File size: 60,140 Bytes
053b80b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 |
// Protocol Buffers - Google's data interchange format
// Copyright 2008 Google Inc. All rights reserved.
// https://developers.google.com/protocol-buffers/
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
// Author: kenton@google.com (Kenton Varda)
// Based on original Protocol Buffers design by
// Sanjay Ghemawat, Jeff Dean, and others.
//
// This file contains the CodedInputStream and CodedOutputStream classes,
// which wrap a ZeroCopyInputStream or ZeroCopyOutputStream, respectively,
// and allow you to read or write individual pieces of data in various
// formats. In particular, these implement the varint encoding for
// integers, a simple variable-length encoding in which smaller numbers
// take fewer bytes.
//
// Typically these classes will only be used internally by the protocol
// buffer library in order to encode and decode protocol buffers. Clients
// of the library only need to know about this class if they wish to write
// custom message parsing or serialization procedures.
//
// CodedOutputStream example:
// // Write some data to "myfile". First we write a 4-byte "magic number"
// // to identify the file type, then write a length-delimited string. The
// // string is composed of a varint giving the length followed by the raw
// // bytes.
// int fd = open("myfile", O_CREAT | O_WRONLY);
// ZeroCopyOutputStream* raw_output = new FileOutputStream(fd);
// CodedOutputStream* coded_output = new CodedOutputStream(raw_output);
//
// int magic_number = 1234;
// char text[] = "Hello world!";
// coded_output->WriteLittleEndian32(magic_number);
// coded_output->WriteVarint32(strlen(text));
// coded_output->WriteRaw(text, strlen(text));
//
// delete coded_output;
// delete raw_output;
// close(fd);
//
// CodedInputStream example:
// // Read a file created by the above code.
// int fd = open("myfile", O_RDONLY);
// ZeroCopyInputStream* raw_input = new FileInputStream(fd);
// CodedInputStream coded_input = new CodedInputStream(raw_input);
//
// coded_input->ReadLittleEndian32(&magic_number);
// if (magic_number != 1234) {
// cerr << "File not in expected format." << endl;
// return;
// }
//
// uint32 size;
// coded_input->ReadVarint32(&size);
//
// char* text = new char[size + 1];
// coded_input->ReadRaw(buffer, size);
// text[size] = '\0';
//
// delete coded_input;
// delete raw_input;
// close(fd);
//
// cout << "Text is: " << text << endl;
// delete [] text;
//
// For those who are interested, varint encoding is defined as follows:
//
// The encoding operates on unsigned integers of up to 64 bits in length.
// Each byte of the encoded value has the format:
// * bits 0-6: Seven bits of the number being encoded.
// * bit 7: Zero if this is the last byte in the encoding (in which
// case all remaining bits of the number are zero) or 1 if
// more bytes follow.
// The first byte contains the least-significant 7 bits of the number, the
// second byte (if present) contains the next-least-significant 7 bits,
// and so on. So, the binary number 1011000101011 would be encoded in two
// bytes as "10101011 00101100".
//
// In theory, varint could be used to encode integers of any length.
// However, for practicality we set a limit at 64 bits. The maximum encoded
// length of a number is thus 10 bytes.
#ifndef GOOGLE_PROTOBUF_IO_CODED_STREAM_H__
#define GOOGLE_PROTOBUF_IO_CODED_STREAM_H__
#include <assert.h>
#include <climits>
#include <string>
#include <utility>
#ifdef _MSC_VER
// Assuming windows is always little-endian.
#if !defined(PROTOBUF_DISABLE_LITTLE_ENDIAN_OPT_FOR_TEST)
#define PROTOBUF_LITTLE_ENDIAN 1
#endif
#if _MSC_VER >= 1300 && !defined(__INTEL_COMPILER)
// If MSVC has "/RTCc" set, it will complain about truncating casts at
// runtime. This file contains some intentional truncating casts.
#pragma runtime_checks("c", off)
#endif
#else
#include <sys/param.h> // __BYTE_ORDER
#if ((defined(__LITTLE_ENDIAN__) && !defined(__BIG_ENDIAN__)) || \
(defined(__BYTE_ORDER) && __BYTE_ORDER == __LITTLE_ENDIAN)) && \
!defined(PROTOBUF_DISABLE_LITTLE_ENDIAN_OPT_FOR_TEST)
#define PROTOBUF_LITTLE_ENDIAN 1
#endif
#endif
#include <google/protobuf/stubs/atomicops.h>
#include <google/protobuf/stubs/common.h>
#include <google/protobuf/stubs/port.h>
#include <google/protobuf/stubs/port.h>
namespace google {
namespace protobuf {
class DescriptorPool;
class MessageFactory;
namespace internal { void MapTestForceDeterministic(); }
namespace io {
// Defined in this file.
class CodedInputStream;
class CodedOutputStream;
// Defined in other files.
class ZeroCopyInputStream; // zero_copy_stream.h
class ZeroCopyOutputStream; // zero_copy_stream.h
// Class which reads and decodes binary data which is composed of varint-
// encoded integers and fixed-width pieces. Wraps a ZeroCopyInputStream.
// Most users will not need to deal with CodedInputStream.
//
// Most methods of CodedInputStream that return a bool return false if an
// underlying I/O error occurs or if the data is malformed. Once such a
// failure occurs, the CodedInputStream is broken and is no longer useful.
class LIBPROTOBUF_EXPORT CodedInputStream {
public:
// Create a CodedInputStream that reads from the given ZeroCopyInputStream.
explicit CodedInputStream(ZeroCopyInputStream* input);
// Create a CodedInputStream that reads from the given flat array. This is
// faster than using an ArrayInputStream. PushLimit(size) is implied by
// this constructor.
explicit CodedInputStream(const uint8* buffer, int size);
// Destroy the CodedInputStream and position the underlying
// ZeroCopyInputStream at the first unread byte. If an error occurred while
// reading (causing a method to return false), then the exact position of
// the input stream may be anywhere between the last value that was read
// successfully and the stream's byte limit.
~CodedInputStream();
// Return true if this CodedInputStream reads from a flat array instead of
// a ZeroCopyInputStream.
inline bool IsFlat() const;
// Skips a number of bytes. Returns false if an underlying read error
// occurs.
inline bool Skip(int count);
// Sets *data to point directly at the unread part of the CodedInputStream's
// underlying buffer, and *size to the size of that buffer, but does not
// advance the stream's current position. This will always either produce
// a non-empty buffer or return false. If the caller consumes any of
// this data, it should then call Skip() to skip over the consumed bytes.
// This may be useful for implementing external fast parsing routines for
// types of data not covered by the CodedInputStream interface.
bool GetDirectBufferPointer(const void** data, int* size);
// Like GetDirectBufferPointer, but this method is inlined, and does not
// attempt to Refresh() if the buffer is currently empty.
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE
void GetDirectBufferPointerInline(const void** data, int* size);
// Read raw bytes, copying them into the given buffer.
bool ReadRaw(void* buffer, int size);
// Like the above, with inlined optimizations. This should only be used
// by the protobuf implementation.
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE
bool InternalReadRawInline(void* buffer, int size);
// Like ReadRaw, but reads into a string.
bool ReadString(string* buffer, int size);
// Like the above, with inlined optimizations. This should only be used
// by the protobuf implementation.
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE
bool InternalReadStringInline(string* buffer, int size);
// Read a 32-bit little-endian integer.
bool ReadLittleEndian32(uint32* value);
// Read a 64-bit little-endian integer.
bool ReadLittleEndian64(uint64* value);
// These methods read from an externally provided buffer. The caller is
// responsible for ensuring that the buffer has sufficient space.
// Read a 32-bit little-endian integer.
static const uint8* ReadLittleEndian32FromArray(const uint8* buffer,
uint32* value);
// Read a 64-bit little-endian integer.
static const uint8* ReadLittleEndian64FromArray(const uint8* buffer,
uint64* value);
// Read an unsigned integer with Varint encoding, truncating to 32 bits.
// Reading a 32-bit value is equivalent to reading a 64-bit one and casting
// it to uint32, but may be more efficient.
bool ReadVarint32(uint32* value);
// Read an unsigned integer with Varint encoding.
bool ReadVarint64(uint64* value);
// Reads a varint off the wire into an "int". This should be used for reading
// sizes off the wire (sizes of strings, submessages, bytes fields, etc).
//
// The value from the wire is interpreted as unsigned. If its value exceeds
// the representable value of an integer on this platform, instead of
// truncating we return false. Truncating (as performed by ReadVarint32()
// above) is an acceptable approach for fields representing an integer, but
// when we are parsing a size from the wire, truncating the value would result
// in us misparsing the payload.
bool ReadVarintSizeAsInt(int* value);
// Read a tag. This calls ReadVarint32() and returns the result, or returns
// zero (which is not a valid tag) if ReadVarint32() fails. Also, ReadTag
// (but not ReadTagNoLastTag) updates the last tag value, which can be checked
// with LastTagWas().
//
// Always inline because this is only called in one place per parse loop
// but it is called for every iteration of said loop, so it should be fast.
// GCC doesn't want to inline this by default.
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE uint32 ReadTag() {
return last_tag_ = ReadTagNoLastTag();
}
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE uint32 ReadTagNoLastTag();
// This usually a faster alternative to ReadTag() when cutoff is a manifest
// constant. It does particularly well for cutoff >= 127. The first part
// of the return value is the tag that was read, though it can also be 0 in
// the cases where ReadTag() would return 0. If the second part is true
// then the tag is known to be in [0, cutoff]. If not, the tag either is
// above cutoff or is 0. (There's intentional wiggle room when tag is 0,
// because that can arise in several ways, and for best performance we want
// to avoid an extra "is tag == 0?" check here.)
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE
std::pair<uint32, bool> ReadTagWithCutoff(uint32 cutoff) {
std::pair<uint32, bool> result = ReadTagWithCutoffNoLastTag(cutoff);
last_tag_ = result.first;
return result;
}
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE
std::pair<uint32, bool> ReadTagWithCutoffNoLastTag(uint32 cutoff);
// Usually returns true if calling ReadVarint32() now would produce the given
// value. Will always return false if ReadVarint32() would not return the
// given value. If ExpectTag() returns true, it also advances past
// the varint. For best performance, use a compile-time constant as the
// parameter.
// Always inline because this collapses to a small number of instructions
// when given a constant parameter, but GCC doesn't want to inline by default.
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE bool ExpectTag(uint32 expected);
// Like above, except this reads from the specified buffer. The caller is
// responsible for ensuring that the buffer is large enough to read a varint
// of the expected size. For best performance, use a compile-time constant as
// the expected tag parameter.
//
// Returns a pointer beyond the expected tag if it was found, or NULL if it
// was not.
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE
static const uint8* ExpectTagFromArray(const uint8* buffer, uint32 expected);
// Usually returns true if no more bytes can be read. Always returns false
// if more bytes can be read. If ExpectAtEnd() returns true, a subsequent
// call to LastTagWas() will act as if ReadTag() had been called and returned
// zero, and ConsumedEntireMessage() will return true.
bool ExpectAtEnd();
// If the last call to ReadTag() or ReadTagWithCutoff() returned the given
// value, returns true. Otherwise, returns false.
// ReadTagNoLastTag/ReadTagWithCutoffNoLastTag do not preserve the last
// returned value.
//
// This is needed because parsers for some types of embedded messages
// (with field type TYPE_GROUP) don't actually know that they've reached the
// end of a message until they see an ENDGROUP tag, which was actually part
// of the enclosing message. The enclosing message would like to check that
// tag to make sure it had the right number, so it calls LastTagWas() on
// return from the embedded parser to check.
bool LastTagWas(uint32 expected);
void SetLastTag(uint32 tag) { last_tag_ = tag; }
// When parsing message (but NOT a group), this method must be called
// immediately after MergeFromCodedStream() returns (if it returns true)
// to further verify that the message ended in a legitimate way. For
// example, this verifies that parsing did not end on an end-group tag.
// It also checks for some cases where, due to optimizations,
// MergeFromCodedStream() can incorrectly return true.
bool ConsumedEntireMessage();
// Limits ----------------------------------------------------------
// Limits are used when parsing length-delimited embedded messages.
// After the message's length is read, PushLimit() is used to prevent
// the CodedInputStream from reading beyond that length. Once the
// embedded message has been parsed, PopLimit() is called to undo the
// limit.
// Opaque type used with PushLimit() and PopLimit(). Do not modify
// values of this type yourself. The only reason that this isn't a
// struct with private internals is for efficiency.
typedef int Limit;
// Places a limit on the number of bytes that the stream may read,
// starting from the current position. Once the stream hits this limit,
// it will act like the end of the input has been reached until PopLimit()
// is called.
//
// As the names imply, the stream conceptually has a stack of limits. The
// shortest limit on the stack is always enforced, even if it is not the
// top limit.
//
// The value returned by PushLimit() is opaque to the caller, and must
// be passed unchanged to the corresponding call to PopLimit().
Limit PushLimit(int byte_limit);
// Pops the last limit pushed by PushLimit(). The input must be the value
// returned by that call to PushLimit().
void PopLimit(Limit limit);
// Returns the number of bytes left until the nearest limit on the
// stack is hit, or -1 if no limits are in place.
int BytesUntilLimit() const;
// Returns current position relative to the beginning of the input stream.
int CurrentPosition() const;
// Total Bytes Limit -----------------------------------------------
// To prevent malicious users from sending excessively large messages
// and causing integer overflows or memory exhaustion, CodedInputStream
// imposes a hard limit on the total number of bytes it will read.
// Sets the maximum number of bytes that this CodedInputStream will read
// before refusing to continue. To prevent integer overflows in the
// protocol buffers implementation, as well as to prevent servers from
// allocating enormous amounts of memory to hold parsed messages, the
// maximum message length should be limited to the shortest length that
// will not harm usability. The theoretical shortest message that could
// cause integer overflows is 512MB. The default limit is 64MB. Apps
// should set shorter limits if possible. For backwards compatibility all
// negative values get squashed to -1, as other negative values might have
// special internal meanings. An error will always be printed to stderr if
// the limit is reached.
//
// This is unrelated to PushLimit()/PopLimit().
//
// Hint: If you are reading this because your program is printing a
// warning about dangerously large protocol messages, you may be
// confused about what to do next. The best option is to change your
// design such that excessively large messages are not necessary.
// For example, try to design file formats to consist of many small
// messages rather than a single large one. If this is infeasible,
// you will need to increase the limit. Chances are, though, that
// your code never constructs a CodedInputStream on which the limit
// can be set. You probably parse messages by calling things like
// Message::ParseFromString(). In this case, you will need to change
// your code to instead construct some sort of ZeroCopyInputStream
// (e.g. an ArrayInputStream), construct a CodedInputStream around
// that, then you can adjust the limit. Then call
// Message::ParseFromCodedStream() instead. Yes, it's more work, but
// you're doing something unusual.
void SetTotalBytesLimit(int total_bytes_limit, int warning_threshold);
// The Total Bytes Limit minus the Current Position, or -1 if there
// is no Total Bytes Limit.
int BytesUntilTotalBytesLimit() const;
// Recursion Limit -------------------------------------------------
// To prevent corrupt or malicious messages from causing stack overflows,
// we must keep track of the depth of recursion when parsing embedded
// messages and groups. CodedInputStream keeps track of this because it
// is the only object that is passed down the stack during parsing.
// Sets the maximum recursion depth. The default is 100.
void SetRecursionLimit(int limit);
// Increments the current recursion depth. Returns true if the depth is
// under the limit, false if it has gone over.
bool IncrementRecursionDepth();
// Decrements the recursion depth if possible.
void DecrementRecursionDepth();
// Decrements the recursion depth blindly. This is faster than
// DecrementRecursionDepth(). It should be used only if all previous
// increments to recursion depth were successful.
void UnsafeDecrementRecursionDepth();
// Shorthand for make_pair(PushLimit(byte_limit), --recursion_budget_).
// Using this can reduce code size and complexity in some cases. The caller
// is expected to check that the second part of the result is non-negative (to
// bail out if the depth of recursion is too high) and, if all is well, to
// later pass the first part of the result to PopLimit() or similar.
std::pair<CodedInputStream::Limit, int> IncrementRecursionDepthAndPushLimit(
int byte_limit);
// Shorthand for PushLimit(ReadVarint32(&length) ? length : 0).
Limit ReadLengthAndPushLimit();
// Helper that is equivalent to: {
// bool result = ConsumedEntireMessage();
// PopLimit(limit);
// UnsafeDecrementRecursionDepth();
// return result; }
// Using this can reduce code size and complexity in some cases.
// Do not use unless the current recursion depth is greater than zero.
bool DecrementRecursionDepthAndPopLimit(Limit limit);
// Helper that is equivalent to: {
// bool result = ConsumedEntireMessage();
// PopLimit(limit);
// return result; }
// Using this can reduce code size and complexity in some cases.
bool CheckEntireMessageConsumedAndPopLimit(Limit limit);
// Extension Registry ----------------------------------------------
// ADVANCED USAGE: 99.9% of people can ignore this section.
//
// By default, when parsing extensions, the parser looks for extension
// definitions in the pool which owns the outer message's Descriptor.
// However, you may call SetExtensionRegistry() to provide an alternative
// pool instead. This makes it possible, for example, to parse a message
// using a generated class, but represent some extensions using
// DynamicMessage.
// Set the pool used to look up extensions. Most users do not need to call
// this as the correct pool will be chosen automatically.
//
// WARNING: It is very easy to misuse this. Carefully read the requirements
// below. Do not use this unless you are sure you need it. Almost no one
// does.
//
// Let's say you are parsing a message into message object m, and you want
// to take advantage of SetExtensionRegistry(). You must follow these
// requirements:
//
// The given DescriptorPool must contain m->GetDescriptor(). It is not
// sufficient for it to simply contain a descriptor that has the same name
// and content -- it must be the *exact object*. In other words:
// assert(pool->FindMessageTypeByName(m->GetDescriptor()->full_name()) ==
// m->GetDescriptor());
// There are two ways to satisfy this requirement:
// 1) Use m->GetDescriptor()->pool() as the pool. This is generally useless
// because this is the pool that would be used anyway if you didn't call
// SetExtensionRegistry() at all.
// 2) Use a DescriptorPool which has m->GetDescriptor()->pool() as an
// "underlay". Read the documentation for DescriptorPool for more
// information about underlays.
//
// You must also provide a MessageFactory. This factory will be used to
// construct Message objects representing extensions. The factory's
// GetPrototype() MUST return non-NULL for any Descriptor which can be found
// through the provided pool.
//
// If the provided factory might return instances of protocol-compiler-
// generated (i.e. compiled-in) types, or if the outer message object m is
// a generated type, then the given factory MUST have this property: If
// GetPrototype() is given a Descriptor which resides in
// DescriptorPool::generated_pool(), the factory MUST return the same
// prototype which MessageFactory::generated_factory() would return. That
// is, given a descriptor for a generated type, the factory must return an
// instance of the generated class (NOT DynamicMessage). However, when
// given a descriptor for a type that is NOT in generated_pool, the factory
// is free to return any implementation.
//
// The reason for this requirement is that generated sub-objects may be
// accessed via the standard (non-reflection) extension accessor methods,
// and these methods will down-cast the object to the generated class type.
// If the object is not actually of that type, the results would be undefined.
// On the other hand, if an extension is not compiled in, then there is no
// way the code could end up accessing it via the standard accessors -- the
// only way to access the extension is via reflection. When using reflection,
// DynamicMessage and generated messages are indistinguishable, so it's fine
// if these objects are represented using DynamicMessage.
//
// Using DynamicMessageFactory on which you have called
// SetDelegateToGeneratedFactory(true) should be sufficient to satisfy the
// above requirement.
//
// If either pool or factory is NULL, both must be NULL.
//
// Note that this feature is ignored when parsing "lite" messages as they do
// not have descriptors.
void SetExtensionRegistry(const DescriptorPool* pool,
MessageFactory* factory);
// Get the DescriptorPool set via SetExtensionRegistry(), or NULL if no pool
// has been provided.
const DescriptorPool* GetExtensionPool();
// Get the MessageFactory set via SetExtensionRegistry(), or NULL if no
// factory has been provided.
MessageFactory* GetExtensionFactory();
private:
GOOGLE_DISALLOW_EVIL_CONSTRUCTORS(CodedInputStream);
const uint8* buffer_;
const uint8* buffer_end_; // pointer to the end of the buffer.
ZeroCopyInputStream* input_;
int total_bytes_read_; // total bytes read from input_, including
// the current buffer
// If total_bytes_read_ surpasses INT_MAX, we record the extra bytes here
// so that we can BackUp() on destruction.
int overflow_bytes_;
// LastTagWas() stuff.
uint32 last_tag_; // result of last ReadTag() or ReadTagWithCutoff().
// This is set true by ReadTag{Fallback/Slow}() if it is called when exactly
// at EOF, or by ExpectAtEnd() when it returns true. This happens when we
// reach the end of a message and attempt to read another tag.
bool legitimate_message_end_;
// See EnableAliasing().
bool aliasing_enabled_;
// Limits
Limit current_limit_; // if position = -1, no limit is applied
// For simplicity, if the current buffer crosses a limit (either a normal
// limit created by PushLimit() or the total bytes limit), buffer_size_
// only tracks the number of bytes before that limit. This field
// contains the number of bytes after it. Note that this implies that if
// buffer_size_ == 0 and buffer_size_after_limit_ > 0, we know we've
// hit a limit. However, if both are zero, it doesn't necessarily mean
// we aren't at a limit -- the buffer may have ended exactly at the limit.
int buffer_size_after_limit_;
// Maximum number of bytes to read, period. This is unrelated to
// current_limit_. Set using SetTotalBytesLimit().
int total_bytes_limit_;
// Current recursion budget, controlled by IncrementRecursionDepth() and
// similar. Starts at recursion_limit_ and goes down: if this reaches
// -1 we are over budget.
int recursion_budget_;
// Recursion depth limit, set by SetRecursionLimit().
int recursion_limit_;
bool disable_strict_correctness_enforcement_;
// See SetExtensionRegistry().
const DescriptorPool* extension_pool_;
MessageFactory* extension_factory_;
// Private member functions.
// Fallback when Skip() goes past the end of the current buffer.
bool SkipFallback(int count, int original_buffer_size);
// Advance the buffer by a given number of bytes.
void Advance(int amount);
// Back up input_ to the current buffer position.
void BackUpInputToCurrentPosition();
// Recomputes the value of buffer_size_after_limit_. Must be called after
// current_limit_ or total_bytes_limit_ changes.
void RecomputeBufferLimits();
// Writes an error message saying that we hit total_bytes_limit_.
void PrintTotalBytesLimitError();
// Called when the buffer runs out to request more data. Implies an
// Advance(BufferSize()).
bool Refresh();
// When parsing varints, we optimize for the common case of small values, and
// then optimize for the case when the varint fits within the current buffer
// piece. The Fallback method is used when we can't use the one-byte
// optimization. The Slow method is yet another fallback when the buffer is
// not large enough. Making the slow path out-of-line speeds up the common
// case by 10-15%. The slow path is fairly uncommon: it only triggers when a
// message crosses multiple buffers. Note: ReadVarint32Fallback() and
// ReadVarint64Fallback() are called frequently and generally not inlined, so
// they have been optimized to avoid "out" parameters. The former returns -1
// if it fails and the uint32 it read otherwise. The latter has a bool
// indicating success or failure as part of its return type.
int64 ReadVarint32Fallback(uint32 first_byte_or_zero);
int ReadVarintSizeAsIntFallback();
std::pair<uint64, bool> ReadVarint64Fallback();
bool ReadVarint32Slow(uint32* value);
bool ReadVarint64Slow(uint64* value);
int ReadVarintSizeAsIntSlow();
bool ReadLittleEndian32Fallback(uint32* value);
bool ReadLittleEndian64Fallback(uint64* value);
// Fallback/slow methods for reading tags. These do not update last_tag_,
// but will set legitimate_message_end_ if we are at the end of the input
// stream.
uint32 ReadTagFallback(uint32 first_byte_or_zero);
uint32 ReadTagSlow();
bool ReadStringFallback(string* buffer, int size);
// Return the size of the buffer.
int BufferSize() const;
static const int kDefaultTotalBytesLimit = INT_MAX;
static int default_recursion_limit_; // 100 by default.
};
// Class which encodes and writes binary data which is composed of varint-
// encoded integers and fixed-width pieces. Wraps a ZeroCopyOutputStream.
// Most users will not need to deal with CodedOutputStream.
//
// Most methods of CodedOutputStream which return a bool return false if an
// underlying I/O error occurs. Once such a failure occurs, the
// CodedOutputStream is broken and is no longer useful. The Write* methods do
// not return the stream status, but will invalidate the stream if an error
// occurs. The client can probe HadError() to determine the status.
//
// Note that every method of CodedOutputStream which writes some data has
// a corresponding static "ToArray" version. These versions write directly
// to the provided buffer, returning a pointer past the last written byte.
// They require that the buffer has sufficient capacity for the encoded data.
// This allows an optimization where we check if an output stream has enough
// space for an entire message before we start writing and, if there is, we
// call only the ToArray methods to avoid doing bound checks for each
// individual value.
// i.e., in the example above:
//
// CodedOutputStream coded_output = new CodedOutputStream(raw_output);
// int magic_number = 1234;
// char text[] = "Hello world!";
//
// int coded_size = sizeof(magic_number) +
// CodedOutputStream::VarintSize32(strlen(text)) +
// strlen(text);
//
// uint8* buffer =
// coded_output->GetDirectBufferForNBytesAndAdvance(coded_size);
// if (buffer != NULL) {
// // The output stream has enough space in the buffer: write directly to
// // the array.
// buffer = CodedOutputStream::WriteLittleEndian32ToArray(magic_number,
// buffer);
// buffer = CodedOutputStream::WriteVarint32ToArray(strlen(text), buffer);
// buffer = CodedOutputStream::WriteRawToArray(text, strlen(text), buffer);
// } else {
// // Make bound-checked writes, which will ask the underlying stream for
// // more space as needed.
// coded_output->WriteLittleEndian32(magic_number);
// coded_output->WriteVarint32(strlen(text));
// coded_output->WriteRaw(text, strlen(text));
// }
//
// delete coded_output;
class LIBPROTOBUF_EXPORT CodedOutputStream {
public:
// Create an CodedOutputStream that writes to the given ZeroCopyOutputStream.
explicit CodedOutputStream(ZeroCopyOutputStream* output);
CodedOutputStream(ZeroCopyOutputStream* output, bool do_eager_refresh);
// Destroy the CodedOutputStream and position the underlying
// ZeroCopyOutputStream immediately after the last byte written.
~CodedOutputStream();
// Trims any unused space in the underlying buffer so that its size matches
// the number of bytes written by this stream. The underlying buffer will
// automatically be trimmed when this stream is destroyed; this call is only
// necessary if the underlying buffer is accessed *before* the stream is
// destroyed.
void Trim();
// Skips a number of bytes, leaving the bytes unmodified in the underlying
// buffer. Returns false if an underlying write error occurs. This is
// mainly useful with GetDirectBufferPointer().
bool Skip(int count);
// Sets *data to point directly at the unwritten part of the
// CodedOutputStream's underlying buffer, and *size to the size of that
// buffer, but does not advance the stream's current position. This will
// always either produce a non-empty buffer or return false. If the caller
// writes any data to this buffer, it should then call Skip() to skip over
// the consumed bytes. This may be useful for implementing external fast
// serialization routines for types of data not covered by the
// CodedOutputStream interface.
bool GetDirectBufferPointer(void** data, int* size);
// If there are at least "size" bytes available in the current buffer,
// returns a pointer directly into the buffer and advances over these bytes.
// The caller may then write directly into this buffer (e.g. using the
// *ToArray static methods) rather than go through CodedOutputStream. If
// there are not enough bytes available, returns NULL. The return pointer is
// invalidated as soon as any other non-const method of CodedOutputStream
// is called.
inline uint8* GetDirectBufferForNBytesAndAdvance(int size);
// Write raw bytes, copying them from the given buffer.
void WriteRaw(const void* buffer, int size);
// Like WriteRaw() but will try to write aliased data if aliasing is
// turned on.
void WriteRawMaybeAliased(const void* data, int size);
// Like WriteRaw() but writing directly to the target array.
// This is _not_ inlined, as the compiler often optimizes memcpy into inline
// copy loops. Since this gets called by every field with string or bytes
// type, inlining may lead to a significant amount of code bloat, with only a
// minor performance gain.
static uint8* WriteRawToArray(const void* buffer, int size, uint8* target);
// Equivalent to WriteRaw(str.data(), str.size()).
void WriteString(const string& str);
// Like WriteString() but writing directly to the target array.
static uint8* WriteStringToArray(const string& str, uint8* target);
// Write the varint-encoded size of str followed by str.
static uint8* WriteStringWithSizeToArray(const string& str, uint8* target);
// Instructs the CodedOutputStream to allow the underlying
// ZeroCopyOutputStream to hold pointers to the original structure instead of
// copying, if it supports it (i.e. output->AllowsAliasing() is true). If the
// underlying stream does not support aliasing, then enabling it has no
// affect. For now, this only affects the behavior of
// WriteRawMaybeAliased().
//
// NOTE: It is caller's responsibility to ensure that the chunk of memory
// remains live until all of the data has been consumed from the stream.
void EnableAliasing(bool enabled);
// Write a 32-bit little-endian integer.
void WriteLittleEndian32(uint32 value);
// Like WriteLittleEndian32() but writing directly to the target array.
static uint8* WriteLittleEndian32ToArray(uint32 value, uint8* target);
// Write a 64-bit little-endian integer.
void WriteLittleEndian64(uint64 value);
// Like WriteLittleEndian64() but writing directly to the target array.
static uint8* WriteLittleEndian64ToArray(uint64 value, uint8* target);
// Write an unsigned integer with Varint encoding. Writing a 32-bit value
// is equivalent to casting it to uint64 and writing it as a 64-bit value,
// but may be more efficient.
void WriteVarint32(uint32 value);
// Like WriteVarint32() but writing directly to the target array.
static uint8* WriteVarint32ToArray(uint32 value, uint8* target);
// Write an unsigned integer with Varint encoding.
void WriteVarint64(uint64 value);
// Like WriteVarint64() but writing directly to the target array.
static uint8* WriteVarint64ToArray(uint64 value, uint8* target);
// Equivalent to WriteVarint32() except when the value is negative,
// in which case it must be sign-extended to a full 10 bytes.
void WriteVarint32SignExtended(int32 value);
// Like WriteVarint32SignExtended() but writing directly to the target array.
static uint8* WriteVarint32SignExtendedToArray(int32 value, uint8* target);
// This is identical to WriteVarint32(), but optimized for writing tags.
// In particular, if the input is a compile-time constant, this method
// compiles down to a couple instructions.
// Always inline because otherwise the aformentioned optimization can't work,
// but GCC by default doesn't want to inline this.
void WriteTag(uint32 value);
// Like WriteTag() but writing directly to the target array.
GOOGLE_PROTOBUF_ATTRIBUTE_ALWAYS_INLINE
static uint8* WriteTagToArray(uint32 value, uint8* target);
// Returns the number of bytes needed to encode the given value as a varint.
static size_t VarintSize32(uint32 value);
// Returns the number of bytes needed to encode the given value as a varint.
static size_t VarintSize64(uint64 value);
// If negative, 10 bytes. Otheriwse, same as VarintSize32().
static size_t VarintSize32SignExtended(int32 value);
// Compile-time equivalent of VarintSize32().
template <uint32 Value>
struct StaticVarintSize32 {
static const size_t value =
(Value < (1 << 7))
? 1
: (Value < (1 << 14))
? 2
: (Value < (1 << 21))
? 3
: (Value < (1 << 28))
? 4
: 5;
};
// Returns the total number of bytes written since this object was created.
inline int ByteCount() const;
// Returns true if there was an underlying I/O error since this object was
// created.
bool HadError() const { return had_error_; }
// Deterministic serialization, if requested, guarantees that for a given
// binary, equal messages will always be serialized to the same bytes. This
// implies:
// . repeated serialization of a message will return the same bytes
// . different processes of the same binary (which may be executing on
// different machines) will serialize equal messages to the same bytes.
//
// Note the deterministic serialization is NOT canonical across languages; it
// is also unstable across different builds with schema changes due to unknown
// fields. Users who need canonical serialization, e.g., persistent storage in
// a canonical form, fingerprinting, etc., should define their own
// canonicalization specification and implement the serializer using
// reflection APIs rather than relying on this API.
//
// If determinisitc serialization is requested, the serializer will
// sort map entries by keys in lexicographical order or numerical order.
// (This is an implementation detail and may subject to change.)
//
// There are two ways to determine whether serialization should be
// deterministic for this CodedOutputStream. If SetSerializationDeterministic
// has not yet been called, then the default comes from the global default,
// which is false, until SetDefaultSerializationDeterministic has been called.
// Otherwise, SetSerializationDeterministic has been called, and the last
// value passed to it is all that matters.
void SetSerializationDeterministic(bool value) {
serialization_deterministic_is_overridden_ = true;
serialization_deterministic_override_ = value;
}
// See above. Also, note that users of this CodedOutputStream may need to
// call IsSerializationDeterministic() to serialize in the intended way. This
// CodedOutputStream cannot enforce a desire for deterministic serialization
// by itself.
bool IsSerializationDeterministic() const {
return serialization_deterministic_is_overridden_ ?
serialization_deterministic_override_ :
IsDefaultSerializationDeterministic();
}
static bool IsDefaultSerializationDeterministic() {
return google::protobuf::internal::NoBarrier_Load(&default_serialization_deterministic_);
}
private:
GOOGLE_DISALLOW_EVIL_CONSTRUCTORS(CodedOutputStream);
ZeroCopyOutputStream* output_;
uint8* buffer_;
int buffer_size_;
int total_bytes_; // Sum of sizes of all buffers seen so far.
bool had_error_; // Whether an error occurred during output.
bool aliasing_enabled_; // See EnableAliasing().
// See SetSerializationDeterministic() regarding these three fields.
bool serialization_deterministic_is_overridden_;
bool serialization_deterministic_override_;
// Conceptually, default_serialization_deterministic_ is an atomic bool.
// TODO(haberman): replace with std::atomic<bool> when we move to C++11.
static google::protobuf::internal::AtomicWord default_serialization_deterministic_;
// Advance the buffer by a given number of bytes.
void Advance(int amount);
// Called when the buffer runs out to request more data. Implies an
// Advance(buffer_size_).
bool Refresh();
// Like WriteRaw() but may avoid copying if the underlying
// ZeroCopyOutputStream supports it.
void WriteAliasedRaw(const void* buffer, int size);
// If this write might cross the end of the buffer, we compose the bytes first
// then use WriteRaw().
void WriteVarint32SlowPath(uint32 value);
void WriteVarint64SlowPath(uint64 value);
// See above. Other projects may use "friend" to allow them to call this.
// After SetDefaultSerializationDeterministic() completes, all protocol
// buffer serializations will be deterministic by default. Thread safe.
// However, the meaning of "after" is subtle here: to be safe, each thread
// that wants deterministic serialization by default needs to call
// SetDefaultSerializationDeterministic() or ensure on its own that another
// thread has done so.
friend void ::google::protobuf::internal::MapTestForceDeterministic();
static void SetDefaultSerializationDeterministic() {
google::protobuf::internal::NoBarrier_Store(&default_serialization_deterministic_, 1);
}
};
// inline methods ====================================================
// The vast majority of varints are only one byte. These inline
// methods optimize for that case.
inline bool CodedInputStream::ReadVarint32(uint32* value) {
uint32 v = 0;
if (GOOGLE_PREDICT_TRUE(buffer_ < buffer_end_)) {
v = *buffer_;
if (v < 0x80) {
*value = v;
Advance(1);
return true;
}
}
int64 result = ReadVarint32Fallback(v);
*value = static_cast<uint32>(result);
return result >= 0;
}
inline bool CodedInputStream::ReadVarint64(uint64* value) {
if (GOOGLE_PREDICT_TRUE(buffer_ < buffer_end_) && *buffer_ < 0x80) {
*value = *buffer_;
Advance(1);
return true;
}
std::pair<uint64, bool> p = ReadVarint64Fallback();
*value = p.first;
return p.second;
}
inline bool CodedInputStream::ReadVarintSizeAsInt(int* value) {
if (GOOGLE_PREDICT_TRUE(buffer_ < buffer_end_)) {
int v = *buffer_;
if (v < 0x80) {
*value = v;
Advance(1);
return true;
}
}
*value = ReadVarintSizeAsIntFallback();
return *value >= 0;
}
// static
inline const uint8* CodedInputStream::ReadLittleEndian32FromArray(
const uint8* buffer,
uint32* value) {
#if defined(PROTOBUF_LITTLE_ENDIAN)
memcpy(value, buffer, sizeof(*value));
return buffer + sizeof(*value);
#else
*value = (static_cast<uint32>(buffer[0]) ) |
(static_cast<uint32>(buffer[1]) << 8) |
(static_cast<uint32>(buffer[2]) << 16) |
(static_cast<uint32>(buffer[3]) << 24);
return buffer + sizeof(*value);
#endif
}
// static
inline const uint8* CodedInputStream::ReadLittleEndian64FromArray(
const uint8* buffer,
uint64* value) {
#if defined(PROTOBUF_LITTLE_ENDIAN)
memcpy(value, buffer, sizeof(*value));
return buffer + sizeof(*value);
#else
uint32 part0 = (static_cast<uint32>(buffer[0]) ) |
(static_cast<uint32>(buffer[1]) << 8) |
(static_cast<uint32>(buffer[2]) << 16) |
(static_cast<uint32>(buffer[3]) << 24);
uint32 part1 = (static_cast<uint32>(buffer[4]) ) |
(static_cast<uint32>(buffer[5]) << 8) |
(static_cast<uint32>(buffer[6]) << 16) |
(static_cast<uint32>(buffer[7]) << 24);
*value = static_cast<uint64>(part0) |
(static_cast<uint64>(part1) << 32);
return buffer + sizeof(*value);
#endif
}
inline bool CodedInputStream::ReadLittleEndian32(uint32* value) {
#if defined(PROTOBUF_LITTLE_ENDIAN)
if (GOOGLE_PREDICT_TRUE(BufferSize() >= static_cast<int>(sizeof(*value)))) {
buffer_ = ReadLittleEndian32FromArray(buffer_, value);
return true;
} else {
return ReadLittleEndian32Fallback(value);
}
#else
return ReadLittleEndian32Fallback(value);
#endif
}
inline bool CodedInputStream::ReadLittleEndian64(uint64* value) {
#if defined(PROTOBUF_LITTLE_ENDIAN)
if (GOOGLE_PREDICT_TRUE(BufferSize() >= static_cast<int>(sizeof(*value)))) {
buffer_ = ReadLittleEndian64FromArray(buffer_, value);
return true;
} else {
return ReadLittleEndian64Fallback(value);
}
#else
return ReadLittleEndian64Fallback(value);
#endif
}
inline uint32 CodedInputStream::ReadTagNoLastTag() {
uint32 v = 0;
if (GOOGLE_PREDICT_TRUE(buffer_ < buffer_end_)) {
v = *buffer_;
if (v < 0x80) {
Advance(1);
return v;
}
}
v = ReadTagFallback(v);
return v;
}
inline std::pair<uint32, bool> CodedInputStream::ReadTagWithCutoffNoLastTag(
uint32 cutoff) {
// In performance-sensitive code we can expect cutoff to be a compile-time
// constant, and things like "cutoff >= kMax1ByteVarint" to be evaluated at
// compile time.
uint32 first_byte_or_zero = 0;
if (GOOGLE_PREDICT_TRUE(buffer_ < buffer_end_)) {
// Hot case: buffer_ non_empty, buffer_[0] in [1, 128).
// TODO(gpike): Is it worth rearranging this? E.g., if the number of fields
// is large enough then is it better to check for the two-byte case first?
first_byte_or_zero = buffer_[0];
if (static_cast<int8>(buffer_[0]) > 0) {
const uint32 kMax1ByteVarint = 0x7f;
uint32 tag = buffer_[0];
Advance(1);
return std::make_pair(tag, cutoff >= kMax1ByteVarint || tag <= cutoff);
}
// Other hot case: cutoff >= 0x80, buffer_ has at least two bytes available,
// and tag is two bytes. The latter is tested by bitwise-and-not of the
// first byte and the second byte.
if (cutoff >= 0x80 &&
GOOGLE_PREDICT_TRUE(buffer_ + 1 < buffer_end_) &&
GOOGLE_PREDICT_TRUE((buffer_[0] & ~buffer_[1]) >= 0x80)) {
const uint32 kMax2ByteVarint = (0x7f << 7) + 0x7f;
uint32 tag = (1u << 7) * buffer_[1] + (buffer_[0] - 0x80);
Advance(2);
// It might make sense to test for tag == 0 now, but it is so rare that
// that we don't bother. A varint-encoded 0 should be one byte unless
// the encoder lost its mind. The second part of the return value of
// this function is allowed to be either true or false if the tag is 0,
// so we don't have to check for tag == 0. We may need to check whether
// it exceeds cutoff.
bool at_or_below_cutoff = cutoff >= kMax2ByteVarint || tag <= cutoff;
return std::make_pair(tag, at_or_below_cutoff);
}
}
// Slow path
const uint32 tag = ReadTagFallback(first_byte_or_zero);
return std::make_pair(tag, static_cast<uint32>(tag - 1) < cutoff);
}
inline bool CodedInputStream::LastTagWas(uint32 expected) {
return last_tag_ == expected;
}
inline bool CodedInputStream::ConsumedEntireMessage() {
return legitimate_message_end_;
}
inline bool CodedInputStream::ExpectTag(uint32 expected) {
if (expected < (1 << 7)) {
if (GOOGLE_PREDICT_TRUE(buffer_ < buffer_end_) && buffer_[0] == expected) {
Advance(1);
return true;
} else {
return false;
}
} else if (expected < (1 << 14)) {
if (GOOGLE_PREDICT_TRUE(BufferSize() >= 2) &&
buffer_[0] == static_cast<uint8>(expected | 0x80) &&
buffer_[1] == static_cast<uint8>(expected >> 7)) {
Advance(2);
return true;
} else {
return false;
}
} else {
// Don't bother optimizing for larger values.
return false;
}
}
inline const uint8* CodedInputStream::ExpectTagFromArray(
const uint8* buffer, uint32 expected) {
if (expected < (1 << 7)) {
if (buffer[0] == expected) {
return buffer + 1;
}
} else if (expected < (1 << 14)) {
if (buffer[0] == static_cast<uint8>(expected | 0x80) &&
buffer[1] == static_cast<uint8>(expected >> 7)) {
return buffer + 2;
}
}
return NULL;
}
inline void CodedInputStream::GetDirectBufferPointerInline(const void** data,
int* size) {
*data = buffer_;
*size = static_cast<int>(buffer_end_ - buffer_);
}
inline bool CodedInputStream::ExpectAtEnd() {
// If we are at a limit we know no more bytes can be read. Otherwise, it's
// hard to say without calling Refresh(), and we'd rather not do that.
if (buffer_ == buffer_end_ &&
((buffer_size_after_limit_ != 0) ||
(total_bytes_read_ == current_limit_))) {
last_tag_ = 0; // Pretend we called ReadTag()...
legitimate_message_end_ = true; // ... and it hit EOF.
return true;
} else {
return false;
}
}
inline int CodedInputStream::CurrentPosition() const {
return total_bytes_read_ - (BufferSize() + buffer_size_after_limit_);
}
inline uint8* CodedOutputStream::GetDirectBufferForNBytesAndAdvance(int size) {
if (buffer_size_ < size) {
return NULL;
} else {
uint8* result = buffer_;
Advance(size);
return result;
}
}
inline uint8* CodedOutputStream::WriteVarint32ToArray(uint32 value,
uint8* target) {
while (value >= 0x80) {
*target = static_cast<uint8>(value | 0x80);
value >>= 7;
++target;
}
*target = static_cast<uint8>(value);
return target + 1;
}
inline uint8* CodedOutputStream::WriteVarint64ToArray(uint64 value,
uint8* target) {
while (value >= 0x80) {
*target = static_cast<uint8>(value | 0x80);
value >>= 7;
++target;
}
*target = static_cast<uint8>(value);
return target + 1;
}
inline void CodedOutputStream::WriteVarint32SignExtended(int32 value) {
WriteVarint64(static_cast<uint64>(value));
}
inline uint8* CodedOutputStream::WriteVarint32SignExtendedToArray(
int32 value, uint8* target) {
return WriteVarint64ToArray(static_cast<uint64>(value), target);
}
inline uint8* CodedOutputStream::WriteLittleEndian32ToArray(uint32 value,
uint8* target) {
#if defined(PROTOBUF_LITTLE_ENDIAN)
memcpy(target, &value, sizeof(value));
#else
target[0] = static_cast<uint8>(value);
target[1] = static_cast<uint8>(value >> 8);
target[2] = static_cast<uint8>(value >> 16);
target[3] = static_cast<uint8>(value >> 24);
#endif
return target + sizeof(value);
}
inline uint8* CodedOutputStream::WriteLittleEndian64ToArray(uint64 value,
uint8* target) {
#if defined(PROTOBUF_LITTLE_ENDIAN)
memcpy(target, &value, sizeof(value));
#else
uint32 part0 = static_cast<uint32>(value);
uint32 part1 = static_cast<uint32>(value >> 32);
target[0] = static_cast<uint8>(part0);
target[1] = static_cast<uint8>(part0 >> 8);
target[2] = static_cast<uint8>(part0 >> 16);
target[3] = static_cast<uint8>(part0 >> 24);
target[4] = static_cast<uint8>(part1);
target[5] = static_cast<uint8>(part1 >> 8);
target[6] = static_cast<uint8>(part1 >> 16);
target[7] = static_cast<uint8>(part1 >> 24);
#endif
return target + sizeof(value);
}
inline void CodedOutputStream::WriteVarint32(uint32 value) {
if (buffer_size_ >= 5) {
// Fast path: We have enough bytes left in the buffer to guarantee that
// this write won't cross the end, so we can skip the checks.
uint8* target = buffer_;
uint8* end = WriteVarint32ToArray(value, target);
int size = static_cast<int>(end - target);
Advance(size);
} else {
WriteVarint32SlowPath(value);
}
}
inline void CodedOutputStream::WriteVarint64(uint64 value) {
if (buffer_size_ >= 10) {
// Fast path: We have enough bytes left in the buffer to guarantee that
// this write won't cross the end, so we can skip the checks.
uint8* target = buffer_;
uint8* end = WriteVarint64ToArray(value, target);
int size = static_cast<int>(end - target);
Advance(size);
} else {
WriteVarint64SlowPath(value);
}
}
inline void CodedOutputStream::WriteTag(uint32 value) {
WriteVarint32(value);
}
inline uint8* CodedOutputStream::WriteTagToArray(
uint32 value, uint8* target) {
return WriteVarint32ToArray(value, target);
}
inline size_t CodedOutputStream::VarintSize32(uint32 value) {
// This computes value == 0 ? 1 : floor(log2(value)) / 7 + 1
// Use an explicit multiplication to implement the divide of
// a number in the 1..31 range.
// Explicit OR 0x1 to avoid calling Bits::Log2FloorNonZero(0), which is
// undefined.
uint32 log2value = Bits::Log2FloorNonZero(value | 0x1);
return static_cast<size_t>((log2value * 9 + 73) / 64);
}
inline size_t CodedOutputStream::VarintSize64(uint64 value) {
// This computes value == 0 ? 1 : floor(log2(value)) / 7 + 1
// Use an explicit multiplication to implement the divide of
// a number in the 1..63 range.
// Explicit OR 0x1 to avoid calling Bits::Log2FloorNonZero(0), which is
// undefined.
uint32 log2value = Bits::Log2FloorNonZero64(value | 0x1);
return static_cast<size_t>((log2value * 9 + 73) / 64);
}
inline size_t CodedOutputStream::VarintSize32SignExtended(int32 value) {
if (value < 0) {
return 10; // TODO(kenton): Make this a symbolic constant.
} else {
return VarintSize32(static_cast<uint32>(value));
}
}
inline void CodedOutputStream::WriteString(const string& str) {
WriteRaw(str.data(), static_cast<int>(str.size()));
}
inline void CodedOutputStream::WriteRawMaybeAliased(
const void* data, int size) {
if (aliasing_enabled_) {
WriteAliasedRaw(data, size);
} else {
WriteRaw(data, size);
}
}
inline uint8* CodedOutputStream::WriteStringToArray(
const string& str, uint8* target) {
return WriteRawToArray(str.data(), static_cast<int>(str.size()), target);
}
inline int CodedOutputStream::ByteCount() const {
return total_bytes_ - buffer_size_;
}
inline void CodedInputStream::Advance(int amount) {
buffer_ += amount;
}
inline void CodedOutputStream::Advance(int amount) {
buffer_ += amount;
buffer_size_ -= amount;
}
inline void CodedInputStream::SetRecursionLimit(int limit) {
recursion_budget_ += limit - recursion_limit_;
recursion_limit_ = limit;
}
inline bool CodedInputStream::IncrementRecursionDepth() {
--recursion_budget_;
return recursion_budget_ >= 0;
}
inline void CodedInputStream::DecrementRecursionDepth() {
if (recursion_budget_ < recursion_limit_) ++recursion_budget_;
}
inline void CodedInputStream::UnsafeDecrementRecursionDepth() {
assert(recursion_budget_ < recursion_limit_);
++recursion_budget_;
}
inline void CodedInputStream::SetExtensionRegistry(const DescriptorPool* pool,
MessageFactory* factory) {
extension_pool_ = pool;
extension_factory_ = factory;
}
inline const DescriptorPool* CodedInputStream::GetExtensionPool() {
return extension_pool_;
}
inline MessageFactory* CodedInputStream::GetExtensionFactory() {
return extension_factory_;
}
inline int CodedInputStream::BufferSize() const {
return static_cast<int>(buffer_end_ - buffer_);
}
inline CodedInputStream::CodedInputStream(ZeroCopyInputStream* input)
: buffer_(NULL),
buffer_end_(NULL),
input_(input),
total_bytes_read_(0),
overflow_bytes_(0),
last_tag_(0),
legitimate_message_end_(false),
aliasing_enabled_(false),
current_limit_(kint32max),
buffer_size_after_limit_(0),
total_bytes_limit_(kDefaultTotalBytesLimit),
recursion_budget_(default_recursion_limit_),
recursion_limit_(default_recursion_limit_),
disable_strict_correctness_enforcement_(true),
extension_pool_(NULL),
extension_factory_(NULL) {
// Eagerly Refresh() so buffer space is immediately available.
Refresh();
}
inline CodedInputStream::CodedInputStream(const uint8* buffer, int size)
: buffer_(buffer),
buffer_end_(buffer + size),
input_(NULL),
total_bytes_read_(size),
overflow_bytes_(0),
last_tag_(0),
legitimate_message_end_(false),
aliasing_enabled_(false),
current_limit_(size),
buffer_size_after_limit_(0),
total_bytes_limit_(kDefaultTotalBytesLimit),
recursion_budget_(default_recursion_limit_),
recursion_limit_(default_recursion_limit_),
disable_strict_correctness_enforcement_(true),
extension_pool_(NULL),
extension_factory_(NULL) {
// Note that setting current_limit_ == size is important to prevent some
// code paths from trying to access input_ and segfaulting.
}
inline bool CodedInputStream::IsFlat() const {
return input_ == NULL;
}
inline bool CodedInputStream::Skip(int count) {
if (count < 0) return false; // security: count is often user-supplied
const int original_buffer_size = BufferSize();
if (count <= original_buffer_size) {
// Just skipping within the current buffer. Easy.
Advance(count);
return true;
}
return SkipFallback(count, original_buffer_size);
}
} // namespace io
} // namespace protobuf
#if defined(_MSC_VER) && _MSC_VER >= 1300 && !defined(__INTEL_COMPILER)
#pragma runtime_checks("c", restore)
#endif // _MSC_VER && !defined(__INTEL_COMPILER)
} // namespace google
#endif // GOOGLE_PROTOBUF_IO_CODED_STREAM_H__
|