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>
diff --git a/qobject/json-lexer.c b/qobject/json-lexer.c
index 2a5561c..a7df209 100644
--- a/qobject/json-lexer.c
+++ b/qobject/json-lexer.c
@@ -115,7 +115,6 @@
IN_SIGN,
IN_KEYWORD,
IN_INTERP,
- IN_WHITESPACE,
IN_START,
IN_START_INTERP, /* must be IN_START + 1 */
};
@@ -228,15 +227,6 @@
['a' ... 'z'] = IN_KEYWORD,
},
- /* whitespace */
- [IN_WHITESPACE] = {
- TERMINAL(JSON_SKIP),
- [' '] = IN_WHITESPACE,
- ['\t'] = IN_WHITESPACE,
- ['\r'] = IN_WHITESPACE,
- ['\n'] = IN_WHITESPACE,
- },
-
/* interpolation */
[IN_INTERP] = {
TERMINAL(JSON_INTERP),
@@ -263,10 +253,10 @@
[','] = JSON_COMMA,
[':'] = JSON_COLON,
['a' ... 'z'] = IN_KEYWORD,
- [' '] = IN_WHITESPACE,
- ['\t'] = IN_WHITESPACE,
- ['\r'] = IN_WHITESPACE,
- ['\n'] = IN_WHITESPACE,
+ [' '] = IN_START,
+ ['\t'] = IN_START,
+ ['\r'] = IN_START,
+ ['\n'] = IN_START,
},
[IN_START_INTERP]['%'] = IN_INTERP,
};
@@ -323,10 +313,8 @@
json_message_process_token(lexer, lexer->token, new_state,
lexer->x, lexer->y);
/* fall through */
- case JSON_SKIP:
- g_string_truncate(lexer->token, 0);
- /* fall through */
case IN_START:
+ g_string_truncate(lexer->token, 0);
new_state = lexer->start_state;
break;
case JSON_ERROR: