diff --git a/MtVerify.h b/MtVerify.h index 899e7d2eefe05274cba3dd9229da9ca01cd22526..58921aa850ab0bc9a8aa0621ea45f0bdb63d09b5 100644 --- a/MtVerify.h +++ b/MtVerify.h @@ -1,263 +1,272 @@ -#pragma comment(lib, "USER32" ) -#include <crtdbg.h> -#include <tchar.h> -#pragma comment(lib, "version.lib") -#define MTVERIFY(a) (a) -#if 0 -#define SHOWERROR(a) PrintError(a,__FILE__,__LINE__,GetLastError()) - -#ifdef DEBUG -#define MTASSERT(a) _ASSERTE(a) -#define MTVERIFY(a) if (!(a)) PrintError(#a,__FILE__,__LINE__,GetLastError()) -#else /*DEBUG*/ -#define MTASSERT(a) -#define MTVERIFY(a) (a) -#endif /*DEBUG*/ - -__inline void PrintError(LPCTSTR linedesc, LPCTSTR filename, int lineno, DWORD errnum) -{ - LPTSTR lpBuffer; - TCHAR errbuf[256]; - -#ifdef _WINDOWS_ - TCHAR modulename[MAX_PATH]; -#else //_WINDOWS_ - DWORD numread; -#endif //_WINDOWS_ - - FormatMessage( - FORMAT_MESSAGE_ALLOCATE_BUFFER | FORMAT_MESSAGE_FROM_SYSTEM, - NULL, - errnum, - LANG_NEUTRAL, - (LPTSTR)&lpBuffer, - 0, - NULL - ); - _stprintf(errbuf, _T("\nThe following call failed at line %d in %s:\n\n %s\n\nReason: %s\n"), - lineno, filename, linedesc, lpBuffer); - -#ifndef _WINDOWS_ - WriteFile(GetStdHandle(STD_ERROR_HANDLE), errbuf, lstrlen(errbuf), &numread, FALSE ); - Sleep(3000); -#else //_WINDOWS_ - GetModuleFileName(NULL, modulename, MAX_PATH); - MessageBox(NULL, errbuf, modulename, MB_ICONWARNING|MB_OK|MB_TASKMODAL|MB_SETFOREGROUND); - OutputDebugString(errbuf); -#endif //_WINDOWS_ - - LocalFree(lpBuffer); - //exit(EXIT_FAILURE); -} -#endif - - - -__inline void WaitTillThreadActive(HANDLE &handle) -{ - if(handle != INVALID_HANDLE_VALUE) - { - BOOL rc = FALSE; - DWORD ec = 0; - for(;;) - { - rc = GetExitCodeThread(handle, &ec); - if(rc && (ec == STILL_ACTIVE)) - break; - Sleep(500); - } - } -} -// obsolete -/* -__inline void WaitTillThreadExited(HANDLE &handle, DWORD dwMilliseconds = 3000) -{ - if(handle != INVALID_HANDLE_VALUE) - { - BOOL rc = FALSE; - DWORD ec = 0; - DWORD dwStart = GetTickCount(); - for(;;) - { - if(GetTickCount() - dwStart >= dwMilliseconds) - { - ::TerminateThread(handle, 0xffffffff); - CloseHandle(handle); - handle = INVALID_HANDLE_VALUE; - break; - } - if(handle == INVALID_HANDLE_VALUE) - break; - rc = GetExitCodeThread(handle, &ec); - if(rc && (ec != STILL_ACTIVE)) - { - CloseHandle(handle); - handle = INVALID_HANDLE_VALUE; - break; - } - Sleep(500); - } - } -} -*/ - -__forceinline void WaitTillThreadExited(HANDLE &handle, DWORD dwMilliseconds = 5000) -{ - if(handle == INVALID_HANDLE_VALUE) - return; - DWORD ret = ::WaitForSingleObject(handle, dwMilliseconds); - if(ret != WAIT_OBJECT_0) - { //::TerminateThread(handle, 0xffffffff); - } - CloseHandle(handle); - handle = INVALID_HANDLE_VALUE; -} - -__inline LPTSTR GetModuleFilePath() -{ - static TCHAR szPath[MAX_PATH] = {'\0'}; - if(lstrlen(szPath) != 0) - return szPath; - - TCHAR szExe[MAX_PATH]; - GetModuleFileName(GetModuleHandle(NULL), szExe, MAX_PATH); - int len = lstrlen(szExe); - for(int i = len; i > 0; i--) - { - if(szExe[i] == '\\') - { - szExe[i] = '\0'; - lstrcpy(szPath, szExe); - break; - } - } - return szPath; -} - -/////////*********************自定义宏********************//////////////////////// -//安全删除普通堆内存 -#define SAFEDELETEP(p) {if(p){delete (p); (p)=NULL;}} - -#define SAFEDELETEARR(pArr) {if((pArr)){delete[] (pArr); (pArr)=NULL;}} - -//安全删除对话框类堆内存 -#define SAFEDELETEDLG(pDlg) {\ - if ((pDlg)) {\ - if (::IsWindow(pDlg->m_hWnd)) {\ - (pDlg)->DestroyWindow();\ - }\ - delete (pDlg);\ - (pDlg)=NULL;\ - }\ -} - -//关闭核心对象句柄 -#define CLOSEHANDLE(h){\ - if (h != INVALID_HANDLE_VALUE && h != NULL) {\ - ::CloseHandle(h);\ - h = INVALID_HANDLE_VALUE;\ - }\ -} - -#define CLOSESOCKET(s){\ - if(s != INVALID_SOCKET){\ - ::closesocket(s); \ - s = INVALID_SOCKET;\ - }\ -} - -#ifdef _DEBUG -#define VERIFYPTR(p, cb) {MTVERIFY(!IsBadWritePtr(p, cb));} -#else -#define VERIFYPTR(p, cb) -#endif - - -/**************UNICODE-ANSI mutually transform**************************/ -// need be manuly delete -__forceinline LPSTR Utf16ToAnsi(const wchar_t * const wSrc) -{ - char* pElementText; - int iTextLen; - iTextLen = WideCharToMultiByte( CP_ACP, 0, wSrc, -1, NULL,0, NULL, NULL ); - pElementText = new char[iTextLen + 1]; - memset( ( void* )pElementText, 0, sizeof( char ) * ( iTextLen + 1 ) ); - ::WideCharToMultiByte( CP_ACP,0,wSrc,-1,pElementText,iTextLen,NULL,NULL); - - return pElementText; -} - -__forceinline BOOL Utf16ToAnsiUseCharArray(const wchar_t * const wSrc, - char *ansiArr, WORD ansiArrLen) -{ - int iTextLen = WideCharToMultiByte( CP_ACP, 0, wSrc, -1, NULL,0, NULL, NULL ); - if(iTextLen < ansiArrLen){ - memset( ( void* )ansiArr, 0, sizeof( char ) * ( iTextLen + 1 ) ); - ::WideCharToMultiByte(CP_ACP,0,wSrc,-1,ansiArr,iTextLen,NULL,NULL); - return TRUE; - } - return FALSE; -} - -__forceinline wchar_t* AnsiToUtf16(PCSTR ansiSrc) -{ - wchar_t *pWide; - int iUnicodeLen = ::MultiByteToWideChar( CP_ACP, - 0, ansiSrc, -1, NULL, 0); - pWide = new wchar_t[iUnicodeLen + 1]; - memset(pWide, 0, (iUnicodeLen+1) * sizeof(wchar_t) ); - ::MultiByteToWideChar( CP_ACP, 0, ansiSrc, -1, (LPWSTR)pWide, iUnicodeLen ); - return pWide; -} - -__forceinline BOOL AnsiToUtf16Array(PCSTR ansiSrc, wchar_t* warr, int warr_len) -{ - int iUnicodeLen = ::MultiByteToWideChar( CP_ACP, - 0, ansiSrc, -1, NULL, 0); - if(warr_len >= iUnicodeLen){ - memset(warr, 0, (iUnicodeLen+1) * sizeof(wchar_t) ); - ::MultiByteToWideChar( CP_ACP, 0, ansiSrc, -1, (LPWSTR)warr, iUnicodeLen ); - return TRUE; - } - return FALSE; -} - -__forceinline wchar_t* Utf8ToUtf16(PCSTR ansiSrc) -{ - wchar_t *pWide; - int iUnicodeLen = ::MultiByteToWideChar( CP_UTF8, - 0, ansiSrc, -1, NULL, 0); - pWide = new wchar_t[iUnicodeLen + 1]; - memset(pWide, 0, (iUnicodeLen+1) * sizeof(wchar_t) ); - ::MultiByteToWideChar( CP_UTF8, 0, ansiSrc, -1, (LPWSTR)pWide, iUnicodeLen ); - return pWide; -} - -/* -__forceinline CString GetFileVersion() -{ - int iVerInfoSize; - char *pBuf; - CString asVer= _T(""); - VS_FIXEDFILEINFO *pVsInfo; - unsigned int iFileInfoSize = sizeof(VS_FIXEDFILEINFO); - TCHAR fileName[MAX_PATH]; - GetModuleFileName(NULL, fileName, MAX_PATH); - iVerInfoSize = GetFileVersionInfoSize(fileName, NULL); - - if(iVerInfoSize != 0){ - pBuf = new char[iVerInfoSize]; - if(GetFileVersionInfo(fileName, 0, iVerInfoSize, pBuf)){ - if(VerQueryValue(pBuf, _T("//"), (void**)&pVsInfo, &iFileInfoSize)){ - asVer.Format(_T("%d.%d.%d.%d"), - HIWORD(pVsInfo->dwFileVersionMS), - LOWORD(pVsInfo->dwFileVersionMS), - HIWORD(pVsInfo->dwFileVersionLS), - LOWORD(pVsInfo->dwFileVersionLS)); - } - } - delete pBuf; - } - return asVer; -} +#pragma comment(lib, "USER32" ) +#include <crtdbg.h> +#include <tchar.h> +#pragma comment(lib, "version.lib") +#define MTVERIFY(a) (a) +#if 0 +#define SHOWERROR(a) PrintError(a,__FILE__,__LINE__,GetLastError()) + +#ifdef DEBUG +#define MTASSERT(a) _ASSERTE(a) +#define MTVERIFY(a) if (!(a)) PrintError(#a,__FILE__,__LINE__,GetLastError()) +#else /*DEBUG*/ +#define MTASSERT(a) +#define MTVERIFY(a) (a) +#endif /*DEBUG*/ + +__inline void PrintError(LPCTSTR linedesc, LPCTSTR filename, int lineno, DWORD errnum) +{ + LPTSTR lpBuffer; + TCHAR errbuf[256]; + +#ifdef _WINDOWS_ + TCHAR modulename[MAX_PATH]; +#else //_WINDOWS_ + DWORD numread; +#endif //_WINDOWS_ + + FormatMessage( + FORMAT_MESSAGE_ALLOCATE_BUFFER | FORMAT_MESSAGE_FROM_SYSTEM, + NULL, + errnum, + LANG_NEUTRAL, + (LPTSTR)&lpBuffer, + 0, + NULL + ); + _stprintf(errbuf, _T("\nThe following call failed at line %d in %s:\n\n %s\n\nReason: %s\n"), + lineno, filename, linedesc, lpBuffer); + +#ifndef _WINDOWS_ + WriteFile(GetStdHandle(STD_ERROR_HANDLE), errbuf, lstrlen(errbuf), &numread, FALSE ); + Sleep(3000); +#else //_WINDOWS_ + GetModuleFileName(NULL, modulename, MAX_PATH); + MessageBox(NULL, errbuf, modulename, MB_ICONWARNING|MB_OK|MB_TASKMODAL|MB_SETFOREGROUND); + OutputDebugString(errbuf); +#endif //_WINDOWS_ + + LocalFree(lpBuffer); + //exit(EXIT_FAILURE); +} +#endif + + + +__inline void WaitTillThreadActive(HANDLE &handle) +{ + if(handle != INVALID_HANDLE_VALUE) + { + BOOL rc = FALSE; + DWORD ec = 0; + for(;;) + { + rc = GetExitCodeThread(handle, &ec); + if(rc && (ec == STILL_ACTIVE)) + break; + Sleep(500); + } + } +} +// obsolete +/* +__inline void WaitTillThreadExited(HANDLE &handle, DWORD dwMilliseconds = 3000) +{ + if(handle != INVALID_HANDLE_VALUE) + { + BOOL rc = FALSE; + DWORD ec = 0; + DWORD dwStart = GetTickCount(); + for(;;) + { + if(GetTickCount() - dwStart >= dwMilliseconds) + { + ::TerminateThread(handle, 0xffffffff); + CloseHandle(handle); + handle = INVALID_HANDLE_VALUE; + break; + } + if(handle == INVALID_HANDLE_VALUE) + break; + rc = GetExitCodeThread(handle, &ec); + if(rc && (ec != STILL_ACTIVE)) + { + CloseHandle(handle); + handle = INVALID_HANDLE_VALUE; + break; + } + Sleep(500); + } + } +} +*/ + +__forceinline void WaitTillThreadExited(HANDLE &handle, DWORD dwMilliseconds = 5000) +{ + if(handle == INVALID_HANDLE_VALUE) + return; + DWORD ret = ::WaitForSingleObject(handle, dwMilliseconds); + if(ret != WAIT_OBJECT_0) + { //::TerminateThread(handle, 0xffffffff); + } + CloseHandle(handle); + handle = INVALID_HANDLE_VALUE; +} + +__inline LPTSTR GetModuleFilePath() +{ + static TCHAR szPath[MAX_PATH] = {'\0'}; + if(lstrlen(szPath) != 0) + return szPath; + + TCHAR szExe[MAX_PATH]; + GetModuleFileName(GetModuleHandle(NULL), szExe, MAX_PATH); + int len = lstrlen(szExe); + for(int i = len; i > 0; i--) + { + if(szExe[i] == '\\') + { + szExe[i] = '\0'; + lstrcpy(szPath, szExe); + break; + } + } + return szPath; +} + +/////////*********************自定义宏********************//////////////////////// +//安全删除普通堆内存 +#define SAFEDELETEP(p) {if(p){delete (p); (p)=NULL;}} + +#define SAFEDELETEARR(pArr) {if((pArr)){delete[] (pArr); (pArr)=NULL;}} + +//安全删除对话框类堆内存 +#define SAFEDELETEDLG(pDlg) {\ + if ((pDlg)) {\ + if (::IsWindow(pDlg->m_hWnd)) {\ + (pDlg)->DestroyWindow();\ + }\ + delete (pDlg);\ + (pDlg)=NULL;\ + }\ +} + +//关闭核心对象句柄 +#define CLOSEHANDLE(h){\ + if (h != INVALID_HANDLE_VALUE && h != NULL) {\ + ::CloseHandle(h);\ + h = INVALID_HANDLE_VALUE;\ + }\ +} + +#define CLOSESOCKET(s){\ + if(s != INVALID_SOCKET){\ + ::closesocket(s); \ + s = INVALID_SOCKET;\ + }\ +} + +#ifdef _DEBUG +#define VERIFYPTR(p, cb) {MTVERIFY(!IsBadWritePtr(p, cb));} +#else +#define VERIFYPTR(p, cb) +#endif + + +/**************UNICODE-ANSI mutually transform**************************/ +// need be manuly delete +__forceinline LPSTR Utf16ToAnsi(const wchar_t * const wSrc) +{ + char* pElementText; + int iTextLen; + iTextLen = WideCharToMultiByte( CP_ACP, 0, wSrc, -1, NULL,0, NULL, NULL ); + pElementText = new char[iTextLen + 1]; + memset( ( void* )pElementText, 0, sizeof( char ) * ( iTextLen + 1 ) ); + ::WideCharToMultiByte( CP_ACP,0,wSrc,-1,pElementText,iTextLen,NULL,NULL); + + return pElementText; +} + +__forceinline BOOL Utf16ToAnsiUseCharArray(const wchar_t * const wSrc, + char *ansiArr, WORD ansiArrLen) +{ + int iTextLen = WideCharToMultiByte( CP_ACP, 0, wSrc, -1, NULL,0, NULL, NULL ); + if(iTextLen < ansiArrLen){ + memset( ( void* )ansiArr, 0, sizeof( char ) * ( iTextLen + 1 ) ); + ::WideCharToMultiByte(CP_ACP,0,wSrc,-1,ansiArr,iTextLen,NULL,NULL); + return TRUE; + } + return FALSE; +} + +__forceinline wchar_t* AnsiToUtf16(PCSTR ansiSrc) +{ + wchar_t *pWide; + int iUnicodeLen = ::MultiByteToWideChar( CP_ACP, + 0, ansiSrc, -1, NULL, 0); + pWide = new wchar_t[iUnicodeLen + 1]; + memset(pWide, 0, (iUnicodeLen+1) * sizeof(wchar_t) ); + ::MultiByteToWideChar( CP_ACP, 0, ansiSrc, -1, (LPWSTR)pWide, iUnicodeLen ); + return pWide; +} + +__forceinline BOOL AnsiToUtf16Array(PCSTR ansiSrc, wchar_t* warr, int warr_len) +{ + int iUnicodeLen = ::MultiByteToWideChar( CP_ACP, + 0, ansiSrc, -1, NULL, 0); + if(warr_len >= iUnicodeLen){ + memset(warr, 0, (iUnicodeLen+1) * sizeof(wchar_t) ); + ::MultiByteToWideChar( CP_ACP, 0, ansiSrc, -1, (LPWSTR)warr, iUnicodeLen ); + return TRUE; + } + return FALSE; +} + +__forceinline wchar_t* Utf8ToUtf16(PCSTR ansiSrc) +{ + wchar_t *pWide; + int iUnicodeLen = ::MultiByteToWideChar( CP_UTF8, + 0, ansiSrc, -1, NULL, 0); + pWide = new wchar_t[iUnicodeLen + 1]; + memset(pWide, 0, (iUnicodeLen+1) * sizeof(wchar_t) ); + ::MultiByteToWideChar( CP_UTF8, 0, ansiSrc, -1, (LPWSTR)pWide, iUnicodeLen ); + return pWide; +} + +__inline const char* Utf16ToUtf8(const wchar_t* utf16, int& out_len) +{ + out_len = ::WideCharToMultiByte(CP_UTF8, 0, utf16, -1, NULL, 0, 0, 0); + char *p8 = new char[out_len + 1]; + memset(p8, 0, (out_len + 1) * sizeof(wchar_t)); + ::WideCharToMultiByte(CP_UTF8, 0, utf16, -1, p8, out_len, 0, 0); + return p8; +} + +/* +__forceinline CString GetFileVersion() +{ + int iVerInfoSize; + char *pBuf; + CString asVer= _T(""); + VS_FIXEDFILEINFO *pVsInfo; + unsigned int iFileInfoSize = sizeof(VS_FIXEDFILEINFO); + TCHAR fileName[MAX_PATH]; + GetModuleFileName(NULL, fileName, MAX_PATH); + iVerInfoSize = GetFileVersionInfoSize(fileName, NULL); + + if(iVerInfoSize != 0){ + pBuf = new char[iVerInfoSize]; + if(GetFileVersionInfo(fileName, 0, iVerInfoSize, pBuf)){ + if(VerQueryValue(pBuf, _T("//"), (void**)&pVsInfo, &iFileInfoSize)){ + asVer.Format(_T("%d.%d.%d.%d"), + HIWORD(pVsInfo->dwFileVersionMS), + LOWORD(pVsInfo->dwFileVersionMS), + HIWORD(pVsInfo->dwFileVersionLS), + LOWORD(pVsInfo->dwFileVersionLS)); + } + } + delete pBuf; + } + return asVer; +} */ \ No newline at end of file diff --git a/global.h b/global.h index 70cfe9b270154e485062914fac06e99e78e1caf0..10c73aaedcea6e307a64c8a675308604a7f172b4 100644 --- a/global.h +++ b/global.h @@ -1,7 +1,7 @@ #pragma once - +#include "C:/Global/utf8.h" #include "C:/Global/LocalLock.h" #include "C:/Global/mtverify.h" #include "C:/Global/FileOper.h" @@ -23,7 +23,7 @@ public: #define AUTO_LOG_FUNCTION LOG_FUNCTION(__FUNCTION__) #include "C:/Global/MyWSAError.h" -#include "c:/Global/observer_macro.h" +#include "C:/Global/observer_macro.h" #define NAMESPACE_END }; @@ -32,14 +32,6 @@ private:\ classname(const classname&) {}\ classname& operator=(const classname&) {} -// singleton -//class CSingletonClassReleaseHelper { -//public: -// CSingletonClassReleaseHelper() {} -// ~CSingletonClassReleaseHelper() {} -//private: -// -//}; #define DECLARE_SINGLETON(class_name) \ private: \ diff --git a/utf8.h b/utf8.h new file mode 100644 index 0000000000000000000000000000000000000000..4e4451403f687e0107e3b950cd2973d8c7c182ce --- /dev/null +++ b/utf8.h @@ -0,0 +1,34 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "utf8/checked.h" +#include "utf8/unchecked.h" + +#endif // header guard diff --git a/utf8/checked.h b/utf8/checked.h new file mode 100644 index 0000000000000000000000000000000000000000..1331155138141bf777cdb9a1e327761358b1921e --- /dev/null +++ b/utf8/checked.h @@ -0,0 +1,327 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "core.h" +#include <stdexcept> + +namespace utf8 +{ + // Base for the exceptions that may be thrown from the library + class exception : public ::std::exception { + }; + + // Exceptions that may be thrown from the library functions. + class invalid_code_point : public exception { + uint32_t cp; + public: + invalid_code_point(uint32_t cp) : cp(cp) {} + virtual const char* what() const throw() { return "Invalid code point"; } + uint32_t code_point() const {return cp;} + }; + + class invalid_utf8 : public exception { + uint8_t u8; + public: + invalid_utf8 (uint8_t u) : u8(u) {} + virtual const char* what() const throw() { return "Invalid UTF-8"; } + uint8_t utf8_octet() const {return u8;} + }; + + class invalid_utf16 : public exception { + uint16_t u16; + public: + invalid_utf16 (uint16_t u) : u16(u) {} + virtual const char* what() const throw() { return "Invalid UTF-16"; } + uint16_t utf16_word() const {return u16;} + }; + + class not_enough_room : public exception { + public: + virtual const char* what() const throw() { return "Not enough space"; } + }; + + /// The library API - functions intended to be called by the users + + template <typename octet_iterator> + octet_iterator append(uint32_t cp, octet_iterator result) + { + if (!utf8::internal::is_code_point_valid(cp)) + throw invalid_code_point(cp); + + if (cp < 0x80) // one octet + *(result++) = static_cast<uint8_t>(cp); + else if (cp < 0x800) { // two octets + *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else if (cp < 0x10000) { // three octets + *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else { // four octets + *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0); + *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + return result; + } + + template <typename octet_iterator, typename output_iterator> + output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement) + { + while (start != end) { + octet_iterator sequence_start = start; + internal::utf_error err_code = utf8::internal::validate_next(start, end); + switch (err_code) { + case internal::UTF8_OK : + for (octet_iterator it = sequence_start; it != start; ++it) + *out++ = *it; + break; + case internal::NOT_ENOUGH_ROOM: + throw not_enough_room(); + case internal::INVALID_LEAD: + out = utf8::append (replacement, out); + ++start; + break; + case internal::INCOMPLETE_SEQUENCE: + case internal::OVERLONG_SEQUENCE: + case internal::INVALID_CODE_POINT: + out = utf8::append (replacement, out); + ++start; + // just one replacement mark for the sequence + while (start != end && utf8::internal::is_trail(*start)) + ++start; + break; + } + } + return out; + } + + template <typename octet_iterator, typename output_iterator> + inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out) + { + static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd); + return utf8::replace_invalid(start, end, out, replacement_marker); + } + + template <typename octet_iterator> + uint32_t next(octet_iterator& it, octet_iterator end) + { + uint32_t cp = 0; + internal::utf_error err_code = utf8::internal::validate_next(it, end, cp); + switch (err_code) { + case internal::UTF8_OK : + break; + case internal::NOT_ENOUGH_ROOM : + throw not_enough_room(); + case internal::INVALID_LEAD : + case internal::INCOMPLETE_SEQUENCE : + case internal::OVERLONG_SEQUENCE : + throw invalid_utf8(*it); + case internal::INVALID_CODE_POINT : + throw invalid_code_point(cp); + } + return cp; + } + + template <typename octet_iterator> + uint32_t peek_next(octet_iterator it, octet_iterator end) + { + return utf8::next(it, end); + } + + template <typename octet_iterator> + uint32_t prior(octet_iterator& it, octet_iterator start) + { + // can't do much if it == start + if (it == start) + throw not_enough_room(); + + octet_iterator end = it; + // Go back until we hit either a lead octet or start + while (utf8::internal::is_trail(*(--it))) + if (it == start) + throw invalid_utf8(*it); // error - no lead byte in the sequence + return utf8::peek_next(it, end); + } + + /// Deprecated in versions that include "prior" + template <typename octet_iterator> + uint32_t previous(octet_iterator& it, octet_iterator pass_start) + { + octet_iterator end = it; + while (utf8::internal::is_trail(*(--it))) + if (it == pass_start) + throw invalid_utf8(*it); // error - no lead byte in the sequence + octet_iterator temp = it; + return utf8::next(temp, end); + } + + template <typename octet_iterator, typename distance_type> + void advance (octet_iterator& it, distance_type n, octet_iterator end) + { + for (distance_type i = 0; i < n; ++i) + utf8::next(it, end); + } + + template <typename octet_iterator> + typename std::iterator_traits<octet_iterator>::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits<octet_iterator>::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::next(first, last); + return dist; + } + + template <typename u16bit_iterator, typename octet_iterator> + octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) + { + while (start != end) { + uint32_t cp = utf8::internal::mask16(*start++); + // Take care of surrogate pairs first + if (utf8::internal::is_lead_surrogate(cp)) { + if (start != end) { + uint32_t trail_surrogate = utf8::internal::mask16(*start++); + if (utf8::internal::is_trail_surrogate(trail_surrogate)) + cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; + else + throw invalid_utf16(static_cast<uint16_t>(trail_surrogate)); + } + else + throw invalid_utf16(static_cast<uint16_t>(cp)); + + } + // Lone trail surrogate + else if (utf8::internal::is_trail_surrogate(cp)) + throw invalid_utf16(static_cast<uint16_t>(cp)); + + result = utf8::append(cp, result); + } + return result; + } + + template <typename u16bit_iterator, typename octet_iterator> + u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) + { + while (start != end) { + uint32_t cp = utf8::next(start, end); + if (cp > 0xffff) { //make a surrogate pair + *result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast<uint16_t>(cp); + } + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::append(*(start++), result); + + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) + { + while (start != end) + (*result++) = utf8::next(start, end); + + return result; + } + + // The iterator class + template <typename octet_iterator> + class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { + octet_iterator it; + octet_iterator range_start; + octet_iterator range_end; + public: + iterator () {} + explicit iterator (const octet_iterator& octet_it, + const octet_iterator& range_start, + const octet_iterator& range_end) : + it(octet_it), range_start(range_start), range_end(range_end) + { + if (it < range_start || it > range_end) + throw std::out_of_range("Invalid utf-8 iterator position"); + } + // the default "big three" are OK + octet_iterator base () const { return it; } + uint32_t operator * () const + { + octet_iterator temp = it; + return utf8::next(temp, range_end); + } + bool operator == (const iterator& rhs) const + { + if (range_start != rhs.range_start || range_end != rhs.range_end) + throw std::logic_error("Comparing utf-8 iterators defined with different ranges"); + return (it == rhs.it); + } + bool operator != (const iterator& rhs) const + { + return !(operator == (rhs)); + } + iterator& operator ++ () + { + utf8::next(it, range_end); + return *this; + } + iterator operator ++ (int) + { + iterator temp = *this; + utf8::next(it, range_end); + return temp; + } + iterator& operator -- () + { + utf8::prior(it, range_start); + return *this; + } + iterator operator -- (int) + { + iterator temp = *this; + utf8::prior(it, range_start); + return temp; + } + }; // class iterator + +} // namespace utf8 + +#endif //header guard + + diff --git a/utf8/core.h b/utf8/core.h new file mode 100644 index 0000000000000000000000000000000000000000..693d388c078de9870d2f19be75d4e7483c393e77 --- /dev/null +++ b/utf8/core.h @@ -0,0 +1,329 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include <iterator> + +namespace utf8 +{ + // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers + // You may need to change them to match your system. + // These typedefs have the same names as ones from cstdint, or boost/cstdint + typedef unsigned char uint8_t; + typedef unsigned short uint16_t; + typedef unsigned int uint32_t; + +// Helper code - not intended to be directly called by the library users. May be changed at any time +namespace internal +{ + // Unicode constants + // Leading (high) surrogates: 0xd800 - 0xdbff + // Trailing (low) surrogates: 0xdc00 - 0xdfff + const uint16_t LEAD_SURROGATE_MIN = 0xd800u; + const uint16_t LEAD_SURROGATE_MAX = 0xdbffu; + const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u; + const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu; + const uint16_t LEAD_OFFSET = LEAD_SURROGATE_MIN - (0x10000 >> 10); + const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN; + + // Maximum valid value for a Unicode code point + const uint32_t CODE_POINT_MAX = 0x0010ffffu; + + template<typename octet_type> + inline uint8_t mask8(octet_type oc) + { + return static_cast<uint8_t>(0xff & oc); + } + template<typename u16_type> + inline uint16_t mask16(u16_type oc) + { + return static_cast<uint16_t>(0xffff & oc); + } + template<typename octet_type> + inline bool is_trail(octet_type oc) + { + return ((utf8::internal::mask8(oc) >> 6) == 0x2); + } + + template <typename u16> + inline bool is_lead_surrogate(u16 cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX); + } + + template <typename u16> + inline bool is_trail_surrogate(u16 cp) + { + return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + template <typename u16> + inline bool is_surrogate(u16 cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + template <typename u32> + inline bool is_code_point_valid(u32 cp) + { + return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp)); + } + + template <typename octet_iterator> + inline typename std::iterator_traits<octet_iterator>::difference_type + sequence_length(octet_iterator lead_it) + { + uint8_t lead = utf8::internal::mask8(*lead_it); + if (lead < 0x80) + return 1; + else if ((lead >> 5) == 0x6) + return 2; + else if ((lead >> 4) == 0xe) + return 3; + else if ((lead >> 3) == 0x1e) + return 4; + else + return 0; + } + + template <typename octet_difference_type> + inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length) + { + if (cp < 0x80) { + if (length != 1) + return true; + } + else if (cp < 0x800) { + if (length != 2) + return true; + } + else if (cp < 0x10000) { + if (length != 3) + return true; + } + + return false; + } + + enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT}; + + /// Helper for get_sequence_x + template <typename octet_iterator> + utf_error increase_safely(octet_iterator& it, octet_iterator end) + { + if (++it == end) + return NOT_ENOUGH_ROOM; + + if (!utf8::internal::is_trail(*it)) + return INCOMPLETE_SEQUENCE; + + return UTF8_OK; + } + + #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;} + + /// get_sequence_x functions decode utf-8 sequences of the length x + template <typename octet_iterator> + utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + return UTF8_OK; + } + + template <typename octet_iterator> + utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f); + + return UTF8_OK; + } + + template <typename octet_iterator> + utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; + } + + template <typename octet_iterator> + utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (utf8::internal::mask8(*it) << 6) & 0xfff; + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; + } + + #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR + + template <typename octet_iterator> + utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + // Save the original value of it so we can go back in case of failure + // Of course, it does not make much sense with i.e. stream iterators + octet_iterator original_it = it; + + uint32_t cp = 0; + // Determine the sequence length based on the lead octet + typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type; + const octet_difference_type length = utf8::internal::sequence_length(it); + + // Get trail octets and calculate the code point + utf_error err = UTF8_OK; + switch (length) { + case 0: + return INVALID_LEAD; + case 1: + err = utf8::internal::get_sequence_1(it, end, cp); + break; + case 2: + err = utf8::internal::get_sequence_2(it, end, cp); + break; + case 3: + err = utf8::internal::get_sequence_3(it, end, cp); + break; + case 4: + err = utf8::internal::get_sequence_4(it, end, cp); + break; + } + + if (err == UTF8_OK) { + // Decoding succeeded. Now, security checks... + if (utf8::internal::is_code_point_valid(cp)) { + if (!utf8::internal::is_overlong_sequence(cp, length)){ + // Passed! Return here. + code_point = cp; + ++it; + return UTF8_OK; + } + else + err = OVERLONG_SEQUENCE; + } + else + err = INVALID_CODE_POINT; + } + + // Failure branch - restore the original value of the iterator + it = original_it; + return err; + } + + template <typename octet_iterator> + inline utf_error validate_next(octet_iterator& it, octet_iterator end) { + uint32_t ignored; + return utf8::internal::validate_next(it, end, ignored); + } + +} // namespace internal + + /// The library API - functions intended to be called by the users + + // Byte order mark + const uint8_t bom[] = {0xef, 0xbb, 0xbf}; + + template <typename octet_iterator> + octet_iterator find_invalid(octet_iterator start, octet_iterator end) + { + octet_iterator result = start; + while (result != end) { + utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end); + if (err_code != internal::UTF8_OK) + return result; + } + return result; + } + + template <typename octet_iterator> + inline bool is_valid(octet_iterator start, octet_iterator end) + { + return (utf8::find_invalid(start, end) == end); + } + + template <typename octet_iterator> + inline bool starts_with_bom (octet_iterator it, octet_iterator end) + { + return ( + ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) && + ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) && + ((it != end) && (utf8::internal::mask8(*it)) == bom[2]) + ); + } + + //Deprecated in release 2.3 + template <typename octet_iterator> + inline bool is_bom (octet_iterator it) + { + return ( + (utf8::internal::mask8(*it++)) == bom[0] && + (utf8::internal::mask8(*it++)) == bom[1] && + (utf8::internal::mask8(*it)) == bom[2] + ); + } +} // namespace utf8 + +#endif // header guard + + diff --git a/utf8/unchecked.h b/utf8/unchecked.h new file mode 100644 index 0000000000000000000000000000000000000000..cb2427166b19cd61df9f338120bac364ccec9d30 --- /dev/null +++ b/utf8/unchecked.h @@ -0,0 +1,228 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "core.h" + +namespace utf8 +{ + namespace unchecked + { + template <typename octet_iterator> + octet_iterator append(uint32_t cp, octet_iterator result) + { + if (cp < 0x80) // one octet + *(result++) = static_cast<uint8_t>(cp); + else if (cp < 0x800) { // two octets + *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else if (cp < 0x10000) { // three octets + *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else { // four octets + *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0); + *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)| 0x80); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + return result; + } + + template <typename octet_iterator> + uint32_t next(octet_iterator& it) + { + uint32_t cp = utf8::internal::mask8(*it); + typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it); + switch (length) { + case 1: + break; + case 2: + it++; + cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f); + break; + case 3: + ++it; + cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); + ++it; + cp += (*it) & 0x3f; + break; + case 4: + ++it; + cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + ++it; + cp += (utf8::internal::mask8(*it) << 6) & 0xfff; + ++it; + cp += (*it) & 0x3f; + break; + } + ++it; + return cp; + } + + template <typename octet_iterator> + uint32_t peek_next(octet_iterator it) + { + return utf8::unchecked::next(it); + } + + template <typename octet_iterator> + uint32_t prior(octet_iterator& it) + { + while (utf8::internal::is_trail(*(--it))) ; + octet_iterator temp = it; + return utf8::unchecked::next(temp); + } + + // Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous) + template <typename octet_iterator> + inline uint32_t previous(octet_iterator& it) + { + return utf8::unchecked::prior(it); + } + + template <typename octet_iterator, typename distance_type> + void advance (octet_iterator& it, distance_type n) + { + for (distance_type i = 0; i < n; ++i) + utf8::unchecked::next(it); + } + + template <typename octet_iterator> + typename std::iterator_traits<octet_iterator>::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits<octet_iterator>::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::unchecked::next(first); + return dist; + } + + template <typename u16bit_iterator, typename octet_iterator> + octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) + { + while (start != end) { + uint32_t cp = utf8::internal::mask16(*start++); + // Take care of surrogate pairs first + if (utf8::internal::is_lead_surrogate(cp)) { + uint32_t trail_surrogate = utf8::internal::mask16(*start++); + cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; + } + result = utf8::unchecked::append(cp, result); + } + return result; + } + + template <typename u16bit_iterator, typename octet_iterator> + u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) + { + while (start < end) { + uint32_t cp = utf8::unchecked::next(start); + if (cp > 0xffff) { //make a surrogate pair + *result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast<uint16_t>(cp); + } + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::unchecked::append(*(start++), result); + + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) + { + while (start < end) + (*result++) = utf8::unchecked::next(start); + + return result; + } + + // The iterator class + template <typename octet_iterator> + class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { + octet_iterator it; + public: + iterator () {} + explicit iterator (const octet_iterator& octet_it): it(octet_it) {} + // the default "big three" are OK + octet_iterator base () const { return it; } + uint32_t operator * () const + { + octet_iterator temp = it; + return utf8::unchecked::next(temp); + } + bool operator == (const iterator& rhs) const + { + return (it == rhs.it); + } + bool operator != (const iterator& rhs) const + { + return !(operator == (rhs)); + } + iterator& operator ++ () + { + ::std::advance(it, utf8::internal::sequence_length(it)); + return *this; + } + iterator operator ++ (int) + { + iterator temp = *this; + ::std::advance(it, utf8::internal::sequence_length(it)); + return temp; + } + iterator& operator -- () + { + utf8::unchecked::prior(it); + return *this; + } + iterator operator -- (int) + { + iterator temp = *this; + utf8::unchecked::prior(it); + return temp; + } + }; // class iterator + + } // namespace utf8::unchecked +} // namespace utf8 + + +#endif // header guard +