|
1 /* |
|
2 * Copyright (c) 1997-1999 Nokia Corporation and/or its subsidiary(-ies). |
|
3 * All rights reserved. |
|
4 * This component and the accompanying materials are made available |
|
5 * under the terms of the License "Eclipse Public License v1.0" |
|
6 * which accompanies this distribution, and is available |
|
7 * at the URL "http://www.eclipse.org/legal/epl-v10.html". |
|
8 * |
|
9 * Initial Contributors: |
|
10 * Nokia Corporation - initial contribution. |
|
11 * |
|
12 * Contributors: |
|
13 * |
|
14 * Description: |
|
15 * |
|
16 */ |
|
17 |
|
18 |
|
19 |
|
20 |
|
21 |
|
22 |
|
23 |
|
24 |
|
25 #include <stdlib.h> |
|
26 |
|
27 const int KErrorIllFormedInput=-1; |
|
28 |
|
29 int Utf8ToUnicode(wchar_t* aUnicode, const char* aUtf8) |
|
30 // must '\0'-terminate the output |
|
31 { |
|
32 wchar_t* startOfUnicode=aUnicode; |
|
33 for (;;) |
|
34 { |
|
35 unsigned int currentUtf8Byte=*aUtf8; |
|
36 if (currentUtf8Byte=='\0') |
|
37 { |
|
38 break; |
|
39 } |
|
40 if ((currentUtf8Byte&0x80)==0x00) |
|
41 { |
|
42 if (startOfUnicode!=NULL) |
|
43 { |
|
44 *aUnicode=(wchar_t)currentUtf8Byte; |
|
45 } |
|
46 } |
|
47 else if ((currentUtf8Byte&0xe0)==0xc0) |
|
48 { |
|
49 unsigned int currentUnicodeCharacter=((currentUtf8Byte&0x1f)<<6); |
|
50 ++aUtf8; |
|
51 currentUtf8Byte=*aUtf8; |
|
52 if ((currentUtf8Byte&0xc0)!=0x80) |
|
53 { |
|
54 return KErrorIllFormedInput; |
|
55 } |
|
56 currentUnicodeCharacter|=(currentUtf8Byte&0x3f); |
|
57 if (startOfUnicode!=NULL) |
|
58 { |
|
59 *aUnicode=(wchar_t)currentUnicodeCharacter; |
|
60 } |
|
61 } |
|
62 else if ((currentUtf8Byte&0xf0)==0xe0) |
|
63 { |
|
64 unsigned int currentUnicodeCharacter=((currentUtf8Byte&0x0f)<<12); |
|
65 ++aUtf8; |
|
66 currentUtf8Byte=*aUtf8; |
|
67 if ((currentUtf8Byte&0xc0)!=0x80) |
|
68 { |
|
69 return KErrorIllFormedInput; |
|
70 } |
|
71 currentUnicodeCharacter|=((currentUtf8Byte&0x3f)<<6); |
|
72 ++aUtf8; |
|
73 currentUtf8Byte=*aUtf8; |
|
74 if ((currentUtf8Byte&0xc0)!=0x80) |
|
75 { |
|
76 return KErrorIllFormedInput; |
|
77 } |
|
78 currentUnicodeCharacter|=(currentUtf8Byte&0x3f); |
|
79 if (startOfUnicode!=NULL) |
|
80 { |
|
81 *aUnicode=(wchar_t)currentUnicodeCharacter; |
|
82 } |
|
83 } |
|
84 else if ((currentUtf8Byte&0xf8)==0xf0) |
|
85 { |
|
86 unsigned int currentUnicodeCharacter=((currentUtf8Byte&0x07)<<8); |
|
87 ++aUtf8; |
|
88 currentUtf8Byte=*aUtf8; |
|
89 if ((currentUtf8Byte&0xc0)!=0x80) |
|
90 { |
|
91 return KErrorIllFormedInput; |
|
92 } |
|
93 currentUnicodeCharacter|=((currentUtf8Byte&0x3f)<<2); |
|
94 if (currentUnicodeCharacter<0x0040) |
|
95 { |
|
96 return KErrorIllFormedInput; |
|
97 } |
|
98 currentUnicodeCharacter-=0x0040; |
|
99 if (currentUnicodeCharacter>=0x0400) |
|
100 { |
|
101 return KErrorIllFormedInput; |
|
102 } |
|
103 ++aUtf8; |
|
104 currentUtf8Byte=*aUtf8; |
|
105 if ((currentUtf8Byte&0xc0)!=0x80) |
|
106 { |
|
107 return KErrorIllFormedInput; |
|
108 } |
|
109 currentUnicodeCharacter|=((currentUtf8Byte&0x30)>>4); |
|
110 if (startOfUnicode!=NULL) |
|
111 { |
|
112 *aUnicode=(wchar_t)(0xd800|currentUnicodeCharacter); |
|
113 } |
|
114 currentUnicodeCharacter=((currentUtf8Byte&0x0f)<<6); |
|
115 ++aUtf8; |
|
116 currentUtf8Byte=*aUtf8; |
|
117 if ((currentUtf8Byte&0xc0)!=0x80) |
|
118 { |
|
119 return KErrorIllFormedInput; |
|
120 } |
|
121 currentUnicodeCharacter|=(currentUtf8Byte&0x3f); |
|
122 ++aUnicode; |
|
123 if (startOfUnicode!=NULL) |
|
124 { |
|
125 *aUnicode=(wchar_t)(0xdc00|currentUnicodeCharacter); |
|
126 } |
|
127 } |
|
128 else |
|
129 { |
|
130 return KErrorIllFormedInput; |
|
131 } |
|
132 ++aUnicode; |
|
133 ++aUtf8; |
|
134 } |
|
135 if (startOfUnicode!=NULL) |
|
136 { |
|
137 *aUnicode='\0'; |
|
138 } |
|
139 return aUnicode-startOfUnicode; |
|
140 } |
|
141 #include <STDIO.H> |
|
142 int UnicodeToUtf8(char* aUtf8, const wchar_t* aUnicode) |
|
143 // must '\0'-terminate the output |
|
144 { |
|
145 char* startOfUtf8=aUtf8; |
|
146 for (;;) |
|
147 { |
|
148 unsigned int currentUnicodeCharacter=*aUnicode; |
|
149 if (currentUnicodeCharacter=='\0') |
|
150 { |
|
151 break; |
|
152 } |
|
153 if ((currentUnicodeCharacter&0xff80)==0x0000) |
|
154 { |
|
155 if (startOfUtf8!=NULL) |
|
156 { |
|
157 *aUtf8=(char)currentUnicodeCharacter; |
|
158 } |
|
159 } |
|
160 else if ((currentUnicodeCharacter&0xf800)==0x0000) |
|
161 { |
|
162 if (startOfUtf8!=NULL) |
|
163 { |
|
164 *aUtf8=(char)(0xc0|(currentUnicodeCharacter>>6)); |
|
165 } |
|
166 ++aUtf8; |
|
167 if (startOfUtf8!=NULL) |
|
168 { |
|
169 *aUtf8=(char)(0x80|(currentUnicodeCharacter&0x3f)); |
|
170 } |
|
171 } |
|
172 else if ((currentUnicodeCharacter&0xfc00)==0xd800) |
|
173 { |
|
174 currentUnicodeCharacter+=0x0040; |
|
175 if (startOfUtf8!=NULL) |
|
176 { |
|
177 *aUtf8=(char)(0xf0|((currentUnicodeCharacter>>8)&0x07)); |
|
178 } |
|
179 ++aUtf8; |
|
180 if (startOfUtf8!=NULL) |
|
181 { |
|
182 *aUtf8=(char)(0x80|((currentUnicodeCharacter>>2)&0x3f)); |
|
183 } |
|
184 { |
|
185 unsigned int currentUtf8Byte=(0x80|((currentUnicodeCharacter&0x03)<<4)); |
|
186 ++aUnicode; |
|
187 currentUnicodeCharacter=*aUnicode; |
|
188 if ((currentUnicodeCharacter&0xfc00)!=0xdc00) |
|
189 { |
|
190 return KErrorIllFormedInput; |
|
191 } |
|
192 currentUtf8Byte|=((currentUnicodeCharacter>>6)&0x0f); |
|
193 ++aUtf8; |
|
194 if (startOfUtf8!=NULL) |
|
195 { |
|
196 *aUtf8=(char)currentUtf8Byte; |
|
197 } |
|
198 } |
|
199 ++aUtf8; |
|
200 if (startOfUtf8!=NULL) |
|
201 { |
|
202 *aUtf8=(char)(0x80|(currentUnicodeCharacter&0x3f)); |
|
203 } |
|
204 } |
|
205 else |
|
206 { |
|
207 if (startOfUtf8!=NULL) |
|
208 { |
|
209 *aUtf8=(char)(0xe0|(currentUnicodeCharacter>>12)); |
|
210 } |
|
211 ++aUtf8; |
|
212 if (startOfUtf8!=NULL) |
|
213 { |
|
214 *aUtf8=(char)(0x80|((currentUnicodeCharacter>>6)&0x3f)); |
|
215 } |
|
216 ++aUtf8; |
|
217 if (startOfUtf8!=NULL) |
|
218 { |
|
219 *aUtf8=(char)(0x80|(currentUnicodeCharacter&0x3f)); |
|
220 } |
|
221 } |
|
222 ++aUtf8; |
|
223 ++aUnicode; |
|
224 } |
|
225 if (startOfUtf8!=NULL) |
|
226 { |
|
227 *aUtf8='\0'; |
|
228 } |
|
229 return aUtf8-startOfUtf8; |
|
230 } |
|
231 |