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
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
|
#! /usr/bin/perl
#
# Copyright (c) 2001-2015, PostgreSQL Global Development Group
#
# src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl
#
# Generate UTF-8 <--> EUC_CN code conversion tables from
# map files provided by Unicode organization.
# Unfortunately it is prohibited by the organization
# to distribute the map files. So if you try to use this script,
# you have to obtain GB2312.TXT from
# the organization's ftp site.
#
# GB2312.TXT format:
# GB2312 code in hex
# UCS-2 code in hex
# # and Unicode name (not used in this script)
require "ucs2utf.pl";
# first generate UTF-8 --> EUC_CN table
$in_file = "GB2312.TXT";
open(FILE, $in_file) || die("cannot open $in_file");
while (<FILE>)
{
chop;
if (/^#/)
{
next;
}
($c, $u, $rest) = split;
$ucs = hex($u);
$code = hex($c);
if ($code >= 0x80 && $ucs >= 0x0080)
{
$utf = &ucs2utf($ucs);
if ($array{$utf} ne "")
{
printf STDERR "Warning: duplicate UTF8: %04x\n", $ucs;
next;
}
$count++;
$array{$utf} = ($code | 0x8080);
}
}
close(FILE);
#
# first, generate UTF8 --> EUC_CN table
#
$file = "utf8_to_euc_cn.map";
open(FILE, "> $file") || die("cannot open $file");
print FILE "static const pg_utf_to_local ULmapEUC_CN[ $count ] = {\n";
for $index (sort { $a <=> $b } keys(%array))
{
$code = $array{$index};
$count--;
if ($count == 0)
{
printf FILE " {0x%04x, 0x%04x}\n", $index, $code;
}
else
{
printf FILE " {0x%04x, 0x%04x},\n", $index, $code;
}
}
print FILE "};\n";
close(FILE);
#
# then generate EUC_JP --> UTF8 table
#
reset 'array';
open(FILE, $in_file) || die("cannot open $in_file");
while (<FILE>)
{
chop;
if (/^#/)
{
next;
}
($c, $u, $rest) = split;
$ucs = hex($u);
$code = hex($c);
if ($code >= 0x80 && $ucs >= 0x0080)
{
$utf = &ucs2utf($ucs);
if ($array{$code} ne "")
{
printf STDERR "Warning: duplicate code: %04x\n", $ucs;
next;
}
$count++;
$code |= 0x8080;
$array{$code} = $utf;
}
}
close(FILE);
$file = "euc_cn_to_utf8.map";
open(FILE, "> $file") || die("cannot open $file");
print FILE "static const pg_local_to_utf LUmapEUC_CN[ $count ] = {\n";
for $index (sort { $a <=> $b } keys(%array))
{
$utf = $array{$index};
$count--;
if ($count == 0)
{
printf FILE " {0x%04x, 0x%04x}\n", $index, $utf;
}
else
{
printf FILE " {0x%04x, 0x%04x},\n", $index, $utf;
}
}
print FILE "};\n";
close(FILE);
|
