| 1 | # Copyright 2000-2002 Double Precision, Inc. |
| 2 | # See COPYING for distribution information. |
| 3 | # |
| 4 | # $Id: mkibm864.pl,v 1.2 2002/11/18 00:54:22 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 2000-2002 Double Precision, Inc. |
| 76 | ** See COPYING for distribution information. |
| 77 | ** |
| 78 | ** $Id: mkibm864.pl,v 1.2 2002/11/18 00:54:22 mrsam Exp $ |
| 79 | */ |
| 80 | |
| 81 | #include "unicode.h" |
| 82 | '; |
| 83 | |
| 84 | |
| 85 | print "static const unicode_char $fwdname [256]={\n"; |
| 86 | |
| 87 | for ($i=0; $i<256; $i++) |
| 88 | { |
| 89 | my $n=$fwd[$i]; |
| 90 | |
| 91 | $n=0 unless $n; |
| 92 | |
| 93 | print "$n"; |
| 94 | print "," if $i < 255; |
| 95 | print "\n" if ($i % 16) == 15; |
| 96 | } |
| 97 | |
| 98 | print "};\n"; |
| 99 | |
| 100 | my $ucname=shift; |
| 101 | |
| 102 | print "static const char $ucname [256]={\n"; |
| 103 | |
| 104 | for ($i=0; $i<256; $i++) |
| 105 | { |
| 106 | my $unicode=$fwd[$i]; |
| 107 | |
| 108 | $unicode=$UC{$unicode} && $rev{$UC{$unicode}} ? $rev{$UC{$unicode}}:$i; |
| 109 | |
| 110 | printf("(char)0x%02x", $unicode); |
| 111 | print "," if $i < 255; |
| 112 | print "\n" if ($i % 8) == 7; |
| 113 | } |
| 114 | |
| 115 | print "};\n"; |
| 116 | |
| 117 | my $lcname=shift; |
| 118 | |
| 119 | print "static const char $lcname [256]={\n"; |
| 120 | |
| 121 | for ($i=0; $i<256; $i++) |
| 122 | { |
| 123 | my $unicode=$fwd[$i]; |
| 124 | |
| 125 | $unicode=$LC{$unicode} && $rev{$LC{$unicode}} ? $rev{$LC{$unicode}}:$i; |
| 126 | |
| 127 | printf("(char)0x%02x", $unicode); |
| 128 | print "," if $i < 255; |
| 129 | print "\n" if ($i % 8) == 7; |
| 130 | } |
| 131 | |
| 132 | print "};\n"; |
| 133 | |
| 134 | my $tcname=shift; |
| 135 | |
| 136 | print "static const char $tcname [256]={\n"; |
| 137 | |
| 138 | for ($i=0; $i<256; $i++) |
| 139 | { |
| 140 | my $unicode=$fwd[$i]; |
| 141 | |
| 142 | $unicode=$TC{$unicode} && $rev{$TC{$unicode}} ? $rev{$TC{$unicode}}:$i; |
| 143 | |
| 144 | printf("(char)0x%02x", $unicode); |
| 145 | print "," if $i < 255; |
| 146 | print "\n" if ($i % 8) == 7; |
| 147 | } |
| 148 | |
| 149 | my $structname=shift; |
| 150 | my $chsetname=shift; |
| 151 | |
| 152 | print "}; |
| 153 | |
| 154 | |
| 155 | static unicode_char *c2u(const struct unicode_info *u, const char *cp, int *ip) |
| 156 | { |
| 157 | return (unicode_ibm864_c2u(cp, ip, $fwdname)); |
| 158 | } |
| 159 | |
| 160 | static char *u2c(const struct unicode_info *u, const unicode_char *cp, int *ip) |
| 161 | { |
| 162 | return (unicode_ibm864_u2c(cp, ip, $fwdname)); |
| 163 | } |
| 164 | |
| 165 | static char *toupper_func(const struct unicode_info *u, const char *cp, int *ip) |
| 166 | { |
| 167 | return (unicode_iso8859_convert(cp, ip, $ucname)); |
| 168 | } |
| 169 | |
| 170 | static char *tolower_func(const struct unicode_info *u, const char *cp, int *ip) |
| 171 | { |
| 172 | return (unicode_iso8859_convert(cp, ip, $lcname)); |
| 173 | } |
| 174 | |
| 175 | static char *totitle_func(const struct unicode_info *u, const char *cp, int *ip) |
| 176 | { |
| 177 | return (unicode_iso8859_convert(cp, ip, $tcname)); |
| 178 | } |
| 179 | |
| 180 | const struct unicode_info $structname = { |
| 181 | \"$chsetname\", |
| 182 | 0, |
| 183 | c2u, |
| 184 | u2c, |
| 185 | toupper_func, |
| 186 | tolower_func, |
| 187 | totitle_func}; |
| 188 | "; |