Plexi09/eden-miror
1
0
Fork 0
mirror of https://git.eden-emu.dev/eden-emu/eden synced 2026-04-11 18:18:58 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

bit of cmake fuckery

Browse source
This commit is contained in:
lizzie 2026-03-24 22:42:33 +00:00
parent 46fdcb3152
commit 5153e61517
9 changed files with 182 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

113
src/common/string_util.cpp
View file

@ -116,18 +116,119 @@ std::string ReplaceAll(std::string result, const std::string& src, const std::st
}
std::string UTF16ToUTF8(std::u16string_view input) {
std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> convert;
return convert.to_bytes(input.data(), input.data() + input.size());
std::string result;
result.reserve(input.size());
for (size_t i = 0; i < input.size(); ++i) {
uint32_t codepoint = input[i];
// Handle surrogate pairs
if (codepoint >= 0xD800 && codepoint <= 0xDBFF) {
if (i + 1 < input.size()) {
uint32_t low = input[i + 1];
if (low >= 0xDC00 && low <= 0xDFFF) {
codepoint = ((codepoint - 0xD800) << 10) + (low - 0xDC00) + 0x10000;
++i;
}
}
}
if (codepoint <= 0x7F) {
result.push_back(static_cast<char>(codepoint));
} else if (codepoint <= 0x7FF) {
result.push_back(static_cast<char>(0xC0 | (codepoint >> 6)));
result.push_back(static_cast<char>(0x80 | (codepoint & 0x3F)));
} else if (codepoint <= 0xFFFF) {
result.push_back(static_cast<char>(0xE0 | (codepoint >> 12)));
result.push_back(static_cast<char>(0x80 | ((codepoint >> 6) & 0x3F)));
result.push_back(static_cast<char>(0x80 | (codepoint & 0x3F)));
} else {
result.push_back(static_cast<char>(0xF0 | (codepoint >> 18)));
result.push_back(static_cast<char>(0x80 | ((codepoint >> 12) & 0x3F)));
result.push_back(static_cast<char>(0x80 | ((codepoint >> 6) & 0x3F)));
result.push_back(static_cast<char>(0x80 | (codepoint & 0x3F)));
}
}
return result;
}
std::u16string UTF8ToUTF16(std::string_view input) {
std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> convert;
return convert.from_bytes(input.data(), input.data() + input.size());
std::u16string result;
size_t i = 0;
while (i < input.size()) {
uint32_t codepoint = 0;
unsigned char c = input[i];
size_t extra = 0;
if ((c & 0x80) == 0) {
codepoint = c;
extra = 0;
} else if ((c & 0xE0) == 0xC0) {
codepoint = c & 0x1F;
extra = 1;
} else if ((c & 0xF0) == 0xE0) {
codepoint = c & 0x0F;
extra = 2;
} else if ((c & 0xF8) == 0xF0) {
codepoint = c & 0x07;
extra = 3;
} else {
// Invalid UTF-8
++i;
continue;
}
if (i + extra >= input.size()) break;
for (size_t j = 1; j <= extra; ++j) {
if ((input[i + j] & 0xC0) != 0x80) {
codepoint = 0xFFFD;
break;
}
codepoint = (codepoint << 6) | (input[i + j] & 0x3F);
}
if (codepoint <= 0xFFFF) {
result.push_back(static_cast<char16_t>(codepoint));
} else {
codepoint -= 0x10000;
result.push_back(static_cast<char16_t>(0xD800 + (codepoint >> 10)));
result.push_back(static_cast<char16_t>(0xDC00 + (codepoint & 0x3FF)));
}
i += extra + 1;
}
return result;
}
std::u32string UTF8ToUTF32(std::string_view input) {
std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> convert;
return convert.from_bytes(input.data(), input.data() + input.size());
std::u32string result;
size_t i = 0;
while (i < input.size()) {
uint32_t codepoint = 0;
unsigned char c = input[i];
size_t extra = 0;
if ((c & 0x80) == 0) {
codepoint = c;
extra = 0;
} else if ((c & 0xE0) == 0xC0) {
codepoint = c & 0x1F;
extra = 1;
} else if ((c & 0xF0) == 0xE0) {
codepoint = c & 0x0F;
extra = 2;
} else if ((c & 0xF8) == 0xF0) {
codepoint = c & 0x07;
extra = 3;
} else {
// Invalid UTF-8
++i;
continue;
}
if (i + extra >= input.size()) break;
for (size_t j = 1; j <= extra; ++j) {
if ((input[i + j] & 0xC0) != 0x80) {
codepoint = 0xFFFD;
break;
}
codepoint = (codepoint << 6) | (input[i + j] & 0x3F);
}
result.push_back(codepoint);
i += extra + 1;
}
return result;
}
#ifdef _WIN32