#include "GeneralUtils.h" // C++ #include #include #include #include #include template inline size_t MinSize(size_t size, const std::basic_string_view& string) { if (size == size_t(-1) || size > string.size()) { return string.size(); } else { return size; } } inline bool IsLeadSurrogate(char16_t c) { return (0xD800 <= c) && (c <= 0xDBFF); } inline bool IsTrailSurrogate(char16_t c) { return (0xDC00 <= c) && (c <= 0xDFFF); } inline void PushUTF8CodePoint(std::string& ret, char32_t cp) { if (cp <= 0x007F) { ret.push_back(static_cast(cp)); } else if (cp <= 0x07FF) { ret.push_back(0xC0 | (cp >> 6)); ret.push_back(0x80 | (cp & 0x3F)); } else if (cp <= 0xFFFF) { ret.push_back(0xE0 | (cp >> 12)); ret.push_back(0x80 | ((cp >> 6) & 0x3F)); ret.push_back(0x80 | (cp & 0x3F)); } else if (cp <= 0x10FFFF) { ret.push_back(0xF0 | (cp >> 18)); ret.push_back(0x80 | ((cp >> 12) & 0x3F)); ret.push_back(0x80 | ((cp >> 6) & 0x3F)); ret.push_back(0x80 | (cp & 0x3F)); } else { assert(false); } } constexpr const char16_t REPLACEMENT_CHARACTER = 0xFFFD; bool _IsSuffixChar(uint8_t c) { return (c & 0xC0) == 0x80; } bool GeneralUtils::_NextUTF8Char(std::string_view& slice, uint32_t& out) { size_t rem = slice.length(); if (slice.empty()) return false; const uint8_t* bytes = (const uint8_t*)&slice.front(); if (rem > 0) { uint8_t first = bytes[0]; if (first < 0x80) { // 1 byte character out = static_cast(first & 0x7F); slice.remove_prefix(1); return true; } else if (first < 0xC0) { // middle byte, not valid at start, fall through } else if (first < 0xE0) { // two byte character if (rem > 1) { uint8_t second = bytes[1]; if (_IsSuffixChar(second)) { out = (static_cast(first & 0x1F) << 6) + static_cast(second & 0x3F); slice.remove_prefix(2); return true; } } } else if (first < 0xF0) { // three byte character if (rem > 2) { uint8_t second = bytes[1]; uint8_t third = bytes[2]; if (_IsSuffixChar(second) && _IsSuffixChar(third)) { out = (static_cast(first & 0x0F) << 12) + (static_cast(second & 0x3F) << 6) + static_cast(third & 0x3F); slice.remove_prefix(3); return true; } } } else if (first < 0xF8) { // four byte character if (rem > 3) { uint8_t second = bytes[1]; uint8_t third = bytes[2]; uint8_t fourth = bytes[3]; if (_IsSuffixChar(second) && _IsSuffixChar(third) && _IsSuffixChar(fourth)) { out = (static_cast(first & 0x07) << 18) + (static_cast(second & 0x3F) << 12) + (static_cast(third & 0x3F) << 6) + static_cast(fourth & 0x3F); slice.remove_prefix(4); return true; } } } out = static_cast(REPLACEMENT_CHARACTER); slice.remove_prefix(1); return true; } return false; } /// See bool PushUTF16CodePoint(std::u16string& output, uint32_t U, size_t size) { if (output.length() >= size) return false; if (U < 0x10000) { // If U < 0x10000, encode U as a 16-bit unsigned integer and terminate. output.push_back(static_cast(U)); return true; } else if (U > 0x10FFFF) { output.push_back(REPLACEMENT_CHARACTER); return true; } else if (output.length() + 1 < size) { // Let U' = U - 0x10000. Because U is less than or equal to 0x10FFFF, // U' must be less than or equal to 0xFFFFF. That is, U' can be // represented in 20 bits. uint32_t Ut = U - 0x10000; // Initialize two 16-bit unsigned integers, W1 and W2, to 0xD800 and // 0xDC00, respectively. These integers each have 10 bits free to // encode the character value, for a total of 20 bits. uint16_t W1 = 0xD800; uint16_t W2 = 0xDC00; // Assign the 10 high-order bits of the 20-bit U' to the 10 low-order // bits of W1 and the 10 low-order bits of U' to the 10 low-order // bits of W2. W1 += static_cast((Ut & 0x3FC00) >> 10); W2 += static_cast((Ut & 0x3FF) >> 0); // Terminate. output.push_back(W1); // high surrogate output.push_back(W2); // low surrogate return true; } else return false; } std::u16string GeneralUtils::UTF8ToUTF16(const std::string_view& string, size_t size) { size_t newSize = MinSize(size, string); std::u16string output; output.reserve(newSize); std::string_view iterator = string; uint32_t c; while (_NextUTF8Char(iterator, c) && PushUTF16CodePoint(output, c, size)) {} return output; } //! Converts an std::string (ASCII) to UCS-2 / UTF-16 std::u16string GeneralUtils::ASCIIToUTF16(const std::string_view& string, size_t size) { size_t newSize = MinSize(size, string); std::u16string ret; ret.reserve(newSize); for (size_t i = 0; i < newSize; i++) { char c = string[i]; // Note: both 7-bit ascii characters and REPLACEMENT_CHARACTER fit in one char16_t ret.push_back((c > 0 && c <= 127) ? static_cast(c) : REPLACEMENT_CHARACTER); } return ret; } //! Converts a (potentially-ill-formed) UTF-16 string to UTF-8 //! See: std::string GeneralUtils::UTF16ToWTF8(const std::u16string_view& string, size_t size) { size_t newSize = MinSize(size, string); std::string ret; ret.reserve(newSize); for (size_t i = 0; i < newSize; i++) { char16_t u = string[i]; if (IsLeadSurrogate(u) && (i + 1) < newSize) { char16_t next = string[i + 1]; if (IsTrailSurrogate(next)) { i += 1; char32_t cp = 0x10000 + ((static_cast(u) - 0xD800) << 10) + (static_cast(next) - 0xDC00); PushUTF8CodePoint(ret, cp); } else { PushUTF8CodePoint(ret, u); } } else { PushUTF8CodePoint(ret, u); } } return ret; } bool GeneralUtils::CaseInsensitiveStringCompare(const std::string& a, const std::string& b) { return std::equal(a.begin(), a.end(), b.begin(), b.end(), [](char a, char b) { return tolower(a) == tolower(b); }); } // MARK: Bits //! Sets a specific bit in a signed 64-bit integer int64_t GeneralUtils::SetBit(int64_t value, uint32_t index) { return value |= 1ULL << index; } //! Clears a specific bit in a signed 64-bit integer int64_t GeneralUtils::ClearBit(int64_t value, uint32_t index) { return value &= ~(1ULL << index); } //! Checks a specific bit in a signed 64-bit integer bool GeneralUtils::CheckBit(int64_t value, uint32_t index) { return value & (1ULL << index); } bool GeneralUtils::ReplaceInString(std::string& str, const std::string& from, const std::string& to) { size_t start_pos = str.find(from); if (start_pos == std::string::npos) return false; str.replace(start_pos, from.length(), to); return true; } std::vector GeneralUtils::SplitString(std::wstring& str, wchar_t delimiter) { std::vector vector = std::vector(); std::wstring current; for (const auto& c : str) { if (c == delimiter) { vector.push_back(current); current = L""; } else { current += c; } } vector.push_back(current); return vector; } std::vector GeneralUtils::SplitString(std::u16string& str, char16_t delimiter) { std::vector vector = std::vector(); std::u16string current; for (const auto& c : str) { if (c == delimiter) { vector.push_back(current); current = u""; } else { current += c; } } vector.push_back(current); return vector; } std::vector GeneralUtils::SplitString(const std::string& str, char delimiter) { std::vector vector = std::vector(); std::string current = ""; for (size_t i = 0; i < str.length(); i++) { char c = str[i]; if (c == delimiter) { vector.push_back(current); current = ""; } else { current += c; } } vector.push_back(current); return vector; } std::u16string GeneralUtils::ReadWString(RakNet::BitStream* inStream) { uint32_t length; inStream->Read(length); std::u16string string; for (auto i = 0; i < length; i++) { uint16_t c; inStream->Read(c); string.push_back(c); } return string; } std::vector GeneralUtils::GetSqlFileNamesFromFolder(const std::string& folder) { // Because we dont know how large the initial number before the first _ is we need to make it a map like so. std::map filenames{}; for (auto& t : std::filesystem::directory_iterator(folder)) { auto filename = t.path().filename().string(); auto index = std::stoi(GeneralUtils::SplitString(filename, '_').at(0)); filenames.insert(std::make_pair(index, filename)); } // Now sort the map by the oldest migration. std::vector sortedFiles{}; auto fileIterator = filenames.begin(); std::map::iterator oldest = filenames.begin(); while (!filenames.empty()) { if (fileIterator == filenames.end()) { sortedFiles.push_back(oldest->second); filenames.erase(oldest); fileIterator = filenames.begin(); oldest = filenames.begin(); continue; } if (oldest->first > fileIterator->first) oldest = fileIterator; fileIterator++; } return sortedFiles; } bool GeneralUtils::TryParse(const std::string& x, const std::string& y, const std::string& z, NiPoint3& dst) { return TryParse(x.c_str(), dst.x) && TryParse(y.c_str(), dst.y) && TryParse(z.c_str(), dst.z); }