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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
|
#! /usr/bin/perl
#
# Copyright (c) 2007-2010, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_SHIFT_JIS_2004.pl,v 1.4 2010/01/02 16:57:56 momjian Exp $
#
# Generate UTF-8 <--> SHIFT_JIS_2004 code conversion tables from
# "sjis-0213-2004-std.txt" (http://x0213.org)
require "ucs2utf.pl";
# first generate UTF-8 --> SHIFT_JIS_2004 table
$in_file = "sjis-0213-2004-std.txt";
open( FILE, $in_file ) || die( "cannot open $in_file" );
reset 'array';
reset 'array1';
reset 'comment';
reset 'comment1';
while($line = <FILE> ){
if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/) {
$c = $1;
$u1 = $2;
$u2 = $3;
$rest = "U+" . $u1 . "+" . $u2 . $4;
$code = hex($c);
$ucs = hex($u1);
$utf1 = &ucs2utf($ucs);
$ucs = hex($u2);
$utf2 = &ucs2utf($ucs);
$str = sprintf "%08x%08x", $utf1, $utf2;
$array1{ $str } = $code;
$comment1{ $str } = $rest;
$count1++;
next;
} elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/) {
$c = $1;
$u = $2;
$rest = "U+" . $u . $3;
} else {
next;
}
$ucs = hex($u);
$code = hex($c);
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate UTF8: %08x UCS: %04x Shift JIS: %04x\n",$utf, $ucs, $code;
next;
}
$count++;
$array{ $utf } = $code;
$comment{ $code } = $rest;
}
close( FILE );
$file = "utf8_to_shift_jis_2004.map";
open( FILE, "> $file" ) || die( "cannot open $file" );
print FILE "/*\n";
print FILE " * This file was generated by UCS_to_SHIFT_JIS_2004.pl\n";
print FILE " */\n";
print FILE "static pg_utf_to_local ULmapSHIFT_JIS_2004[] = {\n";
for $index ( sort {$a <=> $b} keys( %array ) ){
$code = $array{ $index };
$count--;
if( $count == 0 ){
printf FILE " {0x%08x, 0x%06x} /* %s */\n", $index, $code, $comment{ $code };
} else {
printf FILE " {0x%08x, 0x%06x}, /* %s */\n", $index, $code, $comment{ $code };
}
}
print FILE "};\n";
close(FILE);
$file = "utf8_to_shift_jis_2004_combined.map";
open( FILE, "> $file" ) || die( "cannot open $file" );
print FILE "/*\n";
print FILE " * This file was generated by UCS_to_SHIFT_JIS_2004.pl\n";
print FILE " */\n";
print FILE "static pg_utf_to_local_combined ULmapSHIFT_JIS_2004_combined[] = {\n";
for $index ( sort {$a cmp $b} keys( %array1 ) ){
$code = $array1{ $index };
$count1--;
if( $count1 == 0 ){
printf FILE " {0x%s, 0x%s, 0x%04x} /* %s */\n", substr($index, 0, 8), substr($index, 8, 8), $code, $comment1{ $index };
} else {
printf FILE " {0x%s, 0x%s, 0x%04x}, /* %s */\n", substr($index, 0, 8), substr($index, 8, 8), $code, $comment1{ $index };
}
}
print FILE "};\n";
close(FILE);
# then generate SHIFT_JIS_2004 --> UTF-8 table
$in_file = "sjis-0213-2004-std.txt";
open( FILE, $in_file ) || die( "cannot open $in_file" );
reset 'array';
reset 'array1';
reset 'comment';
reset 'comment1';
while($line = <FILE> ){
if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/) {
$c = $1;
$u1 = $2;
$u2 = $3;
$rest = "U+" . $u1 . "+" . $u2 . $4;
$code = hex($c);
$ucs = hex($u1);
$utf1 = &ucs2utf($ucs);
$ucs = hex($u2);
$utf2 = &ucs2utf($ucs);
$str = sprintf "%08x%08x", $utf1, $utf2;
$array1{ $code } = $str;
$comment1{ $code } = $rest;
$count1++;
next;
} elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/) {
$c = $1;
$u = $2;
$rest = "U+" . $u . $3;
} else {
next;
}
$ucs = hex($u);
$code = hex($c);
$utf = &ucs2utf($ucs);
if( $array{ $code } ne "" ){
printf STDERR "Warning: duplicate UTF-8: %08x UCS: %04x Shift JIS: %04x\n",$utf, $ucs, $code;
printf STDERR "Previous value: UTF-8: %08x\n", $array{ $utf };
next;
}
$count++;
$array{ $code } = $utf;
$comment{ $utf } = $rest;
}
close( FILE );
$file = "shift_jis_2004_to_utf8.map";
open( FILE, "> $file" ) || die( "cannot open $file" );
print FILE "/*\n";
print FILE " * This file was generated by UCS_to_SHIFTJIS_2004.pl\n";
print FILE " */\n";
print FILE "static pg_local_to_utf LUmapSHIFT_JIS_2004[] = {\n";
for $index ( sort {$a <=> $b} keys( %array ) ){
$code = $array{ $index };
$count--;
if( $count == 0 ){
printf FILE " {0x%04x, 0x%08x} /* %s */\n", $index, $code, $comment{ $code };
} else {
printf FILE " {0x%04x, 0x%08x}, /* %s */\n", $index, $code, $comment{ $code };
}
}
print FILE "};\n";
close(FILE);
$file = "shift_jis_2004_to_utf8_combined.map";
open( FILE, "> $file" ) || die( "cannot open $file" );
print FILE "/*\n";
print FILE " * This file was generated by UCS_to_SHIFT_JIS_2004.pl\n";
print FILE " */\n";
print FILE "static pg_local_to_utf_combined LUmapSHIFT_JIS_2004_combined[] = {\n";
for $index ( sort {$a <=> $b} keys( %array1 ) ){
$code = $array1{ $index };
$count1--;
if( $count1 == 0 ){
printf FILE " {0x%04x, 0x%s, 0x%s} /* %s */\n", $index, substr($code, 0, 8), substr($code, 8, 8), $comment1{ $index };
} else {
printf FILE " {0x%04x, 0x%s, 0x%s}, /* %s */\n", $index, substr($code, 0, 8), substr($code, 8, 8), $comment1{ $index };
}
}
print FILE "};\n";
close(FILE);
|
