1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/browser/components/translation/cld2/internal/fixunicodevalue.cc Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,54 @@
1.4 +// Copyright 2013 Google Inc. All Rights Reserved.
1.5 +//
1.6 +// Licensed under the Apache License, Version 2.0 (the "License");
1.7 +// you may not use this file except in compliance with the License.
1.8 +// You may obtain a copy of the License at
1.9 +//
1.10 +// http://www.apache.org/licenses/LICENSE-2.0
1.11 +//
1.12 +// Unless required by applicable law or agreed to in writing, software
1.13 +// distributed under the License is distributed on an "AS IS" BASIS,
1.14 +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
1.15 +// See the License for the specific language governing permissions and
1.16 +// limitations under the License.
1.17 +
1.18 +//
1.19 +// Routine that maps a Unicode code point to an interchange-valid one
1.20 +//
1.21 +
1.22 +#include "fixunicodevalue.h"
1.23 +#include "integral_types.h"
1.24 +
1.25 +namespace CLD2 {
1.26 +
1.27 +// Guarantees that the resulting output value is interchange valid
1.28 +// 00-FF; map to spaces or MS CP1252
1.29 +// D800-DFFF; surrogates
1.30 +// FDD0-FDEF; non-characters
1.31 +// xxFFFE-xxFFFF; non-characters
1.32 +char32 FixUnicodeValue(char32 uv) {
1.33 + uint32 uuv = static_cast<uint32>(uv);
1.34 + if (uuv < 0x0100) {
1.35 + return kMapFullMicrosoft1252OrSpace[uuv];
1.36 + }
1.37 + if (uuv < 0xD800) {
1.38 + return uv;
1.39 + }
1.40 + if ((uuv & ~0x0F) == 0xFDD0) { // non-characters
1.41 + return 0xFFFD;
1.42 + }
1.43 + if ((uuv & ~0x0F) == 0xFDE0) { // non-characters
1.44 + return 0xFFFD;
1.45 + }
1.46 + if ((uuv & 0x00FFFE) == 0xFFFE) { // non-characters
1.47 + return 0xFFFD;
1.48 + }
1.49 + if ((0xE000 <= uuv) && (uuv <= 0x10FFFF)) {
1.50 + return uv;
1.51 + }
1.52 + // surrogates and negative and > 0x10FFFF all land here
1.53 + return 0xFFFD;
1.54 +}
1.55 +
1.56 +} // End namespace CLD2
1.57 +
