X-Git-Url: http://review.tizen.org/git/?a=blobdiff_plain;f=glib%2Fgutf8.c;h=579c017f7393fc30a3fe1e0f9fae5929a3853a92;hb=11a21a2a1c2b2d7e0ea1339a8596a2e05c55dfe3;hp=ed830b184ac367cc8b886daf6a3b82bde1af316f;hpb=a4026b4cbff5d59b94a7e4ffabe764f6211839f6;p=platform%2Fupstream%2Fglib.git
diff --git a/glib/gutf8.c b/glib/gutf8.c
index ed830b1..579c017 100644
--- a/glib/gutf8.c
+++ b/glib/gutf8.c
@@ -14,12 +14,10 @@
* 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 .
*/
-#include
+#include "config.h"
#include
#ifdef HAVE_CODESET
@@ -27,9 +25,6 @@
#endif
#include
-#include "galias.h"
-#include "glib.h"
-
#ifdef G_PLATFORM_WIN32
#include
#define STRICT
@@ -37,8 +32,12 @@
#undef STRICT
#endif
-#include "libcharset/libcharset.h"
-
+#include "gconvert.h"
+#include "ghash.h"
+#include "gstrfuncs.h"
+#include "gtestutils.h"
+#include "gtypes.h"
+#include "gthread.h"
#include "glibintl.h"
#define UTF8_COMPUTE(Char, Mask, Len) \
@@ -95,14 +94,22 @@
(Result) <<= 6; \
(Result) |= ((Chars)[(Count)] & 0x3f); \
}
-
+
+/*
+ * Check whether a Unicode (5.2) char is in a valid range.
+ *
+ * The first check comes from the Unicode guarantee to never encode
+ * a point above 0x0010ffff, since UTF-16 couldn't represent it.
+ *
+ * The second check covers surrogate pairs (category Cs).
+ *
+ * @param Char the character
+ */
#define UNICODE_VALID(Char) \
((Char) < 0x110000 && \
- (((Char) & 0xFFFFF800) != 0xD800) && \
- ((Char) < 0xFDD0 || (Char) > 0xFDEF) && \
- ((Char) & 0xFFFE) != 0xFFFE)
-
-
+ (((Char) & 0xFFFFF800) != 0xD800))
+
+
static const gchar utf8_skip_data[256] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
@@ -123,14 +130,14 @@ const gchar * const g_utf8_skip = utf8_skip_data;
*
* Given a position @p with a UTF-8 encoded string @str, find the start
* of the previous UTF-8 character starting before @p. Returns %NULL if no
- * UTF-8 characters are present in @p before @str.
+ * UTF-8 characters are present in @str before @p.
*
* @p does not have to be at the beginning of a UTF-8 character. No check
* is made to see if the character found is actually valid other than
* it starts with an appropriate byte.
*
- * Return value: a pointer to the found character or %NULL.
- **/
+ * Returns: a pointer to the found character or %NULL.
+ */
gchar *
g_utf8_find_prev_char (const char *str,
const char *p)
@@ -146,9 +153,8 @@ g_utf8_find_prev_char (const char *str,
/**
* g_utf8_find_next_char:
* @p: a pointer to a position within a UTF-8 encoded string
- * @end: a pointer to the end of the string, or %NULL to indicate
- * that the string is nul-terminated, in which case
- * the returned value will be
+ * @end: a pointer to the byte following the end of the string,
+ * or %NULL to indicate that the string is nul-terminated
*
* Finds the start of the next UTF-8 character in the string after @p.
*
@@ -156,8 +162,8 @@ g_utf8_find_prev_char (const char *str,
* is made to see if the character found is actually valid other than
* it starts with an appropriate byte.
*
- * Return value: a pointer to the found character or %NULL
- **/
+ * Returns: a pointer to the found character or %NULL
+ */
gchar *
g_utf8_find_next_char (const gchar *p,
const gchar *end)
@@ -185,8 +191,8 @@ g_utf8_find_next_char (const gchar *p,
* it starts with an appropriate byte. If @p might be the first
* character of the string, you must use g_utf8_find_prev_char() instead.
*
- * Return value: a pointer to the found character.
- **/
+ * Returns: a pointer to the found character
+ */
gchar *
g_utf8_prev_char (const gchar *p)
{
@@ -197,19 +203,22 @@ g_utf8_prev_char (const gchar *p)
return (gchar *)p;
}
}
-
+
/**
* g_utf8_strlen:
- * @p: pointer to the start of a UTF-8 encoded string.
+ * @p: pointer to the start of a UTF-8 encoded string
* @max: the maximum number of bytes to examine. If @max
* is less than 0, then the string is assumed to be
- * nul-terminated. If @max is 0, @p will not be examined and
- * may be %NULL.
- *
- * Returns the length of the string in characters.
+ * nul-terminated. If @max is 0, @p will not be examined and
+ * may be %NULL. If @max is greater than 0, up to @max
+ * bytes are examined
*
- * Return value: the length of the string in characters
- **/
+ * Computes the length of the string in characters, not including
+ * the terminating nul character. If the @max'th byte falls in the
+ * middle of a character, the last (partial) character is not counted.
+ *
+ * Returns: the length of the string in characters
+ */
glong
g_utf8_strlen (const gchar *p,
gssize max)
@@ -230,19 +239,19 @@ g_utf8_strlen (const gchar *p,
{
if (max == 0 || !*p)
return 0;
-
- p = g_utf8_next_char (p);
+
+ p = g_utf8_next_char (p);
while (p - start < max && *p)
{
++len;
- p = g_utf8_next_char (p);
+ p = g_utf8_next_char (p);
}
/* only do the last len increment if we got a complete
* char (don't count partial chars)
*/
- if (p - start == max)
+ if (p - start <= max)
++len;
}
@@ -250,17 +259,49 @@ g_utf8_strlen (const gchar *p,
}
/**
+ * g_utf8_substring:
+ * @str: a UTF-8 encoded string
+ * @start_pos: a character offset within @str
+ * @end_pos: another character offset within @str
+ *
+ * Copies a substring out of a UTF-8 encoded string.
+ * The substring will contain @end_pos - @start_pos characters.
+ *
+ * Returns: a newly allocated copy of the requested
+ * substring. Free with g_free() when no longer needed.
+ *
+ * Since: 2.30
+ */
+gchar *
+g_utf8_substring (const gchar *str,
+ glong start_pos,
+ glong end_pos)
+{
+ gchar *start, *end, *out;
+
+ start = g_utf8_offset_to_pointer (str, start_pos);
+ end = g_utf8_offset_to_pointer (start, end_pos - start_pos);
+
+ out = g_malloc (end - start + 1);
+ memcpy (out, start, end - start);
+ out[end - start] = 0;
+
+ return out;
+}
+
+/**
* g_utf8_get_char:
* @p: a pointer to Unicode character encoded as UTF-8
*
* Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
- * If @p does not point to a valid UTF-8 encoded character, results are
- * undefined. If you are not sure that the bytes are complete
+ *
+ * If @p does not point to a valid UTF-8 encoded character, results
+ * are undefined. If you are not sure that the bytes are complete
* valid Unicode characters, you should use g_utf8_get_char_validated()
* instead.
*
- * Return value: the resulting character
- **/
+ * Returns: the resulting character
+ */
gunichar
g_utf8_get_char (const gchar *p)
{
@@ -280,20 +321,51 @@ g_utf8_get_char (const gchar *p)
* g_utf8_offset_to_pointer:
* @str: a UTF-8 encoded string
* @offset: a character offset within @str
- *
+ *
* Converts from an integer character offset to a pointer to a position
* within the string.
- *
- * Return value: the resulting pointer
- **/
+ *
+ * Since 2.10, this function allows to pass a negative @offset to
+ * step backwards. It is usually worth stepping backwards from the end
+ * instead of forwards if @offset is in the last fourth of the string,
+ * since moving forward is about 3 times faster than moving backward.
+ *
+ * Note that this function doesn't abort when reaching the end of @str.
+ * Therefore you should be sure that @offset is within string boundaries
+ * before calling that function. Call g_utf8_strlen() when unsure.
+ * This limitation exists as this function is called frequently during
+ * text rendering and therefore has to be as fast as possible.
+ *
+ * Returns: the resulting pointer
+ */
gchar *
g_utf8_offset_to_pointer (const gchar *str,
- glong offset)
+ glong offset)
{
const gchar *s = str;
- while (offset--)
- s = g_utf8_next_char (s);
-
+
+ if (offset > 0)
+ while (offset--)
+ s = g_utf8_next_char (s);
+ else
+ {
+ const char *s1;
+
+ /* This nice technique for fast backwards stepping
+ * through a UTF-8 string was dubbed "stutter stepping"
+ * by its inventor, Larry Ewing.
+ */
+ while (offset)
+ {
+ s1 = s;
+ s += offset;
+ while ((*s & 0xc0) == 0x80)
+ s--;
+
+ offset += g_utf8_pointer_to_offset (s, s1);
+ }
+ }
+
return (gchar *)s;
}
@@ -304,22 +376,28 @@ g_utf8_offset_to_pointer (const gchar *str,
*
* Converts from a pointer to position within a string to a integer
* character offset.
+ *
+ * Since 2.10, this function allows @pos to be before @str, and returns
+ * a negative offset in this case.
*
- * Return value: the resulting character offset
- **/
+ * Returns: the resulting character offset
+ */
glong
g_utf8_pointer_to_offset (const gchar *str,
const gchar *pos)
{
const gchar *s = str;
glong offset = 0;
-
- while (s < pos)
- {
- s = g_utf8_next_char (s);
- offset++;
- }
+ if (pos < str)
+ offset = - g_utf8_pointer_to_offset (pos, str);
+ else
+ while (s < pos)
+ {
+ s = g_utf8_next_char (s);
+ offset++;
+ }
+
return offset;
}
@@ -330,14 +408,13 @@ g_utf8_pointer_to_offset (const gchar *str,
* @src: UTF-8 encoded string
* @n: character count
*
- * Like the standard C strncpy() function, but
- * copies a given number of characters instead of a given number of
- * bytes. The @src string must be valid UTF-8 encoded text.
- * (Use g_utf8_validate() on all text before trying to use UTF-8
- * utility functions with it.)
+ * Like the standard C strncpy() function, but copies a given number
+ * of characters instead of a given number of bytes. The @src string
+ * must be valid UTF-8 encoded text. (Use g_utf8_validate() on all
+ * text before trying to use UTF-8 utility functions with it.)
*
- * Return value: @dest
- **/
+ * Returns: @dest
+ */
gchar *
g_utf8_strncpy (gchar *dest,
const gchar *src,
@@ -354,188 +431,24 @@ g_utf8_strncpy (gchar *dest,
return dest;
}
-G_LOCK_DEFINE_STATIC (aliases);
-
-static GHashTable *
-get_alias_hash (void)
-{
- static GHashTable *alias_hash = NULL;
- const char *aliases;
-
- G_LOCK (aliases);
-
- if (!alias_hash)
- {
- alias_hash = g_hash_table_new (g_str_hash, g_str_equal);
-
- aliases = _g_locale_get_charset_aliases ();
- while (*aliases != '\0')
- {
- const char *canonical;
- const char *alias;
- const char **alias_array;
- int count = 0;
-
- alias = aliases;
- aliases += strlen (aliases) + 1;
- canonical = aliases;
- aliases += strlen (aliases) + 1;
-
- alias_array = g_hash_table_lookup (alias_hash, canonical);
- if (alias_array)
- {
- while (alias_array[count])
- count++;
- }
-
- alias_array = g_renew (const char *, alias_array, count + 2);
- alias_array[count] = alias;
- alias_array[count + 1] = NULL;
-
- g_hash_table_insert (alias_hash, (char *)canonical, alias_array);
- }
- }
-
- G_UNLOCK (aliases);
-
- return alias_hash;
-}
-
-/* As an abuse of the alias table, the following routines gets
- * the charsets that are aliases for the canonical name.
- */
-const char **
-_g_charset_get_aliases (const char *canonical_name)
-{
- GHashTable *alias_hash = get_alias_hash ();
-
- return g_hash_table_lookup (alias_hash, canonical_name);
-}
-
-static gboolean
-g_utf8_get_charset_internal (const char *raw_data,
- const char **a)
-{
- const char *charset = getenv("CHARSET");
-
- if (charset && *charset)
- {
- *a = charset;
-
- if (charset && strstr (charset, "UTF-8"))
- return TRUE;
- else
- return FALSE;
- }
-
- /* The libcharset code tries to be thread-safe without
- * a lock, but has a memory leak and a missing memory
- * barrier, so we lock for it
- */
- G_LOCK (aliases);
- charset = _g_locale_charset_unalias (raw_data);
- G_UNLOCK (aliases);
-
- if (charset && *charset)
- {
- *a = charset;
-
- if (charset && strstr (charset, "UTF-8"))
- return TRUE;
- else
- return FALSE;
- }
-
- /* Assume this for compatibility at present. */
- *a = "US-ASCII";
-
- return FALSE;
-}
-
-typedef struct _GCharsetCache GCharsetCache;
-
-struct _GCharsetCache {
- gboolean is_utf8;
- gchar *raw;
- gchar *charset;
-};
-
-static void
-charset_cache_free (gpointer data)
-{
- GCharsetCache *cache = data;
- g_free (cache->raw);
- g_free (cache->charset);
- g_free (cache);
-}
-
-/**
- * g_get_charset:
- * @charset: return location for character set name
- *
- * Obtains the character set for the current locale; you might use
- * this character set as an argument to g_convert(), to convert from
- * the current locale's encoding to some other encoding. (Frequently
- * g_locale_to_utf8() and g_locale_from_utf8() are nice shortcuts,
- * though.)
- *
- * The return value is %TRUE if the locale's encoding is UTF-8, in that
- * case you can perhaps avoid calling g_convert().
- *
- * The string returned in @charset is not allocated, and should not be
- * freed.
- *
- * Return value: %TRUE if the returned charset is UTF-8
- **/
-gboolean
-g_get_charset (G_CONST_RETURN char **charset)
-{
- static GStaticPrivate cache_private = G_STATIC_PRIVATE_INIT;
- GCharsetCache *cache = g_static_private_get (&cache_private);
- const gchar *raw;
-
- if (!cache)
- {
- cache = g_new0 (GCharsetCache, 1);
- g_static_private_set (&cache_private, cache, charset_cache_free);
- }
-
- raw = _g_locale_charset_raw ();
-
- if (!(cache->raw && strcmp (cache->raw, raw) == 0))
- {
- const gchar *new_charset;
-
- g_free (cache->raw);
- g_free (cache->charset);
- cache->raw = g_strdup (raw);
- cache->is_utf8 = g_utf8_get_charset_internal (raw, &new_charset);
- cache->charset = g_strdup (new_charset);
- }
-
- if (charset)
- *charset = cache->charset;
-
- return cache->is_utf8;
-}
-
/* unicode_strchr */
/**
* g_unichar_to_utf8:
- * @c: a ISO10646 character code
+ * @c: a Unicode character code
* @outbuf: output buffer, must have at least 6 bytes of space.
* If %NULL, the length will be computed and returned
* and nothing will be written to @outbuf.
*
* Converts a single character to UTF-8.
*
- * Return value: number of bytes written
- **/
+ * Returns: number of bytes written
+ */
int
g_unichar_to_utf8 (gunichar c,
gchar *outbuf)
{
+ /* If this gets modified, also update the copy in g_string_insert_unichar() */
guint len = 0;
int first;
int i;
@@ -588,16 +501,16 @@ g_unichar_to_utf8 (gunichar c,
* g_utf8_strchr:
* @p: a nul-terminated UTF-8 encoded string
* @len: the maximum length of @p
- * @c: a ISO10646 character
+ * @c: a Unicode character
*
- * Finds the leftmost occurrence of the given ISO10646 character
+ * Finds the leftmost occurrence of the given Unicode character
* in a UTF-8 encoded string, while limiting the search to @len bytes.
* If @len is -1, allow unbounded search.
*
- * Return value: %NULL if the string does not contain the character,
- * otherwise, a pointer to the start of the leftmost occurrence of
- * the character in the string.
- **/
+ * Returns: %NULL if the string does not contain the character,
+ * otherwise, a pointer to the start of the leftmost occurrence
+ * of the character in the string.
+ */
gchar *
g_utf8_strchr (const char *p,
gssize len,
@@ -616,16 +529,16 @@ g_utf8_strchr (const char *p,
* g_utf8_strrchr:
* @p: a nul-terminated UTF-8 encoded string
* @len: the maximum length of @p
- * @c: a ISO10646 character
+ * @c: a Unicode character
*
- * Find the rightmost occurrence of the given ISO10646 character
+ * Find the rightmost occurrence of the given Unicode character
* in a UTF-8 encoded string, while limiting the search to @len bytes.
* If @len is -1, allow unbounded search.
*
- * Return value: %NULL if the string does not contain the character,
- * otherwise, a pointer to the start of the rightmost occurrence of the
- * character in the string.
- **/
+ * Returns: %NULL if the string does not contain the character,
+ * otherwise, a pointer to the start of the rightmost occurrence
+ * of the character in the string.
+ */
gchar *
g_utf8_strrchr (const char *p,
gssize len,
@@ -641,20 +554,23 @@ g_utf8_strrchr (const char *p,
/* Like g_utf8_get_char, but take a maximum length
- * and return (gunichar)-2 on incomplete trailing character
+ * and return (gunichar)-2 on incomplete trailing character;
+ * also check for malformed or overlong sequences
+ * and return (gunichar)-1 in this case.
*/
static inline gunichar
g_utf8_get_char_extended (const gchar *p,
- gssize max_len)
+ gssize max_len)
{
guint i, len;
+ gunichar min_code;
gunichar wc = (guchar) *p;
if (wc < 0x80)
{
return wc;
}
- else if (wc < 0xc0)
+ else if (G_UNLIKELY (wc < 0xc0))
{
return (gunichar)-1;
}
@@ -662,33 +578,38 @@ g_utf8_get_char_extended (const gchar *p,
{
len = 2;
wc &= 0x1f;
+ min_code = 1 << 7;
}
else if (wc < 0xf0)
{
len = 3;
wc &= 0x0f;
+ min_code = 1 << 11;
}
else if (wc < 0xf8)
{
len = 4;
wc &= 0x07;
+ min_code = 1 << 16;
}
else if (wc < 0xfc)
{
len = 5;
wc &= 0x03;
+ min_code = 1 << 21;
}
else if (wc < 0xfe)
{
len = 6;
wc &= 0x01;
+ min_code = 1 << 26;
}
else
{
return (gunichar)-1;
}
-
- if (max_len >= 0 && len > max_len)
+
+ if (G_UNLIKELY (max_len >= 0 && len > max_len))
{
for (i = 1; i < max_len; i++)
{
@@ -701,8 +622,8 @@ g_utf8_get_char_extended (const gchar *p,
for (i = 1; i < len; ++i)
{
gunichar ch = ((guchar *)p)[i];
-
- if ((ch & 0xc0) != 0x80)
+
+ if (G_UNLIKELY ((ch & 0xc0) != 0x80))
{
if (ch)
return (gunichar)-1;
@@ -714,32 +635,39 @@ g_utf8_get_char_extended (const gchar *p,
wc |= (ch & 0x3f);
}
- if (UTF8_LENGTH(wc) != len)
+ if (G_UNLIKELY (wc < min_code))
return (gunichar)-1;
-
+
return wc;
}
/**
* g_utf8_get_char_validated:
* @p: a pointer to Unicode character encoded as UTF-8
- * @max_len: the maximum number of bytes to read, or -1, for no maximum.
+ * @max_len: the maximum number of bytes to read, or -1, for no maximum or
+ * if @p is nul-terminated
*
* Convert a sequence of bytes encoded as UTF-8 to a Unicode character.
* This function checks for incomplete characters, for invalid characters
* such as characters that are out of the range of Unicode, and for
* overlong encodings of valid characters.
*
- * Return value: the resulting character. If @p points to a partial
- * sequence at the end of a string that could begin a valid
- * character, returns (gunichar)-2; otherwise, if @p does not point
- * to a valid UTF-8 encoded Unicode character, returns (gunichar)-1.
- **/
+ * Returns: the resulting character. If @p points to a partial
+ * sequence at the end of a string that could begin a valid
+ * character (or if @max_len is zero), returns (gunichar)-2;
+ * otherwise, if @p does not point to a valid UTF-8 encoded
+ * Unicode character, returns (gunichar)-1.
+ */
gunichar
-g_utf8_get_char_validated (const gchar *p,
- gssize max_len)
+g_utf8_get_char_validated (const gchar *p,
+ gssize max_len)
{
- gunichar result = g_utf8_get_char_extended (p, max_len);
+ gunichar result;
+
+ if (max_len == 0)
+ return (gunichar)-2;
+
+ result = g_utf8_get_char_extended (p, max_len);
if (result & 0x80000000)
return result;
@@ -752,25 +680,25 @@ g_utf8_get_char_validated (const gchar *p,
/**
* g_utf8_to_ucs4_fast:
* @str: a UTF-8 encoded string
- * @len: the maximum length of @str to use. If @len < 0, then
- * the string is nul-terminated.
- * @items_written: location to store the number of characters in the
- * result, or %NULL.
+ * @len: the maximum length of @str to use, in bytes. If @len < 0,
+ * then the string is nul-terminated.
+ * @items_written: (allow-none): location to store the number of
+ * characters in the result, or %NULL.
*
* Convert a string from UTF-8 to a 32-bit fixed width
* representation as UCS-4, assuming valid UTF-8 input.
* This function is roughly twice as fast as g_utf8_to_ucs4()
- * but does no error checking on the input.
+ * but does no error checking on the input. A trailing 0 character
+ * will be added to the string after the converted text.
*
- * Return value: a pointer to a newly allocated UCS-4 string.
- * This value must be freed with g_free().
- **/
+ * Returns: a pointer to a newly allocated UCS-4 string.
+ * This value must be freed with g_free().
+ */
gunichar *
g_utf8_to_ucs4_fast (const gchar *str,
glong len,
glong *items_written)
{
- gint j, charlen;
gunichar *result;
gint n_chars, i;
const gchar *p;
@@ -801,49 +729,38 @@ g_utf8_to_ucs4_fast (const gchar *str,
p = str;
for (i=0; i < n_chars; i++)
{
- gunichar wc = ((unsigned char *)p)[0];
+ gunichar wc = (guchar)*p++;
if (wc < 0x80)
{
result[i] = wc;
- p++;
}
else
{
- if (wc < 0xe0)
- {
- charlen = 2;
- wc &= 0x1f;
- }
- else if (wc < 0xf0)
- {
- charlen = 3;
- wc &= 0x0f;
- }
- else if (wc < 0xf8)
- {
- charlen = 4;
- wc &= 0x07;
- }
- else if (wc < 0xfc)
- {
- charlen = 5;
- wc &= 0x03;
- }
- else
+ gunichar mask = 0x40;
+
+ if (G_UNLIKELY ((wc & mask) == 0))
{
- charlen = 6;
- wc &= 0x01;
+ /* It's an out-of-sequence 10xxxxxxx byte.
+ * Rather than making an ugly hash of this and the next byte
+ * and overrunning the buffer, it's more useful to treat it
+ * with a replacement character
+ */
+ result[i] = 0xfffd;
+ continue;
}
- for (j = 1; j < charlen; j++)
+ do
{
wc <<= 6;
- wc |= ((unsigned char *)p)[j] & 0x3f;
+ wc |= (guchar)(*p++) & 0x3f;
+ mask <<= 5;
}
+ while((wc & mask) != 0);
+
+ wc &= mask - 1;
result[i] = wc;
- p += charlen;
}
}
result[i] = 0;
@@ -854,32 +771,41 @@ g_utf8_to_ucs4_fast (const gchar *str,
return result;
}
+static gpointer
+try_malloc_n (gsize n_blocks, gsize n_block_bytes, GError **error)
+{
+ gpointer ptr = g_try_malloc_n (n_blocks, n_block_bytes);
+ if (ptr == NULL)
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_NO_MEMORY,
+ _("Failed to allocate memory"));
+ return ptr;
+}
+
/**
* g_utf8_to_ucs4:
* @str: a UTF-8 encoded string
- * @len: the maximum length of @str to use. If @len < 0, then
- * the string is nul-terminated.
- * @items_read: location to store number of bytes read, or %NULL.
- * If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
- * returned in case @str contains a trailing partial
- * character. If an error occurs then the index of the
- * invalid input is stored here.
- * @items_written: location to store number of characters written or %NULL.
- * The value here stored does not include the trailing 0
- * character.
- * @error: location to store the error occuring, or %NULL to ignore
- * errors. Any of the errors in #GConvertError other than
- * %G_CONVERT_ERROR_NO_CONVERSION may occur.
+ * @len: the maximum length of @str to use, in bytes. If @len < 0,
+ * then the string is nul-terminated.
+ * @items_read: (allow-none): location to store number of bytes read, or %NULL.
+ * If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
+ * returned in case @str contains a trailing partial
+ * character. If an error occurs then the index of the
+ * invalid input is stored here.
+ * @items_written: (allow-none): location to store number of characters
+ * written or %NULL. The value here stored does not include the
+ * trailing 0 character.
+ * @error: location to store the error occurring, or %NULL to ignore
+ * errors. Any of the errors in #GConvertError other than
+ * %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from UTF-8 to a 32-bit fixed width
- * representation as UCS-4. A trailing 0 will be added to the
+ * representation as UCS-4. A trailing 0 character will be added to the
* string after the converted text.
*
- * Return value: a pointer to a newly allocated UCS-4 string.
- * This value must be freed with g_free(). If an
- * error occurs, %NULL will be returned and
- * @error set.
- **/
+ * Returns: a pointer to a newly allocated UCS-4 string.
+ * This value must be freed with g_free(). If an error occurs,
+ * %NULL will be returned and @error set.
+ */
gunichar *
g_utf8_to_ucs4 (const gchar *str,
glong len,
@@ -895,7 +821,7 @@ g_utf8_to_ucs4 (const gchar *str,
n_chars = 0;
while ((len < 0 || str + len - in > 0) && *in)
{
- gunichar wc = g_utf8_get_char_extended (in, str + len - in);
+ gunichar wc = g_utf8_get_char_extended (in, len < 0 ? 6 : str + len - in);
if (wc & 0x80000000)
{
if (wc == (gunichar)-2)
@@ -903,12 +829,12 @@ g_utf8_to_ucs4 (const gchar *str,
if (items_read)
break;
else
- 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"));
}
else
- 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"));
goto err_out;
}
@@ -918,8 +844,10 @@ g_utf8_to_ucs4 (const gchar *str,
in = g_utf8_next_char (in);
}
- result = g_new (gunichar, n_chars + 1);
-
+ result = try_malloc_n (n_chars + 1, sizeof (gunichar), error);
+ if (result == NULL)
+ goto err_out;
+
in = str;
for (i=0; i < n_chars; i++)
{
@@ -941,24 +869,25 @@ g_utf8_to_ucs4 (const gchar *str,
/**
* g_ucs4_to_utf8:
* @str: a UCS-4 encoded string
- * @len: the maximum length of @str to use. If @len < 0, then
- * the string is terminated with a 0 character.
- * @items_read: location to store number of characters read read, or %NULL.
- * @items_written: location to store number of bytes written or %NULL.
- * The value here stored does not include the trailing 0
- * byte.
- * @error: location to store the error occuring, or %NULL to ignore
+ * @len: the maximum length (number of characters) of @str to use.
+ * If @len < 0, then the string is nul-terminated.
+ * @items_read: (allow-none): location to store number of characters
+ * read, or %NULL.
+ * @items_written: (allow-none): location to store number of bytes
+ * written or %NULL. The value here stored does not include the
+ * trailing 0 byte.
+ * @error: location to store the error occurring, or %NULL to ignore
* errors. Any of the errors in #GConvertError other than
* %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from a 32-bit fixed width representation as UCS-4.
* to UTF-8. The result will be terminated with a 0 byte.
*
- * Return value: a pointer to a newly allocated UTF-8 string.
- * This value must be freed with g_free(). If an
- * error occurs, %NULL will be returned and
- * @error set.
- **/
+ * Returns: a pointer to a newly allocated UTF-8 string.
+ * This value must be freed with g_free(). If an error occurs,
+ * %NULL will be returned and @error set. In that case, @items_read
+ * will be set to the position of the first invalid input character.
+ */
gchar *
g_ucs4_to_utf8 (const gunichar *str,
glong len,
@@ -979,18 +908,18 @@ g_ucs4_to_utf8 (const gunichar *str,
if (str[i] >= 0x80000000)
{
- if (items_read)
- *items_read = i;
-
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Character out of range for UTF-8"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Character out of range for UTF-8"));
goto err_out;
}
result_length += UTF8_LENGTH (str[i]);
}
- result = g_malloc (result_length + 1);
+ result = try_malloc_n (result_length + 1, 1, error);
+ if (result == NULL)
+ goto err_out;
+
p = result;
i = 0;
@@ -1014,42 +943,45 @@ g_ucs4_to_utf8 (const gunichar *str,
/**
* g_utf16_to_utf8:
* @str: a UTF-16 encoded string
- * @len: the maximum length of @str to use. If @len < 0, then
- * the string is terminated with a 0 character.
- * @items_read: location to store number of words read, or %NULL.
- * If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
- * returned in case @str contains a trailing partial
- * character. If an error occurs then the index of the
- * invalid input is stored here.
- * @items_written: location to store number of bytes written, or %NULL.
- * The value stored here does not include the trailing
- * 0 byte.
- * @error: location to store the error occuring, or %NULL to ignore
- * errors. Any of the errors in #GConvertError other than
- * %G_CONVERT_ERROR_NO_CONVERSION may occur.
+ * @len: the maximum length (number of #gunichar2) of @str to use.
+ * If @len < 0, then the string is nul-terminated.
+ * @items_read: (allow-none): location to store number of words read,
+ * or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
+ * returned in case @str contains a trailing partial character. If
+ * an error occurs then the index of the invalid input is stored here.
+ * @items_written: (allow-none): location to store number of bytes written,
+ * or %NULL. The value stored here does not include the trailing 0 byte.
+ * @error: location to store the error occurring, or %NULL to ignore
+ * errors. Any of the errors in #GConvertError other than
+ * %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from UTF-16 to UTF-8. The result will be
* terminated with a 0 byte.
*
* Note that the input is expected to be already in native endianness,
* an initial byte-order-mark character is not handled specially.
- * g_convert() can be used to convert a byte buffer of UTF-16 data of
+ * g_convert() can be used to convert a byte buffer of UTF-16 data of
* ambiguous endianess.
- *
- * Return value: a pointer to a newly allocated UTF-8 string.
- * This value must be freed with g_free(). If an
- * error occurs, %NULL will be returned and
- * @error set.
+ *
+ * Further note that this function does not validate the result
+ * string; it may e.g. include embedded NUL characters. The only
+ * validation done by this function is to ensure that the input can
+ * be correctly interpreted as UTF-16, i.e. it doesn't contain
+ * things unpaired surrogates.
+ *
+ * Returns: a pointer to a newly allocated UTF-8 string.
+ * This value must be freed with g_free(). If an error occurs,
+ * %NULL will be returned and @error set.
**/
gchar *
g_utf16_to_utf8 (const gunichar2 *str,
- glong len,
- glong *items_read,
- glong *items_written,
+ glong len,
+ glong *items_read,
+ glong *items_written,
GError **error)
{
- /* This function and g_utf16_to_ucs4 are almost exactly identical - The lines that differ
- * are marked.
+ /* This function and g_utf16_to_ucs4 are almost exactly identical -
+ * The lines that differ are marked.
*/
const gunichar2 *in;
gchar *out;
@@ -1057,7 +989,7 @@ g_utf16_to_utf8 (const gunichar2 *str,
gint n_bytes;
gunichar high_surrogate;
- g_return_val_if_fail (str != 0, NULL);
+ g_return_val_if_fail (str != NULL, NULL);
n_bytes = 0;
in = str;
@@ -1076,8 +1008,8 @@ g_utf16_to_utf8 (const gunichar2 *str,
}
else
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid sequence in conversion input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid sequence in conversion input"));
goto err_out;
}
}
@@ -1085,8 +1017,8 @@ g_utf16_to_utf8 (const gunichar2 *str,
{
if (high_surrogate)
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid sequence in conversion input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid sequence in conversion input"));
goto err_out;
}
@@ -1108,16 +1040,18 @@ g_utf16_to_utf8 (const gunichar2 *str,
if (high_surrogate && !items_read)
{
- 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"));
goto err_out;
}
/* At this point, everything is valid, and we just need to convert
*/
/********** DIFFERENT for UTF8/UCS4 **********/
- result = g_malloc (n_bytes + 1);
-
+ result = try_malloc_n (n_bytes + 1, 1, error);
+ if (result == NULL)
+ goto err_out;
+
high_surrogate = 0;
out = result;
in = str;
@@ -1163,28 +1097,26 @@ g_utf16_to_utf8 (const gunichar2 *str,
/**
* g_utf16_to_ucs4:
* @str: a UTF-16 encoded string
- * @len: the maximum length of @str to use. If @len < 0, then
- * the string is terminated with a 0 character.
- * @items_read: location to store number of words read, or %NULL.
- * If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
- * returned in case @str contains a trailing partial
- * character. If an error occurs then the index of the
- * invalid input is stored here.
- * @items_written: location to store number of characters written, or %NULL.
- * The value stored here does not include the trailing
- * 0 character.
- * @error: location to store the error occuring, or %NULL to ignore
- * errors. Any of the errors in #GConvertError other than
- * %G_CONVERT_ERROR_NO_CONVERSION may occur.
+ * @len: the maximum length (number of #gunichar2) of @str to use.
+ * If @len < 0, then the string is nul-terminated.
+ * @items_read: (allow-none): location to store number of words read,
+ * or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
+ * returned in case @str contains a trailing partial character. If
+ * an error occurs then the index of the invalid input is stored here.
+ * @items_written: (allow-none): location to store number of characters
+ * written, or %NULL. The value stored here does not include the trailing
+ * 0 character.
+ * @error: location to store the error occurring, or %NULL to ignore
+ * errors. Any of the errors in #GConvertError other than
+ * %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
* Convert a string from UTF-16 to UCS-4. The result will be
- * terminated with a 0 character.
+ * nul-terminated.
*
- * Return value: a pointer to a newly allocated UCS-4 string.
- * This value must be freed with g_free(). If an
- * error occurs, %NULL will be returned and
- * @error set.
- **/
+ * Returns: a pointer to a newly allocated UCS-4 string.
+ * This value must be freed with g_free(). If an error occurs,
+ * %NULL will be returned and @error set.
+ */
gunichar *
g_utf16_to_ucs4 (const gunichar2 *str,
glong len,
@@ -1198,7 +1130,7 @@ g_utf16_to_ucs4 (const gunichar2 *str,
gint n_bytes;
gunichar high_surrogate;
- g_return_val_if_fail (str != 0, NULL);
+ g_return_val_if_fail (str != NULL, NULL);
n_bytes = 0;
in = str;
@@ -1206,19 +1138,17 @@ g_utf16_to_ucs4 (const gunichar2 *str,
while ((len < 0 || in - str < len) && *in)
{
gunichar2 c = *in;
- gunichar wc;
if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
{
if (high_surrogate)
{
- wc = SURROGATE_VALUE (high_surrogate, c);
high_surrogate = 0;
}
else
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid sequence in conversion input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid sequence in conversion input"));
goto err_out;
}
}
@@ -1226,8 +1156,8 @@ g_utf16_to_ucs4 (const gunichar2 *str,
{
if (high_surrogate)
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid sequence in conversion input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid sequence in conversion input"));
goto err_out;
}
@@ -1236,8 +1166,6 @@ g_utf16_to_ucs4 (const gunichar2 *str,
high_surrogate = c;
goto next1;
}
- else
- wc = c;
}
/********** DIFFERENT for UTF8/UCS4 **********/
@@ -1249,16 +1177,18 @@ g_utf16_to_ucs4 (const gunichar2 *str,
if (high_surrogate && !items_read)
{
- 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"));
goto err_out;
}
/* At this point, everything is valid, and we just need to convert
*/
/********** DIFFERENT for UTF8/UCS4 **********/
- result = g_malloc (n_bytes + 4);
-
+ result = try_malloc_n (n_bytes + 4, 1, error);
+ if (result == NULL)
+ goto err_out;
+
high_surrogate = 0;
out = result;
in = str;
@@ -1305,33 +1235,31 @@ g_utf16_to_ucs4 (const gunichar2 *str,
/**
* g_utf8_to_utf16:
* @str: a UTF-8 encoded string
- * @len: the maximum length of @str to use. If @len < 0, then
- * the string is nul-terminated.
- * @items_read: location to store number of bytes read, or %NULL.
- * If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
- * returned in case @str contains a trailing partial
- * character. If an error occurs then the index of the
- * invalid input is stored here.
- * @items_written: location to store number of words written, or %NULL.
- * The value stored here does not include the trailing
- * 0 word.
- * @error: location to store the error occuring, or %NULL to ignore
- * errors. Any of the errors in #GConvertError other than
- * %G_CONVERT_ERROR_NO_CONVERSION may occur.
+ * @len: the maximum length (number of bytes) of @str to use.
+ * If @len < 0, then the string is nul-terminated.
+ * @items_read: (allow-none): location to store number of bytes read,
+ * or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
+ * returned in case @str contains a trailing partial character. If
+ * an error occurs then the index of the invalid input is stored here.
+ * @items_written: (allow-none): location to store number of #gunichar2
+ * written, or %NULL. The value stored here does not include the
+ * trailing 0.
+ * @error: location to store the error occurring, or %NULL to ignore
+ * errors. Any of the errors in #GConvertError other than
+ * %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
- * Convert a string from UTF-8 to UTF-16. A 0 word will be
+ * Convert a string from UTF-8 to UTF-16. A 0 character will be
* added to the result after the converted text.
- *
- * Return value: a pointer to a newly allocated UTF-16 string.
- * This value must be freed with g_free(). If an
- * error occurs, %NULL will be returned and
- * @error set.
- **/
+ *
+ * Returns: a pointer to a newly allocated UTF-16 string.
+ * This value must be freed with g_free(). If an error occurs,
+ * %NULL will be returned and @error set.
+ */
gunichar2 *
g_utf8_to_utf16 (const gchar *str,
- glong len,
- glong *items_read,
- glong *items_written,
+ glong len,
+ glong *items_read,
+ glong *items_written,
GError **error)
{
gunichar2 *result = NULL;
@@ -1345,7 +1273,7 @@ g_utf8_to_utf16 (const gchar *str,
n16 = 0;
while ((len < 0 || str + len - in > 0) && *in)
{
- gunichar wc = g_utf8_get_char_extended (in, str + len - in);
+ gunichar wc = g_utf8_get_char_extended (in, len < 0 ? 6 : str + len - in);
if (wc & 0x80000000)
{
if (wc == (gunichar)-2)
@@ -1353,12 +1281,12 @@ g_utf8_to_utf16 (const gchar *str,
if (items_read)
break;
else
- 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"));
}
else
- 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"));
goto err_out;
}
@@ -1367,8 +1295,8 @@ g_utf8_to_utf16 (const gchar *str,
n16 += 1;
else if (wc < 0xe000)
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid sequence in conversion input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid sequence in conversion input"));
goto err_out;
}
@@ -1378,8 +1306,8 @@ g_utf8_to_utf16 (const gchar *str,
n16 += 2;
else
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Character out of range for UTF-16"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Character out of range for UTF-16"));
goto err_out;
}
@@ -1387,8 +1315,10 @@ g_utf8_to_utf16 (const gchar *str,
in = g_utf8_next_char (in);
}
- result = g_new (gunichar2, n16 + 1);
-
+ result = try_malloc_n (n16 + 1, sizeof (gunichar2), error);
+ if (result == NULL)
+ goto err_out;
+
in = str;
for (i = 0; i < n16;)
{
@@ -1422,26 +1352,25 @@ g_utf8_to_utf16 (const gchar *str,
/**
* g_ucs4_to_utf16:
* @str: a UCS-4 encoded string
- * @len: the maximum length of @str to use. If @len < 0, then
- * the string is terminated with a 0 character.
- * @items_read: location to store number of bytes read, or %NULL.
- * If an error occurs then the index of the invalid input
- * is stored here.
- * @items_written: location to store number of words written, or %NULL.
- * The value stored here does not include the trailing
- * 0 word.
- * @error: location to store the error occuring, or %NULL to ignore
- * errors. Any of the errors in #GConvertError other than
- * %G_CONVERT_ERROR_NO_CONVERSION may occur.
+ * @len: the maximum length (number of characters) of @str to use.
+ * If @len < 0, then the string is nul-terminated.
+ * @items_read: (allow-none): location to store number of bytes read,
+ * or %NULL. If an error occurs then the index of the invalid input
+ * is stored here.
+ * @items_written: (allow-none): location to store number of #gunichar2
+ * written, or %NULL. The value stored here does not include the
+ * trailing 0.
+ * @error: location to store the error occurring, or %NULL to ignore
+ * errors. Any of the errors in #GConvertError other than
+ * %G_CONVERT_ERROR_NO_CONVERSION may occur.
*
- * Convert a string from UCS-4 to UTF-16. A 0 word will be
+ * Convert a string from UCS-4 to UTF-16. A 0 character will be
* added to the result after the converted text.
*
- * Return value: a pointer to a newly allocated UTF-16 string.
- * This value must be freed with g_free(). If an
- * error occurs, %NULL will be returned and
- * @error set.
- **/
+ * Returns: a pointer to a newly allocated UTF-16 string.
+ * This value must be freed with g_free(). If an error occurs,
+ * %NULL will be returned and @error set.
+ */
gunichar2 *
g_ucs4_to_utf16 (const gunichar *str,
glong len,
@@ -1463,8 +1392,8 @@ g_ucs4_to_utf16 (const gunichar *str,
n16 += 1;
else if (wc < 0xe000)
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Invalid sequence in conversion input"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Invalid sequence in conversion input"));
goto err_out;
}
@@ -1474,17 +1403,19 @@ g_ucs4_to_utf16 (const gunichar *str,
n16 += 2;
else
{
- g_set_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
- _("Character out of range for UTF-16"));
+ g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
+ _("Character out of range for UTF-16"));
goto err_out;
}
i++;
}
-
- result = g_new (gunichar2, n16 + 1);
-
+
+ result = try_malloc_n (n16 + 1, sizeof (gunichar2), error);
+ if (result == NULL)
+ goto err_out;
+
for (i = 0, j = 0; j < n16; i++)
{
gunichar wc = str[i];
@@ -1511,83 +1442,199 @@ g_ucs4_to_utf16 (const gunichar *str,
return result;
}
+#define CONTINUATION_CHAR \
+ G_STMT_START { \
+ if ((*(guchar *)p & 0xc0) != 0x80) /* 10xxxxxx */ \
+ goto error; \
+ val <<= 6; \
+ val |= (*(guchar *)p) & 0x3f; \
+ } G_STMT_END
+
+static const gchar *
+fast_validate (const char *str)
+
+{
+ gunichar val = 0;
+ gunichar min = 0;
+ const gchar *p;
+
+ for (p = str; *p; p++)
+ {
+ if (*(guchar *)p < 128)
+ /* done */;
+ else
+ {
+ const gchar *last;
+
+ last = p;
+ if ((*(guchar *)p & 0xe0) == 0xc0) /* 110xxxxx */
+ {
+ if (G_UNLIKELY ((*(guchar *)p & 0x1e) == 0))
+ goto error;
+ p++;
+ if (G_UNLIKELY ((*(guchar *)p & 0xc0) != 0x80)) /* 10xxxxxx */
+ goto error;
+ }
+ else
+ {
+ if ((*(guchar *)p & 0xf0) == 0xe0) /* 1110xxxx */
+ {
+ min = (1 << 11);
+ val = *(guchar *)p & 0x0f;
+ goto TWO_REMAINING;
+ }
+ else if ((*(guchar *)p & 0xf8) == 0xf0) /* 11110xxx */
+ {
+ min = (1 << 16);
+ val = *(guchar *)p & 0x07;
+ }
+ else
+ goto error;
+
+ p++;
+ CONTINUATION_CHAR;
+ TWO_REMAINING:
+ p++;
+ CONTINUATION_CHAR;
+ p++;
+ CONTINUATION_CHAR;
+
+ if (G_UNLIKELY (val < min))
+ goto error;
+
+ if (G_UNLIKELY (!UNICODE_VALID(val)))
+ goto error;
+ }
+
+ continue;
+
+ error:
+ return last;
+ }
+ }
+
+ return p;
+}
+
+static const gchar *
+fast_validate_len (const char *str,
+ gssize max_len)
+
+{
+ gunichar val = 0;
+ gunichar min = 0;
+ const gchar *p;
+
+ g_assert (max_len >= 0);
+
+ for (p = str; ((p - str) < max_len) && *p; p++)
+ {
+ if (*(guchar *)p < 128)
+ /* done */;
+ else
+ {
+ const gchar *last;
+
+ last = p;
+ if ((*(guchar *)p & 0xe0) == 0xc0) /* 110xxxxx */
+ {
+ if (G_UNLIKELY (max_len - (p - str) < 2))
+ goto error;
+
+ if (G_UNLIKELY ((*(guchar *)p & 0x1e) == 0))
+ goto error;
+ p++;
+ if (G_UNLIKELY ((*(guchar *)p & 0xc0) != 0x80)) /* 10xxxxxx */
+ goto error;
+ }
+ else
+ {
+ if ((*(guchar *)p & 0xf0) == 0xe0) /* 1110xxxx */
+ {
+ if (G_UNLIKELY (max_len - (p - str) < 3))
+ goto error;
+
+ min = (1 << 11);
+ val = *(guchar *)p & 0x0f;
+ goto TWO_REMAINING;
+ }
+ else if ((*(guchar *)p & 0xf8) == 0xf0) /* 11110xxx */
+ {
+ if (G_UNLIKELY (max_len - (p - str) < 4))
+ goto error;
+
+ min = (1 << 16);
+ val = *(guchar *)p & 0x07;
+ }
+ else
+ goto error;
+
+ p++;
+ CONTINUATION_CHAR;
+ TWO_REMAINING:
+ p++;
+ CONTINUATION_CHAR;
+ p++;
+ CONTINUATION_CHAR;
+
+ if (G_UNLIKELY (val < min))
+ goto error;
+ if (G_UNLIKELY (!UNICODE_VALID(val)))
+ goto error;
+ }
+
+ continue;
+
+ error:
+ return last;
+ }
+ }
+
+ return p;
+}
+
/**
* g_utf8_validate:
- * @str: a pointer to character data
- * @max_len: max bytes to validate, or -1 to go until nul
- * @end: return location for end of valid data
+ * @str: (array length=max_len) (element-type guint8): a pointer to character data
+ * @max_len: max bytes to validate, or -1 to go until NUL
+ * @end: (allow-none) (out) (transfer none): return location for end of valid data
*
* Validates UTF-8 encoded text. @str is the text to validate;
* if @str is nul-terminated, then @max_len can be -1, otherwise
* @max_len should be the number of bytes to validate.
* If @end is non-%NULL, then the end of the valid range
- * will be stored there (i.e. the address of the first invalid byte
- * if some bytes were invalid, or the end of the text being validated
- * otherwise).
+ * will be stored there (i.e. the start of the first invalid
+ * character if some bytes were invalid, or the end of the text
+ * being validated otherwise).
+ *
+ * Note that g_utf8_validate() returns %FALSE if @max_len is
+ * positive and any of the @max_len bytes are nul.
*
* Returns %TRUE if all of @str was valid. Many GLib and GTK+
- * routines require valid UTF-8 as input;
- * so data read from a file or the network should be checked
- * with g_utf8_validate() before doing anything else with it.
+ * routines require valid UTF-8 as input; so data read from a file
+ * or the network should be checked with g_utf8_validate() before
+ * doing anything else with it.
*
- * Return value: %TRUE if the text was valid UTF-8
- **/
+ * Returns: %TRUE if the text was valid UTF-8
+ */
gboolean
-g_utf8_validate (const gchar *str,
- gssize max_len,
- const gchar **end)
-{
+g_utf8_validate (const char *str,
+ gssize max_len,
+ const gchar **end)
+{
const gchar *p;
- g_return_val_if_fail (str != NULL, FALSE);
-
- if (end)
- *end = str;
-
- p = str;
-
- while ((max_len < 0 || (p - str) < max_len) && *p)
- {
- int i, mask = 0, len;
- gunichar result;
- unsigned char c = (unsigned char) *p;
-
- UTF8_COMPUTE (c, mask, len);
-
- if (len == -1)
- break;
-
- /* check that the expected number of bytes exists in str */
- if (max_len >= 0 &&
- ((max_len - (p - str)) < len))
- break;
-
- UTF8_GET (result, p, i, mask, len);
-
- if (UTF8_LENGTH (result) != len) /* Check for overlong UTF-8 */
- break;
-
- if (result == (gunichar)-1)
- break;
-
- if (!UNICODE_VALID (result))
- break;
-
- p += len;
- }
+ if (max_len < 0)
+ p = fast_validate (str);
+ else
+ p = fast_validate_len (str, max_len);
if (end)
*end = p;
- /* See that we covered the entire length if a length was
- * passed in, or that we ended on a nul if not
- */
- if (max_len >= 0 &&
- p != (str + max_len))
- return FALSE;
- else if (max_len < 0 &&
- *p != '\0')
+ if ((max_len >= 0 && p != str + max_len) ||
+ (max_len < 0 && *p != '\0'))
return FALSE;
else
return TRUE;
@@ -1601,7 +1648,7 @@ g_utf8_validate (const gchar *str,
* integer values of @ch will not be valid. 0 is considered a valid
* character, though it's normally a string terminator.
*
- * Return value: %TRUE if @ch is a valid Unicode character
+ * Returns: %TRUE if @ch is a valid Unicode character
**/
gboolean
g_unichar_validate (gunichar ch)
@@ -1612,28 +1659,33 @@ g_unichar_validate (gunichar ch)
/**
* g_utf8_strreverse:
* @str: a UTF-8 encoded string
- * @len: the maximum length of @str to use. If @len < 0, then
- * the string is nul-terminated.
+ * @len: the maximum length of @str to use, in bytes. If @len < 0,
+ * then the string is nul-terminated.
*
* Reverses a UTF-8 string. @str must be valid UTF-8 encoded text.
* (Use g_utf8_validate() on all text before trying to use UTF-8
* utility functions with it.)
*
+ * This function is intended for programmatic uses of reversed strings.
+ * It pays no attention to decomposed characters, combining marks, byte
+ * order marks, directional indicators (LRM, LRO, etc) and similar
+ * characters which might need special handling when reversing a string
+ * for display purposes.
+ *
* Note that unlike g_strreverse(), this function returns
* newly-allocated memory, which should be freed with g_free() when
* no longer needed.
*
- * Returns: a newly-allocated string which is the reverse of @str.
+ * Returns: a newly-allocated string which is the reverse of @str
*
* Since: 2.2
*/
gchar *
-g_utf8_strreverse (const gchar *str,
- gssize len)
+g_utf8_strreverse (const gchar *str,
+ gssize len)
{
- gchar *result;
+ gchar *r, *result;
const gchar *p;
- gchar *m, *r, skip;
if (len < 0)
len = strlen (str);
@@ -1641,9 +1693,9 @@ g_utf8_strreverse (const gchar *str,
result = g_new (gchar, len + 1);
r = result + len;
p = str;
- while (*p)
+ while (r > result)
{
- skip = g_utf8_skip[*(guchar*)p];
+ gchar *m, skip = g_utf8_skip[*(guchar*) p];
r -= skip;
for (m = r; skip; skip--)
*m++ = *p++;
@@ -1652,3 +1704,44 @@ g_utf8_strreverse (const gchar *str,
return result;
}
+
+
+gchar *
+_g_utf8_make_valid (const gchar *name)
+{
+ GString *string;
+ const gchar *remainder, *invalid;
+ gint remaining_bytes, valid_bytes;
+
+ g_return_val_if_fail (name != NULL, NULL);
+
+ 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);
+ /* append U+FFFD REPLACEMENT CHARACTER */
+ g_string_append (string, "\357\277\275");
+
+ remaining_bytes -= valid_bytes + 1;
+ remainder = invalid + 1;
+ }
+
+ if (string == NULL)
+ return g_strdup (name);
+
+ g_string_append (string, remainder);
+
+ g_assert (g_utf8_validate (string->str, -1, NULL));
+
+ return g_string_free (string, FALSE);
+}