[clang][refactor] Refactor findNextTokenIncludingComments

We have two copies of the same code in clang-tidy and
clang-reorder-fields, and those are extremenly similar to
`Lexer::findNextToken`, so just add an extra agument to the latter.

Author: legrosbuffle

clang-tools-extra/clang-reorder-fields/ReorderFieldsAction.cpp

@@ -118,47 +118,19 @@ findMembersUsedInInitExpr(const CXXCtorInitializer *Initializer,
   return Results;
 }
 
-/// Returns the next token after `Loc` (including comment tokens).
-static std::optional<Token> getTokenAfter(SourceLocation Loc,
-                                          const SourceManager &SM,
-                                          const LangOptions &LangOpts) {
-  if (Loc.isMacroID()) {
-    return std::nullopt;
-  }
-  Loc = Lexer::getLocForEndOfToken(Loc, 0, SM, LangOpts);
-
-  // Break down the source location.
-  std::pair<FileID, unsigned> LocInfo = SM.getDecomposedLoc(Loc);
-
-  // Try to load the file buffer.
-  bool InvalidTemp = false;
-  StringRef File = SM.getBufferData(LocInfo.first, &InvalidTemp);
-  if (InvalidTemp)
-    return std::nullopt;
-
-  const char *TokenBegin = File.data() + LocInfo.second;
-
-  Lexer lexer(SM.getLocForStartOfFile(LocInfo.first), LangOpts, File.begin(),
-              TokenBegin, File.end());
-  lexer.SetCommentRetentionState(true);
-  // Find the token.
-  Token Tok;
-  lexer.LexFromRawLexer(Tok);
-  return Tok;
-}
-
 /// Returns the end of the trailing comments after `Loc`.
 static SourceLocation getEndOfTrailingComment(SourceLocation Loc,
                                               const SourceManager &SM,
                                               const LangOptions &LangOpts) {
   // We consider any following comment token that is indented more than the
   // first comment to be part of the trailing comment.
   const unsigned Column = SM.getPresumedColumnNumber(Loc);
-  std::optional<Token> Tok = getTokenAfter(Loc, SM, LangOpts);
+  std::optional<Token> Tok =
+      Lexer::findNextToken(Loc, SM, LangOpts, /*IncludeComments*/ true);
   while (Tok && Tok->is(tok::comment) &&
          SM.getPresumedColumnNumber(Tok->getLocation()) > Column) {
     Loc = Tok->getEndLoc();
-    Tok = getTokenAfter(Loc, SM, LangOpts);
+    Tok = Lexer::findNextToken(Loc, SM, LangOpts, /*IncludeComments*/ true);
   }
   return Loc;
 }

clang-tools-extra/clang-tidy/modernize/ConcatNestedNamespacesCheck.cpp

@@ -59,7 +59,7 @@ SourceRange NS::getNamespaceBackRange(const SourceManager &SM,
   // Back from '}' to conditional '// namespace xxx'
   SourceLocation Loc = front()->getRBraceLoc();
   std::optional<Token> Tok =
-      utils::lexer::findNextTokenIncludingComments(Loc, SM, LangOpts);
+      Lexer::findNextToken(Loc, SM, LangOpts, /*IncludeComments*/ true);
   if (!Tok)
     return getDefaultNamespaceBackRange();
   if (Tok->getKind() != tok::TokenKind::comment)

clang-tools-extra/clang-tidy/modernize/UseOverrideCheck.cpp

@@ -229,9 +229,8 @@ void UseOverrideCheck::check(const MatchFinder::MatchResult &Result) {
   if (HasVirtual) {
     for (Token Tok : Tokens) {
       if (Tok.is(tok::kw_virtual)) {
-        std::optional<Token> NextToken =
-            utils::lexer::findNextTokenIncludingComments(
-                Tok.getEndLoc(), Sources, getLangOpts());
+        std::optional<Token> NextToken = Lexer::findNextToken(
+            Tok.getEndLoc(), Sources, getLangOpts(), /*IncludeComments*/ true);
         if (NextToken.has_value()) {
           Diag << FixItHint::CreateRemoval(CharSourceRange::getCharRange(
               Tok.getLocation(), NextToken->getLocation()));

clang-tools-extra/clang-tidy/utils/LexerUtils.cpp

@@ -86,29 +86,6 @@ SourceLocation findNextTerminator(SourceLocation Start, const SourceManager &SM,
   return findNextAnyTokenKind(Start, SM, LangOpts, tok::comma, tok::semi);
 }
 
-std::optional<Token>
-findNextTokenIncludingComments(SourceLocation Start, const SourceManager &SM,
-                               const LangOptions &LangOpts) {
-  // `Lexer::findNextToken` will ignore comment
-  if (Start.isMacroID())
-    return std::nullopt;
-  Start = Lexer::getLocForEndOfToken(Start, 0, SM, LangOpts);
-  // Break down the source location.
-  std::pair<FileID, unsigned> LocInfo = SM.getDecomposedLoc(Start);
-  bool InvalidTemp = false;
-  StringRef File = SM.getBufferData(LocInfo.first, &InvalidTemp);
-  if (InvalidTemp)
-    return std::nullopt;
-  // Lex from the start of the given location.
-  Lexer L(SM.getLocForStartOfFile(LocInfo.first), LangOpts, File.begin(),
-          File.data() + LocInfo.second, File.end());
-  L.SetCommentRetentionState(true);
-  // Find the token.
-  Token Tok;
-  L.LexFromRawLexer(Tok);
-  return Tok;
-}
-
 std::optional<Token>
 findNextTokenSkippingComments(SourceLocation Start, const SourceManager &SM,
                               const LangOptions &LangOpts) {

clang-tools-extra/clang-tidy/utils/LexerUtils.h

@@ -91,7 +91,9 @@ SourceLocation findNextAnyTokenKind(SourceLocation Start,
 
 std::optional<Token>
 findNextTokenIncludingComments(SourceLocation Start, const SourceManager &SM,
-                               const LangOptions &LangOpts);
+                               const LangOptions &LangOpts) {
+  return Lexer::findNextToken(Start, SM, LangOpts, true);
+}
 
 // Finds next token that's not a comment.
 std::optional<Token> findNextTokenSkippingComments(SourceLocation Start,

clang/include/clang/Lex/Lexer.h

@@ -554,7 +554,8 @@ class Lexer : public PreprocessorLexer {
   /// Returns the next token, or std::nullopt if the location is inside a macro.
   static std::optional<Token> findNextToken(SourceLocation Loc,
                                             const SourceManager &SM,
-                                            const LangOptions &LangOpts);
+                                            const LangOptions &LangOpts,
+                                            bool IncludeComments = false);
 
   /// Checks that the given token is the first token that occurs after
   /// the given location (this excludes comments and whitespace). Returns the

clang/lib/Lex/Lexer.cpp

@@ -1323,7 +1323,8 @@ const char *Lexer::SkipEscapedNewLines(const char *P) {
 
 std::optional<Token> Lexer::findNextToken(SourceLocation Loc,
                                           const SourceManager &SM,
-                                          const LangOptions &LangOpts) {
+                                          const LangOptions &LangOpts,
+                                          bool IncludeComments) {
   if (Loc.isMacroID()) {
     if (!Lexer::isAtEndOfMacroExpansion(Loc, SM, LangOpts, &Loc))
       return std::nullopt;
@@ -1344,6 +1345,7 @@ std::optional<Token> Lexer::findNextToken(SourceLocation Loc,
   // Lex from the start of the given location.
   Lexer lexer(SM.getLocForStartOfFile(LocInfo.first), LangOpts, File.begin(),
                                       TokenBegin, File.end());
+  lexer.SetCommentRetentionState(IncludeComments);
   // Find the token.
   Token Tok;
   lexer.LexFromRawLexer(Tok);