wombatu-kun commented on code in PR #18375:
URL: https://github.com/apache/hudi/pull/18375#discussion_r3071516627
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestSparkSqlCoreFlow.scala:
##########
@@ -47,24 +48,43 @@ class TestSparkSqlCoreFlow extends HoodieSparkSqlTestBase {
val colsToCompare = "timestamp, _row_key, partition_path, rider, driver,
begin_lat, begin_lon, end_lat, end_lon, fare.amount, fare.currency,
_hoodie_is_deleted"
//params for core flow tests
- val params: List[String] = List(
-
"COPY_ON_WRITE|false|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_BLOOM",
-
"COPY_ON_WRITE|true|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_BLOOM",
-
"COPY_ON_WRITE|false|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_SIMPLE",
-
"COPY_ON_WRITE|true|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_SIMPLE",
-
"COPY_ON_WRITE|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|BLOOM",
-
"COPY_ON_WRITE|true|org.apache.hudi.keygen.NonpartitionedKeyGenerator|BLOOM",
-
"COPY_ON_WRITE|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|SIMPLE",
-
"COPY_ON_WRITE|true|org.apache.hudi.keygen.NonpartitionedKeyGenerator|SIMPLE",
-
"MERGE_ON_READ|false|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_BLOOM",
-
"MERGE_ON_READ|true|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_BLOOM",
-
"MERGE_ON_READ|false|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_SIMPLE",
-
"MERGE_ON_READ|true|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_SIMPLE",
-
"MERGE_ON_READ|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|BLOOM",
-
"MERGE_ON_READ|true|org.apache.hudi.keygen.NonpartitionedKeyGenerator|BLOOM",
-
"MERGE_ON_READ|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|SIMPLE",
-
"MERGE_ON_READ|true|org.apache.hudi.keygen.NonpartitionedKeyGenerator|SIMPLE"
- )
+ val params: List[String] = {
+ val allParams: List[String] = List(
+
"COPY_ON_WRITE|false|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_BLOOM|parquet",
+
"COPY_ON_WRITE|true|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_BLOOM|parquet",
+
"COPY_ON_WRITE|false|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_SIMPLE|parquet",
+
"COPY_ON_WRITE|true|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_SIMPLE|parquet",
+
"COPY_ON_WRITE|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|BLOOM|parquet",
+
"COPY_ON_WRITE|true|org.apache.hudi.keygen.NonpartitionedKeyGenerator|BLOOM|parquet",
+
"COPY_ON_WRITE|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|SIMPLE|parquet",
+
"COPY_ON_WRITE|true|org.apache.hudi.keygen.NonpartitionedKeyGenerator|SIMPLE|parquet",
+
"MERGE_ON_READ|false|org.apache.hudi.keygen.SimpleKeyGenerator|GLOBAL_BLOOM|parquet",
Review Comment:
Fair point. Cut the Lance matrix from 16+32 to 4+4 representative rows — one
row per meaningful axis (COW/MOR × partitioned/non-partitioned × global/local
index for `params`; plus insert/bulk_insert for `paramsForImmutable`). Format
is orthogonal to keygen/index/metadata so the full cartesian added little
signal. Format-specific edge cases live in `TestLanceDataSource`.
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestLanceDataSource.scala:
##########
@@ -21,7 +21,7 @@ import org.apache.hudi.DataSourceWriteOptions._
import org.apache.hudi.DefaultSparkRecordMerger
import org.apache.hudi.common.config.{HoodieCommonConfig, HoodieMetadataConfig}
import org.apache.hudi.common.engine.HoodieLocalEngineContext
-import org.apache.hudi.common.model.HoodieTableType
+import org.apache.hudi.common.model.{HoodieFileFormat, HoodieTableType}
Review Comment:
Added: `testBasicWriteAndRead` now asserts both `SELECT count(*) FROM
<table>` (via a temp view) and `readDf.count()`, exercising the column-less
scan path in `SparkLanceReaderBase.read` (the `requiredSchema.isEmpty &&
partitionSchema.isEmpty` branch) that was previously returning `Iterator.empty`
→ `count = 0`.
--
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]
