path: root/include/clang/Lex/Preprocessor.h

//===--- 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/Lexer.h"
#include "clang/Lex/PPCallbacks.h"
#include "clang/Lex/TokenLexer.h"
#include "clang/Basic/IdentifierTable.h"
#include "clang/Basic/SourceLocation.h"
#include "llvm/ADT/DenseMap.h"

namespace clang {
  
class SourceManager;
class FileManager;
class FileEntry;
class HeaderSearch;
class PragmaNamespace;
class PragmaHandler;
class ScratchBuffer;
class TargetInfo;
class PPCallbacks;
class DirectoryLookup;

/// 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 {
  Diagnostic        &Diags;
  const LangOptions &Features;
  TargetInfo        &Target;
  FileManager       &FileMgr;
  SourceManager     &SourceMgr;
  ScratchBuffer     *ScratchBuf;
  HeaderSearch      &HeaderInfo;
    
  /// 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_Pragma, *Ident__VA_ARGS__; // _Pragma, __VA_ARGS__
  
  SourceLocation DATELoc, TIMELoc;

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

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

  /// Identifiers - This is mapping/lookup information for all identifiers in
  /// the program, including program keywords.
  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/instantiated 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 fo the preprocessor.
  SelectorTable Selectors;
  
  /// PragmaHandlers - This tracks all of the pragmas that the client registered
  /// with this preprocessor.
  PragmaNamespace *PragmaHandlers;
  
  /// CurLexer - This is the current top of the stack that we're lexing from if
  /// not expanding a macro.  One of CurLexer and CurTokenLexer must be null.
  Lexer *CurLexer;
  
  /// 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.
  TokenLexer *CurTokenLexer;
  
  /// IncludeMacroStack - This keeps track of the stack of files currently
  /// #included, and macros currently being expanded from, not counting
  /// CurLexer/CurTokenLexer.
  struct IncludeStackInfo {
    Lexer *TheLexer;
    const DirectoryLookup *TheDirLookup;
    TokenLexer *TheTokenLexer;
    IncludeStackInfo(Lexer *L, const DirectoryLookup *D, TokenLexer *TL)
      : TheLexer(L), TheDirLookup(D), TheTokenLexer(TL) {
    }
  };
  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;
  
  // 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];
public:
  Preprocessor(Diagnostic &diags, const LangOptions &opts, TargetInfo &target,
               SourceManager &SM, HeaderSearch &Headers);
  ~Preprocessor();

  Diagnostic &getDiagnostics() const { return Diags; }
  const LangOptions &getLangOptions() const { return Features; }
  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; }
  
  inline FullSourceLoc getFullLoc(SourceLocation Loc) const {
    return FullSourceLoc(Loc, getSourceManager());
  }
  
  /// 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; }
  
  /// isCurrentLexer - Return true if we are lexing directly from the specified
  /// lexer.
  bool isCurrentLexer(const Lexer *L) const {
    return CurLexer == L;
  }
  
  /// getCurrentLexer - 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.
  Lexer *getCurrentFileLexer() const;
  
  /// getPPCallbacks/setPPCallbacks - Accessors for preprocessor callbacks.
  /// Note that this class takes ownership of any PPCallbacks object given to
  /// it.
  PPCallbacks *getPPCallbacks() const { return Callbacks; }
  void setPPCallbacks(PPCallbacks *C) {
    delete 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 {
    return II->hasMacroDefinition() ? Macros.find(II)->second : 0;
  }
  
  /// setMacroInfo - Specify a macro for this identifier.
  ///
  void setMacroInfo(IdentifierInfo *II, MacroInfo *MI);
  
  /// 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(const char *NameStart,
                                    const char *NameEnd) {
    return &Identifiers.get(NameStart, NameEnd);
  }
  IdentifierInfo *getIdentifierInfo(const char *NameStr) {
    return getIdentifierInfo(NameStr, NameStr+strlen(NameStr));
  }
  
  /// 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(const char *Namespace, PragmaHandler *Handler);

  /// EnterMainSourceFile - Enter the specified FileID as the main source file,
  /// which implicitly adds the builtin defines etc.
  void EnterMainSourceFile();  
  
  /// EnterSourceFile - Add a source file to the top of the include stack and
  /// start lexing tokens from it instead of the current buffer.  If isMainFile
  /// is true, this is the main file for the translation unit.
  void EnterSourceFile(unsigned CurFileID, const DirectoryLookup *Dir);

  /// 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.
  void EnterMacro(Token &Identifier, 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.
  ///