mk_combining_map.pl (3548B)
1 2 open(C, "ucs_combining.map"); 3 while(<C>) { 4 /^\s*\{/ || next; 5 /\{\s*(\w+),\s*(\w+)\s*\}/; 6 ($a, $b) = ($1, $2); 7 for $c (hex($a) .. hex($b)) { 8 $COMB{$c} = 1; 9 } 10 } 11 close(C); 12 13 @NAME = (); 14 while(<DATA>) { 15 chop; 16 s/\s*$//; 17 (($n, $m, $c) = split(" ", $_, 3)) >= 3 || next; 18 push(@NAME, $n); 19 $MAP{$n} = $m; 20 $CODE{$n} = $c; 21 } 22 23 foreach $name (@NAME) { 24 25 $code = $CODE{$name}; 26 $map = $MAP{$name}; 27 28 print "$name\t$map\t$code\n"; 29 30 @to_ucs = (); 31 %from_ucs = (); 32 open(MAP, "< $map"); 33 while(<MAP>) { 34 /^#/ && next; 35 s/#.*//; 36 (($i, $u) = split(" ")) || next; 37 $i = hex($i); 38 $u = hex($u); 39 if ($u >= 0xa0) { 40 $to_ucs[$i] = $u; 41 if ($i < 0x80) { 42 print STDERR "$map $i $u\n"; 43 # $from_ucs{$u} = $i; 44 } else { 45 $from_ucs{$u} = $i; 46 } 47 } 48 } 49 close(MAP); 50 51 $ok = 0; 52 @comb = (); 53 foreach $i (0x80 .. 0xFF) { 54 $comb[$i] = $COMB{$to_ucs[$i]} ? 1 : 0; 55 $comb[$i] && ($ok = 1); 56 } 57 $ok || next; 58 59 open(OUT, "> ${name}_combining.map"); 60 print OUT <<EOF; 61 /* $code */ 62 63 static wc_uint8 ${name}_combining_map[ 0x80 ] = { 64 EOF 65 66 foreach $i (0x8 .. 0xF) { 67 print OUT " "; 68 foreach $j (0 .. 0xF) { 69 $_ = $i * 16 + $j; 70 print OUT " $comb[$_],"; 71 } 72 print OUT "\n"; 73 } 74 75 print OUT <<EOF; 76 }; 77 EOF 78 79 } 80 81 __END__ 82 jisx0201k EASTASIA/JIS/JIS0201.TXT JIS X 0201 (Japanese Kana) 83 iso88591 ISO8859/8859-1.TXT ISO-8859-1 (Latin 1) 84 iso88592 ISO8859/8859-2.TXT ISO-8859-2 (Latin 2) 85 iso88593 ISO8859/8859-3.TXT ISO-8859-3 (Latin 3) 86 iso88594 ISO8859/8859-4.TXT ISO-8859-4 (Latin 4) 87 iso88595 ISO8859/8859-5.TXT ISO-8859-5 (Cyrillic) 88 iso88596 ISO8859/8859-6.TXT ISO-8859-6 (Arabic) 89 iso88597 ISO8859/8859-7.TXT ISO-8859-7 (Greek) 90 iso88598 ISO8859/8859-8.TXT ISO-8859-8 (Hebrew) 91 iso88599 ISO8859/8859-9.TXT ISO-8859-9 (Latin 5) 92 iso885910 ISO8859/8859-10.TXT ISO-8859-10 (Latin 6) 93 iso885911 VENDORS/MICSFT/WINDOWS/CP874.TXT ISO-8859-11 (Vietnamese) 94 iso885913 ISO8859/8859-13.TXT ISO-8859-13 (Latin 7) 95 iso885914 ISO8859/8859-14.TXT ISO-8859-14 (Latin 8) 96 iso885915 ISO8859/8859-15.TXT ISO-8859-15 (Latin 9) 97 98 cp856 VENDORS/MISC/CP856.TXT CP856 (Hebrew) 99 cp1006 VENDORS/MISC/CP1006.TXT IBM CP1006 (Arabic) 100 koi8r VENDORS/MISC/KOI8-R.TXT KOI8-R (Cyrillic) 101 102 nextstep VENDORS/NEXT/NEXTSTEP.TXT NeXTSTEP 103 104 cp437 VENDORS/MICSFT/PC/CP437.TXT CP437 (Latin) 105 cp737 VENDORS/MICSFT/PC/CP737.TXT CP737 (Greek) 106 cp775 VENDORS/MICSFT/PC/CP775.TXT CP775 (Baltic Rim) 107 cp850 VENDORS/MICSFT/PC/CP850.TXT CP850 (Latin 1) 108 cp852 VENDORS/MICSFT/PC/CP852.TXT CP852 (Latin 2) 109 cp855 VENDORS/MICSFT/PC/CP855.TXT CP855 (Cyrillic) 110 cp857 VENDORS/MICSFT/PC/CP857.TXT CP857 (Turkish) 111 cp860 VENDORS/MICSFT/PC/CP860.TXT CP860 (Portuguese) 112 cp861 VENDORS/MICSFT/PC/CP861.TXT CP861 (Icelandic) 113 cp862 VENDORS/MICSFT/PC/CP862.TXT CP862 (Hebrew) 114 cp863 VENDORS/MICSFT/PC/CP863.TXT CP863 (Canada French) 115 cp864 VENDORS/MICSFT/PC/CP864.TXT CP864 (Arabic) 116 cp865 VENDORS/MICSFT/PC/CP865.TXT CP865 (Nordic) 117 cp866 VENDORS/MICSFT/PC/CP866.TXT CP866 (Cyrillic Russian) 118 cp869 VENDORS/MICSFT/PC/CP869.TXT CP869 (Greek 2) 119 cp874 VENDORS/MICSFT/PC/CP874.TXT CP874 (Thai) 120 121 cp1250 VENDORS/MICSFT/WINDOWS/CP1250.TXT CP1250 (Latin 2) 122 cp1251 VENDORS/MICSFT/WINDOWS/CP1251.TXT CP1251 (Cyrillic) 123 cp1252 VENDORS/MICSFT/WINDOWS/CP1252.TXT CP1252 (Latin 1) 124 cp1253 VENDORS/MICSFT/WINDOWS/CP1253.TXT CP1253 (Greek) 125 cp1254 VENDORS/MICSFT/WINDOWS/CP1254.TXT CP1254 (Turkish) 126 cp1255 VENDORS/MICSFT/WINDOWS/CP1255.TXT CP1255 (Hebrew) 127 cp1256 VENDORS/MICSFT/WINDOWS/CP1256.TXT CP1256 (Arabic) 128 cp1257 VENDORS/MICSFT/WINDOWS/CP1257.TXT CP1257 (Baltic Rim) 129 cp1258 VENDORS/MICSFT/WINDOWS/CP1258.TXT CP1258 (Vietnamese) 130