os/ossrv/genericopenlibs/cstdlib/LCHAR/MBWCCONV.CPP
changeset 0 bde4ae8d615e
     1.1 --- /dev/null	Thu Jan 01 00:00:00 1970 +0000
     1.2 +++ b/os/ossrv/genericopenlibs/cstdlib/LCHAR/MBWCCONV.CPP	Fri Jun 15 03:10:57 2012 +0200
     1.3 @@ -0,0 +1,253 @@
     1.4 +// Copyright (c) 1999-2009 Nokia Corporation and/or its subsidiary(-ies).
     1.5 +// All rights reserved.
     1.6 +// This component and the accompanying materials are made available
     1.7 +// under the terms of "Eclipse Public License v1.0"
     1.8 +// which accompanies this distribution, and is available
     1.9 +// at the URL "http://www.eclipse.org/legal/epl-v10.html".
    1.10 +//
    1.11 +// Initial Contributors:
    1.12 +// Nokia Corporation - initial contribution.
    1.13 +//
    1.14 +// Contributors:
    1.15 +//
    1.16 +// Description:
    1.17 +// Rrun-time library routines for translating between multibyte and wide characters
    1.18 +// mbstowcs, mbtowc, wcstombs, wctomb and mblen
    1.19 +// 
    1.20 +//
    1.21 +
    1.22 +#include <e32std.h>
    1.23 +#include <utf.h>
    1.24 +#include <stdlib.h>
    1.25 +#include <string.h>
    1.26 +
    1.27 +
    1.28 +
    1.29 +
    1.30 +extern "C"
    1.31 +{
    1.32 +
    1.33 +/**
    1.34 +Converts the multibyte character addressed by s into the corresponding UNICODE
    1.35 +character pwc
    1.36 +@return the length, in bytes, of the multibyte character for which it found 
    1.37 +a UNICODE equivalent
    1.38 +@param pwc Is the address of a wide character, type wchar_t, 
    1.39 +to receive the UNICODE equivalent of s.
    1.40 +@param s Points to the multibyte character to be converted to UNICODE.
    1.41 +@param n Is the maximum width, in bytes, for which to scan s for a valid multibyte
    1.42 +sequence. Regardless of the value of n, no more than MB_CUR_MAX bytes are examined.
    1.43 +*/
    1.44 +EXPORT_C int mbtowc (wchar_t *pwc, const char *s, size_t n)
    1.45 +	{
    1.46 +
    1.47 +	int rval = 0;
    1.48 +	if (s)
    1.49 +		{
    1.50 +		wchar_t wide;
    1.51 +
    1.52 +		//number of chars to convert has a max of MB_CUR_MAX
    1.53 +		TInt maxlen = (n > MB_CUR_MAX ? MB_CUR_MAX : n);
    1.54 +		
    1.55 +		TPtrC8 src((const TUint8*)s, maxlen);
    1.56 +		TPtr16 awc((TUint16*)&wide, 1);		//length of 1 as we only want 1 wide character
    1.57 +
    1.58 +		TInt ret = CnvUtfConverter::ConvertToUnicodeFromUtf8(awc, src);
    1.59 +	
    1.60 +		//return the number of chars converted which is the max number - the number not converted
    1.61 +		//unless the character converted was the wide null character
    1.62 +		if (ret >= 0)
    1.63 +			{
    1.64 +			rval = (L'\0' != wide) ? maxlen - ret : 0;
    1.65 +
    1.66 +			if (pwc)
    1.67 +				*pwc = wide;	//only assign the return if we have a target
    1.68 +			}
    1.69 +		else
    1.70 +			return -1;	//the conversion failed.
    1.71 +
    1.72 +		}
    1.73 +	return rval;
    1.74 +	}
    1.75 +}
    1.76 +
    1.77 +
    1.78 +extern "C"
    1.79 +{
    1.80 +
    1.81 +EXPORT_C int mbstowcs (wchar_t *wstring, const char * string, size_t size)
    1.82 +	{
    1.83 +	//convert the string "string" to wide characters
    1.84 +	//return number of wide characters
    1.85 +
    1.86 +	if (string)
    1.87 +		{
    1.88 +		
    1.89 +		if (wstring)
    1.90 +			{
    1.91 +			TPtrC8 src((const TUint8*)string);
    1.92 +			TPtr16 awc((TUint16*)wstring, size);		//max length of size
    1.93 +
    1.94 +			TInt ret = CnvUtfConverter::ConvertToUnicodeFromUtf8(awc, src);
    1.95 +		
    1.96 +			if (ret >= 0)
    1.97 +				{
    1.98 +				TUint len = awc.Length();	//return number of wide characters
    1.99 +				if (len < size)
   1.100 +					awc.ZeroTerminate();
   1.101 +				return len;
   1.102 +				}
   1.103 +			else
   1.104 +				return -1;	//the conversion failed.
   1.105 +			}
   1.106 +		else
   1.107 +			{
   1.108 +			//we have no output string.  
   1.109 +			//ms say return len required
   1.110 +			//gcc says nowt
   1.111 +			return 1+strlen(string);	//max is could be
   1.112 +			}
   1.113 +		}
   1.114 +	return 0;	
   1.115 +	}
   1.116 +
   1.117 +
   1.118 +	
   1.119 +}
   1.120 +
   1.121 +
   1.122 +
   1.123 +extern "C"
   1.124 +{
   1.125 +
   1.126 +/**
   1.127 +Converts a wide character to a multibyte character
   1.128 +@return If s is null, the return value is true (non-zero) if multibyte 
   1.129 +characters have state-dependent encodings, or false (zero) if they do not.
   1.130 +@param mbchar multibyte character
   1.131 +@param wc wide character
   1.132 +*/
   1.133 +EXPORT_C int wctomb (char * mbchar, wchar_t wc)
   1.134 +	{
   1.135 +	if (mbchar)
   1.136 +		{
   1.137 +		//deal with the special null character case
   1.138 +		if (L'\0' == wc)
   1.139 +			{
   1.140 +			*mbchar = '\0';
   1.141 +			return 1;
   1.142 +			}
   1.143 +
   1.144 +		//so we have possible character which is not null
   1.145 +		TPtr8 multi((TUint8*)mbchar, 0, MB_CUR_MAX);	//limit max length to MB_CUR_MAX
   1.146 +		TPtrC16 wide ((const TUint16*)&wc);
   1.147 +
   1.148 +		TInt ret = CnvUtfConverter::ConvertFromUnicodeToUtf8(multi, wide);
   1.149 +
   1.150 +		//ret has the number of wide characters left to convert, or an error
   1.151 +		if (ret >= 0)	//we didn't get an error
   1.152 +			//return the number of characters in the output
   1.153 +			return multi.Length();
   1.154 +		else
   1.155 +			return -1;
   1.156 +
   1.157 +		}
   1.158 +		//calling with a null dest string is used to initialise shift state
   1.159 +		//we are only dealing with UTF8 which hasn't got one,
   1.160 +		//therefore we always return 0.
   1.161 +	else
   1.162 +		return 0;
   1.163 +	}
   1.164 +}
   1.165 +
   1.166 +extern "C"
   1.167 +{
   1.168 +/**
   1.169 +The wcstombs function converts a wide string to a string of multibyte
   1.170 +characters.
   1.171 +@return 
   1.172 +@param string multibyte string
   1.173 +@param wstring wide string
   1.174 +@param size number of bytes written to.
   1.175 +*/
   1.176 +EXPORT_C int wcstombs (char * string, const wchar_t * wstring, size_t size)
   1.177 +	{
   1.178 +	if (wstring)
   1.179 +		{
   1.180 +		if (string)
   1.181 +			{
   1.182 +			TPtr8 multi((TUint8*)string, size);	//limit max length to size
   1.183 +			TPtrC16 wide((TText16*)wstring);
   1.184 +
   1.185 +			TInt ret = CnvUtfConverter::ConvertFromUnicodeToUtf8(multi, wide);
   1.186 +
   1.187 +			if (ret >= 0)	//we didn't get an error
   1.188 +				{
   1.189 +				TUint len = multi.Length();
   1.190 +				if (len < size)
   1.191 +					multi.ZeroTerminate();
   1.192 +				return len;			//null terminate
   1.193 +				}
   1.194 +			else
   1.195 +				return -1;
   1.196 +			}
   1.197 +		else
   1.198 +			{
   1.199 +			//we have a null output string
   1.200 +			//ms expects the length back.
   1.201 +			//gcc says nothing about it.
   1.202 +			//quick and dirty!!
   1.203 +			return 1 + (MB_CUR_MAX * wcslen(wstring));		//max it can be
   1.204 +			}
   1.205 +		}
   1.206 +	else
   1.207 +		return 0;
   1.208 +	}
   1.209 +}
   1.210 +
   1.211 +
   1.212 +
   1.213 +extern "C"
   1.214 +{
   1.215 +/**
   1.216 +If string is not a null pointer, the function returns the number of bytes in the 
   1.217 +multibyte string 
   1.218 +that constitute the next multibyte character, 
   1.219 +or it returns -1 if the next n (or the remaining) bytes do not constitute a valid 
   1.220 +multibyte character. mblen does not include the terminating null in the count of bytes. 
   1.221 +@return the number of bytes in the multibyte string
   1.222 +@param string 
   1.223 +@param size 
   1.224 +*/
   1.225 +EXPORT_C int mblen (const char *string, size_t size)
   1.226 +	{
   1.227 +	if (string)
   1.228 +		{
   1.229 +		wchar_t wide;
   1.230 +
   1.231 +		
   1.232 +		//deal with an empty string without doing the conversion.
   1.233 +		if ('\0' == *string)
   1.234 +			return 0;
   1.235 +
   1.236 +		TInt maxlen = (size > MB_CUR_MAX ? MB_CUR_MAX : size);
   1.237 +
   1.238 +		TPtrC8 src((const TUint8*)string, maxlen);
   1.239 +		TPtr16 awc((TUint16*)&wide, 1);		//length of 1 as we only want 1 wide character
   1.240 +
   1.241 +		TInt ret = CnvUtfConverter::ConvertToUnicodeFromUtf8(awc, src);
   1.242 +	
   1.243 +		//return the number of chars converted which is the max number - the number not converted
   1.244 +		//unless the character converted was the wide null character
   1.245 +		if (ret >= 0)
   1.246 +			{
   1.247 +			return ((L'\0' != wide) ? maxlen - ret : 0);
   1.248 +			}
   1.249 +		else
   1.250 +			return -1;
   1.251 +
   1.252 +		}
   1.253 +		//shift state would be initialised here if were using them
   1.254 +		return 0;
   1.255 +	}
   1.256 +}