Function parse_string

cJSON.c:233–336

static const unsigned char firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0,
                0xF8, 0xFC };
static const char *parse_string(cJSON *item, const char *str, const char **ep)
{
    const char *ptr = str + 1;
    char *ptr2;
    char *out;
    int len = 0;
    unsigned uc, uc2;
    if (*str != '\"')
    {
        *ep = str;
        return 0;
    } /* not a string! */

    while (*ptr != '\"' && *ptr && ++len)
        if (*ptr++ == '\\')
            ptr++; /* Skip escaped quotes. */

    out = (char*) cJSON_malloc(len + 1); /* This is how long we need for the string, roughly. */
    if (!out)
        return 0;

    ptr = str + 1;
    ptr2 = out;
    while (*ptr != '\"' && *ptr)
    {
        if (*ptr != '\\')
            *ptr2++ = *ptr++;
        else
        {
            ptr++;
            switch (*ptr)
            {
            case 'b':
                *ptr2++ = '\b';
                break;
            case 'f':
                *ptr2++ = '\f';
                break;
            case 'n':
                *ptr2++ = '\n';
                break;
            case 'r':
                *ptr2++ = '\r';
                break;
            case 't':
                *ptr2++ = '\t';
                break;
            case 'u': /* transcode utf16 to utf8. */
                sscanf(ptr + 1, "%4x", &uc);
                ptr += 4; /* get the unicode char. */

                if ((uc >= 0xDC00 && uc <= 0xDFFF) || uc == 0)
                    break;	// check for invalid.

                if (uc >= 0xD800 && uc <= 0xDBFF)	// UTF16 surrogate pairs.
                {
                    if (ptr[1] != '\\' || ptr[2] != 'u')
                        break;	// missing second-half of surrogate.