This is an automated email from the ASF dual-hosted git repository.
zhli 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 5bd7e3f7e [VL] Enable levenshtein function (#6389)
5bd7e3f7e is described below
commit 5bd7e3f7e1914c8198313ea95e4cd346d36f6a88
Author: Zhen Li <[email protected]>
AuthorDate: Wed Jul 10 19:00:16 2024 +0800
[VL] Enable levenshtein function (#6389)
[VL] Enable levenshtein function.
---
.../gluten/execution/ScalarFunctionsValidateSuite.scala | 12 ++++++++++++
.../scalar_function_parser/CommonScalarFunctionParser.cpp | 2 +-
docs/velox-backend-support-progress.md | 2 +-
.../scala/org/apache/gluten/expression/ExpressionNames.scala | 2 +-
4 files changed, 15 insertions(+), 3 deletions(-)
diff --git
a/backends-velox/src/test/scala/org/apache/gluten/execution/ScalarFunctionsValidateSuite.scala
b/backends-velox/src/test/scala/org/apache/gluten/execution/ScalarFunctionsValidateSuite.scala
index 9d0a926e3..c8da6f79c 100644
---
a/backends-velox/src/test/scala/org/apache/gluten/execution/ScalarFunctionsValidateSuite.scala
+++
b/backends-velox/src/test/scala/org/apache/gluten/execution/ScalarFunctionsValidateSuite.scala
@@ -1189,4 +1189,16 @@ class ScalarFunctionsValidateSuite extends
FunctionsValidateTest {
}
}
}
+
+ test("levenshtein") {
+ runQueryAndCompare("select levenshtein(c_comment, c_address) from customer
limit 50") {
+ checkGlutenOperatorMatch[ProjectExecTransformer]
+ }
+ }
+
+ testWithSpecifiedSparkVersion("levenshtein with limit", Some("3.5")) {
+ runQueryAndCompare("select levenshtein(c_comment, c_address, 3) from
customer limit 50") {
+ checkGlutenOperatorMatch[ProjectExecTransformer]
+ }
+ }
}
diff --git
a/cpp-ch/local-engine/Parser/scalar_function_parser/CommonScalarFunctionParser.cpp
b/cpp-ch/local-engine/Parser/scalar_function_parser/CommonScalarFunctionParser.cpp
index ca90b0bdb..e4855b507 100644
---
a/cpp-ch/local-engine/Parser/scalar_function_parser/CommonScalarFunctionParser.cpp
+++
b/cpp-ch/local-engine/Parser/scalar_function_parser/CommonScalarFunctionParser.cpp
@@ -129,7 +129,7 @@ REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Translate,
translate, translateUTF8);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Initcap, initcap, initcapUTF8);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Conv, conv, sparkConv);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Uuid, uuid, generateUUIDv4);
-REGISTER_COMMON_SCALAR_FUNCTION_PARSER(LevenshteinDistance,
levenshteinDistance, editDistanceUTF8);
+REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Levenshtein, levenshtein,
editDistanceUTF8);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Crc32, crc32, CRC32);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Murmur3Hash, murmur3hash,
sparkMurmurHash3_32);
diff --git a/docs/velox-backend-support-progress.md
b/docs/velox-backend-support-progress.md
index f3f1e100b..5a2d53376 100644
--- a/docs/velox-backend-support-progress.md
+++ b/docs/velox-backend-support-progress.md
@@ -161,7 +161,7 @@ Gluten supports 199 functions. (Drag to right to see all
data types)
| lcase, lower | lower | lower
| S | | | | | | |
| | | | S | | | | |
| | | |
| left | |
| S | | | | | | |
| | | | S | | | | |
| | | |
| length | length | length
| S | | | | | | |
| | | | S | | | | |
| | | |
-| levenshtein | |
| | | | | | | |
| | | | | | | | |
| | | |
+| levenshtein | | levenshtein
| S | | | | |
| | | | | | | | |
| | | | | |
| locate | strpos |
| S | Mismatched | | | | | |
| | | | S | | | | |
| | | |
| lower | lower | lower
| S | | | | | | |
| | | | S | | | | |
| | | |
| lpad | lpad |
| S | | | | | | |
| | | | S | | | | |
| | | |
diff --git
a/shims/common/src/main/scala/org/apache/gluten/expression/ExpressionNames.scala
b/shims/common/src/main/scala/org/apache/gluten/expression/ExpressionNames.scala
index e3dc3a8ab..0b31ec346 100644
---
a/shims/common/src/main/scala/org/apache/gluten/expression/ExpressionNames.scala
+++
b/shims/common/src/main/scala/org/apache/gluten/expression/ExpressionNames.scala
@@ -128,7 +128,7 @@ object ExpressionNames {
final val UUID = "uuid"
final val BIT_LENGTH = "bit_length"
final val OCTET_LENGTH = "octet_length"
- final val LEVENSHTEIN = "levenshteinDistance"
+ final val LEVENSHTEIN = "levenshtein"
final val UNBASE64 = "unbase64"
final val BASE64 = "base64"
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
