jansson/src/utf.c
Petri Lehtinen 902bcdaa5e Decode and check for correct UTF-8
All strings (decoded JSON text, the argument of json_string(), the key
argument of json_object_set()) are checked for valid UTF-8.
2009-07-13 23:38:01 +03:00

117 lines
2.3 KiB
C

#include <string.h>
int utf8_check_first(char byte)
{
unsigned char u = (unsigned char)byte;
if(u < 0x80)
return 1;
if(0x80 <= u && u <= 0xBF) {
/* second, third or fourth byte of a multi-byte
sequence, i.e. a "continuation byte" */
return 0;
}
else if(u == 0xC0 || u == 0xC1) {
/* overlong encoding of an ASCII byte */
return 0;
}
else if(0xC2 <= u && u <= 0xDF) {
/* 2-byte sequence */
return 2;
}
else if(0xE0 <= u && u <= 0xEF) {
/* 3-byte sequence */
return 3;
}
else if(0xF0 <= u && u <= 0xF4) {
/* 4-byte sequence */
return 4;
}
else { /* u >= 0xF5 */
/* Restricted (start of 4-, 5- or 6-byte sequence) or invalid
UTF-8 */
return 0;
}
}
int utf8_check_full(const char *buffer, int size)
{
int i, value = 0;
unsigned char u = (unsigned char)buffer[0];
if(size == 2)
{
value = u & 0x1F;
}
else if(size == 3)
{
value = u & 0xF;
}
else if(size == 4)
{
value = u & 0x7;
}
else
return 0;
for(i = 1; i < size; i++)
{
u = (unsigned char)buffer[i];
if(u < 0x80 || u > 0xBF) {
/* not a continuation byte */
return 0;
}
value = (value << 6) + (u & 0x3F);
}
if(value > 0x10FFFF) {
/* not in Unicode range */
return 0;
}
else if(0xD800 <= value && value <= 0xDFFF) {
/* invalid code point (UTF-16 surrogate halves) */
return 0;
}
else if((size == 2 && value < 0x80) ||
(size == 3 && value < 0x800) ||
(size == 4 && value < 0x10000)) {
/* overlong encoding */
return 0;
}
return 1;
}
int utf8_check_string(const char *string, int length)
{
int i;
if(length == -1)
length = strlen(string);
for(i = 0; i < length; i++)
{
int count = utf8_check_first(string[i]);
if(count == 0)
return 0;
else if(count > 1)
{
if(i + count > length)
return 0;
if(!utf8_check_full(&string[i], count))
return 0;
i += count - 1;
}
}
return 1;
}