| <html lang="en"> |
| <head> |
| <title>Multibyte Conversion Example - The GNU C Library</title> |
| <meta http-equiv="Content-Type" content="text/html"> |
| <meta name="description" content="The GNU C Library"> |
| <meta name="generator" content="makeinfo 4.13"> |
| <link title="Top" rel="start" href="index.html#Top"> |
| <link rel="up" href="Restartable-multibyte-conversion.html#Restartable-multibyte-conversion" title="Restartable multibyte conversion"> |
| <link rel="prev" href="Converting-Strings.html#Converting-Strings" title="Converting Strings"> |
| <link href="http://www.gnu.org/software/texinfo/" rel="generator-home" title="Texinfo Homepage"> |
| <!-- |
| This file documents the GNU C library. |
| |
| This is Edition 0.12, last updated 2007-10-27, |
| of `The GNU C Library Reference Manual', for version |
| 2.8 (Sourcery G++ Lite 2011.03-41). |
| |
| Copyright (C) 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2001, 2002, |
| 2003, 2007, 2008, 2010 Free Software Foundation, Inc. |
| |
| Permission is granted to copy, distribute and/or modify this document |
| under the terms of the GNU Free Documentation License, Version 1.3 or |
| any later version published by the Free Software Foundation; with the |
| Invariant Sections being ``Free Software Needs Free Documentation'' |
| and ``GNU Lesser General Public License'', the Front-Cover texts being |
| ``A GNU Manual'', and with the Back-Cover Texts as in (a) below. A |
| copy of the license is included in the section entitled "GNU Free |
| Documentation License". |
| |
| (a) The FSF's Back-Cover Text is: ``You have the freedom to |
| copy and modify this GNU manual. Buying copies from the FSF |
| supports it in developing GNU and promoting software freedom.''--> |
| <meta http-equiv="Content-Style-Type" content="text/css"> |
| <style type="text/css"><!-- |
| pre.display { font-family:inherit } |
| pre.format { font-family:inherit } |
| pre.smalldisplay { font-family:inherit; font-size:smaller } |
| pre.smallformat { font-family:inherit; font-size:smaller } |
| pre.smallexample { font-size:smaller } |
| pre.smalllisp { font-size:smaller } |
| span.sc { font-variant:small-caps } |
| span.roman { font-family:serif; font-weight:normal; } |
| span.sansserif { font-family:sans-serif; font-weight:normal; } |
| --></style> |
| <link rel="stylesheet" type="text/css" href="../cs.css"> |
| </head> |
| <body> |
| <div class="node"> |
| <a name="Multibyte-Conversion-Example"></a> |
| <p> |
| Previous: <a rel="previous" accesskey="p" href="Converting-Strings.html#Converting-Strings">Converting Strings</a>, |
| Up: <a rel="up" accesskey="u" href="Restartable-multibyte-conversion.html#Restartable-multibyte-conversion">Restartable multibyte conversion</a> |
| <hr> |
| </div> |
| |
| <h4 class="subsection">6.3.5 A Complete Multibyte Conversion Example</h4> |
| |
| <p>The example programs given in the last sections are only brief and do |
| not contain all the error checking, etc. Presented here is a complete |
| and documented example. It features the <code>mbrtowc</code> function but it |
| should be easy to derive versions using the other functions. |
| |
| <pre class="smallexample"> int |
| file_mbsrtowcs (int input, int output) |
| { |
| /* <span class="roman">Note the use of </span><code>MB_LEN_MAX</code><span class="roman">.</span> |
| <code>MB_CUR_MAX</code><span class="roman"> cannot portably be used here.</span> */ |
| char buffer[BUFSIZ + MB_LEN_MAX]; |
| mbstate_t state; |
| int filled = 0; |
| int eof = 0; |
| |
| /* <span class="roman">Initialize the state.</span> */ |
| memset (&state, '\0', sizeof (state)); |
| |
| while (!eof) |
| { |
| ssize_t nread; |
| ssize_t nwrite; |
| char *inp = buffer; |
| wchar_t outbuf[BUFSIZ]; |
| wchar_t *outp = outbuf; |
| |
| /* <span class="roman">Fill up the buffer from the input file.</span> */ |
| nread = read (input, buffer + filled, BUFSIZ); |
| if (nread < 0) |
| { |
| perror ("read"); |
| return 0; |
| } |
| /* <span class="roman">If we reach end of file, make a note to read no more.</span> */ |
| if (nread == 0) |
| eof = 1; |
| |
| /* <code>filled</code><span class="roman"> is now the number of bytes in </span><code>buffer</code><span class="roman">.</span> */ |
| filled += nread; |
| |
| /* <span class="roman">Convert those bytes to wide characters--as many as we can.</span> */ |
| while (1) |
| { |
| size_t thislen = mbrtowc (outp, inp, filled, &state); |
| /* <span class="roman">Stop converting at invalid character;</span> |
| <span class="roman">this can mean we have read just the first part</span> |
| <span class="roman">of a valid character.</span> */ |
| if (thislen == (size_t) -1) |
| break; |
| /* <span class="roman">We want to handle embedded NUL bytes</span> |
| <span class="roman">but the return value is 0. Correct this.</span> */ |
| if (thislen == 0) |
| thislen = 1; |
| /* <span class="roman">Advance past this character.</span> */ |
| inp += thislen; |
| filled -= thislen; |
| ++outp; |
| } |
| |
| /* <span class="roman">Write the wide characters we just made.</span> */ |
| nwrite = write (output, outbuf, |
| (outp - outbuf) * sizeof (wchar_t)); |
| if (nwrite < 0) |
| { |
| perror ("write"); |
| return 0; |
| } |
| |
| /* <span class="roman">See if we have a </span><em>real</em><span class="roman"> invalid character.</span> */ |
| if ((eof && filled > 0) || filled >= MB_CUR_MAX) |
| { |
| error (0, 0, "invalid multibyte character"); |
| return 0; |
| } |
| |
| /* <span class="roman">If any characters must be carried forward,</span> |
| <span class="roman">put them at the beginning of </span><code>buffer</code><span class="roman">.</span> */ |
| if (filled > 0) |
| memmove (buffer, inp, filled); |
| } |
| |
| return 1; |
| } |
| </pre> |
| </body></html> |
| |
