nastra commented on code in PR #13859:
URL: https://github.com/apache/iceberg/pull/13859#discussion_r2285852772
##########
spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/data/vectorized/parquet/TestParquetVectorizedReads.java:
##########
@@ -39,27 +44,50 @@
import org.apache.iceberg.parquet.Parquet;
import org.apache.iceberg.relocated.com.google.common.base.Function;
import org.apache.iceberg.relocated.com.google.common.base.Strings;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList;
import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
import org.apache.iceberg.relocated.com.google.common.collect.Iterables;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
+import org.apache.iceberg.spark.SparkSchemaUtil;
import org.apache.iceberg.spark.data.AvroDataTestBase;
import org.apache.iceberg.spark.data.GenericsHelpers;
import org.apache.iceberg.spark.data.RandomData;
+import org.apache.iceberg.spark.data.SparkParquetReaders;
import org.apache.iceberg.spark.data.vectorized.VectorizedSparkParquetReaders;
+import org.apache.iceberg.types.Type.PrimitiveType;
import org.apache.iceberg.types.TypeUtil;
import org.apache.iceberg.types.Types;
import org.apache.parquet.column.ParquetProperties;
import org.apache.parquet.schema.GroupType;
import org.apache.parquet.schema.MessageType;
import org.apache.parquet.schema.Type;
+import org.apache.spark.sql.catalyst.InternalRow;
+import org.apache.spark.sql.catalyst.json.JSONOptions;
+import org.apache.spark.sql.catalyst.json.JacksonGenerator;
+import org.apache.spark.sql.types.StructType;
import org.apache.spark.sql.vectorized.ColumnarBatch;
import org.junit.jupiter.api.Test;
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.Arguments;
+import org.junit.jupiter.params.provider.MethodSource;
public class TestParquetVectorizedReads extends AvroDataTestBase {
private static final int NUM_ROWS = 200_000;
static final int BATCH_SIZE = 10_000;
+ private static final String PLAIN = "PLAIN";
+ private static final List<String> GOLDEN_FILE_ENCODINGS =
+ ImmutableList.of("PLAIN_DICTIONARY", "RLE_DICTIONARY",
"DELTA_BINARY_PACKED");
Review Comment:
@eric-maynard what do you mean by it's no longer in Spark 4 anymore? My main
point is that this doesn't seem to be a clean backport of the code that we have
for Spark 4 (which is fine if that's the case, but it's helpful to point that
out that the backport isn't clean for reviewers)
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
