This is an automated email from the ASF dual-hosted git repository.
shangxinli pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/parquet-mr.git
The following commit(s) were added to refs/heads/master by this push:
new 48f5195 [WIP] Refactor GroupReadSupport to unuse deprecated api (#894)
48f5195 is described below
commit 48f5195cfb2662f021e928211687192249752818
Author: Xuedong Luan <[email protected]>
AuthorDate: Sat Apr 24 01:05:05 2021 +0800
[WIP] Refactor GroupReadSupport to unuse deprecated api (#894)
Co-authored-by: Luan <[email protected]>
---
.../apache/parquet/hadoop/example/GroupReadSupport.java | 15 +++++++--------
.../parquet/hadoop/example/GroupReadSupportTest.java | 16 +++++++++-------
.../hadoop/thrift/TestThriftToParquetFileWriter.java | 3 ++-
3 files changed, 18 insertions(+), 16 deletions(-)
diff --git
a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/example/GroupReadSupport.java
b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/example/GroupReadSupport.java
index c49b681..304a1eb 100644
---
a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/example/GroupReadSupport.java
+++
b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/example/GroupReadSupport.java
@@ -1,4 +1,4 @@
-/*
+/*
* 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
@@ -6,9 +6,9 @@
* 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
@@ -24,6 +24,7 @@ import org.apache.hadoop.conf.Configuration;
import org.apache.parquet.example.data.Group;
import org.apache.parquet.example.data.simple.convert.GroupRecordConverter;
+import org.apache.parquet.hadoop.api.InitContext;
import org.apache.parquet.hadoop.api.ReadSupport;
import org.apache.parquet.io.api.RecordMaterializer;
import org.apache.parquet.schema.MessageType;
@@ -31,11 +32,9 @@ import org.apache.parquet.schema.MessageType;
public class GroupReadSupport extends ReadSupport<Group> {
@Override
- public org.apache.parquet.hadoop.api.ReadSupport.ReadContext init(
- Configuration configuration, Map<String, String> keyValueMetaData,
- MessageType fileSchema) {
- String partialSchemaString =
configuration.get(ReadSupport.PARQUET_READ_SCHEMA);
- MessageType requestedProjection = getSchemaForRead(fileSchema,
partialSchemaString);
+ public ReadContext init(InitContext context) {
+ String partialSchemaString =
context.getConfiguration().get(ReadSupport.PARQUET_READ_SCHEMA);
+ MessageType requestedProjection =
getSchemaForRead(context.getFileSchema(), partialSchemaString);
return new ReadContext(requestedProjection);
}
diff --git
a/parquet-hadoop/src/test/java/org/apache/parquet/hadoop/example/GroupReadSupportTest.java
b/parquet-hadoop/src/test/java/org/apache/parquet/hadoop/example/GroupReadSupportTest.java
index 2a99a1b..9d97c57 100644
---
a/parquet-hadoop/src/test/java/org/apache/parquet/hadoop/example/GroupReadSupportTest.java
+++
b/parquet-hadoop/src/test/java/org/apache/parquet/hadoop/example/GroupReadSupportTest.java
@@ -1,4 +1,4 @@
-/*
+/*
* 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
@@ -6,9 +6,9 @@
* 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
@@ -18,7 +18,9 @@
*/
package org.apache.parquet.hadoop.example;
+import java.util.Set;
import org.apache.hadoop.conf.Configuration;
+import org.apache.parquet.hadoop.api.InitContext;
import org.junit.Test;
import org.apache.parquet.hadoop.api.ReadSupport;
import org.apache.parquet.schema.MessageType;
@@ -43,10 +45,10 @@ public class GroupReadSupportTest {
public void testInitWithoutSpecifyingRequestSchema() throws Exception {
GroupReadSupport s = new GroupReadSupport();
Configuration configuration = new Configuration();
- Map<String, String> keyValueMetaData = new HashMap<String, String>();
+ Map<String, Set<String>> keyValueMetaData = new HashMap<>();
MessageType fileSchema = MessageTypeParser.parseMessageType(fullSchemaStr);
- ReadSupport.ReadContext context = s.init(configuration, keyValueMetaData,
fileSchema);
+ ReadSupport.ReadContext context = s.init(new InitContext(configuration,
keyValueMetaData, fileSchema));
assertEquals(context.getRequestedSchema(), fileSchema);
}
@@ -54,12 +56,12 @@ public class GroupReadSupportTest {
public void testInitWithPartialSchema() {
GroupReadSupport s = new GroupReadSupport();
Configuration configuration = new Configuration();
- Map<String, String> keyValueMetaData = new HashMap<String, String>();
+ Map<String, Set<String>> keyValueMetaData = new HashMap<>();
MessageType fileSchema = MessageTypeParser.parseMessageType(fullSchemaStr);
MessageType partialSchema =
MessageTypeParser.parseMessageType(partialSchemaStr);
configuration.set(ReadSupport.PARQUET_READ_SCHEMA, partialSchemaStr);
- ReadSupport.ReadContext context = s.init(configuration, keyValueMetaData,
fileSchema);
+ ReadSupport.ReadContext context = s.init(new InitContext(configuration,
keyValueMetaData, fileSchema));
assertEquals(context.getRequestedSchema(), partialSchema);
}
}
diff --git
a/parquet-thrift/src/test/java/org/apache/parquet/hadoop/thrift/TestThriftToParquetFileWriter.java
b/parquet-thrift/src/test/java/org/apache/parquet/hadoop/thrift/TestThriftToParquetFileWriter.java
index e96b226..7de4476 100644
---
a/parquet-thrift/src/test/java/org/apache/parquet/hadoop/thrift/TestThriftToParquetFileWriter.java
+++
b/parquet-thrift/src/test/java/org/apache/parquet/hadoop/thrift/TestThriftToParquetFileWriter.java
@@ -28,6 +28,7 @@ import java.util.Map;
import org.apache.hadoop.fs.FileStatus;
import org.apache.parquet.column.statistics.*;
+import org.apache.parquet.hadoop.api.InitContext;
import org.apache.parquet.hadoop.metadata.BlockMetaData;
import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
import org.apache.parquet.hadoop.util.ContextUtil;
@@ -328,7 +329,7 @@ public class TestThriftToParquetFileWriter {
ParquetMetadata readFooter = ParquetFileReader.readFooter(configuration,
parquetFilePath);
MessageType schema = readFooter.getFileMetaData().getSchema();
- readSupport.init(configuration, null, schema);
+ readSupport.init(new InitContext(configuration, null, schema));
return new ParquetReader<Group>(parquetFilePath, readSupport);
}
