[Qemu-devel] [PATCH v3 26/58] json: Leave rejecting invalid escape sequences to parser

[Markus Armbruster]

Both lexer and parser reject invalid escape sequences in strings.  The
parser's check is useless.

The lexer ends the token right after the first non-well-formed byte.
This tends to lead to suboptimal error reporting.  For instance, input

    {"address@hidden": 1}

produces the tokens

    JSON_LCURLY   {
    JSON_ERROR    "abc\@
    JSON_KEYWORD  ijk
    JSON_ERROR   ": 1}\n

The parser then reports three errors

    Invalid JSON syntax
    JSON parse error, invalid keyword 'ijk'
    Invalid JSON syntax

before it recovers at the newline.

Drop the lexer's escape sequence checking, and make it accept the same
characters after backslash it accepts elsewhere in strings.  It now
produces

    JSON_LCURLY   {
    JSON_STRING   "address@hidden"
    JSON_COLON    :
    JSON_INTEGER  1
    JSON_RCURLY

and the parser reports just

    JSON parse error, invalid escape sequence in string

While there, fix parse_string()'s inaccurate function comment.

Signed-off-by: Markus Armbruster <address@hidden>
Reviewed-by: Eric Blake <address@hidden>
---
 qobject/json-lexer.c  | 72 +++----------------------------------------
 qobject/json-parser.c | 56 +++++++++++++++++++--------------
 2 files changed, 37 insertions(+), 91 deletions(-)

diff --git a/qobject/json-lexer.c b/qobject/json-lexer.c
index 4c402f62d3..0731779470 100644
--- a/qobject/json-lexer.c
+++ b/qobject/json-lexer.c
@@ -80,6 +80,8 @@
  *    escape = %x5C              ; \
  *    quotation-mark = %x22      ; "
  *    unescaped = %x20-21 / %x23-5B / %x5D-10FFFF
+ *    [This lexer accepts any non-control character after escape, and
+ *    leaves rejecting invalid ones to the parser.]
  *
  *
  * Extensions over RFC 8259:
@@ -99,16 +101,8 @@
 
 enum json_lexer_state {
     IN_ERROR = 0,               /* must really be 0, see json_lexer[] */
-    IN_DQ_UCODE3,
-    IN_DQ_UCODE2,
-    IN_DQ_UCODE1,
-    IN_DQ_UCODE0,
     IN_DQ_STRING_ESCAPE,
     IN_DQ_STRING,
-    IN_SQ_UCODE3,
-    IN_SQ_UCODE2,
-    IN_SQ_UCODE1,
-    IN_SQ_UCODE0,
     IN_SQ_STRING_ESCAPE,
     IN_SQ_STRING,
     IN_ZERO,
@@ -144,37 +138,8 @@ static const uint8_t json_lexer[][256] =  {
     /* Relies on default initialization to IN_ERROR! */
 
     /* double quote string */
-    [IN_DQ_UCODE3] = {
-        ['0' ... '9'] = IN_DQ_STRING,
-        ['a' ... 'f'] = IN_DQ_STRING,
-        ['A' ... 'F'] = IN_DQ_STRING,
-    },
-    [IN_DQ_UCODE2] = {
-        ['0' ... '9'] = IN_DQ_UCODE3,
-        ['a' ... 'f'] = IN_DQ_UCODE3,
-        ['A' ... 'F'] = IN_DQ_UCODE3,
-    },
-    [IN_DQ_UCODE1] = {
-        ['0' ... '9'] = IN_DQ_UCODE2,
-        ['a' ... 'f'] = IN_DQ_UCODE2,
-        ['A' ... 'F'] = IN_DQ_UCODE2,
-    },
-    [IN_DQ_UCODE0] = {
-        ['0' ... '9'] = IN_DQ_UCODE1,
-        ['a' ... 'f'] = IN_DQ_UCODE1,
-        ['A' ... 'F'] = IN_DQ_UCODE1,
-    },
     [IN_DQ_STRING_ESCAPE] = {
-        ['b'] = IN_DQ_STRING,
-        ['f'] =  IN_DQ_STRING,
-        ['n'] =  IN_DQ_STRING,
-        ['r'] =  IN_DQ_STRING,
-        ['t'] =  IN_DQ_STRING,
-        ['/'] = IN_DQ_STRING,
-        ['\\'] = IN_DQ_STRING,
-        ['\''] = IN_DQ_STRING,
-        ['\"'] = IN_DQ_STRING,
-        ['u'] = IN_DQ_UCODE0,
+        [0x20 ... 0xFD] = IN_DQ_STRING,
     },
     [IN_DQ_STRING] = {
         [0x20 ... 0xFD] = IN_DQ_STRING,
@@ -183,37 +148,8 @@ static const uint8_t json_lexer[][256] =  {
     },
 
     /* single quote string */
-    [IN_SQ_UCODE3] = {
-        ['0' ... '9'] = IN_SQ_STRING,
-        ['a' ... 'f'] = IN_SQ_STRING,
-        ['A' ... 'F'] = IN_SQ_STRING,
-    },
-    [IN_SQ_UCODE2] = {
-        ['0' ... '9'] = IN_SQ_UCODE3,
-        ['a' ... 'f'] = IN_SQ_UCODE3,
-        ['A' ... 'F'] = IN_SQ_UCODE3,
-    },
-    [IN_SQ_UCODE1] = {
-        ['0' ... '9'] = IN_SQ_UCODE2,
-        ['a' ... 'f'] = IN_SQ_UCODE2,
-        ['A' ... 'F'] = IN_SQ_UCODE2,
-    },
-    [IN_SQ_UCODE0] = {
-        ['0' ... '9'] = IN_SQ_UCODE1,
-        ['a' ... 'f'] = IN_SQ_UCODE1,
-        ['A' ... 'F'] = IN_SQ_UCODE1,
-    },
     [IN_SQ_STRING_ESCAPE] = {
-        ['b'] = IN_SQ_STRING,
-        ['f'] =  IN_SQ_STRING,
-        ['n'] =  IN_SQ_STRING,
-        ['r'] =  IN_SQ_STRING,
-        ['t'] =  IN_SQ_STRING,
-        ['/'] = IN_SQ_STRING,
-        ['\\'] = IN_SQ_STRING,
-        ['\''] = IN_SQ_STRING,
-        ['\"'] = IN_SQ_STRING,
-        ['u'] = IN_SQ_UCODE0,
+        [0x20 ... 0xFD] = IN_SQ_STRING,
     },
     [IN_SQ_STRING] = {
         [0x20 ... 0xFD] = IN_SQ_STRING,
diff --git a/qobject/json-parser.c b/qobject/json-parser.c
index a9b227f56c..7437827c24 100644
--- a/qobject/json-parser.c
+++ b/qobject/json-parser.c
@@ -106,30 +106,40 @@ static int hex2decimal(char ch)
 }
 
 /**
- * parse_string(): Parse a json string and return a QObject
+ * parse_string(): Parse a JSON string
  *
- *  string
- *      ""
- *      " chars "
- *  chars
- *      char
- *      char chars
- *  char
- *      any-Unicode-character-
- *          except-"-or-\-or-
- *          control-character
- *      \"
- *      \\
- *      \/
- *      \b
- *      \f
- *      \n
- *      \r
- *      \t
- *      \u four-hex-digits 
+ * From RFC 8259 "The JavaScript Object Notation (JSON) Data
+ * Interchange Format":
+ *
+ *    char = unescaped /
+ *        escape (
+ *            %x22 /          ; "    quotation mark  U+0022
+ *            %x5C /          ; \    reverse solidus U+005C
+ *            %x2F /          ; /    solidus         U+002F
+ *            %x62 /          ; b    backspace       U+0008
+ *            %x66 /          ; f    form feed       U+000C
+ *            %x6E /          ; n    line feed       U+000A
+ *            %x72 /          ; r    carriage return U+000D
+ *            %x74 /          ; t    tab             U+0009
+ *            %x75 4HEXDIG )  ; uXXXX                U+XXXX
+ *    escape = %x5C              ; \
+ *    quotation-mark = %x22      ; "
+ *    unescaped = %x20-21 / %x23-5B / %x5D-10FFFF
+ *
+ * Extensions over RFC 8259:
+ * - Extra escape sequence in strings:
+ *   0x27 (apostrophe) is recognized after escape, too
+ * - Single-quoted strings:
+ *   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.
+ *
+ * Note:
+ * - Encoding is modified UTF-8.
+ * - Invalid Unicode characters are rejected.
+ * - Control characters \x00..\x1F are rejected by the lexer.
  */
-static QString *qstring_from_escaped_str(JSONParserContext *ctxt,
-                                         JSONToken *token)
+static QString *parse_string(JSONParserContext *ctxt, JSONToken *token)
 {
     const char *ptr = token->str;
     QString *str;
@@ -495,7 +505,7 @@ static QObject *parse_literal(JSONParserContext *ctxt)
 
     switch (token->type) {
     case JSON_STRING:
-        return QOBJECT(qstring_from_escaped_str(ctxt, token));
+        return QOBJECT(parse_string(ctxt, token));
     case JSON_INTEGER: {
         /*
          * Represent JSON_INTEGER as QNUM_I64 if possible, else as
-- 
2.17.1