Update to a 7-Aug-2011 release.

Approved by:	re (kib)

contrib/one-true-awk/FIXES

@@ -25,6 +25,24 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the AWK book
 was sent to the printers in August, 1987.
 
+Aug 7, 2011:
+	split(s, a, //) now behaves the same as split(s, a, "")
+
+Jun 12, 2011:
+	/pat/, \n /pat/ {...} is now legal, though bad style to use.
+
+	added checks to new -v code that permits -vnospace; thanks to
+	ruslan ermilov for spotting this and providing the patch. 
+
+	removed fixed limit on number of open files; thanks to aleksey
+	cheusov and christos zoulos. 
+
+	fixed day 1 bug that resurrected deleted elements of ARGV when
+	used as filenames (in lib.c).
+
+	minor type fiddles to make gcc -Wall -pedantic happier (but not
+	totally so); turned on -fno-strict-aliasing in makefile.
+
 May 6, 2011:
 	added #ifdef for isblank.
 	now allows -ffoo as well as -f foo arguments.

contrib/one-true-awk/awkgram.y

@@ -174,8 +174,8 @@ pa_pat:
 pa_stat:
 	  pa_pat			{ $$ = stat2(PASTAT, $1, stat2(PRINT, rectonode(), NIL)); }
 	| pa_pat lbrace stmtlist '}'	{ $$ = stat2(PASTAT, $1, $3); }
-	| pa_pat ',' pa_pat		{ $$ = pa2stat($1, $3, stat2(PRINT, rectonode(), NIL)); }
-	| pa_pat ',' pa_pat lbrace stmtlist '}'	{ $$ = pa2stat($1, $3, $5); }
+	| pa_pat ',' opt_nl pa_pat		{ $$ = pa2stat($1, $4, stat2(PRINT, rectonode(), NIL)); }
+	| pa_pat ',' opt_nl pa_pat lbrace stmtlist '}'	{ $$ = pa2stat($1, $4, $6); }
 	| lbrace stmtlist '}'		{ $$ = stat2(PASTAT, NIL, $2); }
 	| XBEGIN lbrace stmtlist '}'
 		{ beginloc = linkum(beginloc, $3); $$ = 0; }

contrib/one-true-awk/b.c

@@ -234,7 +234,7 @@ void freetr(Node *p)	/* free parse tree */
 /* in the parsing of regular expressions, metacharacters like . have */
 /* to be seen literally;  \056 is not a metacharacter. */
 
-int hexstr(char **pp)	/* find and eval hex string at pp, return new p */
+int hexstr(uschar **pp)	/* find and eval hex string at pp, return new p */
 {			/* only pick up one 8-bit byte (2 chars) */
 	uschar *p;
 	int n = 0;
@@ -248,16 +248,16 @@ int hexstr(char **pp)	/* find and eval hex string at pp, return new p */
 		else if (*p >= 'A' && *p <= 'F')
 			n = 16 * n + *p - 'A' + 10;
 	}
-	*pp = (char *) p;
+	*pp = (uschar *) p;
 	return n;
 }
 
 #define isoctdigit(c) ((c) >= '0' && (c) <= '7')	/* multiple use of arg */
 
-int quoted(char **pp)	/* pick up next thing after a \\ */
+int quoted(uschar **pp)	/* pick up next thing after a \\ */
 			/* and increment *pp */
 {
-	char *p = *pp;
+	uschar *p = *pp;
 	int c;
 
 	if ((c = *p++) == 't')
@@ -314,13 +314,13 @@ char *cclenter(const char *argp)	/* add a character class */
 	bp = buf;
 	for (i = 0; (c = *p++) != 0; ) {
 		if (c == '\\') {
-			c = quoted((char **) &p);
+			c = quoted(&p);
 		} else if (c == '-' && i > 0 && bp[-1] != 0) {
 			if (*p != 0) {
 				c = bp[-1];
 				c2 = *p++;
 				if (c2 == '\\')
-					c2 = quoted((char **) &p);
+					c2 = quoted(&p);
 				if (collate_range_cmp(c, c2) > 0) {
 					bp--;
 					i--;
@@ -807,7 +807,7 @@ int relex(void)		/* lexical analyzer for reparse */
 	case ')':
 		return c;
 	case '\\':
-		rlxval = quoted((char **) &prestr);
+		rlxval = quoted(&prestr);
 		return CHAR;
 	default:
 		rlxval = c;

contrib/one-true-awk/lex.c

@@ -411,7 +411,7 @@ int string(void)
 				}
 				*px = 0;
 				unput(c);
-	  			sscanf(xbuf, "%x", &n);
+	  			sscanf(xbuf, "%x", (unsigned int *) &n);
 				*bp++ = n;
 				break;
 			    }

contrib/one-true-awk/lib.c

@@ -124,7 +124,7 @@ int getrec(char **pbuf, int *pbufsize, int isrecord)	/* get next input record */
 		   dprintf( ("argno=%d, file=|%s|\n", argno, file) );
 		if (infile == NULL) {	/* have to open a new file */
 			file = getargv(argno);
-			if (*file == '\0') {	/* it's been zapped */
+			if (file == NULL || *file == '\0') {	/* deleted or zapped */
 				argno++;
 				continue;
 			}
@@ -187,6 +187,7 @@ int readrec(char **pbuf, int *pbufsize, FILE *inf)	/* read one record into buf *
 
 	if (strlen(*FS) >= sizeof(inputFS))
 		FATAL("field separator %.10s... is too long", *FS);
+	/*fflush(stdout); avoids some buffering problem but makes it 25% slower*/
 	strcpy(inputFS, *FS);	/* for subsequent field splitting */
 	if ((sep = **RS) == 0) {
 		sep = '\n';
@@ -227,6 +228,8 @@ char *getargv(int n)	/* get ARGV[n] */
 	extern Array *ARGVtab;
 
 	sprintf(temp, "%d", n);
+	if (lookup(temp, ARGVtab) == NULL)
+		return NULL;
 	x = setsymtab(temp, "", 0.0, STR, ARGVtab);
 	s = getsval(x);
 	   dprintf( ("getargv(%d) returns |%s|\n", n, s) );
@@ -477,14 +480,14 @@ void recbld(void)	/* create $0 from $1..$NF if necessary */
 	if (!adjbuf(&record, &recsize, 2+r-record, recsize, &r, "recbld 3"))
 		FATAL("built giant record `%.30s...'", record);
 	*r = '\0';
-	   dprintf( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, fldtab[0]) );
+	   dprintf( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, (void*)fldtab[0]) );
 
 	if (freeable(fldtab[0]))
 		xfree(fldtab[0]->sval);
 	fldtab[0]->tval = REC | STR | DONTFREE;
 	fldtab[0]->sval = record;
 
-	   dprintf( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, fldtab[0]) );
+	   dprintf( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, (void*)fldtab[0]) );
 	   dprintf( ("recbld = |%s|\n", record) );
 	donerec = 1;
 }

contrib/one-true-awk/main.c

@@ -25,7 +25,7 @@ THIS SOFTWARE.
 #include <sys/cdefs.h>
 __FBSDID("$FreeBSD$");
 
-const char	*version = "version 20110506 (FreeBSD)";
+const char	*version = "version 20110807 (FreeBSD)";
 
 #define DEBUG
 #include <stdio.h>
@@ -125,10 +125,20 @@ int main(int argc, char *argv[])
 				WARNING("field separator FS is empty");
 			break;
 		case 'v':	/* -v a=1 to be done NOW.  one -v for each */
-			if (argv[1][2] == '\0' && --argc > 1 && isclvar((++argv)[1]))
-				setclvar(argv[1]);
-			else if (argv[1][2] != '\0')
-				setclvar(&argv[1][2]);
+			if (argv[1][2] != 0) {  /* arg is -vsomething */
+				if (isclvar(&argv[1][2]))
+					setclvar(&argv[1][2]);
+				else
+					FATAL("invalid -v option argument: %s", &argv[1][2]);
+			} else {		/* arg is -v something */
+				argc--; argv++;
+				if (argc <= 1)
+					FATAL("no variable name");
+				if (isclvar(argv[1]))
+					setclvar(argv[1]);
+				else
+					FATAL("invalid -v option argument: %s", argv[1]);
+			}
 			break;
 		case 'd':
 			dbg = atoi(&argv[1][2]);

contrib/one-true-awk/makefile

@@ -30,7 +30,7 @@ CC = gcc -Wall -g
 CC = cc
 CC = gcc -Wall -g -Wwrite-strings
 CC = gcc -fprofile-arcs -ftest-coverage # then gcov f1.c; cat f1.c.gcov
-CC = gcc -O4
+CC = gcc -O4 -Wall -pedantic -fno-strict-aliasing
 
 YACC = bison -y
 YACC = yacc

contrib/one-true-awk/proto.h

@@ -43,8 +43,8 @@ extern	fa	*mkdfa(const char *, int);
 extern	int	makeinit(fa *, int);
 extern	void	penter(Node *);
 extern	void	freetr(Node *);
-extern	int	hexstr(char **);
-extern	int	quoted(char **);
+extern	int	hexstr(uschar **);
+extern	int	quoted(uschar **);
 extern	char	*cclenter(const char *);
 extern	void	overflo(const char *);
 extern	void	cfoll(fa *, Node *);

contrib/one-true-awk/run.c

@@ -1239,6 +1239,12 @@ Cell *split(Node **a, int nnn)	/* split(a[0], a[1], a[2]); a[3] is type */
 	ap->sval = (char *) makesymtab(NSYMTAB);
 
 	n = 0;
+        if (arg3type == REGEXPR && strlen((char*)((fa*)a[2])->restr) == 0) {
+		/* split(s, a, //); have to arrange that it looks like empty sep */
+		arg3type = 0;
+		fs = "";
+		sep = 0;
+	}
 	if (*s != '\0' && (strlen(fs) > 1 || arg3type == REGEXPR)) {	/* reg expr */
 		fa *pfa;
 		if (arg3type == REGEXPR) {	/* it's ready already */
@@ -1621,17 +1627,25 @@ struct files {
 	FILE	*fp;
 	const char	*fname;
 	int	mode;	/* '|', 'a', 'w' => LE/LT, GT */
-} files[FOPEN_MAX] ={
-	{ NULL,  "/dev/stdin",  LT },	/* watch out: don't free this! */
-	{ NULL, "/dev/stdout", GT },
-	{ NULL, "/dev/stderr", GT }
-};
+} *files;
+
+int nfiles;
 
 void stdinit(void)	/* in case stdin, etc., are not constants */
 {
-	files[0].fp = stdin;
-	files[1].fp = stdout;
-	files[2].fp = stderr;
+	nfiles = FOPEN_MAX;
+	files = calloc(nfiles, sizeof(*files));
+	if (files == NULL)
+		FATAL("can't allocate file memory for %u files", nfiles);
+        files[0].fp = stdin;
+	files[0].fname = "/dev/stdin";
+	files[0].mode = LT;
+        files[1].fp = stdout;
+	files[1].fname = "/dev/stdout";
+	files[1].mode = GT;
+        files[2].fp = stderr;
+	files[2].fname = "/dev/stderr";
+	files[2].mode = GT;
 }
 
 FILE *openfile(int a, const char *us)
@@ -1642,7 +1656,7 @@ FILE *openfile(int a, const char *us)
 
 	if (*s == '\0')
 		FATAL("null file name in print or getline");
-	for (i=0; i < FOPEN_MAX; i++)
+	for (i=0; i < nfiles; i++)
 		if (files[i].fname && strcmp(s, files[i].fname) == 0) {
 			if (a == files[i].mode || (a==APPEND && files[i].mode==GT))
 				return files[i].fp;
@@ -1652,11 +1666,19 @@ FILE *openfile(int a, const char *us)
 	if (a == FFLUSH)	/* didn't find it, so don't create it! */
 		return NULL;
 
-	for (i=0; i < FOPEN_MAX; i++)
+	for (i=0; i < nfiles; i++)
 		if (files[i].fp == 0)
 			break;
-	if (i >= FOPEN_MAX)
-		FATAL("%s makes too many open files", s);
+	if (i >= nfiles) {
+		struct files *nf;
+		int nnf = nfiles + FOPEN_MAX;
+		nf = realloc(files, nnf * sizeof(*nf));
+		if (nf == NULL)
+			FATAL("cannot grow files for %s and %d files", s, nnf);
+		memset(&nf[nfiles], 0, FOPEN_MAX * sizeof(*nf));
+		nfiles = nnf;
+		files = nf;
+	}
 	fflush(stdout);	/* force a semblance of order */
 	m = a;
 	if (a == GT) {
@@ -1684,7 +1706,7 @@ const char *filename(FILE *fp)
 {
 	int i;
 
-	for (i = 0; i < FOPEN_MAX; i++)
+	for (i = 0; i < nfiles; i++)
 		if (fp == files[i].fp)
 			return files[i].fname;
 	return "???";
@@ -1699,7 +1721,7 @@ Cell *closefile(Node **a, int n)
 	x = execute(a[0]);
 	getsval(x);
 	stat = -1;
-	for (i = 0; i < FOPEN_MAX; i++) {
+	for (i = 0; i < nfiles; i++) {
 		if (files[i].fname && strcmp(x->sval, files[i].fname) == 0) {
 			if (ferror(files[i].fp))
 				WARNING( "i/o error occurred on %s", files[i].fname );
@@ -1743,7 +1765,7 @@ void flush_all(void)
 {
 	int i;
 
-	for (i = 0; i < FOPEN_MAX; i++)
+	for (i = 0; i < nfiles; i++)
 		if (files[i].fp)
 			fflush(files[i].fp);
 }

contrib/one-true-awk/tran.c

@@ -212,7 +212,7 @@ Cell *setsymtab(const char *n, const char *s, Awkfloat f, unsigned t, Array *tp)
 
 	if (n != NULL && (p = lookup(n, tp)) != NULL) {
 		   dprintf( ("setsymtab found %p: n=%s s=\"%s\" f=%g t=%o\n",
-			p, NN(p->nval), NN(p->sval), p->fval, p->tval) );
+			(void*)p, NN(p->nval), NN(p->sval), p->fval, p->tval) );
 		return(p);
 	}
 	p = (Cell *) malloc(sizeof(Cell));
@@ -231,7 +231,7 @@ Cell *setsymtab(const char *n, const char *s, Awkfloat f, unsigned t, Array *tp)
 	p->cnext = tp->tab[h];
 	tp->tab[h] = p;
 	   dprintf( ("setsymtab set %p: n=%s s=\"%s\" f=%g t=%o\n",
-		p, p->nval, p->sval, p->fval, p->tval) );
+		(void*)p, p->nval, p->sval, p->fval, p->tval) );
 	return(p);
 }
 
@@ -298,7 +298,7 @@ Awkfloat setfval(Cell *vp, Awkfloat f)	/* set float val of a Cell */
 		xfree(vp->sval); /* free any previous string */
 	vp->tval &= ~STR;	/* mark string invalid */
 	vp->tval |= NUM;	/* mark number ok */
-	   dprintf( ("setfval %p: %s = %g, t=%o\n", vp, NN(vp->nval), f, vp->tval) );
+	   dprintf( ("setfval %p: %s = %g, t=%o\n", (void*)vp, NN(vp->nval), f, vp->tval) );
 	return vp->fval = f;
 }
 
@@ -318,7 +318,7 @@ char *setsval(Cell *vp, const char *s)	/* set string val of a Cell */
 	int fldno;
 
 	   dprintf( ("starting setsval %p: %s = \"%s\", t=%o, r,f=%d,%d\n", 
-		vp, NN(vp->nval), s, vp->tval, donerec, donefld) );
+		(void*)vp, NN(vp->nval), s, vp->tval, donerec, donefld) );
 	if ((vp->tval & (NUM | STR)) == 0)
 		funnyvar(vp, "assign to");
 	if (isfld(vp)) {
@@ -338,7 +338,7 @@ char *setsval(Cell *vp, const char *s)	/* set string val of a Cell */
 	vp->tval |= STR;
 	vp->tval &= ~DONTFREE;
 	   dprintf( ("setsval %p: %s = \"%s (%p) \", t=%o r,f=%d,%d\n", 
-		vp, NN(vp->nval), t,t, vp->tval, donerec, donefld) );
+		(void*)vp, NN(vp->nval), t,t, vp->tval, donerec, donefld) );
 	return(vp->sval = t);
 }
 
@@ -355,7 +355,8 @@ Awkfloat getfval(Cell *vp)	/* get float val of a Cell */
 		if (is_number(vp->sval) && !(vp->tval&CON))
 			vp->tval |= NUM;	/* make NUM only sparingly */
 	}
-	   dprintf( ("getfval %p: %s = %g, t=%o\n", vp, NN(vp->nval), vp->fval, vp->tval) );
+	   dprintf( ("getfval %p: %s = %g, t=%o\n",
+		(void*)vp, NN(vp->nval), vp->fval, vp->tval) );
 	return(vp->fval);
 }
 
@@ -381,7 +382,8 @@ static char *get_str_val(Cell *vp, char **fmt)        /* get string val of a Cel
 		vp->tval &= ~DONTFREE;
 		vp->tval |= STR;
 	}
-	   dprintf( ("getsval %p: %s = \"%s (%p)\", t=%o\n", vp, NN(vp->nval), vp->sval, vp->sval, vp->tval) );
+	   dprintf( ("getsval %p: %s = \"%s (%p)\", t=%o\n",
+		(void*)vp, NN(vp->nval), vp->sval, vp->sval, vp->tval) );
 	return(vp->sval);
 }