jonvex commented on code in PR #10957:
URL: https://github.com/apache/hudi/pull/10957#discussion_r1571162253
##########
hudi-spark-datasource/hudi-spark-common/src/test/scala/org/apache/spark/execution/datasources/parquet/TestHoodieFileGroupReaderBasedParquetFileFormat.scala:
##########
@@ -34,63 +32,17 @@ class TestHoodieFileGroupReaderBasedParquetFileFormat
extends SparkClientFunctio
IsNotNull("non_key_column"),
EqualTo("non_key_column", 1)
)
- val filtersWithoutKeyColumn =
HoodieFileGroupReaderBasedParquetFileFormat.getRecordKeyRelatedFilters(
+ val filtersWithoutKeyColumn =
SparkFileFormatInternalRowReaderContext.getRecordKeyRelatedFilters(
filters, "key_column");
assertEquals(0, filtersWithoutKeyColumn.size)
val filtersWithKeys = Seq(
EqualTo("key_column", 1),
GreaterThan("non_key_column", 2)
)
- val filtersWithKeyColumn =
HoodieFileGroupReaderBasedParquetFileFormat.getRecordKeyRelatedFilters(
+ val filtersWithKeyColumn =
SparkFileFormatInternalRowReaderContext.getRecordKeyRelatedFilters(
filtersWithKeys, "key_column")
assertEquals(1, filtersWithKeyColumn.size)
assertEquals("key_column", filtersWithKeyColumn.head.references.head)
}
-
- @Test
- def testGetAppliedRequiredSchema(): Unit = {
- val fields = Array(
- StructField("column_a", LongType, nullable = false),
- StructField("column_b", StringType, nullable = false))
- val requiredSchema = StructType(fields)
-
- val appliedSchema: StructType =
HoodieFileGroupReaderBasedParquetFileFormat.getAppliedRequiredSchema(
- requiredSchema, shouldUseRecordPosition = true, "row_index")
- if (HoodieSparkUtils.gteqSpark3_5) {
- assertEquals(3, appliedSchema.fields.length)
- } else {
- assertEquals(2, appliedSchema.fields.length)
- }
-
- val schemaWithoutRowIndexColumn =
HoodieFileGroupReaderBasedParquetFileFormat.getAppliedRequiredSchema(
- requiredSchema, shouldUseRecordPosition = false, "row_index")
- assertEquals(2, schemaWithoutRowIndexColumn.fields.length)
- }
-
- @Test
- def testGetAppliedFilters(): Unit = {
- val filters = Seq(
Review Comment:
No. They don't make sense anymore.
##########
hudi-spark-datasource/hudi-spark-common/src/test/scala/org/apache/spark/execution/datasources/parquet/TestHoodieFileGroupReaderBasedParquetFileFormat.scala:
##########
@@ -34,63 +32,17 @@ class TestHoodieFileGroupReaderBasedParquetFileFormat
extends SparkClientFunctio
IsNotNull("non_key_column"),
EqualTo("non_key_column", 1)
)
- val filtersWithoutKeyColumn =
HoodieFileGroupReaderBasedParquetFileFormat.getRecordKeyRelatedFilters(
+ val filtersWithoutKeyColumn =
SparkFileFormatInternalRowReaderContext.getRecordKeyRelatedFilters(
filters, "key_column");
assertEquals(0, filtersWithoutKeyColumn.size)
val filtersWithKeys = Seq(
EqualTo("key_column", 1),
GreaterThan("non_key_column", 2)
)
- val filtersWithKeyColumn =
HoodieFileGroupReaderBasedParquetFileFormat.getRecordKeyRelatedFilters(
+ val filtersWithKeyColumn =
SparkFileFormatInternalRowReaderContext.getRecordKeyRelatedFilters(
filtersWithKeys, "key_column")
assertEquals(1, filtersWithKeyColumn.size)
assertEquals("key_column", filtersWithKeyColumn.head.references.head)
}
-
- @Test
- def testGetAppliedRequiredSchema(): Unit = {
- val fields = Array(
- StructField("column_a", LongType, nullable = false),
- StructField("column_b", StringType, nullable = false))
- val requiredSchema = StructType(fields)
-
- val appliedSchema: StructType =
HoodieFileGroupReaderBasedParquetFileFormat.getAppliedRequiredSchema(
- requiredSchema, shouldUseRecordPosition = true, "row_index")
- if (HoodieSparkUtils.gteqSpark3_5) {
- assertEquals(3, appliedSchema.fields.length)
- } else {
- assertEquals(2, appliedSchema.fields.length)
- }
-
- val schemaWithoutRowIndexColumn =
HoodieFileGroupReaderBasedParquetFileFormat.getAppliedRequiredSchema(
- requiredSchema, shouldUseRecordPosition = false, "row_index")
- assertEquals(2, schemaWithoutRowIndexColumn.fields.length)
- }
-
- @Test
- def testGetAppliedFilters(): Unit = {
- val filters = Seq(
Review Comment:
No. They don't make sense anymore to have.
--
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]
