1 Fix problem with lost precision in rank with OR-ed lexemes

feodor · feodor · commit 21b748e76acc · 2005-10-28T13:05:06.000Z
2 Allow tsquery_in to input void tsquery: resolve dump/restore problem with tsquery
diff --git a/contrib/tsearch2/expected/tsearch2.out b/contrib/tsearch2/expected/tsearch2.out
@@ -746,21 +746,21 @@ select count(*) FROM test_tsvector WHERE a @@ to_tsquery('copyright');
 (1 row)
 
 select rank(' a:1 s:2C d g'::tsvector, 'a | s');
- rank 
-------
- 0.28
+   rank    
+-----------
+ 0.0911891
 (1 row)
 
 select rank(' a:1 s:2B d g'::tsvector, 'a | s');
- rank 
-------
- 0.46
+   rank   
+----------
+ 0.151982
 (1 row)
 
 select rank(' a:1 s:2 d g'::tsvector, 'a | s');
- rank 
-------
- 0.19
+   rank    
+-----------
+ 0.0607927
 (1 row)
 
 select rank(' a:1 s:2C d g'::tsvector, 'a & s');
diff --git a/contrib/tsearch2/query.c b/contrib/tsearch2/query.c
@@ -55,6 +55,7 @@ Datum		to_tsquery_current(PG_FUNCTION_ARGS);
 /* parser's states */
 #define WAITOPERAND 1
 #define WAITOPERATOR	2
+#define WAITFIRSTOPERAND 3
 
 /*
  * node of query tree, also used
@@ -137,6 +138,7 @@ gettoken_query(QPRS_STATE * state, int4 *val, int4 *lenval, char **strval, int2
 	{
 		switch (state->state)
 		{
+			case WAITFIRSTOPERAND:
 			case WAITOPERAND:
 				if (*(state->buf) == '!')
 				{
@@ -159,14 +161,16 @@ gettoken_query(QPRS_STATE * state, int4 *val, int4 *lenval, char **strval, int2
 				else if (*(state->buf) != ' ')
 				{
 					state->valstate.prsbuf = state->buf;
-					state->state = WAITOPERATOR;
 					if (gettoken_tsvector(&(state->valstate)))
 					{
 						*strval = state->valstate.word;
 						*lenval = state->valstate.curpos - state->valstate.word;
 						state->buf = get_weight(state->valstate.prsbuf, weight);
+						state->state = WAITOPERATOR;
 						return VAL;
 					}
+					else if ( state->state == WAITFIRSTOPERAND ) 
+						return END;
 					else
 						ereport(ERROR,
 								(errcode(ERRCODE_SYNTAX_ERROR),
@@ -596,7 +600,7 @@ static QUERYTYPE *
 
 	/* init state */
 	state.buf = buf;
-	state.state = WAITOPERAND;
+	state.state = WAITFIRSTOPERAND;
 	state.count = 0;
 	state.num = 0;
 	state.str = NULL;
@@ -616,10 +620,13 @@ static QUERYTYPE *
 	/* parse query & make polish notation (postfix, but in reverse order) */
 	makepol(&state, pushval);
 	pfree(state.valstate.word);
-	if (!state.num)
-		ereport(ERROR,
-				(errcode(ERRCODE_SYNTAX_ERROR),
-				 errmsg("empty query")));
+	if (!state.num) {
+		elog(NOTICE, "Query doesn't contain lexem(s)");
+		query = (QUERYTYPE*)palloc( HDRSIZEQT );
+		query->len = HDRSIZEQT;
+		query->size = 0;
+		return query; 
+	}
 
 	/* make finish struct */
 	commonlen = COMPUTESIZE(state.num, state.sumlen);
@@ -905,6 +912,10 @@ to_tsquery(PG_FUNCTION_ARGS)
 	PG_FREE_IF_COPY(in, 1);
 
 	query = queryin(str, pushval_morph, PG_GETARG_INT32(0));
+	
+	if ( query->size == 0 )
+		PG_RETURN_POINTER(query);
+
 	res = clean_fakeval_v2(GETQUERY(query), &len);
 	if (!res)
 	{
diff --git a/contrib/tsearch2/rank.c b/contrib/tsearch2/rank.c
@@ -257,7 +257,7 @@ calc_rank_or(float *w, tsvector * t, QUERYTYPE * q)
 	int4		dimt,
 				j,
 				i;
-	float		res = -1.0;
+	float		res = 0.0;
 	ITEM	  **item;
 	int			size = q->size;
 
@@ -266,6 +266,8 @@ calc_rank_or(float *w, tsvector * t, QUERYTYPE * q)
 
 	for (i = 0; i < size; i++)
 	{
+		float resj,wjm;
+		int4  jm;
 		entry = find_wordentry(t, q, item[i]);
 		if (!entry)
 			continue;
@@ -281,14 +283,27 @@ calc_rank_or(float *w, tsvector * t, QUERYTYPE * q)
 			post = POSNULL + 1;
 		}
 
-		for (j = 0; j < dimt; j++)
-		{
-			if (res < 0)
-				res = wpos(post[j]);
-			else
-				res = 1.0 - (1.0 - res) * (1.0 - wpos(post[j]));
-		}
+                resj = 0.0;
+                wjm = -1.0;
+                jm = 0;
+                for (j = 0; j < dimt; j++)
+                {
+                        resj = resj + wpos(post[j])/((j+1)*(j+1));
+                        if ( wpos(post[j]) > wjm ) {
+                                wjm = wpos(post[j]);
+                                jm  = j;
+                        }
+                }
+/* 
+        limit (sum(i/i^2),i->inf) = pi^2/6
+        resj = sum(wi/i^2),i=1,noccurence,
+        wi - should be sorted desc, 
+        don't sort for now, just choose maximum weight. This should be corrected
+		Oleg Bartunov
+*/
+                res = res + ( wjm + resj - wjm/((jm+1)*(jm+1)))/1.64493406685; 
 	}
+	res = res /size;
 	pfree(item);
 	return res;
 }
