| 1 | ##---------------------------------------------------------------------------## | ||
| 2 | ## File: | ||
| 3 | ## $Id: MapUTF8.pm,v 1.2 2003/03/05 22:17:15 ehood Exp $ | ||
| 4 | ## Author: | ||
| 5 | ## Earl Hood earl@earlhood.com | ||
| 6 | ## Description: | ||
| 7 | ## POD after __END__. | ||
| 8 | ##---------------------------------------------------------------------------## | ||
| 9 | ## Copyright (C) 2002 Earl Hood, earl@earlhood.com | ||
| 10 | ## | ||
| 11 | ## This program is free software; you can redistribute it and/or modify | ||
| 12 | ## it under the terms of the GNU General Public License as published by | ||
| 13 | ## the Free Software Foundation; either version 2 of the License, or | ||
| 14 | ## (at your option) any later version. | ||
| 15 | ## | ||
| 16 | ## This program is distributed in the hope that it will be useful, | ||
| 17 | ## but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| 18 | ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
| 19 | ## GNU General Public License for more details. | ||
| 20 | ## | ||
| 21 | ## You should have received a copy of the GNU General Public License | ||
| 22 | ## along with this program; if not, write to the Free Software | ||
| 23 | ## Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA | ||
| 24 | ## 02111-1307, USA | ||
| 25 | ##---------------------------------------------------------------------------## | ||
| 26 | |||
| 27 | package MHonArc::UTF8::MapUTF8; | ||
| 28 | |||
| 29 | use strict; | ||
| 30 | use Unicode::String; | ||
| 31 | use Unicode::MapUTF8; | ||
| 32 | use MHonArc::CharMaps; | ||
| 33 | |||
| 34 | our $VERSION = '2.6.24'; | ||
| 35 | |||
| 36 | sub clip { | ||
| 37 | use utf8; | ||
| 38 | my $str = \shift; # Prevent unnecessary copy. | ||
| 39 | my $len = shift; # Clip length | ||
| 40 | my $is_html = shift; # If entity references should be considered | ||
| 41 | my $has_tags = shift; # If html tags should be stripped | ||
| 42 | |||
| 43 | my $u = Unicode::String::utf8($$str); | ||
| 44 | |||
| 45 | if (!$is_html) { | ||
| 46 | return $u->substr(0, $len); | ||
| 47 | } | ||
| 48 | |||
| 49 | my $text = Unicode::String::utf8(''); | ||
| 50 | my $subtext; | ||
| 51 | my $html_len = $u->length; | ||
| 52 | my ($pos, $sublen, $real_len, $semi); | ||
| 53 | my $er_len = 0; | ||
| 54 | |||
| 55 | for ($pos = 0, $sublen = $len; $pos < $html_len;) { | ||
| 56 | $subtext = $u->substr($pos, $sublen); | ||
| 57 | $pos += $sublen; | ||
| 58 | |||
| 59 | # strip tags | ||
| 60 | if ($has_tags) { | ||
| 61 | # Strip full tags | ||
| 62 | $subtext =~ s/<[^>]*>//g; | ||
| 63 | # Check if clipped part of a tag | ||
| 64 | if ($subtext =~ s/<[^>]*\Z//) { | ||
| 65 | my $gt = $u->index('>', $pos); | ||
| 66 | $pos = ($gt < 0) ? $html_len : ($gt + 1); | ||
| 67 | } | ||
| 68 | } | ||
| 69 | |||
| 70 | # check for clipped entity reference | ||
| 71 | if (($pos < $html_len) && ($subtext =~ /\&[^;]*\Z/)) { | ||
| 72 | my $semi = $u->index(';', $pos); | ||
| 73 | if ($semi < 0) { | ||
| 74 | # malformed entity reference | ||
| 75 | $subtext .= $u->substr($pos); | ||
| 76 | $pos = $html_len; | ||
| 77 | } else { | ||
| 78 | $subtext .= $u->substr($pos, $semi - $pos + 1); | ||
| 79 | $pos = $semi + 1; | ||
| 80 | } | ||
| 81 | } | ||
| 82 | |||
| 83 | # compute entity reference lengths to determine "real" character | ||
| 84 | # count and not raw character count. | ||
| 85 | while ($subtext =~ /(\&[^;]+);/g) { | ||
| 86 | $er_len += length($1); | ||
| 87 | } | ||
| 88 | |||
| 89 | $text .= $subtext; | ||
| 90 | |||
| 91 | # done if we have enough | ||
| 92 | $real_len = $text->length - $er_len; | ||
| 93 | if ($real_len >= $len) { | ||
| 94 | last; | ||
| 95 | } | ||
| 96 | $sublen = $len - ($text->length - $er_len); | ||
| 97 | } | ||
| 98 | $text; | ||
| 99 | } | ||
| 100 | |||
| 101 | sub to_utf8 { | ||
| 102 | my $text = shift; | ||
| 103 | my $charset = lc shift; | ||
| 104 | my $text_r = ref($text) ? $text : \$text; | ||
| 105 | |||
| 106 | if (Unicode::MapUTF8::utf8_supported_charset($charset)) { | ||
| 107 | return Unicode::MapUTF8::to_utf8( | ||
| 108 | {-string => $$text_r, -charset => $charset}); | ||
| 109 | } | ||
| 110 | # Invoke fallback implementation. | ||
| 111 | require MHonArc::UTF8::MhaEncode; | ||
| 112 | return MHonArc::UTF8::MhaEncode::to_utf8($text_r, $charset); | ||
| 113 | } | ||
| 114 | |||
| 115 | sub str2sgml { | ||
| 116 | my $text = shift; | ||
| 117 | my $charset = lc shift; | ||
| 118 | my $text_r = ref($text) ? $text : \$text; | ||
| 119 | |||
| 120 | if ($charset eq 'us-ascii') { | ||
| 121 | if ($$text_r =~ /[\x80-\xFF]/) { | ||
| 122 | $charset = 'iso-8859-1'; | ||
| 123 | } else { | ||
| 124 | $$text_r =~ s/([$HTMLSpecials])/$HTMLSpecials{$1}/go; | ||
| 125 | return $$text_r; | ||
| 126 | } | ||
| 127 | } | ||
| 128 | if ($charset eq 'utf-8' || $charset eq 'utf8') { | ||
| 129 | $$text_r =~ s/([$HTMLSpecials])/$HTMLSpecials{$1}/go; | ||
| 130 | return $$text_r; | ||
| 131 | } | ||
| 132 | if ($charset eq 'utf-8' || $charset eq 'utf8') { | ||
| 133 | $$text_r =~ s/([$HTMLSpecials])/$HTMLSpecials{$1}/go; | ||
| 134 | return $$text_r; | ||
| 135 | } | ||
| 136 | if (Unicode::MapUTF8::utf8_supported_charset($charset)) { | ||
| 137 | $$text_r = Unicode::MapUTF8::to_utf8( | ||
| 138 | {-string => $$text_r, -charset => $charset}); | ||
| 139 | $$text_r =~ s/([$HTMLSpecials])/$HTMLSpecials{$1}/go; | ||
| 140 | return $$text_r; | ||
| 141 | } | ||
| 142 | # Invoke fallback implementation. | ||
| 143 | require MHonArc::UTF8::MhaEncode; | ||
| 144 | return MHonArc::UTF8::MhaEncode::str2sgml($text_r, $charset); | ||
| 145 | } | ||
| 146 | |||
| 147 | ##---------------------------------------------------------------------------## | ||
| 148 | 1; | ||
| 149 | __END__ |