Implementation of subscripting for jsonb

Subscripting for jsonb does not support slices, does not have a limit for the
number of subscripts, and an assignment expects a replace value to have jsonb
type.  There is also one functional difference between assignment via
subscripting and assignment via jsonb_set().  When an original jsonb container
is NULL, the subscripting replaces it with an empty jsonb and proceeds with
an assignment.

For the sake of code reuse, we rearrange some parts of jsonb functionality
to allow the usage of the same functions for jsonb_set and assign subscripting
operation.

The original idea belongs to Oleg Bartunov.

Catversion is bumped.

Discussion: https://postgr.es/m/CA%2Bq6zcV8qvGcDXurwwgUbwACV86Th7G80pnubg42e-p9gsSf%3Dg%40mail.gmail.com
Discussion: https://postgr.es/m/CA%2Bq6zcX3mdxGCgdThzuySwH-ApyHHM-G4oB1R0fn0j2hZqqkLQ%40mail.gmail.com
Discussion: https://postgr.es/m/CA%2Bq6zcVDuGBv%3DM0FqBYX8DPebS3F_0KQ6OVFobGJPM507_SZ_w%40mail.gmail.com
Discussion: https://postgr.es/m/CA%2Bq6zcVovR%2BXY4mfk-7oNk-rF91gH0PebnNfuUjuuDsyHjOcVA%40mail.gmail.com
Author: Dmitry Dolgov
Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay
Reviewed-by: Andrew Dunstan, Chapman Flack, Merlin Moncure, Peter Geoghegan
Reviewed-by: Alvaro Herrera, Jim Nasby, Josh Berkus, Victor Wagner
Reviewed-by: Aleksander Alekseev, Robert Haas, Oleg Bartunov

Author: akorotkov

doc/src/sgml/json.sgml

@@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu
   </para>
  </sect2>
 
+ <sect2 id="jsonb-subscripting">
+  <title><type>jsonb</type> Subscripting</title>
+  <para>
+   The <type>jsonb</type> data type supports array-style subscripting expressions
+   to extract and modify elements. Nested values can be indicated by chaining
+   subscripting expressions, following the same rules as the <literal>path</literal>
+   argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type>
+   value is an array, numeric subscripts start at zero, and negative integers count
+   backwards from the last element of the array. Slice expressions are not supported.
+   The result of a subscripting expression is always of the jsonb data type.
+  </para>
+
+  <para>
+   An example of subscripting syntax:
+<programlisting>
+
+-- Extract object value by key
+SELECT ('{"a": 1}'::jsonb)['a'];
+
+-- Extract nested object value by key path
+SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c'];
+
+-- Extract array element by index
+SELECT ('[1, "2", null]'::jsonb)[1];
+
+-- Update object value by key. Note the quotes around '1': the assigned
+-- value must be of the jsonb type as well
+UPDATE table_name SET jsonb_field['key'] = '1';
+
+-- Filter records using a WHERE clause with subscripting. Since the result of
+-- subscripting is jsonb, the value we compare it against must also be jsonb.
+-- The double quotes make "value" also a valid jsonb string.
+SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"';
+</programlisting>
+
+   <type>jsonb</type> assignment via subscripting handles a few edge cases
+   differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type>
+   is <literal>NULL</literal>, assignment via subscripting will proceed as if
+   it was an empty JSON object:
+
+<programlisting>
+-- Where jsonb_field was NULL, it is now {"a": 1}
+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>
+
+  </para>
+ </sect2>
+
  <sect2>
   <title>Transforms</title>
 

src/backend/utils/adt/Makefile

@@ -50,6 +50,7 @@ OBJS = \
 	jsonb_op.o \
 	jsonb_util.o \
 	jsonfuncs.o \
+	jsonbsubs.o \
 	jsonpath.o \
 	jsonpath_exec.o \
 	jsonpath_gram.o \

src/backend/utils/adt/jsonb_util.c

@@ -68,18 +68,25 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate,
 										JsonbIteratorToken seq,
 										JsonbValue *scalarVal);
 
+void
+JsonbToJsonbValue(Jsonb *jsonb, JsonbValue *val)
+{
+	val->type = jbvBinary;
+	val->val.binary.data = &jsonb->root;
+	val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ;
+}
+
 /*
  * Turn an in-memory JsonbValue into a Jsonb for on-disk storage.
  *
- * There isn't a JsonbToJsonbValue(), because generally we find it more
- * convenient to directly iterate through the Jsonb representation and only
- * really convert nested scalar values.  JsonbIteratorNext() does this, so that
- * clients of the iteration code don't have to directly deal with the binary
- * representation (JsonbDeepContains() is a notable exception, although all
- * exceptions are internal to this module).  In general, functions that accept
- * a JsonbValue argument are concerned with the manipulation of scalar values,
- * or simple containers of scalar values, where it would be inconvenient to
- * deal with a great amount of other state.
+ * Generally we find it more convenient to directly iterate through the Jsonb
+ * representation and only really convert nested scalar values.
+ * JsonbIteratorNext() does this, so that clients of the iteration code don't
+ * have to directly deal with the binary representation (JsonbDeepContains() is
+ * a notable exception, although all exceptions are internal to this module).
+ * In general, functions that accept a JsonbValue argument are concerned with
+ * the manipulation of scalar values, or simple containers of scalar values,
+ * where it would be inconvenient to deal with a great amount of other state.
  */
 Jsonb *
 JsonbValueToJsonb(JsonbValue *val)
@@ -563,6 +570,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq,
 	JsonbValue *res = NULL;
 	JsonbValue	v;
 	JsonbIteratorToken tok;
+	int			i;
+
+	if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject)
+	{
+		pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL);
+		for (i = 0; i < jbval->val.object.nPairs; i++)
+		{
+			pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key);
+			pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value);
+		}
+
+		return pushJsonbValue(pstate, WJB_END_OBJECT, NULL);
+	}
+
+	if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray)
+	{
+		pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL);
+		for (i = 0; i < jbval->val.array.nElems; i++)
+		{
+			pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]);
+		}
+
+		return pushJsonbValue(pstate, WJB_END_ARRAY, NULL);
+	}
 
 	if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) ||
 		jbval->type != jbvBinary)
@@ -573,9 +604,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq,
 
 	/* unpack the binary and add each piece to the pstate */
 	it = JsonbIteratorInit(jbval->val.binary.data);
+
+	if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate)
+	{
+		tok = JsonbIteratorNext(&it, &v, true);
+		Assert(tok == WJB_BEGIN_ARRAY);
+		Assert(v.type == jbvArray && v.val.array.rawScalar);
+
+		tok = JsonbIteratorNext(&it, &v, true);
+		Assert(tok == WJB_ELEM);
+
+		res = pushJsonbValueScalar(pstate, seq, &v);
+
+		tok = JsonbIteratorNext(&it, &v, true);
+		Assert(tok == WJB_END_ARRAY);
+		Assert(it == NULL);
+
+		return res;
+	}
+
 	while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE)
 		res = pushJsonbValueScalar(pstate, tok,
-								   tok < WJB_BEGIN_ARRAY ? &v : NULL);
+								   tok < WJB_BEGIN_ARRAY ||
+								   (tok == WJB_BEGIN_ARRAY &&
+									v.val.array.rawScalar) ? &v : NULL);
 
 	return res;
 }