Regression test for Utf-8 BOM handling (crbug.com/685618).

test/cctest/parsing/test-scanner-streams.cc

 // Copyright 2016 the V8 project authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "src/factory.h"  // for i::Factory::NewExternalStringFrom*Byte
 #include "src/objects-inl.h"
 #include "src/parsing/scanner-character-streams.h"
 #include "src/parsing/scanner.h"
 #include "src/type-feedback-vector-inl.h"  // for include "src/factory.h"
 #include "test/cctest/cctest.h"
@@ skipping 114 matching lines @@
     CHECK_EQ(unicode_ucs2[i], stream->Advance());
   }
   CHECK_EQ(v8::internal::Utf16CharacterStream::kEndOfInput, stream->Advance());
 
   // Make sure seek works.
   stream->Seek(0);
   CHECK_EQ(unicode_ucs2[0], stream->Advance());
 
   stream->Seek(5);
   CHECK_EQ(unicode_ucs2[5], stream->Advance());
+
+  // Try again, but make sure we have to seek 'backwards'.
+  while (v8::internal::Utf16CharacterStream::kEndOfInput != stream->Advance()) {
+    // Do nothing. We merely advance the stream to the end of its input.
+  }
+  stream->Seek(5);
+  CHECK_EQ(unicode_ucs2[5], stream->Advance());
 }
 
 TEST(Utf8SplitBOM) {
   // Construct chunks with a BOM split into two chunks.
   char partial_bom[] = "\xef\xbb";
   char data[1 + arraysize(unicode_utf8)] = {"\xbf"};
   strncpy(data + 1, unicode_utf8, arraysize(unicode_utf8));
 
   {
     const char* chunks[] = {partial_bom, data, "\0"};
@@ skipping 295 matching lines @@
     // 65533) instead of the incorrectly coded Latin1 char.
     ChunkSource chunks(bytes, len, false);
     std::unique_ptr<i::Utf16CharacterStream> stream(i::ScannerStream::For(
         &chunks, v8::ScriptCompiler::StreamedSource::UTF8, nullptr));
     for (size_t i = 0; i < len; i++) {
       CHECK_EQ(unicode[i], stream->Advance());
     }
     CHECK_EQ(i::Utf16CharacterStream::kEndOfInput, stream->Advance());
   }
 }