1 Minimize memory allocation for void (but not null) value.

2 Add silly ordering for ts_vector to aim grouping, union, except etc. Don't use BTree opclass (tsvector_ops).

contrib/tsearch2/sql/tsearch2.sql

@@ -247,3 +247,9 @@ Upon a woman s face. E.  J.  Pratt  (1882 1964)
 
 --check debug
 select * from ts_debug('Tsearch module for PostgreSQL 7.3.3');
+
+--check ordering
+drop trigger tsvectorupdate on test_tsvector;
+insert into test_tsvector values (null, null);
+select a is null, a from test_tsvector order by a;
+

contrib/tsearch2/tsearch.sql.in

@@ -702,6 +702,112 @@ where
         c.oid=show_curcfg() 
 ' language 'SQL' with(isstrict);
 
+--compare functions
+CREATE FUNCTION tsvector_cmp(tsvector,tsvector)
+RETURNS int4
+AS 'MODULE_PATHNAME'
+LANGUAGE 'C' WITH (isstrict,iscachable);
+
+CREATE FUNCTION tsvector_lt(tsvector,tsvector)
+RETURNS bool
+AS 'MODULE_PATHNAME'
+LANGUAGE 'C' WITH (isstrict,iscachable);
+
+CREATE FUNCTION tsvector_le(tsvector,tsvector)
+RETURNS bool
+AS 'MODULE_PATHNAME'
+LANGUAGE 'C' WITH (isstrict,iscachable);
+        
+CREATE FUNCTION tsvector_eq(tsvector,tsvector)
+RETURNS bool
+AS 'MODULE_PATHNAME'
+LANGUAGE 'C' WITH (isstrict,iscachable);
+
+CREATE FUNCTION tsvector_ge(tsvector,tsvector)
+RETURNS bool
+AS 'MODULE_PATHNAME'
+LANGUAGE 'C' WITH (isstrict,iscachable);
+        
+CREATE FUNCTION tsvector_gt(tsvector,tsvector)
+RETURNS bool
+AS 'MODULE_PATHNAME'
+LANGUAGE 'C' WITH (isstrict,iscachable);
+
+CREATE FUNCTION tsvector_ne(tsvector,tsvector)
+RETURNS bool
+AS 'MODULE_PATHNAME'
+LANGUAGE 'C' WITH (isstrict,iscachable);
+
+CREATE OPERATOR < (
+        LEFTARG = tsvector,
+        RIGHTARG = tsvector,
+        PROCEDURE = tsvector_lt,
+        COMMUTATOR = '>',
+        NEGATOR = '>=',
+        RESTRICT = contsel,
+        JOIN = contjoinsel
+);
+
+CREATE OPERATOR <= (
+        LEFTARG = tsvector,
+        RIGHTARG = tsvector,
+        PROCEDURE = tsvector_le,
+        COMMUTATOR = '>=',
+        NEGATOR = '>',
+        RESTRICT = contsel,
+        JOIN = contjoinsel
+);
+
+CREATE OPERATOR >= (
+        LEFTARG = tsvector,
+        RIGHTARG = tsvector,
+        PROCEDURE = tsvector_ge,
+        COMMUTATOR = '<=',
+        NEGATOR = '<',
+        RESTRICT = contsel,
+        JOIN = contjoinsel
+);
+
+CREATE OPERATOR > (
+        LEFTARG = tsvector,
+        RIGHTARG = tsvector,
+        PROCEDURE = tsvector_gt,
+        COMMUTATOR = '<',
+        NEGATOR = '<=',
+        RESTRICT = contsel,
+        JOIN = contjoinsel
+);
+
+CREATE OPERATOR = (
+        LEFTARG = tsvector,
+        RIGHTARG = tsvector,
+        PROCEDURE = tsvector_eq,
+        COMMUTATOR = '=',
+        NEGATOR = '<>',
+        RESTRICT = eqsel,
+        JOIN = eqjoinsel,
+        SORT1 = '<',
+        SORT2 = '<'
+);
+
+CREATE OPERATOR <> (
+        LEFTARG = tsvector,
+        RIGHTARG = tsvector,
+        PROCEDURE = tsvector_ne,
+        COMMUTATOR = '<>',
+        NEGATOR = '=',
+        RESTRICT = neqsel,
+        JOIN = neqjoinsel
+);
+
+CREATE OPERATOR CLASS tsvector_ops
+    DEFAULT FOR TYPE tsvector USING btree AS
+        OPERATOR        1       < ,
+        OPERATOR        2       <= , 
+        OPERATOR        3       = ,
+        OPERATOR        4       >= ,
+        OPERATOR        5       > ,
+        FUNCTION        1       tsvector_cmp(tsvector, tsvector);
 
 --example of ISpell dictionary
 --update pg_ts_dict set dict_initoption='DictFile="/usr/local/share/ispell/russian.dict" ,AffFile ="/usr/local/share/ispell/russian.aff", StopFile="/usr/local/share/ispell/russian.stop"' where dict_id=4;

contrib/tsearch2/tsvector.c

@@ -451,6 +451,8 @@ tsvector_in(PG_FUNCTION_ARGS)
 
 	if (len > 0)
 		len = uniqueentry(arr, len, tmpbuf, &buflen);
+	else
+		buflen=0;
 	totallen = CALCDATASIZE(len, buflen);
 	in = (tsvector *) palloc(totallen);
 	memset(in, 0, totallen);
@@ -932,3 +934,91 @@ tsearch2(PG_FUNCTION_ARGS)
 
 	return PointerGetDatum(rettuple);
 }
+
+static int
+silly_cmp_tsvector(const tsvector *a, const tsvector *b) {
+	if ( a->len < b->len ) 	
+		return -1;
+	else if ( a->len > b->len )
+		return 1;
+	else if ( a->size < b->size ) 
+		return -1;
+	else if ( a->size > b->size )
+		return 1;
+	else {
+		unsigned char *aptr=(unsigned char *)(a->data) + DATAHDRSIZE;
+		unsigned char *bptr=(unsigned char *)(b->data) + DATAHDRSIZE;
+		
+		while( aptr - ( (unsigned char *)(a->data) ) < a->len ) {
+			if ( *aptr != *bptr )
+				return ( *aptr < *bptr ) ? -1 : 1;
+			aptr++; bptr++;
+		} 
+	}
+	return 0;	
+}
+
+PG_FUNCTION_INFO_V1(tsvector_cmp);
+PG_FUNCTION_INFO_V1(tsvector_lt);
+PG_FUNCTION_INFO_V1(tsvector_le);
+PG_FUNCTION_INFO_V1(tsvector_eq);
+PG_FUNCTION_INFO_V1(tsvector_ne);
+PG_FUNCTION_INFO_V1(tsvector_ge);
+PG_FUNCTION_INFO_V1(tsvector_gt);
+Datum           tsvector_cmp(PG_FUNCTION_ARGS);
+Datum           tsvector_lt(PG_FUNCTION_ARGS);
+Datum           tsvector_le(PG_FUNCTION_ARGS);
+Datum           tsvector_eq(PG_FUNCTION_ARGS);
+Datum           tsvector_ne(PG_FUNCTION_ARGS);
+Datum           tsvector_ge(PG_FUNCTION_ARGS);
+Datum           tsvector_gt(PG_FUNCTION_ARGS);
+
+#define RUNCMP     									\
+tsvector *a        = (tsvector *) DatumGetPointer(PG_DETOAST_DATUM(PG_GETARG_DATUM(0)));\
+tsvector *b        = (tsvector *) DatumGetPointer(PG_DETOAST_DATUM(PG_GETARG_DATUM(1)));\
+int res = silly_cmp_tsvector(a,b);							\
+PG_FREE_IF_COPY(a,0);									\
+PG_FREE_IF_COPY(b,1);									\
+
+Datum
+tsvector_cmp(PG_FUNCTION_ARGS)   {
+	RUNCMP
+	PG_RETURN_INT32(res);
+}
+
+Datum
+tsvector_lt(PG_FUNCTION_ARGS) {
+	RUNCMP
+	PG_RETURN_BOOL((res < 0) ? true : false);
+}
+
+Datum
+tsvector_le(PG_FUNCTION_ARGS) {
+	RUNCMP
+	PG_RETURN_BOOL((res <= 0) ? true : false);
+}
+
+Datum
+tsvector_eq(PG_FUNCTION_ARGS) {
+	RUNCMP
+	PG_RETURN_BOOL((res == 0) ? true : false);
+}
+
+Datum
+tsvector_ge(PG_FUNCTION_ARGS) {
+	RUNCMP
+	PG_RETURN_BOOL((res >= 0) ? true : false);
+}
+ 
+Datum
+tsvector_gt(PG_FUNCTION_ARGS) {
+	RUNCMP
+	PG_RETURN_BOOL((res > 0) ? true : false);
+}               
+ 
+Datum
+tsvector_ne(PG_FUNCTION_ARGS) {   
+	RUNCMP      
+	PG_RETURN_BOOL((res != 0) ? true : false);
+}
+