Last active
September 22, 2016 00:22
-
-
Save mortehu/48eceafeb6cff05002759e9434f887c4 to your computer and use it in GitHub Desktop.
UTF-8 case folding in C++14
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <codecvt> | |
#include <iomanip> | |
#include <iostream> | |
#include <locale> | |
#include <string> | |
#include "zip.h" // See https://gist.github.com/mortehu/373069390c75b02f98b655e3f7dbef9a | |
const auto low = u8"abcæøåαβγ"; | |
const auto upp = u8"ABCÆØÅΑΒΓ"; | |
int main(int argc, char** argv) { | |
const std::locale locale("en_US.UTF-8"); | |
std::wstring_convert<std::codecvt_utf8<wchar_t>, wchar_t> ucs2conv; | |
auto low_ucs = ucs2conv.from_bytes(low); | |
auto upp_ucs = ucs2conv.from_bytes(upp); | |
for (auto&& g : zip(low_ucs, upp_ucs)) | |
{ | |
std::cerr << std::setw(3) << std::tolower(std::get<0>(g), locale) << ' ' | |
<< std::tolower(std::get<1>(g), locale) << '\n'; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment