karuppayya commented on code in PR #10176:
URL: https://github.com/apache/iceberg/pull/10176#discussion_r1704749308


##########
data/src/main/java/org/apache/iceberg/data/PartitionStatsGenerator.java:
##########
@@ -0,0 +1,128 @@
+/*
+ * 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.data;
+
+import java.io.IOException;
+import java.io.UncheckedIOException;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import org.apache.iceberg.ImmutableGenericPartitionStatisticsFile;
+import org.apache.iceberg.ManifestFile;
+import org.apache.iceberg.PartitionStatisticsFile;
+import org.apache.iceberg.PartitionStatsUtil;
+import org.apache.iceberg.Partitioning;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Snapshot;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.io.CloseableIterable;
+import org.apache.iceberg.io.OutputFile;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.relocated.com.google.common.collect.Iterators;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.apache.iceberg.relocated.com.google.common.collect.Maps;
+import org.apache.iceberg.types.Comparators;
+import org.apache.iceberg.types.Types;
+import org.apache.iceberg.util.SnapshotUtil;
+import org.apache.iceberg.util.Tasks;
+import org.apache.iceberg.util.ThreadPools;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+public class PartitionStatsGenerator {
+  private static final Logger LOG = 
LoggerFactory.getLogger(PartitionStatsGenerator.class);
+
+  private final Table table;
+  private String branch;
+
+  public PartitionStatsGenerator(Table table) {
+    this.table = table;
+  }
+
+  public PartitionStatsGenerator(Table table, String branch) {
+    this.table = table;
+    this.branch = branch;

Review Comment:
   We would be storing one partition stats file per snapshot + branch 
combination? Also looks like we don't have branch information in spec?



##########
data/src/main/java/org/apache/iceberg/data/PartitionStatsWriterUtil.java:
##########
@@ -0,0 +1,93 @@
+/*
+ * 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.data;
+
+import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT;
+import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT_DEFAULT;
+
+import java.io.Closeable;
+import java.io.IOException;
+import java.io.UncheckedIOException;
+import java.util.Iterator;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.HasTableOperations;
+import org.apache.iceberg.PartitionSpec;
+import org.apache.iceberg.PartitionStatsUtil;
+import org.apache.iceberg.Partitioning;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.data.parquet.GenericParquetReaders;
+import org.apache.iceberg.encryption.EncryptedFiles;
+import org.apache.iceberg.encryption.EncryptionKeyMetadata;
+import org.apache.iceberg.io.CloseableIterable;
+import org.apache.iceberg.io.DataWriter;
+import org.apache.iceberg.io.FileWriterFactory;
+import org.apache.iceberg.io.InputFile;
+import org.apache.iceberg.io.OutputFile;
+import org.apache.iceberg.parquet.Parquet;
+
+public final class PartitionStatsWriterUtil {
+
+  private PartitionStatsWriterUtil() {}
+
+  public static OutputFile newPartitionStatsFile(Table table, long snapshotId) 
{
+    FileFormat fileFormat =
+        FileFormat.fromString(
+            table.properties().getOrDefault(DEFAULT_FILE_FORMAT, 
DEFAULT_FILE_FORMAT_DEFAULT));
+    return table
+        .io()
+        .newOutputFile(
+            ((HasTableOperations) table)
+                .operations()
+                .metadataFileLocation(
+                    
fileFormat.addExtension(String.format("partition-stats-%d", snapshotId))));
+  }
+
+  public static void writePartitionStatsFile(
+      Table table, Iterator<Record> records, OutputFile outputFile) {
+    Schema dataSchema = 
PartitionStatsUtil.schema(Partitioning.partitionType(table));
+    FileFormat fileFormat =
+        FileFormat.fromString(

Review Comment:
   I think the properties are not associated to any snapshot. In which case we 
wouldn't know the format with which it was written for a specific snapshot?
   



##########
core/src/main/java/org/apache/iceberg/PartitionStatsUtil.java:
##########
@@ -0,0 +1,240 @@
+/*
+ * 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;
+
+import java.util.Map;
+import org.apache.iceberg.data.GenericRecord;
+import org.apache.iceberg.data.IdentityPartitionConverters;
+import org.apache.iceberg.data.Record;
+import org.apache.iceberg.io.CloseableIterable;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.types.Types;
+import org.apache.iceberg.util.PartitionUtil;
+
+public class PartitionStatsUtil {
+
+  private PartitionStatsUtil() {}
+
+  public enum Column {
+    PARTITION,
+    SPEC_ID,
+    DATA_RECORD_COUNT,
+    DATA_FILE_COUNT,
+    TOTAL_DATA_FILE_SIZE_IN_BYTES,
+    POSITION_DELETE_RECORD_COUNT,
+    POSITION_DELETE_FILE_COUNT,
+    EQUALITY_DELETE_RECORD_COUNT,
+    EQUALITY_DELETE_FILE_COUNT,
+    TOTAL_RECORD_COUNT,
+    LAST_UPDATED_AT,
+    LAST_UPDATED_SNAPSHOT_ID
+  }
+
+  /**
+   * Generates a schema as per partition statistics spec based on the given 
partition type.
+   *
+   * @param partitionType the struct type that defines the structure of the 
partition.
+   * @return a schema that corresponds to the provided partition type.
+   */
+  public static Schema schema(Types.StructType partitionType) {
+    Preconditions.checkState(
+        !partitionType.fields().isEmpty(), "getting schema for an 
unpartitioned table");
+
+    return new Schema(
+        Types.NestedField.required(1, Column.PARTITION.name(), partitionType),
+        Types.NestedField.required(2, Column.SPEC_ID.name(), 
Types.IntegerType.get()),

Review Comment:
   Here are we referring to the spec id corresponding to the snapshot for which 
stats are collected? (We store the unified partition spec, but also store 
spec_id. The spec referred to will not be same as the one stored in stats 
files, is that intended?)



-- 
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: issues-unsubscr...@iceberg.apache.org

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

Reply via email to