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 2a5561c917adfe1bc534d2eaf01f3866cccb92ad..a7df2093aa3059304450e09f9f81de2a4a1a8d01 100644 (file)
--- a/qobject/json-lexer.c
+++ b/qobject/json-lexer.c
@@ -115,7 +115,6 @@ enum json_lexer_state {
     IN_SIGN,
     IN_KEYWORD,
     IN_INTERP,
-    IN_WHITESPACE,
     IN_START,
     IN_START_INTERP,            /* must be IN_START + 1 */
 };
@@ -228,15 +227,6 @@ static const uint8_t json_lexer[][256] =  {
         ['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 @@ static const uint8_t json_lexer[][256] =  {
         [','] = 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 @@ static void json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
             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:

diff --git a/qobject/json-parser-int.h b/qobject/json-parser-int.h
index 57cb8e79d3152d2856fba39b389629fc2bee4099..16a25d00bb62f31ab4c7f8eabb48f624b12b616b 100644 (file)
--- a/qobject/json-parser-int.h
+++ b/qobject/json-parser-int.h
@@ -31,7 +31,6 @@ typedef enum json_token_type {
     JSON_KEYWORD,
     JSON_STRING,
     JSON_INTERP,
-    JSON_SKIP,
     JSON_END_OF_INPUT,
     JSON_MAX = JSON_END_OF_INPUT
 } JSONTokenType;