Added:

Artur Zakirov · Artur Zakirov · commit 00ceebc5dcfc · 2016-08-24T14:22:34.000+03:00
- rum_distance_query type, casting from tquery to rum_distance_query
- rum_ts_distance() overloads to enable calculate distance with normalization parameter
- &lt;=&gt; operator overload
diff --git a/expected/rum.out b/expected/rum.out
@@ -150,6 +150,29 @@ SELECT
   57.5727 |         57.5727 | thinking--“to go or not to go?” We are this far on the way. Reached | 'far':11 'go':3,7 'reach':15 'think':1 'way':14
 (2 rows)
 
+-- Check ranking normalization
+SELECT rum_ts_distance(a, to_tsquery('pg_catalog.english', 'way'), 0), *
+	FROM test_rum
+	WHERE a @@ to_tsquery('pg_catalog.english', 'way')
+	ORDER BY a <=> to_tsquery('pg_catalog.english', 'way');
+ rum_ts_distance |                                    t                                     |                               a                               
+-----------------+--------------------------------------------------------------------------+---------------------------------------------------------------
+         16.4493 | my appreciation of you in a more complimentary way than by sending this  | 'appreci':2 'complimentari':8 'send':12 'way':9
+         16.4493 | itself. Put on your “specs” and look at the castle, half way up the      | 'castl':10 'half':11 'look':7 'put':2 'spec':5 'way':12
+         16.4493 | so well that only a fragment, as it were, gave way. It still hangs as if | 'fragment':6 'gave':10 'hang':14 'still':13 'way':11 'well':2
+         16.4493 | thinking--“to go or not to go?” We are this far on the way. Reached      | 'far':11 'go':3,7 'reach':15 'think':1 'way':14
+(4 rows)
+
+SELECT rum_ts_distance(a, row(to_tsquery('pg_catalog.english', 'way & (go | half)'), 0)::rum_distance_query), *
+	FROM test_rum
+	WHERE a @@ to_tsquery('pg_catalog.english', 'way & (go | half)')
+	ORDER BY a <=> to_tsquery('pg_catalog.english', 'way & (go | half)');
+ rum_ts_distance |                                  t                                  |                            a                            
+-----------------+---------------------------------------------------------------------+---------------------------------------------------------
+         8.22467 | itself. Put on your “specs” and look at the castle, half way up the | 'castl':10 'half':11 'look':7 'put':2 'spec':5 'way':12
+         57.5727 | thinking--“to go or not to go?” We are this far on the way. Reached | 'far':11 'go':3,7 'reach':15 'think':1 'way':14
+(2 rows)
+
 INSERT INTO test_rum (t) VALUES ('foo bar foo the over foo qq bar');
 INSERT INTO test_rum (t) VALUES ('345 qwerty copyright');
 INSERT INTO test_rum (t) VALUES ('345 qwerty');
diff --git a/rum--1.0.sql b/rum--1.0.sql
@@ -6,10 +6,31 @@ LANGUAGE C;
 -- Access method
 CREATE ACCESS METHOD rum TYPE INDEX HANDLER rumhandler;
 
--- Opclasses
+-- tsvector opclasses
+
+CREATE TYPE rum_distance_query AS (query tsquery, method int);
+
+CREATE FUNCTION tsquery_to_distance_query(tsquery)
+RETURNS rum_distance_query
+AS 'MODULE_PATHNAME', 'tsquery_to_distance_query'
+LANGUAGE C IMMUTABLE STRICT;
+
+CREATE CAST (tsquery AS rum_distance_query)
+		WITH FUNCTION tsquery_to_distance_query(tsquery) AS IMPLICIT;
+
 CREATE FUNCTION rum_ts_distance(tsvector,tsquery)
 RETURNS float4
-AS 'MODULE_PATHNAME'
+AS 'MODULE_PATHNAME', 'rum_ts_distance_tt'
+LANGUAGE C IMMUTABLE STRICT;
+
+CREATE FUNCTION rum_ts_distance(tsvector,tsquery,int)
+RETURNS float4
+AS 'MODULE_PATHNAME', 'rum_ts_distance_ttf'
+LANGUAGE C IMMUTABLE STRICT;
+
+CREATE FUNCTION rum_ts_distance(tsvector,rum_distance_query)
+RETURNS float4
+AS 'MODULE_PATHNAME', 'rum_ts_distance_td'
 LANGUAGE C IMMUTABLE STRICT;
 
 CREATE OPERATOR <=> (
@@ -18,6 +39,12 @@ CREATE OPERATOR <=> (
         PROCEDURE = rum_ts_distance
 );
 
+CREATE OPERATOR <=> (
+		LEFTARG = tsvector,
+		RIGHTARG = rum_distance_query,
+		PROCEDURE = rum_ts_distance
+);
+
 CREATE FUNCTION rum_extract_tsvector(tsvector,internal,internal,internal,internal)
 RETURNS internal
 AS 'MODULE_PATHNAME'
diff --git a/rum.h b/rum.h
@@ -767,7 +767,12 @@ extern Datum rum_extract_tsquery(PG_FUNCTION_ARGS);
 extern Datum rum_tsvector_config(PG_FUNCTION_ARGS);
 extern Datum rum_tsquery_pre_consistent(PG_FUNCTION_ARGS);
 extern Datum rum_tsquery_distance(PG_FUNCTION_ARGS);
-extern Datum rum_ts_distance(PG_FUNCTION_ARGS);
+extern Datum rum_ts_distance_tt(PG_FUNCTION_ARGS);
+extern Datum rum_ts_distance_ttf(PG_FUNCTION_ARGS);
+extern Datum rum_ts_distance_td(PG_FUNCTION_ARGS);
+
+extern Datum tsquery_to_distance_query(PG_FUNCTION_ARGS);
+
 
 /* GUC parameters */
 extern PGDLLIMPORT int RumFuzzySearchLimit;
diff --git a/rum_ts_utils.c b/rum_ts_utils.c
@@ -11,12 +11,15 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "catalog/pg_type.h"
+#include "funcapi.h"
 #include "miscadmin.h"
 #include "tsearch/ts_type.h"
 #include "tsearch/ts_utils.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
+#include "utils/typcache.h"
 
 #include "rum.h"
 
@@ -29,7 +32,11 @@ PG_FUNCTION_INFO_V1(rum_tsquery_pre_consistent);
 PG_FUNCTION_INFO_V1(rum_tsquery_consistent);
 PG_FUNCTION_INFO_V1(rum_tsquery_timestamp_consistent);
 PG_FUNCTION_INFO_V1(rum_tsquery_distance);
-PG_FUNCTION_INFO_V1(rum_ts_distance);
+PG_FUNCTION_INFO_V1(rum_ts_distance_tt);
+PG_FUNCTION_INFO_V1(rum_ts_distance_ttf);
+PG_FUNCTION_INFO_V1(rum_ts_distance_td);
+
+PG_FUNCTION_INFO_V1(tsquery_to_distance_query);
 
 static int	count_pos(char *ptr, int len);
 static char *decompress_pos(char *ptr, uint16 *pos);
@@ -1182,7 +1189,7 @@ rum_tsquery_distance(PG_FUNCTION_ARGS)
 }
 
 Datum
-rum_ts_distance(PG_FUNCTION_ARGS)
+rum_ts_distance_tt(PG_FUNCTION_ARGS)
 {
 	TSVector	txt = PG_GETARG_TSVECTOR(0);
 	TSQuery		query = PG_GETARG_TSQUERY(1);
@@ -1198,6 +1205,95 @@ rum_ts_distance(PG_FUNCTION_ARGS)
 		PG_RETURN_FLOAT4(1.0 / res);
 }
 
+Datum
+rum_ts_distance_ttf(PG_FUNCTION_ARGS)
+{
+	TSVector	txt = PG_GETARG_TSVECTOR(0);
+	TSQuery		query = PG_GETARG_TSQUERY(1);
+	int			method = PG_GETARG_INT32(2);
+	float4		res;
+
+	res = calc_score(weights, txt, query, method);
+
+	PG_FREE_IF_COPY(txt, 0);
+	PG_FREE_IF_COPY(query, 1);
+	if (res == 0)
+		PG_RETURN_FLOAT4(get_float4_infinity());
+	else
+		PG_RETURN_FLOAT4(1.0 / res);
+}
+
+Datum
+rum_ts_distance_td(PG_FUNCTION_ARGS)
+{
+	TSVector	txt = PG_GETARG_TSVECTOR(0);
+	HeapTupleHeader d = PG_GETARG_HEAPTUPLEHEADER(1);
+
+	Oid			tupType = HeapTupleHeaderGetTypeId(d);
+	int32		tupTypmod = HeapTupleHeaderGetTypMod(d);
+	TupleDesc	tupdesc = lookup_rowtype_tupdesc(tupType, tupTypmod);
+	HeapTupleData tuple;
+
+	TSQuery		query;
+	int			method;
+	bool		isnull;
+	float4		res;
+
+	tuple.t_len = HeapTupleHeaderGetDatumLength(d);
+	ItemPointerSetInvalid(&(tuple.t_self));
+	tuple.t_tableOid = InvalidOid;
+	tuple.t_data = d;
+
+	query = DatumGetTSQuery(fastgetattr(&tuple, 1, tupdesc, &isnull));
+	if (isnull)
+	{
+		ReleaseTupleDesc(tupdesc);
+		PG_FREE_IF_COPY(txt, 0);
+		PG_FREE_IF_COPY(d, 1);
+		elog(ERROR, "NULL query value is not allowed");
+	}
+
+	method = DatumGetInt32(fastgetattr(&tuple, 2, tupdesc, &isnull));
+	if (isnull)
+		method = 0;
+
+	res = calc_score(weights, txt, query, method);
+
+	ReleaseTupleDesc(tupdesc);
+	PG_FREE_IF_COPY(txt, 0);
+	PG_FREE_IF_COPY(d, 1);
+
+	if (res == 0)
+		PG_RETURN_FLOAT4(get_float4_infinity());
+	else
+		PG_RETURN_FLOAT4(1.0 / res);
+}
+
+Datum
+tsquery_to_distance_query(PG_FUNCTION_ARGS)
+{
+	TSQuery		query = PG_GETARG_TSQUERY(0);
+
+	TupleDesc	tupdesc;
+	HeapTuple	htup;
+	Datum		values[2];
+	bool		nulls[2];
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	tupdesc = BlessTupleDesc(tupdesc);
+
+	MemSet(nulls, 0, sizeof(nulls));
+	values[0] = TSQueryGetDatum(query);
+	values[1] = Int32GetDatum(DEF_NORM_METHOD);
+
+	htup = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(htup));
+}
+
 Datum
 rum_tsvector_config(PG_FUNCTION_ARGS)
 {
diff --git a/sql/rum.sql b/sql/rum.sql
@@ -52,6 +52,16 @@ SELECT
 	FROM test_rum
 	ORDER BY a <=> to_tsquery('pg_catalog.english', 'way & (go | half)') limit 2;
 
+-- Check ranking normalization
+SELECT rum_ts_distance(a, to_tsquery('pg_catalog.english', 'way'), 0), *
+	FROM test_rum
+	WHERE a @@ to_tsquery('pg_catalog.english', 'way')
+	ORDER BY a <=> to_tsquery('pg_catalog.english', 'way');
+SELECT rum_ts_distance(a, row(to_tsquery('pg_catalog.english', 'way & (go | half)'), 0)::rum_distance_query), *
+	FROM test_rum
+	WHERE a @@ to_tsquery('pg_catalog.english', 'way & (go | half)')
+	ORDER BY a <=> to_tsquery('pg_catalog.english', 'way & (go | half)');
+
 INSERT INTO test_rum (t) VALUES ('foo bar foo the over foo qq bar');
 INSERT INTO test_rum (t) VALUES ('345 qwerty copyright');
 INSERT INTO test_rum (t) VALUES ('345 qwerty');
