*
* gconvert.c: Convert between character sets using iconv
* Copyright Red Hat Inc., 2000
- * Authors: Havoc Pennington <hp@redhat.com>, Owen Taylor <otaylor@redhat.com
+ * Authors: Havoc Pennington <hp@redhat.com>, Owen Taylor <otaylor@redhat.com>
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
*/
#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 "galias.h"
-#include "glib.h"
-#include "gprintfint.h"
-#include "gthreadinit.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
+
+/**
+ * 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)
{
- static GQuark quark;
- if (!quark)
- quark = g_quark_from_static_string ("g_convert_error");
-
- return quark;
+ return g_quark_from_static_string ("g_convert_error");
}
static gboolean
return FALSE;
}
-extern const char **_g_charset_get_aliases (const char *canonical_name) G_GNUC_INTERNAL;
+G_GNUC_INTERNAL extern const char **
+_g_charset_get_aliases (const char *canonical_name);
/**
* g_iconv_open:
*
* Return value: count of non-reversible conversions, or -1 on error
**/
-size_t
+gsize
g_iconv (GIConv converter,
gchar **inbuf,
gsize *inbytes_left,
}
+#ifdef NEED_ICONV_CACHE
+
#define ICONV_CACHE_SIZE (16)
struct _iconv_cache_bucket {
}
-/**
+/*
* iconv_cache_bucket_new:
* @key: cache key
* @cd: iconv descriptor
* Creates a new cache bucket, inserts it into the cache and
* increments the cache size.
*
+ * This assumes ownership of @key.
+ *
* Returns a pointer to the newly allocated cache bucket.
**/
static struct _iconv_cache_bucket *
-iconv_cache_bucket_new (const gchar *key, GIConv cd)
+iconv_cache_bucket_new (gchar *key, GIConv cd)
{
struct _iconv_cache_bucket *bucket;
bucket = g_new (struct _iconv_cache_bucket, 1);
- bucket->key = g_strdup (key);
+ bucket->key = key;
bucket->refcount = 1;
bucket->used = TRUE;
bucket->cd = cd;
}
-/**
+/*
* 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
GError **error)
{
struct _iconv_cache_bucket *bucket;
- gchar *key;
+ gchar *key, *dyn_key, auto_key[80];
GIConv cd;
+ gsize len_from_codeset, len_to_codeset;
/* create our key */
- key = g_alloca (strlen (from_codeset) + strlen (to_codeset) + 2);
- _g_sprintf (key, "%s:%s", from_codeset, to_codeset);
-
+ len_from_codeset = strlen (from_codeset);
+ len_to_codeset = strlen (to_codeset);
+ if (len_from_codeset + len_to_codeset + 2 < sizeof (auto_key))
+ {
+ key = auto_key;
+ dyn_key = NULL;
+ }
+ else
+ key = dyn_key = g_malloc (len_from_codeset + len_to_codeset + 2);
+ memcpy (key, from_codeset, len_from_codeset);
+ key[len_from_codeset] = ':';
+ strcpy (key + len_from_codeset + 1, to_codeset);
+
G_LOCK (iconv_cache_lock);
/* make sure the cache has been initialized */
bucket = g_hash_table_lookup (iconv_cache, key);
if (bucket)
{
+ g_free (dyn_key);
+
if (bucket->used)
{
cd = g_iconv_open (to_codeset, from_codeset);
else
{
cd = g_iconv_open (to_codeset, from_codeset);
- if (cd == (GIConv) -1)
- goto error;
+ if (cd == (GIConv) -1)
+ {
+ g_free (dyn_key);
+ goto error;
+ }
iconv_cache_expire_unused ();
-
- bucket = iconv_cache_bucket_new (key, cd);
+
+ bucket = iconv_cache_bucket_new (dyn_key ? dyn_key : g_strdup (key), cd);
}
g_hash_table_insert (iconv_open_hash, cd, bucket->key);
G_UNLOCK (iconv_cache_lock);
/* Something went wrong. */
- if (errno == EINVAL)
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_NO_CONVERSION,
- _("Conversion from character set '%s' to '%s' is not supported"),
- from_codeset, to_codeset);
- else
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_FAILED,
- _("Could not open converter from '%s' to '%s'"),
- from_codeset, to_codeset);
+ if (error)
+ {
+ if (errno == EINVAL)
+ g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_NO_CONVERSION,
+ _("Conversion from character set '%s' to '%s' is not supported"),
+ from_codeset, to_codeset);
+ else
+ g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_FAILED,
+ _("Could not open converter from '%s' to '%s'"),
+ from_codeset, to_codeset);
+ }
return cd;
}
return 0;
}
+#else /* !NEED_ICONV_CACHE */
-/**
- * g_convert:
- * @str: the string to convert
- * @len: the length of the string
- * @to_codeset: name of character set into which to convert @str
- * @from_codeset: character set of @str.
- * @bytes_read: location to store the number of bytes in the
- * input string that were successfully converted, or %NULL.
- * Even if the conversion was successful, this may be
- * less than @len if there were partial characters
- * at the end of the input. If the error
- * #G_CONVERT_ERROR_ILLEGAL_SEQUENCE occurs, the value
- * stored will the byte offset after the last valid
- * input sequence.
- * @bytes_written: the number of bytes stored in the output buffer (not
- * including the terminating nul).
- * @error: location to store the error occuring, or %NULL to ignore
- * errors. Any of the errors in #GConvertError may occur.
- *
- * Converts a string from one character set to another.
- *
- * Return value: If the conversion was successful, a newly allocated
- * nul-terminated string, which must be freed with
- * g_free(). Otherwise %NULL and @error will be set.
- **/
-gchar*
-g_convert (const gchar *str,
- gssize len,
- const gchar *to_codeset,
- const gchar *from_codeset,
- gsize *bytes_read,
- gsize *bytes_written,
- GError **error)
+static GIConv
+open_converter (const gchar *to_codeset,
+ const gchar *from_codeset,
+ GError **error)
{
- gchar *res;
GIConv cd;
-
- g_return_val_if_fail (str != NULL, NULL);
- g_return_val_if_fail (to_codeset != NULL, NULL);
- g_return_val_if_fail (from_codeset != NULL, NULL);
-
- cd = open_converter (to_codeset, from_codeset, error);
+
+ cd = g_iconv_open (to_codeset, from_codeset);
if (cd == (GIConv) -1)
{
- if (bytes_read)
- *bytes_read = 0;
-
- if (bytes_written)
- *bytes_written = 0;
-
- return NULL;
+ /* Something went wrong. */
+ if (error)
+ {
+ if (errno == EINVAL)
+ g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_NO_CONVERSION,
+ _("Conversion from character set '%s' to '%s' is not supported"),
+ from_codeset, to_codeset);
+ else
+ g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_FAILED,
+ _("Could not open converter from '%s' to '%s'"),
+ from_codeset, to_codeset);
+ }
}
-
- res = g_convert_with_iconv (str, len, cd,
- bytes_read, bytes_written,
- error);
- close_converter (cd);
+ return cd;
+}
- return res;
+static int
+close_converter (GIConv cd)
+{
+ if (cd == (GIConv) -1)
+ return 0;
+
+ return g_iconv_close (cd);
}
+#endif /* NEED_ICONV_CACHE */
+
/**
* g_convert_with_iconv:
* @str: the string to convert
- * @len: the length of the string
+ * @len: the length of the string, or -1 if the string is
+ * nul-terminated<footnoteref linkend="nul-unsafe"/>.
* @converter: conversion descriptor from g_iconv_open()
* @bytes_read: location to store the number of bytes in the
* input string that were successfully converted, or %NULL.
* @error: location to store the error occuring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
- * Converts a string from one character set to another.
+ * Converts a string from one character set to another.
+ *
+ * Note that you should use g_iconv() for streaming
+ * conversions<footnote id="streaming-state">
+ * <para>
+ * Despite the fact that @byes_read can return information about partial
+ * characters, the <literal>g_convert_...</literal> functions
+ * are not generally suitable for streaming. If the underlying converter
+ * being used maintains internal state, then this won't be preserved
+ * across successive calls to g_convert(), g_convert_with_iconv() or
+ * g_convert_with_fallback(). (An example of this is the GNU C converter
+ * for CP1255 which does not emit a base character until it knows that
+ * the next character is not a mark that could combine with the base
+ * character.)
+ * </para>
+ * </footnote>.
*
* Return value: If the conversion was successful, a newly allocated
* nul-terminated string, which must be freed with
gsize err;
gsize outbuf_size;
gboolean have_error = FALSE;
+ gboolean done = FALSE;
+ gboolean reset = FALSE;
- g_return_val_if_fail (str != NULL, NULL);
g_return_val_if_fail (converter != (GIConv) -1, NULL);
if (len < 0)
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);
- again:
-
- err = g_iconv (converter, (char **)&p, &inbytes_remaining, &outp, &outbytes_remaining);
-
- if (err == (size_t) -1)
+ while (!done && !have_error)
{
- switch (errno)
+ if (reset)
+ err = g_iconv (converter, NULL, &inbytes_remaining, &outp, &outbytes_remaining);
+ else
+ err = g_iconv (converter, (char **)&p, &inbytes_remaining, &outp, &outbytes_remaining);
+
+ if (err == (gsize) -1)
{
- case EINVAL:
- /* Incomplete text, do not report an error */
- break;
- case E2BIG:
- {
- size_t used = outp - dest;
-
- outbuf_size *= 2;
- dest = g_realloc (dest, outbuf_size);
+ switch (errno)
+ {
+ case EINVAL:
+ /* Incomplete text, do not report an error */
+ done = TRUE;
+ break;
+ case E2BIG:
+ {
+ gsize used = outp - dest;
+
+ outbuf_size *= 2;
+ dest = g_realloc (dest, outbuf_size);
- outp = dest + used;
- outbytes_remaining = outbuf_size - used - 1; /* -1 for nul */
-
- goto again;
- }
- case EILSEQ:
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid byte sequence in conversion input"));
- have_error = TRUE;
- break;
- default:
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_FAILED,
- _("Error during conversion: %s"),
- g_strerror (errno));
- have_error = TRUE;
- break;
+ outp = dest + used;
+ outbytes_remaining = outbuf_size - used - NUL_TERMINATOR_LENGTH;
+ }
+ break;
+ case EILSEQ:
+ if (error)
+ 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)
+ {
+ 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;
+ }
+ }
+ else
+ {
+ if (!reset)
+ {
+ /* call g_iconv with NULL inbuf to cleanup shift state */
+ reset = TRUE;
+ inbytes_remaining = 0;
+ }
+ else
+ done = TRUE;
}
}
- *outp = '\0';
+ memset (outp, 0, NUL_TERMINATOR_LENGTH);
if (bytes_read)
*bytes_read = p - str;
{
if (!have_error)
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
- _("Partial character sequence at end of input"));
+ if (error)
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
+ _("Partial character sequence at end of input"));
have_error = TRUE;
}
}
}
/**
+ * g_convert:
+ * @str: the string to convert
+ * @len: the length of the string, or -1 if the string is
+ * nul-terminated<footnote id="nul-unsafe">
+ <para>
+ Note that some encodings may allow nul bytes to
+ occur inside strings. In that case, using -1 for
+ the @len parameter is unsafe.
+ </para>
+ </footnote>.
+ * @to_codeset: name of character set into which to convert @str
+ * @from_codeset: character set of @str.
+ * @bytes_read: location to store the number of bytes in the
+ * input string that were successfully converted, or %NULL.
+ * Even if the conversion was successful, this may be
+ * less than @len if there were partial characters
+ * at the end of the input. If the error
+ * #G_CONVERT_ERROR_ILLEGAL_SEQUENCE occurs, the value
+ * stored will the byte offset after the last valid
+ * input sequence.
+ * @bytes_written: the number of bytes stored in the output buffer (not
+ * including the terminating nul).
+ * @error: location to store the error occuring, or %NULL to ignore
+ * errors. Any of the errors in #GConvertError may occur.
+ *
+ * Converts a string from one character set to another.
+ *
+ * Note that you should use g_iconv() for streaming
+ * conversions<footnoteref linkend="streaming-state"/>.
+ *
+ * Return value: If the conversion was successful, a newly allocated
+ * nul-terminated string, which must be freed with
+ * g_free(). Otherwise %NULL and @error will be set.
+ **/
+gchar*
+g_convert (const gchar *str,
+ gssize len,
+ const gchar *to_codeset,
+ const gchar *from_codeset,
+ gsize *bytes_read,
+ gsize *bytes_written,
+ GError **error)
+{
+ gchar *res;
+ GIConv cd;
+
+ g_return_val_if_fail (str != NULL, NULL);
+ g_return_val_if_fail (to_codeset != NULL, NULL);
+ g_return_val_if_fail (from_codeset != NULL, NULL);
+
+ cd = open_converter (to_codeset, from_codeset, error);
+
+ if (cd == (GIConv) -1)
+ {
+ if (bytes_read)
+ *bytes_read = 0;
+
+ if (bytes_written)
+ *bytes_written = 0;
+
+ return NULL;
+ }
+
+ res = g_convert_with_iconv (str, len, cd,
+ bytes_read, bytes_written,
+ error);
+
+ close_converter (cd);
+
+ return res;
+}
+
+/**
* g_convert_with_fallback:
* @str: the string to convert
- * @len: the length of the string
+ * @len: the length of the string, or -1 if the string is
+ * nul-terminated<footnoteref linkend="nul-unsafe"/>.
* @to_codeset: name of character set into which to convert @str
* @from_codeset: character set of @str.
* @fallback: UTF-8 string to use in place of character not
- * present in the target encoding. (This must be
- * in the target encoding), if %NULL, characters
- * not in the target encoding will be represented
- * as Unicode escapes \uxxxx or \Uxxxxyyyy.
+ * present in the target encoding. (The string must be
+ * representable in the target encoding).
+ If %NULL, characters not in the target encoding will
+ be represented as Unicode escapes \uxxxx or \Uxxxxyyyy.
* @bytes_read: location to store the number of bytes in the
* input string that were successfully converted, or %NULL.
* Even if the conversion was successful, this may be
* 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.
*
+ * Note that you should use g_iconv() for streaming
+ * conversions<footnoteref linkend="streaming-state"/>.
+ *
* Return value: If the conversion was successful, a newly allocated
* nul-terminated string, which must be freed with
* g_free(). Otherwise %NULL and @error will be set.
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)
{
- size_t inbytes_tmp = inbytes_remaining;
+ gsize inbytes_tmp = inbytes_remaining;
err = g_iconv (cd, (char **)&p, &inbytes_tmp, &outp, &outbytes_remaining);
inbytes_remaining = inbytes_tmp;
- if (err == (size_t) -1)
+ if (err == (gsize) -1)
{
switch (errno)
{
break;
case E2BIG:
{
- size_t used = outp - dest;
+ gsize used = outp - dest;
outbuf_size *= 2;
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;
}
have_error = TRUE;
break;
}
- else
+ else if (p)
{
if (!fallback)
{
save_inbytes = inbytes_remaining - (save_p - p);
p = insert_str;
inbytes_remaining = strlen (p);
+ break;
}
- 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;
}
inbytes_remaining = save_inbytes;
save_p = NULL;
}
+ else if (p)
+ {
+ /* call g_iconv with NULL inbuf to cleanup shift state */
+ p = NULL;
+ inbytes_remaining = 0;
+ }
else
done = TRUE;
}
/* 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;
}
/**
* g_locale_to_utf8:
- * @opsysstring: a string in the encoding of the current locale
+ * @opsysstring: a string in the encoding of the current locale. On Windows
+ * this means the system codepage.
* @len: the length of the string, or -1 if the string is
- * nul-terminated.
+ * nul-terminated<footnoteref linkend="nul-unsafe"/>.
* @bytes_read: location to store the number of bytes in the
* input string that were successfully converted, or %NULL.
* Even if the conversion was successful, this may be
*
* Converts a string which is in the encoding used for strings by
* the C runtime (usually the same as that used by the operating
- * system) in the current locale into a UTF-8 string.
+ * system) in the <link linkend="setlocale">current locale</link> into a
+ * UTF-8 string.
*
* Return value: The converted string, or %NULL on an error.
**/
* g_locale_from_utf8:
* @utf8string: a UTF-8 encoded string
* @len: the length of the string, or -1 if the string is
- * nul-terminated.
+ * nul-terminated<footnoteref linkend="nul-unsafe"/>.
* @bytes_read: location to store the number of bytes in the
* input string that were successfully converted, or %NULL.
* Even if the conversion was successful, this may be
*
* 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 current locale.
+ * 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.
**/
struct _GFilenameCharsetCache {
gboolean is_utf8;
gchar *charset;
- gchar *filename_charset;
+ gchar **filename_charsets;
};
static void
{
GFilenameCharsetCache *cache = data;
g_free (cache->charset);
- g_free (cache->filename_charset);
+ g_strfreev (cache->filename_charsets);
g_free (cache);
}
-/*
- * get_filename_charset:
- * @charset: return location for the name of the filename encoding
+/**
+ * g_get_filename_charsets:
+ * @charsets: return location for the %NULL-terminated list of encoding names
*
- * Determines the preferred character set used for filenames by
- * consulting the environment variables G_FILENAME_ENCODING and
- * G_BROKEN_FILENAMES.
+ * Determines the preferred character sets used for filenames.
+ * The first character set from the @charsets is the filename encoding, the
+ * subsequent character sets are used when trying to generate a displayable
+ * representation of a filename, see g_filename_display_name().
*
- * G_FILENAME_ENCODING may be set to a comma-separated list of character
- * set names. The special token "@locale" is taken to mean the character set
- * for the current locale. The first character set from the list is taken
- * as the filename encoding.
- * If G_FILENAME_ENCODING is not set, but G_BROKEN_FILENAMES is, the
- * character set of the current locale is taken as the filename encoding.
+ * On Unix, the character sets are determined by consulting the
+ * environment variables <envar>G_FILENAME_ENCODING</envar> and
+ * <envar>G_BROKEN_FILENAMES</envar>. On Windows, the character set
+ * used in the GLib API is always UTF-8 and said environment variables
+ * have no effect.
*
- * The returned @charset belongs to GLib and must not be freed.
+ * <envar>G_FILENAME_ENCODING</envar> may be set to a comma-separated list
+ * of character set names. The special token "@locale" is taken to
+ * mean the character set for the <link linkend="setlocale">current
+ * locale</link>. If <envar>G_FILENAME_ENCODING</envar> is not set, but
+ * <envar>G_BROKEN_FILENAMES</envar> is, the character set of the current
+ * locale is taken as the filename encoding. If neither environment variable
+ * is set, UTF-8 is taken as the filename encoding, but the character
+ * set of the current locale is also put in the list of encodings.
+ *
+ * The returned @charsets belong to GLib and must not be freed.
*
* Note that on Unix, regardless of the locale character set or
- * G_FILENAME_ENCODING value, the actual file names present on a
- * system might be in any random encoding or just gibberish.
+ * <envar>G_FILENAME_ENCODING</envar> value, the actual file names present
+ * on a system might be in any random encoding or just gibberish.
*
- * Return value: %TRUE
- * if the charset used for filename is UTF-8.
+ * Return value: %TRUE if the filename encoding is UTF-8.
+ *
+ * Since: 2.6
*/
-static gboolean
-get_filename_charset (const gchar **filename_charset)
+gboolean
+g_get_filename_charsets (G_CONST_RETURN gchar ***filename_charsets)
{
static GStaticPrivate cache_private = G_STATIC_PRIVATE_INIT;
GFilenameCharsetCache *cache = g_static_private_get (&cache_private);
const gchar *charset;
-
+
if (!cache)
{
cache = g_new0 (GFilenameCharsetCache, 1);
if (!(cache->charset && strcmp (cache->charset, charset) == 0))
{
const gchar *new_charset;
- gchar *p, *q;
+ gchar *p;
+ gint i;
g_free (cache->charset);
- g_free (cache->filename_charset);
+ g_strfreev (cache->filename_charsets);
cache->charset = g_strdup (charset);
p = getenv ("G_FILENAME_ENCODING");
- if (p != NULL)
+ if (p != NULL && p[0] != '\0')
{
- q = strchr (p, ',');
- if (!q)
- q = p + strlen (p);
+ cache->filename_charsets = g_strsplit (p, ",", 0);
+ cache->is_utf8 = (strcmp (cache->filename_charsets[0], "UTF-8") == 0);
- if (strncmp ("@locale", p, q - p) == 0)
- {
- cache->is_utf8 = g_get_charset (&new_charset);
- cache->filename_charset = g_strdup (new_charset);
- }
- else
+ for (i = 0; cache->filename_charsets[i]; i++)
{
- cache->filename_charset = g_strndup (p, q - p);
- cache->is_utf8 = (strcmp (cache->filename_charset, "UTF-8") == 0);
+ if (strcmp ("@locale", cache->filename_charsets[i]) == 0)
+ {
+ g_get_charset (&new_charset);
+ g_free (cache->filename_charsets[i]);
+ cache->filename_charsets[i] = g_strdup (new_charset);
+ }
}
}
else if (getenv ("G_BROKEN_FILENAMES") != NULL)
{
+ cache->filename_charsets = g_new0 (gchar *, 2);
cache->is_utf8 = g_get_charset (&new_charset);
- cache->filename_charset = g_strdup (new_charset);
+ cache->filename_charsets[0] = g_strdup (new_charset);
}
else
{
- cache->filename_charset = g_strdup ("UTF-8");
+ cache->filename_charsets = g_new0 (gchar *, 3);
cache->is_utf8 = TRUE;
+ cache->filename_charsets[0] = g_strdup ("UTF-8");
+ if (!g_get_charset (&new_charset))
+ cache->filename_charsets[1] = g_strdup (new_charset);
}
}
- if (filename_charset)
- *filename_charset = cache->filename_charset;
+ if (filename_charsets)
+ *filename_charsets = (const gchar **)cache->filename_charsets;
return cache->is_utf8;
}
#else /* G_PLATFORM_WIN32 */
-static gboolean
-get_filename_charset (const gchar **filename_charset)
+gboolean
+g_get_filename_charsets (G_CONST_RETURN gchar ***filename_charsets)
{
+ static const gchar *charsets[] = {
+ "UTF-8",
+ NULL
+ };
+
#ifdef G_OS_WIN32
/* On Windows GLib pretends that the filename charset is UTF-8 */
- if (filename_charset)
- *filename_charset = "UTF-8";
+ if (filename_charsets)
+ *filename_charsets = charsets;
+
return TRUE;
#else
+ gboolean result;
+
/* Cygwin works like before */
- g_get_charset (filename_charset);
- return FALSE;
+ result = g_get_charset (&(charsets[0]));
+
+ if (filename_charsets)
+ *filename_charsets = charsets;
+
+ return result;
#endif
}
-#ifdef G_OS_WIN32
+#endif /* G_PLATFORM_WIN32 */
static gboolean
-old_get_filename_charset (const gchar **filename_charset)
+get_filename_charset (const gchar **filename_charset)
{
- g_get_charset (filename_charset);
- return FALSE;
-}
-
-#endif
+ const gchar **charsets;
+ gboolean is_utf8;
+
+ is_utf8 = g_get_filename_charsets (&charsets);
-#endif /* G_PLATFORM_WIN32 */
+ if (filename_charset)
+ *filename_charset = charsets[0];
+
+ return is_utf8;
+}
/* This is called from g_thread_init(). It's used to
* initialize some static data in a threadsafe way.
void
_g_convert_thread_init (void)
{
- const gchar *dummy;
- (void) get_filename_charset (&dummy);
+ const gchar **dummy;
+ (void) g_get_filename_charsets (&dummy);
}
/**
* g_filename_to_utf8:
* @opsysstring: a string in the encoding for filenames
* @len: the length of the string, or -1 if the string is
- * nul-terminated.
+ * nul-terminated<footnoteref linkend="nul-unsafe"/>.
* @bytes_read: location to store the number of bytes in the
* input string that were successfully converted, or %NULL.
* Even if the conversion was successful, this may be
* @error: location to store the error occuring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
- * Converts a string which is in the encoding used for filenames
- * into a UTF-8 string.
+ * Converts a string which is in the encoding used by GLib for
+ * filenames into a UTF-8 string. Note that on Windows GLib uses UTF-8
+ * for filenames; on other platforms, this function indirectly depends on
+ * the <link linkend="setlocale">current locale</link>.
*
* 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,
{
const gchar *charset;
- if (old_get_filename_charset (&charset))
+ if (g_get_charset (&charset))
return strdup_len (opsysstring, len, bytes_read, bytes_written, error);
else
return g_convert (opsysstring, len,
* @error: location to store the error occuring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
- * Converts a string from UTF-8 to the encoding used for filenames.
+ * Converts a string from UTF-8 to the encoding GLib uses for
+ * filenames. Note that on Windows GLib uses UTF-8 for filenames;
+ * on other platforms, this function indirectly depends on the
+ * <link linkend="setlocale">current locale</link>.
*
* Return value: The converted string, or %NULL on an error.
**/
charset, "UTF-8", bytes_read, bytes_written, error);
}
-#ifdef G_OS_WIN32
+#if defined (G_OS_WIN32) && !defined (_WIN64)
#undef g_filename_from_utf8
{
const gchar *charset;
- if (old_get_filename_charset (&charset))
+ if (g_get_charset (&charset))
return strdup_len (utf8string, len, bytes_read, bytes_written, error);
else
return g_convert (utf8string, len,
return result;
}
+#if defined (G_OS_WIN32) && !defined (_WIN64)
+
+#undef g_filename_from_uri
+
+gchar *
+g_filename_from_uri (const gchar *uri,
+ gchar **hostname,
+ GError **error)
+{
+ gchar *utf8_filename;
+ gchar *retval = NULL;
+
+ utf8_filename = g_filename_from_uri_utf8 (uri, hostname, error);
+ if (utf8_filename)
+ {
+ retval = g_locale_from_utf8 (utf8_filename, -1, NULL, NULL, error);
+ g_free (utf8_filename);
+ }
+ return retval;
+}
+
+#endif
+
/**
* g_filename_to_uri:
- * @filename: an absolute filename specified in the encoding
- * used for filenames by the operating system.
+ * @filename: an absolute filename specified in the GLib file name encoding,
+ * which is the on-disk file name bytes on Unix, and UTF-8 on
+ * Windows
* @hostname: A UTF-8 encoded hostname, or %NULL for none.
* @error: location to store the error occuring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
- * Converts an absolute filename to an escaped ASCII-encoded URI.
+ * Converts an absolute filename to an escaped ASCII-encoded URI, with the path
+ * component following Section 3.3. of RFC 2396.
*
* Return value: a newly-allocated string holding the resulting
* URI, or %NULL on an error.
**/
gchar *
-g_filename_to_uri (const gchar *filename,
- const gchar *hostname,
- GError **error)
+g_filename_to_uri (const gchar *filename,
+ const gchar *hostname,
+ GError **error)
{
char *escaped_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;
}
+#if defined (G_OS_WIN32) && !defined (_WIN64)
+
+#undef g_filename_to_uri
+
+gchar *
+g_filename_to_uri (const gchar *filename,
+ const gchar *hostname,
+ GError **error)
+{
+ gchar *utf8_filename;
+ gchar *retval = NULL;
+
+ utf8_filename = g_locale_to_utf8 (filename, -1, NULL, NULL, error);
+
+ if (utf8_filename)
+ {
+ retval = g_filename_to_uri_utf8 (utf8_filename, hostname, error);
+ g_free (utf8_filename);
+ }
+
+ return retval;
+}
+
+#endif
+
/**
* g_uri_list_extract_uris:
* @uri_list: an URI list
return result;
}
+
+/**
+ * g_filename_display_basename:
+ * @filename: an absolute pathname in the GLib file name encoding
+ *
+ * Returns the display basename for the particular filename, guaranteed
+ * to be valid UTF-8. The display name might not be identical to the filename,
+ * for instance there might be problems converting it to UTF-8, and some files
+ * can be translated in the display.
+ *
+ * If GLib can not make sense of the encoding of @filename, as a last resort it
+ * replaces unknown characters with U+FFFD, the Unicode replacement character.
+ * You can search the result for the UTF-8 encoding of this character (which is
+ * "\357\277\275" in octal notation) to find out if @filename was in an invalid
+ * encoding.
+ *
+ * You must pass the whole absolute pathname to this functions so that
+ * translation of well known locations can be done.
+ *
+ * This function is preferred over g_filename_display_name() if you know the
+ * whole path, as it allows translation.
+ *
+ * Return value: a newly allocated string containing
+ * a rendition of the basename of the filename in valid UTF-8
+ *
+ * Since: 2.6
+ **/
+gchar *
+g_filename_display_basename (const gchar *filename)
+{
+ char *basename;
+ char *display_name;
+
+ g_return_val_if_fail (filename != NULL, NULL);
+
+ basename = g_path_get_basename (filename);
+ display_name = g_filename_display_name (basename);
+ g_free (basename);
+ return display_name;
+}
+
+/**
+ * g_filename_display_name:
+ * @filename: a pathname hopefully in the GLib file name encoding
+ *
+ * Converts a filename into a valid UTF-8 string. The conversion is
+ * not necessarily reversible, so you should keep the original around
+ * and use the return value of this function only for display purposes.
+ * Unlike g_filename_to_utf8(), the result is guaranteed to be non-%NULL
+ * even if the filename actually isn't in the GLib file name encoding.
+ *
+ * If GLib can not make sense of the encoding of @filename, as a last resort it
+ * replaces unknown characters with U+FFFD, the Unicode replacement character.
+ * You can search the result for the UTF-8 encoding of this character (which is
+ * "\357\277\275" in octal notation) to find out if @filename was in an invalid
+ * encoding.
+ *
+ * If you know the whole pathname of the file you should use
+ * g_filename_display_basename(), since that allows location-based
+ * translation of filenames.
+ *
+ * Return value: a newly allocated string containing
+ * a rendition of the filename in valid UTF-8
+ *
+ * Since: 2.6
+ **/
+gchar *
+g_filename_display_name (const gchar *filename)
+{
+ gint i;
+ const gchar **charsets;
+ gchar *display_name = NULL;
+ gboolean is_utf8;
+
+ is_utf8 = g_get_filename_charsets (&charsets);
+
+ if (is_utf8)
+ {
+ if (g_utf8_validate (filename, -1, NULL))
+ display_name = g_strdup (filename);
+ }
+
+ if (!display_name)
+ {
+ /* Try to convert from the filename charsets to UTF-8.
+ * Skip the first charset if it is UTF-8.
+ */
+ for (i = is_utf8 ? 1 : 0; charsets[i]; i++)
+ {
+ display_name = g_convert (filename, -1, "UTF-8", charsets[i],
+ NULL, NULL, NULL);
+
+ if (display_name)
+ break;
+ }
+ }
+
+ /* if all conversions failed, we replace invalid UTF-8
+ * by a question mark
+ */
+ if (!display_name)
+ display_name = _g_utf8_make_valid (filename);
+
+ return display_name;
+}