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

1 files changed, 86 insertions, 49 deletions

diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c
index 5e63238f030..f6cf7e72a1e 100644
--- 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)
@@ -10574,6 +10585,23 @@ get_opclass_name(Oid opclass, Oid actual_datatype,
 }
 
 /*
+ * 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
  *
  * We strip any top-level FieldStore or assignment SubscriptingRef nodes that
@@ -11251,6 +11279,62 @@ string_to_text(char *str)
 }
 
 /*
+ * 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.
  */
 static char *
@@ -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;
 	}