From 852dfa76b85c5d23541377809aa4bcfb4fc037db Mon Sep 17 00:00:00 2001 From: Markus Armbruster Date: Fri, 31 Aug 2018 09:58:37 +0200 Subject: [PATCH] json: Clean up how lexer consumes "end of input" When the lexer isn't in its start state at the end of input, it's working on a token. To flush it out, it needs to transit to its start state on "end of input" lookahead. There are two ways to the start state, depending on the current state: * If the lexer is in a TERMINAL(JSON_FOO) state, it can emit a JSON_FOO token. * Else, it can go to IN_ERROR state, and emit a JSON_ERROR token. There are complications, however: * The transition to IN_ERROR state consumes the input character and adds it to the JSON_ERROR token. The latter is inappropriate for the "end of input" character, so we suppress that. See also recent commit a2ec6be72b8 "json: Fix lexer to include the bad character in JSON_ERROR token". * The transition to a TERMINAL(JSON_FOO) state doesn't consume the input character. In that case, the lexer normally loops until it is consumed. We have to suppress that for the "end of input" input character. If we didn't, the lexer would consume it by entering IN_ERROR state, emitting a bogus JSON_ERROR token. We fixed that in commit bd3924a33a6. However, simply breaking the loop this way assumes that the lexer needs exactly one state transition to reach its start state. That assumption is correct now, but it's unclean, and I'll soon break it. Clean up: instead of breaking the loop after one iteration, break it after it reached the start state. Signed-off-by: Markus Armbruster Reviewed-by: Eric Blake Message-Id: <20180831075841.13363-3-armbru@redhat.com> --- qobject/json-lexer.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/qobject/json-lexer.c b/qobject/json-lexer.c index 4867839f66..ec3aec726f 100644 --- a/qobject/json-lexer.c +++ b/qobject/json-lexer.c @@ -261,7 +261,8 @@ void json_lexer_init(JSONLexer *lexer, bool enable_interpolation) static void json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush) { - int char_consumed, new_state; + int new_state; + bool char_consumed = false; lexer->x++; if (ch == '\n') { @@ -269,11 +270,12 @@ static void json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush) lexer->y++; } - do { + while (flush ? lexer->state != lexer->start_state : !char_consumed) { assert(lexer->state <= ARRAY_SIZE(json_lexer)); new_state = json_lexer[lexer->state][(uint8_t)ch]; - char_consumed = !TERMINAL_NEEDED_LOOKAHEAD(lexer->state, new_state); - if (char_consumed && !flush) { + char_consumed = !flush + && !TERMINAL_NEEDED_LOOKAHEAD(lexer->state, new_state); + if (char_consumed) { g_string_append_c(lexer->token, ch); } @@ -318,7 +320,7 @@ static void json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush) break; } lexer->state = new_state; - } while (!char_consumed && !flush); + } /* Do not let a single token grow to an arbitrarily large size, * this is a security consideration. @@ -342,9 +344,8 @@ void json_lexer_feed(JSONLexer *lexer, const char *buffer, size_t size) void json_lexer_flush(JSONLexer *lexer) { - if (lexer->state != lexer->start_state) { - json_lexer_feed_char(lexer, 0, true); - } + json_lexer_feed_char(lexer, 0, true); + assert(lexer->state == lexer->start_state); json_message_process_token(lexer, lexer->token, JSON_END_OF_INPUT, lexer->x, lexer->y); }