yabola commented on code in PR #39950:
URL: https://github.com/apache/spark/pull/39950#discussion_r1153377375
##########
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetFooterReader.java:
##########
@@ -17,23 +17,53 @@
package org.apache.spark.sql.execution.datasources.parquet;
+import java.io.IOException;
+
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapred.FileSplit;
import org.apache.parquet.HadoopReadOptions;
import org.apache.parquet.ParquetReadOptions;
import org.apache.parquet.format.converter.ParquetMetadataConverter;
import org.apache.parquet.hadoop.ParquetFileReader;
import org.apache.parquet.hadoop.metadata.ParquetMetadata;
import org.apache.parquet.hadoop.util.HadoopInputFile;
-import java.io.IOException;
-
/**
* `ParquetFooterReader` is a util class which encapsulates the helper
* methods of reading parquet file footer
*/
public class ParquetFooterReader {
+
+ public static final boolean SKIP_ROW_GROUPS = true;
+ public static final boolean WITH_ROW_GROUPS = false;
+
+ /**
+ * method to read parquet file footer
+ *
+ * @param configuration hadoop configuration of file
+ * @param split file spit
+ * @param skipRowGroup If true, skip reading row groups;
+ * if false, read row groups according to the file range
+ */
+ public static ParquetMetadata readFooter(
+ Configuration configuration,
+ FileSplit split,
Review Comment:
done, I have changed to pass `PartitionedFile`
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
