fix(Core/Misc): few improvements to ut8 handling (#2455)

This commit is contained in:
Viste
2019-12-02 10:33:44 +03:00
committed by Stoabrogga
parent ad320ec9d9
commit ec808793ae
11 changed files with 200 additions and 94 deletions

View File

@@ -16,6 +16,8 @@
#include "Errors.h" // for ASSERT
#include <ace/TSS_T.h>
#include <array>
#include <cwchar>
#include <string>
typedef ACE_TSS<SFMTRand> SFMTRandTSS;
static SFMTRandTSS sfmtRand;
@@ -251,22 +253,29 @@ bool IsIPAddrInNetwork(ACE_INET_Addr const& net, ACE_INET_Addr const& addr, ACE_
}
/// create PID file
uint32 CreatePIDFile(const std::string& filename)
uint32 CreatePIDFile(std::string const& filename)
{
FILE* pid_file = fopen (filename.c_str(), "w" );
if (pid_file == NULL)
FILE* pid_file = fopen(filename.c_str(), "w");
if (pid_file == nullptr)
return 0;
uint32 pid = GetPID();
fprintf(pid_file, "%u", pid);
fclose(pid_file);
return pid;
}
uint32 GetPID()
{
#ifdef _WIN32
DWORD pid = GetCurrentProcessId();
#else
pid_t pid = getpid();
#endif
fprintf(pid_file, "%u", pid );
fclose(pid_file);
return (uint32)pid;
return uint32(pid);
}
size_t utf8length(std::string& utf8str)
@@ -275,9 +284,9 @@ size_t utf8length(std::string& utf8str)
{
return utf8::distance(utf8str.c_str(), utf8str.c_str()+utf8str.size());
}
catch(std::exception)
catch(std::exception const&)
{
utf8str = "";
utf8str.clear();
return 0;
}
}
@@ -297,9 +306,9 @@ void utf8truncate(std::string& utf8str, size_t len)
char* oend = utf8::utf16to8(wstr.c_str(), wstr.c_str()+wstr.size(), &utf8str[0]);
utf8str.resize(oend-(&utf8str[0])); // remove unused tail
}
catch(std::exception)
catch(std::exception const&)
{
utf8str = "";
utf8str.clear();
}
}
@@ -307,24 +316,30 @@ bool Utf8toWStr(char const* utf8str, size_t csize, wchar_t* wstr, size_t& wsize)
{
try
{
size_t len = utf8::distance(utf8str, utf8str+csize);
if (len > wsize)
{
if (wsize > 0)
wstr[0] = L'\0';
wsize = 0;
return false;
}
wsize = len;
utf8::utf8to16(utf8str, utf8str+csize, wstr);
wstr[len] = L'\0';
acore::CheckedBufferOutputIterator<wchar_t> out(wstr, wsize);
out = utf8::utf8to16(utf8str, utf8str+csize, out);
wsize -= out.remaining(); // remaining unused space
wstr[wsize] = L'\0';
}
catch(std::exception)
catch(std::exception const&)
{
if (wsize > 0)
// Replace the converted string with an error message if there is enough space
// Otherwise just return an empty string
const wchar_t* errorMessage = L"An error occurred converting string from UTF-8 to WStr";
std::size_t errorMessageLength = std::char_traits<wchar_t>::length(errorMessage);
if (wsize >= errorMessageLength)
{
std::wcscpy(wstr, errorMessage);
wsize = std::char_traits<wchar_t>::length(wstr);
}
else if (wsize > 0)
{
wstr[0] = L'\0';
wsize = 0;
wsize = 0;
}
else
wsize = 0;
return false;
}
@@ -361,16 +376,16 @@ bool WStrToUtf8(wchar_t* wstr, size_t size, std::string& utf8str)
}
utf8str = utf8str2;
}
catch(std::exception)
catch(std::exception const&)
{
utf8str = "";
utf8str.clear();
return false;
}
return true;
}
bool WStrToUtf8(std::wstring wstr, std::string& utf8str)
bool WStrToUtf8(std::wstring const& wstr, std::string& utf8str)
{
try
{
@@ -384,9 +399,9 @@ bool WStrToUtf8(std::wstring wstr, std::string& utf8str)
}
utf8str = utf8str2;
}
catch(std::exception)
catch(std::exception const&)
{
utf8str = "";
utf8str.clear();
return false;
}
@@ -395,14 +410,23 @@ bool WStrToUtf8(std::wstring wstr, std::string& utf8str)
typedef wchar_t const* const* wstrlist;
std::wstring GetMainPartOfName(std::wstring wname, uint32 declension)
void wstrToUpper(std::wstring& str)
{
std::transform(str.begin(), str.end(), str.begin(), wcharToUpper);
}
void wstrToLower(std::wstring& str)
{
std::transform(str.begin(), str.end(), str.begin(), wcharToLower);
}
std::wstring GetMainPartOfName(std::wstring const& wname, uint32 declension)
{
// supported only Cyrillic cases
if (wname.empty() || !isCyrillicCharacter(wname[0]) || declension > 5)
return wname;
// Important: end length must be <= MAX_INTERNAL_PLAYER_NAME-MAX_PLAYER_NAME (3 currently)
static std::wstring const a_End = { wchar_t(0x0430), wchar_t(0x0000) };
static std::wstring const o_End = { wchar_t(0x043E), wchar_t(0x0000) };
static std::wstring const ya_End = { wchar_t(0x044F), wchar_t(0x0000) };
@@ -467,7 +491,7 @@ bool consoleToUtf8(const std::string& conStr, std::string& utf8str)
#if AC_PLATFORM == AC_PLATFORM_WINDOWS
std::wstring wstr;
wstr.resize(conStr.size());
OemToCharBuffW(&conStr[0], &wstr[0], conStr.size());
OemToCharBuffW(&conStr[0], &wstr[0], uint32(conStr.size()));
return WStrToUtf8(wstr, utf8str);
#else
@@ -477,7 +501,7 @@ bool consoleToUtf8(const std::string& conStr, std::string& utf8str)
#endif
}
bool Utf8FitTo(const std::string& str, std::wstring search)
bool Utf8FitTo(const std::string& str, std::wstring const& search)
{
std::wstring temp;
@@ -485,7 +509,7 @@ bool Utf8FitTo(const std::string& str, std::wstring search)
return false;
// converting to lower case
wstrToLower( temp );
wstrToLower(temp);
if (temp.find(search) == std::wstring::npos)
return false;
@@ -504,10 +528,10 @@ void utf8printf(FILE* out, const char *str, ...)
void vutf8printf(FILE* out, const char *str, va_list* ap)
{
#if AC_PLATFORM == AC_PLATFORM_WINDOWS
char temp_buf[32*1024];
wchar_t wtemp_buf[32*1024];
char temp_buf[32 * 1024];
wchar_t wtemp_buf[32 * 1024];
size_t temp_len = vsnprintf(temp_buf, 32*1024, str, *ap);
size_t temp_len = vsnprintf(temp_buf, 32 * 1024, str, *ap);
//vsnprintf returns -1 if the buffer is too small
if (temp_len == size_t(-1))
temp_len = 32*1024-1;
@@ -515,13 +539,24 @@ void vutf8printf(FILE* out, const char *str, va_list* ap)
size_t wtemp_len = 32*1024-1;
Utf8toWStr(temp_buf, temp_len, wtemp_buf, wtemp_len);
CharToOemBuffW(&wtemp_buf[0], &temp_buf[0], wtemp_len+1);
CharToOemBuffW(&wtemp_buf[0], &temp_buf[0], uint32(wtemp_len + 1));
fprintf(out, "%s", temp_buf);
#else
vfprintf(out, str, *ap);
#endif
}
bool Utf8ToUpperOnlyLatin(std::string& utf8String)
{
std::wstring wstr;
if (!Utf8toWStr(utf8String, wstr))
return false;
std::transform(wstr.begin(), wstr.end(), wstr.begin(), wcharToUpperOnlyLatin);
return WStrToUtf8(wstr, utf8String);
}
std::string ByteArrayToHexStr(uint8 const* bytes, uint32 arrayLen, bool reverse /* = false */)
{
int32 init = 0;
@@ -545,3 +580,41 @@ std::string ByteArrayToHexStr(uint8 const* bytes, uint32 arrayLen, bool reverse
return ss.str();
}
void HexStrToByteArray(std::string const& str, uint8* out, bool reverse /*= false*/)
{
// string must have even number of characters
if (str.length() & 1)
return;
int32 init = 0;
int32 end = int32(str.length());
int8 op = 1;
if (reverse)
{
init = int32(str.length() - 2);
end = -2;
op = -1;
}
uint32 j = 0;
for (int32 i = init; i != end; i += 2 * op)
{
char buffer[3] = { str[i], str[i + 1], '\0' };
out[j++] = uint8(strtoul(buffer, nullptr, 16));
}
}
bool StringToBool(std::string const& str)
{
std::string lowerStr = str;
std::transform(str.begin(), str.end(), lowerStr.begin(), ::tolower);
return lowerStr == "1" || lowerStr == "true" || lowerStr == "yes";
}
bool StringContainsStringI(std::string const& haystack, std::string const& needle)
{
return haystack.end() !=
std::search(haystack.begin(), haystack.end(), needle.begin(), needle.end(), [](char c1, char c2) { return std::toupper(c1) == std::toupper(c2); });
}