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 <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20180823164025.12553-19-armbru@redhat.com>

diff --git a/qobject/json-lexer.c b/qobject/json-lexer.c
index 7c0875d225653e485d0c2c238896fbf28f75230c..e85e9a78ffe3ef79904da540b6ccd4a77c8bb3d3 100644 (file)
--- a/qobject/json-lexer.c
+++ b/qobject/json-lexer.c
@@ -115,7 +115,7 @@ static const uint8_t json_lexer[][256] =  {
         ['u'] = IN_DQ_UCODE0,
     },
     [IN_DQ_STRING] = {
-        [1 ... 0xBF] = IN_DQ_STRING,
+        [0x20 ... 0xBF] = IN_DQ_STRING,
         [0xC2 ... 0xF4] = IN_DQ_STRING,
         ['\\'] = IN_DQ_STRING_ESCAPE,
         ['"'] = JSON_STRING,
@@ -155,7 +155,7 @@ static const uint8_t json_lexer[][256] =  {
         ['u'] = IN_SQ_UCODE0,
     },
     [IN_SQ_STRING] = {
-        [1 ... 0xBF] = IN_SQ_STRING,
+        [0x20 ... 0xBF] = IN_SQ_STRING,
         [0xC2 ... 0xF4] = IN_SQ_STRING,
         ['\\'] = IN_SQ_STRING_ESCAPE,
         ['\''] = JSON_STRING,

diff --git a/tests/check-qjson.c b/tests/check-qjson.c
index 1688b2f5c1e437446cac4bb1f181bdd298208e29..f1405ad47acd9e0e09aa0f09eb51c66d27de8807 100644 (file)
--- 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"

diff --git a/tests/qmp-test.c b/tests/qmp-test.c
index 5edc97f63fd9fbb989a1fe051bbccbc24490abc4..7b3ba17c4acca820a4360e1168da32be618560f9 100644 (file)
--- a/tests/qmp-test.c
+++ b/tests/qmp-test.c
@@ -86,9 +86,9 @@ static void test_malformed(QTestState *qts)
     g_assert(recovered(qts));
 
     /* lexical error: control character in string */
-    qtest_qmp_send_raw(qts, "{'execute': 'nonexistent', 'id':'\n'}");
+    qtest_qmp_send_raw(qts, "{'execute': 'nonexistent', 'id':'\n");
     resp = qtest_qmp_receive(qts);
-    g_assert_cmpstr(get_error_class(resp), ==, "CommandNotFound"); /* BUG */
+    g_assert_cmpstr(get_error_class(resp), ==, "GenericError");
     qobject_unref(resp);
     g_assert(recovered(qts));