1#! /usr/local/bin/perl 2# 3# $FreeBSD$ 4# 5# This file and its contents are supplied under the terms of the 6# Common Development and Distribution License ("CDDL"), version 1.0. 7# You may only use this file in accordance with the terms of version 8# 1.0 of the CDDL. 9# 10# A full copy of the text of the CDDL should have accompanied this 11# source. A copy is of the CDDL is also available via the Internet 12# at http://www.illumos.org/license/CDDL. 13# 14 15# 16# Copyright 2010 Nexenta Systems, Inc. All rights reserved. 17# Copyright 2015 John Marino <draco@marino.st> 18# 19 20# This converts MAPPING files to localedef character maps 21# suitable for use with the UTF-8 derived localedef data. 22 23sub ucs_to_utf8 24{ 25 my $ucs = shift; 26 my $utf8; 27 28 if ($ucs <= 0x7f) { 29 $utf8 = sprintf("\\x%02X", $ucs).$utf8; 30 } elsif ($ucs <= 0x7ff) { 31 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 32 $ucs >>= 6; 33 $utf8 = sprintf("\\x%02X", $ucs | 0xc0).$utf8; 34 35 } elsif ($ucs <= 0xffff) { 36 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 37 $ucs >>= 6; 38 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 39 $ucs >>= 6; 40 $utf8 = sprintf("\\x%02X", $ucs | 0xe0).$utf8; 41 42 } elsif ($ucs <= 0x1fffff) { 43 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 44 $ucs >>= 6; 45 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 46 $ucs >>= 6; 47 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 48 $ucs >>= 6; 49 $utf8 = sprintf("\\x%02X", $ucs | 0xf0).$utf8; 50 51 } elsif ($ucs <= 0x03ffffff) { 52 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 53 $ucs >>= 6; 54 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 55 $ucs >>= 6; 56 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 57 $ucs >>= 6; 58 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 59 $ucs >>= 6; 60 $utf8 = sprintf("\\x%02X", $ucs | 0xf8).$utf8; 61 62 } else { 63 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 64 $ucs >>= 6; 65 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 66 $ucs >>= 6; 67 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 68 $ucs >>= 6; 69 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 70 $ucs >>= 6; 71 $utf8 = sprintf("\\x%02X", ($ucs & 0x3f) | 0x80).$utf8; 72 $ucs >>= 6; 73 $utf8 = sprintf("\\x%02X", $ucs | 0xf8).$utf8; 74 } 75 76 return ($utf8); 77} 78 79my %unames; 80my %uvalues; 81 82# 83# This is not a general purpose Character Map parser, but its good enough 84# for the stock one supplied with CLDR. 85# 86sub load_utf8_cm 87{ 88 my $file = shift; 89 90 open(UTF8, "$file") || die "open"; 91 92 while (<UTF8>) { 93 next if (/^#/); 94 next if (/^\s*$/); 95 next if (/^\s*CHARMAP\s*$/); 96 next if (/^\s*END\s*CHARMAP\s*$/); 97 chomp; 98 @words = split /\s+/; 99 $name = $words[0]; 100 $utf8val = $words[1]; 101 102 if (defined($unames{$utf8val})) { 103 $unames{$utf8val} .= "\n" .$name; 104 } else { 105 $unames{$utf8val} = $name; 106 } 107 $uvalues{$name} = $utf8val; 108 } 109 close(UTF8); 110} 111 112my %map; 113 114sub load_map 115{ 116 my $file = shift; 117 118 open(MAP, "$file") || die "open"; 119 120 while (<MAP>) { 121 next if (/^#/); 122 next if (/^\s*$/); 123 next if (/^0x..\+0x../); 124 next if (/^0x[0-9A-F]{4}\t0x[0-9A-F]{4} 0x[0-9A-F]{4}/); 125 next if (/^0x[0-9A-F]{2}\s+#/); 126 next if (/# ... NO MAPPING .../); 127 chomp; 128 @words = split /\s+/; 129 $utf8 = $words[1]; 130 $utf8 =~ s/^\\x[0]*//; 131 $utf8 = ucs_to_utf8(hex($utf8)); 132 $val = $words[0]; 133 if (defined ($map{$val})) { 134 $map{$val} .= " ".$utf8; 135 } else { 136 $map{$val} = $utf8; 137 } 138 } 139} 140 141sub mb_str 142{ 143 my $val = shift; 144 my $str = ""; 145 $val = hex($val); 146 147 if ($val == 0) { 148 return ("\\x00"); 149 } 150 while ($val) { 151 $str = sprintf("\\x%02x", $val & 0xff).$str; 152 $val >>= 8; 153 } 154 return ($str); 155} 156 157$mf = shift(@ARGV); 158$codeset = shift(@ARGV); 159my $max_mb; 160 161load_utf8_cm("etc/final-maps/map.UTF-8"); 162load_map($mf); 163 164 165 if ($codeset eq "SJIS") { $max_mb = 2 } 166elsif ($codeset eq "eucCN") { $max_mb = 2 } 167elsif ($codeset eq "eucJP") { $max_mb = 3 } 168elsif ($codeset eq "eucKR") { $max_mb = 2 } 169elsif ($codeset eq "GBK") { $max_mb = 2 } 170elsif ($codeset eq "GB2312") { $max_mb = 2 } 171elsif ($codeset eq "Big5") { $max_mb = 2 } 172else { $max_mb = 1 }; 173print("<code_set_name> \"$codeset\"\n"); 174print("<mb_cur_min> 1\n"); 175print("<mb_cur_max> $max_mb\n"); 176 177print("CHARMAP\n"); 178foreach $val (sort (keys (%map))) { 179 #$utf8 = $map{$val}; 180 foreach $utf8 (split / /, $map{$val}) { 181 $ref = $unames{$utf8}; 182 foreach $name (sort (split /\n/, $ref)) { 183 print "$name"; 184 my $nt = int((64 - length($name) + 7) / 8); 185 while ($nt) { 186 print "\t"; 187 $nt--; 188 } 189 print mb_str($val)."\n"; 190 } 191 } 192} 193print "END CHARMAP\n"; 194