*/
#include "qemu/osdep.h"
-#include "qemu-common.h"
-#include "qapi/qmp/json-lexer.h"
+#include "json-parser-int.h"
#define MAX_TOKEN_SIZE (64ULL << 20)
* 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:
* 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 = %((l|ll|I64)[du]|[ipsf])
+ * - Interpolation, if enabled:
+ * The lexer accepts %[A-Za-z0-9]*, and leaves rejecting invalid
+ * ones to the parser.
*
* Note:
- * - Input must be encoded in UTF-8.
+ * - Input must be encoded in modified UTF-8.
* - Decoding and validating is left to the parser.
*/
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_RECOVERY = 1,
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,
- IN_DIGITS,
- IN_DIGIT,
+ IN_EXP_DIGITS,
+ IN_EXP_SIGN,
IN_EXP_E,
IN_MANTISSA,
IN_MANTISSA_DIGITS,
- IN_NONZERO_NUMBER,
- IN_NEG_NONZERO_NUMBER,
+ IN_DIGITS,
+ IN_SIGN,
IN_KEYWORD,
- IN_ESCAPE,
- IN_ESCAPE_L,
- IN_ESCAPE_LL,
- IN_ESCAPE_I,
- IN_ESCAPE_I6,
- IN_ESCAPE_I64,
- IN_WHITESPACE,
+ IN_INTERP,
IN_START,
+ IN_START_INTERP, /* must be IN_START + 1 */
};
-QEMU_BUILD_BUG_ON((int)JSON_MIN <= (int)IN_START);
-
-#define TERMINAL(state) [0 ... 0x7F] = (state)
+QEMU_BUILD_BUG_ON(JSON_ERROR != 0);
+QEMU_BUILD_BUG_ON(IN_RECOVERY != JSON_ERROR + 1);
+QEMU_BUILD_BUG_ON((int)JSON_MIN <= (int)IN_START_INTERP);
+QEMU_BUILD_BUG_ON(JSON_MAX >= 0x80);
+QEMU_BUILD_BUG_ON(IN_START_INTERP != IN_START + 1);
-/* Return whether TERMINAL is a terminal state and the transition to it
- from OLD_STATE required lookahead. This happens whenever the table
- below uses the TERMINAL macro. */
-#define TERMINAL_NEEDED_LOOKAHEAD(old_state, terminal) \
- (terminal != IN_ERROR && json_lexer[(old_state)][0] == (terminal))
+#define LOOKAHEAD 0x80
+#define TERMINAL(state) [0 ... 0xFF] = ((state) | LOOKAHEAD)
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,
+ /* error recovery */
+ [IN_RECOVERY] = {
+ /*
+ * Skip characters until a structural character, an ASCII
+ * control character other than '\t', or impossible UTF-8
+ * bytes '\xFE', '\xFF'. Structural characters and line
+ * endings are promising resynchronization points. Clients
+ * may use the others to force the JSON parser into known-good
+ * state; see docs/interop/qmp-spec.rst.
+ */
+ [0 ... 0x1F] = IN_START | LOOKAHEAD,
+ [0x20 ... 0xFD] = IN_RECOVERY,
+ [0xFE ... 0xFF] = IN_START | LOOKAHEAD,
+ ['\t'] = IN_RECOVERY,
+ ['['] = IN_START | LOOKAHEAD,
+ [']'] = IN_START | LOOKAHEAD,
+ ['{'] = IN_START | LOOKAHEAD,
+ ['}'] = IN_START | LOOKAHEAD,
+ [':'] = IN_START | LOOKAHEAD,
+ [','] = IN_START | LOOKAHEAD,
},
+
+ /* double quote string */
[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 ... 0xBF] = IN_DQ_STRING,
- [0xC2 ... 0xF4] = IN_DQ_STRING,
+ [0x20 ... 0xFD] = IN_DQ_STRING,
['\\'] = IN_DQ_STRING_ESCAPE,
['"'] = JSON_STRING,
},
/* 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 ... 0xBF] = IN_SQ_STRING,
- [0xC2 ... 0xF4] = IN_SQ_STRING,
+ [0x20 ... 0xFD] = IN_SQ_STRING,
['\\'] = IN_SQ_STRING_ESCAPE,
['\''] = JSON_STRING,
},
/* Zero */
[IN_ZERO] = {
TERMINAL(JSON_INTEGER),
- ['0' ... '9'] = IN_ERROR,
+ ['0' ... '9'] = JSON_ERROR,
['.'] = IN_MANTISSA,
},
/* Float */
- [IN_DIGITS] = {
+ [IN_EXP_DIGITS] = {
TERMINAL(JSON_FLOAT),
- ['0' ... '9'] = IN_DIGITS,
+ ['0' ... '9'] = IN_EXP_DIGITS,
},
- [IN_DIGIT] = {
- ['0' ... '9'] = IN_DIGITS,
+ [IN_EXP_SIGN] = {
+ ['0' ... '9'] = IN_EXP_DIGITS,
},
[IN_EXP_E] = {
- ['-'] = IN_DIGIT,
- ['+'] = IN_DIGIT,
- ['0' ... '9'] = IN_DIGITS,
+ ['-'] = IN_EXP_SIGN,
+ ['+'] = IN_EXP_SIGN,
+ ['0' ... '9'] = IN_EXP_DIGITS,
},
[IN_MANTISSA_DIGITS] = {
},
/* Number */
- [IN_NONZERO_NUMBER] = {
+ [IN_DIGITS] = {
TERMINAL(JSON_INTEGER),
- ['0' ... '9'] = IN_NONZERO_NUMBER,
+ ['0' ... '9'] = IN_DIGITS,
['e'] = IN_EXP_E,
['E'] = IN_EXP_E,
['.'] = IN_MANTISSA,
},
- [IN_NEG_NONZERO_NUMBER] = {
+ [IN_SIGN] = {
['0'] = IN_ZERO,
- ['1' ... '9'] = IN_NONZERO_NUMBER,
+ ['1' ... '9'] = IN_DIGITS,
},
/* keywords */
['a' ... 'z'] = IN_KEYWORD,
},
- /* whitespace */
- [IN_WHITESPACE] = {
- TERMINAL(JSON_SKIP),
- [' '] = IN_WHITESPACE,
- ['\t'] = IN_WHITESPACE,
- ['\r'] = IN_WHITESPACE,
- ['\n'] = IN_WHITESPACE,
- },
-
- /* escape */
- [IN_ESCAPE_LL] = {
- ['d'] = JSON_ESCAPE,
- ['u'] = JSON_ESCAPE,
+ /* interpolation */
+ [IN_INTERP] = {
+ TERMINAL(JSON_INTERP),
+ ['A' ... 'Z'] = IN_INTERP,
+ ['a' ... 'z'] = IN_INTERP,
+ ['0' ... '9'] = IN_INTERP,
},
- [IN_ESCAPE_L] = {
- ['d'] = JSON_ESCAPE,
- ['l'] = IN_ESCAPE_LL,
- ['u'] = JSON_ESCAPE,
- },
-
- [IN_ESCAPE_I64] = {
- ['d'] = JSON_ESCAPE,
- ['u'] = JSON_ESCAPE,
- },
-
- [IN_ESCAPE_I6] = {
- ['4'] = IN_ESCAPE_I64,
- },
-
- [IN_ESCAPE_I] = {
- ['6'] = IN_ESCAPE_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,
- },
-
- /* 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,
- ['1' ... '9'] = IN_NONZERO_NUMBER,
- ['-'] = IN_NEG_NONZERO_NUMBER,
+ ['1' ... '9'] = IN_DIGITS,
+ ['-'] = IN_SIGN,
['{'] = JSON_LCURLY,
['}'] = JSON_RCURLY,
['['] = JSON_LSQUARE,
[','] = JSON_COMMA,
[':'] = JSON_COLON,
['a' ... 'z'] = IN_KEYWORD,
- ['%'] = IN_ESCAPE,
- [' '] = IN_WHITESPACE,
- ['\t'] = IN_WHITESPACE,
- ['\r'] = IN_WHITESPACE,
- ['\n'] = IN_WHITESPACE,
+ [' '] = IN_START,
+ ['\t'] = IN_START,
+ ['\r'] = IN_START,
+ ['\n'] = IN_START,
},
+ [IN_START_INTERP]['%'] = IN_INTERP,
};
-void json_lexer_init(JSONLexer *lexer, JSONLexerEmitter func)
+static inline uint8_t next_state(JSONLexer *lexer, char ch, bool flush,
+ bool *char_consumed)
{
- lexer->emit = func;
- lexer->state = IN_START;
+ uint8_t next;
+
+ assert(lexer->state < ARRAY_SIZE(json_lexer));
+ next = json_lexer[lexer->state][(uint8_t)ch];
+ *char_consumed = !flush && !(next & LOOKAHEAD);
+ return next & ~LOOKAHEAD;
+}
+
+void json_lexer_init(JSONLexer *lexer, bool enable_interpolation)
+{
+ 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;
+ int new_state;
+ bool char_consumed = false;
lexer->x++;
if (ch == '\n') {
lexer->y++;
}
- do {
- assert(lexer->state <= ARRAY_SIZE(json_lexer));
- new_state = json_lexer[lexer->state][(uint8_t)ch];
- char_consumed = !TERMINAL_NEEDED_LOOKAHEAD(lexer->state, new_state);
- if (char_consumed && !flush) {
+ while (flush ? lexer->state != lexer->start_state : !char_consumed) {
+ new_state = next_state(lexer, ch, flush, &char_consumed);
+ if (char_consumed) {
+ assert(!flush);
g_string_append_c(lexer->token, ch);
}
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:
+ case IN_START:
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
- * unresponsive state where we consume unpredictable amounts of
- * subsequent "good" input, percolate this error state up to the
- * tokenizer/parser by forcing a NULL object to be emitted, then
- * reset state.
- *
- * Also note that this handling is required for reliable channel
- * negotiation between QMP and the guest agent, since chr(0xFF)
- * is placed at the beginning of certain events to ensure proper
- * delivery when the channel is in an unknown state. chr(0xFF) is
- * 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);
+ case JSON_ERROR:
+ json_message_process_token(lexer, lexer->token, JSON_ERROR,
+ lexer->x, lexer->y);
+ new_state = IN_RECOVERY;
+ /* fall through */
+ case IN_RECOVERY:
g_string_truncate(lexer->token, 0);
- new_state = IN_START;
- lexer->state = new_state;
- return 0;
+ break;
default:
break;
}
lexer->state = new_state;
- } while (!char_consumed && !flush);
+ }
/* Do not let a single token grow to an arbitrarily large size,
* 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);
+ json_lexer_feed_char(lexer, 0, true);
+ assert(lexer->state == lexer->start_state);
+ json_message_process_token(lexer, lexer->token, JSON_END_OF_INPUT,
+ lexer->x, lexer->y);
}
void json_lexer_destroy(JSONLexer *lexer)
projects / mirror_qemu.git / blobdiff