*
* 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#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 "gthreadinit.h"
+#ifdef G_OS_WIN32
+#include "win_iconv.c"
+#endif
#ifdef G_PLATFORM_WIN32
#define STRICT
#undef STRICT
#endif
+#include "gconvert.h"
+
+#include "gcharsetprivate.h"
+#include "gslist.h"
+#include "gstrfuncs.h"
+#include "gtestutils.h"
+#include "gthread.h"
+#include "gunicode.h"
+#include "gfileutils.h"
+
#include "glibintl.h"
#if defined(USE_LIBICONV_GNU) && !defined (_LIBICONV_H)
#error GNU libiconv in use but included iconv.h not from libiconv
#endif
-#if !defined(USE_LIBICONV_GNU) && defined (_LIBICONV_H)
+#if !defined(USE_LIBICONV_GNU) && defined (_LIBICONV_H) \
+ && !defined (__APPLE_CC__) && !defined (__LP_64__)
#error GNU libiconv not in use but included iconv.h is from libiconv
#endif
-#include "galias.h"
-GQuark
-g_convert_error_quark (void)
-{
- static GQuark quark;
- if (!quark)
- quark = g_quark_from_static_string ("g_convert_error");
+/**
+ * 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.
+ *
+ * ## File Name Encodings
+ *
+ * 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
+ * "Presentación.sxi". If the application which created it uses
+ * ISO-8859-1 for its encoding,
+ * |[
+ * 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
+ * ]|
+ * However, if the application use UTF-8, the actual file name on
+ * disk would look like this:
+ * |[
+ * 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
+ * ]|
+ * 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() or from g_dir_read_name(), and you wish
+ * to display the file name to the user, you will 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()
+ * or fopen().
+ *
+ * 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 [`G_FILENAME_ENCODING`][G_FILENAME_ENCODING]
+ * environment variable. For example, if your installation uses
+ * ISO-8859-1 for file names, you can put this in your `~/.profile`
+ * |[
+ * export G_FILENAME_ENCODING=ISO-8859-1
+ * ]|
+ * 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 `G_FILENAME_ENCODING` to UTF-8 and vice-versa. This
+ * [diagram][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.
+ *
+ * ## Conversion between file name encodings # {#file-name-encodings-diagram)
+ *
+ * 
+ *
+ * ## Checklist for Application Writers
+ *
+ * This section is a practical summary of the detailed
+
+ * things to do to make sure your applications process file
+ * name encodings correctly.
+ *
+ * 1. If you get a file name from the file system from a function
+ * such as readdir() or gtk_file_chooser_get_filename(), you do
+ * not need to do any conversion to pass that file name to
+ * functions like open(), rename(), or fopen() -- those are "raw"
+ * file names which the file system understands.
+ *
+ * 2. 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 "Unknown file name". Do not 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 `G_FILENAME_ENCODING`
+ * environment variable even though he has files whose names are
+ * not encoded in UTF-8.
+ *
+ * 3. 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(). If conversion fails, ask the
+ * user to enter a different file name. This can happen if the user
+ * types Japanese characters when `G_FILENAME_ENCODING` is set to
+ * `ISO-8859-1`, for example.
+ */
- return quark;
-}
+/* 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
+
+G_DEFINE_QUARK (g_convert_error, g_convert_error)
static gboolean
try_conversion (const char *to_codeset,
return FALSE;
}
-extern const char **_g_charset_get_aliases (const char *canonical_name) G_GNUC_INTERNAL;
-
/**
* g_iconv_open:
* @to_codeset: destination codeset
* GLib provides g_convert() and g_locale_to_utf8() which are likely
* more convenient than the raw iconv wrappers.
*
- * Return value: a "conversion descriptor", or (GIConv)-1 if
+ * Returns: a "conversion descriptor", or (GIConv)-1 if
* opening the converter failed.
**/
GIConv
* GLib provides g_convert() and g_locale_to_utf8() which are likely
* more convenient than the raw iconv wrappers.
*
- * Return value: count of non-reversible conversions, or -1 on error
+ * Returns: count of non-reversible conversions, or -1 on error
**/
-size_t
+gsize
g_iconv (GIConv converter,
gchar **inbuf,
gsize *inbytes_left,
* GLib provides g_convert() and g_locale_to_utf8() which are likely
* more convenient than the raw iconv wrappers.
*
- * Return value: -1 on error, 0 on success
+ * Returns: -1 on error, 0 on success
**/
gint
g_iconv_close (GIConv converter)
return iconv_close (cd);
}
-
-#define ICONV_CACHE_SIZE (16)
-
-struct _iconv_cache_bucket {
- gchar *key;
- guint32 refcount;
- gboolean used;
- GIConv cd;
-};
-
-static GList *iconv_cache_list;
-static GHashTable *iconv_cache;
-static GHashTable *iconv_open_hash;
-static guint iconv_cache_size = 0;
-G_LOCK_DEFINE_STATIC (iconv_cache_lock);
-
-/* caller *must* hold the iconv_cache_lock */
-static void
-iconv_cache_init (void)
-{
- static gboolean initialized = FALSE;
-
- if (initialized)
- return;
-
- iconv_cache_list = NULL;
- iconv_cache = g_hash_table_new (g_str_hash, g_str_equal);
- iconv_open_hash = g_hash_table_new (g_direct_hash, g_direct_equal);
-
- initialized = TRUE;
-}
-
-
-/**
- * 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.
- *
- * Returns a pointer to the newly allocated cache bucket.
- **/
-static struct _iconv_cache_bucket *
-iconv_cache_bucket_new (const gchar *key, GIConv cd)
-{
- struct _iconv_cache_bucket *bucket;
-
- bucket = g_new (struct _iconv_cache_bucket, 1);
- bucket->key = g_strdup (key);
- bucket->refcount = 1;
- bucket->used = TRUE;
- bucket->cd = cd;
-
- g_hash_table_insert (iconv_cache, bucket->key, bucket);
-
- /* FIXME: if we sorted the list so items with few refcounts were
- first, then we could expire them faster in iconv_cache_expire_unused () */
- iconv_cache_list = g_list_prepend (iconv_cache_list, bucket);
-
- iconv_cache_size++;
-
- return bucket;
-}
-
-
-/**
- * iconv_cache_bucket_expire:
- * @node: cache bucket's node
- * @bucket: cache bucket
- *
- * Expires a single cache bucket @bucket. This should only ever be
- * called on a bucket that currently has no used iconv descriptors
- * open.
- *
- * @node is not a required argument. If @node is not supplied, we
- * search for it ourselves.
- **/
-static void
-iconv_cache_bucket_expire (GList *node, struct _iconv_cache_bucket *bucket)
-{
- g_hash_table_remove (iconv_cache, bucket->key);
-
- if (node == NULL)
- node = g_list_find (iconv_cache_list, bucket);
-
- g_assert (node != NULL);
-
- if (node->prev)
- {
- node->prev->next = node->next;
- if (node->next)
- node->next->prev = node->prev;
- }
- else
- {
- iconv_cache_list = node->next;
- if (node->next)
- node->next->prev = NULL;
- }
-
- g_list_free_1 (node);
-
- g_free (bucket->key);
- g_iconv_close (bucket->cd);
- g_free (bucket);
-
- iconv_cache_size--;
-}
-
-
-/**
- * iconv_cache_expire_unused:
- *
- * Expires as many unused cache buckets as it needs to in order to get
- * the total number of buckets < ICONV_CACHE_SIZE.
- **/
-static void
-iconv_cache_expire_unused (void)
-{
- struct _iconv_cache_bucket *bucket;
- GList *node, *next;
-
- node = iconv_cache_list;
- while (node && iconv_cache_size >= ICONV_CACHE_SIZE)
- {
- next = node->next;
-
- bucket = node->data;
- if (bucket->refcount == 0)
- iconv_cache_bucket_expire (node, bucket);
-
- node = next;
- }
-}
-
static GIConv
open_converter (const gchar *to_codeset,
const gchar *from_codeset,
GError **error)
{
- struct _iconv_cache_bucket *bucket;
- gchar *key;
GIConv cd;
-
- /* create our key */
- key = g_alloca (strlen (from_codeset) + strlen (to_codeset) + 2);
- _g_sprintf (key, "%s:%s", from_codeset, to_codeset);
-
- G_LOCK (iconv_cache_lock);
-
- /* make sure the cache has been initialized */
- iconv_cache_init ();
-
- bucket = g_hash_table_lookup (iconv_cache, key);
- if (bucket)
- {
- if (bucket->used)
- {
- cd = g_iconv_open (to_codeset, from_codeset);
- if (cd == (GIConv) -1)
- goto error;
- }
- else
- {
- /* Apparently iconv on Solaris <= 7 segfaults if you pass in
- * NULL for anything but inbuf; work around that. (NULL outbuf
- * or NULL *outbuf is allowed by Unix98.)
- */
- gsize inbytes_left = 0;
- gchar *outbuf = NULL;
- gsize outbytes_left = 0;
-
- cd = bucket->cd;
- bucket->used = TRUE;
-
- /* reset the descriptor */
- g_iconv (cd, NULL, &inbytes_left, &outbuf, &outbytes_left);
- }
-
- bucket->refcount++;
- }
- else
- {
- cd = g_iconv_open (to_codeset, from_codeset);
- if (cd == (GIConv) -1)
- goto error;
-
- iconv_cache_expire_unused ();
-
- bucket = iconv_cache_bucket_new (key, cd);
- }
-
- g_hash_table_insert (iconv_open_hash, cd, bucket->key);
-
- G_UNLOCK (iconv_cache_lock);
-
- return cd;
-
- error:
-
- G_UNLOCK (iconv_cache_lock);
-
- /* Something went wrong. */
- if (error)
+
+ cd = g_iconv_open (to_codeset, from_codeset);
+
+ if (cd == (GIConv) -1)
{
- 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);
+ /* 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);
+ }
}
return cd;
}
static int
-close_converter (GIConv converter)
+close_converter (GIConv cd)
{
- struct _iconv_cache_bucket *bucket;
- const gchar *key;
- GIConv cd;
-
- cd = converter;
-
if (cd == (GIConv) -1)
return 0;
- G_LOCK (iconv_cache_lock);
-
- key = g_hash_table_lookup (iconv_open_hash, cd);
- if (key)
- {
- g_hash_table_remove (iconv_open_hash, cd);
-
- bucket = g_hash_table_lookup (iconv_cache, key);
- g_assert (bucket);
-
- bucket->refcount--;
-
- if (cd == bucket->cd)
- bucket->used = FALSE;
- else
- g_iconv_close (cd);
-
- if (!bucket->refcount && iconv_cache_size > ICONV_CACHE_SIZE)
- {
- /* expire this cache bucket */
- iconv_cache_bucket_expire (NULL, bucket);
- }
- }
- else
- {
- G_UNLOCK (iconv_cache_lock);
-
- g_warning ("This iconv context wasn't opened using open_converter");
-
- return g_iconv_close (converter);
- }
-
- G_UNLOCK (iconv_cache_lock);
-
- return 0;
+ return g_iconv_close (cd);
}
/**
* g_convert_with_iconv:
* @str: the string to convert
- * @len: the length of the string, or -1 if the string is
- * nul-terminated<footnoteref linkend="nul-unsafe"/>.
+ * @len: the length of the string in bytes, or -1 if the string is
+ * nul-terminated (Note that some encodings may allow nul
+ * bytes to occur inside strings. In that case, using -1
+ * for the @len parameter is 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.
* 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
+ * @error: location to store the error occurring, 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<footnote id="streaming-state">
- * <para>
+ * Note that you should use g_iconv() for streaming conversions.
* 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>.
+ * characters, the g_convert_... functions are not generally suitable
+ * for streaming. If the underlying converter 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.)
*
- * Return value: If the conversion was successful, a newly allocated
+ * Returns: 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 *dest;
gchar *outp;
const gchar *p;
- const gchar *shift_p = NULL;
gsize inbytes_remaining;
gsize outbytes_remaining;
gsize err;
gsize outbuf_size;
gboolean have_error = FALSE;
gboolean done = FALSE;
+ gboolean reset = FALSE;
g_return_val_if_fail (converter != (GIConv) -1, NULL);
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)
{
- err = g_iconv (converter, (char **)&p, &inbytes_remaining, &outp, &outbytes_remaining);
+ 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 == (size_t) -1)
+ if (err == (gsize) -1)
{
switch (errno)
{
case EINVAL:
/* Incomplete text, do not report an error */
+ done = TRUE;
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;
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;
}
}
else
{
- if (!shift_p)
+ if (!reset)
{
/* call g_iconv with NULL inbuf to cleanup shift state */
- shift_p = p;
- p = NULL;
+ reset = TRUE;
inbytes_remaining = 0;
}
else
}
}
- if (shift_p)
- p = shift_p;
-
- *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;
}
}
/**
* 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>.
+ * @len: the length of the string in bytes, or -1 if the string is
+ * nul-terminated (Note that some encodings may allow nul
+ * bytes to occur inside strings. In that case, using -1
+ * for the @len parameter is unsafe)
* @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
+ * @bytes_read: (out): 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
* #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
+ * @bytes_written: (out): 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
+ * @error: location to store the error occurring, 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"/>.
+ * Note that you should use g_iconv() for streaming conversions.
+ * Despite the fact that @byes_read can return information about partial
+ * characters, the g_convert_... functions are not generally suitable
+ * for streaming. If the underlying converter 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.)
+ *
+ * Using extensions such as "//TRANSLIT" may not work (or may not work
+ * well) on many platforms. Consider using g_str_to_ascii() instead.
*
- * Return value: If the conversion was successful, a newly allocated
+ * Returns: 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.
**/
/**
* g_convert_with_fallback:
* @str: the string to convert
- * @len: the length of the string, or -1 if the string is
- * nul-terminated<footnoteref linkend="nul-unsafe"/>.
+ * @len: the length of the string in bytes, or -1 if the string is
+ * nul-terminated (Note that some encodings may allow nul
+ * bytes to occur inside strings. In that case, using -1
+ * for the @len parameter is 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
* at the end of the input.
* @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
+ * @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
* Converts a string from one character set to another, possibly
* 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"/>.
+ * Note that you should use g_iconv() for streaming conversions.
+ * Despite the fact that @byes_read can return information about partial
+ * characters, the g_convert_... functions are not generally suitable
+ * for streaming. If the underlying converter 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.)
*
- * Return value: If the conversion was successful, a newly allocated
+ * Returns: 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;
}
}
/* 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;
}
* @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<footnoteref linkend="nul-unsafe"/>.
+ * nul-terminated (Note that some encodings may allow nul
+ * bytes to occur inside strings. In that case, using -1
+ * for the @len parameter is 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
* 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
+ * @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
* 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 [current locale][setlocale] into a UTF-8 string.
*
- * Return value: The converted string, or %NULL on an error.
+ * Returns: A newly-allocated buffer containing the converted string,
+ * or %NULL on an error, and error will be set.
**/
gchar *
g_locale_to_utf8 (const gchar *opsysstring,
* g_locale_from_utf8:
* @utf8string: a UTF-8 encoded string
* @len: the length of the string, or -1 if the string is
- * nul-terminated<footnoteref linkend="nul-unsafe"/>.
+ * nul-terminated (Note that some encodings may allow nul
+ * bytes to occur inside strings. In that case, using -1
+ * for the @len parameter is 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
* 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
+ * @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
* 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 [current locale][setlocale]. On Windows this means
+ * the system codepage.
*
- * Return value: The converted string, or %NULL on an error.
+ * Returns: A newly-allocated buffer containing the converted string,
+ * or %NULL on an error, and error will be set.
**/
gchar *
g_locale_from_utf8 (const gchar *utf8string,
* representation of a filename, see g_filename_display_name().
*
* 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.
+ * environment variables `G_FILENAME_ENCODING` and `G_BROKEN_FILENAMES`.
+ * On Windows, the character set used in the GLib API is always UTF-8
+ * and said environment variables have no effect.
*
- * <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 current locale. 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.
+ * `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][setlocale].
+ * 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. 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
- * <envar>G_FILENAME_ENCODING</envar> value, the actual file names present on a
- * system might be in any random encoding or just gibberish.
+ * `G_FILENAME_ENCODING` value, the actual file names present
+ * on a system might be in any random encoding or just gibberish.
*
- * Return value: %TRUE if the filename encoding is UTF-8.
+ * Returns: %TRUE if the filename encoding is UTF-8.
*
* Since: 2.6
*/
gboolean
-g_get_filename_charsets (G_CONST_RETURN gchar ***filename_charsets)
+g_get_filename_charsets (const gchar ***filename_charsets)
{
- static GStaticPrivate cache_private = G_STATIC_PRIVATE_INIT;
- GFilenameCharsetCache *cache = g_static_private_get (&cache_private);
+ static GPrivate cache_private = G_PRIVATE_INIT (filename_charset_cache_free);
+ GFilenameCharsetCache *cache = g_private_get (&cache_private);
const gchar *charset;
if (!cache)
{
cache = g_new0 (GFilenameCharsetCache, 1);
- g_static_private_set (&cache_private, cache, filename_charset_cache_free);
+ g_private_set (&cache_private, cache);
}
g_get_charset (&charset);
#else /* G_PLATFORM_WIN32 */
gboolean
-g_get_filename_charsets (G_CONST_RETURN gchar ***filename_charsets)
+g_get_filename_charsets (const gchar ***filename_charsets)
{
static const gchar *charsets[] = {
"UTF-8",
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) 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<footnoteref linkend="nul-unsafe"/>.
+ * nul-terminated (Note that some encodings may allow nul
+ * bytes to occur inside strings. In that case, using -1
+ * for the @len parameter is 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
* 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
+ * @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
* 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.
+ * for filenames; on other platforms, this function indirectly depends on
+ * the [current locale][setlocale].
*
- * Return value: The converted string, or %NULL on an error.
+ * Returns: The converted string, or %NULL on an error.
**/
gchar*
g_filename_to_utf8 (const gchar *opsysstring,
{
const gchar *charset;
+ g_return_val_if_fail (opsysstring != NULL, NULL);
+
if (get_filename_charset (&charset))
return strdup_len (opsysstring, len, bytes_read, bytes_written, error);
else
"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;
+ g_return_val_if_fail (opsysstring != NULL, NULL);
+
if (g_get_charset (&charset))
return strdup_len (opsysstring, len, bytes_read, bytes_written, error);
else
* @utf8string: a UTF-8 encoded string.
* @len: the length of the string, or -1 if the string is
* nul-terminated.
- * @bytes_read: location to store the number of bytes in the
- * input string that were successfully converted, or %NULL.
+ * @bytes_read: (out) (allow-none): 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
+ * @bytes_written: (out): 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
+ * @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
* Converts a string from UTF-8 to the encoding GLib uses for
- * filenames. Note that on Windows GLib uses UTF-8 for filenames.
+ * filenames. Note that on Windows GLib uses UTF-8 for filenames;
+ * on other platforms, this function indirectly depends on the
+ * [current locale][setlocale].
*
- * Return value: The converted string, or %NULL on an error.
+ * Returns: (array length=bytes_written) (element-type guint8) (transfer full):
+ * The converted string, or %NULL on an error.
**/
gchar*
g_filename_from_utf8 (const gchar *utf8string,
charset, "UTF-8", bytes_read, bytes_written, error);
}
-#ifdef G_OS_WIN32
+#if defined (G_OS_WIN32) && !defined (_WIN64)
#undef g_filename_from_utf8
/**
* g_filename_from_uri:
* @uri: a uri describing a filename (escaped, encoded in ASCII).
- * @hostname: Location to store hostname for the URI, or %NULL.
+ * @hostname: (out) (allow-none): Location to store hostname for the URI, or %NULL.
* If there is no hostname in the URI, %NULL will be
* stored in this location.
- * @error: location to store the error occuring, or %NULL to ignore
+ * @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError may occur.
*
* Converts an escaped ASCII-encoded URI to a local filename in the
* encoding used for filenames.
*
- * Return value: a newly-allocated string holding the resulting
- * filename, or %NULL on an error.
+ * Returns: (type filename): a newly-allocated string holding
+ * the resulting filename, or %NULL on an error.
**/
gchar *
g_filename_from_uri (const gchar *uri,
return result;
}
-#ifdef G_OS_WIN32
+#if defined (G_OS_WIN32) && !defined (_WIN64)
#undef g_filename_from_uri
* @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
+ * @hostname: (allow-none): A UTF-8 encoded hostname, or %NULL for none.
+ * @error: location to store the error occurring, 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
+ * Returns: a newly-allocated string holding the resulting
* URI, or %NULL on an error.
**/
gchar *
!(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
* mime type defined in RFC 2483 into individual URIs,
* discarding any comments. The URIs are not validated.
*
- * Returns: a newly allocated %NULL-terminated list of
- * strings holding the individual URIs. The array should
- * be freed with g_strfreev().
+ * Returns: (transfer full): a newly allocated %NULL-terminated list
+ * of strings holding the individual URIs. The array should be freed
+ * with g_strfreev().
*
* Since: 2.6
*/
return result;
}
-static gchar *
-make_valid_utf8 (const gchar *name)
-{
- GString *string;
- const gchar *remainder, *invalid;
- gint remaining_bytes, valid_bytes;
-
- string = NULL;
- remainder = name;
- remaining_bytes = strlen (name);
-
- while (remaining_bytes != 0)
- {
- if (g_utf8_validate (remainder, remaining_bytes, &invalid))
- break;
- valid_bytes = invalid - remainder;
-
- if (string == NULL)
- string = g_string_sized_new (remaining_bytes);
-
- g_string_append_len (string, remainder, valid_bytes);
- g_string_append_c (string, '?');
-
- remaining_bytes -= valid_bytes + 1;
- remainder = invalid + 1;
- }
-
- if (string == NULL)
- return g_strdup (name);
-
- g_string_append (string, remainder);
- g_string_append (string, " (invalid encoding)");
-
- g_assert (g_utf8_validate (string->str, -1, NULL));
-
- return g_string_free (string, FALSE);
-}
-
/**
* 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
+ * can be translated in the display.
+ *
+ * If GLib cannot 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
+ * Returns: a newly allocated string containing
* a rendition of the basename of the filename in valid UTF-8
*
* Since: 2.6
* 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.
+ * 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 cannot 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
+ * Returns: a newly allocated string containing
* a rendition of the filename in valid UTF-8
*
* Since: 2.6
* by a question mark
*/
if (!display_name)
- display_name = make_valid_utf8 (filename);
+ display_name = _g_utf8_make_valid (filename);
return display_name;
}
-
-#define __G_CONVERT_C__
-#include "galiasdef.c"
projects / platform / upstream / glib.git / blobdiff