Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[GLUTEN-6813][CH] Support soundex function #7093

Merged
merged 4 commits into from
Sep 5, 2024
Merged

[GLUTEN-6813][CH] Support soundex function #7093

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
34b4a39
support soundex function
taiyang-li Sep 3, 2024
5914798
add uts
taiyang-li Sep 4, 2024
fc9efea
fix style
taiyang-li Sep 4, 2024
51ed143
fix failed uts
taiyang-li Sep 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion backends-clickhouse/src/main/scala/org/apache/gluten/utils/CHExpressionUtil.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,7 +207,6 @@ object CHExpressionUtil {
URL_ENCODE -> DefaultValidator(),
FORMAT_STRING -> FormatStringValidator(),
SKEWNESS -> DefaultValidator(),
SOUNDEX -> DefaultValidator(),
MAKE_YM_INTERVAL -> DefaultValidator(),
MAP_ZIP_WITH -> DefaultValidator(),
ZIP_WITH -> DefaultValidator(),
Expand Down
6 changes: 6 additions & 0 deletions ...est/scala/org/apache/gluten/execution/tpch/GlutenClickHouseTPCHSaltNullParquetSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2936,5 +2936,11 @@ class GlutenClickHouseTPCHSaltNullParquetSuite extends GlutenClickHouseTPCHAbstr
checkBHJWithIsNullAwareAntiJoin(df)
})
}

test("soundex") {
runQueryAndCompare("select soundex(c_mktsegment) from customer limit 50") {
checkGlutenOperatorMatch[ProjectExecTransformer]
}
}
}
// scalastyle:on line.size.limit
3 changes: 2 additions & 1 deletion cpp-ch/local-engine/Parser/scalar_function_parser/CommonScalarFunctionParser.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ REGISTER_COMMON_SCALAR_FUNCTION_PARSER(LT, lt, less);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(And, and, and);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Or, or, or);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Equal, equal, equals);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Not, not, not);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Not, not, not );
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Xor, xor, xor);

REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Cast, cast, CAST);
Expand Down Expand Up @@ -134,6 +134,7 @@ REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Uuid, uuid, generateUUIDv4);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Levenshtein, levenshtein, editDistanceUTF8);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(FormatString, format_string, printf);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Concat, concat, concat);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(SoundEx, soundex, soundex);

REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Crc32, crc32, CRC32);
REGISTER_COMMON_SCALAR_FUNCTION_PARSER(Murmur3Hash, murmur3hash, sparkMurmurHash3_32);
Expand Down
3 changes: 3 additions & 0 deletions ...ut/spark32/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -911,6 +911,9 @@ class ClickHouseTestSettings extends BackendTestSettings {
.exclude("ParseUrl")
.exclude("SPARK-33468: ParseUrl in ANSI mode should fail if input string is not a valid url")
.exclude("FORMAT") // refer https://github.com/apache/incubator-gluten/issues/6765
.exclude(
"soundex unit test"
) // CH and spark returns different results when input non-ASCII characters
.excludeGlutenTest("SPARK-40213: ascii for Latin-1 Supplement characters")
enableSuite[GlutenTryCastSuite]
.exclude("null cast")
Expand Down
3 changes: 3 additions & 0 deletions ...ut/spark33/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -907,6 +907,9 @@ class ClickHouseTestSettings extends BackendTestSettings {
.exclude("ParseUrl")
.exclude("SPARK-33468: ParseUrl in ANSI mode should fail if input string is not a valid url")
.exclude("FORMAT") // refer https://github.com/apache/incubator-gluten/issues/6765
.exclude(
"soundex unit test"
) // CH and spark returns different results when input non-ASCII characters
enableSuite[GlutenTryCastSuite]
.exclude("null cast")
.exclude("cast string to date")
Expand Down
3 changes: 3 additions & 0 deletions ...ut/spark34/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -811,6 +811,9 @@ class ClickHouseTestSettings extends BackendTestSettings {
.exclude("ParseUrl")
.exclude("SPARK-33468: ParseUrl in ANSI mode should fail if input string is not a valid url")
.exclude("FORMAT") // refer https://github.com/apache/incubator-gluten/issues/6765
.exclude(
"soundex unit test"
) // CH and spark returns different results when input non-ASCII characters
enableSuite[GlutenDataSourceV2DataFrameSessionCatalogSuite]
enableSuite[GlutenDataSourceV2SQLSessionCatalogSuite]
enableSuite[GlutenDataSourceV2SQLSuiteV1Filter]
Expand Down
3 changes: 3 additions & 0 deletions ...ut/spark35/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -811,6 +811,9 @@ class ClickHouseTestSettings extends BackendTestSettings {
.exclude("ParseUrl")
.exclude("SPARK-33468: ParseUrl in ANSI mode should fail if input string is not a valid url")
.exclude("FORMAT") // refer https://github.com/apache/incubator-gluten/issues/6765
.exclude(
"soundex unit test"
) // CH and spark returns different results when input non-ASCII characters
enableSuite[GlutenDataSourceV2DataFrameSessionCatalogSuite]
enableSuite[GlutenDataSourceV2SQLSessionCatalogSuite]
enableSuite[GlutenDataSourceV2SQLSuiteV1Filter]
Expand Down
Loading