gdk/win32/gdkdrawable-win32.c (gdk_win32_draw_text)

2004-07-07  Tor Lillqvist  <tml@iki.fi>

	* gdk/win32/gdkdrawable-win32.c (gdk_win32_draw_text)
	* gdk/win32/gdkfont-win32.c (gdk_text_extents)
	* gdk/win32/gdkproperty-win32.c (find_common_locale,
	gdk_property_change)
	* gdk/win32/gdkselection-win32.c (gdk_selection_convert): Use
	g_utf8_to_utf16() instead of the removed _gdk_utf8_to_ucs2() (see
	below).

	* gdk/win32/gdkglobals-win32.c
	* gdk/win32/gdkmain-win32.c (_gdk_windowing_init)
	* gdk/win3/gdkprivate-win32.h: Add a variable for the TARGETS
	atom. Initialize it. Declare it. Drop the variable for the
	COMPOUND_TEXT atom.

	* gdk/win32/gdkim-win32.c (gdk_wcstombs): Don't return UTF-8. This
	function is supposed to return the string in the locale's charset
	and encoding. Use g_convert().

	(gdk_mbstowcs): Similarily, don't take an UTF-8 string, but a
	string in the locale's charset. Use g_convert().

	(_gdk_ucs2_to_utf8, _gdk_utf8_to_wcs, _gdk_utf8_to_ucs2):
	Delete. The UCS-2 functions didn't handle surrogates anyway. Use
	GLib's UTF-16 functions instead. Windows uses UTF-16.

	* gdk/win32/gdkprivate-win32.h: Remove declarations of the deleted
	functions mentioned above.

	* gdk/win32/gdkproperty-win32.c (gdk_property_change): Use CF_TEXT
	also if the string is of type STRING, i.e. ISO-8859-1, and the
	current codepage is 1252, and contains no C1 chars. Accept
	also UTF8_STRING.

	* gdk/win32/gdkselection-win32.c (_gdk_selection_property_store):
	Mark as static. When storing STRING data, convert to
	Latin-1. (#140537)
	(gdk_selection_owner_set_for_display): Now that STRING is always
	ISO-8859-1, use UTF8_STRING when sending the selection request
	to ourselves.

	(gdk_selection_convert): Handle also UTF8_STRING. (#140537, John
	Ehresman)

	(gdk_text_property_to_text_list_for_display): Make work more like
	X11 version. Do obey the encoding parameter.

	(gdk_string_to_compound_text_for_display,
	gdk_utf8_to_compound_text_for_display): Don't even pretend
	supporting COMPOUND_TEXT.

	(gdk_utf8_to_string_target): Convert to ISO-8859-1, like on X11.

	(sanitize_utf8): Zero-terminate string.

1 files changed, 18 insertions, 304 deletions

diff --git a/gdk/win32/gdkim-win32.c b/gdk/win32/gdkim-win32.c
index b31b1b5dd3..aeb29bf7dd 100644
--- a/gdk/win32/gdkim-win32.c
+++ b/gdk/win32/gdkim-win32.c
@@ -1,6 +1,6 @@
 /* GDK - The GIMP Drawing Kit
  * Copyright (C) 1995-1997 Peter Mattis, Spencer Kimball and Josh MacDonald
- * Copyright (C) 1998-2002 Tor Lillqvist
+ * Copyright (C) 1998-2004 Tor Lillqvist
  *
  * This library is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Lesser General Public
@@ -58,321 +58,35 @@ gdk_set_locale (void)
   return g_win32_getlocale ();
 }
 
-/*
- * gdk_wcstombs 
- *
- * Returns a multi-byte string converted from the specified array
- * of wide characters. The string is newly allocated. The array of
- * wide characters must be null-terminated. If the conversion is
- * failed, it returns NULL.
- *
- * On Win32, we always use UTF-8.
- */
 gchar *
 gdk_wcstombs (const GdkWChar *src)
 {
-  gint len;
-  const GdkWChar *wcp;
-  guchar *mbstr, *bp;
-
-  wcp = src;
-  len = 0;
-  while (*wcp)
-    {
-      const GdkWChar c = *wcp++;
-
-      if (c < 0x80)
-	len += 1;
-      else if (c < 0x800)
-	len += 2;
-      else if (c < 0x10000)
-	len += 3;
-      else if (c < 0x200000)
-	len += 4;
-      else if (c < 0x4000000)
-	len += 5;
-      else
-	len += 6;
-    }
-
-  mbstr = g_malloc (len + 1);
-  
-  wcp = src;
-  bp = mbstr;
-  while (*wcp)
-    {
-      int first;
-      GdkWChar c = *wcp++;
-
-      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;
-	}
-      
-      /* Woo-hoo! */
-      switch (len)
-	{
-	case 6: bp[5] = (c & 0x3f) | 0x80; c >>= 6; /* Fall through */
-	case 5: bp[4] = (c & 0x3f) | 0x80; c >>= 6; /* Fall through */
-	case 4: bp[3] = (c & 0x3f) | 0x80; c >>= 6; /* Fall through */
-	case 3: bp[2] = (c & 0x3f) | 0x80; c >>= 6; /* Fall through */
-	case 2: bp[1] = (c & 0x3f) | 0x80; c >>= 6; /* Fall through */
-	case 1: bp[0] = c | first;
-	}
-
-      bp += len;
-    }
-  *bp = 0;
-  return mbstr;
-}
-
-/* A vesion that converts from wchar_t strings to UTF-8 */
-
-gchar *
-_gdk_ucs2_to_utf8 (const wchar_t *src,
-		   gint           src_len)
-{
-  gint len;
-  const wchar_t *wcp;
-  guchar *mbstr, *bp;
-
-  wcp = src;
-  len = 0;
-  while (wcp < src + src_len)
-    {
-      const wchar_t c = *wcp++;
-
-      if (c < 0x80)
-	len += 1;
-      else if (c < 0x800)
-	len += 2;
-      else
-	len += 3;
-    }
-
-  mbstr = g_malloc (len + 1);
-  
-  wcp = src;
-  bp = mbstr;
-  while (wcp < src + src_len)
-    {
-      int first;
-      wchar_t c = *wcp++;
-
-      if (c < 0x80)
-	{
-	  first = 0;
-	  len = 1;
-	}
-      else if (c < 0x800)
-	{
-	  first = 0xc0;
-	  len = 2;
-	}
-      else
-	{
-	  first = 0xe0;
-	  len = 3;
-	}
-      
-      /* Woo-hoo! */
-      switch (len)
-	{
-	case 3: bp[2] = (c & 0x3f) | 0x80; c >>= 6; /* Fall through */
-	case 2: bp[1] = (c & 0x3f) | 0x80; c >>= 6; /* Fall through */
-	case 1: bp[0] = c | first;
-	}
-
-      bp += len;
-    }
-  *bp = 0;
-
-  return mbstr;
-}
-  
-/* Convert from UTF-8 to GdkWChar */
-
-gint
-_gdk_utf8_to_wcs (GdkWChar    *dest,
-		  const gchar *src,
-		  gint         src_len,
-		  gint         dest_max)
-{
-  guchar *cp, *end;
-  gint n;
-  
-  cp = (guchar *) src;
-  end = cp + src_len;
-  n = 0;
-  while (cp != end && dest != dest + dest_max)
-    {
-      gint i, mask = 0, len;
-      guchar c = *cp;
-
-      if (c < 0x80)
-	{
-	  len = 1;
-	  mask = 0x7f;
-	}
-      else if ((c & 0xe0) == 0xc0)
-	{
-	  len = 2;
-	  mask = 0x1f;
-	}
-      else if ((c & 0xf0) == 0xe0)
-	{
-	  len = 3;
-	  mask = 0x0f;
-	}
-      else if ((c & 0xf8) == 0xf0)
-	{
-	  len = 4;
-	  mask = 0x07;
-	}
-      else if ((c & 0xfc) == 0xf8)
-	{
-	  len = 5;
-	  mask = 0x03;
-	}
-      else if ((c & 0xfc) == 0xfc)
-	{
-	  len = 6;
-	  mask = 0x01;
-	}
-      else
-	return -1;
+  gchar *utf8;
+  gchar *retval;
+  const gchar *charset;
 
-      if (cp + len > end)
-	return -1;
-
-      *dest = (cp[0] & mask);
-      for (i = 1; i < len; i++)
-	{
-	  if ((cp[i] & 0xc0) != 0x80)
-	    return -1;
-	  *dest <<= 6;
-	  *dest |= (cp[i] & 0x3f);
-	}
-      if (*dest == -1)
-	return -1;
-
-      cp += len;
-      dest++;
-      n++;
-    }
-  if (cp != end)
-    return -1;
-
-  return n;
+  g_get_charset (&charset);
+  return g_convert (src, -1, charset, "UCS-4LE", NULL, NULL, NULL);
 }
 
-/*
- * gdk_mbstowcs
- *
- * Converts the specified string into GDK wide characters, and,
- * returns the number of wide characters written. The string 'src'
- * must be null-terminated. If the conversion is failed, it returns
- * -1.
- *
- * On Win32, the string is assumed to be in UTF-8.  Also note that
- * GdkWChar is 32 bits, while wchar_t, and the wide characters the
- * Windows API uses, are 16 bits!
- */
-
 gint
 gdk_mbstowcs (GdkWChar    *dest,
 	      const gchar *src,
 	      gint         dest_max)
 {
-  return _gdk_utf8_to_wcs (dest, src, strlen (src), dest_max);
-}
-
-
-/* A version that converts to a wchar_t string */
-
-gint
-_gdk_utf8_to_ucs2 (wchar_t     *dest,
-		   const gchar *src,
-		   gint         src_len,
-		   gint         dest_max)
-{
-  wchar_t *wcp;
-  guchar *cp, *end;
-  gint n;
-  
-  wcp = dest;
-  cp = (guchar *) src;
-  end = cp + src_len;
-  n = 0;
-  while (cp != end && wcp != dest + dest_max)
-    {
-      gint i, mask = 0, len;
-      guchar c = *cp;
-
-      if (c < 0x80)
-	{
-	  len = 1;
-	  mask = 0x7f;
-	}
-      else if ((c & 0xe0) == 0xc0)
-	{
-	  len = 2;
-	  mask = 0x1f;
-	}
-      else if ((c & 0xf0) == 0xe0)
-	{
-	  len = 3;
-	  mask = 0x0f;
-	}
-      else /* Other lengths are not possible with 16-bit wchar_t! */
-	return -1;
-
-      if (cp + len > end)
-	return -1;
+  gint retval;
+  gsize nwritten;
+  gint n_ucs4;
+  gunichar *ucs4;
+  const gchar *charset;
 
-      *wcp = (cp[0] & mask);
-      for (i = 1; i < len; i++)
-	{
-	  if ((cp[i] & 0xc0) != 0x80)
-	    return -1;
-	  *wcp <<= 6;
-	  *wcp |= (cp[i] & 0x3f);
-	}
-      if (*wcp == 0xFFFF)
-	return -1;
+  g_get_charset (&charset);
+  ucs4 = g_convert (src, -1, "UCS-4LE", charset, NULL, &nwritten, NULL);
+  n_ucs4 = nwritten * sizeof (GdkWChar);
 
-      cp += len;
-      wcp++;
-      n++;
-    }
-  if (cp != end)
-    return -1;
+  retval = MIN (dest_max, n_ucs4);
+  memmove (dest, ucs4, retval * sizeof (GdkWChar));
+  g_free (ucs4);
 
-  return n;
+  return retval;
 }