util.cpp

软件是使用VC70

			} else {
				if(str[1] == 0 ||
					!((((unsigned char)str[1]) & ~0x3f) == 0x80)) 
				{
					str++;
					return 0;
				}
				c = ((wchar_t)(unsigned char)str[0] & 0x1f) << 6 |
					((wchar_t)(unsigned char)str[1] & 0x3f);
				str += 2;
			}
		} else {
			str++;
			return 0;
		}
	} else {
		wchar_t c = Text::asciiToLower((char)str[0]);
		str++;
		return c;
	}

	return Text::toLower(c);
}

string::size_type Util::findSubString(const string& aString, const string& aSubString, string::size_type start) throw() {
	if(aString.length() < start)
		return (string::size_type)string::npos;

	if(aString.length() - start < aSubString.length())
		return (string::size_type)string::npos;

	if(aSubString.empty())
		return 0;

	// Hm, should start measure in characters or in bytes? bytes for now...
	const u_int8_t* tx = (const u_int8_t*)aString.c_str() + start;
	const u_int8_t* px = (const u_int8_t*)aSubString.c_str();

	const u_int8_t* end = tx + aString.length() - start - aSubString.length() + 1;

	wchar_t wp = utf8ToLC(px);

	while(tx < end) {
		const u_int8_t* otx = tx;
		if(wp == utf8ToLC(tx)) {
			const u_int8_t* px2 = px;
			const u_int8_t* tx2 = tx;

			for(;;) {
				if(*px2 == 0)
					return otx - (u_int8_t*)aString.c_str();

				if(utf8ToLC(px2) != utf8ToLC(tx2))
					break;
			}
		}
	}
	return (string::size_type)string::npos;
}

int Util::stricmp(const char* a, const char* b) {
	while(*a) {
		wchar_t ca = 0, cb = 0;
		int na = Text::utf8ToWc(a, ca);
		int nb = Text::utf8ToWc(b, cb);
		ca = Text::toLower(ca);
		cb = Text::toLower(cb);
		if(ca != cb) {
			return (int)ca - (int)cb;
		}
		a+= na < 0 ? 1 : na;
		b+= nb < 0 ? 1 : nb;
	}
	wchar_t ca = 0, cb = 0;
	Text::utf8ToWc(a, ca);
	Text::utf8ToWc(b, cb);

	return (int)Text::toLower(ca) - (int)Text::toLower(cb);
}

int Util::strnicmp(const char* a, const char* b, size_t n) {
	const char* end = a + n;
	while(*a && a < end) {
		wchar_t ca = 0, cb = 0;
		int na = Text::utf8ToWc(a, ca);
		int nb = Text::utf8ToWc(b, cb);
		ca = Text::toLower(ca);
		cb = Text::toLower(cb);
		if(ca != cb) {
			return (int)ca - (int)cb;
		}
		a+= na < 0 ? 1 : na;
		b+= nb < 0 ? 1 : nb;
	}
	wchar_t ca = 0, cb = 0;
	Text::utf8ToWc(a, ca);
	Text::utf8ToWc(b, cb);
	return (a >= end) ? 0 : ((int)Text::toLower(ca) - (int)Text::toLower(cb));
}

string Util::encodeURI(const string& aString, bool reverse) {
	// reference: rfc2396
	string tmp = aString;
	if(reverse) {
		string::size_type idx;
		for(idx = 0; idx < tmp.length(); ++idx) {
			if(tmp.length() > idx + 2 && tmp[idx] == '%' && isxdigit(tmp[idx+1]) && isxdigit(tmp[idx+2])) {
				tmp[idx] = fromHexEscape(tmp.substr(idx+1,2));
				tmp.erase(idx+1, 2);
			} else { // reference: rfc1630, magnet-uri draft
				if(tmp[idx] == '+')
					tmp[idx] = ' ';
			}
		}
	} else {
		const string disallowed = ";/?:@&=+$," // reserved
			                      "<>#%\" "    // delimiters
		                          "{}|\\^[]`"; // unwise
		string::size_type idx, loc;
		for(idx = 0; idx < tmp.length(); ++idx) {
			if(tmp[idx] == ' ') {
				tmp[idx] = '+';
			} else {
				if(tmp[idx] <= 0x1F || tmp[idx] >= 0x7f || (loc = disallowed.find_first_of(tmp[idx])) != string::npos) {
					tmp.replace(idx, 1, toHexEscape(tmp[idx]));
					idx+=2;
				}
			}
		}
	}
	return tmp;
}

/**
 * This function takes a string and a set of parameters and transforms them according to
 * a simple formatting rule, similar to strftime. In the message, every parameter should be
 * represented by %[name]. It will then be replaced by the corresponding item in 
 * the params stringmap. After that, the string is passed through strftime with the current
 * date/time and then finally written to the log file. If the parameter is not present at all,
 * it is removed from the string completely...
 */
string Util::formatParams(const string& msg, StringMap& params) {
	string result = msg;

	string::size_type i, j, k;
	i = 0;
	while (( j = result.find("%[", i)) != string::npos) {
		if( (result.size() < j + 2) || ((k = result.find(']', j + 2)) == string::npos) ) {
			break;
		}
		string name = result.substr(j + 2, k - j - 2);
		StringMapIter smi = params.find(name);
		if(smi == params.end()) {
			result.erase(j, k-j + 1);
			i = j;
		} else {
			if(smi->second.find('%') != string::npos) {
				string tmp = smi->second;	// replace all % in params with %% for strftime
				string::size_type m = 0;
				while(( m = tmp.find('%', m)) != string::npos) {
					tmp.replace(m, 1, "%%");
					m+=2;
				}
				result.replace(j, k-j + 1, tmp);
				i = j + tmp.size();
			} else {
				result.replace(j, k-j + 1, smi->second);
				i = j + smi->second.size();
			}
		}
	}

	result = formatTime(result, time(NULL));
	
	return result;
}

/** Fix for wide formatting bug in wcsftime in the ms c lib for multibyte encodings of unicode in singlebyte locales */
string fixedftime(const string& format, struct tm* t) {
	string ret = format;
	const char codes[] = "aAbBcdHIjmMpSUwWxXyYzZ%";

	char tmp[4];
	tmp[0] = '%';
	tmp[1] = tmp[2] = tmp[3] = 0;

	StringMap sm;
	AutoArray<char> buf(1024);
	for(size_t i = 0; i < sizeof(codes); ++i) {
		tmp[1] = codes[i];
		tmp[2] = 0;
		strftime(buf, 1024-1, tmp, t);
		sm[tmp] = buf; 

		tmp[1] = '#';
		tmp[2] = codes[i];
		strftime(buf, 1024-1, tmp, t);
		sm[tmp] = buf; 		
	}

	for(StringMapIter i = sm.begin(); i != sm.end(); ++i) {
		for(string::size_type j = ret.find(i->first); j != string::npos; j = ret.find(i->first, j)) {
			ret.replace(j, i->first.length(), i->second);
			j += i->second.length() - i->first.length();
		}
	}

	return ret;
}

string Util::formatTime(const string &msg, const time_t t) {
	if (!msg.empty()) {
		size_t bufsize = msg.size() + 256;
		struct tm* loc = localtime(&t);

		if(!loc) {
			return Util::emptyString;
		}
#if _WIN32
		AutoArray<TCHAR> buf(bufsize);

		if(!_tcsftime(buf, bufsize-1, Text::toT(msg).c_str(), loc)) {
			return fixedftime(msg, loc);
		}

		return Text::fromT(tstring(buf));
#else
		// will this give wide representations for %a and %A?
		// surely win32 can't have a leg up on linux/unixen in this area. - Todd
		AutoArray<char> buf(bufsize);

		while(!strftime(buf, bufsize-1, msg.c_str(), loc)) {
			bufsize+=64;
			buf = new char[bufsize];
		}

		return string(buf);
#endif
	}
	return Util::emptyString;
}

/* Below is a high-speed random number generator with much
   better granularity than the CRT one in msvc...(no, I didn't
   write it...see copyright) */ 
/* Copyright (C) 1997 Makoto Matsumoto and Takuji Nishimura.
   Any feedback is very welcome. For any question, comments,       
   see http://www.math.keio.ac.jp/matumoto/emt.html or email       
   [e-mail] */       
/* Period parameters */  
#define N 624
#define M 397
#define MATRIX_A 0x9908b0df   /* constant vector a */
#define UPPER_MASK 0x80000000 /* most significant w-r bits */
#define LOWER_MASK 0x7fffffff /* least significant r bits */

/* Tempering parameters */   
#define TEMPERING_MASK_B 0x9d2c5680
#define TEMPERING_MASK_C 0xefc60000
#define TEMPERING_SHIFT_U(y)  (y >> 11)
#define TEMPERING_SHIFT_S(y)  (y << 7)
#define TEMPERING_SHIFT_T(y)  (y << 15)
#define TEMPERING_SHIFT_L(y)  (y >> 18)

static unsigned long mt[N]; /* the array for the state vector  */
static int mti=N+1; /* mti==N+1 means mt[N] is not initialized */

/* initializing the array with a NONZERO seed */
static void sgenrand(unsigned long seed) {
	/* setting initial seeds to mt[N] using         */
	/* the generator Line 25 of Table 1 in          */
	/* [KNUTH 1981, The Art of Computer Programming */
	/*    Vol. 2 (2nd Ed.), pp102]                  */
	mt[0]= seed & 0xffffffff;
	for (mti=1; mti<N; mti++)
		mt[mti] = (69069 * mt[mti-1]) & 0xffffffff;
}

u_int32_t Util::rand() {
	unsigned long y;
	static unsigned long mag01[2]={0x0, MATRIX_A};
	/* mag01[x] = x * MATRIX_A  for x=0,1 */

	if (mti >= N) { /* generate N words at one time */
		int kk;

		if (mti == N+1)   /* if sgenrand() has not been called, */
			sgenrand(4357); /* a default initial seed is used   */

		for (kk=0;kk<N-M;kk++) {
			y = (mt[kk]&UPPER_MASK)|(mt[kk+1]&LOWER_MASK);
			mt[kk] = mt[kk+M] ^ (y >> 1) ^ mag01[y & 0x1];
		}
		for (;kk<N-1;kk++) {
			y = (mt[kk]&UPPER_MASK)|(mt[kk+1]&LOWER_MASK);
			mt[kk] = mt[kk+(M-N)] ^ (y >> 1) ^ mag01[y & 0x1];
		}
		y = (mt[N-1]&UPPER_MASK)|(mt[0]&LOWER_MASK);
		mt[N-1] = mt[M-1] ^ (y >> 1) ^ mag01[y & 0x1];

		mti = 0;
	}

	y = mt[mti++];
	y ^= TEMPERING_SHIFT_U(y);
	y ^= TEMPERING_SHIFT_S(y) & TEMPERING_MASK_B;
	y ^= TEMPERING_SHIFT_T(y) & TEMPERING_MASK_C;
	y ^= TEMPERING_SHIFT_L(y);

	return y; 
}

string Util::getOsVersion() {
#ifdef _WIN32
	string os;

	OSVERSIONINFOEX ver;
	memset(&ver, 0, sizeof(OSVERSIONINFOEX));
	ver.dwOSVersionInfoSize = sizeof(OSVERSIONINFOEX);

	if(!GetVersionEx((OSVERSIONINFO*)&ver)) {
		ver.dwOSVersionInfoSize = sizeof(OSVERSIONINFO);
		if(!GetVersionEx((OSVERSIONINFO*)&ver)) {
			os = "Windows (version unknown)";
		}
	}

	if(os.empty()) {
		if(ver.dwPlatformId != VER_PLATFORM_WIN32_NT) {
			os = "Win9x/ME/Junk";
		} else if(ver.dwMajorVersion == 4) {
			os = "WinNT4";
		} else if(ver.dwMajorVersion == 5) {
			if(ver.dwMinorVersion == 0) {
				os = "Win2000";
			} else if(ver.dwMinorVersion == 1) {
				os = "WinXP";
			} else if(ver.dwMinorVersion == 2) {
				os = "Win2003";
			} else {
				os = "Unknown WinNT5";
			}

			if(ver.wProductType & VER_NT_WORKSTATION)
				os += " Pro";
			else if(ver.wProductType & VER_NT_SERVER)
				os += " Server";
			else if(ver.wProductType & VER_NT_DOMAIN_CONTROLLER)
				os += " DC";
		}

		if(ver.wServicePackMajor != 0) {
			os += "SP";
			os += Util::toString(ver.wServicePackMajor);
			if(ver.wServicePackMinor != 0) {
				os += '.';
				os += Util::toString(ver.wServicePackMinor);
			}
		}
	}

	return os;

#else // _WIN32
	utsname n;

	if(uname(&n) != 0) {
		return "unix (unknown version)";
	}

	return string(n.sysname) + " " + string(n.release) + " (" + string(n.machine) + ")";

#endif // _WIN32
}

/*	getIpCountry
	This function returns the country(Abbreviation) of an ip
	for exemple: it returns "PT", whitch standards for "Portugal"
	more info: http://www.maxmind.com/app/csv
*/
string Util::getIpCountry (string IP) {
	if (BOOLSETTING(GET_USER_COUNTRY)) {
		dcassert(count(IP.begin(), IP.end(), '.') == 3);

		//e.g IP 23.24.25.26 : w=23, x=24, y=25, z=26
		string::size_type a = IP.find('.');
		string::size_type b = IP.find('.', a+1);
		string::size_type c = IP.find('.', b+2);

		u_int32_t ipnum = (Util::toUInt32(IP.c_str()) << 24) | 
			(Util::toUInt32(IP.c_str() + a + 1) << 16) | 
			(Util::toUInt32(IP.c_str() + b + 1) << 8) | 
			(Util::toUInt32(IP.c_str() + c + 1) );

		CountryIter i = countries.lower_bound(ipnum);

		if(i != countries.end()) {
			return string((char*)&(i->second), 2);
		}
	}

	return Util::emptyString; //if doesn't returned anything already, something is wrong...
}

string Util::toDOS(const string& tmp) {
	if(tmp.empty())
		return Util::emptyString;

	string tmp2(tmp);

	if(tmp2[0] == '\r' && (tmp2.size() == 1 || tmp2[1] != '\n')) {
		tmp2.insert(1, "\n");
	}
	for(string::size_type i = 1; i < tmp2.size() - 1; ++i) {
		if(tmp2[i] == '\r' && tmp2[i+1] != '\n') {
			// Mac ending
			tmp2.insert(i+1, "\n");
			i++;
		} else if(tmp2[i] == '\n' && tmp2[i-1] != '\r') {
			// Unix encoding
			tmp2.insert(i, "\r");
			i++;
		}
	}
	return tmp2;
}

/**
 * @file
 * $Id: Util.cpp,v 1.83 2005/03/03 11:58:30 arnetheduck Exp $
 */