tsrank.c

来自「postgresql8.3.4源码,开源数据库」· C语言 代码 · 共 857 行 · 第 1/2 页

	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_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(getWeights(NULL), txt, query, method);

	PG_FREE_IF_COPY(txt, 0);
	PG_FREE_IF_COPY(query, 1);
	PG_RETURN_FLOAT4(res);
}

Datum
ts_rank_tt(PG_FUNCTION_ARGS)
{
	TSVector	txt = PG_GETARG_TSVECTOR(0);
	TSQuery		query = PG_GETARG_TSQUERY(1);
	float		res;

	res = calc_rank(getWeights(NULL), txt, query, DEF_NORM_METHOD);

	PG_FREE_IF_COPY(txt, 0);
	PG_FREE_IF_COPY(query, 1);
	PG_RETURN_FLOAT4(res);
}

typedef struct
{
	QueryItem **item;
	int16		nitem;
	uint8		wclass;
	int32		pos;
} DocRepresentation;

static int
compareDocR(const void *va, const void *vb)
{
	DocRepresentation *a = (DocRepresentation *) va;
	DocRepresentation *b = (DocRepresentation *) vb;

	if (a->pos == b->pos)
		return 0;
	return (a->pos > b->pos) ? 1 : -1;
}

typedef struct
{
	TSQuery		query;
	bool	   *operandexist;
} QueryRepresentation;

#define QR_GET_OPERAND_EXISTS(q, v)		( (q)->operandexist[ ((QueryItem*)(v)) - GETQUERY((q)->query) ] )
#define QR_SET_OPERAND_EXISTS(q, v)  QR_GET_OPERAND_EXISTS(q,v) = true

static bool
checkcondition_QueryOperand(void *checkval, QueryOperand *val)
{
	QueryRepresentation *qr = (QueryRepresentation *) checkval;

	return QR_GET_OPERAND_EXISTS(qr, val);
}

typedef struct
{
	int			pos;
	int			p;
	int			q;
	DocRepresentation *begin;
	DocRepresentation *end;
} Extention;


static bool
Cover(DocRepresentation *doc, int len, QueryRepresentation *qr, Extention *ext)
{
	DocRepresentation *ptr;
	int			lastpos = ext->pos;
	int			i;
	bool		found = false;

	/*
	 * since this function recurses, it could be driven to stack overflow.
	 * (though any decent compiler will optimize away the tail-recursion.
	 */
	check_stack_depth();

	memset(qr->operandexist, 0, sizeof(bool) * qr->query->size);

	ext->p = 0x7fffffff;
	ext->q = 0;
	ptr = doc + ext->pos;

	/* find upper bound of cover from current position, move up */
	while (ptr - doc < len)
	{
		for (i = 0; i < ptr->nitem; i++)
		{
			if (ptr->item[i]->type == QI_VAL)
				QR_SET_OPERAND_EXISTS(qr, ptr->item[i]);
		}
		if (TS_execute(GETQUERY(qr->query), (void *) qr, false, checkcondition_QueryOperand))
		{
			if (ptr->pos > ext->q)
			{
				ext->q = ptr->pos;
				ext->end = ptr;
				lastpos = ptr - doc;
				found = true;
			}
			break;
		}
		ptr++;
	}

	if (!found)
		return false;

	memset(qr->operandexist, 0, sizeof(bool) * qr->query->size);

	ptr = doc + lastpos;

	/* find lower bound of cover from found upper bound, move down */
	while (ptr >= doc + ext->pos)
	{
		for (i = 0; i < ptr->nitem; i++)
			if (ptr->item[i]->type == QI_VAL)
				QR_SET_OPERAND_EXISTS(qr, ptr->item[i]);
		if (TS_execute(GETQUERY(qr->query), (void *) qr, true, checkcondition_QueryOperand))
		{
			if (ptr->pos < ext->p)
			{
				ext->begin = ptr;
				ext->p = ptr->pos;
			}
			break;
		}
		ptr--;
	}

	if (ext->p <= ext->q)
	{
		/*
		 * set position for next try to next lexeme after begining of founded
		 * cover
		 */
		ext->pos = (ptr - doc) + 1;
		return true;
	}

	ext->pos++;
	return Cover(doc, len, qr, ext);
}

static DocRepresentation *
get_docrep(TSVector txt, QueryRepresentation *qr, int *doclen)
{
	QueryItem  *item = GETQUERY(qr->query);
	WordEntry  *entry;
	WordEntryPos *post;
	int4		dimt,
				j,
				i;
	int			len = qr->query->size * 4,
				cur = 0;
	DocRepresentation *doc;
	char	   *operand;

	doc = (DocRepresentation *) palloc(sizeof(DocRepresentation) * len);
	operand = GETOPERAND(qr->query);

	for (i = 0; i < qr->query->size; i++)
	{
		QueryOperand *curoperand;

		if (item[i].type != QI_VAL)
			continue;

		curoperand = &item[i].operand;

		if (QR_GET_OPERAND_EXISTS(qr, &item[i]))
			continue;

		entry = find_wordentry(txt, qr->query, curoperand);
		if (!entry)
			continue;

		if (entry->haspos)
		{
			dimt = POSDATALEN(txt, entry);
			post = POSDATAPTR(txt, entry);
		}
		else
		{
			dimt = POSNULL.npos;
			post = POSNULL.pos;
		}

		while (cur + dimt >= len)
		{
			len *= 2;
			doc = (DocRepresentation *) repalloc(doc, sizeof(DocRepresentation) * len);
		}

		for (j = 0; j < dimt; j++)
		{
			if (j == 0)
			{
				int			k;

				doc[cur].nitem = 0;
				doc[cur].item = (QueryItem **) palloc(sizeof(QueryItem *) * qr->query->size);

				for (k = 0; k < qr->query->size; k++)
				{
					QueryOperand *kptr = &item[k].operand;
					QueryOperand *iptr = &item[i].operand;

					if (k == i ||
						(item[k].type == QI_VAL &&
						 compareQueryOperand(&kptr, &iptr, operand) == 0))
					{
						/*
						 * if k == i, we've already checked above that it's
						 * type == Q_VAL
						 */
						doc[cur].item[doc[cur].nitem] = item + k;
						doc[cur].nitem++;
						QR_SET_OPERAND_EXISTS(qr, item + k);
					}
				}
			}
			else
			{
				doc[cur].nitem = doc[cur - 1].nitem;
				doc[cur].item = doc[cur - 1].item;
			}
			doc[cur].pos = WEP_GETPOS(post[j]);
			doc[cur].wclass = WEP_GETWEIGHT(post[j]);
			cur++;
		}
	}

	*doclen = cur;

	if (cur > 0)
	{
		qsort((void *) doc, cur, sizeof(DocRepresentation), compareDocR);
		return doc;
	}

	pfree(doc);
	return NULL;
}

static float4
calc_rank_cd(float4 *arrdata, TSVector txt, TSQuery 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;
	QueryRepresentation qr;


	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];
	}

	qr.query = query;
	qr.operandexist = (bool *) palloc0(sizeof(bool) * query->size);

	doc = get_docrep(txt, &qr, &doclen);
	if (!doc)
	{
		pfree(qr.operandexist);
		return 0.0;
	}

	MemSet(&ext, 0, sizeof(Extention));
	while (Cover(doc, doclen, &qr, &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) && NExtent > 0 && 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);

	if (method & RANK_NORM_RDIVRPLUS1)
		Wdoc /= (Wdoc + 1);

	pfree(doc);

	pfree(qr.operandexist);

	return (float4) Wdoc;
}

Datum
ts_rankcd_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_cd(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
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_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_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);
}