Created
February 25, 2024 17:05
-
-
Save takezoe/24a0c62335923d4ed378026e7509b697 to your computer and use it in GitHub Desktop.
Trino UDF for generating row-level checksum
This file contains 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
package io.trino.operator.scalar; | |
import com.google.common.collect.ImmutableList; | |
import io.airlift.slice.Slice; | |
import io.airlift.slice.Slices; | |
import io.trino.annotation.UsedByGeneratedCode; | |
import io.trino.metadata.SqlScalarFunction; | |
import io.trino.spi.block.Block; | |
import io.trino.spi.block.SqlRow; | |
import io.trino.spi.function.BoundSignature; | |
import io.trino.spi.function.FunctionMetadata; | |
import io.trino.spi.function.Signature; | |
import io.trino.spi.function.TypeVariableConstraint; | |
import io.trino.spi.type.Type; | |
import io.trino.spi.type.TypeOperators; | |
import io.trino.spi.type.TypeSignature; | |
import io.trino.spi.type.TypeSignatureParameter; | |
import io.trino.type.BlockTypeOperators; | |
import java.lang.invoke.MethodHandle; | |
import java.util.ArrayList; | |
import java.util.List; | |
import static io.trino.spi.function.InvocationConvention.InvocationArgumentConvention.NEVER_NULL; | |
import static io.trino.spi.function.InvocationConvention.InvocationReturnConvention.FAIL_ON_NULL; | |
import static io.trino.spi.type.VarbinaryType.VARBINARY; | |
import static io.trino.util.Reflection.methodHandle; | |
public class RowChecksumFunction extends SqlScalarFunction { | |
private static final long PRIME64 = 0x9E3779B185EBCA87L; | |
private final BlockTypeOperators blockTypeOperators; | |
private static final MethodHandle METHOD_HANDLE = methodHandle(RowChecksumFunction.class, "rowToString", List.class, SqlRow.class); | |
public RowChecksumFunction(TypeOperators typeOperators) { | |
super(FunctionMetadata.scalarBuilder("row_checksum") | |
.signature(Signature.builder() | |
.typeVariableConstraint( | |
TypeVariableConstraint.builder("T") | |
.variadicBound("row") | |
.build()) | |
.returnType(VARBINARY) | |
.argumentType(new TypeSignature("T")) | |
.build()) | |
.description("Generate row-level checksum") | |
.build()); | |
this.blockTypeOperators = new BlockTypeOperators(typeOperators); | |
} | |
@Override | |
protected SpecializedSqlScalarFunction specialize(BoundSignature boundSignature) | |
{ | |
Type type = boundSignature.getArgumentType(0); | |
List<Type> fieldTypes = type.getTypeParameters(); | |
List<BlockTypeOperators.BlockPositionXxHash64> fieldHashOperators = new ArrayList<>(fieldTypes.size()); | |
List<TypeSignatureParameter> typeSignatureParameters = type.getTypeSignature().getParameters(); | |
for (int i = 0; i < fieldTypes.size(); i++) { | |
fieldHashOperators.add(blockTypeOperators.getXxHash64Operator(type)); | |
} | |
MethodHandle methodHandle = METHOD_HANDLE.bindTo(fieldHashOperators); | |
return new ChoicesSpecializedSqlScalarFunction( | |
boundSignature, | |
FAIL_ON_NULL, | |
ImmutableList.of(NEVER_NULL), | |
methodHandle); | |
} | |
@UsedByGeneratedCode | |
public static Slice rowToString(List<BlockTypeOperators.BlockPositionXxHash64> fieldHashOperators, SqlRow sqlRow) | |
{ | |
try { | |
int rawIndex = sqlRow.getRawIndex(); | |
long hash = 0; | |
for (int i = 0; i < sqlRow.getFieldCount(); i++) { | |
Block fieldBlock = sqlRow.getRawFieldBlock(i); | |
if (fieldBlock.isNull(rawIndex)) { | |
hash = hash + PRIME64; | |
} else { | |
hash = hash + fieldHashOperators.get(i).xxHash64(fieldBlock, rawIndex) * PRIME64; | |
} | |
} | |
Slice value = Slices.allocate(Long.BYTES); | |
value.setLong(0, hash); | |
return value; | |
} | |
catch (RuntimeException e) { | |
throw e; | |
} | |
catch (Exception e) { | |
throw new RuntimeException(e); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment