echauchot commented on code in PR #3: URL: https://github.com/apache/flink-connector-cassandra/pull/3#discussion_r1137115950
########## flink-connector-cassandra/src/main/java/org/apache/flink/connector/cassandra/source/CassandraSource.java: ########## @@ -0,0 +1,192 @@ +/* + * 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.connector.cassandra.source; + +import org.apache.flink.annotation.Internal; +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.api.common.ExecutionConfig; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.connector.source.Boundedness; +import org.apache.flink.api.connector.source.Source; +import org.apache.flink.api.connector.source.SourceReader; +import org.apache.flink.api.connector.source.SourceReaderContext; +import org.apache.flink.api.connector.source.SplitEnumerator; +import org.apache.flink.api.connector.source.SplitEnumeratorContext; +import org.apache.flink.api.java.ClosureCleaner; +import org.apache.flink.api.java.typeutils.ResultTypeQueryable; +import org.apache.flink.connector.cassandra.source.enumerator.CassandraEnumeratorState; +import org.apache.flink.connector.cassandra.source.enumerator.CassandraEnumeratorStateSerializer; +import org.apache.flink.connector.cassandra.source.enumerator.CassandraSplitEnumerator; +import org.apache.flink.connector.cassandra.source.reader.CassandraSourceReaderFactory; +import org.apache.flink.connector.cassandra.source.split.CassandraSplit; +import org.apache.flink.connector.cassandra.source.split.CassandraSplitSerializer; +import org.apache.flink.core.io.SimpleVersionedSerializer; +import org.apache.flink.streaming.connectors.cassandra.ClusterBuilder; +import org.apache.flink.streaming.connectors.cassandra.MapperOptions; + +import javax.annotation.Nullable; + +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +import static org.apache.flink.util.Preconditions.checkNotNull; +import static org.apache.flink.util.Preconditions.checkState; + +/** + * A bounded source to read from Cassandra and return a collection of entities as {@code + * DataStream<Entity>}. An entity is built by Cassandra mapper ({@code + * com.datastax.driver.mapping.EntityMapper}) based on a POJO containing annotations (as described + * in <a + * href="https://docs.datastax.com/en/developer/java-driver/3.11/manual/object_mapper/creating/";> + * Cassandra object mapper</a>). + * + * <p>To use it, do the following: + * + * <pre>{@code + * ClusterBuilder clusterBuilder = new ClusterBuilder() { + * @Override + * protected Cluster buildCluster(Cluster.Builder builder) { + * return builder.addContactPointsWithPorts(new InetSocketAddress(HOST,PORT)) + * .withQueryOptions(new QueryOptions().setConsistencyLevel(CL)) + * .withSocketOptions(new SocketOptions() + * .setConnectTimeoutMillis(CONNECT_TIMEOUT) + * .setReadTimeoutMillis(READ_TIMEOUT)) + * .build(); + * } + * }; + * long maxSplitMemorySize = ... //optional max split size in bytes. If not set, maxSplitMemorySize = tableSize / parallelism + * Source cassandraSource = new CassandraSource(clusterBuilder, + * maxSplitMemorySize, + * Pojo.class, + * "select ... from KEYSPACE.TABLE ...;", + * () -> new Mapper.Option[] {Mapper.Option.saveNullFields(true)}); + * + * DataStream<Pojo> stream = env.fromSource(cassandraSource, WatermarkStrategy.noWatermarks(), + * "CassandraSource"); + * }</pre> + */ +@PublicEvolving +public class CassandraSource<OUT> + implements Source<OUT, CassandraSplit, CassandraEnumeratorState>, ResultTypeQueryable<OUT> { + + public static final String CQL_PROHIBITED_CLAUSES_REGEXP = + "(?i).*(AVG|COUNT|MIN|MAX|SUM|ORDER|GROUP BY).*"; + public static final String SELECT_REGEXP = "(?i)select .+ from (\\w+)\\.(\\w+).*;$"; Review Comment: :+1: -- 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]
