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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
|
/* Copyright 2000-2005 The Apache Software Foundation or its licensors, as
* applicable.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include "apr.h"
#include "apr_private.h"
#include "apr_errno.h"
#include "apr_arch_utf8.h"
/* Implement the design principal specified by RFC 2718 2.2.5
* Guidelines for new URL Schemes - within the APR.
*
* Since many architectures support unicode, and UCS2 is the most
* efficient storage used by those archictures, these functions
* exist to validate a UCS string. It is up to the operating system
* to determine the validitity of the string in the context of it's
* native language support. File systems that support filename
* characters of 0x80-0xff but have no support of Unicode will find
* this function useful only for validating the character sequences
* and rejecting poorly encoded strings, if RFC 2718 2.2.5 naming is
* desired.
*
* from RFC 2279 UTF-8, a transformation format of ISO 10646
*
* UCS-4 range (hex.) UTF-8 octet sequence (binary)
* 1:2 0000 0000-0000 007F 0xxxxxxx
* 2:2 0000 0080-0000 07FF 110XXXXx 10xxxxxx
* 3:2 0000 0800-0000 FFFF 1110XXXX 10Xxxxxx 10xxxxxx
* 4:4 0001 0000-001F FFFF 11110zXX 10XXxxxx 10xxxxxx 10xxxxxx
* inv 0020 0000-03FF FFFF 111110XX 10XXXxxx 10xxxxxx 10xxxxxx 10xxxxxx
* inv 0400 0000-7FFF FFFF 1111110X 10XXXXxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
*
* One of the X values must be one for the encoding length to be legit.
* Neither the z bit, nor the final two forms, are used for ucs-2
*
* "Pairs of UCS-2 values between D800 and DFFF (surrogate pairs in
* Unicode parlance), being actually UCS-4 characters transformed
* through UTF-16, need special treatment: the UTF-16 transformation
* must be undone, yielding a UCS-4 character that is then transformed
* as above."
*
* from RFC2781 UTF-16: the compressed ISO 10646 encoding bitmask
*
* U' = U - 0x10000
* U' = 000000000000yyyyyyyyyyxxxxxxxxxx
* W1 = 110110yyyyyyyyyy
* W2 = 110111xxxxxxxxxx
*
* apr_conv_utf8_to_ucs2 out bytes:sizeof(in) * 1 <= Req <= sizeof(in) * 2
*
* apr_conv_ucs2_to_utf8 out words:sizeof(in) / 2 <= Req <= sizeof(in) * 3 / 2
*/
APR_DECLARE(apr_status_t) apr_conv_utf8_to_ucs2(const char *in,
apr_size_t *inbytes,
apr_wchar_t *out,
apr_size_t *outwords)
{
apr_int64_t newch, mask;
apr_size_t expect, eating;
int ch;
while (*inbytes && *outwords)
{
ch = (unsigned char)(*in++);
if (!(ch & 0200)) {
/* US-ASCII-7 plain text
*/
--*inbytes;
--*outwords;
*(out++) = ch;
}
else
{
if ((ch & 0300) != 0300) {
/* Multibyte Continuation is out of place
*/
return APR_EINVAL;
}
else
{
/* Multibyte Sequence Lead Character
*
* Compute the expected bytes while adjusting
* or lead byte and leading zeros mask.
*/
mask = 0340;
expect = 1;
while ((ch & mask) == mask) {
mask |= mask >> 1;
if (++expect > 3) /* (truly 5 for ucs-4) */
return APR_EINVAL;
}
newch = ch & ~mask;
eating = expect + 1;
if (*inbytes <= expect)
return APR_INCOMPLETE;
/* Reject values of excessive leading 0 bits
* utf-8 _demands_ the shortest possible byte length
*/
if (expect == 1) {
if (!(newch & 0036))
return APR_EINVAL;
}
else {
/* Reject values of excessive leading 0 bits
*/
if (!newch && !((unsigned char)*in & 0077 & (mask << 1)))
return APR_EINVAL;
if (expect == 2) {
/* Reject values D800-DFFF when not utf16 encoded
* (may not be an appropriate restriction for ucs-4)
*/
if (newch == 0015 && ((unsigned char)*in & 0040))
return APR_EINVAL;
}
else if (expect == 3) {
/* Short circuit values > 110000
*/
if (newch > 4)
return APR_EINVAL;
if (newch == 4 && ((unsigned char)*in & 0060))
return APR_EINVAL;
}
}
/* Where the boolean (expect > 2) is true, we will need
* an extra word for the output.
*/
if (*outwords < (apr_size_t)(expect > 2) + 1)
break; /* buffer full */
while (expect--)
{
/* Multibyte Continuation must be legal */
if (((ch = (unsigned char)*(in++)) & 0300) != 0200)
return APR_EINVAL;
newch <<= 6;
newch |= (ch & 0077);
}
*inbytes -= eating;
/* newch is now a true ucs-4 character
*
* now we need to fold to ucs-2
*/
if (newch < 0x10000)
{
--*outwords;
*(out++) = (apr_wchar_t) newch;
}
else
{
*outwords -= 2;
newch -= 0x10000;
*(out++) = (apr_wchar_t) (0xD800 | (newch >> 10));
*(out++) = (apr_wchar_t) (0xDC00 | (newch & 0x03FF));
}
}
}
}
/* Buffer full 'errors' aren't errors, the client must inspect both
* the inbytes and outwords values
*/
return APR_SUCCESS;
}
APR_DECLARE(apr_status_t) apr_conv_ucs2_to_utf8(const apr_wchar_t *in,
apr_size_t *inwords,
char *out,
apr_size_t *outbytes)
{
apr_int64_t newch, require;
apr_size_t need;
char *invout;
int ch;
while (*inwords && *outbytes)
{
ch = (unsigned short)(*in++);
if (ch < 0x80)
{
--*inwords;
--*outbytes;
*(out++) = (unsigned char) ch;
}
else
{
if ((ch & 0xFC00) == 0xDC00) {
/* Invalid Leading ucs-2 Multiword Continuation Character
*/
return APR_EINVAL;
}
if ((ch & 0xFC00) == 0xD800) {
/* Leading ucs-2 Multiword Character
*/
if (*inwords < 2) {
/* Missing ucs-2 Multiword Continuation Character
*/
return APR_INCOMPLETE;
}
if (((unsigned short)(*in) & 0xFC00) != 0xDC00) {
/* Invalid ucs-2 Multiword Continuation Character
*/
return APR_EINVAL;
}
newch = (ch & 0x03FF) << 10 | ((unsigned short)(*in++) & 0x03FF);
newch += 0x10000;
}
else {
/* ucs-2 Single Word Character
*/
newch = ch;
}
/* Determine the absolute minimum utf-8 bytes required
*/
require = newch >> 11;
need = 1;
while (require)
require >>= 5, ++need;
if (need >= *outbytes)
break; /* Insufficient buffer */
*inwords -= (need > 2) + 1;
*outbytes -= need + 1;
/* Compute the utf-8 characters in last to first order,
* calculating the lead character length bits along the way.
*/
ch = 0200;
out += need + 1;
invout = out;
while (need--) {
ch |= ch >> 1;
*(--invout) = (unsigned char)(0200 | (newch & 0077));
newch >>= 6;
}
/* Compute the lead utf-8 character and move the dest offset
*/
*(--invout) = (unsigned char)(ch | newch);
}
}
/* Buffer full 'errors' aren't errors, the client must inspect both
* the inwords and outbytes values
*/
return APR_SUCCESS;
}
|
