From 340db1ed82f8ced40a3e778c08963005369e2926 Mon Sep 17 00:00:00 2001 From: Markus Armbruster Date: Thu, 23 Aug 2018 18:39:45 +0200 Subject: json: Reject unescaped control characters Fix the lexer to reject unescaped control characters in JSON strings, in accordance with RFC 8259 "The JavaScript Object Notation (JSON) Data Interchange Format". Bonus: we now recover more nicely from unclosed strings. E.g. {"one: 1}\n{"two": 2} now recovers cleanly after the newline, where before the lexer remained confused until the next unpaired double quote or lexical error. Signed-off-by: Markus Armbruster Reviewed-by: Eric Blake Message-Id: <20180823164025.12553-19-armbru@redhat.com> --- tests/check-qjson.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'tests/check-qjson.c') diff --git a/tests/check-qjson.c b/tests/check-qjson.c index 1688b2f5c1..f1405ad47a 100644 --- a/tests/check-qjson.c +++ b/tests/check-qjson.c @@ -202,11 +202,7 @@ static void utf8_string(void) "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F" "\x10\x11\x12\x13\x14\x15\x16\x17" "\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F", - /* bug: not corrected (valid UTF-8, but invalid JSON) */ - "\x01\x02\x03\x04\x05\x06\x07" - "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F" - "\x10\x11\x12\x13\x14\x15\x16\x17" - "\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F", + NULL, "\\u0001\\u0002\\u0003\\u0004\\u0005\\u0006\\u0007" "\\b\\t\\n\\u000B\\f\\r\\u000E\\u000F" "\\u0010\\u0011\\u0012\\u0013\\u0014\\u0015\\u0016\\u0017" -- cgit 1.4.1