5 files changed, 40 insertions, 19 deletions

diff --git a/clang/lib/Lex/DependencyDirectivesScanner.cpp b/clang/lib/Lex/DependencyDirectivesScanner.cpp
index 869c9ce..9ccff5e 100644
--- a/clang/lib/Lex/DependencyDirectivesScanner.cpp
+++ b/clang/lib/Lex/DependencyDirectivesScanner.cpp
@@ -560,15 +560,13 @@ bool Scanner::lexModuleDirectiveBody(DirectiveKind Kind, const char *&First,
     if (Tok.is(tok::semi))
       break;
   }
+
+  const auto &Tok = lexToken(First, End);
   pushDirective(Kind);
-  skipWhitespace(First, End);
-  if (First == End)
+  if (Tok.is(tok::eof) || Tok.is(tok::eod))
     return false;
-  if (!isVerticalWhitespace(*First))
-    return reportError(
-        DirectiveLoc, diag::err_dep_source_scanner_unexpected_tokens_at_import);
-  skipNewline(First, End);
-  return false;
+  return reportError(DirectiveLoc,
+                     diag::err_dep_source_scanner_unexpected_tokens_at_import);
 }
 
 dependency_directives_scan::Token &Scanner::lexToken(const char *&First,
@@ -735,6 +733,13 @@ bool Scanner::lexModule(const char *&First, const char *const End) {
       return false;
     break;
   }
+  case ';': {
+    // Handle the global module fragment `module;`.
+    if (Id == "module" && !Export)
+      break;
+    skipLine(First, End);
+    return false;
+  }
   case '<':
   case '"':
     break;
@@ -905,14 +910,6 @@ bool Scanner::lexPPLine(const char *&First, const char *const End) {
     CurDirToks.clear();
   });
 
-  // Handle "@import".
-  if (*First == '@')
-    return lexAt(First, End);
-
-  // Handle module directives for C++20 modules.
-  if (*First == 'i' || *First == 'e' || *First == 'm')
-    return lexModule(First, End);
-
   if (*First == '_') {
     if (isNextIdentifierOrSkipLine("_Pragma", First, End))
       return lex_Pragma(First, End);
@@ -925,6 +922,14 @@ bool Scanner::lexPPLine(const char *&First, const char *const End) {
   auto ScEx2 = make_scope_exit(
       [&]() { TheLexer.setParsingPreprocessorDirective(false); });
 
+  // Handle "@import".
+  if (*First == '@')
+    return lexAt(First, End);
+
+  // Handle module directives for C++20 modules.
+  if (*First == 'i' || *First == 'e' || *First == 'm')
+    return lexModule(First, End);
+
   // Lex '#'.
   const dependency_directives_scan::Token &HashTok = lexToken(First, End);
   if (HashTok.is(tok::hashhash)) {
diff --git a/clang/lib/Lex/LiteralSupport.cpp b/clang/lib/Lex/LiteralSupport.cpp
index a62508e..5b08d7f 100644
--- a/clang/lib/Lex/LiteralSupport.cpp
+++ b/clang/lib/Lex/LiteralSupport.cpp
@@ -1467,7 +1467,7 @@ void NumericLiteralParser::ParseNumberStartingWithZero(SourceLocation TokLoc) {
   if (s != PossibleNewDigitStart)
     DigitsBegin = PossibleNewDigitStart;
   else
-    IsSingleZero = (s == ThisTokEnd); // Is the only thing we've seen a 0?
+    IsSingleZero = (s == ThisTokBegin + 1);
 
   if (s == ThisTokEnd)
     return; // Done, simple octal number like 01234
diff --git a/clang/lib/Lex/PPMacroExpansion.cpp b/clang/lib/Lex/PPMacroExpansion.cpp
index 890567c..6f12ac8 100644
--- a/clang/lib/Lex/PPMacroExpansion.cpp
+++ b/clang/lib/Lex/PPMacroExpansion.cpp
@@ -1760,7 +1760,8 @@ void Preprocessor::ExpandBuiltinMacro(Token &Tok) {
               Tok, *this, diag::err_feature_check_malformed);
           if (!II)
             return false;
-          else if (II->getBuiltinID() != 0) {
+          unsigned BuiltinID = II->getBuiltinID();
+          if (BuiltinID != 0) {
             switch (II->getBuiltinID()) {
             case Builtin::BI__builtin_cpu_is:
               return getTargetInfo().supportsCpuIs();
@@ -1774,8 +1775,11 @@ void Preprocessor::ExpandBuiltinMacro(Token &Tok) {
               // usual allocation and deallocation functions. Required by libc++
               return 201802;
             default:
+              // __has_builtin should return false for aux builtins.
+              if (getBuiltinInfo().isAuxBuiltinID(BuiltinID))
+                return false;
               return Builtin::evaluateRequiredTargetFeatures(
-                  getBuiltinInfo().getRequiredFeatures(II->getBuiltinID()),
+                  getBuiltinInfo().getRequiredFeatures(BuiltinID),
                   getTargetInfo().getTargetOpts().FeatureMap);
             }
             return true;
diff --git a/clang/lib/Lex/Pragma.cpp b/clang/lib/Lex/Pragma.cpp
index 01c85e6..bba3c89 100644
--- a/clang/lib/Lex/Pragma.cpp
+++ b/clang/lib/Lex/Pragma.cpp
@@ -591,7 +591,8 @@ IdentifierInfo *Preprocessor::ParsePragmaPushOrPopMacro(Token &Tok) {
   }
 
   // Remember the macro string.
-  std::string StrVal = getSpelling(Tok);
+  Token StrTok = Tok;
+  std::string StrVal = getSpelling(StrTok);
 
   // Read the ')'.
   Lex(Tok);
@@ -604,6 +605,15 @@ IdentifierInfo *Preprocessor::ParsePragmaPushOrPopMacro(Token &Tok) {
   assert(StrVal[0] == '"' && StrVal[StrVal.size()-1] == '"' &&
          "Invalid string token!");
 
+  if (StrVal.size() <= 2) {
+    Diag(StrTok.getLocation(), diag::warn_pargma_push_pop_macro_empty_string)
+        << SourceRange(
+               StrTok.getLocation(),
+               StrTok.getLocation().getLocWithOffset(StrTok.getLength()))
+        << PragmaTok.getIdentifierInfo()->isStr("pop_macro");
+    return nullptr;
+  }
+
   // Create a Token from the string.
   Token MacroTok;
   MacroTok.startToken();
diff --git a/clang/lib/Lex/Preprocessor.cpp b/clang/lib/Lex/Preprocessor.cpp
index bcd3ea6..e278846 100644
--- a/clang/lib/Lex/Preprocessor.cpp
+++ b/clang/lib/Lex/Preprocessor.cpp
@@ -950,6 +950,8 @@ void Preprocessor::Lex(Token &Result) {
     case tok::period:
       ModuleDeclState.handlePeriod();
       break;
+    case tok::eod:
+      break;
     case tok::identifier:
       // Check "import" and "module" when there is no open bracket. The two
       // identifiers are not meaningful with open brackets.