[Backport] Using annotation to distinguish Hadoop Configuration in each module (#9013)

extensions-core/hdfs-storage/src/main/java/org/apache/druid/firehose/hdfs/HdfsFirehoseFactory.java

@@ -27,6 +27,7 @@
 import org.apache.druid.data.input.InputSplit;
 import org.apache.druid.data.input.impl.StringInputRowParser;
 import org.apache.druid.data.input.impl.prefetch.PrefetchableTextFilesFirehoseFactory;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.inputsource.hdfs.HdfsInputSource;
 import org.apache.druid.storage.hdfs.HdfsDataSegmentPuller;
 import org.apache.druid.utils.CompressionUtils;
@@ -46,7 +47,7 @@ public class HdfsFirehoseFactory extends PrefetchableTextFilesFirehoseFactory<Pa
 
   @JsonCreator
   public HdfsFirehoseFactory(
-      @JacksonInject Configuration conf,
+      @JacksonInject @Hdfs Configuration conf,
       @JsonProperty("paths") Object inputPaths,
       @JsonProperty("maxCacheCapacityBytes") Long maxCacheCapacityBytes,
       @JsonProperty("maxFetchCapacityBytes") Long maxFetchCapacityBytes,

extensions-core/hdfs-storage/src/main/java/org/apache/druid/guice/Hdfs.java

@@ -0,0 +1,40 @@
+/*
+ * 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.druid.guice;
+
+import com.google.inject.BindingAnnotation;
+
+import java.lang.annotation.ElementType;
+import java.lang.annotation.Retention;
+import java.lang.annotation.RetentionPolicy;
+import java.lang.annotation.Target;
+
+/**
+ * Each extension module needs to properly bind whatever it will use, but sometimes different modules need to bind the
+ * same class which will lead to the duplicate injection error. To avoid this problem, each module is supposed to bind
+ * different instances. This is a binding annotation for druid-hdfs-storage extension. Any binding for the same type
+ * should be distinguished by using this annotation.
+ */
+@Target({ElementType.FIELD, ElementType.PARAMETER, ElementType.METHOD})
+@Retention(RetentionPolicy.RUNTIME)
+@BindingAnnotation
+public @interface Hdfs
+{
+}

extensions-core/hdfs-storage/src/main/java/org/apache/druid/inputsource/hdfs/HdfsInputSource.java

@@ -32,6 +32,7 @@
 import org.apache.druid.data.input.SplitHintSpec;
 import org.apache.druid.data.input.impl.InputEntityIteratingReader;
 import org.apache.druid.data.input.impl.SplittableInputSource;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.java.util.common.IAE;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
@@ -72,7 +73,7 @@ public class HdfsInputSource extends AbstractInputSource implements SplittableIn
   @JsonCreator
   public HdfsInputSource(
       @JsonProperty(PROP_PATHS) Object inputPaths,
-      @JacksonInject Configuration configuration
+      @JacksonInject @Hdfs Configuration configuration
   )
   {
     this.inputPaths = coerceInputPathsToList(inputPaths, PROP_PATHS);

extensions-core/hdfs-storage/src/main/java/org/apache/druid/storage/hdfs/HdfsDataSegmentKiller.java

@@ -22,6 +22,7 @@
 import com.google.common.base.Preconditions;
 import com.google.inject.Inject;
 import org.apache.commons.lang.StringUtils;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.java.util.emitter.EmittingLogger;
 import org.apache.druid.segment.loading.DataSegmentKiller;
 import org.apache.druid.segment.loading.SegmentLoadingException;
@@ -43,7 +44,7 @@ public class HdfsDataSegmentKiller implements DataSegmentKiller
   private final Path storageDirectory;
 
   @Inject
-  public HdfsDataSegmentKiller(final Configuration config, final HdfsDataSegmentPusherConfig pusherConfig)
+  public HdfsDataSegmentKiller(@Hdfs final Configuration config, final HdfsDataSegmentPusherConfig pusherConfig)
   {
     this.config = config;
     this.storageDirectory = new Path(pusherConfig.getStorageDirectory());

extensions-core/hdfs-storage/src/main/java/org/apache/druid/storage/hdfs/HdfsDataSegmentPuller.java

@@ -22,6 +22,7 @@
 import com.google.common.base.Predicate;
 import com.google.common.io.ByteSource;
 import com.google.inject.Inject;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.java.util.common.FileUtils;
 import org.apache.druid.java.util.common.IAE;
 import org.apache.druid.java.util.common.RetryUtils;
@@ -178,7 +179,7 @@ public boolean delete()
   protected final Configuration config;
 
   @Inject
-  public HdfsDataSegmentPuller(final Configuration config)
+  public HdfsDataSegmentPuller(@Hdfs final Configuration config)
   {
     this.config = config;
   }

extensions-core/hdfs-storage/src/main/java/org/apache/druid/storage/hdfs/HdfsDataSegmentPusher.java

@@ -26,6 +26,7 @@
 import com.google.common.collect.ImmutableMap;
 import com.google.inject.Inject;
 import org.apache.druid.common.utils.UUIDUtils;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.java.util.common.IOE;
 import org.apache.druid.java.util.common.StringUtils;
 import org.apache.druid.java.util.common.logger.Logger;
@@ -60,7 +61,11 @@ public class HdfsDataSegmentPusher implements DataSegmentPusher
   private final Supplier<String> fullyQualifiedStorageDirectory;
 
   @Inject
-  public HdfsDataSegmentPusher(HdfsDataSegmentPusherConfig config, Configuration hadoopConfig, ObjectMapper jsonMapper)
+  public HdfsDataSegmentPusher(
+      HdfsDataSegmentPusherConfig config,
+      @Hdfs Configuration hadoopConfig,
+      ObjectMapper jsonMapper
+  )
   {
     this.hadoopConfig = hadoopConfig;
     this.jsonMapper = jsonMapper;

extensions-core/hdfs-storage/src/main/java/org/apache/druid/storage/hdfs/HdfsFileTimestampVersionFinder.java

@@ -21,6 +21,7 @@
 
 import com.google.inject.Inject;
 import org.apache.druid.data.SearchableVersionedDataFinder;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.java.util.common.RetryUtils;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FileStatus;
@@ -36,7 +37,7 @@
 public class HdfsFileTimestampVersionFinder extends HdfsDataSegmentPuller implements SearchableVersionedDataFinder<URI>
 {
   @Inject
-  public HdfsFileTimestampVersionFinder(Configuration config)
+  public HdfsFileTimestampVersionFinder(@Hdfs Configuration config)
   {
     super(config);
   }

extensions-core/hdfs-storage/src/main/java/org/apache/druid/storage/hdfs/HdfsStorageAuthentication.java

@@ -22,6 +22,7 @@
 
 import com.google.common.base.Strings;
 import com.google.inject.Inject;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.guice.ManageLifecycle;
 import org.apache.druid.java.util.common.ISE;
 import org.apache.druid.java.util.common.lifecycle.LifecycleStart;
@@ -40,7 +41,7 @@ public class HdfsStorageAuthentication
   private final Configuration hadoopConf;
 
   @Inject
-  public HdfsStorageAuthentication(HdfsKerberosConfig hdfsKerberosConfig, Configuration hadoopConf)
+  public HdfsStorageAuthentication(HdfsKerberosConfig hdfsKerberosConfig, @Hdfs Configuration hadoopConf)
   {
     this.hdfsKerberosConfig = hdfsKerberosConfig;
     this.hadoopConf = hadoopConf;

extensions-core/hdfs-storage/src/main/java/org/apache/druid/storage/hdfs/HdfsStorageDruidModule.java

@@ -28,6 +28,7 @@
 import org.apache.druid.data.SearchableVersionedDataFinder;
 import org.apache.druid.firehose.hdfs.HdfsFirehoseFactory;
 import org.apache.druid.guice.Binders;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.guice.JsonConfigProvider;
 import org.apache.druid.guice.LazySingleton;
 import org.apache.druid.guice.LifecycleModule;
@@ -108,7 +109,7 @@ public void configure(Binder binder)
       }
     }
 
-    binder.bind(Configuration.class).toInstance(conf);
+    binder.bind(Configuration.class).annotatedWith(Hdfs.class).toInstance(conf);
     JsonConfigProvider.bind(binder, "druid.storage", HdfsDataSegmentPusherConfig.class);
 
     Binders.taskLogsBinder(binder).addBinding("hdfs").to(HdfsTaskLogs.class);
@@ -117,6 +118,5 @@ public void configure(Binder binder)
     JsonConfigProvider.bind(binder, "druid.hadoop.security.kerberos", HdfsKerberosConfig.class);
     binder.bind(HdfsStorageAuthentication.class).in(ManageLifecycle.class);
     LifecycleModule.register(binder, HdfsStorageAuthentication.class);
-
   }
 }

extensions-core/hdfs-storage/src/main/java/org/apache/druid/storage/hdfs/tasklog/HdfsTaskLogs.java

@@ -23,6 +23,7 @@
 import com.google.common.io.ByteSource;
 import com.google.common.io.ByteStreams;
 import com.google.inject.Inject;
+import org.apache.druid.guice.Hdfs;
 import org.apache.druid.java.util.common.IOE;
 import org.apache.druid.java.util.common.logger.Logger;
 import org.apache.druid.tasklogs.TaskLogs;
@@ -51,7 +52,7 @@ public class HdfsTaskLogs implements TaskLogs
   private final Configuration hadoopConfig;
 
   @Inject
-  public HdfsTaskLogs(HdfsTaskLogsConfig config, Configuration hadoopConfig)
+  public HdfsTaskLogs(HdfsTaskLogsConfig config, @Hdfs Configuration hadoopConfig)
   {
     this.config = config;
     this.hadoopConfig = hadoopConfig;

extensions-core/orc-extensions/src/main/java/org/apache/druid/data/input/orc/OrcExtensionsModule.java

@@ -24,6 +24,7 @@
 import com.fasterxml.jackson.databind.module.SimpleModule;
 import com.google.inject.Binder;
 import com.google.inject.Inject;
+import org.apache.druid.data.input.orc.guice.Orc;
 import org.apache.druid.initialization.DruidModule;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FileSystem;
@@ -89,6 +90,6 @@ public void configure(Binder binder)
       }
     }
 
-    binder.bind(Configuration.class).toInstance(conf);
+    binder.bind(Configuration.class).annotatedWith(Orc.class).toInstance(conf);
   }
 }

extensions-core/orc-extensions/src/main/java/org/apache/druid/data/input/orc/OrcInputFormat.java

@@ -26,6 +26,7 @@
 import org.apache.druid.data.input.InputEntityReader;
 import org.apache.druid.data.input.InputRowSchema;
 import org.apache.druid.data.input.impl.NestedInputFormat;
+import org.apache.druid.data.input.orc.guice.Orc;
 import org.apache.druid.java.util.common.parsers.JSONPathSpec;
 import org.apache.hadoop.conf.Configuration;
 
@@ -42,7 +43,7 @@ public class OrcInputFormat extends NestedInputFormat
   public OrcInputFormat(
       @JsonProperty("flattenSpec") @Nullable JSONPathSpec flattenSpec,
       @JsonProperty("binaryAsString") @Nullable Boolean binaryAsString,
-      @JacksonInject Configuration conf
+      @JacksonInject @Orc Configuration conf
   )
   {
     super(flattenSpec);

extensions-core/orc-extensions/src/main/java/org/apache/druid/data/input/orc/guice/Orc.java

@@ -0,0 +1,40 @@
+/*
+ * 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.druid.data.input.orc.guice;
+
+import com.google.inject.BindingAnnotation;
+
+import java.lang.annotation.ElementType;
+import java.lang.annotation.Retention;
+import java.lang.annotation.RetentionPolicy;
+import java.lang.annotation.Target;
+
+/**
+ * Each extension module needs to properly bind whatever it will use, but sometimes different modules need to bind the
+ * same class which will lead to the duplicate injection error. To avoid this problem, each module is supposed to bind
+ * different instances. This is a binding annotation for druid-orc-extensions extension. Any binding for the same type
+ * should be distinguished by using this annotation.
+ */
+@Target({ElementType.FIELD, ElementType.PARAMETER, ElementType.METHOD})
+@Retention(RetentionPolicy.RUNTIME)
+@BindingAnnotation
+public @interface Orc
+{
+}

extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/ParquetExtensionsModule.java

@@ -25,6 +25,7 @@
 import com.google.inject.Binder;
 import com.google.inject.Inject;
 import org.apache.druid.data.input.parquet.avro.ParquetAvroHadoopInputRowParser;
+import org.apache.druid.data.input.parquet.guice.Parquet;
 import org.apache.druid.data.input.parquet.simple.ParquetHadoopInputRowParser;
 import org.apache.druid.data.input.parquet.simple.ParquetParseSpec;
 import org.apache.druid.initialization.DruidModule;
@@ -98,6 +99,6 @@ public void configure(Binder binder)
       }
     }
 
-    binder.bind(Configuration.class).toInstance(conf);
+    binder.bind(Configuration.class).annotatedWith(Parquet.class).toInstance(conf);
   }
 }

extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/ParquetInputFormat.java

@@ -19,13 +19,16 @@
 
 package org.apache.druid.data.input.parquet;
 
+import com.fasterxml.jackson.annotation.JacksonInject;
 import com.fasterxml.jackson.annotation.JsonCreator;
 import com.fasterxml.jackson.annotation.JsonProperty;
 import org.apache.druid.data.input.InputEntity;
 import org.apache.druid.data.input.InputEntityReader;
 import org.apache.druid.data.input.InputRowSchema;
 import org.apache.druid.data.input.impl.NestedInputFormat;
+import org.apache.druid.data.input.parquet.guice.Parquet;
 import org.apache.druid.java.util.common.parsers.JSONPathSpec;
+import org.apache.hadoop.conf.Configuration;
 
 import javax.annotation.Nullable;
 import java.io.File;
@@ -35,15 +38,18 @@
 public class ParquetInputFormat extends NestedInputFormat
 {
   private final boolean binaryAsString;
+  private final Configuration conf;
 
   @JsonCreator
   public ParquetInputFormat(
       @JsonProperty("flattenSpec") @Nullable JSONPathSpec flattenSpec,
-      @JsonProperty("binaryAsString") @Nullable Boolean binaryAsString
+      @JsonProperty("binaryAsString") @Nullable Boolean binaryAsString,
+      @JacksonInject @Parquet Configuration conf
   )
   {
     super(flattenSpec);
     this.binaryAsString = binaryAsString == null ? false : binaryAsString;
+    this.conf = conf;
   }
 
   @JsonProperty
@@ -65,7 +71,7 @@ public InputEntityReader createReader(
       File temporaryDirectory
   ) throws IOException
   {
-    return new ParquetReader(inputRowSchema, source, temporaryDirectory, getFlattenSpec(), binaryAsString);
+    return new ParquetReader(conf, inputRowSchema, source, temporaryDirectory, getFlattenSpec(), binaryAsString);
   }
 
   @Override

extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/ParquetReader.java

@@ -31,6 +31,7 @@
 import org.apache.druid.java.util.common.parsers.ObjectFlattener;
 import org.apache.druid.java.util.common.parsers.ObjectFlatteners;
 import org.apache.druid.java.util.common.parsers.ParseException;
+import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
 import org.apache.parquet.example.data.Group;
 import org.apache.parquet.hadoop.example.GroupReadSupport;
@@ -51,6 +52,7 @@ public class ParquetReader extends IntermediateRowParsingReader<Group>
   private final Closer closer;
 
   ParquetReader(
+      Configuration conf,
       InputRowSchema inputRowSchema,
       InputEntity source,
       File temporaryDirectory,
@@ -69,7 +71,9 @@ public class ParquetReader extends IntermediateRowParsingReader<Group>
     final ClassLoader currentClassLoader = Thread.currentThread().getContextClassLoader();
     try {
       Thread.currentThread().setContextClassLoader(getClass().getClassLoader());
-      reader = closer.register(org.apache.parquet.hadoop.ParquetReader.builder(new GroupReadSupport(), path).build());
+      reader = closer.register(org.apache.parquet.hadoop.ParquetReader.builder(new GroupReadSupport(), path)
+                                                                      .withConf(conf)
+                                                                      .build());
     }
     finally {
       Thread.currentThread().setContextClassLoader(currentClassLoader);