Skip to content

Use iconv() in utf8.cpp module on non-Windows platforms. #174

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
daliborfox wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Use iconv() in utf8.cpp module on non-Windows platforms. #174

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 52 additions & 0 deletions code/utf8.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,12 @@
#ifndef NOMINMAX
#define NOMINMAX
#endif

#ifdef _WIN32
#include <windows.h>
#else
#include <iconv.h>
#endif


namespace {
Expand Down Expand Up @@ -208,12 +213,59 @@ int Best_Fit_Index(unsigned page, short * cache, char32_t code)

short & slot = cache[code];
if (slot == 0) {
#ifdef _WIN32
wchar_t wide = (wchar_t)code;
char narrow = 0;
BOOL defaulted = FALSE;
int written = WideCharToMultiByte(page, 0, &wide, 1, &narrow, 1, NULL, &defaulted);
unsigned char byte = (unsigned char)narrow;
slot = (written == 1 && !defaulted && byte >= 0x20 && byte != 0x7F) ? (short)byte : (short)-1;
#else
static iconv_t conv_oem437 = (iconv_t)-1;
static iconv_t conv_win1252 = (iconv_t)-1;

iconv_t conv = (iconv_t)-1;
switch (page) {
case 437:
if (conv_oem437 == (iconv_t)-1) {
conv_oem437 = iconv_open("437//TRANSLIT", "UTF32");
}
if (conv_oem437 == (iconv_t)-1) {
conv_oem437 = iconv_open("437", "UTF32");
}
conv = conv_oem437;
break;

case 1252:
if (conv_win1252 == (iconv_t)-1) {
conv_win1252 = iconv_open("WINDOWS-1252//TRANSLIT", "UTF32");
}
if (conv_win1252 == (iconv_t)-1) {
conv_win1252 = iconv_open("WINDOWS-1252", "UTF32");
}
conv = conv_win1252;
break;
}
char narrow = 0;
size_t ret = 0;

char *wide_ptr = reinterpret_cast<char *>(&code);
char *narrow_ptr = reinterpret_cast<char *>(&narrow);
size_t bytes_left_wide = sizeof(code);
size_t bytes_left_narrow = sizeof(narrow);

if (conv != (iconv_t)-1) {
ret = iconv(conv, &wide_ptr, &bytes_left_wide, &narrow_ptr, &bytes_left_narrow);

if ((narrow == '?' && code != '?') || /* BSD/Solaris fallback detection */
(narrow == '*' && code != '*')) { /* MUSL fallback detection */

ret = (size_t)-1;
}
}
unsigned char byte = (unsigned char)narrow;
slot = (ret != (size_t)-1 && bytes_left_narrow == 0 && bytes_left_wide == 0 && byte >= 0x20 && byte != 0x7F) ? (short)byte : (short)-1;
#endif
}
return(slot);
}
Expand Down
Loading