Handle BOMs in dart2js.

sdk/lib/_internal/compiler/implementation/scanner/utf8_bytes_scanner.dart

Index: sdk/lib/_internal/compiler/implementation/scanner/utf8_bytes_scanner.dart
diff --git a/sdk/lib/_internal/compiler/implementation/scanner/utf8_bytes_scanner.dart b/sdk/lib/_internal/compiler/implementation/scanner/utf8_bytes_scanner.dart
index 62722ea6f7d0357831bf497801eca8244806f53f..c2adeb41672d726ff10b7d4a3a8c3f31a7cc0189 100644
--- a/sdk/lib/_internal/compiler/implementation/scanner/utf8_bytes_scanner.dart
+++ b/sdk/lib/_internal/compiler/implementation/scanner/utf8_bytes_scanner.dart
@@ -69,6 +69,8 @@ class Utf8BytesScanner extends ArrayBasedScanner {
       : bytes = file.slowUtf8Bytes(),
         super(file, includeComments) {
     ensureZeroTermination();
+    // Skip a leading BOM.
+    if (_containsBomAt(0)) byteOffset += 3;
   }
 
   /**
@@ -95,6 +97,15 @@ class Utf8BytesScanner extends ArrayBasedScanner {
     }
   }
 
+  bool _containsBomAt(int offset) {
+    const BOM_UTF8 = const [0xEF, 0xBB, 0xBF];
+
+    return offset + 3 < bytes.length &&
+        bytes[offset] == BOM_UTF8[0] &&
+        bytes[offset + 1] == BOM_UTF8[1] &&
+        bytes[offset + 2] == BOM_UTF8[2];
+  }
+
   int advance() => bytes[++byteOffset];
 
   int peek() => bytes[byteOffset + 1];
@@ -120,6 +131,13 @@ class Utf8BytesScanner extends ArrayBasedScanner {
     // TODO(lry): measurably slow, decode creates first a Utf8Decoder and a
     // _Utf8Decoder instance. Also the sublist is eagerly allocated.
     String codePoint = UTF8.decode(bytes.sublist(startOffset, end));
+    if (codePoint.length == 0) {
+      // The UTF-8 decoder discards leading BOM characters.
+      // TODO(floitsch): don't just assume that removed characters were the
+      // BOM.
+      assert(_containsBomAt(startOffset));
+      codePoint = new String.fromCharCode(UNICODE_BOM_CHARACTER_RUNE);
+    }
     if (codePoint.length == 1) {
       if (advance) {
         utf8Slack += (numBytes - 1);