Skip to content
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

Jump to bottom

Add a new HudiHFileBootstrapIndex with HBase 2.4.9 #11

Open
wants to merge 28 commits into
base: hudi-plugin-cleanup
Choose a base branch
from
Open

Add a new HudiHFileBootstrapIndex with HBase 2.4.9 #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
28 commits
Select commit Hold shift + click to select a range
122a9e1
Add Hudi plugin
codope Sep 27, 2021
39f855b
Add concrete implementation of connector metadata and split
codope Dec 9, 2021
4871157
Add Hudi plugin to trino-server-dev
codope Dec 10, 2021
c609b2e
Add table and column metadata
codope Dec 13, 2021
26a901e
Fix show tables
codope Dec 14, 2021
4964b6e
Handle partition and add support for metadata listing
codope Dec 16, 2021
955a6f5
Add tests for the connector
codope Dec 17, 2021
08a4737
Fix partition column and apply filter
codope Dec 20, 2021
0d2017f
Add splits to split source
yihua Dec 16, 2021
4602d02
Fix configuration for list status
yihua Dec 17, 2021
47ecc78
Fix logic using HoodieParquetInputFormat to get splits and support bo…
yihua Dec 17, 2021
8097d61
Add flag to control how to fetch splits
yihua Dec 20, 2021
025e269
Refactor file listing and Hudi split
yihua Dec 21, 2021
bad991c
Remove unused variables
yihua Dec 21, 2021
068f4a6
Fix partition keys
yihua Dec 21, 2021
7fc6d47
Use empty partition keys for now
yihua Dec 21, 2021
fd6e4dc
Consider bootstrap base file when getting the file status
yihua Dec 21, 2021
7d5e8d5
Fix partition keys
yihua Dec 21, 2021
ae1f0ea
Add argument for dynamic filter
yihua Dec 22, 2021
1f478e0
Add batch processing in split source
yihua Dec 23, 2021
af87fa9
Add logs for partition info from metastore
yihua Dec 23, 2021
c55ff21
Add a hack to construct partition keys without using hive metastore
yihua Dec 23, 2021
f246f0a
Refactoring and more tests
codope Dec 27, 2021
93d267a
Remove debug logs
codope Dec 27, 2021
6276915
Fix dependency issue after rebase on master
codope Dec 28, 2021
97937a9
Fix describe table query
codope Dec 29, 2021
22a5cb2
Add partition filtering in split source (#9)
yihua Dec 29, 2021
db6f09a
Use HBase 2.4.9
yihua Jan 3, 2022
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
6 changes: 6 additions & 0 deletions core/trino-server/src/main/provisio/presto.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,12 @@
</artifact>
</artifactSet>

<artifactSet to="plugin/hudi">
<artifact id="${project.groupId}:trino-hudi:zip:${project.version}">
<unpack />
</artifact>
</artifactSet>

<artifactSet to="plugin/iceberg">
<artifact id="${project.groupId}:trino-iceberg:zip:${project.version}">
<unpack />
Expand Down
27 changes: 1 addition & 26 deletions plugin/trino-hive/src/main/java/io/trino/plugin/hive/BackgroundHiveSplitLoader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,6 @@
import io.trino.plugin.hive.HiveSplit.BucketConversion;
import io.trino.plugin.hive.HiveSplit.BucketValidation;
import io.trino.plugin.hive.acid.AcidTransaction;
import io.trino.plugin.hive.metastore.Column;
import io.trino.plugin.hive.metastore.Partition;
import io.trino.plugin.hive.metastore.Table;
import io.trino.plugin.hive.util.HiveBucketing.BucketingVersion;
Expand Down Expand Up @@ -100,8 +99,6 @@
import static io.trino.plugin.hive.HiveErrorCode.HIVE_BAD_DATA;
import static io.trino.plugin.hive.HiveErrorCode.HIVE_FILESYSTEM_ERROR;
import static io.trino.plugin.hive.HiveErrorCode.HIVE_INVALID_BUCKET_FILES;
import static io.trino.plugin.hive.HiveErrorCode.HIVE_INVALID_METADATA;
import static io.trino.plugin.hive.HiveErrorCode.HIVE_INVALID_PARTITION_VALUE;
import static io.trino.plugin.hive.HiveErrorCode.HIVE_UNKNOWN_ERROR;
import static io.trino.plugin.hive.HivePartitionManager.partitionMatches;
import static io.trino.plugin.hive.HiveSessionProperties.getMaxInitialSplitSize;
Expand All @@ -114,11 +111,11 @@
import static io.trino.plugin.hive.util.HiveFileIterator.NestedDirectoryPolicy.FAIL;
import static io.trino.plugin.hive.util.HiveFileIterator.NestedDirectoryPolicy.IGNORED;
import static io.trino.plugin.hive.util.HiveFileIterator.NestedDirectoryPolicy.RECURSE;
import static io.trino.plugin.hive.util.HiveUtil.checkCondition;
import static io.trino.plugin.hive.util.HiveUtil.getFooterCount;
import static io.trino.plugin.hive.util.HiveUtil.getHeaderCount;
import static io.trino.plugin.hive.util.HiveUtil.getInputFormat;
import static io.trino.plugin.hive.util.HiveUtil.getPartitionKeyColumnHandles;
import static io.trino.plugin.hive.util.HiveUtil.getPartitionKeys;
import static io.trino.spi.StandardErrorCode.NOT_SUPPORTED;
import static java.lang.Integer.parseInt;
import static java.lang.Math.max;
Expand Down Expand Up @@ -942,28 +939,6 @@ private static List<Path> getTargetPathsFromSymlink(FileSystem fileSystem, Path
}
}

private static List<HivePartitionKey> getPartitionKeys(Table table, Optional<Partition> partition)
{
if (partition.isEmpty()) {
return ImmutableList.of();
}
ImmutableList.Builder<HivePartitionKey> partitionKeys = ImmutableList.builder();
List<Column> keys = table.getPartitionColumns();
List<String> values = partition.get().getValues();
checkCondition(keys.size() == values.size(), HIVE_INVALID_METADATA, "Expected %s partition key values, but got %s", keys.size(), values.size());
for (int i = 0; i < keys.size(); i++) {
String name = keys.get(i).getName();
HiveType hiveType = keys.get(i).getType();
if (!hiveType.isSupportedType(table.getStorage().getStorageFormat())) {
throw new TrinoException(NOT_SUPPORTED, format("Unsupported Hive type %s found in partition keys of table %s.%s", hiveType, table.getDatabaseName(), table.getTableName()));
}
String value = values.get(i);
checkCondition(value != null, HIVE_INVALID_PARTITION_VALUE, "partition key value cannot be null for field: %s", name);
partitionKeys.add(new HivePartitionKey(name, value));
}
return partitionKeys.build();
}

private static Properties getPartitionSchema(Table table, Optional<Partition> partition)
{
if (partition.isEmpty()) {
Expand Down
10 changes: 5 additions & 5 deletions plugin/trino-hive/src/main/java/io/trino/plugin/hive/parquet/ParquetPageSourceFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -290,9 +290,9 @@ && predicateMatches(parquetPredicate, block, dataSource, descriptorsByPath, parq

Optional<ReaderColumns> readerProjections = projectBaseColumns(columns);
List<HiveColumnHandle> baseColumns = readerProjections.map(projection ->
projection.get().stream()
.map(HiveColumnHandle.class::cast)
.collect(toUnmodifiableList()))
projection.get().stream()
.map(HiveColumnHandle.class::cast)
.collect(toUnmodifiableList()))
.orElse(columns);

for (HiveColumnHandle column : baseColumns) {
Expand Down Expand Up @@ -365,7 +365,7 @@ public static Optional<org.apache.parquet.schema.Type> getColumnType(HiveColumnH
return Optional.of(new GroupType(baseType.getRepetition(), baseType.getName(), ImmutableList.of(type)));
}

private static Optional<ColumnIndexStore> getColumnIndexStore(
public static Optional<ColumnIndexStore> getColumnIndexStore(
ParquetDataSource dataSource,
BlockMetaData blockMetadata,
Map<List<String>, RichColumnDescriptor> descriptorsByPath,
Expand Down Expand Up @@ -440,7 +440,7 @@ public static TupleDomain<ColumnDescriptor> getParquetTupleDomain(
return TupleDomain.withColumnDomains(predicate.build());
}

private static org.apache.parquet.schema.Type getParquetType(HiveColumnHandle column, MessageType messageType, boolean useParquetColumnNames)
public static org.apache.parquet.schema.Type getParquetType(HiveColumnHandle column, MessageType messageType, boolean useParquetColumnNames)
{
if (useParquetColumnNames) {
return getParquetTypeByName(column.getBaseColumnName(), messageType);
Expand Down
23 changes: 23 additions & 0 deletions plugin/trino-hive/src/main/java/io/trino/plugin/hive/util/HiveUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@
import io.trino.plugin.hive.HiveType;
import io.trino.plugin.hive.avro.TrinoAvroSerDe;
import io.trino.plugin.hive.metastore.Column;
import io.trino.plugin.hive.metastore.Partition;
import io.trino.plugin.hive.metastore.SortingColumn;
import io.trino.plugin.hive.metastore.Table;
import io.trino.spi.ErrorCodeSupplier;
Expand Down Expand Up @@ -1143,4 +1144,26 @@ public static boolean isIcebergTable(Table table)
{
return ICEBERG_TABLE_TYPE_VALUE.equalsIgnoreCase(table.getParameters().get(ICEBERG_TABLE_TYPE_NAME));
}

public static List<HivePartitionKey> getPartitionKeys(Table table, Optional<Partition> partition)
{
if (partition.isEmpty()) {
return ImmutableList.of();
}
ImmutableList.Builder<HivePartitionKey> partitionKeys = ImmutableList.builder();
List<Column> keys = table.getPartitionColumns();
List<String> values = partition.get().getValues();
checkCondition(keys.size() == values.size(), HIVE_INVALID_METADATA, "Expected %s partition key values, but got %s", keys.size(), values.size());
for (int i = 0; i < keys.size(); i++) {
String name = keys.get(i).getName();
HiveType hiveType = keys.get(i).getType();
if (!hiveType.isSupportedType(table.getStorage().getStorageFormat())) {
throw new TrinoException(NOT_SUPPORTED, format("Unsupported Hive type %s found in partition keys of table %s.%s", hiveType, table.getDatabaseName(), table.getTableName()));
}
String value = values.get(i);
checkCondition(value != null, HIVE_INVALID_PARTITION_VALUE, "partition key value cannot be null for field: %s", name);
partitionKeys.add(new HivePartitionKey(name, value));
}
return partitionKeys.build();
}
}
Loading