yihua commented on code in PR #11649:
URL: https://github.com/apache/hudi/pull/11649#discussion_r1750995641
##########
hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/utils/HoodieArrayWritableAvroUtils.java:
##########
@@ -37,12 +38,17 @@ public class HoodieArrayWritableAvroUtils {
private static final Cache<String, ObjectInspectorCache>
OBJECT_INSPECTOR_TABLE_CACHE =
Caffeine.newBuilder().maximumSize(1000).build();
- public static ObjectInspectorCache getCacheForTable(String table, Schema
tableSchema, JobConf jobConf) {
- ObjectInspectorCache cache =
OBJECT_INSPECTOR_TABLE_CACHE.getIfPresent(table);
- if (cache == null) {
- cache = new ObjectInspectorCache(tableSchema, jobConf);
- }
- return cache;
+ public static ObjectInspectorCache getCacheForTable(String table) {
+ return OBJECT_INSPECTOR_TABLE_CACHE.getIfPresent(table);
+ }
+
+ public static ObjectInspectorCache initCacheForTable(String table, Schema
tableSchema, JobConf jobConf) {
+ return OBJECT_INSPECTOR_TABLE_CACHE.get(table, t -> new
ObjectInspectorCache(tableSchema, jobConf));
+ }
+
+ @VisibleForTesting
+ public static void resetCache() {
+ OBJECT_INSPECTOR_TABLE_CACHE.invalidateAll();
Review Comment:
What is the cache being used for? The cache should be automatically
invalidated. Wondering if the Hive reader context should always build the
column type map in the constructor without getting it from the cache since the
map can change (safety over performance).
##########
hudi-client/hudi-java-client/src/test/java/org/apache/hudi/hadoop/TestHoodieFileGroupReaderOnHive.java:
##########
@@ -0,0 +1,329 @@
+/*
+ * 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.hadoop;
+
+import org.apache.hudi.avro.HoodieAvroUtils;
+import org.apache.hudi.client.HoodieJavaWriteClient;
+import org.apache.hudi.client.common.HoodieJavaEngineContext;
+import org.apache.hudi.common.config.HoodieMemoryConfig;
+import org.apache.hudi.common.config.HoodieReaderConfig;
+import org.apache.hudi.common.config.RecordMergeMode;
+import org.apache.hudi.common.engine.EngineType;
+import org.apache.hudi.common.engine.HoodieReaderContext;
+import org.apache.hudi.common.model.DefaultHoodieRecordPayload;
+import org.apache.hudi.common.model.HoodieRecord;
+import org.apache.hudi.common.model.HoodieRecordMerger;
+import org.apache.hudi.common.model.OverwriteWithLatestAvroPayload;
+import org.apache.hudi.common.table.HoodieTableMetaClient;
+import org.apache.hudi.common.table.read.CustomPayloadForTesting;
+import org.apache.hudi.common.table.read.TestHoodieFileGroupReaderBase;
+import org.apache.hudi.common.testutils.HoodieTestDataGenerator;
+import org.apache.hudi.common.testutils.HoodieTestUtils;
+import org.apache.hudi.common.testutils.minicluster.HdfsTestService;
+import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.hadoop.hive.HoodieCombineHiveInputFormat;
+import org.apache.hudi.hadoop.realtime.HoodieParquetRealtimeInputFormat;
+import org.apache.hudi.hadoop.utils.HoodieArrayWritableAvroUtils;
+import org.apache.hudi.storage.HoodieStorage;
+import org.apache.hudi.storage.StorageConfiguration;
+import org.apache.hudi.storage.hadoop.HoodieHadoopStorage;
+import org.apache.hudi.testutils.HoodieJavaClientTestHarness;
+
+import org.apache.avro.Schema;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.RawLocalFileSystem;
+import org.apache.hadoop.hive.metastore.api.hive_metastoreConstants;
+import org.apache.hadoop.hive.ql.exec.Utilities;
+import org.apache.hadoop.hive.ql.exec.mr.ExecMapper;
+import org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat;
+import org.apache.hadoop.hive.ql.plan.MapredWork;
+import org.apache.hadoop.hive.ql.plan.PartitionDesc;
+import org.apache.hadoop.hive.ql.plan.TableDesc;
+import org.apache.hadoop.hive.serde2.ColumnProjectionUtils;
+import org.apache.hadoop.io.ArrayWritable;
+import org.apache.hadoop.io.NullWritable;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.InputSplit;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.RecordReader;
+import org.apache.hadoop.mapred.Reporter;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.Disabled;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.LinkedHashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+
+import static org.apache.hadoop.hive.ql.exec.Utilities.HAS_MAP_WORK;
+import static org.apache.hadoop.hive.ql.exec.Utilities.MAPRED_MAPPER_CLASS;
+import static
org.apache.hudi.hadoop.HoodieFileGroupReaderBasedRecordReader.getRecordKeyField;
+import static
org.apache.hudi.hadoop.HoodieFileGroupReaderBasedRecordReader.getStoredPartitionFieldNames;
+import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertNotNull;
+
+public class TestHoodieFileGroupReaderOnHive extends
TestHoodieFileGroupReaderBase<ArrayWritable> {
+
+ @Override
+ @Disabled
+ public void testReadLogFilesOnlyInMergeOnReadTable(RecordMergeMode
recordMergeMode, String logDataBlockFormat) throws Exception {}
+
+ private static final String PARTITION_COLUMN = "datestr";
+ private static JobConf baseJobConf;
+ private static HdfsTestService hdfsTestService;
+ private static HoodieStorage storage;
+ private static FileSystem fs;
+ private static StorageConfiguration<Configuration> storageConf;
+
+ @BeforeAll
+ public static void setUpClass() throws IOException, InterruptedException {
+ // Append is not supported in LocalFileSystem. HDFS needs to be setup.
+ hdfsTestService = new HdfsTestService();
+ fs = hdfsTestService.start(true).getFileSystem();
+ storageConf = HoodieTestUtils.getDefaultStorageConf();
+ baseJobConf = new JobConf(storageConf.unwrap());
+ baseJobConf.set(HoodieMemoryConfig.MAX_DFS_STREAM_BUFFER_SIZE.key(),
String.valueOf(1024 * 1024));
+ fs.setConf(baseJobConf);
+ storage = new HoodieHadoopStorage(fs);
Review Comment:
OK makes sense. This is for Hive tests only correct?
--
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]
