wenshao commented on code in PR #4320: URL: https://github.com/apache/flink-cdc/pull/4320#discussion_r3042808005
########## flink-cdc-connect/flink-cdc-pipeline-connectors/flink-cdc-pipeline-connector-sqlserver/src/main/java/org/apache/flink/cdc/connectors/sqlserver/source/SqlServerDataSourceOptions.java: ########## @@ -0,0 +1,258 @@ +/* + * 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.cdc.connectors.sqlserver.source; + +import org.apache.flink.cdc.common.annotation.Experimental; +import org.apache.flink.cdc.common.annotation.PublicEvolving; +import org.apache.flink.cdc.common.configuration.ConfigOption; +import org.apache.flink.cdc.common.configuration.ConfigOptions; + +import java.time.Duration; + +/** Configurations for {@link SqlServerDataSource}. */ +@PublicEvolving +public class SqlServerDataSourceOptions { + + public static final ConfigOption<String> HOSTNAME = + ConfigOptions.key("hostname") + .stringType() + .noDefaultValue() + .withDescription("IP address or hostname of the SQL Server database server."); + + public static final ConfigOption<Integer> PORT = + ConfigOptions.key("port") + .intType() + .defaultValue(1433) + .withDescription("Integer port number of the SQL Server database server."); + + public static final ConfigOption<String> USERNAME = + ConfigOptions.key("username") + .stringType() + .noDefaultValue() + .withDescription( + "Name of the SQL Server database to use when connecting to the SQL Server database server."); + + public static final ConfigOption<String> PASSWORD = + ConfigOptions.key("password") + .stringType() + .noDefaultValue() + .withDescription( + "Password to use when connecting to the SQL Server database server."); + + public static final ConfigOption<String> TABLES = + ConfigOptions.key("tables") + .stringType() + .noDefaultValue() + .withDescription( + "Table names of the SQL Server tables to monitor. Regular expressions are supported. " + + "It is important to note that the dot (.) is treated as a delimiter for database, schema and table names. " + + "If there is a need to use a dot (.) in a regular expression to match any character, " + + "it is necessary to escape the dot with a backslash." + + "eg. db0.dbo.\\.*, db1.dbo.user_table_[0-9]+, db[1-2].dbo.[app|web]_order_\\.*"); + + public static final ConfigOption<String> SERVER_TIME_ZONE = + ConfigOptions.key("server-time-zone") + .stringType() + .noDefaultValue() + .withDescription( + "The session time zone in database server. If not set, then " + + "ZoneId.systemDefault() is used to determine the server time zone."); + + public static final ConfigOption<String> SCAN_INCREMENTAL_SNAPSHOT_CHUNK_KEY_COLUMN = + ConfigOptions.key("scan.incremental.snapshot.chunk.key-column") + .stringType() + .noDefaultValue() + .withDescription( + "The chunk key of table snapshot, captured tables are split into multiple chunks by a chunk key when read the snapshot of table." + + "By default, the chunk key is the first column of the primary key." + + "This column must be a column of the primary key."); + + public static final ConfigOption<Integer> SCAN_INCREMENTAL_SNAPSHOT_CHUNK_SIZE = + ConfigOptions.key("scan.incremental.snapshot.chunk.size") + .intType() + .defaultValue(8096) + .withDescription( + "The chunk size (number of rows) of table snapshot, captured tables are split into multiple chunks when read the snapshot of table."); + + public static final ConfigOption<Integer> SCAN_SNAPSHOT_FETCH_SIZE = + ConfigOptions.key("scan.snapshot.fetch.size") + .intType() + .defaultValue(1024) + .withDescription( + "The maximum fetch size for per poll when read table snapshot."); + + public static final ConfigOption<Duration> CONNECT_TIMEOUT = + ConfigOptions.key("connect.timeout") + .durationType() + .defaultValue(Duration.ofSeconds(30)) + .withDescription( + "The maximum time that the connector should wait after trying to connect to the SQL Server database server before timing out."); + + public static final ConfigOption<Integer> CONNECTION_POOL_SIZE = + ConfigOptions.key("connection.pool.size") + .intType() + .defaultValue(20) + .withDescription("The connection pool size."); + + public static final ConfigOption<Integer> CONNECT_MAX_RETRIES = + ConfigOptions.key("connect.max-retries") + .intType() + .defaultValue(3) + .withDescription( + "The max retry times that the connector should retry to build SQL Server database server connection."); + + public static final ConfigOption<String> SCAN_STARTUP_MODE = + ConfigOptions.key("scan.startup.mode") + .stringType() + .defaultValue("initial") + .withDescription( + "Optional startup mode for SQL Server CDC consumer, valid enumerations are " + + "\"initial\", \"latest-offset\", \"snapshot\" or \"timestamp\""); + + public static final ConfigOption<Long> SCAN_STARTUP_TIMESTAMP_MILLIS = + ConfigOptions.key("scan.startup.timestamp-millis") + .longType() + .noDefaultValue() + .withDescription( + "Optional timestamp used in case of \"timestamp\" startup mode"); + + public static final ConfigOption<Double> SPLIT_KEY_EVEN_DISTRIBUTION_FACTOR_UPPER_BOUND = Review Comment: **[Suggestion]** `SPLIT_KEY_EVEN_DISTRIBUTION_FACTOR_UPPER_BOUND`/`LOWER_BOUND` are defined with identical keys, defaults, and fallback keys as `CHUNK_KEY_EVEN_DISTRIBUTION_FACTOR_UPPER_BOUND`/`LOWER_BOUND`. The factory reads values from `CHUNK_KEY_*` but error messages reference `SPLIT_KEY_*`, creating confusing inconsistency. Other pipeline connectors (e.g., Oracle) only have the `CHUNK_KEY_*` variants. **Suggested fix:** Remove `SPLIT_KEY_*` variants and update error messages in `validateDistributionFactorUpper`/`validateDistributionFactorLower` to use `CHUNK_KEY_*.key()`. _— glm-5.1_ -- 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]
