drw.c: use the same pattern as ellipsis_width to check for infinite recursion

previously drw_text would do the width calculations as if
invalid utf8 sequences were replaced with U+FFFD but would pass
the invalid utf8 sequence to xft to render where xft would just
cut it off at the first invalid byte.

this change makes invalid utf8 render as U+FFFD and avoids
sending invalid sequences to xft. the following can be used to
check the behavior before and after the patch:

	$ printf "0\xef1234567\ntest" | dmenu

Ref: https://lists.suckless.org/dev/2407/35646.html

drw.c

@@ -9,54 +9,40 @@
 #include "util.h"
 
 #define UTF_INVALID 0xFFFD
-#define UTF_SIZ     4
 
-static const unsigned char utfbyte[UTF_SIZ + 1] = {0x80,    0, 0xC0, 0xE0, 0xF0};
+static int
-static const unsigned char utfmask[UTF_SIZ + 1] = {0xC0, 0x80, 0xE0, 0xF0, 0xF8};
+utf8decode(const char *s_in, long *u, int *err)
-static const long utfmin[UTF_SIZ + 1] = {       0,    0,  0x80,  0x800,  0x10000};
-static const long utfmax[UTF_SIZ + 1] = {0x10FFFF, 0x7F, 0x7FF, 0xFFFF, 0x10FFFF};
-
-static long
-utf8decodebyte(const char c, size_t *i)
 {
-	for (*i = 0; *i < (UTF_SIZ + 1); ++(*i))
+	static const unsigned char lens[] = {
-		if (((unsigned char)c & utfmask[*i]) == utfbyte[*i])
+		/* 0XXXX */ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
-			return (unsigned char)c & ~utfmask[*i];
+		/* 10XXX */ 0, 0, 0, 0, 0, 0, 0, 0,  /* invalid */
-	return 0;
+		/* 110XX */ 2, 2, 2, 2,
-}
+		/* 1110X */ 3, 3,
+		/* 11110 */ 4,
+		/* 11111 */ 0,  /* invalid */
+	};
+	static const unsigned char leading_mask[] = { 0x7F, 0x1F, 0x0F, 0x07 };
+	static const unsigned int overlong[] = { 0x0, 0x80, 0x0800, 0x10000 };
 
-static size_t
+	const unsigned char *s = (const unsigned char *)s_in;
-utf8validate(long *u, size_t i)
+	int len = lens[*s >> 3];
-{
-	if (!BETWEEN(*u, utfmin[i], utfmax[i]) || BETWEEN(*u, 0xD800, 0xDFFF))
 	*u = UTF_INVALID;
-	for (i = 1; *u > utfmax[i]; ++i)
+	*err = 1;
-		;
+	if (len == 0)
-	return i;
-}
-
-static size_t
-utf8decode(const char *c, long *u, size_t clen)
-{
-	size_t i, j, len, type;
-	long udecoded;
-
-	*u = UTF_INVALID;
-	if (!clen)
-		return 0;
-	udecoded = utf8decodebyte(c[0], &len);
-	if (!BETWEEN(len, 1, UTF_SIZ))
 		return 1;
-	for (i = 1, j = 1; i < clen && j < len; ++i, ++j) {
-		udecoded = (udecoded << 6) | utf8decodebyte(c[i], &type);
-		if (type)
-			return j;
-	}
-	if (j < len)
-		return 0;
-	*u = udecoded;
-	utf8validate(u, len);
 
+	long cp = s[0] & leading_mask[len - 1];
+	for (int i = 1; i < len; ++i) {
+		if (s[i] == '\0' || (s[i] & 0xC0) != 0x80)
+			return i;
+		cp = (cp << 6) | (s[i] & 0x3F);
+	}
+	/* out of range, surrogate, overlong encoding */
+	if (cp > 0x10FFFF || (cp >> 11) == 0x1B || cp < overlong[len - 1])
+		return len;
+
+	*err = 0;
+	*u = cp;
 	return len;
 }
 
@@ -242,7 +228,7 @@ drw_text(Drw *drw, int x, int y, unsigned int w, unsigned int h, unsigned int lp
 	unsigned int tmpw, ew, ellipsis_w = 0, ellipsis_len, hash, h0, h1;
 	XftDraw *d = NULL;
 	Fnt *usedfont, *curfont, *nextfont;
-	int utf8strlen, utf8charlen, render = x || y || w || h;
+	int utf8strlen, utf8charlen, utf8err, render = x || y || w || h;
 	long utf8codepoint = 0;
 	const char *utf8str;
 	FcCharSet *fccharset;
@@ -251,7 +237,8 @@ drw_text(Drw *drw, int x, int y, unsigned int w, unsigned int h, unsigned int lp
 	XftResult result;
 	int charexists = 0, overflow = 0;
 	/* keep track of a couple codepoints for which we have no match. */
-	static unsigned int nomatches[128], ellipsis_width;
+	static unsigned int nomatches[128], ellipsis_width, invalid_width;
+	static const char invalid[] = "<EFBFBD>";
 
 	if (!drw || (render && (!drw->scheme || !w)) || !text || !drw->fonts)
 		return 0;
@@ -271,12 +258,14 @@ drw_text(Drw *drw, int x, int y, unsigned int w, unsigned int h, unsigned int lp
 	usedfont = drw->fonts;
 	if (!ellipsis_width && render)
 		ellipsis_width = drw_fontset_getwidth(drw, "...");
+	if (!invalid_width && render)
+		invalid_width = drw_fontset_getwidth(drw, invalid);
 	while (1) {
-		ew = ellipsis_len = utf8strlen = 0;
+		ew = ellipsis_len = utf8err = utf8charlen = utf8strlen = 0;
 		utf8str = text;
 		nextfont = NULL;
 		while (*text) {
-			utf8charlen = utf8decode(text, &utf8codepoint, UTF_SIZ);
+			utf8charlen = utf8decode(text, &utf8codepoint, &utf8err);
 			for (curfont = drw->fonts; curfont; curfont = curfont->next) {
 				charexists = charexists || XftCharExists(drw->dpy, curfont->xfont, utf8codepoint);
 				if (charexists) {
@@ -298,9 +287,9 @@ drw_text(Drw *drw, int x, int y, unsigned int w, unsigned int h, unsigned int lp
 						else
 							utf8strlen = ellipsis_len;
 					} else if (curfont == usedfont) {
-						utf8strlen += utf8charlen;
 						text += utf8charlen;
-						ew += tmpw;
+						utf8strlen += utf8err ? 0 : utf8charlen;
+						ew += utf8err ? 0 : tmpw;
 					} else {
 						nextfont = curfont;
 					}
@@ -308,7 +297,7 @@ drw_text(Drw *drw, int x, int y, unsigned int w, unsigned int h, unsigned int lp
 				}
 			}
 
-			if (overflow || !charexists || nextfont)
+			if (overflow || !charexists || nextfont || utf8err)
 				break;
 			else
 				charexists = 0;
@@ -323,6 +312,12 @@ drw_text(Drw *drw, int x, int y, unsigned int w, unsigned int h, unsigned int lp
 			x += ew;
 			w -= ew;
 		}
+		if (utf8err && (!render || invalid_width < w)) {
+			if (render)
+				drw_text(drw, x, y, w, h, 0, invalid, invert);
+			x += invalid_width;
+			w -= invalid_width;
+		}
 		if (render && overflow)
 			drw_text(drw, ellipsis_x, y, ellipsis_w, h, 0, "...", invert);