1#! /usr/bin/perl
2#
3# Copyright (c) 2007-2020, PostgreSQL Global Development Group
4#
5# src/backend/utils/mb/Unicode/UCS_to_GB18030.pl
6#
7# Generate UTF-8 <--> GB18030 code conversion tables from
8# "gb-18030-2000.xml", obtained from
9# http://source.icu-project.org/repos/icu/data/trunk/charset/data/xml/
10#
11# The lines we care about in the source file look like
12#    <a u="009A" b="81 30 83 36"/>
13# where the "u" field is the Unicode code point in hex,
14# and the "b" field is the hex byte sequence for GB18030
15
16use strict;
17use warnings;
18
19use convutils;
20
21my $this_script = 'src/backend/utils/mb/Unicode/UCS_to_GB18030.pl';
22
23# Read the input
24
25my $in_file = "gb-18030-2000.xml";
26
27open(my $in, '<', $in_file) || die("cannot open $in_file");
28
29my @mapping;
30
31while (<$in>)
32{
33	next if (!m/<a u="([0-9A-F]+)" b="([0-9A-F ]+)"/);
34	my ($u, $c) = ($1, $2);
35	$c =~ s/ //g;
36	my $ucs  = hex($u);
37	my $code = hex($c);
38	if ($code >= 0x80 && $ucs >= 0x0080)
39	{
40		push @mapping,
41		  {
42			ucs       => $ucs,
43			code      => $code,
44			direction => BOTH,
45			f         => $in_file,
46			l         => $.
47		  };
48	}
49}
50close($in);
51
52print_conversion_tables($this_script, "GB18030", \@mapping);
53