unicode/mkiso8859.pl

   1 # Copyright 2000-2006 Double Precision, Inc.
   2 # See COPYING for distribution information.
   3 #
   4 # $Id: mkiso8859.pl,v 1.7 2006/03/25 14:24:43 mrsam Exp $
   5 #
   6 # Generate iso-8859* unicode tables
   7
   8 my $set=shift;
   9
  10 open (U, "UnicodeData.txt") || die "$!\n";
  11
  12 while (<U>)
  13 {
  14         chomp;
  15
  16 my @fields= split /;/;
  17
  18 my ($code, $uc, $lc, $tc);
  19
  20         $code="0x$fields[0]";
  21         eval "\$code=$code;";
  22
  23         $uc=$fields[12];
  24         if ($uc ne "")
  25         {
  26                 eval "\$uc=0x$uc;";
  27                 $UC{$code}=$uc;
  28         }
  29
  30         $lc=$fields[13];
  31         if ($lc ne "")
  32         {
  33                 eval "\$lc=0x$lc;";
  34                 $LC{$code}=$lc;
  35         }
  36
  37         $tc=$fields[14];
  38         if ($tc ne "")
  39         {
  40                 eval "\$tc=0x$tc;";
  41                 $TC{$code}=$tc;
  42         }
  43 }
  44
  45 close(U);
  46
  47 my @fwd;
  48
  49 my $rev;
  50
  51 open (SET, $set) || die "$set: $!\n";
  52 while (<SET>)
  53 {
  54         chomp;
  55         s/\#.*//;
  56
  57 my ($code, $unicode)=split /[ \t]+/;
  58
  59         next unless $code ne "";
  60
  61         eval "\$code=$code;";
  62         eval "\$unicode=$unicode;";
  63
  64         die if $code < 0 || $code > 255;
  65
  66         $fwd[$code]=$unicode;
  67         $rev{$unicode}=$code;
  68 }
  69 close(SET);
  70
  71 my $fwdname=shift;
  72
  73 print '
  74 /*
  75 ** Copyright 2000-2006 Double Precision, Inc.
  76 ** See COPYING for distribution information.
  77 **
  78 ** $Id: mkiso8859.pl,v 1.7 2006/03/25 14:24:43 mrsam Exp $
  79 */
  80
  81 #include "unicode.h"
  82 ';
  83
  84
  85 print "static const unicode_char $fwdname [128]={\n";
  86
  87 for ($i=0; $i<128; $i++)
  88 {
  89     die "Unicode map not US-ASCII: $i\n" unless $fwd[$i] == $i;
  90 }
  91
  92 for ($i=128; $i<256; $i++)
  93 {
  94 my $n=$fwd[$i];
  95
  96         $n=0 unless $n;
  97
  98         print "$n";
  99         print "," if $i < 255;
 100         print "\n" if ($i % 16) == 15;
 101 }
 102
 103 print "};\n";
 104
 105 my $ucname=shift;
 106
 107 print "static const char $ucname [256]={\n";
 108
 109 for ($i=0; $i<256; $i++)
 110 {
 111 my $unicode=$fwd[$i];
 112
 113         $unicode=$UC{$unicode} && $rev{$UC{$unicode}} ? $rev{$UC{$unicode}}:$i;
 114
 115         printf("(char)0x%02x", $unicode);
 116         print "," if $i < 255;
 117         print "\n" if ($i % 8) == 7;
 118 }
 119
 120 print "};\n";
 121
 122 my $lcname=shift;
 123
 124 print "static const char $lcname [256]={\n";
 125
 126 for ($i=0; $i<256; $i++)
 127 {
 128 my $unicode=$fwd[$i];
 129
 130         $unicode=$LC{$unicode} && $rev{$LC{$unicode}} ? $rev{$LC{$unicode}}:$i;
 131
 132         printf("(char)0x%02x", $unicode);
 133         print "," if $i < 255;
 134         print "\n" if ($i % 8) == 7;
 135 }
 136
 137 print "};\n";
 138
 139 my $tcname=shift;
 140
 141 print "static const char $tcname [256]={\n";
 142
 143 for ($i=0; $i<256; $i++)
 144 {
 145 my $unicode=$fwd[$i];
 146
 147         $unicode=$TC{$unicode} && $rev{$TC{$unicode}} ? $rev{$TC{$unicode}}:$i;
 148
 149         printf("(char)0x%02x", $unicode);
 150         print "," if $i < 255;
 151         print "\n" if ($i % 8) == 7;
 152 }
 153
 154 my $structname=shift;
 155 my $chsetname=shift;
 156
 157 print "};
 158
 159
 160 static unicode_char *c2u(const struct unicode_info *u, const char *cp, int *ip)
 161 {
 162         return (unicode_iso8859_c2u(cp, ip, $fwdname));
 163 }
 164
 165 static char *u2c(const struct unicode_info *u, const unicode_char *cp, int *ip)
 166 {
 167         return ("
 168 .
 169 ($set eq "windows-874.txt" ? "unicode_windows874_u2c":"unicode_iso8859_u2c")
 170 . "(cp, ip, $fwdname));
 171 }
 172
 173 static char *toupper_func(const struct unicode_info *u, const char *cp, int *ip)
 174 {
 175         return (unicode_iso8859_convert(cp, ip, $ucname));
 176 }
 177
 178 static char *tolower_func(const struct unicode_info *u, const char *cp, int *ip)
 179 {
 180         return (unicode_iso8859_convert(cp, ip, $lcname));
 181 }
 182
 183 static char *totitle_func(const struct unicode_info *u, const char *cp, int *ip)
 184 {
 185         return (unicode_iso8859_convert(cp, ip, $tcname));
 186 }
 187
 188 const struct unicode_info $structname = {
 189         \"$chsetname\"," . ($set =~ /^8859*/ || $set =~ /^windows-12/ ? "
 190         UNICODE_USASCII |
 191         UNICODE_HEADER_QUOPRI | UNICODE_BODY_QUOPRI," :
 192  $set eq "windows-874.txt" ? "
 193         UNICODE_USASCII |
 194         UNICODE_HEADER_BASE64 | UNICODE_BODY_BASE64," :"
 195         UNICODE_USASCII,") . "
 196         c2u,
 197         u2c,
 198         toupper_func,
 199         tolower_func,
 200         totitle_func};
 201 ";