*/
#include "config.h"
+#include "glibconfig.h"
+#ifndef G_OS_WIN32
#include <iconv.h>
+#endif
#include <errno.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
-#include "glib.h"
-#include "gprintfint.h"
-#include "gthreadprivate.h"
-#include "gunicode.h"
+#ifdef G_OS_WIN32
+#include "win_iconv.c"
+#endif
#ifdef G_PLATFORM_WIN32
#define STRICT
#undef STRICT
#endif
+#include "gconvert.h"
+
+#include "gprintfint.h"
+#include "gslist.h"
+#include "gstrfuncs.h"
+#include "gtestutils.h"
+#include "gthread.h"
+#include "gthreadprivate.h"
+#include "gunicode.h"
+
+#ifdef NEED_ICONV_CACHE
+#include "glist.h"
+#include "ghash.h"
+#endif
+
#include "glibintl.h"
#if defined(USE_LIBICONV_GNU) && !defined (_LIBICONV_H)
#error GNU libiconv not in use but included iconv.h is from libiconv
#endif
-#include "galias.h"
+
+/**
+ * SECTION:conversions
+ * @title: Character Set Conversion
+ * @short_description: Convert strings between different character sets
+ *
+ * The g_convert() family of function wraps the functionality of iconv(). In
+ * addition to pure character set conversions, GLib has functions to deal
+ * with the extra complications of encodings for file names.
+ *
+ * <refsect2 id="file-name-encodings">
+ * <title>File Name Encodings</title>
+ * <para>
+ * Historically, Unix has not had a defined encoding for file
+ * names: a file name is valid as long as it does not have path
+ * separators in it ("/"). However, displaying file names may
+ * require conversion: from the character set in which they were
+ * created, to the character set in which the application
+ * operates. Consider the Spanish file name
+ * "<filename>Presentación.sxi</filename>". If the
+ * application which created it uses ISO-8859-1 for its encoding,
+ * </para>
+ * <programlisting id="filename-iso8859-1">
+ * Character: P r e s e n t a c i ó n . s x i
+ * Hex code: 50 72 65 73 65 6e 74 61 63 69 f3 6e 2e 73 78 69
+ * </programlisting>
+ * <para>
+ * However, if the application use UTF-8, the actual file name on
+ * disk would look like this:
+ * </para>
+ * <programlisting id="filename-utf-8">
+ * Character: P r e s e n t a c i ó n . s x i
+ * Hex code: 50 72 65 73 65 6e 74 61 63 69 c3 b3 6e 2e 73 78 69
+ * </programlisting>
+ * <para>
+ * Glib uses UTF-8 for its strings, and GUI toolkits like GTK+
+ * that use Glib do the same thing. If you get a file name from
+ * the file system, for example, from readdir(3) or from g_dir_read_name(),
+ * and you wish to display the file name to the user, you
+ * <emphasis>will</emphasis> need to convert it into UTF-8. The
+ * opposite case is when the user types the name of a file he
+ * wishes to save: the toolkit will give you that string in
+ * UTF-8 encoding, and you will need to convert it to the
+ * character set used for file names before you can create the
+ * file with open(2) or fopen(3).
+ * </para>
+ * <para>
+ * By default, Glib assumes that file names on disk are in UTF-8
+ * encoding. This is a valid assumption for file systems which
+ * were created relatively recently: most applications use UTF-8
+ * encoding for their strings, and that is also what they use for
+ * the file names they create. However, older file systems may
+ * still contain file names created in "older" encodings, such as
+ * ISO-8859-1. In this case, for compatibility reasons, you may
+ * want to instruct Glib to use that particular encoding for file
+ * names rather than UTF-8. You can do this by specifying the
+ * encoding for file names in the <link
+ * linkend="G_FILENAME_ENCODING"><envar>G_FILENAME_ENCODING</envar></link>
+ * environment variable. For example, if your installation uses
+ * ISO-8859-1 for file names, you can put this in your
+ * <filename>~/.profile</filename>:
+ * </para>
+ * <programlisting>
+ * export G_FILENAME_ENCODING=ISO-8859-1
+ * </programlisting>
+ * <para>
+ * Glib provides the functions g_filename_to_utf8() and
+ * g_filename_from_utf8() to perform the necessary conversions. These
+ * functions convert file names from the encoding specified in
+ * <envar>G_FILENAME_ENCODING</envar> to UTF-8 and vice-versa.
+ * <xref linkend="file-name-encodings-diagram"/> illustrates how
+ * these functions are used to convert between UTF-8 and the
+ * encoding for file names in the file system.
+ * </para>
+ * <figure id="file-name-encodings-diagram">
+ * <title>Conversion between File Name Encodings</title>
+ * <graphic fileref="file-name-encodings.png" format="PNG"/>
+ * </figure>
+ * <refsect3 id="file-name-encodings-checklist">
+ * <title>Checklist for Application Writers</title>
+ * <para>
+ * This section is a practical summary of the detailed
+ * description above. You can use this as a checklist of
+ * things to do to make sure your applications process file
+ * name encodings correctly.
+ * </para>
+ * <orderedlist>
+ * <listitem><para>
+ * If you get a file name from the file system from a function
+ * such as readdir(3) or gtk_file_chooser_get_filename(),
+ * you do not need to do any conversion to pass that
+ * file name to functions like open(2), rename(2), or
+ * fopen(3) — those are "raw" file names which the file
+ * system understands.
+ * </para></listitem>
+ * <listitem><para>
+ * If you need to display a file name, convert it to UTF-8 first by
+ * using g_filename_to_utf8(). If conversion fails, display a string like
+ * "<literal>Unknown file name</literal>". <emphasis>Do not</emphasis>
+ * convert this string back into the encoding used for file names if you
+ * wish to pass it to the file system; use the original file name instead.
+ * For example, the document window of a word processor could display
+ * "Unknown file name" in its title bar but still let the user save the
+ * file, as it would keep the raw file name internally. This can happen
+ * if the user has not set the <envar>G_FILENAME_ENCODING</envar>
+ * environment variable even though he has files whose names are not
+ * encoded in UTF-8.
+ * </para></listitem>
+ * <listitem><para>
+ * If your user interface lets the user type a file name for saving or
+ * renaming, convert it to the encoding used for file names in the file
+ * system by using g_filename_from_utf8(). Pass the converted file name
+ * to functions like fopen(3). If conversion fails, ask the user to enter
+ * a different file name. This can happen if the user types Japanese
+ * characters when <envar>G_FILENAME_ENCODING</envar> is set to
+ * <literal>ISO-8859-1</literal>, for example.
+ * </para></listitem>
+ * </orderedlist>
+ * </refsect3>
+ * </refsect2>
+ */
+
+/* We try to terminate strings in unknown charsets with this many zero bytes
+ * to ensure that multibyte strings really are nul-terminated when we return
+ * them from g_convert() and friends.
+ */
+#define NUL_TERMINATOR_LENGTH 4
GQuark
g_convert_error_quark (void)
}
-/**
+/*
* iconv_cache_bucket_new:
* @key: cache key
* @cd: iconv descriptor
}
-/**
+/*
* iconv_cache_bucket_expire:
* @node: cache bucket's node
* @bucket: cache bucket
}
-/**
+/*
* iconv_cache_expire_unused:
*
* Expires as many unused cache buckets as it needs to in order to get
p = str;
inbytes_remaining = len;
- outbuf_size = len + 1; /* + 1 for nul in case len == 1 */
+ outbuf_size = len + NUL_TERMINATOR_LENGTH;
- outbytes_remaining = outbuf_size - 1; /* -1 for nul */
+ outbytes_remaining = outbuf_size - NUL_TERMINATOR_LENGTH;
outp = dest = g_malloc (outbuf_size);
while (!done && !have_error)
dest = g_realloc (dest, outbuf_size);
outp = dest + used;
- outbytes_remaining = outbuf_size - used - 1; /* -1 for nul */
+ outbytes_remaining = outbuf_size - used - NUL_TERMINATOR_LENGTH;
}
break;
case EILSEQ:
if (error)
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid byte sequence in conversion input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid byte sequence in conversion input"));
have_error = TRUE;
break;
default:
if (error)
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_FAILED,
- _("Error during conversion: %s"),
- g_strerror (errno));
+ {
+ int errsv = errno;
+
+ g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_FAILED,
+ _("Error during conversion: %s"),
+ g_strerror (errsv));
+ }
have_error = TRUE;
break;
}
}
}
- *outp = '\0';
+ memset (outp, 0, NUL_TERMINATOR_LENGTH);
if (bytes_read)
*bytes_read = p - str;
if (!have_error)
{
if (error)
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
- _("Partial character sequence at end of input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
+ _("Partial character sequence at end of input"));
have_error = TRUE;
}
}
* including fallback sequences for characters not representable
* in the output. Note that it is not guaranteed that the specification
* for the fallback sequences in @fallback will be honored. Some
- * systems may do a approximate conversion from @from_codeset
+ * systems may do an approximate conversion from @from_codeset
* to @to_codeset in their iconv() functions,
* in which case GLib will simply return that approximate conversion.
*
gssize len,
const gchar *to_codeset,
const gchar *from_codeset,
- gchar *fallback,
+ const gchar *fallback,
gsize *bytes_read,
gsize *bytes_written,
GError **error)
*/
p = utf8;
- outbuf_size = len + 1; /* + 1 for nul in case len == 1 */
- outbytes_remaining = outbuf_size - 1; /* -1 for nul */
+ outbuf_size = len + NUL_TERMINATOR_LENGTH;
+ outbytes_remaining = outbuf_size - NUL_TERMINATOR_LENGTH;
outp = dest = g_malloc (outbuf_size);
while (!done && !have_error)
dest = g_realloc (dest, outbuf_size);
outp = dest + used;
- outbytes_remaining = outbuf_size - used - 1; /* -1 for nul */
+ outbytes_remaining = outbuf_size - used - NUL_TERMINATOR_LENGTH;
break;
}
}
/* fall thru if p is NULL */
default:
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_FAILED,
- _("Error during conversion: %s"),
- g_strerror (errno));
+ {
+ int errsv = errno;
+
+ g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_FAILED,
+ _("Error during conversion: %s"),
+ g_strerror (errsv));
+ }
+
have_error = TRUE;
break;
}
/* Cleanup
*/
- *outp = '\0';
+ memset (outp, 0, NUL_TERMINATOR_LENGTH);
close_converter (cd);
if (bytes_written)
*bytes_written = 0;
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid byte sequence in conversion input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid byte sequence in conversion input"));
return NULL;
}
*
* Converts a string from UTF-8 to the encoding used for strings by
* the C runtime (usually the same as that used by the operating
- * system) in the <link linkend="setlocale">current locale</link>.
+ * system) in the <link linkend="setlocale">current locale</link>. On
+ * Windows this means the system codepage.
*
* Return value: The converted string, or %NULL on an error.
**/
"UTF-8", charset, bytes_read, bytes_written, error);
}
-#ifdef G_OS_WIN32
+#if defined (G_OS_WIN32) && !defined (_WIN64)
#undef g_filename_to_utf8
-/* Binary compatibility version. Not for newly compiled code. */
+/* Binary compatibility version. Not for newly compiled code. Also not needed for
+ * 64-bit versions as there should be no old deployed binaries that would use
+ * the old versions.
+ */
gchar*
g_filename_to_utf8 (const gchar *opsysstring,
charset, "UTF-8", bytes_read, bytes_written, error);
}
-#ifdef G_OS_WIN32
+#if defined (G_OS_WIN32) && !defined (_WIN64)
#undef g_filename_from_utf8
return result;
}
-#ifdef G_OS_WIN32
+#if defined (G_OS_WIN32) && !defined (_WIN64)
#undef g_filename_from_uri
!(g_utf8_validate (hostname, -1, NULL)
&& hostname_validate (hostname)))
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid hostname"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid hostname"));
return NULL;
}
return escaped_uri;
}
-#ifdef G_OS_WIN32
+#if defined (G_OS_WIN32) && !defined (_WIN64)
#undef g_filename_to_uri
return display_name;
}
-
-#define __G_CONVERT_C__
-#include "galiasdef.c"