[GitHub] [beam] iemejia commented on a change in pull request #14117: [BEAM-7929] Support column projection for Parquet Tables

[GitBox <gi...@apache.org>]

iemejia commented on a change in pull request #14117:
URL: https://github.com/apache/beam/pull/14117#discussion_r584283424



##########
File path: sdks/java/extensions/sql/src/main/java/org/apache/beam/sdk/extensions/sql/meta/provider/parquet/ParquetTable.java
##########
@@ -0,0 +1,119 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.beam.sdk.extensions.sql.meta.provider.parquet;
+
+import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+import org.apache.avro.Schema;
+import org.apache.avro.Schema.Field;
+import org.apache.avro.generic.GenericRecord;
+import org.apache.beam.sdk.annotations.Internal;
+import org.apache.beam.sdk.extensions.sql.impl.BeamTableStatistics;
+import org.apache.beam.sdk.extensions.sql.meta.BeamSqlTableFilter;
+import org.apache.beam.sdk.extensions.sql.meta.ProjectSupport;
+import org.apache.beam.sdk.extensions.sql.meta.SchemaBaseBeamTable;
+import org.apache.beam.sdk.extensions.sql.meta.Table;
+import org.apache.beam.sdk.io.FileIO;
+import org.apache.beam.sdk.io.parquet.ParquetIO;
+import org.apache.beam.sdk.io.parquet.ParquetIO.Read;
+import org.apache.beam.sdk.options.PipelineOptions;
+import org.apache.beam.sdk.schemas.transforms.Convert;
+import org.apache.beam.sdk.schemas.utils.AvroUtils;
+import org.apache.beam.sdk.values.PBegin;
+import org.apache.beam.sdk.values.PCollection;
+import org.apache.beam.sdk.values.PCollection.IsBounded;
+import org.apache.beam.sdk.values.POutput;
+import org.apache.beam.sdk.values.Row;
+
+@Internal
+@SuppressWarnings({"nullness"})
+class ParquetTable extends SchemaBaseBeamTable implements Serializable {
+  private final Table table;
+
+  ParquetTable(Table table) {
+    super(table.getSchema());
+    this.table = table;
+  }
+
+  @Override
+  public PCollection<Row> buildIOReader(PBegin begin) {
+    final Schema schema = AvroUtils.toAvroSchema(table.getSchema());
+    Read read = ParquetIO.read(schema).withBeamSchemas(true).from(table.getLocation() + "/*");
+    return begin.apply("ParquetIORead", read).apply("ToRows", Convert.toRows());
+  }
+
+  @Override
+  public PCollection<Row> buildIOReader(
+      PBegin begin, BeamSqlTableFilter filters, List<String> fieldNames) {
+    final Schema schema = AvroUtils.toAvroSchema(table.getSchema());
+    Read read = ParquetIO.read(schema).withBeamSchemas(true).from(table.getLocation() + "/*");
+    if (!fieldNames.isEmpty()) {
+      Schema projectionSchema = projectSchema(schema, fieldNames);
+      read = read.withProjection(projectionSchema, projectionSchema);

Review comment:
       Requiring two schemas is a bit odd but I will fix this in a future PR in the ParquetIO side




----------------------------------------------------------------
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.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org