UTF8_API size_t utf8envlocale()
{
/*
Sources for locales and code pages
Windows
https://msdn.microsoft.com/en-US/goglobal/bb896001.aspx
POSIX
https://www-01.ibm.com/support/knowledgecenter/ssw_aix_61/com.ibm.aix.nlsgdrf/support_languages_locales.htm
*/
#if WIN32 || _WINDOWS
#define UTF8_LOCALE_CHECK(_name, _ansiCodepage, _oemCodepage) \
(codepage == _ansiCodepage || codepage == _oemCodepage)
// Microsoft changed the name of the codepage member in VS2015.
#if _MSC_VER >= 1900
#define UTF8_CODEPAGE_GET(_locale) ((__crt_locale_data_public*)(_locale)->locinfo)->_locale_lc_codepage
#else
#define UTF8_CODEPAGE_GET(_locale) (_locale)->locinfo->lc_codepage
#endif
unsigned int codepage;
_locale_t locale = _get_current_locale();
if (locale == 0)
{
return UTF8_LOCALE_DEFAULT;
}
codepage = UTF8_CODEPAGE_GET(locale);
#else
#define UTF8_LOCALE_CHECK(_name, _ansiCodepage, _oemCodepage) \
!strncasecmp(locale, _name, 5)
const char* locale = setlocale(LC_ALL, 0);
if (locale == 0)
{
return UTF8_LOCALE_DEFAULT;
}
#endif
if (UTF8_LOCALE_CHECK("lt_lt", 1257, 775))
{
return UTF8_LOCALE_LITHUANIAN;
}
else if (
UTF8_LOCALE_CHECK("tr_tr", 1254, 857) ||
UTF8_LOCALE_CHECK("az_az", 1254, 857))
{
return UTF8_LOCALE_TURKISH_AND_AZERI_LATIN;
}
return UTF8_LOCALE_DEFAULT;
}
void check_locale()
{
_locale_t currloc = _get_current_locale();
#ifdef _DEBUG
puts("Checking decimal point...\n");
#endif
lconv * sysloc = localeconv();
if(currloc->locinfo->lconv->decimal_point == (char*)(',')) {
//if(sysloc->decimal_point == (char*)(',')) {
#ifdef _DEBUG
puts(">>>>>>>>>>>>>>>>>>>Warrning: Decimal point changing to '.'!\n");
#endif
setlocale(LC_NUMERIC, "C");
}
}
//----------------------------------------------------------------
CPUTResult CPUTConfigFile::LoadFile(const cString &szFilename)
{
// Load the file
cString szCurrLine;
CPUTConfigBlock *pCurrBlock = NULL;
FILE *pFile = NULL;
int nCurrBlock = 0;
CPUTResult result = CPUTOSServices::GetOSServices()->OpenFile(szFilename, &pFile);
if(CPUTFAILED(result))
{
return result;
}
_locale_t locale = _get_current_locale();
/* Determine file size */
fseek(pFile, 0, SEEK_END);
int nBytes = ftell(pFile); // for text files, this is an overestimate
fseek(pFile, 0, SEEK_SET);
/* Read the whole thing */
char *pFileContents = new char[nBytes + 1];
nBytes = (int)fread(pFileContents, 1, nBytes, pFile);
fclose(pFile);
pFileContents[nBytes] = 0; // add 0-terminator
/* Count the number of blocks */
const char *pCur = pFileContents;
const char *pStart, *pEnd;
while(ReadLine(&pStart, &pEnd, &pCur))
{
const char *pOpen = FindFirst(pStart, pEnd, '[');
const char *pClose = FindLast(pOpen + 1, pEnd, ']');
if (pOpen < pClose)
{
// This line is a valid block header
mnBlockCount++;
}
}
// For files that don't have any blocks, just add the entire file to one block
if(mnBlockCount == 0)
{
mnBlockCount = 1;
}
pCur = pFileContents;
mpBlocks = new CPUTConfigBlock[mnBlockCount];
pCurrBlock = mpBlocks;
/* Find the first block first */
while(ReadLine(&pStart, &pEnd, &pCur))
{
const char *pOpen = FindFirst(pStart, pEnd, '[');
const char *pClose = FindLast(pOpen + 1, pEnd, ']');
if (pOpen < pClose)
{
// This line is a valid block header
pCurrBlock = mpBlocks + nCurrBlock++;
AssignStr(pCurrBlock->mszName, pOpen + 1, pClose, locale);
std::transform(pCurrBlock->mszName.begin(), pCurrBlock->mszName.end(), pCurrBlock->mszName.begin(), ::tolower);
}
else if (pStart < pEnd)
{
// It's a value
if (pCurrBlock == NULL)
{
continue;
}
const char *pEquals = FindFirst(pStart, pEnd, '=');
if (pEquals == pEnd)
{
// No value, just a key, save it anyway
// Optimistically, we assume it's new
cString &name = pCurrBlock->mpValues[pCurrBlock->mnValueCount].szName;
AssignStr(name, pStart, pEnd, locale);
bool dup = false;
for(int ii=0;ii<pCurrBlock->mnValueCount;++ii)
{
if(!pCurrBlock->mpValues[ii].szName.compare(name))
{
dup = true;
break;
}
}
if(!dup)
{
pCurrBlock->mnValueCount++;
}
}
else
{
const char *pNameStart = pStart;
const char *pNameEnd = pEquals;
const char *pValStart = pEquals + 1;
const char *pValEnd = pEnd;
RemoveWhitespace(pNameStart, pNameEnd);
RemoveWhitespace(pValStart, pValEnd);
// Optimistically assume the name is new
cString &name = pCurrBlock->mpValues[pCurrBlock->mnValueCount].szName;
AssignStr(name, pNameStart, pNameEnd, locale);
std::transform(name.begin(), name.end(), name.begin(), ::tolower);
bool dup = false;
for(int ii=0;ii<pCurrBlock->mnValueCount;++ii)
{
if(!pCurrBlock->mpValues[ii].szName.compare(name))
{
dup = true;
break;
}
}
if(!dup)
{
AssignStr(pCurrBlock->mpValues[pCurrBlock->mnValueCount].szValue, pValStart, pValEnd, locale);
pCurrBlock->mnValueCount++;
}
}
}
}
delete[] pFileContents;
return CPUT_SUCCESS;
}
char *nl_langinfo(nl_item item)
{
char *l, *p;
_locale_t lt;
//if (item != DEF_CODESET)
// return NULL;
//p = local_charset();
p = setlocale(LC_ALL, "");
//p = setlocale(LC_ALL, NULL);
if (p) {
printf("setlocal: %s\n", p);
}
lt = _get_current_locale();
if (lt) {
int loci = (int)lt->locinfo;
//const char *ccp = get_name_from_clid(loci);
//const char *ccp2 = get_name_from_clid(item);
//SPRTF("Got locinfo %d (0x%08X) %s\n", loci, loci, (ccp2 ? ccp2 : "no value"));
_free_locale(lt);
}
if (((l = getenv("LC_ALL")) && *l) ||
((l = getenv("LC_CTYPE")) && *l) ||
((l = getenv("LANG")) && *l))
{
/* check standardized locales */
if (!strcmp(l, "C") || !strcmp(l, "POSIX"))
return C_CODESET;
/* check for encoding name fragment */
if (strstr(l, "UTF") || strstr(l, "utf"))
return "UTF-8";
if ((p = strstr(l, "8859-")))
{
memcpy(buf, "ISO-8859-\0\0", 12);
p += 5;
if (digit(*p))
{
buf[9] = *p++;
if (digit(*p))
buf[10] = *p++;
return buf;
}
}
if (strstr(l, "KOI8-R"))
return "KOI8-R";
if (strstr(l, "KOI8-U"))
return "KOI8-U";
if (strstr(l, "620"))
return "TIS-620";
if (strstr(l, "2312"))
return "GB2312";
if (strstr(l, "HKSCS"))
return "Big5HKSCS"; /* no MIME charset */
if (strstr(l, "Big5") || strstr(l, "BIG5"))
return "Big5";
if (strstr(l, "GBK"))
return "GBK"; /* no MIME charset */
if (strstr(l, "18030"))
return "GB18030"; /* no MIME charset */
if (strstr(l, "Shift_JIS") || strstr(l, "SJIS"))
return "Shift_JIS";
/* check for conclusive modifier */
if (strstr(l, "euro"))
return "ISO-8859-15";
/* check for language (and perhaps country) codes */
if (strstr(l, "zh_TW"))
return "Big5";
if (strstr(l, "zh_HK"))
return "Big5HKSCS"; /* no MIME charset */
if (strstr(l, "zh"))
return "GB2312";
if (strstr(l, "ja"))
return "EUC-JP";
if (strstr(l, "ko"))
return "EUC-KR";
if (strstr(l, "ru"))
return "KOI8-R";
if (strstr(l, "uk"))
return "KOI8-U";
if (strstr(l, "pl") || strstr(l, "hr") ||
strstr(l, "hu") || strstr(l, "cs") ||
strstr(l, "sk") || strstr(l, "sl"))
return "ISO-8859-2";
if (strstr(l, "eo") || strstr(l, "mt"))
return "ISO-8859-3";
if (strstr(l, "el"))
return "ISO-8859-7";
if (strstr(l, "he"))
return "ISO-8859-8";
if (strstr(l, "tr"))
return "ISO-8859-9";
if (strstr(l, "th"))
return "TIS-620"; /* or ISO-8859-11 */
if (strstr(l, "lt"))
return "ISO-8859-13";
if (strstr(l, "cy"))
return "ISO-8859-14";
if (strstr(l, "ro"))
return "ISO-8859-2"; /* or ISO-8859-16 */
if (strstr(l, "am") || strstr(l, "vi"))
return "UTF-8";
/* Send me further rules if you like, but don't forget that we are
* *only* interested in locale naming conventions on platforms
* that do not already provide an nl_langinfo(CODESET) implementation. */
//return "ISO-8859-1"; /* should perhaps be "UTF-8" instead */
//return "UTF-8"; /* have set default return as "UTF-8"!!! */
}
return C_CODESET;
}
