static float
calc_rank(float *w, tsvector * t, QUERYTYPE * q, int4 method)
{
ITEM *item = GETQUERY(q);
float res = 0.0;
int len;
if (!t->size || !q->size)
return 0.0;
res = (item->type != VAL && item->val == (int4) '&') ?
calc_rank_and(w, t, q) : calc_rank_or(w, t, q);
if (res < 0)
res = 1e-20;
if ((method & RANK_NORM_LOGLENGTH) && t->size > 0)
res /= log((double) (cnt_length(t) + 1)) / log(2.0);
if (method & RANK_NORM_LENGTH)
{
len = cnt_length(t);
if (len > 0)
res /= (float) len;
}
if ((method & RANK_NORM_UNIQ) && t->size > 0)
res /= (float) (t->size);
if ((method & RANK_NORM_LOGUNIQ) && t->size > 0)
res /= log((double) (t->size + 1)) / log(2.0);
return res;
}
static float
calc_rank(float *w, TSVector t, TSQuery q, int32 method)
{
QueryItem *item = GETQUERY(q);
float res = 0.0;
int len;
if (!t->size || !q->size)
return 0.0;
/* XXX: What about NOT? */
res = (item->type == QI_OPR && item->qoperator.oper == OP_AND) ?
calc_rank_and(w, t, q) : calc_rank_or(w, t, q);
if (res < 0)
res = 1e-20f;
if ((method & RANK_NORM_LOGLENGTH) && t->size > 0)
res /= log((double) (cnt_length(t) + 1)) / log(2.0);
if (method & RANK_NORM_LENGTH)
{
len = cnt_length(t);
if (len > 0)
res /= (float) len;
}
/* RANK_NORM_EXTDIST not applicable */
if ((method & RANK_NORM_UNIQ) && t->size > 0)
res /= (float) (t->size);
if ((method & RANK_NORM_LOGUNIQ) && t->size > 0)
res /= log((double) (t->size + 1)) / log(2.0);
if (method & RANK_NORM_RDIVRPLUS1)
res /= (res + 1);
return res;
}
static float4
calc_rank_cd(float4 *arrdata, tsvector * txt, QUERYTYPE * query, int method)
{
DocRepresentation *doc;
int len,
i,
doclen = 0;
Extention ext;
double Wdoc = 0.0;
double invws[lengthof(weights)];
double SumDist = 0.0,
PrevExtPos = 0.0,
CurExtPos = 0.0;
int NExtent = 0;
for (i = 0; i < lengthof(weights); i++)
{
invws[i] = ((double) ((arrdata[i] >= 0) ? arrdata[i] : weights[i]));
if (invws[i] > 1.0)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("weight out of range")));
invws[i] = 1.0 / invws[i];
}
doc = get_docrep(txt, query, &doclen);
if (!doc)
return 0.0;
MemSet(&ext, 0, sizeof(Extention));
while (Cover(doc, doclen, query, &ext))
{
double Cpos = 0.0;
double InvSum = 0.0;
int nNoise;
DocRepresentation *ptr = ext.begin;
while (ptr <= ext.end)
{
InvSum += invws[ptr->wclass];
ptr++;
}
Cpos = ((double) (ext.end - ext.begin + 1)) / InvSum;
/*
* if doc are big enough then ext.q may be equal to ext.p
* due to limit of posional information. In this case we
* approximate number of noise word as half cover's
* length
*/
nNoise = (ext.q - ext.p) - (ext.end - ext.begin);
if ( nNoise < 0 )
nNoise = (ext.end - ext.begin) / 2;
Wdoc += Cpos / ((double) (1 + nNoise));
CurExtPos = ((double) (ext.q + ext.p)) / 2.0;
if (NExtent > 0 && CurExtPos > PrevExtPos /* prevent devision by
* zero in a case of
multiple lexize */ )
SumDist += 1.0 / (CurExtPos - PrevExtPos);
PrevExtPos = CurExtPos;
NExtent++;
}
if ((method & RANK_NORM_LOGLENGTH) && txt->size > 0)
Wdoc /= log((double) (cnt_length(txt) + 1));
if (method & RANK_NORM_LENGTH)
{
len = cnt_length(txt);
if (len > 0)
Wdoc /= (double) len;
}
if ((method & RANK_NORM_EXTDIST) && SumDist > 0)
Wdoc /= ((double) NExtent) / SumDist;
if ((method & RANK_NORM_UNIQ) && txt->size > 0)
Wdoc /= (double) (txt->size);
if ((method & RANK_NORM_LOGUNIQ) && txt->size > 0)
Wdoc /= log((double) (txt->size + 1)) / log(2.0);
for (i = 0; i < doclen; i++)
if (doc[i].needfree)
pfree(doc[i].item);
pfree(doc);
return (float4) Wdoc;
}
