gutf8.c

嵌入式下基于MiniGUI的Web Browser

/* gutf8.c - Operations on UTF-8 strings.
 *
 * Copyright (C) 1999 Tom Tromey
 * Copyright (C) 2000 Red Hat, Inc.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the GNU
 * 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.
 */

#include "glibconfig.h"

#include <stdlib.h>
#ifdef HAVE_CODESET
#include <langinfo.h>
#endif
#include <string.h>

#include "glib.h"

#ifdef G_PLATFORM_WIN32
#include <stdio.h>
#define STRICT
#include <windows.h>
#undef STRICT
#endif

#include "libcharset.h"

#include "glibintl.h"

#define UTF8_COMPUTE(Char, Mask, Len)					      \
  if (Char < 128)							      \
    {									      \
      Len = 1;								      \
      Mask = 0x7f;							      \
    }									      \
  else if ((Char & 0xe0) == 0xc0)					      \
    {									      \
      Len = 2;								      \
      Mask = 0x1f;							      \
    }									      \
  else if ((Char & 0xf0) == 0xe0)					      \
    {									      \
      Len = 3;								      \
      Mask = 0x0f;							      \
    }									      \
  else if ((Char & 0xf8) == 0xf0)					      \
    {									      \
      Len = 4;								      \
      Mask = 0x07;							      \
    }									      \
  else if ((Char & 0xfc) == 0xf8)					      \
    {									      \
      Len = 5;								      \
      Mask = 0x03;							      \
    }									      \
  else if ((Char & 0xfe) == 0xfc)					      \
    {									      \
      Len = 6;								      \
      Mask = 0x01;							      \
    }									      \
  else									      \
    Len = -1;

#define UTF8_LENGTH(Char)              \
  ((Char) < 0x80 ? 1 :                 \
   ((Char) < 0x800 ? 2 :               \
    ((Char) < 0x10000 ? 3 :            \
     ((Char) < 0x200000 ? 4 :          \
      ((Char) < 0x4000000 ? 5 : 6)))))
   

#define UTF8_GET(Result, Chars, Count, Mask, Len)			      \
  (Result) = (Chars)[0] & (Mask);					      \
  for ((Count) = 1; (Count) < (Len); ++(Count))				      \
    {									      \
      if (((Chars)[(Count)] & 0xc0) != 0x80)				      \
	{								      \
	  (Result) = -1;						      \
	  break;							      \
	}								      \
      (Result) <<= 6;							      \
      (Result) |= ((Chars)[(Count)] & 0x3f);				      \
    }

#define UNICODE_VALID(Char)                   \
    ((Char) < 0x110000 &&                     \
     ((Char) < 0xD800 || (Char) >= 0xE000) && \
     (Char) != 0xFFFE && (Char) != 0xFFFF)
   
     
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,
  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,
  3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
};

const gchar * const g_utf8_skip = utf8_skip_data;

/**
 * g_utf8_find_prev_char:
 * @str: pointer to the beginning of a UTF-8 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 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.
 **/
gchar *
g_utf8_find_prev_char (const char *str,
		       const char *p)
{
  for (--p; p >= str; --p)
    {
      if ((*p & 0xc0) != 0x80)
	return (gchar *)p;
    }
  return NULL;
}

/**
 * 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 
 *
 * 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 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
 **/
gchar *
g_utf8_find_next_char (const gchar *p,
		       const gchar *end)
{
  if (*p)
    {
      if (end)
	for (++p; p < end && (*p & 0xc0) == 0x80; ++p)
	  ;
      else
	for (++p; (*p & 0xc0) == 0x80; ++p)
	  ;
    }
  return (p == end) ? NULL : (gchar *)p;
}

/**
 * g_utf8_prev_char:
 * @p: a pointer to a position within a UTF-8 encoded string
 *
 * 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.
 * 
 * Return value: a pointer to the found character.
 **/
gchar *
g_utf8_prev_char (const gchar *p)
{
  while (TRUE)
    {
      p--;
      if ((*p & 0xc0) != 0x80)
	return (gchar *)p;
    }
}

/**
 * g_utf8_strlen:
 * @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.
 * 
 * Returns the length of the string in characters.
 *
 * Return value: the length of the string in characters
 **/
glong
g_utf8_strlen (const gchar *p,
               gssize       max)
{
  glong len = 0;
  const gchar *start = p;

  if (max < 0)
    {
      while (*p)
        {
          p = g_utf8_next_char (p);
          ++len;
        }
    }
  else
    {
      if (max == 0 || !*p)
        return 0;
      
      p = g_utf8_next_char (p);          

      while (p - start < max && *p)
        {
          ++len;
          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)
        ++len;
    }

  return len;
}

/**
 * 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
 * valid Unicode characters, you should use g_utf8_get_char_validated()
 * instead.
 * 
 * Return value: the resulting character
 **/
gunichar
g_utf8_get_char (const gchar *p)
{
  int i, mask = 0, len;
  gunichar result;
  unsigned char c = (unsigned char) *p;

  UTF8_COMPUTE (c, mask, len);
  if (len == -1)
    return (gunichar)-1;
  UTF8_GET (result, p, i, mask, len);

  return result;
}

/**
 * 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
 **/
gchar *
g_utf8_offset_to_pointer  (const gchar *str,
			   glong        offset)    
{
  const gchar *s = str;
  while (offset--)
    s = g_utf8_next_char (s);
  
  return (gchar *)s;
}

/**
 * g_utf8_pointer_to_offset:
 * @str: a UTF-8 encoded string
 * @pos: a pointer to a position within @str
 * 
 * Converts from a pointer to position within a string to a integer
 * character offset.
 * 
 * Return value: 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++;
    }

  return offset;
}


/**
 * g_utf8_strncpy:
 * @dest: buffer to fill with characters from @src
 * @src: UTF-8 encoded string
 * @n: character count
 * 
 * Like the standard C <function>strncpy()</function> 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,
		gsize        n)
{
  const gchar *s = src;
  while (n && *s)
    {
      s = g_utf8_next_char(s);
      n--;
    }
  strncpy(dest, src, s - src);
  dest[s - src] = 0;
  return dest;
}