freebsd-src/parse.c
Warner Losh 2e406c584f ota: Import One True Awk from 20231102 (254b979f32df)
This is a rollup of a lot of changes. In summary, lots of bug fixes,
Unicode support and CSV support to match the 2nd Edition of the Awk
Book.

In detail, from AWK's FIXES and FIXES.1e:

From FIXES:
Oct 30, 2023:
	multiple fixes and a minor code cleanup.
	disabled utf-8 for non-multibyte locales, such as C or POSIX.
	fixed a bad char * cast that causes incorrect results on big-endian
	systems. also fixed an out-of-bounds read for empty CCL.
	fixed a buffer overflow in substr with utf-8 strings.
	many thanks to Todd C Miller.

Sep 24, 2023:
	fnematch and getrune have been overhauled to solve issues around
	unicode FS and RS. also fixed gsub null match issue with unicode.
	big thanks to Arnold Robbins.

Sep 12, 2023:
	Fixed a length error in u8_byte2char that set RSTART to
	incorrect (cannot happen) value for EOL match(str, /$/).

-----------------------------------------------------------------

[This entry is a summary, not a precise list of changes.]

	Added --csv option to enable processing of comma-separated
	values inputs.  When --csv is enabled, fields are separated
	by commas, fields may be quoted with " double quotes, fields
	may contain embedded newlines.

	If no explicit separator argument is provided, split() uses
	the setting of --csv to determine how fields are split.

	Strings may now contain UTF-8 code points (not necessarily
	characters).  Functions that operate on characters, like
	length, substr, index, match, etc., use UTF-8, so the length
	of a string of 3 emojis is 3, not 12 as it would be if bytes
	were counted.

	Regular expressions are processes as UTF-8.

	Unicode literals can be written as \u followed by one
	to eight hexadecimal digits.  These may appear in strings and
	regular expressions.

From FIXES.1e:

Sep 06, 2023:
	Fix edge case where FS is changed on commandline. Thanks to
	Gordon Shephard and Miguel Pineiro Jr.

	Fix regular expression clobbering in the lexer, where lexer does
	not make a copy of regexp literals. also makedfa memory leaks have
	been plugged. Thanks to Miguel Pineiro Jr.

Dec 15, 2022:
	Force hex escapes in strings to be no more than two characters,
	as they already are in regular expressions. This brings internal
	consistency, as well as consistency with gawk. Thanks to
	Arnold Robbins.

Sep 12, 2022:
	adjbuf minlen error (cannot be 0) in cat, resulting in NULL pbuf.
	discovered by todd miller. also use-after-free issue with
	tempfree in cat, thanks to Miguel Pineiro Jr and valgrind.

Aug 30, 2022:
	Various leaks and use-after-free issues plugged/fixed.
	Thanks to Miguel Pineiro Jr. <mpj@pineiro.cc>.

May 23, 2022:
	Memory leak when assigning a string to some of the built-in
	variables. allocated string erroneously marked DONTFREE.
	Thanks to Miguel Pineiro Jr. <mpj@pineiro.cc>.

Mar 14, 2022:
	Historic bug: command-line "name=value" assignment had been
	truncating its entry in ARGV. (circa 1989) Thanks to
	Miguel Pineiro Jr. <mpj@pineiro.cc>.

Mar 3, 2022:
	Fixed file management memory leak that appears to have been
	there since the files array was first initialized with stdin,
	stdout, and stderr (circa 1992). Thanks to Miguel Pineiro Jr.
	<mpj@pineiro.cc>.

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.

Sponsored by:		Netflix
2023-11-02 10:20:09 -06:00

300 lines
5.4 KiB
C

/****************************************************************
Copyright (C) Lucent Technologies 1997
All Rights Reserved
Permission to use, copy, modify, and distribute this software and
its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all
copies and that both that the copyright notice and this
permission notice and warranty disclaimer appear in supporting
documentation, and that the name Lucent Technologies or any of
its entities not be used in advertising or publicity pertaining
to distribution of the software without specific, written prior
permission.
LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
****************************************************************/
#define DEBUG
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "awk.h"
#include "awkgram.tab.h"
Node *nodealloc(size_t n)
{
Node *x;
x = (Node *) malloc(sizeof(*x) + (n-1) * sizeof(x));
if (x == NULL)
FATAL("out of space in nodealloc");
x->nnext = NULL;
x->lineno = lineno;
return(x);
}
Node *exptostat(Node *a)
{
a->ntype = NSTAT;
return(a);
}
Node *node1(int a, Node *b)
{
Node *x;
x = nodealloc(1);
x->nobj = a;
x->narg[0]=b;
return(x);
}
Node *node2(int a, Node *b, Node *c)
{
Node *x;
x = nodealloc(2);
x->nobj = a;
x->narg[0] = b;
x->narg[1] = c;
return(x);
}
Node *node3(int a, Node *b, Node *c, Node *d)
{
Node *x;
x = nodealloc(3);
x->nobj = a;
x->narg[0] = b;
x->narg[1] = c;
x->narg[2] = d;
return(x);
}
Node *node4(int a, Node *b, Node *c, Node *d, Node *e)
{
Node *x;
x = nodealloc(4);
x->nobj = a;
x->narg[0] = b;
x->narg[1] = c;
x->narg[2] = d;
x->narg[3] = e;
return(x);
}
Node *node5(int a, Node *b, Node *c, Node *d, Node *e, Node *f)
{
Node *x;
x = nodealloc(5);
x->nobj = a;
x->narg[0] = b;
x->narg[1] = c;
x->narg[2] = d;
x->narg[3] = e;
x->narg[4] = f;
return(x);
}
Node *stat1(int a, Node *b)
{
Node *x;
x = node1(a,b);
x->ntype = NSTAT;
return(x);
}
Node *stat2(int a, Node *b, Node *c)
{
Node *x;
x = node2(a,b,c);
x->ntype = NSTAT;
return(x);
}
Node *stat3(int a, Node *b, Node *c, Node *d)
{
Node *x;
x = node3(a,b,c,d);
x->ntype = NSTAT;
return(x);
}
Node *stat4(int a, Node *b, Node *c, Node *d, Node *e)
{
Node *x;
x = node4(a,b,c,d,e);
x->ntype = NSTAT;
return(x);
}
Node *op1(int a, Node *b)
{
Node *x;
x = node1(a,b);
x->ntype = NEXPR;
return(x);
}
Node *op2(int a, Node *b, Node *c)
{
Node *x;
x = node2(a,b,c);
x->ntype = NEXPR;
return(x);
}
Node *op3(int a, Node *b, Node *c, Node *d)
{
Node *x;
x = node3(a,b,c,d);
x->ntype = NEXPR;
return(x);
}
Node *op4(int a, Node *b, Node *c, Node *d, Node *e)
{
Node *x;
x = node4(a,b,c,d,e);
x->ntype = NEXPR;
return(x);
}
Node *op5(int a, Node *b, Node *c, Node *d, Node *e, Node *f)
{
Node *x;
x = node5(a,b,c,d,e,f);
x->ntype = NEXPR;
return(x);
}
Node *celltonode(Cell *a, int b)
{
Node *x;
a->ctype = OCELL;
a->csub = b;
x = node1(0, (Node *) a);
x->ntype = NVALUE;
return(x);
}
Node *rectonode(void) /* make $0 into a Node */
{
extern Cell *literal0;
return op1(INDIRECT, celltonode(literal0, CUNK));
}
Node *makearr(Node *p)
{
Cell *cp;
if (isvalue(p)) {
cp = (Cell *) (p->narg[0]);
if (isfcn(cp))
SYNTAX( "%s is a function, not an array", cp->nval );
else if (!isarr(cp)) {
xfree(cp->sval);
cp->sval = (char *) makesymtab(NSYMTAB);
cp->tval = ARR;
}
}
return p;
}
#define PA2NUM 50 /* max number of pat,pat patterns allowed */
int paircnt; /* number of them in use */
int pairstack[PA2NUM]; /* state of each pat,pat */
Node *pa2stat(Node *a, Node *b, Node *c) /* pat, pat {...} */
{
Node *x;
x = node4(PASTAT2, a, b, c, itonp(paircnt));
if (paircnt++ >= PA2NUM)
SYNTAX( "limited to %d pat,pat statements", PA2NUM );
x->ntype = NSTAT;
return(x);
}
Node *linkum(Node *a, Node *b)
{
Node *c;
if (errorflag) /* don't link things that are wrong */
return a;
if (a == NULL)
return(b);
else if (b == NULL)
return(a);
for (c = a; c->nnext != NULL; c = c->nnext)
;
c->nnext = b;
return(a);
}
void defn(Cell *v, Node *vl, Node *st) /* turn on FCN bit in definition, */
{ /* body of function, arglist */
Node *p;
int n;
if (isarr(v)) {
SYNTAX( "`%s' is an array name and a function name", v->nval );
return;
}
if (isarg(v->nval) != -1) {
SYNTAX( "`%s' is both function name and argument name", v->nval );
return;
}
v->tval = FCN;
v->sval = (char *) st;
n = 0; /* count arguments */
for (p = vl; p; p = p->nnext)
n++;
v->fval = n;
DPRINTF("defining func %s (%d args)\n", v->nval, n);
}
int isarg(const char *s) /* is s in argument list for current function? */
{ /* return -1 if not, otherwise arg # */
extern Node *arglist;
Node *p = arglist;
int n;
for (n = 0; p != NULL; p = p->nnext, n++)
if (strcmp(((Cell *)(p->narg[0]))->nval, s) == 0)
return n;
return -1;
}
int ptoi(void *p) /* convert pointer to integer */
{
return (int) (long) p; /* swearing that p fits, of course */
}
Node *itonp(int i) /* and vice versa */
{
return (Node *) (long) i;
}