error_setg(&ctxt->err, "JSON parse error, %s", message);
}
-/**
- * String helpers
- *
- * These helpers are used to unescape strings.
- */
-static void wchar_to_utf8(uint16_t wchar, char *buffer, size_t buffer_length)
+static int cvt4hex(const char *s)
{
- if (wchar <= 0x007F) {
- BUG_ON(buffer_length < 2);
-
- buffer[0] = wchar & 0x7F;
- buffer[1] = 0;
- } else if (wchar <= 0x07FF) {
- BUG_ON(buffer_length < 3);
-
- buffer[0] = 0xC0 | ((wchar >> 6) & 0x1F);
- buffer[1] = 0x80 | (wchar & 0x3F);
- buffer[2] = 0;
- } else {
- BUG_ON(buffer_length < 4);
-
- buffer[0] = 0xE0 | ((wchar >> 12) & 0x0F);
- buffer[1] = 0x80 | ((wchar >> 6) & 0x3F);
- buffer[2] = 0x80 | (wchar & 0x3F);
- buffer[3] = 0;
- }
-}
+ int cp, i;
-static int hex2decimal(char ch)
-{
- if (ch >= '0' && ch <= '9') {
- return (ch - '0');
- } else if (ch >= 'a' && ch <= 'f') {
- return 10 + (ch - 'a');
- } else if (ch >= 'A' && ch <= 'F') {
- return 10 + (ch - 'A');
+ cp = 0;
+ for (i = 0; i < 4; i++) {
+ if (!qemu_isxdigit(s[i])) {
+ return -1;
+ }
+ cp <<= 4;
+ if (s[i] >= '0' && s[i] <= '9') {
+ cp |= s[i] - '0';
+ } else if (s[i] >= 'a' && s[i] <= 'f') {
+ cp |= 10 + s[i] - 'a';
+ } else if (s[i] >= 'A' && s[i] <= 'F') {
+ cp |= 10 + s[i] - 'A';
+ } else {
+ return -1;
+ }
}
-
- return -1;
+ return cp;
}
/**
const char *ptr = token->str;
QString *str;
char quote;
- int cp;
+ const char *beg;
+ int cp, trailing;
char *end;
ssize_t len;
char utf8_buf[5];
while (*ptr != quote) {
assert(*ptr);
if (*ptr == '\\') {
- ptr++;
+ beg = ptr++;
switch (*ptr++) {
case '"':
- qstring_append(str, "\"");
+ qstring_append_chr(str, '"');
break;
case '\'':
- qstring_append(str, "'");
+ qstring_append_chr(str, '\'');
break;
case '\\':
- qstring_append(str, "\\");
+ qstring_append_chr(str, '\\');
break;
case '/':
- qstring_append(str, "/");
+ qstring_append_chr(str, '/');
break;
case 'b':
- qstring_append(str, "\b");
+ qstring_append_chr(str, '\b');
break;
case 'f':
- qstring_append(str, "\f");
+ qstring_append_chr(str, '\f');
break;
case 'n':
- qstring_append(str, "\n");
+ qstring_append_chr(str, '\n');
break;
case 'r':
- qstring_append(str, "\r");
+ qstring_append_chr(str, '\r');
break;
case 't':
- qstring_append(str, "\t");
+ qstring_append_chr(str, '\t');
break;
- case 'u': {
- uint16_t unicode_char = 0;
- char utf8_char[4];
- int i = 0;
-
- for (i = 0; i < 4; i++) {
- if (qemu_isxdigit(*ptr)) {
- unicode_char |= hex2decimal(*ptr) << ((3 - i) * 4);
+ case 'u':
+ cp = cvt4hex(ptr);
+ ptr += 4;
+
+ /* handle surrogate pairs */
+ if (cp >= 0xD800 && cp <= 0xDBFF
+ && ptr[0] == '\\' && ptr[1] == 'u') {
+ /* leading surrogate followed by \u */
+ cp = 0x10000 + ((cp & 0x3FF) << 10);
+ trailing = cvt4hex(ptr + 2);
+ if (trailing >= 0xDC00 && trailing <= 0xDFFF) {
+ /* followed by trailing surrogate */
+ cp |= trailing & 0x3FF;
+ ptr += 6;
} else {
- parse_error(ctxt, token,
- "invalid hex escape sequence in string");
- goto out;
+ cp = -1; /* invalid */
}
- ptr++;
}
- wchar_to_utf8(unicode_char, utf8_char, sizeof(utf8_char));
- qstring_append(str, utf8_char);
- } break;
+ if (mod_utf8_encode(utf8_buf, sizeof(utf8_buf), cp) < 0) {
+ parse_error(ctxt, token,
+ "%.*s is not a valid Unicode character",
+ (int)(ptr - beg), beg);
+ goto out;
+ }
+ qstring_append(str, utf8_buf);
+ break;
default:
parse_error(ctxt, token, "invalid escape sequence in string");
goto out;
return g_queue_peek_head(ctxt->buf);
}
-static JSONParserContext *parser_context_new(GQueue *tokens)
-{
- JSONParserContext *ctxt;
-
- if (!tokens) {
- return NULL;
- }
-
- ctxt = g_malloc0(sizeof(JSONParserContext));
- ctxt->buf = tokens;
-
- return ctxt;
-}
-
-/* to support error propagation, ctxt->err must be freed separately */
-static void parser_context_free(JSONParserContext *ctxt)
-{
- if (ctxt) {
- while (!g_queue_is_empty(ctxt->buf)) {
- parser_context_pop_token(ctxt);
- }
- g_free(ctxt->current);
- g_queue_free(ctxt->buf);
- g_free(ctxt);
- }
-}
-
/**
* Parsing rules
*/
QObject *json_parser_parse_err(GQueue *tokens, va_list *ap, Error **errp)
{
- JSONParserContext *ctxt = parser_context_new(tokens);
+ JSONParserContext ctxt = { .buf = tokens };
QObject *result;
- if (!ctxt) {
+ if (!tokens) {
return NULL;
}
- result = parse_value(ctxt, ap);
+ result = parse_value(&ctxt, ap);
- error_propagate(errp, ctxt->err);
+ error_propagate(errp, ctxt.err);
- parser_context_free(ctxt);
+ while (!g_queue_is_empty(ctxt.buf)) {
+ parser_context_pop_token(&ctxt);
+ }
+ g_free(ctxt.current);
+ g_queue_free(ctxt.buf);
return result;
}