Jiabao-Sun commented on code in PR #1: URL: https://github.com/apache/flink-connector-mongodb/pull/1#discussion_r1097121821
########## flink-connector-mongodb/src/main/java/org/apache/flink/connector/mongodb/table/MongoConnectorOptions.java: ########## @@ -0,0 +1,143 @@ +/* + * 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.mongodb.table; + +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.configuration.ConfigOption; +import org.apache.flink.configuration.ConfigOptions; +import org.apache.flink.configuration.MemorySize; +import org.apache.flink.connector.base.DeliveryGuarantee; +import org.apache.flink.connector.mongodb.source.enumerator.splitter.PartitionStrategy; + +import java.time.Duration; + +/** + * Base options for the MongoDB connector. Needs to be public so that the {@link + * org.apache.flink.table.api.TableDescriptor} can access it. + */ +@PublicEvolving +public class MongoConnectorOptions { + + private MongoConnectorOptions() {} + + public static final ConfigOption<String> URI = + ConfigOptions.key("uri") + .stringType() + .noDefaultValue() + .withDescription("Specifies the connection uri of MongoDB."); + + public static final ConfigOption<String> DATABASE = + ConfigOptions.key("database") + .stringType() + .noDefaultValue() + .withDescription("Specifies the database to read or write of MongoDB."); + + public static final ConfigOption<String> COLLECTION = + ConfigOptions.key("collection") + .stringType() + .noDefaultValue() + .withDescription("Specifies the collection to read or write of MongoDB."); + + public static final ConfigOption<Integer> SCAN_FETCH_SIZE = + ConfigOptions.key("scan.fetch-size") + .intType() + .defaultValue(2048) + .withDescription( + "Gives the reader a hint as to the number of documents that should be fetched from the database per round-trip when reading. "); + + public static final ConfigOption<Integer> SCAN_CURSOR_BATCH_SIZE = Review Comment: Thanks @zentol to catch this. The original intention of introducing `cusro.batch-size` is that this configuration is similar to 'select from limit' to limit the number of documents returned to reduce memory overhead. I checked some MongoDB documents and found that `cusor.batch-size` will only return up to 16mb of data. This is meaningless for protecting the memory size, so I deleted this configuration item. https://www.mongodb.com/docs/manual/tutorial/iterate-a-cursor/#cursor-batches > The MongoDB server returns the query results in batches. The amount of data in the batch will not exceed the [maximum BSON document size](https://www.mongodb.com/docs/manual/reference/limits/#std-label-limit-bson-document-size). To override the default size of the batch, see [batchSize()](https://www.mongodb.com/docs/manual/reference/method/cursor.batchSize/#mongodb-method-cursor.batchSize) and [limit().](https://www.mongodb.com/docs/manual/reference/method/cursor.limit/#mongodb-method-cursor.limit) https://www.mongodb.com/community/forums/t/mis-understanding-batchsize/169713 > find() and aggregate() operations have an initial batch size of 101 documents by default. Subsequent [getMore 10](https://www.mongodb.com/docs/manual/reference/command/getMore/#mongodb-dbcommand-dbcmd.getMore) operations issued against the resulting cursor have no default batch size, so they are limited only by the 16 megabyte message size. -- 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]
