path: root/include/clang/Basic/IdentifierTable.h

//===--- IdentifierTable.h - Hash table for identifier lookup ---*- C++ -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
///
/// \file
/// \brief Defines the clang::IdentifierInfo, clang::IdentifierTable, and
/// clang::Selector interfaces.
///
//===----------------------------------------------------------------------===//

#ifndef LLVM_CLANG_BASIC_IDENTIFIERTABLE_H
#define LLVM_CLANG_BASIC_IDENTIFIERTABLE_H

#include "clang/Basic/LLVM.h"
#include "clang/Basic/OperatorKinds.h"
#include "clang/Basic/TokenKinds.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/PointerLikeTypeTraits.h"
#include <cassert>
#include <string>

namespace llvm {
  template <typename T> struct DenseMapInfo;
}

namespace clang {
  class LangOptions;
  class IdentifierInfo;
  class IdentifierTable;
  class SourceLocation;
  class MultiKeywordSelector; // private class used by Selector
  class DeclarationName;      // AST class that stores declaration names

  /// \brief A simple pair of identifier info and location.
  typedef std::pair<IdentifierInfo*, SourceLocation> IdentifierLocPair;


/// One of these records is kept for each identifier that
/// is lexed.  This contains information about whether the token was \#define'd,
/// is a language keyword, or if it is a front-end token of some sort (e.g. a
/// variable or function name).  The preprocessor keeps this information in a
/// set, and all tok::identifier tokens have a pointer to one of these.
class IdentifierInfo {
  unsigned TokenID            : 9; // Front-end token ID or tok::identifier.
  // Objective-C keyword ('protocol' in '@protocol') or builtin (__builtin_inf).
  // First NUM_OBJC_KEYWORDS values are for Objective-C, the remaining values
  // are for builtins.
  unsigned ObjCOrBuiltinID    :11;
  bool HasMacro               : 1; // True if there is a #define for this.
  bool HadMacro               : 1; // True if there was a #define for this.
  bool IsExtension            : 1; // True if identifier is a lang extension.
  bool IsCXX11CompatKeyword   : 1; // True if identifier is a keyword in C++11.
  bool IsPoisoned             : 1; // True if identifier is poisoned.
  bool IsCPPOperatorKeyword   : 1; // True if ident is a C++ operator keyword.
  bool NeedsHandleIdentifier  : 1; // See "RecomputeNeedsHandleIdentifier".
  bool IsFromAST              : 1; // True if identifier was loaded (at least 
                                   // partially) from an AST file.
  bool ChangedAfterLoad       : 1; // True if identifier has changed from the
                                   // definition loaded from an AST file.
  bool RevertedTokenID        : 1; // True if RevertTokenIDToIdentifier was
                                   // called.
  bool OutOfDate              : 1; // True if there may be additional
                                   // information about this identifier
                                   // stored externally.
  bool IsModulesImport        : 1; // True if this is the 'import' contextual
                                   // keyword.
  // 32-bit word is filled.

  void *FETokenInfo;               // Managed by the language front-end.
  llvm::StringMapEntry<IdentifierInfo*> *Entry;

  IdentifierInfo(const IdentifierInfo&) LLVM_DELETED_FUNCTION;
  void operator=(const IdentifierInfo&) LLVM_DELETED_FUNCTION;

  friend class IdentifierTable;
  
public:
  IdentifierInfo();


  /// \brief Return true if this is the identifier for the specified string.
  ///
  /// This is intended to be used for string literals only: II->isStr("foo").
  template <std::size_t StrLen>
  bool isStr(const char (&Str)[StrLen]) const {
    return getLength() == StrLen-1 && !memcmp(getNameStart(), Str, StrLen-1);
  }

  /// \brief Return the beginning of the actual null-terminated string for this
  /// identifier.
  ///
  const char *getNameStart() const {
    if (Entry) return Entry->getKeyData();
    // FIXME: This is gross. It would be best not to embed specific details
    // of the PTH file format here.
    // The 'this' pointer really points to a
    // std::pair<IdentifierInfo, const char*>, where internal pointer
    // points to the external string data.
    typedef std::pair<IdentifierInfo, const char*> actualtype;
    return ((const actualtype*) this)->second;
  }

  /// \brief Efficiently return the length of this identifier info.
  ///
  unsigned getLength() const {
    if (Entry) return Entry->getKeyLength();
    // FIXME: This is gross. It would be best not to embed specific details
    // of the PTH file format here.
    // The 'this' pointer really points to a
    // std::pair<IdentifierInfo, const char*>, where internal pointer
    // points to the external string data.
    typedef std::pair<IdentifierInfo, const char*> actualtype;
    const char* p = ((const actualtype*) this)->second - 2;
    return (((unsigned) p[0]) | (((unsigned) p[1]) << 8)) - 1;
  }

  /// \brief Return the actual identifier string.
  StringRef getName() const {
    return StringRef(getNameStart(), getLength());
  }

  /// \brief Return true if this identifier is \#defined to some other value.
  bool hasMacroDefinition() const {
    return HasMacro;
  }
  void setHasMacroDefinition(bool Val) {
    if (HasMacro == Val) return;

    HasMacro = Val;
    if (Val) {
      NeedsHandleIdentifier = 1;
      HadMacro = true;
    } else {
      RecomputeNeedsHandleIdentifier();
    }
  }
  /// \brief Returns true if this identifier was \#defined to some value at any
  /// moment. In this case there should be an entry for the identifier in the
  /// macro history table in Preprocessor.
  bool hadMacroDefinition() const {
    return HadMacro;
  }

  /// getTokenID - If this is a source-language token (e.g. 'for'), this API
  /// can be used to cause the lexer to map identifiers to source-language
  /// tokens.
  tok::TokenKind getTokenID() const { return (tok::TokenKind)TokenID; }

  /// \brief True if RevertTokenIDToIdentifier() was called.
  bool hasRevertedTokenIDToIdentifier() const { return RevertedTokenID; }

  /// \brief Revert TokenID to tok::identifier; used for GNU libstdc++ 4.2
  /// compatibility.
  ///
  /// TokenID is normally read-only but there are 2 instances where we revert it
  /// to tok::identifier for libstdc++ 4.2. Keep track of when this happens
  /// using this method so we can inform serialization about it.
  void RevertTokenIDToIdentifier() {
    assert(TokenID != tok::identifier && "Already at tok::identifier");
    TokenID = tok::identifier;
    RevertedTokenID = true;
  }

  /// \brief Return the preprocessor keyword ID for this identifier.
  ///
  /// For example, "define" will return tok::pp_define.
  tok::PPKeywordKind getPPKeywordID() const;

  /// \brief Return the Objective-C keyword ID for the this identifier.
  ///
  /// For example, 'class' will return tok::objc_class if ObjC is enabled.
  tok::ObjCKeywordKind getObjCKeywordID() const {
    if (ObjCOrBuiltinID < tok::NUM_OBJC_KEYWORDS)
      return tok::ObjCKeywordKind(ObjCOrBuiltinID);
    else
      return tok::objc_not_keyword;
  }
  void setObjCKeywordID(tok::ObjCKeywordKind ID) { ObjCOrBuiltinID = ID; }

  /// getBuiltinID - Return a value indicating whether this is a builtin
  /// function.  0 is not-built-in.  1 is builtin-for-some-nonprimary-target.
  /// 2+ are specific builtin func