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
|
** http://en.wikipedia.org/wiki/UTF-8#Invalid_byte_sequences
** except for the "overlong form" of \u0000 (Modified UTF-8)
** which is not considered invalid here: Some languages like
** Java and Tcl use it. This function also considers valid
** the derivatives CESU-8 & WTF-8 (as described in the same
** wikipedia article referenced previously).
*/
int invalid_utf8(
const Blob *pContent
){
/* definitions for various UTF-8 sequence lengths */
static unsigned char def_2a[] = {
2, 0xC0, 0xC0, 0x80, 0x80
};
static unsigned char def_2b[] = {
2, 0xC2, 0xDF, 0x80, 0xBF
};
static unsigned char def_3a[] = {
3, 0xE0, 0xE0, 0xA0, 0xBF, 0x80, 0xBF
};
static unsigned char def_3b[] = {
3, 0xE1, 0xEF, 0x80, 0xBF, 0x80, 0xBF
};
static unsigned char def_4a[] = {
4, 0xF0, 0xF0, 0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF
};
static unsigned char def_4b[] = {
4, 0xF1, 0xF3, 0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF
};
static unsigned char def_4c[] = {
4, 0xF4, 0xF4, 0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF
};
/* an array of all the definitions */
static unsigned char* def_arr[] = {
def_2a, def_2b, def_3a, def_3b, def_4a, def_4b, def_4c, NULL
};
/* a table used for quick lookup of the definition that goes with a
* particular lead byte */
static unsigned char* lb_tab[256] = { NULL };
/* a pointer to the table; NULL means not yet setup */
static unsigned char** lb_ptr = NULL;
const unsigned char *z;
unsigned int n;
/* if the table pointer hasn't been initialized */
if( lb_ptr==NULL ){
unsigned char** pp;
/* for each definition, set the lead byte table pointer to the
* proper definition */
lb_ptr = lb_tab;
pp = def_arr;
while( *pp!=NULL ){
unsigned char lo = pp[0][1];
unsigned char hi = pp[0][2];
unsigned char i;
for(i=lo; i<=hi; ++i){
lb_ptr[i] = pp[0];
}
++pp;
}
}
z = (unsigned char *)blob_buffer(pContent);
n = blob_size(pContent);
unsigned char* def = lb_ptr[*z++];
unsigned char i, len;
/* if the definition doesn't exist, return invalid */
if( !def ) return LOOK_INVALID;
/* get the expected sequence length */
len = *def;
/* if there aren't enough bytes left, return invalid */
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
|
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
|
** http://en.wikipedia.org/wiki/UTF-8#Invalid_byte_sequences
** except for the "overlong form" of \u0000 (Modified UTF-8)
** which is not considered invalid here: Some languages like
** Java and Tcl use it. This function also considers valid
** the derivatives CESU-8 & WTF-8 (as described in the same
** wikipedia article referenced previously).
*/
/* definitions for various UTF-8 sequence lengths */
static const unsigned char us2a[] = {
2, 0xC0, 0xC0, 0x80, 0x80
};
static const unsigned char us2b[] = {
2, 0xC2, 0xDF, 0x80, 0xBF
};
static const unsigned char us3a[] = {
3, 0xE0, 0xE0, 0xA0, 0xBF, 0x80, 0xBF
};
static const unsigned char us3b[] = {
3, 0xE1, 0xEF, 0x80, 0xBF, 0x80, 0xBF
};
static const unsigned char us4a[] = {
4, 0xF0, 0xF0, 0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF
};
static const unsigned char us4b[] = {
4, 0xF1, 0xF3, 0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF
};
static const unsigned char us4c[] = {
4, 0xF4, 0xF4, 0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF
};
/* a table used for quick lookup of the definition that goes with a
* particular lead byte */
static const unsigned char* lb_tab[] = {
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
us2a, NULL, us2b, us2b, us2b, us2b, us2b, us2b,
us2b, us2b, us2b, us2b, us2b, us2b, us2b, us2b,
us2b, us2b, us2b, us2b, us2b, us2b, us2b, us2b,
us2b, us2b, us2b, us2b, us2b, us2b, us2b, us2b,
us3a, us3b, us3b, us3b, us3b, us3b, us3b, us3b,
us3b, us3b, us3b, us3b, us3b, us3b, us3b, us3b,
us4a, us4b, us4b, us4b, us4c, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL
};
int invalid_utf8(
const Blob *pContent
){
/* buffer pointer and size */
const unsigned char *z = (unsigned char *)blob_buffer(pContent);
unsigned int n = blob_size(pContent);
/* while we haven't checked all the bytes in the buffer */
while( n>0 ){
/* ascii is trivial */
if( *z<0x80 ){
++z;
--n;
}else{
/* get the definition for this lead byte */
unsigned char* def = lb_tab[(*z++)-0x80];
unsigned char i, len;
/* if the definition doesn't exist, return invalid */
if( !def ) return LOOK_INVALID;
/* get the expected sequence length */
len = *def;
/* if there aren't enough bytes left, return invalid */
|