Datum
gin_extract_tsvector(PG_FUNCTION_ARGS)
{
TSVector vector = PG_GETARG_TSVECTOR(0);
int32 *nentries = (int32 *) PG_GETARG_POINTER(1);
Datum *entries = NULL;
*nentries = vector->size;
if (vector->size > 0)
{
int i;
WordEntry *we = ARRPTR(vector);
entries = (Datum *) palloc(sizeof(Datum) * vector->size);
for (i = 0; i < vector->size; i++)
{
text *txt;
txt = cstring_to_text_with_len(STRPTR(vector) + we->pos, we->len);
entries[i] = PointerGetDatum(txt);
we++;
}
}
PG_FREE_IF_COPY(vector, 0);
PG_RETURN_POINTER(entries);
}
Datum
ts_match_vq(PG_FUNCTION_ARGS)
{
TSVector val = PG_GETARG_TSVECTOR(0);
TSQuery query = PG_GETARG_TSQUERY(1);
CHKVAL chkval;
bool result;
if (!val->size || !query->size)
{
PG_FREE_IF_COPY(val, 0);
PG_FREE_IF_COPY(query, 1);
PG_RETURN_BOOL(false);
}
chkval.arrb = ARRPTR(val);
chkval.arre = chkval.arrb + val->size;
chkval.values = STRPTR(val);
chkval.operand = GETOPERAND(query);
result = TS_execute(
GETQUERY(query),
&chkval,
true,
checkcondition_str
);
PG_FREE_IF_COPY(val, 0);
PG_FREE_IF_COPY(query, 1);
PG_RETURN_BOOL(result);
}
Datum
tsvector_strip(PG_FUNCTION_ARGS)
{
TSVector in = PG_GETARG_TSVECTOR(0);
TSVector out;
int i,
len = 0;
WordEntry *arrin = ARRPTR(in),
*arrout;
char *cur;
for (i = 0; i < in->size; i++)
len += arrin[i].len;
len = CALCDATASIZE(in->size, len);
out = (TSVector) palloc0(len);
SET_VARSIZE(out, len);
out->size = in->size;
arrout = ARRPTR(out);
cur = STRPTR(out);
for (i = 0; i < in->size; i++)
{
memcpy(cur, STRPTR(in) + arrin[i].pos, arrin[i].len);
arrout[i].haspos = 0;
arrout[i].len = arrin[i].len;
arrout[i].pos = cur - STRPTR(out);
cur += arrout[i].len;
}
PG_FREE_IF_COPY(in, 0);
PG_RETURN_POINTER(out);
}
Datum
tsvector2textarray(PG_FUNCTION_ARGS)
{
TSVector ts = PG_GETARG_TSVECTOR(0);
ArrayType *a;
Datum *words;
int i;
WordEntry *wptr = ARRPTR(ts);
words = palloc( sizeof(Datum) * (ts->size+1) );
for(i=0; i<ts->size; i++)
{
text *t = palloc(VARHDRSZ + wptr->len);
SET_VARSIZE(t, VARHDRSZ + wptr->len);
memcpy( VARDATA(t), STRPTR(ts) + wptr->pos, wptr->len);
words[i] = PointerGetDatum(t);
wptr++;
}
a = construct_array( words, ts->size,
TEXTOID, -1, false, 'i' );
PG_FREE_IF_COPY(ts, 0);
PG_RETURN_ARRAYTYPE_P(a);
}
Datum
gin_extract_tsvector(PG_FUNCTION_ARGS)
{
TSVector vector = PG_GETARG_TSVECTOR(0);
int32 *nentries = (int32 *) PG_GETARG_POINTER(1);
Datum *entries = NULL;
*nentries = vector->size;
if (vector->size > 0)
{
int i;
WordEntry *we = ARRPTR(vector);
entries = (Datum *) palloc(sizeof(Datum) * vector->size);
for (i = 0; i < vector->size; i++)
{
text *txt = (text *) palloc(VARHDRSZ + we->len);
SET_VARSIZE(txt, VARHDRSZ + we->len);
memcpy(VARDATA(txt), STRPTR(vector) + we->pos, we->len);
entries[i] = PointerGetDatum(txt);
we++;
}
}
PG_FREE_IF_COPY(vector, 0);
PG_RETURN_POINTER(entries);
}
Datum
tsvector_length(PG_FUNCTION_ARGS)
{
TSVector in = PG_GETARG_TSVECTOR(0);
int32 ret = in->size;
PG_FREE_IF_COPY(in, 0);
PG_RETURN_INT32(ret);
}
Datum
tsvector_setweight(PG_FUNCTION_ARGS)
{
TSVector in = PG_GETARG_TSVECTOR(0);
char cw = PG_GETARG_CHAR(1);
TSVector out;
int i,
j;
WordEntry *entry;
WordEntryPos *p;
int w = 0;
switch (cw)
{
case 'A':
case 'a':
w = 3;
break;
case 'B':
case 'b':
w = 2;
break;
case 'C':
case 'c':
w = 1;
break;
case 'D':
case 'd':
w = 0;
break;
default:
/* internal error */
elog(ERROR, "unrecognized weight: %d", cw);
}
out = (TSVector) palloc(VARSIZE(in));
memcpy(out, in, VARSIZE(in));
entry = ARRPTR(out);
i = out->size;
while (i--)
{
if ((j = POSDATALEN(out, entry)) != 0)
{
p = POSDATAPTR(out, entry);
while (j--)
{
WEP_SETWEIGHT(*p, w);
p++;
}
}
entry++;
}
PG_FREE_IF_COPY(in, 0);
PG_RETURN_POINTER(out);
}
Datum
ts_rankcd_tt(PG_FUNCTION_ARGS)
{
TSVector txt = PG_GETARG_TSVECTOR(0);
TSQuery query = PG_GETARG_TSQUERY(1);
float res;
res = calc_rank_cd(getWeights(NULL), txt, query, DEF_NORM_METHOD);
PG_FREE_IF_COPY(txt, 0);
PG_FREE_IF_COPY(query, 1);
PG_RETURN_FLOAT4(res);
}
Datum
ts_rankcd_ttf(PG_FUNCTION_ARGS)
{
TSVector txt = PG_GETARG_TSVECTOR(0);
TSQuery query = PG_GETARG_TSQUERY(1);
int method = PG_GETARG_INT32(2);
float res;
res = calc_rank_cd(getWeights(NULL), txt, query, method);
PG_FREE_IF_COPY(txt, 0);
PG_FREE_IF_COPY(query, 1);
PG_RETURN_FLOAT4(res);
}
Datum
ts_rankcd_wtt(PG_FUNCTION_ARGS)
{
ArrayType *win = (ArrayType *) PG_DETOAST_DATUM(PG_GETARG_DATUM(0));
TSVector txt = PG_GETARG_TSVECTOR(1);
TSQuery query = PG_GETARG_TSQUERY(2);
float res;
res = calc_rank_cd(getWeights(win), txt, query, DEF_NORM_METHOD);
PG_FREE_IF_COPY(win, 0);
PG_FREE_IF_COPY(txt, 1);
PG_FREE_IF_COPY(query, 2);
PG_RETURN_FLOAT4(res);
}
Datum
ts_rank_wttf(PG_FUNCTION_ARGS)
{
ArrayType *win = (ArrayType *) PG_DETOAST_DATUM(PG_GETARG_DATUM(0));
TSVector txt = PG_GETARG_TSVECTOR(1);
TSQuery query = PG_GETARG_TSQUERY(2);
int method = PG_GETARG_INT32(3);
float res;
res = calc_rank(getWeights(win), txt, query, method);
PG_FREE_IF_COPY(win, 0);
PG_FREE_IF_COPY(txt, 1);
PG_FREE_IF_COPY(query, 2);
PG_RETURN_FLOAT4(res);
}
Datum
tsvectorsend(PG_FUNCTION_ARGS)
{
TSVector vec = PG_GETARG_TSVECTOR(0);
StringInfoData buf;
int i,
j;
WordEntry *weptr = ARRPTR(vec);
pq_begintypsend(&buf);
pq_sendint(&buf, vec->size, sizeof(int32));
for (i = 0; i < vec->size; i++)
{
uint16 npos;
/*
* the strings in the TSVector array are not null-terminated, so we
* have to send the null-terminator separately
*/
pq_sendtext(&buf, STRPTR(vec) + weptr->pos, weptr->len);
pq_sendbyte(&buf, '\0');
npos = POSDATALEN(vec, weptr);
pq_sendint(&buf, npos, sizeof(uint16));
if (npos > 0)
{
WordEntryPos *wepptr = POSDATAPTR(vec, weptr);
for (j = 0; j < npos; j++)
pq_sendint(&buf, wepptr[j], sizeof(WordEntryPos));
}
weptr++;
}
PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
}
Datum
tsvector_concat(PG_FUNCTION_ARGS)
{
TSVector in1 = PG_GETARG_TSVECTOR(0);
TSVector in2 = PG_GETARG_TSVECTOR(1);
TSVector out;
WordEntry *ptr;
WordEntry *ptr1,
*ptr2;
WordEntryPos *p;
int maxpos = 0,
i,
j,
i1,
i2,
dataoff,
output_bytes,
output_size;
char *data,
*data1,
*data2;
/* Get max position in in1; we'll need this to offset in2's positions */
ptr = ARRPTR(in1);
i = in1->size;
while (i--)
{
if ((j = POSDATALEN(in1, ptr)) != 0)
{
p = POSDATAPTR(in1, ptr);
while (j--)
{
if (WEP_GETPOS(*p) > maxpos)
maxpos = WEP_GETPOS(*p);
p++;
}
}
ptr++;
}
ptr1 = ARRPTR(in1);
ptr2 = ARRPTR(in2);
data1 = STRPTR(in1);
data2 = STRPTR(in2);
i1 = in1->size;
i2 = in2->size;
/*
* Conservative estimate of space needed. We might need all the data in
* both inputs, and conceivably add a pad byte before position data for
* each item where there was none before.
*/
output_bytes = VARSIZE(in1) + VARSIZE(in2) + i1 + i2;
out = (TSVector) palloc0(output_bytes);
SET_VARSIZE(out, output_bytes);
/*
* We must make out->size valid so that STRPTR(out) is sensible. We'll
* collapse out any unused space at the end.
*/
out->size = in1->size + in2->size;
ptr = ARRPTR(out);
data = STRPTR(out);
dataoff = 0;
while (i1 && i2)
{
int cmp = compareEntry(data1, ptr1, data2, ptr2);
if (cmp < 0)
{ /* in1 first */
ptr->haspos = ptr1->haspos;
ptr->len = ptr1->len;
memcpy(data + dataoff, data1 + ptr1->pos, ptr1->len);
ptr->pos = dataoff;
dataoff += ptr1->len;
if (ptr->haspos)
{
dataoff = SHORTALIGN(dataoff);
memcpy(data + dataoff, _POSVECPTR(in1, ptr1), POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16));
dataoff += POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16);
}
ptr++;
ptr1++;
i1--;
}
else if (cmp > 0)
{ /* in2 first */
ptr->haspos = ptr2->haspos;
ptr->len = ptr2->len;
memcpy(data + dataoff, data2 + ptr2->pos, ptr2->len);
ptr->pos = dataoff;
dataoff += ptr2->len;
if (ptr->haspos)
{
int addlen = add_pos(in2, ptr2, out, ptr, maxpos);
if (addlen == 0)
ptr->haspos = 0;
else
{
dataoff = SHORTALIGN(dataoff);
dataoff += addlen * sizeof(WordEntryPos) + sizeof(uint16);
}
}
ptr++;
ptr2++;
i2--;
}
else
{
ptr->haspos = ptr1->haspos | ptr2->haspos;
ptr->len = ptr1->len;
memcpy(data + dataoff, data1 + ptr1->pos, ptr1->len);
ptr->pos = dataoff;
dataoff += ptr1->len;
if (ptr->haspos)
{
if (ptr1->haspos)
{
dataoff = SHORTALIGN(dataoff);
memcpy(data + dataoff, _POSVECPTR(in1, ptr1), POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16));
dataoff += POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16);
if (ptr2->haspos)
dataoff += add_pos(in2, ptr2, out, ptr, maxpos) * sizeof(WordEntryPos);
}
else /* must have ptr2->haspos */
{
int addlen = add_pos(in2, ptr2, out, ptr, maxpos);
if (addlen == 0)
ptr->haspos = 0;
else
{
dataoff = SHORTALIGN(dataoff);
dataoff += addlen * sizeof(WordEntryPos) + sizeof(uint16);
}
}
}
ptr++;
ptr1++;
ptr2++;
i1--;
i2--;
}
}
while (i1)
{
ptr->haspos = ptr1->haspos;
ptr->len = ptr1->len;
memcpy(data + dataoff, data1 + ptr1->pos, ptr1->len);
ptr->pos = dataoff;
dataoff += ptr1->len;
if (ptr->haspos)
{
dataoff = SHORTALIGN(dataoff);
memcpy(data + dataoff, _POSVECPTR(in1, ptr1), POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16));
dataoff += POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16);
}
ptr++;
ptr1++;
i1--;
}
while (i2)
{
ptr->haspos = ptr2->haspos;
ptr->len = ptr2->len;
memcpy(data + dataoff, data2 + ptr2->pos, ptr2->len);
ptr->pos = dataoff;
dataoff += ptr2->len;
if (ptr->haspos)
{
int addlen = add_pos(in2, ptr2, out, ptr, maxpos);
if (addlen == 0)
ptr->haspos = 0;
else
{
dataoff = SHORTALIGN(dataoff);
dataoff += addlen * sizeof(WordEntryPos) + sizeof(uint16);
}
}
ptr++;
ptr2++;
i2--;
}
/*
* Instead of checking each offset individually, we check for overflow of
* pos fields once at the end.
*/
if (dataoff > MAXSTRPOS)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("string is too long for tsvector (%d bytes, max %d bytes)", dataoff, MAXSTRPOS)));
/*
* Adjust sizes (asserting that we didn't overrun the original estimates)
* and collapse out any unused array entries.
*/
output_size = ptr - ARRPTR(out);
Assert(output_size <= out->size);
out->size = output_size;
if (data != STRPTR(out))
memmove(STRPTR(out), data, dataoff);
output_bytes = CALCDATASIZE(out->size, dataoff);
Assert(output_bytes <= VARSIZE(out));
SET_VARSIZE(out, output_bytes);
PG_FREE_IF_COPY(in1, 0);
PG_FREE_IF_COPY(in2, 1);
PG_RETURN_POINTER(out);
}
Datum
tsvector_concat(PG_FUNCTION_ARGS)
{
TSVector in1 = PG_GETARG_TSVECTOR(0);
TSVector in2 = PG_GETARG_TSVECTOR(1);
TSVector out;
WordEntry *ptr;
WordEntry *ptr1,
*ptr2;
WordEntryPos *p;
int maxpos = 0,
i,
j,
i1,
i2,
dataoff;
char *data,
*data1,
*data2;
ptr = ARRPTR(in1);
i = in1->size;
while (i--)
{
if ((j = POSDATALEN(in1, ptr)) != 0)
{
p = POSDATAPTR(in1, ptr);
while (j--)
{
if (WEP_GETPOS(*p) > maxpos)
maxpos = WEP_GETPOS(*p);
p++;
}
}
ptr++;
}
ptr1 = ARRPTR(in1);
ptr2 = ARRPTR(in2);
data1 = STRPTR(in1);
data2 = STRPTR(in2);
i1 = in1->size;
i2 = in2->size;
/* conservative estimate of space needed */
out = (TSVector) palloc0(VARSIZE(in1) + VARSIZE(in2));
SET_VARSIZE(out, VARSIZE(in1) + VARSIZE(in2));
out->size = in1->size + in2->size;
ptr = ARRPTR(out);
data = STRPTR(out);
dataoff = 0;
while (i1 && i2)
{
int cmp = compareEntry(data1, ptr1, data2, ptr2);
if (cmp < 0)
{ /* in1 first */
ptr->haspos = ptr1->haspos;
ptr->len = ptr1->len;
memcpy(data + dataoff, data1 + ptr1->pos, ptr1->len);
ptr->pos = dataoff;
dataoff += ptr1->len;
if (ptr->haspos)
{
dataoff = SHORTALIGN(dataoff);
memcpy(data + dataoff, _POSVECPTR(in1, ptr1), POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16));
dataoff += POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16);
}
ptr++;
ptr1++;
i1--;
}
else if (cmp > 0)
{ /* in2 first */
ptr->haspos = ptr2->haspos;
ptr->len = ptr2->len;
memcpy(data + dataoff, data2 + ptr2->pos, ptr2->len);
ptr->pos = dataoff;
dataoff += ptr2->len;
if (ptr->haspos)
{
int addlen = add_pos(in2, ptr2, out, ptr, maxpos);
if (addlen == 0)
ptr->haspos = 0;
else
{
dataoff = SHORTALIGN(dataoff);
dataoff += addlen * sizeof(WordEntryPos) + sizeof(uint16);
}
}
ptr++;
ptr2++;
i2--;
}
else
{
ptr->haspos = ptr1->haspos | ptr2->haspos;
ptr->len = ptr1->len;
memcpy(data + dataoff, data1 + ptr1->pos, ptr1->len);
ptr->pos = dataoff;
dataoff += ptr1->len;
if (ptr->haspos)
{
if (ptr1->haspos)
{
dataoff = SHORTALIGN(dataoff);
memcpy(data + dataoff, _POSVECPTR(in1, ptr1), POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16));
dataoff += POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16);
if (ptr2->haspos)
dataoff += add_pos(in2, ptr2, out, ptr, maxpos) * sizeof(WordEntryPos);
}
else /* must have ptr2->haspos */
{
int addlen = add_pos(in2, ptr2, out, ptr, maxpos);
if (addlen == 0)
ptr->haspos = 0;
else
{
dataoff = SHORTALIGN(dataoff);
dataoff += addlen * sizeof(WordEntryPos) + sizeof(uint16);
}
}
}
ptr++;
ptr1++;
ptr2++;
i1--;
i2--;
}
}
while (i1)
{
ptr->haspos = ptr1->haspos;
ptr->len = ptr1->len;
memcpy(data + dataoff, data1 + ptr1->pos, ptr1->len);
ptr->pos = dataoff;
dataoff += ptr1->len;
if (ptr->haspos)
{
dataoff = SHORTALIGN(dataoff);
memcpy(data + dataoff, _POSVECPTR(in1, ptr1), POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16));
dataoff += POSDATALEN(in1, ptr1) * sizeof(WordEntryPos) + sizeof(uint16);
}
ptr++;
ptr1++;
i1--;
}
while (i2)
{
ptr->haspos = ptr2->haspos;
ptr->len = ptr2->len;
memcpy(data + dataoff, data2 + ptr2->pos, ptr2->len);
ptr->pos = dataoff;
dataoff += ptr2->len;
if (ptr->haspos)
{
int addlen = add_pos(in2, ptr2, out, ptr, maxpos);
if (addlen == 0)
ptr->haspos = 0;
else
{
dataoff = SHORTALIGN(dataoff);
dataoff += addlen * sizeof(WordEntryPos) + sizeof(uint16);
}
}
ptr++;
ptr2++;
i2--;
}
/*
* Instead of checking each offset individually, we check for overflow of
* pos fields once at the end.
*/
if (dataoff > MAXSTRPOS)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("string is too long for tsvector (%d bytes, max %d bytes)", dataoff, MAXSTRPOS)));
out->size = ptr - ARRPTR(out);
SET_VARSIZE(out, CALCDATASIZE(out->size, dataoff));
if (data != STRPTR(out))
memmove(STRPTR(out), data, dataoff);
PG_FREE_IF_COPY(in1, 0);
PG_FREE_IF_COPY(in2, 1);
PG_RETURN_POINTER(out);
}
Datum
tsvectorout(PG_FUNCTION_ARGS)
{
TSVector out = PG_GETARG_TSVECTOR(0);
char *outbuf;
int32 i,
lenbuf = 0,
pp;
WordEntry *ptr = ARRPTR(out);
char *curbegin,
*curin,
*curout;
lenbuf = out->size * 2 /* '' */ + out->size - 1 /* space */ + 2 /* \0 */ ;
for (i = 0; i < out->size; i++)
{
lenbuf += ptr[i].len * 2 * pg_database_encoding_max_length() /* for escape */ ;
if (ptr[i].haspos)
lenbuf += 1 /* : */ + 7 /* int2 + , + weight */ * POSDATALEN(out, &(ptr[i]));
}
curout = outbuf = (char *) palloc(lenbuf);
for (i = 0; i < out->size; i++)
{
curbegin = curin = STRPTR(out) + ptr->pos;
if (i != 0)
*curout++ = ' ';
*curout++ = '\'';
while (curin - curbegin < ptr->len)
{
int len = pg_mblen(curin);
if (t_iseq(curin, '\''))
*curout++ = '\'';
else if (t_iseq(curin, '\\'))
*curout++ = '\\';
while (len--)
*curout++ = *curin++;
}
*curout++ = '\'';
if ((pp = POSDATALEN(out, ptr)) != 0)
{
WordEntryPos *wptr;
*curout++ = ':';
wptr = POSDATAPTR(out, ptr);
while (pp)
{
curout += sprintf(curout, "%d", WEP_GETPOS(*wptr));
switch (WEP_GETWEIGHT(*wptr))
{
case 3:
*curout++ = 'A';
break;
case 2:
*curout++ = 'B';
break;
case 1:
*curout++ = 'C';
break;
case 0:
default:
break;
}
if (pp > 1)
*curout++ = ',';
pp--;
wptr++;
}
}
ptr++;
}
*curout = '\0';
PG_FREE_IF_COPY(out, 0);
PG_RETURN_CSTRING(outbuf);
}
