| 1 | // Copyright 2011 Google Inc. All Rights Reserved.
|
|---|
| 2 | //
|
|---|
| 3 | // Licensed under the Apache License, Version 2.0 (the "License"); you
|
|---|
| 4 | // may not use this file except in compliance with the License. You
|
|---|
| 5 | // may obtain a copy of the License at
|
|---|
| 6 | //
|
|---|
| 7 | // http://www.apache.org/licenses/LICENSE-2.0
|
|---|
| 8 | //
|
|---|
| 9 | // Unless required by applicable law or agreed to in writing, software
|
|---|
| 10 | // distributed under the License is distributed on an "AS IS" BASIS,
|
|---|
| 11 | // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|---|
| 12 | // implied. See the License for the specific language governing
|
|---|
| 13 | // permissions and limitations under the License.
|
|---|
| 14 |
|
|---|
| 15 | #ifndef WEBGL_LOADER_UTF8_H_
|
|---|
| 16 | #define WEBGL_LOADER_UTF8_H_
|
|---|
| 17 |
|
|---|
| 18 | #include "base.h"
|
|---|
| 19 | #include "stream.h"
|
|---|
| 20 |
|
|---|
| 21 | namespace webgl_loader {
|
|---|
| 22 |
|
|---|
| 23 | const uint8 kUtf8MoreBytesPrefix = 0x80;
|
|---|
| 24 | const uint8 kUtf8TwoBytePrefix = 0xC0;
|
|---|
| 25 | const uint8 kUtf8ThreeBytePrefix = 0xE0;
|
|---|
| 26 |
|
|---|
| 27 | const uint16 kUtf8TwoByteLimit = 0x0800;
|
|---|
| 28 | const uint16 kUtf8SurrogatePairStart = 0xD800;
|
|---|
| 29 | const uint16 kUtf8SurrogatePairNum = 0x0800;
|
|---|
| 30 | const uint16 kUtf8EncodableEnd = 0x10000 - kUtf8SurrogatePairNum;
|
|---|
| 31 |
|
|---|
| 32 | const uint16 kUtf8MoreBytesMask = 0x3F;
|
|---|
| 33 |
|
|---|
| 34 | bool Uint16ToUtf8(uint16 word, ByteSinkInterface* sink) {
|
|---|
| 35 | if (word < 0x80) {
|
|---|
| 36 | sink->Put(static_cast<char>(word));
|
|---|
| 37 | } else if (word < kUtf8TwoByteLimit) {
|
|---|
| 38 | sink->Put(static_cast<char>(kUtf8TwoBytePrefix + (word >> 6)));
|
|---|
| 39 | sink->Put(static_cast<char>(kUtf8MoreBytesPrefix +
|
|---|
| 40 | (word & kUtf8MoreBytesMask)));
|
|---|
| 41 | } else if (word < kUtf8EncodableEnd) {
|
|---|
| 42 | // We can only encode 65535 - 2048 values because of illegal UTF-8
|
|---|
| 43 | // characters, such as surrogate pairs in [0xD800, 0xDFFF].
|
|---|
| 44 | if (word >= kUtf8SurrogatePairStart) {
|
|---|
| 45 | // Shift the result to avoid the surrogate pair range.
|
|---|
| 46 | word += kUtf8SurrogatePairNum;
|
|---|
| 47 | }
|
|---|
| 48 | sink->Put(static_cast<char>(kUtf8ThreeBytePrefix + (word >> 12)));
|
|---|
| 49 | sink->Put(static_cast<char>(kUtf8MoreBytesPrefix +
|
|---|
| 50 | ((word >> 6) & kUtf8MoreBytesMask)));
|
|---|
| 51 | sink->Put(static_cast<char>(kUtf8MoreBytesPrefix +
|
|---|
| 52 | (word & kUtf8MoreBytesMask)));
|
|---|
| 53 | } else {
|
|---|
| 54 | return false;
|
|---|
| 55 | }
|
|---|
| 56 | return true;
|
|---|
| 57 | }
|
|---|
| 58 |
|
|---|
| 59 | } // namespace webgl_loader
|
|---|
| 60 |
|
|---|
| 61 | #endif // WEBGL_LOADER_UTF8_H_
|
|---|
