['u'] = IN_DQ_UCODE0,
},
[IN_DQ_STRING] = {
- [1 ... 0xFF] = IN_DQ_STRING,
+ [1 ... 0xBF] = IN_DQ_STRING,
+ [0xC2 ... 0xF4] = IN_DQ_STRING,
['\\'] = IN_DQ_STRING_ESCAPE,
['"'] = JSON_STRING,
},
['u'] = IN_SQ_UCODE0,
},
[IN_SQ_STRING] = {
- [1 ... 0xFF] = IN_SQ_STRING,
+ [1 ... 0xBF] = IN_SQ_STRING,
+ [0xC2 ... 0xF4] = IN_SQ_STRING,
['\\'] = IN_SQ_STRING_ESCAPE,
['\''] = JSON_STRING,
},
new_state = IN_START;
break;
case IN_ERROR:
+ /* XXX: To avoid having previous bad input leaving the parser in an
+ * unresponsive state where we consume unpredictable amounts of
+ * subsequent "good" input, percolate this error state up to the
+ * tokenizer/parser by forcing a NULL object to be emitted, then
+ * reset state.
+ *
+ * Also note that this handling is required for reliable channel
+ * negotiation between QMP and the guest agent, since chr(0xFF)
+ * is placed at the beginning of certain events to ensure proper
+ * delivery when the channel is in an unknown state. chr(0xFF) is
+ * never a valid ASCII/UTF-8 sequence, so this should reliably
+ * induce an error/flush state.
+ */
+ lexer->emit(lexer, lexer->token, JSON_ERROR, lexer->x, lexer->y);
QDECREF(lexer->token);
lexer->token = qstring_new();
new_state = IN_START;
- return -EINVAL;
+ lexer->state = new_state;
+ return 0;
default:
break;
}
int json_lexer_flush(JSONLexer *lexer)
{
- return lexer->state == IN_START ? 0 : json_lexer_feed_char(lexer, 0);
+ return lexer->state == IN_START ? 0 : json_lexer_feed_char(lexer, 0, true);
}
void json_lexer_destroy(JSONLexer *lexer)