latin12utf8map.sed

# Latin1 incompatibility
# While ISO-8859-1 (the widespread Latin1 that is HTML's historical default
# charset) is a code subset of Unicode, ISO-8859-1's 8bit encoding scheme is no
# code subset of UTF-8. Latin1 letters look quite different when transformed into
# UTF-8. Non-ASCII characters in UTF-8 output look illegible on Latin-1 terminals.
# The many existing and unlabeled Latin1 texts are no legal UTF-8 input. Contrary
# to UTF-8, SCSU, JAVA and HTML allow Latin1 text to pass through transparently
# without being limited to Latin1.
# Source: http://www.czyborra.com/utf/

s/Â//g
s/¡/¡/g
s/¢/¢/g
s/£/£/g
s/¤/¤/g
s/Â¥/¥/g
s/¦/¦/g
s/§/§/g
s/¨/¨/g
s/©/©/g
s/ª/ª/g
s/«/«/g
s/¬/¬/g
s/­/­/g
s/®/®/g
s/¯/¯/g
s/°/°/g
s/±/±/g
s/²/²/g
s/³/³/g
s/´/´/g
s/µ/µ/g
s/¶/¶/g
s/·/·/g
s/¸/¸/g
s/¹/¹/g
s/º/º/g
s/»/»/g
s/¼/¼/g
s/½/½/g
s/¾/¾/g
s/¿/¿/g
s/À/À/g
s/Ã /Á/g
s/Â/Â/g
s/Ã/Ã/g
s/Ä/Ä/g
s/Ã…/Å/g
s/Æ/Æ/g
s/Ç/Ç/g
s/È/È/g
s/É/É/g
s/Ê/Ê/g
s/Ë/Ë/g
s/ÃŒ/Ì/g
s/Ã /Í/g
s/ÃŽ/Î/g
s/Ã /Ï/g
s/Ã /Ð/g
s/Ñ/Ñ/g
s/Ã’/Ò/g
s/Ó/Ó/g
s/Ô/Ô/g
s/Õ/Õ/g
s/Ö/Ö/g
s/×/×/g
s/Ø/Ø/g
s/Ù/Ù/g
s/Ú/Ú/g
s/Û/Û/g
s/Ãœ/Ü/g
s/Ã /Ý/g
s/Þ/Þ/g
s/ß/ß/g
s/Ã /à/g
s/á/á/g
s/â/â/g
s/ã/ã/g
s/ä/ä/g
s/Ã¥/å/g
s/æ/æ/g
s/ç/ç/g
s/è/è/g
s/é/é/g
s/ê/ê/g
s/ë/ë/g
s/ì/ì/g
s/í/í/g
s/î/î/g
s/ï/ï/g
s/ð/ð/g
s/ñ/ñ/g
s/ò/ò/g
s/ó/ó/g
s/ô/ô/g
s/õ/õ/g
s/ö/ö/g
s/÷/÷/g
s/ø/ø/g
s/ù/ù/g
s/ú/ú/g
s/û/û/g
s/ü/ü/g
s/ý/ý/g
s/þ/þ/g
s/ÿ/ÿ/g