[clang] Refactor doc comments to Decls attribution

- Create ASTContext::attachCommentsToJustParsedDecls so we don't have to load external comments in Sema when trying to attach existing comments to just parsed Decls.
- Keep comments ordered and cache their decomposed location - faster SourceLoc-based searching.
- Optimize work with redeclarations.
- Keep one comment per redeclaration chain (represented by canonical Decl) instead of comment per redeclaration.
- For redeclaration chains with no comment attached keep just the last declaration in chain that had no comment instead of every comment-less redeclaration.

Differential Revision: https://reviews.llvm.org/D65301

llvm-svn: 368732

Author: jkorous-apple

clang/include/clang/AST/ASTContext.h

@@ -729,71 +729,49 @@ class ASTContext : public RefCountedBase<ASTContext> {
   /// True if comments are already loaded from ExternalASTSource.
   mutable bool CommentsLoaded = false;
 
-  class RawCommentAndCacheFlags {
-  public:
-    enum Kind {
-      /// We searched for a comment attached to the particular declaration, but
-      /// didn't find any.
-      ///
-      /// getRaw() == 0.
-      NoCommentInDecl = 0,
-
-      /// We have found a comment attached to this particular declaration.
-      ///
-      /// getRaw() != 0.
-      FromDecl,
-
-      /// This declaration does not have an attached comment, and we have
-      /// searched the redeclaration chain.
-      ///
-      /// If getRaw() == 0, the whole redeclaration chain does not have any
-      /// comments.
-      ///
-      /// If getRaw() != 0, it is a comment propagated from other
-      /// redeclaration.
-      FromRedecl
-    };
-
-    Kind getKind() const LLVM_READONLY {
-      return Data.getInt();
-    }
-
-    void setKind(Kind K) {
-      Data.setInt(K);
-    }
-
-    const RawComment *getRaw() const LLVM_READONLY {
-      return Data.getPointer();
-    }
-
-    void setRaw(const RawComment *RC) {
-      Data.setPointer(RC);
-    }
-
-    const Decl *getOriginalDecl() const LLVM_READONLY {
-      return OriginalDecl;
-    }
-
-    void setOriginalDecl(const Decl *Orig) {
-      OriginalDecl = Orig;
-    }
-
-  private:
-    llvm::PointerIntPair<const RawComment *, 2, Kind> Data;
-    const Decl *OriginalDecl;
-  };
+  /// Mapping from declaration to directly attached comment.
+  ///
+  /// Raw comments are owned by Comments list.  This mapping is populated
+  /// lazily.
+  mutable llvm::DenseMap<const Decl *, const RawComment *> DeclRawComments;
 
-  /// Mapping from declarations to comments attached to any
-  /// redeclaration.
+  /// Mapping from canonical declaration to the first redeclaration in chain
+  /// that has a comment attached.
   ///
   /// Raw comments are owned by Comments list.  This mapping is populated
   /// lazily.
-  mutable llvm::DenseMap<const Decl *, RawCommentAndCacheFlags> RedeclComments;
+  mutable llvm::DenseMap<const Decl *, const Decl *> RedeclChainComments;
+
+  /// Keeps track of redeclaration chains that don't have any comment attached.
+  /// Mapping from canonical declaration to redeclaration chain that has no
+  /// comments attached to any redeclaration. Specifically it's mapping to
+  /// the last redeclaration we've checked.
+  ///
+  /// Shall not contain declarations that have comments attached to any
+  /// redeclaration in their chain.
+  mutable llvm::DenseMap<const Decl *, const Decl *> CommentlessRedeclChains;
 
   /// Mapping from declarations to parsed comments attached to any
   /// redeclaration.
   mutable llvm::DenseMap<const Decl *, comments::FullComment *> ParsedComments;
 
+  /// Attaches \p Comment to \p OriginalD and to its redeclaration chain
+  /// and removes the redeclaration chain from the set of commentless chains.
+  ///
+  /// Don't do anything if a comment has already been attached to \p OriginalD
+  /// or its redeclaration chain.
+  void cacheRawCommentForDecl(const Decl &OriginalD,
+                              const RawComment &Comment) const;
+
+  /// \returns searches \p CommentsInFile for doc comment for \p D.
+  ///
+  /// \p RepresentativeLocForDecl is used as a location for searching doc
+  /// comments. \p CommentsInFile is a mapping offset -> comment of files in the
+  /// same file where \p RepresentativeLocForDecl is.
+  RawComment *getRawCommentForDeclNoCacheImpl(
+      const Decl *D, const SourceLocation RepresentativeLocForDecl,
+      const std::map<unsigned, RawComment *> &CommentsInFile) const;
+
   /// Return the documentation comment attached to a given declaration,
   /// without looking into cache.
   RawComment *getRawCommentForDeclNoCache(const Decl *D) const;
@@ -818,6 +796,16 @@ class ASTContext : public RefCountedBase<ASTContext> {
   getRawCommentForAnyRedecl(const Decl *D,
                             const Decl **OriginalDecl = nullptr) const;
 
+  /// Searches existing comments for doc comments that should be attached to \p
+  /// Decls. If any doc comment is found, it is parsed.
+  ///
+  /// Requirement: All \p Decls are in the same file.
+  ///
+  /// If the last comment in the file is already attached we assume
+  /// there are not comments left to be attached to \p Decls.
+  void attachCommentsToJustParsedDecls(ArrayRef<Decl *> Decls,
+                                       const Preprocessor *PP);
+
   /// Return parsed documentation comment attached to a given declaration.
   /// Returns nullptr if no comment is attached.
   ///

clang/include/clang/AST/RawCommentList.h

@@ -10,8 +10,11 @@
 #define LLVM_CLANG_AST_RAWCOMMENTLIST_H
 
 #include "clang/Basic/CommentOptions.h"
+#include "clang/Basic/SourceLocation.h"
 #include "clang/Basic/SourceManager.h"
 #include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/DenseMap.h"
+#include <map>
 
 namespace clang {
 
@@ -196,17 +199,24 @@ class RawCommentList {
   void addComment(const RawComment &RC, const CommentOptions &CommentOpts,
                   llvm::BumpPtrAllocator &Allocator);
 
-  ArrayRef<RawComment *> getComments() const {
-    return Comments;
-  }
+  /// \returns nullptr in case there are no comments in in \p File.
+  const std::map<unsigned, RawComment *> *getCommentsInFile(FileID File) const;
+
+  bool empty() const;
+
+  unsigned getCommentBeginLine(RawComment *C, FileID File,
+                               unsigned Offset) const;
+  unsigned getCommentEndOffset(RawComment *C) const;
 
 private:
   SourceManager &SourceMgr;
-  std::vector<RawComment *> Comments;
-
-  void addDeserializedComments(ArrayRef<RawComment *> DeserializedComments);
+  // mapping: FileId -> comment begin offset -> comment
+  llvm::DenseMap<FileID, std::map<unsigned, RawComment *>> OrderedComments;
+  mutable llvm::DenseMap<RawComment *, unsigned> CommentBeginLine;
+  mutable llvm::DenseMap<RawComment *, unsigned> CommentEndOffset;
 
   friend class ASTReader;
+  friend class ASTWriter;
 };
 
 } // end namespace clang