You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@orc.apache.org by do...@apache.org on 2022/11/07 04:05:54 UTC
[orc] branch branch-1.8 updated: ORC-1305: Add `CompressionWriter` and `InMemoryEncryption[Reader|Writer]` examples
This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch branch-1.8
in repository https://gitbox.apache.org/repos/asf/orc.git
The following commit(s) were added to refs/heads/branch-1.8 by this push:
new da67f40e8 ORC-1305: Add `CompressionWriter` and `InMemoryEncryption[Reader|Writer]` examples
da67f40e8 is described below
commit da67f40e846b8c82248b70e235c8bbb1550566d3
Author: deshanxiao <de...@microsoft.com>
AuthorDate: Sun Nov 6 20:05:25 2022 -0800
ORC-1305: Add `CompressionWriter` and `InMemoryEncryption[Reader|Writer]` examples
### What changes were proposed in this pull request?
This PR is aimed to add more java examples.
### Why are the changes needed?
We need more examples in **InMemoryCryption** and **Compression**.
### How was this patch tested?
UT
Closes #1302 from deshanxiao/deshan/add-more-example.
Authored-by: deshanxiao <de...@microsoft.com>
Signed-off-by: Dongjoon Hyun <do...@apache.org>
(cherry picked from commit 31acaaa2bcf9a454030ff7d4d44c59adb235b156)
Signed-off-by: Dongjoon Hyun <do...@apache.org>
---
java/examples/pom.xml | 4 ++
.../org/apache/orc/examples/CompressionWriter.java | 66 ++++++++++++++++++++
.../src/java/org/apache/orc/examples/Driver.java | 9 +++
.../orc/examples/InMemoryEncryptionReader.java | 68 ++++++++++++++++++++
.../orc/examples/InMemoryEncryptionWriter.java | 72 ++++++++++++++++++++++
5 files changed, 219 insertions(+)
diff --git a/java/examples/pom.xml b/java/examples/pom.xml
index bbaea6114..3e898fd3f 100644
--- a/java/examples/pom.xml
+++ b/java/examples/pom.xml
@@ -36,6 +36,10 @@
<groupId>org.apache.orc</groupId>
<artifactId>orc-core</artifactId>
</dependency>
+ <dependency>
+ <groupId>org.apache.orc</groupId>
+ <artifactId>orc-shims</artifactId>
+ </dependency>
<!-- inter-project -->
<dependency>
diff --git a/java/examples/src/java/org/apache/orc/examples/CompressionWriter.java b/java/examples/src/java/org/apache/orc/examples/CompressionWriter.java
new file mode 100644
index 000000000..3f6ce3557
--- /dev/null
+++ b/java/examples/src/java/org/apache/orc/examples/CompressionWriter.java
@@ -0,0 +1,66 @@
+/*
+ * 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
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * 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.orc.examples;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+import org.apache.orc.OrcFile;
+import org.apache.orc.OrcFile.WriterOptions;
+import org.apache.orc.TypeDescription;
+import org.apache.orc.Writer;
+
+import java.io.IOException;
+
+import static org.apache.orc.CompressionKind.SNAPPY;
+
+public class CompressionWriter {
+ public static void main(Configuration conf, String[] args) throws IOException {
+ TypeDescription schema = TypeDescription.fromString("struct<x:int,y:string>");
+ // Set compress kind to snappy. Now we have much compression
+ // method such as ZLIB, SNAPPY, LZO, LZ4, ZSTD.
+ WriterOptions options = OrcFile.writerOptions(conf).setSchema(schema).compress(SNAPPY);
+ Writer snappyWriter = OrcFile.createWriter(new Path("compressed.orc"), options);
+
+ VectorizedRowBatch batch = schema.createRowBatch();
+ LongColumnVector x = (LongColumnVector) batch.cols[0];
+ BytesColumnVector y = (BytesColumnVector) batch.cols[1];
+ for (int r = 0; r < 10000; ++r) {
+ int row = batch.size++;
+ x.vector[row] = r;
+ byte[] buffer = ("byte-" + r).getBytes();
+ y.setRef(row, buffer, 0, buffer.length);
+ // If the batch is full, write it out and start over.
+ if (batch.size == batch.getMaxSize()) {
+ snappyWriter.addRowBatch(batch);
+ batch.reset();
+ }
+ }
+ if (batch.size != 0) {
+ snappyWriter.addRowBatch(batch);
+ }
+ snappyWriter.close();
+ }
+
+ public static void main(String[] args) throws IOException {
+ main(new Configuration(), args);
+ }
+}
diff --git a/java/examples/src/java/org/apache/orc/examples/Driver.java b/java/examples/src/java/org/apache/orc/examples/Driver.java
index 7d13a1f41..69cd2b536 100644
--- a/java/examples/src/java/org/apache/orc/examples/Driver.java
+++ b/java/examples/src/java/org/apache/orc/examples/Driver.java
@@ -75,6 +75,9 @@ public class Driver {
System.err.println(" read - read a sample ORC file");
System.err.println(" write2 - write a sample ORC file with a map");
System.err.println(" read2 - read a sample ORC file with a map");
+ System.err.println(" compressWriter - write a ORC file with snappy compression");
+ System.err.println(" inMemoryEncryptionWriter - write a ORC file with encryption");
+ System.err.println(" inMemoryEncryptionReader - read a ORC file with encryption");
System.err.println();
System.err.println("To get more help, provide -h to the command");
System.exit(1);
@@ -95,6 +98,12 @@ public class Driver {
AdvancedWriter.main(conf, options.commandArgs);
} else if ("read2".equals(options.command)) {
AdvancedReader.main(conf, options.commandArgs);
+ } else if ("compressWriter".equals(options.command)) {
+ CompressionWriter.main(conf, options.commandArgs);
+ } else if ("inMemoryEncryptionWriter".equals(options.command)) {
+ InMemoryEncryptionWriter.main(conf, options.commandArgs);
+ } else if ("inMemoryEncryptionReader".equals(options.command)) {
+ InMemoryEncryptionReader.main(conf, options.commandArgs);
} else {
System.err.println("Unknown subcommand: " + options.command);
System.exit(1);
diff --git a/java/examples/src/java/org/apache/orc/examples/InMemoryEncryptionReader.java b/java/examples/src/java/org/apache/orc/examples/InMemoryEncryptionReader.java
new file mode 100644
index 000000000..368dbd3a7
--- /dev/null
+++ b/java/examples/src/java/org/apache/orc/examples/InMemoryEncryptionReader.java
@@ -0,0 +1,68 @@
+/*
+ * 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
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * 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.orc.examples;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+import org.apache.orc.InMemoryKeystore;
+import org.apache.orc.OrcFile;
+import org.apache.orc.OrcFile.ReaderOptions;
+import org.apache.orc.Reader;
+import org.apache.orc.RecordReader;
+import org.apache.orc.TypeDescription;
+
+import java.io.IOException;
+import java.nio.charset.StandardCharsets;
+
+import static org.apache.orc.EncryptionAlgorithm.AES_CTR_128;
+
+public class InMemoryEncryptionReader {
+ public static void main(Configuration conf, String[] args) throws IOException {
+ byte[] kmsKey = "secret123".getBytes(StandardCharsets.UTF_8);
+ // InMemoryKeystore is used to get key to read encryption data.
+ InMemoryKeystore keyProvider = new InMemoryKeystore().addKey("pii", AES_CTR_128, kmsKey);
+ ReaderOptions readerOptions = OrcFile.readerOptions(conf).setKeyProvider(keyProvider);
+ Reader reader = OrcFile.createReader(new Path("encrypted.orc"), readerOptions);
+
+ System.out.println("File schema: " + reader.getSchema());
+ System.out.println("Row count: " + reader.getNumberOfRows());
+
+ // Pick the schema we want to read using schema evolution
+ TypeDescription schema = TypeDescription.fromString("struct<x:int,y:string>");
+ // Read the encryption data
+ VectorizedRowBatch batch = schema.createRowBatch();
+ RecordReader rowIterator = reader.rows(reader.options().schema(schema));
+ LongColumnVector x = (LongColumnVector) batch.cols[0];
+ BytesColumnVector y = (BytesColumnVector) batch.cols[1];
+ while (rowIterator.nextBatch(batch)) {
+ for (int row = 0; row < batch.size; ++row) {
+ System.out.println("x: " + x.vector[row]);
+ System.out.println("y: " + y.toString(row));
+ }
+ }
+ rowIterator.close();
+ }
+
+ public static void main(String[] args) throws IOException {
+ main(new Configuration(), args);
+ }
+}
diff --git a/java/examples/src/java/org/apache/orc/examples/InMemoryEncryptionWriter.java b/java/examples/src/java/org/apache/orc/examples/InMemoryEncryptionWriter.java
new file mode 100644
index 000000000..f8edfd171
--- /dev/null
+++ b/java/examples/src/java/org/apache/orc/examples/InMemoryEncryptionWriter.java
@@ -0,0 +1,72 @@
+/*
+ * 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
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * 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.orc.examples;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+import org.apache.orc.InMemoryKeystore;
+import org.apache.orc.OrcFile;
+import org.apache.orc.OrcFile.WriterOptions;
+import org.apache.orc.TypeDescription;
+import org.apache.orc.Writer;
+
+import java.io.IOException;
+import java.nio.charset.StandardCharsets;
+
+import static org.apache.orc.EncryptionAlgorithm.AES_CTR_128;
+
+public class InMemoryEncryptionWriter {
+ public static void main(Configuration conf, String[] args) throws IOException {
+ TypeDescription schema = TypeDescription.fromString("struct<x:int,y:string>");
+ byte[] kmsKey = "secret123".getBytes(StandardCharsets.UTF_8);
+ // The primary use of InMemoryKeystore is for used who doesn't have a
+ // Hadoop KMS.
+ InMemoryKeystore provider = new InMemoryKeystore().addKey("pii", AES_CTR_128, kmsKey);
+ String encryption = "pii:x,y";
+ WriterOptions writerOptions =
+ OrcFile.writerOptions(conf).setSchema(schema).setKeyProvider(provider).encrypt(encryption);
+ Writer writer = OrcFile.createWriter(new Path("encrypted.orc"), writerOptions);
+
+ VectorizedRowBatch batch = schema.createRowBatch();
+ LongColumnVector x = (LongColumnVector) batch.cols[0];
+ BytesColumnVector y = (BytesColumnVector) batch.cols[1];
+ for (int r = 0; r < 10000; ++r) {
+ int row = batch.size++;
+ x.vector[row] = r;
+ byte[] buffer = ("byte-" + r).getBytes();
+ y.setRef(row, buffer, 0, buffer.length);
+ // If the batch is full, write it out and start over.
+ if (batch.size == batch.getMaxSize()) {
+ writer.addRowBatch(batch);
+ batch.reset();
+ }
+ }
+ if (batch.size != 0) {
+ writer.addRowBatch(batch);
+ }
+ writer.close();
+ }
+
+ public static void main(String[] args) throws IOException {
+ main(new Configuration(), args);
+ }
+}