agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v45 2/3] Filling gaps in jsonb
173+ messages / 3 participants
[nested] [flat]

* [PATCH v45 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 460 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b7c268b53f 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--2v7pubbjx3p2om6u
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v45-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v40 2/2] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 src/backend/utils/adt/jsonfuncs.c   | 148 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out |  54 ++++++++++
 src/test/regress/sql/jsonb.sql      |  31 ++++++
 3 files changed, 227 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..2be4a6517a 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,26 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4796,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4865,6 +4894,82 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 		(void) pushJsonbValue(st, WJB_VALUE, newval);
 	}
 
+	/*
+	 * if we find an empty object not at the end of the path and instructed to
+	 * fill the whole path, create the whole chain of objects.
+	 */
+	if ((npairs == 0) && (op_type & JB_PATH_FILL_GAPS) &&
+		(level < path_len - 1))
+	{
+		/* remember the expected types, object or array */
+		enum jbvType *tpath = palloc((path_len - level) * sizeof(enum jbvType));
+		long		 lindex;
+
+		/* create first part of the chain with beginning tokens */
+		for(int i = level; i < path_len; i++)
+		{
+			char   	   *c, *badp;
+			JsonbValue	newkey;
+
+			if (path_nulls[i])
+				break;
+
+			/*
+			 * try to convert to an integer to find out the expected type,
+			 * object or array.
+			 */
+			c = TextDatumGetCString(path_elems[i]);
+			errno = 0;
+			lindex = strtol(c, &badp, 10);
+			if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+				lindex < INT_MIN)
+			{
+				/* text, an object is expected */
+				newkey.type = jbvString;
+				newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+				newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+				(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+				(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+				tpath[i] = jbvObject;
+			}
+			else
+			{
+				/* integer, an array is expected */
+				(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+				push_null_elements(st, lindex);
+
+				tpath[i] = jbvArray;
+			}
+
+		}
+
+		/* insert an actual value for either an object or array */
+		if (tpath[path_len - 1] == jbvArray)
+		{
+			(void) pushJsonbValue(st, WJB_ELEM, newval);
+		}
+		else
+			(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+		/*
+		 * Close everything up to the last but one level. The last one will be
+		 * closed outside of this function.
+		 */
+		for(int i = path_len - 1; i > level; i--)
+		{
+			if (path_nulls[i])
+				break;
+
+			if (tpath[i] == jbvObject)
+				(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+			else
+				(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+		}
+	}
+
 	for (i = 0; i < npairs; i++)
 	{
 		JsonbIteratorToken r = JsonbIteratorNext(it, &k, true);
@@ -4978,25 +5083,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5057,10 +5185,18 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
 				level == path_len - 1 && i == nelems - 1)
 			{
+				/*
+				 * If asked to fill the gaps, idx could be bigger than nelems,
+				 * so prepend the new element with nulls if that's the case.
+				 */
+				if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+					push_null_elements(st, idx - nelems);
+
 				(void) pushJsonbValue(st, WJB_ELEM, newval);
 			}
 		}
 	}
+
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..9f10289a17 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,60 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..940198c28c 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,37 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--byo64sf23gz7hdj6--





^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v41 2/2] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 +++++
 src/backend/utils/adt/jsonfuncs.c   | 207 +++++++++++++++++++++++++++-
 src/test/regress/expected/jsonb.out |  85 ++++++++++++
 src/test/regress/sql/jsonb.sql      |  50 +++++++
 4 files changed, 369 insertions(+), 6 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..c8edc8db4c 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,108 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	enum jbvType *tpath = palloc((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/* Create first part of the chain with beginning tokens */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			if (i > level)
+				(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[path_len - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4878,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4940,6 +5051,35 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, nothing is pushed into the state yet
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		/* If an object is currently empty, start a new one */
+		if (npairs == 0)
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5118,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5057,10 +5220,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
 				level == path_len - 1 && i == nelems - 1)
 			{
+				/*
+				 * If asked to fill the gaps, idx could be bigger than nelems,
+				 * so prepend the new element with nulls if that's the case.
+				 */
+				if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+					push_null_elements(st, idx - nelems);
+
 				(void) pushJsonbValue(st, WJB_ELEM, newval);
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, nothing is pushed into the state yet
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		/* If an array is currently empty, start a new one */
+		if (nelems == 0)
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..07f570b751 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,91 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..812a92d37e 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,56 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--bnxkghd4qzx6dtmd--





^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v42 2/2] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 106 +++++++++++++
 src/test/regress/sql/jsonb.sql      |  63 ++++++++
 4 files changed, 413 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..07c7062b31 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,108 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	enum jbvType *tpath = palloc((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/* Create first part of the chain with beginning tokens */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			if (i > level)
+				(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[path_len - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4878,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4987,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5008,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5052,35 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, nothing is pushed into the state yet
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		/* If an object is currently empty, start a new one */
+		if (npairs == 0)
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5119,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5171,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5190,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5217,46 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, nothing is pushed into the state yet
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		/* If an array is currently empty, start a new one */
+		if (nelems == 0)
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b50a76783c 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,112 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..d5c35d66a0 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,69 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--2lozexjxkmbehzdg--





^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v43 2/2] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 460 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b7c268b53f 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--6snw7vcvuujiswgu--





^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v44 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 460 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b7c268b53f 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--i5uwshohlpbxyckd
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v44-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v45 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 460 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b7c268b53f 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--2v7pubbjx3p2om6u
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v45-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v46 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  24 +++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 451 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 3ace5e444b..07bd19f974 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -648,6 +648,30 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- Where jsonb_field was NULL, it is now [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   If an index is specified for an array containing too few elements,
+   <literal>NULL</literal> elements will be appended until the index is reachable
+   and the value can be set.
+
+<programlisting>
+-- Where jsonb_field was [], it is now [null, null, 2];
+-- where jsonb_field was [0], it is now [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   A <type>jsonb</type> value will accept assignments to nonexistent subscript
+   paths as long as the last existing path key is an object or an array. Since
+   the final subscript is not traversed, it may be an object key. Nested arrays
+   will be created and <literal>NULL</literal>-padded according to the path until
+   the value can be placed appropriately.
+
+<programlisting>
+-- Where jsonb_field was {}, it is now {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- Where jsonb_field was [], it is now [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index 46bf2e2353..5b5510c4fd 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--mygb4tp4jvuwryfl
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v46-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v48 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  24 +++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 451 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 3ace5e444b..07bd19f974 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -648,6 +648,30 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- Where jsonb_field was NULL, it is now [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   If an index is specified for an array containing too few elements,
+   <literal>NULL</literal> elements will be appended until the index is reachable
+   and the value can be set.
+
+<programlisting>
+-- Where jsonb_field was [], it is now [null, null, 2];
+-- where jsonb_field was [0], it is now [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   A <type>jsonb</type> value will accept assignments to nonexistent subscript
+   paths as long as the last existing path key is an object or an array. Since
+   the final subscript is not traversed, it may be an object key. Nested arrays
+   will be created and <literal>NULL</literal>-padded according to the path until
+   the value can be placed appropriately.
+
+<programlisting>
+-- Where jsonb_field was {}, it is now {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- Where jsonb_field was [], it is now [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index 46bf2e2353..5b5510c4fd 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--m4t3wpskod5t4yye
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v48-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v49 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  24 +++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 451 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 3ace5e444b..07bd19f974 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -648,6 +648,30 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- Where jsonb_field was NULL, it is now [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   If an index is specified for an array containing too few elements,
+   <literal>NULL</literal> elements will be appended until the index is reachable
+   and the value can be set.
+
+<programlisting>
+-- Where jsonb_field was [], it is now [null, null, 2];
+-- where jsonb_field was [0], it is now [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   A <type>jsonb</type> value will accept assignments to nonexistent subscript
+   paths as long as the last existing path key is an object or an array. Since
+   the final subscript is not traversed, it may be an object key. Nested arrays
+   will be created and <literal>NULL</literal>-padded according to the path until
+   the value can be placed appropriately.
+
+<programlisting>
+-- Where jsonb_field was {}, it is now {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- Where jsonb_field was [], it is now [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index 46bf2e2353..5b5510c4fd 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--3x42k255okwqcjpg
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v49-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v41 2/2] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 +++++
 src/backend/utils/adt/jsonfuncs.c   | 207 +++++++++++++++++++++++++++-
 src/test/regress/expected/jsonb.out |  85 ++++++++++++
 src/test/regress/sql/jsonb.sql      |  50 +++++++
 4 files changed, 369 insertions(+), 6 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..c8edc8db4c 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,108 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	enum jbvType *tpath = palloc((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/* Create first part of the chain with beginning tokens */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			if (i > level)
+				(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[path_len - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4878,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4940,6 +5051,35 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, nothing is pushed into the state yet
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		/* If an object is currently empty, start a new one */
+		if (npairs == 0)
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5118,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5057,10 +5220,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
 				level == path_len - 1 && i == nelems - 1)
 			{
+				/*
+				 * If asked to fill the gaps, idx could be bigger than nelems,
+				 * so prepend the new element with nulls if that's the case.
+				 */
+				if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+					push_null_elements(st, idx - nelems);
+
 				(void) pushJsonbValue(st, WJB_ELEM, newval);
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, nothing is pushed into the state yet
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		/* If an array is currently empty, start a new one */
+		if (nelems == 0)
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..07f570b751 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,91 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..812a92d37e 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,56 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--bnxkghd4qzx6dtmd--





^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v42 2/2] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 106 +++++++++++++
 src/test/regress/sql/jsonb.sql      |  63 ++++++++
 4 files changed, 413 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..07c7062b31 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,108 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	enum jbvType *tpath = palloc((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/* Create first part of the chain with beginning tokens */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			if (i > level)
+				(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[path_len - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4878,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4987,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5008,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5052,35 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, nothing is pushed into the state yet
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		/* If an object is currently empty, start a new one */
+		if (npairs == 0)
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5119,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5171,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5190,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5217,46 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, nothing is pushed into the state yet
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		/* If an array is currently empty, start a new one */
+		if (nelems == 0)
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b50a76783c 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,112 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..d5c35d66a0 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,69 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--2lozexjxkmbehzdg--





^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v43 2/2] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 460 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b7c268b53f 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--6snw7vcvuujiswgu--





^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v44 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 460 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b7c268b53f 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--i5uwshohlpbxyckd
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v44-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v45 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  33 ++++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 460 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 100d1a60f4..9af015d222 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -645,6 +645,39 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- If jsonb_field here is NULL, the result is [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   Jsonb assignment via subscripting handles few edge cases differently
+   from <literal>jsonb_set</literal>. When assigning to the jsonb array
+   to the specified index, but there are no other elements present, the
+   result will be a jsonb array with the ewn value by specified index and
+   <type>null</type> elements from the first index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [], the result is [null, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning to the jsonb array to the specified index, but position
+   of the last element in the array is less than the specified index, the
+   result will be a jsonb array with the new value by specified index and
+   <type>null</type> elements from the last index to the specified index.
+
+<programlisting>
+-- If jsonb_field is [0], the result is [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   When assigning using the path which is not present in the source jsonb,
+   the result will be a jsonb with the specified path created and the new
+   value at the end of the path.
+
+<programlisting>
+-- If jsonb_field is {}, the result is {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- If jsonb_field is [], the result is [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index bb3f25ec3f..b7c268b53f 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--2v7pubbjx3p2om6u
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v45-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v46 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  24 +++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 451 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 3ace5e444b..07bd19f974 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -648,6 +648,30 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- Where jsonb_field was NULL, it is now [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   If an index is specified for an array containing too few elements,
+   <literal>NULL</literal> elements will be appended until the index is reachable
+   and the value can be set.
+
+<programlisting>
+-- Where jsonb_field was [], it is now [null, null, 2];
+-- where jsonb_field was [0], it is now [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   A <type>jsonb</type> value will accept assignments to nonexistent subscript
+   paths as long as the last existing path key is an object or an array. Since
+   the final subscript is not traversed, it may be an object key. Nested arrays
+   will be created and <literal>NULL</literal>-padded according to the path until
+   the value can be placed appropriately.
+
+<programlisting>
+-- Where jsonb_field was {}, it is now {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- Where jsonb_field was [], it is now [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index 46bf2e2353..5b5510c4fd 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--mygb4tp4jvuwryfl
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v46-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread

* [PATCH v48 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 173+ messages in thread

From: Dmitrii Dolgov @ 2020-12-31 14:19 UTC (permalink / raw)

Introduces two new modes for jsonb assignment:

* Appending array elements on the specified position, gaps filled with
nulls (similar to JavaScript behavior). This mode also instructs to
create the whole path in a jsonb object if some part of the path (more
than just the last element) is not present.

* Assigning keeps array positions consistent by prevent prepending of
elements.

Originally proposed by Nikita Glukhov based on polymorphic subscripting
patch, but transformed into an independent change.
---
 doc/src/sgml/json.sgml              |  24 +++
 src/backend/utils/adt/jsonfuncs.c   | 226 ++++++++++++++++++++++++++--
 src/test/regress/expected/jsonb.out | 135 +++++++++++++++++
 src/test/regress/sql/jsonb.sql      |  81 ++++++++++
 4 files changed, 451 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 3ace5e444b..07bd19f974 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -648,6 +648,30 @@ UPDATE table_name SET jsonb_field['a'] = '1';
 
 -- Where jsonb_field was NULL, it is now [1]
 UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+   If an index is specified for an array containing too few elements,
+   <literal>NULL</literal> elements will be appended until the index is reachable
+   and the value can be set.
+
+<programlisting>
+-- Where jsonb_field was [], it is now [null, null, 2];
+-- where jsonb_field was [0], it is now [0, null, 2]
+UPDATE table_name SET jsonb_field[2] = '2';
+</programlisting>
+
+   A <type>jsonb</type> value will accept assignments to nonexistent subscript
+   paths as long as the last existing path key is an object or an array. Since
+   the final subscript is not traversed, it may be an object key. Nested arrays
+   will be created and <literal>NULL</literal>-padded according to the path until
+   the value can be placed appropriately.
+
+<programlisting>
+-- Where jsonb_field was {}, it is now {'a': [{'b': 1}]}
+UPDATE table_name SET jsonb_field['a'][0]['b'] = '1';
+
+-- Where jsonb_field was [], it is now [{'a': 1}]
+UPDATE table_name SET jsonb_field[0]['a'] = '1';
 </programlisting>
 
   </para>
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 5a0ba6b220..f14f6c3191 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -44,6 +44,8 @@
 #define JB_PATH_INSERT_AFTER			0x0010
 #define JB_PATH_CREATE_OR_INSERT \
 	(JB_PATH_INSERT_BEFORE | JB_PATH_INSERT_AFTER | JB_PATH_CREATE)
+#define JB_PATH_FILL_GAPS				0x0020
+#define JB_PATH_CONSISTENT_POSITION		0x0040
 
 /* state for json_object_keys */
 typedef struct OkeysState
@@ -1634,14 +1636,116 @@ jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
 
 	it = JsonbIteratorInit(&jb->root);
 
-	res = setPath(&it, path, path_nulls, path_len, &state, 0,
-				  newval, JB_PATH_CREATE);
+	res = setPath(&it, path, path_nulls, path_len, &state, 0, newval,
+				  JB_PATH_CREATE | JB_PATH_FILL_GAPS |
+				  JB_PATH_CONSISTENT_POSITION);
 
 	pfree(path_nulls);
 
 	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
 }
 
+static void
+push_null_elements(JsonbParseState **ps, int num)
+{
+		JsonbValue	null;
+
+		null.type = jbvNull;
+
+		while (num-- > 0)
+				pushJsonbValue(ps, WJB_ELEM, &null);
+}
+
+/*
+ * Prepare a new structure containing nested empty objects and arrays
+ * corresponding to the specified path, and assign a new value at the end of
+ * this path. E.g. the path [a][0][b] with the new value 1 will produce the
+ * structure {a: [{b: 1}]}.
+ *
+ * Called is responsible to make sure such path does not exist yet.
+ */
+static void
+push_path(JsonbParseState **st, int level, Datum *path_elems,
+		  bool *path_nulls, int path_len, JsonbValue *newval)
+{
+	/*
+	 * tpath contains expected type of an empty jsonb created at each level
+	 * higher or equal than the current one, either jbvObject or jbvArray.
+	 * Since it contains only information about path slice from level to the
+	 * end, the access index must be normalized by level.
+	 */
+	enum jbvType *tpath = palloc0((path_len - level) * sizeof(enum jbvType));
+	long		 lindex;
+	JsonbValue	 newkey;
+
+	/*
+	 * Create first part of the chain with beginning tokens. For the current
+	 * level WJB_BEGIN_OBJECT/WJB_BEGIN_ARRAY was already created, so start
+	 * with the next one.
+	 */
+	for(int i = level + 1; i < path_len; i++)
+	{
+		char   	   *c, *badp;
+
+		if (path_nulls[i])
+			break;
+
+		/*
+		 * Try to convert to an integer to find out the expected type,
+		 * object or array.
+		 */
+		c = TextDatumGetCString(path_elems[i]);
+		errno = 0;
+		lindex = strtol(c, &badp, 10);
+		if (errno != 0 || badp == c || *badp != '\0' || lindex > INT_MAX ||
+			lindex < INT_MIN)
+		{
+			/* text, an object is expected */
+			newkey.type = jbvString;
+			newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[i]);
+			newkey.val.string.val = VARDATA_ANY(path_elems[i]);
+
+			(void) pushJsonbValue(st, WJB_BEGIN_OBJECT, NULL);
+			(void) pushJsonbValue(st, WJB_KEY, &newkey);
+
+			tpath[i - level] = jbvObject;
+		}
+		else
+		{
+			/* integer, an array is expected */
+			(void) pushJsonbValue(st, WJB_BEGIN_ARRAY, NULL);
+
+			push_null_elements(st, lindex);
+
+			tpath[i - level] = jbvArray;
+		}
+
+	}
+
+	/* Insert an actual value for either an object or array */
+	if (tpath[(path_len - level) - 1] == jbvArray)
+	{
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+	}
+	else
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
+
+	/*
+	 * Close everything up to the last but one level. The last one will be
+	 * closed outside of this function.
+	 */
+	for(int i = path_len - 1; i > level; i--)
+	{
+		if (path_nulls[i])
+			break;
+
+		if (tpath[i - level] == jbvObject)
+			(void) pushJsonbValue(st, WJB_END_OBJECT, NULL);
+		else
+			(void) pushJsonbValue(st, WJB_END_ARRAY, NULL);
+	}
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4782,6 +4886,21 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * Bits JB_PATH_INSERT_BEFORE and JB_PATH_INSERT_AFTER in op_type
  * behave as JB_PATH_CREATE if new value is inserted in JsonbObject.
  *
+ * If JB_PATH_FILL_GAPS bit is set, this will change an assignment logic in
+ * case if target is an array. The assignment index will not be restricted by
+ * number of elements in the array, and if there are any empty slots between
+ * last element of the array and a new one they will be filled with nulls. If
+ * the index is negative, it still will be considered an an index from the end
+ * of the array. Of a part of the path is not present and this part is more
+ * than just one last element, this flag will instruct to create the whole
+ * chain of corresponding objects and insert the value.
+ *
+ * JB_PATH_CONSISTENT_POSITION for an array indicates that the called wants to
+ * keep values with fixed indices. Indices for existing elements could be
+ * changed (shifted forward) in case if the array is prepended with a new value
+ * and a negative index out of the range, so this behavior will be prevented
+ * and return an error.
+ *
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
@@ -4876,6 +4995,8 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			memcmp(k.val.string.val, VARDATA_ANY(path_elems[level]),
 				   k.val.string.len) == 0)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				/*
@@ -4895,7 +5016,6 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, WJB_KEY, &k);
 					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
-				done = true;
 			}
 			else
 			{
@@ -4940,6 +5060,31 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			}
 		}
 	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open object with some keys/values was
+	 *   pushed into the state
+	 * - an object is empty, only WJB_BEGIN_OBJECT is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		JsonbValue	 newkey;
+
+		newkey.type = jbvString;
+		newkey.val.string.len = VARSIZE_ANY_EXHDR(path_elems[level]);
+		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
+
+		(void) pushJsonbValue(st, WJB_KEY, &newkey);
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
@@ -4978,25 +5123,48 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 	if (idx < 0)
 	{
 		if (-idx > nelems)
-			idx = INT_MIN;
+		{
+			/*
+			 * If asked to keep elements position consistent, it's not allowed
+			 * to prepend the array.
+			 */
+			if (op_type & JB_PATH_CONSISTENT_POSITION)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("path element at position %d is out of range: %d",
+								level + 1, idx)));
+			else
+				idx = INT_MIN;
+		}
 		else
 			idx = nelems + idx;
 	}
 
-	if (idx > 0 && idx > nelems)
-		idx = nelems;
+	/*
+	 * Filling the gaps means there are no limits on the positive index are
+	 * imposed, we can set any element. Otherwise limit the index by nelems.
+	 */
+	if (!(op_type & JB_PATH_FILL_GAPS))
+	{
+		if (idx > 0 && idx > nelems)
+			idx = nelems;
+	}
 
 	/*
 	 * if we're creating, and idx == INT_MIN, we prepend the new value to the
 	 * array also if the array is empty - in which case we don't really care
 	 * what the idx value is
 	 */
-
 	if ((idx == INT_MIN || nelems == 0) && (level == path_len - 1) &&
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
+
+		if (op_type & JB_PATH_FILL_GAPS && nelems == 0 && idx > 0)
+			push_null_elements(st, idx);
+
 		(void) pushJsonbValue(st, WJB_ELEM, newval);
+
 		done = true;
 	}
 
@@ -5007,6 +5175,8 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 		if (i == idx && level < path_len)
 		{
+			done = true;
+
 			if (level == path_len - 1)
 			{
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
@@ -5024,8 +5194,6 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
 					(void) pushJsonbValue(st, WJB_ELEM, newval);
-
-				done = true;
 			}
 			else
 				(void) setPath(it, path_elems, path_nulls, path_len,
@@ -5053,14 +5221,42 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, r < WJB_BEGIN_ARRAY ? &v : NULL);
 				}
 			}
-
-			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
-				level == path_len - 1 && i == nelems - 1)
-			{
-				(void) pushJsonbValue(st, WJB_ELEM, newval);
-			}
 		}
 	}
+
+	if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1)
+	{
+		/*
+		 * If asked to fill the gaps, idx could be bigger than nelems,
+		 * so prepend the new element with nulls if that's the case.
+		 */
+		if (op_type & JB_PATH_FILL_GAPS && idx > nelems)
+			push_null_elements(st, idx - nelems);
+
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
+		done = true;
+	}
+
+	/*
+	 * If we got here there are only few possibilities:
+	 * - no target path was found, and an open array with some keys/values was
+	 *   pushed into the state
+	 * - an array is empty, only WJB_BEGIN_ARRAY is pushed
+	 *
+	 * In both cases if instructed to create the path when not present,
+	 * generate the whole chain of empty objects and insert the new value
+	 * there.
+	 */
+	if (!done && (op_type & JB_PATH_FILL_GAPS) && (level < path_len - 1))
+	{
+		if (idx > 0)
+			push_null_elements(st, idx - nelems);
+
+		(void) push_path(st, level, path_elems, path_nulls,
+						 path_len, newval);
+
+		/* Result is closed with WJB_END_OBJECT outside of this function */
+	}
 }
 
 /*
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index 46bf2e2353..5b5510c4fd 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4999,6 +4999,141 @@ select * from test_jsonb_subscript;
   3 | [1]
 (3 rows)
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |           test_json            
+----+--------------------------------
+  1 | [0, null, null, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+update test_jsonb_subscript set test_json[-8] = '1';
+ERROR:  path element at position 1 is out of range: -8
+select * from test_jsonb_subscript;
+ id |          test_json          
+----+-----------------------------
+  1 | [0, null, 1, null, null, 1]
+(1 row)
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+ id |             test_json             
+----+-----------------------------------
+  1 | [null, null, null, null, null, 1]
+(1 row)
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | {"a": [{"b": [{"c": 1}]}]}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |                            test_json                             
+----+------------------------------------------------------------------
+  1 | {"a": [null, null, {"b": [null, null, {"c": [null, null, 1]}]}]}
+(1 row)
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+ id |     test_json      
+----+--------------------
+  1 | {"a": [2], "b": 1}
+(1 row)
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+ id |    test_json    
+----+-----------------
+  1 | {"0": {"a": 1}}
+(1 row)
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+ id |         test_json          
+----+----------------------------
+  1 | [{"a": 1}, null, {"b": 2}]
+(1 row)
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                 test_json                                  
+----+----------------------------------------------------------------------------
+  1 | {"a": {"b": [null, 1, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+ id | test_json  
+----+------------
+  1 | [[[1, 1]]]
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+ id |                                                                      test_json                                                                       
+----+------------------------------------------------------------------------------------------------------------------------------------------------------
+  1 | {"a": {"b": [null, null, null, null, null, null, null, null, null, null, 1], "10": [null, null, null, null, null, null, null, null, null, null, 1]}}
+(1 row)
+
+-- an empty sub element
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |              test_json               
+----+--------------------------------------
+  1 | {"a": {"b": {"c": [null, null, 1]}}}
+(1 row)
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+ id |               test_json               
+----+---------------------------------------
+  1 | {"a": [null, {"c": [null, null, 1]}]}
+(1 row)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index 20aa8fe0e2..0320db0ea4 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1290,6 +1290,87 @@ update test_jsonb_subscript set test_json = NULL where id = 3;
 update test_jsonb_subscript set test_json[0] = '1';
 select * from test_jsonb_subscript;
 
+-- Fill the gaps logic
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[0]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-4] = '1';
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json[-8] = '1';
+select * from test_jsonb_subscript;
+
+-- keep consistent values position
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+
+update test_jsonb_subscript set test_json[5] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][0]['b'][0]['c'] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a'][2]['b'][2]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+-- create the whole path with already existing keys
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"b": 1}');
+update test_jsonb_subscript set test_json['a'][0] = '2';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an object, first subscript is treated as a key
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+select * from test_jsonb_subscript;
+
+-- the start jsonb is an array
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0]['a'] = '1';
+update test_jsonb_subscript set test_json[2]['b'] = '2';
+select * from test_jsonb_subscript;
+
+-- overwriting an existing path
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][1] = '1';
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '[]');
+update test_jsonb_subscript set test_json[0][0][0] = '1';
+update test_jsonb_subscript set test_json[0][0][1] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{}');
+update test_jsonb_subscript set test_json['a']['b'][10] = '1';
+update test_jsonb_subscript set test_json['a'][10][10] = '1';
+select * from test_jsonb_subscript;
+
+-- an empty sub element
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": {}}');
+update test_jsonb_subscript set test_json['a']['b']['c'][2] = '1';
+select * from test_jsonb_subscript;
+
+delete from test_jsonb_subscript;
+insert into test_jsonb_subscript values (1, '{"a": []}');
+update test_jsonb_subscript set test_json['a'][1]['c'][2] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--m4t3wpskod5t4yye
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v48-0003-Replace-assuming-a-composite-object-on-a-scalar.patch"



^ permalink  raw  reply  [nested|flat] 173+ messages in thread