fhueske commented on a change in pull request #8064: [FLINK-7244] Add parquet table source URL: https://github.com/apache/flink/pull/8064#discussion_r275994008
########## File path: flink-formats/flink-parquet/src/main/java/org/apache/flink/formats/parquet/ParquetTableSource.java ########## @@ -0,0 +1,482 @@ +/* + * 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.flink.formats.parquet; + +import org.apache.flink.annotation.VisibleForTesting; +import org.apache.flink.api.common.typeinfo.BasicTypeInfo; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.java.DataSet; +import org.apache.flink.api.java.ExecutionEnvironment; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.api.java.typeutils.RowTypeInfo; +import org.apache.flink.core.fs.Path; +import org.apache.flink.formats.parquet.utils.ParquetSchemaConverter; +import org.apache.flink.table.api.TableSchema; +import org.apache.flink.table.expressions.And; +import org.apache.flink.table.expressions.Attribute; +import org.apache.flink.table.expressions.BinaryComparison; +import org.apache.flink.table.expressions.BinaryExpression; +import org.apache.flink.table.expressions.EqualTo; +import org.apache.flink.table.expressions.Expression; +import org.apache.flink.table.expressions.GreaterThan; +import org.apache.flink.table.expressions.GreaterThanOrEqual; +import org.apache.flink.table.expressions.LessThan; +import org.apache.flink.table.expressions.LessThanOrEqual; +import org.apache.flink.table.expressions.Literal; +import org.apache.flink.table.expressions.Not; +import org.apache.flink.table.expressions.NotEqualTo; +import org.apache.flink.table.expressions.Or; +import org.apache.flink.table.sources.BatchTableSource; +import org.apache.flink.table.sources.FilterableTableSource; +import org.apache.flink.table.sources.ProjectableTableSource; +import org.apache.flink.table.sources.TableSource; +import org.apache.flink.types.Row; +import org.apache.flink.util.Preconditions; + +import org.apache.hadoop.conf.Configuration; +import org.apache.parquet.filter2.predicate.FilterApi; +import org.apache.parquet.filter2.predicate.FilterPredicate; +import org.apache.parquet.filter2.predicate.Operators; +import org.apache.parquet.filter2.predicate.Operators.BinaryColumn; +import org.apache.parquet.filter2.predicate.Operators.BooleanColumn; +import org.apache.parquet.filter2.predicate.Operators.Column; +import org.apache.parquet.filter2.predicate.Operators.DoubleColumn; +import org.apache.parquet.filter2.predicate.Operators.FloatColumn; +import org.apache.parquet.filter2.predicate.Operators.IntColumn; +import org.apache.parquet.filter2.predicate.Operators.LongColumn; +import org.apache.parquet.io.api.Binary; +import org.apache.parquet.schema.MessageType; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.util.List; + +/** + * A TableSource to read Parquet files. + * + * <p>The {@link ParquetTableSource} supports projection and filter push-down.</p> + * + * <p>An {@link ParquetTableSource} is used as shown in the example below. + */ +public class ParquetTableSource + implements BatchTableSource<Row>, FilterableTableSource<Row>, ProjectableTableSource<Row> { + + private static final Logger LOG = LoggerFactory.getLogger(ParquetTableSource.class); + + // path to read Parquet files from + private final String path; + // schema of the Parquet file + private final MessageType parquetSchema; + // the schema of table + private final TableSchema tableSchema; + // the configuration to read the file + private final Configuration parquetConfig; + + // type information of the data returned by the InputFormat + private final RowTypeInfo typeInfo; + // list of selected Parquet fields to return + private final int[] selectedFields; + // list of predicates to apply Review comment: change to `predicate expressions to apply` since it's not really a list? ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services
