Implement operator class parameters

PostgreSQL provides set of template index access methods, where opclasses have much freedom in the semantics of indexing. These index AMs are GiST, GIN, SP-GiST and BRIN. There opclasses define representation of keys, operations on them and supported search strategies. So, it's natural that opclasses may be faced some tradeoffs, which require user-side decision. This commit implements opclass parameters allowing users to set some values, which tell opclass how to index the particular dataset. This commit doesn't introduce new storage in system catalog. Instead it uses pg_attribute.attoptions, which is used for table column storage options but unused for index attributes. In order to evade changing signature of each opclass support function, we implement unified way to pass options to opclass support functions. Options are set to fn_expr as the constant bytea expression. It's possible due to the fact that opclass support functions are executed outside of expressions, so fn_expr is unused for them. This commit comes with some examples of opclass options usage. We parametrize signature length in GiST. That applies to multiple opclasses: tsvector_ops, gist__intbig_ops, gist_ltree_ops, gist__ltree_ops, gist_trgm_ops and gist_hstore_ops. Also we parametrize maximum number of integer ranges for gist__int_ops. However, the main future usage of this feature is expected to be json, where users would be able to specify which way to index particular json parts. Catversion is bumped. Discussion: https://postgr.es/m/d22c3a18-31c7-1879-fc11-4c1ce2f5e5af%40postgrespro.ru Author: Nikita Glukhov, revised by me Reviwed-by: Nikolay Shaplov, Robert Haas, Tom Lane, Tomas Vondra, Alvaro Herrera
2025-08-31 17:02:12 +03:00 · 2020-03-30 19:17:11 +03:00
parent 1d53432ff9
commit 911e702077
108 changed files with 4086 additions and 924 deletions
--- a/src/backend/utils/adt/ruleutils.c
+++ b/src/backend/utils/adt/ruleutils.c
@@ -480,6 +480,7 @@ static void add_cast_to(StringInfo buf, Oid typid);
 static char *generate_qualified_type_name(Oid typid);
 static text *string_to_text(char *str);
 static char *flatten_reloptions(Oid relid);
+static void get_reloptions(StringInfo buf, Datum reloptions);

 #define only_marker(rte)  ((rte)->inh ? "" : "ONLY ")

@@ -1384,6 +1385,8 @@ pg_get_indexdef_worker(Oid indexrelid, int colno,
 		{
 			int16		opt = indoption->values[keyno];
 			Oid			indcoll = indcollation->values[keyno];
+			Datum		attoptions = get_attoptions(indexrelid, keyno + 1);
+			bool		has_options = attoptions != (Datum) 0;

 			/* Add collation, if not default for column */
 			if (OidIsValid(indcoll) && indcoll != keycolcollation)
@@ -1391,7 +1394,15 @@ pg_get_indexdef_worker(Oid indexrelid, int colno,
 								 generate_collation_name((indcoll)));

 			/* Add the operator class name, if not default */
-			get_opclass_name(indclass->values[keyno], keycoltype, &buf);
+			get_opclass_name(indclass->values[keyno],
+							 has_options ? InvalidOid : keycoltype, &buf);
+
+			if (has_options)
+			{
+				appendStringInfoString(&buf, " (");
+				get_reloptions(&buf, attoptions);
+				appendStringInfoChar(&buf, ')');
+			}

 			/* Add options if relevant */
 			if (amroutine->amcanorder)
@@ -10573,6 +10584,23 @@ get_opclass_name(Oid opclass, Oid actual_datatype,
 	ReleaseSysCache(ht_opc);
 }

+/*
+ * generate_opclass_name
+ *		Compute the name to display for a opclass specified by OID
+ *
+ * The result includes all necessary quoting and schema-prefixing.
+ */
+char *
+generate_opclass_name(Oid opclass)
+{
+	StringInfoData buf;
+
+	initStringInfo(&buf);
+	get_opclass_name(opclass, InvalidOid, &buf);
+
+	return &buf.data[1];	/* get_opclass_name() prepends space */
+}
+
 /*
 * processIndirection - take care of array and subfield assignment
 *
@@ -11250,6 +11278,62 @@ string_to_text(char *str)
 	return result;
 }

+/*
+ * Generate a C string representing a relation options from text[] datum.
+ */
+static void
+get_reloptions(StringInfo buf, Datum reloptions)
+{
+	Datum	   *options;
+	int			noptions;
+	int			i;
+
+	deconstruct_array(DatumGetArrayTypeP(reloptions),
+					  TEXTOID, -1, false, TYPALIGN_INT,
+					  &options, NULL, &noptions);
+
+	for (i = 0; i < noptions; i++)
+	{
+		char	   *option = TextDatumGetCString(options[i]);
+		char	   *name;
+		char	   *separator;
+		char	   *value;
+
+		/*
+		 * Each array element should have the form name=value.  If the "="
+		 * is missing for some reason, treat it like an empty value.
+		 */
+		name = option;
+		separator = strchr(option, '=');
+		if (separator)
+		{
+			*separator = '\0';
+			value = separator + 1;
+		}
+		else
+			value = "";
+
+		if (i > 0)
+			appendStringInfoString(buf, ", ");
+		appendStringInfo(buf, "%s=", quote_identifier(name));
+
+		/*
+		 * In general we need to quote the value; but to avoid unnecessary
+		 * clutter, do not quote if it is an identifier that would not
+		 * need quoting.  (We could also allow numbers, but that is a bit
+		 * trickier than it looks --- for example, are leading zeroes
+		 * significant?  We don't want to assume very much here about what
+		 * custom reloptions might mean.)
+		 */
+		if (quote_identifier(value) == value)
+			appendStringInfoString(buf, value);
+		else
+			simple_quote_literal(buf, value);
+
+		pfree(option);
+	}
+}
+
 /*
 * Generate a C string representing a relation's reloptions, or NULL if none.
 */
@@ -11270,56 +11354,9 @@ flatten_reloptions(Oid relid)
 	if (!isnull)
 	{
 		StringInfoData buf;
-		Datum	   *options;
-		int			noptions;
-		int			i;

 		initStringInfo(&buf);
-
-		deconstruct_array(DatumGetArrayTypeP(reloptions),
-						  TEXTOID, -1, false, TYPALIGN_INT,
-						  &options, NULL, &noptions);
-
-		for (i = 0; i < noptions; i++)
-		{
-			char	   *option = TextDatumGetCString(options[i]);
-			char	   *name;
-			char	   *separator;
-			char	   *value;
-
-			/*
-			 * Each array element should have the form name=value.  If the "="
-			 * is missing for some reason, treat it like an empty value.
-			 */
-			name = option;
-			separator = strchr(option, '=');
-			if (separator)
-			{
-				*separator = '\0';
-				value = separator + 1;
-			}
-			else
-				value = "";
-
-			if (i > 0)
-				appendStringInfoString(&buf, ", ");
-			appendStringInfo(&buf, "%s=", quote_identifier(name));
-
-			/*
-			 * In general we need to quote the value; but to avoid unnecessary
-			 * clutter, do not quote if it is an identifier that would not
-			 * need quoting.  (We could also allow numbers, but that is a bit
-			 * trickier than it looks --- for example, are leading zeroes
-			 * significant?  We don't want to assume very much here about what
-			 * custom reloptions might mean.)
-			 */
-			if (quote_identifier(value) == value)
-				appendStringInfoString(&buf, value);
-			else
-				simple_quote_literal(&buf, value);
-
-			pfree(option);
-		}
+		get_reloptions(&buf, reloptions);

 		result = buf.data;
 	}
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -6367,6 +6367,7 @@ gincost_pattern(IndexOptInfo *index, int indexcol,
 				Oid clause_op, Datum query,
 				GinQualCounts *counts)
 {
+	FmgrInfo	flinfo;
 	Oid			extractProcOid;
 	Oid			collation;
 	int			strategy_op;
@@ -6416,15 +6417,19 @@ gincost_pattern(IndexOptInfo *index, int indexcol,
 	else
 		collation = DEFAULT_COLLATION_OID;

-	OidFunctionCall7Coll(extractProcOid,
-						 collation,
-						 query,
-						 PointerGetDatum(&nentries),
-						 UInt16GetDatum(strategy_op),
-						 PointerGetDatum(&partial_matches),
-						 PointerGetDatum(&extra_data),
-						 PointerGetDatum(&nullFlags),
-						 PointerGetDatum(&searchMode));
+	fmgr_info(extractProcOid, &flinfo);
+
+	set_fn_opclass_options(&flinfo, index->opclassoptions[indexcol]);
+
+	FunctionCall7Coll(&flinfo,
+					  collation,
+					  query,
+					  PointerGetDatum(&nentries),
+					  UInt16GetDatum(strategy_op),
+					  PointerGetDatum(&partial_matches),
+					  PointerGetDatum(&extra_data),
+					  PointerGetDatum(&nullFlags),
+					  PointerGetDatum(&searchMode));

 	if (nentries <= 0 && searchMode == GIN_SEARCH_MODE_DEFAULT)
 	{
--- a/src/backend/utils/adt/tsgistidx.c
+++ b/src/backend/utils/adt/tsgistidx.c
@@ -16,6 +16,7 @@

 #include "access/gist.h"
 #include "access/heaptoast.h"
+#include "access/reloptions.h"
 #include "lib/qunique.h"
 #include "port/pg_bitutils.h"
 #include "tsearch/ts_utils.h"
@@ -23,17 +24,25 @@
 #include "utils/pg_crc.h"


-#define SIGLENINT  31			/* >121 => key will toast, so it will not work
-								 * !!! */
+/* tsvector_ops opclass options */
+typedef struct
+{
+	int32		vl_len_;		/* varlena header (do not touch directly!) */
+	int			siglen;			/* signature length */
+} GistTsVectorOptions;

-#define SIGLEN	( sizeof(int32) * SIGLENINT )
-#define SIGLENBIT (SIGLEN * BITS_PER_BYTE)
+#define SIGLEN_DEFAULT	(31 * 4)
+#define SIGLEN_MAX		GISTMaxIndexKeySize
+#define GET_SIGLEN()	(PG_HAS_OPCLASS_OPTIONS() ? \
+						 ((GistTsVectorOptions *) PG_GET_OPCLASS_OPTIONS())->siglen : \
+						 SIGLEN_DEFAULT)
+
+#define SIGLENBIT(siglen) ((siglen) * BITS_PER_BYTE)

-typedef char BITVEC[SIGLEN];
 typedef char *BITVECP;

-#define LOOPBYTE \
-			for(i=0;i<SIGLEN;i++)
+#define LOOPBYTE(siglen) \
+			for (i = 0; i < siglen; i++)

 #define GETBYTE(x,i) ( *( (BITVECP)(x) + (int)( (i) / BITS_PER_BYTE ) ) )
 #define GETBITBYTE(x,i) ( ((char)(x)) >> (i) & 0x01 )
@@ -41,8 +50,8 @@ typedef char *BITVECP;
 #define SETBIT(x,i)   GETBYTE(x,i) |=  ( 0x01 << ( (i) % BITS_PER_BYTE ) )
 #define GETBIT(x,i) ( (GETBYTE(x,i) >> ( (i) % BITS_PER_BYTE )) & 0x01 )

-#define HASHVAL(val) (((unsigned int)(val)) % SIGLENBIT)
-#define HASH(sign, val) SETBIT((sign), HASHVAL(val))
+#define HASHVAL(val, siglen) (((unsigned int)(val)) % SIGLENBIT(siglen))
+#define HASH(sign, val, siglen) SETBIT((sign), HASHVAL(val, siglen))

 #define GETENTRY(vec,pos) ((SignTSVector *) DatumGetPointer((vec)->vector[(pos)].key))

@@ -66,13 +75,14 @@ typedef struct
 #define ISALLTRUE(x)	( ((SignTSVector*)(x))->flag & ALLISTRUE )

 #define GTHDRSIZE	( VARHDRSZ + sizeof(int32) )
-#define CALCGTSIZE(flag, len) ( GTHDRSIZE + ( ( (flag) & ARRKEY ) ? ((len)*sizeof(int32)) : (((flag) & ALLISTRUE) ? 0 : SIGLEN) ) )
+#define CALCGTSIZE(flag, len) ( GTHDRSIZE + ( ( (flag) & ARRKEY ) ? ((len)*sizeof(int32)) : (((flag) & ALLISTRUE) ? 0 : (len)) ) )

 #define GETSIGN(x)	( (BITVECP)( (char*)(x)+GTHDRSIZE ) )
+#define GETSIGLEN(x)( VARSIZE(x) - GTHDRSIZE )
 #define GETARR(x)	( (int32*)( (char*)(x)+GTHDRSIZE ) )
 #define ARRNELEM(x) ( ( VARSIZE(x) - GTHDRSIZE )/sizeof(int32) )

-static int32 sizebitvec(BITVECP sign);
+static int32 sizebitvec(BITVECP sign, int siglen);

 Datum
 gtsvectorin(PG_FUNCTION_ARGS)
@@ -103,9 +113,10 @@ gtsvectorout(PG_FUNCTION_ARGS)
 		sprintf(outbuf, ARROUTSTR, (int) ARRNELEM(key));
 	else
 	{
-		int			cnttrue = (ISALLTRUE(key)) ? SIGLENBIT : sizebitvec(GETSIGN(key));
+		int			siglen = GETSIGLEN(key);
+		int			cnttrue = (ISALLTRUE(key)) ? SIGLENBIT(siglen) : sizebitvec(GETSIGN(key), siglen);

-		sprintf(outbuf, SINGOUTSTR, cnttrue, (int) SIGLENBIT - cnttrue);
+		sprintf(outbuf, SINGOUTSTR, cnttrue, (int) SIGLENBIT(siglen) - cnttrue);
 	}

 	PG_FREE_IF_COPY(key, 0);
@@ -124,36 +135,49 @@ compareint(const void *va, const void *vb)
 }

 static void
-makesign(BITVECP sign, SignTSVector *a)
+makesign(BITVECP sign, SignTSVector *a, int siglen)
 {
 	int32		k,
 				len = ARRNELEM(a);
 	int32	   *ptr = GETARR(a);

-	MemSet((void *) sign, 0, sizeof(BITVEC));
+	MemSet((void *) sign, 0, siglen);
 	for (k = 0; k < len; k++)
-		HASH(sign, ptr[k]);
+		HASH(sign, ptr[k], siglen);
 }

+static SignTSVector *
+gtsvector_alloc(int flag, int len, BITVECP sign)
+{
+	int			size = CALCGTSIZE(flag, len);
+	SignTSVector *res = palloc(size);
+
+	SET_VARSIZE(res, size);
+	res->flag = flag;
+
+	if ((flag & (SIGNKEY | ALLISTRUE)) == SIGNKEY && sign)
+		memcpy(GETSIGN(res), sign, len);
+
+	return res;
+}
+
+
 Datum
 gtsvector_compress(PG_FUNCTION_ARGS)
 {
 	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
+	int			siglen = GET_SIGLEN();
 	GISTENTRY  *retval = entry;

 	if (entry->leafkey)
 	{							/* tsvector */
-		SignTSVector *res;
 		TSVector	val = DatumGetTSVector(entry->key);
+		SignTSVector *res = gtsvector_alloc(ARRKEY, val->size, NULL);
 		int32		len;
 		int32	   *arr;
 		WordEntry  *ptr = ARRPTR(val);
 		char	   *words = STRPTR(val);

-		len = CALCGTSIZE(ARRKEY, val->size);
-		res = (SignTSVector *) palloc(len);
-		SET_VARSIZE(res, len);
-		res->flag = ARRKEY;
 		arr = GETARR(res);
 		len = val->size;
 		while (len--)
@@ -185,13 +209,9 @@ gtsvector_compress(PG_FUNCTION_ARGS)
 		/* make signature, if array is too long */
 		if (VARSIZE(res) > TOAST_INDEX_TARGET)
 		{
-			SignTSVector *ressign;
+			SignTSVector *ressign = gtsvector_alloc(SIGNKEY, siglen, NULL);

-			len = CALCGTSIZE(SIGNKEY, 0);
-			ressign = (SignTSVector *) palloc(len);
-			SET_VARSIZE(ressign, len);
-			ressign->flag = SIGNKEY;
-			makesign(GETSIGN(ressign), res);
+			makesign(GETSIGN(ressign), res, siglen);
 			res = ressign;
 		}

@@ -203,22 +223,17 @@ gtsvector_compress(PG_FUNCTION_ARGS)
 	else if (ISSIGNKEY(DatumGetPointer(entry->key)) &&
 			 !ISALLTRUE(DatumGetPointer(entry->key)))
 	{
-		int32		i,
-					len;
+		int32		i;
 		SignTSVector *res;
 		BITVECP		sign = GETSIGN(DatumGetPointer(entry->key));

-		LOOPBYTE
+		LOOPBYTE(siglen)
 		{
 			if ((sign[i] & 0xff) != 0xff)
 				PG_RETURN_POINTER(retval);
 		}

-		len = CALCGTSIZE(SIGNKEY | ALLISTRUE, 0);
-		res = (SignTSVector *) palloc(len);
-		SET_VARSIZE(res, len);
-		res->flag = SIGNKEY | ALLISTRUE;
-
+		res = gtsvector_alloc(SIGNKEY | ALLISTRUE, siglen, sign);
 		retval = (GISTENTRY *) palloc(sizeof(GISTENTRY));
 		gistentryinit(*retval, PointerGetDatum(res),
 					  entry->rel, entry->page,
@@ -292,12 +307,14 @@ checkcondition_arr(void *checkval, QueryOperand *val, ExecPhraseData *data)
 static bool
 checkcondition_bit(void *checkval, QueryOperand *val, ExecPhraseData *data)
 {
+	void *key = (SignTSVector *) checkval;
+
 	/*
 	 * we are not able to find a prefix in signature tree
 	 */
 	if (val->prefix)
 		return true;
-	return GETBIT(checkval, HASHVAL(val->valcrc));
+	return GETBIT(GETSIGN(key), HASHVAL(val->valcrc, GETSIGLEN(key)));
 }

 Datum
@@ -324,7 +341,7 @@ gtsvector_consistent(PG_FUNCTION_ARGS)

 		/* since signature is lossy, cannot specify CALC_NOT here */
 		PG_RETURN_BOOL(TS_execute(GETQUERY(query),
-								  (void *) GETSIGN(key),
+								  key,
 								  TS_EXEC_PHRASE_NO_POS,
 								  checkcondition_bit));
 	}
@@ -342,7 +359,7 @@ gtsvector_consistent(PG_FUNCTION_ARGS)
 }

 static int32
-unionkey(BITVECP sbase, SignTSVector *add)
+unionkey(BITVECP sbase, SignTSVector *add, int siglen)
 {
 	int32		i;

@@ -353,7 +370,9 @@ unionkey(BITVECP sbase, SignTSVector *add)
 		if (ISALLTRUE(add))
 			return 1;

-		LOOPBYTE
+		Assert(GETSIGLEN(add) == siglen);
+
+		LOOPBYTE(siglen)
 			sbase[i] |= sadd[i];
 	}
 	else
@@ -361,7 +380,7 @@ unionkey(BITVECP sbase, SignTSVector *add)
 		int32	   *ptr = GETARR(add);

 		for (i = 0; i < ARRNELEM(add); i++)
-			HASH(sbase, ptr[i]);
+			HASH(sbase, ptr[i], siglen);
 	}
 	return 0;
 }
@@ -372,30 +391,24 @@ gtsvector_union(PG_FUNCTION_ARGS)
 {
 	GistEntryVector *entryvec = (GistEntryVector *) PG_GETARG_POINTER(0);
 	int		   *size = (int *) PG_GETARG_POINTER(1);
-	BITVEC		base;
-	int32		i,
-				len;
-	int32		flag = 0;
-	SignTSVector *result;
+	int			siglen = GET_SIGLEN();
+	SignTSVector *result = gtsvector_alloc(SIGNKEY, siglen, NULL);
+	BITVECP		base = GETSIGN(result);
+	int32		i;
+
+	memset(base, 0, siglen);

-	MemSet((void *) base, 0, sizeof(BITVEC));
 	for (i = 0; i < entryvec->n; i++)
 	{
-		if (unionkey(base, GETENTRY(entryvec, i)))
+		if (unionkey(base, GETENTRY(entryvec, i), siglen))
 		{
-			flag = ALLISTRUE;
+			result->flag |= ALLISTRUE;
+			SET_VARSIZE(result, CALCGTSIZE(result->flag, siglen));
 			break;
 		}
 	}

-	flag |= SIGNKEY;
-	len = CALCGTSIZE(flag, 0);
-	result = (SignTSVector *) palloc(len);
-	*size = len;
-	SET_VARSIZE(result, len);
-	result->flag = flag;
-	if (!ISALLTRUE(result))
-		memcpy((void *) GETSIGN(result), (void *) base, sizeof(BITVEC));
+	*size = VARSIZE(result);

 	PG_RETURN_POINTER(result);
 }
@@ -406,6 +419,7 @@ gtsvector_same(PG_FUNCTION_ARGS)
 	SignTSVector *a = (SignTSVector *) PG_GETARG_POINTER(0);
 	SignTSVector *b = (SignTSVector *) PG_GETARG_POINTER(1);
 	bool	   *result = (bool *) PG_GETARG_POINTER(2);
+	int			siglen = GET_SIGLEN();

 	if (ISSIGNKEY(a))
 	{							/* then b also ISSIGNKEY */
@@ -421,8 +435,10 @@ gtsvector_same(PG_FUNCTION_ARGS)
 			BITVECP		sa = GETSIGN(a),
 						sb = GETSIGN(b);

+			Assert(GETSIGLEN(a) == siglen && GETSIGLEN(b) == siglen);
+
 			*result = true;
-			LOOPBYTE
+			LOOPBYTE(siglen)
 			{
 				if (sa[i] != sb[i])
 				{
@@ -459,19 +475,19 @@ gtsvector_same(PG_FUNCTION_ARGS)
 }

 static int32
-sizebitvec(BITVECP sign)
+sizebitvec(BITVECP sign, int siglen)
 {
-	return pg_popcount(sign, SIGLEN);
+	return pg_popcount(sign, siglen);
 }

 static int
-hemdistsign(BITVECP a, BITVECP b)
+hemdistsign(BITVECP a, BITVECP b, int siglen)
 {
 	int			i,
 				diff,
 				dist = 0;

-	LOOPBYTE
+	LOOPBYTE(siglen)
 	{
 		diff = (unsigned char) (a[i] ^ b[i]);
 		/* Using the popcount functions here isn't likely to win */
@@ -483,17 +499,22 @@ hemdistsign(BITVECP a, BITVECP b)
 static int
 hemdist(SignTSVector *a, SignTSVector *b)
 {
+	int siglena = GETSIGLEN(a);
+	int siglenb = GETSIGLEN(b);
+
 	if (ISALLTRUE(a))
 	{
 		if (ISALLTRUE(b))
 			return 0;
 		else
-			return SIGLENBIT - sizebitvec(GETSIGN(b));
+			return SIGLENBIT(siglenb) - sizebitvec(GETSIGN(b), siglenb);
 	}
 	else if (ISALLTRUE(b))
-		return SIGLENBIT - sizebitvec(GETSIGN(a));
+		return SIGLENBIT(siglena) - sizebitvec(GETSIGN(a), siglena);

-	return hemdistsign(GETSIGN(a), GETSIGN(b));
+	Assert(siglena == siglenb);
+
+	return hemdistsign(GETSIGN(a), GETSIGN(b), siglena);
 }

 Datum
@@ -502,6 +523,7 @@ gtsvector_penalty(PG_FUNCTION_ARGS)
 	GISTENTRY  *origentry = (GISTENTRY *) PG_GETARG_POINTER(0); /* always ISSIGNKEY */
 	GISTENTRY  *newentry = (GISTENTRY *) PG_GETARG_POINTER(1);
 	float	   *penalty = (float *) PG_GETARG_POINTER(2);
+	int			siglen = GET_SIGLEN();
 	SignTSVector *origval = (SignTSVector *) DatumGetPointer(origentry->key);
 	SignTSVector *newval = (SignTSVector *) DatumGetPointer(newentry->key);
 	BITVECP		orig = GETSIGN(origval);
@@ -510,14 +532,22 @@ gtsvector_penalty(PG_FUNCTION_ARGS)

 	if (ISARRKEY(newval))
 	{
-		BITVEC		sign;
+		BITVECP		sign = palloc(siglen);

-		makesign(sign, newval);
+		makesign(sign, newval, siglen);

 		if (ISALLTRUE(origval))
-			*penalty = ((float) (SIGLENBIT - sizebitvec(sign))) / (float) (SIGLENBIT + 1);
+		{
+			int			siglenbit = SIGLENBIT(siglen);
+
+			*penalty =
+				(float) (siglenbit - sizebitvec(sign, siglen)) /
+				(float) (siglenbit + 1);
+		}
 		else
-			*penalty = hemdistsign(sign, orig);
+			*penalty = hemdistsign(sign, orig, siglen);
+
+		pfree(sign);
 	}
 	else
 		*penalty = hemdist(origval, newval);
@@ -527,19 +557,19 @@ gtsvector_penalty(PG_FUNCTION_ARGS)
 typedef struct
 {
 	bool		allistrue;
-	BITVEC		sign;
+	BITVECP		sign;
 } CACHESIGN;

 static void
-fillcache(CACHESIGN *item, SignTSVector *key)
+fillcache(CACHESIGN *item, SignTSVector *key, int siglen)
 {
 	item->allistrue = false;
 	if (ISARRKEY(key))
-		makesign(item->sign, key);
+		makesign(item->sign, key, siglen);
 	else if (ISALLTRUE(key))
 		item->allistrue = true;
 	else
-		memcpy((void *) item->sign, (void *) GETSIGN(key), sizeof(BITVEC));
+		memcpy((void *) item->sign, (void *) GETSIGN(key), siglen);
 }

 #define WISH_F(a,b,c) (double)( -(double)(((a)-(b))*((a)-(b))*((a)-(b)))*(c) )
@@ -563,19 +593,19 @@ comparecost(const void *va, const void *vb)


 static int
-hemdistcache(CACHESIGN *a, CACHESIGN *b)
+hemdistcache(CACHESIGN *a, CACHESIGN *b, int siglen)
 {
 	if (a->allistrue)
 	{
 		if (b->allistrue)
 			return 0;
 		else
-			return SIGLENBIT - sizebitvec(b->sign);
+			return SIGLENBIT(siglen) - sizebitvec(b->sign, siglen);
 	}
 	else if (b->allistrue)
-		return SIGLENBIT - sizebitvec(a->sign);
+		return SIGLENBIT(siglen) - sizebitvec(a->sign, siglen);

-	return hemdistsign(a->sign, b->sign);
+	return hemdistsign(a->sign, b->sign, siglen);
 }

 Datum
@@ -583,6 +613,7 @@ gtsvector_picksplit(PG_FUNCTION_ARGS)
 {
 	GistEntryVector *entryvec = (GistEntryVector *) PG_GETARG_POINTER(0);
 	GIST_SPLITVEC *v = (GIST_SPLITVEC *) PG_GETARG_POINTER(1);
+	int			siglen = GET_SIGLEN();
 	OffsetNumber k,
 				j;
 	SignTSVector *datum_l,
@@ -602,6 +633,7 @@ gtsvector_picksplit(PG_FUNCTION_ARGS)
 	BITVECP		ptr;
 	int			i;
 	CACHESIGN  *cache;
+	char	   *cache_sign;
 	SPLITCOST  *costvector;

 	maxoff = entryvec->n - 2;
@@ -610,16 +642,22 @@ gtsvector_picksplit(PG_FUNCTION_ARGS)
 	v->spl_right = (OffsetNumber *) palloc(nbytes);

 	cache = (CACHESIGN *) palloc(sizeof(CACHESIGN) * (maxoff + 2));
-	fillcache(&cache[FirstOffsetNumber], GETENTRY(entryvec, FirstOffsetNumber));
+	cache_sign = palloc(siglen * (maxoff + 2));
+
+	for (j = 0; j < maxoff + 2; j++)
+		cache[j].sign = &cache_sign[siglen * j];
+
+	fillcache(&cache[FirstOffsetNumber], GETENTRY(entryvec, FirstOffsetNumber),
+			  siglen);

 	for (k = FirstOffsetNumber; k < maxoff; k = OffsetNumberNext(k))
 	{
 		for (j = OffsetNumberNext(k); j <= maxoff; j = OffsetNumberNext(j))
 		{
 			if (k == FirstOffsetNumber)
-				fillcache(&cache[j], GETENTRY(entryvec, j));
+				fillcache(&cache[j], GETENTRY(entryvec, j), siglen);

-			size_waste = hemdistcache(&(cache[j]), &(cache[k]));
+			size_waste = hemdistcache(&(cache[j]), &(cache[k]), siglen);
 			if (size_waste > waste)
 			{
 				waste = size_waste;
@@ -641,44 +679,21 @@ gtsvector_picksplit(PG_FUNCTION_ARGS)
 	}

 	/* form initial .. */
-	if (cache[seed_1].allistrue)
-	{
-		datum_l = (SignTSVector *) palloc(CALCGTSIZE(SIGNKEY | ALLISTRUE, 0));
-		SET_VARSIZE(datum_l, CALCGTSIZE(SIGNKEY | ALLISTRUE, 0));
-		datum_l->flag = SIGNKEY | ALLISTRUE;
-	}
-	else
-	{
-		datum_l = (SignTSVector *) palloc(CALCGTSIZE(SIGNKEY, 0));
-		SET_VARSIZE(datum_l, CALCGTSIZE(SIGNKEY, 0));
-		datum_l->flag = SIGNKEY;
-		memcpy((void *) GETSIGN(datum_l), (void *) cache[seed_1].sign, sizeof(BITVEC));
-	}
-	if (cache[seed_2].allistrue)
-	{
-		datum_r = (SignTSVector *) palloc(CALCGTSIZE(SIGNKEY | ALLISTRUE, 0));
-		SET_VARSIZE(datum_r, CALCGTSIZE(SIGNKEY | ALLISTRUE, 0));
-		datum_r->flag = SIGNKEY | ALLISTRUE;
-	}
-	else
-	{
-		datum_r = (SignTSVector *) palloc(CALCGTSIZE(SIGNKEY, 0));
-		SET_VARSIZE(datum_r, CALCGTSIZE(SIGNKEY, 0));
-		datum_r->flag = SIGNKEY;
-		memcpy((void *) GETSIGN(datum_r), (void *) cache[seed_2].sign, sizeof(BITVEC));
-	}
-
+	datum_l = gtsvector_alloc(SIGNKEY | (cache[seed_1].allistrue ? ALLISTRUE : 0),
+							  siglen, cache[seed_1].sign);
+	datum_r = gtsvector_alloc(SIGNKEY | (cache[seed_2].allistrue ? ALLISTRUE : 0),
+							  siglen, cache[seed_2].sign);
 	union_l = GETSIGN(datum_l);
 	union_r = GETSIGN(datum_r);
 	maxoff = OffsetNumberNext(maxoff);
-	fillcache(&cache[maxoff], GETENTRY(entryvec, maxoff));
+	fillcache(&cache[maxoff], GETENTRY(entryvec, maxoff), siglen);
 	/* sort before ... */
 	costvector = (SPLITCOST *) palloc(sizeof(SPLITCOST) * maxoff);
 	for (j = FirstOffsetNumber; j <= maxoff; j = OffsetNumberNext(j))
 	{
 		costvector[j - 1].pos = j;
-		size_alpha = hemdistcache(&(cache[seed_1]), &(cache[j]));
-		size_beta = hemdistcache(&(cache[seed_2]), &(cache[j]));
+		size_alpha = hemdistcache(&(cache[seed_1]), &(cache[j]), siglen);
+		size_beta = hemdistcache(&(cache[seed_2]), &(cache[j]), siglen);
 		costvector[j - 1].cost = Abs(size_alpha - size_beta);
 	}
 	qsort((void *) costvector, maxoff, sizeof(SPLITCOST), comparecost);
@@ -704,36 +719,40 @@ gtsvector_picksplit(PG_FUNCTION_ARGS)
 			if (ISALLTRUE(datum_l) && cache[j].allistrue)
 				size_alpha = 0;
 			else
-				size_alpha = SIGLENBIT - sizebitvec((cache[j].allistrue) ?
-													GETSIGN(datum_l) :
-													GETSIGN(cache[j].sign));
+				size_alpha = SIGLENBIT(siglen) -
+					sizebitvec((cache[j].allistrue) ?
+								GETSIGN(datum_l) :
+								GETSIGN(cache[j].sign),
+								siglen);
 		}
 		else
-			size_alpha = hemdistsign(cache[j].sign, GETSIGN(datum_l));
+			size_alpha = hemdistsign(cache[j].sign, GETSIGN(datum_l), siglen);

 		if (ISALLTRUE(datum_r) || cache[j].allistrue)
 		{
 			if (ISALLTRUE(datum_r) && cache[j].allistrue)
 				size_beta = 0;
 			else
-				size_beta = SIGLENBIT - sizebitvec((cache[j].allistrue) ?
-												   GETSIGN(datum_r) :
-												   GETSIGN(cache[j].sign));
+				size_beta = SIGLENBIT(siglen) -
+					sizebitvec((cache[j].allistrue) ?
+							   GETSIGN(datum_r) :
+							   GETSIGN(cache[j].sign),
+							   siglen);
 		}
 		else
-			size_beta = hemdistsign(cache[j].sign, GETSIGN(datum_r));
+			size_beta = hemdistsign(cache[j].sign, GETSIGN(datum_r), siglen);

 		if (size_alpha < size_beta + WISH_F(v->spl_nleft, v->spl_nright, 0.1))
 		{
 			if (ISALLTRUE(datum_l) || cache[j].allistrue)
 			{
 				if (!ISALLTRUE(datum_l))
-					MemSet((void *) GETSIGN(datum_l), 0xff, sizeof(BITVEC));
+					MemSet((void *) GETSIGN(datum_l), 0xff, siglen);
 			}
 			else
 			{
 				ptr = cache[j].sign;
-				LOOPBYTE
+				LOOPBYTE(siglen)
 					union_l[i] |= ptr[i];
 			}
 			*left++ = j;
@@ -744,12 +763,12 @@ gtsvector_picksplit(PG_FUNCTION_ARGS)
 			if (ISALLTRUE(datum_r) || cache[j].allistrue)
 			{
 				if (!ISALLTRUE(datum_r))
-					MemSet((void *) GETSIGN(datum_r), 0xff, sizeof(BITVEC));
+					MemSet((void *) GETSIGN(datum_r), 0xff, siglen);
 			}
 			else
 			{
 				ptr = cache[j].sign;
-				LOOPBYTE
+				LOOPBYTE(siglen)
 					union_r[i] |= ptr[i];
 			}
 			*right++ = j;
@@ -776,3 +795,16 @@ gtsvector_consistent_oldsig(PG_FUNCTION_ARGS)
 {
 	return gtsvector_consistent(fcinfo);
 }
+
+Datum
+gtsvector_options(PG_FUNCTION_ARGS)
+{
+	local_relopts *relopts = (local_relopts *) PG_GETARG_POINTER(0);
+
+	init_local_reloptions(relopts, sizeof(GistTsVectorOptions));
+	add_local_int_reloption(relopts, "siglen", "signature length",
+							SIGLEN_DEFAULT, 1, SIGLEN_MAX,
+							offsetof(GistTsVectorOptions, siglen));
+
+	PG_RETURN_VOID();
+}
--- a/src/backend/utils/cache/lsyscache.c
+++ b/src/backend/utils/cache/lsyscache.c
@@ -909,6 +909,41 @@ get_atttypetypmodcoll(Oid relid, AttrNumber attnum,
 	ReleaseSysCache(tp);
 }

+/*
+ * get_attoptions
+ *
+ *		Given the relation id and the attribute number,
+ *		return the attribute options text[] datum, if any.
+ */
+Datum
+get_attoptions(Oid relid, int16 attnum)
+{
+	HeapTuple	tuple;
+	Datum		attopts;
+	Datum		result;
+	bool		isnull;
+
+	tuple = SearchSysCache2(ATTNUM,
+							ObjectIdGetDatum(relid),
+							Int16GetDatum(attnum));
+
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for attribute %d of relation %u",
+			 attnum, relid);
+
+	attopts = SysCacheGetAttr(ATTNAME, tuple, Anum_pg_attribute_attoptions,
+							  &isnull);
+
+	if (isnull)
+		result = (Datum) 0;
+	else
+		result = datumCopy(attopts, false, -1);		/* text[] */
+
+	ReleaseSysCache(tuple);
+
+	return result;
+}
+
 /*				---------- PG_CAST CACHE ----------					 */

 /*
--- a/src/backend/utils/cache/relcache.c
+++ b/src/backend/utils/cache/relcache.c
@@ -1426,7 +1426,7 @@ RelationInitIndexAccessInfo(Relation relation)
 	amsupport = relation->rd_indam->amsupport;
 	if (amsupport > 0)
 	{
-		int			nsupport = indnatts * amsupport;
+		int			nsupport = indnatts * (amsupport + 1);

 		relation->rd_support = (RegProcedure *)
 			MemoryContextAllocZero(indexcxt, nsupport * sizeof(RegProcedure));
@@ -1490,6 +1490,8 @@ RelationInitIndexAccessInfo(Relation relation)
 	indoption = (int2vector *) DatumGetPointer(indoptionDatum);
 	memcpy(relation->rd_indoption, indoption->values, indnkeyatts * sizeof(int16));

+	(void) RelationGetIndexAttOptions(relation, false);
+
 	/*
 	 * expressions, predicate, exclusion caches will be filled later
 	 */
@@ -1539,9 +1541,9 @@ IndexSupportInitialize(oidvector *indclass,
 		opFamily[attIndex] = opcentry->opcfamily;
 		opcInType[attIndex] = opcentry->opcintype;
 		if (maxSupportNumber > 0)
-			memcpy(&indexSupport[attIndex * maxSupportNumber],
+			memcpy(&indexSupport[attIndex * (maxSupportNumber + 1)],
 				   opcentry->supportProcs,
-				   maxSupportNumber * sizeof(RegProcedure));
+				   (maxSupportNumber + 1) * sizeof(RegProcedure));
 	}
 }

@@ -1606,7 +1608,7 @@ LookupOpclassInfo(Oid operatorClassOid,
 		if (numSupport > 0)
 			opcentry->supportProcs = (RegProcedure *)
 				MemoryContextAllocZero(CacheMemoryContext,
-									   numSupport * sizeof(RegProcedure));
+									   (numSupport + 1) * sizeof(RegProcedure));
 		else
 			opcentry->supportProcs = NULL;
 	}
@@ -1693,13 +1695,12 @@ LookupOpclassInfo(Oid operatorClassOid,
 		{
 			Form_pg_amproc amprocform = (Form_pg_amproc) GETSTRUCT(htup);

-			if (amprocform->amprocnum <= 0 ||
+			if (amprocform->amprocnum < 0 ||
 				(StrategyNumber) amprocform->amprocnum > numSupport)
 				elog(ERROR, "invalid amproc number %d for opclass %u",
 					 amprocform->amprocnum, operatorClassOid);

-			opcentry->supportProcs[amprocform->amprocnum - 1] =
-				amprocform->amproc;
+			opcentry->supportProcs[amprocform->amprocnum] = amprocform->amproc;
 		}

 		systable_endscan(scan);
@@ -3980,6 +3981,8 @@ load_critical_index(Oid indexoid, Oid heapoid)
 	ird->rd_refcnt = 1;
 	UnlockRelationOid(indexoid, AccessShareLock);
 	UnlockRelationOid(heapoid, AccessShareLock);
+
+	(void) RelationGetIndexAttOptions(ird, false);
 }

 /*
@@ -5185,6 +5188,100 @@ GetRelationPublicationActions(Relation relation)
 	return pubactions;
 }

+/*
+ * RelationGetIndexRawAttOptions -- get AM/opclass-specific options for the index
+ */
+Datum *
+RelationGetIndexRawAttOptions(Relation indexrel)
+{
+	Oid			indexrelid = RelationGetRelid(indexrel);
+	int16		natts = RelationGetNumberOfAttributes(indexrel);
+	Datum	   *options = NULL;
+	int16		attnum;
+
+	for (attnum = 1; attnum <= natts; attnum++)
+	{
+		if (!OidIsValid(index_getprocid(indexrel, attnum,
+										indexrel->rd_indam->amoptsprocnum)))
+			continue;
+
+		if (!options)
+			options = palloc0(sizeof(Datum) * natts);
+
+		options[attnum - 1] = get_attoptions(indexrelid, attnum);
+	}
+
+	return options;
+}
+
+static bytea **
+CopyIndexAttOptions(bytea **srcopts, int natts)
+{
+	bytea	  **opts = palloc(sizeof(*opts) * natts);
+
+	for (int i = 0; i < natts; i++)
+	{
+		bytea	   *opt = srcopts[i];
+
+		opts[i] = !opt ? NULL : (bytea *)
+			DatumGetPointer(datumCopy(PointerGetDatum(opt), false, -1));
+	}
+
+	return opts;
+}
+
+/*
+ * RelationGetIndexAttOptions
+ *		get AM/opclass-specific options for an index parsed into a binary form
+ */
+bytea **
+RelationGetIndexAttOptions(Relation relation, bool copy)
+{
+	MemoryContext oldcxt;
+	bytea	  **opts = relation->rd_opcoptions;
+	Oid			relid = RelationGetRelid(relation);
+	int			natts = RelationGetNumberOfAttributes(relation);	/* XXX IndexRelationGetNumberOfKeyAttributes */
+	int			i;
+
+	/* Try to copy cached options. */
+	if (opts)
+		return copy ? CopyIndexAttOptions(opts, natts) : opts;
+
+	/* Get and parse opclass options. */
+	opts = palloc0(sizeof(*opts) * natts);
+
+	for (i = 0; i < natts; i++)
+	{
+		if (criticalRelcachesBuilt && relid != AttributeRelidNumIndexId)
+		{
+			Datum		attoptions = get_attoptions(relid, i + 1);
+
+			opts[i] = index_opclass_options(relation, i + 1, attoptions, false);
+
+			if (attoptions != (Datum) 0)
+				pfree(DatumGetPointer(attoptions));
+		}
+	}
+
+	/* Copy parsed options to the cache. */
+	oldcxt = MemoryContextSwitchTo(relation->rd_indexcxt);
+	relation->rd_opcoptions = CopyIndexAttOptions(opts, natts);
+	MemoryContextSwitchTo(oldcxt);
+
+	if (copy)
+		return opts;
+
+	for (i = 0; i < natts; i++)
+	{
+		if (opts[i])
+			pfree(opts[i]);
+	}
+
+	pfree(opts);
+
+	return relation->rd_opcoptions;
+}
+
 /*
 * Routines to support ereport() reports of relation-related errors
 *
@@ -5546,8 +5643,25 @@ load_relcache_init_file(bool shared)

 			rel->rd_indoption = indoption;

+			/* finally, read the vector of opcoptions values */
+			rel->rd_opcoptions = (bytea **)
+				MemoryContextAllocZero(indexcxt, sizeof(*rel->rd_opcoptions) * relform->relnatts);
+
+			for (i = 0; i < relform->relnatts; i++)
+			{
+				if (fread(&len, 1, sizeof(len), fp) != sizeof(len))
+					goto read_failed;
+
+				if (len > 0)
+				{
+					rel->rd_opcoptions[i] = (bytea *) MemoryContextAlloc(indexcxt, len);
+					if (fread(rel->rd_opcoptions[i], 1, len, fp) != len)
+						goto read_failed;
+				}
+			}
+
 			/* set up zeroed fmgr-info vector */
-			nsupport = relform->relnatts * rel->rd_indam->amsupport;
+			nsupport = relform->relnatts * (rel->rd_indam->amsupport + 1);
 			rel->rd_supportinfo = (FmgrInfo *)
 				MemoryContextAllocZero(indexcxt, nsupport * sizeof(FmgrInfo));
 		}
@@ -5574,6 +5688,7 @@ load_relcache_init_file(bool shared)
 			Assert(rel->rd_supportinfo == NULL);
 			Assert(rel->rd_indoption == NULL);
 			Assert(rel->rd_indcollation == NULL);
+			Assert(rel->rd_opcoptions == NULL);
 		}

 		/*
@@ -5847,7 +5962,7 @@ write_relcache_init_file(bool shared)

 			/* next, write the vector of support procedure OIDs */
 			write_item(rel->rd_support,
-					   relform->relnatts * (rel->rd_indam->amsupport * sizeof(RegProcedure)),
+					   relform->relnatts * ((rel->rd_indam->amsupport + 1) * sizeof(RegProcedure)),
 					   fp);

 			/* next, write the vector of collation OIDs */
@@ -5859,6 +5974,16 @@ write_relcache_init_file(bool shared)
 			write_item(rel->rd_indoption,
 					   relform->relnatts * sizeof(int16),
 					   fp);
+
+			Assert(rel->rd_opcoptions);
+
+			/* finally, write the vector of opcoptions values */
+			for (i = 0; i < relform->relnatts; i++)
+			{
+				bytea	   *opt = rel->rd_opcoptions[i];
+
+				write_item(opt, opt ? VARSIZE(opt) : 0, fp);
+			}
 		}
 	}

--- a/src/backend/utils/fmgr/fmgr.c
+++ b/src/backend/utils/fmgr/fmgr.c
@@ -18,9 +18,11 @@
 #include "access/detoast.h"
 #include "catalog/pg_language.h"
 #include "catalog/pg_proc.h"
+#include "catalog/pg_type.h"
 #include "executor/functions.h"
 #include "lib/stringinfo.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "pgstat.h"
 #include "utils/acl.h"
@@ -1952,6 +1954,57 @@ get_fn_expr_variadic(FmgrInfo *flinfo)
 		return false;
 }

+/*
+ * Set options to FmgrInfo of opclass support function.
+ *
+ * Opclass support functions are called outside of expressions.  Thanks to that
+ * we can use fn_expr to store opclass options as bytea constant.
+ */
+void
+set_fn_opclass_options(FmgrInfo *flinfo, bytea *options)
+{
+	flinfo->fn_expr = (Node *) makeConst(BYTEAOID, -1, InvalidOid, -1,
+										 PointerGetDatum(options),
+										 options == NULL, false);
+}
+
+/*
+ * Check if options are defined for opclass support function.
+ */
+bool
+has_fn_opclass_options(FmgrInfo *flinfo)
+{
+	if (flinfo && flinfo->fn_expr && IsA(flinfo->fn_expr, Const))
+	{
+		Const	   *expr = (Const *) flinfo->fn_expr;
+
+		if (expr->consttype == BYTEAOID)
+			return !expr->constisnull;
+	}
+	return false;
+}
+
+/*
+ * Get options for opclass support function.
+ */
+bytea *
+get_fn_opclass_options(FmgrInfo *flinfo)
+{
+	if (flinfo && flinfo->fn_expr && IsA(flinfo->fn_expr, Const))
+	{
+		Const	   *expr = (Const *) flinfo->fn_expr;
+
+		if (expr->consttype == BYTEAOID)
+			return expr->constisnull ? NULL : DatumGetByteaP(expr->constvalue);
+	}
+
+	ereport(ERROR,
+			(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+			 errmsg("opclass options info is absent in function call context")));
+
+	return NULL;
+}
+
 /*-------------------------------------------------------------------------
 *		Support routines for procedural language implementations
 *-------------------------------------------------------------------------