llstring.cpp

/** 
 * @file llstring.cpp
 * @brief String utility functions and the std::string class.
 *
 * $LicenseInfo:firstyear=2001&license=viewerlgpl$
 * Second Life Viewer Source Code
 * Copyright (C) 2010, Linden Research, Inc.
 * 
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation;
 * version 2.1 of the License only.
 * 
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 * 
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 * 
 * Linden Research, Inc., 945 Battery Street, San Francisco, CA  94111  USA
 * $/LicenseInfo$
 */

#include "linden_common.h"

#include "llstring.h"
#include "llerror.h"
#include "llfasttimer.h"
#include "llsd.h"
#include <vector>

#if LL_WINDOWS
#include "llwin32headerslean.h"
#include <winnls.h> // for WideCharToMultiByte
#endif

#include <absl/strings/str_format.h>

LLTrace::BlockTimerStatHandle FT_STRING_FORMAT("String Format");


std::string ll_safe_string(const char* in)
{
	if(in) return std::string(in);
	return std::string();
}

std::string ll_safe_string(const char* in, S32 maxlen)
{
	if(in && maxlen > 0 ) return std::string(in, maxlen);

	return std::string();
}

bool is_char_hex(char hex)
{
	if((hex >= '0') && (hex <= '9'))
	{
		return true;
	}
	else if((hex >= 'a') && (hex <='f'))
	{
		return true;
	}
	else if((hex >= 'A') && (hex <='F'))
	{
		return true;
	}
	return false; // uh - oh, not hex any more...
}

U8 hex_as_nybble(char hex)
{
	if((hex >= '0') && (hex <= '9'))
	{
		return (U8)(hex - '0');
	}
	else if((hex >= 'a') && (hex <='f'))
	{
		return (U8)(10 + hex - 'a');
	}
	else if((hex >= 'A') && (hex <='F'))
	{
		return (U8)(10 + hex - 'A');
	}
	return 0; // uh - oh, not hex any more...
}

bool iswindividual(llwchar elem)
{   
	U32 cur_char = (U32)elem;
	bool result = false;
	if (0x2E80<= cur_char && cur_char <= 0x9FFF)
	{
		result = true;
	}
	else if (0xAC00<= cur_char && cur_char <= 0xD7A0 )
	{
		result = true;
	}
	else if (0xF900<= cur_char && cur_char <= 0xFA60 )
	{
		result = true;
	}
	return result;
}

bool _read_file_into_string(std::string& str, const std::string& filename)
{
	llifstream ifs(filename.c_str(), llifstream::binary);
	if (!ifs.is_open())
	{
		LL_INFOS() << "Unable to open file " << filename << LL_ENDL;
		return false;
	}

	std::ostringstream oss;

	oss << ifs.rdbuf();
	str = oss.str();
	ifs.close();
	return true;
}




// See http://www.unicode.org/Public/BETA/CVTUTF-1-2/ConvertUTF.c
// for the Unicode implementation - this doesn't match because it was written before finding
// it.


std::ostream& operator<<(std::ostream &s, const LLWString &wstr)
{
	std::string utf8_str = wstring_to_utf8str(wstr);
	s << utf8_str;
	return s;
}

std::string rawstr_to_utf8(const std::string& raw)
{
	LLWString wstr(utf8str_to_wstring(raw));
	return wstring_to_utf8str(wstr);
}

S32 wchar_to_utf8chars(llwchar in_char, char* outchars)
{
	U32 cur_char = (U32)in_char;
	char* base = outchars;
	if (cur_char < 0x80)
	{
		*outchars++ = (U8)cur_char;
	}
	else if (cur_char < 0x800)
	{
		*outchars++ = 0xC0 | (cur_char >> 6);
		*outchars++ = 0x80 | (cur_char & 0x3F);
	}
	else if (cur_char < 0x10000)
	{
		*outchars++ = 0xE0 | (cur_char >> 12);
		*outchars++ = 0x80 | ((cur_char >> 6) & 0x3F);
		*outchars++ = 0x80 | (cur_char & 0x3F);
	}
	else if (cur_char < 0x200000)
	{
		*outchars++ = 0xF0 | (cur_char >> 18);
		*outchars++ = 0x80 | ((cur_char >> 12) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 6) & 0x3F);
		*outchars++ = 0x80 | (cur_char & 0x3F);
	}
	else if (cur_char < 0x4000000)
	{
		*outchars++ = 0xF8 | (cur_char >> 24);
		*outchars++ = 0x80 | ((cur_char >> 18) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 12) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 6) & 0x3F);
		*outchars++ = 0x80 | (cur_char & 0x3F);
	}
	else if (cur_char < 0x80000000)
	{
		*outchars++ = 0xFC | (cur_char >> 30);
		*outchars++ = 0x80 | ((cur_char >> 24) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 18) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 12) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 6) & 0x3F);
		*outchars++ = 0x80 | (cur_char & 0x3F);
	}
	else
	{
		LL_WARNS() << "Invalid Unicode character " << cur_char << "!" << LL_ENDL;
		*outchars++ = LL_UNKNOWN_CHAR;
	}
	return outchars - base;
}	

S32 utf16chars_to_wchar(const U16* inchars, llwchar* outchar)