Add prefix operator for TEXT type.

The prefix operator along with SP-GiST indexes can be used as an alternative
for LIKE 'word%' commands  and it doesn't have a limitation of string/prefix
length as B-Tree has.

Bump catalog version

Author: Ildus Kurbangaliev with some editorization by me
Review by: Arthur Zakirov, Alexander Korotkov, and me
Discussion: https://www.postgresql.org/message-id/flat/20180202180327.222b04b3@wp.localdomain

3 files changed, 100 insertions, 4 deletions

diff --git a/src/backend/access/spgist/spgtextproc.c b/src/backend/access/spgist/spgtextproc.c
index f156b2166e6..76c0305695b 100644
--- a/src/backend/access/spgist/spgtextproc.c
+++ b/src/backend/access/spgist/spgtextproc.c
@@ -67,6 +67,20 @@
  */
 #define SPGIST_MAX_PREFIX_LENGTH	Max((int) (BLCKSZ - 258 * 16 - 100), 32)
 
+/*
+ * Strategy for collation aware operator on text is equal to btree strategy
+ * plus value of 10.
+ *
+ * Current collation aware strategies and their corresponding btree strategies:
+ * 11 BTLessStrategyNumber
+ * 12 BTLessEqualStrategyNumber
+ * 14 BTGreaterEqualStrategyNumber
+ * 15 BTGreaterStrategyNumber
+ */
+#define SPG_STRATEGY_ADDITION	(10)
+#define SPG_IS_COLLATION_AWARE_STRATEGY(s) ((s) > SPG_STRATEGY_ADDITION \
+										 && (s) != RTPrefixStrategyNumber)
+
 /* Struct for sorting values in picksplit */
 typedef struct spgNodePtr
 {
@@ -496,10 +510,10 @@ spg_text_inner_consistent(PG_FUNCTION_ARGS)
 			 * well end with a partial multibyte character, so that applying
 			 * any encoding-sensitive test to it would be risky anyhow.)
 			 */
-			if (strategy > 10)
+			if (SPG_IS_COLLATION_AWARE_STRATEGY(strategy))
 			{
 				if (collate_is_c)
-					strategy -= 10;
+					strategy -= SPG_STRATEGY_ADDITION;
 				else
 					continue;
 			}
@@ -526,6 +540,10 @@ spg_text_inner_consistent(PG_FUNCTION_ARGS)
 					if (r < 0)
 						res = false;
 					break;
+				case RTPrefixStrategyNumber:
+					if (r != 0)
+						res = false;
+					break;
 				default:
 					elog(ERROR, "unrecognized strategy number: %d",
 						 in->scankeys[j].sk_strategy);
@@ -605,10 +623,27 @@ spg_text_leaf_consistent(PG_FUNCTION_ARGS)
 		int			queryLen = VARSIZE_ANY_EXHDR(query);
 		int			r;
 
-		if (strategy > 10)
+		if (strategy == RTPrefixStrategyNumber)
+		{
+			/*
+			 * if level >= length of query then reconstrValue is began with
+			 * query (prefix) string and we don't need to check it again.
+			 */
+
+			res = (level >= queryLen) ||
+					DatumGetBool(DirectFunctionCall2(text_starts_with,
+								 out->leafValue, PointerGetDatum(query)));
+
+			if (!res) /* no need to consider remaining conditions */
+				break;
+
+			continue;
+		}
+
+		if (SPG_IS_COLLATION_AWARE_STRATEGY(strategy))
 		{
 			/* Collation-aware comparison */
-			strategy -= 10;
+			strategy -= SPG_STRATEGY_ADDITION;
 
 			/* If asserts enabled, verify encoding of reconstructed string */
 			Assert(pg_verifymbstr(fullValue, fullLen, false));
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index bf240aa9c5a..f998d859c1c 100644
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -1488,6 +1488,16 @@ likesel(PG_FUNCTION_ARGS)
 }
 
 /*
+ *		prefixsel			- selectivity of prefix operator
+ */
+Datum
+prefixsel(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Prefix, false));
+}
+
+/*
+ *
  *		iclikesel			- Selectivity of ILIKE pattern match.
  */
 Datum
@@ -2907,6 +2917,15 @@ likejoinsel(PG_FUNCTION_ARGS)
 }
 
 /*
+ *		prefixjoinsel			- Join selectivity of prefix operator
+ */
+Datum
+prefixjoinsel(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Prefix, false));
+}
+
+/*
  *		iclikejoinsel			- Join selectivity of ILIKE pattern match.
  */
 Datum
@@ -5947,6 +5966,20 @@ pattern_fixed_prefix(Const *patt, Pattern_Type ptype, Oid collation,
 			result = regex_fixed_prefix(patt, true, collation,
 										prefix, rest_selec);
 			break;
+		case Pattern_Type_Prefix:
+			/* Prefix type work is trivial.  */
+			result = Pattern_Prefix_Partial;
+			*rest_selec = 1.0;	/* all */
+			*prefix = makeConst(patt->consttype,
+								patt->consttypmod,
+								patt->constcollid,
+								patt->constlen,
+								datumCopy(patt->constvalue,
+										  patt->constbyval,
+										  patt->constlen),
+								patt->constisnull,
+								patt->constbyval);
+			break;
 		default:
 			elog(ERROR, "unrecognized ptype: %d", (int) ptype);
 			result = Pattern_Prefix_None;	/* keep compiler quiet */
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 4346410d5a9..e8500b274dc 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -1762,6 +1762,34 @@ text_ge(PG_FUNCTION_ARGS)
 }
 
 Datum
+text_starts_with(PG_FUNCTION_ARGS)
+{
+	Datum		arg1 = PG_GETARG_DATUM(0);
+	Datum		arg2 = PG_GETARG_DATUM(1);
+	bool		result;
+	Size		len1,
+				len2;
+
+	len1 = toast_raw_datum_size(arg1);
+	len2 = toast_raw_datum_size(arg2);
+	if (len2 > len1)
+		result = false;
+	else
+	{
+		text	   *targ1 = DatumGetTextPP(arg1);
+		text	   *targ2 = DatumGetTextPP(arg2);
+
+		result = (memcmp(VARDATA_ANY(targ1), VARDATA_ANY(targ2),
+						 VARSIZE_ANY_EXHDR(targ2)) == 0);
+
+		PG_FREE_IF_COPY(targ1, 0);
+		PG_FREE_IF_COPY(targ2, 1);
+	}
+
+	PG_RETURN_BOOL(result);
+}
+
+Datum
 bttextcmp(PG_FUNCTION_ARGS)
 {
 	text	   *arg1 = PG_GETARG_TEXT_PP(0);