This is an automated email from the ASF dual-hosted git repository.
lzljs3620320 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
The following commit(s) were added to refs/heads/master by this push:
new 82144effc [core] Support statistics system table for paimon (#3172)
82144effc is described below
commit 82144effcae98607078c0214ae7e4e6100fcf7e5
Author: xuzifu666 <[email protected]>
AuthorDate: Wed Apr 10 14:41:49 2024 +0800
[core] Support statistics system table for paimon (#3172)
---
.../apache/paimon/table/system/StatisticTable.java | 228 +++++++++++++++++++++
.../paimon/table/system/SystemTableLoader.java | 3 +
.../paimon/spark/sql/AnalyzeTableTestBase.scala | 20 ++
3 files changed, 251 insertions(+)
diff --git
a/paimon-core/src/main/java/org/apache/paimon/table/system/StatisticTable.java
b/paimon-core/src/main/java/org/apache/paimon/table/system/StatisticTable.java
new file mode 100644
index 000000000..2f795fd4a
--- /dev/null
+++
b/paimon-core/src/main/java/org/apache/paimon/table/system/StatisticTable.java
@@ -0,0 +1,228 @@
+/*
+ * 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.paimon.table.system;
+
+import org.apache.paimon.data.BinaryString;
+import org.apache.paimon.data.GenericRow;
+import org.apache.paimon.data.InternalRow;
+import org.apache.paimon.disk.IOManager;
+import org.apache.paimon.fs.FileIO;
+import org.apache.paimon.fs.Path;
+import org.apache.paimon.predicate.Predicate;
+import org.apache.paimon.reader.RecordReader;
+import org.apache.paimon.stats.Statistics;
+import org.apache.paimon.table.FileStoreTable;
+import org.apache.paimon.table.ReadonlyTable;
+import org.apache.paimon.table.Table;
+import org.apache.paimon.table.source.InnerTableRead;
+import org.apache.paimon.table.source.InnerTableScan;
+import org.apache.paimon.table.source.ReadOnceTableScan;
+import org.apache.paimon.table.source.Split;
+import org.apache.paimon.table.source.TableRead;
+import org.apache.paimon.types.BigIntType;
+import org.apache.paimon.types.DataField;
+import org.apache.paimon.types.RowType;
+import org.apache.paimon.utils.IteratorRecordReader;
+import org.apache.paimon.utils.JsonSerdeUtil;
+import org.apache.paimon.utils.ProjectedRow;
+import org.apache.paimon.utils.SerializationUtils;
+import org.apache.paimon.utils.SnapshotManager;
+
+import org.apache.paimon.shade.guava30.com.google.common.collect.Iterators;
+
+import java.io.IOException;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import java.util.Objects;
+
+import static org.apache.paimon.catalog.Catalog.SYSTEM_TABLE_SPLITTER;
+
+/** A {@link Table} for showing statistic of table. */
+public class StatisticTable implements ReadonlyTable {
+
+ private static final long serialVersionUID = 1L;
+
+ public static final String STATISTICS = "statistics";
+
+ public static final RowType TABLE_TYPE =
+ new RowType(
+ Arrays.asList(
+ new DataField(0, "snapshot_id", new
BigIntType(false)),
+ new DataField(1, "schema_id", new
BigIntType(false)),
+ new DataField(2, "mergedRecordCount", new
BigIntType(true)),
+ new DataField(3, "mergedRecordSize", new
BigIntType(true)),
+ new DataField(2, "colstat",
SerializationUtils.newStringType(true))));
+
+ private final FileIO fileIO;
+ private final Path location;
+
+ private final FileStoreTable dataTable;
+
+ public StatisticTable(FileIO fileIO, Path location, FileStoreTable
dataTable) {
+ this.fileIO = fileIO;
+ this.location = location;
+ this.dataTable = dataTable;
+ }
+
+ @Override
+ public String name() {
+ return dataTable.name() + SYSTEM_TABLE_SPLITTER + STATISTICS;
+ }
+
+ @Override
+ public RowType rowType() {
+ return TABLE_TYPE;
+ }
+
+ @Override
+ public List<String> primaryKeys() {
+ return Collections.singletonList("snapshot_id");
+ }
+
+ @Override
+ public InnerTableScan newScan() {
+ return new StatisticTable.StatisticScan();
+ }
+
+ @Override
+ public InnerTableRead newRead() {
+ return new StatisticRead(fileIO, dataTable);
+ }
+
+ @Override
+ public Table copy(Map<String, String> dynamicOptions) {
+ return new StatisticTable(fileIO, location,
dataTable.copy(dynamicOptions));
+ }
+
+ private class StatisticScan extends ReadOnceTableScan {
+
+ @Override
+ public InnerTableScan withFilter(Predicate predicate) {
+ // TODO
+ return this;
+ }
+
+ @Override
+ public Plan innerPlan() {
+ long rowCount;
+ try {
+ rowCount = new SnapshotManager(fileIO,
location).snapshotCount();
+ } catch (IOException e) {
+ throw new RuntimeException(e);
+ }
+ return () ->
+ Collections.singletonList(
+ new StatisticTable.StatisticSplit(rowCount,
location));
+ }
+ }
+
+ private static class StatisticSplit implements Split {
+
+ private static final long serialVersionUID = 1L;
+
+ private final long rowCount;
+ private final Path location;
+
+ private StatisticSplit(long rowCount, Path location) {
+ this.location = location;
+ this.rowCount = rowCount;
+ }
+
+ @Override
+ public long rowCount() {
+ return rowCount;
+ }
+
+ @Override
+ public boolean equals(Object o) {
+ if (this == o) {
+ return true;
+ }
+ if (o == null || getClass() != o.getClass()) {
+ return false;
+ }
+ StatisticTable.StatisticSplit that =
(StatisticTable.StatisticSplit) o;
+ return Objects.equals(location, that.location);
+ }
+
+ @Override
+ public int hashCode() {
+ return Objects.hash(location);
+ }
+ }
+
+ private static class StatisticRead implements InnerTableRead {
+
+ private final FileIO fileIO;
+ private int[][] projection;
+
+ private final FileStoreTable dataTable;
+
+ public StatisticRead(FileIO fileIO, FileStoreTable dataTable) {
+ this.fileIO = fileIO;
+ this.dataTable = dataTable;
+ }
+
+ @Override
+ public InnerTableRead withFilter(Predicate predicate) {
+ // TODO
+ return this;
+ }
+
+ @Override
+ public InnerTableRead withProjection(int[][] projection) {
+ this.projection = projection;
+ return this;
+ }
+
+ @Override
+ public TableRead withIOManager(IOManager ioManager) {
+ return this;
+ }
+
+ @Override
+ public RecordReader<InternalRow> createReader(Split split) throws
IOException {
+ if (!(split instanceof StatisticTable.StatisticSplit)) {
+ throw new IllegalArgumentException("Unsupported split: " +
split.getClass());
+ }
+ Statistics statistics = dataTable.statistics().get();
+ Iterator<Statistics> statisticsIterator =
+ Collections.singletonList(statistics).iterator();
+ Iterator<InternalRow> rows =
Iterators.transform(statisticsIterator, this::toRow);
+ if (projection != null) {
+ rows =
+ Iterators.transform(
+ rows, row ->
ProjectedRow.from(projection).replaceRow(row));
+ }
+ return new IteratorRecordReader<>(rows);
+ }
+
+ private InternalRow toRow(Statistics statistics) {
+ return GenericRow.of(
+ statistics.snapshotId(),
+ statistics.schemaId(),
+ statistics.mergedRecordCount().getAsLong(),
+ statistics.mergedRecordSize().getAsLong(),
+
BinaryString.fromString(JsonSerdeUtil.toJson(statistics.colStats())));
+ }
+ }
+}
diff --git
a/paimon-core/src/main/java/org/apache/paimon/table/system/SystemTableLoader.java
b/paimon-core/src/main/java/org/apache/paimon/table/system/SystemTableLoader.java
index dcbe0fed1..8dbd53fe9 100644
---
a/paimon-core/src/main/java/org/apache/paimon/table/system/SystemTableLoader.java
+++
b/paimon-core/src/main/java/org/apache/paimon/table/system/SystemTableLoader.java
@@ -48,6 +48,7 @@ import static
org.apache.paimon.table.system.SchemasTable.SCHEMAS;
import static
org.apache.paimon.table.system.SinkTableLineageTable.SINK_TABLE_LINEAGE;
import static org.apache.paimon.table.system.SnapshotsTable.SNAPSHOTS;
import static
org.apache.paimon.table.system.SourceTableLineageTable.SOURCE_TABLE_LINEAGE;
+import static org.apache.paimon.table.system.StatisticTable.STATISTICS;
import static org.apache.paimon.table.system.TagsTable.TAGS;
import static org.apache.paimon.utils.Preconditions.checkNotNull;
@@ -82,6 +83,8 @@ public class SystemTableLoader {
return new ReadOptimizedTable(dataTable);
case AGGREGATION:
return new AggregationFieldsTable(fileIO, location);
+ case STATISTICS:
+ return new StatisticTable(fileIO, location, dataTable);
default:
return null;
}
diff --git
a/paimon-spark/paimon-spark-common/src/test/scala/org/apache/paimon/spark/sql/AnalyzeTableTestBase.scala
b/paimon-spark/paimon-spark-common/src/test/scala/org/apache/paimon/spark/sql/AnalyzeTableTestBase.scala
index b25881b72..dbe069be3 100644
---
a/paimon-spark/paimon-spark-common/src/test/scala/org/apache/paimon/spark/sql/AnalyzeTableTestBase.scala
+++
b/paimon-spark/paimon-spark-common/src/test/scala/org/apache/paimon/spark/sql/AnalyzeTableTestBase.scala
@@ -50,6 +50,26 @@ abstract class AnalyzeTableTestBase extends
PaimonSparkTestBase {
Assertions.assertTrue(stats.colStats().isEmpty)
}
+ test("Paimon analyze: test statistic system table") {
+ spark.sql(s"""
+ |CREATE TABLE T (id STRING, name STRING, i INT, l LONG)
+ |USING PAIMON
+ |TBLPROPERTIES ('primary-key'='id')
+ |""".stripMargin)
+
+ spark.sql(s"INSERT INTO T VALUES ('1', 'a', 1, 1)")
+ spark.sql(s"INSERT INTO T VALUES ('2', 'aaa', 1, 2)")
+
+ spark.sql(s"ANALYZE TABLE T COMPUTE STATISTICS")
+
+ val df =
+ spark.sql("select snapshot_id, schema_id, mergedRecordCount, colstat
from `T$statistics`")
+ Assertions.assertEquals(df.collect().size, 1)
+ checkAnswer(
+ spark.sql("SELECT snapshot_id, schema_id, mergedRecordCount, colstat
from `T$statistics`"),
+ Row(2, 0, 2, "{ }"))
+ }
+
test("Paimon analyze: analyze no scan") {
spark.sql(s"CREATE TABLE T (id STRING, name STRING)")
assertThatThrownBy(() => spark.sql(s"ANALYZE TABLE T COMPUTE STATISTICS
NOSCAN"))
