Skip to content

[core] Add min_partition_stats and max_partition_stats columns to manifests system table #4922

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JingsongLi merged 1 commit into from
Jan 16, 2025
Merged

[core] Add min_partition_stats and max_partition_stats columns to manifests system table #4922

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 21 additions & 21 deletions docs/content/concepts/system-tables.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -279,45 +279,45 @@ You can query all manifest files contained in the latest snapshot or the specifi
SELECT * FROM my_table$manifests;

/*
+--------------------------------+-------------+------------------+-------------------+---------------+
| file_name | file_size | num_added_files | num_deleted_files | schema_id |
+--------------------------------+-------------+------------------+-------------------+---------------+
| manifest-f4dcab43-ef6b-4713... | 12365| 40 | 0 | 0 |
| manifest-f4dcab43-ef6b-4713... | 1648 | 1 | 0 | 0 |
+--------------------------------+-------------+------------------+-------------------+---------------+
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
| file_name | file_size | num_added_files | num_deleted_files | schema_id | min_partition_stats | max_partition_stats |
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
| manifest-f4dcab43-ef6b-4713... | 12365| 40 | 0 | 0 | {20230315, 00} | {20230315, 20} |
| manifest-f4dcab43-ef6b-4713... | 1648 | 1 | 0 | 0 | {20230115, 00} | {20230316, 23} |
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
2 rows in set
*/

-- You can also query the manifest with specified snapshot
SELECT * FROM my_table$manifests /*+ OPTIONS('scan.snapshot-id'='1') */;
/*
+--------------------------------+-------------+------------------+-------------------+---------------+
| file_name | file_size | num_added_files | num_deleted_files | schema_id |
+--------------------------------+-------------+------------------+-------------------+---------------+
| manifest-f4dcab43-ef6b-4713... | 12365| 40 | 0 | 0 |
+--------------------------------+-------------+------------------+-------------------+---------------+
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
| file_name | file_size | num_added_files | num_deleted_files | schema_id | min_partition_stats | max_partition_stats |
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
| manifest-f4dcab43-ef6b-4713... | 12365| 40 | 0 | 0 | {20230315, 00} | {20230315, 20} |
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
1 rows in set
*/

- You can also query the manifest with specified tagName
SELECT * FROM my_table$manifests /*+ OPTIONS('scan.tag-name'='tag1') */;
/*
+--------------------------------+-------------+------------------+-------------------+---------------+
| file_name | file_size | num_added_files | num_deleted_files | schema_id |
+--------------------------------+-------------+------------------+-------------------+---------------+
| manifest-f4dcab43-ef6b-4713... | 12365| 40 | 0 | 0 |
+--------------------------------+-------------+------------------+-------------------+---------------+
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
| file_name | file_size | num_added_files | num_deleted_files | schema_id | min_partition_stats | max_partition_stats |
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
| manifest-f4dcab43-ef6b-4713... | 12365| 40 | 0 | 0 | {20230315, 00} | {20230315, 20} |
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
1 rows in set
*/

- You can also query the manifest with specified timestamp in unix milliseconds
SELECT * FROM my_table$manifests /*+ OPTIONS('scan.timestamp-millis'='1678883047356') */;
/*
+--------------------------------+-------------+------------------+-------------------+---------------+
| file_name | file_size | num_added_files | num_deleted_files | schema_id |
+--------------------------------+-------------+------------------+-------------------+---------------+
| manifest-f4dcab43-ef6b-4713... | 12365| 40 | 0 | 0 |
+--------------------------------+-------------+------------------+-------------------+---------------+
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
| file_name | file_size | num_added_files | num_deleted_files | schema_id | min_partition_stats | max_partition_stats |
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
| manifest-f4dcab43-ef6b-4713... | 12365| 40 | 0 | 0 | {20230315, 00} | {20230315, 20} |
+--------------------------------+-------------+------------------+-------------------+---------------+---------------------+---------------------+
1 rows in set
*/
```
Expand Down
32 changes: 27 additions & 5 deletions paimon-core/src/main/java/org/apache/paimon/table/system/ManifestsTable.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,8 @@

import org.apache.paimon.CoreOptions;
import org.apache.paimon.Snapshot;
import org.apache.paimon.casting.CastExecutor;
import org.apache.paimon.casting.CastExecutors;
import org.apache.paimon.data.BinaryString;
import org.apache.paimon.data.GenericRow;
import org.apache.paimon.data.InternalRow;
Expand Down Expand Up @@ -64,7 +66,7 @@ public class ManifestsTable implements ReadonlyTable {

private static final Logger LOG = LoggerFactory.getLogger(ManifestsTable.class);

private static final long serialVersionUID = 1L;
private static final long serialVersionUID = 2L;

public static final String MANIFESTS = "manifests";

Expand All @@ -75,7 +77,15 @@ public class ManifestsTable implements ReadonlyTable {
new DataField(1, "file_size", new BigIntType(false)),
new DataField(2, "num_added_files", new BigIntType(false)),
new DataField(3, "num_deleted_files", new BigIntType(false)),
new DataField(4, "schema_id", new BigIntType(false))));
new DataField(4, "schema_id", new BigIntType(false)),
new DataField(
5,
"min_partition_stats",
SerializationUtils.newStringType(true)),
new DataField(
6,
"max_partition_stats",
SerializationUtils.newStringType(true))));

private final FileStoreTable dataTable;

Expand Down Expand Up @@ -176,8 +186,16 @@ public RecordReader<InternalRow> createReader(Split split) {
}
List<ManifestFileMeta> manifestFileMetas = allManifests(dataTable);

@SuppressWarnings("unchecked")
CastExecutor<InternalRow, BinaryString> partitionCastExecutor =
(CastExecutor<InternalRow, BinaryString>)
CastExecutors.resolveToString(
dataTable.schema().logicalPartitionType());

Iterator<InternalRow> rows =
Iterators.transform(manifestFileMetas.iterator(), this::toRow);
Iterators.transform(
manifestFileMetas.iterator(),
meta -> toRow(meta, partitionCastExecutor));
if (readType != null) {
rows =
Iterators.transform(
Expand All @@ -189,13 +207,17 @@ public RecordReader<InternalRow> createReader(Split split) {
return new IteratorRecordReader<>(rows);
}

private InternalRow toRow(ManifestFileMeta manifestFileMeta) {
private InternalRow toRow(
ManifestFileMeta manifestFileMeta,
CastExecutor<InternalRow, BinaryString> partitionCastExecutor) {
return GenericRow.of(
BinaryString.fromString(manifestFileMeta.fileName()),
manifestFileMeta.fileSize(),
manifestFileMeta.numAddedFiles(),
manifestFileMeta.numDeletedFiles(),
manifestFileMeta.schemaId());
manifestFileMeta.schemaId(),
partitionCastExecutor.cast(manifestFileMeta.partitionStats().minValues()),
partitionCastExecutor.cast(manifestFileMeta.partitionStats().maxValues()));
}
}

Expand Down
16 changes: 15 additions & 1 deletion paimon-core/src/test/java/org/apache/paimon/table/system/ManifestsTableTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,7 +177,21 @@ private List<InternalRow> getExpectedResult(long snapshotId) {
manifestFileMeta.fileSize(),
manifestFileMeta.numAddedFiles(),
manifestFileMeta.numDeletedFiles(),
manifestFileMeta.schemaId()));
manifestFileMeta.schemaId(),
BinaryString.fromString(
String.format(
"{%d}",
manifestFileMeta
.partitionStats()
.minValues()
.getInt(0))),
BinaryString.fromString(
String.format(
"{%d}",
manifestFileMeta
.partitionStats()
.maxValues()
.getInt(0)))));
}
return expectedRow;
}
Expand Down
Loading