package HTML::Entities; # $Id: Entities.pm,v 1.8 1996/09/06 07:18:46 aas Exp $ =head1 NAME decode - Expand HTML entities in a string encode - Encode chars in a string using HTML entities =head1 SYNOPSIS use HTML::Entities; $a = "Våre norske tegn bør æres"; decode_entities($a); encode_entities($a, "\200-\377"); =head1 DESCRIPTION The decode_entities() routine replaces valid HTML entities found in the string with the corresponding ISO-8859/1 character. The encode_entities() routine replaces the characters specified by the second argument with their entity representation. The default set of characters to expand are control chars, high-bit chars and the '<', '&', '>' and '"' character. Both routines modify the string passed in as the first argument and return it. If you prefer not to import these routines into your namespace you can call them as: use HTML::Entities (); $encoded = HTML::Entities::encode($a); $decoded = HTML::Entities::decode($a); The module can also export the %char2entity and the %entity2char hashes which contains the mapping from all characters to the corresponding entities. =head1 COPYRIGHT Copyright 1995, 1996 Gisle Aas. All rights reserved. This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself. =head1 AUTHOR Gisle Aas =cut require Exporter; @ISA = qw(Exporter); @EXPORT = qw(encode_entities decode_entities); @EXPORT_OK = qw(%entity2char %char2entity); $VERSION = sprintf("%d.%02d", q$Revision: 1.8 $ =~ /(\d+)\.(\d+)/); sub Version { $VERSION; } %entity2char = ( # Some normal chars that have special meaning in SGML context amp => '&', # ampersand 'gt' => '>', # greater than 'lt' => '<', # less than quot => '"', # double quote # PUBLIC ISO 8879-1986//ENTITIES Added Latin 1//EN//HTML AElig => 'Æ', # capital AE diphthong (ligature) Aacute => 'Á', # capital A, acute accent Acirc => 'Â', # capital A, circumflex accent Agrave => 'À', # capital A, grave accent Aring => 'Å', # capital A, ring Atilde => 'Ã', # capital A, tilde Auml => 'Ä', # capital A, dieresis or umlaut mark Ccedil => 'Ç', # capital C, cedilla ETH => 'Ð', # capital Eth, Icelandic Eacute => 'É', # capital E, acute accent Ecirc => 'Ê', # capital E, circumflex accent Egrave => 'È', # capital E, grave accent Euml => 'Ë', # capital E, dieresis or umlaut mark Iacute => 'Í', # capital I, acute accent Icirc => 'Î', # capital I, circumflex accent Igrave => 'Ì', # capital I, grave accent Iuml => 'Ï', # capital I, dieresis or umlaut mark Ntilde => 'Ñ', # capital N, tilde Oacute => 'Ó', # capital O, acute accent Ocirc => 'Ô', # capital O, circumflex accent Ograve => 'Ò', # capital O, grave accent Oslash => 'Ø', # capital O, slash Otilde => 'Õ', # capital O, tilde Ouml => 'Ö', # capital O, dieresis or umlaut mark THORN => 'Þ', # capital THORN, Icelandic Uacute => 'Ú', # capital U, acute accent Ucirc => 'Û', # capital U, circumflex accent Ugrave => 'Ù', # capital U, grave accent Uuml => 'Ü', # capital U, dieresis or umlaut mark Yacute => 'Ý', # capital Y, acute accent aacute => 'á', # small a, acute accent acirc => 'â', # small a, circumflex accent aelig => 'æ', # small ae diphthong (ligature) agrave => 'à', # small a, grave accent aring => 'å', # small a, ring atilde => 'ã', # small a, tilde auml => 'ä', # small a, dieresis or umlaut mark ccedil => 'ç', # small c, cedilla eacute => 'é', # small e, acute accent ecirc => 'ê', # small e, circumflex accent egrave => 'è', # small e, grave accent eth => 'ð', # small eth, Icelandic euml => 'ë', # small e, dieresis or umlaut mark iacute => 'í', # small i, acute accent icirc => 'î', # small i, circumflex accent igrave => 'ì', # small i, grave accent iuml => 'ï', # small i, dieresis or umlaut mark ntilde => 'ñ', # small n, tilde oacute => 'ó', # small o, acute accent ocirc => 'ô', # small o, circumflex accent ograve => 'ò', # small o, grave accent oslash => 'ø', # small o, slash otilde => 'õ', # small o, tilde ouml => 'ö', # small o, dieresis or umlaut mark szlig => 'ß', # small sharp s, German (sz ligature) thorn => 'þ', # small thorn, Icelandic uacute => 'ú', # small u, acute accent ucirc => 'û', # small u, circumflex accent ugrave => 'ù', # small u, grave accent uuml => 'ü', # small u, dieresis or umlaut mark yacute => 'ý', # small y, acute accent yuml => 'ÿ', # small y, dieresis or umlaut mark # Some extra Latin 1 chars that are listed in the HTML3.2 draft (21-May-96) copy => '©', # copyright sign reg => '®', # registered sign nbsp => "\240", # non breaking space # Additional ISO-8859/1 entities listed in rfc1866 (section 14) iexcl => '¡', cent => '¢', pound => '£', curren => '¤', yen => '¥', brvbar => '¦', sect => '§', uml => '¨', ordf => 'ª', laquo => '«', 'not' => '¬', # not is a keyword in perl shy => '­', macr => '¯', deg => '°', plusmn => '±', sup1 => '¹', sup2 => '²', sup3 => '³', acute => '´', micro => 'µ', para => '¶', middot => '·', cedil => '¸', ordm => 'º', raquo => '»', frac14 => '¼', frac12 => '½', frac34 => '¾', iquest => '¿', 'times' => '×', # times is a keyword in perl divide => '÷', ); # Make the oposite mapping while (($entity, $char) = each(%entity2char)) { $char2entity{$char} = "&$entity;"; } # Fill inn missing entities for (0 .. 255) { next if exists $char2entity{chr($_)}; $char2entity{chr($_)} = "&#$_;"; } sub decode_entities { for (@_) { s/(&\#(\d+);?)/$2 < 256 ? chr($2) : $1/eg; s/(&(\w+);?)/$entity2char{$2} || $1/eg; } $_[0]; } sub encode_entities { if (defined $_[1]) { unless (exists $subst{$_[1]}) { # Because we can't compile regex we fake it with a cached sub $subst{$_[1]} = eval "sub {\$_[0] =~ s/([$_[1]])/\$char2entity{\$1}/g; }"; die $@ if $@; } &{$subst{$_[1]}}($_[0]); } else { # Encode control chars, high bit chars and '<', '&', '>', '"' $_[0] =~ s/([^\n\t !\#\$%\'-;=?-~])/$char2entity{$1}/g; } $_[0]; } # Set up aliases *encode = \&encode_entities; *decode = \&decode_entities; 1;