strip UTF-8 BOM in -frewrite-includes (PR#15664)

llvm-svn: 195877

3 files changed, 10 insertions, 0 deletions

diff --git a/clang/lib/Rewrite/Frontend/InclusionRewriter.cpp b/clang/lib/Rewrite/Frontend/InclusionRewriter.cpp
index bd4250adaad..71ceb5f0b6a 100644
--- a/clang/lib/Rewrite/Frontend/InclusionRewriter.cpp
+++ b/clang/lib/Rewrite/Frontend/InclusionRewriter.cpp
@@ -367,6 +367,11 @@ bool InclusionRewriter::Process(FileID FileId,
   unsigned NextToWrite = 0;
   int Line = 1; // The current input file line number.
 
+  // Ignore UTF-8 BOM, otherwise it'd end up somewhere else than the start
+  // of the resulting file.
+  if (FromFile.getBuffer().startswith("\xEF\xBB\xBF"))
+    NextToWrite = 3;
+
   Token RawToken;
   RawLex.LexFromRawLexer(RawToken);
 
diff --git a/clang/test/Frontend/Inputs/rewrite-includes-bom.h b/clang/test/Frontend/Inputs/rewrite-includes-bom.h
new file mode 100644
index 00000000000..7ba011fc2d7
--- /dev/null
+++ b/clang/test/Frontend/Inputs/rewrite-includes-bom.h
@@ -0,0 +1 @@
+// This file starts with UTF-8 BOM marker.
diff --git a/clang/test/Frontend/rewrite-includes-bom.c b/clang/test/Frontend/rewrite-includes-bom.c
new file mode 100644
index 00000000000..a1aa4c98f86
--- /dev/null
+++ b/clang/test/Frontend/rewrite-includes-bom.c
@@ -0,0 +1,4 @@
+// RUN: %clang -E -frewrite-includes -I %S/Inputs %s -o - | %clang -fsyntax-only -Xclang -verify -x c -
+// expected-no-diagnostics
+
+#include "rewrite-includes-bom.h"