qobject/json-parser.c

   1 /*
   2  * JSON Parser
   3  *
   4  * Copyright IBM, Corp. 2009
   5  *
   6  * Authors:
   7  *  Anthony Liguori   <aliguori@us.ibm.com>
   8  *
   9  * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
  10  * See the COPYING.LIB file in the top-level directory.
  11  *
  12  */
  13
  14 #include "qemu/osdep.h"
  15 #include "qemu/cutils.h"
  16 #include "qapi/error.h"
  17 #include "qemu-common.h"
  18 #include "qapi/qmp/qbool.h"
  19 #include "qapi/qmp/qdict.h"
  20 #include "qapi/qmp/qlist.h"
  21 #include "qapi/qmp/qnull.h"
  22 #include "qapi/qmp/qnum.h"
  23 #include "qapi/qmp/qstring.h"
  24 #include "qapi/qmp/json-parser.h"
  25 #include "qapi/qmp/json-lexer.h"
  26 #include "qapi/qmp/json-streamer.h"
  27
  28 typedef struct JSONParserContext
  29 {
  30     Error *err;
  31     JSONToken *current;
  32     GQueue *buf;
  33 } JSONParserContext;
  34
  35 #define BUG_ON(cond) assert(!(cond))
  36
  37 /**
  38  * TODO
  39  *
  40  * 0) make errors meaningful again
  41  * 1) add geometry information to tokens
  42  * 3) should we return a parsed size?
  43  * 4) deal with premature EOI
  44  */
  45
  46 static QObject *parse_value(JSONParserContext *ctxt, va_list *ap);
  47
  48 /**
  49  * Error handler
  50  */
  51 static void GCC_FMT_ATTR(3, 4) parse_error(JSONParserContext *ctxt,
  52                                            JSONToken *token, const char *msg, ...)
  53 {
  54     va_list ap;
  55     char message[1024];
  56     va_start(ap, msg);
  57     vsnprintf(message, sizeof(message), msg, ap);
  58     va_end(ap);
  59     if (ctxt->err) {
  60         error_free(ctxt->err);
  61         ctxt->err = NULL;
  62     }
  63     error_setg(&ctxt->err, "JSON parse error, %s", message);
  64 }
  65
  66 /**
  67  * String helpers
  68  *
  69  * These helpers are used to unescape strings.
  70  */
  71 static void wchar_to_utf8(uint16_t wchar, char *buffer, size_t buffer_length)
  72 {
  73     if (wchar <= 0x007F) {
  74         BUG_ON(buffer_length < 2);
  75
  76         buffer[0] = wchar & 0x7F;
  77         buffer[1] = 0;
  78     } else if (wchar <= 0x07FF) {
  79         BUG_ON(buffer_length < 3);
  80
  81         buffer[0] = 0xC0 | ((wchar >> 6) & 0x1F);
  82         buffer[1] = 0x80 | (wchar & 0x3F);
  83         buffer[2] = 0;
  84     } else {
  85         BUG_ON(buffer_length < 4);
  86
  87         buffer[0] = 0xE0 | ((wchar >> 12) & 0x0F);
  88         buffer[1] = 0x80 | ((wchar >> 6) & 0x3F);
  89         buffer[2] = 0x80 | (wchar & 0x3F);
  90         buffer[3] = 0;
  91     }
  92 }
  93
  94 static int hex2decimal(char ch)
  95 {
  96     if (ch >= '0' && ch <= '9') {
  97         return (ch - '0');
  98     } else if (ch >= 'a' && ch <= 'f') {
  99         return 10 + (ch - 'a');
 100     } else if (ch >= 'A' && ch <= 'F') {
 101         return 10 + (ch - 'A');
 102     }
 103
 104     return -1;
 105 }
 106
 107 /**
 108  * parse_string(): Parse a json string and return a QObject
 109  *
 110  *  string
 111  *      ""
 112  *      " chars "
 113  *  chars
 114  *      char
 115  *      char chars
 116  *  char
 117  *      any-Unicode-character-
 118  *          except-"-or-\-or-
 119  *          control-character
 120  *      \"
 121  *      \\
 122  *      \/
 123  *      \b
 124  *      \f
 125  *      \n
 126  *      \r
 127  *      \t
 128  *      \u four-hex-digits
 129  */
 130 static QString *qstring_from_escaped_str(JSONParserContext *ctxt,
 131                                          JSONToken *token)
 132 {
 133     const char *ptr = token->str;
 134     QString *str;
 135     int double_quote = 1;
 136
 137     if (*ptr == '"') {
 138         double_quote = 1;
 139     } else {
 140         double_quote = 0;
 141     }
 142     ptr++;
 143
 144     str = qstring_new();
 145     while (*ptr &&
 146            ((double_quote && *ptr != '"') || (!double_quote && *ptr != '\''))) {
 147         if (*ptr == '\\') {
 148             ptr++;
 149
 150             switch (*ptr) {
 151             case '"':
 152                 qstring_append(str, "\"");
 153                 ptr++;
 154                 break;
 155             case '\'':
 156                 qstring_append(str, "'");
 157                 ptr++;
 158                 break;
 159             case '\\':
 160                 qstring_append(str, "\\");
 161                 ptr++;
 162                 break;
 163             case '/':
 164                 qstring_append(str, "/");
 165                 ptr++;
 166                 break;
 167             case 'b':
 168                 qstring_append(str, "\b");
 169                 ptr++;
 170                 break;
 171             case 'f':
 172                 qstring_append(str, "\f");
 173                 ptr++;
 174                 break;
 175             case 'n':
 176                 qstring_append(str, "\n");
 177                 ptr++;
 178                 break;
 179             case 'r':
 180                 qstring_append(str, "\r");
 181                 ptr++;
 182                 break;
 183             case 't':
 184                 qstring_append(str, "\t");
 185                 ptr++;
 186                 break;
 187             case 'u': {
 188                 uint16_t unicode_char = 0;
 189                 char utf8_char[4];
 190                 int i = 0;
 191
 192                 ptr++;
 193
 194                 for (i = 0; i < 4; i++) {
 195                     if (qemu_isxdigit(*ptr)) {
 196                         unicode_char |= hex2decimal(*ptr) << ((3 - i) * 4);
 197                     } else {
 198                         parse_error(ctxt, token,
 199                                     "invalid hex escape sequence in string");
 200                         goto out;
 201                     }
 202                     ptr++;
 203                 }
 204
 205                 wchar_to_utf8(unicode_char, utf8_char, sizeof(utf8_char));
 206                 qstring_append(str, utf8_char);
 207             }   break;
 208             default:
 209                 parse_error(ctxt, token, "invalid escape sequence in string");
 210                 goto out;
 211             }
 212         } else {
 213             char dummy[2];
 214
 215             dummy[0] = *ptr++;
 216             dummy[1] = 0;
 217
 218             qstring_append(str, dummy);
 219         }
 220     }
 221
 222     return str;
 223
 224 out:
 225     QDECREF(str);
 226     return NULL;
 227 }
 228
 229 /* Note: the token object returned by parser_context_peek_token or
 230  * parser_context_pop_token is deleted as soon as parser_context_pop_token
 231  * is called again.
 232  */
 233 static JSONToken *parser_context_pop_token(JSONParserContext *ctxt)
 234 {
 235     g_free(ctxt->current);
 236     assert(!g_queue_is_empty(ctxt->buf));
 237     ctxt->current = g_queue_pop_head(ctxt->buf);
 238     return ctxt->current;
 239 }
 240
 241 static JSONToken *parser_context_peek_token(JSONParserContext *ctxt)
 242 {
 243     assert(!g_queue_is_empty(ctxt->buf));
 244     return g_queue_peek_head(ctxt->buf);
 245 }
 246
 247 static JSONParserContext *parser_context_new(GQueue *tokens)
 248 {
 249     JSONParserContext *ctxt;
 250
 251     if (!tokens) {
 252         return NULL;
 253     }
 254
 255     ctxt = g_malloc0(sizeof(JSONParserContext));
 256     ctxt->buf = tokens;
 257
 258     return ctxt;
 259 }
 260
 261 /* to support error propagation, ctxt->err must be freed separately */
 262 static void parser_context_free(JSONParserContext *ctxt)
 263 {
 264     if (ctxt) {
 265         while (!g_queue_is_empty(ctxt->buf)) {
 266             parser_context_pop_token(ctxt);
 267         }
 268         g_free(ctxt->current);
 269         g_queue_free(ctxt->buf);
 270         g_free(ctxt);
 271     }
 272 }
 273
 274 /**
 275  * Parsing rules
 276  */
 277 static int parse_pair(JSONParserContext *ctxt, QDict *dict, va_list *ap)
 278 {
 279     QObject *value;
 280     QString *key = NULL;
 281     JSONToken *peek, *token;
 282
 283     peek = parser_context_peek_token(ctxt);
 284     if (peek == NULL) {
 285         parse_error(ctxt, NULL, "premature EOI");
 286         goto out;
 287     }
 288
 289     key = qobject_to(QString, parse_value(ctxt, ap));
 290     if (!key) {
 291         parse_error(ctxt, peek, "key is not a string in object");
 292         goto out;
 293     }
 294
 295     token = parser_context_pop_token(ctxt);
 296     if (token == NULL) {
 297         parse_error(ctxt, NULL, "premature EOI");
 298         goto out;
 299     }
 300
 301     if (token->type != JSON_COLON) {
 302         parse_error(ctxt, token, "missing : in object pair");
 303         goto out;
 304     }
 305
 306     value = parse_value(ctxt, ap);
 307     if (value == NULL) {
 308         parse_error(ctxt, token, "Missing value in dict");
 309         goto out;
 310     }
 311
 312     qdict_put_obj(dict, qstring_get_str(key), value);
 313
 314     QDECREF(key);
 315
 316     return 0;
 317
 318 out:
 319     QDECREF(key);
 320
 321     return -1;
 322 }
 323
 324 static QObject *parse_object(JSONParserContext *ctxt, va_list *ap)
 325 {
 326     QDict *dict = NULL;
 327     JSONToken *token, *peek;
 328
 329     token = parser_context_pop_token(ctxt);
 330     assert(token && token->type == JSON_LCURLY);
 331
 332     dict = qdict_new();
 333
 334     peek = parser_context_peek_token(ctxt);
 335     if (peek == NULL) {
 336         parse_error(ctxt, NULL, "premature EOI");
 337         goto out;
 338     }
 339
 340     if (peek->type != JSON_RCURLY) {
 341         if (parse_pair(ctxt, dict, ap) == -1) {
 342             goto out;
 343         }
 344
 345         token = parser_context_pop_token(ctxt);
 346         if (token == NULL) {
 347             parse_error(ctxt, NULL, "premature EOI");
 348             goto out;
 349         }
 350
 351         while (token->type != JSON_RCURLY) {
 352             if (token->type != JSON_COMMA) {
 353                 parse_error(ctxt, token, "expected separator in dict");
 354                 goto out;
 355             }
 356
 357             if (parse_pair(ctxt, dict, ap) == -1) {
 358                 goto out;
 359             }
 360
 361             token = parser_context_pop_token(ctxt);
 362             if (token == NULL) {
 363                 parse_error(ctxt, NULL, "premature EOI");
 364                 goto out;
 365             }
 366         }
 367     } else {
 368         (void)parser_context_pop_token(ctxt);
 369     }
 370
 371     return QOBJECT(dict);
 372
 373 out:
 374     QDECREF(dict);
 375     return NULL;
 376 }
 377
 378 static QObject *parse_array(JSONParserContext *ctxt, va_list *ap)
 379 {
 380     QList *list = NULL;
 381     JSONToken *token, *peek;
 382
 383     token = parser_context_pop_token(ctxt);
 384     assert(token && token->type == JSON_LSQUARE);
 385
 386     list = qlist_new();
 387
 388     peek = parser_context_peek_token(ctxt);
 389     if (peek == NULL) {
 390         parse_error(ctxt, NULL, "premature EOI");
 391         goto out;
 392     }
 393
 394     if (peek->type != JSON_RSQUARE) {
 395         QObject *obj;
 396
 397         obj = parse_value(ctxt, ap);
 398         if (obj == NULL) {
 399             parse_error(ctxt, token, "expecting value");
 400             goto out;
 401         }
 402
 403         qlist_append_obj(list, obj);
 404
 405         token = parser_context_pop_token(ctxt);
 406         if (token == NULL) {
 407             parse_error(ctxt, NULL, "premature EOI");
 408             goto out;
 409         }
 410
 411         while (token->type != JSON_RSQUARE) {
 412             if (token->type != JSON_COMMA) {
 413                 parse_error(ctxt, token, "expected separator in list");
 414                 goto out;
 415             }
 416
 417             obj = parse_value(ctxt, ap);
 418             if (obj == NULL) {
 419                 parse_error(ctxt, token, "expecting value");
 420                 goto out;
 421             }
 422
 423             qlist_append_obj(list, obj);
 424
 425             token = parser_context_pop_token(ctxt);
 426             if (token == NULL) {
 427                 parse_error(ctxt, NULL, "premature EOI");
 428                 goto out;
 429             }
 430         }
 431     } else {
 432         (void)parser_context_pop_token(ctxt);
 433     }
 434
 435     return QOBJECT(list);
 436
 437 out:
 438     QDECREF(list);
 439     return NULL;
 440 }
 441
 442 static QObject *parse_keyword(JSONParserContext *ctxt)
 443 {
 444     JSONToken *token;
 445
 446     token = parser_context_pop_token(ctxt);
 447     assert(token && token->type == JSON_KEYWORD);
 448
 449     if (!strcmp(token->str, "true")) {
 450         return QOBJECT(qbool_from_bool(true));
 451     } else if (!strcmp(token->str, "false")) {
 452         return QOBJECT(qbool_from_bool(false));
 453     } else if (!strcmp(token->str, "null")) {
 454         return QOBJECT(qnull());
 455     }
 456     parse_error(ctxt, token, "invalid keyword '%s'", token->str);
 457     return NULL;
 458 }
 459
 460 static QObject *parse_escape(JSONParserContext *ctxt, va_list *ap)
 461 {
 462     JSONToken *token;
 463
 464     if (ap == NULL) {
 465         return NULL;
 466     }
 467
 468     token = parser_context_pop_token(ctxt);
 469     assert(token && token->type == JSON_ESCAPE);
 470
 471     if (!strcmp(token->str, "%p")) {
 472         return va_arg(*ap, QObject *);
 473     } else if (!strcmp(token->str, "%i")) {
 474         return QOBJECT(qbool_from_bool(va_arg(*ap, int)));
 475     } else if (!strcmp(token->str, "%d")) {
 476         return QOBJECT(qnum_from_int(va_arg(*ap, int)));
 477     } else if (!strcmp(token->str, "%ld")) {
 478         return QOBJECT(qnum_from_int(va_arg(*ap, long)));
 479     } else if (!strcmp(token->str, "%lld") ||
 480                !strcmp(token->str, "%I64d")) {
 481         return QOBJECT(qnum_from_int(va_arg(*ap, long long)));
 482     } else if (!strcmp(token->str, "%u")) {
 483         return QOBJECT(qnum_from_uint(va_arg(*ap, unsigned int)));
 484     } else if (!strcmp(token->str, "%lu")) {
 485         return QOBJECT(qnum_from_uint(va_arg(*ap, unsigned long)));
 486     } else if (!strcmp(token->str, "%llu") ||
 487                !strcmp(token->str, "%I64u")) {
 488         return QOBJECT(qnum_from_uint(va_arg(*ap, unsigned long long)));
 489     } else if (!strcmp(token->str, "%s")) {
 490         return QOBJECT(qstring_from_str(va_arg(*ap, const char *)));
 491     } else if (!strcmp(token->str, "%f")) {
 492         return QOBJECT(qnum_from_double(va_arg(*ap, double)));
 493     }
 494     return NULL;
 495 }
 496
 497 static QObject *parse_literal(JSONParserContext *ctxt)
 498 {
 499     JSONToken *token;
 500
 501     token = parser_context_pop_token(ctxt);
 502     assert(token);
 503
 504     switch (token->type) {
 505     case JSON_STRING:
 506         return QOBJECT(qstring_from_escaped_str(ctxt, token));
 507     case JSON_INTEGER: {
 508         /*
 509          * Represent JSON_INTEGER as QNUM_I64 if possible, else as
 510          * QNUM_U64, else as QNUM_DOUBLE.  Note that qemu_strtoi64()
 511          * and qemu_strtou64() fail with ERANGE when it's not
 512          * possible.
 513          *
 514          * qnum_get_int() will then work for any signed 64-bit
 515          * JSON_INTEGER, qnum_get_uint() for any unsigned 64-bit
 516          * integer, and qnum_get_double() both for any JSON_INTEGER
 517          * and any JSON_FLOAT (with precision loss for integers beyond
 518          * 53 bits)
 519          */
 520         int ret;
 521         int64_t value;
 522         uint64_t uvalue;
 523
 524         ret = qemu_strtoi64(token->str, NULL, 10, &value);
 525         if (!ret) {
 526             return QOBJECT(qnum_from_int(value));
 527         }
 528         assert(ret == -ERANGE);
 529
 530         if (token->str[0] != '-') {
 531             ret = qemu_strtou64(token->str, NULL, 10, &uvalue);
 532             if (!ret) {
 533                 return QOBJECT(qnum_from_uint(uvalue));
 534             }
 535             assert(ret == -ERANGE);
 536         }
 537         /* fall through to JSON_FLOAT */
 538     }
 539     case JSON_FLOAT:
 540         /* FIXME dependent on locale; a pervasive issue in QEMU */
 541         /* FIXME our lexer matches RFC 7159 in forbidding Inf or NaN,
 542          * but those might be useful extensions beyond JSON */
 543         return QOBJECT(qnum_from_double(strtod(token->str, NULL)));
 544     default:
 545         abort();
 546     }
 547 }
 548
 549 static QObject *parse_value(JSONParserContext *ctxt, va_list *ap)
 550 {
 551     JSONToken *token;
 552
 553     token = parser_context_peek_token(ctxt);
 554     if (token == NULL) {
 555         parse_error(ctxt, NULL, "premature EOI");
 556         return NULL;
 557     }
 558
 559     switch (token->type) {
 560     case JSON_LCURLY:
 561         return parse_object(ctxt, ap);
 562     case JSON_LSQUARE:
 563         return parse_array(ctxt, ap);
 564     case JSON_ESCAPE:
 565         return parse_escape(ctxt, ap);
 566     case JSON_INTEGER:
 567     case JSON_FLOAT:
 568     case JSON_STRING:
 569         return parse_literal(ctxt);
 570     case JSON_KEYWORD:
 571         return parse_keyword(ctxt);
 572     default:
 573         parse_error(ctxt, token, "expecting value");
 574         return NULL;
 575     }
 576 }
 577
 578 QObject *json_parser_parse(GQueue *tokens, va_list *ap)
 579 {
 580     return json_parser_parse_err(tokens, ap, NULL);
 581 }
 582
 583 QObject *json_parser_parse_err(GQueue *tokens, va_list *ap, Error **errp)
 584 {
 585     JSONParserContext *ctxt = parser_context_new(tokens);
 586     QObject *result;
 587
 588     if (!ctxt) {
 589         return NULL;
 590     }
 591
 592     result = parse_value(ctxt, ap);
 593
 594     error_propagate(errp, ctxt->err);
 595
 596     parser_context_free(ctxt);
 597
 598     return result;
 599 }