1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
|
#! /usr/bin/perl
#
# Copyright (c) 2007-2017, PostgreSQL Global Development Group
#
# src/backend/utils/mb/Unicode/UCS_to_EUC_JIS_2004.pl
#
# Generate UTF-8 <--> EUC_JIS_2004 code conversion tables from
# "euc-jis-2004-std.txt" (http://x0213.org)
use strict;
use convutils;
my $this_script = $0;
# first generate UTF-8 --> EUC_JIS_2004 table
my $in_file = "euc-jis-2004-std.txt";
open(my $in, '<', $in_file) || die("cannot open $in_file");
my @all;
while (my $line = <$in>)
{
if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/)
{
# combined characters
my ($c, $u1, $u2) = ($1, $2, $3);
my $rest = "U+" . $u1 . "+" . $u2 . $4;
my $code = hex($c);
my $ucs1 = hex($u1);
my $ucs2 = hex($u2);
push @all, { direction => BOTH,
ucs => $ucs1,
ucs_second => $ucs2,
code => $code,
comment => $rest,
f => $in_file,
l => $.
};
}
elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/)
{
# non-combined characters
my ($c, $u, $rest) = ($1, $2, "U+" . $2 . $3);
my $ucs = hex($u);
my $code = hex($c);
next if ($code < 0x80 && $ucs < 0x80);
push @all, { direction => BOTH,
ucs => $ucs,
code => $code,
comment => $rest,
f => $in_file,
l => $.
};
}
}
close($in);
print_conversion_tables($this_script, "EUC_JIS_2004", \@all);
|
