[clang-tools-extra] [clang-tidy] Add bugprone-macro-condition check (PR #210768)

[Zeyi Xu via cfe-commits]

================
@@ -0,0 +1,357 @@
+//===----------------------------------------------------------------------===//
+//
+// 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 "MacroConditionCheck.h"
+#include "clang/Lex/Lexer.h"
+#include "clang/Lex/MacroInfo.h"
+#include "clang/Lex/PPCallbacks.h"
+#include "clang/Lex/Preprocessor.h"
+#include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringSet.h"
+#include <memory>
+#include <string>
+#include <utility>
+
+namespace clang::tidy::bugprone {
+
+namespace {
+class MacroConditionCallbacks : public PPCallbacks {
+public:
+  MacroConditionCallbacks(MacroConditionCheck *Check, const SourceManager &SM,
+                          Preprocessor &PP)
+      : Check(Check), SM(SM), PP(PP) {}
+
+  void If(SourceLocation Loc, SourceRange ConditionRange,
+          ConditionValueKind ConditionValue) override;
+  void Ifdef(SourceLocation Loc, const Token &MacroNameTok,
+             const MacroDefinition &MD) override;
+  void Ifndef(SourceLocation Loc, const Token &MacroNameTok,
+              const MacroDefinition &MD) override;
+  void Elif(SourceLocation Loc, SourceRange ConditionRange,
+            ConditionValueKind ConditionValue, SourceLocation IfLoc) override;
+  void Elifdef(SourceLocation Loc, const Token &MacroNameTok,
+               const MacroDefinition &MD) override;
+  void Elifdef(SourceLocation Loc, SourceRange ConditionRange,
+               SourceLocation IfLoc) override;
+  void Elifndef(SourceLocation Loc, const Token &MacroNameTok,
+                const MacroDefinition &MD) override;
+  void Elifndef(SourceLocation Loc, SourceRange ConditionRange,
+                SourceLocation IfLoc) override;
+  void Else(SourceLocation Loc, SourceLocation IfLoc) override;
+  void Endif(SourceLocation Loc, SourceLocation IfLoc) override;
+
+private:
+  struct MacroReference {
+    std::string Name;
+    SourceLocation Loc;
+  };
+
+  struct ConditionReferences {
+    SmallVector<MacroReference, 2> Definition;
+    SmallVector<MacroReference, 2> Value;
+  };
+
+  struct DefinitionCheck {
+    std::string Name;
+    SourceLocation DefinitionLoc;
+    SourceLocation CheckLoc;
+    bool ValueTested = false;
+  };
+
+  struct ConditionalBranch {
+    SmallVector<DefinitionCheck, 2> Checks;
+    llvm::StringSet<> DefinitionTests;
+  };
+
+  ConditionReferences referencesInCondition(SourceRange ConditionRange) const;
+  MacroReference referenceFromRange(SourceRange Range,
+                                    SourceLocation Loc) const;
+  bool isIgnoredIdentifier(StringRef Name) const;
+  void startCondition(const ConditionReferences &References);
+  void startDefinitionCondition(StringRef Name, SourceLocation Loc);
+  void nextBranch(const ConditionReferences &References = {});
+  void processReferences(const ConditionReferences &References);
+  void finishBranch(ConditionalBranch &Branch);
+  void checkDefinitionReference(const MacroReference &Reference,
+                                ConditionalBranch &Branch);
+  void checkValueReference(const MacroReference &Reference);
+  bool isDefinitionTestActive(StringRef Name) const;
+
+  SmallVector<ConditionalBranch, 8> Conditions;
+  llvm::DenseSet<unsigned> DiagnosedDefinitions;
+  MacroConditionCheck *Check;
+  const SourceManager &SM;
+  Preprocessor &PP;
+};
+
+} // namespace
+
+static StringRef getTokenName(const Token &Tok) {
+  if (Tok.is(tok::raw_identifier))
+    return Tok.getRawIdentifier();
+  if (const IdentifierInfo *Info = Tok.getIdentifierInfo())
+    return Info->getName();
+  return {};
+}
+
+MacroConditionCallbacks::ConditionReferences
+MacroConditionCallbacks::referencesInCondition(
+    SourceRange ConditionRange) const {
+  ConditionReferences References;
+  const SourceLocation BeginLoc = SM.getExpansionLoc(ConditionRange.getBegin());
+  if (BeginLoc.isInvalid())
+    return References;
+
+  const std::pair<FileID, unsigned> Decomposed = SM.getDecomposedLoc(BeginLoc);
+  bool Invalid = false;
+  StringRef Buffer = SM.getBufferData(Decomposed.first, &Invalid);
+  if (Invalid || Decomposed.second >= Buffer.size())
+    return References;
+
+  size_t End = Decomposed.second;
+  while (End < Buffer.size()) {
----------------
zeyi2 wrote:

Could we use `Lexer::getSourceText(CharSourceRange::getTokenRange(ConditionRange), ...)` here?

AFAIK [`readability-use-concise-preprocessor-directives`](https://github.com/llvm/llvm-project/blob/4f607e3cd911ccc3d1aab73129aacea97d864663/clang-tools-extra/clang-tidy/readability/UseConcisePreprocessorDirectivesCheck.cpp#L38-L46) handles the same `PPCallbacks` range this way.

https://github.com/llvm/llvm-project/pull/210768