×»w»iõ½mGºµ¾·]Þç—mwg{{¶Ã¯]ó;¾çmßv»¼ù}ïMÞ�=#Ñõݾ޽åŽç]ìÏY»ÚÖæ¶÷»kͯ´ùï·{½y®Û{›ï³ï»{O�³¾÷=×Þëï|Ò÷ß7·;Ú÷Ö>Ù}ŒVÓÛ{<ºïZöö¼Þö÷×{ëï}ö¾s�³<íï•ç�-ït®î»®nöo{£½ŒÜôqÛ{ÝÞmÉï:�Ûq»³�{ÞöÞÖûÞ:û]ßt¯m¯hק}ßu÷Ï·¯{�_+ÛÓ½Þ[yMw¼÷z7��î®ã»µ+�ëK^ëÝÝÍïMÞöêîî�³{Ù|{¼÷|ë×»Î=½w·­¹×ww½nO{ÞïVœç½Þ}Ûî <uSý L F˜ ‚dÄÀj� FL �dÈ` �À ©âa�™4Á0
4h1 4É=

Thanks for sharing this. In my case, I had an even more severely garbled MySQL table where "é" had become "é", "è" had become "è", etc.

I first had to convert that using the query shown here: https://stackoverflow.com/a/74092827/3018750, and then convert that down using your conversion table.

That whole thing converted to an SQL query became:

SELECT 

REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE( REPLACE(

CONVERT(BINARY(CONVERT(CONVERT(post_content USING utf8mb4) USING latin1)) USING utf8mb4),

'á', 'á'), 'ä', 'ä'), 'Ä', 'ä'), 'ç', 'ç'), 'é', 'é'), 'É', 'É'), 'è', 'è'), 'ì', 'ě'), 'ê', 'ê'), 'í', 'í'), 'ï', 'ï'), 'Ä©', 'ĩ'), 'ó', 'ó'), 'ø', 'ø'), 'ö', 'ö'), 'Ö', 'ö'), 'Å¡', 'š'), 'ü', 'ü'), 'Lú', 'ú'), 'Å©', 'ũ'), 'ñ', 'ñ'), 'Ã¥', 'å'), 'ä', 'ä'), 'ö', 'ö'), 'Ã…', 'Å'), 'Ä', 'Ä'), 'Ö', 'Ö'), 'é', '©'), 'ø', 'œ'), 'æ', 'æ'), 'Ø', 'Ø'), 'õ', 'õ'), '•', '-'), 'ú', 'ú'), 'Ã', 'À'), 'Ã', 'Ã'), 'Ç', 'Ç'), 'â€', '"'), '“', '"'), 'É', 'É'), '”', 'ö'), 'Ù', 'Ù'), '„', 'Ä'), '´', 'ô'), '†', 'Æ'), 'ÿ', 'ÿ'), 'ë', 'ë'), '›', 'Û'), 'À', 'À'), 'Â', 'Â'), 'Ã', 'Ã'), 'È', 'È'), 'É', 'É'), 'Ê', 'Ê'), 'Ë', 'Ë'), 'ÃŒ', 'Ì'), '„', 'Ä'), '†', 'Æ'), '”', 'ö'), '›', 'Û'), 'ÃŒ', 'Ì');