1 /*
2 * Copyright (c) Huawei Technologies Co., Ltd. 2023. All rights reserved.
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 "codec_cov.h"
17
18 #include <memory>
19 #include <iostream>
20 #ifdef _WIN32
21 #include <windows.h>
22 #endif
23
24 namespace SysTuning {
25 namespace base {
PreNum(unsigned char byte)26 int32_t PreNum(unsigned char byte)
27 {
28 constexpr uint32_t BITS = 8;
29 unsigned char mask = 0x80;
30 int32_t num = 0;
31 for (uint32_t i = 0; i < BITS; i++) {
32 if ((byte & mask) == mask) {
33 mask = mask >> 1;
34 num++;
35 } else {
36 break;
37 }
38 }
39 return num;
40 }
41
IsUTF8(const uint8_t * data,int32_t len)42 bool IsUTF8(const uint8_t *data, int32_t len)
43 {
44 constexpr uint8_t mask = 0x80;
45 constexpr uint8_t firstByte = 0xc0;
46 constexpr int32_t target = 2;
47 int32_t num = 0;
48 int32_t i = 0;
49 while (i < len) {
50 if ((data[i] & mask) == 0x00) {
51 i++;
52 continue;
53 }
54 if ((num = PreNum(data[i])) <= target) {
55 return false;
56 }
57 i++;
58 for (int32_t j = 0; j < num - 1; j++) {
59 if ((data[i] & firstByte) != mask) {
60 return false;
61 }
62 i++;
63 }
64 }
65 return true;
66 }
67
IsGBK(const uint8_t * data,int32_t len)68 bool IsGBK(const uint8_t *data, int32_t len)
69 {
70 constexpr int32_t step = 2;
71 constexpr uint8_t asciiEnd = 0x7f;
72 constexpr uint8_t firstByte = 0x81;
73 constexpr uint8_t firstByteEnd = 0xfe;
74 constexpr uint8_t secondByteOne = 0x40;
75 constexpr uint8_t secondByteTwoEnd = 0xfe;
76 constexpr uint8_t gbkMask = 0x7f;
77 int32_t i = 0;
78 while (i < len) {
79 if (data[i] <= asciiEnd) {
80 i++;
81 continue;
82 } else {
83 if (data[i] >= firstByte && data[i] <= firstByteEnd && data[i + 1] >= secondByteOne &&
84 data[i + 1] <= secondByteTwoEnd && data[i + 1] != gbkMask) {
85 i += step;
86 continue;
87 } else {
88 return false;
89 }
90 }
91 }
92 return true;
93 }
94
GetCoding(const uint8_t * data,int32_t len)95 CODING GetCoding(const uint8_t *data, int32_t len)
96 {
97 CODING coding;
98 if (IsUTF8(data, len)) {
99 coding = UTF8;
100 } else if (IsGBK(data, len)) {
101 coding = GBK;
102 } else {
103 coding = UNKOWN;
104 }
105 return coding;
106 }
107
108 #ifdef _WIN32
GbkToUtf8(const char * srcStr)109 std::string GbkToUtf8(const char *srcStr)
110 {
111 int32_t len = MultiByteToWideChar(CP_ACP, 0, srcStr, -1, NULL, 0);
112 std::unique_ptr<wchar_t[]> wstr = std::make_unique<wchar_t[]>(len + 1);
113 MultiByteToWideChar(CP_ACP, 0, srcStr, -1, wstr.get(), len);
114 len = WideCharToMultiByte(CP_UTF8, 0, wstr.get(), -1, NULL, 0, NULL, NULL);
115 std::unique_ptr<char[]> str = std::make_unique<char[]>(len + 1);
116 WideCharToMultiByte(CP_UTF8, 0, wstr.get(), -1, str.get(), len, NULL, NULL);
117 return std::string(str.get());
118 }
Utf8ToGbk(const char * srcStr)119 std::string Utf8ToGbk(const char *srcStr)
120 {
121 int32_t len = MultiByteToWideChar(CP_UTF8, 0, srcStr, -1, NULL, 0);
122 std::unique_ptr<wchar_t[]> wstr = std::make_unique<wchar_t[]>(len + 1);
123 MultiByteToWideChar(CP_UTF8, 0, srcStr, -1, wstr.get(), len);
124 len = WideCharToMultiByte(CP_ACP, 0, wstr.get(), -1, NULL, 0, NULL, NULL);
125 std::unique_ptr<char[]> str = std::make_unique<char[]>(len + 1);
126 WideCharToMultiByte(CP_ACP, 0, wstr.get(), -1, str.get(), len, NULL, NULL);
127 return std::string(str.get());
128 }
129 /** @fn std::wstring String2WString(const std::string& strInput)
130 * @brief string转换为wstring
131 * @param (IN) const std::string&
132 * @return std::wstring
133 */
String2WString(const std::string & strInput)134 std::wstring String2WString(const std::string &strInput)
135 {
136 auto codePage = IsGBK(reinterpret_cast<const uint8_t *>(strInput.c_str()), strInput.length()) ? CP_ACP : CP_UTF8;
137 if (strInput.empty()) {
138 std::cout << "strInput is empty" << std::endl;
139 return L"";
140 }
141
142 // 获取待转换的数据的长度
143 int len_in = MultiByteToWideChar(codePage, 0, (LPCSTR)strInput.c_str(), -1, NULL, 0);
144 if (len_in <= 0) {
145 std::cout << "The result of WideCharToMultiByte is Invalid!" << std::endl;
146 return L"";
147 }
148
149 // 为输出数据申请空间
150 std::wstring wstr_out;
151 wstr_out.resize(len_in - 1, L'\0');
152
153 // 数据格式转换
154 int to_result = MultiByteToWideChar(codePage, 0, (LPCSTR)strInput.c_str(), -1, (LPWSTR)wstr_out.c_str(), len_in);
155 // 判断转换结果
156 if (0 == to_result) {
157 std::cout << "Can't transfer String to WString" << std::endl;
158 }
159
160 return wstr_out;
161 }
162 #endif
163 } // namespace base
164 } // namespace SysTuning
165