#include <string.h>
#include "glib.h"
+#include "galias.h"
#ifdef G_PLATFORM_WIN32
#include <stdio.h>
#undef STRICT
#endif
+#include "libcharset/libcharset.h"
+
#include "glibintl.h"
#define UTF8_COMPUTE(Char, Mask, Len) \
#define UNICODE_VALID(Char) \
((Char) < 0x110000 && \
- ((Char) < 0xD800 || (Char) >= 0xE000) && \
- (Char) != 0xFFFE && (Char) != 0xFFFF)
+ (((Char) & 0xFFFFF800) != 0xD800) && \
+ ((Char) < 0xFDD0 || (Char) > 0xFDEF) && \
+ ((Char) & 0xFFFE) != 0xFFFE)
-gchar g_utf8_skip[256] = {
+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,
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,
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,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
- 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,0,0
+ 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
};
+const gchar * const g_utf8_skip = utf8_skip_data;
+
/**
* g_utf8_find_prev_char:
- * @str: pointer to the beginning of a UTF-8 string
+ * @str: pointer to the beginning of a UTF-8 encoded string
* @p: pointer to some position within @str
*
* 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.
*
- * @p does not have to be at the beginning of a UTF-8 chracter. No check
+ * @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.
*
g_utf8_find_prev_char (const char *str,
const char *p)
{
- for (--p; p > str; --p)
+ for (--p; p >= str; --p)
{
if ((*p & 0xc0) != 0x80)
return (gchar *)p;
* 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 NULL terminated, in which case
+ * that the string is nul-terminated, in which case
* the returned value will be
*
- * Find the start of the next utf-8 character in the string after @p
+ * Finds the start of the next UTF-8 character in the string after @p.
*
- * @p does not have to be at the beginning of a UTF-8 chracter. No check
+ * @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.
*
* g_utf8_prev_char:
* @p: a pointer to a position within a UTF-8 encoded string
*
- * Find the previous UTF-8 character in the string before @p.
+ * Finds the previous UTF-8 character in the string 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. If @p might be the first
- * character of the string, you must use g_utf8_find_prev_char instead.
+ * character of the string, you must use g_utf8_find_prev_char() instead.
*
* Return value: a pointer to the found character.
**/
/**
* g_utf8_strlen:
- * @p: pointer to the start of a UTF-8 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.
+ * nul-terminated. If @max is 0, @p will not be examined and
+ * may be %NULL.
*
+ * Returns the length of the string in characters.
+ *
* Return value: the length of the string in characters
**/
glong
{
glong len = 0;
const gchar *start = p;
+ g_return_val_if_fail (p != NULL || max == 0, 0);
if (max < 0)
{
/**
* g_utf8_get_char:
- * @p: a pointer to unicode character encoded as UTF-8
+ * @p: a pointer to Unicode character encoded as UTF-8
*
- * Convert a sequence of bytes encoded as UTF-8 to a unicode character.
+ * 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.
+ * 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
**/
/**
* g_utf8_offset_to_pointer:
* @str: a UTF-8 encoded string
- * @offset: a character offset within the 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.
+ *
* Return value: the resulting pointer
**/
gchar *
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;
}
* @pos: a pointer to a position within @str
*
* Converts from a pointer to position within a string to a integer
- * character offset
+ * 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;
}
/**
* g_utf8_strncpy:
* @dest: buffer to fill with characters from @src
- * @src: UTF-8 string
+ * @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
**/
gchar *
-g_utf8_strncpy (gchar *dest, const gchar *src, size_t n)
+g_utf8_strncpy (gchar *dest,
+ const gchar *src,
+ gsize n)
{
const gchar *s = src;
while (n && *s)
return dest;
}
-static gboolean
-g_utf8_get_charset_internal (char **a)
-{
- char *charset = getenv("CHARSET");
+G_LOCK_DEFINE_STATIC (aliases);
- if (charset && a && ! *a)
- *a = charset;
+static GHashTable *
+get_alias_hash (void)
+{
+ static GHashTable *alias_hash = NULL;
+ const char *aliases;
- if (charset && strstr (charset, "UTF-8"))
- return TRUE;
+ G_LOCK (aliases);
-#ifdef HAVE_CODESET
- charset = nl_langinfo(CODESET);
- if (charset)
+ if (!alias_hash)
{
- if (a && ! *a)
- *a = charset;
- if (strcmp (charset, "UTF-8") == 0)
- return TRUE;
+ 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);
+ }
}
-#endif
-
-#if 0 /* #ifdef _NL_CTYPE_CODESET_NAME */
- charset = nl_langinfo (_NL_CTYPE_CODESET_NAME);
- if (charset)
+
+ 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)
{
- if (a && ! *a)
- *a = charset;
- if (strcmp (charset, "UTF-8") == 0)
+ *a = charset;
+
+ if (charset && strstr (charset, "UTF-8"))
return TRUE;
+ else
+ return FALSE;
}
-#endif
-#ifdef G_PLATFORM_WIN32
- if (a && ! *a)
+ /* 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)
{
- static char codepage[10];
+ *a = charset;
- sprintf (codepage, "CP%d", GetACP ());
- *a = codepage;
- /* What about codepage 1200? Is that UTF-8? */
- return FALSE;
+ if (charset && strstr (charset, "UTF-8"))
+ return TRUE;
+ else
+ return FALSE;
}
-#else
- if (a && ! *a)
- *a = "US-ASCII";
-#endif
/* Assume this for compatibility at present. */
+ *a = "US-ASCII";
+
return FALSE;
}
-static int utf8_locale_cache = -1;
-static char *utf8_charset_cache = NULL;
+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:
gboolean
g_get_charset (G_CONST_RETURN char **charset)
{
- if (utf8_locale_cache != -1)
+ static GStaticPrivate cache_private = G_STATIC_PRIVATE_INIT;
+ GCharsetCache *cache = g_static_private_get (&cache_private);
+ const gchar *raw;
+
+ if (!cache)
{
- if (charset)
- *charset = utf8_charset_cache;
- return utf8_locale_cache;
+ cache = g_new0 (GCharsetCache, 1);
+ g_static_private_set (&cache_private, cache, charset_cache_free);
}
- utf8_locale_cache = g_utf8_get_charset_internal (&utf8_charset_cache);
- if (charset)
- *charset = utf8_charset_cache;
- return utf8_locale_cache;
+
+ 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 @out.
+ * and nothing will be written to @outbuf.
*
- * Convert a single character to utf8
+ * Converts a single character to UTF-8.
*
* Return value: number of bytes written
**/
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 string
- * @p_len: the maximum length of p
- * @c: a iso-10646 character
+ * @p: a nul-terminated UTF-8 encoded string
+ * @len: the maximum length of @p
+ * @c: a Unicode character
*
- * Find the leftmost occurence of the given iso-10646 character
- * in a UTF-8 string, while limiting the search to p_len bytes.
- * If len is -1, allow unbounded search.
+ * 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
- * a pointer to the start of the leftmost of the character in the string.
+ * 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.
**/
gchar *
g_utf8_strchr (const char *p,
- gssize p_len,
+ gssize len,
gunichar c)
{
gchar ch[10];
- gint len = g_unichar_to_utf8 (c, ch);
- ch[len] = '\0';
+ gint charlen = g_unichar_to_utf8 (c, ch);
+ ch[charlen] = '\0';
- return g_strstr_len (p, p_len, ch);
+ return g_strstr_len (p, len, ch);
}
/**
* g_utf8_strrchr:
- * @p: a nul-terminated utf-8 string
- * @p_len: the maximum length of p
- * @c: a iso-10646 character/
+ * @p: a nul-terminated UTF-8 encoded string
+ * @len: the maximum length of @p
+ * @c: a Unicode character
*
- * Find the rightmost occurence of the given iso-10646 character
- * in a UTF-8 string, while limiting the search to p_len bytes.
- * If len is -1, allow unbounded search.
+ * 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
- * a pointer to the start of the rightmost of the character in the string.
+ * 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.
**/
gchar *
g_utf8_strrchr (const char *p,
- gssize p_len,
+ gssize len,
gunichar c)
{
gchar ch[10];
- gint len = g_unichar_to_utf8 (c, ch);
- ch[len] = '\0';
+ gint charlen = g_unichar_to_utf8 (c, ch);
+ ch[charlen] = '\0';
- return g_strrstr_len (p, p_len, ch);
+ return g_strrstr_len (p, len, ch);
}
* and return (gunichar)-2 on incomplete trailing character
*/
static inline gunichar
-g_utf8_get_char_extended (const gchar *p, gsize max_len)
+g_utf8_get_char_extended (const gchar *p,
+ gssize max_len)
{
guint i, len;
gunichar wc = (guchar) *p;
}
/**
+ * 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.
+ *
+ * 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.
+ **/
+gunichar
+g_utf8_get_char_validated (const gchar *p,
+ gssize max_len)
+{
+ gunichar result = g_utf8_get_char_extended (p, max_len);
+
+ if (result & 0x80000000)
+ return result;
+ else if (!UNICODE_VALID (result))
+ return (gunichar)-1;
+ else
+ return result;
+}
+
+/**
* g_utf8_to_ucs4_fast:
* @str: a UTF-8 encoded string
- * @len: the maximum length of @str to use. If < 0, then
- * the string is %NULL terminated.
+ * @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.
*
* but does no error checking on the input.
*
* Return value: a pointer to a newly allocated UCS-4 string.
- * This value must be freed with g_free()
+ * This value must be freed with g_free().
**/
gunichar *
g_utf8_to_ucs4_fast (const gchar *str,
/**
* g_utf8_to_ucs4:
* @str: a UTF-8 encoded string
- * @len: the maximum length of @str to use. If < 0, then
- * the string is %NULL terminated.
+ * @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
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)
/**
* g_ucs4_to_utf8:
* @str: a UCS-4 encoded string
- * @len: the maximum length of @str to use. If < 0, then
- * the string is %NULL terminated.
- * @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 terminated with a 0 character.
+ * @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"));
goto err_out;
/**
* g_utf16_to_utf8:
* @str: a UTF-16 encoded string
- * @len: the maximum length of @str to use. If < 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 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
*
* 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.
*
* Return value: a pointer to a newly allocated UTF-8 string.
* This value must be freed with g_free(). If an
/**
* g_utf16_to_ucs4:
* @str: a UTF-16 encoded string
- * @len: the maximum length of @str to use. If < 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 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
/**
* g_utf8_to_utf16:
* @str: a UTF-8 encoded string
- * @len: the maximum length of @str to use. If < 0, then
- * the string is %NULL terminated.
-
+ * @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 %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.
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)
/**
* g_ucs4_to_utf16:
* @str: a UCS-4 encoded string
- * @len: the maximum length of @str to use. If < 0, then
- * the string is terminated with a zero character.
+ * @len: the maximum length (number of characters) 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.
+ * @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.
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;
+
+ for (p = str; (max_len < 0 || (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 >= 0 && 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 >= 0 && 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 >= 0 && 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).
*
- * Returns TRUE if all of @str was valid. Many GLib and GTK+
- * routines <emphasis>require</emphasis> valid UTF8 as input;
+ * 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;
* 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.
+ * 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_unichar_validate:
* @ch: a Unicode character
{
return UNICODE_VALID (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.
+ *
+ * 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.)
+ *
+ * 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.
+ *
+ * Since: 2.2
+ */
+gchar *
+g_utf8_strreverse (const gchar *str,
+ gssize len)
+{
+ gchar *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)
+ {
+ skip = g_utf8_skip[*(guchar*)p];
+ r -= skip;
+ for (m = r; skip; skip--)
+ *m++ = *p++;
+ }
+ result[len] = 0;
+
+ return result;
+}
+
+#define __G_UTF8_C__
+#include "galiasdef.c"
projects / platform / upstream / glib.git / blobdiff