10  * See the COPYING.LIB file in the top-level directory.
15 #include "json-parser-int.h"
28  *    begin-array     = ws %x5B ws  ; [ left square bracket
29  *    begin-object    = ws %x7B ws  ; { left curly bracket
30  *    end-array       = ws %x5D ws  ; ] right square bracket
31  *    end-object      = ws %x7D ws  ; } right curly bracket
32  *    name-separator  = ws %x3A ws  ; : colon
33  *    value-separator = ws %x2C ws  ; , comma
49  *  [This lexer accepts [a-z]+, and leaves rejecting unknown literal
55  *    decimal-point = %x2E       ; .
56  *    digit1-9 = %x31-39         ; 1-9
59  *    frac = decimal-point 1*DIGIT
60  *    int = zero / ( digit1-9 *DIGIT )
61  *    minus = %x2D               ; -
63  *    zero = %x30                ; 0
66  *    string = quotation-mark *char quotation-mark
80  *    quotation-mark = %x22      ; "
81  *    unescaped = %x20-21 / %x23-5B / %x5D-10FFFF
82  *    [This lexer accepts any non-control character after escape, and
87  * - Extra escape sequence in strings:
88  *   0x27 (apostrophe) is recognized after escape, too
89  * - Single-quoted strings:
90  *   Like double-quoted strings, except they're delimited by %x27
93  * - Interpolation, if enabled:
94  *   The lexer accepts %[A-Za-z0-9]*, and leaves rejecting invalid
98  * - Input must be encoded in modified UTF-8.
99  * - Decoding and validating is left to the parser.
122 QEMU_BUILD_BUG_ON(JSON_ERROR != 0);
125 QEMU_BUILD_BUG_ON(JSON_MAX >= 0x80);
128 #define LOOKAHEAD 0x80
129 #define TERMINAL(state) [0 ... 0xFF] = ((state) | LOOKAHEAD)
138          * control character other than '\t', or impossible UTF-8
141          * may use the others to force the JSON parser into known-good
142          * state; see docs/interop/qmp-spec.rst.
144         [0 ... 0x1F] = IN_START | LOOKAHEAD,
145         [0x20 ... 0xFD] = IN_RECOVERY,
146         [0xFE ... 0xFF] = IN_START | LOOKAHEAD,
158         [0x20 ... 0xFD] = IN_DQ_STRING,
161         [0x20 ... 0xFD] = IN_DQ_STRING,
168         [0x20 ... 0xFD] = IN_SQ_STRING,
171         [0x20 ... 0xFD] = IN_SQ_STRING,
179         ['0' ... '9'] = JSON_ERROR,
186         ['0' ... '9'] = IN_EXP_DIGITS,
190         ['0' ... '9'] = IN_EXP_DIGITS,
194         ['-'] = IN_EXP_SIGN,
196         ['0' ... '9'] = IN_EXP_DIGITS,
201         ['0' ... '9'] = IN_MANTISSA_DIGITS,
207         ['0' ... '9'] = IN_MANTISSA_DIGITS,
213         ['0' ... '9'] = IN_DIGITS,
220         ['0'] = IN_ZERO,
221         ['1' ... '9'] = IN_DIGITS,
235         ['0' ... '9'] = IN_INTERP,
240      * - IN_START recognizes JSON tokens with our string extensions
241      * - IN_START_INTERP additionally recognizes interpolation.
246         ['0'] = IN_ZERO,
247         ['1' ... '9'] = IN_DIGITS,
248         ['-'] = IN_SIGN,
269     assert(lexer->state < ARRAY_SIZE(json_lexer));  in next_state()
270     next = json_lexer[lexer->state][(uint8_t)ch];  in next_state()
277     lexer->start_state = lexer->state = enable_interpolation  in json_lexer_init()
279     lexer->token = g_string_sized_new(3);  in json_lexer_init()
280     lexer->x = lexer->y = 0;  in json_lexer_init()
288     lexer->x++;  in json_lexer_feed_char()
290         lexer->x = 0;  in json_lexer_feed_char()
291         lexer->y++;  in json_lexer_feed_char()
294     while (flush ? lexer->state != lexer->start_state : !char_consumed) {  in json_lexer_feed_char()
298             g_string_append_c(lexer->token, ch);  in json_lexer_feed_char()
313             json_message_process_token(lexer, lexer->token, new_state,  in json_lexer_feed_char()
314                                        lexer->x, lexer->y);  in json_lexer_feed_char()
317             g_string_truncate(lexer->token, 0);  in json_lexer_feed_char()
318             new_state = lexer->start_state;  in json_lexer_feed_char()
321             json_message_process_token(lexer, lexer->token, JSON_ERROR,  in json_lexer_feed_char()
322                                        lexer->x, lexer->y);  in json_lexer_feed_char()
326             g_string_truncate(lexer->token, 0);  in json_lexer_feed_char()
331         lexer->state = new_state;  in json_lexer_feed_char()
337     if (lexer->token->len > MAX_TOKEN_SIZE) {  in json_lexer_feed_char()
338         json_message_process_token(lexer, lexer->token, lexer->state,  in json_lexer_feed_char()
339                                    lexer->x, lexer->y);  in json_lexer_feed_char()
340         g_string_truncate(lexer->token, 0);  in json_lexer_feed_char()
341         lexer->state = lexer->start_state;  in json_lexer_feed_char()
349     for (i = 0; i < size; i++) {  in json_lexer_feed()
356     json_lexer_feed_char(lexer, 0, true);  in json_lexer_flush()
357     assert(lexer->state == lexer->start_state);  in json_lexer_flush()
358     json_message_process_token(lexer, lexer->token, JSON_END_OF_INPUT,  in json_lexer_flush()
359                                lexer->x, lexer->y);  in json_lexer_flush()
364     g_string_free(lexer->token, true);  in json_lexer_destroy()