* Boston, MA 02111-1307, USA.
*/
-#include <config.h>
+#include "config.h"
#include <stdlib.h>
#ifdef HAVE_CODESET
#endif
#include <string.h>
-#include "glib.h"
-
#ifdef G_PLATFORM_WIN32
#include <stdio.h>
#define STRICT
#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) \
(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).
+ *
+ * The last two checks cover "Noncharacter": defined as:
+ * "A code point that is permanently reserved for
+ * internal use, and that should never be interchanged. In
+ * Unicode 3.1, these consist of the values U+nFFFE and U+nFFFF
+ * (where n is from 0 to 10_16) and the values U+FDD0..U+FDEF."
+ *
+ * @param Char the character
+ */
#define UNICODE_VALID(Char) \
((Char) < 0x110000 && \
(((Char) & 0xFFFFF800) != 0xD800) && \
*
* 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
/**
* 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.
*
/**
* 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
+ * nul-terminated. If @max is 0, @p will not be examined and
* may be %NULL.
- *
- * Returns the length of the string in characters.
+ *
+ * Computes the length of the string in characters, not including
+ * the terminating nul character.
*
* Return value: the length of the string in characters
**/
{
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;
}
* 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.
- *
+ *
+ * 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><para>
+ * 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.
+ * </para></note>
+ *
* Return value: 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;
}
*
* 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
**/
{
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;
}
* @src: UTF-8 encoded string
* @n: character count
*
- * Like the standard C <function>strncpy()</function> function, but
+ * 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
/* As an abuse of the alias table, the following routines gets
* the charsets that are aliases for the canonical name.
*/
-const char **
+G_GNUC_INTERNAL const char **
_g_charset_get_aliases (const char *canonical_name)
{
GHashTable *alias_hash = get_alias_hash ();
* 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.)
+ * Obtains the character set for the <link linkend="setlocale">current
+ * locale</link>; 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.)
+ *
+ * On Windows the character set returned by this function is the
+ * so-called system default ANSI code-page. That is the character set
+ * used by the "narrow" versions of C library and Win32 functions that
+ * handle file names. It might be different from the character set
+ * used by the C library's current locale.
*
* The return value is %TRUE if the locale's encoding is UTF-8, in that
* case you can perhaps avoid calling g_convert().
* Return value: %TRUE if the returned charset is UTF-8
**/
gboolean
-g_get_charset (G_CONST_RETURN char **charset)
+g_get_charset (const char **charset)
{
static GStaticPrivate cache_private = G_STATIC_PRIVATE_INIT;
GCharsetCache *cache = g_static_private_get (&cache_private);
/**
* 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.
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;
* 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.
*
* 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.
*
/* 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;
}
{
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++)
{
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;
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
* 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.
+ * 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)
{
- 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;
/**
* 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.
+ * @len: the maximum length of @str to use, in bytes. If @len < 0,
+ * then the string is nul-terminated.
* @items_written: location to store the number of characters in the
* result, or %NULL.
*
/**
* 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.
+ * @len: the maximum length of @str to use, in bytes. 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
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)
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;
}
/**
* 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.
+ * @len: the maximum length (number of characters) of @str to use.
+ * If @len < 0, then the string is nul-terminated.
+ * @items_read: location to store number of characters 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.
* 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.
+ * @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,
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;
}
/**
* 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.
+ * @len: the maximum length (number of <type>gunichar2</type>) of @str to use.
+ * If @len < 0, then the string is nul-terminated.
* @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
*
* 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
+ * ambiguous endianess.
+ *
+ * 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.
+ *
* 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
**/
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
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;
}
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;
}
}
{
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;
}
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;
}
/**
* 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.
+ * @len: the maximum length (number of <type>gunichar2</type>) of @str to use.
+ * If @len < 0, then the string is nul-terminated.
* @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
* %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
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;
}
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;
}
}
{
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;
}
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;
}
/**
* 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.
+ * @len: the maximum length (number of bytes) 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.
+ * @items_written: location to store number of <type>gunichar2</type> written,
+ * or %NULL.
+ * The value stored here does not include the trailing 0.
* @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.
*
- * 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
**/
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;
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)
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;
}
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;
}
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;
}
/**
* 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.
+ * @len: the maximum length (number of characters) 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 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.
+ * @items_written: location to store number of <type>gunichar2</type>
+ * written, or %NULL. The value stored here does not
+ * include the trailing 0.
* @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.
*
- * 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.
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;
}
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;
}
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
+ * @max_len: max bytes to validate, or -1 to go until NUL
* @end: 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 NUL is met before @max_len bytes have been read.
*
* Returns %TRUE if all of @str was valid. Many GLib and GTK+
* routines <emphasis>require</emphasis> valid UTF-8 as input;
* Return value: %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;
/**
* 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.
* 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);
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++;
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);
+}