hudi-agent commented on code in PR #19853:
URL: https://github.com/apache/hudi/pull/19853#discussion_r3995591465
##########
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/procedures/HoodieProcedureFilterUtils.scala:
##########
@@ -389,6 +416,154 @@ 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 instead of letting eval() throw silently.
+ private def resolveViaFunctionRegistry(unresolvedFunc: UnresolvedFunction,
sparkSession: SparkSession): Expression = {
+ Try {
+ val castedResolved =
applySparkAnalyzerCoercionRules(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
+ }
+ }
+
+ // Runs a handful of the analyzer's own coercion rules on a single
expression, the same rules
+ // lookupFunction skips: ImplicitTypeCasts for nodes declaring a real
input-type contract,
+ // FunctionArgumentConversion/ConcatCoercion/IfCoercion for the builtins
whose argument types get
+ // unified before the type check even sees them (concat(id, 'x') casts the
Int to String via
+ // ConcatCoercion in a real query; without it Concat.checkInputDataTypes
just fails). Order
+ // mirrors TypeCoercion's own rule list - ImplicitTypeCasts last, as a
catch-all. Anything not
+ // covered by one of these four passes through unchanged.
+ private def applySparkAnalyzerCoercionRules(expression: Expression):
Expression = {
+ val engine: TypeCoercionBase = if (SQLConf.get.ansiEnabled)
AnsiTypeCoercion else TypeCoercion
+ Seq(engine.FunctionArgumentConversion, engine.ConcatCoercion,
engine.IfCoercion, engine.ImplicitTypeCasts)
+ .foldLeft(expression) { (expr, rule) => rule.transform.applyOrElse(expr,
identity[Expression]) }
+ }
+
+ // 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(applyHudiWideningRules)
+ 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
= {
+ val bareIdentifier = FunctionIdentifier(funcName)
+ if (HoodieSparkUtils.gteqSpark4_2) {
+ // FunctionIdentifier only gained the catalog parameter from Spark 3.4
onward - this file
+ // still compiles against 3.3 too, where the case class has just
funcName/database, so a
+ // direct 3-arg call wouldn't compile there. Reached through reflection
instead, the same way
+ // the With handling below reaches classes that don't exist on every
targeted version.
+ bareIdentifier.getClass
Review Comment:
🤖 nit: could you use `classOf[FunctionIdentifier].getConstructor(...)` here
instead of going through `bareIdentifier.getClass`? Then `bareIdentifier` only
needs to be built in the `else` branch, which makes it clearer the 4.2+ path
never uses the bare identifier at all.
<sub><i>⚠️ AI-generated; verify before applying. React 👍/👎 to flag
quality.</i></sub>
--
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]
