anshulsingh-py commented on code in PR #19853:
URL: https://github.com/apache/hudi/pull/19853#discussion_r3977268360
##########
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/procedures/HoodieProcedureFilterUtils.scala:
##########
@@ -737,6 +906,19 @@ object HoodieProcedureFilterUtils {
}
}
+ // Runs a handful of the analyzer's own coercion rules on a single
expression, the same rules
Review Comment:
Moved `applyImplicitCasts` directly after `resolveViaFunctionRegistry`, its
only caller.
##########
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/procedures/HoodieProcedureFilterUtils.scala:
##########
@@ -389,6 +419,136 @@ object HoodieProcedureFilterUtils {
}
}
+ // Resolves a function not covered by the hardcoded table above via Spark's
own FunctionRegistry,
+ // then checks the result is actually usable outside a real query plan -
both steps a plain
+ // lookupFunction call skips or can't tell on its own. Anything that isn't
falls through to the
+ // existing rejection path (see #19850) instead of letting eval() throw
silently.
+ private def resolveViaFunctionRegistry(unresolvedFunc: UnresolvedFunction,
sparkSession: SparkSession): Expression = {
+ Try {
+ val castedResolved = applyImplicitCasts(lookupBuiltin(unresolvedFunc,
sparkSession))
+ // Checked here, on the raw wrapper, before unwrapping: a
RuntimeReplaceable wrapper's own
+ // declared input-type contract (nvl needing matching operand types,
split_part needing
+ // string/string/int) is otherwise discarded once unwrapped to a form
with a weaker or
+ // absent contract of its own.
+ if (!castedResolved.checkInputDataTypes().isSuccess) {
+ unresolvedFunc
+ } else {
+ val finalized = finalizeRegistryResolution(castedResolved)
+ if (isUsableOutsideQueryPlan(finalized)) finalized else unresolvedFunc
+ }
+ } match {
+ case Success(resolved) => resolved
+ case Failure(_) => unresolvedFunc
+ }
+ }
+
+ // Filter expressions only ever call plain builtins. A db-qualified or 3+
part name (db.func,
+ // catalog.db.func) can only be resolved by guessing which part is the real
function name - that
+ // risks matching an unrelated same-named function, so those are left
unresolved instead.
+ //
+ // Each argument gets widened before the lookup, not just the call's own
result afterward: an
+ // argument like ts + 1 (Long + Int) is still an unresolved Add at this
point, and the wrapper's
+ // checkInputDataTypes right after runs before pass three ever gets a chance
to widen it -
+ // sqrt(ts + 1) would fail that check for the same reason nvl(ts, 0) needed
pre-lookup widening,
+ // while the hardcoded abs(ts + 1) already works because pass three widens
its argument too, just
+ // later in the pipeline.
+ private def lookupBuiltin(unresolvedFunc: UnresolvedFunction, sparkSession:
SparkSession): Expression =
+ unresolvedFunc.nameParts match {
+ case Seq(funcName) =>
+ val widenedArguments = unresolvedFunc.arguments.map(applyCoercionRules)
+ sparkSession.sessionState.functionRegistry
+ .lookupFunction(builtinFunctionIdentifier(funcName),
widenedArguments)
+ case _ => unresolvedFunc
+ }
+
+ // A session's function registry is a clone of FunctionRegistry.builtin,
keyed the same way
+ // builtins are actually registered - a bare name pre-4.2, but the fully
qualified
+ // system.builtin.<name> from 4.2 onward, where a session-level clone
(unlike the builtin
+ // singleton itself) stops auto-qualifying a bare name it's given and
asserts instead.
+ private def builtinFunctionIdentifier(funcName: String): FunctionIdentifier =
+ if (HoodieSparkUtils.gteqSpark4_2) {
+ FunctionIdentifier(funcName, Some("builtin"), Some("system"))
+ } else {
+ FunctionIdentifier(funcName)
+ }
+
+ // RuntimeReplaceable placeholders (nvl, ifnull, left, right, ...) need
substitution the analyzer
+ // normally performs but lookupFunction skips, and can themselves unwrap to
another
+ // RuntimeReplaceable (regexp_substr -> NullIf), so the unwrap runs to a
fixed point. Then widens
+ // numeric operands the same way pass three would - nvl(ts, 0) unwraps to
Coalesce(ts, 0), which
+ // needs the same widening the hardcoded coalesce(ts, 0) case gets - so a
registry function and
+ // its hardcoded-table equivalent agree on what counts as resolved.
+ //
+ // A replacement can itself be a With(child, defs) common-subexpression
wrapper from 4.0 onward
+ // (NullIf's, for instance) - Unevaluable like any other holder, so it needs
inlining here too or
+ // isUsableOutsideQueryPlan rejects it outright.
With/CommonExpressionDef/CommonExpressionRef
+ // don't exist before 4.0, so this goes by reflection rather than a direct
import; evaluating a
+ // filter once per row rather than once per query makes the dedup With
exists for irrelevant, so
+ // inlining each reference in place of its definition is exactly equivalent
to keeping it.
+ private def finalizeRegistryResolution(expression: Expression): Expression =
{
+ def unwrapReplacements(expr: Expression): Expression = {
+ val next = expr.transformUp {
+ case r: RuntimeReplaceable => r.replacement
+ case withExpr if withExpr.getClass.getSimpleName == "With" =>
inlineCommonExpressions(withExpr)
+ }
+ if (next.fastEquals(expr)) next else unwrapReplacements(next)
Review Comment:
Extracted into `isWithNode`/`isCommonExpressionRef`, both used from
`finalizeRegistryResolution` and `inlineCommonExpressions` now.
--
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]
