-
-
Save adz/fde89d28b60c58c8ed798b9663bdf5aa to your computer and use it in GitHub Desktop.
Repair utf-8 strings that contain iso-8599 encoded utf-8 characters
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
class EncodingRepairer | |
REPLACEMENTS = { | |
"€" => "€", "‚" => "‚", "„" => "„", "…" => "…", "ˆ" => "ˆ", | |
"‹" => "‹", "‘" => "‘", "’" => "’", "“" => "“", "â€" => "”", | |
"•" => "•", "–" => "–", "—" => "—", "Ëœ" => "˜", "â„¢" => "™", | |
"›" => "›", "Å“" => "œ", "Å’" => "Œ", "ž" => "ž", "Ÿ" => "Ÿ", | |
"Å¡" => "š", "Ž" => "Ž", "¡" => "¡", "¢" => "¢", "£" => "£", | |
"¤" => "¤", "Â¥" => "¥", "¦" => "¦", "§" => "§", "¨" => "¨", | |
"©" => "©", "ª" => "ª", "«" => "«", "¬" => "¬", "®" => "®", | |
"¯" => "¯", "°" => "°", "±" => "±", "²" => "²", "³" => "³", | |
"´" => "´", "µ" => "µ", "¶" => "¶", "·" => "·", "¸" => "¸", | |
"¹" => "¹", "º" => "º", "»" => "»", "¼" => "¼", "½" => "½", | |
"¾" => "¾", "¿" => "¿", "À" => "À", "Â" => "Â", "Ã" => "Ã", | |
"Ä" => "Ä", "Ã…" => "Å", "Æ" => "Æ", "Ç" => "Ç", "È" => "È", | |
"É" => "É", "Ê" => "Ê", "Ë" => "Ë", "ÃŒ" => "Ì", "ÃŽ" => "Î", | |
"Ñ" => "Ñ", "Ã’" => "Ò", "Ó" => "Ó", "Ô" => "Ô", "Õ" => "Õ", | |
"Ö" => "Ö", "×" => "×", "Ø" => "Ø", "Ù" => "Ù", "Ú" => "Ú", | |
"Û" => "Û", "Ãœ" => "Ü", "Þ" => "Þ", "ß" => "ß", "á" => "á", | |
"â" => "â", "ã" => "ã", "ä" => "ä", "Ã¥" => "å", "æ" => "æ", | |
"ç" => "ç", "è" => "è", "é" => "é", "ê" => "ê", "ë" => "ë", | |
"ì" => "ì", "Ã" => "í", "î" => "î", "ï" => "ï", "ð" => "ð", | |
"ñ" => "ñ", "ò" => "ò", "ó" => "ó", "ô" => "ô", "õ" => "õ", | |
"ö" => "ö", "÷" => "÷", "ø" => "ø", "ù" => "ù", "ú" => "ú", | |
"û" => "û", "ü" => "ü", "ý" => "ý", "þ" => "þ", "ÿ" => "ÿ" | |
} | |
def repair(value) | |
value or return | |
value.gsub!(Regexp.new(REPLACEMENTS.keys * ?|), REPLACEMENTS) | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment