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 "qemu/unicode.h"
  17 #include "qapi/error.h"
  18 #include "qemu-common.h"
  19 #include "qapi/qmp/qbool.h"
  20 #include "qapi/qmp/qdict.h"
  21 #include "qapi/qmp/qlist.h"
  22 #include "qapi/qmp/qnull.h"
  23 #include "qapi/qmp/qnum.h"
  24 #include "qapi/qmp/qstring.h"
  25 #include "json-parser-int.h"
  26
  27 struct JSONToken {
  28     JSONTokenType type;
  29     int x;
  30     int y;
  31     char str[];
  32 };
  33
  34 typedef struct JSONParserContext
  35 {
  36     Error *err;
  37     JSONToken *current;
  38     GQueue *buf;
  39     va_list *ap;
  40 } JSONParserContext;
  41
  42 #define BUG_ON(cond) assert(!(cond))
  43
  44 /**
  45  * TODO
  46  *
  47  * 0) make errors meaningful again
  48  * 1) add geometry information to tokens
  49  * 3) should we return a parsed size?
  50  * 4) deal with premature EOI
  51  */
  52
  53 static QObject *parse_value(JSONParserContext *ctxt);
  54
  55 /**
  56  * Error handler
  57  */
  58 static void GCC_FMT_ATTR(3, 4) parse_error(JSONParserContext *ctxt,
  59                                            JSONToken *token, const char *msg, ...)
  60 {
  61     va_list ap;
  62     char message[1024];
  63
  64     if (ctxt->err) {
  65         return;
  66     }
  67     va_start(ap, msg);
  68     vsnprintf(message, sizeof(message), msg, ap);
  69     va_end(ap);
  70     error_setg(&ctxt->err, "JSON parse error, %s", message);
  71 }
  72
  73 static int cvt4hex(const char *s)
  74 {
  75     int cp, i;
  76
  77     cp = 0;
  78     for (i = 0; i < 4; i++) {
  79         if (!qemu_isxdigit(s[i])) {
  80             return -1;
  81         }
  82         cp <<= 4;
  83         if (s[i] >= '0' && s[i] <= '9') {
  84             cp |= s[i] - '0';
  85         } else if (s[i] >= 'a' && s[i] <= 'f') {
  86             cp |= 10 + s[i] - 'a';
  87         } else if (s[i] >= 'A' && s[i] <= 'F') {
  88             cp |= 10 + s[i] - 'A';
  89         } else {
  90             return -1;
  91         }
  92     }
  93     return cp;
  94 }
  95
  96 /**
  97  * parse_string(): Parse a JSON string
  98  *
  99  * From RFC 8259 "The JavaScript Object Notation (JSON) Data
 100  * Interchange Format":
 101  *
 102  *    char = unescaped /
 103  *        escape (
 104  *            %x22 /          ; "    quotation mark  U+0022
 105  *            %x5C /          ; \    reverse solidus U+005C
 106  *            %x2F /          ; /    solidus         U+002F
 107  *            %x62 /          ; b    backspace       U+0008
 108  *            %x66 /          ; f    form feed       U+000C
 109  *            %x6E /          ; n    line feed       U+000A
 110  *            %x72 /          ; r    carriage return U+000D
 111  *            %x74 /          ; t    tab             U+0009
 112  *            %x75 4HEXDIG )  ; uXXXX                U+XXXX
 113  *    escape = %x5C              ; \
 114  *    quotation-mark = %x22      ; "
 115  *    unescaped = %x20-21 / %x23-5B / %x5D-10FFFF
 116  *
 117  * Extensions over RFC 8259:
 118  * - Extra escape sequence in strings:
 119  *   0x27 (apostrophe) is recognized after escape, too
 120  * - Single-quoted strings:
 121  *   Like double-quoted strings, except they're delimited by %x27
 122  *   (apostrophe) instead of %x22 (quotation mark), and can't contain
 123  *   unescaped apostrophe, but can contain unescaped quotation mark.
 124  *
 125  * Note:
 126  * - Encoding is modified UTF-8.
 127  * - Invalid Unicode characters are rejected.
 128  * - Control characters \x00..\x1F are rejected by the lexer.
 129  */
 130 static QString *parse_string(JSONParserContext *ctxt, JSONToken *token)
 131 {
 132     const char *ptr = token->str;
 133     QString *str;
 134     char quote;
 135     const char *beg;
 136     int cp, trailing;
 137     char *end;
 138     ssize_t len;
 139     char utf8_buf[5];
 140
 141     assert(*ptr == '"' || *ptr == '\'');
 142     quote = *ptr++;
 143     str = qstring_new();
 144
 145     while (*ptr != quote) {
 146         assert(*ptr);
 147         switch (*ptr) {
 148         case '\\':
 149             beg = ptr++;
 150             switch (*ptr++) {
 151             case '"':
 152                 qstring_append_chr(str, '"');
 153                 break;
 154             case '\'':
 155                 qstring_append_chr(str, '\'');
 156                 break;
 157             case '\\':
 158                 qstring_append_chr(str, '\\');
 159                 break;
 160             case '/':
 161                 qstring_append_chr(str, '/');
 162                 break;
 163             case 'b':
 164                 qstring_append_chr(str, '\b');
 165                 break;
 166             case 'f':
 167                 qstring_append_chr(str, '\f');
 168                 break;
 169             case 'n':
 170                 qstring_append_chr(str, '\n');
 171                 break;
 172             case 'r':
 173                 qstring_append_chr(str, '\r');
 174                 break;
 175             case 't':
 176                 qstring_append_chr(str, '\t');
 177                 break;
 178             case 'u':
 179                 cp = cvt4hex(ptr);
 180                 ptr += 4;
 181
 182                 /* handle surrogate pairs */
 183                 if (cp >= 0xD800 && cp <= 0xDBFF
 184                     && ptr[0] == '\\' && ptr[1] == 'u') {
 185                     /* leading surrogate followed by \u */
 186                     cp = 0x10000 + ((cp & 0x3FF) << 10);
 187                     trailing = cvt4hex(ptr + 2);
 188                     if (trailing >= 0xDC00 && trailing <= 0xDFFF) {
 189                         /* followed by trailing surrogate */
 190                         cp |= trailing & 0x3FF;
 191                         ptr += 6;
 192                     } else {
 193                         cp = -1; /* invalid */
 194                     }
 195                 }
 196
 197                 if (mod_utf8_encode(utf8_buf, sizeof(utf8_buf), cp) < 0) {
 198                     parse_error(ctxt, token,
 199                                 "%.*s is not a valid Unicode character",
 200                                 (int)(ptr - beg), beg);
 201                     goto out;
 202                 }
 203                 qstring_append(str, utf8_buf);
 204                 break;
 205             default:
 206                 parse_error(ctxt, token, "invalid escape sequence in string");
 207                 goto out;
 208             }
 209             break;
 210         case '%':
 211             if (ctxt->ap && ptr[1] != '%') {
 212                 parse_error(ctxt, token, "can't interpolate into string");
 213                 goto out;
 214             }
 215             ptr++;
 216             /* fall through */
 217         default:
 218             cp = mod_utf8_codepoint(ptr, 6, &end);
 219             if (cp < 0) {
 220                 parse_error(ctxt, token, "invalid UTF-8 sequence in string");
 221                 goto out;
 222             }
 223             ptr = end;
 224             len = mod_utf8_encode(utf8_buf, sizeof(utf8_buf), cp);
 225             assert(len >= 0);
 226             qstring_append(str, utf8_buf);
 227         }
 228     }
 229
 230     return str;
 231
 232 out:
 233     qobject_unref(str);
 234     return NULL;
 235 }
 236
 237 /* Note: the token object returned by parser_context_peek_token or
 238  * parser_context_pop_token is deleted as soon as parser_context_pop_token
 239  * is called again.
 240  */
 241 static JSONToken *parser_context_pop_token(JSONParserContext *ctxt)
 242 {
 243     g_free(ctxt->current);
 244     ctxt->current = g_queue_pop_head(ctxt->buf);
 245     return ctxt->current;
 246 }
 247
 248 static JSONToken *parser_context_peek_token(JSONParserContext *ctxt)
 249 {
 250     return g_queue_peek_head(ctxt->buf);
 251 }
 252
 253 /**
 254  * Parsing rules
 255  */
 256 static int parse_pair(JSONParserContext *ctxt, QDict *dict)
 257 {
 258     QObject *value;
 259     QString *key = NULL;
 260     JSONToken *peek, *token;
 261
 262     peek = parser_context_peek_token(ctxt);
 263     if (peek == NULL) {
 264         parse_error(ctxt, NULL, "premature EOI");
 265         goto out;
 266     }
 267
 268     key = qobject_to(QString, parse_value(ctxt));
 269     if (!key) {
 270         parse_error(ctxt, peek, "key is not a string in object");
 271         goto out;
 272     }
 273
 274     token = parser_context_pop_token(ctxt);
 275     if (token == NULL) {
 276         parse_error(ctxt, NULL, "premature EOI");
 277         goto out;
 278     }
 279
 280     if (token->type != JSON_COLON) {
 281         parse_error(ctxt, token, "missing : in object pair");
 282         goto out;
 283     }
 284
 285     value = parse_value(ctxt);
 286     if (value == NULL) {
 287         parse_error(ctxt, token, "Missing value in dict");
 288         goto out;
 289     }
 290
 291     qdict_put_obj(dict, qstring_get_str(key), value);
 292
 293     qobject_unref(key);
 294
 295     return 0;
 296
 297 out:
 298     qobject_unref(key);
 299
 300     return -1;
 301 }
 302
 303 static QObject *parse_object(JSONParserContext *ctxt)
 304 {
 305     QDict *dict = NULL;
 306     JSONToken *token, *peek;
 307
 308     token = parser_context_pop_token(ctxt);
 309     assert(token && token->type == JSON_LCURLY);
 310
 311     dict = qdict_new();
 312
 313     peek = parser_context_peek_token(ctxt);
 314     if (peek == NULL) {
 315         parse_error(ctxt, NULL, "premature EOI");
 316         goto out;
 317     }
 318
 319     if (peek->type != JSON_RCURLY) {
 320         if (parse_pair(ctxt, dict) == -1) {
 321             goto out;
 322         }
 323
 324         token = parser_context_pop_token(ctxt);
 325         if (token == NULL) {
 326             parse_error(ctxt, NULL, "premature EOI");
 327             goto out;
 328         }
 329
 330         while (token->type != JSON_RCURLY) {
 331             if (token->type != JSON_COMMA) {
 332                 parse_error(ctxt, token, "expected separator in dict");
 333                 goto out;
 334             }
 335
 336             if (parse_pair(ctxt, dict) == -1) {
 337                 goto out;
 338             }
 339
 340             token = parser_context_pop_token(ctxt);
 341             if (token == NULL) {
 342                 parse_error(ctxt, NULL, "premature EOI");
 343                 goto out;
 344             }
 345         }
 346     } else {
 347         (void)parser_context_pop_token(ctxt);
 348     }
 349
 350     return QOBJECT(dict);
 351
 352 out:
 353     qobject_unref(dict);
 354     return NULL;
 355 }
 356
 357 static QObject *parse_array(JSONParserContext *ctxt)
 358 {
 359     QList *list = NULL;
 360     JSONToken *token, *peek;
 361
 362     token = parser_context_pop_token(ctxt);
 363     assert(token && token->type == JSON_LSQUARE);
 364
 365     list = qlist_new();
 366
 367     peek = parser_context_peek_token(ctxt);
 368     if (peek == NULL) {
 369         parse_error(ctxt, NULL, "premature EOI");
 370         goto out;
 371     }
 372
 373     if (peek->type != JSON_RSQUARE) {
 374         QObject *obj;
 375
 376         obj = parse_value(ctxt);
 377         if (obj == NULL) {
 378             parse_error(ctxt, token, "expecting value");
 379             goto out;
 380         }
 381
 382         qlist_append_obj(list, obj);
 383
 384         token = parser_context_pop_token(ctxt);
 385         if (token == NULL) {
 386             parse_error(ctxt, NULL, "premature EOI");
 387             goto out;
 388         }
 389
 390         while (token->type != JSON_RSQUARE) {
 391             if (token->type != JSON_COMMA) {
 392                 parse_error(ctxt, token, "expected separator in list");
 393                 goto out;
 394             }
 395
 396             obj = parse_value(ctxt);
 397             if (obj == NULL) {
 398                 parse_error(ctxt, token, "expecting value");
 399                 goto out;
 400             }
 401
 402             qlist_append_obj(list, obj);
 403
 404             token = parser_context_pop_token(ctxt);
 405             if (token == NULL) {
 406                 parse_error(ctxt, NULL, "premature EOI");
 407                 goto out;
 408             }
 409         }
 410     } else {
 411         (void)parser_context_pop_token(ctxt);
 412     }
 413
 414     return QOBJECT(list);
 415
 416 out:
 417     qobject_unref(list);
 418     return NULL;
 419 }
 420
 421 static QObject *parse_keyword(JSONParserContext *ctxt)
 422 {
 423     JSONToken *token;
 424
 425     token = parser_context_pop_token(ctxt);
 426     assert(token && token->type == JSON_KEYWORD);
 427
 428     if (!strcmp(token->str, "true")) {
 429         return QOBJECT(qbool_from_bool(true));
 430     } else if (!strcmp(token->str, "false")) {
 431         return QOBJECT(qbool_from_bool(false));
 432     } else if (!strcmp(token->str, "null")) {
 433         return QOBJECT(qnull());
 434     }
 435     parse_error(ctxt, token, "invalid keyword '%s'", token->str);
 436     return NULL;
 437 }
 438
 439 static QObject *parse_interpolation(JSONParserContext *ctxt)
 440 {
 441     JSONToken *token;
 442
 443     token = parser_context_pop_token(ctxt);
 444     assert(token && token->type == JSON_INTERP);
 445
 446     if (!strcmp(token->str, "%p")) {
 447         return va_arg(*ctxt->ap, QObject *);
 448     } else if (!strcmp(token->str, "%i")) {
 449         return QOBJECT(qbool_from_bool(va_arg(*ctxt->ap, int)));
 450     } else if (!strcmp(token->str, "%d")) {
 451         return QOBJECT(qnum_from_int(va_arg(*ctxt->ap, int)));
 452     } else if (!strcmp(token->str, "%ld")) {
 453         return QOBJECT(qnum_from_int(va_arg(*ctxt->ap, long)));
 454     } else if (!strcmp(token->str, "%lld")) {
 455         return QOBJECT(qnum_from_int(va_arg(*ctxt->ap, long long)));
 456     } else if (!strcmp(token->str, "%" PRId64)) {
 457         return QOBJECT(qnum_from_int(va_arg(*ctxt->ap, int64_t)));
 458     } else if (!strcmp(token->str, "%u")) {
 459         return QOBJECT(qnum_from_uint(va_arg(*ctxt->ap, unsigned int)));
 460     } else if (!strcmp(token->str, "%lu")) {
 461         return QOBJECT(qnum_from_uint(va_arg(*ctxt->ap, unsigned long)));
 462     } else if (!strcmp(token->str, "%llu")) {
 463         return QOBJECT(qnum_from_uint(va_arg(*ctxt->ap, unsigned long long)));
 464     } else if (!strcmp(token->str, "%" PRIu64)) {
 465         return QOBJECT(qnum_from_uint(va_arg(*ctxt->ap, uint64_t)));
 466     } else if (!strcmp(token->str, "%s")) {
 467         return QOBJECT(qstring_from_str(va_arg(*ctxt->ap, const char *)));
 468     } else if (!strcmp(token->str, "%f")) {
 469         return QOBJECT(qnum_from_double(va_arg(*ctxt->ap, double)));
 470     }
 471     parse_error(ctxt, token, "invalid interpolation '%s'", token->str);
 472     return NULL;
 473 }
 474
 475 static QObject *parse_literal(JSONParserContext *ctxt)
 476 {
 477     JSONToken *token;
 478
 479     token = parser_context_pop_token(ctxt);
 480     assert(token);
 481
 482     switch (token->type) {
 483     case JSON_STRING:
 484         return QOBJECT(parse_string(ctxt, token));
 485     case JSON_INTEGER: {
 486         /*
 487          * Represent JSON_INTEGER as QNUM_I64 if possible, else as
 488          * QNUM_U64, else as QNUM_DOUBLE.  Note that qemu_strtoi64()
 489          * and qemu_strtou64() fail with ERANGE when it's not
 490          * possible.
 491          *
 492          * qnum_get_int() will then work for any signed 64-bit
 493          * JSON_INTEGER, qnum_get_uint() for any unsigned 64-bit
 494          * integer, and qnum_get_double() both for any JSON_INTEGER
 495          * and any JSON_FLOAT (with precision loss for integers beyond
 496          * 53 bits)
 497          */
 498         int ret;
 499         int64_t value;
 500         uint64_t uvalue;
 501
 502         ret = qemu_strtoi64(token->str, NULL, 10, &value);
 503         if (!ret) {
 504             return QOBJECT(qnum_from_int(value));
 505         }
 506         assert(ret == -ERANGE);
 507
 508         if (token->str[0] != '-') {
 509             ret = qemu_strtou64(token->str, NULL, 10, &uvalue);
 510             if (!ret) {
 511                 return QOBJECT(qnum_from_uint(uvalue));
 512             }
 513             assert(ret == -ERANGE);
 514         }
 515         /* fall through to JSON_FLOAT */
 516     }
 517     case JSON_FLOAT:
 518         /* FIXME dependent on locale; a pervasive issue in QEMU */
 519         /* FIXME our lexer matches RFC 8259 in forbidding Inf or NaN,
 520          * but those might be useful extensions beyond JSON */
 521         return QOBJECT(qnum_from_double(strtod(token->str, NULL)));
 522     default:
 523         abort();
 524     }
 525 }
 526
 527 static QObject *parse_value(JSONParserContext *ctxt)
 528 {
 529     JSONToken *token;
 530
 531     token = parser_context_peek_token(ctxt);
 532     if (token == NULL) {
 533         parse_error(ctxt, NULL, "premature EOI");
 534         return NULL;
 535     }
 536
 537     switch (token->type) {
 538     case JSON_LCURLY:
 539         return parse_object(ctxt);
 540     case JSON_LSQUARE:
 541         return parse_array(ctxt);
 542     case JSON_INTERP:
 543         return parse_interpolation(ctxt);
 544     case JSON_INTEGER:
 545     case JSON_FLOAT:
 546     case JSON_STRING:
 547         return parse_literal(ctxt);
 548     case JSON_KEYWORD:
 549         return parse_keyword(ctxt);
 550     default:
 551         parse_error(ctxt, token, "expecting value");
 552         return NULL;
 553     }
 554 }
 555
 556 JSONToken *json_token(JSONTokenType type, int x, int y, GString *tokstr)
 557 {
 558     JSONToken *token = g_malloc(sizeof(JSONToken) + tokstr->len + 1);
 559
 560     token->type = type;
 561     memcpy(token->str, tokstr->str, tokstr->len);
 562     token->str[tokstr->len] = 0;
 563     token->x = x;
 564     token->y = y;
 565     return token;
 566 }
 567
 568 QObject *json_parser_parse(GQueue *tokens, va_list *ap, Error **errp)
 569 {
 570     JSONParserContext ctxt = { .buf = tokens, .ap = ap };
 571     QObject *result;
 572
 573     result = parse_value(&ctxt);
 574     assert(ctxt.err || g_queue_is_empty(ctxt.buf));
 575
 576     error_propagate(errp, ctxt.err);
 577
 578     while (!g_queue_is_empty(ctxt.buf)) {
 579         parser_context_pop_token(&ctxt);
 580     }
 581     g_free(ctxt.current);
 582
 583     return result;
 584 }