gutf8.c

嵌入式下基于MiniGUI的Web Browser

/* unicode_strchr */

/**
 * g_unichar_to_utf8:
 * @c: a ISO10646 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
 **/
int
g_unichar_to_utf8 (gunichar c,
		   gchar   *outbuf)
{
  guint len = 0;    
  int first;
  int i;

  if (c < 0x80)
    {
      first = 0;
      len = 1;
    }
  else if (c < 0x800)
    {
      first = 0xc0;
      len = 2;
    }
  else if (c < 0x10000)
    {
      first = 0xe0;
      len = 3;
    }
   else if (c < 0x200000)
    {
      first = 0xf0;
      len = 4;
    }
  else if (c < 0x4000000)
    {
      first = 0xf8;
      len = 5;
    }
  else
    {
      first = 0xfc;
      len = 6;
    }

  if (outbuf)
    {
      for (i = len - 1; i > 0; --i)
	{
	  outbuf[i] = (c & 0x3f) | 0x80;
	  c >>= 6;
	}
      outbuf[0] = c | first;
    }

  return len;
}

/**
 * g_utf8_strchr:
 * @p: a nul-terminated UTF-8 encoded string
 * @len: the maximum length of @p
 * @c: a ISO10646 character
 * 
 * Finds the leftmost occurrence of the given ISO10646 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.
 **/
gchar *
g_utf8_strchr (const char *p,
	       gssize      len,
	       gunichar    c)
{
  gchar ch[10];

  gint charlen = g_unichar_to_utf8 (c, ch);
  ch[charlen] = '\0';
  
  return g_strstr_len (p, len, ch);
}


/**
 * g_utf8_strrchr:
 * @p: a nul-terminated UTF-8 encoded string
 * @len: the maximum length of @p
 * @c: a ISO10646 character
 * 
 * Find the rightmost occurrence of the given ISO10646 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.
 **/
gchar *
g_utf8_strrchr (const char *p,
		gssize      len,
		gunichar    c)
{
  gchar ch[10];

  gint charlen = g_unichar_to_utf8 (c, ch);
  ch[charlen] = '\0';
  
  return g_strrstr_len (p, len, ch);
}


/* Like g_utf8_get_char, but take a maximum length
 * and return (gunichar)-2 on incomplete trailing character
 */
static inline gunichar
g_utf8_get_char_extended (const  gchar *p,
			  gssize max_len)  
{
  guint i, len;
  gunichar wc = (guchar) *p;

  if (wc < 0x80)
    {
      return wc;
    }
  else if (wc < 0xc0)
    {
      return (gunichar)-1;
    }
  else if (wc < 0xe0)
    {
      len = 2;
      wc &= 0x1f;
    }
  else if (wc < 0xf0)
    {
      len = 3;
      wc &= 0x0f;
    }
  else if (wc < 0xf8)
    {
      len = 4;
      wc &= 0x07;
    }
  else if (wc < 0xfc)
    {
      len = 5;
      wc &= 0x03;
    }
  else if (wc < 0xfe)
    {
      len = 6;
      wc &= 0x01;
    }
  else
    {
      return (gunichar)-1;
    }
  
  if (max_len >= 0 && len > max_len)
    {
      for (i = 1; i < max_len; i++)
	{
	  if ((((guchar *)p)[i] & 0xc0) != 0x80)
	    return (gunichar)-1;
	}
      return (gunichar)-2;
    }

  for (i = 1; i < len; ++i)
    {
      gunichar ch = ((guchar *)p)[i];
      
      if ((ch & 0xc0) != 0x80)
	{
	  if (ch)
	    return (gunichar)-1;
	  else
	    return (gunichar)-2;
	}

      wc <<= 6;
      wc |= (ch & 0x3f);
    }

  if (UTF8_LENGTH(wc) != len)
    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.
 * 
 * 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 @len < 0, then
 *       the string is nul-terminated.
 * @items_written: 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.
 * 
 * Return value: 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;

  g_return_val_if_fail (str != NULL, NULL);

  p = str;
  n_chars = 0;
  if (len < 0)
    {
      while (*p)
	{
	  p = g_utf8_next_char (p);
	  ++n_chars;
	}
    }
  else
    {
      while (p < str + len && *p)
	{
	  p = g_utf8_next_char (p);
	  ++n_chars;
	}
    }
  
  result = g_new (gunichar, n_chars + 1);
  
  p = str;
  for (i=0; i < n_chars; i++)
    {
      gunichar wc = ((unsigned char *)p)[0];

      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
	    {
	      charlen = 6;
	      wc &= 0x01;
	    }

	  for (j = 1; j < charlen; j++)
	    {
	      wc <<= 6;
	      wc |= ((unsigned char *)p)[j] & 0x3f;
	    }

	  result[i] = wc;
	  p += charlen;
	}
    }
  result[i] = 0;

  if (items_written)
    *items_written = i;

  return result;
}

/**
 * g_unichar_validate:
 * @ch: a Unicode character
 * 
 * Checks whether @ch is a valid Unicode character. Some possible
 * 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
 **/
gboolean
g_unichar_validate (gunichar ch)
{
  return UNICODE_VALID (ch);
}