[scanner] Fix bom handling

src/parsing/scanner-character-streams.cc

Index: src/parsing/scanner-character-streams.cc
diff --git a/src/parsing/scanner-character-streams.cc b/src/parsing/scanner-character-streams.cc
index b5e9c171da0561ee81dcdd5be0a388cce419c883..d3162dfbb2263bfd5bcb29a0b85346df3ce4d2c1 100644
--- a/src/parsing/scanner-character-streams.cc
+++ b/src/parsing/scanner-character-streams.cc
@@ -15,6 +15,10 @@
 namespace v8 {
 namespace internal {
 
+namespace {
+const unibrow::uchar kUtf8Bom = 0xfeff;
+}  // namespace
+
 // ----------------------------------------------------------------------------
 // BufferedUtf16CharacterStreams
 //
@@ -263,7 +267,9 @@ bool Utf8ExternalStreamingStream::SkipToPosition(size_t position) {
   while (it < chunk.length && chars < position) {
     unibrow::uchar t =
         unibrow::Utf8::ValueOfIncremental(chunk.data[it], &incomplete_char);
-    if (t != unibrow::Utf8::kIncomplete) {
+    if (t == kUtf8Bom && current_.pos.chars == 0) {
+      // BOM detected at beginning of the stream. Don't copy it.

[vogelheim, 2017/01/30 18:59:32]

copy -> count. This loop doesn't copy anything; it merely counts characters to
determine the correct position.

+    } else if (t != unibrow::Utf8::kIncomplete) {
       chars++;
       if (t > unibrow::Utf16::kMaxNonSurrogateCharCode) chars++;
     }
@@ -304,8 +310,6 @@ void Utf8ExternalStreamingStream::FillBufferFromCurrentChunk() {
     return;
   }
 
-  static const unibrow::uchar kUtf8Bom = 0xfeff;
-
   unibrow::Utf8::Utf8IncrementalBuffer incomplete_char =
       current_.pos.incomplete_char;
   size_t it;