Provide and use a safe Token::getRawIdentifier() accessor

llvm-svn: 209061

8 files changed, 28 insertions, 33 deletions

diff --git a/clang/include/clang/Lex/Token.h b/clang/include/clang/Lex/Token.h
index a38e92d40e4..c8b77d11747 100644
--- a/clang/include/clang/Lex/Token.h
+++ b/clang/include/clang/Lex/Token.h
@@ -18,6 +18,7 @@
 #include "clang/Basic/SourceLocation.h"
 #include "clang/Basic/TemplateKinds.h"
 #include "clang/Basic/TokenKinds.h"
+#include "llvm/ADT/StringRef.h"
 #include <cstdlib>
 
 namespace clang {
@@ -167,12 +168,12 @@ public:
     PtrData = (void*) II;
   }
 
-  /// getRawIdentifierData - For a raw identifier token (i.e., an identifier
-  /// lexed in raw mode), returns a pointer to the start of it in the text
-  /// buffer if known, null otherwise.
-  const char *getRawIdentifierData() const {
+  /// getRawIdentifier - For a raw identifier token (i.e., an identifier
+  /// lexed in raw mode), returns a reference to the text substring in the
+  /// buffer if known.
+  StringRef getRawIdentifier() const {
     assert(is(tok::raw_identifier));
-    return reinterpret_cast<const char*>(PtrData);
+    return StringRef(reinterpret_cast<const char *>(PtrData), getLength());
   }
   void setRawIdentifierData(const char *Ptr) {
     assert(is(tok::raw_identifier));
diff --git a/clang/lib/ARCMigrate/Transforms.cpp b/clang/lib/ARCMigrate/Transforms.cpp
index c349cb59f8f..6ff7b6b9db8 100644
--- a/clang/lib/ARCMigrate/Transforms.cpp
+++ b/clang/lib/ARCMigrate/Transforms.cpp
@@ -413,8 +413,7 @@ bool MigrationContext::rewritePropertyAttribute(StringRef fromAttr,
   if (tok.isNot(tok::at)) return false;
   lexer.LexFromRawLexer(tok);
   if (tok.isNot(tok::raw_identifier)) return false;
-  if (StringRef(tok.getRawIdentifierData(), tok.getLength())
-        != "property")
+  if (tok.getRawIdentifier() != "property")
     return false;
   lexer.LexFromRawLexer(tok);
   if (tok.isNot(tok::l_paren)) return false;
@@ -430,8 +429,7 @@ bool MigrationContext::rewritePropertyAttribute(StringRef fromAttr,
 
   while (1) {
     if (tok.isNot(tok::raw_identifier)) return false;
-    StringRef ident(tok.getRawIdentifierData(), tok.getLength());
-    if (ident == fromAttr) {
+    if (tok.getRawIdentifier() == fromAttr) {
       if (!toAttr.empty()) {
         Pass.TA.replaceText(tok.getLocation(), fromAttr, toAttr);
         return true;
@@ -496,8 +494,7 @@ bool MigrationContext::addPropertyAttribute(StringRef attr,
   if (tok.isNot(tok::at)) return false;
   lexer.LexFromRawLexer(tok);
   if (tok.isNot(tok::raw_identifier)) return false;
-  if (StringRef(tok.getRawIdentifierData(), tok.getLength())
-        != "property")
+  if (tok.getRawIdentifier() != "property")
     return false;
   lexer.LexFromRawLexer(tok);
 
diff --git a/clang/lib/Lex/Lexer.cpp b/clang/lib/Lex/Lexer.cpp
index 0955cc5b335..2e859d663ff 100644
--- a/clang/lib/Lex/Lexer.cpp
+++ b/clang/lib/Lex/Lexer.cpp
@@ -382,7 +382,7 @@ unsigned Lexer::getSpelling(const Token &Tok, const char *&Buffer,
   const char *TokStart = 0;
   // NOTE: this has to be checked *before* testing for an IdentifierInfo.
   if (Tok.is(tok::raw_identifier))
-    TokStart = Tok.getRawIdentifierData();
+    TokStart = Tok.getRawIdentifier().data();
   else if (!Tok.hasUCN()) {
     if (const IdentifierInfo *II = Tok.getIdentifierInfo()) {
       // Just return the string from the identifier table, which is very quick.
@@ -637,8 +637,7 @@ Lexer::ComputePreamble(const llvm::MemoryBuffer *Buffer,
       // the raw identifier to recognize and categorize preprocessor directives.
       TheLexer.LexFromRawLexer(TheTok);
       if (TheTok.getKind() == tok::raw_identifier && !TheTok.needsCleaning()) {
-        StringRef Keyword(TheTok.getRawIdentifierData(),
-                                TheTok.getLength());
+        StringRef Keyword = TheTok.getRawIdentifier();
         PreambleDirectiveKind PDK
           = llvm::StringSwitch<PreambleDirectiveKind>(Keyword)
               .Case("include", PDK_Skipped)
diff --git a/clang/lib/Lex/ModuleMap.cpp b/clang/lib/Lex/ModuleMap.cpp
index ce2c4f02e39..bdf71b5f4a1 100644
--- a/clang/lib/Lex/ModuleMap.cpp
+++ b/clang/lib/Lex/ModuleMap.cpp
@@ -1055,10 +1055,11 @@ retry:
   L.LexFromRawLexer(LToken);
   Tok.Location = LToken.getLocation().getRawEncoding();
   switch (LToken.getKind()) {
-  case tok::raw_identifier:
-    Tok.StringData = LToken.getRawIdentifierData();
-    Tok.StringLength = LToken.getLength();
-    Tok.Kind = llvm::StringSwitch<MMToken::TokenKind>(Tok.getString())
+  case tok::raw_identifier: {
+    StringRef RI = LToken.getRawIdentifier();
+    Tok.StringData = RI.data();
+    Tok.StringLength = RI.size();
+    Tok.Kind = llvm::StringSwitch<MMToken::TokenKind>(RI)
                  .Case("config_macros", MMToken::ConfigMacros)
                  .Case("conflict", MMToken::Conflict)
                  .Case("exclude", MMToken::ExcludeKeyword)
@@ -1075,6 +1076,7 @@ retry:
                  .Case("use", MMToken::UseKeyword)
                  .Default(MMToken::Identifier);
     break;
+  }
 
   case tok::comma:
     Tok.Kind = MMToken::Comma;
diff --git a/clang/lib/Lex/PPDirectives.cpp b/clang/lib/Lex/PPDirectives.cpp
index b1675bc043c..537d5bf69da 100644
--- a/clang/lib/Lex/PPDirectives.cpp
+++ b/clang/lib/Lex/PPDirectives.cpp
@@ -310,9 +310,9 @@ void Preprocessor::SkipExcludedConditionalBlock(SourceLocation IfTokenLoc,
     // to spell an i/e in a strange way that is another letter.  Skipping this
     // allows us to avoid looking up the identifier info for #define/#undef and
     // other common directives.
-    const char *RawCharData = Tok.getRawIdentifierData();
+    StringRef RI = Tok.getRawIdentifier();
 
-    char FirstChar = RawCharData[0];
+    char FirstChar = RI[0];
     if (FirstChar >= 'a' && FirstChar <= 'z' &&
         FirstChar != 'i' && FirstChar != 'e') {
       CurPPLexer->ParsingPreprocessorDirective = false;
@@ -326,8 +326,8 @@ void Preprocessor::SkipExcludedConditionalBlock(SourceLocation IfTokenLoc,
     // when skipping.
     char DirectiveBuf[20];
     StringRef Directive;
-    if (!Tok.needsCleaning() && Tok.getLength() < 20) {
-      Directive = StringRef(RawCharData, Tok.getLength());
+    if (!Tok.needsCleaning() && RI.size() < 20) {
+      Directive = RI;
     } else {
       std::string DirectiveStr = getSpelling(Tok);
       unsigned IdLen = DirectiveStr.size();
diff --git a/clang/lib/Lex/Preprocessor.cpp b/clang/lib/Lex/Preprocessor.cpp
index fec0d5bd732..5072978ed65 100644
--- a/clang/lib/Lex/Preprocessor.cpp
+++ b/clang/lib/Lex/Preprocessor.cpp
@@ -501,14 +501,13 @@ void Preprocessor::EndSourceFile() {
 /// identifier information for the token and install it into the token,
 /// updating the token kind accordingly.
 IdentifierInfo *Preprocessor::LookUpIdentifierInfo(Token &Identifier) const {
-  assert(Identifier.getRawIdentifierData() != 0 && "No raw identifier data!");
+  assert(!Identifier.getRawIdentifier().empty() && "No raw identifier data!");
 
   // Look up this token, see if it is a macro, or if it is a language keyword.
   IdentifierInfo *II;
   if (!Identifier.needsCleaning() && !Identifier.hasUCN()) {
     // No cleaning needed, just use the characters from the lexed buffer.
-    II = getIdentifierInfo(StringRef(Identifier.getRawIdentifierData(),
-                                     Identifier.getLength()));
+    II = getIdentifierInfo(Identifier.getRawIdentifier());
   } else {
     // Cleaning needed, alloca a buffer, clean into it, then use the buffer.
     SmallString<64> IdentifierBuffer;
diff --git a/clang/lib/Sema/SemaObjCProperty.cpp b/clang/lib/Sema/SemaObjCProperty.cpp
index 1b49c2abdc9..6ece0a53c71 100644
--- a/clang/lib/Sema/SemaObjCProperty.cpp
+++ b/clang/lib/Sema/SemaObjCProperty.cpp
@@ -292,8 +292,7 @@ static bool LocPropertyAttribute( ASTContext &Context, const char *attrName,
   Token Tok;
   do {
     lexer.LexFromRawLexer(Tok);
-    if (Tok.is(tok::raw_identifier) &&
-        StringRef(Tok.getRawIdentifierData(), Tok.getLength()) == attrName) {
+    if (Tok.is(tok::raw_identifier) && Tok.getRawIdentifier() == attrName) {
       Loc = Tok.getLocation();
       return true;
     }
diff --git a/clang/tools/libclang/CIndex.cpp b/clang/tools/libclang/CIndex.cpp
index 91205602c9f..5710d66890d 100644
--- a/clang/tools/libclang/CIndex.cpp
+++ b/clang/tools/libclang/CIndex.cpp
@@ -5694,14 +5694,13 @@ static void annotatePreprocessorTokens(CXTranslationUnit TU,
         break;
 
       MacroInfo *MI = 0;
-      if (Tok.is(tok::raw_identifier) &&
-          StringRef(Tok.getRawIdentifierData(), Tok.getLength()) == "define") {
+      if (Tok.is(tok::raw_identifier) && Tok.getRawIdentifier() == "define") {
         if (lexNext(Lex, Tok, NextIdx, NumTokens))
           break;
 
         if (Tok.is(tok::raw_identifier)) {
-          StringRef Name(Tok.getRawIdentifierData(), Tok.getLength());
-          IdentifierInfo &II = PP.getIdentifierTable().get(Name);
+          IdentifierInfo &II =
+              PP.getIdentifierTable().get(Tok.getRawIdentifier());
           SourceLocation MappedTokLoc =
               CXXUnit->mapLocationToPreamble(Tok.getLocation());
           MI = getMacroInfo(II, MappedTokLoc, TU);
@@ -6819,8 +6818,7 @@ MacroDefinition *cxindex::checkForMacroInMacroDefinition(const MacroInfo *MI,
   if (!PPRec)
     return 0;
 
-  StringRef Name(Tok.getRawIdentifierData(), Tok.getLength());
-  IdentifierInfo &II = PP.getIdentifierTable().get(Name);
+  IdentifierInfo &II = PP.getIdentifierTable().get(Tok.getRawIdentifier());
   if (!II.hadMacroDefinition())
     return 0;