json-parser.c 14.6 KB
Newer Older
A
Anthony Liguori 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 * JSON Parser 
 *
 * 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.
 *
 */

14
#include <stdarg.h>
A
Anthony Liguori 已提交
15 16 17 18 19 20 21 22 23 24

#include "qemu-common.h"
#include "qstring.h"
#include "qint.h"
#include "qdict.h"
#include "qlist.h"
#include "qfloat.h"
#include "qbool.h"
#include "json-parser.h"
#include "json-lexer.h"
25
#include "qerror.h"
A
Anthony Liguori 已提交
26 27 28

typedef struct JSONParserContext
{
29
    Error *err;
A
Anthony Liguori 已提交
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
} JSONParserContext;

#define BUG_ON(cond) assert(!(cond))

/**
 * TODO
 *
 * 0) make errors meaningful again
 * 1) add geometry information to tokens
 * 3) should we return a parsed size?
 * 4) deal with premature EOI
 */

static QObject *parse_value(JSONParserContext *ctxt, QList **tokens, va_list *ap);

/**
 * Token manipulators
 *
 * tokens are dictionaries that contain a type, a string value, and geometry information
 * about a token identified by the lexer.  These are routines that make working with
 * these objects a bit easier.
 */
static const char *token_get_value(QObject *obj)
{
    return qdict_get_str(qobject_to_qdict(obj), "token");
}

static JSONTokenType token_get_type(QObject *obj)
{
    return qdict_get_int(qobject_to_qdict(obj), "type");
}

static int token_is_operator(QObject *obj, char op)
{
    const char *val;

    if (token_get_type(obj) != JSON_OPERATOR) {
        return 0;
    }

    val = token_get_value(obj);

    return (val[0] == op) && (val[1] == 0);
}

static int token_is_keyword(QObject *obj, const char *value)
{
    if (token_get_type(obj) != JSON_KEYWORD) {
        return 0;
    }

    return strcmp(token_get_value(obj), value) == 0;
}

static int token_is_escape(QObject *obj, const char *value)
{
    if (token_get_type(obj) != JSON_ESCAPE) {
        return 0;
    }

    return (strcmp(token_get_value(obj), value) == 0);
}

/**
 * Error handler
 */
S
Stefan Weil 已提交
96 97
static void GCC_FMT_ATTR(3, 4) parse_error(JSONParserContext *ctxt,
                                           QObject *token, const char *msg, ...)
A
Anthony Liguori 已提交
98
{
99
    va_list ap;
100
    char message[1024];
101
    va_start(ap, msg);
102
    vsnprintf(message, sizeof(message), msg, ap);
103
    va_end(ap);
104 105 106 107 108
    if (ctxt->err) {
        error_free(ctxt->err);
        ctxt->err = NULL;
    }
    error_set(&ctxt->err, QERR_JSON_PARSE_ERROR, message);
A
Anthony Liguori 已提交
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
}

/**
 * String helpers
 *
 * These helpers are used to unescape strings.
 */
static void wchar_to_utf8(uint16_t wchar, char *buffer, size_t buffer_length)
{
    if (wchar <= 0x007F) {
        BUG_ON(buffer_length < 2);

        buffer[0] = wchar & 0x7F;
        buffer[1] = 0;
    } else if (wchar <= 0x07FF) {
        BUG_ON(buffer_length < 3);

        buffer[0] = 0xC0 | ((wchar >> 6) & 0x1F);
        buffer[1] = 0x80 | (wchar & 0x3F);
        buffer[2] = 0;
    } else {
        BUG_ON(buffer_length < 4);

        buffer[0] = 0xE0 | ((wchar >> 12) & 0x0F);
        buffer[1] = 0x80 | ((wchar >> 6) & 0x3F);
        buffer[2] = 0x80 | (wchar & 0x3F);
        buffer[3] = 0;
    }
}

static int hex2decimal(char ch)
{
    if (ch >= '0' && ch <= '9') {
        return (ch - '0');
    } else if (ch >= 'a' && ch <= 'f') {
        return 10 + (ch - 'a');
    } else if (ch >= 'A' && ch <= 'F') {
        return 10 + (ch - 'A');
    }

    return -1;
}

/**
 * parse_string(): Parse a json string and return a QObject
 *
 *  string
 *      ""
 *      " chars "
 *  chars
 *      char
 *      char chars
 *  char
 *      any-Unicode-character-
 *          except-"-or-\-or-
 *          control-character
 *      \"
 *      \\
 *      \/
 *      \b
 *      \f
 *      \n
 *      \r
 *      \t
 *      \u four-hex-digits 
 */
static QString *qstring_from_escaped_str(JSONParserContext *ctxt, QObject *token)
{
    const char *ptr = token_get_value(token);
    QString *str;
    int double_quote = 1;

    if (*ptr == '"') {
        double_quote = 1;
    } else {
        double_quote = 0;
    }
    ptr++;

    str = qstring_new();
    while (*ptr && 
           ((double_quote && *ptr != '"') || (!double_quote && *ptr != '\''))) {
        if (*ptr == '\\') {
            ptr++;

            switch (*ptr) {
            case '"':
                qstring_append(str, "\"");
                ptr++;
                break;
            case '\'':
                qstring_append(str, "'");
                ptr++;
                break;
            case '\\':
                qstring_append(str, "\\");
                ptr++;
                break;
            case '/':
                qstring_append(str, "/");
                ptr++;
                break;
            case 'b':
                qstring_append(str, "\b");
                ptr++;
                break;
L
Luiz Capitulino 已提交
215 216 217 218
            case 'f':
                qstring_append(str, "\f");
                ptr++;
                break;
A
Anthony Liguori 已提交
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
            case 'n':
                qstring_append(str, "\n");
                ptr++;
                break;
            case 'r':
                qstring_append(str, "\r");
                ptr++;
                break;
            case 't':
                qstring_append(str, "\t");
                ptr++;
                break;
            case 'u': {
                uint16_t unicode_char = 0;
                char utf8_char[4];
                int i = 0;

                ptr++;

                for (i = 0; i < 4; i++) {
                    if (qemu_isxdigit(*ptr)) {
                        unicode_char |= hex2decimal(*ptr) << ((3 - i) * 4);
                    } else {
                        parse_error(ctxt, token,
                                    "invalid hex escape sequence in string");
                        goto out;
                    }
                    ptr++;
                }

                wchar_to_utf8(unicode_char, utf8_char, sizeof(utf8_char));
                qstring_append(str, utf8_char);
            }   break;
            default:
                parse_error(ctxt, token, "invalid escape sequence in string");
                goto out;
            }
        } else {
            char dummy[2];

            dummy[0] = *ptr++;
            dummy[1] = 0;

            qstring_append(str, dummy);
        }
    }

    return str;

out:
    QDECREF(str);
    return NULL;
}

/**
 * Parsing rules
 */
static int parse_pair(JSONParserContext *ctxt, QDict *dict, QList **tokens, va_list *ap)
{
278
    QObject *key = NULL, *token = NULL, *value, *peek;
A
Anthony Liguori 已提交
279 280 281
    QList *working = qlist_copy(*tokens);

    peek = qlist_peek(working);
282 283 284 285 286
    if (peek == NULL) {
        parse_error(ctxt, NULL, "premature EOI");
        goto out;
    }

A
Anthony Liguori 已提交
287
    key = parse_value(ctxt, &working, ap);
288
    if (!key || qobject_type(key) != QTYPE_QSTRING) {
A
Anthony Liguori 已提交
289 290 291 292 293
        parse_error(ctxt, peek, "key is not a string in object");
        goto out;
    }

    token = qlist_pop(working);
294 295 296 297 298
    if (token == NULL) {
        parse_error(ctxt, NULL, "premature EOI");
        goto out;
    }

A
Anthony Liguori 已提交
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
    if (!token_is_operator(token, ':')) {
        parse_error(ctxt, token, "missing : in object pair");
        goto out;
    }

    value = parse_value(ctxt, &working, ap);
    if (value == NULL) {
        parse_error(ctxt, token, "Missing value in dict");
        goto out;
    }

    qdict_put_obj(dict, qstring_get_str(qobject_to_qstring(key)), value);

    qobject_decref(token);
    qobject_decref(key);
    QDECREF(*tokens);
    *tokens = working;

    return 0;

out:
    qobject_decref(token);
    qobject_decref(key);
    QDECREF(working);

    return -1;
}

static QObject *parse_object(JSONParserContext *ctxt, QList **tokens, va_list *ap)
{
    QDict *dict = NULL;
    QObject *token, *peek;
    QList *working = qlist_copy(*tokens);

    token = qlist_pop(working);
334 335 336 337
    if (token == NULL) {
        goto out;
    }

A
Anthony Liguori 已提交
338 339 340 341 342 343 344 345 346
    if (!token_is_operator(token, '{')) {
        goto out;
    }
    qobject_decref(token);
    token = NULL;

    dict = qdict_new();

    peek = qlist_peek(working);
347 348 349 350 351
    if (peek == NULL) {
        parse_error(ctxt, NULL, "premature EOI");
        goto out;
    }

A
Anthony Liguori 已提交
352 353 354 355 356 357
    if (!token_is_operator(peek, '}')) {
        if (parse_pair(ctxt, dict, &working, ap) == -1) {
            goto out;
        }

        token = qlist_pop(working);
358 359 360 361 362
        if (token == NULL) {
            parse_error(ctxt, NULL, "premature EOI");
            goto out;
        }

A
Anthony Liguori 已提交
363 364 365 366 367 368 369 370 371 372 373 374 375
        while (!token_is_operator(token, '}')) {
            if (!token_is_operator(token, ',')) {
                parse_error(ctxt, token, "expected separator in dict");
                goto out;
            }
            qobject_decref(token);
            token = NULL;

            if (parse_pair(ctxt, dict, &working, ap) == -1) {
                goto out;
            }

            token = qlist_pop(working);
376 377 378 379
            if (token == NULL) {
                parse_error(ctxt, NULL, "premature EOI");
                goto out;
            }
A
Anthony Liguori 已提交
380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407
        }
        qobject_decref(token);
        token = NULL;
    } else {
        token = qlist_pop(working);
        qobject_decref(token);
        token = NULL;
    }

    QDECREF(*tokens);
    *tokens = working;

    return QOBJECT(dict);

out:
    qobject_decref(token);
    QDECREF(working);
    QDECREF(dict);
    return NULL;
}

static QObject *parse_array(JSONParserContext *ctxt, QList **tokens, va_list *ap)
{
    QList *list = NULL;
    QObject *token, *peek;
    QList *working = qlist_copy(*tokens);

    token = qlist_pop(working);
408 409 410 411
    if (token == NULL) {
        goto out;
    }

A
Anthony Liguori 已提交
412 413 414 415 416 417 418 419 420
    if (!token_is_operator(token, '[')) {
        goto out;
    }
    qobject_decref(token);
    token = NULL;

    list = qlist_new();

    peek = qlist_peek(working);
421 422 423 424 425
    if (peek == NULL) {
        parse_error(ctxt, NULL, "premature EOI");
        goto out;
    }

A
Anthony Liguori 已提交
426 427 428 429 430 431 432 433 434 435 436 437
    if (!token_is_operator(peek, ']')) {
        QObject *obj;

        obj = parse_value(ctxt, &working, ap);
        if (obj == NULL) {
            parse_error(ctxt, token, "expecting value");
            goto out;
        }

        qlist_append_obj(list, obj);

        token = qlist_pop(working);
438 439 440 441 442
        if (token == NULL) {
            parse_error(ctxt, NULL, "premature EOI");
            goto out;
        }

A
Anthony Liguori 已提交
443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
        while (!token_is_operator(token, ']')) {
            if (!token_is_operator(token, ',')) {
                parse_error(ctxt, token, "expected separator in list");
                goto out;
            }

            qobject_decref(token);
            token = NULL;

            obj = parse_value(ctxt, &working, ap);
            if (obj == NULL) {
                parse_error(ctxt, token, "expecting value");
                goto out;
            }

            qlist_append_obj(list, obj);

            token = qlist_pop(working);
461 462 463 464
            if (token == NULL) {
                parse_error(ctxt, NULL, "premature EOI");
                goto out;
            }
A
Anthony Liguori 已提交
465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492
        }

        qobject_decref(token);
        token = NULL;
    } else {
        token = qlist_pop(working);
        qobject_decref(token);
        token = NULL;
    }

    QDECREF(*tokens);
    *tokens = working;

    return QOBJECT(list);

out:
    qobject_decref(token);
    QDECREF(working);
    QDECREF(list);
    return NULL;
}

static QObject *parse_keyword(JSONParserContext *ctxt, QList **tokens)
{
    QObject *token, *ret;
    QList *working = qlist_copy(*tokens);

    token = qlist_pop(working);
493 494 495
    if (token == NULL) {
        goto out;
    }
A
Anthony Liguori 已提交
496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532

    if (token_get_type(token) != JSON_KEYWORD) {
        goto out;
    }

    if (token_is_keyword(token, "true")) {
        ret = QOBJECT(qbool_from_int(true));
    } else if (token_is_keyword(token, "false")) {
        ret = QOBJECT(qbool_from_int(false));
    } else {
        parse_error(ctxt, token, "invalid keyword `%s'", token_get_value(token));
        goto out;
    }

    qobject_decref(token);
    QDECREF(*tokens);
    *tokens = working;

    return ret;

out: 
    qobject_decref(token);
    QDECREF(working);

    return NULL;
}

static QObject *parse_escape(JSONParserContext *ctxt, QList **tokens, va_list *ap)
{
    QObject *token = NULL, *obj;
    QList *working = qlist_copy(*tokens);

    if (ap == NULL) {
        goto out;
    }

    token = qlist_pop(working);
533 534 535
    if (token == NULL) {
        goto out;
    }
A
Anthony Liguori 已提交
536 537 538 539 540 541 542 543 544

    if (token_is_escape(token, "%p")) {
        obj = va_arg(*ap, QObject *);
    } else if (token_is_escape(token, "%i")) {
        obj = QOBJECT(qbool_from_int(va_arg(*ap, int)));
    } else if (token_is_escape(token, "%d")) {
        obj = QOBJECT(qint_from_int(va_arg(*ap, int)));
    } else if (token_is_escape(token, "%ld")) {
        obj = QOBJECT(qint_from_int(va_arg(*ap, long)));
R
Roy Tam 已提交
545 546
    } else if (token_is_escape(token, "%lld") ||
               token_is_escape(token, "%I64d")) {
A
Anthony Liguori 已提交
547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574
        obj = QOBJECT(qint_from_int(va_arg(*ap, long long)));
    } else if (token_is_escape(token, "%s")) {
        obj = QOBJECT(qstring_from_str(va_arg(*ap, const char *)));
    } else if (token_is_escape(token, "%f")) {
        obj = QOBJECT(qfloat_from_double(va_arg(*ap, double)));
    } else {
        goto out;
    }

    qobject_decref(token);
    QDECREF(*tokens);
    *tokens = working;

    return obj;

out:
    qobject_decref(token);
    QDECREF(working);

    return NULL;
}

static QObject *parse_literal(JSONParserContext *ctxt, QList **tokens)
{
    QObject *token, *obj;
    QList *working = qlist_copy(*tokens);

    token = qlist_pop(working);
575 576 577 578
    if (token == NULL) {
        goto out;
    }

A
Anthony Liguori 已提交
579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628
    switch (token_get_type(token)) {
    case JSON_STRING:
        obj = QOBJECT(qstring_from_escaped_str(ctxt, token));
        break;
    case JSON_INTEGER:
        obj = QOBJECT(qint_from_int(strtoll(token_get_value(token), NULL, 10)));
        break;
    case JSON_FLOAT:
        /* FIXME dependent on locale */
        obj = QOBJECT(qfloat_from_double(strtod(token_get_value(token), NULL)));
        break;
    default:
        goto out;
    }

    qobject_decref(token);
    QDECREF(*tokens);
    *tokens = working;

    return obj;

out:
    qobject_decref(token);
    QDECREF(working);

    return NULL;
}

static QObject *parse_value(JSONParserContext *ctxt, QList **tokens, va_list *ap)
{
    QObject *obj;

    obj = parse_object(ctxt, tokens, ap);
    if (obj == NULL) {
        obj = parse_array(ctxt, tokens, ap);
    }
    if (obj == NULL) {
        obj = parse_escape(ctxt, tokens, ap);
    }
    if (obj == NULL) {
        obj = parse_keyword(ctxt, tokens);
    } 
    if (obj == NULL) {
        obj = parse_literal(ctxt, tokens);
    }

    return obj;
}

QObject *json_parser_parse(QList *tokens, va_list *ap)
629 630 631 632 633
{
    return json_parser_parse_err(tokens, ap, NULL);
}

QObject *json_parser_parse_err(QList *tokens, va_list *ap, Error **errp)
A
Anthony Liguori 已提交
634 635
{
    JSONParserContext ctxt = {};
636
    QList *working;
A
Anthony Liguori 已提交
637 638
    QObject *result;

639 640 641 642
    if (!tokens) {
        return NULL;
    }
    working = qlist_copy(tokens);
A
Anthony Liguori 已提交
643 644 645 646
    result = parse_value(&ctxt, &working, ap);

    QDECREF(working);

647 648
    error_propagate(errp, ctxt.err);

A
Anthony Liguori 已提交
649 650
    return result;
}