For my last project I needed to convert several CSV files from Windows-1250 to UTF-8, and after several days of searching around I found a function that is partially solved my problem, but it still has not transformed all the characters. So I made this:
function w1250_to_utf8($text) {
// map based on:
// http://konfiguracja.c0.pl/iso02vscp1250en.html
// http://konfiguracja.c0.pl/webpl/index_en.html#examp
// http://www.htmlentities.com/html/entities/
$map = array(
chr(0x8A) => chr(0xA9),
chr(0x8C) => chr(0xA6),
chr(0x8D) => chr(0xAB),
chr(0x8E) => chr(0xAE),
chr(0x8F) => chr(0xAC),
chr(0x9C) => chr(0xB6),
chr(0x9D) => chr(0xBB),
chr(0xA1) => chr(0xB7),
chr(0xA5) => chr(0xA1),
chr(0xBC) => chr(0xA5),
chr(0x9F) => chr(0xBC),
chr(0xB9) => chr(0xB1),
chr(0x9A) => chr(0xB9),
chr(0xBE) => chr(0xB5),
chr(0x9E) => chr(0xBE),
chr(0x80) => '€',
chr(0x82) => '‚',
chr(0x84) => '„',
chr(0x85) => '…',
chr(0x86) => '†',
chr(0x87) => '‡',
chr(0x89) => '‰',
chr(0x8B) => '‹',
chr(0x91) => '‘',
chr(0x92) => '’',
chr(0x93) => '“',
chr(0x94) => '”',
chr(0x95) => '•',
chr(0x96) => '–',
chr(0x97) => '—',
chr(0x99) => '™',
chr(0x9B) => '’',
chr(0xA6) => '¦',
chr(0xA9) => '©',
chr(0xAB) => '«',
chr(0xAE) => '®',
chr(0xB1) => '±',
chr(0xB5) => 'µ',
chr(0xB6) => '¶',
chr(0xB7) => '·',
chr(0xBB) => '»',
);
return html_entity_decode(mb_convert_encoding(strtr($text, $map), 'UTF-8', 'ISO-8859-2'), ENT_QUOTES, 'UTF-8');
}