Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit2dbbf33

Browse files
committed
Add seven kanji characters defined in the Windows 950 codepage to our
big5/win950 <-> UTF8 conversion tables.Per report by Roger Chang.
1 parent8e1a8fe commit2dbbf33

File tree

4 files changed

+195
-5
lines changed

4 files changed

+195
-5
lines changed
Lines changed: 177 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,177 @@
1+
#! /usr/bin/perl
2+
#
3+
# Copyright (c) 2001-2009, PostgreSQL Global Development Group
4+
#
5+
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_big5.pl,v 1.1 2009/03/18 16:17:58 heikki Exp $
6+
#
7+
# Generate UTF-8 <--> BIG5 conversion tables from
8+
# map files provided by Unicode organization.
9+
# Unfortunately it is prohibited by the organization
10+
# to distribute the map files. So if you try to use this script,
11+
# you have to obtain the map files from the organization's ftp site.
12+
# ftp://www.unicode.org/Public/MAPPINGS/
13+
#
14+
# Our "big5" comes from BIG5.TXT, with the addition of the characters
15+
# in the range 0xf9d6-0xf9dc from CP950.TXT.
16+
#
17+
# BIG5.TXT format:
18+
# BIG5 code in hex
19+
# UCS-2 code in hex
20+
# # and Unicode name (not used in this script)
21+
#
22+
# CP950.TXT format:
23+
# CP950 code in hex
24+
# UCS-2 code in hex
25+
# # and Unicode name (not used in this script)
26+
27+
28+
require"ucs2utf.pl";
29+
30+
31+
#
32+
# first, generate UTF8 --> BIG5 table
33+
#
34+
$in_file ="BIG5.TXT";
35+
36+
open( FILE,$in_file ) ||die("cannot open$in_file" );
37+
38+
reset'array';
39+
40+
while( <FILE> ){
41+
chop;
42+
if(/^#/ ){
43+
next;
44+
}
45+
($c,$u,$rest ) =split;
46+
$ucs =hex($u);
47+
$code =hex($c);
48+
if($code >= 0x80 &&$ucs >= 0x0080){
49+
$utf = &ucs2utf($ucs);
50+
if($array{$utf }ne"" ){
51+
printfSTDERR"Warning: duplicate UTF8: %04x\n",$ucs;
52+
next;
53+
}
54+
$count++;
55+
$array{$utf } =$code;
56+
}
57+
}
58+
close( FILE );
59+
60+
$in_file ="CP950.TXT";
61+
62+
open( FILE,$in_file ) ||die("cannot open$in_file" );
63+
64+
while( <FILE> ){
65+
chop;
66+
if(/^#/ ){
67+
next;
68+
}
69+
($c,$u,$rest ) =split;
70+
$ucs =hex($u);
71+
$code =hex($c);
72+
73+
# Pick only the ETEN extended characters in the range 0xf9d6 - 0xf9dc
74+
# from CP950.TXT
75+
if($code >= 0x80 &&$ucs >= 0x0080 &&
76+
$code >= 0xf9d6 &&$code <= 0xf9dc ){
77+
$utf = &ucs2utf($ucs);
78+
if($array{$utf }ne"" ){
79+
printfSTDERR"Warning: duplicate UTF8: %04x\n",$ucs;
80+
next;
81+
}
82+
$count++;
83+
$array{$utf } =$code;
84+
}
85+
}
86+
close( FILE );
87+
88+
$file =lc("utf8_to_big5.map");
89+
open( FILE,">$file" ) ||die("cannot open$file" );
90+
print FILE"static pg_utf_to_local ULmapBIG5[$count ] = {\n";
91+
92+
for$index (sort {$a<=>$b}keys(%array ) ){
93+
$code =$array{$index };
94+
$count--;
95+
if($count == 0 ){
96+
printf FILE" {0x%04x, 0x%04x}\n",$index,$code;
97+
}else {
98+
printf FILE" {0x%04x, 0x%04x},\n",$index,$code;
99+
}
100+
}
101+
102+
print FILE"};\n";
103+
close(FILE);
104+
105+
#
106+
# then generate BIG5 --> UTF8 table
107+
#
108+
$in_file ="BIG5.TXT";
109+
110+
open( FILE,$in_file ) ||die("cannot open$in_file" );
111+
112+
reset'array';
113+
114+
while( <FILE> ){
115+
chop;
116+
if(/^#/ ){
117+
next;
118+
}
119+
($c,$u,$rest ) =split;
120+
$ucs =hex($u);
121+
$code =hex($c);
122+
if($code >= 0x80 &&$ucs >= 0x0080){
123+
$utf = &ucs2utf($ucs);
124+
if($array{$utf }ne"" ){
125+
printfSTDERR"Warning: duplicate UTF8: %04x\n",$ucs;
126+
next;
127+
}
128+
$count++;
129+
$array{$code } =$utf;
130+
}
131+
}
132+
close( FILE );
133+
134+
$in_file ="CP950.TXT";
135+
136+
open( FILE,$in_file ) ||die("cannot open$in_file" );
137+
138+
while( <FILE> ){
139+
chop;
140+
if(/^#/ ){
141+
next;
142+
}
143+
($c,$u,$rest ) =split;
144+
$ucs =hex($u);
145+
$code =hex($c);
146+
147+
# Pick only the ETEN extended characters in the range 0xf9d6 - 0xf9dc
148+
# from CP950.TXT
149+
if($code >= 0x80 &&$ucs >= 0x0080 &&
150+
$code >= 0xf9d6 &&$code <= 0xf9dc ){
151+
$utf = &ucs2utf($ucs);
152+
if($array{$utf }ne"" ){
153+
printfSTDERR"Warning: duplicate UTF8: %04x\n",$ucs;
154+
next;
155+
}
156+
$count++;
157+
$array{$code } =$utf;
158+
}
159+
}
160+
close( FILE );
161+
162+
$file =lc("big5_to_utf8.map");
163+
open( FILE,">$file" ) ||die("cannot open$file" );
164+
print FILE"static pg_local_to_utf LUmapBIG5[$count ] = {\n";
165+
for$index (sort {$a<=>$b}keys(%array ) ){
166+
$utf =$array{$index };
167+
$count--;
168+
if($count == 0 ){
169+
printf FILE" {0x%04x, 0x%04x}\n",$index,$utf;
170+
}else {
171+
printf FILE" {0x%04x, 0x%04x},\n",$index,$utf;
172+
}
173+
}
174+
175+
print FILE"};\n";
176+
close(FILE);
177+

‎src/backend/utils/mb/Unicode/UCS_to_most.pl

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
#
33
# Copyright (c) 2001-2009, PostgreSQL Global Development Group
44
#
5-
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_most.pl,v 1.7 2009/02/10 19:29:39 petere Exp $
5+
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_most.pl,v 1.8 2009/03/18 16:17:28 heikki Exp $
66
#
77
# Generate UTF-8 <--> character code conversion tables from
88
# map files provided by Unicode organization.
@@ -47,7 +47,6 @@
4747
'GBK'=>'CP936.TXT',
4848
'UHC'=>'CP949.TXT',
4949
'JOHAB'=>'JOHAB.TXT',
50-
'BIG5'=>'BIG5.TXT',
5150
);
5251

5352
@charsets =keys(filename);

‎src/backend/utils/mb/Unicode/big5_to_utf8.map

Lines changed: 9 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
static pg_local_to_utf LUmapBIG5[13710 ] = {
1+
static pg_local_to_utf LUmapBIG5[13717 ] = {
22
{0xa140, 0xe38080},
33
{0xa141, 0xefbc8c},
44
{0xa142, 0xe38081},
@@ -13708,5 +13708,12 @@ static pg_local_to_utf LUmapBIG5[ 13710 ] = {
1370813708
{0xf9d2, 0xe9baa4},
1370913709
{0xf9d3, 0xe9bdbe},
1371013710
{0xf9d4, 0xe9bd89},
13711-
{0xf9d5, 0xe9be98}
13711+
{0xf9d5, 0xe9be98},
13712+
{0xf9d6, 0xe7a281},
13713+
{0xf9d7, 0xe98ab9},
13714+
{0xf9d8, 0xe8a38f},
13715+
{0xf9d9, 0xe5a2bb},
13716+
{0xf9da, 0xe68192},
13717+
{0xf9db, 0xe7b2a7},
13718+
{0xf9dc, 0xe5abba}
1371213719
};

‎src/backend/utils/mb/Unicode/utf8_to_big5.map

Lines changed: 8 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
static pg_utf_to_local ULmapBIG5[13704 ] = {
1+
static pg_utf_to_local ULmapBIG5[13711 ] = {
22
{0xc2a2, 0xa246},
33
{0xc2a3, 0xa247},
44
{0xc2a5, 0xa244},
@@ -2140,6 +2140,7 @@ static pg_utf_to_local ULmapBIG5[ 13704 ] = {
21402140
{0xe5a2b1, 0xe54c},
21412141
{0xe5a2b3, 0xbc58},
21422142
{0xe5a2ba, 0xe94d},
2143+
{0xe5a2bb, 0xf9d9},
21432144
{0xe5a2bc, 0xe94f},
21442145
{0xe5a2bd, 0xe94a},
21452146
{0xe5a2be, 0xbec1},
@@ -2508,6 +2509,7 @@ static pg_utf_to_local ULmapBIG5[ 13704 ] = {
25082509
{0xe5abb7, 0xe557},
25092510
{0xe5abb8, 0xe55a},
25102511
{0xe5abb9, 0xe55c},
2512+
{0xe5abba, 0xf9dc},
25112513
{0xe5abbb, 0xbc5f},
25122514
{0xe5abbd, 0xe556},
25132515
{0xe5abbf, 0xe554},
@@ -3370,6 +3372,7 @@ static pg_utf_to_local ULmapBIG5[ 13704 ] = {
33703372
{0xe6818c, 0xcec9},
33713373
{0xe6818d, 0xabe9},
33723374
{0xe68190, 0xaea3},
3375+
{0xe68192, 0xf9da},
33733376
{0xe68193, 0xcec5},
33743377
{0xe68194, 0xcec1},
33753378
{0xe68195, 0xaea4},
@@ -7482,6 +7485,7 @@ static pg_utf_to_local ULmapBIG5[ 13704 ] = {
74827485
{0xe7a1be, 0xe2f0},
74837486
{0xe7a1bf, 0xb851},
74847487
{0xe7a280, 0xdef0},
7488+
{0xe7a281, 0xf9d6},
74857489
{0xe7a283, 0xdeed},
74867490
{0xe7a284, 0xdee8},
74877491
{0xe7a285, 0xdeea},
@@ -8142,6 +8146,7 @@ static pg_utf_to_local ULmapBIG5[ 13704 ] = {
81428146
{0xe7b2a2, 0xdae7},
81438147
{0xe7b2a3, 0xd6e1},
81448148
{0xe7b2a5, 0xb5b0},
8149+
{0xe7b2a7, 0xf9db},
81458150
{0xe7b2a8, 0xdae9},
81468151
{0xe7b2af, 0xdf56},
81478152
{0xe7b2b1, 0xb864},
@@ -10208,6 +10213,7 @@ static pg_utf_to_local ULmapBIG5[ 13704 ] = {
1020810213
{0xe8a38c, 0xdff8},
1020910214
{0xe8a38d, 0xdff3},
1021010215
{0xe8a38e, 0xdff4},
10216+
{0xe8a38f, 0xf9d8},
1021110217
{0xe8a390, 0xdff9},
1021210218
{0xe8a392, 0xb8cf},
1021310219
{0xe8a394, 0xb8c7},
@@ -11806,6 +11812,7 @@ static pg_utf_to_local ULmapBIG5[ 13704 ] = {
1180611812
{0xe98ab5, 0xe8a1},
1180711813
{0xe98ab6, 0xe867},
1180811814
{0xe98ab7, 0xbe50},
11815+
{0xe98ab9, 0xf9d7},
1180911816
{0xe98abb, 0xbe4f},
1181011817
{0xe98abc, 0xbe56},
1181111818
{0xe98b80, 0xe865},

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp