yihua commented on code in PR #5364:
URL: https://github.com/apache/hudi/pull/5364#discussion_r853620708
##########
hudi-spark-datasource/hudi-spark3/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark32HoodieParquetFileFormat.scala:
##########
@@ -27,233 +25,262 @@ import org.apache.hadoop.mapreduce.{JobID, TaskAttemptID,
TaskID, TaskType}
import org.apache.hudi.client.utils.SparkInternalSchemaConverter
import org.apache.hudi.common.fs.FSUtils
import org.apache.hudi.common.util.InternalSchemaCache
+import org.apache.hudi.common.util.StringUtils.isNullOrEmpty
import org.apache.hudi.common.util.collection.Pair
import org.apache.hudi.internal.schema.InternalSchema
import org.apache.hudi.internal.schema.action.InternalSchemaMerger
import org.apache.hudi.internal.schema.utils.{InternalSchemaUtils, SerDeHelper}
import org.apache.parquet.filter2.compat.FilterCompat
import org.apache.parquet.filter2.predicate.FilterApi
import
org.apache.parquet.format.converter.ParquetMetadataConverter.SKIP_ROW_GROUPS
-import org.apache.parquet.hadoop.{ParquetFileReader, ParquetInputFormat,
ParquetRecordReader}
+import org.apache.parquet.hadoop.{ParquetInputFormat, ParquetRecordReader}
import org.apache.spark.TaskContext
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.{Cast, JoinedRow}
import
org.apache.spark.sql.catalyst.expressions.codegen.GenerateUnsafeProjection
import org.apache.spark.sql.catalyst.util.DateTimeUtils
+import
org.apache.spark.sql.execution.datasources.parquet.Spark32HoodieParquetFileFormat.{pruneInternalSchema,
rebuildFilterFromParquet}
import org.apache.spark.sql.execution.datasources.{DataSourceUtils,
PartitionedFile, RecordReaderIterator}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.sources._
import org.apache.spark.sql.types.{AtomicType, DataType, StructField,
StructType}
import org.apache.spark.util.SerializableConfiguration
-class Spark32HoodieParquetFileFormat extends ParquetFileFormat {
-
- // reference ParquetFileFormat from spark project
- override def buildReaderWithPartitionValues(
- sparkSession: SparkSession,
- dataSchema: StructType,
- partitionSchema: StructType,
- requiredSchema: StructType,
- filters: Seq[Filter],
- options: Map[String, String],
- hadoopConf: Configuration):
PartitionedFile => Iterator[InternalRow] = {
- if (hadoopConf.get(SparkInternalSchemaConverter.HOODIE_QUERY_SCHEMA,
"").isEmpty) {
- // fallback to origin parquet File read
- super.buildReaderWithPartitionValues(sparkSession, dataSchema,
partitionSchema, requiredSchema, filters, options, hadoopConf)
Review Comment:
Sg
--
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]
