C++ StringRef::edit_distance方法代码示例

static unsigned getCallEditDistance(DeclName writtenName,
                                    DeclName correctedName,
                                    unsigned maxEditDistance) {
  // TODO: consider arguments.
  // TODO: maybe ignore certain kinds of missing / present labels for the
  //   first argument label?
  // TODO: word-based rather than character-based?
  if (writtenName.getBaseName().getKind() !=
        correctedName.getBaseName().getKind()) {
    return UnreasonableCallEditDistance;
  }

  if (writtenName.getBaseName().getKind() != DeclBaseName::Kind::Normal) {
    return 0;
  }

  StringRef writtenBase = writtenName.getBaseName().userFacingName();
  StringRef correctedBase = correctedName.getBaseName().userFacingName();

  unsigned distance = writtenBase.edit_distance(correctedBase, maxEditDistance);

  // Bound the distance to UnreasonableCallEditDistance.
  if (distance >= maxEditDistance ||
      distance > (correctedBase.size() + 2) / 3) {
    return UnreasonableCallEditDistance;
  }

  return distance;
}

unsigned Pattern::ComputeMatchDistance(StringRef Buffer,
                              const StringMap<StringRef> &VariableTable) const {
  // Just compute the number of matching characters. For regular expressions, we
  // just compare against the regex itself and hope for the best.
  //
  // FIXME: One easy improvement here is have the regex lib generate a single
  // example regular expression which matches, and use that as the example
  // string.
  StringRef ExampleString(FixedStr);
  if (ExampleString.empty())
    ExampleString = RegExStr;

  // Only compare up to the first line in the buffer, or the string size.
  StringRef BufferPrefix = Buffer.substr(0, ExampleString.size());
  BufferPrefix = BufferPrefix.split('\n').first;
  return BufferPrefix.edit_distance(ExampleString);
}

static unsigned getCallEditDistance(DeclName argName, DeclName paramName,
                                    unsigned maxEditDistance) {
  // TODO: consider arguments.
  // TODO: maybe ignore certain kinds of missing / present labels for the
  //   first argument label?
  // TODO: word-based rather than character-based?
  StringRef argBase = argName.getBaseName().str();
  StringRef paramBase = paramName.getBaseName().str();

  unsigned distance = argBase.edit_distance(paramBase, maxEditDistance);

  // Bound the distance to UnreasonableCallEditDistance.
  if (distance >= maxEditDistance ||
      distance > (paramBase.size() + 2) / 3) {
    return UnreasonableCallEditDistance;
  }

  return distance;
}

static void
HelperTypoCorrectCommandInfo(SmallVectorImpl<const CommandInfo *> &BestCommand,
                             StringRef Typo, const CommandInfo *Command) {
  const unsigned MaxEditDistance = 1;
  unsigned BestEditDistance = MaxEditDistance + 1;
  StringRef Name = Command->Name;
  
  unsigned MinPossibleEditDistance = abs((int)Name.size() - (int)Typo.size());
  if (MinPossibleEditDistance > 0 &&
      Typo.size() / MinPossibleEditDistance < 1)
    return;
  unsigned EditDistance = Typo.edit_distance(Name, true, MaxEditDistance);
  if (EditDistance > MaxEditDistance)
    return;
  if (EditDistance == BestEditDistance)
    BestCommand.push_back(Command);
  else if (EditDistance < BestEditDistance) {
    BestCommand.clear();
    BestCommand.push_back(Command);
    BestEditDistance = EditDistance;
  }
}

//.........这里部分代码省略.........
    if (!Module) {
      // If we loaded the module directly, without finding a module map first,
      // we'll have loaded the module's information from the module itself.
      Module = PP->getHeaderSearchInfo().getModuleMap()
                 .findModule((Path[0].first->getName()));
    }

    if (Module)
      Module->setASTFile(ModuleFile);
    
    // Cache the result of this top-level module lookup for later.
    Known = KnownModules.insert(std::make_pair(Path[0].first, Module)).first;
  }
  
  // If we never found the module, fail.
  if (!Module)
    return ModuleLoadResult();
  
  // Verify that the rest of the module path actually corresponds to
  // a submodule.
  if (Path.size() > 1) {
    for (unsigned I = 1, N = Path.size(); I != N; ++I) {
      StringRef Name = Path[I].first->getName();
      clang::Module *Sub = Module->findSubmodule(Name);
      
      if (!Sub) {
        // Attempt to perform typo correction to find a module name that works.
        llvm::SmallVector<StringRef, 2> Best;
        unsigned BestEditDistance = (std::numeric_limits<unsigned>::max)();
        
        for (clang::Module::submodule_iterator J = Module->submodule_begin(), 
                                            JEnd = Module->submodule_end();
             J != JEnd; ++J) {
          unsigned ED = Name.edit_distance((*J)->Name,
                                           /*AllowReplacements=*/true,
                                           BestEditDistance);
          if (ED <= BestEditDistance) {
            if (ED < BestEditDistance) {
              Best.clear();
              BestEditDistance = ED;
            }
            
            Best.push_back((*J)->Name);
          }
        }
        
        // If there was a clear winner, user it.
        if (Best.size() == 1) {
          getDiagnostics().Report(Path[I].second, 
                                  diag::err_no_submodule_suggest)
            << Path[I].first << Module->getFullModuleName() << Best[0]
            << SourceRange(Path[0].second, Path[I-1].second)
            << FixItHint::CreateReplacement(SourceRange(Path[I].second),
                                            Best[0]);
          
          Sub = Module->findSubmodule(Best[0]);
        }
      }
      
      if (!Sub) {
        // No submodule by this name. Complain, and don't look for further
        // submodules.
        getDiagnostics().Report(Path[I].second, diag::err_no_submodule)
          << Path[I].first << Module->getFullModuleName()
          << SourceRange(Path[0].second, Path[I-1].second);
        break;

/// HandleEndOfFile - This callback is invoked when the lexer hits the end of
/// the current file.  This either returns the EOF token or pops a level off
/// the include stack and keeps going.
bool Preprocessor::HandleEndOfFile(Token &Result, bool isEndOfMacro) {
  assert(!CurTokenLexer &&
         "Ending a file when currently in a macro!");

  // See if this file had a controlling macro.
  if (CurPPLexer) {  // Not ending a macro, ignore it.
    if (const IdentifierInfo *ControllingMacro =
          CurPPLexer->MIOpt.GetControllingMacroAtEndOfFile()) {
      // Okay, this has a controlling macro, remember in HeaderFileInfo.
      if (const FileEntry *FE =
            SourceMgr.getFileEntryForID(CurPPLexer->getFileID())) {
        HeaderInfo.SetFileControllingMacro(FE, ControllingMacro);
        if (MacroInfo *MI =
              getMacroInfo(const_cast<IdentifierInfo*>(ControllingMacro))) {
          MI->UsedForHeaderGuard = true;
        }
        if (const IdentifierInfo *DefinedMacro =
              CurPPLexer->MIOpt.GetDefinedMacro()) {
          if (!ControllingMacro->hasMacroDefinition() &&
              DefinedMacro != ControllingMacro &&
              HeaderInfo.FirstTimeLexingFile(FE)) {

            // If the edit distance between the two macros is more than 50%,
            // DefinedMacro may not be header guard, or can be header guard of
            // another header file. Therefore, it maybe defining something
            // completely different. This can be observed in the wild when
            // handling feature macros or header guards in different files.

            const StringRef ControllingMacroName = ControllingMacro->getName();
            const StringRef DefinedMacroName = DefinedMacro->getName();
            const size_t MaxHalfLength = std::max(ControllingMacroName.size(),
                                                  DefinedMacroName.size()) / 2;
            const unsigned ED = ControllingMacroName.edit_distance(
                DefinedMacroName, true, MaxHalfLength);
            if (ED <= MaxHalfLength) {
              // Emit a warning for a bad header guard.
              Diag(CurPPLexer->MIOpt.GetMacroLocation(),
                   diag::warn_header_guard)
                  << CurPPLexer->MIOpt.GetMacroLocation() << ControllingMacro;
              Diag(CurPPLexer->MIOpt.GetDefinedLocation(),
                   diag::note_header_guard)
                  << CurPPLexer->MIOpt.GetDefinedLocation() << DefinedMacro
                  << ControllingMacro
                  << FixItHint::CreateReplacement(
                         CurPPLexer->MIOpt.GetDefinedLocation(),
                         ControllingMacro->getName());
            }
          }
        }
      }
    }
  }

  // Complain about reaching a true EOF within arc_cf_code_audited.
  // We don't want to complain about reaching the end of a macro
  // instantiation or a _Pragma.
  if (PragmaARCCFCodeAuditedLoc.isValid() &&
      !isEndOfMacro && !(CurLexer && CurLexer->Is_PragmaLexer)) {
    Diag(PragmaARCCFCodeAuditedLoc, diag::err_pp_eof_in_arc_cf_code_audited);

    // Recover by leaving immediately.
    PragmaARCCFCodeAuditedLoc = SourceLocation();
  }

  // If this is a #include'd file, pop it off the include stack and continue
  // lexing the #includer file.
  if (!IncludeMacroStack.empty()) {

    // If we lexed the code-completion file, act as if we reached EOF.
    if (isCodeCompletionEnabled() && CurPPLexer &&
        SourceMgr.getLocForStartOfFile(CurPPLexer->getFileID()) ==
            CodeCompletionFileLoc) {
      if (CurLexer) {
        Result.startToken();
        CurLexer->FormTokenWithChars(Result, CurLexer->BufferEnd, tok::eof);
        CurLexer.reset();
      } else {
        assert(CurPTHLexer && "Got EOF but no current lexer set!");
        CurPTHLexer->getEOF(Result);
        CurPTHLexer.reset();
      }

      CurPPLexer = nullptr;
      return true;
    }

    if (!isEndOfMacro && CurPPLexer &&
        SourceMgr.getIncludeLoc(CurPPLexer->getFileID()).isValid()) {
      // Notify SourceManager to record the number of FileIDs that were created
      // during lexing of the #include'd file.
      unsigned NumFIDs =
          SourceMgr.local_sloc_entry_size() -
          CurPPLexer->getInitialNumSLocEntries() + 1/*#include'd file*/;
      SourceMgr.setNumCreatedFIDsForFileID(CurPPLexer->getFileID(), NumFIDs);
    }

    FileID ExitedFID;
//.........这里部分代码省略.........

/// HandleEndOfFile - This callback is invoked when the lexer hits the end of
/// the current file.  This either returns the EOF token or pops a level off
/// the include stack and keeps going.
bool Preprocessor::HandleEndOfFile(Token &Result, bool isEndOfMacro) {
  assert(!CurTokenLexer &&
         "Ending a file when currently in a macro!");

  // If we have an unclosed module region from a pragma at the end of a
  // module, complain and close it now.
  // FIXME: This is not correct if we are building a module from PTH.
  const bool LeavingSubmodule = CurLexer && CurLexerSubmodule;
  if ((LeavingSubmodule || IncludeMacroStack.empty()) &&
      !BuildingSubmoduleStack.empty() &&
      BuildingSubmoduleStack.back().IsPragma) {
    Diag(BuildingSubmoduleStack.back().ImportLoc,
         diag::err_pp_module_begin_without_module_end);
    Module *M = LeaveSubmodule(/*ForPragma*/true);

    Result.startToken();
    const char *EndPos = getCurLexerEndPos();
    CurLexer->BufferPtr = EndPos;
    CurLexer->FormTokenWithChars(Result, EndPos, tok::annot_module_end);
    Result.setAnnotationEndLoc(Result.getLocation());
    Result.setAnnotationValue(M);
    return true;
  }

  // See if this file had a controlling macro.
  if (CurPPLexer) {  // Not ending a macro, ignore it.
    if (const IdentifierInfo *ControllingMacro =
          CurPPLexer->MIOpt.GetControllingMacroAtEndOfFile()) {
      // Okay, this has a controlling macro, remember in HeaderFileInfo.
      if (const FileEntry *FE = CurPPLexer->getFileEntry()) {
        HeaderInfo.SetFileControllingMacro(FE, ControllingMacro);
        if (MacroInfo *MI =
              getMacroInfo(const_cast<IdentifierInfo*>(ControllingMacro)))
          MI->setUsedForHeaderGuard(true);
        if (const IdentifierInfo *DefinedMacro =
              CurPPLexer->MIOpt.GetDefinedMacro()) {
          if (!isMacroDefined(ControllingMacro) &&
              DefinedMacro != ControllingMacro &&
              HeaderInfo.FirstTimeLexingFile(FE)) {

            // If the edit distance between the two macros is more than 50%,
            // DefinedMacro may not be header guard, or can be header guard of
            // another header file. Therefore, it maybe defining something
            // completely different. This can be observed in the wild when
            // handling feature macros or header guards in different files.

            const StringRef ControllingMacroName = ControllingMacro->getName();
            const StringRef DefinedMacroName = DefinedMacro->getName();
            const size_t MaxHalfLength = std::max(ControllingMacroName.size(),
                                                  DefinedMacroName.size()) / 2;
            const unsigned ED = ControllingMacroName.edit_distance(
                DefinedMacroName, true, MaxHalfLength);
            if (ED <= MaxHalfLength) {
              // Emit a warning for a bad header guard.
              Diag(CurPPLexer->MIOpt.GetMacroLocation(),
                   diag::warn_header_guard)
                  << CurPPLexer->MIOpt.GetMacroLocation() << ControllingMacro;
              Diag(CurPPLexer->MIOpt.GetDefinedLocation(),
                   diag::note_header_guard)
                  << CurPPLexer->MIOpt.GetDefinedLocation() << DefinedMacro
                  << ControllingMacro
                  << FixItHint::CreateReplacement(
                         CurPPLexer->MIOpt.GetDefinedLocation(),
                         ControllingMacro->getName());
            }
          }
        }
      }
    }
  }

  // Complain about reaching a true EOF within arc_cf_code_audited.
  // We don't want to complain about reaching the end of a macro
  // instantiation or a _Pragma.
  if (PragmaARCCFCodeAuditedLoc.isValid() &&
      !isEndOfMacro && !(CurLexer && CurLexer->Is_PragmaLexer)) {
    Diag(PragmaARCCFCodeAuditedLoc, diag::err_pp_eof_in_arc_cf_code_audited);

    // Recover by leaving immediately.
    PragmaARCCFCodeAuditedLoc = SourceLocation();
  }

  // Complain about reaching a true EOF within assume_nonnull.
  // We don't want to complain about reaching the end of a macro
  // instantiation or a _Pragma.
  if (PragmaAssumeNonNullLoc.isValid() &&
      !isEndOfMacro && !(CurLexer && CurLexer->Is_PragmaLexer)) {
    Diag(PragmaAssumeNonNullLoc, diag::err_pp_eof_in_assume_nonnull);

    // Recover by leaving immediately.
    PragmaAssumeNonNullLoc = SourceLocation();
  }

  bool LeavingPCHThroughHeader = false;

  // If this is a #include'd file, pop it off the include stack and continue
  // lexing the #includer file.
//.........这里部分代码省略.........