the-other-tim-brown commented on code in PR #13882:
URL: https://github.com/apache/hudi/pull/13882#discussion_r2345032403
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/io/storage/row/HoodieRowParquetWriteSupport.java:
##########
@@ -18,47 +18,149 @@
package org.apache.hudi.io.storage.row;
+import org.apache.hudi.HoodieSparkUtils;
+import org.apache.hudi.SparkAdapterSupport;
+import org.apache.hudi.avro.HoodieAvroUtils;
import org.apache.hudi.avro.HoodieBloomFilterWriteSupport;
import org.apache.hudi.common.bloom.BloomFilter;
import org.apache.hudi.common.config.HoodieConfig;
import org.apache.hudi.common.config.HoodieStorageConfig;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.common.util.ReflectionUtils;
+import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.internal.schema.convert.AvroInternalSchemaConverter;
+import org.apache.hudi.internal.schema.utils.SerDeHelper;
+import org.apache.avro.LogicalType;
+import org.apache.avro.LogicalTypes;
+import org.apache.avro.Schema;
import org.apache.hadoop.conf.Configuration;
+import org.apache.parquet.avro.AvroSchemaConverter;
+import org.apache.parquet.avro.AvroWriteSupport;
import org.apache.parquet.hadoop.api.WriteSupport;
+import org.apache.parquet.io.api.Binary;
+import org.apache.parquet.io.api.RecordConsumer;
+import org.apache.parquet.schema.MessageType;
+import org.apache.spark.sql.HoodieInternalRowUtils;
+import org.apache.spark.sql.catalyst.InternalRow;
+import org.apache.spark.sql.catalyst.expressions.SpecializedGetters;
+import org.apache.spark.sql.catalyst.util.ArrayData;
+import org.apache.spark.sql.catalyst.util.DateTimeUtils;
+import org.apache.spark.sql.catalyst.util.MapData;
+import org.apache.spark.sql.execution.datasources.DataSourceUtils;
import org.apache.spark.sql.execution.datasources.parquet.ParquetWriteSupport;
+import org.apache.spark.sql.internal.SQLConf;
+import org.apache.spark.sql.types.ArrayType;
+import org.apache.spark.sql.types.DataType;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.sql.types.Decimal;
+import org.apache.spark.sql.types.DecimalType;
+import org.apache.spark.sql.types.MapType;
import org.apache.spark.sql.types.StructType;
+import org.apache.spark.sql.types.TimestampNTZType;
import org.apache.spark.unsafe.types.UTF8String;
+import org.apache.spark.util.VersionUtils;
import java.util.Collections;
+import java.util.HashMap;
import java.util.Map;
+import java.util.stream.IntStream;
+import scala.Enumeration;
+import scala.Function1;
+
+import static org.apache.hudi.avro.AvroSchemaUtils.resolveNullableSchema;
import static
org.apache.hudi.common.config.HoodieStorageConfig.PARQUET_FIELD_ID_WRITE_ENABLED;
/**
- * Hoodie Write Support for directly writing Row to Parquet.
+ * Hoodie Write Support for directly writing Row to Parquet and adding the
Hudi bloom index to the file metadata.
+ * The implementation is adapted from Spark's {@link
org.apache.spark.sql.execution.datasources.parquet.ParquetWriteSupport} but has
the following major differences:
+ * <ul>
+ * <li>Decimals are always written with the legacy format to ensure
compatibility with parquet-avro and other readers</li>
+ * <li>Writing 2-level or 3-level lists is configurable with either the Hudi
option, hoodie.parquet.writelegacyformat.enabled, or the parquet-avro option,
parquet.avro.write-old-list-structure
+ * to ensure consistency across writer paths.</li>
Review Comment:
it will exceed the line length limit
--
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]
