agora inbox for pgsql-hackers@postgresql.org
help / color / mirror / Atom feed[PATCH v48 2/3] Filling gaps in jsonb
3+ messages / 3 participants
[nested] [flat]
* [PATCH v48 2/3] Filling gaps in jsonb
@ 2020-12-31 14:19 Dmitrii Dolgov <9erthalion6@gmail.com>
0 siblings, 0 replies; 3+ 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] 3+ messages in thread
* Re: XMAX_LOCK_ONLY and XMAX_COMMITTED (fk/multixact code)
@ 2022-10-21 00:16 Corey Huinker <corey.huinker@gmail.com>
0 siblings, 0 replies; 3+ messages in thread
From: Corey Huinker @ 2022-10-21 00:16 UTC (permalink / raw)
To: Nathan Bossart <nathandbossart@gmail.com>; +Cc: Andres Freund <andres@anarazel.de>; Bossart, Nathan <bossartn@amazon.com>; Mark Dilger <mark.dilger@enterprisedb.com>; Peter Geoghegan <pg@bowt.ie>; Alvaro Herrera <alvherre@2ndquadrant.com>; Schneider (AWS), Jeremy <schnjere@amazon.com>; pgsql-hackers
On Tue, Sep 20, 2022 at 2:32 PM Nathan Bossart <nathandbossart@gmail.com>
wrote:
> Here is a rebased patch for cfbot.
>
>
>
Applies, passes make check world.
Patch is straightforward, but the previous code is less so. It purported to
set XMAX_COMMITTED _or_ XMAX_INVALID, but never seemed to un-set
XMAX_COMMITTED, was that the source of the double-setting?
^ permalink raw reply [nested|flat] 3+ messages in thread
* [PATCH v17 2/8] Row pattern recognition patch (parse/analysis).
@ 2024-04-28 11:00 Tatsuo Ishii <ishii@postgresql.org>
0 siblings, 0 replies; 3+ messages in thread
From: Tatsuo Ishii @ 2024-04-28 11:00 UTC (permalink / raw)
---
src/backend/parser/parse_agg.c | 7 +
src/backend/parser/parse_clause.c | 296 +++++++++++++++++++++++++++++-
src/backend/parser/parse_expr.c | 4 +
src/backend/parser/parse_func.c | 3 +
4 files changed, 309 insertions(+), 1 deletion(-)
diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c
index bee7d8346a..9bc22a836a 100644
--- a/src/backend/parser/parse_agg.c
+++ b/src/backend/parser/parse_agg.c
@@ -577,6 +577,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr)
errkind = true;
break;
+ case EXPR_KIND_RPR_DEFINE:
+ errkind = true;
+ break;
+
/*
* There is intentionally no default: case here, so that the
* compiler will warn if we add a new ParseExprKind without
@@ -967,6 +971,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc,
case EXPR_KIND_CYCLE_MARK:
errkind = true;
break;
+ case EXPR_KIND_RPR_DEFINE:
+ errkind = true;
+ break;
/*
* There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c
index 4fc5fc87e0..003a1e14ce 100644
--- a/src/backend/parser/parse_clause.c
+++ b/src/backend/parser/parse_clause.c
@@ -98,7 +98,14 @@ static WindowClause *findWindowClause(List *wclist, const char *name);
static Node *transformFrameOffset(ParseState *pstate, int frameOptions,
Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc,
Node *clause);
-
+static void transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+ List **targetlist);
+static List *transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+ List **targetlist);
+static void transformPatternClause(ParseState *pstate, WindowClause *wc,
+ WindowDef *windef);
+static List *transformMeasureClause(ParseState *pstate, WindowClause *wc,
+ WindowDef *windef);
/*
* transformFromClause -
@@ -2956,6 +2963,10 @@ transformWindowDefinitions(ParseState *pstate,
rangeopfamily, rangeopcintype,
&wc->endInRangeFunc,
windef->endOffset);
+
+ /* Process Row Pattern Recognition related clauses */
+ transformRPR(pstate, wc, windef, targetlist);
+
wc->runCondition = NIL;
wc->winref = winref;
@@ -3821,3 +3832,286 @@ transformFrameOffset(ParseState *pstate, int frameOptions,
return node;
}
+
+/*
+ * transformRPR
+ * Process Row Pattern Recognition related clauses
+ */
+static void
+transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+ List **targetlist)
+{
+ /*
+ * Window definition exists?
+ */
+ if (windef == NULL)
+ return;
+
+ /*
+ * Row Pattern Common Syntax clause exists?
+ */
+ if (windef->rpCommonSyntax == NULL)
+ return;
+
+ /* Check Frame option. Frame must start at current row */
+ if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0)
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("FRAME must start at current row when row patttern recognition is used")));
+
+ /* Transform AFTER MACH SKIP TO clause */
+ wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo;
+
+ /* Transform AFTER MACH SKIP TO variable */
+ wc->rpSkipVariable = windef->rpCommonSyntax->rpSkipVariable;
+
+ /* Transform SEEK or INITIAL clause */
+ wc->initial = windef->rpCommonSyntax->initial;
+
+ /* Transform DEFINE clause into list of TargetEntry's */
+ wc->defineClause = transformDefineClause(pstate, wc, windef, targetlist);
+
+ /* Check PATTERN clause and copy to patternClause */
+ transformPatternClause(pstate, wc, windef);
+
+ /* Transform MEASURE clause */
+ transformMeasureClause(pstate, wc, windef);
+}
+
+/*
+ * transformDefineClause Process DEFINE clause and transform ResTarget into
+ * list of TargetEntry.
+ *
+ * XXX we only support column reference in row pattern definition search
+ * condition, e.g. "price". <row pattern definition variable name>.<column
+ * reference> is not supported, e.g. "A.price".
+ */
+static List *
+transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+ List **targetlist)
+{
+ /* DEFINE variable name initials */
+ static char *defineVariableInitials = "abcdefghijklmnopqrstuvwxyz";
+
+ ListCell *lc,
+ *l;
+ ResTarget *restarget,
+ *r;
+ List *restargets;
+ List *defineClause;
+ char *name;
+ int initialLen;
+ int i;
+
+ /*
+ * If Row Definition Common Syntax exists, DEFINE clause must exist. (the
+ * raw parser should have already checked it.)
+ */
+ Assert(windef->rpCommonSyntax->rpDefs != NULL);
+
+ /*
+ * Check and add "A AS A IS TRUE" if pattern variable is missing in DEFINE
+ * per the SQL standard.
+ */
+ restargets = NIL;
+ foreach(lc, windef->rpCommonSyntax->rpPatterns)
+ {
+ A_Expr *a;
+ bool found = false;
+
+ if (!IsA(lfirst(lc), A_Expr))
+ ereport(ERROR,
+ errmsg("node type is not A_Expr"));
+
+ a = (A_Expr *) lfirst(lc);
+ name = strVal(a->lexpr);
+
+ foreach(l, windef->rpCommonSyntax->rpDefs)
+ {
+ restarget = (ResTarget *) lfirst(l);
+
+ if (!strcmp(restarget->name, name))
+ {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found)
+ {
+ /*
+ * "name" is missing. So create "name AS name IS TRUE" ResTarget
+ * node and add it to the temporary list.
+ */
+ A_Const *n;
+
+ restarget = makeNode(ResTarget);
+ n = makeNode(A_Const);
+ n->val.boolval.type = T_Boolean;
+ n->val.boolval.boolval = true;
+ n->location = -1;
+ restarget->name = pstrdup(name);
+ restarget->indirection = NIL;
+ restarget->val = (Node *) n;
+ restarget->location = -1;
+ restargets = lappend((List *) restargets, restarget);
+ }
+ }
+
+ if (list_length(restargets) >= 1)
+ {
+ /* add missing DEFINEs */
+ windef->rpCommonSyntax->rpDefs =
+ list_concat(windef->rpCommonSyntax->rpDefs, restargets);
+ list_free(restargets);
+ }
+
+ /*
+ * Check for duplicate row pattern definition variables. The standard
+ * requires that no two row pattern definition variable names shall be
+ * equivalent.
+ */
+ restargets = NIL;
+ foreach(lc, windef->rpCommonSyntax->rpDefs)
+ {
+ restarget = (ResTarget *) lfirst(lc);
+ name = restarget->name;
+
+ /*
+ * Add DEFINE expression (Restarget->val) to the targetlist as a
+ * TargetEntry if it does not exist yet. Planner will add the column
+ * ref var node to the outer plan's target list later on. This makes
+ * DEFINE expression could access the outer tuple while evaluating
+ * PATTERN.
+ *
+ * XXX: adding whole expressions of DEFINE to the plan.targetlist is
+ * not so good, because it's not necessary to evalute the expression
+ * in the target list while running the plan. We should extract the
+ * var nodes only then add them to the plan.targetlist.
+ */
+ findTargetlistEntrySQL99(pstate, (Node *) restarget->val,
+ targetlist, EXPR_KIND_RPR_DEFINE);
+
+ /*
+ * Make sure that the row pattern definition search condition is a
+ * boolean expression.
+ */
+ transformWhereClause(pstate, restarget->val,
+ EXPR_KIND_RPR_DEFINE, "DEFINE");
+
+ foreach(l, restargets)
+ {
+ char *n;
+
+ r = (ResTarget *) lfirst(l);
+ n = r->name;
+
+ if (!strcmp(n, name))
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("row pattern definition variable name \"%s\" appears more than once in DEFINE clause",
+ name),
+ parser_errposition(pstate, exprLocation((Node *) r))));
+ }
+ restargets = lappend(restargets, restarget);
+ }
+ list_free(restargets);
+
+ /*
+ * Create list of row pattern DEFINE variable name's initial. We assign
+ * [a-z] to them (up to 26 variable names are allowed).
+ */
+ restargets = NIL;
+ i = 0;
+ initialLen = strlen(defineVariableInitials);
+
+ foreach(lc, windef->rpCommonSyntax->rpDefs)
+ {
+ char initial[2];
+
+ restarget = (ResTarget *) lfirst(lc);
+ name = restarget->name;
+
+ if (i >= initialLen)
+ {
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("number of row pattern definition variable names exceeds %d",
+ initialLen),
+ parser_errposition(pstate,
+ exprLocation((Node *) restarget))));
+ }
+ initial[0] = defineVariableInitials[i++];
+ initial[1] = '\0';
+ wc->defineInitial = lappend(wc->defineInitial,
+ makeString(pstrdup(initial)));
+ }
+
+ defineClause = transformTargetList(pstate, windef->rpCommonSyntax->rpDefs,
+ EXPR_KIND_RPR_DEFINE);
+
+ /* mark column origins */
+ markTargetListOrigins(pstate, defineClause);
+
+ /* mark all nodes in the DEFINE clause tree with collation information */
+ assign_expr_collations(pstate, (Node *) defineClause);
+
+ return defineClause;
+}
+
+/*
+ * transformPatternClause
+ * Process PATTERN clause and return PATTERN clause in the raw parse tree
+ */
+static void
+transformPatternClause(ParseState *pstate, WindowClause *wc,
+ WindowDef *windef)
+{
+ ListCell *lc;
+
+ /*
+ * Row Pattern Common Syntax clause exists?
+ */
+ if (windef->rpCommonSyntax == NULL)
+ return;
+
+ wc->patternVariable = NIL;
+ wc->patternRegexp = NIL;
+ foreach(lc, windef->rpCommonSyntax->rpPatterns)
+ {
+ A_Expr *a;
+ char *name;
+ char *regexp;
+
+ if (!IsA(lfirst(lc), A_Expr))
+ ereport(ERROR,
+ errmsg("node type is not A_Expr"));
+
+ a = (A_Expr *) lfirst(lc);
+ name = strVal(a->lexpr);
+
+ wc->patternVariable = lappend(wc->patternVariable, makeString(pstrdup(name)));
+ regexp = strVal(lfirst(list_head(a->name)));
+
+ wc->patternRegexp = lappend(wc->patternRegexp, makeString(pstrdup(regexp)));
+ }
+}
+
+/*
+ * transformMeasureClause
+ * Process MEASURE clause
+ * XXX MEASURE clause is not supported yet
+ */
+static List *
+transformMeasureClause(ParseState *pstate, WindowClause *wc,
+ WindowDef *windef)
+{
+ if (windef->rowPatternMeasures == NIL)
+ return NIL;
+
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("%s", "MEASURE clause is not supported yet"),
+ parser_errposition(pstate, exprLocation((Node *) windef->rowPatternMeasures))));
+ return NIL;
+}
diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c
index 1c1c86aa3e..5540a0fb0a 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -578,6 +578,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref)
case EXPR_KIND_COPY_WHERE:
case EXPR_KIND_GENERATED_COLUMN:
case EXPR_KIND_CYCLE_MARK:
+ case EXPR_KIND_RPR_DEFINE:
/* okay */
break;
@@ -1817,6 +1818,7 @@ transformSubLink(ParseState *pstate, SubLink *sublink)
case EXPR_KIND_VALUES:
case EXPR_KIND_VALUES_SINGLE:
case EXPR_KIND_CYCLE_MARK:
+ case EXPR_KIND_RPR_DEFINE:
/* okay */
break;
case EXPR_KIND_CHECK_CONSTRAINT:
@@ -3197,6 +3199,8 @@ ParseExprKindName(ParseExprKind exprKind)
return "GENERATED AS";
case EXPR_KIND_CYCLE_MARK:
return "CYCLE";
+ case EXPR_KIND_RPR_DEFINE:
+ return "DEFINE";
/*
* There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_func.c b/src/backend/parser/parse_func.c
index 0cbc950c95..ad982a7c17 100644
--- a/src/backend/parser/parse_func.c
+++ b/src/backend/parser/parse_func.c
@@ -2657,6 +2657,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location)
case EXPR_KIND_CYCLE_MARK:
errkind = true;
break;
+ case EXPR_KIND_RPR_DEFINE:
+ errkind = true;
+ break;
/*
* There is intentionally no default: case here, so that the
--
2.25.1
----Next_Part(Sun_Apr_28_20_28_26_2024_444)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
filename="v17-0003-Row-pattern-recognition-patch-rewriter.patch"
^ permalink raw reply [nested|flat] 3+ messages in thread
end of thread, other threads:[~2024-04-28 11:00 UTC | newest]
Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-12-31 14:19 [PATCH v48 2/3] Filling gaps in jsonb Dmitrii Dolgov <9erthalion6@gmail.com>
2022-10-21 00:16 Re: XMAX_LOCK_ONLY and XMAX_COMMITTED (fk/multixact code) Corey Huinker <corey.huinker@gmail.com>
2024-04-28 11:00 [PATCH v17 2/8] Row pattern recognition patch (parse/analysis). Tatsuo Ishii <ishii@postgresql.org>
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox