cmathiesen commented on a change in pull request #933: URL: https://github.com/apache/iceberg/pull/933#discussion_r439539602
########## File path: mr/src/main/java/org/apache/iceberg/mr/mapred/IcebergInputFormat.java ########## @@ -0,0 +1,306 @@ +/* + * 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.iceberg.mr.mapred; + +import java.io.DataInput; +import java.io.DataOutput; +import java.io.IOException; +import java.net.URI; +import java.util.Iterator; +import java.util.List; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.exec.SerializationUtilities; +import org.apache.hadoop.hive.ql.io.CombineHiveInputFormat; +import org.apache.hadoop.hive.ql.io.sarg.ConvertAstToSearchArg; +import org.apache.hadoop.hive.ql.io.sarg.PredicateLeaf; +import org.apache.hadoop.hive.ql.io.sarg.SearchArgument; +import org.apache.hadoop.hive.ql.plan.ExprNodeGenericFuncDesc; +import org.apache.hadoop.hive.ql.plan.TableScanDesc; +import org.apache.hadoop.hive.serde2.ColumnProjectionUtils; +import org.apache.hadoop.mapred.FileSplit; +import org.apache.hadoop.mapred.InputFormat; +import org.apache.hadoop.mapred.InputSplit; +import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.mapred.RecordReader; +import org.apache.hadoop.mapred.Reporter; +import org.apache.iceberg.CombinedScanTask; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.SnapshotsTable; +import org.apache.iceberg.Table; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.mr.InputFormatConfig; +import org.apache.iceberg.mr.SerializationUtil; +import org.apache.iceberg.mr.mapred.iterables.SnapshotIterable; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * CombineHiveInputFormat.AvoidSplitCombination is implemented to correctly delegate InputSplit + * creation to this class. See: https://stackoverflow.com/questions/29133275/ + * custom-inputformat-getsplits-never-called-in-hive + */ +public class IcebergInputFormat<T> implements InputFormat<Void, T>, CombineHiveInputFormat.AvoidSplitCombination { + private static final Logger LOG = LoggerFactory.getLogger(IcebergInputFormat.class); + + private Table table; + private long currentSnapshotId; + private String virtualSnapshotIdColumnName; + + @Override + public InputSplit[] getSplits(JobConf conf, int numSplits) throws IOException { + table = TableResolver.resolveTableFromJob(conf); + URI location = TableResolver.pathAsURI(conf.get(InputFormatConfig.TABLE_LOCATION)); + List<CombinedScanTask> tasks = planTasks(conf); + return createSplits(tasks, location.toString()); + } + + private List<CombinedScanTask> planTasks(JobConf conf) { + // Set defaults for virtual column + Snapshot currentSnapshot = table.currentSnapshot(); + if (currentSnapshot != null) { + currentSnapshotId = currentSnapshot.snapshotId(); + } + virtualSnapshotIdColumnName = SystemTableUtil.getVirtualColumnName(conf); + + String[] readColumns = ColumnProjectionUtils.getReadColumnNames(conf); + List<CombinedScanTask> tasks; + if (conf.get(TableScanDesc.FILTER_EXPR_CONF_STR) == null) { + tasks = Lists.newArrayList(table + .newScan() + .select(readColumns) + .planTasks()); + } else { + ExprNodeGenericFuncDesc exprNodeDesc = SerializationUtilities + .deserializeObject(conf.get(TableScanDesc.FILTER_EXPR_CONF_STR), ExprNodeGenericFuncDesc.class); + SearchArgument sarg = ConvertAstToSearchArg.create(conf, exprNodeDesc); + Expression filter = IcebergFilterFactory.generateFilterExpression(sarg); + + long snapshotIdToScan = extractSnapshotID(conf, exprNodeDesc); Review comment: Yeah, this was an edge case that cropped up when we were testing. We got around it by making it configurable but with a default of `snapshot__id`. So by default we're adding this extra column to a table schema, but if a user knows they already have a column with this same name they can set the virtual column to a different name: ``` TBLPROPERTIES ('iceberg.hive.snapshot.virtual.column.name' = 'new_column_name') ``` But reserving column names would be a nice addition so this check doesn't need to happen ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
