refldbld(uchar *rec, uchar *fs) /* build fields from reg expr in FS */
{
uchar *fr;
int i, tempstat;
fa *pfa;
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 < nfields; i++) {
if (!(fldtab[i].tval & DONTFREE))
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 */
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;
}
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;
}
static int refldbld(unsigned char *rec,
unsigned char *fs) /* build fields from reg expr in FS */
{
unsigned char *fr;
int i;
fa *pfa;
fr = fields;
*fr = '\0';
if (*rec == '\0')
return 0;
pfa = makedfa(fs, 1);
dprintf( ("into refldbld, rec = <%s>, pat = <%s>\n", rec,
fs) );
pfa->notbol = 0;
for (i = 1; ; i++) {
if (i >= MAXFLD)
morefields();
if (!(fldtab[i]->tval & DONTFREE))
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->notbol = REG_NOTBOL;
dprintf( ("match %s (%d chars\n",
patbeg, patlen) );
strncpy((char*) fr, (char*) rec, patbeg-rec);
fr += patbeg - rec + 1;
*(fr-1) = '\0';
rec = patbeg + patlen;
} else {
dprintf( ("no match %s\n", rec) );
strcpy((char*) fr, (char*) rec);
pfa->notbol = 0;
break;
}
}
return i;
}
Cell *split(Node **a, int nnn) /* split(a[0], a[1], a[2]); a[3] is type */
{
Cell *x = 0, *y, *ap;
char *s;
int sep;
char *t, temp, num[10], *fs = 0;
int n, tempstat;
y = execute(a[0]); /* source string */
s = getsval(y);
if (a[2] == 0) /* fs string */
fs = *FS;
else if ((int) a[3] == STRING) { /* split(str,arr,"string") */
x = execute(a[2]);
fs = getsval(x);
} else if ((int) a[3] == REGEXPR)
fs = (char*) "(regexpr)"; /* split(str,arr,/regexpr/) */
else
ERROR "illegal type of split()" FATAL;
sep = *fs;
ap = execute(a[1]); /* array name */
freesymtab(ap);
dprintf( ("split: s=|%s|, a=%s, sep=|%s|\n", s, ap->nval, fs) );
ap->tval &= ~STR;
ap->tval |= ARR;
ap->sval = (char *) makesymtab(NSYMTAB);
n = 0;
if ((*s != '\0' && strlen(fs) > 1) || (int) a[3] == REGEXPR) { /* reg expr */
fa *pfa;
if ((int) a[3] == REGEXPR) { /* it's ready already */
pfa = (fa *) a[2];
} else {
pfa = makedfa(fs, 1);
}
if (nematch(pfa,s)) {
tempstat = pfa->initstat;
pfa->initstat = 2;
do {
n++;
sprintf((char *)num, "%d", n);
temp = *patbeg;
*patbeg = '\0';
if (isnumber(s))
setsymtab(num, s, atof((char *)s), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, s, 0.0, STR, (Array *) ap->sval);
*patbeg = temp;
s = patbeg + patlen;
if (*(patbeg+patlen-1) == 0 || *s == 0) {
n++;
sprintf((char *)num, "%d", n);
setsymtab(num, "", 0.0, STR, (Array *) ap->sval);
pfa->initstat = tempstat;
goto spdone;
}
} while (nematch(pfa,s));
}
n++;
sprintf((char *)num, "%d", n);
if (isnumber(s))
setsymtab(num, s, atof((char *)s), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, s, 0.0, STR, (Array *) ap->sval);
spdone:
pfa = NULL;
} else if (sep == ' ') {
for (n = 0; ; ) {
while (*s == ' ' || *s == '\t' || *s == '\n')
s++;
if (*s == 0)
break;
n++;
t = s;
do
s++;
while (*s!=' ' && *s!='\t' && *s!='\n' && *s!='\0');
temp = *s;
*s = '\0';
sprintf((char *)num, "%d", n);
if (isnumber(t))
setsymtab(num, t, atof((char *)t), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, t, 0.0, STR, (Array *) ap->sval);
*s = temp;
if (*s != 0)
s++;
}
} else if (sep == 0) { /* new: split(s, a, "") => 1 char/elem */
for (n = 0; *s != 0; s++) {
char buf[2];
n++;
sprintf((char *)num, "%d", n);
buf[0] = *s;
buf[1] = 0;
if (isdigit(buf[0]))
setsymtab(num, buf, atof(buf), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, buf, 0.0, STR, (Array *) ap->sval);
}
} else if (*s != 0) {
for (;;) {
n++;
t = s;
while (*s != sep && *s != '\n' && *s != '\0')
s++;
temp = *s;
*s = '\0';
sprintf((char *)num, "%d", n);
if (isnumber(t))
setsymtab(num, t, atof((char *)t), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, t, 0.0, STR, (Array *) ap->sval);
*s = temp;
if (*s++ == 0)
break;
}
}
tempfree(ap);
tempfree(y);
if (a[2] != 0 && (int) a[3] == STRING)
tempfree(x);
x = gettemp();
x->tval = NUM;
x->fval = n;
return(x);
}
Cell *split(Node **a, int nnn) /* split(a[0], a[1], a[2]); a[3] is type */
{
Cell *x = 0, *y, *ap;
char *s, *origs;
int sep;
char *t, temp, num[50], *fs = 0;
int n, tempstat, arg3type;
y = execute(a[0]); /* source string */
origs = s = strdup(getsval(y));
arg3type = ptoi(a[3]);
if (a[2] == 0) /* fs string */
fs = *FS;
else if (arg3type == STRING) { /* split(str,arr,"string") */
x = execute(a[2]);
fs = getsval(x);
} else if (arg3type == REGEXPR)
fs = "(regexpr)"; /* split(str,arr,/regexpr/) */
else
FATAL("illegal type of split");
sep = *fs;
ap = execute(a[1]); /* array name */
freesymtab(ap);
dprintf( ("split: s=|%s|, a=%s, sep=|%s|\n", s, NN(ap->nval), fs) );
ap->tval &= ~STR;
ap->tval |= ARR;
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 */
pfa = (fa *) a[2];
} else {
pfa = makedfa(fs, 1);
}
if (nematch(pfa,s)) {
tempstat = pfa->initstat;
pfa->initstat = 2;
do {
n++;
sprintf(num, "%d", n);
temp = *patbeg;
*patbeg = '\0';
if (is_number(s))
setsymtab(num, s, atof(s), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, s, 0.0, STR, (Array *) ap->sval);
*patbeg = temp;
s = patbeg + patlen;
if (*(patbeg+patlen-1) == 0 || *s == 0) {
n++;
sprintf(num, "%d", n);
setsymtab(num, "", 0.0, STR, (Array *) ap->sval);
pfa->initstat = tempstat;
goto spdone;
}
} while (nematch(pfa,s));
pfa->initstat = tempstat; /* bwk: has to be here to reset */
/* cf gsub and refldbld */
}
n++;
sprintf(num, "%d", n);
if (is_number(s))
setsymtab(num, s, atof(s), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, s, 0.0, STR, (Array *) ap->sval);
spdone:
pfa = NULL;
} else if (sep == ' ') {
for (n = 0; ; ) {
while (*s == ' ' || *s == '\t' || *s == '\n')
s++;
if (*s == 0)
break;
n++;
t = s;
do
s++;
while (*s!=' ' && *s!='\t' && *s!='\n' && *s!='\0');
temp = *s;
*s = '\0';
sprintf(num, "%d", n);
if (is_number(t))
setsymtab(num, t, atof(t), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, t, 0.0, STR, (Array *) ap->sval);
*s = temp;
if (*s != 0)
s++;
}
} else if (sep == 0) { /* new: split(s, a, "") => 1 char/elem */
for (n = 0; *s != 0; s++) {
char buf[2];
n++;
sprintf(num, "%d", n);
buf[0] = *s;
buf[1] = 0;
if (isdigit((uschar)buf[0]))
setsymtab(num, buf, atof(buf), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, buf, 0.0, STR, (Array *) ap->sval);
}
} else if (*s != 0) {
for (;;) {
n++;
t = s;
while (*s != sep && *s != '\n' && *s != '\0')
s++;
temp = *s;
*s = '\0';
sprintf(num, "%d", n);
if (is_number(t))
setsymtab(num, t, atof(t), STR|NUM, (Array *) ap->sval);
else
setsymtab(num, t, 0.0, STR, (Array *) ap->sval);
*s = temp;
if (*s++ == 0)
break;
}
}
tempfree(ap);
tempfree(y);
free(origs);
if (a[2] != 0 && arg3type == STRING) {
tempfree(x);
}
x = gettemp();
x->tval = NUM;
x->fval = n;
return(x);
}
