[clang-tidy][modernize-raw-string-literal] Don't replace upper ASCII with raw literals

It's useless and not safe to replace UTF-8 encoded with escaped ASCII to raw UTF-8 chars:
"\xE2\x98\x83" ---> <snowman>
So don't do it.

llvm-svn: 331297

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

@@ -42,28 +42,15 @@ bool isRawStringLiteral(StringRef Text) {
 }
 
 bool containsEscapedCharacters(const MatchFinder::MatchResult &Result,
-                               const StringLiteral *Literal) {
+                               const StringLiteral *Literal,
+                               const CharsBitSet &DisallowedChars) {
   // 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;
+  for (const unsigned char C : Literal->getBytes())
+    if (DisallowedChars.test(C))
+      return false;
 
   CharSourceRange CharRange = Lexer::makeFileCharRange(
       CharSourceRange::getTokenRange(Literal->getSourceRange()),
@@ -102,7 +89,28 @@ RawStringLiteralCheck::RawStringLiteralCheck(StringRef Name,
                                              ClangTidyContext *Context)
     : ClangTidyCheck(Name, Context),
       DelimiterStem(Options.get("DelimiterStem", "lit")),
-      ReplaceShorterLiterals(Options.get("ReplaceShorterLiterals", false)) {}
+      ReplaceShorterLiterals(Options.get("ReplaceShorterLiterals", false)) {
+  // Non-printing characters are disallowed:
+  // \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
+  for (const unsigned char C : 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))
+    DisallowedChars.set(C);
+
+  // Non-ASCII are disallowed too.
+  for (unsigned int C = 0x80u; C <= 0xFFu; ++C)
+    DisallowedChars.set(static_cast<unsigned char>(C));
+}
 
 void RawStringLiteralCheck::storeOptions(ClangTidyOptions::OptionMap &Options) {
   ClangTidyCheck::storeOptions(Options);
@@ -124,7 +132,7 @@ void RawStringLiteralCheck::check(const MatchFinder::MatchResult &Result) {
   if (Literal->getLocStart().isMacroID())
     return;
 
-  if (containsEscapedCharacters(Result, Literal)) {
+  if (containsEscapedCharacters(Result, Literal, DisallowedChars)) {
     std::string Replacement = asRawStringLiteral(Literal, DelimiterStem);
     if (ReplaceShorterLiterals ||
         Replacement.length() <=

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

@@ -11,11 +11,14 @@
 #define LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MODERNIZE_RAW_STRING_LITERAL_H
 
 #include "../ClangTidy.h"
+#include <bitset>
 
 namespace clang {
 namespace tidy {
 namespace modernize {
 
+using CharsBitSet = std::bitset<1 << CHAR_BIT>;
+
 /// This check replaces string literals with escaped characters to
 /// raw string literals.
 ///
@@ -35,6 +38,7 @@ private:
       const StringLiteral *Literal, StringRef Replacement);
 
   std::string DelimiterStem;
+  CharsBitSet DisallowedChars;
   const bool ReplaceShorterLiterals;
 };
 

clang-tools-extra/test/clang-tidy/modernize-raw-string-literal.cpp

@@ -40,6 +40,8 @@ char const *const Rs("goink\\\036");
 char const *const Us("goink\\\037");
 char const *const HexNonPrintable("\\\x03");
 char const *const Delete("\\\177");
+char const *const MultibyteSnowman("\xE2\x98\x83");
+// CHECK-FIXES: {{^}}char const *const MultibyteSnowman("\xE2\x98\x83");{{$}}
 
 char const *const TrailingSpace("A line \\with space. \n");
 char const *const TrailingNewLine("A single \\line.\n");