docs/latex/wx/mbconv.tex

   1 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
   2 %% Name:        mbconv.tex
   3 %% Purpose:     wxMBConv documentation
   4 %% Author:      Ove Kaaven, Vadim Zeitlin
   5 %% Created:     2000-03-25
   6 %% RCS-ID:      $Id$
   7 %% Copyright:   (c) 2000 Ove Kaaven
   8 %%              (c) 2003-2006 Vadim Zeitlin
   9 %% License:     wxWindows license
  10 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  11
  12
  13 \section{\class{wxMBConv}}\label{wxmbconv}
  14
  15 This class is the base class of a hierarchy of classes capable of converting
  16 text strings between multibyte (SBCS or DBCS) encodings and Unicode.
  17
  18 In the documentation for this and related classes please notice that
  19 \emph{length} of the string refers to the number of characters in the string
  20 not counting the terminating \NUL, if any. While the \emph{size} of the string
  21 is the total number of bytes in the string, including any trailing \NUL.
  22 Thus, length of wide character string \texttt{L"foo"} is $3$ while its size can
  23 be either $8$ or $16$ depending on whether \texttt{wchar\_t} is $2$ bytes (as
  24 under Windows) or $4$ (Unix).
  25
  26 \wxheading{Global variables}
  27
  28 There are several predefined instances of this class:
  29 \begin{twocollist}
  30 \twocolitem{\textbf{wxConvLibc}}{Uses the standard ANSI C \texttt{mbstowcs()} and
  31 \texttt{wcstombs()} functions to perform the conversions; thus depends on the
  32 current locale.}
  33 \twocolitem{\textbf{wxConvLocal}}{Another conversion corresponding to the
  34 current locale but this one uses the best available conversion.}
  35 \twocolitem{\textbf{wxConvUI}}{The conversion used for hte standard UI elements
  36 such as menu items and buttons. This is a pointer which is initially set to
  37 \texttt{wxConvLocal} as the program uses the current locale by default but can
  38 be set to some specific conversion if the program needs to use a specific
  39 encoding for its UI.}
  40 \twocolitem{\textbf{wxConvISO8859\_1}}{Conversion to and from ISO-8859-1 (Latin I)
  41 encoding.}
  42 \twocolitem{\textbf{wxConvUTF8}}{Conversion to and from UTF-8 encoding.}
  43 \twocolitem{\textbf{wxConvFile}}{The appropriate conversion for the file names,
  44 depends on the system.}
  45 % \twocolitem{\textbf{wxConvCurrent}}{Not really clear what is it for...}
  46 \end{twocollist}
  47
  48
  49 \wxheading{Constants}
  50
  51 \texttt{wxCONV\_FAILED} value is defined as \texttt{(size\_t)$-1$} and is
  52 returned by the conversion functions instead of the length of the converted
  53 string if the conversion fails.
  54
  55
  56 \wxheading{Derived from}
  57
  58 No base class
  59
  60 \wxheading{Include files}
  61
  62 <wx/strconv.h>
  63
  64 \wxheading{See also}
  65
  66 \helpref{wxCSConv}{wxcsconv},
  67 \helpref{wxEncodingConverter}{wxencodingconverter},
  68 \helpref{wxMBConv classes overview}{mbconvclasses}
  69
  70
  71 \latexignore{\rtfignore{\wxheading{Members}}}
  72
  73
  74 \membersection{wxMBConv::wxMBConv}\label{wxmbconvwxmbconv}
  75
  76 \func{}{wxMBConv}{\void}
  77
  78 Trivial default constructor.
  79
  80
  81 \membersection{wxMBConv::MB2WC}\label{wxmbconvmb2wc}
  82
  83 \constfunc{virtual size\_t}{MB2WC}{\param{wchar\_t *}{out}, \param{const char *}{in}, \param{size\_t }{outLen}}
  84
  85 \deprecated{\helpref{ToWChar}{wxmbconvtowchar}}
  86
  87 Converts from a string \arg{in} in multibyte encoding to Unicode putting up to
  88 \arg{outLen} characters into the buffer \arg{out}.
  89
  90 If \arg{out} is \NULL, only the length of the string which would result from
  91 the conversion is calculated and returned. Note that this is the length and not
  92 size, i.e. the returned value does \emph{not} include the trailing \NUL. But
  93 when the function is called with a non-\NULL \arg{out} buffer, the \arg{outLen}
  94 parameter should be one more to allow to properly \NUL-terminate the string.
  95
  96 \wxheading{Parameters}
  97
  98 \docparam{out}{The output buffer, may be \NULL if the caller is only
  99 interested in the length of the resulting string}
 100
 101 \docparam{in}{The \NUL-terminated input string, cannot be \NULL}
 102
 103 \docparam{outLen}{The length of the output buffer but \emph{including}
 104 \NUL, ignored if \arg{out} is \NULL}
 105
 106 \wxheading{Return value}
 107
 108 The length of the converted string \emph{excluding} the trailing \NUL.
 109
 110
 111 \membersection{wxMBConv::WC2MB}\label{wxmbconvwc2mb}
 112
 113 \constfunc{virtual size\_t}{WC2MB}{\param{char* }{buf}, \param{const wchar\_t* }{psz}, \param{size\_t }{n}}
 114
 115 \deprecated{\helpref{FromWChar}{wxmbconvfromwchar}}
 116
 117 Converts from Unicode to multibyte encoding. The semantics of this function
 118 (including the return value meaning) is the same as for
 119 \helpref{MB2WC}{wxmbconvmb2wc}.
 120
 121 Notice that when the function is called with a non-\NULL buffer, the
 122 {\it n} parameter should be the size of the buffer and so it \emph{should} take
 123 into account the trailing \NUL, which might take two or four bytes for some
 124 encodings (UTF-16 and UTF-32) and not one.
 125
 126
 127 \membersection{wxMBConv::cMB2WC}\label{wxmbconvcmb2wc}
 128
 129 \constfunc{const wxWCharBuffer}{cMB2WC}{\param{const char *}{in}}
 130
 131 \constfunc{const wxWCharBuffer}{cMB2WC}{\param{const char *}{in}, \param{size\_t }{inLen}, \param{size\_t }{*outLen}}
 132
 133 Converts from multibyte encoding to Unicode by calling
 134 \helpref{MB2WC}{wxmbconvmb2wc}, allocating a temporary wxWCharBuffer to hold
 135 the result.
 136
 137 The first overload takes a \NUL-terminated input string. The second one takes a
 138 string of exactly the specified length and the string may include or not the
 139 trailing \NUL character(s). If the string is not \NUL-terminated, a temporary
 140 \NUL-terminated copy of it suitable for passing to \helpref{MB2WC}{wxmbconvmb2wc}
 141 is made, so it is more efficient to ensure that the string is does have the
 142 appropriate number of \NUL bytes (which is usually $1$ but may be $2$ or $4$
 143 for UTF-16 or UTF-32, see \helpref{GetMBNulLen}{wxmbconvgetmbnullen}),
 144 especially for long strings.
 145
 146 If \arg{outLen} is not-\NULL, it receives the length of the converted
 147 string.
 148
 149
 150 \membersection{wxMBConv::cWC2MB}\label{wxmbconvcwc2mb}
 151
 152 \constfunc{const wxCharBuffer}{cWC2MB}{\param{const wchar\_t* }{in}}
 153
 154 \constfunc{const wxCharBuffer}{cWC2MB}{\param{const wchar\_t* }{in}, \param{size\_t }{inLen}, \param{size\_t }{*outLen}}
 155
 156 Converts from Unicode to multibyte encoding by calling WC2MB,
 157 allocating a temporary wxCharBuffer to hold the result.
 158
 159 The second overload of this function allows to convert a string of the given
 160 length \arg{inLen}, whether it is \NUL-terminated or not (for wide character
 161 strings, unlike for the multibyte ones, a single \NUL is always enough).
 162 But notice that just as with \helpref{cMB2WC}{wxmbconvmb2wc}, it is more
 163 efficient to pass an already terminated string to this function as otherwise a
 164 copy is made internally.
 165
 166 If \arg{outLen} is not-\NULL, it receives the length of the converted
 167 string.
 168
 169
 170 \membersection{wxMBConv::cMB2WX}\label{wxmbconvcmb2wx}
 171
 172 \constfunc{const char*}{cMB2WX}{\param{const char* }{psz}}
 173
 174 \constfunc{const wxWCharBuffer}{cMB2WX}{\param{const char* }{psz}}
 175
 176 Converts from multibyte encoding to the current wxChar type
 177 (which depends on whether wxUSE\_UNICODE is set to 1). If wxChar is char,
 178 it returns the parameter unaltered. If wxChar is wchar\_t, it returns the
 179 result in a wxWCharBuffer. The macro wxMB2WXbuf is defined as the correct
 180 return type (without const).
 181
 182
 183 \membersection{wxMBConv::cWX2MB}\label{wxmbconvcwx2mb}
 184
 185 \constfunc{const char*}{cWX2MB}{\param{const wxChar* }{psz}}
 186
 187 \constfunc{const wxCharBuffer}{cWX2MB}{\param{const wxChar* }{psz}}
 188
 189 Converts from the current wxChar type to multibyte encoding. If wxChar is char,
 190 it returns the parameter unaltered. If wxChar is wchar\_t, it returns the
 191 result in a wxCharBuffer. The macro wxWX2MBbuf is defined as the correct
 192 return type (without const).
 193
 194
 195 \membersection{wxMBConv::cWC2WX}\label{wxmbconvcwc2wx}
 196
 197 \constfunc{const wchar\_t*}{cWC2WX}{\param{const wchar\_t* }{psz}}
 198
 199 \constfunc{const wxCharBuffer}{cWC2WX}{\param{const wchar\_t* }{psz}}
 200
 201 Converts from Unicode to the current wxChar type. If wxChar is wchar\_t,
 202 it returns the parameter unaltered. If wxChar is char, it returns the
 203 result in a wxCharBuffer. The macro wxWC2WXbuf is defined as the correct
 204 return type (without const).
 205
 206
 207 \membersection{wxMBConv::cWX2WC}\label{wxmbconvcwx2wc}
 208
 209 \constfunc{const wchar\_t*}{cWX2WC}{\param{const wxChar* }{psz}}
 210
 211 \constfunc{const wxWCharBuffer}{cWX2WC}{\param{const wxChar* }{psz}}
 212
 213 Converts from the current wxChar type to Unicode. If wxChar is wchar\_t,
 214 it returns the parameter unaltered. If wxChar is char, it returns the
 215 result in a wxWCharBuffer. The macro wxWX2WCbuf is defined as the correct
 216 return type (without const).
 217
 218
 219 \membersection{wxMBConv::FromWChar}\label{wxmbconvfromwchar}
 220
 221 \constfunc{virtual size\_t}{FromWChar}{\param{wchar\_t *}{dst}, \param{size\_t }{dstLen}, \param{const char *}{src}, \param{size\_t }{srcLen = $-1$}}
 222
 223 The most general function for converting a multibyte string to a wide string.
 224 The main case is when \arg{dst} is not \NULL and \arg{srcLen} is not $-1$: then
 225 the function converts exactly \arg{srcLen} bytes starting at \arg{src} into
 226 wide string which it output to \arg{dst}. If the length of the resulting wide
 227 string is greater than \arg{dstLen}, an error is returned. Note that if
 228 \arg{srcLen} bytes don't include \NUL characters, the resulting wide string is
 229 not \NUL-terminated neither.
 230
 231 If \arg{srcLen} is $-1$, the function supposes that the string is properly
 232 (i.e. as necessary for the encoding handled by this conversion) \NUL-terminated
 233 and converts the entire string, including any trailing \NUL bytes. In this case
 234 the wide string is also \NUL-terminated.
 235
 236 Finally, if \arg{dst} is \NULL, the function returns the length of the needed
 237 buffer.
 238
 239 \wxheading{Return value}
 240
 241 The number of characters written to \arg{dst} (or the number of characters
 242 which would have been written to it if it were non-\NULL) on success or
 243 \texttt{wxCONV\_FAILED} on error.
 244
 245
 246 \membersection{wxMBConv::GetMaxMBNulLen}\label{wxmbconvgetmaxmbnullen}
 247
 248 \func{const size\_t}{GetMaxMBNulLen}{\void}
 249
 250 Returns the maximal value which can be returned by
 251 \helpref{GetMBNulLen}{wxmbconvgetmbnullen} for any conversion object. Currently
 252 this value is $4$.
 253
 254 This method can be used to allocate the buffer with enough space for the
 255 trailing \NUL characters for any encoding.
 256
 257
 258 \membersection{wxMBConv::GetMBNulLen}\label{wxmbconvgetmbnullen}
 259
 260 \constfunc{size\_t}{GetMBNulLen}{\void}
 261
 262 This function returns $1$ for most of the multibyte encodings in which the
 263 string is terminated by a single \NUL, $2$ for UTF-16 and $4$ for UTF-32 for
 264 which the string is terminated with $2$ and $4$ \NUL characters respectively.
 265 The other cases are not currently supported and $-1$ is returned for them.
 266
 267
 268 \membersection{wxMBConv::ToWChar}\label{wxmbconvtowchar}
 269
 270 \constfunc{virtual size\_t}{ToWChar}{\param{char\_t *}{dst}, \param{size\_t }{dstLen}, \param{const wchar\_t *}{src}, \param{size\_t }{srcLen = $-1$}}
 271
 272 This function has the same semantics as \helpref{FromWChar}{wxmbconvfromwchar}
 273 except that it converts a wide string to multibyte one.
 274
 275