From ff6e4441b93953efb2c52995e79e211a49ffac06 Mon Sep 17 00:00:00 2001
From: Alex Richardson <Alexander.Richardson@cl.cam.ac.uk>
Date: Wed, 7 Oct 2020 16:29:22 +0100
Subject: [PATCH] [clang-format][tests] Fix MacroExpander lexer not parsing C++
 keywords

While debugging a different clang-format failure, I tried to reuse the
MacroExpander lexer, but was surprised to see that it marks all C++
keywords (e.g. const, decltype) as being of type identifier. After stepping
through the ::format() code, I noticed that the difference between these
two is that the identifier table was not being initialized based on the
FormatStyle, so only basic tokens such as tok::semi, tok::plus, etc. were
being handled.

Reviewed By: klimek

Differential Revision: https://reviews.llvm.org/D88952
---
 clang/unittests/Format/MacroExpanderTest.cpp | 16 ++++++++++++++++
 clang/unittests/Format/TestLexer.h           |  6 ++++--
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/clang/unittests/Format/MacroExpanderTest.cpp b/clang/unittests/Format/MacroExpanderTest.cpp
index 59c67f29bedd..20e1dba0d49a 100644
--- a/clang/unittests/Format/MacroExpanderTest.cpp
+++ b/clang/unittests/Format/MacroExpanderTest.cpp
@@ -182,6 +182,22 @@ TEST_F(MacroExpanderTest, SingleExpansion) {
   EXPECT_ATTRIBUTES(Result, Attributes);
 }
 
+TEST_F(MacroExpanderTest, UnderstandsCppTokens) {
+  auto Macros = create({"A(T,name)=T name = 0;"});
+  auto *A = Lex.id("A");
+  auto Args = lexArgs({"const int", "x"});
+  auto Result = uneof(Macros->expand(A, Args));
+  std::vector<MacroAttributes> Attributes = {
+      {tok::kw_const, MR_ExpandedArg, 1, 0, {A}},
+      {tok::kw_int, MR_ExpandedArg, 0, 0, {A}},
+      {tok::identifier, MR_ExpandedArg, 0, 0, {A}},
+      {tok::equal, MR_Hidden, 0, 0, {A}},
+      {tok::numeric_constant, MR_Hidden, 0, 0, {A}},
+      {tok::semi, MR_Hidden, 0, 1, {A}},
+  };
+  EXPECT_ATTRIBUTES(Result, Attributes);
+}
+
 } // namespace
 } // namespace format
 } // namespace clang
diff --git a/clang/unittests/Format/TestLexer.h b/clang/unittests/Format/TestLexer.h
index 8c5eb2b029fb..2b56f10dd379 100644
--- a/clang/unittests/Format/TestLexer.h
+++ b/clang/unittests/Format/TestLexer.h
@@ -55,7 +55,9 @@ inline std::string text(llvm::ArrayRef<FormatToken *> Tokens) {
 
 class TestLexer {
 public:
-  TestLexer() : SourceMgr("test.cpp", "") {}
+  TestLexer(FormatStyle Style = getLLVMStyle())
+      : Style(Style), SourceMgr("test.cpp", ""),
+        IdentTable(getFormattingLangOpts(Style)) {}
 
   TokenList lex(llvm::StringRef Code) {
     Buffers.push_back(
@@ -74,7 +76,7 @@ public:
     return Result[0];
   }
 
-  FormatStyle Style = getLLVMStyle();
+  FormatStyle Style;
   encoding::Encoding Encoding = encoding::Encoding_UTF8;
   std::vector<std::unique_ptr<llvm::MemoryBuffer>> Buffers;
   clang::SourceManagerForFile SourceMgr;