1 /*
2 * Copyright (c) 2021-2022 Huawei Device Co., Ltd.
3 * Licensed under the Apache License, Version 2.0 (the "License");
4 * you may not use this file except in compliance with the License.
5 * You 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 implied.
12 * See the License for the specific language governing permissions and
13 * limitations under the License.
14 */
15
16 #include "ustring.h"
17
18 #include <iterator>
19
20 namespace panda::es2panda::util {
21
Mutf8() const22 std::string StringView::Mutf8() const noexcept
23 {
24 std::string mutf8;
25 mutf8.reserve(sv_.size());
26
27 Iterator iter(*this);
28
29 while (iter.HasNext()) {
30 Mutf8Encode(&mutf8, iter.Next());
31 }
32
33 return mutf8;
34 }
35
DecodeSurrogates(char32_t high,char32_t low)36 char32_t StringView::DecodeSurrogates(char32_t high, char32_t low)
37 {
38 constexpr auto OFFSET = 10;
39 char32_t result = (high - Constants::SURROGATE_HIGH_MIN) << OFFSET;
40 result += low - Constants::SURROGATE_LOW_MAX;
41 result += Constants::CELESTIAL_OFFSET;
42 return result;
43 }
44
EncodeSurrogate(char32_t cp)45 std::tuple<char32_t, char32_t> StringView::EncodeSurrogate(char32_t cp)
46 {
47 constexpr auto OFFSET = 10;
48 char32_t cu1 = ((cp - Constants::CELESTIAL_OFFSET) >> OFFSET) | Constants::SURROGATE_HIGH_MIN;
49 char32_t cu2 = (cp & Constants::SURROGATE_LOW_MARKER) | Constants::SURROGATE_HIGH_MAX;
50
51 return {cu1, cu2};
52 }
53
SkipCp() const54 void StringView::Iterator::SkipCp() const
55 {
56 if (!HasNext()) {
57 return;
58 }
59
60 char32_t cu0 = static_cast<uint8_t>(*iter_++);
61
62 if (cu0 < Constants::UTF8_1BYTE_LIMIT) {
63 return;
64 }
65
66 if ((cu0 & Constants::UTF8_3BYTE_HEADER) == Constants::UTF8_2BYTE_HEADER) {
67 iter_ += 1U;
68 return;
69 }
70
71 if ((cu0 & Constants::UTF8_4BYTE_HEADER) == Constants::UTF8_3BYTE_HEADER) {
72 iter_ += 2U;
73 return;
74 }
75
76 if (((cu0 & Constants::UTF8_DECODE_4BYTE_MASK) == Constants::UTF8_4BYTE_HEADER) &&
77 (cu0 <= Constants::UTF8_DECODE_4BYTE_LIMIT)) {
78 iter_ += 3U;
79 return;
80 }
81 }
82
83 } // namespace panda::es2panda::util
84
85 // NOLINTNEXTLINE(cert-dcl58-cpp)
86 namespace std {
87
operator <<(ostream & os,const panda::es2panda::util::StringView & us)88 ostream &operator<<(ostream &os, const panda::es2panda::util::StringView &us)
89 {
90 os << us.Utf8();
91 return os;
92 }
93
94 } // namespace std
95