This file is indexed.

/usr/include/clang/Lex/Preprocessor.h is in libclang-dev 3.0-6ubuntu3.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

   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
//===--- Preprocessor.h - C Language Family Preprocessor --------*- C++ -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
//  This file defines the Preprocessor interface.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_CLANG_LEX_PREPROCESSOR_H
#define LLVM_CLANG_LEX_PREPROCESSOR_H

#include "clang/Lex/MacroInfo.h"
#include "clang/Lex/Lexer.h"
#include "clang/Lex/PTHLexer.h"
#include "clang/Lex/PPCallbacks.h"
#include "clang/Lex/TokenLexer.h"
#include "clang/Lex/PTHManager.h"
#include "clang/Basic/Builtins.h"
#include "clang/Basic/Diagnostic.h"
#include "clang/Basic/IdentifierTable.h"
#include "clang/Basic/SourceLocation.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/IntrusiveRefCntPtr.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/OwningPtr.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/Support/Allocator.h"
#include <vector>

namespace clang {

class SourceManager;
class ExternalPreprocessorSource;
class FileManager;
class FileEntry;
class HeaderSearch;
class PragmaNamespace;
class PragmaHandler;
class CommentHandler;
class ScratchBuffer;
class TargetInfo;
class PPCallbacks;
class CodeCompletionHandler;
class DirectoryLookup;
class PreprocessingRecord;
class ModuleLoader;
  
/// Preprocessor - This object engages in a tight little dance with the lexer to
/// efficiently preprocess tokens.  Lexers know only about tokens within a
/// single source file, and don't know anything about preprocessor-level issues
/// like the #include stack, token expansion, etc.
///
class Preprocessor : public llvm::RefCountedBase<Preprocessor> {
  DiagnosticsEngine        *Diags;
  LangOptions       &Features;
  const TargetInfo  *Target;
  FileManager       &FileMgr;
  SourceManager     &SourceMgr;
  ScratchBuffer     *ScratchBuf;
  HeaderSearch      &HeaderInfo;
  ModuleLoader      &TheModuleLoader;

  /// \brief External source of macros.
  ExternalPreprocessorSource *ExternalSource;

  
  /// PTH - An optional PTHManager object used for getting tokens from
  ///  a token cache rather than lexing the original source file.
  llvm::OwningPtr<PTHManager> PTH;

  /// BP - A BumpPtrAllocator object used to quickly allocate and release
  ///  objects internal to the Preprocessor.
  llvm::BumpPtrAllocator BP;

  /// Identifiers for builtin macros and other builtins.
  IdentifierInfo *Ident__LINE__, *Ident__FILE__;   // __LINE__, __FILE__
  IdentifierInfo *Ident__DATE__, *Ident__TIME__;   // __DATE__, __TIME__
  IdentifierInfo *Ident__INCLUDE_LEVEL__;          // __INCLUDE_LEVEL__
  IdentifierInfo *Ident__BASE_FILE__;              // __BASE_FILE__
  IdentifierInfo *Ident__TIMESTAMP__;              // __TIMESTAMP__
  IdentifierInfo *Ident__COUNTER__;                // __COUNTER__
  IdentifierInfo *Ident_Pragma, *Ident__pragma;    // _Pragma, __pragma
  IdentifierInfo *Ident__VA_ARGS__;                // __VA_ARGS__
  IdentifierInfo *Ident__has_feature;              // __has_feature
  IdentifierInfo *Ident__has_extension;            // __has_extension
  IdentifierInfo *Ident__has_builtin;              // __has_builtin
  IdentifierInfo *Ident__has_attribute;            // __has_attribute
  IdentifierInfo *Ident__has_include;              // __has_include
  IdentifierInfo *Ident__has_include_next;         // __has_include_next
  IdentifierInfo *Ident__has_warning;              // __has_warning

  SourceLocation DATELoc, TIMELoc;
  unsigned CounterValue;  // Next __COUNTER__ value.

  enum {
    /// MaxIncludeStackDepth - Maximum depth of #includes.
    MaxAllowedIncludeStackDepth = 200
  };

  // State that is set before the preprocessor begins.
  bool KeepComments : 1;
  bool KeepMacroComments : 1;
  bool SuppressIncludeNotFoundError : 1;
  bool AutoModuleImport : 1;
  
  // State that changes while the preprocessor runs:
  bool InMacroArgs : 1;            // True if parsing fn macro invocation args.

  /// Whether the preprocessor owns the header search object.
  bool OwnsHeaderSearch : 1;

  /// DisableMacroExpansion - True if macro expansion is disabled.
  bool DisableMacroExpansion : 1;

  /// \brief Whether we have already loaded macros from the external source.
  mutable bool ReadMacrosFromExternalSource : 1;

  /// Identifiers - This is mapping/lookup information for all identifiers in
  /// the program, including program keywords.
  mutable IdentifierTable Identifiers;

  /// Selectors - This table contains all the selectors in the program. Unlike
  /// IdentifierTable above, this table *isn't* populated by the preprocessor.
  /// It is declared/expanded here because it's role/lifetime is
  /// conceptually similar the IdentifierTable. In addition, the current control
  /// flow (in clang::ParseAST()), make it convenient to put here.
  /// FIXME: Make sure the lifetime of Identifiers/Selectors *isn't* tied to
  /// the lifetime of the preprocessor.
  SelectorTable Selectors;

  /// BuiltinInfo - Information about builtins.
  Builtin::Context BuiltinInfo;

  /// PragmaHandlers - This tracks all of the pragmas that the client registered
  /// with this preprocessor.
  PragmaNamespace *PragmaHandlers;

  /// \brief Tracks all of the comment handlers that the client registered
  /// with this preprocessor.
  std::vector<CommentHandler *> CommentHandlers;

  /// \brief The code-completion handler.
  CodeCompletionHandler *CodeComplete;
  
  /// \brief The file that we're performing code-completion for, if any.
  const FileEntry *CodeCompletionFile;

  /// \brief The offset in file for the code-completion point.
  unsigned CodeCompletionOffset;

  /// \brief The location for the code-completion point. This gets instantiated
  /// when the CodeCompletionFile gets #include'ed for preprocessing.
  SourceLocation CodeCompletionLoc;

  /// \brief The start location for the file of the code-completion point.
  /// This gets instantiated when the CodeCompletionFile gets #include'ed
  /// for preprocessing.
  SourceLocation CodeCompletionFileLoc;

  /// \brief The source location of the __import_module__ keyword we just
  /// lexed, if any.
  SourceLocation ModuleImportLoc;

  /// \brief The source location of the currently-active
  /// #pragma clang arc_cf_code_audited begin.
  SourceLocation PragmaARCCFCodeAuditedLoc;
  
  /// \brief True if we hit the code-completion point.
  bool CodeCompletionReached;

  /// \brief The number of bytes that we will initially skip when entering the
  /// main file, which is used when loading a precompiled preamble, along
  /// with a flag that indicates whether skipping this number of bytes will
  /// place the lexer at the start of a line.
  std::pair<unsigned, bool> SkipMainFilePreamble;
  
  /// CurLexer - This is the current top of the stack that we're lexing from if
  /// not expanding a macro and we are lexing directly from source code.
  ///  Only one of CurLexer, CurPTHLexer, or CurTokenLexer will be non-null.
  llvm::OwningPtr<Lexer> CurLexer;

  /// CurPTHLexer - This is the current top of stack that we're lexing from if
  ///  not expanding from a macro and we are lexing from a PTH cache.
  ///  Only one of CurLexer, CurPTHLexer, or CurTokenLexer will be non-null.
  llvm::OwningPtr<PTHLexer> CurPTHLexer;

  /// CurPPLexer - This is the current top of the stack what we're lexing from
  ///  if not expanding a macro.  This is an alias for either CurLexer or
  ///  CurPTHLexer.
  PreprocessorLexer *CurPPLexer;
    
  /// CurLookup - The DirectoryLookup structure used to find the current
  /// FileEntry, if CurLexer is non-null and if applicable.  This allows us to
  /// implement #include_next and find directory-specific properties.
  const DirectoryLookup *CurDirLookup;

  /// CurTokenLexer - This is the current macro we are expanding, if we are
  /// expanding a macro.  One of CurLexer and CurTokenLexer must be null.
  llvm::OwningPtr<TokenLexer> CurTokenLexer;

  /// \brief The kind of lexer we're currently working with.
  enum CurLexerKind { 
    CLK_Lexer, 
    CLK_PTHLexer, 
    CLK_TokenLexer, 
    CLK_CachingLexer,
    CLK_LexAfterModuleImport
  } CurLexerKind;

  /// IncludeMacroStack - This keeps track of the stack of files currently
  /// #included, and macros currently being expanded from, not counting
  /// CurLexer/CurTokenLexer.
  struct IncludeStackInfo {
    enum CurLexerKind     CurLexerKind;
    Lexer                 *TheLexer;
    PTHLexer              *ThePTHLexer;
    PreprocessorLexer     *ThePPLexer;
    TokenLexer            *TheTokenLexer;
    const DirectoryLookup *TheDirLookup;

    IncludeStackInfo(enum CurLexerKind K, Lexer *L, PTHLexer* P, 
                     PreprocessorLexer* PPL,
                     TokenLexer* TL, const DirectoryLookup *D)
      : CurLexerKind(K), TheLexer(L), ThePTHLexer(P), ThePPLexer(PPL), 
        TheTokenLexer(TL), TheDirLookup(D) {}
  };
  std::vector<IncludeStackInfo> IncludeMacroStack;

  /// Callbacks - These are actions invoked when some preprocessor activity is
  /// encountered (e.g. a file is #included, etc).
  PPCallbacks *Callbacks;

  /// Macros - For each IdentifierInfo with 'HasMacro' set, we keep a mapping
  /// to the actual definition of the macro.
  llvm::DenseMap<IdentifierInfo*, MacroInfo*> Macros;

  /// \brief Macros that we want to warn because they are not used at the end
  /// of the translation unit; we store just their SourceLocations instead
  /// something like MacroInfo*. The benefit of this is that when we are
  /// deserializing from PCH, we don't need to deserialize identifier & macros
  /// just so that we can report that they are unused, we just warn using
  /// the SourceLocations of this set (that will be filled by the ASTReader).
  /// We are using SmallPtrSet instead of a vector for faster removal.
  typedef llvm::SmallPtrSet<SourceLocation, 32> WarnUnusedMacroLocsTy;
  WarnUnusedMacroLocsTy WarnUnusedMacroLocs;

  /// MacroArgCache - This is a "freelist" of MacroArg objects that can be
  /// reused for quick allocation.
  MacroArgs *MacroArgCache;
  friend class MacroArgs;
 
  /// PragmaPushMacroInfo - For each IdentifierInfo used in a #pragma 
  /// push_macro directive, we keep a MacroInfo stack used to restore 
  /// previous macro value.
  llvm::DenseMap<IdentifierInfo*, std::vector<MacroInfo*> > PragmaPushMacroInfo;

  // Various statistics we track for performance analysis.
  unsigned NumDirectives, NumIncluded, NumDefined, NumUndefined, NumPragma;
  unsigned NumIf, NumElse, NumEndif;
  unsigned NumEnteredSourceFiles, MaxIncludeStackDepth;
  unsigned NumMacroExpanded, NumFnMacroExpanded, NumBuiltinMacroExpanded;
  unsigned NumFastMacroExpanded, NumTokenPaste, NumFastTokenPaste;
  unsigned NumSkipped;

  /// Predefines - This string is the predefined macros that preprocessor
  /// should use from the command line etc.
  std::string Predefines;

  /// TokenLexerCache - Cache macro expanders to reduce malloc traffic.
  enum { TokenLexerCacheSize = 8 };
  unsigned NumCachedTokenLexers;
  TokenLexer *TokenLexerCache[TokenLexerCacheSize];

  /// \brief Keeps macro expanded tokens for TokenLexers.
  //
  /// Works like a stack; a TokenLexer adds the macro expanded tokens that is
  /// going to lex in the cache and when it finishes the tokens are removed
  /// from the end of the cache.
  SmallVector<Token, 16> MacroExpandedTokens;
  std::vector<std::pair<TokenLexer *, size_t> > MacroExpandingLexersStack;

  /// \brief A record of the macro definitions and expansions that
  /// occurred during preprocessing. 
  ///
  /// This is an optional side structure that can be enabled with
  /// \c createPreprocessingRecord() prior to preprocessing.
  PreprocessingRecord *Record;
  
private:  // Cached tokens state.
  typedef SmallVector<Token, 1> CachedTokensTy;

  /// CachedTokens - Cached tokens are stored here when we do backtracking or
  /// lookahead. They are "lexed" by the CachingLex() method.
  CachedTokensTy CachedTokens;

  /// CachedLexPos - The position of the cached token that CachingLex() should
  /// "lex" next. If it points beyond the CachedTokens vector, it means that
  /// a normal Lex() should be invoked.
  CachedTokensTy::size_type CachedLexPos;

  /// BacktrackPositions - Stack of backtrack positions, allowing nested
  /// backtracks. The EnableBacktrackAtThisPos() method pushes a position to
  /// indicate where CachedLexPos should be set when the BackTrack() method is
  /// invoked (at which point the last position is popped).
  std::vector<CachedTokensTy::size_type> BacktrackPositions;

  struct MacroInfoChain {
    MacroInfo MI;
    MacroInfoChain *Next;
    MacroInfoChain *Prev;
  };

  /// MacroInfos are managed as a chain for easy disposal.  This is the head
  /// of that list.
  MacroInfoChain *MIChainHead;

  /// MICache - A "freelist" of MacroInfo objects that can be reused for quick
  /// allocation.
  MacroInfoChain *MICache;

  MacroInfo *getInfoForMacro(IdentifierInfo *II) const;
  
public:
  Preprocessor(DiagnosticsEngine &diags, LangOptions &opts,
               const TargetInfo *target,
               SourceManager &SM, HeaderSearch &Headers,
               ModuleLoader &TheModuleLoader,
               IdentifierInfoLookup *IILookup = 0,
               bool OwnsHeaderSearch = false,
               bool DelayInitialization = false);

  ~Preprocessor();

  /// \brief Initialize the preprocessor, if the constructor did not already
  /// perform the initialization.
  ///
  /// \param Target Information about the target.
  void Initialize(const TargetInfo &Target);
  
  DiagnosticsEngine &getDiagnostics() const { return *Diags; }
  void setDiagnostics(DiagnosticsEngine &D) { Diags = &D; }

  const LangOptions &getLangOptions() const { return Features; }
  const TargetInfo &getTargetInfo() const { return *Target; }
  FileManager &getFileManager() const { return FileMgr; }
  SourceManager &getSourceManager() const { return SourceMgr; }
  HeaderSearch &getHeaderSearchInfo() const { return HeaderInfo; }

  IdentifierTable &getIdentifierTable() { return Identifiers; }
  SelectorTable &getSelectorTable() { return Selectors; }
  Builtin::Context &getBuiltinInfo() { return BuiltinInfo; }
  llvm::BumpPtrAllocator &getPreprocessorAllocator() { return BP; }

  void setPTHManager(PTHManager* pm);

  PTHManager *getPTHManager() { return PTH.get(); }

  void setExternalSource(ExternalPreprocessorSource *Source) {
    ExternalSource = Source;
  }

  ExternalPreprocessorSource *getExternalSource() const {
    return ExternalSource;
  }

  /// \brief Retrieve the module loader associated with this preprocessor.
  ModuleLoader &getModuleLoader() const { return TheModuleLoader; }
  
  /// SetCommentRetentionState - Control whether or not the preprocessor retains
  /// comments in output.
  void SetCommentRetentionState(bool KeepComments, bool KeepMacroComments) {
    this->KeepComments = KeepComments | KeepMacroComments;
    this->KeepMacroComments = KeepMacroComments;
  }

  bool getCommentRetentionState() const { return KeepComments; }

  void SetSuppressIncludeNotFoundError(bool Suppress) {
    SuppressIncludeNotFoundError = Suppress;
  }

  bool GetSuppressIncludeNotFoundError() {
    return SuppressIncludeNotFoundError;
  }

  /// \brief Specify whether automatic module imports are enabled.
  void setAutoModuleImport(bool AutoModuleImport = true) {
    this->AutoModuleImport = AutoModuleImport;
  }
  
  /// isCurrentLexer - Return true if we are lexing directly from the specified
  /// lexer.
  bool isCurrentLexer(const PreprocessorLexer *L) const {
    return CurPPLexer == L;
  }

  /// getCurrentLexer - Return the current lexer being lexed from.  Note
  /// that this ignores any potentially active macro expansions and _Pragma
  /// expansions going on at the time.
  PreprocessorLexer *getCurrentLexer() const { return CurPPLexer; }

  /// getCurrentFileLexer - Return the current file lexer being lexed from.
  /// Note that this ignores any potentially active macro expansions and _Pragma
  /// expansions going on at the time.
  PreprocessorLexer *getCurrentFileLexer() const;

  /// getPPCallbacks/addPPCallbacks - Accessors for preprocessor callbacks.
  /// Note that this class takes ownership of any PPCallbacks object given to
  /// it.
  PPCallbacks *getPPCallbacks() const { return Callbacks; }
  void addPPCallbacks(PPCallbacks *C) {
    if (Callbacks)
      C = new PPChainedCallbacks(C, Callbacks);
    Callbacks = C;
  }

  /// getMacroInfo - Given an identifier, return the MacroInfo it is #defined to
  /// or null if it isn't #define'd.
  MacroInfo *getMacroInfo(IdentifierInfo *II) const {
    if (!II->hasMacroDefinition())
      return 0;
    
    return getInfoForMacro(II);
  }

  /// setMacroInfo - Specify a macro for this identifier.
  ///
  void setMacroInfo(IdentifierInfo *II, MacroInfo *MI);

  /// macro_iterator/macro_begin/macro_end - This allows you to walk the current
  /// state of the macro table.  This visits every currently-defined macro.
  typedef llvm::DenseMap<IdentifierInfo*,
                         MacroInfo*>::const_iterator macro_iterator;
  macro_iterator macro_begin(bool IncludeExternalMacros = true) const;
  macro_iterator macro_end(bool IncludeExternalMacros = true) const;

  const std::string &getPredefines() const { return Predefines; }
  /// setPredefines - Set the predefines for this Preprocessor.  These
  /// predefines are automatically injected when parsing the main file.
  void setPredefines(const char *P) { Predefines = P; }
  void setPredefines(const std::string &P) { Predefines = P; }

  /// getIdentifierInfo - Return information about the specified preprocessor
  /// identifier token.  The version of this method that takes two character
  /// pointers is preferred unless the identifier is already available as a
  /// string (this avoids allocation and copying of memory to construct an
  /// std::string).
  IdentifierInfo *getIdentifierInfo(StringRef Name) const {
    return &Identifiers.get(Name);
  }

  /// AddPragmaHandler - Add the specified pragma handler to the preprocessor.
  /// If 'Namespace' is non-null, then it is a token required to exist on the
  /// pragma line before the pragma string starts, e.g. "STDC" or "GCC".
  void AddPragmaHandler(StringRef Namespace, PragmaHandler *Handler);
  void AddPragmaHandler(PragmaHandler *Handler) {
    AddPragmaHandler(StringRef(), Handler);
  }

  /// RemovePragmaHandler - Remove the specific pragma handler from
  /// the preprocessor. If \arg Namespace is non-null, then it should
  /// be the namespace that \arg Handler was added to. It is an error
  /// to remove a handler that has not been registered.
  void RemovePragmaHandler(StringRef Namespace, PragmaHandler *Handler);
  void RemovePragmaHandler(PragmaHandler *Handler) {
    RemovePragmaHandler(StringRef(), Handler);
  }

  /// \brief Add the specified comment handler to the preprocessor.
  void AddCommentHandler(CommentHandler *Handler);

  /// \brief Remove the specified comment handler.
  ///
  /// It is an error to remove a handler that has not been registered.
  void RemoveCommentHandler(CommentHandler *Handler);

  /// \brief Set the code completion handler to the given object.
  void setCodeCompletionHandler(CodeCompletionHandler &Handler) {
    CodeComplete = &Handler;
  }
  
  /// \brief Retrieve the current code-completion handler.
  CodeCompletionHandler *getCodeCompletionHandler() const {
    return CodeComplete;
  }
  
  /// \brief Clear out the code completion handler.
  void clearCodeCompletionHandler() {
    CodeComplete = 0;
  }
  
  /// \brief Hook used by the lexer to invoke the "natural language" code
  /// completion point.
  void CodeCompleteNaturalLanguage();
  
  /// \brief Retrieve the preprocessing record, or NULL if there is no
  /// preprocessing record.
  PreprocessingRecord *getPreprocessingRecord() const { return Record; }
  
  /// \brief Create a new preprocessing record, which will keep track of 
  /// all macro expansions, macro definitions, etc.
  void createPreprocessingRecord(bool IncludeNestedMacroExpansions);
  
  /// EnterMainSourceFile - Enter the specified FileID as the main source file,
  /// which implicitly adds the builtin defines etc.
  void EnterMainSourceFile();

  /// EndSourceFile - Inform the preprocessor callbacks that processing is
  /// complete.
  void EndSourceFile();

  /// EnterSourceFile - Add a source file to the top of the include stack and
  /// start lexing tokens from it instead of the current buffer.  Emit an error
  /// and don't enter the file on error.
  void EnterSourceFile(FileID CurFileID, const DirectoryLookup *Dir,
                       SourceLocation Loc);

  /// EnterMacro - Add a Macro to the top of the include stack and start lexing
  /// tokens from it instead of the current buffer.  Args specifies the
  /// tokens input to a function-like macro.
  ///
  /// ILEnd specifies the location of the ')' for a function-like macro or the
  /// identifier for an object-like macro.
  void EnterMacro(Token &Identifier, SourceLocation ILEnd, MacroArgs *Args);

  /// EnterTokenStream - Add a "macro" context to the top of the include stack,
  /// which will cause the lexer to start returning the specified tokens.
  ///
  /// If DisableMacroExpansion is true, tokens lexed from the token stream will
  /// not be subject to further macro expansion.  Otherwise, these tokens will
  /// be re-macro-expanded when/if expansion is enabled.
  ///
  /// If OwnsTokens is false, this method assumes that the specified stream of
  /// tokens has a permanent owner somewhere, so they do not need to be copied.
  /// If it is true, it assumes the array of tokens is allocated with new[] and
  /// must be freed.
  ///
  void EnterTokenStream(const Token *Toks, unsigned NumToks,
                        bool DisableMacroExpansion, bool OwnsTokens);

  /// RemoveTopOfLexerStack - Pop the current lexer/macro exp off the top of the
  /// lexer stack.  This should only be used in situations where the current
  /// state of the top-of-stack lexer is known.
  void RemoveTopOfLexerStack();

  /// EnableBacktrackAtThisPos - From the point that this method is called, and
  /// until CommitBacktrackedTokens() or Backtrack() is called, the Preprocessor
  /// keeps track of the lexed tokens so that a subsequent Backtrack() call will
  /// make the Preprocessor re-lex the same tokens.
  ///
  /// Nested backtracks are allowed, meaning that EnableBacktrackAtThisPos can
  /// be called multiple times and CommitBacktrackedTokens/Backtrack calls will
  /// be combined with the EnableBacktrackAtThisPos calls in reverse order.
  ///
  /// NOTE: *DO NOT* forget to call either CommitBacktrackedTokens or Backtrack
  /// at some point after EnableBacktrackAtThisPos. If you don't, caching of
  /// tokens will continue indefinitely.
  ///
  void EnableBacktrackAtThisPos();

  /// CommitBacktrackedTokens - Disable the last EnableBacktrackAtThisPos call.
  void CommitBacktrackedTokens();

  /// Backtrack - Make Preprocessor re-lex the tokens that were lexed since
  /// EnableBacktrackAtThisPos() was previously called.
  void Backtrack();

  /// isBacktrackEnabled - True if EnableBacktrackAtThisPos() was called and
  /// caching of tokens is on.
  bool isBacktrackEnabled() const { return !BacktrackPositions.empty(); }

  /// Lex - To lex a token from the preprocessor, just pull a token from the
  /// current lexer or macro object.
  void Lex(Token &Result) {
    switch (CurLexerKind) {
    case CLK_Lexer: CurLexer->Lex(Result); break;
    case CLK_PTHLexer: CurPTHLexer->Lex(Result); break;
    case CLK_TokenLexer: CurTokenLexer->Lex(Result); break;
    case CLK_CachingLexer: CachingLex(Result); break;
    case CLK_LexAfterModuleImport: LexAfterModuleImport(Result); break;
    }
  }

  void LexAfterModuleImport(Token &Result);
  
  /// LexNonComment - Lex a token.  If it's a comment, keep lexing until we get
  /// something not a comment.  This is useful in -E -C mode where comments
  /// would foul up preprocessor directive handling.
  void LexNonComment(Token &Result) {
    do
      Lex(Result);
    while (Result.getKind() == tok::comment);
  }

  /// LexUnexpandedToken - This is just like Lex, but this disables macro
  /// expansion of identifier tokens.
  void LexUnexpandedToken(Token &Result) {
    // Disable macro expansion.
    bool OldVal = DisableMacroExpansion;
    DisableMacroExpansion = true;
    // Lex the token.
    Lex(Result);

    // Reenable it.
    DisableMacroExpansion = OldVal;
  }

  /// LexUnexpandedNonComment - Like LexNonComment, but this disables macro
  /// expansion of identifier tokens.
  void LexUnexpandedNonComment(Token &Result) {
    do
      LexUnexpandedToken(Result);
    while (Result.getKind() == tok::comment);
  }

  /// LookAhead - This peeks ahead N tokens and returns that token without
  /// consuming any tokens.  LookAhead(0) returns the next token that would be
  /// returned by Lex(), LookAhead(1) returns the token after it, etc.  This
  /// returns normal tokens after phase 5.  As such, it is equivalent to using
  /// 'Lex', not 'LexUnexpandedToken'.
  const Token &LookAhead(unsigned N) {
    if (CachedLexPos + N < CachedTokens.size())
      return CachedTokens[CachedLexPos+N];
    else
      return PeekAhead(N+1);
  }

  /// RevertCachedTokens - When backtracking is enabled and tokens are cached,
  /// this allows to revert a specific number of tokens.
  /// Note that the number of tokens being reverted should be up to the last
  /// backtrack position, not more.
  void RevertCachedTokens(unsigned N) {
    assert(isBacktrackEnabled() &&
           "Should only be called when tokens are cached for backtracking");
    assert(signed(CachedLexPos) - signed(N) >= signed(BacktrackPositions.back())
         && "Should revert tokens up to the last backtrack position, not more");
    assert(signed(CachedLexPos) - signed(N) >= 0 &&
           "Corrupted backtrack positions ?");
    CachedLexPos -= N;
  }

  /// EnterToken - Enters a token in the token stream to be lexed next. If
  /// BackTrack() is called afterwards, the token will remain at the insertion
  /// point.
  void EnterToken(const Token &Tok) {
    EnterCachingLexMode();
    CachedTokens.insert(CachedTokens.begin()+CachedLexPos, Tok);
  }

  /// AnnotateCachedTokens - We notify the Preprocessor that if it is caching
  /// tokens (because backtrack is enabled) it should replace the most recent
  /// cached tokens with the given annotation token. This function has no effect
  /// if backtracking is not enabled.
  ///
  /// Note that the use of this function is just for optimization; so that the
  /// cached tokens doesn't get re-parsed and re-resolved after a backtrack is
  /// invoked.
  void AnnotateCachedTokens(const Token &Tok) {
    assert(Tok.isAnnotation() && "Expected annotation token");
    if (CachedLexPos != 0 && isBacktrackEnabled())
      AnnotatePreviousCachedTokens(Tok);
  }

  /// \brief Replace the last token with an annotation token.
  ///
  /// Like AnnotateCachedTokens(), this routine replaces an
  /// already-parsed (and resolved) token with an annotation
  /// token. However, this routine only replaces the last token with
  /// the annotation token; it does not affect any other cached
  /// tokens. This function has no effect if backtracking is not
  /// enabled.
  void ReplaceLastTokenWithAnnotation(const Token &Tok) {
    assert(Tok.isAnnotation() && "Expected annotation token");
    if (CachedLexPos != 0 && isBacktrackEnabled())
      CachedTokens[CachedLexPos-1] = Tok;
  }

  /// \brief Specify the point at which code-completion will be performed.
  ///
  /// \param File the file in which code completion should occur. If
  /// this file is included multiple times, code-completion will
  /// perform completion the first time it is included. If NULL, this
  /// function clears out the code-completion point.
  ///
  /// \param Line the line at which code completion should occur
  /// (1-based).
  ///
  /// \param Column the column at which code completion should occur
  /// (1-based).
  ///
  /// \returns true if an error occurred, false otherwise.
  bool SetCodeCompletionPoint(const FileEntry *File,
                              unsigned Line, unsigned Column);

  /// \brief Determine if we are performing code completion.
  bool isCodeCompletionEnabled() const { return CodeCompletionFile != 0; }

  /// \brief Returns the location of the code-completion point.
  /// Returns an invalid location if code-completion is not enabled or the file
  /// containing the code-completion point has not been lexed yet.
  SourceLocation getCodeCompletionLoc() const { return CodeCompletionLoc; }

  /// \brief Returns the start location of the file of code-completion point.
  /// Returns an invalid location if code-completion is not enabled or the file
  /// containing the code-completion point has not been lexed yet.
  SourceLocation getCodeCompletionFileLoc() const {
    return CodeCompletionFileLoc;
  }

  /// \brief Returns true if code-completion is enabled and we have hit the
  /// code-completion point.
  bool isCodeCompletionReached() const { return CodeCompletionReached; }

  /// \brief Note that we hit the code-completion point.
  void setCodeCompletionReached() {
    assert(isCodeCompletionEnabled() && "Code-completion not enabled!");
    CodeCompletionReached = true;
    // Silence any diagnostics that occur after we hit the code-completion.
    getDiagnostics().setSuppressAllDiagnostics(true);
  }

  /// \brief The location of the currently-active #pragma clang
  /// arc_cf_code_audited begin.  Returns an invalid location if there
  /// is no such pragma active.
  SourceLocation getPragmaARCCFCodeAuditedLoc() const {
    return PragmaARCCFCodeAuditedLoc;
  }

  /// \brief Set the location of the currently-active #pragma clang
  /// arc_cf_code_audited begin.  An invalid location ends the pragma.
  void setPragmaARCCFCodeAuditedLoc(SourceLocation Loc) {
    PragmaARCCFCodeAuditedLoc = Loc;
  }

  /// \brief Instruct the preprocessor to skip part of the main
  /// the main source file.
  ///
  /// \brief Bytes The number of bytes in the preamble to skip.
  ///
  /// \brief StartOfLine Whether skipping these bytes puts the lexer at the
  /// start of a line.
  void setSkipMainFilePreamble(unsigned Bytes, bool StartOfLine) { 
    SkipMainFilePreamble.first = Bytes;
    SkipMainFilePreamble.second = StartOfLine;
  }
  
  /// Diag - Forwarding function for diagnostics.  This emits a diagnostic at
  /// the specified Token's location, translating the token's start
  /// position in the current buffer into a SourcePosition object for rendering.
  DiagnosticBuilder Diag(SourceLocation Loc, unsigned DiagID) const {
    return Diags->Report(Loc, DiagID);
  }

  DiagnosticBuilder Diag(const Token &Tok, unsigned DiagID) const {
    return Diags->Report(Tok.getLocation(), DiagID);
  }

  /// getSpelling() - Return the 'spelling' of the token at the given
  /// location; does not go up to the spelling location or down to the
  /// expansion location.
  ///
  /// \param buffer A buffer which will be used only if the token requires
  ///   "cleaning", e.g. if it contains trigraphs or escaped newlines
  /// \param invalid If non-null, will be set \c true if an error occurs.
  StringRef getSpelling(SourceLocation loc,
                              SmallVectorImpl<char> &buffer,
                              bool *invalid = 0) const {
    return Lexer::getSpelling(loc, buffer, SourceMgr, Features, invalid);
  }

  /// getSpelling() - Return the 'spelling' of the Tok token.  The spelling of a
  /// token is the characters used to represent the token in the source file
  /// after trigraph expansion and escaped-newline folding.  In particular, this
  /// wants to get the true, uncanonicalized, spelling of things like digraphs
  /// UCNs, etc.
  ///
  /// \param Invalid If non-null, will be set \c true if an error occurs.
  std::string getSpelling(const Token &Tok, bool *Invalid = 0) const {
    return Lexer::getSpelling(Tok, SourceMgr, Features, Invalid);
  }

  /// getSpelling - This method is used to get the spelling of a token into a
  /// preallocated buffer, instead of as an std::string.  The caller is required
  /// to allocate enough space for the token, which is guaranteed to be at least
  /// Tok.getLength() bytes long.  The length of the actual result is returned.
  ///
  /// Note that this method may do two possible things: it may either fill in
  /// the buffer specified with characters, or it may *change the input pointer*
  /// to point to a constant buffer with the data already in it (avoiding a
  /// copy).  The caller is not allowed to modify the returned buffer pointer
  /// if an internal buffer is returned.
  unsigned getSpelling(const Token &Tok, const char *&Buffer, 
                       bool *Invalid = 0) const {
    return Lexer::getSpelling(Tok, Buffer, SourceMgr, Features, Invalid);
  }

  /// getSpelling - This method is used to get the spelling of a token into a
  /// SmallVector. Note that the returned StringRef may not point to the
  /// supplied buffer if a copy can be avoided.
  StringRef getSpelling(const Token &Tok,
                              SmallVectorImpl<char> &Buffer, 
                              bool *Invalid = 0) const;

  /// getSpellingOfSingleCharacterNumericConstant - Tok is a numeric constant
  /// with length 1, return the character.
  char getSpellingOfSingleCharacterNumericConstant(const Token &Tok, 
                                                   bool *Invalid = 0) const {
    assert(Tok.is(tok::numeric_constant) &&
           Tok.getLength() == 1 && "Called on unsupported token");
    assert(!Tok.needsCleaning() && "Token can't need cleaning with length 1");

    // If the token is carrying a literal data pointer, just use it.
    if (const char *D = Tok.getLiteralData())
      return *D;

    // Otherwise, fall back on getCharacterData, which is slower, but always
    // works.
    return *SourceMgr.getCharacterData(Tok.getLocation(), Invalid);
  }

  /// CreateString - Plop the specified string into a scratch buffer and set the
  /// specified token's location and length to it.  If specified, the source
  /// location provides a location of the expansion point of the token.
  void CreateString(const char *Buf, unsigned Len, Token &Tok,
                    SourceLocation ExpansionLocStart = SourceLocation(),
                    SourceLocation ExpansionLocEnd = SourceLocation());

  /// \brief Computes the source location just past the end of the
  /// token at this source location.
  ///
  /// This routine can be used to produce a source location that
  /// points just past the end of the token referenced by \p Loc, and
  /// is generally used when a diagnostic needs to point just after a
  /// token where it expected something different that it received. If
  /// the returned source location would not be meaningful (e.g., if
  /// it points into a macro), this routine returns an invalid
  /// source location.
  ///
  /// \param Offset an offset from the end of the token, where the source
  /// location should refer to. The default offset (0) produces a source
  /// location pointing just past the end of the token; an offset of 1 produces
  /// a source location pointing to the last character in the token, etc.
  SourceLocation getLocForEndOfToken(SourceLocation Loc, unsigned Offset = 0) {
    return Lexer::getLocForEndOfToken(Loc, Offset, SourceMgr, Features);
  }

  /// \brief Returns true if the given MacroID location points at the first
  /// token of the macro expansion.
  bool isAtStartOfMacroExpansion(SourceLocation loc) const {
    return Lexer::isAtStartOfMacroExpansion(loc, SourceMgr, Features);
  }

  /// \brief Returns true if the given MacroID location points at the last
  /// token of the macro expansion.
  bool isAtEndOfMacroExpansion(SourceLocation loc) const {
    return Lexer::isAtEndOfMacroExpansion(loc, SourceMgr, Features);
  }

  /// DumpToken - Print the token to stderr, used for debugging.
  ///
  void DumpToken(const Token &Tok, bool DumpFlags = false) const;
  void DumpLocation(SourceLocation Loc) const;
  void DumpMacro(const MacroInfo &MI) const;

  /// AdvanceToTokenCharacter - Given a location that specifies the start of a
  /// token, return a new location that specifies a character within the token.
  SourceLocation AdvanceToTokenCharacter(SourceLocation TokStart,
                                         unsigned Char) const {
    return Lexer::AdvanceToTokenCharacter(TokStart, Char, SourceMgr, Features);
  }

  /// IncrementPasteCounter - Increment the counters for the number of token
  /// paste operations performed.  If fast was specified, this is a 'fast paste'
  /// case we handled.
  ///
  void IncrementPasteCounter(bool isFast) {
    if (isFast)
      ++NumFastTokenPaste;
    else
      ++NumTokenPaste;
  }

  void PrintStats();

  size_t getTotalMemory() const;

  /// HandleMicrosoftCommentPaste - When the macro expander pastes together a
  /// comment (/##/) in microsoft mode, this method handles updating the current
  /// state, returning the token on the next source line.
  void HandleMicrosoftCommentPaste(Token &Tok);

  //===--------------------------------------------------------------------===//
  // Preprocessor callback methods.  These are invoked by a lexer as various
  // directives and events are found.

  /// LookUpIdentifierInfo - Given a tok::raw_identifier token, look up the
  /// identifier information for the token and install it into the token,
  /// updating the token kind accordingly.
  IdentifierInfo *LookUpIdentifierInfo(Token &Identifier) const;

private:
  llvm::DenseMap<IdentifierInfo*,unsigned> PoisonReasons;

public:

  // SetPoisonReason - Call this function to indicate the reason for
  // poisoning an identifier. If that identifier is accessed while
  // poisoned, then this reason will be used instead of the default
  // "poisoned" diagnostic.
  void SetPoisonReason(IdentifierInfo *II, unsigned DiagID);

  // HandlePoisonedIdentifier - Display reason for poisoned
  // identifier.
  void HandlePoisonedIdentifier(Token & Tok);

  void MaybeHandlePoisonedIdentifier(Token & Identifier) {
    if(IdentifierInfo * II = Identifier.getIdentifierInfo()) {
      if(II->isPoisoned()) {
        HandlePoisonedIdentifier(Identifier);
      }
    }
  }

private:
  /// Identifiers used for SEH handling in Borland. These are only
  /// allowed in particular circumstances
  IdentifierInfo *Ident__exception_code, *Ident___exception_code, *Ident_GetExceptionCode; // __except block
  IdentifierInfo *Ident__exception_info, *Ident___exception_info, *Ident_GetExceptionInfo; // __except filter expression
  IdentifierInfo *Ident__abnormal_termination, *Ident___abnormal_termination, *Ident_AbnormalTermination; // __finally
public:
  void PoisonSEHIdentifiers(bool Poison = true); // Borland

  /// HandleIdentifier - This callback is invoked when the lexer reads an
  /// identifier and has filled in the tokens IdentifierInfo member.  This
  /// callback potentially macro expands it or turns it into a named token (like
  /// 'for').
  void HandleIdentifier(Token &Identifier);


  /// HandleEndOfFile - This callback is invoked when the lexer hits the end of
  /// the current file.  This either returns the EOF token and returns true, or
  /// pops a level off the include stack and returns false, at which point the
  /// client should call lex again.
  bool HandleEndOfFile(Token &Result, bool isEndOfMacro = false);

  /// HandleEndOfTokenLexer - This callback is invoked when the current
  /// TokenLexer hits the end of its token stream.
  bool HandleEndOfTokenLexer(Token &Result);

  /// HandleDirective - This callback is invoked when the lexer sees a # token
  /// at the start of a line.  This consumes the directive, modifies the
  /// lexer/preprocessor state, and advances the lexer(s) so that the next token
  /// read is the correct one.
  void HandleDirective(Token &Result);

  /// CheckEndOfDirective - Ensure that the next token is a tok::eod token.  If
  /// not, emit a diagnostic and consume up until the eod.  If EnableMacros is
  /// true, then we consider macros that expand to zero tokens as being ok.
  void CheckEndOfDirective(const char *Directive, bool EnableMacros = false);

  /// DiscardUntilEndOfDirective - Read and discard all tokens remaining on the
  /// current line until the tok::eod token is found.
  void DiscardUntilEndOfDirective();

  /// SawDateOrTime - This returns true if the preprocessor has seen a use of
  /// __DATE__ or __TIME__ in the file so far.
  bool SawDateOrTime() const {
    return DATELoc != SourceLocation() || TIMELoc != SourceLocation();
  }
  unsigned getCounterValue() const { return CounterValue; }
  void setCounterValue(unsigned V) { CounterValue = V; }

  /// AllocateMacroInfo - Allocate a new MacroInfo object with the provide
  ///  SourceLocation.
  MacroInfo *AllocateMacroInfo(SourceLocation L);

  /// CloneMacroInfo - Allocate a new MacroInfo object which is clone of MI.
  MacroInfo *CloneMacroInfo(const MacroInfo &MI);

  /// GetIncludeFilenameSpelling - Turn the specified lexer token into a fully
  /// checked and spelled filename, e.g. as an operand of #include. This returns
  /// true if the input filename was in <>'s or false if it were in ""'s.  The
  /// caller is expected to provide a buffer that is large enough to hold the
  /// spelling of the filename, but is also expected to handle the case when
  /// this method decides to use a different buffer.
  bool GetIncludeFilenameSpelling(SourceLocation Loc,StringRef &Filename);

  /// LookupFile - Given a "foo" or <foo> reference, look up the indicated file,
  /// return null on failure.  isAngled indicates whether the file reference is
  /// for system #include's or not (i.e. using <> instead of "").
  const FileEntry *LookupFile(StringRef Filename,
                              bool isAngled, const DirectoryLookup *FromDir,
                              const DirectoryLookup *&CurDir,
                              SmallVectorImpl<char> *SearchPath,
                              SmallVectorImpl<char> *RelativePath,
                              StringRef *SuggestedModule);

  /// GetCurLookup - The DirectoryLookup structure used to find the current
  /// FileEntry, if CurLexer is non-null and if applicable.  This allows us to
  /// implement #include_next and find directory-specific properties.
  const DirectoryLookup *GetCurDirLookup() { return CurDirLookup; }

  /// isInPrimaryFile - Return true if we're in the top-level file, not in a
  /// #include.
  bool isInPrimaryFile() const;

  /// ConcatenateIncludeName - Handle cases where the #include name is expanded
  /// from a macro as multiple tokens, which need to be glued together.  This
  /// occurs for code like:
  ///    #define FOO <a/b.h>
  ///    #include FOO
  /// because in this case, "<a/b.h>" is returned as 7 tokens, not one.
  ///
  /// This code concatenates and consumes tokens up to the '>' token.  It
  /// returns false if the > was found, otherwise it returns true if it finds
  /// and consumes the EOD marker.
  bool ConcatenateIncludeName(llvm::SmallString<128> &FilenameBuffer,
                              SourceLocation &End);

  /// LexOnOffSwitch - Lex an on-off-switch (C99 6.10.6p2) and verify that it is
  /// followed by EOD.  Return true if the token is not a valid on-off-switch.
  bool LexOnOffSwitch(tok::OnOffSwitch &OOS);

private:

  void PushIncludeMacroStack() {
    IncludeMacroStack.push_back(IncludeStackInfo(CurLexerKind,
                                                 CurLexer.take(),
                                                 CurPTHLexer.take(),
                                                 CurPPLexer,
                                                 CurTokenLexer.take(),
                                                 CurDirLookup));
    CurPPLexer = 0;
  }

  void PopIncludeMacroStack() {
    CurLexer.reset(IncludeMacroStack.back().TheLexer);
    CurPTHLexer.reset(IncludeMacroStack.back().ThePTHLexer);
    CurPPLexer = IncludeMacroStack.back().ThePPLexer;
    CurTokenLexer.reset(IncludeMacroStack.back().TheTokenLexer);
    CurDirLookup  = IncludeMacroStack.back().TheDirLookup;
    CurLexerKind = IncludeMacroStack.back().CurLexerKind;
    IncludeMacroStack.pop_back();
  }

  /// AllocateMacroInfo - Allocate a new MacroInfo object.
  MacroInfo *AllocateMacroInfo();

  /// ReleaseMacroInfo - Release the specified MacroInfo.  This memory will
  ///  be reused for allocating new MacroInfo objects.
  void ReleaseMacroInfo(MacroInfo* MI);

  /// ReadMacroName - Lex and validate a macro name, which occurs after a
  /// #define or #undef.  This emits a diagnostic, sets the token kind to eod,
  /// and discards the rest of the macro line if the macro name is invalid.
  void ReadMacroName(Token &MacroNameTok, char isDefineUndef = 0);

  /// ReadMacroDefinitionArgList - The ( starting an argument list of a macro
  /// definition has just been read.  Lex the rest of the arguments and the
  /// closing ), updating MI with what we learn.  Return true if an error occurs
  /// parsing the arg list.
  bool ReadMacroDefinitionArgList(MacroInfo *MI);

  /// SkipExcludedConditionalBlock - We just read a #if or related directive and
  /// decided that the subsequent tokens are in the #if'd out portion of the
  /// file.  Lex the rest of the file, until we see an #endif.  If
  /// FoundNonSkipPortion is true, then we have already emitted code for part of
  /// this #if directive, so #else/#elif blocks should never be entered. If
  /// FoundElse is false, then #else directives are ok, if not, then we have
  /// already seen one so a #else directive is a duplicate.  When this returns,
  /// the caller can lex the first valid token.
  void SkipExcludedConditionalBlock(SourceLocation IfTokenLoc,
                                    bool FoundNonSkipPortion, bool FoundElse,
                                    SourceLocation ElseLoc = SourceLocation());

  /// PTHSkipExcludedConditionalBlock - A fast PTH version of
  ///  SkipExcludedConditionalBlock.
  void PTHSkipExcludedConditionalBlock();

  /// EvaluateDirectiveExpression - Evaluate an integer constant expression that
  /// may occur after a #if or #elif directive and return it as a bool.  If the
  /// expression is equivalent to "!defined(X)" return X in IfNDefMacro.
  bool EvaluateDirectiveExpression(IdentifierInfo *&IfNDefMacro);

  /// RegisterBuiltinPragmas - Install the standard preprocessor pragmas:
  /// #pragma GCC poison/system_header/dependency and #pragma once.
  void RegisterBuiltinPragmas();

  /// RegisterBuiltinMacros - Register builtin macros, such as __LINE__ with the
  /// identifier table.
  void RegisterBuiltinMacros();

  /// HandleMacroExpandedIdentifier - If an identifier token is read that is to
  /// be expanded as a macro, handle it and return the next token as 'Tok'.  If
  /// the macro should not be expanded return true, otherwise return false.
  bool HandleMacroExpandedIdentifier(Token &Tok, MacroInfo *MI);

  /// \brief Cache macro expanded tokens for TokenLexers.
  //
  /// Works like a stack; a TokenLexer adds the macro expanded tokens that is
  /// going to lex in the cache and when it finishes the tokens are removed
  /// from the end of the cache.
  Token *cacheMacroExpandedTokens(TokenLexer *tokLexer,
                                  ArrayRef<Token> tokens);
  void removeCachedMacroExpandedTokensOfLastLexer();
  friend void TokenLexer::ExpandFunctionArguments();

  /// isNextPPTokenLParen - Determine whether the next preprocessor token to be
  /// lexed is a '('.  If so, consume the token and return true, if not, this
  /// method should have no observable side-effect on the lexed tokens.
  bool isNextPPTokenLParen();

  /// ReadFunctionLikeMacroArgs - After reading "MACRO(", this method is
  /// invoked to read all of the formal arguments specified for the macro
  /// invocation.  This returns null on error.
  MacroArgs *ReadFunctionLikeMacroArgs(Token &MacroName, MacroInfo *MI,
                                       SourceLocation &ExpansionEnd);

  /// ExpandBuiltinMacro - If an identifier token is read that is to be expanded
  /// as a builtin macro, handle it and return the next token as 'Tok'.
  void ExpandBuiltinMacro(Token &Tok);

  /// Handle_Pragma - Read a _Pragma directive, slice it up, process it, then
  /// return the first token after the directive.  The _Pragma token has just
  /// been read into 'Tok'.
  void Handle_Pragma(Token &Tok);

  /// HandleMicrosoft__pragma - Like Handle_Pragma except the pragma text
  /// is not enclosed within a string literal.
  void HandleMicrosoft__pragma(Token &Tok);

  /// EnterSourceFileWithLexer - Add a lexer to the top of the include stack and
  /// start lexing tokens from it instead of the current buffer.
  void EnterSourceFileWithLexer(Lexer *TheLexer, const DirectoryLookup *Dir);

  /// EnterSourceFileWithPTH - Add a lexer to the top of the include stack and
  /// start getting tokens from it using the PTH cache.
  void EnterSourceFileWithPTH(PTHLexer *PL, const DirectoryLookup *Dir);

  /// IsFileLexer - Returns true if we are lexing from a file and not a
  ///  pragma or a macro.
  static bool IsFileLexer(const Lexer* L, const PreprocessorLexer* P) {
    return L ? !L->isPragmaLexer() : P != 0;
  }

  static bool IsFileLexer(const IncludeStackInfo& I) {
    return IsFileLexer(I.TheLexer, I.ThePPLexer);
  }

  bool IsFileLexer() const {
    return IsFileLexer(CurLexer.get(), CurPPLexer);
  }

  //===--------------------------------------------------------------------===//
  // Caching stuff.
  void CachingLex(Token &Result);
  bool InCachingLexMode() const {
    // If the Lexer pointers are 0 and IncludeMacroStack is empty, it means
    // that we are past EOF, not that we are in CachingLex mode.
    return CurPPLexer == 0 && CurTokenLexer == 0 && CurPTHLexer == 0 && 
           !IncludeMacroStack.empty();
  }
  void EnterCachingLexMode();
  void ExitCachingLexMode() {
    if (InCachingLexMode())
      RemoveTopOfLexerStack();
  }
  const Token &PeekAhead(unsigned N);
  void AnnotatePreviousCachedTokens(const Token &Tok);

  //===--------------------------------------------------------------------===//
  /// Handle*Directive - implement the various preprocessor directives.  These
  /// should side-effect the current preprocessor object so that the next call
  /// to Lex() will return the appropriate token next.
  void HandleLineDirective(Token &Tok);
  void HandleDigitDirective(Token &Tok);
  void HandleUserDiagnosticDirective(Token &Tok, bool isWarning);
  void HandleIdentSCCSDirective(Token &Tok);
  void HandleMacroExportDirective(Token &Tok);
  
  // File inclusion.
  void HandleIncludeDirective(SourceLocation HashLoc,
                              Token &Tok,
                              const DirectoryLookup *LookupFrom = 0,
                              bool isImport = false);
  void HandleIncludeNextDirective(SourceLocation HashLoc, Token &Tok);
  void HandleIncludeMacrosDirective(SourceLocation HashLoc, Token &Tok);
  void HandleImportDirective(SourceLocation HashLoc, Token &Tok);

  // Macro handling.
  void HandleDefineDirective(Token &Tok);
  void HandleUndefDirective(Token &Tok);

  // Conditional Inclusion.
  void HandleIfdefDirective(Token &Tok, bool isIfndef,
                            bool ReadAnyTokensBeforeDirective);
  void HandleIfDirective(Token &Tok, bool ReadAnyTokensBeforeDirective);
  void HandleEndifDirective(Token &Tok);
  void HandleElseDirective(Token &Tok);
  void HandleElifDirective(Token &Tok);

  // Pragmas.
  void HandlePragmaDirective(unsigned Introducer);
public:
  void HandlePragmaOnce(Token &OnceTok);
  void HandlePragmaMark();
  void HandlePragmaPoison(Token &PoisonTok);
  void HandlePragmaSystemHeader(Token &SysHeaderTok);
  void HandlePragmaDependency(Token &DependencyTok);
  void HandlePragmaComment(Token &CommentTok);
  void HandlePragmaMessage(Token &MessageTok);
  void HandlePragmaPushMacro(Token &Tok);
  void HandlePragmaPopMacro(Token &Tok);
  IdentifierInfo *ParsePragmaPushOrPopMacro(Token &Tok);

  // Return true and store the first token only if any CommentHandler
  // has inserted some tokens and getCommentRetentionState() is false.
  bool HandleComment(Token &Token, SourceRange Comment);

  /// \brief A macro is used, update information about macros that need unused
  /// warnings.
  void markMacroAsUsed(MacroInfo *MI);
};

/// \brief Abstract base class that describes a handler that will receive
/// source ranges for each of the comments encountered in the source file.
class CommentHandler {
public:
  virtual ~CommentHandler();

  // The handler shall return true if it has pushed any tokens
  // to be read using e.g. EnterToken or EnterTokenStream.
  virtual bool HandleComment(Preprocessor &PP, SourceRange Comment) = 0;
};

}  // end namespace clang

#endif