org.apache.iceberg.mr.hive

Class HiveIcebergStorageHandler

java.lang.Object

org.apache.iceberg.mr.hive.HiveIcebergStorageHandler

All Implemented Interfaces:

org.apache.hadoop.conf.Configurable, org.apache.hadoop.hive.ql.metadata.HiveStorageHandler, org.apache.hadoop.hive.ql.metadata.HiveStoragePredicateHandler

public class HiveIcebergStorageHandler
extends java.lang.Object
implements org.apache.hadoop.hive.ql.metadata.HiveStoragePredicateHandler, org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

Nested Class Summary

Nested classes/interfaces inherited from interface org.apache.hadoop.hive.ql.metadata.HiveStoragePredicateHandler

org.apache.hadoop.hive.ql.metadata.HiveStoragePredicateHandler.DecomposedPredicate

Constructor Summary

Constructors

Constructor and Description
HiveIcebergStorageHandler()

Method Summary

Modifier and Type	Method and Description
void	configureInputJobCredentials(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc, java.util.Map<java.lang.String,java.lang.String> secrets)
void	configureInputJobProperties(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc, java.util.Map<java.lang.String,java.lang.String> map)
void	configureJobConf(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc, org.apache.hadoop.mapred.JobConf jobConf)
void	configureOutputJobProperties(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc, java.util.Map<java.lang.String,java.lang.String> map)
void	configureTableJobProperties(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc, java.util.Map<java.lang.String,java.lang.String> map)
org.apache.hadoop.hive.ql.metadata.HiveStoragePredicateHandler.DecomposedPredicate	decomposePredicate(org.apache.hadoop.mapred.JobConf jobConf, org.apache.hadoop.hive.serde2.Deserializer deserializer, org.apache.hadoop.hive.ql.plan.ExprNodeDesc exprNodeDesc)
static EncryptionManager	encryption(org.apache.hadoop.conf.Configuration config) Returns the Table EncryptionManager serialized to the configuration.
org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider	getAuthorizationProvider()
org.apache.hadoop.conf.Configuration	getConf()
java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat>	getInputFormatClass()
org.apache.hadoop.hive.metastore.HiveMetaHook	getMetaHook()
java.lang.Class<? extends org.apache.hadoop.mapred.OutputFormat>	getOutputFormatClass()
java.lang.Class<? extends org.apache.hadoop.hive.serde2.AbstractSerDe>	getSerDeClass()
static FileIO	io(org.apache.hadoop.conf.Configuration config) Returns the Table FileIO serialized to the configuration.
static LocationProvider	location(org.apache.hadoop.conf.Configuration config) Returns the Table LocationProvider serialized to the configuration.
static Schema	schema(org.apache.hadoop.conf.Configuration config) Returns the Table Schema serialized to the configuration.
void	setConf(org.apache.hadoop.conf.Configuration conf)
static PartitionSpec	spec(org.apache.hadoop.conf.Configuration config) Returns the Table PartitionSpec serialized to the configuration.
java.lang.String	toString()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

getLockType, getStorageHandlerInfo

Constructor Detail

HiveIcebergStorageHandler

public HiveIcebergStorageHandler()

Method Detail

getInputFormatClass

public java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat> getInputFormatClass()

Specified by:

getInputFormatClass in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

getOutputFormatClass

public java.lang.Class<? extends org.apache.hadoop.mapred.OutputFormat> getOutputFormatClass()

Specified by:

getOutputFormatClass in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

getSerDeClass

public java.lang.Class<? extends org.apache.hadoop.hive.serde2.AbstractSerDe> getSerDeClass()

Specified by:

getSerDeClass in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

getMetaHook

public org.apache.hadoop.hive.metastore.HiveMetaHook getMetaHook()

Specified by:

getMetaHook in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

getAuthorizationProvider

public org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider getAuthorizationProvider()

Specified by:

getAuthorizationProvider in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

configureInputJobProperties

public void configureInputJobProperties(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc,
                                        java.util.Map<java.lang.String,java.lang.String> map)

Specified by:

configureInputJobProperties in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

configureOutputJobProperties

public void configureOutputJobProperties(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc,
                                         java.util.Map<java.lang.String,java.lang.String> map)

Specified by:

configureOutputJobProperties in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

configureTableJobProperties

public void configureTableJobProperties(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc,
                                        java.util.Map<java.lang.String,java.lang.String> map)

Specified by:

configureTableJobProperties in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

configureInputJobCredentials

public void configureInputJobCredentials(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc,
                                         java.util.Map<java.lang.String,java.lang.String> secrets)

Specified by:

configureInputJobCredentials in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

configureJobConf

public void configureJobConf(org.apache.hadoop.hive.ql.plan.TableDesc tableDesc,
                             org.apache.hadoop.mapred.JobConf jobConf)

Specified by:

configureJobConf in interface org.apache.hadoop.hive.ql.metadata.HiveStorageHandler

getConf

public org.apache.hadoop.conf.Configuration getConf()

Specified by:

getConf in interface org.apache.hadoop.conf.Configurable

setConf

public void setConf(org.apache.hadoop.conf.Configuration conf)

Specified by:

setConf in interface org.apache.hadoop.conf.Configurable

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

decomposePredicate

public org.apache.hadoop.hive.ql.metadata.HiveStoragePredicateHandler.DecomposedPredicate decomposePredicate(org.apache.hadoop.mapred.JobConf jobConf,
                                                                                                             org.apache.hadoop.hive.serde2.Deserializer deserializer,
                                                                                                             org.apache.hadoop.hive.ql.plan.ExprNodeDesc exprNodeDesc)

Specified by:

decomposePredicate in interface org.apache.hadoop.hive.ql.metadata.HiveStoragePredicateHandler

Parameters:

jobConf - Job configuration for InputFormat to access

deserializer - Deserializer

exprNodeDesc - Filter expression extracted by Hive

Returns:

Entire filter to take advantage of Hive's pruning as well as Iceberg's pruning.

io

public static FileIO io(org.apache.hadoop.conf.Configuration config)

Returns the Table FileIO serialized to the configuration.

Parameters:

config - The configuration used to get the data from

Returns:

The Table FileIO object

location

public static LocationProvider location(org.apache.hadoop.conf.Configuration config)

Returns the Table LocationProvider serialized to the configuration.

Parameters:

config - The configuration used to get the data from

Returns:

The Table LocationProvider object

encryption

public static EncryptionManager encryption(org.apache.hadoop.conf.Configuration config)

Returns the Table EncryptionManager serialized to the configuration.

Parameters:

config - The configuration used to get the data from

Returns:

The Table EncryptionManager object

schema

public static Schema schema(org.apache.hadoop.conf.Configuration config)

Returns the Table Schema serialized to the configuration.

Parameters:

config - The configuration used to get the data from

Returns:

The Table Schema object

spec

public static PartitionSpec spec(org.apache.hadoop.conf.Configuration config)

Returns the Table PartitionSpec serialized to the configuration.

Parameters:

config - The configuration used to get the data from

Returns:

The Table PartitionSpec object