diff options
author | Kadir Cetinkaya <kadircet@google.com> | 2022-01-28 16:18:24 +0100 |
---|---|---|
committer | Kadir Cetinkaya <kadircet@google.com> | 2022-01-31 16:15:16 +0100 |
commit | ff77071a4d672fab7c8b30bea8525b89be8596fc (patch) | |
tree | 53d79281604ef1c1cd8e3e371b4045e5d74c5950 /clang/unittests/Lex/LexerTest.cpp | |
parent | 8faad296347a2c6d0567f28b307bfc40acc26e07 (diff) | |
download | llvm-ff77071a4d672fab7c8b30bea8525b89be8596fc.zip llvm-ff77071a4d672fab7c8b30bea8525b89be8596fc.tar.gz llvm-ff77071a4d672fab7c8b30bea8525b89be8596fc.tar.bz2 |
[clang][Lexer] Make raw and normal lexer behave the same for line comments
Normally there are heruistics in lexer to treat `//*` specially in
language modes that don't have line comments (to emit `/`). Unfortunately this
only applied to the first occurence of a line comment inside the file, as the
subsequent line comments were treated as if language had support for them.
This unfortunately only holds in normal lexing mode, as in raw mode all
occurences of line comments received this treatment, which created discrepancies
when comparing expanded and spelled tokens.
The proper fix would be to just make sure we treat all the line comments with a
subsequent `*` the same way, but it would imply breaking some code that's
accepted by clang today. So instead we introduce the same bug into raw lexing
mode.
Fixes https://github.com/clangd/clangd/issues/1003.
Differential Revision: https://reviews.llvm.org/D118471
Diffstat (limited to 'clang/unittests/Lex/LexerTest.cpp')
-rw-r--r-- | clang/unittests/Lex/LexerTest.cpp | 25 |
1 files changed, 25 insertions, 0 deletions
diff --git a/clang/unittests/Lex/LexerTest.cpp b/clang/unittests/Lex/LexerTest.cpp index 319c63f..df22e77 100644 --- a/clang/unittests/Lex/LexerTest.cpp +++ b/clang/unittests/Lex/LexerTest.cpp @@ -23,6 +23,8 @@ #include "clang/Lex/ModuleLoader.h" #include "clang/Lex/Preprocessor.h" #include "clang/Lex/PreprocessorOptions.h" +#include "llvm/ADT/ArrayRef.h" +#include "llvm/ADT/StringRef.h" #include "gmock/gmock.h" #include "gtest/gtest.h" #include <memory> @@ -632,4 +634,27 @@ TEST_F(LexerTest, CreatedFIDCountForPredefinedBuffer) { EXPECT_EQ(SourceMgr.getNumCreatedFIDsForFileID(PP->getPredefinesFileID()), 1U); } + +TEST_F(LexerTest, RawAndNormalLexSameForLineComments) { + const llvm::StringLiteral Source = R"cpp( + // First line comment. + //* Second line comment which is ambigious. + )cpp"; + LangOpts.LineComment = false; + auto Toks = Lex(Source); + auto &SM = PP->getSourceManager(); + auto SrcBuffer = SM.getBufferData(SM.getMainFileID()); + Lexer L(SM.getLocForStartOfFile(SM.getMainFileID()), PP->getLangOpts(), + SrcBuffer.data(), SrcBuffer.data(), + SrcBuffer.data() + SrcBuffer.size()); + + auto ToksView = llvm::makeArrayRef(Toks); + clang::Token T; + while (!L.LexFromRawLexer(T)) { + ASSERT_TRUE(!ToksView.empty()); + EXPECT_EQ(T.getKind(), ToksView.front().getKind()); + ToksView = ToksView.drop_front(); + } + EXPECT_TRUE(ToksView.empty()); +} } // anonymous namespace |