shithub: trueawk

Info  •  Files  •  Log  •  Branches

Cast to uschar when storing a char in an int that will be used as an index (#88)

* Cast to uschar when storing a char in an int that will be used as an index.
Fixes a heap underflow when the input char has the high bit set and
FS is a regex.

* Add regress test for underflow when RS is a regex and input is 8-bit.

--- a/b.c

+++ b/b.c

@@ -684,7 +684,7 @@

 						FATAL("stream '%.30s...' too long", buf);

 				buf[k++] = (c = getc(f)) != EOF ? c : 0;

 			}

-			c = buf[j];

+			c = (uschar)buf[j];

 			/* assert(c < NCHARS); */

 			if ((ns = pfa->gototab[s][c]) != 0)

--- /dev/null

+++ b/bugs-fixed/rs_underflow.awk

@@ -1,0 +1,1 @@

+BEGIN { RS="zx" } { print $1 }

--- /dev/null

+++ b/bugs-fixed/rs_underflow.in

@@ -1,0 +1,1 @@

+�

--- /dev/null

+++ b/bugs-fixed/rs_underflow.ok

@@ -1,0 +1,1 @@

+�

--- a/lex.c

+++ b/lex.c

@@ -148,7 +148,7 @@

 		strtod(buf, &rem);	/* parse the number */

 		if (rem == buf) {	/* it wasn't a valid number at all */

 			buf[1] = 0;	/* return one character as token */

-			retc = buf[0];	/* character is its own type */

+			retc = (uschar)buf[0];	/* character is its own type */

 			unputstr(rem+1); /* put rest back for later */

 		} else {	/* some prefix was a number */

 			unputstr(rem);	/* put rest back for later */

-- 

⑨