vingov commented on a change in pull request #2896: URL: https://github.com/apache/hudi/pull/2896#discussion_r648015740
########## File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/SqlSource.java ########## @@ -0,0 +1,79 @@ +/* + * 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.hudi.utilities.sources; + +import org.apache.hudi.DataSourceUtils; +import org.apache.hudi.common.config.TypedProperties; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.collection.Pair; +import org.apache.hudi.utilities.schema.SchemaProvider; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; + +import java.util.Collections; + +/** + * SQL Source that reads from any table, used mainly for backfill jobs which will process specific partition dates. + */ +public class SqlSource extends RowSource { + private static final long serialVersionUID = 1L; + private static final Logger LOG = LogManager.getLogger(SqlSource.class); + private final String sourceSql; + private final SparkSession spark; + + public SqlSource( + TypedProperties props, + JavaSparkContext sparkContext, + SparkSession sparkSession, + SchemaProvider schemaProvider) { + super(props, sparkContext, sparkSession, schemaProvider); + DataSourceUtils.checkRequiredProperties( + props, Collections.singletonList(SqlSource.Config.SOURCE_SQL)); + sourceSql = props.getString(SqlSource.Config.SOURCE_SQL); + spark = sparkSession; + } + + @Override + protected Pair<Option<Dataset<Row>>, String> fetchNextBatch( + Option<String> lastCkptStr, long sourceLimit) { + LOG.warn(sourceSql); + Dataset<Row> source = spark.sql(sourceSql); + LOG.warn(source.showString(10, 0, true)); + // Remove Hoodie meta columns except partition path from input source. + Dataset<Row> src = + source.drop( + HoodieRecord.HOODIE_META_COLUMNS.stream() + .filter(x -> !x.equals(HoodieRecord.PARTITION_PATH_METADATA_FIELD)) + .toArray(String[]::new)); + return Pair.of(Option.of(src), null); + } + + /** + * Configs supported. + */ + private static class Config { + + private static final String SOURCE_SQL = "hoodie.deltastreamer.source.sql"; Review comment: got it, updated the same. -- 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
