|
sl@0
|
1 |
#
|
|
sl@0
|
2 |
# Copyright (c) 2000-2009 Nokia Corporation and/or its subsidiary(-ies).
|
|
sl@0
|
3 |
# All rights reserved.
|
|
sl@0
|
4 |
# This component and the accompanying materials are made available
|
|
sl@0
|
5 |
# under the terms of "Eclipse Public License v1.0"
|
|
sl@0
|
6 |
# which accompanies this distribution, and is available
|
|
sl@0
|
7 |
# at the URL "http://www.eclipse.org/legal/epl-v10.html".
|
|
sl@0
|
8 |
#
|
|
sl@0
|
9 |
# Initial Contributors:
|
|
sl@0
|
10 |
# Nokia Corporation - initial contribution.
|
|
sl@0
|
11 |
#
|
|
sl@0
|
12 |
# Contributors:
|
|
sl@0
|
13 |
#
|
|
sl@0
|
14 |
# Description:
|
|
sl@0
|
15 |
#
|
|
sl@0
|
16 |
|
|
sl@0
|
17 |
use strict;
|
|
sl@0
|
18 |
use integer;
|
|
sl@0
|
19 |
|
|
sl@0
|
20 |
package UTF;
|
|
sl@0
|
21 |
require Exporter;
|
|
sl@0
|
22 |
@UTF::ISA=qw(Exporter);
|
|
sl@0
|
23 |
@UTF::EXPORT=qw(Utf8ToUnicode UnicodeToUtf8);
|
|
sl@0
|
24 |
|
|
sl@0
|
25 |
my $KErrorIllFormedInput=-1;
|
|
sl@0
|
26 |
|
|
sl@0
|
27 |
sub Utf8ToUnicode
|
|
sl@0
|
28 |
{
|
|
sl@0
|
29 |
my $Unicode = shift;
|
|
sl@0
|
30 |
my $Utf8 = shift;
|
|
sl@0
|
31 |
my $UnicodeTemplate = shift;
|
|
sl@0
|
32 |
my $Utf8Index = 0;
|
|
sl@0
|
33 |
my $UnicodeIndex = 0;
|
|
sl@0
|
34 |
my $numOfBytes = length($Utf8);
|
|
sl@0
|
35 |
my @Utf8Unpacked = unpack "C*",$Utf8;
|
|
sl@0
|
36 |
my @UnicodeUnpacked = ();
|
|
sl@0
|
37 |
|
|
sl@0
|
38 |
for (;;)
|
|
sl@0
|
39 |
{
|
|
sl@0
|
40 |
if ($Utf8Index > $#Utf8Unpacked)
|
|
sl@0
|
41 |
{
|
|
sl@0
|
42 |
last;
|
|
sl@0
|
43 |
}
|
|
sl@0
|
44 |
|
|
sl@0
|
45 |
my $currentUtf8Byte = $Utf8Unpacked[$Utf8Index];
|
|
sl@0
|
46 |
|
|
sl@0
|
47 |
if (($currentUtf8Byte&0x80)==0x00)
|
|
sl@0
|
48 |
{
|
|
sl@0
|
49 |
$UnicodeUnpacked[$UnicodeIndex] = $currentUtf8Byte;
|
|
sl@0
|
50 |
}
|
|
sl@0
|
51 |
|
|
sl@0
|
52 |
elsif (($currentUtf8Byte&0xe0)==0xc0)
|
|
sl@0
|
53 |
{
|
|
sl@0
|
54 |
my $currentUnicodeCharacter=(($currentUtf8Byte&0x1f)<<6);
|
|
sl@0
|
55 |
++$Utf8Index;
|
|
sl@0
|
56 |
$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
|
|
sl@0
|
57 |
if (($currentUtf8Byte&0xc0)!=0x80)
|
|
sl@0
|
58 |
{
|
|
sl@0
|
59 |
return $KErrorIllFormedInput;
|
|
sl@0
|
60 |
}
|
|
sl@0
|
61 |
$currentUnicodeCharacter|=($currentUtf8Byte&0x3f);
|
|
sl@0
|
62 |
$UnicodeUnpacked[$UnicodeIndex] = $currentUnicodeCharacter;
|
|
sl@0
|
63 |
}
|
|
sl@0
|
64 |
|
|
sl@0
|
65 |
elsif (($currentUtf8Byte&0xf0)==0xe0)
|
|
sl@0
|
66 |
{
|
|
sl@0
|
67 |
my $currentUnicodeCharacter=(($currentUtf8Byte&0x0f)<<12);
|
|
sl@0
|
68 |
++$Utf8Index;
|
|
sl@0
|
69 |
$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
|
|
sl@0
|
70 |
if (($currentUtf8Byte&0xc0)!=0x80)
|
|
sl@0
|
71 |
{
|
|
sl@0
|
72 |
return $KErrorIllFormedInput;
|
|
sl@0
|
73 |
}
|
|
sl@0
|
74 |
$currentUnicodeCharacter|=(($currentUtf8Byte&0x3f)<<6);
|
|
sl@0
|
75 |
++$Utf8Index;
|
|
sl@0
|
76 |
$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
|
|
sl@0
|
77 |
if (($currentUtf8Byte&0xc0)!=0x80)
|
|
sl@0
|
78 |
{
|
|
sl@0
|
79 |
return $KErrorIllFormedInput;
|
|
sl@0
|
80 |
}
|
|
sl@0
|
81 |
$currentUnicodeCharacter|=($currentUtf8Byte&0x3f);
|
|
sl@0
|
82 |
$UnicodeUnpacked[$UnicodeIndex] = $currentUnicodeCharacter;
|
|
sl@0
|
83 |
}
|
|
sl@0
|
84 |
|
|
sl@0
|
85 |
elsif (($currentUtf8Byte&0xf8)==0xf0)
|
|
sl@0
|
86 |
{
|
|
sl@0
|
87 |
my $currentUnicodeCharacter=(($currentUtf8Byte&0x07)<<8);
|
|
sl@0
|
88 |
++$Utf8Index;
|
|
sl@0
|
89 |
$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
|
|
sl@0
|
90 |
if (($currentUtf8Byte&0xc0)!=0x80)
|
|
sl@0
|
91 |
{
|
|
sl@0
|
92 |
return $KErrorIllFormedInput;
|
|
sl@0
|
93 |
}
|
|
sl@0
|
94 |
$currentUnicodeCharacter|=(($currentUtf8Byte&0x3f)<<2);
|
|
sl@0
|
95 |
if ($currentUnicodeCharacter<0x0040)
|
|
sl@0
|
96 |
{
|
|
sl@0
|
97 |
return $KErrorIllFormedInput;
|
|
sl@0
|
98 |
}
|
|
sl@0
|
99 |
$currentUnicodeCharacter-=0x0040;
|
|
sl@0
|
100 |
if ($currentUnicodeCharacter>=0x0400)
|
|
sl@0
|
101 |
{
|
|
sl@0
|
102 |
return $KErrorIllFormedInput;
|
|
sl@0
|
103 |
}
|
|
sl@0
|
104 |
++$Utf8Index;
|
|
sl@0
|
105 |
$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
|
|
sl@0
|
106 |
if (($currentUtf8Byte&0xc0)!=0x80)
|
|
sl@0
|
107 |
{
|
|
sl@0
|
108 |
return $KErrorIllFormedInput;
|
|
sl@0
|
109 |
}
|
|
sl@0
|
110 |
$currentUnicodeCharacter|=(($currentUtf8Byte&0x30)>>4);
|
|
sl@0
|
111 |
$UnicodeUnpacked[$UnicodeIndex] = (0xd800|$currentUnicodeCharacter);
|
|
sl@0
|
112 |
$currentUnicodeCharacter=(($currentUtf8Byte&0x0f)<<6);
|
|
sl@0
|
113 |
++$Utf8Index;
|
|
sl@0
|
114 |
$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
|
|
sl@0
|
115 |
if (($currentUtf8Byte&0xc0)!=0x80)
|
|
sl@0
|
116 |
{
|
|
sl@0
|
117 |
return $KErrorIllFormedInput;
|
|
sl@0
|
118 |
}
|
|
sl@0
|
119 |
$currentUnicodeCharacter|=($currentUtf8Byte&0x3f);
|
|
sl@0
|
120 |
++$UnicodeIndex;
|
|
sl@0
|
121 |
$UnicodeUnpacked[$UnicodeIndex] = (0xdc00|$currentUnicodeCharacter);
|
|
sl@0
|
122 |
}
|
|
sl@0
|
123 |
else
|
|
sl@0
|
124 |
{
|
|
sl@0
|
125 |
return $KErrorIllFormedInput;
|
|
sl@0
|
126 |
}
|
|
sl@0
|
127 |
++$UnicodeIndex;
|
|
sl@0
|
128 |
++$Utf8Index;
|
|
sl@0
|
129 |
}
|
|
sl@0
|
130 |
$$Unicode = ();
|
|
sl@0
|
131 |
$$Unicode = pack "$UnicodeTemplate*", @UnicodeUnpacked;
|
|
sl@0
|
132 |
return $UnicodeIndex;
|
|
sl@0
|
133 |
}
|
|
sl@0
|
134 |
|
|
sl@0
|
135 |
sub UnicodeToUtf8
|
|
sl@0
|
136 |
{
|
|
sl@0
|
137 |
my $Utf8 = shift;
|
|
sl@0
|
138 |
my $Unicode = shift;
|
|
sl@0
|
139 |
my $UnicodeTemplate = shift;
|
|
sl@0
|
140 |
my $Utf8Index = 0;
|
|
sl@0
|
141 |
my $UnicodeIndex = 0;
|
|
sl@0
|
142 |
my $numOfBytes = length($Unicode);
|
|
sl@0
|
143 |
my @UnicodeUnpacked = unpack "$UnicodeTemplate*", $Unicode;
|
|
sl@0
|
144 |
my @Utf8Unpacked = ();
|
|
sl@0
|
145 |
|
|
sl@0
|
146 |
for (;;)
|
|
sl@0
|
147 |
{
|
|
sl@0
|
148 |
# exit the loop if no more in the UnicodeUnpacked
|
|
sl@0
|
149 |
if ($UnicodeIndex > $#UnicodeUnpacked)
|
|
sl@0
|
150 |
{
|
|
sl@0
|
151 |
last;
|
|
sl@0
|
152 |
}
|
|
sl@0
|
153 |
|
|
sl@0
|
154 |
my $currentUnicodeCharacter=$UnicodeUnpacked[$UnicodeIndex];
|
|
sl@0
|
155 |
if (($currentUnicodeCharacter&0xff80)==0x0000)
|
|
sl@0
|
156 |
{
|
|
sl@0
|
157 |
$Utf8Unpacked[$Utf8Index]= $currentUnicodeCharacter;
|
|
sl@0
|
158 |
}
|
|
sl@0
|
159 |
elsif (($currentUnicodeCharacter&0xf800)==0x0000)
|
|
sl@0
|
160 |
{
|
|
sl@0
|
161 |
|
|
sl@0
|
162 |
$Utf8Unpacked[$Utf8Index]= (0xc0 | $currentUnicodeCharacter >> 6);
|
|
sl@0
|
163 |
++$Utf8Index;
|
|
sl@0
|
164 |
$Utf8Unpacked[$Utf8Index]= (0x80 | $currentUnicodeCharacter&0x3f);
|
|
sl@0
|
165 |
}
|
|
sl@0
|
166 |
elsif (($currentUnicodeCharacter&0xfc00)==0xd800)
|
|
sl@0
|
167 |
{
|
|
sl@0
|
168 |
$currentUnicodeCharacter+=0x0040;
|
|
sl@0
|
169 |
$Utf8Unpacked[$Utf8Index]= (0xf0|(($currentUnicodeCharacter>>8)&0x07));
|
|
sl@0
|
170 |
++$Utf8Index;
|
|
sl@0
|
171 |
$Utf8Unpacked[$Utf8Index]= (0x80|(($currentUnicodeCharacter>>2)&0x3f));
|
|
sl@0
|
172 |
my $currentUtf8Byte=(0x80|(($currentUnicodeCharacter&0x03)<<4));
|
|
sl@0
|
173 |
++$UnicodeIndex;
|
|
sl@0
|
174 |
$currentUnicodeCharacter=$UnicodeUnpacked[$UnicodeIndex];
|
|
sl@0
|
175 |
if (($currentUnicodeCharacter&0xfc00)!=0xdc00)
|
|
sl@0
|
176 |
{
|
|
sl@0
|
177 |
return $KErrorIllFormedInput;
|
|
sl@0
|
178 |
}
|
|
sl@0
|
179 |
$currentUtf8Byte|=(($currentUnicodeCharacter>>6)&0x0f);
|
|
sl@0
|
180 |
++$Utf8Index;
|
|
sl@0
|
181 |
$Utf8Unpacked[$Utf8Index]= $currentUtf8Byte;
|
|
sl@0
|
182 |
++$Utf8Index;
|
|
sl@0
|
183 |
$Utf8Unpacked[$Utf8Index]= (0x80| ($currentUnicodeCharacter&0x3f));
|
|
sl@0
|
184 |
}
|
|
sl@0
|
185 |
else
|
|
sl@0
|
186 |
{
|
|
sl@0
|
187 |
$Utf8Unpacked[$Utf8Index]= (0xe0|($currentUnicodeCharacter>>12));
|
|
sl@0
|
188 |
++$Utf8Index;
|
|
sl@0
|
189 |
$Utf8Unpacked[$Utf8Index]= (0x80|(($currentUnicodeCharacter>>6)&0x3f));
|
|
sl@0
|
190 |
++$Utf8Index;
|
|
sl@0
|
191 |
$Utf8Unpacked[$Utf8Index]= (0x80| ($currentUnicodeCharacter&0x3f));
|
|
sl@0
|
192 |
}
|
|
sl@0
|
193 |
++$Utf8Index;
|
|
sl@0
|
194 |
++$UnicodeIndex;
|
|
sl@0
|
195 |
}
|
|
sl@0
|
196 |
$$Utf8 = ();
|
|
sl@0
|
197 |
$$Utf8 = pack "C*", @Utf8Unpacked;
|
|
sl@0
|
198 |
return $Utf8Index;
|
|
sl@0
|
199 |
|
|
sl@0
|
200 |
}
|