Add support for retrieving the Doxygen comment associated with a given

declaration in the AST. 

The new ASTContext::getCommentForDecl function searches for a comment
that is attached to the given declaration, and returns that comment, 
which may be composed of several comment blocks.

Comments are always available in an AST. However, to avoid harming
performance, we don't actually parse the comments. Rather, we keep the
source ranges of all of the comments within a large, sorted vector,
then lazily extract comments via a binary search in that vector only
when needed (which never occurs in a "normal" compile).

Comments are written to a precompiled header/AST file as a blob of
source ranges. That blob is only lazily loaded when one requests a
comment for a declaration (this never occurs in a "normal" compile). 

The indexer testbed now supports comment extraction. When the
-point-at location points to a declaration with a Doxygen-style
comment, the indexer testbed prints the associated comment
block(s). See test/Index/comments.c for an example.

Some notes:
  - We don't actually attempt to parse the comment blocks themselves,
  beyond identifying them as Doxygen comment blocks to associate them
  with a declaration.
  - We won't find comment blocks that aren't adjacent to the
  declaration, because we start our search based on the location of
  the declaration.
  - We don't go through the necessary hops to find, for example,
  whether some redeclaration of a declaration has comments when our
  current declaration does not. Similarly, we don't attempt to
  associate a \param Foo marker in a function body comment with the
  parameter named Foo (although that is certainly possible).
  - Verification of my "no performance impact" claims is still "to be
  done".



git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@74704 91177308-0d34-0410-b5e6-96231b3b80d8

include/clang/AST/ASTContext.h

@@ -141,10 +141,19 @@ class ASTContext {
   ///  this ASTContext object.
   LangOptions LangOpts;
 
+  /// \brief Whether we have already loaded comment source ranges from an
+  /// external source.
+  bool LoadedExternalComments;
+  
   /// MallocAlloc/BumpAlloc - The allocator objects used to create AST objects.
   bool FreeMemory;
   llvm::MallocAllocator MallocAlloc;
   llvm::BumpPtrAllocator BumpAlloc;
+  
+  /// \brief Mapping from declarations to their comments, once we have
+  /// already looked up the comment associated with a given declaration.
+  llvm::DenseMap<const Decl *, std::string> DeclComments;
+  
 public:  
   TargetInfo &Target;
   IdentifierTable &Idents;
@@ -154,6 +163,10 @@ public:
   llvm::OwningPtr<ExternalASTSource> ExternalSource;
   clang::PrintingPolicy PrintingPolicy;
 
+  /// \brief Source ranges for all of the comments in the source file,
+  /// sorted in order of appearance in the translation unit.
+  std::vector<SourceRange> Comments;
+  
   SourceManager& getSourceManager() { return SourceMgr; }
   const SourceManager& getSourceManager() const { return SourceMgr; }
   void *Allocate(unsigned Size, unsigned Align = 8) {
@@ -178,7 +191,8 @@ public:
   
   TranslationUnitDecl *getTranslationUnitDecl() const { return TUDecl; }
 
-
+  const char *getCommentForDecl(const Decl *D);
+  
   // Builtin Types.
   QualType VoidTy;
   QualType BoolTy;

include/clang/AST/ExternalASTSource.h

@@ -18,6 +18,7 @@
 #include "clang/AST/Type.h"
 #include "llvm/ADT/SmallVector.h"
 #include <cassert>
+#include <vector>
 namespace clang {
 
 class ASTConsumer;
@@ -57,6 +58,14 @@ public:
 
   virtual ~ExternalASTSource();
 
+  /// \brief Reads the source ranges that correspond to comments from
+  /// an external AST source.
+  ///
+  /// \param Comments the contents of this vector will be
+  /// replaced with the sorted set of source ranges corresponding to
+  /// comments in the source code.
+  virtual void ReadComments(std::vector<SourceRange> &Comments) = 0;
+  
   /// \brief Resolve a type ID into a type, potentially building a new
   /// type.
   virtual QualType GetType(uint32_t ID) = 0;

include/clang/Frontend/PCHBitCodes.h

@@ -218,7 +218,11 @@ namespace clang {
 
       /// \brief Record code for the original file that was used to
       /// generate the precompiled header.
-      ORIGINAL_FILE_NAME = 20
+      ORIGINAL_FILE_NAME = 20,
+      
+      /// \brief Record code for the sorted array of source ranges where
+      /// comments were encountered in the source code.
+      COMMENT_RANGES = 21
     };
 
     /// \brief Record types used within a source manager block.

include/clang/Frontend/PCHReader.h

@@ -279,6 +279,12 @@ private:
   /// been loaded.
   llvm::SmallVector<Selector, 16> SelectorsLoaded;
 
+  /// \brief A sorted array of source ranges containing comments.
+  SourceRange *Comments;
+      
+  /// \brief The number of source ranges in the Comments array.
+  unsigned NumComments;
+      
   /// \brief The set of external definitions stored in the the PCH
   /// file.
   llvm::SmallVector<uint64_t, 16> ExternalDefinitions;
@@ -452,6 +458,14 @@ public:
   /// build prior to including the precompiled header.
   const std::string &getSuggestedPredefines() { return SuggestedPredefines; }
 
+  /// \brief Reads the source ranges that correspond to comments from
+  /// an external AST source.
+  ///
+  /// \param Comments the contents of this vector will be
+  /// replaced with the sorted set of source ranges corresponding to
+  /// comments in the source code.
+  virtual void ReadComments(std::vector<SourceRange> &Comments);
+      
   /// \brief Resolve a type ID into a type, potentially building a new
   /// type.
   virtual QualType GetType(pch::TypeID ID);

include/clang/Frontend/PCHWriter.h

@@ -166,6 +166,7 @@ private:
   void WriteSourceManagerBlock(SourceManager &SourceMgr, 
                                const Preprocessor &PP);
   void WritePreprocessor(const Preprocessor &PP);
+  void WriteComments(ASTContext &Context);
   void WriteType(const Type *T);
   void WriteTypesBlock(ASTContext &Context);
   uint64_t WriteDeclContextLexicalBlock(ASTContext &Context, DeclContext *DC);

include/clang/Lex/Preprocessor.h

@@ -26,6 +26,7 @@
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/OwningPtr.h"
 #include "llvm/Support/Allocator.h"
+#include <vector>
 
 namespace clang {
   
@@ -35,6 +36,7 @@ class FileEntry;
 class HeaderSearch;
 class PragmaNamespace;
 class PragmaHandler;
+class CommentHandler;
 class ScratchBuffer;
 class TargetInfo;
 class PPCallbacks;
@@ -109,6 +111,10 @@ class Preprocessor {
   /// with this preprocessor.
   PragmaNamespace *PragmaHandlers;
   
+  /// \brief Tracks all of the comment handlers that the client registered 
+  /// with this preprocessor.
+  std::vector<CommentHandler *> CommentHandlers;
+  
   /// 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.
@@ -301,6 +307,14 @@ public:
   /// to remove a handler that has not been registered.
   void RemovePragmaHandler(const char *Namespace, PragmaHandler *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);
+  
   /// EnterMainSourceFile - Enter the specified FileID as the main source file,
   /// which implicitly adds the builtin defines etc.
   void EnterMainSourceFile();  
@@ -791,6 +805,7 @@ public:
   void HandlePragmaSystemHeader(Token &SysHeaderTok);
   void HandlePragmaDependency(Token &DependencyTok);
   void HandlePragmaComment(Token &CommentTok);
+  void HandleComment(SourceRange Comment);
 };
 
 /// PreprocessorFactory - A generic factory interface for lazily creating
@@ -801,6 +816,15 @@ public:
   virtual Preprocessor* CreatePreprocessor() = 0;  
 };
   
+/// \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();
+  
+  virtual void HandleComment(Preprocessor &PP, SourceRange Comment) = 0;
+};
+  
 }  // end namespace clang
 
 #endif

include/clang/Parse/Action.h

@@ -152,6 +152,10 @@ public:
   /// an empty string if not.  This is used for pretty crash reporting. 
   virtual std::string getDeclName(DeclPtrTy D) { return ""; }
   
+  /// \brief Invoked for each comment in the source code, providing the source
+  /// range that contains the comment.
+  virtual void ActOnComment(SourceRange Comment) { }
+  
   //===--------------------------------------------------------------------===//
   // Declaration Tracking Callbacks.
   //===--------------------------------------------------------------------===//

include/clang/Parse/Parser.h

@@ -82,7 +82,8 @@ class Parser {
   llvm::OwningPtr<PragmaHandler> PackHandler;
   llvm::OwningPtr<PragmaHandler> UnusedHandler;
   llvm::OwningPtr<PragmaHandler> WeakHandler;
-
+  llvm::OwningPtr<clang::CommentHandler> CommentHandler;
+  
   /// Whether the '>' token acts as an operator or not. This will be
   /// true except when we are parsing an expression within a C++
   /// template argument list, where the '>' closes the template

lib/AST/ASTContext.cpp

@@ -37,7 +37,8 @@ ASTContext::ASTContext(const LangOptions& LOpts, SourceManager &SM,
                        bool FreeMem, unsigned size_reserve) : 
   GlobalNestedNameSpecifier(0), CFConstantStringTypeDecl(0), 
   ObjCFastEnumerationStateTypeDecl(0), SourceMgr(SM), LangOpts(LOpts), 
-  FreeMemory(FreeMem), Target(t), Idents(idents), Selectors(sels),
+  LoadedExternalComments(false), FreeMemory(FreeMem), Target(t), 
+  Idents(idents), Selectors(sels),
   BuiltinInfo(builtins), ExternalSource(0), PrintingPolicy(LOpts) {  
   if (size_reserve > 0) Types.reserve(size_reserve);    
   InitBuiltinTypes();
@@ -202,6 +203,207 @@ void ASTContext::InitBuiltinTypes() {
   InitBuiltinType(NullPtrTy,           BuiltinType::NullPtr);
 }
 
+namespace {
+  class BeforeInTranslationUnit 
+    : std::binary_function<SourceRange, SourceRange, bool> {
+    SourceManager *SourceMgr;
+    
+  public:
+    explicit BeforeInTranslationUnit(SourceManager *SM) : SourceMgr(SM) { }
+      
+    bool operator()(SourceRange X, SourceRange Y) {
+      return SourceMgr->isBeforeInTranslationUnit(X.getBegin(), Y.getBegin());
+    }
+  };
+}
+
+/// \brief Determine whether the given comment is a Doxygen-style comment.
+///
+/// \param Start the start of the comment text.
+///
+/// \param End the end of the comment text.
+///
+/// \param Member whether we want to check whether this is a member comment
+/// (which requires a < after the Doxygen-comment delimiter). Otherwise,
+/// we only return true when we find a non-member comment.
+static bool 
+isDoxygenComment(SourceManager &SourceMgr, SourceRange Comment, 
+                 bool Member = false) {
+  const char *BufferStart 
+    = SourceMgr.getBufferData(SourceMgr.getFileID(Comment.getBegin())).first;
+  const char *Start = BufferStart + SourceMgr.getFileOffset(Comment.getBegin());
+  const char* End = BufferStart + SourceMgr.getFileOffset(Comment.getEnd());
+  
+  if (End - Start < 4)
+    return false;
+
+  assert(Start[0] == '/' && "Not a comment?");
+  if (Start[1] == '*' && !(Start[2] == '!' || Start[2] == '*'))
+    return false;
+  if (Start[1] == '/' && !(Start[2] == '!' || Start[2] == '/'))
+    return false;
+
+  return (Start[3] == '<') == Member;
+}
+
+/// \brief Retrieve the comment associated with the given declaration, if
+/// it has one. 
+const char *ASTContext::getCommentForDecl(const Decl *D) {
+  if (!D)
+    return 0;
+  
+  // Check whether we have cached a comment string for this declaration
+  // already.
+  llvm::DenseMap<const Decl *, std::string>::iterator Pos 
+    = DeclComments.find(D);
+  if (Pos != DeclComments.end())
+    return Pos->second.c_str();
+
+  // If we have an external AST source and have not yet loaded comments from 
+  // that source, do so now.
+  if (ExternalSource && !LoadedExternalComments) {
+    std::vector<SourceRange> LoadedComments;
+    ExternalSource->ReadComments(LoadedComments);
+    
+    if (!LoadedComments.empty())
+      Comments.insert(Comments.begin(), LoadedComments.begin(),
+                      LoadedComments.end());
+    
+    LoadedExternalComments = true;
+  }
+  
+  // If there are no comments anywhere, we won't find anything.  
+  if (Comments.empty())
+    return 0;
+
+  // If the declaration doesn't map directly to a location in a file, we
+  // can't find the comment.
+  SourceLocation DeclStartLoc = D->getLocStart();
+  if (DeclStartLoc.isInvalid() || !DeclStartLoc.isFileID())
+    return 0;
+
+  // Find the comment that occurs just before this declaration.
+  std::vector<SourceRange>::iterator LastComment
+    = std::lower_bound(Comments.begin(), Comments.end(), 
+                       SourceRange(DeclStartLoc),
+                       BeforeInTranslationUnit(&SourceMgr));
+  
+  // Decompose the location for the start of the declaration and find the
+  // beginning of the file buffer.
+  std::pair<FileID, unsigned> DeclStartDecomp 
+    = SourceMgr.getDecomposedLoc(DeclStartLoc);
+  const char *FileBufferStart 
+    = SourceMgr.getBufferData(DeclStartDecomp.first).first;
+  
+  // First check whether we have a comment for a member.
+  if (LastComment != Comments.end() &&
+      !isa<TagDecl>(D) && !isa<NamespaceDecl>(D) &&
+      isDoxygenComment(SourceMgr, *LastComment, true)) {
+    std::pair<FileID, unsigned> LastCommentEndDecomp
+      = SourceMgr.getDecomposedLoc(LastComment->getEnd());
+    if (DeclStartDecomp.first == LastCommentEndDecomp.first &&
+        SourceMgr.getLineNumber(DeclStartDecomp.first, DeclStartDecomp.second)
+          == SourceMgr.getLineNumber(LastCommentEndDecomp.first, 
+                                     LastCommentEndDecomp.second)) {
+      // The Doxygen member comment comes after the declaration starts and
+      // is on the same line and in the same file as the declaration. This
+      // is the comment we want.
+      std::string &Result = DeclComments[D];
+      Result.append(FileBufferStart + 
+                      SourceMgr.getFileOffset(LastComment->getBegin()), 
+                    FileBufferStart + LastCommentEndDecomp.second + 1);
+      return Result.c_str();
+    }
+  }
+  
+  if (LastComment == Comments.begin())
+    return 0;
+  --LastComment;
+
+  // Decompose the end of the comment.
+  std::pair<FileID, unsigned> LastCommentEndDecomp
+    = SourceMgr.getDecomposedLoc(LastComment->getEnd());
+  
+  // If the comment and the declaration aren't in the same file, then they
+  // aren't related.
+  if (DeclStartDecomp.first != LastCommentEndDecomp.first)
+    return 0;
+  
+  // Check that we actually have a Doxygen comment.
+  if (!isDoxygenComment(SourceMgr, *LastComment))
+    return 0;
+      
+  // Compute the starting line for the declaration and for the end of the
+  // comment (this is expensive).
+  unsigned DeclStartLine 
+    = SourceMgr.getLineNumber(DeclStartDecomp.first, DeclStartDecomp.second);
+  unsigned CommentEndLine
+    = SourceMgr.getLineNumber(LastCommentEndDecomp.first, 
+                              LastCommentEndDecomp.second);
+  
+  // If the comment does not end on the line prior to the declaration, then
+  // the comment is not associated with the declaration at all.
+  if (CommentEndLine + 1 != DeclStartLine)
+    return 0;
+  
+  // We have a comment, but there may be more comments on the previous lines.
+  // Keep looking so long as the comments are still Doxygen comments and are
+  // still adjacent.
+  unsigned ExpectedLine 
+    = SourceMgr.getSpellingLineNumber(LastComment->getBegin()) - 1;
+  std::vector<SourceRange>::iterator FirstComment = LastComment;
+  while (FirstComment != Comments.begin()) {
+    // Look at the previous comment
+    --FirstComment;
+    std::pair<FileID, unsigned> Decomp
+      = SourceMgr.getDecomposedLoc(FirstComment->getEnd());
+    
+    // If this previous comment is in a different file, we're done.
+    if (Decomp.first != DeclStartDecomp.first) {
+      ++FirstComment;
+      break;
+    }
+    
+    // If this comment is not a Doxygen comment, we're done.
+    if (!isDoxygenComment(SourceMgr, *FirstComment)) {
+      ++FirstComment;
+      break;
+    }
+    
+    // If the line number is not what we expected, we're done.
+    unsigned Line = SourceMgr.getLineNumber(Decomp.first, Decomp.second);
+    if (Line != ExpectedLine) {
+      ++FirstComment;
+      break;
+    }
+    
+    // Set the next expected line number.
+    ExpectedLine 
+      = SourceMgr.getSpellingLineNumber(FirstComment->getBegin()) - 1;
+  }
+  
+  // The iterator range [FirstComment, LastComment] contains all of the
+  // BCPL comments that, together, are associated with this declaration.
+  // Form a single comment block string for this declaration that concatenates
+  // all of these comments.
+  std::string &Result = DeclComments[D];
+  while (FirstComment != LastComment) {
+    std::pair<FileID, unsigned> DecompStart
+      = SourceMgr.getDecomposedLoc(FirstComment->getBegin());
+    std::pair<FileID, unsigned> DecompEnd
+      = SourceMgr.getDecomposedLoc(FirstComment->getEnd());
+    Result.append(FileBufferStart + DecompStart.second,
+                  FileBufferStart + DecompEnd.second + 1);
+    ++FirstComment;
+  }
+  
+  // Append the last comment line.
+  Result.append(FileBufferStart + 
+                  SourceMgr.getFileOffset(LastComment->getBegin()), 
+                FileBufferStart + LastCommentEndDecomp.second + 1);
+  return Result.c_str();
+}
+
 //===----------------------------------------------------------------------===//
 //                         Type Sizing and Analysis
 //===----------------------------------------------------------------------===//

lib/Frontend/PCHReader.cpp

@@ -344,7 +344,8 @@ PCHReader::PCHReader(Preprocessor &PP, ASTContext *Context)
     IdentifierOffsets(0),
     MethodPoolLookupTable(0), MethodPoolLookupTableData(0),
     TotalSelectorsInMethodPool(0), SelectorOffsets(0),
-    TotalNumSelectors(0), NumStatHits(0), NumStatMisses(0), 
+    TotalNumSelectors(0), Comments(0), NumComments(0), 
+    NumStatHits(0), NumStatMisses(0), 
     NumSLocEntriesRead(0), NumStatementsRead(0), 
     NumMacrosRead(0), NumMethodPoolSelectorsRead(0), NumMethodPoolMisses(0),
     NumLexicalDeclContextsRead(0), NumVisibleDeclContextsRead(0) { }
@@ -1350,6 +1351,11 @@ PCHReader::ReadPCHBlock() {
     case pch::ORIGINAL_FILE_NAME:
       OriginalFileName.assign(BlobStart, BlobLen);
       break;
+        
+    case pch::COMMENT_RANGES:
+      Comments = (SourceRange *)BlobStart;
+      NumComments = BlobLen / sizeof(SourceRange);
+      break;
     }
   }
   Error("premature end of bitstream in PCH file");
@@ -1664,6 +1670,12 @@ bool PCHReader::ParseLanguageOptions(
   return false;
 }
 
+void PCHReader::ReadComments(std::vector<SourceRange> &Comments) {
+  Comments.resize(NumComments);
+  std::copy(this->Comments, this->Comments + NumComments,
+            Comments.begin());
+}
+
 /// \brief Read and return the type at the given offset.
 ///
 /// This routine actually reads the record corresponding to the type

lib/Frontend/PCHWriter.cpp

@@ -374,7 +374,8 @@ void PCHWriter::WriteBlockInfoBlock() {
   RECORD(STAT_CACHE);
   RECORD(EXT_VECTOR_DECLS);
   RECORD(OBJC_CATEGORY_IMPLEMENTATIONS);
-
+  RECORD(COMMENT_RANGES);
+  
   // SourceManager Block.
   BLOCK(SOURCE_MANAGER_BLOCK);
   RECORD(SM_SLOC_FILE_ENTRY);
@@ -989,6 +990,24 @@ void PCHWriter::WritePreprocessor(const Preprocessor &PP) {
   Stream.ExitBlock();
 }
 
+void PCHWriter::WriteComments(ASTContext &Context) {
+  using namespace llvm;
+  
+  if (Context.Comments.empty())
+    return;
+  
+  BitCodeAbbrev *CommentAbbrev = new BitCodeAbbrev();
+  CommentAbbrev->Add(BitCodeAbbrevOp(pch::COMMENT_RANGES));
+  CommentAbbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob));
+  unsigned CommentCode = Stream.EmitAbbrev(CommentAbbrev);
+  
+  RecordData Record;
+  Record.push_back(pch::COMMENT_RANGES);
+  Stream.EmitRecordWithBlob(CommentCode, Record, 
+                            (const char*)&Context.Comments[0],
+                            Context.Comments.size() * sizeof(SourceRange));
+}
+
 //===----------------------------------------------------------------------===//
 // Type Serialization
 //===----------------------------------------------------------------------===//
@@ -1746,7 +1765,8 @@ void PCHWriter::WritePCH(Sema &SemaRef, MemorizeStatCalls *StatCalls) {
     WriteStatCache(*StatCalls);
   WriteSourceManagerBlock(Context.getSourceManager(), PP);
   WritePreprocessor(PP);
-
+  WriteComments(Context);  
+  
   // Keep writing types and declarations until all types and
   // declarations have been written.
   do {

lib/Lex/Lexer.cpp

@@ -903,7 +903,10 @@ bool Lexer::SkipBCPLComment(Token &Result, const char *CurPtr) {
   } while (C != '\n' && C != '\r');
 
   // Found but did not consume the newline.
-    
+  if (PP)
+    PP->HandleComment(SourceRange(getSourceLocation(BufferPtr), 
+                                  getSourceLocation(CurPtr)));
+                   
   // If we are returning comments as tokens, return this comment as a token.
   if (inKeepCommentMode())
     return SaveBCPLComment(Result, CurPtr);
@@ -1146,6 +1149,10 @@ bool Lexer::SkipBlockComment(Token &Result, const char *CurPtr) {
     C = *CurPtr++;
   }
   
+  if (PP) 
+    PP->HandleComment(SourceRange(getSourceLocation(BufferPtr), 
+                                  getSourceLocation(CurPtr)));
+
   // If we are returning comments as tokens, return this comment as a token.
   if (inKeepCommentMode()) {
     FormTokenWithChars(Result, CurPtr, tok::comment);

lib/Lex/Pragma.cpp

@@ -19,6 +19,7 @@
 #include "clang/Lex/LexDiagnostic.h"
 #include "clang/Basic/FileManager.h"
 #include "clang/Basic/SourceManager.h"
+#include <algorithm>
 using namespace clang;
 
 // Out-of-line destructor to provide a home for the class.

lib/Lex/Preprocessor.cpp

@@ -476,3 +476,26 @@ void Preprocessor::HandleIdentifier(Token &Identifier) {
   if (II.isExtensionToken() && !DisableMacroExpansion)
     Diag(Identifier, diag::ext_token_used);
 }
+
+void Preprocessor::AddCommentHandler(CommentHandler *Handler) {
+  assert(Handler && "NULL comment handler");
+  assert(std::find(CommentHandlers.begin(), CommentHandlers.end(), Handler) ==
+         CommentHandlers.end() && "Comment handler already registered");
+  CommentHandlers.push_back(Handler);
+}
+
+void Preprocessor::RemoveCommentHandler(CommentHandler *Handler) {
+  std::vector<CommentHandler *>::iterator Pos
+  = std::find(CommentHandlers.begin(), CommentHandlers.end(), Handler);
+  assert(Pos != CommentHandlers.end() && "Comment handler not registered");
+  CommentHandlers.erase(Pos);
+}
+
+void Preprocessor::HandleComment(SourceRange Comment) {
+  for (std::vector<CommentHandler *>::iterator H = CommentHandlers.begin(),
+       HEnd = CommentHandlers.end();
+       H != HEnd; ++H)
+    (*H)->HandleComment(*this, Comment);
+}
+
+CommentHandler::~CommentHandler() { }

lib/Parse/Parser.cpp

@@ -20,6 +20,19 @@
 #include "ParsePragma.h"
 using namespace clang;
 
+/// \brief A comment handler that passes comments found by the preprocessor
+/// to the parser action.
+class ActionCommentHandler : public CommentHandler {
+  Action &Actions;
+  
+public:
+  explicit ActionCommentHandler(Action &Actions) : Actions(Actions) { }
+  
+  virtual void HandleComment(Preprocessor &PP, SourceRange Comment) {
+    Actions.ActOnComment(Comment);
+  }
+};
+
 Parser::Parser(Preprocessor &pp, Action &actions)
   : CrashInfo(*this), PP(pp), Actions(actions), Diags(PP.getDiagnostics()), 
     GreaterThanIsOperator(true) {
@@ -43,6 +56,9 @@ Parser::Parser(Preprocessor &pp, Action &actions)
   WeakHandler.reset(new
           PragmaWeakHandler(&PP.getIdentifierTable().get("weak"), actions));
   PP.AddPragmaHandler(0, WeakHandler.get());
+      
+  CommentHandler.reset(new ActionCommentHandler(actions));
+  PP.AddCommentHandler(CommentHandler.get());    
 }
 
 /// If a crash happens while the parser is active, print out a line indicating
@@ -294,6 +310,7 @@ Parser::~Parser() {
   UnusedHandler.reset();
   PP.RemovePragmaHandler(0, WeakHandler.get());
   WeakHandler.reset();
+  PP.RemoveCommentHandler(CommentHandler.get());
 }
 
 /// Initialize - Warm up the parser.

lib/Sema/Sema.cpp

@@ -345,3 +345,7 @@ Sema::SemaDiagnosticBuilder::~SemaDiagnosticBuilder() {
       = SemaRef.ActiveTemplateInstantiations.back();
   }
 }
+
+void Sema::ActOnComment(SourceRange Comment) {
+  Context.Comments.push_back(Comment);
+}

lib/Sema/Sema.h

@@ -362,6 +362,8 @@ public:
     return CurBlock ? CurBlock->SwitchStack : FunctionSwitchStack;
   }
   
+  virtual void ActOnComment(SourceRange Comment);
+
   //===--------------------------------------------------------------------===//
   // Type Analysis / Processing: SemaType.cpp.
   //

test/CMakeLists.txt

@@ -8,6 +8,7 @@ set(CLANG_TEST_DIRECTORIES
   "Driver"
   "FixIt"
   "Frontend"
+  "Index"
   "Lexer"
   "Misc"
   "PCH"
@@ -54,6 +55,6 @@ if(PYTHONINTERP_FOUND)
     --clang-cc=${LLVM_TOOLS_PATH}/${CMAKE_CFG_INTDIR}/clang-cc
     ${all_testdirs}
     WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
-    DEPENDS clang clang-cc
+    DEPENDS clang clang-cc index-test
     COMMENT "Running Clang regression tests")
 endif()  

test/Index/comments.c

@@ -0,0 +1,30 @@
+// RUN: clang-cc -emit-pch -o %t.ast %s &&
+// RUN: index-test %t.ast -point-at %s:22:6 | grep "starts here" &&
+// RUN: index-test %t.ast -point-at %s:22:6 | grep "block comment" &&
+// RUN: index-test %t.ast -point-at %s:28:6 | grep "BCPL" &&
+// RUN: index-test %t.ast -point-at %s:28:6 | grep "But" &&
+// RUN: index-test %t.ast -point-at %s:28:6 | grep "NOT" | count 0 &&
+// RUN: index-test %t.ast -point-at %s:30:6 | grep "member"
+
+
+
+
+
+
+//! It all starts here.
+/*! It's a little odd to continue line this,
+ *
+ * but we need more multi-line comments. */
+/// This comment comes before my other comments
+/** This is a block comment that is associated with the function f. It
+ *  runs for three lines.
+ */
+void f(int, int);
+
+// NOT IN THE COMMENT
+/// This is a BCPL comment that is associated with the function g.
+/// It has only two lines.
+/** But there are other blocks that are part of the comment, too. */
+void g(int);
+
+void h(int); ///< This is a member comment.

tools/index-test/index-test.cpp

@@ -130,6 +130,9 @@ int main(int argc, char **argv) {
       OS << ND->getNameAsString();
     OS << "\n";
     
+    if (const char *Comment = AST->getASTContext().getCommentForDecl(Point.D))
+      OS << "Comment associated with this declaration:\n" << Comment << "\n";
+        
     if (Point.Node) {
       OS << "Statement node at point: " << Point.Node->getStmtClassName()
          << " ";