Re: [BUG] SIGSEGV under certain circumstances

[Bart Schaefer <schaefer@xxxxxxxxxxxxxxxx>]

On Mar 5,  3:07pm, Bart Schaefer wrote:
}
} Also, it seems to me cl needs to be the number of bytes compared by
} pattern_match(), which is not always just 1 or 2 with wide characters.

Let's try this?  Hopefully zero'ing the mbstate_t is both correct and
not too time consuming in unmeta_one().  It'd be nice if pattern_match()
could return the size but there are too many possibilities (including a
successful match of zero length, it seems).

This is against master, NOT on top of my previous patch.

diff --git a/Src/Zle/compmatch.c b/Src/Zle/compmatch.c
index aedf463..1cdbb8a 100644
--- a/Src/Zle/compmatch.c
+++ b/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;
-#ifdef MULTIBYTE_SUPPORT
-    mbstate_t lstate, wstate;
-
-    memset(&lstate, 0, sizeof(lstate));
-    memset(&wstate, 0, sizeof(wstate));
-#endif
+    int len = 0, wlen = 0, mt, wmt;
 
     while (p && wp && *s && *ws) {
 	/* First test the word character */
-#ifdef MULTIBYTE_SUPPORT
-	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
+	wc = unmeta_one(ws, &wlen);
 	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
-	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
+	c = unmeta_one(s, &len);
 	/*
 	 * 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
-	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
+	c = unmeta_one(s, &len);
 	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
-	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
+	wc = unmeta_one(ws, &wlen);
 	if (!pattern_match1(wp, wc, &wmt))
 	    return 0;
 	wp = wp->next;
diff --git a/Src/Zle/computil.c b/Src/Zle/computil.c
index 325da6d..4ea409d 100644
--- a/Src/Zle/computil.c
+++ b/Src/Zle/computil.c
@@ -4485,10 +4485,10 @@ 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 +4505,10 @@ 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 +4531,7 @@ 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;
 		}
diff --git a/Src/utils.c b/Src/utils.c
index 7f3ddad..58983d3 100644
--- a/Src/utils.c
+++ b/Src/utils.c
@@ -4788,6 +4788,56 @@ unmeta(const char *file_name)
 }
 
 /*
+ * Unmetafy just one character and store the number of bytes it occupied.
+ */
+/**/
+mod_export convchar_t
+unmeta_one(const char *in, int *sz)
+{
+#ifdef MB_CUR_MAX
+    VARARR(char,out,MB_CUR_MAX+1);
+#else
+#define MB_CUR_MAX 2
+    char out[MB_CUR_MAX+1];
+#endif
+    convchar_t wc;
+    char *p;
+    const char *t;
+    int newsz;
+#ifdef MULTIBYTE_SUPPORT
+    int ulen;
+    mbstate_t wstate;
+#endif
+
+    if (!sz)
+	sz = &newsz;
+    *sz = 0;
+
+    if (!in)
+	return 0;
+
+    for (t = in, p = out; *t && (p - out <= MB_CUR_MAX); p++)
+	if ((*p = *t++) == Meta && *t)
+	    *p = *t++ ^ 32;
+    *p = '\0';	/* Unnecessary? */
+
+#ifdef MULTIBYTE_SUPPORT
+    memset(&wstate, 0, sizeof(wstate));
+    ulen = mb_metacharlenconv_r(out, &wc, &wstate);
+    while (ulen-- > 0) {
+	if (in[*sz] == Meta)
+		*sz += 2;
+	    else
+		*sz += 1;
+    }
+#else
+    *sz = p - out;
+    wc = STOUC(out[0]);
+#endif
+    return wc;
+}
+
+/*
  * Unmetafy and compare two strings, comparing unsigned character values.
  * "a\0" sorts after "a".
  *