Upgrade one-true-awk to 9c63cb6ccd303fb64b703ff0836400f204078621 am: 2aef6cef71

Original change: https://android-review.googlesource.com/c/platform/external/one-true-awk/+/1395714

Change-Id: Ib3cd6d13cc36a5e9a6447d3db55faa084c99e62a

20 files changed, 103 insertions, 70 deletions

diff --git a/.gitignore b/.gitignore
index f469d21..c426b13 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,6 +1,4 @@
 a.out
 maketab
 proctab.c
-ytab.c
-ytab.h
 *.o
diff --git a/Android.bp b/Android.bp
index def4247..1fd1ac5 100644
--- a/Android.bp
+++ b/Android.bp
@@ -26,9 +26,9 @@ cc_defaults {
 }
 
 genrule {
-    name: "ytab.c",
-    cmd: "M4=$(location m4) $(location bison) -y --output=$(genDir)/ytab.c $(in)",
-    out: ["ytab.c"],
+    name: "awkgram.tab.c",
+    cmd: "M4=$(location m4) $(location bison) -y --output=$(genDir)/awkgram.tab.c $(in)",
+    out: ["awkgram.tab.c"],
     srcs: ["awkgram.y"],
     tools: [
         "bison",
@@ -37,9 +37,9 @@ genrule {
 }
 
 genrule {
-    name: "ytab.h",
-    cmd: "M4=$(location m4) $(location bison) -y --defines=$(genDir)/ytab.h --output=$(genDir)/ytab.c $(in)",
-    out: ["ytab.h"],
+    name: "awkgram.tab.h",
+    cmd: "M4=$(location m4) $(location bison) -y --defines=$(genDir)/awkgram.tab.h --output=$(genDir)/awkgram.tab.c $(in)",
+    out: ["awkgram.tab.h"],
     srcs: ["awkgram.y"],
     tools: [
         "bison",
@@ -52,20 +52,20 @@ genrule {
     tools: ["awk-maketab"],
     cmd: "$(location awk-maketab) $(in) > $(genDir)/proctab.c",
     out: ["proctab.c"],
-    srcs: [":ytab.h"],
+    srcs: [":awkgram.tab.h"],
 }
 
 cc_binary_host {
     name: "awk-maketab",
     defaults: ["awk-flags"],
-    generated_headers: ["ytab.h"],
+    generated_headers: ["awkgram.tab.h"],
     srcs: ["maketab.c"],
 }
 
 cc_defaults {
     name: "awk-defaults",
     defaults: ["awk-flags"],
-    generated_headers: ["ytab.h"],
+    generated_headers: ["awkgram.tab.h"],
     srcs: [
         "b.c",
         "lex.c",
@@ -75,7 +75,7 @@ cc_defaults {
         ":proctab.c",
         "run.c",
         "tran.c",
-        ":ytab.c",
+        ":awkgram.tab.c",
     ],
 }
 
diff --git a/ChangeLog b/ChangeLog
index 4e95699..6ce9417 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+2020-07-30         Arnold D. Robbins     <arnold@skeeve.com>
+
+	By fiat, we use bison for $(YACC). Trying to accommodate
+	different versions didn't work.
+
+	* makefile: Significant cleanup. Replace all ytab* references
+	with awkgram.tab.* and simplify definition of YACC.
+	* .gitignore: Remove ytab* references.
+	* b.c, lex.c, maketab.c, parse.c, run.c: Replace include of ytab.h
+	with awkgram.tab.h.
+	* lib.c, main.c, tran.c: Remove include of ytab.h, wasn't needed.
+
 2020-01-20         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* run.c (openfile): Set the close-on-exec flag for file
diff --git a/FIXES b/FIXES
index 9516a36..0bfdccd 100644
--- a/FIXES
+++ b/FIXES
@@ -25,6 +25,23 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the AWK book
 was sent to the printers in August, 1987.
 
+August 7, 2020:
+	Merge PR #93, which adds casts to (void*) for debug prints
+	using the %p format specifier. Thanks to GitHub user YongHaoWu
+	("Chris") for the fixes.
+
+August 4, 2020:
+	In run.c, use non-restartable multibyte routines to attain
+	portability to DJGPP. Should fix Issue 92. Thanks to Albert Wik
+	for the report and to Todd Miller for the suggested fix.
+
+July 30, 2020:
+	Merge PRs 88-91 which fix small bugs. Thanks to Todd Miller and
+	Tim van der Molen for the fixes.
+
+	In order to make life easier, we move exclusively to bison
+	as the parser generator.
+
 July 2, 2020:
 	Merge PRs 85 and 86 which fix regressions. Thanks to
 	Tim van der Molen for the fixes.
diff --git a/METADATA b/METADATA
index b15dff8..d9354a6 100644
--- a/METADATA
+++ b/METADATA
@@ -5,11 +5,11 @@ third_party {
     type: GIT
     value: "https://github.com/onetrueawk/awk.git"
   }
-  version: "2a4146ec3027d12e375209e03ed1c5a9ab230da4"
+  version: "9c63cb6ccd303fb64b703ff0836400f204078621"
   license_type: NOTICE
   last_upgrade_date {
     year: 2020
-    month: 7
-    day: 10
+    month: 8
+    day: 13
   }
 }
diff --git a/b.c b/b.c
index c167b50..776a806 100644
--- a/b.c
+++ b/b.c
@@ -32,7 +32,7 @@ THIS SOFTWARE.
 #include <string.h>
 #include <stdlib.h>
 #include "awk.h"
-#include "ytab.h"
+#include "awkgram.tab.h"
 
 #define MAXLIN 22
 
@@ -684,7 +684,7 @@ bool fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum)
 						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)
diff --git a/bugs-fixed/pfile-overflow.awk b/bugs-fixed/pfile-overflow.awk
new file mode 100644
index 0000000..b7d5379
--- /dev/null
+++ b/bugs-fixed/pfile-overflow.awk
@@ -0,0 +1 @@
+\
\ No newline at end of file
diff --git a/bugs-fixed/pfile-overflow.ok b/bugs-fixed/pfile-overflow.ok
new file mode 100644
index 0000000..a0de50f
--- /dev/null
+++ b/bugs-fixed/pfile-overflow.ok
@@ -0,0 +1,4 @@
+../a.out: syntax error at source line 1 source file pfile-overflow.awk
+ context is
+	 >>>  <<< 
+../a.out: bailing out at source line 1 source file pfile-overflow.awk
diff --git a/bugs-fixed/rs_underflow.awk b/bugs-fixed/rs_underflow.awk
new file mode 100644
index 0000000..4cf1702
--- /dev/null
+++ b/bugs-fixed/rs_underflow.awk
@@ -0,0 +1 @@
+BEGIN { RS="zx" } { print $1 }
diff --git a/bugs-fixed/rs_underflow.in b/bugs-fixed/rs_underflow.in
new file mode 100644
index 0000000..74c8035
--- /dev/null
+++ b/bugs-fixed/rs_underflow.in
@@ -0,0 +1 @@
+Ä
diff --git a/bugs-fixed/rs_underflow.ok b/bugs-fixed/rs_underflow.ok
new file mode 100644
index 0000000..74c8035
--- /dev/null
+++ b/bugs-fixed/rs_underflow.ok
@@ -0,0 +1 @@
+Ä
diff --git a/lex.c b/lex.c
index 0d2142c..73cdddb 100644
--- a/lex.c
+++ b/lex.c
@@ -27,7 +27,7 @@ THIS SOFTWARE.
 #include <string.h>
 #include <ctype.h>
 #include "awk.h"
-#include "ytab.h"
+#include "awkgram.tab.h"
 
 extern YYSTYPE	yylval;
 extern bool	infunc;
@@ -148,7 +148,7 @@ static int gettok(char **pbuf, int *psz)	/* get next input token */
 		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 */
diff --git a/lib.c b/lib.c
index ab3ae53..92f28f5 100644
--- a/lib.c
+++ b/lib.c
@@ -31,7 +31,6 @@ THIS SOFTWARE.
 #include <stdarg.h>
 #include <limits.h>
 #include "awk.h"
-#include "ytab.h"
 
 char	EMPTY[] = { '\0' };
 FILE	*infile	= NULL;
diff --git a/main.c b/main.c
index 535f1aa..0f3c4a7 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 20200702";
+const char	*version = "version 20200807";
 
 #define DEBUG
 #include <stdio.h>
@@ -32,7 +32,6 @@ const char	*version = "version 20200702";
 #include <string.h>
 #include <signal.h>
 #include "awk.h"
-#include "ytab.h"
 
 extern	char	**environ;
 extern	int	nfields;
@@ -256,7 +255,7 @@ int pgetc(void)		/* get 1 character from awk program */
 char *cursource(void)	/* current source file name */
 {
 	if (npfile > 0)
-		return pfile[curpfile];
+		return pfile[curpfile < npfile ? curpfile : curpfile - 1];
 	else
 		return NULL;
 }
diff --git a/makefile b/makefile
index d7d4bd2..5133698 100644
--- a/makefile
+++ b/makefile
@@ -34,54 +34,43 @@ CFLAGS = -O2
 HOSTCC = gcc -g -Wall -pedantic -Wcast-qual
 CC = $(HOSTCC)  # change this is cross-compiling.
 
-# yacc options.  pick one; this varies a lot by system.
-#YFLAGS = -d -S
+# By fiat, to make our lives easier, yacc is now defined to be bison.
+# If you want something else, you're on your own.
 YACC = bison -d
-#YACC = yacc -d
-#		-S uses sprintf in yacc parser instead of sprint
 
 OFILES = b.o main.o parse.o proctab.o tran.o lib.o run.o lex.o
 
-SOURCE = awk.h ytab.c ytab.h proto.h awkgram.y lex.c b.c main.c \
+SOURCE = awk.h awkgram.tab.c awkgram.tab.h proto.h awkgram.y lex.c b.c main.c \
 	maketab.c parse.c lib.c run.c tran.c proctab.c
 
 LISTING = awk.h proto.h awkgram.y lex.c b.c main.c maketab.c parse.c \
 	lib.c run.c tran.c
 
-SHIP = README LICENSE FIXES $(SOURCE) ytab[ch].bak makefile  \
+SHIP = README LICENSE FIXES $(SOURCE) awkgram.tab.[ch].bak makefile  \
 	 awk.1
 
-a.out:	ytab.o $(OFILES)
-	$(CC) $(CFLAGS) ytab.o $(OFILES) $(ALLOC)  -lm
+a.out:	awkgram.tab.o $(OFILES)
+	$(CC) $(CFLAGS) awkgram.tab.o $(OFILES) $(ALLOC)  -lm
 
-$(OFILES):	awk.h ytab.h proto.h
+$(OFILES):	awk.h awkgram.tab.h proto.h
 
-# Clear dependency for parallel build: (make -j)
-# Depending if we used yacc or bison we can be generating different names
-# ({awkgram,y}.tab.{c,h}) so try to move both. We could be using -p to
-# specify the output prefix, but older yacc's don't support it.
-ytab.c ytab.h:	awk.h proto.h awkgram.y
+awkgram.tab.c awkgram.tab.h:	awk.h proto.h awkgram.y
 	$(YACC) $(YFLAGS) awkgram.y
-	-@for i in c h; do for j in awkgram y; do \
-	     if [ -f "$$j.tab.$$i" ]; then mv $$j.tab.$$i ytab.$$i; fi; \
-	  done; done
-
-ytab.h:	ytab.c
 
 proctab.c:	maketab
-	./maketab ytab.h >proctab.c
+	./maketab awkgram.tab.h >proctab.c
 
-maketab:	ytab.h maketab.c
+maketab:	awkgram.tab.h maketab.c
 	$(HOSTCC) $(CFLAGS) maketab.c -o maketab
 
 bundle:
-	@cp ytab.h ytabh.bak
-	@cp ytab.c ytabc.bak
+	@cp awkgram.tab.h awkgram.tab.h.bak
+	@cp awkgram.tab.c awkgram.tab.c.bak
 	@bundle $(SHIP)
 
 tar:
-	@cp ytab.h ytabh.bak
-	@cp ytab.c ytabc.bak
+	@cp awkgram.tab.h awkgram.tab.h.bak
+	@cp awkgram.tab.c awkgram.tab.c.bak
 	@bundle $(SHIP) >awk.shar
 	@tar cf awk.tar $(SHIP)
 	gzip awk.tar
@@ -110,7 +99,7 @@ clean: testclean
 	rm -f a.out *.o *.obj maketab maketab.exe *.bb *.bbg *.da *.gcov *.gcno *.gcda # proctab.c
 
 cleaner: testclean
-	rm -f a.out *.o *.obj maketab maketab.exe *.bb *.bbg *.da *.gcov *.gcno *.gcda proctab.c ytab*
+	rm -f a.out *.o *.obj maketab maketab.exe *.bb *.bbg *.da *.gcov *.gcno *.gcda proctab.c awkgram.tab.*
 
 # This is a bit of a band-aid until we can invest some more time
 # in the test suite.
@@ -119,4 +108,4 @@ testclean:
 		glop glop1 glop2 lilly.diff tempbig tempsmall time
 
 # For the habits of GNU maintainers:
-distclean: clean
+distclean: cleaner
diff --git a/maketab.c b/maketab.c
index 2384d51..433541e 100644
--- a/maketab.c
+++ b/maketab.c
@@ -25,14 +25,14 @@ THIS SOFTWARE.
 /*
  * this program makes the table to link function names
  * and type indices that is used by execute() in run.c.
- * it finds the indices in ytab.h, produced by yacc.
+ * it finds the indices in awkgram.tab.h, produced by bison.
  */
 
 #include <stdio.h>
 #include <string.h>
 #include <stdlib.h>
 #include "awk.h"
-#include "ytab.h"
+#include "awkgram.tab.h"
 
 struct xx
 {	int token;
@@ -122,7 +122,7 @@ int main(int argc, char *argv[])
 
 	printf("#include <stdio.h>\n");
 	printf("#include \"awk.h\"\n");
-	printf("#include \"ytab.h\"\n\n");
+	printf("#include \"awkgram.tab.h\"\n\n");
 
 	if (argc != 2) {
 		fprintf(stderr, "usage: maketab YTAB_H\n");
diff --git a/parse.c b/parse.c
index b13e0c4..1466c38 100644
--- a/parse.c
+++ b/parse.c
@@ -27,7 +27,7 @@ THIS SOFTWARE.
 #include <string.h>
 #include <stdlib.h>
 #include "awk.h"
-#include "ytab.h"
+#include "awkgram.tab.h"
 
 Node *nodealloc(int n)
 {
diff --git a/run.c b/run.c
index 98787f1..01b4597 100644
--- a/run.c
+++ b/run.c
@@ -38,7 +38,7 @@ THIS SOFTWARE.
 #include <sys/types.h>
 #include <sys/wait.h>
 #include "awk.h"
-#include "ytab.h"
+#include "awkgram.tab.h"
 
 static void stdinit(void);
 static void flush_all(void);
@@ -119,7 +119,7 @@ int adjbuf(char **pbuf, int *psiz, int minlen, int quantum, char **pbptr,
 		if (rminlen)
 			minlen += quantum - rminlen;
 		tbuf = realloc(*pbuf, minlen);
-		DPRINTF("adjbuf %s: %d %d (pbuf=%p, tbuf=%p)\n", whatrtn, *psiz, minlen, *pbuf, tbuf);
+		DPRINTF("adjbuf %s: %d %d (pbuf=%p, tbuf=%p)\n", whatrtn, *psiz, minlen, (void*)*pbuf, (void*)tbuf);
 		if (tbuf == NULL) {
 			if (whatrtn)
 				FATAL("out of memory in %s", whatrtn);
@@ -1521,7 +1521,6 @@ static char *nawk_convert(const char *s, int (*fun_c)(int),
 	char *pbuf     = NULL;
 	const char *ps = NULL;
 	size_t n       = 0;
-	mbstate_t mbs, mbs2;
 	wchar_t wc;
 	size_t sz = MB_CUR_MAX;
 
@@ -1536,17 +1535,24 @@ static char *nawk_convert(const char *s, int (*fun_c)(int),
 		/* upper/lower character may be shorter/longer */
 		buf = tostringN(s, strlen(s) * sz + 1);
 
-		memset(&mbs,  0, sizeof(mbs));
-		memset(&mbs2, 0, sizeof(mbs2));
+		(void) mbtowc(NULL, NULL, 0);	/* reset internal state */
+		/*
+		 * Reset internal state here too.
+		 * Assign result to avoid a compiler warning. (Casting to void
+		 * doesn't work.)
+		 * Increment said variable to avoid a different warning.
+		 */
+		int unused = wctomb(NULL, L'\0');
+		unused++;
 
 		ps   = s;
 		pbuf = buf;
-		while (n = mbrtowc(&wc, ps, sz, &mbs),
+		while (n = mbtowc(&wc, ps, sz),
 		       n > 0 && n != (size_t)-1 && n != (size_t)-2)
 		{
 			ps += n;
 
-			n = wcrtomb(pbuf, fun_wc(wc), &mbs2);
+			n = wctomb(pbuf, fun_wc(wc));
 			if (n == (size_t)-1)
 				FATAL("illegal wide character %s", s);
 
@@ -1837,7 +1843,7 @@ const char *filename(FILE *fp)
  	Cell *x;
 	size_t i;
 	bool stat;
- 
+
  	x = execute(a[0]);
  	getsval(x);
 	stat = true;
@@ -1846,7 +1852,10 @@ const char *filename(FILE *fp)
 			continue;
 		if (ferror(files[i].fp))
 			FATAL("i/o error occurred on %s", files[i].fname);
-		if (files[i].mode == '|' || files[i].mode == LE)
+		if (files[i].fp == stdin || files[i].fp == stdout ||
+		    files[i].fp == stderr)
+			stat = freopen("/dev/null", "r+", files[i].fp) == NULL;
+		else if (files[i].mode == '|' || files[i].mode == LE)
 			stat = pclose(files[i].fp) == -1;
 		else
 			stat = fclose(files[i].fp) == EOF;
@@ -1856,6 +1865,7 @@ const char *filename(FILE *fp)
 			xfree(files[i].fname);
 		files[i].fname = NULL;	/* watch out for ref thru this */
 		files[i].fp = NULL;
+		break;
  	}
  	tempfree(x);
  	x = gettemp();
@@ -1873,8 +1883,12 @@ void closeall(void)
 			continue;
 		if (ferror(files[i].fp))
 			FATAL( "i/o error occurred on %s", files[i].fname );
+		if (files[i].fp == stdin)
+			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)
diff --git a/testdir/T.errmsg b/testdir/T.errmsg
index fcaaf9b..bf2fd6a 100755
--- a/testdir/T.errmsg
+++ b/testdir/T.errmsg
@@ -186,7 +186,7 @@ BEGIN { foo() }
 
 this should print a BAD message
 BEGIN { print }
-!!!
+!!!!
 
 
 echo '	running tests in foo.sh'
@@ -213,5 +213,3 @@ grep 'print | is unsafe' foo2 >/dev/null || echo 'BAD: T.errmsg print | unsafe'
 
 $awk -safe 'BEGIN {system("date")}' >foo 2>foo2
 grep 'system is unsafe' foo2 >/dev/null || echo 'BAD: T.errmsg system unsafe'
-
-!!!!
diff --git a/tran.c b/tran.c
index f0a0a09..ee5facb 100644
--- a/tran.c
+++ b/tran.c
@@ -29,7 +29,6 @@ THIS SOFTWARE.
 #include <string.h>
 #include <stdlib.h>
 #include "awk.h"
-#include "ytab.h"
 
 #define	FULLTAB	2	/* rehash when table gets this x full */
 #define	GROWTAB 4	/* grow table by this factor */
@@ -362,7 +361,7 @@ char *setsval(Cell *vp, const char *s)	/* set string val of a Cell */
 		fldno = atoi(vp->nval);
 		if (fldno > *NF)
 			newfld(fldno);
-		DPRINTF("setting field %d to %s (%p)\n", fldno, s, s);
+		DPRINTF("setting field %d to %s (%p)\n", fldno, s, (const void*)s);
 	} else if (isrec(vp)) {
 		donefld = false;	/* mark $1... invalid */
 		donerec = true;
@@ -379,7 +378,7 @@ char *setsval(Cell *vp, const char *s)	/* set string val of a Cell */
 	vp->fmt = NULL;
 	setfree(vp);
 	DPRINTF("setsval %p: %s = \"%s (%p) \", t=%o r,f=%d,%d\n",
-		(void*)vp, NN(vp->nval), t, t, vp->tval, donerec, donefld);
+		(void*)vp, NN(vp->nval), t, (void*)t, vp->tval, donerec, donefld);
 	vp->sval = t;
 	if (&vp->fval == NF) {
 		donerec = false;	/* mark $0 invalid */
@@ -493,7 +492,7 @@ static char *get_str_val(Cell *vp, char **fmt)        /* get string val of a Cel
 	}
 done:
 	DPRINTF("getsval %p: %s = \"%s (%p)\", t=%o\n",
-		(void*)vp, NN(vp->nval), vp->sval, vp->sval, vp->tval);
+		(void*)vp, NN(vp->nval), vp->sval, (void*)vp->sval, vp->tval);
 	return(vp->sval);
 }