taherk77 commented on a change in pull request #969: [HUDI-251] JDBC
incremental load to HUDI DeltaStreamer
URL: https://github.com/apache/incubator-hudi/pull/969#discussion_r340638091
##########
File path:
hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/JDBCSource.java
##########
@@ -0,0 +1,239 @@
+package org.apache.hudi.utilities.sources;
+
+import java.util.Arrays;
+import java.util.Set;
+import java.util.stream.Collectors;
+import org.apache.hadoop.conf.Configuration;
+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.hudi.DataSourceUtils;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.StringUtils;
+import org.apache.hudi.common.util.TypedProperties;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.exception.HoodieException;
+import org.apache.hudi.utilities.schema.SchemaProvider;
+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.jetbrains.annotations.NotNull;
+
+
+public class JDBCSource extends RowSource {
+
+ private static Logger LOG = LogManager.getLogger(JDBCSource.class);
+
+ public JDBCSource(TypedProperties props, JavaSparkContext sparkContext,
SparkSession sparkSession,
+ SchemaProvider schemaProvider) {
+ super(props, sparkContext, sparkSession, schemaProvider);
+ }
+
+ private static DataFrameReader validatePropsAndGetDataFrameReader(final
SparkSession session,
+ final TypedProperties properties)
+ throws HoodieException {
+ DataFrameReader dataFrameReader = null;
+ 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) && !StringUtils
+ .isNullOrEmpty(properties.getString(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(new Configuration());
+ passwordFileStream = fileSystem.open(new
Path(properties.getString(Config.PASSWORD_FILE)));
+ byte[] bytes = new byte[passwordFileStream.available()];
+ passwordFileStream.read(bytes);
Review comment:
Here I need to read from FS like hdfs, gcs or s3 which the hadoop fs
FileSystem will be useful for. FileIOUtils dont use FileSystem for reads
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
