[clang-scan-deps] Skip UTF-8 BOM in source minimizer

Differential Revision: https://reviews.llvm.org/D66511

llvm-svn: 369993

2 files changed, 17 insertions, 0 deletions

diff --git a/clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp b/clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
index 265a6e44e33..a350481df9a 100644
--- a/clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
+++ b/clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
@@ -834,7 +834,14 @@ bool Minimizer::lexPPLine(const char *&First, const char *const End) {
   return lexDefault(Kind, Id.Name, First, End);
 }
 
+static void skipUTF8ByteOrderMark(const char *&First, const char *const End) {
+  if ((End - First) >= 3 && First[0] == '\xef' && First[1] == '\xbb' &&
+      First[2] == '\xbf')
+    First += 3;
+}
+
 bool Minimizer::minimizeImpl(const char *First, const char *const End) {
+  skipUTF8ByteOrderMark(First, End);
   while (First != End)
     if (lexPPLine(First, End))
       return true;
diff --git a/clang/test/Lexer/minimize_source_to_dependency_directives_utf8bom.c b/clang/test/Lexer/minimize_source_to_dependency_directives_utf8bom.c
new file mode 100644
index 00000000000..305442fbd28
--- /dev/null
+++ b/clang/test/Lexer/minimize_source_to_dependency_directives_utf8bom.c
@@ -0,0 +1,10 @@
+// Test UTF8 BOM at start of file

+// RUN: printf '\xef\xbb\xbf' > %t.c

+// RUN: echo '#ifdef TEST\n' >> %t.c

+// RUN: echo '#include <string>' >> %t.c

+// RUN: echo '#endif' >> %t.c

+// RUN: %clang_cc1 -DTEST -print-dependency-directives-minimized-source %t.c 2>&1 | FileCheck %s

+

+// CHECK:      #ifdef TEST

+// CHECK-NEXT: #include <string>

+// CHECK-NEXT: #endif