[clang-tidy] Add modernize-use-std-format check (#90397)

Add a new clang-tidy check that converts absl::StrFormat (and similar
functions) to std::format (and similar functions.)

Split the configuration of FormatStringConverter out to a separate
Configuration class so that we don't risk confusion by passing two
boolean configuration parameters into the constructor. Add
AllowTrailingNewlineRemoval option since we never want to remove
trailing newlines in this check.

Author: mikecrowe

clang-tools-extra/clang-tidy/modernize/CMakeLists.txt

@@ -41,6 +41,7 @@ add_clang_library(clangTidyModernizeModule
   UseNullptrCheck.cpp
   UseOverrideCheck.cpp
   UseStartsEndsWithCheck.cpp
+  UseStdFormatCheck.cpp
   UseStdNumbersCheck.cpp
   UseStdPrintCheck.cpp
   UseTrailingReturnTypeCheck.cpp

clang-tools-extra/clang-tidy/modernize/ModernizeTidyModule.cpp

@@ -42,6 +42,7 @@
 #include "UseNullptrCheck.h"
 #include "UseOverrideCheck.h"
 #include "UseStartsEndsWithCheck.h"
+#include "UseStdFormatCheck.h"
 #include "UseStdNumbersCheck.h"
 #include "UseStdPrintCheck.h"
 #include "UseTrailingReturnTypeCheck.h"
@@ -76,6 +77,7 @@ class ModernizeModule : public ClangTidyModule {
         "modernize-use-designated-initializers");
     CheckFactories.registerCheck<UseStartsEndsWithCheck>(
         "modernize-use-starts-ends-with");
+    CheckFactories.registerCheck<UseStdFormatCheck>("modernize-use-std-format");
     CheckFactories.registerCheck<UseStdNumbersCheck>(
         "modernize-use-std-numbers");
     CheckFactories.registerCheck<UseStdPrintCheck>("modernize-use-std-print");

clang-tools-extra/clang-tidy/modernize/UseStdFormatCheck.cpp

@@ -0,0 +1,107 @@
+//===--- UseStdFormatCheck.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 "UseStdFormatCheck.h"
+#include "../utils/FormatStringConverter.h"
+#include "../utils/Matchers.h"
+#include "../utils/OptionsUtils.h"
+#include "clang/ASTMatchers/ASTMatchFinder.h"
+#include "clang/Lex/Lexer.h"
+#include "clang/Tooling/FixIt.h"
+
+using namespace clang::ast_matchers;
+
+namespace clang::tidy::modernize {
+
+namespace {
+AST_MATCHER(StringLiteral, isOrdinary) { return Node.isOrdinary(); }
+} // namespace
+
+UseStdFormatCheck::UseStdFormatCheck(StringRef Name, ClangTidyContext *Context)
+    : ClangTidyCheck(Name, Context),
+      StrictMode(Options.getLocalOrGlobal("StrictMode", false)),
+      StrFormatLikeFunctions(utils::options::parseStringList(
+          Options.get("StrFormatLikeFunctions", ""))),
+      ReplacementFormatFunction(
+          Options.get("ReplacementFormatFunction", "std::format")),
+      IncludeInserter(Options.getLocalOrGlobal("IncludeStyle",
+                                               utils::IncludeSorter::IS_LLVM),
+                      areDiagsSelfContained()),
+      MaybeHeaderToInclude(Options.get("FormatHeader")) {
+  if (StrFormatLikeFunctions.empty())
+    StrFormatLikeFunctions.push_back("absl::StrFormat");
+
+  if (!MaybeHeaderToInclude && ReplacementFormatFunction == "std::format")
+    MaybeHeaderToInclude = "<format>";
+}
+
+void UseStdFormatCheck::registerPPCallbacks(const SourceManager &SM,
+                                            Preprocessor *PP,
+                                            Preprocessor *ModuleExpanderPP) {
+  IncludeInserter.registerPreprocessor(PP);
+}
+
+void UseStdFormatCheck::registerMatchers(MatchFinder *Finder) {
+  Finder->addMatcher(
+      callExpr(argumentCountAtLeast(1),
+               hasArgument(0, stringLiteral(isOrdinary())),
+               callee(functionDecl(unless(cxxMethodDecl()),
+                                   matchers::matchesAnyListedName(
+                                       StrFormatLikeFunctions))
+                          .bind("func_decl")))
+          .bind("strformat"),
+      this);
+}
+
+void UseStdFormatCheck::storeOptions(ClangTidyOptions::OptionMap &Opts) {
+  using utils::options::serializeStringList;
+  Options.store(Opts, "StrictMode", StrictMode);
+  Options.store(Opts, "StrFormatLikeFunctions",
+                serializeStringList(StrFormatLikeFunctions));
+  Options.store(Opts, "ReplacementFormatFunction", ReplacementFormatFunction);
+  Options.store(Opts, "IncludeStyle", IncludeInserter.getStyle());
+  if (MaybeHeaderToInclude)
+    Options.store(Opts, "FormatHeader", *MaybeHeaderToInclude);
+}
+
+void UseStdFormatCheck::check(const MatchFinder::MatchResult &Result) {
+  const unsigned FormatArgOffset = 0;
+  const auto *OldFunction = Result.Nodes.getNodeAs<FunctionDecl>("func_decl");
+  const auto *StrFormat = Result.Nodes.getNodeAs<CallExpr>("strformat");
+
+  utils::FormatStringConverter::Configuration ConverterConfig;
+  ConverterConfig.StrictMode = StrictMode;
+  utils::FormatStringConverter Converter(Result.Context, StrFormat,
+                                         FormatArgOffset, ConverterConfig,
+                                         getLangOpts());
+  const Expr *StrFormatCall = StrFormat->getCallee();
+  if (!Converter.canApply()) {
+    diag(StrFormat->getBeginLoc(),
+         "unable to use '%0' instead of %1 because %2")
+        << StrFormatCall->getSourceRange() << ReplacementFormatFunction
+        << OldFunction->getIdentifier()
+        << Converter.conversionNotPossibleReason();
+    return;
+  }
+
+  DiagnosticBuilder Diag =
+      diag(StrFormatCall->getBeginLoc(), "use '%0' instead of %1")
+      << ReplacementFormatFunction << OldFunction->getIdentifier();
+  Diag << FixItHint::CreateReplacement(
+      CharSourceRange::getTokenRange(StrFormatCall->getSourceRange()),
+      ReplacementFormatFunction);
+  Converter.applyFixes(Diag, *Result.SourceManager);
+
+  if (MaybeHeaderToInclude)
+    Diag << IncludeInserter.createIncludeInsertion(
+        Result.Context->getSourceManager().getFileID(
+            StrFormatCall->getBeginLoc()),
+        *MaybeHeaderToInclude);
+}
+
+} // namespace clang::tidy::modernize

clang-tools-extra/clang-tidy/modernize/UseStdFormatCheck.h

@@ -0,0 +1,51 @@
+//===--- UseStdFormatCheck.h - clang-tidy -----------------------*- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MODERNIZE_USESTDFORMATCHECK_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MODERNIZE_USESTDFORMATCHECK_H
+
+#include "../ClangTidyCheck.h"
+#include "../utils/IncludeInserter.h"
+
+namespace clang::tidy::modernize {
+
+/// Converts calls to absl::StrFormat, or other functions via configuration
+/// options, to C++20's std::format, or another function via a configuration
+/// option, modifying the format string appropriately and removing
+/// now-unnecessary calls to std::string::c_str() and std::string::data().
+///
+/// For the user-facing documentation see:
+/// http://clang.llvm.org/extra/clang-tidy/checks/modernize/use-std-format.html
+class UseStdFormatCheck : public ClangTidyCheck {
+public:
+  UseStdFormatCheck(StringRef Name, ClangTidyContext *Context);
+  bool isLanguageVersionSupported(const LangOptions &LangOpts) const override {
+    if (ReplacementFormatFunction == "std::format")
+      return LangOpts.CPlusPlus20;
+    return LangOpts.CPlusPlus;
+  }
+  void registerPPCallbacks(const SourceManager &SM, Preprocessor *PP,
+                           Preprocessor *ModuleExpanderPP) override;
+  void storeOptions(ClangTidyOptions::OptionMap &Opts) override;
+  void registerMatchers(ast_matchers::MatchFinder *Finder) override;
+  void check(const ast_matchers::MatchFinder::MatchResult &Result) override;
+  std::optional<TraversalKind> getCheckTraversalKind() const override {
+    return TK_IgnoreUnlessSpelledInSource;
+  }
+
+private:
+  bool StrictMode;
+  std::vector<StringRef> StrFormatLikeFunctions;
+  StringRef ReplacementFormatFunction;
+  utils::IncludeInserter IncludeInserter;
+  std::optional<StringRef> MaybeHeaderToInclude;
+};
+
+} // namespace clang::tidy::modernize
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MODERNIZE_USESTDFORMATCHECK_H

clang-tools-extra/clang-tidy/modernize/UseStdPrintCheck.cpp

@@ -129,8 +129,11 @@ void UseStdPrintCheck::check(const MatchFinder::MatchResult &Result) {
     FormatArgOffset = 1;
   }
 
+  utils::FormatStringConverter::Configuration ConverterConfig;
+  ConverterConfig.StrictMode = StrictMode;
+  ConverterConfig.AllowTrailingNewlineRemoval = true;
   utils::FormatStringConverter Converter(
-      Result.Context, Printf, FormatArgOffset, StrictMode, getLangOpts());
+      Result.Context, Printf, FormatArgOffset, ConverterConfig, getLangOpts());
   const Expr *PrintfCall = Printf->getCallee();
   const StringRef ReplacementFunction = Converter.usePrintNewlineFunction()
                                             ? ReplacementPrintlnFunction

clang-tools-extra/clang-tidy/utils/FormatStringConverter.cpp

@@ -198,10 +198,11 @@ static bool castMismatchedIntegerTypes(const CallExpr *Call, bool StrictMode) {
 FormatStringConverter::FormatStringConverter(ASTContext *ContextIn,
                                              const CallExpr *Call,
                                              unsigned FormatArgOffset,
-                                             bool StrictMode,
+                                             const Configuration ConfigIn,
                                              const LangOptions &LO)
-    : Context(ContextIn),
-      CastMismatchedIntegerTypes(castMismatchedIntegerTypes(Call, StrictMode)),
+    : Context(ContextIn), Config(ConfigIn),
+      CastMismatchedIntegerTypes(
+          castMismatchedIntegerTypes(Call, ConfigIn.StrictMode)),
       Args(Call->getArgs()), NumArgs(Call->getNumArgs()),
       ArgsOffset(FormatArgOffset + 1), LangOpts(LO) {
   assert(ArgsOffset <= NumArgs);
@@ -627,9 +628,12 @@ void FormatStringConverter::finalizeFormatText() {
 
   // It's clearer to convert printf("Hello\r\n"); to std::print("Hello\r\n")
   // than to std::println("Hello\r");
-  if (StringRef(StandardFormatString).ends_with("\\n") &&
-      !StringRef(StandardFormatString).ends_with("\\\\n") &&
-      !StringRef(StandardFormatString).ends_with("\\r\\n")) {
+  // Use StringRef until C++20 std::string::ends_with() is available.
+  const auto StandardFormatStringRef = StringRef(StandardFormatString);
+  if (Config.AllowTrailingNewlineRemoval &&
+      StandardFormatStringRef.ends_with("\\n") &&
+      !StandardFormatStringRef.ends_with("\\\\n") &&
+      !StandardFormatStringRef.ends_with("\\r\\n")) {
     UsePrintNewlineFunction = true;
     FormatStringNeededRewriting = true;
     StandardFormatString.erase(StandardFormatString.end() - 2,

clang-tools-extra/clang-tidy/utils/FormatStringConverter.h

@@ -32,8 +32,14 @@ class FormatStringConverter
 public:
   using ConversionSpecifier = clang::analyze_format_string::ConversionSpecifier;
   using PrintfSpecifier = analyze_printf::PrintfSpecifier;
+
+  struct Configuration {
+    bool StrictMode = false;
+    bool AllowTrailingNewlineRemoval = false;
+  };
+
   FormatStringConverter(ASTContext *Context, const CallExpr *Call,
-                        unsigned FormatArgOffset, bool StrictMode,
+                        unsigned FormatArgOffset, Configuration Config,
                         const LangOptions &LO);
 
   bool canApply() const { return ConversionNotPossibleReason.empty(); }
@@ -45,6 +51,7 @@ class FormatStringConverter
 
 private:
   ASTContext *Context;
+  const Configuration Config;
   const bool CastMismatchedIntegerTypes;
   const Expr *const *Args;
   const unsigned NumArgs;

clang-tools-extra/docs/ReleaseNotes.rst

@@ -150,6 +150,15 @@ New checks
   Finds initializer lists for aggregate types that could be
   written as designated initializers instead.
 
+- New :doc:`modernize-use-std-format
+  <clang-tidy/checks/modernize/use-std-format>` check.
+
+  Converts calls to ``absl::StrFormat``, or other functions via
+  configuration options, to C++20's ``std::format``, or another function
+  via a configuration option, modifying the format string appropriately and
+  removing now-unnecessary calls to ``std::string::c_str()`` and
+  ``std::string::data()``.
+
 - New :doc:`readability-enum-initial-value
   <clang-tidy/checks/readability/enum-initial-value>` check.
 

clang-tools-extra/docs/clang-tidy/checks/list.rst

@@ -300,6 +300,7 @@ Clang-Tidy Checks
    :doc:`modernize-use-nullptr <modernize/use-nullptr>`, "Yes"
    :doc:`modernize-use-override <modernize/use-override>`, "Yes"
    :doc:`modernize-use-starts-ends-with <modernize/use-starts-ends-with>`, "Yes"
+   :doc:`modernize-use-std-format <modernize/use-std-format>`, "Yes"
    :doc:`modernize-use-std-numbers <modernize/use-std-numbers>`, "Yes"
    :doc:`modernize-use-std-print <modernize/use-std-print>`, "Yes"
    :doc:`modernize-use-trailing-return-type <modernize/use-trailing-return-type>`, "Yes"

clang-tools-extra/docs/clang-tidy/checks/modernize/use-std-format.rst

@@ -0,0 +1,84 @@
+.. title:: clang-tidy - modernize-use-std-format
+
+modernize-use-std-format
+========================
+
+Converts calls to ``absl::StrFormat``, or other functions via
+configuration options, to C++20's ``std::format``, or another function
+via a configuration option, modifying the format string appropriately and
+removing now-unnecessary calls to ``std::string::c_str()`` and
+``std::string::data()``.
+
+For example, it turns lines like
+
+.. code-block:: c++
+
+  return absl::StrFormat("The %s is %3d", description.c_str(), value);
+
+into:
+
+.. code-block:: c++
+
+  return std::format("The {} is {:3}", description, value);
+
+The check uses the same format-string-conversion algorithm as
+`modernize-use-std-print <../modernize/use-std-print.html>`_ and its
+shortcomings are described in the documentation for that check.
+
+Options
+-------
+
+.. option:: StrictMode
+
+   When `true`, the check will add casts when converting from variadic
+   functions and printing signed or unsigned integer types (including
+   fixed-width integer types from ``<cstdint>``, ``ptrdiff_t``, ``size_t``
+   and ``ssize_t``) as the opposite signedness to ensure that the output
+   would matches that of a simple wrapper for ``std::sprintf`` that
+   accepted a C-style variable argument list. For example, with
+   `StrictMode` enabled,
+
+  .. code-block:: c++
+
+    extern std::string strprintf(const char *format, ...);
+    int i = -42;
+    unsigned int u = 0xffffffff;
+    return strprintf("%d %u\n", i, u);
+
+  would be converted to
+
+  .. code-block:: c++
+
+    return std::format("{} {}\n", static_cast<unsigned int>(i), static_cast<int>(u));
+
+  to ensure that the output will continue to be the unsigned representation
+  of -42 and the signed representation of 0xffffffff (often 4294967254
+  and -1 respectively). When `false` (which is the default), these casts
+  will not be added which may cause a change in the output. Note that this
+  option makes no difference for the default value of
+  `StrFormatLikeFunctions` since ``absl::StrFormat`` takes a function
+  parameter pack and is not a variadic function.
+
+.. option:: StrFormatLikeFunctions
+
+   A semicolon-separated list of (fully qualified) function names to
+   replace, with the requirement that the first parameter contains the
+   printf-style format string and the arguments to be formatted follow
+   immediately afterwards. The default value for this option is
+   `absl::StrFormat`.
+
+.. option:: ReplacementFormatFunction
+
+   The function that will be used to replace the function set by the
+   `StrFormatLikeFunctions` option rather than the default
+   `std::format`. It is expected that the function provides an interface
+   that is compatible with ``std::format``. A suitable candidate would be
+   `fmt::format`.
+
+.. option:: FormatHeader
+
+   The header that must be included for the declaration of
+   `ReplacementFormatFunction` so that a ``#include`` directive can be added if
+   required. If `ReplacementFormatFunction` is `std::format` then this option will
+   default to ``<format>``, otherwise this option will default to nothing
+   and no ``#include`` directive will be added.