[
https://issues.apache.org/jira/browse/PARQUET-2075?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17655956#comment-17655956
]
ASF GitHub Bot commented on PARQUET-2075:
-----------------------------------------
ggershinsky commented on code in PR #1014:
URL: https://github.com/apache/parquet-mr/pull/1014#discussion_r1064348254
##########
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/rewrite/RewriteOptions.java:
##########
@@ -0,0 +1,178 @@
+/*
+ * 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.parquet.hadoop.rewrite;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.parquet.Preconditions;
+import org.apache.parquet.crypto.FileEncryptionProperties;
+import org.apache.parquet.hadoop.metadata.CompressionCodecName;
+
+import java.util.List;
+import java.util.Map;
+
+// A set of options to create a ParquetRewriter.
+public class RewriteOptions {
+
+ final Configuration conf;
+ final Path inputFile;
+ final Path outputFile;
+ final List<String> pruneColumns;
+ final CompressionCodecName newCodecName;
+ final Map<String, MaskMode> maskColumns;
+ final List<String> encryptColumns;
+ final FileEncryptionProperties fileEncryptionProperties;
+
+ private RewriteOptions(Configuration conf,
+ Path inputFile,
+ Path outputFile,
+ List<String> pruneColumns,
+ CompressionCodecName newCodecName,
+ Map<String, MaskMode> maskColumns,
+ List<String> encryptColumns,
+ FileEncryptionProperties fileEncryptionProperties) {
+ this.conf = conf;
+ this.inputFile = inputFile;
+ this.outputFile = outputFile;
+ this.pruneColumns = pruneColumns;
+ this.newCodecName = newCodecName;
+ this.maskColumns = maskColumns;
+ this.encryptColumns = encryptColumns;
+ this.fileEncryptionProperties = fileEncryptionProperties;
+ }
+
+ public Configuration getConf() {
+ return conf;
+ }
+
+ public Path getInputFile() {
+ return inputFile;
+ }
+
+ public Path getOutputFile() {
+ return outputFile;
+ }
+
+ public List<String> getPruneColumns() {
+ return pruneColumns;
+ }
+
+ public CompressionCodecName getNewCodecName() {
+ return newCodecName;
+ }
+
+ public Map<String, MaskMode> getMaskColumns() {
+ return maskColumns;
+ }
+
+ public List<String> getEncryptColumns() {
+ return encryptColumns;
+ }
+
+ public FileEncryptionProperties getFileEncryptionProperties() {
+ return fileEncryptionProperties;
+ }
+
+ // Builder to create a RewriterOptions.
+ public static class Builder {
+ private Configuration conf;
+ private Path inputFile;
+ private Path outputFile;
+ private List<String> pruneColumns;
+ private CompressionCodecName newCodecName;
+ private Map<String, MaskMode> maskColumns;
+ private List<String> encryptColumns;
+ private FileEncryptionProperties fileEncryptionProperties;
+
+ public Builder(Configuration conf, Path inputFile, Path outputFile) {
+ this.conf = conf;
+ this.inputFile = inputFile;
+ this.outputFile = outputFile;
+ }
+
+ public Builder prune(List<String> columns) {
+ this.pruneColumns = columns;
+ return this;
+ }
+
+ public Builder transform(CompressionCodecName newCodecName) {
+ this.newCodecName = newCodecName;
+ return this;
+ }
+
+ public Builder mask(Map<String, MaskMode> maskColumns) {
+ this.maskColumns = maskColumns;
+ return this;
+ }
+
+ public Builder encrypt(List<String> encryptColumns) {
+ this.encryptColumns = encryptColumns;
+ return this;
+ }
+
+ public Builder encryptionProperties(FileEncryptionProperties
fileEncryptionProperties) {
+ this.fileEncryptionProperties = fileEncryptionProperties;
+ return this;
+ }
+
+ public RewriteOptions build() {
+ Preconditions.checkArgument(inputFile != null, "Input file is required");
+ Preconditions.checkArgument(outputFile != null, "Output file is
required");
+
+ if (pruneColumns != null) {
+ if (maskColumns != null) {
+ for (String pruneColumn : pruneColumns) {
+ Preconditions.checkArgument(!maskColumns.containsKey(pruneColumn),
+ "Cannot prune and mask same column");
+ }
+ }
+
+ if (encryptColumns != null) {
+ for (String pruneColumn : pruneColumns) {
+ Preconditions.checkArgument(!encryptColumns.contains(pruneColumn),
+ "Cannot prune and mask same column");
Review Comment:
Cannot prune and encrypt same column?
##########
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/rewrite/RewriteOptions.java:
##########
@@ -0,0 +1,178 @@
+/*
+ * 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.parquet.hadoop.rewrite;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.parquet.Preconditions;
+import org.apache.parquet.crypto.FileEncryptionProperties;
+import org.apache.parquet.hadoop.metadata.CompressionCodecName;
+
+import java.util.List;
+import java.util.Map;
+
+// A set of options to create a ParquetRewriter.
+public class RewriteOptions {
+
+ final Configuration conf;
+ final Path inputFile;
+ final Path outputFile;
+ final List<String> pruneColumns;
+ final CompressionCodecName newCodecName;
+ final Map<String, MaskMode> maskColumns;
+ final List<String> encryptColumns;
+ final FileEncryptionProperties fileEncryptionProperties;
+
+ private RewriteOptions(Configuration conf,
+ Path inputFile,
+ Path outputFile,
+ List<String> pruneColumns,
+ CompressionCodecName newCodecName,
+ Map<String, MaskMode> maskColumns,
+ List<String> encryptColumns,
+ FileEncryptionProperties fileEncryptionProperties) {
+ this.conf = conf;
+ this.inputFile = inputFile;
+ this.outputFile = outputFile;
+ this.pruneColumns = pruneColumns;
+ this.newCodecName = newCodecName;
+ this.maskColumns = maskColumns;
+ this.encryptColumns = encryptColumns;
+ this.fileEncryptionProperties = fileEncryptionProperties;
+ }
+
+ public Configuration getConf() {
+ return conf;
+ }
+
+ public Path getInputFile() {
+ return inputFile;
+ }
+
+ public Path getOutputFile() {
+ return outputFile;
+ }
+
+ public List<String> getPruneColumns() {
+ return pruneColumns;
+ }
+
+ public CompressionCodecName getNewCodecName() {
+ return newCodecName;
+ }
+
+ public Map<String, MaskMode> getMaskColumns() {
+ return maskColumns;
+ }
+
+ public List<String> getEncryptColumns() {
+ return encryptColumns;
+ }
+
+ public FileEncryptionProperties getFileEncryptionProperties() {
+ return fileEncryptionProperties;
+ }
+
+ // Builder to create a RewriterOptions.
+ public static class Builder {
+ private Configuration conf;
+ private Path inputFile;
+ private Path outputFile;
+ private List<String> pruneColumns;
+ private CompressionCodecName newCodecName;
+ private Map<String, MaskMode> maskColumns;
+ private List<String> encryptColumns;
+ private FileEncryptionProperties fileEncryptionProperties;
+
+ public Builder(Configuration conf, Path inputFile, Path outputFile) {
+ this.conf = conf;
+ this.inputFile = inputFile;
+ this.outputFile = outputFile;
+ }
+
+ public Builder prune(List<String> columns) {
+ this.pruneColumns = columns;
+ return this;
+ }
+
+ public Builder transform(CompressionCodecName newCodecName) {
+ this.newCodecName = newCodecName;
+ return this;
+ }
+
+ public Builder mask(Map<String, MaskMode> maskColumns) {
+ this.maskColumns = maskColumns;
+ return this;
+ }
+
+ public Builder encrypt(List<String> encryptColumns) {
+ this.encryptColumns = encryptColumns;
+ return this;
+ }
+
+ public Builder encryptionProperties(FileEncryptionProperties
fileEncryptionProperties) {
+ this.fileEncryptionProperties = fileEncryptionProperties;
+ return this;
+ }
+
+ public RewriteOptions build() {
+ Preconditions.checkArgument(inputFile != null, "Input file is required");
+ Preconditions.checkArgument(outputFile != null, "Output file is
required");
+
+ if (pruneColumns != null) {
+ if (maskColumns != null) {
+ for (String pruneColumn : pruneColumns) {
+ Preconditions.checkArgument(!maskColumns.containsKey(pruneColumn),
+ "Cannot prune and mask same column");
+ }
+ }
+
+ if (encryptColumns != null) {
+ for (String pruneColumn : pruneColumns) {
+ Preconditions.checkArgument(!encryptColumns.contains(pruneColumn),
+ "Cannot prune and mask same column");
+ }
+ }
+ }
+
+ // TODO: support masking and encrypting same columns
+ if (maskColumns != null && encryptColumns != null) {
+ for (String encryptColumn : encryptColumns) {
+ Preconditions.checkArgument(!maskColumns.containsKey(encryptColumn),
+ "Cannot encrypt and mask same column");
+ }
+ }
+
+ if (encryptColumns != null && !encryptColumns.isEmpty()) {
+ Preconditions.checkArgument(fileEncryptionProperties != null,
Review Comment:
what if `fileEncryptionProperties` was set, but the `encryptColumns` is null
or `encryptColumns.isEmpty()`?
##########
parquet-hadoop/src/test/java/org/apache/parquet/hadoop/rewrite/ParquetRewriterTest.java:
##########
@@ -0,0 +1,308 @@
+/*
+ * 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.parquet.hadoop.rewrite;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.parquet.HadoopReadOptions;
+import org.apache.parquet.column.ParquetProperties;
+import org.apache.parquet.example.data.Group;
+import org.apache.parquet.example.data.simple.SimpleGroup;
+import org.apache.parquet.format.DataPageHeader;
+import org.apache.parquet.format.DataPageHeaderV2;
+import org.apache.parquet.format.PageHeader;
+import org.apache.parquet.format.converter.ParquetMetadataConverter;
+import org.apache.parquet.hadoop.ParquetFileReader;
+import org.apache.parquet.hadoop.ParquetReader;
+import org.apache.parquet.hadoop.example.GroupReadSupport;
+import org.apache.parquet.hadoop.metadata.BlockMetaData;
+import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
+import org.apache.parquet.hadoop.metadata.CompressionCodecName;
+import org.apache.parquet.hadoop.metadata.ParquetMetadata;
+import
org.apache.parquet.hadoop.util.CompressionConverter.TransParquetFileReader;
+import org.apache.parquet.hadoop.util.EncryptionTestFile;
+import org.apache.parquet.hadoop.util.HadoopInputFile;
+import org.apache.parquet.hadoop.util.TestFileBuilder;
+import org.apache.parquet.internal.column.columnindex.ColumnIndex;
+import org.apache.parquet.internal.column.columnindex.OffsetIndex;
+import org.apache.parquet.schema.GroupType;
+import org.apache.parquet.schema.MessageType;
+import org.apache.parquet.schema.PrimitiveType;
+import org.apache.parquet.schema.Type;
+import org.junit.Assert;
+import org.junit.Test;
+
+import java.io.IOException;
+import java.util.*;
+
+import static
org.apache.parquet.format.converter.ParquetMetadataConverter.NO_FILTER;
+import static org.apache.parquet.schema.PrimitiveType.PrimitiveTypeName.BINARY;
+import static org.apache.parquet.schema.PrimitiveType.PrimitiveTypeName.INT64;
+import static org.apache.parquet.schema.Type.Repetition.*;
+import static org.junit.Assert.*;
+
+public class ParquetRewriterTest {
+
+ private final int numRecord = 100000;
+ private Configuration conf = new Configuration();
+ private EncryptionTestFile inputFile = null;
+ private String outputFile = null;
+ private ParquetRewriter rewriter = null;
+
+ @Test
+ public void testPruneSingleColumnAndTranslateCodec() throws Exception {
Review Comment:
do we also have an encryption rewrite unitest?
##########
parquet-hadoop/src/test/java/org/apache/parquet/hadoop/rewrite/ParquetRewriterTest.java:
##########
@@ -0,0 +1,308 @@
+/*
+ * 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.parquet.hadoop.rewrite;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.parquet.HadoopReadOptions;
+import org.apache.parquet.column.ParquetProperties;
+import org.apache.parquet.example.data.Group;
+import org.apache.parquet.example.data.simple.SimpleGroup;
+import org.apache.parquet.format.DataPageHeader;
+import org.apache.parquet.format.DataPageHeaderV2;
+import org.apache.parquet.format.PageHeader;
+import org.apache.parquet.format.converter.ParquetMetadataConverter;
+import org.apache.parquet.hadoop.ParquetFileReader;
+import org.apache.parquet.hadoop.ParquetReader;
+import org.apache.parquet.hadoop.example.GroupReadSupport;
+import org.apache.parquet.hadoop.metadata.BlockMetaData;
+import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
+import org.apache.parquet.hadoop.metadata.CompressionCodecName;
+import org.apache.parquet.hadoop.metadata.ParquetMetadata;
+import
org.apache.parquet.hadoop.util.CompressionConverter.TransParquetFileReader;
+import org.apache.parquet.hadoop.util.EncryptionTestFile;
+import org.apache.parquet.hadoop.util.HadoopInputFile;
+import org.apache.parquet.hadoop.util.TestFileBuilder;
+import org.apache.parquet.internal.column.columnindex.ColumnIndex;
+import org.apache.parquet.internal.column.columnindex.OffsetIndex;
+import org.apache.parquet.schema.GroupType;
+import org.apache.parquet.schema.MessageType;
+import org.apache.parquet.schema.PrimitiveType;
+import org.apache.parquet.schema.Type;
+import org.junit.Assert;
+import org.junit.Test;
+
+import java.io.IOException;
+import java.util.*;
Review Comment:
please don't use * (also in lines 57, 58)
> Unified Rewriter Tool
> -----------------------
>
> Key: PARQUET-2075
> URL: https://issues.apache.org/jira/browse/PARQUET-2075
> Project: Parquet
> Issue Type: New Feature
> Reporter: Xinli Shang
> Assignee: Gang Wu
> Priority: Major
>
> During the discussion of PARQUET-2071, we came up with the idea of a
> universal tool to translate the existing file to a different state while
> skipping some level steps like encoding/decoding, to gain speed. For example,
> only decompress pages and then compress directly. For PARQUET-2071, we only
> decrypt and then encrypt directly. This will be useful for the existing data
> to onboard Parquet features like column encryption, zstd etc.
> We already have tools like trans-compression, column pruning etc. We will
> consolidate all these tools with this universal tool.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
