1 files changed, 23 insertions, 3 deletions
diff --git a/clang/include/clang/Tooling/Syntax/Tokens.h b/clang/include/clang/Tooling/Syntax/Tokens.h
index 301432d3888b..a210815d49f9 100644
--- a/clang/include/clang/Tooling/Syntax/Tokens.h
+++ b/clang/include/clang/Tooling/Syntax/Tokens.h
@@ -78,6 +78,10 @@ struct FileRange {
   /// Gets the substring that this FileRange refers to.
   llvm::StringRef text(const SourceManager &SM) const;
 
+  /// Convert to the clang range. The returned range is always a char range,
+  /// never a token range.
+  CharSourceRange toCharRange(const SourceManager &SM) const;
+
   friend bool operator==(const FileRange &L, const FileRange &R) {
     return std::tie(L.File, L.Begin, L.End) == std::tie(R.File, R.Begin, R.End);
   }
@@ -175,6 +179,7 @@ public:
   /// All tokens produced by the preprocessor after all macro replacements,
   /// directives, etc. Source locations found in the clang AST will always
   /// point to one of these tokens.
+  /// Tokens are in TU order (per SourceManager::isBeforeInTranslationUnit()).
   /// FIXME: figure out how to handle token splitting, e.g. '>>' can be split
   ///        into two '>' tokens by the parser. However, TokenBuffer currently
   ///        keeps it as a single '>>' token.
@@ -182,6 +187,10 @@ public:
     return ExpandedTokens;
   }
 
+  /// Returns the subrange of expandedTokens() corresponding to the closed
+  /// token range R.
+  llvm::ArrayRef<syntax::Token> expandedTokens(SourceRange R) const;
+
   /// Find the subrange of spelled tokens that produced the corresponding \p
   /// Expanded tokens.
   ///
@@ -231,9 +240,9 @@ public:
   /// Lexed tokens of a file before preprocessing. E.g. for the following input
   ///     #define DECL(name) int name = 10
   ///     DECL(a);
-  /// spelledTokens() returns {"#", "define", "DECL", "(", "name", ")", "eof"}.
-  /// FIXME: we do not yet store tokens of directives, like #include, #define,
-  ///        #pragma, etc.
+  /// spelledTokens() returns
+  ///    {"#", "define", "DECL", "(", "name", ")", "int", "name", "=", "10",
+  ///     "DECL", "(", "a", ")", ";"}
   llvm::ArrayRef<syntax::Token> spelledTokens(FileID FID) const;
 
   /// Get all tokens that expand a macro in \p FID. For the following input
@@ -304,6 +313,17 @@ private:
   const SourceManager *SourceMgr;
 };
 
+/// The spelled tokens that overlap or touch a spelling location Loc.
+/// This always returns 0-2 tokens.
+llvm::ArrayRef<syntax::Token>
+spelledTokensTouching(SourceLocation Loc, const syntax::TokenBuffer &Tokens);
+
+/// The identifier token that overlaps or touches a spelling location Loc.
+/// If there is none, returns nullptr.
+const syntax::Token *
+spelledIdentifierTouching(SourceLocation Loc,
+                          const syntax::TokenBuffer &Tokens);
+
 /// Lex the text buffer, corresponding to \p FID, in raw mode and record the
 /// resulting spelled tokens. Does minimal post-processing on raw identifiers,
 /// setting the appropriate token kind (instead of the raw_identifier reported