Move all utf8 decoding under fx_string.h

Put encoder in cfx_utf8encoder.{h,cpp} to parallel decoder.
Add tests, and fix one corner case involving 0xff.

Change-Id: Ib97540afdc708bcc6280a79c76734ec68ea72690
Reviewed-on: https://pdfium-review.googlesource.com/39770
Commit-Queue: Lei Zhang <thestig@chromium.org>
Reviewed-by: Lei Zhang <thestig@chromium.org>

1 files changed, 31 insertions, 0 deletions

diff --git a/core/fxcrt/cfx_utf8encoder.h b/core/fxcrt/cfx_utf8encoder.h
new file mode 100644
index 0000000000..d44a829108
--- /dev/null
+++ b/core/fxcrt/cfx_utf8encoder.h
@@ -0,0 +1,31 @@
+// Copyright 2018 PDFium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com
+
+#ifndef CORE_FXCRT_CFX_UTF8ENCODER_H_
+#define CORE_FXCRT_CFX_UTF8ENCODER_H_
+
+#include <vector>
+
+#include "core/fxcrt/fx_string.h"
+
+class CFX_UTF8Encoder {
+ public:
+  CFX_UTF8Encoder();
+  ~CFX_UTF8Encoder();
+
+  void Input(wchar_t unicodeAsWchar);
+
+  // The data returned by GetResult() is invalidated when this is modified by
+  // appending any data.
+  ByteStringView GetResult() const {
+    return ByteStringView(m_Buffer.data(), m_Buffer.size());
+  }
+
+ private:
+  std::vector<uint8_t> m_Buffer;
+};
+
+#endif  // CORE_FXCRT_CFX_UTF8ENCODER_H_