freebsd-skq/contrib/one-true-awk/lib.c
Warner Losh b525355729 Merge from upstream at 4189ef5d from https://github.com/onetrueawk/awk.git
Note: this backs out a number of changes we've made to awk because
they aren't upstream, but are on the vendor branch. Those will be
reapplied. svn makes it needlessly difficult to know which ones, but
at least r315426, r301289, and maybe r301691, though there may be
others too. None of these are critical, so bisecting through this
point is safe for all but awk regression tests :).
2019-06-02 16:25:07 +00:00

730 lines
17 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 <ctype.h>
#include <errno.h>
#include <stdlib.h>
#include <stdarg.h>
#include "awk.h"
#include "ytab.h"
FILE *infile = NULL;
char *file = "";
char *record;
int recsize = RECSIZE;
char *fields;
int fieldssize = RECSIZE;
Cell **fldtab; /* pointers to Cells */
char inputFS[100] = " ";
#define MAXFLD 2
int nfields = MAXFLD; /* last allocated slot for $i */
int donefld; /* 1 = implies rec broken into fields */
int donerec; /* 1 = record is valid (no flds have changed) */
int lastfld = 0; /* last used field */
int argno = 1; /* current input argument number */
extern Awkfloat *ARGC;
static Cell dollar0 = { OCELL, CFLD, NULL, "", 0.0, REC|STR|DONTFREE };
static Cell dollar1 = { OCELL, CFLD, NULL, "", 0.0, FLD|STR|DONTFREE };
void recinit(unsigned int n)
{
if ( (record = (char *) malloc(n)) == NULL
|| (fields = (char *) malloc(n+1)) == NULL
|| (fldtab = (Cell **) malloc((nfields+2) * sizeof(Cell *))) == NULL
|| (fldtab[0] = (Cell *) malloc(sizeof(Cell))) == NULL )
FATAL("out of space for $0 and fields");
*record = '\0';
*fldtab[0] = dollar0;
fldtab[0]->sval = record;
fldtab[0]->nval = tostring("0");
makefields(1, nfields);
}
void makefields(int n1, int n2) /* create $n1..$n2 inclusive */
{
char temp[50];
int i;
for (i = n1; i <= n2; i++) {
fldtab[i] = (Cell *) malloc(sizeof (struct Cell));
if (fldtab[i] == NULL)
FATAL("out of space in makefields %d", i);
*fldtab[i] = dollar1;
sprintf(temp, "%d", i);
fldtab[i]->nval = tostring(temp);
}
}
void initgetrec(void)
{
int i;
char *p;
for (i = 1; i < *ARGC; i++) {
p = getargv(i); /* find 1st real filename */
if (p == NULL || *p == '\0') { /* deleted or zapped */
argno++;
continue;
}
if (!isclvar(p)) {
setsval(lookup("FILENAME", symtab), p);
return;
}
setclvar(p); /* a commandline assignment before filename */
argno++;
}
infile = stdin; /* no filenames, so use stdin */
}
static int firsttime = 1;
int getrec(char **pbuf, int *pbufsize, int isrecord) /* get next input record */
{ /* note: cares whether buf == record */
int c;
char *buf = *pbuf;
uschar saveb0;
int bufsize = *pbufsize, savebufsize = bufsize;
if (firsttime) {
firsttime = 0;
initgetrec();
}
dprintf( ("RS=<%s>, FS=<%s>, ARGC=%g, FILENAME=%s\n",
*RS, *FS, *ARGC, *FILENAME) );
if (isrecord) {
donefld = 0;
donerec = 1;
}
saveb0 = buf[0];
buf[0] = 0;
while (argno < *ARGC || infile == stdin) {
dprintf( ("argno=%d, file=|%s|\n", argno, file) );
if (infile == NULL) { /* have to open a new file */
file = getargv(argno);
if (file == NULL || *file == '\0') { /* deleted or zapped */
argno++;
continue;
}
if (isclvar(file)) { /* a var=value arg */
setclvar(file);
argno++;
continue;
}
*FILENAME = file;
dprintf( ("opening file %s\n", file) );
if (*file == '-' && *(file+1) == '\0')
infile = stdin;
else if ((infile = fopen(file, "r")) == NULL)
FATAL("can't open file %s", file);
setfval(fnrloc, 0.0);
}
c = readrec(&buf, &bufsize, infile);
if (c != 0 || buf[0] != '\0') { /* normal record */
if (isrecord) {
if (freeable(fldtab[0]))
xfree(fldtab[0]->sval);
fldtab[0]->sval = buf; /* buf == record */
fldtab[0]->tval = REC | STR | DONTFREE;
if (is_number(fldtab[0]->sval)) {
fldtab[0]->fval = atof(fldtab[0]->sval);
fldtab[0]->tval |= NUM;
}
}
setfval(nrloc, nrloc->fval+1);
setfval(fnrloc, fnrloc->fval+1);
*pbuf = buf;
*pbufsize = bufsize;
return 1;
}
/* EOF arrived on this file; set up next */
if (infile != stdin)
fclose(infile);
infile = NULL;
argno++;
}
buf[0] = saveb0;
*pbuf = buf;
*pbufsize = savebufsize;
return 0; /* true end of file */
}
void nextfile(void)
{
if (infile != NULL && infile != stdin)
fclose(infile);
infile = NULL;
argno++;
}
int readrec(char **pbuf, int *pbufsize, FILE *inf) /* read one record into buf */
{
int sep, c;
char *rr, *buf = *pbuf;
int bufsize = *pbufsize;
char *rs = getsval(rsloc);
if (strlen(getsval(fsloc)) >= 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';
while ((c=getc(inf)) == '\n' && c != EOF) /* skip leading \n's */
;
if (c != EOF)
ungetc(c, inf);
}
for (rr = buf; ; ) {
for (; (c=getc(inf)) != sep && c != EOF; ) {
if (rr-buf+1 > bufsize)
if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 1"))
FATAL("input record `%.30s...' too long", buf);
*rr++ = c;
}
if (*rs == sep || c == EOF)
break;
if ((c = getc(inf)) == '\n' || c == EOF) /* 2 in a row */
break;
if (!adjbuf(&buf, &bufsize, 2+rr-buf, recsize, &rr, "readrec 2"))
FATAL("input record `%.30s...' too long", buf);
*rr++ = '\n';
*rr++ = c;
}
if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 3"))
FATAL("input record `%.30s...' too long", buf);
*rr = 0;
dprintf( ("readrec saw <%s>, returns %d\n", buf, c == EOF && rr == buf ? 0 : 1) );
*pbuf = buf;
*pbufsize = bufsize;
return c == EOF && rr == buf ? 0 : 1;
}
char *getargv(int n) /* get ARGV[n] */
{
Cell *x;
char *s, temp[50];
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) );
return s;
}
void setclvar(char *s) /* set var=value from s */
{
char *p;
Cell *q;
for (p=s; *p != '='; p++)
;
*p++ = 0;
p = qstring(p, '\0');
q = setsymtab(s, p, 0.0, STR, symtab);
setsval(q, p);
if (is_number(q->sval)) {
q->fval = atof(q->sval);
q->tval |= NUM;
}
dprintf( ("command line set %s to |%s|\n", s, p) );
}
void fldbld(void) /* create fields from current record */
{
/* this relies on having fields[] the same length as $0 */
/* the fields are all stored in this one array with \0's */
/* possibly with a final trailing \0 not associated with any field */
char *r, *fr, sep;
Cell *p;
int i, j, n;
if (donefld)
return;
if (!isstr(fldtab[0]))
getsval(fldtab[0]);
r = fldtab[0]->sval;
n = strlen(r);
if (n > fieldssize) {
xfree(fields);
if ((fields = (char *) malloc(n+2)) == NULL) /* possibly 2 final \0s */
FATAL("out of space for fields in fldbld %d", n);
fieldssize = n;
}
fr = fields;
i = 0; /* number of fields accumulated here */
if (strlen(getsval(fsloc)) >= sizeof (inputFS))
FATAL("field separator %.10s... is too long", *FS);
strcpy(inputFS, *FS);
if (strlen(inputFS) > 1) { /* it's a regular expression */
i = refldbld(r, inputFS);
} else if ((sep = *inputFS) == ' ') { /* default whitespace */
for (i = 0; ; ) {
while (*r == ' ' || *r == '\t' || *r == '\n')
r++;
if (*r == 0)
break;
i++;
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
fldtab[i]->sval = fr;
fldtab[i]->tval = FLD | STR | DONTFREE;
do
*fr++ = *r++;
while (*r != ' ' && *r != '\t' && *r != '\n' && *r != '\0');
*fr++ = 0;
}
*fr = 0;
} else if ((sep = *inputFS) == 0) { /* new: FS="" => 1 char/field */
for (i = 0; *r != 0; r++) {
char buf[2];
i++;
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
buf[0] = *r;
buf[1] = 0;
fldtab[i]->sval = tostring(buf);
fldtab[i]->tval = FLD | STR;
}
*fr = 0;
} else if (*r != 0) { /* if 0, it's a null field */
/* subtlecase : if length(FS) == 1 && length(RS > 0)
* \n is NOT a field separator (cf awk book 61,84).
* this variable is tested in the inner while loop.
*/
int rtest = '\n'; /* normal case */
if (strlen(*RS) > 0)
rtest = '\0';
for (;;) {
i++;
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
fldtab[i]->sval = fr;
fldtab[i]->tval = FLD | STR | DONTFREE;
while (*r != sep && *r != rtest && *r != '\0') /* \n is always a separator */
*fr++ = *r++;
*fr++ = 0;
if (*r++ == 0)
break;
}
*fr = 0;
}
if (i > nfields)
FATAL("record `%.30s...' has too many fields; can't happen", r);
cleanfld(i+1, lastfld); /* clean out junk from previous record */
lastfld = i;
donefld = 1;
for (j = 1; j <= lastfld; j++) {
p = fldtab[j];
if(is_number(p->sval)) {
p->fval = atof(p->sval);
p->tval |= NUM;
}
}
setfval(nfloc, (Awkfloat) lastfld);
donerec = 1; /* restore */
if (dbg) {
for (j = 0; j <= lastfld; j++) {
p = fldtab[j];
printf("field %d (%s): |%s|\n", j, p->nval, p->sval);
}
}
}
void cleanfld(int n1, int n2) /* clean out fields n1 .. n2 inclusive */
{ /* nvals remain intact */
Cell *p;
int i;
for (i = n1; i <= n2; i++) {
p = fldtab[i];
if (freeable(p))
xfree(p->sval);
p->sval = "";
p->tval = FLD | STR | DONTFREE;
}
}
void newfld(int n) /* add field n after end of existing lastfld */
{
if (n > nfields)
growfldtab(n);
cleanfld(lastfld+1, n);
lastfld = n;
setfval(nfloc, (Awkfloat) n);
}
void setlastfld(int n) /* set lastfld cleaning fldtab cells if necessary */
{
if (n < 0)
FATAL("cannot set NF to a negative value");
if (n > nfields)
growfldtab(n);
if (lastfld < n)
cleanfld(lastfld+1, n);
else
cleanfld(n+1, lastfld);
lastfld = n;
}
Cell *fieldadr(int n) /* get nth field */
{
if (n < 0)
FATAL("trying to access out of range field %d", n);
if (n > nfields) /* fields after NF are empty */
growfldtab(n); /* but does not increase NF */
return(fldtab[n]);
}
void growfldtab(int n) /* make new fields up to at least $n */
{
int nf = 2 * nfields;
size_t s;
if (n > nf)
nf = n;
s = (nf+1) * (sizeof (struct Cell *)); /* freebsd: how much do we need? */
if (s / sizeof(struct Cell *) - 1 == nf) /* didn't overflow */
fldtab = (Cell **) realloc(fldtab, s);
else /* overflow sizeof int */
xfree(fldtab); /* make it null */
if (fldtab == NULL)
FATAL("out of space creating %d fields", nf);
makefields(nfields+1, nf);
nfields = nf;
}
int refldbld(const char *rec, const char *fs) /* build fields from reg expr in FS */
{
/* this relies on having fields[] the same length as $0 */
/* the fields are all stored in this one array with \0's */
char *fr;
int i, tempstat, n;
fa *pfa;
n = strlen(rec);
if (n > fieldssize) {
xfree(fields);
if ((fields = (char *) malloc(n+1)) == NULL)
FATAL("out of space for fields in refldbld %d", n);
fieldssize = n;
}
fr = fields;
*fr = '\0';
if (*rec == '\0')
return 0;
pfa = makedfa(fs, 1);
dprintf( ("into refldbld, rec = <%s>, pat = <%s>\n", rec, fs) );
tempstat = pfa->initstat;
for (i = 1; ; i++) {
if (i > nfields)
growfldtab(i);
if (freeable(fldtab[i]))
xfree(fldtab[i]->sval);
fldtab[i]->tval = FLD | STR | DONTFREE;
fldtab[i]->sval = fr;
dprintf( ("refldbld: i=%d\n", i) );
if (nematch(pfa, rec)) {
pfa->initstat = 2; /* horrible coupling to b.c */
dprintf( ("match %s (%d chars)\n", patbeg, patlen) );
strncpy(fr, rec, patbeg-rec);
fr += patbeg - rec + 1;
*(fr-1) = '\0';
rec = patbeg + patlen;
} else {
dprintf( ("no match %s\n", rec) );
strcpy(fr, rec);
pfa->initstat = tempstat;
break;
}
}
return i;
}
void recbld(void) /* create $0 from $1..$NF if necessary */
{
int i;
char *r, *p;
char *sep = getsval(ofsloc);
if (donerec == 1)
return;
r = record;
for (i = 1; i <= *NF; i++) {
p = getsval(fldtab[i]);
if (!adjbuf(&record, &recsize, 1+strlen(p)+r-record, recsize, &r, "recbld 1"))
FATAL("created $0 `%.30s...' too long", record);
while ((*r = *p++) != 0)
r++;
if (i < *NF) {
if (!adjbuf(&record, &recsize, 2+strlen(sep)+r-record, recsize, &r, "recbld 2"))
FATAL("created $0 `%.30s...' too long", record);
for (p = sep; (*r = *p++) != 0; )
r++;
}
}
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, (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, (void*)fldtab[0]) );
dprintf( ("recbld = |%s|\n", record) );
donerec = 1;
}
int errorflag = 0;
void yyerror(const char *s)
{
SYNTAX("%s", s);
}
void SYNTAX(const char *fmt, ...)
{
extern char *cmdname, *curfname;
static int been_here = 0;
va_list varg;
if (been_here++ > 2)
return;
fprintf(stderr, "%s: ", cmdname);
va_start(varg, fmt);
vfprintf(stderr, fmt, varg);
va_end(varg);
fprintf(stderr, " at source line %d", lineno);
if (curfname != NULL)
fprintf(stderr, " in function %s", curfname);
if (compile_time == 1 && cursource() != NULL)
fprintf(stderr, " source file %s", cursource());
fprintf(stderr, "\n");
errorflag = 2;
eprint();
}
void fpecatch(int n)
{
FATAL("floating point exception %d", n);
}
extern int bracecnt, brackcnt, parencnt;
void bracecheck(void)
{
int c;
static int beenhere = 0;
if (beenhere++)
return;
while ((c = input()) != EOF && c != '\0')
bclass(c);
bcheck2(bracecnt, '{', '}');
bcheck2(brackcnt, '[', ']');
bcheck2(parencnt, '(', ')');
}
void bcheck2(int n, int c1, int c2)
{
if (n == 1)
fprintf(stderr, "\tmissing %c\n", c2);
else if (n > 1)
fprintf(stderr, "\t%d missing %c's\n", n, c2);
else if (n == -1)
fprintf(stderr, "\textra %c\n", c2);
else if (n < -1)
fprintf(stderr, "\t%d extra %c's\n", -n, c2);
}
void FATAL(const char *fmt, ...)
{
extern char *cmdname;
va_list varg;
fflush(stdout);
fprintf(stderr, "%s: ", cmdname);
va_start(varg, fmt);
vfprintf(stderr, fmt, varg);
va_end(varg);
error();
if (dbg > 1) /* core dump if serious debugging on */
abort();
exit(2);
}
void WARNING(const char *fmt, ...)
{
extern char *cmdname;
va_list varg;
fflush(stdout);
fprintf(stderr, "%s: ", cmdname);
va_start(varg, fmt);
vfprintf(stderr, fmt, varg);
va_end(varg);
error();
}
void error()
{
extern Node *curnode;
fprintf(stderr, "\n");
if (compile_time != 2 && NR && *NR > 0) {
fprintf(stderr, " input record number %d", (int) (*FNR));
if (strcmp(*FILENAME, "-") != 0)
fprintf(stderr, ", file %s", *FILENAME);
fprintf(stderr, "\n");
}
if (compile_time != 2 && curnode)
fprintf(stderr, " source line number %d", curnode->lineno);
else if (compile_time != 2 && lineno)
fprintf(stderr, " source line number %d", lineno);
if (compile_time == 1 && cursource() != NULL)
fprintf(stderr, " source file %s", cursource());
fprintf(stderr, "\n");
eprint();
}
void eprint(void) /* try to print context around error */
{
char *p, *q;
int c;
static int been_here = 0;
extern char ebuf[], *ep;
if (compile_time == 2 || compile_time == 0 || been_here++ > 0 || ebuf == ep)
return;
if (ebuf == ep)
return;
p = ep - 1;
if (p > ebuf && *p == '\n')
p--;
for ( ; p > ebuf && *p != '\n' && *p != '\0'; p--)
;
while (*p == '\n')
p++;
fprintf(stderr, " context is\n\t");
for (q=ep-1; q>=p && *q!=' ' && *q!='\t' && *q!='\n'; q--)
;
for ( ; p < q; p++)
if (*p)
putc(*p, stderr);
fprintf(stderr, " >>> ");
for ( ; p < ep; p++)
if (*p)
putc(*p, stderr);
fprintf(stderr, " <<< ");
if (*ep)
while ((c = input()) != '\n' && c != '\0' && c != EOF) {
putc(c, stderr);
bclass(c);
}
putc('\n', stderr);
ep = ebuf;
}
void bclass(int c)
{
switch (c) {
case '{': bracecnt++; break;
case '}': bracecnt--; break;
case '[': brackcnt++; break;
case ']': brackcnt--; break;
case '(': parencnt++; break;
case ')': parencnt--; break;
}
}
double errcheck(double x, const char *s)
{
if (errno == EDOM) {
errno = 0;
WARNING("%s argument out of domain", s);
x = 1;
} else if (errno == ERANGE) {
errno = 0;
WARNING("%s result out of range", s);
x = 1;
}
return x;
}
int isclvar(const char *s) /* is s of form var=something ? */
{
const char *os = s;
if (!isalpha((uschar) *s) && *s != '_')
return 0;
for ( ; *s; s++)
if (!(isalnum((uschar) *s) || *s == '_'))
break;
return *s == '=' && s > os;
}
/* strtod is supposed to be a proper test of what's a valid number */
/* appears to be broken in gcc on linux: thinks 0x123 is a valid FP number */
/* wrong: violates 4.10.1.4 of ansi C standard */
#include <math.h>
int is_number(const char *s)
{
double r;
char *ep;
errno = 0;
r = strtod(s, &ep);
if (ep == s || r == HUGE_VAL || errno == ERANGE)
return 0;
while (*ep == ' ' || *ep == '\t' || *ep == '\n')
ep++;
if (*ep == '\0')
return 1;
else
return 0;
}