[clang] Add a namespace for interesting identifiers.

Differential Revision: https://reviews.llvm.org/D146148

Author: zahiraam

clang/include/clang/Basic/IdentifierTable.h

@@ -76,6 +76,21 @@ enum { IdentifierInfoAlignment = 8 };
 
 static constexpr int ObjCOrBuiltinIDBits = 16;
 
+/// The "layout" of ObjCOrBuiltinID is:
+///  - The first value (0) represents "not a special identifier".
+///  - The next (NUM_OBJC_KEYWORDS - 1) values represent ObjCKeywordKinds (not
+///    including objc_not_keyword).
+///  - The next (NUM_INTERESTING_IDENTIFIERS - 1) values represent
+///    InterestingIdentifierKinds (not including not_interesting).
+///  - The rest of the values represent builtin IDs (not including NotBuiltin).
+static constexpr int FirstObjCKeywordID = 1;
+static constexpr int LastObjCKeywordID =
+    FirstObjCKeywordID + tok::NUM_OBJC_KEYWORDS - 2;
+static constexpr int FirstInterestingIdentifierID = LastObjCKeywordID + 1;
+static constexpr int LastInterestingIdentifierID =
+    FirstInterestingIdentifierID + tok::NUM_INTERESTING_IDENTIFIERS - 2;
+static constexpr int FirstBuiltinID = LastInterestingIdentifierID + 1;
+
 /// One of these records is kept for each identifier that
 /// is lexed.  This contains information about whether the token was \#define'd,
 /// is a language keyword, or if it is a front-end token of some sort (e.g. a
@@ -290,7 +305,9 @@ class alignas(IdentifierInfoAlignment) IdentifierInfo {
   ///
   /// For example, 'class' will return tok::objc_class if ObjC is enabled.
   tok::ObjCKeywordKind getObjCKeywordID() const {
-    if (ObjCOrBuiltinID < tok::NUM_OBJC_KEYWORDS)
+    static_assert(FirstObjCKeywordID == 1,
+                  "hard-coding this assumption to simplify code");
+    if (ObjCOrBuiltinID <= LastObjCKeywordID)
       return tok::ObjCKeywordKind(ObjCOrBuiltinID);
     else
       return tok::objc_not_keyword;
@@ -301,15 +318,30 @@ class alignas(IdentifierInfoAlignment) IdentifierInfo {
   ///
   /// 0 is not-built-in. 1+ are specific builtin functions.
   unsigned getBuiltinID() const {
-    if (ObjCOrBuiltinID >= tok::NUM_OBJC_KEYWORDS)
-      return ObjCOrBuiltinID - tok::NUM_OBJC_KEYWORDS;
+    if (ObjCOrBuiltinID >= FirstBuiltinID)
+      return 1 + (ObjCOrBuiltinID - FirstBuiltinID);
     else
       return 0;
   }
   void setBuiltinID(unsigned ID) {
-    ObjCOrBuiltinID = ID + tok::NUM_OBJC_KEYWORDS;
-    assert(ObjCOrBuiltinID - unsigned(tok::NUM_OBJC_KEYWORDS) == ID
-           && "ID too large for field!");
+    assert(ID != 0);
+    ObjCOrBuiltinID = FirstBuiltinID + (ID - 1);
+    assert(getBuiltinID() == ID && "ID too large for field!");
+  }
+  void clearBuiltinID() { ObjCOrBuiltinID = 0; }
+
+  tok::InterestingIdentifierKind getInterestingIdentifierID() const {
+    if (ObjCOrBuiltinID >= FirstInterestingIdentifierID &&
+        ObjCOrBuiltinID <= LastInterestingIdentifierID)
+      return tok::InterestingIdentifierKind(
+          1 + (ObjCOrBuiltinID - FirstInterestingIdentifierID));
+    else
+      return tok::not_interesting;
+  }
+  void setInterestingIdentifierID(unsigned ID) {
+    assert(ID != tok::not_interesting);
+    ObjCOrBuiltinID = FirstInterestingIdentifierID + (ID - 1);
+    assert(getInterestingIdentifierID() == ID && "ID too large for field!");
   }
 
   unsigned getObjCOrBuiltinID() const { return ObjCOrBuiltinID; }

clang/include/clang/Basic/TokenKinds.def

@@ -85,6 +85,9 @@
 #ifndef PRAGMA_ANNOTATION
 #define PRAGMA_ANNOTATION(X) ANNOTATION(X)
 #endif
+#ifndef INTERESTING_IDENTIFIER
+#define INTERESTING_IDENTIFIER(X)
+#endif
 
 //===----------------------------------------------------------------------===//
 // Preprocessor keywords.
@@ -794,6 +797,15 @@ OBJC_AT_KEYWORD(dynamic)
 OBJC_AT_KEYWORD(import)
 OBJC_AT_KEYWORD(available)
 
+//===----------------------------------------------------------------------===//
+// Interesting idenitifiers.
+//===----------------------------------------------------------------------===//
+INTERESTING_IDENTIFIER(not_interesting)
+INTERESTING_IDENTIFIER(FILE)
+INTERESTING_IDENTIFIER(jmp_buf)
+INTERESTING_IDENTIFIER(sigjmp_buf)
+INTERESTING_IDENTIFIER(ucontext_t)
+
 // TODO: What to do about context-sensitive keywords like:
 //       bycopy/byref/in/inout/oneway/out?
 
@@ -974,3 +986,4 @@ ANNOTATION(repl_input_end)
 #undef TOK
 #undef C99_KEYWORD
 #undef C2X_KEYWORD
+#undef INTERESTING_IDENTIFIER

clang/include/clang/Basic/TokenKinds.h

@@ -44,6 +44,14 @@ enum ObjCKeywordKind {
   NUM_OBJC_KEYWORDS
 };
 
+/// Provides a namespace for interesting identifers such as float_t and
+/// double_t.
+enum InterestingIdentifierKind {
+#define INTERESTING_IDENTIFIER(X) X,
+#include "clang/Basic/TokenKinds.def"
+  NUM_INTERESTING_IDENTIFIERS
+};
+
 /// Defines the possible values of an on-off-switch (C99 6.10.6p2).
 enum OnOffSwitch {
   OOS_ON, OOS_OFF, OOS_DEFAULT

clang/lib/Basic/Builtins.cpp

@@ -151,7 +151,7 @@ void Builtin::Context::initializeBuiltins(IdentifierTable &Table,
       unsigned ID = NameIt->second->getBuiltinID();
       if (ID != Builtin::NotBuiltin && isPredefinedLibFunction(ID) &&
           isInStdNamespace(ID) == InStdNamespace) {
-        Table.get(Name).setBuiltinID(Builtin::NotBuiltin);
+        NameIt->second->clearBuiltinID();
       }
     }
   }

clang/lib/Basic/IdentifierTable.cpp

@@ -279,6 +279,16 @@ static void AddObjCKeyword(StringRef Name,
   Table.get(Name).setObjCKeywordID(ObjCID);
 }
 
+static void AddInterestingIdentifier(StringRef Name,
+                                     tok::InterestingIdentifierKind BTID,
+                                     IdentifierTable &Table) {
+  // Don't add 'not_interesting' identifier.
+  if (BTID != tok::not_interesting) {
+    IdentifierInfo &Info = Table.get(Name, tok::identifier);
+    Info.setInterestingIdentifierID(BTID);
+  }
+}
+
 /// AddKeywords - Add all keywords to the symbol table.
 ///
 void IdentifierTable::AddKeywords(const LangOptions &LangOpts) {
@@ -295,6 +305,9 @@ void IdentifierTable::AddKeywords(const LangOptions &LangOpts) {
 #define OBJC_AT_KEYWORD(NAME)  \
   if (LangOpts.ObjC)           \
     AddObjCKeyword(StringRef(#NAME), tok::objc_##NAME, *this);
+#define INTERESTING_IDENTIFIER(NAME)                                           \
+  AddInterestingIdentifier(StringRef(#NAME), tok::NAME, *this);
+
 #define TESTING_KEYWORD(NAME, FLAGS)
 #include "clang/Basic/TokenKinds.def"
 

clang/lib/Sema/SemaDecl.cpp

@@ -6764,14 +6764,22 @@ Sema::ActOnTypedefNameDecl(Scope *S, DeclContext *DC, TypedefNameDecl *NewTD,
   if (IdentifierInfo *II = NewTD->getIdentifier())
     if (!NewTD->isInvalidDecl() &&
         NewTD->getDeclContext()->getRedeclContext()->isTranslationUnit()) {
-      if (II->isStr("FILE"))
+      switch (II->getInterestingIdentifierID()) {
+      case tok::InterestingIdentifierKind::FILE:
         Context.setFILEDecl(NewTD);
-      else if (II->isStr("jmp_buf"))
+        break;
+      case tok::InterestingIdentifierKind::jmp_buf:
         Context.setjmp_bufDecl(NewTD);
-      else if (II->isStr("sigjmp_buf"))
+        break;
+      case tok::InterestingIdentifierKind::sigjmp_buf:
         Context.setsigjmp_bufDecl(NewTD);
-      else if (II->isStr("ucontext_t"))
+        break;
+      case tok::InterestingIdentifierKind::ucontext_t:
         Context.setucontext_tDecl(NewTD);
+        break;
+      default:
+        break;
+      }
     }
 
   return NewTD;