clang-tidy: Add check modernize-raw-string-literal
llvm-svn: 264539
diff --git a/clang-tools-extra/clang-tidy/modernize/CMakeLists.txt b/clang-tools-extra/clang-tidy/modernize/CMakeLists.txt
index f4a192a..b43b2a9 100644
--- a/clang-tools-extra/clang-tidy/modernize/CMakeLists.txt
+++ b/clang-tools-extra/clang-tidy/modernize/CMakeLists.txt
@@ -7,6 +7,7 @@
MakeUniqueCheck.cpp
ModernizeTidyModule.cpp
PassByValueCheck.cpp
+ RawStringLiteralCheck.cpp
RedundantVoidArgCheck.cpp
ReplaceAutoPtrCheck.cpp
ShrinkToFitCheck.cpp
diff --git a/clang-tools-extra/clang-tidy/modernize/ModernizeTidyModule.cpp b/clang-tools-extra/clang-tidy/modernize/ModernizeTidyModule.cpp
index 7b0db71..d7bda45 100644
--- a/clang-tools-extra/clang-tidy/modernize/ModernizeTidyModule.cpp
+++ b/clang-tools-extra/clang-tidy/modernize/ModernizeTidyModule.cpp
@@ -14,6 +14,7 @@
#include "LoopConvertCheck.h"
#include "MakeUniqueCheck.h"
#include "PassByValueCheck.h"
+#include "RawStringLiteralCheck.h"
#include "RedundantVoidArgCheck.h"
#include "ReplaceAutoPtrCheck.h"
#include "ShrinkToFitCheck.h"
@@ -36,6 +37,8 @@
CheckFactories.registerCheck<LoopConvertCheck>("modernize-loop-convert");
CheckFactories.registerCheck<MakeUniqueCheck>("modernize-make-unique");
CheckFactories.registerCheck<PassByValueCheck>("modernize-pass-by-value");
+ CheckFactories.registerCheck<RawStringLiteralCheck>(
+ "modernize-raw-string-literal");
CheckFactories.registerCheck<RedundantVoidArgCheck>(
"modernize-redundant-void-arg");
CheckFactories.registerCheck<ReplaceAutoPtrCheck>(
diff --git a/clang-tools-extra/clang-tidy/modernize/RawStringLiteralCheck.cpp b/clang-tools-extra/clang-tidy/modernize/RawStringLiteralCheck.cpp
new file mode 100644
index 0000000..b9641c3
--- /dev/null
+++ b/clang-tools-extra/clang-tidy/modernize/RawStringLiteralCheck.cpp
@@ -0,0 +1,140 @@
+//===--- RawStringLiteralCheck.cpp - clang-tidy----------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "RawStringLiteralCheck.h"
+#include "clang/AST/ASTContext.h"
+#include "clang/ASTMatchers/ASTMatchFinder.h"
+#include "clang/Lex/Lexer.h"
+
+using namespace clang::ast_matchers;
+
+namespace clang {
+namespace tidy {
+namespace modernize {
+
+namespace {
+
+bool containsEscapes(StringRef HayStack, StringRef Escapes) {
+ size_t BackSlash = HayStack.find('\\');
+ if (BackSlash == StringRef::npos)
+ return false;
+
+ while (BackSlash != StringRef::npos) {
+ if (Escapes.find(HayStack[BackSlash + 1]) == StringRef::npos)
+ return false;
+ BackSlash = HayStack.find('\\', BackSlash + 2);
+ }
+
+ return true;
+}
+
+bool isRawStringLiteral(StringRef Text) {
+ // Already a raw string literal if R comes before ".
+ const size_t QuotePos = Text.find('"');
+ assert(QuotePos != StringRef::npos);
+ return (QuotePos > 0) && (Text[QuotePos - 1] == 'R');
+}
+
+bool containsEscapedCharacters(const MatchFinder::MatchResult &Result,
+ const StringLiteral *Literal) {
+ // FIXME: Handle L"", u8"", u"" and U"" literals.
+ if (!Literal->isAscii())
+ return false;
+
+ StringRef Bytes = Literal->getBytes();
+ // Non-printing characters disqualify this literal:
+ // \007 = \a bell
+ // \010 = \b backspace
+ // \011 = \t horizontal tab
+ // \012 = \n new line
+ // \013 = \v vertical tab
+ // \014 = \f form feed
+ // \015 = \r carriage return
+ // \177 = delete
+ if (Bytes.find_first_of(StringRef("\000\001\002\003\004\005\006\a"
+ "\b\t\n\v\f\r\016\017"
+ "\020\021\022\023\024\025\026\027"
+ "\030\031\032\033\034\035\036\037"
+ "\177",
+ 33)) != StringRef::npos)
+ return false;
+
+ CharSourceRange CharRange = Lexer::makeFileCharRange(
+ CharSourceRange::getTokenRange(Literal->getSourceRange()),
+ *Result.SourceManager, Result.Context->getLangOpts());
+ StringRef Text = Lexer::getSourceText(CharRange, *Result.SourceManager,
+ Result.Context->getLangOpts());
+ if (isRawStringLiteral(Text))
+ return false;
+
+ return containsEscapes(Text, R"('\"?x01)");
+}
+
+bool containsDelimiter(StringRef Bytes, const std::string &Delimiter) {
+ return Bytes.find(Delimiter.empty()
+ ? std::string(R"lit()")lit")
+ : (")" + Delimiter + R"(")")) != StringRef::npos;
+}
+
+std::string asRawStringLiteral(const StringLiteral *Literal,
+ const std::string &DelimiterStem) {
+ const StringRef Bytes = Literal->getBytes();
+ std::string Delimiter;
+ for (int I = 0; containsDelimiter(Bytes, Delimiter); ++I) {
+ Delimiter = (I == 0) ? DelimiterStem : DelimiterStem + std::to_string(I);
+ }
+
+ if (Delimiter.empty())
+ return (R"(R"()" + Bytes + R"lit()")lit").str();
+
+ return (R"(R")" + Delimiter + "(" + Bytes + ")" + Delimiter + R"(")").str();
+}
+
+} // namespace
+
+RawStringLiteralCheck::RawStringLiteralCheck(StringRef Name,
+ ClangTidyContext *Context)
+ : ClangTidyCheck(Name, Context),
+ DelimiterStem(Options.get("DelimiterStem", "lit")) {}
+
+void RawStringLiteralCheck::storeOptions(ClangTidyOptions::OptionMap &Options) {
+ ClangTidyCheck::storeOptions(Options);
+}
+
+void RawStringLiteralCheck::registerMatchers(MatchFinder *Finder) {
+ Finder->addMatcher(stringLiteral().bind("lit"), this);
+}
+
+void RawStringLiteralCheck::check(const MatchFinder::MatchResult &Result) {
+ // Raw string literals require C++11 or later.
+ if (!Result.Context->getLangOpts().CPlusPlus11)
+ return;
+
+ const auto *Literal = Result.Nodes.getNodeAs<StringLiteral>("lit");
+ if (Literal->getLocStart().isMacroID())
+ return;
+
+ if (containsEscapedCharacters(Result, Literal))
+ replaceWithRawStringLiteral(Result, Literal);
+}
+
+void RawStringLiteralCheck::replaceWithRawStringLiteral(
+ const MatchFinder::MatchResult &Result, const StringLiteral *Literal) {
+ CharSourceRange CharRange = Lexer::makeFileCharRange(
+ CharSourceRange::getTokenRange(Literal->getSourceRange()),
+ *Result.SourceManager, Result.Context->getLangOpts());
+ diag(Literal->getLocStart(),
+ "escaped string literal can be written as a raw string literal")
+ << FixItHint::CreateReplacement(
+ CharRange, asRawStringLiteral(Literal, DelimiterStem));
+}
+
+} // namespace modernize
+} // namespace tidy
+} // namespace clang
diff --git a/clang-tools-extra/clang-tidy/modernize/RawStringLiteralCheck.h b/clang-tools-extra/clang-tidy/modernize/RawStringLiteralCheck.h
new file mode 100644
index 0000000..aabd435
--- /dev/null
+++ b/clang-tools-extra/clang-tidy/modernize/RawStringLiteralCheck.h
@@ -0,0 +1,45 @@
+//===--- RawStringLiteralCheck.h - clang-tidy--------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MODERNIZE_RAW_STRING_LITERAL_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MODERNIZE_RAW_STRING_LITERAL_H
+
+#include "../ClangTidy.h"
+//#include <string>
+
+namespace clang {
+namespace tidy {
+namespace modernize {
+
+/// This check replaces string literals with escaped characters to
+/// raw string literals.
+///
+/// For the user-facing documentation see:
+/// http://clang.llvm.org/extra/clang-tidy/checks/modernize-raw-string-literal.html
+class RawStringLiteralCheck : public ClangTidyCheck {
+public:
+ RawStringLiteralCheck(StringRef Name, ClangTidyContext *Context);
+
+ void storeOptions(ClangTidyOptions::OptionMap &Options) override;
+ void registerMatchers(ast_matchers::MatchFinder *Finder) override;
+ void check(const ast_matchers::MatchFinder::MatchResult &Result) override;
+
+private:
+ void replaceWithRawStringLiteral(
+ const ast_matchers::MatchFinder::MatchResult &Result,
+ const StringLiteral *Literal);
+
+ std::string DelimiterStem;
+};
+
+} // namespace modernize
+} // namespace tidy
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MODERNIZE_RAW_STRING_LITERAL_H