[clang] fix out of bounds access in an empty string when lexing a _Pragma with missing string token

[arphaman]

Summary

The lexer can attempt to lex a _Pragma and crash with an out of bounds string access when it's
lexing a _Pragma whose string token is in an invalid buffer, e.g. when a module header file from which the macro
expansion for that token came from was deleted from the file system.

[arphaman]

Fix test failure with asserts enabled.

[egorzhdan]

LGTM!

clang/lib/Frontend/PrintPreprocessedOutput.cpp

public:
   /// @param Tok                 Token where to move to.
   /// @param RequireStartOfLine  Whether the next line depends on being in the
   ///                            first column, such as a directive.
   ///
   /// @return Whether column adjustments are necessary.
   bool MoveToLine(const Token &Tok, bool RequireStartOfLine) {
     PresumedLoc PLoc = SM.getPresumedLoc(Tok.getLocation());
     unsigned TargetLine = PLoc.isValid() ? PLoc.getLine() : CurLine;
-    bool IsFirstInFile = Tok.isAtStartOfLine() && PLoc.getLine() == 1;
+    bool IsFirstInFile =
+        Tok.isAtStartOfLine() && PLoc.isValid() && PLoc.getLine() == 1;
     return MoveToLine(TargetLine, RequireStartOfLine) || IsFirstInFile;
   }
 
   /// Move to the line of the provided source location. Returns true if a new
   /// line was inserted.
   bool MoveToLine(SourceLocation Loc, bool RequireStartOfLine) {
     PresumedLoc PLoc = SM.getPresumedLoc(Loc);
     unsigned TargetLine = PLoc.isValid() ? PLoc.getLine() : CurLine;

clang/lib/Lex/Pragma.cpp

void Preprocessor::Handle_Pragma(Token &Tok) {
 
   // If we're expanding a macro argument, put the tokens back.
   if (InMacroArgPreExpansion) {
     Toks.revert();
     return;
   }
 
   SourceLocation RParenLoc = Tok.getLocation();
-  std::string StrVal = getSpelling(StrTok);
+  bool Invalid = false;
+  std::string StrVal = getSpelling(StrTok, &Invalid);
+  if (Invalid) {
+    Diag(PragmaLoc, diag::err__Pragma_malformed);
+    return;
+  }
 
   // The _Pragma is lexically sound.  Destringize according to C11 6.10.9.1:
   // "The string literal is destringized by deleting any encoding prefix,
   // deleting the leading and trailing double-quotes, replacing each escape
   // sequence \" by a double-quote, and replacing each escape sequence \\ by a
   // single backslash."
   if (StrVal[0] == 'L' || StrVal[0] == 'U' ||
       (StrVal[0] == 'u' && StrVal[1] != '8'))

clang/test/Preprocessor/pragma-missing-string-token.c

+// RUN: rm -rf %t
+// RUN: split-file %s %t
+
+// RUN: %clang_cc1 -emit-module -x c -fmodules -I %t/Inputs -fmodule-name=aa %t/Inputs/module.modulemap -o %t/aa.pcm
+// RUN: rm %t/Inputs/b.h
+// RUN: not %clang_cc1 -E -fmodules -I %t/Inputs -fmodule-file=%t/aa.pcm %s -o - -fallow-pcm-with-compiler-errors 2>&1 | FileCheck %s
+
+//--- Inputs/module.modulemap
+module aa {
+    header "a.h"
+    header "b.h"
+}
+
+//--- Inputs/a.h
+#define TEST(x) x
+
+//--- Inputs/b.h
+#define SUB "mypragma"
+
+//--- test.c
+#include "a.h"
+
+_Pragma(SUB);
+int a = TEST(SUB);
+
+// CHECK: int a
+// CHECK: 1 error generated