*
* 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 "glib.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"
+#include "gthreadprivate.h"
+#include "gunicode.h"
#ifdef G_PLATFORM_WIN32
#define STRICT
#include "galias.h"
+#ifdef G_OS_WIN32
+#include "win_iconv.c"
+#endif
+
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);
return 0;
}
+#else /* !NEED_ICONV_CACHE */
-/**
- * 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.
- *
- * 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
* @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)
outbytes_remaining = outbuf_size - 1; /* -1 for nul */
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;
- outp = dest + used;
- outbytes_remaining = outbuf_size - used - 1; /* -1 for nul */
-
- goto again;
- }
- case EILSEQ:
- if (error)
- g_set_error (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));
- have_error = TRUE;
- break;
+ outbuf_size *= 2;
+ dest = g_realloc (dest, outbuf_size);
+
+ outp = dest + used;
+ outbytes_remaining = outbuf_size - used - 1; /* -1 for nul */
+ }
+ break;
+ case EILSEQ:
+ if (error)
+ g_set_error (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));
+ 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;
}
}
}
/**
+ * 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, or -1 if the string is
* 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.
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);
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"),
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;
}
*
* 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.
**/
*
* 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>.
*
* Return value: The converted string, or %NULL on an error.
**/
* 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
+ * 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
- * <envar>G_FILENAME_ENCODING</envar> 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 filename encoding is UTF-8.
*
*
* 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 <link linkend="setlocale">current locale</link>.
*
* Return value: The converted string, or %NULL on an error.
**/
* 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
+ * <link linkend="setlocale">current locale</link>.
*
* Return value: The converted string, or %NULL on an error.
**/
* @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.
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 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.
* 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 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
* by a question mark
*/
if (!display_name)
- display_name = make_valid_utf8 (filename);
+ display_name = _g_utf8_make_valid (filename);
return display_name;
}
projects / platform / upstream / glib.git / blobdiff