ganeshashree commented on code in PR #58450:
URL: https://github.com/apache/spark/pull/58450#discussion_r4032830997
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:
##########
@@ -1651,6 +1651,134 @@ object JsonArray {
}
}
+// Built-in forms for the plain SQL/JSON constructor and path-function calls
that `AstBuilder`
+// routes through function resolution. Each rebuilds its expression with the
standard clause
+// defaults when unshadowed.
+
+@ExpressionDescription(
+ usage = "_FUNC_([expr[, ...]]) - Returns a JSON array string with NULL
elements dropped.",
+ arguments = """
+ Arguments:
+ * expr - the elements to place in the array.
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_(1, 'x', true);
+ [1,"x",true]
+ > SELECT _FUNC_(1, NULL, 3);
+ [1,3]
+ > SELECT _FUNC_();
+ []
+ """,
+ since = "4.4.0",
+ group = "json_funcs")
+object JsonArrayExpressionBuilder extends ExpressionBuilder {
+ override def build(funcName: String, expressions: Seq[Expression]):
Expression = {
+ // A routed call carries no lexical FORMAT JSON, so every element is a
plain value (quoted).
+ // Splicing a nested constructor is only reachable via `JSON_ARRAY(...)`
syntax (which freezes
Review Comment:
Done.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala:
##########
@@ -404,6 +388,110 @@ class FunctionResolution(
}
}
+ /**
+ * Returns whether an unqualified function name reaches `system.builtin`
before any temp or
+ * persistent function in the effective SQL PATH. When a temp or persistent
function shadows the
+ * builtin, special-syntax handling that only applies to Spark's builtins
must not fire, since the
+ * name no longer refers to the builtin -- e.g. rejecting a direct star
(bare `*` or qualified
+ * `t.*`) in a routed SQL/JSON function or the `count(tbl.*)` guard.
Parser-built `count(*)` is
+ * normalized to `count(1)` in `AstBuilder` so it skips this probe, but a
DataFrame `count("*")`
+ * keeps its star and does reach the probe during analyzer normalization.
+ *
+ * Precondition: `functionName` must already be known to be a stock built-in
name (as
+ * `functionNameResolvesToBuiltin` ensures by checking
`FunctionRegistry.functionSet` first). This
+ * returns true as soon as the PATH reaches `system.builtin`, without
verifying that
+ * `system.builtin` actually defines a function of this name, so calling it
for a non-builtin name
+ * would wrongly report builtin ownership.
+ */
+ def unqualifiedFunctionResolvesToBuiltinBeforeAnyShadow(functionName:
String): Boolean = {
+ // Walk the PATH in order and stop at the first entry that owns the name.
The default order puts
+ // system.builtin first, so the common case returns on the first entry
with no catalog lookup;
+ // only a custom PATH that lists a persistent catalog ahead of
system.builtin reaches the probe
+ // below (one lookup per such preceding entry, recomputed on each call --
not cached).
+ sqlResolutionPathEntriesForAnalysis.foreach { pathEntry =>
+ val candidate = pathEntry :+ functionName
+ FunctionResolution.sessionNamespaceKind(candidate) match {
+ case
Some(org.apache.spark.sql.catalyst.catalog.SessionCatalog.Builtin) =>
+ return true
+ case Some(org.apache.spark.sql.catalyst.catalog.SessionCatalog.Temp) =>
+ // A visible temp scalar function shadows the builtin; a visible
temp *table* function
+ // makes scalar resolution terminal at this PATH entry
(NOT_A_SCALAR_FUNCTION). Either way
+ // the name never reaches system.builtin, mirroring
`resolveFunctionCandidate`.
+ val ident = FunctionIdentifier(functionName)
+ if (v1SessionCatalog.isTemporaryScalarFunctionVisible(ident) ||
+ v1SessionCatalog.isTemporaryTableFunctionVisible(ident)) {
+ return false
+ }
+ case None =>
+ if (persistentFunctionExists(candidate)) {
+ return false
+ }
+ }
+ }
+ false
+ }
+
+ /**
+ * Returns true when a function reference resolves to the system built-in
with the requested name.
+ * This mirrors [[resolveFunction]] for special parser/analyzer rewrites
that must run only for
+ * Spark's built-ins. In particular, two-part `builtin.name` is not always a
system built-in:
+ * with `spark.sql.legacy.persistentCatalogFirst=true`, an existing
persistent
+ * `current_catalog.builtin.name` takes precedence.
+ */
+ def functionNameResolvesToBuiltin(nameParts: Seq[String], expectedName:
String): Boolean = {
+ if (!FunctionRegistry.functionSet.contains(
+ FunctionRegistry.builtinFunctionIdentifier(expectedName)) ||
+ !FunctionResolution.isUnqualifiedOrBuiltinFunctionName(nameParts,
expectedName)) {
+ return false
+ }
+ nameParts.length match {
+ case 1 =>
+ unqualifiedFunctionResolvesToBuiltinBeforeAnyShadow(nameParts.head)
+ case 2 =>
+ conf.prioritizeSystemCatalog || !persistentFunctionExists(nameParts)
+ case 3 =>
+ true
+ case _ =>
+ false
+ }
+ }
+
+ // All routed SQL/JSON functions (JSON_ARRAY, JSON_VALUE, JSON_QUERY,
JSON_EXISTS) forbid a direct
+ // star argument (a bare `*` or a qualified `t.*`). Derived from the single
registry list so a
+ // newly routed function is covered without editing this file too.
+ private val starDisallowedJsonConstructors =
FunctionRegistry.routedJsonConstructorNames
+
+ /**
+ * True if `nameParts` resolves to Spark's stock built-in routed SQL/JSON
function that forbids a
+ * direct star. The `isStockBuiltinFunction` check excludes an
`injectFunction` replacement of
+ * the name, whose expanded star is passed through rather than rejected.
+ */
+ def resolvesToStarDisallowedJsonConstructor(nameParts: Seq[String]): Boolean
=
+ starDisallowedJsonConstructors.exists { name =>
+ functionNameResolvesToBuiltin(nameParts, name) &&
+ v1SessionCatalog.isStockBuiltinFunction(name)
+ }
+
+ private def persistentFunctionExists(nameParts: Seq[String]): Boolean = {
+ try {
+ // Expand through the view's frozen catalog/namespace exactly as
`resolveFunctionCandidate`
+ // does, so the shadow probe queries the same catalog the real resolver
would inside a view.
+ relationResolution.expandIdentifier(nameParts) match {
+ case CatalogAndIdentifier(catalog, ident) =>
+ catalog.asFunctionCatalog.functionExists(ident)
+ case _ =>
+ false
+ }
+ } catch {
Review Comment:
Done.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
