From 3144749f8bf9bbf7c027f2161a930bff80ad6f72 Mon Sep 17 00:00:00 2001
From: Argyrios Kyrtzidis <akyrtzi@gmail.com>
Date: Thu, 3 May 2012 17:50:32 +0000
Subject: [PATCH] In StringLiteralParser::init, make sure we emit an error when
 failing to lex the string, as suggested by Eli.

Part of rdar://11305263.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@156081 91177308-0d34-0410-b5e6-96231b3b80d8
---
 include/clang/Basic/DiagnosticLexKinds.td |  1 +
 include/clang/Lex/LiteralSupport.h        |  1 +
 lib/Lex/LiteralSupport.cpp                | 27 +++++++++++------------
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/include/clang/Basic/DiagnosticLexKinds.td b/include/clang/Basic/DiagnosticLexKinds.td
index 670283ef1a..3bad7b9012 100644
--- a/include/clang/Basic/DiagnosticLexKinds.td
+++ b/include/clang/Basic/DiagnosticLexKinds.td
@@ -177,6 +177,7 @@ def err_bad_character_encoding : Error<
 def warn_bad_character_encoding : ExtWarn<
   "illegal character encoding in character literal">,
   InGroup<DiagGroup<"invalid-source-encoding">>;
+def err_lexing_string : Error<"failure when lexing a string">;
 
 
 //===----------------------------------------------------------------------===//
diff --git a/include/clang/Lex/LiteralSupport.h b/include/clang/Lex/LiteralSupport.h
index 7e7f82f05f..bbce62d1d4 100644
--- a/include/clang/Lex/LiteralSupport.h
+++ b/include/clang/Lex/LiteralSupport.h
@@ -232,6 +232,7 @@ private:
   void init(const Token *StringToks, unsigned NumStringToks);
   bool CopyStringFragment(StringRef Fragment);
   bool DiagnoseBadString(const Token& Tok);
+  void DiagnoseLexingError(SourceLocation Loc);
 };
 
 }  // end namespace clang
diff --git a/lib/Lex/LiteralSupport.cpp b/lib/Lex/LiteralSupport.cpp
index b01fc1f8c6..c7120f2bef 100644
--- a/lib/Lex/LiteralSupport.cpp
+++ b/lib/Lex/LiteralSupport.cpp
@@ -1037,10 +1037,8 @@ StringLiteralParser(const Token *StringToks, unsigned NumStringToks,
 void StringLiteralParser::init(const Token *StringToks, unsigned NumStringToks){
   // The literal token may have come from an invalid source location (e.g. due
   // to a PCH error), in which case the token length will be 0.
-  if (NumStringToks == 0 || StringToks[0].getLength() < 2) {
-    hadError = true;
-    return;
-  }
+  if (NumStringToks == 0 || StringToks[0].getLength() < 2)
+    return DiagnoseLexingError(SourceLocation());
 
   // Scan all of the string portions, remember the max individual token length,
   // computing a bound on the concatenated string length, and see whether any
@@ -1057,10 +1055,8 @@ void StringLiteralParser::init(const Token *StringToks, unsigned NumStringToks){
   // Implement Translation Phase #6: concatenation of string literals
   /// (C99 5.1.1.2p1).  The common case is only one string fragment.
   for (unsigned i = 1; i != NumStringToks; ++i) {
-    if (StringToks[i].getLength() < 2) {
-      hadError = true;
-      return;
-    }
+    if (StringToks[i].getLength() < 2)
+      return DiagnoseLexingError(StringToks[i].getLocation());
 
     // The string could be shorter than this if it needs cleaning, but this is a
     // reasonable bound, which is all we need.
@@ -1123,10 +1119,8 @@ void StringLiteralParser::init(const Token *StringToks, unsigned NumStringToks){
     unsigned ThisTokLen = 
       Lexer::getSpelling(StringToks[i], ThisTokBuf, SM, Features,
                          &StringInvalid);
-    if (StringInvalid) {
-      hadError = true;
-      continue;
-    }
+    if (StringInvalid)
+      return DiagnoseLexingError(StringToks[i].getLocation());
 
     const char *ThisTokBegin = ThisTokBuf;
     const char *ThisTokEnd = ThisTokBuf+ThisTokLen;
@@ -1195,8 +1189,7 @@ void StringLiteralParser::init(const Token *StringToks, unsigned NumStringToks){
       if (ThisTokBuf[0] != '"') {
         // The file may have come from PCH and then changed after loading the
         // PCH; Fail gracefully.
-        hadError = true;
-        continue;
+        return DiagnoseLexingError(StringToks[i].getLocation());
       }
       ++ThisTokBuf; // skip "
 
@@ -1354,6 +1347,12 @@ bool StringLiteralParser::DiagnoseBadString(const Token &Tok) {
   return !NoErrorOnBadEncoding;
 }
 
+void StringLiteralParser::DiagnoseLexingError(SourceLocation Loc) {
+  hadError = true;
+  if (Diags)
+    Diags->Report(Loc, diag::err_lexing_string);
+}
+
 /// getOffsetOfStringByte - This function returns the offset of the
 /// specified byte of the string data represented by Token.  This handles
 /// advancing over escape sequences in the string.
-- 
2.40.0