wgtmac commented on code in PR #1016: URL: https://github.com/apache/parquet-mr/pull/1016#discussion_r1062349914
########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/DataMaskingUtil.java: ########## @@ -0,0 +1,95 @@ +/* + * 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.util; + +import org.apache.parquet.hadoop.metadata.ColumnPath; +import org.apache.parquet.schema.GroupType; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type; + +import java.util.ArrayList; +import java.util.HashSet; +import java.util.List; +import java.util.Set; + +public class DataMaskingUtil +{ Review Comment: The left curly brace should be moved to the end of the above line. ########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/example/GroupReadSupport.java: ########## @@ -35,8 +37,21 @@ 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); - return new ReadContext(requestedProjection); + String removeColumns = configuration.get(DataMaskingUtil.DATA_MASKING_COLUMNS); Review Comment: It seems that only the example `ReadSupport` has enabled skipping masked columns. Does it mean that other ReadSupport implementations are required to apply the same approach? If yes, does the `AvroReadSupport` class require the change, too? ########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/DataMaskingUtil.java: ########## @@ -0,0 +1,95 @@ +/* + * 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.util; + +import org.apache.parquet.hadoop.metadata.ColumnPath; +import org.apache.parquet.schema.GroupType; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type; + +import java.util.ArrayList; +import java.util.HashSet; +import java.util.List; +import java.util.Set; + +public class DataMaskingUtil +{ + public final static String DATA_MASKING_COLUMNS = "parquet.data.masking.columns"; + public final static String DELIMITER = ","; + + public static MessageType removeColumnsInSchema(MessageType schema, String removeColumns) + { + if (removeColumns == null || removeColumns.isEmpty()) { + return schema; + } + + Set<ColumnPath> paths = getColumnPaths(removeColumns); + List<String> currentPath = new ArrayList<>(); + List<Type> prunedFields = removeColumnsInFields(schema.getFields(), currentPath, paths); + return new MessageType(schema.getName(), prunedFields); Review Comment: What if all columns have been pruned and an empty schema is returned? ########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/DataMaskingUtil.java: ########## @@ -0,0 +1,95 @@ +/* + * 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.util; + +import org.apache.parquet.hadoop.metadata.ColumnPath; +import org.apache.parquet.schema.GroupType; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type; + +import java.util.ArrayList; +import java.util.HashSet; +import java.util.List; +import java.util.Set; + +public class DataMaskingUtil +{ + public final static String DATA_MASKING_COLUMNS = "parquet.data.masking.columns"; Review Comment: Should we update the [doc](https://github.com/apache/parquet-mr/blob/master/parquet-hadoop/README.md#class-readsupport) to reflect the new config? ########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/DataMaskingUtil.java: ########## @@ -0,0 +1,95 @@ +/* + * 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.util; + +import org.apache.parquet.hadoop.metadata.ColumnPath; +import org.apache.parquet.schema.GroupType; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type; + +import java.util.ArrayList; +import java.util.HashSet; +import java.util.List; +import java.util.Set; + +public class DataMaskingUtil +{ + public final static String DATA_MASKING_COLUMNS = "parquet.data.masking.columns"; + public final static String DELIMITER = ","; + + public static MessageType removeColumnsInSchema(MessageType schema, String removeColumns) + { Review Comment: ditto ########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/example/GroupReadSupport.java: ########## @@ -35,8 +37,21 @@ 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); - return new ReadContext(requestedProjection); + String removeColumns = configuration.get(DataMaskingUtil.DATA_MASKING_COLUMNS); + + if (removeColumns == null) { + MessageType requestedProjection = getSchemaForRead(fileSchema, partialSchemaString); + return new ReadContext(requestedProjection); + } + + if (partialSchemaString == null) { + return new ReadContext(DataMaskingUtil.removeColumnsInSchema(fileSchema, removeColumns)); + } else { + MessageType updatedSchema = DataMaskingUtil.removeColumnsInSchema( + MessageTypeParser.parseMessageType(partialSchemaString), removeColumns); + MessageType requestedProjection = getSchemaForRead(fileSchema, updatedSchema.toString()); Review Comment: Why not calling `MessageType requestedProjection = getSchemaForRead(fileSchema, updatedSchema);` -- 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: dev-unsubscr...@parquet.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
