[PATCH] D133725: Searching for tokens including comments

[Bartłomiej Cieślar via Phabricator via cfe-commits]

barcisz created this revision.
Herald added a project: All.
barcisz requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

This is a small diff that adds an optional argument to the Lexer::findNextToken that allows for searching for the token while including comments (instead of having to 
instantiate the lexer separately)


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D133725

Files:
  clang/include/clang/Lex/Lexer.h
  clang/lib/Lex/Lexer.cpp
  clang/unittests/Lex/LexerTest.cpp


Index: clang/unittests/Lex/LexerTest.cpp
===================================================================
--- clang/unittests/Lex/LexerTest.cpp
+++ clang/unittests/Lex/LexerTest.cpp
@@ -622,6 +622,24 @@
                                                 "xyz", "=", "abcd", ";"));
 }
 
+TEST_F(LexerTest, FindNextTokenWithComments) {
+  Lex("int /* type */ abcd = 0; // vardecl\n"
+      "int /*other type*/ xyz = abcd; //other vardecl \n");
+  std::vector<std::string> GeneratedByNextToken;
+  SourceLocation Loc =
+      SourceMgr.getLocForStartOfFile(SourceMgr.getMainFileID());
+  while (true) {
+    auto T = Lexer::findNextToken(Loc, SourceMgr, LangOpts, true);
+    ASSERT_TRUE(T);
+    if (T->is(tok::eof))
+      break;
+    GeneratedByNextToken.push_back(getSourceText(*T, *T));
+    Loc = T->getLocation();
+  }
+  EXPECT_THAT(GeneratedByNextToken, ElementsAre("/* type */", "abcd", "=", "0", ";", "// vardecl", "int", "/*other type*/",
+                                                "xyz", "=", "abcd", ";", "//other vardecl "));
+}
+
 TEST_F(LexerTest, CreatedFIDCountForPredefinedBuffer) {
   TrivialModuleLoader ModLoader;
   auto PP = CreatePP("", ModLoader);
Index: clang/lib/Lex/Lexer.cpp
===================================================================
--- clang/lib/Lex/Lexer.cpp
+++ clang/lib/Lex/Lexer.cpp
@@ -1258,7 +1258,8 @@
 
 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 None;
@@ -1274,11 +1275,13 @@
   if (InvalidTemp)
     return None;
 
-  const char *TokenBegin = File.data() + LocInfo.second;
+  const char *const TokenBegin = File.data() + LocInfo.second;
 
   // 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);
Index: clang/include/clang/Lex/Lexer.h
===================================================================
--- clang/include/clang/Lex/Lexer.h
+++ clang/include/clang/Lex/Lexer.h
@@ -554,7 +554,8 @@
   /// Returns the next token, or none if the location is inside a macro.
   static 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


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D133725.459550.patch
Type: text/x-patch
Size: 3051 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220912/593369e0/attachment.bin>