org.apache.hudi.utilities.sources.SqlFileBasedSource Maven / Gradle / Ivy
/*
* 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.common.config.TypedProperties;
import org.apache.hudi.common.table.checkpoint.Checkpoint;
import org.apache.hudi.common.table.checkpoint.StreamerCheckpointV2;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.common.util.collection.Pair;
import org.apache.hudi.exception.HoodieIOException;
import org.apache.hudi.hadoop.fs.HadoopFSUtils;
import org.apache.hudi.utilities.schema.SchemaProvider;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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 org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.IOException;
import java.util.Collections;
import java.util.Scanner;
import static org.apache.hudi.common.util.ConfigUtils.checkRequiredConfigProperties;
import static org.apache.hudi.common.util.ConfigUtils.getBooleanWithAltKeys;
import static org.apache.hudi.common.util.ConfigUtils.getStringWithAltKeys;
import static org.apache.hudi.utilities.config.SqlFileBasedSourceConfig.EMIT_EPOCH_CHECKPOINT;
import static org.apache.hudi.utilities.config.SqlFileBasedSourceConfig.SOURCE_SQL_FILE;
/**
* File-based SQL Source that uses SQL queries in a file to read from any table.
*
* SQL file path should be configured using this hoodie config:
*
*
hoodie.streamer.source.sql.file = 'hdfs://xxx/source.sql'
*
*
File-based SQL Source is used for one time backfill scenarios, this won't update the deltastreamer.checkpoint.key
* to the processed commit, instead it will fetch the latest successful checkpoint key and set that value as
* this backfill commits checkpoint so that it won't interrupt the regular incremental processing.
*
*
To fetch and use the latest incremental checkpoint, you need to also set this hoodie_conf for deltastremer jobs:
*
*
hoodie.write.meta.key.prefixes = 'deltastreamer.checkpoint.key'
*/
public class SqlFileBasedSource extends RowSource {
private static final Logger LOG = LoggerFactory.getLogger(SqlFileBasedSource.class);
private final String sourceSqlFile;
private final boolean shouldEmitCheckPoint;
public SqlFileBasedSource(
TypedProperties props,
JavaSparkContext sparkContext,
SparkSession sparkSession,
SchemaProvider schemaProvider) {
super(props, sparkContext, sparkSession, schemaProvider);
checkRequiredConfigProperties(props, Collections.singletonList(SOURCE_SQL_FILE));
sourceSqlFile = getStringWithAltKeys(props, SOURCE_SQL_FILE);
shouldEmitCheckPoint = getBooleanWithAltKeys(props, EMIT_EPOCH_CHECKPOINT);
}
@Override
protected Pair