wuwenchi commented on code in PR #44267:
URL: https://github.com/apache/doris/pull/44267#discussion_r1859641277
##########
gensrc/thrift/PlanNodes.thrift:
##########
@@ -448,6 +447,8 @@ struct TFileScanRangeParams {
22: optional TTextSerdeType text_serde_type
// used by flexible partial update
23: optional string sequence_map_col
+ // if set true, be will be forced to use jni reader
+ 24: bool force_jni_reader;
Review Comment:
Should this behavior be specified in FE? Otherwise, when checking the plan,
we won't know how many JNIs have been used.
##########
fe/be-java-extensions/hadoop-hudi-scanner/src/main/java/org/apache/doris/hudi/HadoopHudiJniScanner.java:
##########
@@ -0,0 +1,272 @@
+// 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.doris.hudi;
+
+import org.apache.doris.common.classloader.ThreadClassLoaderContext;
+import org.apache.doris.common.jni.JniScanner;
+import org.apache.doris.common.jni.vec.ColumnType;
+
+import com.google.common.base.Joiner;
+import com.google.common.base.Preconditions;
+import com.google.common.base.Strings;
+import com.google.common.collect.Maps;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.common.JavaUtils;
+import org.apache.hadoop.hive.serde2.Deserializer;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.StructField;
+import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
+import org.apache.hadoop.io.ArrayWritable;
+import org.apache.hadoop.io.NullWritable;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.hadoop.mapred.InputFormat;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.RecordReader;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.util.ReflectionUtils;
+import org.apache.hudi.common.model.HoodieLogFile;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.hadoop.realtime.HoodieRealtimeFileSplit;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.time.ZoneId;
+import java.util.Arrays;
+import java.util.List;
+import java.util.Map;
+import java.util.Properties;
+import java.util.stream.Collectors;
+import java.util.stream.IntStream;
+
+/**
+ * HadoopHudiJniScanner is a JniScanner implementation that reads Hudi data
using hudi-hadoop-mr.
+ */
+public class HadoopHudiJniScanner extends JniScanner {
+ private static final Logger LOG =
LoggerFactory.getLogger(HadoopHudiJniScanner.class);
+
+ private static final String HADOOP_CONF_PREFIX = "hadoop_conf.";
+
+ // Hudi data info
+ private final String basePath;
+ private final String dataFilePath;
+ private final long dataFileLength;
+ private final String[] deltaFilePaths;
+ private final String instantTime;
+ private final String serde;
+ private final String inputFormat;
+
+ // schema info
+ private final String hudiColumnNames;
+ private final String[] hudiColumnTypes;
+ private final String[] requiredFields;
+ private List<Integer> requiredColumnIds;
+ private ColumnType[] requiredTypes;
+ // private final String[] nestedFields;
Review Comment:
delete useless variable
--
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: commits-unsubscr...@doris.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org
