[clang-tools-extra] [clang-tidy] [NFC] Move comment scanning to `LexerUtils` and add tests (PR #180371)

[Victor Chernyakin via cfe-commits]

================
@@ -0,0 +1,149 @@
+//===--- LexerUtilsTest.cpp - clang-tidy ---------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "../clang-tidy/utils/LexerUtils.h"
+
+#include "clang/Basic/FileManager.h"
+#include "clang/Basic/SourceManager.h"
+#include "clang/Frontend/ASTUnit.h"
+#include "clang/Serialization/PCHContainerOperations.h"
+#include "clang/Tooling/Tooling.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Testing/Annotations/Annotations.h"
+#include "gtest/gtest.h"
+
+namespace clang::tidy::test {
+
+using clang::tooling::FileContentMappings;
+
+static std::unique_ptr<ASTUnit>
+buildAST(StringRef Code, const FileContentMappings &Mappings = {}) {
+  std::vector<std::string> Args = {"-std=c++20"};
+  return clang::tooling::buildASTFromCodeWithArgs(
+      Code, Args, "input.cc", "clang-tool",
+      std::make_shared<PCHContainerOperations>(),
+      clang::tooling::getClangStripDependencyFileAdjuster(), Mappings);
+}
+
+static CharSourceRange rangeFromAnnotations(const llvm::Annotations &A,
+                                            const SourceManager &SM, FileID FID,
+                                            llvm::StringRef Name = "") {
+  const auto R = A.range(Name);
+  const SourceLocation Begin =
+      SM.getLocForStartOfFile(FID).getLocWithOffset(R.Begin);
+  const SourceLocation End =
+      SM.getLocForStartOfFile(FID).getLocWithOffset(R.End);
+  return CharSourceRange::getCharRange(Begin, End);
+}
+
+namespace {
+
+TEST(LexerUtilsTest, GetTrailingCommentsInRangeAdjacentComments) {
+  llvm::Annotations Code(R"cpp(
+void f() {
+  $range[[/*first*/ /*second*/]]
+  int x = 0;
+}
+)cpp");
+  std::unique_ptr<ASTUnit> AST = buildAST(Code.code());
+  ASSERT_TRUE(AST);
+  const ASTContext &Context = AST->getASTContext();
+  const SourceManager &SM = Context.getSourceManager();
+  const LangOptions &LangOpts = Context.getLangOpts();
+
+  const CharSourceRange Range =
+      rangeFromAnnotations(Code, SM, SM.getMainFileID(), "range");
+  const std::vector<utils::lexer::CommentToken> Comments =
+      utils::lexer::getTrailingCommentsInRange(Range, SM, LangOpts);
+  ASSERT_EQ(2u, Comments.size());
+  EXPECT_EQ("/*first*/", Comments[0].Text);
+  EXPECT_EQ("/*second*/", Comments[1].Text);
+  const StringRef CodeText = Code.code();
+  const size_t FirstOffset = CodeText.find("/*first*/");
+  ASSERT_NE(StringRef::npos, FirstOffset);
+  const size_t SecondOffset = CodeText.find("/*second*/");
+  ASSERT_NE(StringRef::npos, SecondOffset);
+  EXPECT_EQ(static_cast<unsigned>(FirstOffset),
----------------
localspook wrote:

The casts to `unsigned` here and below seem unnecessary; there's nothing wrong with comparing an `unsigned` and a `size_t` and letting implicit conversions do their thing

https://github.com/llvm/llvm-project/pull/180371