/usr/share/doc/libunicode-map-perl/examples/mkCSGB2312

#!/usr/bin/perl
#
# Create a character mapping for GB2312 encoding.
# usage: mkCSGB2312.pl
#
# Requires the map file GB2312.TXT (mapping actually GB2312-80) in the
# current directory, produces the map file CSGB2312.TXT 
#
# Copyright (C) 2000 Martin Schwartz. All rights reserved.
# This program is free software; you can redistribute it and/or
# modify it under the same terms as Perl itself.
#
# Contact: Martin Schwartz <martin@nacho.de>
#

my $info = <<END;
#
# GB2312 to Unicode table; a mixed one byte, two byte mapping.
#
# NOTE: This file is generated automatically from GB2312.TXT by mkCSGB2312
# It is constructed from the mappings of:
#
#     - ISO8859-1 characters 0x0000 .. 0x00FF
#
#     - GB2312-80 characters in EUC form.
#
# Actually GB2312 should not incorporate the whole ISO8859-1 set, but only the
# Unicode characters 0x0020 to 0x007f. World's usage is different...
# As an effect of this a round trip conversion GB2312 -> UTF16 -> GB2312 will
# produce differences if the original GB2312 encoding contains one or more
# of these ISO-8859-1 one byte characters:
# 
#     0xA4, 0xA7, 0xA8, 0xB0, 0xB1, 0xD7, 0xE0, 0xE1, 0xE8, 0xE9,
#     0xEA, 0xEC, 0xED, 0xF2, 0xF3, 0xF7, 0xF9, 0xFA, 0xFC
#     
# Anyway these differences shouldn't cause rendering problems, since the
# translation back to GB2312 for these characters will utilize an original
# character of set GB2312-80.
#  
# martin [2000-Jun-19]
#
END

use strict;

main: {
    print "Creating GB2312 encoding, based on GB2312-80 encoding.\n";
    _open ( );
    _createInfo ( );
    _createMapping ( );
    _close ( );
    print "Done. Saved as CSGB2312.TXT\n";
}

sub _open {
    open ( GB2312, "GB2312.TXT" )
        or die "Can't open input file GB2312.TXT! ($!)"
    ;
    open ( CSGB2312, ">CSGB2312.TXT" )
        or die "Can't open output file CSGB2312.TXT! ($!)"
    ;
}

sub _createInfo {
    print CSGB2312 $info;
}

sub _createMapping {
    print CSGB2312 "\n# ISO-8859-1 characters (0x0000-0x00ff):\n\n";
    for ( 0x00 .. 0xff ) {
        printf CSGB2312 "0x%02x\t0x%04x\n", $_, $_;
    }

    # print CSGB2312 "\n\n# Unambiguous ISO-8859-1 characters:\n\n";
    # for (
    #     0x80..0xa3, 0xa5..0xa6, 0xa9..0xaf, 0xb2..0xd6, 
    #     0xd8..0xdf, 0xe2..0xe7, 0xeb, 0xee..0xf1, 0xf4..0xf6,
    #     0xf8, 0xfb, 0xfd, 0xfe, 0xff
    # ) {
    #     printf CSGB2312 "0x%02x\t0x%04x\n", $_, $_;
    # }

    print CSGB2312 "\n\n# GB2312-80 characters:\n\n";
    while ( <GB2312> ) {
        next unless /^0x/i;
        my ($gb, $uni) = /(0x....)\s+(0x....)/;
        if ( $gb && $uni ) {
            my $euc = hex ($gb) | 0x8080;
            printf CSGB2312 "0x%04x\t$uni\n", $euc;
        }
    }

    print CSGB2312 "\n# End of file\n";
}

sub _close {
    close CSGB2312
        or die "Can't close input file GB2312.TXT! ($!)"
    ;
    close GB2312
        or die "Can't close output file CSGB2312.TXT! ($!)"
    ;
}

Generated by dwww version 1.15 on Thu May 23 02:14:38 CEST 2024.