xemu/qobject/json-streamer.c

135 lines
3.6 KiB
C
Raw Permalink Normal View History

/*
* JSON streaming support
*
* Copyright IBM, Corp. 2009
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "json-parser-int.h"
#define MAX_TOKEN_SIZE (64ULL << 20)
#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;
json: Redesign the callback to consume JSON values The classical way to structure parser and lexer is to have the client call the parser to get an abstract syntax tree, the parser call the lexer to get the next token, and the lexer call some function to get input characters. Another way to structure them would be to have the client feed characters to the lexer, the lexer feed tokens to the parser, and the parser feed abstract syntax trees to some callback provided by the client. This way is more easily integrated into an event loop that dispatches input characters as they arrive. Our JSON parser is kind of between the two. The lexer feeds tokens to a "streamer" instead of a real parser. The streamer accumulates tokens until it got the sequence of tokens that comprise a single JSON value (it counts curly braces and square brackets to decide). It feeds those token sequences to a callback provided by the client. The callback passes each token sequence to the parser, and gets back an abstract syntax tree. I figure it was done that way to make a straightforward recursive descent parser possible. "Get next token" becomes "pop the first token off the token sequence". Drawback: we need to store a complete token sequence. Each token eats 13 + input characters + malloc overhead bytes. Observations: 1. This is not the only way to use recursive descent. If we replaced "get next token" by a coroutine yield, we could do without a streamer. 2. The lexer reports errors by passing a JSON_ERROR token to the streamer. This communicates the offending input characters and their location, but no more. 3. The streamer reports errors by passing a null token sequence to the callback. The (already poor) lexical error information is thrown away. 4. Having the callback receive a token sequence duplicates the code to convert token sequence to abstract syntax tree in every callback. 5. Known bug: the streamer silently drops incomplete token sequences. This commit rectifies 4. by lifting the call of the parser from the callbacks into the streamer. Later commits will address 3. and 5. The lifting removes a bug from qjson.c's parse_json(): it passed a pointer to a non-null Error * in certain cases, as demonstrated by check-qjson.c. json_parser_parse() is now unused. It's a stupid wrapper around json_parser_parse_err(). Drop it, and rename json_parser_parse_err() to json_parser_parse(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180823164025.12553-35-armbru@redhat.com>
2018-08-23 16:40:01 +00:00
Error *err = NULL;
JSONToken *token;
switch (type) {
case JSON_LCURLY:
parser->brace_count++;
break;
case JSON_RCURLY:
parser->brace_count--;
break;
case JSON_LSQUARE:
parser->bracket_count++;
break;
case JSON_RSQUARE:
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:
if (g_queue_is_empty(&parser->tokens)) {
return;
}
json = json_parser_parse(&parser->tokens, parser->ap, &err);
goto out_emit;
default:
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;
}
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)
&& parser->brace_count >= 0 && parser->bracket_count >= 0) {
return;
}
json = json_parser_parse(&parser->tokens, parser->ap, &err);
out_emit:
parser->brace_count = 0;
parser->bracket_count = 0;
json_message_free_tokens(parser);
parser->token_size = 0;
json: Redesign the callback to consume JSON values The classical way to structure parser and lexer is to have the client call the parser to get an abstract syntax tree, the parser call the lexer to get the next token, and the lexer call some function to get input characters. Another way to structure them would be to have the client feed characters to the lexer, the lexer feed tokens to the parser, and the parser feed abstract syntax trees to some callback provided by the client. This way is more easily integrated into an event loop that dispatches input characters as they arrive. Our JSON parser is kind of between the two. The lexer feeds tokens to a "streamer" instead of a real parser. The streamer accumulates tokens until it got the sequence of tokens that comprise a single JSON value (it counts curly braces and square brackets to decide). It feeds those token sequences to a callback provided by the client. The callback passes each token sequence to the parser, and gets back an abstract syntax tree. I figure it was done that way to make a straightforward recursive descent parser possible. "Get next token" becomes "pop the first token off the token sequence". Drawback: we need to store a complete token sequence. Each token eats 13 + input characters + malloc overhead bytes. Observations: 1. This is not the only way to use recursive descent. If we replaced "get next token" by a coroutine yield, we could do without a streamer. 2. The lexer reports errors by passing a JSON_ERROR token to the streamer. This communicates the offending input characters and their location, but no more. 3. The streamer reports errors by passing a null token sequence to the callback. The (already poor) lexical error information is thrown away. 4. Having the callback receive a token sequence duplicates the code to convert token sequence to abstract syntax tree in every callback. 5. Known bug: the streamer silently drops incomplete token sequences. This commit rectifies 4. by lifting the call of the parser from the callbacks into the streamer. Later commits will address 3. and 5. The lifting removes a bug from qjson.c's parse_json(): it passed a pointer to a non-null Error * in certain cases, as demonstrated by check-qjson.c. json_parser_parse() is now unused. It's a stupid wrapper around json_parser_parse_err(). Drop it, and rename json_parser_parse_err() to json_parser_parse(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180823164025.12553-35-armbru@redhat.com>
2018-08-23 16:40:01 +00:00
parser->emit(parser->opaque, json, err);
}
void json_message_parser_init(JSONMessageParser *parser,
json: Redesign the callback to consume JSON values The classical way to structure parser and lexer is to have the client call the parser to get an abstract syntax tree, the parser call the lexer to get the next token, and the lexer call some function to get input characters. Another way to structure them would be to have the client feed characters to the lexer, the lexer feed tokens to the parser, and the parser feed abstract syntax trees to some callback provided by the client. This way is more easily integrated into an event loop that dispatches input characters as they arrive. Our JSON parser is kind of between the two. The lexer feeds tokens to a "streamer" instead of a real parser. The streamer accumulates tokens until it got the sequence of tokens that comprise a single JSON value (it counts curly braces and square brackets to decide). It feeds those token sequences to a callback provided by the client. The callback passes each token sequence to the parser, and gets back an abstract syntax tree. I figure it was done that way to make a straightforward recursive descent parser possible. "Get next token" becomes "pop the first token off the token sequence". Drawback: we need to store a complete token sequence. Each token eats 13 + input characters + malloc overhead bytes. Observations: 1. This is not the only way to use recursive descent. If we replaced "get next token" by a coroutine yield, we could do without a streamer. 2. The lexer reports errors by passing a JSON_ERROR token to the streamer. This communicates the offending input characters and their location, but no more. 3. The streamer reports errors by passing a null token sequence to the callback. The (already poor) lexical error information is thrown away. 4. Having the callback receive a token sequence duplicates the code to convert token sequence to abstract syntax tree in every callback. 5. Known bug: the streamer silently drops incomplete token sequences. This commit rectifies 4. by lifting the call of the parser from the callbacks into the streamer. Later commits will address 3. and 5. The lifting removes a bug from qjson.c's parse_json(): it passed a pointer to a non-null Error * in certain cases, as demonstrated by check-qjson.c. json_parser_parse() is now unused. It's a stupid wrapper around json_parser_parse_err(). Drop it, and rename json_parser_parse_err() to json_parser_parse(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180823164025.12553-35-armbru@redhat.com>
2018-08-23 16:40:01 +00:00
void (*emit)(void *opaque, QObject *json,
Error *err),
void *opaque, va_list *ap)
{
json: Redesign the callback to consume JSON values The classical way to structure parser and lexer is to have the client call the parser to get an abstract syntax tree, the parser call the lexer to get the next token, and the lexer call some function to get input characters. Another way to structure them would be to have the client feed characters to the lexer, the lexer feed tokens to the parser, and the parser feed abstract syntax trees to some callback provided by the client. This way is more easily integrated into an event loop that dispatches input characters as they arrive. Our JSON parser is kind of between the two. The lexer feeds tokens to a "streamer" instead of a real parser. The streamer accumulates tokens until it got the sequence of tokens that comprise a single JSON value (it counts curly braces and square brackets to decide). It feeds those token sequences to a callback provided by the client. The callback passes each token sequence to the parser, and gets back an abstract syntax tree. I figure it was done that way to make a straightforward recursive descent parser possible. "Get next token" becomes "pop the first token off the token sequence". Drawback: we need to store a complete token sequence. Each token eats 13 + input characters + malloc overhead bytes. Observations: 1. This is not the only way to use recursive descent. If we replaced "get next token" by a coroutine yield, we could do without a streamer. 2. The lexer reports errors by passing a JSON_ERROR token to the streamer. This communicates the offending input characters and their location, but no more. 3. The streamer reports errors by passing a null token sequence to the callback. The (already poor) lexical error information is thrown away. 4. Having the callback receive a token sequence duplicates the code to convert token sequence to abstract syntax tree in every callback. 5. Known bug: the streamer silently drops incomplete token sequences. This commit rectifies 4. by lifting the call of the parser from the callbacks into the streamer. Later commits will address 3. and 5. The lifting removes a bug from qjson.c's parse_json(): it passed a pointer to a non-null Error * in certain cases, as demonstrated by check-qjson.c. json_parser_parse() is now unused. It's a stupid wrapper around json_parser_parse_err(). Drop it, and rename json_parser_parse_err() to json_parser_parse(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180823164025.12553-35-armbru@redhat.com>
2018-08-23 16:40:01 +00:00
parser->emit = emit;
parser->opaque = opaque;
parser->ap = ap;
parser->brace_count = 0;
parser->bracket_count = 0;
g_queue_init(&parser->tokens);
parser->token_size = 0;
json_lexer_init(&parser->lexer, !!ap);
}
void json_message_parser_feed(JSONMessageParser *parser,
const char *buffer, size_t size)
{
json_lexer_feed(&parser->lexer, buffer, size);
}
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);
}