json: Eliminate lexer state IN_WHITESPACE, pseudo-token JSON_SKIP
The lexer ignores whitespace like this: on whitespace on non-ws spontaneously IN_START --> IN_WHITESPACE --> JSON_SKIP --> IN_START ^ | \__/ on whitespace This accumulates a whitespace token in state IN_WHITESPACE, only to throw it away on the transition via JSON_SKIP to the start state. Wasteful. Go from IN_START to IN_START on whitespace directly, dropping the whitespace character. Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180831075841.13363-7-armbru@redhat.com>
This commit is contained in:
parent
2ce4ee64c4
commit
1e960b4602
@ -115,7 +115,6 @@ enum json_lexer_state {
|
|||||||
IN_SIGN,
|
IN_SIGN,
|
||||||
IN_KEYWORD,
|
IN_KEYWORD,
|
||||||
IN_INTERP,
|
IN_INTERP,
|
||||||
IN_WHITESPACE,
|
|
||||||
IN_START,
|
IN_START,
|
||||||
IN_START_INTERP, /* must be IN_START + 1 */
|
IN_START_INTERP, /* must be IN_START + 1 */
|
||||||
};
|
};
|
||||||
@ -228,15 +227,6 @@ static const uint8_t json_lexer[][256] = {
|
|||||||
['a' ... 'z'] = IN_KEYWORD,
|
['a' ... 'z'] = IN_KEYWORD,
|
||||||
},
|
},
|
||||||
|
|
||||||
/* whitespace */
|
|
||||||
[IN_WHITESPACE] = {
|
|
||||||
TERMINAL(JSON_SKIP),
|
|
||||||
[' '] = IN_WHITESPACE,
|
|
||||||
['\t'] = IN_WHITESPACE,
|
|
||||||
['\r'] = IN_WHITESPACE,
|
|
||||||
['\n'] = IN_WHITESPACE,
|
|
||||||
},
|
|
||||||
|
|
||||||
/* interpolation */
|
/* interpolation */
|
||||||
[IN_INTERP] = {
|
[IN_INTERP] = {
|
||||||
TERMINAL(JSON_INTERP),
|
TERMINAL(JSON_INTERP),
|
||||||
@ -263,10 +253,10 @@ static const uint8_t json_lexer[][256] = {
|
|||||||
[','] = JSON_COMMA,
|
[','] = JSON_COMMA,
|
||||||
[':'] = JSON_COLON,
|
[':'] = JSON_COLON,
|
||||||
['a' ... 'z'] = IN_KEYWORD,
|
['a' ... 'z'] = IN_KEYWORD,
|
||||||
[' '] = IN_WHITESPACE,
|
[' '] = IN_START,
|
||||||
['\t'] = IN_WHITESPACE,
|
['\t'] = IN_START,
|
||||||
['\r'] = IN_WHITESPACE,
|
['\r'] = IN_START,
|
||||||
['\n'] = IN_WHITESPACE,
|
['\n'] = IN_START,
|
||||||
},
|
},
|
||||||
[IN_START_INTERP]['%'] = IN_INTERP,
|
[IN_START_INTERP]['%'] = IN_INTERP,
|
||||||
};
|
};
|
||||||
@ -323,10 +313,8 @@ static void json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
|
|||||||
json_message_process_token(lexer, lexer->token, new_state,
|
json_message_process_token(lexer, lexer->token, new_state,
|
||||||
lexer->x, lexer->y);
|
lexer->x, lexer->y);
|
||||||
/* fall through */
|
/* fall through */
|
||||||
case JSON_SKIP:
|
|
||||||
g_string_truncate(lexer->token, 0);
|
|
||||||
/* fall through */
|
|
||||||
case IN_START:
|
case IN_START:
|
||||||
|
g_string_truncate(lexer->token, 0);
|
||||||
new_state = lexer->start_state;
|
new_state = lexer->start_state;
|
||||||
break;
|
break;
|
||||||
case JSON_ERROR:
|
case JSON_ERROR:
|
||||||
|
@ -31,7 +31,6 @@ typedef enum json_token_type {
|
|||||||
JSON_KEYWORD,
|
JSON_KEYWORD,
|
||||||
JSON_STRING,
|
JSON_STRING,
|
||||||
JSON_INTERP,
|
JSON_INTERP,
|
||||||
JSON_SKIP,
|
|
||||||
JSON_END_OF_INPUT,
|
JSON_END_OF_INPUT,
|
||||||
JSON_MAX = JSON_END_OF_INPUT
|
JSON_MAX = JSON_END_OF_INPUT
|
||||||
} JSONTokenType;
|
} JSONTokenType;
|
||||||
|
Loading…
Reference in New Issue
Block a user