Snap for 8564071 from 2591b9c58663d594be6db5830ac7d404301f71d6 to mainline-extservices-releaseaml_ext_331814220aml_ext_331412000aml_ext_331312000aml_ext_331112010aml_ext_331012020android13-mainline-extservices-release

Change-Id: Ice5b80f7b278fe5a650797c88cd7b28b07da85ec

11 files changed, 119 insertions, 40 deletions

diff --git a/FIXES b/FIXES
index 516458e..8e49fe9 100644
--- a/FIXES
+++ b/FIXES
@@ -25,6 +25,38 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the AWK book
 was sent to the printers in August, 1987.
 
+December 8, 2021:
+	The error handling in closefile and closeall was mangled. Long
+	standing warnings had been made fatal and some fatal errors went
+	undetected. Thanks to Miguel Pineiro Jr. <mpj@pineiro.cc>.
+
+Nov 03, 2021:
+        getline accesses uninitialized data after getrec()
+	returns 0 on EOF and leaves the contents of buf unchanged.
+	Thanks to Volodymyr Gubarkov, and Todd C Miller.
+
+Oct 12, 2021:
+	The fix for #83 changed the code to insert 2 chars, but the
+	call to adjbuf just above it only allows for 1 char. This can
+	cause a heap buffer overflow.
+
+July 27, 2021:
+	As per IEEE Std 1003.1-2008, -F "str" is now consistent with
+	-v FS="str" when str is null. Thanks to Warner Losh.
+
+July 24, 2021:
+	Fix readrec's definition of a record. This fixes an issue
+	with NetBSD's RS regular expression support that can cause
+	an infinite read loop. Thanks to Miguel Pineiro Jr.
+
+	Fix regular expression RS ^-anchoring. RS ^-anchoring needs to
+	know if it is reading the first record of a file. This change
+	restores a missing line that was overlooked when porting NetBSD's
+	RS regex functionality. Thanks to Miguel Pineiro Jr.
+
+	Fix size computation in replace_repeat() for special case
+	REPEAT_WITH_Q. Thanks to Todd C. Miller.
+
 February 15, 2021:
 	Small fix so that awk will compile again with g++. Thanks to
 	Arnold Robbins.
diff --git a/METADATA b/METADATA
index 49d2ed8..052f466 100644
--- a/METADATA
+++ b/METADATA
@@ -5,11 +5,11 @@ third_party {
     type: GIT
     value: "https://github.com/onetrueawk/awk.git"
   }
-  version: "c0f4e97e4561ff42544e92512bbaf3d7d1f6a671"
+  version: "075624a72ab15649f255a3a1dabfd7cb7766a7d7"
   license_type: NOTICE
   last_upgrade_date {
-    year: 2021
-    month: 4
-    day: 1
+    year: 2022
+    month: 3
+    day: 7
   }
 }
diff --git a/README.md b/README.md
index b8089b3..d9cd62c 100644
--- a/README.md
+++ b/README.md
@@ -35,7 +35,7 @@ in `FIXES`.  If you distribute this code further, please please please
 distribute `FIXES` with it.
 
 If you find errors, please report them
-to bwk@cs.princeton.edu.
+to the current maintainer, ozan.yigit@gmail.com.
 Please _also_ open an issue in the GitHub issue tracker, to make
 it easy to track issues.
 Thanks.
@@ -90,7 +90,7 @@ move this to some place like `/usr/bin/awk`.
 If your system does not have `yacc` or `bison` (the GNU
 equivalent), you need to install one of them first.
 
-NOTE: This version uses ANSI C (C 99), as you should also.  We have
+NOTE: This version uses ISO/IEC C99, as you should also.  We have
 compiled this without any changes using `gcc -Wall` and/or local C
 compilers on a variety of systems, but new systems or compilers
 may raise some new complaint; reports of difficulties are
@@ -107,13 +107,18 @@ astonishly slow.  If `awk` seems slow, you might try fixing that.
 More generally, turning on optimization can significantly improve
 `awk`'s speed, perhaps by 1/3 for highest levels.
 
+## A Note About Releases
+
+We don't usually do releases. 
+
 ## A Note About Maintenance
 
-NOTICE! Maintenance of this program is on a ``best effort''
+NOTICE! Maintenance of this program is on a ''best effort''
 basis.  We try to get to issues and pull requests as quickly
 as we can.  Unfortunately, however, keeping this program going
 is not at the top of our priority list.
 
 #### Last Updated
 
-Fri Dec 25 16:53:34 EST 2020
+Sun 23 Jan 2022 03:48:01 PM EST
+
diff --git a/b.c b/b.c
index f889ee5..6fb7343 100644
--- a/b.c
+++ b/b.c
@@ -935,7 +935,7 @@ replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom,
 	if (special_case == REPEAT_PLUS_APPENDED) {
 		size++;		/* for the final + */
 	} else if (special_case == REPEAT_WITH_Q) {
-		size += init_q + (atomlen+1)* n_q_reps;
+		size += init_q + (atomlen+1)* (n_q_reps-init_q);
 	} else if (special_case == REPEAT_ZERO) {
 		size += 2;	/* just a null ERE: () */
 	}
@@ -964,11 +964,8 @@ replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom,
 		}
 	}
 	memcpy(&buf[j], reptok+reptoklen, suffix_length);
-	if (special_case == REPEAT_ZERO) {
-		buf[j+suffix_length] = '\0';
-	} else {
-		buf[size] = '\0';
-	}
+	j += suffix_length;
+	buf[j] = '\0';
 	/* free old basestr */
 	if (firstbasestr != basestr) {
 		if (basestr)
@@ -1104,7 +1101,7 @@ rescan:
 					 * program to track each string's length.
 					 */
 					for (i = 1; i <= UCHAR_MAX; i++) {
-						if (!adjbuf((char **) &buf, &bufsz, bp-buf+1, 100, (char **) &bp, "relex2"))
+						if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "relex2"))
 						    FATAL("out of space for reg expr %.10s...", lastre);
 						if (cc->cc_func(i)) {
 							/* escape backslash */
diff --git a/bugs-fixed/getline-corruption.awk b/bugs-fixed/getline-corruption.awk
new file mode 100644
index 0000000..461e551
--- /dev/null
+++ b/bugs-fixed/getline-corruption.awk
@@ -0,0 +1,5 @@
+BEGIN { 
+	getline l
+	getline l
+	print (s=substr(l,1,10)) " len=" length(s)
+}
diff --git a/bugs-fixed/getline-corruption.in b/bugs-fixed/getline-corruption.in
new file mode 100644
index 0000000..7898192
--- /dev/null
+++ b/bugs-fixed/getline-corruption.in
@@ -0,0 +1 @@
+a
diff --git a/bugs-fixed/getline-corruption.ok b/bugs-fixed/getline-corruption.ok
new file mode 100644
index 0000000..3efb545
--- /dev/null
+++ b/bugs-fixed/getline-corruption.ok
@@ -0,0 +1 @@
+a len=1
diff --git a/lib.c b/lib.c
index 18adbd2..c7709f7 100644
--- a/lib.c
+++ b/lib.c
@@ -176,6 +176,7 @@ int getrec(char **pbuf, int *pbufsize, bool isrecord)	/* get next input record *
 				infile = stdin;
 			else if ((infile = fopen(file, "r")) == NULL)
 				FATAL("can't open file %s", file);
+			innew = true;
 			setfval(fnrloc, 0.0);
 		}
 		c = readrec(&buf, &bufsize, infile, innew);
@@ -241,6 +242,7 @@ int readrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag)	/* read one rec
 		}
 		if (found)
 			setptr(patbeg, '\0');
+		isrec = (found == 0 && *buf == '\0') ? false : true;
 	} else {
 		if ((sep = *rs) == 0) {
 			sep = '\n';
@@ -270,10 +272,10 @@ int readrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag)	/* read one rec
 		if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 3"))
 			FATAL("input record `%.30s...' too long", buf);
 		*rr = 0;
+		isrec = (c == EOF && rr == buf) ? false : true;
 	}
 	*pbuf = buf;
 	*pbufsize = bufsize;
-	isrec = *buf || !feof(inf);
 	DPRINTF("readrec saw <%s>, returns %d\n", buf, isrec);
 	return isrec;
 }
diff --git a/main.c b/main.c
index f393634..986f1a3 100644
--- a/main.c
+++ b/main.c
@@ -22,7 +22,7 @@ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
 THIS SOFTWARE.
 ****************************************************************/
 
-const char	*version = "version 20210215";
+const char	*version = "version 20211208";
 
 #define DEBUG
 #include <stdio.h>
@@ -91,9 +91,7 @@ setfs(char *p)
 	/* wart: t=>\t */
 	if (p[0] == 't' && p[1] == '\0')
 		return "\t";
-	else if (p[0] != '\0')
-		return p;
-	return NULL;
+	return p;
 }
 
 static char *
@@ -169,8 +167,6 @@ int main(int argc, char *argv[])
  			break;
 		case 'F':	/* set field separator */
 			fs = setfs(getarg(&argc, &argv, "no field separator"));
-			if (fs == NULL)
-				WARNING("field separator FS is empty");
 			break;
 		case 'v':	/* -v a=1 to be done NOW.  one -v for each */
 			vn = getarg(&argc, &argv, "no variable name");
diff --git a/run.c b/run.c
index da4f555..f5c19a1 100644
--- a/run.c
+++ b/run.c
@@ -447,13 +447,15 @@ Cell *awkgetline(Node **a, int n)	/* get next line from specific input */
 			n = getrec(&record, &recsize, true);
 		else {			/* getline var */
 			n = getrec(&buf, &bufsize, false);
-			x = execute(a[0]);
-			setsval(x, buf);
-			if (is_number(x->sval, & result)) {
-				x->fval = result;
-				x->tval |= NUM;
+			if (n > 0) {
+				x = execute(a[0]);
+				setsval(x, buf);
+				if (is_number(x->sval, & result)) {
+					x->fval = result;
+					x->tval |= NUM;
+				}
+				tempfree(x);
 			}
-			tempfree(x);
 		}
 	}
 	setfval(r, (Awkfloat) n);
@@ -1858,8 +1860,8 @@ const char *filename(FILE *fp)
 	return "???";
 }
 
- Cell *closefile(Node **a, int n)
- {
+Cell *closefile(Node **a, int n)
+{
  	Cell *x;
 	size_t i;
 	bool stat;
@@ -1870,8 +1872,15 @@ const char *filename(FILE *fp)
  	for (i = 0; i < nfiles; i++) {
 		if (!files[i].fname || strcmp(x->sval, files[i].fname) != 0)
 			continue;
-		if (ferror(files[i].fp))
-			FATAL("i/o error occurred on %s", files[i].fname);
+		if (files[i].mode == GT || files[i].mode == '|')
+			fflush(files[i].fp);
+		if (ferror(files[i].fp)) {
+			if ((files[i].mode == GT && files[i].fp != stderr)
+			  || files[i].mode == '|')
+				FATAL("write error on %s", files[i].fname);
+			else
+				WARNING("i/o error occurred on %s", files[i].fname);
+		}
 		if (files[i].fp == stdin || files[i].fp == stdout ||
 		    files[i].fp == stderr)
 			stat = freopen("/dev/null", "r+", files[i].fp) == NULL;
@@ -1880,7 +1889,7 @@ const char *filename(FILE *fp)
 		else
 			stat = fclose(files[i].fp) == EOF;
 		if (stat)
-			FATAL("i/o error occurred closing %s", files[i].fname);
+			WARNING("i/o error occurred closing %s", files[i].fname);
 		if (i > 2)	/* don't do /dev/std... */
 			xfree(files[i].fname);
 		files[i].fname = NULL;	/* watch out for ref thru this */
@@ -1891,7 +1900,7 @@ const char *filename(FILE *fp)
  	x = gettemp();
 	setfval(x, (Awkfloat) (stat ? -1 : 0));
  	return(x);
- }
+}
 
 void closeall(void)
 {
@@ -1901,18 +1910,24 @@ void closeall(void)
 	for (i = 0; i < nfiles; i++) {
 		if (! files[i].fp)
 			continue;
-		if (ferror(files[i].fp))
-			FATAL( "i/o error occurred on %s", files[i].fname );
-		if (files[i].fp == stdin)
+		if (files[i].mode == GT || files[i].mode == '|')
+			fflush(files[i].fp);
+		if (ferror(files[i].fp)) {
+			if ((files[i].mode == GT && files[i].fp != stderr)
+			  || files[i].mode == '|')
+				FATAL("write error on %s", files[i].fname);
+			else
+				WARNING("i/o error occurred on %s", files[i].fname);
+		}
+		if (files[i].fp == stdin || files[i].fp == stdout ||
+		    files[i].fp == stderr)
 			continue;
 		if (files[i].mode == '|' || files[i].mode == LE)
 			stat = pclose(files[i].fp) == -1;
-		else if (files[i].fp == stdout || files[i].fp == stderr)
-			stat = fflush(files[i].fp) == EOF;
 		else
 			stat = fclose(files[i].fp) == EOF;
 		if (stat)
-			FATAL( "i/o error occurred while closing %s", files[i].fname );
+			WARNING("i/o error occurred while closing %s", files[i].fname);
 	}
 }
 
diff --git a/testdir/T.misc b/testdir/T.misc
index dff57db..ad34ab8 100755
--- a/testdir/T.misc
+++ b/testdir/T.misc
@@ -186,6 +186,13 @@ BEGIN {	RS = ""
 }' >foo1
 $awk 'END {print NR}' foo1 | grep 4 >/dev/null || echo 'BAD: T.misc abcdef fails'
 
+# Test for RS regex matching an empty record at EOF
+echo a | $awk 1 RS='a\n' > foo1
+cat << \EOF > foo2
+
+EOF
+diff foo1 foo2 || echo 'BAD: T.misc RS regex matching an empty record at EOF fails'
+
 # Test for RS regex being reapplied
 echo aaa1a2a | $awk 1 RS='^a' >foo1
 cat << \EOF > foo2
@@ -195,6 +202,24 @@ aa1a2a
 EOF
 diff foo1 foo2 || echo 'BAD: T.misc ^regex reapplied fails'
 
+# ^-anchored RS matching should be active at the start of each input file
+tee foo1 foo2 >foo3 << \EOF
+aaa
+EOF
+$awk 1 RS='^a' foo1 foo2 foo3 >foo4
+cat << \EOF > foo5
+
+aa
+
+
+aa
+
+
+aa
+
+EOF
+diff foo4 foo5 || echo 'BAD: T.misc ^RS matches the start of every input file fails'
+
 # The following should not produce a warning about changing a constant
 # nor about a curdled tempcell list
 $awk 'function f(x) { x = 2 }