aboutsummaryrefslogtreecommitdiff
path: root/json-lexer.c
blob: c21338f66db75814e504ca86bf29c7b7487c3903 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
/*
 * JSON lexer
 *
 * Copyright IBM, Corp. 2009
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
 * See the COPYING.LIB file in the top-level directory.
 *
 */

#include "qstring.h"
#include "qlist.h"
#include "qdict.h"
#include "qint.h"
#include "qemu-common.h"
#include "json-lexer.h"

#define MAX_TOKEN_SIZE (64ULL << 20)

/*
 * \"([^\\\"]|(\\\"\\'\\\\\\/\\b\\f\\n\\r\\t\\u[0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F]))*\"
 * '([^\\']|(\\\"\\'\\\\\\/\\b\\f\\n\\r\\t\\u[0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F]))*'
 * 0|([1-9][0-9]*(.[0-9]+)?([eE]([-+])?[0-9]+))
 * [{}\[\],:]
 * [a-z]+
 *
 */

enum json_lexer_state {
    IN_ERROR = 0,
    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,
    IN_DIGITS,
    IN_DIGIT,
    IN_EXP_E,
    IN_MANTISSA,
    IN_MANTISSA_DIGITS,
    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_WHITESPACE,
    IN_START,
};

#define TERMINAL(state) [0 ... 0x7F] = (state)

/* 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) \
            (json_lexer[(old_state)][0] == (terminal))

static const uint8_t json_lexer[][256] =  {
    /* 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,
    },
    [IN_DQ_STRING] = {
        [1 ... 0xBF] = IN_DQ_STRING,
        [0xC2 ... 0xF4] = 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_DQ_STRING,
        ['\\'] = IN_DQ_STRING,
        ['\''] = IN_SQ_STRING,
        ['\"'] = IN_SQ_STRING,
        ['u'] = IN_SQ_UCODE0,
    },
    [IN_SQ_STRING] = {
        [1 ... 0xBF] = IN_SQ_STRING,
        [0xC2 ... 0xF4] = IN_SQ_STRING,
        ['\\'] = IN_SQ_STRING_ESCAPE,
        ['\''] = JSON_STRING,
    },

    /* Zero */
    [IN_ZERO] = {
        TERMINAL(JSON_INTEGER),
        ['0' ... '9'] = IN_ERROR,
        ['.'] = IN_MANTISSA,
    },

    /* Float */
    [IN_DIGITS] = {
        TERMINAL(JSON_FLOAT),
        ['0' ... '9'] = IN_DIGITS,
    },

    [IN_DIGIT] = {
        ['0' ... '9'] = IN_DIGITS,
    },

    [IN_EXP_E] = {
        ['-'] = IN_DIGIT,
        ['+'] = IN_DIGIT,
        ['0' ... '9'] = IN_DIGITS,
    },

    [IN_MANTISSA_DIGITS] = {
        TERMINAL(JSON_FLOAT),
        ['0' ... '9'] = IN_MANTISSA_DIGITS,
        ['e'] = IN_EXP_E,
        ['E'] = IN_EXP_E,
    },

    [IN_MANTISSA] = {
        ['0' ... '9'] = IN_MANTISSA_DIGITS,
    },

    /* Number */
    [IN_NONZERO_NUMBER] = {
        TERMINAL(JSON_INTEGER),
        ['0' ... '9'] = IN_NONZERO_NUMBER,
        ['e'] = IN_EXP_E,
        ['E'] = IN_EXP_E,
        ['.'] = IN_MANTISSA,
    },

    [IN_NEG_NONZERO_NUMBER] = {
        ['0'] = IN_ZERO,
        ['1' ... '9'] = IN_NONZERO_NUMBER,
    },

    /* keywords */
    [IN_KEYWORD] = {
        TERMINAL(JSON_KEYWORD),
        ['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,
    },

    [IN_ESCAPE_L] = {
        ['d'] = JSON_ESCAPE,
        ['l'] = IN_ESCAPE_LL,
    },

    [IN_ESCAPE_I64] = {
        ['d'] = 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,
        ['f'] = JSON_ESCAPE,
        ['l'] = IN_ESCAPE_L,
        ['I'] = IN_ESCAPE_I,
    },

    /* top level rule */
    [IN_START] = {
        ['"'] = IN_DQ_STRING,
        ['\''] = IN_SQ_STRING,
        ['0'] = IN_ZERO,
        ['1' ... '9'] = IN_NONZERO_NUMBER,
        ['-'] = IN_NEG_NONZERO_NUMBER,
        ['{'] = JSON_OPERATOR,
        ['}'] = JSON_OPERATOR,
        ['['] = JSON_OPERATOR,
        [']'] = JSON_OPERATOR,
        [','] = JSON_OPERATOR,
        [':'] = JSON_OPERATOR,
        ['a' ... 'z'] = IN_KEYWORD,
        ['%'] = IN_ESCAPE,
        [' '] = IN_WHITESPACE,
        ['\t'] = IN_WHITESPACE,
        ['\r'] = IN_WHITESPACE,
        ['\n'] = IN_WHITESPACE,
    },
};

void json_lexer_init(JSONLexer *lexer, JSONLexerEmitter func)
{
    lexer->emit = func;
    lexer->state = IN_START;
    lexer->token = qstring_new();
    lexer->x = lexer->y = 0;
}

static int json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
{
    int char_consumed, new_state;

    lexer->x++;
    if (ch == '\n') {
        lexer->x = 0;
        lexer->y++;
    }

    do {
        new_state = json_lexer[lexer->state][(uint8_t)ch];
        char_consumed = !TERMINAL_NEEDED_LOOKAHEAD(lexer->state, new_state);
        if (char_consumed) {
            qstring_append_chr(lexer->token, ch);
        }

        switch (new_state) {
        case JSON_OPERATOR:
        case JSON_ESCAPE:
        case JSON_INTEGER:
        case JSON_FLOAT:
        case JSON_KEYWORD:
        case JSON_STRING:
            lexer->emit(lexer, lexer->token, new_state, lexer->x, lexer->y);
        case JSON_SKIP:
            QDECREF(lexer->token);
            lexer->token = qstring_new();
            new_state = IN_START;
            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);
            QDECREF(lexer->token);
            lexer->token = qstring_new();
            new_state = IN_START;
            lexer->state = new_state;
            return 0;
        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->length > MAX_TOKEN_SIZE) {
        lexer->emit(lexer, lexer->token, lexer->state, lexer->x, lexer->y);
        QDECREF(lexer->token);
        lexer->token = qstring_new();
        lexer->state = IN_START;
    }

    return 0;
}

int 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;
        }
    }

    return 0;
}

int json_lexer_flush(JSONLexer *lexer)
{
    return lexer->state == IN_START ? 0 : json_lexer_feed_char(lexer, 0, true);
}

void json_lexer_destroy(JSONLexer *lexer)
{
    QDECREF(lexer->token);
}