codepage/gensubset.pl

   1 #!/usr/bin/perl
   2 #
   3 # Generate a subset of the UnicodeData.txt file, available from
   4 # ftp://ftp.unicode.org/Public/UNIDATA/UnicodeData.txt
   5 #
   6 # Usage:
   7 #   gensubset.pl [subset files] < UnicodeData.txt > MiniUCD.txt
   8 #
   9
  10 %need_these = ();
  11
  12 foreach $file (@ARGV) {
  13     open(F, '<', $file) or die;
  14     while (defined($line = <F>)) {
  15         $line =~ s/\s*(\#.*|)$//; # Remove comments and final blanks
  16         @f = split(/\s+/, $line);
  17         next if (scalar @f != 2);
  18         $need_these{hex $f[1]}++;
  19     }
  20     close(F);
  21 }
  22
  23 while (defined($line = <STDIN>)) {
  24     ($v, $l) = split(/;/, $line, 2);
  25     if ($v =~ /^([0-9a-f]+)\-([0-9a-f]+)$/i) {
  26         $r1 = hex $1;
  27         $r2 = hex $2;
  28     } elsif ($v =~ /^([0-9a-f]+)$/i) {
  29         $r1 = $r2 = hex $1;
  30     } else {
  31         next;
  32     }
  33     for ($r = $r1; $r <= $r2; $r++) {
  34         printf "%04X;%s", $r, $l if ($need_these{$r});
  35     }
  36 }
  37
  38