Remove get_utf8_char/utf16_char_to_utf8 in favour of glib

g_utf8_get_char_validated/g_unichar_to_utf8.


git-svn-id: file:///var/www/svn.irssi.org/SVN/irssi/trunk@4893 dbcabf3a-b0e7-0310-adc4-f8d773084564

src/fe-common/core/utf8.c

@@ -24,74 +24,6 @@
 
 #include "module.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_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);				      \
-    }
-
-int get_utf8_char(const unsigned char **ptr, int len, unichar *chr_r)
-{
-	int i, result, mask, chrlen;
-
-        mask = 0;
-	UTF8_COMPUTE(**ptr, mask, chrlen);
-	if (chrlen == -1)
-		return -2;
-
-	if (chrlen > len)
-                return -1;
-
-	UTF8_GET(result, *ptr, i, mask, chrlen);
-	if (result == -1)
-                return -2;
-	
-	*chr_r = (unichar) result;
-	*ptr += chrlen-1;
-        return result;
-}
-
 int strlen_utf8(const char *str)
 {
 	const unsigned char *p = (const unsigned char *) str;
@@ -99,65 +31,27 @@ int strlen_utf8(const char *str)
 	unichar chr_r;
 
 	len = 0;
-	while (*p != '\0' && get_utf8_char(&p, 6, &chr_r) > 0) {
+	while (*p != '\0') {
+		chr_r = g_utf8_get_char_validated(p, -1);
+		if (chr_r & 0x80000000)
+			break;
 		len++;
-                p++;
+                p = g_utf8_next_char(p);
 	}
         return len;
 }
 
-int utf16_char_to_utf8(unichar c, char *outbuf)
-{
-	int len, i, first;
-
-        len = 0;
-	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;
-}
-
 void utf8_to_utf16(const char *str, unichar *out)
 {
 	const unsigned char *p = (const unsigned char *) str;
-        int i, result, mask, len;
+	unichar result;
 
 	while (*p != '\0') {
-                mask = 0;
+		result = g_utf8_get_char_validated(p, -1);
-		UTF8_COMPUTE(*p, mask, len);
+		if (result & 0x80000000)
-		if (len == -1)
+			break;
-                        break;
 
-		UTF8_GET(result, p, i, mask, len);
+                p = g_utf8_next_char(p);
-		if (result == -1)
-                        break;
-
-                p += len;
                 *out++ = result;
 	}
 
@@ -169,7 +63,7 @@ void utf16_to_utf8(const unichar *str, char *out)
 	int len;
 
 	while (*str != '\0') {
-		len = utf16_char_to_utf8(*str, out);
+		len = g_unichar_to_utf8(*str, out);
                 out += len;
 
 		str++;
@@ -185,7 +79,7 @@ void utf16_to_utf8_with_pos(const unichar *str, int spos, char *out, int *opos)
 
 	*opos = 0;
 	while (*str != '\0') {
-		len = utf16_char_to_utf8(*str, out);
+		len = g_unichar_to_utf8(*str, out);
                 out += len;
 
 		str++;

src/fe-common/core/utf8.h

@@ -1,19 +1,12 @@
 #ifndef __UTF8_H
 #define __UTF8_H
 
-/* Returns -2 = invalid, -1 = need more data, otherwise unichar. */
-int get_utf8_char(const unsigned char **ptr, int len, unichar *chr_r);
-
 /* Returns length of UTF8 string */
 int strlen_utf8(const char *str);
 
 /* UTF-8 -> unichar string. The NUL is copied as well. */
 void utf8_to_utf16(const char *str, unichar *out);
 
-/* unichar -> UTF-8 string. outbuf must be at least 6 chars long.
-   Returns outbuf string length. */
-int utf16_char_to_utf8(unichar c, char *outbuf);
-
 /* unichar -> UTF-8 string. The NUL is copied as well.
    Make sure out is at least 6 x length of str. */
 void utf16_to_utf8(const unichar *str, char *out);

src/fe-text/gui-readline.c

@@ -295,7 +295,7 @@ static void paste_send(void)
 				    active_win->active);
 			g_string_truncate(str, 0);
 		} else if (active_entry->utf8) {
-			out[utf16_char_to_utf8(arr[i], out)] = '\0';
+			out[g_unichar_to_utf8(arr[i], out)] = '\0';
 			g_string_append(str, out);
 		} else if (term_type == TERM_TYPE_BIG5) {
 			if (arr[i] > 0xff)
@@ -490,7 +490,7 @@ static void sig_gui_key_pressed(gpointer keyp)
 		}
 	} else {
                 /* need to convert to utf8 */
-		str[utf16_char_to_utf8(key, str)] = '\0';
+		str[g_unichar_to_utf8(key, str)] = '\0';
 	}
 
 	if (strcmp(str, "^") == 0) {

src/fe-text/term-terminfo.c

@@ -389,7 +389,7 @@ static void term_addch_utf8(TERM_WINDOW *window, unichar chr)
 	char buf[10];
 	int i, len;
 
-	len = utf16_char_to_utf8(chr, buf);
+	len = g_unichar_to_utf8(chr, buf);
 	for (i = 0;  i < len; i++)
                 putc(buf[i], window->term->out);
 }