| 1 | /* |
| 2 | * Copyright 2010-2017 Amazon.com, Inc. or its affiliates. All Rights Reserved. |
| 3 | * |
| 4 | * Licensed under the Apache License, Version 2.0 (the "License"). |
| 5 | * You may not use this file except in compliance with the License. |
| 6 | * A copy of the License is located at |
| 7 | * |
| 8 | * http://aws.amazon.com/apache2.0 |
| 9 | * |
| 10 | * or in the "license" file accompanying this file. This file is distributed |
| 11 | * on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either |
| 12 | * express or implied. See the License for the specific language governing |
| 13 | * permissions and limitations under the License. |
| 14 | */ |
| 15 | |
| 16 | |
| 17 | #include <aws/core/utils/StringUtils.h> |
| 18 | #include <aws/core/utils/memory/stl/AWSStringStream.h> |
| 19 | #include <algorithm> |
| 20 | #include <iomanip> |
| 21 | #include <cstdlib> |
| 22 | #include <cstdio> |
| 23 | #include <cstring> |
| 24 | #include <functional> |
| 25 | |
| 26 | #ifdef _WIN32 |
| 27 | #include <Windows.h> |
| 28 | #endif |
| 29 | |
| 30 | using namespace Aws::Utils; |
| 31 | |
| 32 | void StringUtils::Replace(Aws::String& s, const char* search, const char* replace) |
| 33 | { |
| 34 | if(!search || !replace) |
| 35 | { |
| 36 | return; |
| 37 | } |
| 38 | |
| 39 | size_t replaceLength = strlen(replace); |
| 40 | size_t searchLength = strlen(search); |
| 41 | |
| 42 | for (std::size_t pos = 0;; pos += replaceLength) |
| 43 | { |
| 44 | pos = s.find(search, pos); |
| 45 | if (pos == Aws::String::npos) |
| 46 | break; |
| 47 | |
| 48 | s.erase(pos, searchLength); |
| 49 | s.insert(pos, replace); |
| 50 | } |
| 51 | } |
| 52 | |
| 53 | |
| 54 | Aws::String StringUtils::ToLower(const char* source) |
| 55 | { |
| 56 | Aws::String copy; |
| 57 | size_t sourceLength = strlen(source); |
| 58 | copy.resize(sourceLength); |
| 59 | //appease the latest whims of the VC++ 2017 gods |
| 60 | std::transform(source, source + sourceLength, copy.begin(), [](unsigned char c) { return (char)::tolower(c); }); |
| 61 | |
| 62 | return copy; |
| 63 | } |
| 64 | |
| 65 | |
| 66 | Aws::String StringUtils::ToUpper(const char* source) |
| 67 | { |
| 68 | Aws::String copy; |
| 69 | size_t sourceLength = strlen(source); |
| 70 | copy.resize(sourceLength); |
| 71 | //appease the latest whims of the VC++ 2017 gods |
| 72 | std::transform(source, source + sourceLength, copy.begin(), [](unsigned char c) { return (char)::toupper(c); }); |
| 73 | |
| 74 | return copy; |
| 75 | } |
| 76 | |
| 77 | |
| 78 | bool StringUtils::CaselessCompare(const char* value1, const char* value2) |
| 79 | { |
| 80 | Aws::String value1Lower = ToLower(value1); |
| 81 | Aws::String value2Lower = ToLower(value2); |
| 82 | |
| 83 | return value1Lower == value2Lower; |
| 84 | } |
| 85 | |
| 86 | Aws::Vector<Aws::String> StringUtils::Split(const Aws::String& toSplit, char splitOn) |
| 87 | { |
| 88 | return Split(toSplit, splitOn, SIZE_MAX, SplitOptions::NOT_SET); |
| 89 | } |
| 90 | |
| 91 | Aws::Vector<Aws::String> StringUtils::Split(const Aws::String& toSplit, char splitOn, SplitOptions option) |
| 92 | { |
| 93 | return Split(toSplit, splitOn, SIZE_MAX, option); |
| 94 | } |
| 95 | |
| 96 | Aws::Vector<Aws::String> StringUtils::Split(const Aws::String& toSplit, char splitOn, size_t numOfTargetParts) |
| 97 | { |
| 98 | return Split(toSplit, splitOn, numOfTargetParts, SplitOptions::NOT_SET); |
| 99 | } |
| 100 | |
| 101 | Aws::Vector<Aws::String> StringUtils::Split(const Aws::String& toSplit, char splitOn, size_t numOfTargetParts, SplitOptions option) |
| 102 | { |
| 103 | Aws::Vector<Aws::String> returnValues; |
| 104 | Aws::StringStream input(toSplit); |
| 105 | Aws::String item; |
| 106 | |
| 107 | while(returnValues.size() < numOfTargetParts - 1 && std::getline(input, item, splitOn)) |
| 108 | { |
| 109 | if (!item.empty() || option == SplitOptions::INCLUDE_EMPTY_ENTRIES) |
| 110 | { |
| 111 | returnValues.emplace_back(std::move(item)); |
| 112 | } |
| 113 | } |
| 114 | |
| 115 | if (std::getline(input, item, static_cast<char>(EOF))) |
| 116 | { |
| 117 | if (option != SplitOptions::INCLUDE_EMPTY_ENTRIES) |
| 118 | { |
| 119 | // Trim all leading delimiters. |
| 120 | item.erase(item.begin(), std::find_if(item.begin(), item.end(), [splitOn](int ch) { return ch != splitOn; })); |
| 121 | if (!item.empty()) |
| 122 | { |
| 123 | returnValues.emplace_back(std::move(item)); |
| 124 | } |
| 125 | } |
| 126 | else |
| 127 | { |
| 128 | returnValues.emplace_back(std::move(item)); |
| 129 | } |
| 130 | |
| 131 | } |
| 132 | // To handle the case when there are trailing delimiters. |
| 133 | else if (!toSplit.empty() && toSplit.back() == splitOn && option == SplitOptions::INCLUDE_EMPTY_ENTRIES) |
| 134 | { |
| 135 | returnValues.emplace_back(); |
| 136 | } |
| 137 | |
| 138 | return returnValues; |
| 139 | } |
| 140 | |
| 141 | Aws::Vector<Aws::String> StringUtils::SplitOnLine(const Aws::String& toSplit) |
| 142 | { |
| 143 | Aws::StringStream input(toSplit); |
| 144 | Aws::Vector<Aws::String> returnValues; |
| 145 | Aws::String item; |
| 146 | |
| 147 | while (std::getline(input, item)) |
| 148 | { |
| 149 | if (item.size() > 0) |
| 150 | { |
| 151 | returnValues.push_back(item); |
| 152 | } |
| 153 | } |
| 154 | |
| 155 | return returnValues; |
| 156 | } |
| 157 | |
| 158 | |
| 159 | Aws::String StringUtils::URLEncode(const char* unsafe) |
| 160 | { |
| 161 | Aws::StringStream escaped; |
| 162 | escaped.fill('0'); |
| 163 | escaped << std::hex << std::uppercase; |
| 164 | |
| 165 | size_t unsafeLength = strlen(unsafe); |
| 166 | for (auto i = unsafe, n = unsafe + unsafeLength; i != n; ++i) |
| 167 | { |
| 168 | char c = *i; |
| 169 | if (IsAlnum(c) || c == '-' || c == '_' || c == '.' || c == '~') |
| 170 | { |
| 171 | escaped << (char)c; |
| 172 | } |
| 173 | else |
| 174 | { |
| 175 | //this unsigned char cast allows us to handle unicode characters. |
| 176 | escaped << '%' << std::setw(2) << int((unsigned char)c) << std::setw(0); |
| 177 | } |
| 178 | } |
| 179 | |
| 180 | return escaped.str(); |
| 181 | } |
| 182 | |
| 183 | Aws::String StringUtils::UTF8Escape(const char* unicodeString, const char* delimiter) |
| 184 | { |
| 185 | Aws::StringStream escaped; |
| 186 | escaped.fill('0'); |
| 187 | escaped << std::hex << std::uppercase; |
| 188 | |
| 189 | size_t unsafeLength = strlen(unicodeString); |
| 190 | for (auto i = unicodeString, n = unicodeString + unsafeLength; i != n; ++i) |
| 191 | { |
| 192 | int c = *i; |
| 193 | if (c >= ' ' && c < 127 ) |
| 194 | { |
| 195 | escaped << (char)c; |
| 196 | } |
| 197 | else |
| 198 | { |
| 199 | //this unsigned char cast allows us to handle unicode characters. |
| 200 | escaped << delimiter << std::setw(2) << int((unsigned char)c) << std::setw(0); |
| 201 | } |
| 202 | } |
| 203 | |
| 204 | return escaped.str(); |
| 205 | } |
| 206 | |
| 207 | Aws::String StringUtils::URLEncode(double unsafe) |
| 208 | { |
| 209 | char buffer[32]; |
| 210 | #if defined(_MSC_VER) && _MSC_VER < 1900 |
| 211 | _snprintf_s(buffer, sizeof(buffer), _TRUNCATE, "%g" , unsafe); |
| 212 | #else |
| 213 | snprintf(buffer, sizeof(buffer), "%g" , unsafe); |
| 214 | #endif |
| 215 | |
| 216 | return StringUtils::URLEncode(buffer); |
| 217 | } |
| 218 | |
| 219 | |
| 220 | Aws::String StringUtils::URLDecode(const char* safe) |
| 221 | { |
| 222 | Aws::String unescaped; |
| 223 | |
| 224 | for (; *safe; safe++) |
| 225 | { |
| 226 | switch(*safe) |
| 227 | { |
| 228 | case '%': |
| 229 | { |
| 230 | int hex = 0; |
| 231 | auto ch = *++safe; |
| 232 | if (ch >= '0' && ch <= '9') |
| 233 | { |
| 234 | hex = (ch - '0') * 16; |
| 235 | } |
| 236 | else if (ch >= 'A' && ch <= 'F') |
| 237 | { |
| 238 | hex = (ch - 'A' + 10) * 16; |
| 239 | } |
| 240 | else if (ch >= 'a' && ch <= 'f') |
| 241 | { |
| 242 | hex = (ch - 'a' + 10) * 16; |
| 243 | } |
| 244 | else |
| 245 | { |
| 246 | unescaped.push_back('%'); |
| 247 | if (ch == 0) |
| 248 | { |
| 249 | return unescaped; |
| 250 | } |
| 251 | unescaped.push_back(ch); |
| 252 | break; |
| 253 | } |
| 254 | |
| 255 | ch = *++safe; |
| 256 | if (ch >= '0' && ch <= '9') |
| 257 | { |
| 258 | hex += (ch - '0'); |
| 259 | } |
| 260 | else if (ch >= 'A' && ch <= 'F') |
| 261 | { |
| 262 | hex += (ch - 'A' + 10); |
| 263 | } |
| 264 | else if (ch >= 'a' && ch <= 'f') |
| 265 | { |
| 266 | hex += (ch - 'a' + 10); |
| 267 | } |
| 268 | else |
| 269 | { |
| 270 | unescaped.push_back('%'); |
| 271 | unescaped.push_back(*(safe - 1)); |
| 272 | if (ch == 0) |
| 273 | { |
| 274 | return unescaped; |
| 275 | } |
| 276 | unescaped.push_back(ch); |
| 277 | break; |
| 278 | } |
| 279 | |
| 280 | unescaped.push_back(char(hex)); |
| 281 | break; |
| 282 | } |
| 283 | case '+': |
| 284 | unescaped.push_back(' '); |
| 285 | break; |
| 286 | default: |
| 287 | unescaped.push_back(*safe); |
| 288 | break; |
| 289 | } |
| 290 | } |
| 291 | |
| 292 | return unescaped; |
| 293 | } |
| 294 | |
| 295 | static bool IsSpace(int ch) |
| 296 | { |
| 297 | if (ch < -1 || ch > 255) |
| 298 | { |
| 299 | return false; |
| 300 | } |
| 301 | |
| 302 | return ::isspace(ch) != 0; |
| 303 | } |
| 304 | |
| 305 | Aws::String StringUtils::LTrim(const char* source) |
| 306 | { |
| 307 | Aws::String copy(source); |
| 308 | copy.erase(copy.begin(), std::find_if(copy.begin(), copy.end(), [](int ch) { return !IsSpace(ch); })); |
| 309 | return copy; |
| 310 | } |
| 311 | |
| 312 | // trim from end |
| 313 | Aws::String StringUtils::RTrim(const char* source) |
| 314 | { |
| 315 | Aws::String copy(source); |
| 316 | copy.erase(std::find_if(copy.rbegin(), copy.rend(), [](int ch) { return !IsSpace(ch); }).base(), copy.end()); |
| 317 | return copy; |
| 318 | } |
| 319 | |
| 320 | // trim from both ends |
| 321 | Aws::String StringUtils::Trim(const char* source) |
| 322 | { |
| 323 | return LTrim(RTrim(source).c_str()); |
| 324 | } |
| 325 | |
| 326 | long long StringUtils::ConvertToInt64(const char* source) |
| 327 | { |
| 328 | if(!source) |
| 329 | { |
| 330 | return 0; |
| 331 | } |
| 332 | |
| 333 | #ifdef __ANDROID__ |
| 334 | return atoll(source); |
| 335 | #else |
| 336 | return std::atoll(source); |
| 337 | #endif // __ANDROID__ |
| 338 | } |
| 339 | |
| 340 | |
| 341 | long StringUtils::ConvertToInt32(const char* source) |
| 342 | { |
| 343 | if (!source) |
| 344 | { |
| 345 | return 0; |
| 346 | } |
| 347 | |
| 348 | return std::atol(source); |
| 349 | } |
| 350 | |
| 351 | |
| 352 | bool StringUtils::ConvertToBool(const char* source) |
| 353 | { |
| 354 | if(!source) |
| 355 | { |
| 356 | return false; |
| 357 | } |
| 358 | |
| 359 | Aws::String strValue = ToLower(source); |
| 360 | if(strValue == "true" || strValue == "1" ) |
| 361 | { |
| 362 | return true; |
| 363 | } |
| 364 | |
| 365 | return false; |
| 366 | } |
| 367 | |
| 368 | |
| 369 | double StringUtils::ConvertToDouble(const char* source) |
| 370 | { |
| 371 | if(!source) |
| 372 | { |
| 373 | return 0.0; |
| 374 | } |
| 375 | |
| 376 | return std::strtod(source, NULL); |
| 377 | } |
| 378 | |
| 379 | #ifdef _WIN32 |
| 380 | |
| 381 | Aws::WString StringUtils::ToWString(const char* source) |
| 382 | { |
| 383 | const auto len = static_cast<int>(std::strlen(source)); |
| 384 | Aws::WString outString; |
| 385 | outString.resize(len); // there is no way UTF-16 would require _more_ code-points than UTF-8 for the _same_ string |
| 386 | const auto result = MultiByteToWideChar(CP_UTF8 /*CodePage*/, |
| 387 | 0 /*dwFlags*/, |
| 388 | source /*lpMultiByteStr*/, |
| 389 | len /*cbMultiByte*/, |
| 390 | &outString[0] /*lpWideCharStr*/, |
| 391 | static_cast<int>(outString.length())/*cchWideChar*/); |
| 392 | if (!result) |
| 393 | { |
| 394 | return L"" ; |
| 395 | } |
| 396 | outString.resize(result); |
| 397 | return outString; |
| 398 | } |
| 399 | |
| 400 | Aws::String StringUtils::FromWString(const wchar_t* source) |
| 401 | { |
| 402 | const auto len = static_cast<int>(std::wcslen(source)); |
| 403 | Aws::String output; |
| 404 | if (int requiredSizeInBytes = WideCharToMultiByte(CP_UTF8 /*CodePage*/, |
| 405 | 0 /*dwFlags*/, |
| 406 | source /*lpWideCharStr*/, |
| 407 | len /*cchWideChar*/, |
| 408 | nullptr /*lpMultiByteStr*/, |
| 409 | 0 /*cbMultiByte*/, |
| 410 | nullptr /*lpDefaultChar*/, |
| 411 | nullptr /*lpUsedDefaultChar*/)) |
| 412 | { |
| 413 | output.resize(requiredSizeInBytes); |
| 414 | } |
| 415 | const auto result = WideCharToMultiByte(CP_UTF8 /*CodePage*/, |
| 416 | 0 /*dwFlags*/, |
| 417 | source /*lpWideCharStr*/, |
| 418 | len /*cchWideChar*/, |
| 419 | &output[0] /*lpMultiByteStr*/, |
| 420 | static_cast<int>(output.length()) /*cbMultiByte*/, |
| 421 | nullptr /*lpDefaultChar*/, |
| 422 | nullptr /*lpUsedDefaultChar*/); |
| 423 | if (!result) |
| 424 | { |
| 425 | return "" ; |
| 426 | } |
| 427 | output.resize(result); |
| 428 | return output; |
| 429 | } |
| 430 | |
| 431 | #endif |
| 432 | |