Add basic JSON_TABLE() functionality

JSON_TABLE() allows JSON data to be converted into a relational view
and thus used, for example, in a FROM clause, like other tabular
data.  Data to show in the view is selected from a source JSON object
using a JSON path expression to get a sequence of JSON objects that's
called a "row pattern", which becomes the source to compute the
SQL/JSON values that populate the view's output columns.  Column
values themselves are computed using JSON path expressions applied to
each of the JSON objects comprising the "row pattern", for which the
SQL/JSON query functions added in 6185c9737cf4 are used.

To implement JSON_TABLE() as a table function, this augments the
TableFunc and TableFuncScanState nodes that are currently used to
support XMLTABLE() with some JSON_TABLE()-specific fields.

Note that the JSON_TABLE() spec includes NESTED COLUMNS and PLAN
clauses, which are required to provide more flexibility to extract
data out of nested JSON objects, but they are not implemented here
to keep this commit of manageable size.

Author: Nikita Glukhov <n.gluhov@postgrespro.ru>
Author: Teodor Sigaev <teodor@sigaev.ru>
Author: Oleg Bartunov <obartunov@gmail.com>
Author: Alexander Korotkov <aekorotkov@gmail.com>
Author: Andrew Dunstan <andrew@dunslane.net>
Author: Amit Langote <amitlangote09@gmail.com>
Author: Jian He <jian.universality@gmail.com>

Reviewers have included (in no particular order):

Andres Freund, Alexander Korotkov, Pavel Stehule, Andrew Alsup,
Erik Rijkers, Zihong Yu, Himanshu Upadhyaya, Daniel Gustafsson,
Justin Pryzby, Álvaro Herrera, Jian He

Discussion: https://postgr.es/m/cd0bb935-0158-78a7-08b5-904886deac4b@postgrespro.ru
Discussion: https://postgr.es/m/20220616233130.rparivafipt6doj3@alap3.anarazel.de
Discussion: https://postgr.es/m/abd9b83b-aa66-f230-3d6d-734817f0995d%40postgresql.org
Discussion: https://postgr.es/m/CA+HiwqE4XTdfb1nW=Ojoy_tQSRhYt-q_kb6i5d4xcKyrLC1Nbg@mail.gmail.com

1 files changed, 180 insertions, 5 deletions

diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c
index 0f7f40c50f6..c9e3ac88cb1 100644
--- a/src/backend/utils/adt/ruleutils.c
+++ b/src/backend/utils/adt/ruleutils.c
@@ -524,6 +524,8 @@ static char *flatten_reloptions(Oid relid);
 static void get_reloptions(StringInfo buf, Datum reloptions);
 static void get_json_path_spec(Node *path_spec, deparse_context *context,
 							   bool showimplicit);
+static void get_json_table_columns(TableFunc *tf, deparse_context *context,
+								   bool showimplicit);
 
 #define only_marker(rte)  ((rte)->inh ? "" : "ONLY ")
 
@@ -8833,7 +8835,8 @@ get_json_behavior(JsonBehavior *behavior, deparse_context *context,
 /*
  * get_json_expr_options
  *
- * Parse back common options for JSON_QUERY, JSON_VALUE, JSON_EXISTS.
+ * Parse back common options for JSON_QUERY, JSON_VALUE, JSON_EXISTS and
+ * JSON_TABLE columns.
  */
 static void
 get_json_expr_options(JsonExpr *jsexpr, deparse_context *context,
@@ -11519,16 +11522,14 @@ get_sublink_expr(SubLink *sublink, deparse_context *context)
 
 
 /* ----------
- * get_tablefunc			- Parse back a table function
+ * get_xmltable			- Parse back a XMLTABLE function
  * ----------
  */
 static void
-get_tablefunc(TableFunc *tf, deparse_context *context, bool showimplicit)
+get_xmltable(TableFunc *tf, deparse_context *context, bool showimplicit)
 {
 	StringInfo	buf = context->buf;
 
-	/* XMLTABLE is the only existing implementation.  */
-
 	appendStringInfoString(buf, "XMLTABLE(");
 
 	if (tf->ns_uris != NIL)
@@ -11619,6 +11620,180 @@ get_tablefunc(TableFunc *tf, deparse_context *context, bool showimplicit)
 	appendStringInfoChar(buf, ')');
 }
 
+/*
+ * get_json_table_columns - Parse back JSON_TABLE columns
+ */
+static void
+get_json_table_columns(TableFunc *tf, deparse_context *context,
+					   bool showimplicit)
+{
+	StringInfo	buf = context->buf;
+	JsonExpr   *jexpr = castNode(JsonExpr, tf->docexpr);
+	ListCell   *lc_colname;
+	ListCell   *lc_coltype;
+	ListCell   *lc_coltypmod;
+	ListCell   *lc_colvalexpr;
+	int			colnum = 0;
+
+	appendStringInfoChar(buf, ' ');
+	appendContextKeyword(context, "COLUMNS (", 0, 0, 0);
+
+	if (PRETTY_INDENT(context))
+		context->indentLevel += PRETTYINDENT_VAR;
+
+	forfour(lc_colname, tf->colnames,
+			lc_coltype, tf->coltypes,
+			lc_coltypmod, tf->coltypmods,
+			lc_colvalexpr, tf->colvalexprs)
+	{
+		char	   *colname = strVal(lfirst(lc_colname));
+		JsonExpr   *colexpr;
+		Oid			typid;
+		int32		typmod;
+		bool		ordinality;
+		JsonBehaviorType default_behavior;
+
+		typid = lfirst_oid(lc_coltype);
+		typmod = lfirst_int(lc_coltypmod);
+		colexpr = castNode(JsonExpr, lfirst(lc_colvalexpr));
+
+		if (colnum > 0)
+			appendStringInfoString(buf, ", ");
+
+		colnum++;
+
+		ordinality = !colexpr;
+
+		appendContextKeyword(context, "", 0, 0, 0);
+
+		appendStringInfo(buf, "%s %s", quote_identifier(colname),
+						 ordinality ? "FOR ORDINALITY" :
+						 format_type_with_typemod(typid, typmod));
+		if (ordinality)
+			continue;
+
+		if (colexpr->op == JSON_EXISTS_OP)
+		{
+			appendStringInfoString(buf, " EXISTS");
+			default_behavior = JSON_BEHAVIOR_FALSE;
+		}
+		else
+		{
+			if (colexpr->op == JSON_QUERY_OP)
+			{
+				char		typcategory;
+				bool		typispreferred;
+
+				get_type_category_preferred(typid, &typcategory, &typispreferred);
+
+				if (typcategory == TYPCATEGORY_STRING)
+					appendStringInfoString(buf,
+										   colexpr->format->format_type == JS_FORMAT_JSONB ?
+										   " FORMAT JSONB" : " FORMAT JSON");
+			}
+
+			default_behavior = JSON_BEHAVIOR_NULL;
+		}
+
+		if (jexpr->on_error->btype == JSON_BEHAVIOR_ERROR)
+			default_behavior = JSON_BEHAVIOR_ERROR;
+
+		appendStringInfoString(buf, " PATH ");
+
+		get_json_path_spec(colexpr->path_spec, context, showimplicit);
+
+		get_json_expr_options(colexpr, context, default_behavior);
+	}
+
+	if (PRETTY_INDENT(context))
+		context->indentLevel -= PRETTYINDENT_VAR;
+
+	appendContextKeyword(context, ")", 0, 0, 0);
+}
+
+/* ----------
+ * get_json_table			- Parse back a JSON_TABLE function
+ * ----------
+ */
+static void
+get_json_table(TableFunc *tf, deparse_context *context, bool showimplicit)
+{
+	StringInfo	buf = context->buf;
+	JsonExpr   *jexpr = castNode(JsonExpr, tf->docexpr);
+	JsonTablePathScan *root = castNode(JsonTablePathScan, tf->plan);
+
+	appendStringInfoString(buf, "JSON_TABLE(");
+
+	if (PRETTY_INDENT(context))
+		context->indentLevel += PRETTYINDENT_VAR;
+
+	appendContextKeyword(context, "", 0, 0, 0);
+
+	get_rule_expr(jexpr->formatted_expr, context, showimplicit);
+
+	appendStringInfoString(buf, ", ");
+
+	get_const_expr(root->path->value, context, -1);
+
+	appendStringInfo(buf, " AS %s", quote_identifier(root->path->name));
+
+	if (jexpr->passing_values)
+	{
+		ListCell   *lc1,
+				   *lc2;
+		bool		needcomma = false;
+
+		appendStringInfoChar(buf, ' ');
+		appendContextKeyword(context, "PASSING ", 0, 0, 0);
+
+		if (PRETTY_INDENT(context))
+			context->indentLevel += PRETTYINDENT_VAR;
+
+		forboth(lc1, jexpr->passing_names,
+				lc2, jexpr->passing_values)
+		{
+			if (needcomma)
+				appendStringInfoString(buf, ", ");
+			needcomma = true;
+
+			appendContextKeyword(context, "", 0, 0, 0);
+
+			get_rule_expr((Node *) lfirst(lc2), context, false);
+			appendStringInfo(buf, " AS %s",
+							 quote_identifier((lfirst_node(String, lc1))->sval)
+				);
+		}
+
+		if (PRETTY_INDENT(context))
+			context->indentLevel -= PRETTYINDENT_VAR;
+	}
+
+	get_json_table_columns(tf, context, showimplicit);
+
+	if (jexpr->on_error->btype != JSON_BEHAVIOR_EMPTY)
+		get_json_behavior(jexpr->on_error, context, "ERROR");
+
+	if (PRETTY_INDENT(context))
+		context->indentLevel -= PRETTYINDENT_VAR;
+
+	appendContextKeyword(context, ")", 0, 0, 0);
+}
+
+/* ----------
+ * get_tablefunc			- Parse back a table function
+ * ----------
+ */
+static void
+get_tablefunc(TableFunc *tf, deparse_context *context, bool showimplicit)
+{
+	/* XMLTABLE and JSON_TABLE are the only existing implementations.  */
+
+	if (tf->functype == TFT_XMLTABLE)
+		get_xmltable(tf, context, showimplicit);
+	else if (tf->functype == TFT_JSON_TABLE)
+		get_json_table(tf, context, showimplicit);
+}
+
 /* ----------
  * get_from_clause			- Parse back a FROM clause
  *