mirror of
https://github.com/qemu/qemu.git
synced 2026-07-08 17:46:17 +00:00
json-streamer: remove token queue
Now fully exploit the push parser, feeding it one token at a time
without having to wait until braces and brackets are balanced.
While the nesting counts are retained for error recovery purposes,
the system can now report the first parsing error without waiting
for parentheses to be balanced. This also means that JSON_ERROR
can be handled in json-parser.c, not json-streamer.c.
After reporting the error, json-streamer.c then enters an error recovery
mode where subsequent errors are suppressed. This mimics the previous
error reporting behavior, but it provides prompt feedback on parsing
errors. As an example, here is an example interaction with qemu-ga.
BEFORE (error reported only once braces are balanced):
>> {"execute":foo
>> }
<< {"error": {"class": "GenericError", "desc": "JSON parse error, invalid keyword 'foo'"}}
>> {"execute":"somecommand"}
<< {"error": {"class": "CommandNotFound", "desc": "The command somecommand has not been found"}}
AFTER (error reported immediately, but similar error recovery as before):
>> {"execute":foo
<< {"error": {"class": "GenericError", "desc": "JSON parse error, invalid keyword 'foo'"}}
>> }
>> {"execute":"somecommand"}
<< {"error": {"class": "CommandNotFound", "desc": "The command somecommand has not been found"}}
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20260626101727.1727389-5-pbonzini@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
[Token size limit check off-by-one fixed]
Signed-off-by: Markus Armbruster <armbru@redhat.com>
This commit is contained in:
committed by
Markus Armbruster
parent
19c04b99ca
commit
ddd1f36f81
@@ -33,7 +33,8 @@ typedef struct JSONMessageParser {
|
||||
JSONParserContext parser;
|
||||
unsigned int brace_count;
|
||||
unsigned int bracket_count;
|
||||
GQueue tokens;
|
||||
unsigned int token_count;
|
||||
bool error;
|
||||
uint64_t token_size;
|
||||
} JSONMessageParser;
|
||||
|
||||
|
||||
@@ -675,6 +675,10 @@ QObject *json_parser_feed(JSONParserContext *ctxt, const JSONToken *token,
|
||||
|
||||
assert(!ctxt->err);
|
||||
switch (token->type) {
|
||||
case JSON_ERROR:
|
||||
parse_error(ctxt, token, "stray '%s'", token->str);
|
||||
break;
|
||||
|
||||
case JSON_END_OF_INPUT:
|
||||
/* Check for premature end of input */
|
||||
if (!g_queue_is_empty(ctxt->stack)) {
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/*
|
||||
* JSON streaming support
|
||||
* JSON parser - callback interface and error recovery
|
||||
*
|
||||
* Copyright IBM, Corp. 2009
|
||||
*
|
||||
@@ -19,23 +19,16 @@
|
||||
#define MAX_TOKEN_COUNT (2ULL << 20)
|
||||
#define MAX_NESTING (1 << 10)
|
||||
|
||||
static void json_message_free_tokens(JSONMessageParser *parser)
|
||||
{
|
||||
JSONToken *token;
|
||||
|
||||
while ((token = g_queue_pop_head(&parser->tokens))) {
|
||||
g_free(token);
|
||||
}
|
||||
}
|
||||
|
||||
void json_message_process_token(JSONLexer *lexer, GString *input,
|
||||
JSONTokenType type, int x, int y)
|
||||
{
|
||||
JSONMessageParser *parser = container_of(lexer, JSONMessageParser, lexer);
|
||||
QObject *json = NULL;
|
||||
Error *err = NULL;
|
||||
JSONToken *token;
|
||||
|
||||
parser->token_size += input->len;
|
||||
parser->token_count++;
|
||||
|
||||
/* Detect message boundaries for error recovery purposes. */
|
||||
switch (type) {
|
||||
case JSON_LCURLY:
|
||||
parser->brace_count++;
|
||||
@@ -56,16 +49,6 @@ void json_message_process_token(JSONLexer *lexer, GString *input,
|
||||
parser->bracket_count--;
|
||||
break;
|
||||
case JSON_ERROR:
|
||||
error_setg(&err, "JSON parse error, stray '%s'", input->str);
|
||||
goto out_emit;
|
||||
case JSON_END_OF_INPUT:
|
||||
/*
|
||||
* Force the parentheses to appear balanced and the queue
|
||||
* to be emptied, causing a parse error if it wasn't.
|
||||
*/
|
||||
if (g_queue_is_empty(&parser->tokens)) {
|
||||
return;
|
||||
}
|
||||
end_error_recovery:
|
||||
/*
|
||||
* We come here due to receiving either JSON_ERROR or a
|
||||
@@ -81,49 +64,43 @@ void json_message_process_token(JSONLexer *lexer, GString *input,
|
||||
break;
|
||||
}
|
||||
|
||||
/*
|
||||
* Security consideration, we limit total memory allocated per object
|
||||
* and the maximum recursion depth that a message can force.
|
||||
*/
|
||||
if (parser->token_size + input->len + 1 > MAX_TOKEN_SIZE) {
|
||||
error_setg(&err, "JSON token size limit exceeded");
|
||||
goto out_emit;
|
||||
}
|
||||
if (g_queue_get_length(&parser->tokens) + 1 > MAX_TOKEN_COUNT) {
|
||||
error_setg(&err, "JSON token count limit exceeded");
|
||||
goto out_emit;
|
||||
}
|
||||
if (parser->bracket_count + parser->brace_count > MAX_NESTING) {
|
||||
error_setg(&err, "JSON nesting depth limit exceeded");
|
||||
goto out_emit;
|
||||
}
|
||||
if (parser->error) {
|
||||
/* error recovery, eat tokens until parentheses balance */
|
||||
} else {
|
||||
/*
|
||||
* Safety consideration, we limit total memory allocated per object
|
||||
* and the maximum nesting depth that a message can force.
|
||||
*/
|
||||
if (parser->token_size >= MAX_TOKEN_SIZE) {
|
||||
error_setg(&err, "JSON token size limit exceeded");
|
||||
} else if (parser->token_count > MAX_TOKEN_COUNT) {
|
||||
error_setg(&err, "JSON token count limit exceeded");
|
||||
} else if (parser->bracket_count + parser->brace_count > MAX_NESTING) {
|
||||
error_setg(&err, "JSON nesting depth limit exceeded");
|
||||
} else {
|
||||
g_autofree JSONToken *token = json_token(type, x, y, input);
|
||||
QObject *json = json_parser_feed(&parser->parser, token, &err);
|
||||
if (json) {
|
||||
parser->emit(parser->opaque, json, NULL);
|
||||
}
|
||||
}
|
||||
|
||||
token = json_token(type, x, y, input);
|
||||
parser->token_size += input->len;
|
||||
|
||||
g_queue_push_tail(&parser->tokens, token);
|
||||
|
||||
if (parser->brace_count > 0 || parser->bracket_count > 0) {
|
||||
return;
|
||||
}
|
||||
|
||||
/* Process all tokens in the queue */
|
||||
while (!g_queue_is_empty(&parser->tokens)) {
|
||||
token = g_queue_pop_head(&parser->tokens);
|
||||
json = json_parser_feed(&parser->parser, token, &err);
|
||||
g_free(token);
|
||||
if (json || err) {
|
||||
break;
|
||||
if (err) {
|
||||
parser->emit(parser->opaque, NULL, err);
|
||||
/* start recovery */
|
||||
parser->error = true;
|
||||
}
|
||||
}
|
||||
|
||||
out_emit:
|
||||
json_parser_reset(&parser->parser);
|
||||
parser->brace_count = 0;
|
||||
parser->bracket_count = 0;
|
||||
json_message_free_tokens(parser);
|
||||
parser->token_size = 0;
|
||||
parser->emit(parser->opaque, json, err);
|
||||
if ((parser->brace_count == 0 && parser->bracket_count == 0)
|
||||
|| type == JSON_END_OF_INPUT) {
|
||||
json_parser_reset(&parser->parser);
|
||||
parser->error = false;
|
||||
parser->brace_count = 0;
|
||||
parser->bracket_count = 0;
|
||||
parser->token_count = 0;
|
||||
parser->token_size = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void json_message_parser_init(JSONMessageParser *parser,
|
||||
@@ -133,9 +110,10 @@ void json_message_parser_init(JSONMessageParser *parser,
|
||||
{
|
||||
parser->emit = emit;
|
||||
parser->opaque = opaque;
|
||||
parser->error = false;
|
||||
parser->brace_count = 0;
|
||||
parser->bracket_count = 0;
|
||||
g_queue_init(&parser->tokens);
|
||||
parser->token_count = 0;
|
||||
parser->token_size = 0;
|
||||
|
||||
json_parser_init(&parser->parser, ap);
|
||||
@@ -151,12 +129,10 @@ void json_message_parser_feed(JSONMessageParser *parser,
|
||||
void json_message_parser_flush(JSONMessageParser *parser)
|
||||
{
|
||||
json_lexer_flush(&parser->lexer);
|
||||
assert(g_queue_is_empty(&parser->tokens));
|
||||
}
|
||||
|
||||
void json_message_parser_destroy(JSONMessageParser *parser)
|
||||
{
|
||||
json_lexer_destroy(&parser->lexer);
|
||||
json_message_free_tokens(parser);
|
||||
json_parser_destroy(&parser->parser);
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user