Iceberg: Use table schema corresponding to snapshot in snapshot queries #12786
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -316,18 +316,31 @@ public IcebergTableHandle getTableHandle( | |
| throw new TrinoException(GENERIC_USER_ERROR, "Cannot specify end version both in table name and FOR clause"); | ||
| } | ||
|
|
||
| Optional<Long> tableSnapshotId; | ||
| Schema tableSchema; | ||
| Optional<PartitionSpec> partitionSpec; | ||
| if (endVersion.isPresent() || name.getSnapshotId().isPresent()) { | ||
| long snapshotId = endVersion.map(connectorTableVersion -> getSnapshotIdFromVersion(table, connectorTableVersion)) | ||
| .orElseGet(() -> resolveSnapshotId(table, name.getSnapshotId().get(), isAllowLegacySnapshotSyntax(session))); | ||
| tableSnapshotId = Optional.of(snapshotId); | ||
| tableSchema = table.schemas().get(table.snapshot(snapshotId).schemaId()); | ||
| partitionSpec = Optional.empty(); | ||
| } | ||
| else { | ||
| tableSnapshotId = Optional.ofNullable(table.currentSnapshot()).map(Snapshot::snapshotId); | ||
| tableSchema = table.schema(); | ||
| partitionSpec = Optional.of(table.spec()); | ||
| } | ||
|
|
||
| Map<String, String> tableProperties = table.properties(); | ||
| String nameMappingJson = tableProperties.get(TableProperties.DEFAULT_NAME_MAPPING); | ||
| return new IcebergTableHandle( | ||
| tableName.getSchemaName(), | ||
| name.getTableName(), | ||
| name.getTableType(), | ||
| tableSnapshotId, | ||
| SchemaParser.toJson(tableSchema), | ||
| partitionSpec.map(PartitionSpecParser::toJson), | ||
| table.operations().current().formatVersion(), | ||
| TupleDomain.all(), | ||
| TupleDomain.all(), | ||
|
|
@@ -508,7 +521,10 @@ public ConnectorTableProperties getTableProperties(ConnectorSession session, Con | |
| @Override | ||
| public ConnectorTableMetadata getTableMetadata(ConnectorSession session, ConnectorTableHandle table) | ||
| { | ||
| IcebergTableHandle tableHandle = (IcebergTableHandle) table; | ||
| Table icebergTable = catalog.loadTable(session, tableHandle.getSchemaTableName()); | ||
| List<ColumnMetadata> columns = getColumnMetadatas(SchemaParser.fromJson(tableHandle.getTableSchemaJson())); | ||
| return new ConnectorTableMetadata(tableHandle.getSchemaTableName(), columns, getIcebergTableProperties(icebergTable), getTableComment(icebergTable)); | ||
| } | ||
|
|
||
| @Override | ||
|
|
@@ -566,7 +582,10 @@ public Iterator<TableColumnsMetadata> streamTableColumns(ConnectorSession sessio | |
| if (redirectTable(session, tableName).isPresent()) { | ||
| return Stream.of(TableColumnsMetadata.forRedirectedTable(tableName)); | ||
| } | ||
|
|
||
| Table icebergTable = catalog.loadTable(session, tableName); | ||
| List<ColumnMetadata> columns = getColumnMetadatas(icebergTable.schema()); | ||
| return Stream.of(TableColumnsMetadata.forTable(tableName, columns)); | ||
| } | ||
| catch (TableNotFoundException e) { | ||
| // Table disappeared during listing operation | ||
|
|
@@ -1282,13 +1301,12 @@ private void scanAndDeleteInvalidFiles(Table table, ConnectorSession session, Sc | |
| public Optional<Object> getInfo(ConnectorTableHandle tableHandle) | ||
| { | ||
| IcebergTableHandle icebergTableHandle = (IcebergTableHandle) tableHandle; | ||
| Optional<Boolean> partitioned = icebergTableHandle.getPartitionSpecJson() | ||
| .map(partitionSpecJson -> PartitionSpecParser.fromJson(SchemaParser.fromJson(icebergTableHandle.getTableSchemaJson()), partitionSpecJson).isPartitioned()); | ||
|
|
||
| return Optional.of(new IcebergInputInfo( | ||
| icebergTableHandle.getSnapshotId(), | ||
| partitioned, | ||
| getFileFormat(icebergTableHandle.getStorageProperties()).name())); | ||
| } | ||
|
|
||
|
|
@@ -1409,24 +1427,11 @@ public void renameColumn(ConnectorSession session, ConnectorTableHandle tableHan | |
| icebergTable.updateSchema().renameColumn(columnHandle.getName(), target).commit(); | ||
| } | ||
|
|
||
| private List<ColumnMetadata> getColumnMetadatas(Schema schema) | ||
| { | ||
| ImmutableList.Builder<ColumnMetadata> columns = ImmutableList.builder(); | ||
|
|
||
| List<ColumnMetadata> schemaColumns = schema.columns().stream() | ||
| .map(column -> | ||
| ColumnMetadata.builder() | ||
| .setName(column.name()) | ||
|
|
@@ -1435,6 +1440,10 @@ private List<ColumnMetadata> getColumnMetadatas(Table table) | |
| .setComment(Optional.ofNullable(column.doc())) | ||
| .build()) | ||
| .collect(toImmutableList()); | ||
| columns.addAll(schemaColumns); | ||
| columns.add(pathColumnMetadata()); | ||
| columns.add(fileModifiedTimeColumnMetadata()); | ||
| return columns.build(); | ||
| } | ||
|
|
||
| @Override | ||
|
|
@@ -1958,13 +1967,17 @@ private Optional<Long> getSnapshotId(Table table, Optional<Long> snapshotId, boo | |
| { | ||
| // table.name() is an encoded version of SchemaTableName | ||
| return snapshotId | ||
| .map(id -> resolveSnapshotId(table, id, allowLegacySnapshotSyntax)) | ||
| .or(() -> Optional.ofNullable(table.currentSnapshot()).map(Snapshot::snapshotId)); | ||
| } | ||
|
|
||
| private long resolveSnapshotId(Table table, long id, boolean allowLegacySnapshotSyntax) | ||
| { | ||
| return snapshotIds.computeIfAbsent( | ||
| table.name() + "@" + id, | ||
| ignored -> IcebergUtil.resolveSnapshotId(table, id, allowLegacySnapshotSyntax)); | ||
|
Member
There was a problem hiding this comment.
(pre-existing, but still sth to fix)
Contributor
Author
There was a problem hiding this comment. In case that I don't see the purpose behind this request.
Member
There was a problem hiding this comment.
only if |
||
| } | ||
|
|
||
| Table getIcebergTable(ConnectorSession session, SchemaTableName schemaTableName) | ||
| { | ||
| return catalog.loadTable(session, schemaTableName); | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nit, personally I think it make sense to add the path column to the list here. The other method is responsible for columns that come from the Iceberg schema.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I did this refactor with the intention of not having code duplication in the methods where the column metadatas are built.
Should I try a better naming for the method?