[GitHub] [hudi] codope commented on a change in pull request #2915: [HUDI-251] Adds JDBC source support for DeltaStreamer

[GitBox <gi...@apache.org>]

codope commented on a change in pull request #2915:
URL: https://github.com/apache/hudi/pull/2915#discussion_r633690635



##########
File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/JdbcSource.java
##########
@@ -0,0 +1,326 @@
+/*
+ * 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.util.Option;
+import org.apache.hudi.common.util.StringUtils;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.exception.HoodieException;
+import org.apache.hudi.utilities.SqlQueryBuilder;
+import org.apache.hudi.utilities.schema.SchemaProvider;
+
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.IOUtils;
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.Column;
+import org.apache.spark.sql.DataFrameReader;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+import org.apache.spark.sql.functions;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.storage.StorageLevel;
+import org.jetbrains.annotations.NotNull;
+
+import java.net.URI;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.List;
+import java.util.Set;
+
+/**
+ * Reads data from RDBMS data sources.
+ */
+
+public class JdbcSource extends RowSource {
+
+  private static final Logger LOG = LogManager.getLogger(JdbcSource.class);
+  private static final List<String> DB_LIMIT_CLAUSE = Arrays.asList("mysql", "postgresql", "h2");
+  private static final String URI_JDBC_PREFIX = "jdbc:";
+
+  public JdbcSource(TypedProperties props, JavaSparkContext sparkContext, SparkSession sparkSession,
+                    SchemaProvider schemaProvider) {
+    super(props, sparkContext, sparkSession, schemaProvider);
+  }
+
+  /**
+   * Validates all user properties and prepares the {@link DataFrameReader} to read from RDBMS.
+   *
+   * @param session    The {@link SparkSession}.
+   * @param properties The JDBC connection properties and data source options.
+   * @return The {@link DataFrameReader} to read from RDBMS
+   * @throws HoodieException
+   */
+  private static DataFrameReader validatePropsAndGetDataFrameReader(final SparkSession session,
+                                                                    final TypedProperties properties)
+      throws HoodieException {
+    DataFrameReader dataFrameReader;
+    FSDataInputStream passwordFileStream = null;
+    try {
+      dataFrameReader = session.read().format("jdbc");
+      dataFrameReader = dataFrameReader.option(Config.URL_PROP, properties.getString(Config.URL));
+      dataFrameReader = dataFrameReader.option(Config.USER_PROP, properties.getString(Config.USER));
+      dataFrameReader = dataFrameReader.option(Config.DRIVER_PROP, properties.getString(Config.DRIVER_CLASS));
+      dataFrameReader = dataFrameReader
+          .option(Config.RDBMS_TABLE_PROP, properties.getString(Config.RDBMS_TABLE_NAME));
+
+      if (properties.containsKey(Config.PASSWORD)) {
+        LOG.info("Reading JDBC password from properties file....");
+        dataFrameReader = dataFrameReader.option(Config.PASSWORD_PROP, properties.getString(Config.PASSWORD));
+      } else if (properties.containsKey(Config.PASSWORD_FILE)
+          && !StringUtils.isNullOrEmpty(properties.getString(Config.PASSWORD_FILE))) {
+        LOG.info(String.format("Reading JDBC password from password file %s", properties.getString(Config.PASSWORD_FILE)));
+        FileSystem fileSystem = FileSystem.get(session.sparkContext().hadoopConfiguration());
+        passwordFileStream = fileSystem.open(new Path(properties.getString(Config.PASSWORD_FILE)));
+        byte[] bytes = new byte[passwordFileStream.available()];
+        passwordFileStream.read(bytes);
+        dataFrameReader = dataFrameReader.option(Config.PASSWORD_PROP, new String(bytes));
+      } else {
+        throw new IllegalArgumentException(String.format("JDBCSource needs either a %s or %s to connect to RDBMS "
+            + "datasource", Config.PASSWORD_FILE, Config.PASSWORD));
+      }
+
+      addExtraJdbcOptions(properties, dataFrameReader);
+
+      if (properties.getBoolean(Config.IS_INCREMENTAL)) {
+        DataSourceUtils.checkRequiredProperties(properties, Collections.singletonList(Config.INCREMENTAL_COLUMN));

Review comment:
       Would it be okay to do an additional query before fetching the dataset for this validation?




-- 
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:
users@infra.apache.org