json: Reject invalid \uXXXX, fix \u0000

The JSON parser translates invalid \uXXXX to garbage instead of
rejecting it, and swallows \u0000.

Fix by using mod_utf8_encode() instead of flawed wchar_to_utf8().

Valid surrogate pairs are now differently broken: they're rejected
instead of translated to garbage.  The next commit will fix them.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20180823164025.12553-29-armbru@redhat.com>

2 files changed, 17 insertions, 59 deletions

diff --git a/qobject/json-parser.c b/qobject/json-parser.c
index 9cb363f7e1..e49da192fe 100644
--- a/qobject/json-parser.c
+++ b/qobject/json-parser.c
@@ -64,34 +64,6 @@ static void GCC_FMT_ATTR(3, 4) parse_error(JSONParserContext *ctxt,
     error_setg(&ctxt->err, "JSON parse error, %s", message);
 }
 
-/**
- * String helpers
- *
- * These helpers are used to unescape strings.
- */
-static void wchar_to_utf8(uint16_t wchar, char *buffer, size_t buffer_length)
-{
-    if (wchar <= 0x007F) {
-        BUG_ON(buffer_length < 2);
-
-        buffer[0] = wchar & 0x7F;
-        buffer[1] = 0;
-    } else if (wchar <= 0x07FF) {
-        BUG_ON(buffer_length < 3);
-
-        buffer[0] = 0xC0 | ((wchar >> 6) & 0x1F);
-        buffer[1] = 0x80 | (wchar & 0x3F);
-        buffer[2] = 0;
-    } else {
-        BUG_ON(buffer_length < 4);
-
-        buffer[0] = 0xE0 | ((wchar >> 12) & 0x0F);
-        buffer[1] = 0x80 | ((wchar >> 6) & 0x3F);
-        buffer[2] = 0x80 | (wchar & 0x3F);
-        buffer[3] = 0;
-    }
-}
-
 static int hex2decimal(char ch)
 {
     if (ch >= '0' && ch <= '9') {
@@ -197,7 +169,12 @@ static QString *parse_string(JSONParserContext *ctxt, JSONToken *token)
                     ptr++;
                 }
 
-                wchar_to_utf8(cp, utf8_buf, sizeof(utf8_buf));
+                if (mod_utf8_encode(utf8_buf, sizeof(utf8_buf), cp) < 0) {
+                    parse_error(ctxt, token,
+                                "\\u%.4s is not a valid Unicode character",
+                                ptr - 3);
+                    goto out;
+                }
                 qstring_append(str, utf8_buf);
                 break;
             default:
diff --git a/tests/check-qjson.c b/tests/check-qjson.c
index 3abf12b4d2..4abb5847ad 100644
--- a/tests/check-qjson.c
+++ b/tests/check-qjson.c
@@ -64,7 +64,7 @@ static void escaped_string(void)
         { "triple byte utf-8 \\u20AC", "triple byte utf-8 \xe2\x82\xac" },
         { "quadruple byte utf-8 \\uD834\\uDD1E", /* U+1D11E */
           /* bug: want \xF0\x9D\x84\x9E */
-          "quadruple byte utf-8 \xED\xA0\xB4\xED\xB4\x9E", .skip = 1 },
+          NULL },
         { "\\", NULL },
         { "\\z", NULL },
         { "\\ux", NULL },
@@ -72,35 +72,16 @@ static void escaped_string(void)
         { "\\u12x", NULL },
         { "\\u123x", NULL },
         { "\\u12345", "\341\210\2645" },
-        { "\\u0000x", "x", .skip = 1}, /* bug: want \xC0\x80x */
-        { "unpaired leading surrogate \\uD800",
-          /* bug: not rejected */
-          "unpaired leading surrogate \355\240\200", .skip = 1 },
-        { "unpaired leading surrogate \\uD800\\uCAFE",
-          /* bug: not rejected */
-          "unpaired leading surrogate \355\240\200\354\253\276", .skip = 1 },
-        { "unpaired leading surrogate \\uD800\\uD801\\uDC02",
-          /* bug: not rejected */
-          "unpaired leading surrogate \355\240\200\355\240\201\355\260\202",
-          .skip = 1 },
-        { "unpaired trailing surrogate \\uDC00",
-          /* bug: not rejected */
-          "unpaired trailing surrogate \355\260\200", .skip = 1},
-        { "backward surrogate pair \\uDC00\\uD800",
-          /* bug: not rejected */
-          "backward surrogate pair \355\260\200\355\240\200", .skip = 1},
-        { "noncharacter U+FDD0 \\uFDD0",
-          /* bug: not rejected */
-          "noncharacter U+FDD0 \xEF\xB7\x90", .skip = 1},
-        { "noncharacter U+FDEF \\uFDEF",
-          /* bug: not rejected */
-          "noncharacter U+FDEF \xEF\xB7\xAF", .skip = 1},
-        { "noncharacter U+1FFFE \\uD87F\\uDFFE",
-          /* bug: not rejected */
-          "noncharacter U+1FFFE \xED\xA1\xBF\xED\xBF\xBE", .skip = 1},
-        { "noncharacter U+10FFFF \\uDC3F\\uDFFF",
-          /* bug: not rejected */
-          "noncharacter U+10FFFF \xED\xB0\xBF\xED\xBF\xBF", .skip = 1},
+        { "\\u0000x", "\xC0\x80x" },
+        { "unpaired leading surrogate \\uD800", NULL },
+        { "unpaired leading surrogate \\uD800\\uCAFE", NULL },
+        { "unpaired leading surrogate \\uD800\\uD801\\uDC02", NULL },
+        { "unpaired trailing surrogate \\uDC00", NULL },
+        { "backward surrogate pair \\uDC00\\uD800", NULL },
+        { "noncharacter U+FDD0 \\uFDD0", NULL },
+        { "noncharacter U+FDEF \\uFDEF", NULL },
+        { "noncharacter U+1FFFE \\uD87F\\uDFFE", NULL },
+        { "noncharacter U+10FFFF \\uDC3F\\uDFFF", NULL },
         {}
     };
     int i, j;