postgresql/contrib/pg_trgm/trgm_gist.c

635 lines
14 KiB
C
Raw Normal View History

#include "trgm.h"
#include "access/gist.h"
#include "access/itup.h"
2005-11-07 18:36:47 +01:00
#include "access/tuptoaster.h"
#include "storage/bufpage.h"
#include "utils/array.h"
#include "utils/builtins.h"
PG_FUNCTION_INFO_V1(gtrgm_in);
Datum gtrgm_in(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(gtrgm_out);
Datum gtrgm_out(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(gtrgm_compress);
Datum gtrgm_compress(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(gtrgm_decompress);
Datum gtrgm_decompress(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(gtrgm_consistent);
Datum gtrgm_consistent(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(gtrgm_union);
Datum gtrgm_union(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(gtrgm_same);
Datum gtrgm_same(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(gtrgm_penalty);
Datum gtrgm_penalty(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(gtrgm_picksplit);
Datum gtrgm_picksplit(PG_FUNCTION_ARGS);
#define GETENTRY(vec,pos) ((TRGM *) DatumGetPointer((vec)->vector[(pos)].key))
/* Number of one-bits in an unsigned byte */
static const uint8 number_of_ones[256] = {
0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8
};
Datum
gtrgm_in(PG_FUNCTION_ARGS)
{
elog(ERROR, "not implemented");
PG_RETURN_DATUM(0);
}
Datum
gtrgm_out(PG_FUNCTION_ARGS)
{
elog(ERROR, "not implemented");
PG_RETURN_DATUM(0);
}
static void
makesign(BITVECP sign, TRGM * a)
{
int4 k,
len = ARRNELEM(a);
trgm *ptr = GETARR(a);
2004-08-29 07:07:03 +02:00
int4 tmp = 0;
MemSet((void *) sign, 0, sizeof(BITVEC));
2004-08-29 07:07:03 +02:00
SETBIT(sign, SIGLENBIT); /* set last unused bit */
for (k = 0; k < len; k++)
{
CPTRGM(((char *) &tmp), ptr + k);
HASH(sign, tmp);
}
}
Datum
gtrgm_compress(PG_FUNCTION_ARGS)
{
GISTENTRY *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
GISTENTRY *retval = entry;
if (entry->leafkey)
{ /* trgm */
2004-08-29 07:07:03 +02:00
TRGM *res;
text *val = DatumGetTextP(entry->key);
res = generate_trgm(VARDATA(val), VARSIZE(val) - VARHDRSZ);
retval = (GISTENTRY *) palloc(sizeof(GISTENTRY));
gistentryinit(*retval, PointerGetDatum(res),
entry->rel, entry->page,
entry->offset, FALSE);
}
else if (ISSIGNKEY(DatumGetPointer(entry->key)) &&
!ISALLTRUE(DatumGetPointer(entry->key)))
{
int4 i,
len;
2004-08-29 07:07:03 +02:00
TRGM *res;
BITVECP sign = GETSIGN(DatumGetPointer(entry->key));
LOOPBYTE
{
if ((sign[i] & 0xff) != 0xff)
PG_RETURN_POINTER(retval);
}
len = CALCGTSIZE(SIGNKEY | ALLISTRUE, 0);
res = (TRGM *) palloc(len);
SET_VARSIZE(res, len);
res->flag = SIGNKEY | ALLISTRUE;
retval = (GISTENTRY *) palloc(sizeof(GISTENTRY));
gistentryinit(*retval, PointerGetDatum(res),
entry->rel, entry->page,
entry->offset, FALSE);
}
PG_RETURN_POINTER(retval);
}
Datum
gtrgm_decompress(PG_FUNCTION_ARGS)
{
GISTENTRY *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
GISTENTRY *retval;
text *key;
key = DatumGetTextP(entry->key);
if (key != (text *) DatumGetPointer(entry->key))
{
/* need to pass back the decompressed item */
retval = palloc(sizeof(GISTENTRY));
gistentryinit(*retval, PointerGetDatum(key),
entry->rel, entry->page, entry->offset, entry->leafkey);
PG_RETURN_POINTER(retval);
}
else
{
/* we can return the entry as-is */
PG_RETURN_POINTER(entry);
}
}
Datum
gtrgm_consistent(PG_FUNCTION_ARGS)
{
GISTENTRY *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
text *query = PG_GETARG_TEXT_P(1);
/* StrategyNumber strategy = (StrategyNumber) PG_GETARG_UINT16(2); */
/* Oid subtype = PG_GETARG_OID(3); */
bool *recheck = (bool *) PG_GETARG_POINTER(4);
TRGM *key = (TRGM *) DatumGetPointer(entry->key);
2004-08-29 07:07:03 +02:00
TRGM *qtrg = generate_trgm(VARDATA(query), VARSIZE(query) - VARHDRSZ);
bool res = false;
/* All cases served by this function are exact */
*recheck = false;
2004-08-29 07:07:03 +02:00
if (GIST_LEAF(entry))
2004-08-29 07:07:03 +02:00
{ /* all leafs contains orig trgm */
float4 tmpsml = cnt_sml(key, qtrg);
/* strange bug at freebsd 5.2.1 and gcc 3.3.3 */
res = (*(int *) &tmpsml == *(int *) &trgm_limit || tmpsml > trgm_limit) ? true : false;
}
else if (ISALLTRUE(key))
{ /* non-leaf contains signature */
res = true;
2004-08-29 07:07:03 +02:00
}
else
{ /* non-leaf contains signature */
int4 count = 0;
int4 k,
len = ARRNELEM(qtrg);
trgm *ptr = GETARR(qtrg);
2004-08-29 07:07:03 +02:00
BITVECP sign = GETSIGN(key);
int4 tmp = 0;
2004-08-29 07:07:03 +02:00
for (k = 0; k < len; k++)
{
CPTRGM(((char *) &tmp), ptr + k);
count += GETBIT(sign, HASHVAL(tmp));
}
#ifdef DIVUNION
2004-08-29 07:07:03 +02:00
res = (len == count) ? true : ((((((float4) count) / ((float4) (len - count)))) >= trgm_limit) ? true : false);
#else
2004-08-29 07:07:03 +02:00
res = (len == 0) ? false : ((((((float4) count) / ((float4) len))) >= trgm_limit) ? true : false);
#endif
}
PG_RETURN_BOOL(res);
}
static int4
unionkey(BITVECP sbase, TRGM * add)
{
int4 i;
if (ISSIGNKEY(add))
{
BITVECP sadd = GETSIGN(add);
if (ISALLTRUE(add))
return 1;
LOOPBYTE
sbase[i] |= sadd[i];
}
else
{
trgm *ptr = GETARR(add);
2004-08-29 07:07:03 +02:00
int4 tmp = 0;
2004-08-29 07:07:03 +02:00
for (i = 0; i < ARRNELEM(add); i++)
{
CPTRGM(((char *) &tmp), ptr + i);
HASH(sbase, tmp);
}
}
return 0;
}
Datum
gtrgm_union(PG_FUNCTION_ARGS)
{
2004-08-29 07:07:03 +02:00
GistEntryVector *entryvec = (GistEntryVector *) PG_GETARG_POINTER(0);
int4 len = entryvec->n;
int *size = (int *) PG_GETARG_POINTER(1);
BITVEC base;
int4 i;
int4 flag = 0;
2004-08-29 07:07:03 +02:00
TRGM *result;
MemSet((void *) base, 0, sizeof(BITVEC));
for (i = 0; i < len; i++)
{
if (unionkey(base, GETENTRY(entryvec, i)))
{
flag = ALLISTRUE;
break;
}
}
flag |= SIGNKEY;
len = CALCGTSIZE(flag, 0);
result = (TRGM *) palloc(len);
SET_VARSIZE(result, len);
result->flag = flag;
if (!ISALLTRUE(result))
memcpy((void *) GETSIGN(result), (void *) base, sizeof(BITVEC));
*size = len;
PG_RETURN_POINTER(result);
}
Datum
gtrgm_same(PG_FUNCTION_ARGS)
{
2004-08-29 07:07:03 +02:00
TRGM *a = (TRGM *) PG_GETARG_POINTER(0);
TRGM *b = (TRGM *) PG_GETARG_POINTER(1);
bool *result = (bool *) PG_GETARG_POINTER(2);
if (ISSIGNKEY(a))
{ /* then b also ISSIGNKEY */
if (ISALLTRUE(a) && ISALLTRUE(b))
*result = true;
else if (ISALLTRUE(a))
*result = false;
else if (ISALLTRUE(b))
*result = false;
else
{
int4 i;
BITVECP sa = GETSIGN(a),
sb = GETSIGN(b);
*result = true;
LOOPBYTE
{
if (sa[i] != sb[i])
{
*result = false;
break;
}
}
}
}
else
{ /* a and b ISARRKEY */
int4 lena = ARRNELEM(a),
lenb = ARRNELEM(b);
if (lena != lenb)
*result = false;
else
{
trgm *ptra = GETARR(a),
*ptrb = GETARR(b);
int4 i;
*result = true;
for (i = 0; i < lena; i++)
2004-08-29 07:07:03 +02:00
if (CMPTRGM(ptra + i, ptrb + i))
{
*result = false;
break;
}
}
}
PG_RETURN_POINTER(result);
}
static int4
sizebitvec(BITVECP sign)
{
int4 size = 0,
i;
LOOPBYTE
size += number_of_ones[(unsigned char) sign[i]];
return size;
}
static int
2004-08-29 07:07:03 +02:00
hemdistsign(BITVECP a, BITVECP b)
{
int i,
diff,
2004-08-29 07:07:03 +02:00
dist = 0;
LOOPBYTE
{
diff = (unsigned char) (a[i] ^ b[i]);
dist += number_of_ones[diff];
}
return dist;
}
static int
2004-08-29 07:07:03 +02:00
hemdist(TRGM * a, TRGM * b)
{
if (ISALLTRUE(a))
{
if (ISALLTRUE(b))
return 0;
else
2004-08-29 07:07:03 +02:00
return SIGLENBIT - sizebitvec(GETSIGN(b));
}
else if (ISALLTRUE(b))
return SIGLENBIT - sizebitvec(GETSIGN(a));
2004-08-29 07:07:03 +02:00
return hemdistsign(GETSIGN(a), GETSIGN(b));
}
Datum
gtrgm_penalty(PG_FUNCTION_ARGS)
{
GISTENTRY *origentry = (GISTENTRY *) PG_GETARG_POINTER(0); /* always ISSIGNKEY */
GISTENTRY *newentry = (GISTENTRY *) PG_GETARG_POINTER(1);
float *penalty = (float *) PG_GETARG_POINTER(2);
2004-08-29 07:07:03 +02:00
TRGM *origval = (TRGM *) DatumGetPointer(origentry->key);
TRGM *newval = (TRGM *) DatumGetPointer(newentry->key);
BITVECP orig = GETSIGN(origval);
*penalty = 0.0;
2004-08-29 07:07:03 +02:00
if (ISARRKEY(newval))
{
BITVEC sign;
makesign(sign, newval);
2004-08-29 07:07:03 +02:00
if (ISALLTRUE(origval))
*penalty = ((float) (SIGLENBIT - sizebitvec(sign))) / (float) (SIGLENBIT + 1);
else
*penalty = hemdistsign(sign, orig);
}
2004-08-29 07:07:03 +02:00
else
*penalty = hemdist(origval, newval);
PG_RETURN_POINTER(penalty);
}
typedef struct
{
bool allistrue;
BITVEC sign;
} CACHESIGN;
static void
fillcache(CACHESIGN *item, TRGM * key)
{
item->allistrue = false;
if (ISARRKEY(key))
makesign(item->sign, key);
else if (ISALLTRUE(key))
item->allistrue = true;
else
memcpy((void *) item->sign, (void *) GETSIGN(key), sizeof(BITVEC));
}
#define WISH_F(a,b,c) (double)( -(double)(((a)-(b))*((a)-(b))*((a)-(b)))*(c) )
typedef struct
{
OffsetNumber pos;
int4 cost;
} SPLITCOST;
static int
comparecost(const void *a, const void *b)
{
if (((SPLITCOST *) a)->cost == ((SPLITCOST *) b)->cost)
return 0;
else
return (((SPLITCOST *) a)->cost > ((SPLITCOST *) b)->cost) ? 1 : -1;
}
static int
hemdistcache(CACHESIGN *a, CACHESIGN *b)
2004-08-29 07:07:03 +02:00
{
if (a->allistrue)
{
if (b->allistrue)
return 0;
else
2004-08-29 07:07:03 +02:00
return SIGLENBIT - sizebitvec(b->sign);
}
else if (b->allistrue)
return SIGLENBIT - sizebitvec(a->sign);
2004-08-29 07:07:03 +02:00
return hemdistsign(a->sign, b->sign);
}
Datum
gtrgm_picksplit(PG_FUNCTION_ARGS)
{
2004-08-29 07:07:03 +02:00
GistEntryVector *entryvec = (GistEntryVector *) PG_GETARG_POINTER(0);
OffsetNumber maxoff = entryvec->n - 2;
GIST_SPLITVEC *v = (GIST_SPLITVEC *) PG_GETARG_POINTER(1);
OffsetNumber k,
j;
2004-08-29 07:07:03 +02:00
TRGM *datum_l,
*datum_r;
BITVECP union_l,
union_r;
int4 size_alpha,
size_beta;
int4 size_waste,
waste = -1;
int4 nbytes;
OffsetNumber seed_1 = 0,
seed_2 = 0;
OffsetNumber *left,
*right;
BITVECP ptr;
int i;
CACHESIGN *cache;
SPLITCOST *costvector;
nbytes = (maxoff + 2) * sizeof(OffsetNumber);
v->spl_left = (OffsetNumber *) palloc(nbytes);
v->spl_right = (OffsetNumber *) palloc(nbytes);
cache = (CACHESIGN *) palloc(sizeof(CACHESIGN) * (maxoff + 2));
fillcache(&cache[FirstOffsetNumber], GETENTRY(entryvec, FirstOffsetNumber));
2004-08-29 07:07:03 +02:00
for (k = FirstOffsetNumber; k < maxoff; k = OffsetNumberNext(k))
{
for (j = OffsetNumberNext(k); j <= maxoff; j = OffsetNumberNext(j))
{
if (k == FirstOffsetNumber)
fillcache(&cache[j], GETENTRY(entryvec, j));
2004-08-29 07:07:03 +02:00
size_waste = hemdistcache(&(cache[j]), &(cache[k]));
if (size_waste > waste)
{
waste = size_waste;
seed_1 = k;
seed_2 = j;
}
}
}
left = v->spl_left;
v->spl_nleft = 0;
right = v->spl_right;
v->spl_nright = 0;
2004-08-29 07:07:03 +02:00
if (seed_1 == 0 || seed_2 == 0)
{
seed_1 = 1;
seed_2 = 2;
}
/* form initial .. */
2004-08-29 07:07:03 +02:00
if (cache[seed_1].allistrue)
{
datum_l = (TRGM *) palloc(CALCGTSIZE(SIGNKEY | ALLISTRUE, 0));
SET_VARSIZE(datum_l, CALCGTSIZE(SIGNKEY | ALLISTRUE, 0));
datum_l->flag = SIGNKEY | ALLISTRUE;
2004-08-29 07:07:03 +02:00
}
else
{
datum_l = (TRGM *) palloc(CALCGTSIZE(SIGNKEY, 0));
SET_VARSIZE(datum_l, CALCGTSIZE(SIGNKEY, 0));
datum_l->flag = SIGNKEY;
memcpy((void *) GETSIGN(datum_l), (void *) cache[seed_1].sign, sizeof(BITVEC));
}
2004-08-29 07:07:03 +02:00
if (cache[seed_2].allistrue)
{
datum_r = (TRGM *) palloc(CALCGTSIZE(SIGNKEY | ALLISTRUE, 0));
SET_VARSIZE(datum_r, CALCGTSIZE(SIGNKEY | ALLISTRUE, 0));
datum_r->flag = SIGNKEY | ALLISTRUE;
2004-08-29 07:07:03 +02:00
}
else
{
datum_r = (TRGM *) palloc(CALCGTSIZE(SIGNKEY, 0));
SET_VARSIZE(datum_r, CALCGTSIZE(SIGNKEY, 0));
datum_r->flag = SIGNKEY;
memcpy((void *) GETSIGN(datum_r), (void *) cache[seed_2].sign, sizeof(BITVEC));
}
2004-08-29 07:07:03 +02:00
union_l = GETSIGN(datum_l);
union_r = GETSIGN(datum_r);
maxoff = OffsetNumberNext(maxoff);
fillcache(&cache[maxoff], GETENTRY(entryvec, maxoff));
/* sort before ... */
costvector = (SPLITCOST *) palloc(sizeof(SPLITCOST) * maxoff);
2004-08-29 07:07:03 +02:00
for (j = FirstOffsetNumber; j <= maxoff; j = OffsetNumberNext(j))
{
costvector[j - 1].pos = j;
size_alpha = hemdistcache(&(cache[seed_1]), &(cache[j]));
2004-08-29 07:07:03 +02:00
size_beta = hemdistcache(&(cache[seed_2]), &(cache[j]));
costvector[j - 1].cost = abs(size_alpha - size_beta);
}
qsort((void *) costvector, maxoff, sizeof(SPLITCOST), comparecost);
2004-08-29 07:07:03 +02:00
for (k = 0; k < maxoff; k++)
{
j = costvector[k].pos;
2004-08-29 07:07:03 +02:00
if (j == seed_1)
{
*left++ = j;
v->spl_nleft++;
continue;
2004-08-29 07:07:03 +02:00
}
else if (j == seed_2)
{
*right++ = j;
v->spl_nright++;
continue;
}
2004-08-29 07:07:03 +02:00
if (ISALLTRUE(datum_l) || cache[j].allistrue)
{
if (ISALLTRUE(datum_l) && cache[j].allistrue)
size_alpha = 0;
else
2004-08-29 07:07:03 +02:00
size_alpha = SIGLENBIT - sizebitvec(
(cache[j].allistrue) ? GETSIGN(datum_l) : GETSIGN(cache[j].sign)
);
}
2004-08-29 07:07:03 +02:00
else
size_alpha = hemdistsign(cache[j].sign, GETSIGN(datum_l));
2004-08-29 07:07:03 +02:00
if (ISALLTRUE(datum_r) || cache[j].allistrue)
{
if (ISALLTRUE(datum_r) && cache[j].allistrue)
size_beta = 0;
else
2004-08-29 07:07:03 +02:00
size_beta = SIGLENBIT - sizebitvec(
(cache[j].allistrue) ? GETSIGN(datum_r) : GETSIGN(cache[j].sign)
);
}
2004-08-29 07:07:03 +02:00
else
size_beta = hemdistsign(cache[j].sign, GETSIGN(datum_r));
2004-08-29 07:07:03 +02:00
if (size_alpha < size_beta + WISH_F(v->spl_nleft, v->spl_nright, 0.1))
{
if (ISALLTRUE(datum_l) || cache[j].allistrue)
{
if (!ISALLTRUE(datum_l))
MemSet((void *) GETSIGN(datum_l), 0xff, sizeof(BITVEC));
2004-08-29 07:07:03 +02:00
}
else
{
ptr = cache[j].sign;
LOOPBYTE
union_l[i] |= ptr[i];
}
*left++ = j;
v->spl_nleft++;
2004-08-29 07:07:03 +02:00
}
else
{
if (ISALLTRUE(datum_r) || cache[j].allistrue)
{
if (!ISALLTRUE(datum_r))
MemSet((void *) GETSIGN(datum_r), 0xff, sizeof(BITVEC));
2004-08-29 07:07:03 +02:00
}
else
{
ptr = cache[j].sign;
LOOPBYTE
union_r[i] |= ptr[i];
}
*right++ = j;
v->spl_nright++;
}
}
*right = *left = FirstOffsetNumber;
v->spl_ldatum = PointerGetDatum(datum_l);
v->spl_rdatum = PointerGetDatum(datum_r);
PG_RETURN_POINTER(v);
}