json: Treat unwanted interpolation as lexical error

[mirror_qemu.git] / qobject / json-lexer.c

diff --git a/qobject/json-lexer.c b/qobject/json-lexer.c
index 073177947049f0d2e7f7d3d062a21b00ac1ebf09..96fe13621d30dfd3cd56af58469b11dbeea42014 100644 (file)
--- a/qobject/json-lexer.c
+++ b/qobject/json-lexer.c
@@ -14,6 +14,7 @@
 #include "qemu/osdep.h"
 #include "qemu-common.h"
 #include "qapi/qmp/json-lexer.h"
+#include "qapi/qmp/json-streamer.h"
 
 #define MAX_TOKEN_SIZE (64ULL << 20)
 
@@ -91,7 +92,7 @@
  *   Like double-quoted strings, except they're delimited by %x27
  *   (apostrophe) instead of %x22 (quotation mark), and can't contain
  *   unescaped apostrophe, but can contain unescaped quotation mark.
- * - Interpolation:
+ * - Interpolation, if enabled:
  *   interpolation = %((l|ll|I64)[du]|[ipsf])
  *
  * Note:
@@ -114,17 +115,19 @@ enum json_lexer_state {
     IN_NONZERO_NUMBER,
     IN_NEG_NONZERO_NUMBER,
     IN_KEYWORD,
-    IN_ESCAPE,
-    IN_ESCAPE_L,
-    IN_ESCAPE_LL,
-    IN_ESCAPE_I,
-    IN_ESCAPE_I6,
-    IN_ESCAPE_I64,
+    IN_INTERP,
+    IN_INTERP_L,
+    IN_INTERP_LL,
+    IN_INTERP_I,
+    IN_INTERP_I6,
+    IN_INTERP_I64,
     IN_WHITESPACE,
     IN_START,
+    IN_START_INTERP,            /* must be IN_START + 1 */
 };
 
-QEMU_BUILD_BUG_ON((int)JSON_MIN <= (int)IN_START);
+QEMU_BUILD_BUG_ON((int)JSON_MIN <= (int)IN_START_INTERP);
+QEMU_BUILD_BUG_ON(IN_START_INTERP != IN_START + 1);
 
 #define TERMINAL(state) [0 ... 0x7F] = (state)
 
@@ -220,44 +223,48 @@ static const uint8_t json_lexer[][256] =  {
         ['\n'] = IN_WHITESPACE,
     },
 
-    /* escape */
-    [IN_ESCAPE_LL] = {
-        ['d'] = JSON_ESCAPE,
-        ['u'] = JSON_ESCAPE,
+    /* interpolation */
+    [IN_INTERP_LL] = {
+        ['d'] = JSON_INTERP,
+        ['u'] = JSON_INTERP,
     },
 
-    [IN_ESCAPE_L] = {
-        ['d'] = JSON_ESCAPE,
-        ['l'] = IN_ESCAPE_LL,
-        ['u'] = JSON_ESCAPE,
+    [IN_INTERP_L] = {
+        ['d'] = JSON_INTERP,
+        ['l'] = IN_INTERP_LL,
+        ['u'] = JSON_INTERP,
     },
 
-    [IN_ESCAPE_I64] = {
-        ['d'] = JSON_ESCAPE,
-        ['u'] = JSON_ESCAPE,
+    [IN_INTERP_I64] = {
+        ['d'] = JSON_INTERP,
+        ['u'] = JSON_INTERP,
     },
 
-    [IN_ESCAPE_I6] = {
-        ['4'] = IN_ESCAPE_I64,
+    [IN_INTERP_I6] = {
+        ['4'] = IN_INTERP_I64,
     },
 
-    [IN_ESCAPE_I] = {
-        ['6'] = IN_ESCAPE_I6,
+    [IN_INTERP_I] = {
+        ['6'] = IN_INTERP_I6,
     },
 
-    [IN_ESCAPE] = {
-        ['d'] = JSON_ESCAPE,
-        ['i'] = JSON_ESCAPE,
-        ['p'] = JSON_ESCAPE,
-        ['s'] = JSON_ESCAPE,
-        ['u'] = JSON_ESCAPE,
-        ['f'] = JSON_ESCAPE,
-        ['l'] = IN_ESCAPE_L,
-        ['I'] = IN_ESCAPE_I,
+    [IN_INTERP] = {
+        ['d'] = JSON_INTERP,
+        ['i'] = JSON_INTERP,
+        ['p'] = JSON_INTERP,
+        ['s'] = JSON_INTERP,
+        ['u'] = JSON_INTERP,
+        ['f'] = JSON_INTERP,
+        ['l'] = IN_INTERP_L,
+        ['I'] = IN_INTERP_I,
     },
 
-    /* top level rule */
-    [IN_START] = {
+    /*
+     * Two start states:
+     * - IN_START recognizes JSON tokens with our string extensions
+     * - IN_START_INTERP additionally recognizes interpolation.
+     */
+    [IN_START ... IN_START_INTERP] = {
         ['"'] = IN_DQ_STRING,
         ['\''] = IN_SQ_STRING,
         ['0'] = IN_ZERO,
@@ -270,23 +277,23 @@ static const uint8_t json_lexer[][256] =  {
         [','] = JSON_COMMA,
         [':'] = JSON_COLON,
         ['a' ... 'z'] = IN_KEYWORD,
-        ['%'] = IN_ESCAPE,
         [' '] = IN_WHITESPACE,
         ['\t'] = IN_WHITESPACE,
         ['\r'] = IN_WHITESPACE,
         ['\n'] = IN_WHITESPACE,
     },
+    [IN_START_INTERP]['%'] = IN_INTERP,
 };
 
-void json_lexer_init(JSONLexer *lexer, JSONLexerEmitter func)
+void json_lexer_init(JSONLexer *lexer, bool enable_interpolation)
 {
-    lexer->emit = func;
-    lexer->state = IN_START;
+    lexer->start_state = lexer->state = enable_interpolation
+        ? IN_START_INTERP : IN_START;
     lexer->token = g_string_sized_new(3);
     lexer->x = lexer->y = 0;
 }
 
-static int json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
+static void json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
 {
     int char_consumed, new_state;
 
@@ -311,16 +318,17 @@ static int json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
         case JSON_RSQUARE:
         case JSON_COLON:
         case JSON_COMMA:
-        case JSON_ESCAPE:
+        case JSON_INTERP:
         case JSON_INTEGER:
         case JSON_FLOAT:
         case JSON_KEYWORD:
         case JSON_STRING:
-            lexer->emit(lexer, lexer->token, new_state, lexer->x, lexer->y);
+            json_message_process_token(lexer, lexer->token, new_state,
+                                       lexer->x, lexer->y);
             /* fall through */
         case JSON_SKIP:
             g_string_truncate(lexer->token, 0);
-            new_state = IN_START;
+            new_state = lexer->start_state;
             break;
         case IN_ERROR:
             /* XXX: To avoid having previous bad input leaving the parser in an
@@ -336,11 +344,11 @@ static int json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
              * never a valid ASCII/UTF-8 sequence, so this should reliably
              * induce an error/flush state.
              */
-            lexer->emit(lexer, lexer->token, JSON_ERROR, lexer->x, lexer->y);
+            json_message_process_token(lexer, lexer->token, JSON_ERROR,
+                                       lexer->x, lexer->y);
             g_string_truncate(lexer->token, 0);
-            new_state = IN_START;
-            lexer->state = new_state;
-            return 0;
+            lexer->state = lexer->start_state;
+            return;
         default:
             break;
         }
@@ -351,33 +359,27 @@ static int json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
      * this is a security consideration.
      */
     if (lexer->token->len > MAX_TOKEN_SIZE) {
-        lexer->emit(lexer, lexer->token, lexer->state, lexer->x, lexer->y);
+        json_message_process_token(lexer, lexer->token, lexer->state,
+                                   lexer->x, lexer->y);
         g_string_truncate(lexer->token, 0);
-        lexer->state = IN_START;
+        lexer->state = lexer->start_state;
     }
-
-    return 0;
 }
 
-int json_lexer_feed(JSONLexer *lexer, const char *buffer, size_t size)
+void json_lexer_feed(JSONLexer *lexer, const char *buffer, size_t size)
 {
     size_t i;
 
     for (i = 0; i < size; i++) {
-        int err;
-
-        err = json_lexer_feed_char(lexer, buffer[i], false);
-        if (err < 0) {
-            return err;
-        }
+        json_lexer_feed_char(lexer, buffer[i], false);
     }
-
-    return 0;
 }
 
-int json_lexer_flush(JSONLexer *lexer)
+void json_lexer_flush(JSONLexer *lexer)
 {
-    return lexer->state == IN_START ? 0 : json_lexer_feed_char(lexer, 0, true);
+    if (lexer->state != lexer->start_state) {
+        json_lexer_feed_char(lexer, 0, true);
+    }
 }
 
 void json_lexer_destroy(JSONLexer *lexer)