Skip to content

[core] Add file_name and clustering_columns fields to files system table #7667

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

Open
heye1005 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[core] Add file_name and clustering_columns fields to files system table #7667

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
34 changes: 17 additions & 17 deletions docs/content/concepts/system-tables.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -250,30 +250,30 @@ You can query the files of the table with specific snapshot.
SELECT * FROM my_table$files;

/*
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+
| partition | bucket | file_path | file_format | schema_id | level | record_count | file_size_in_bytes | min_key | max_key | null_value_counts | min_value_stats | max_value_stats | min_sequence_number | max_sequence_number | creation_time |
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+
| {3} | 0 | data-8f64af95-29cc-4342-adc... | orc | 0 | 0 | 1 | 593 | [c] | [c] | {cnt=0, val=0, word=0} | {cnt=3, val=33, word=c} | {cnt=3, val=33, word=c} | 1691551246234 | 1691551246637 |2023-02-24T16:06:21.166|
| {2} | 0 | data-8b369068-0d37-4011-aa5... | orc | 0 | 0 | 1 | 593 | [b] | [b] | {cnt=0, val=0, word=0} | {cnt=2, val=22, word=b} | {cnt=2, val=22, word=b} | 1691551246233 | 1691551246732 |2023-02-24T16:06:21.166|
| {2} | 0 | data-83aa7973-060b-40b6-8c8... | orc | 0 | 0 | 1 | 605 | [d] | [d] | {cnt=0, val=0, word=0} | {cnt=2, val=32, word=d} | {cnt=2, val=32, word=d} | 1691551246267 | 1691551246798 |2023-02-24T16:06:21.166|
| {5} | 0 | data-3d304f4a-bcea-44dc-a13... | orc | 0 | 0 | 1 | 593 | [c] | [c] | {cnt=0, val=0, word=0} | {cnt=5, val=51, word=c} | {cnt=5, val=51, word=c} | 1691551246788 | 1691551246152 |2023-02-24T16:06:21.166|
| {1} | 0 | data-10abb5bc-0170-43ae-b6a... | orc | 0 | 0 | 1 | 595 | [a] | [a] | {cnt=0, val=0, word=0} | {cnt=1, val=11, word=a} | {cnt=1, val=11, word=a} | 1691551246722 | 1691551246273 |2023-02-24T16:06:21.166|
| {4} | 0 | data-2c9b7095-65b7-4013-a7a... | orc | 0 | 0 | 1 | 593 | [a] | [a] | {cnt=0, val=0, word=0} | {cnt=4, val=12, word=a} | {cnt=4, val=12, word=a} | 1691551246321 | 1691551246109 |2023-02-24T16:06:21.166|
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+--------------------------------+--------------------+
| partition | bucket | file_path | file_format | schema_id | level | record_count | file_size_in_bytes | min_key | max_key | null_value_counts | min_value_stats | max_value_stats | min_sequence_number | max_sequence_number | creation_time | file_name | clustering_columns |
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+--------------------------------+--------------------+
| {3} | 0 | data-8f64af95-29cc-4342-adc... | orc | 0 | 0 | 1 | 593 | [c] | [c] | {cnt=0, val=0, word=0} | {cnt=3, val=33, word=c} | {cnt=3, val=33, word=c} | 1691551246234 | 1691551246637 |2023-02-24T16:06:21.166| data-8f64af95-29cc-4342-adc... | NULL |
| {2} | 0 | data-8b369068-0d37-4011-aa5... | orc | 0 | 0 | 1 | 593 | [b] | [b] | {cnt=0, val=0, word=0} | {cnt=2, val=22, word=b} | {cnt=2, val=22, word=b} | 1691551246233 | 1691551246732 |2023-02-24T16:06:21.166| data-8b369068-0d37-4011-aa5... | NULL |
| {2} | 0 | data-83aa7973-060b-40b6-8c8... | orc | 0 | 0 | 1 | 605 | [d] | [d] | {cnt=0, val=0, word=0} | {cnt=2, val=32, word=d} | {cnt=2, val=32, word=d} | 1691551246267 | 1691551246798 |2023-02-24T16:06:21.166| data-83aa7973-060b-40b6-8c8... | NULL |
| {5} | 0 | data-3d304f4a-bcea-44dc-a13... | orc | 0 | 0 | 1 | 593 | [c] | [c] | {cnt=0, val=0, word=0} | {cnt=5, val=51, word=c} | {cnt=5, val=51, word=c} | 1691551246788 | 1691551246152 |2023-02-24T16:06:21.166| data-3d304f4a-bcea-44dc-a13... | NULL |
| {1} | 0 | data-10abb5bc-0170-43ae-b6a... | orc | 0 | 0 | 1 | 595 | [a] | [a] | {cnt=0, val=0, word=0} | {cnt=1, val=11, word=a} | {cnt=1, val=11, word=a} | 1691551246722 | 1691551246273 |2023-02-24T16:06:21.166| data-10abb5bc-0170-43ae-b6a... | NULL |
| {4} | 0 | data-2c9b7095-65b7-4013-a7a... | orc | 0 | 0 | 1 | 593 | [a] | [a] | {cnt=0, val=0, word=0} | {cnt=4, val=12, word=a} | {cnt=4, val=12, word=a} | 1691551246321 | 1691551246109 |2023-02-24T16:06:21.166| data-2c9b7095-65b7-4013-a7a... | NULL |
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+--------------------------------+--------------------+
6 rows in set
*/

-- You can also query the files with specific snapshot
SELECT * FROM my_table$files /*+ OPTIONS('scan.snapshot-id'='1') */;

/*
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+
| partition | bucket | file_path | file_format | schema_id | level | record_count | file_size_in_bytes | min_key | max_key | null_value_counts | min_value_stats | max_value_stats | min_sequence_number | max_sequence_number | creation_time |
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+
| {3} | 0 | data-8f64af95-29cc-4342-adc... | orc | 0 | 0 | 1 | 593 | [c] | [c] | {cnt=0, val=0, word=0} | {cnt=3, val=33, word=c} | {cnt=3, val=33, word=c} | 1691551246234 | 1691551246637 |2023-02-24T16:06:21.166|
| {2} | 0 | data-8b369068-0d37-4011-aa5... | orc | 0 | 0 | 1 | 593 | [b] | [b] | {cnt=0, val=0, word=0} | {cnt=2, val=22, word=b} | {cnt=2, val=22, word=b} | 1691551246233 | 1691551246732 |2023-02-24T16:06:21.166|
| {1} | 0 | data-10abb5bc-0170-43ae-b6a... | orc | 0 | 0 | 1 | 595 | [a] | [a] | {cnt=0, val=0, word=0} | {cnt=1, val=11, word=a} | {cnt=1, val=11, word=a} | 1691551246267 | 1691551246798 |2023-02-24T16:06:21.166|
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+--------------------------------+--------------------+
| partition | bucket | file_path | file_format | schema_id | level | record_count | file_size_in_bytes | min_key | max_key | null_value_counts | min_value_stats | max_value_stats | min_sequence_number | max_sequence_number | creation_time | file_name | clustering_columns |
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+--------------------------------+--------------------+
| {3} | 0 | data-8f64af95-29cc-4342-adc... | orc | 0 | 0 | 1 | 593 | [c] | [c] | {cnt=0, val=0, word=0} | {cnt=3, val=33, word=c} | {cnt=3, val=33, word=c} | 1691551246234 | 1691551246637 |2023-02-24T16:06:21.166| data-8f64af95-29cc-4342-adc... | NULL |
| {2} | 0 | data-8b369068-0d37-4011-aa5... | orc | 0 | 0 | 1 | 593 | [b] | [b] | {cnt=0, val=0, word=0} | {cnt=2, val=22, word=b} | {cnt=2, val=22, word=b} | 1691551246233 | 1691551246732 |2023-02-24T16:06:21.166| data-8b369068-0d37-4011-aa5... | NULL |
| {1} | 0 | data-10abb5bc-0170-43ae-b6a... | orc | 0 | 0 | 1 | 595 | [a] | [a] | {cnt=0, val=0, word=0} | {cnt=1, val=11, word=a} | {cnt=1, val=11, word=a} | 1691551246267 | 1691551246798 |2023-02-24T16:06:21.166| data-10abb5bc-0170-43ae-b6a... | NULL |
+-----------+--------+--------------------------------+-------------+-----------+-------+--------------+--------------------+---------+---------+------------------------+-------------------------+-------------------------+---------------------+---------------------+-----------------------+--------------------------------+--------------------+
3 rows in set
*/
```
Expand Down
35 changes: 34 additions & 1 deletion paimon-core/src/main/java/org/apache/paimon/table/system/FilesTable.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@

package org.apache.paimon.table.system;

import org.apache.paimon.CoreOptions;
import org.apache.paimon.casting.CastExecutor;
import org.apache.paimon.casting.CastExecutors;
import org.apache.paimon.data.BinaryRow;
Expand Down Expand Up @@ -120,7 +121,12 @@ public class FilesTable implements ReadonlyTable {
new DataField(16, "deleteRowCount", DataTypes.BIGINT()),
new DataField(17, "file_source", DataTypes.STRING()),
new DataField(18, "first_row_id", DataTypes.BIGINT()),
new DataField(19, "write_cols", DataTypes.ARRAY(DataTypes.STRING()))));
new DataField(19, "write_cols", DataTypes.ARRAY(DataTypes.STRING())),
new DataField(20, "file_name", SerializationUtils.newStringType(false)),
new DataField(
21,
"clustering_columns",
SerializationUtils.newStringType(true))));

private final FileStoreTable storeTable;

Expand Down Expand Up @@ -353,6 +359,24 @@ public RowDataToObjectArrayConverter apply(Long schemaId) {
});
}
};

Function<Long, List<String>> clusteringColumnsGetter =
new Function<Long, List<String>>() {
final Map<Long, List<String>> cache = new HashMap<>();

@Override
public List<String> apply(Long schemaId) {
if (cache.containsKey(schemaId)) {
return cache.get(schemaId);
}
TableSchema dataSchema = schemaManager.schema(schemaId);
CoreOptions options = new CoreOptions(dataSchema.options());
List<String> cols = options.clusteringColumns();
cache.put(schemaId, cols);
return cols;
}
};

for (Split dataSplit : splits) {
iteratorList.add(
Iterators.transform(
Expand All @@ -362,6 +386,7 @@ public RowDataToObjectArrayConverter apply(Long schemaId) {
(DataSplit) dataSplit,
partitionCastExecutor,
keyConverters,
clusteringColumnsGetter,
file,
simpleStatsEvolutions)));
}
Expand All @@ -381,6 +406,7 @@ private LazyGenericRow toRow(
DataSplit dataSplit,
CastExecutor<InternalRow, BinaryString> partitionCastExecutor,
Function<Long, RowDataToObjectArrayConverter> keyConverters,
Function<Long, List<String>> clusteringColumnsGetter,
DataFileMeta file,
SimpleStatsEvolutions simpleStatsEvolutions) {
StatsLazyGetter statsGetter = new StatsLazyGetter(file, simpleStatsEvolutions);
Expand Down Expand Up @@ -441,6 +467,13 @@ private LazyGenericRow toRow(
return new GenericArray(
writeCols.stream().map(BinaryString::fromString).toArray());
},
() -> BinaryString.fromString(file.fileName()),
() -> {
List<String> cols = clusteringColumnsGetter.apply(file.schemaId());
return cols.isEmpty()
? null
: BinaryString.fromString(String.join(",", cols));
},
};

return new LazyGenericRow(fields);
Expand Down
52 changes: 52 additions & 0 deletions paimon-core/src/test/java/org/apache/paimon/table/system/FilesTableTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,6 +223,56 @@ public void testReadFilesFromNotExistSnapshot() {
.satisfies(anyCauseMatches(IllegalArgumentException.class));
}

@Test
public void testFileNameAndClusteringColumns() throws Exception {
String clusterTableName = "ClusterTable";
FileIO fileIO = LocalFileIO.create();
Path clusterTablePath =
new Path(String.format("%s/%s.db/%s", warehouse, database, clusterTableName));
Schema clusterSchema =
Schema.newBuilder()
.column("pk", DataTypes.INT())
.column("pt", DataTypes.INT())
.column("col1", DataTypes.INT())
.column("col2", DataTypes.STRING())
.partitionKeys("pt")
.primaryKey("pk", "pt")
.option(CoreOptions.BUCKET.key(), "1")
.option(CoreOptions.SEQUENCE_FIELD.key(), "col1")
.option("clustering.columns", "col1,col2")
.build();
TableSchema clusterTableSchema =
SchemaUtils.forceCommit(new SchemaManager(fileIO, clusterTablePath), clusterSchema);
FileStoreTable clusterTable =
FileStoreTableFactory.create(
LocalFileIO.create(), clusterTablePath, clusterTableSchema);
write(clusterTable, GenericRow.of(1, 1, 100, BinaryString.fromString("abc")));

Identifier clusterFilesId =
identifier(clusterTableName + SYSTEM_TABLE_SPLITTER + FilesTable.FILES);
FilesTable clusterFilesTable = (FilesTable) catalog.getTable(clusterFilesId);
List<InternalRow> result = read(clusterFilesTable);

assertThat(result).hasSize(1);
InternalRow row = result.get(0);
String filePath = row.getString(2).toString();
String expectedFileName = filePath.substring(filePath.lastIndexOf("/") + 1);
String fileName = row.getString(20).toString();
assertThat(fileName).isEqualTo(expectedFileName);
String clusteringCols = row.getString(21).toString();
assertThat(clusteringCols).isEqualTo("col1,col2");
}

@Test
public void testClusteringColumnsNull() throws Exception {
List<InternalRow> result = read(filesTable);
assertThat(result).isNotEmpty();
for (InternalRow row : result) {
assertThat(row.getString(20).toString()).isNotEmpty();
assertThat(row.isNullAt(21)).isTrue();
}
}

private List<InternalRow> getExpectedResult(long snapshotId) {
if (!snapshotManager.snapshotExists(snapshotId)) {
return Collections.emptyList();
Expand Down Expand Up @@ -279,6 +329,8 @@ private List<InternalRow> getExpectedResult(long snapshotId) {
BinaryString.fromString(
file.fileSource().map(Object::toString).orElse(null)),
file.firstRowId(),
null,
BinaryString.fromString(file.fileName()),
null));
}
return expectedRow;
Expand Down
Loading