Allow to omit boundaries in array subscript

Allow to omiy lower or upper or both boundaries in array subscript
for selecting slice of array.

Author: YUriy Zhuravlev

doc/src/sgml/array.sgml

@@ -255,6 +255,26 @@ SELECT schedule[1:2][1:1] FROM sal_emp WHERE name = 'Bill';
 ------------------------
  {{meeting},{training}}
 (1 row)
+</programlisting>
+
+  Possible to skip the <literal><replaceable>lower-bound</replaceable></literal> or
+  <literal><replaceable>upper-bound</replaceable></literal>
+  for get first or last element in slice.
+
+<programlisting>
+SELECT schedule[:][:] FROM sal_emp WHERE name = 'Bill';
+
+        schedule
+------------------------
+ {{meeting,lunch},{training,presentation}}
+(1 row)
+
+SELECT schedule[:2][2:] FROM sal_emp WHERE name = 'Bill';
+
+        schedule
+------------------------
+ {{lunch},{presentation}}
+(1 row)
 </programlisting>
 
   If any dimension is written as a slice, i.e., contains a colon, then all

src/backend/executor/execQual.c

@@ -268,10 +268,12 @@ ExecEvalArrayRef(ArrayRefExprState *astate,
 	bool		eisnull;
 	ListCell   *l;
 	int			i = 0,
-				j = 0;
+				j = 0,
+				indexexpr;
 	IntArray	upper,
 				lower;
 	int		   *lIndex;
+	AnyArrayType *arrays;
 
 	array_source = ExecEvalExpr(astate->refexpr,
 								econtext,
@@ -293,6 +295,7 @@ ExecEvalArrayRef(ArrayRefExprState *astate,
 	foreach(l, astate->refupperindexpr)
 	{
 		ExprState  *eltstate = (ExprState *) lfirst(l);
+		eisnull = false;
 
 		if (i >= MAXDIM)
 			ereport(ERROR,
@@ -300,10 +303,23 @@ ExecEvalArrayRef(ArrayRefExprState *astate,
 					 errmsg("number of array dimensions (%d) exceeds the maximum allowed (%d)",
 							i + 1, MAXDIM)));
 
-		upper.indx[i++] = DatumGetInt32(ExecEvalExpr(eltstate,
-													 econtext,
-													 &eisnull,
-													 NULL));
+		if (eltstate == NULL && astate->refattrlength <= 0)
+		{
+			if (isAssignment)
+				ereport(ERROR,
+					(errcode(ERRCODE_ARRAY_SUBSCRIPT_ERROR),
+					 errmsg("cannot determine upper index for empty array")));
+			arrays = (AnyArrayType *)DatumGetArrayTypeP(array_source);
+			indexexpr = AARR_LBOUND(arrays)[i] + AARR_DIMS(arrays)[i] - 1;
+		}
+		else
+			indexexpr = DatumGetInt32(ExecEvalExpr(eltstate,
+												   econtext,
+												   &eisnull,
+												   NULL));
+
+		upper.indx[i++] = indexexpr;
+
 		/* If any index expr yields NULL, result is NULL or error */
 		if (eisnull)
 		{
@@ -321,6 +337,7 @@ ExecEvalArrayRef(ArrayRefExprState *astate,
 		foreach(l, astate->reflowerindexpr)
 		{
 			ExprState  *eltstate = (ExprState *) lfirst(l);
+			eisnull = false;
 
 			if (j >= MAXDIM)
 				ereport(ERROR,
@@ -328,10 +345,19 @@ ExecEvalArrayRef(ArrayRefExprState *astate,
 						 errmsg("number of array dimensions (%d) exceeds the maximum allowed (%d)",
 								j + 1, MAXDIM)));
 
-			lower.indx[j++] = DatumGetInt32(ExecEvalExpr(eltstate,
-														 econtext,
-														 &eisnull,
-														 NULL));
+			if (eltstate == NULL)
+			{
+				arrays = (AnyArrayType *)DatumGetArrayTypeP(array_source);
+				indexexpr = AARR_LBOUND(arrays)[j];
+			}
+			else
+				indexexpr = DatumGetInt32(ExecEvalExpr(eltstate,
+													   econtext,
+													   &eisnull,
+													   NULL));
+
+			lower.indx[j++] = indexexpr;
+
 			/* If any index expr yields NULL, result is NULL or error */
 			if (eisnull)
 			{

src/backend/nodes/copyfuncs.c

@@ -2403,6 +2403,8 @@ _copyAIndices(const A_Indices *from)
 
 	COPY_NODE_FIELD(lidx);
 	COPY_NODE_FIELD(uidx);
+	COPY_SCALAR_FIELD(lidx_default);
+	COPY_SCALAR_FIELD(uidx_default);
 
 	return newnode;
 }

src/backend/nodes/equalfuncs.c

@@ -2153,6 +2153,8 @@ _equalAIndices(const A_Indices *a, const A_Indices *b)
 {
 	COMPARE_NODE_FIELD(lidx);
 	COMPARE_NODE_FIELD(uidx);
+	COMPARE_SCALAR_FIELD(lidx_default);
+	COMPARE_SCALAR_FIELD(uidx_default);
 
 	return true;
 }

src/backend/nodes/outfuncs.c

@@ -2765,6 +2765,8 @@ _outA_Indices(StringInfo str, const A_Indices *node)
 
 	WRITE_NODE_FIELD(lidx);
 	WRITE_NODE_FIELD(uidx);
+	WRITE_BOOL_FIELD(lidx_default);
+	WRITE_BOOL_FIELD(uidx_default);
 }
 
 static void

src/backend/parser/gram.y

@@ -13193,6 +13193,35 @@ indirection_el:
 					A_Indices *ai = makeNode(A_Indices);
 					ai->lidx = NULL;
 					ai->uidx = $2;
+					ai->lidx_default = false;
+					ai->uidx_default = false;
+					$$ = (Node *) ai;
+				}
+			| '[' ':' ']'
+				{
+					A_Indices *ai = makeNode(A_Indices);
+					ai->lidx = NULL;
+					ai->uidx = NULL;
+					ai->lidx_default = true;
+					ai->uidx_default = true;
+					$$ = (Node *) ai;
+				}
+			| '[' ':' a_expr ']'
+				{
+					A_Indices *ai = makeNode(A_Indices);
+					ai->lidx = NULL;
+					ai->uidx = $3;
+					ai->lidx_default = true;
+					ai->uidx_default = false;
+					$$ = (Node *) ai;
+				}
+			| '[' a_expr ':' ']'
+				{
+					A_Indices *ai = makeNode(A_Indices);
+					ai->lidx = $2;
+					ai->uidx = NULL;
+					ai->lidx_default = false;
+					ai->uidx_default = true;
 					$$ = (Node *) ai;
 				}
 			| '[' a_expr ':' a_expr ']'
@@ -13200,6 +13229,8 @@ indirection_el:
 					A_Indices *ai = makeNode(A_Indices);
 					ai->lidx = $2;
 					ai->uidx = $4;
+					ai->lidx_default = false;
+					ai->uidx_default = false;
 					$$ = (Node *) ai;
 				}
 		;

src/backend/parser/parse_node.c

@@ -311,7 +311,7 @@ transformArraySubscripts(ParseState *pstate,
 		elementType = transformArrayType(&arrayType, &arrayTypMod);
 
 	/*
-	 * A list containing only single subscripts refers to a single array
+	 * A list containing only single subscripts (uidx) refers to a single array
 	 * element.  If any of the items are double subscripts (lower:upper), then
 	 * the subscript expression means an array slice operation. In this case,
 	 * we supply a default lower bound of 1 for any items that contain only a
@@ -322,7 +322,7 @@ transformArraySubscripts(ParseState *pstate,
 	{
 		A_Indices  *ai = (A_Indices *) lfirst(idx);
 
-		if (ai->lidx != NULL)
+		if (ai->lidx != NULL || ai->lidx_default)
 		{
 			isSlice = true;
 			break;
@@ -335,9 +335,17 @@ transformArraySubscripts(ParseState *pstate,
 	foreach(idx, indirection)
 	{
 		A_Indices  *ai = (A_Indices *) lfirst(idx);
-		Node	   *subexpr;
+		Node	   *subexpr = NULL;
 
 		Assert(IsA(ai, A_Indices));
+		if ((ai->uidx_default || ai->lidx_default) && assignFrom != NULL)
+			ereport(ERROR,
+					(errcode(ERRCODE_ARRAY_SUBSCRIPT_ERROR),
+					 errmsg("array subscript must have both boundaries"),
+					 errhint("You can't omit the upper or lower"
+							 " boundaries when updating or inserting"),
+					 parser_errposition(pstate, exprLocation(arrayBase))));
+
 		if (isSlice)
 		{
 			if (ai->lidx)
@@ -356,7 +364,7 @@ transformArraySubscripts(ParseState *pstate,
 							 errmsg("array subscript must have type integer"),
 						parser_errposition(pstate, exprLocation(ai->lidx))));
 			}
-			else
+			else if (ai->lidx_default == false)
 			{
 				/* Make a constant 1 */
 				subexpr = (Node *) makeConst(INT4OID,
@@ -369,19 +377,26 @@ transformArraySubscripts(ParseState *pstate,
 			}
 			lowerIndexpr = lappend(lowerIndexpr, subexpr);
 		}
-		subexpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind);
-		/* If it's not int4 already, try to coerce */
-		subexpr = coerce_to_target_type(pstate,
-										subexpr, exprType(subexpr),
-										INT4OID, -1,
-										COERCION_ASSIGNMENT,
-										COERCE_IMPLICIT_CAST,
-										-1);
-		if (subexpr == NULL)
-			ereport(ERROR,
-					(errcode(ERRCODE_DATATYPE_MISMATCH),
-					 errmsg("array subscript must have type integer"),
-					 parser_errposition(pstate, exprLocation(ai->uidx))));
+
+		if (ai->uidx_default == false)
+		{
+			subexpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind);
+			/* If it's not int4 already, try to coerce */
+			subexpr = coerce_to_target_type(pstate,
+											subexpr, exprType(subexpr),
+											INT4OID, -1,
+											COERCION_ASSIGNMENT,
+											COERCE_IMPLICIT_CAST,
+											-1);
+			if (subexpr == NULL)
+				ereport(ERROR,
+						(errcode(ERRCODE_DATATYPE_MISMATCH),
+						 errmsg("array subscript must have type integer"),
+						 parser_errposition(pstate, exprLocation(ai->uidx))));
+		}
+		else
+			subexpr = NULL;
+
 		upperIndexpr = lappend(upperIndexpr, subexpr);
 	}
 

src/backend/parser/parse_target.c

@@ -650,7 +650,7 @@ transformAssignmentIndirection(ParseState *pstate,
 		if (IsA(n, A_Indices))
 		{
 			subscripts = lappend(subscripts, n);
-			if (((A_Indices *) n)->lidx != NULL)
+			if (((A_Indices *) n)->lidx != NULL || ((A_Indices *) n)->lidx_default)
 				isSlice = true;
 		}
 		else if (IsA(n, A_Star))

src/include/nodes/parsenodes.h

@@ -358,6 +358,8 @@ typedef struct A_Indices
 	NodeTag		type;
 	Node	   *lidx;			/* NULL if it's a single subscript */
 	Node	   *uidx;
+	bool		lidx_default;
+	bool		uidx_default;
 } A_Indices;
 
 /*

src/test/regress/expected/arrays.out

@@ -2031,3 +2031,43 @@ SELECT width_bucket(5, ARRAY[3, 4, NULL]);
 ERROR:  thresholds array must not contain NULLs
 SELECT width_bucket(5, ARRAY[ARRAY[1, 2], ARRAY[3, 4]]);
 ERROR:  thresholds must be one-dimensional array
+-- slices with empty lower and/or upper index
+CREATE TABLE arrtest_s (
+  a       int2[],
+  b       int2[][]
+);
+INSERT INTO arrtest_s VALUES ('{1,2,3,4,5}', '{{1,2,3}, {4,5,6}, {7,8,9}}');
+SELECT a[:3], b[:2][:2] FROM arrtest_s;
+    a    |       b       
+---------+---------------
+ {1,2,3} | {{1,2},{4,5}}
+(1 row)
+
+SELECT a[2:], b[2:][2:] FROM arrtest_s;
+     a     |       b       
+-----------+---------------
+ {2,3,4,5} | {{5,6},{8,9}}
+(1 row)
+
+SELECT a[:], b[:] FROM arrtest_s;
+      a      |             b             
+-------------+---------------------------
+ {1,2,3,4,5} | {{1,2,3},{4,5,6},{7,8,9}}
+(1 row)
+
+-- errors
+UPDATE arrtest_s SET a[:3] = '{11, 12, 13}', b[:2][:2] = '{{11,12}, {14, 15}}';
+ERROR:  array subscript must have both boundaries
+LINE 1: UPDATE arrtest_s SET a[:3] = '{11, 12, 13}', b[:2][:2] = '{{...
+                             ^
+HINT:  You can't omit the upper or lower boundaries when updating or inserting
+UPDATE arrtest_s SET a[3:] = '{23, 24, 25}', b[2:][2:] = '{{25,26}, {28, 29}}';
+ERROR:  array subscript must have both boundaries
+LINE 1: UPDATE arrtest_s SET a[3:] = '{23, 24, 25}', b[2:][2:] = '{{...
+                             ^
+HINT:  You can't omit the upper or lower boundaries when updating or inserting
+UPDATE arrtest_s SET a[:] = '{23, 24, 25}';
+ERROR:  array subscript must have both boundaries
+LINE 1: UPDATE arrtest_s SET a[:] = '{23, 24, 25}';
+                             ^
+HINT:  You can't omit the upper or lower boundaries when updating or inserting

src/test/regress/output/misc.source

@@ -586,6 +586,7 @@ SELECT user_relns() AS user_relns
  array_index_op_test
  array_op_test
  arrtest
+ arrtest_s
  b
  b_star
  bb
@@ -710,7 +711,7 @@ SELECT user_relns() AS user_relns
  tvvmv
  varchar_tbl
  xacttest
-(132 rows)
+(133 rows)
 
 SELECT name(equipment(hobby_construct(text 'skywalking', text 'mer')));
  name 

src/test/regress/sql/arrays.sql

@@ -609,3 +609,18 @@ SELECT width_bucket(5, '{}');
 SELECT width_bucket('5'::text, ARRAY[3, 4]::integer[]);
 SELECT width_bucket(5, ARRAY[3, 4, NULL]);
 SELECT width_bucket(5, ARRAY[ARRAY[1, 2], ARRAY[3, 4]]);
+
+-- slices with empty lower and/or upper index
+CREATE TABLE arrtest_s (
+  a       int2[],
+  b       int2[][]
+);
+INSERT INTO arrtest_s VALUES ('{1,2,3,4,5}', '{{1,2,3}, {4,5,6}, {7,8,9}}');
+SELECT a[:3], b[:2][:2] FROM arrtest_s;
+SELECT a[2:], b[2:][2:] FROM arrtest_s;
+SELECT a[:], b[:] FROM arrtest_s;
+
+-- errors
+UPDATE arrtest_s SET a[:3] = '{11, 12, 13}', b[:2][:2] = '{{11,12}, {14, 15}}';
+UPDATE arrtest_s SET a[3:] = '{23, 24, 25}', b[2:][2:] = '{{25,26}, {28, 29}}';
+UPDATE arrtest_s SET a[:] = '{23, 24, 25}';
\ No newline at end of file