aboutsummaryrefslogtreecommitdiffstats
path: root/b.c
diff options
context:
space:
mode:
authorzoulasc <zoulasc@users.noreply.github.com>2019-10-17 13:04:46 -0400
committerArnold Robbins <arnold@skeeve.com>2019-10-17 13:04:45 -0400
commitc16e8696d7f40f041fdfd7a730d8656bcda437b6 (patch)
treefb2267b063f58c95c1f52f77b91c31988fd75446 /b.c
parent0ba1d0391d75532d3e75142bc904f862b0e033a4 (diff)
downloadplatform_external_one-true-awk-c16e8696d7f40f041fdfd7a730d8656bcda437b6.tar.gz
platform_external_one-true-awk-c16e8696d7f40f041fdfd7a730d8656bcda437b6.tar.bz2
platform_external_one-true-awk-c16e8696d7f40f041fdfd7a730d8656bcda437b6.zip
Amended the all pull request. (#51)
* [from NetBSD] - dynamic state allocation - centralize vector growth - centralize int array allocation - no casts for void * functions * - add missing allocation - revert change loop in pmatch
Diffstat (limited to 'b.c')
-rw-r--r--b.c196
1 files changed, 103 insertions, 93 deletions
diff --git a/b.c b/b.c
index ea70fd5..bf7fcd6 100644
--- a/b.c
+++ b/b.c
@@ -76,10 +76,71 @@ static int poscnt;
char *patbeg;
int patlen;
-#define NFA 20 /* cache this many dynamic fa's */
+#define NFA 128 /* cache this many dynamic fa's */
fa *fatab[NFA];
int nfatab = 0; /* entries in fatab */
+static int *
+intalloc(size_t n, const char *f)
+{
+ void *p = calloc(n, sizeof(int));
+ if (p == NULL)
+ overflo(f);
+ return p;
+}
+
+static void
+resizesetvec(const char *f)
+{
+ if (maxsetvec == 0)
+ maxsetvec = MAXLIN;
+ else
+ maxsetvec *= 4;
+ setvec = realloc(setvec, maxsetvec * sizeof(*setvec));
+ tmpset = realloc(tmpset, maxsetvec * sizeof(*tmpset));
+ if (setvec == NULL || tmpset == NULL)
+ overflo(f);
+}
+
+static void
+resize_state(fa *f, int state)
+{
+ void *p;
+ int i, new_count;
+
+ if (++state < f->state_count)
+ return;
+
+ new_count = state + 10; /* needs to be tuned */
+
+ p = realloc(f->gototab, new_count * sizeof(f->gototab[0]));
+ if (p == NULL)
+ goto out;
+ f->gototab = p;
+
+ p = realloc(f->out, new_count * sizeof(f->out[0]));
+ if (p == NULL)
+ goto out;
+ f->out = p;
+
+ p = realloc(f->posns, new_count * sizeof(f->posns[0]));
+ if (p == NULL)
+ goto out;
+ f->posns = p;
+
+ for (i = f->state_count; i < new_count; ++i) {
+ f->gototab[i] = calloc(NCHARS, sizeof(**f->gototab));
+ if (f->gototab[i] == NULL)
+ goto out;
+ f->out[i] = 0;
+ f->posns[i] = NULL;
+ }
+ f->state_count = new_count;
+ return;
+out:
+ overflo(__func__);
+}
+
fa *makedfa(const char *s, int anchor) /* returns dfa for reg expr s */
{
int i, use, nuse;
@@ -87,11 +148,7 @@ fa *makedfa(const char *s, int anchor) /* returns dfa for reg expr s */
static int now = 1;
if (setvec == NULL) { /* first time through any RE */
- maxsetvec = MAXLIN;
- setvec = (int *) malloc(maxsetvec * sizeof(int));
- tmpset = (int *) malloc(maxsetvec * sizeof(int));
- if (setvec == NULL || tmpset == NULL)
- overflo("out of space initializing makedfa");
+ resizesetvec(__func__);
}
if (compile_time) /* a constant for sure */
@@ -139,14 +196,13 @@ fa *mkdfa(const char *s, int anchor) /* does the real work of making a dfa */
poscnt = 0;
penter(p1); /* enter parent pointers and leaf indices */
if ((f = (fa *) calloc(1, sizeof(fa) + poscnt*sizeof(rrow))) == NULL)
- overflo("out of space for fa");
+ overflo(__func__);
f->accept = poscnt-1; /* penter has computed number of positions in re */
cfoll(f, p1); /* set up follow sets */
freetr(p1);
- if ((f->posns[0] = (int *) calloc(*(f->re[0].lfollow), sizeof(int))) == NULL)
- overflo("out of space in makedfa");
- if ((f->posns[1] = (int *) calloc(1, sizeof(int))) == NULL)
- overflo("out of space in makedfa");
+ resize_state(f, 1);
+ f->posns[0] = intalloc(*(f->re[0].lfollow), __func__);
+ f->posns[1] = intalloc(1, __func__);
*f->posns[1] = 0;
f->initstat = makeinit(f, anchor);
f->anchor = anchor;
@@ -164,11 +220,9 @@ int makeinit(fa *f, int anchor)
f->curstat = 2;
f->out[2] = 0;
- f->reset = 0;
k = *(f->re[0].lfollow);
xfree(f->posns[2]);
- if ((f->posns[2] = (int *) calloc(k+1, sizeof(int))) == NULL)
- overflo("out of space in makeinit");
+ f->posns[2] = intalloc(k + 1, __func__);
for (i=0; i <= k; i++) {
(f->posns[2])[i] = (f->re[0].lfollow)[i];
}
@@ -308,7 +362,7 @@ char *cclenter(const char *argp) /* add a character class */
static int bufsz = 100;
op = p;
- if (buf == NULL && (buf = (uschar *) malloc(bufsz)) == NULL)
+ if (buf == NULL && (buf = malloc(bufsz)) == NULL)
FATAL("out of space for character class [%.10s...] 1", p);
bp = buf;
for (i = 0; (c = *p++) != 0; ) {
@@ -347,7 +401,7 @@ char *cclenter(const char *argp) /* add a character class */
void overflo(const char *s)
{
- FATAL("regular expression too big: %.30s...", s);
+ FATAL("regular expression too big: out of space in %.30s...", s);
}
void cfoll(fa *f, Node *v) /* enter follow set of each leaf of vertex v into lfollow[leaf] */
@@ -361,18 +415,13 @@ void cfoll(fa *f, Node *v) /* enter follow set of each leaf of vertex v into lfo
f->re[info(v)].ltype = type(v);
f->re[info(v)].lval.np = right(v);
while (f->accept >= maxsetvec) { /* guessing here! */
- maxsetvec *= 4;
- setvec = (int *) realloc(setvec, maxsetvec * sizeof(int));
- tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int));
- if (setvec == NULL || tmpset == NULL)
- overflo("out of space in cfoll()");
+ resizesetvec(__func__);
}
for (i = 0; i <= f->accept; i++)
setvec[i] = 0;
setcnt = 0;
follow(v); /* computes setvec and setcnt */
- if ((p = (int *) calloc(setcnt+1, sizeof(int))) == NULL)
- overflo("out of space building follow set");
+ p = intalloc(setcnt + 1, __func__);
f->re[info(v)].lfollow = p;
*p = setcnt;
for (i = f->accept; i >= 0; i--)
@@ -402,11 +451,7 @@ int first(Node *p) /* collects initially active leaves of p into setvec */
LEAF
lp = info(p); /* look for high-water mark of subscripts */
while (setcnt >= maxsetvec || lp >= maxsetvec) { /* guessing here! */
- maxsetvec *= 4;
- setvec = (int *) realloc(setvec, maxsetvec * sizeof(int));
- tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int));
- if (setvec == NULL || tmpset == NULL)
- overflo("out of space in first()");
+ resizesetvec(__func__);
}
if (type(p) == EMPTYRE) {
setvec[lp] = 0;
@@ -484,7 +529,9 @@ int match(fa *f, const char *p0) /* shortest match ? */
int s, ns;
uschar *p = (uschar *) p0;
- s = f->reset ? makeinit(f,0) : f->initstat;
+ s = f->initstat;
+ assert (s < f->state_count);
+
if (f->out[s])
return(1);
do {
@@ -504,15 +551,11 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */
int s, ns;
uschar *p = (uschar *) p0;
uschar *q;
- int i, k;
- /* s = f->reset ? makeinit(f,1) : f->initstat; */
- if (f->reset) {
- f->initstat = s = makeinit(f,1);
- } else {
- s = f->initstat;
- }
- patbeg = (char *) p;
+ s = f->initstat;
+ assert(s < f->state_count);
+
+ patbeg = (char *)p;
patlen = -1;
do {
q = p;
@@ -524,6 +567,9 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */
s = ns;
else
s = cgoto(f, s, *q);
+
+ assert(s < f->state_count);
+
if (s == 1) { /* no transition */
if (patlen >= 0) {
patbeg = (char *) p;
@@ -541,20 +587,7 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */
}
nextin:
s = 2;
- if (f->reset) {
- for (i = 2; i <= f->curstat; i++)
- xfree(f->posns[i]);
- k = *f->posns[0];
- if ((f->posns[2] = (int *) calloc(k+1, sizeof(int))) == NULL)
- overflo("out of space in pmatch");
- for (i = 0; i <= k; i++)
- (f->posns[2])[i] = (f->posns[0])[i];
- f->initstat = f->curstat = 2;
- f->out[2] = f->out[0];
- for (i = 0; i < NCHARS; i++)
- f->gototab[2][i] = 0;
- }
- } while (*p++ != 0);
+ } while (*p++);
return (0);
}
@@ -563,14 +596,11 @@ int nematch(fa *f, const char *p0) /* non-empty match, for sub */
int s, ns;
uschar *p = (uschar *) p0;
uschar *q;
- int i, k;
- /* s = f->reset ? makeinit(f,1) : f->initstat; */
- if (f->reset) {
- f->initstat = s = makeinit(f,1);
- } else {
- s = f->initstat;
- }
+ s = f->initstat;
+ assert(s < f->state_count);
+
+ patbeg = (char *)p;
patlen = -1;
while (*p) {
q = p;
@@ -598,19 +628,6 @@ int nematch(fa *f, const char *p0) /* non-empty match, for sub */
}
nnextin:
s = 2;
- if (f->reset) {
- for (i = 2; i <= f->curstat; i++)
- xfree(f->posns[i]);
- k = *f->posns[0];
- if ((f->posns[2] = (int *) calloc(k+1, sizeof(int))) == NULL)
- overflo("out of state space");
- for (i = 0; i <= k; i++)
- (f->posns[2])[i] = (f->posns[0])[i];
- f->initstat = f->curstat = 2;
- f->out[2] = f->out[0];
- for (i = 0; i < NCHARS; i++)
- f->gototab[2][i] = 0;
- }
p++;
}
return (0);
@@ -909,7 +926,7 @@ replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom,
} else if (special_case == REPEAT_ZERO) {
size += 2; /* just a null ERE: () */
}
- if ((buf = (uschar *) malloc(size+1)) == NULL)
+ if ((buf = malloc(size + 1)) == NULL)
FATAL("out of space in reg expr %.10s..", lastre);
memcpy(buf, basestr, prefix_length); /* copy prefix */
j = prefix_length;
@@ -1035,7 +1052,7 @@ rescan:
rlxval = c;
return CHAR;
case '[':
- if (buf == NULL && (buf = (uschar *) malloc(bufsz)) == NULL)
+ if (buf == NULL && (buf = malloc(bufsz)) == NULL)
FATAL("out of space in reg expr %.10s..", lastre);
bp = buf;
if (*prestr == '^') {
@@ -1203,20 +1220,17 @@ rescan:
int cgoto(fa *f, int s, int c)
{
- int i, j, k;
int *p, *q;
+ int i, j, k;
assert(c == HAT || c < NCHARS);
while (f->accept >= maxsetvec) { /* guessing here! */
- maxsetvec *= 4;
- setvec = (int *) realloc(setvec, maxsetvec * sizeof(int));
- tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int));
- if (setvec == NULL || tmpset == NULL)
- overflo("out of space in cgoto()");
+ resizesetvec(__func__);
}
for (i = 0; i <= f->accept; i++)
setvec[i] = 0;
setcnt = 0;
+ resize_state(f, s);
/* compute positions of gototab[s,c] into setvec */
p = f->posns[s];
for (i = 1; i <= *p; i++) {
@@ -1230,11 +1244,7 @@ int cgoto(fa *f, int s, int c)
q = f->re[p[i]].lfollow;
for (j = 1; j <= *q; j++) {
if (q[j] >= maxsetvec) {
- maxsetvec *= 4;
- setvec = (int *) realloc(setvec, maxsetvec * sizeof(int));
- tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int));
- if (setvec == NULL || tmpset == NULL)
- overflo("cgoto overflow");
+ resizesetvec(__func__);
}
if (setvec[q[j]] == 0) {
setcnt++;
@@ -1251,6 +1261,7 @@ int cgoto(fa *f, int s, int c)
if (setvec[i]) {
tmpset[j++] = i;
}
+ resize_state(f, f->curstat > s ? f->curstat : s);
/* tmpset == previous state? */
for (i = 1; i <= f->curstat; i++) {
p = f->posns[i];
@@ -1266,18 +1277,12 @@ int cgoto(fa *f, int s, int c)
}
/* add tmpset to current set of states */
- if (f->curstat >= NSTATES-1) {
- f->curstat = 2;
- f->reset = 1;
- for (i = 2; i < NSTATES; i++)
- xfree(f->posns[i]);
- } else
- ++(f->curstat);
+ ++(f->curstat);
+ resize_state(f, f->curstat);
for (i = 0; i < NCHARS; i++)
f->gototab[f->curstat][i] = 0;
xfree(f->posns[f->curstat]);
- if ((p = (int *) calloc(setcnt+1, sizeof(int))) == NULL)
- overflo("out of space in cgoto");
+ p = intalloc(setcnt + 1, __func__);
f->posns[f->curstat] = p;
f->gototab[s][c] = f->curstat;
@@ -1297,6 +1302,8 @@ void freefa(fa *f) /* free a finite automaton */
if (f == NULL)
return;
+ for (i = 0; i < f->state_count; i++)
+ xfree(f->gototab[i])
for (i = 0; i <= f->curstat; i++)
xfree(f->posns[i]);
for (i = 0; i <= f->accept; i++) {
@@ -1305,5 +1312,8 @@ void freefa(fa *f) /* free a finite automaton */
xfree((f->re[i].lval.np));
}
xfree(f->restr);
+ xfree(f->out);
+ xfree(f->posns);
+ xfree(f->gototab);
xfree(f);
}