/usr/share/namazu/pl/extutf8.pl is in namazu2-index-tools 2.0.21-21.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 | #
# -*- Perl -*-
# $Id: extutf8.pl,v 1.1.4.5 2008-07-26 06:14:37 opengl2772 Exp $
# Copyright (C) 2008 Tadamasa Teranishi All rights reserved.
# Copyright (C) 2008 Namazu Project All rights reserved.
# This is free software with ABSOLUTELY NO WARRANTY.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either versions 2, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
# 02111-1307, USA
#
# This file must be encoded in EUC-JP encoding
#
package extutf8;
use strict;
use English;
require 'util.pl';
eval 'require NKF;';
use vars qw($utf8_to_eucjp $codeconv_document);
$utf8_to_eucjp = undef;
$codeconv_document = undef;
my $_converter = '';
my $_utfconvpath = undef;
my $_nkfversion = 0.00;
sub setup()
{
return 'yes' if (defined $codeconv_document);
if (!util::islang("ja")) {
$utf8_to_eucjp = \&_utf8_to_usascii;
$codeconv_document = \&_codeconv_document_usascii;
$_converter = 'to_usascii';
return 'yes';
}
eval '$_nkfversion = $NKF::VERSION;';
$_nkfversion = 0.00 if (!defined $_nkfversion);
if ($_nkfversion >= 2.04) {
$utf8_to_eucjp = \&_nkf_utf8_to_eucjp;
$codeconv_document = \&_nkf_codeconv_document;
$_converter = 'module_nkf';
return 'yes';
}
if ($English::PERL_VERSION >= 5.008) {
eval 'use Encode qw/from_to Unicode JP/;';
$utf8_to_eucjp = \&_encode_utf8_to_eucjp;
$codeconv_document = \&_encode_codeconv_document;
$_converter = 'module_encode';
return 'yes';
}
$_utfconvpath = util::checkcmd('lv');
if (defined $_utfconvpath) {
$utf8_to_eucjp = \&_lv_utf8_to_eucjp;
$codeconv_document = \&_lv_codeconv_document;
$_converter = 'lv';
return 'yes';
}
if (defined util::checklib('unicode.pl')) {
eval require 'unicode.pl';
$utf8_to_eucjp = \&_unicode_utf8_to_eucjp;
$codeconv_document = \&_unicode_codeconv_document;
$_converter = 'unicode.pl';
return 'yes';
}
return 'no';
}
sub converter()
{
return $_converter;
}
#
#
#
sub _utf8_to_usascii($)
{
my ($contref) = @_;
codeconv::tousascii($contref);
return $$contref;
}
sub _codeconv_document_usascii($)
{
my ($contref) = @_;
_utf8_to_usascii($contref);
codeconv::normalize_document($contref);
return $$contref;
}
#
# Conversion by "Encode"
# Perl 5.8 or later
#
sub _encode_utf8_to_eucjp($)
{
my ($contref) = @_;
Encode::from_to($$contref, "utf-8", "euc-jp");
return $$contref;
}
sub _encode_codeconv_document($)
{
my ($contref) = @_;
Encode::from_to($$contref, "utf-8", "euc-jp");
codeconv::normalize_eucjp_document($contref);
return $$contref;
}
#
# Conversion by "NKF Perl module"
# version 2.04 or later
#
sub _nkf_utf8_to_eucjp($)
{
my ($contref) = @_;
$$contref = NKF::nkf("-Wex", $$contref);
return $$contref;
}
sub _nkf_codeconv_document($)
{
my ($contref) = @_;
$$contref = NKF::nkf("-WemXZ1", $$contref);
codeconv::normalize_document($contref);
return $$contref;
}
#
# [obsolute] Conversion by "lv"
# It is slow.
#
sub _lv_utf8_to_eucjp($)
{
my ($contref) = @_;
my $tmpfile = util::tmpnam('NMZ.tmp.utf8');
{
my $fh = util::efopen("> $tmpfile");
print $fh $$contref;
util::fclose($fh);
}
$$contref = "";
my @cmd = ($_utfconvpath, "-Iu8", "-Oej", $tmpfile);
my $status = util::syscmd(
command => \@cmd,
option => {
"stdout" => $contref,
"stderr" => "/dev/null",
},
);
unlink $tmpfile;
return $$contref;
}
sub _lv_codeconv_document($)
{
my ($contref) = @_;
_lv_utf8_to_eucjp($contref);
codeconv::normalize_eucjp_document($contref);
return $$contref;
}
#
# [obsolute] Conversion by "unicode.pl"
#
sub _unicode_utf8_to_eucjp($)
{
my ($contref) = @_;
my @unicodeList = unicode::UTF8toUTF16($$contref);
$$contref = unicode::u2e(@unicodeList);
$$contref =~ s/\00//g;
return $$contref;
}
sub _unicode_codeconv_document($)
{
my ($contref) = @_;
_unicode_utf8_to_eucjp($contref);
codeconv::normalize_eucjp_document($contref);
return $$contref;
}
1;
|