40763: count wide characters and Cmatcher pointers more sanely in cfp_matcher_pats(), and count characters in pattern_match() the same way to stay in sync

Might not fix wide-char matching in completion matcher-lists but should
avoid wild pointer crash

ChangeLog

@@ -1,3 +1,11 @@
+2017-03-08  Barton E. Schaefer  <schaefer@brasslantern.com>
+
+	* 40763: Src/Zle/compmatch.c, Src/Zle/computil.c, Src/utils.c:
+	count wide characters and Cmatcher pointers more sanely in
+	cfp_matcher_pats(), and count characters in pattern_match()
+	the same way to stay in sync; might not fix wide-char matching
+	in completion matcher-lists but should avoid wild pointer crash
+
 2017-03-08  Daniel Shahaf  <d.s@daniel.shahaf.name>
 
 	* 40745 + 40753: Src/init.c, Src/params.c: Fix 'unset

Src/Zle/compmatch.c

@@ -1548,27 +1548,11 @@ pattern_match(Cpattern p, char *s, Cpattern wp, char *ws)
 {
     convchar_t c, wc;
     convchar_t ind, wind;
-    int len = 0, wlen, mt, wmt;
+    int len = 0, wlen = 0, mt, wmt;
-#ifdef MULTIBYTE_SUPPORT
-    mbstate_t lstate, wstate;
-
-    memset(&lstate, 0, sizeof(lstate));
-    memset(&wstate, 0, sizeof(wstate));
-#endif
 
     while (p && wp && *s && *ws) {
 	/* First test the word character */
-#ifdef MULTIBYTE_SUPPORT
+	wc = unmeta_one(ws, &wlen);
-	wlen = mb_metacharlenconv_r(ws, &wc, &wstate);
-#else
-	if (*ws == Meta) {
-	    wc = STOUC(ws[1]) ^ 32;
-	    wlen = 2;
-	} else {
-	    wc = STOUC(*ws);
-	    wlen = 1;
-	}
-#endif
 	wind = pattern_match1(wp, wc, &wmt);
 	if (!wind)
 	    return 0;
@@ -1576,18 +1560,7 @@ pattern_match(Cpattern p, char *s, Cpattern wp, char *ws)
 	/*
 	 * Now the line character.
 	 */
-#ifdef MULTIBYTE_SUPPORT
+	c = unmeta_one(s, &len);
-	len = mb_metacharlenconv_r(s, &c, &lstate);
-#else
-	/* We have the character itself. */
-	if (*s == Meta) {
-	    c = STOUC(s[1]) ^ 32;
-	    len = 2;
-	} else {
-	    c = STOUC(*s);
-	    len = 1;
-	}
-#endif
 	/*
 	 * If either is "?", they match each other; no further tests.
 	 * Apply this even if the character wasn't convertable;
@@ -1627,17 +1600,7 @@ pattern_match(Cpattern p, char *s, Cpattern wp, char *ws)
     }
 
     while (p && *s) {
-#ifdef MULTIBYTE_SUPPORT
+	c = unmeta_one(s, &len);
-	len = mb_metacharlenconv_r(s, &c, &lstate);
-#else
-	if (*s == Meta) {
-	    c = STOUC(s[1]) ^ 32;
-	    len = 2;
-	} else {
-	    c = STOUC(*s);
-	    len = 1;
-	}
-#endif
 	if (!pattern_match1(p, c, &mt))
 	    return 0;
 	p = p->next;
@@ -1645,17 +1608,7 @@ pattern_match(Cpattern p, char *s, Cpattern wp, char *ws)
     }
 
     while (wp && *ws) {
-#ifdef MULTIBYTE_SUPPORT
+	wc = unmeta_one(ws, &wlen);
-	wlen = mb_metacharlenconv_r(ws, &wc, &wstate);
-#else
-	if (*ws == Meta) {
-	    wc = STOUC(ws[1]) ^ 32;
-	    wlen = 2;
-	} else {
-	    wc = STOUC(*ws);
-	    wlen = 1;
-	}
-#endif
 	if (!pattern_match1(wp, wc, &wmt))
 	    return 0;
 	wp = wp->next;

Src/Zle/computil.c

@@ -4465,17 +4465,24 @@ cfp_matcher_pats(char *matcher, char *add)
     if (m && m != pcm_err) {
 	char *tmp;
 	int al = strlen(add), zl = ztrlen(add), tl, cl;
-	VARARR(Cmatcher, ms, zl);
+	VARARR(Cmatcher, ms, zl);	/* One Cmatcher per character */
 	Cmatcher *mp;
 	Cpattern stopp;
 	int stopl = 0;
 
+	/* zl >= (number of wide characters) is guaranteed */
 	memset(ms, 0, zl * sizeof(Cmatcher));
 
 	for (; m && *add; m = m->next) {
 	    stopp = NULL;
 	    if (!(m->flags & (CMF_LEFT|CMF_RIGHT))) {
 		if (m->llen == 1 && m->wlen == 1) {
+		    /*
+		     * In this loop and similar loops below we step
+		     * through tmp one (possibly wide) character at a
+		     * time.  pattern_match() compares only the first
+		     * character using unmeta_one() so keep in step.
+		     */
 		    for (tmp = add, tl = al, mp = ms; tl; ) {
 			if (pattern_match(m->line, tmp, NULL, NULL)) {
 			    if (*mp) {
@@ -4485,10 +4492,10 @@ cfp_matcher_pats(char *matcher, char *add)
 			    } else
 				*mp = m;
 			}
-			cl = (*tmp == Meta) ? 2 : 1;
+			(void) unmeta_one(tmp, &cl);
 			tl -= cl;
 			tmp += cl;
-			mp += cl;
+			mp++;
 		    }
 		} else {
 		    stopp = m->line;
@@ -4505,10 +4512,10 @@ cfp_matcher_pats(char *matcher, char *add)
 			    } else
 				*mp = m;
 			}
-			cl = (*tmp == Meta) ? 2 : 1;
+			(void) unmeta_one(tmp, &cl);
 			tl -= cl;
 			tmp += cl;
-			mp += cl;
+			mp++;
 		    }
 		} else if (m->llen) {
 		    stopp = m->line;
@@ -4531,7 +4538,7 @@ cfp_matcher_pats(char *matcher, char *add)
 			al = tmp - add;
 			break;
 		    }
-		    cl = (*tmp == Meta) ? 2 : 1;
+		    (void) unmeta_one(tmp, &cl);
 		    tl -= cl;
 		    tmp += cl;
 		}

Src/utils.c

@@ -4787,6 +4787,48 @@ unmeta(const char *file_name)
     return fn;
 }
 
+/*
+ * Unmetafy just one character and store the number of bytes it occupied.
+ */
+/**/
+mod_export convchar_t
+unmeta_one(const char *in, int *sz)
+{
+    convchar_t wc;
+    int newsz;
+#ifdef MULTIBYTE_SUPPORT
+    int ulen;
+    mbstate_t wstate;
+#endif
+
+    if (!sz)
+	sz = &newsz;
+    *sz = 0;
+
+    if (!in || !*in)
+	return 0;
+
+#ifdef MULTIBYTE_SUPPORT
+    memset(&wstate, 0, sizeof(wstate));
+    ulen = mb_metacharlenconv_r(in, &wc, &wstate);
+    while (ulen-- > 0) {
+	if (in[*sz] == Meta)
+	    *sz += 2;
+	else
+	    *sz += 1;
+    }
+#else
+    if (in[0] == Meta) {
+      *sz = 2;
+      wc = STOUC(in[1] ^ 32);
+    } else {
+      *sz = 1;
+      wc = STOUC(in[0]);
+    }
+#endif
+    return wc;
+}
+
 /*
  * Unmetafy and compare two strings, comparing unsigned character values.
  * "a\0" sorts after "a".