[clang-tools-extra] [clang-tidy] New bugprone-unsafe-format-string check (PR #168691)

[Yanzuo Liu via cfe-commits]

================
@@ -0,0 +1,272 @@
+//===----------------------------------------------------------------------===//
+//
+// 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 "UnsafeFormatStringCheck.h"
+#include "../utils/OptionsUtils.h"
+#include "clang/ASTMatchers/ASTMatchFinder.h"
+#include "llvm/Support/ConvertUTF.h"
+#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/Regex.h"
+#include <string>
+
+using namespace clang::ast_matchers;
+
+namespace clang::tidy::bugprone {
+
+static constexpr llvm::StringRef OptionNameCustomPrintfFunctions =
+    "CustomPrintfFunctions";
+static constexpr llvm::StringRef OptionNameCustomScanfFunctions =
+    "CustomScanfFunctions";
+
+static constexpr llvm::StringRef BuiltInFormatBind = "format";
+static constexpr llvm::StringRef BuiltInCallBind = "call";
+static constexpr llvm::StringRef PrintfCallBind = "printfcall";
+static constexpr llvm::StringRef ScanfCallBind = "scanfcall";
+
+static std::vector<UnsafeFormatStringCheck::CheckedFunction>
+parseCheckedFunctions(StringRef Option, ClangTidyContext *Context) {
+  const std::vector<StringRef> Functions =
+      utils::options::parseStringList(Option);
+  std::vector<UnsafeFormatStringCheck::CheckedFunction> Result;
+  Result.reserve(Functions.size());
+
+  for (const StringRef Function : Functions) {
+    if (Function.empty())
+      continue;
+    const auto [Name, ParamCount] = Function.split(',');
+    unsigned long Count = 0;
+    if (Name.trim().empty() || ParamCount.trim().empty() ||
+        ParamCount.trim().getAsInteger(10, Count)) {
+      Context->configurationDiag(
+          "invalid configuration value for option '%0'; "
+          "expected <functionname>, <paramcount>; pairs.")
+          << OptionNameCustomPrintfFunctions;
+      continue;
+    }
+    Result.push_back(
+        {Name.trim().str(),
+         matchers::MatchesAnyListedRegexNameMatcher::NameMatcher(Name.trim()),
+         Count});
+  }
+
+  return Result;
+}
+
+UnsafeFormatStringCheck::UnsafeFormatStringCheck(StringRef Name,
+                                                 ClangTidyContext *Context)
+    : ClangTidyCheck(Name, Context),
+      CustomPrintfFunctions(parseCheckedFunctions(
+          Options.get(OptionNameCustomPrintfFunctions, ""), Context)),
+      CustomScanfFunctions(parseCheckedFunctions(
+          Options.get(OptionNameCustomScanfFunctions, ""), Context)) {}
+
+void UnsafeFormatStringCheck::registerMatchers(MatchFinder *Finder) {
+  // Matches sprintf and scanf family functions in std namespace in C++ and
+  // globally in C.
+  const auto VulnerableFunctionsArg0 =
+      hasAnyName("scanf", "vscanf", "wscanf", "vwscanf");
+  const auto VulnerableFunctionsArg1 =
+      hasAnyName("sprintf", "vsprintf", "fscanf", "sscanf", "vscanf", "vfscanf",
+                 "vsscanf", "fwscanf", "swscanf", "vfwscanf", "vswscanf");
+  Finder->addMatcher(
+      callExpr(
+          callee(functionDecl(VulnerableFunctionsArg0,
+                              anyOf(isInStdNamespace(),
+                                    hasDeclContext(translationUnitDecl())))),
+          hasArgument(0, stringLiteral().bind(BuiltInFormatBind)))
+          .bind(BuiltInCallBind),
+      this);
+
+  Finder->addMatcher(
+      callExpr(
+          callee(functionDecl(VulnerableFunctionsArg1,
+                              anyOf(isInStdNamespace(),
+                                    hasDeclContext(translationUnitDecl())))),
+          hasArgument(1, stringLiteral().bind(BuiltInFormatBind)))
+          .bind(BuiltInCallBind),
+      this);
+
+  if (!CustomPrintfFunctions.empty()) {
+    std::vector<llvm::StringRef> FunctionNames;
+    FunctionNames.reserve(CustomPrintfFunctions.size());
+
+    for (const CheckedFunction &Entry : CustomPrintfFunctions)
+      FunctionNames.emplace_back(Entry.Name);
+
+    const auto CustomFunctionsMatcher =
+        matchers::matchesAnyListedRegexName(FunctionNames);
+
+    Finder->addMatcher(callExpr(callee(functionDecl(CustomFunctionsMatcher)))
+                           .bind(PrintfCallBind),
+                       this);
+  }
+
+  if (!CustomScanfFunctions.empty()) {
+    std::vector<llvm::StringRef> FunctionNames;
+    FunctionNames.reserve(CustomScanfFunctions.size());
+
+    for (const CheckedFunction &Entry : CustomScanfFunctions)
+      FunctionNames.emplace_back(Entry.Name);
+
+    const auto CustomFunctionsMatcher =
+        matchers::matchesAnyListedRegexName(FunctionNames);
+
+    Finder->addMatcher(callExpr(callee(functionDecl(CustomFunctionsMatcher)))
+                           .bind(ScanfCallBind),
+                       this);
+  }
+}
+
+void UnsafeFormatStringCheck::storeOptions(ClangTidyOptions::OptionMap &Opts) {
+  Options.store(Opts, OptionNameCustomPrintfFunctions, "");
+  Options.store(Opts, OptionNameCustomScanfFunctions, "");
----------------
zwuis wrote:

Should not pass empty string.

https://github.com/llvm/llvm-project/pull/168691