This is an automated email from the ASF dual-hosted git repository.
yao pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-gluten.git
The following commit(s) were added to refs/heads/main by this push:
new a8f3f0c8fa [GLUTEN-11016][VL] Validate regex pattern of spilt function
(#11017)
a8f3f0c8fa is described below
commit a8f3f0c8fa0684f978c768da1b4b9f305817ad98
Author: Zhen Wang <[email protected]>
AuthorDate: Wed Nov 5 11:00:42 2025 +0800
[GLUTEN-11016][VL] Validate regex pattern of spilt function (#11017)
* [GLUTEN-11016][VL] Validate regex pattern of spilt function
* test
---
.../test/scala/org/apache/gluten/execution/FallbackSuite.scala | 8 ++++++++
cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc | 3 ++-
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git
a/backends-velox/src/test/scala/org/apache/gluten/execution/FallbackSuite.scala
b/backends-velox/src/test/scala/org/apache/gluten/execution/FallbackSuite.scala
index c357e488b6..70ef9e19ec 100644
---
a/backends-velox/src/test/scala/org/apache/gluten/execution/FallbackSuite.scala
+++
b/backends-velox/src/test/scala/org/apache/gluten/execution/FallbackSuite.scala
@@ -304,4 +304,12 @@ class FallbackSuite extends
VeloxWholeStageTransformerSuite with AdaptiveSparkPl
}
}
}
+
+ test("fallback on spilt with unsupported regex") {
+ runQueryAndCompare("SELECT split(cast(c1 as string),
'(?<=\\\\}),(?=\\\\{)') from tmp1") {
+ df =>
+ val columnarToRow =
collectColumnarToRow(df.queryExecution.executedPlan)
+ assert(columnarToRow == 1)
+ }
+ }
}
diff --git a/cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc
b/cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc
index ad6c0e15a8..ae66c7e5f0 100644
--- a/cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc
+++ b/cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc
@@ -56,7 +56,8 @@ const std::unordered_set<std::string> kRegexFunctions = {
"regexp_extract",
"regexp_extract_all",
"regexp_replace",
- "rlike"};
+ "rlike",
+ "split"};
const std::unordered_set<std::string> kBlackList =
{"split_part", "sequence", "approx_percentile", "map_from_arrays"};
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
