org.calrissian.accumulorecipes.commons.iterators

Class AndIterator

java.lang.Object

org.calrissian.accumulorecipes.commons.iterators.AndIterator

All Implemented Interfaces:

org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

public class AndIterator
extends Object
implements org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
protected static class	AndIterator.TermSource Used in representing a Term that is intersected on.

Field Summary

Fields

Modifier and Type	Field and Description
static String	columnFamiliesOptionName
protected byte[]	emptyByteArray
protected static org.apache.log4j.Logger	log
static String	notFlagsOptionName
protected org.apache.hadoop.io.Text	nullText
static String	termValuesOptionName
protected org.apache.accumulo.core.data.Value	value

Constructor Summary

Constructors

Constructor and Description
AndIterator() Empty default constructor
AndIterator(AndIterator other, org.apache.accumulo.core.iterators.IteratorEnvironment env)

Method Summary

Methods

Modifier and Type	Method and Description
void	addSource(org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> source, org.apache.accumulo.core.iterators.IteratorEnvironment env, org.apache.hadoop.io.Text term, boolean notFlag)
void	addSource(org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> source, org.apache.accumulo.core.iterators.IteratorEnvironment env, org.apache.hadoop.io.Text dataLocation, org.apache.hadoop.io.Text term, boolean notFlag)
protected void	advanceToIntersection()
protected org.apache.accumulo.core.data.Key	buildFollowingPartitionKey(org.apache.accumulo.core.data.Key key) Return the key that directly follows the given key
protected org.apache.accumulo.core.data.Key	buildKey(org.apache.hadoop.io.Text row, org.apache.hadoop.io.Text dataLocation) Build a key from the given row and dataLocation
protected org.apache.accumulo.core.data.Key	buildKey(org.apache.hadoop.io.Text row, org.apache.hadoop.io.Text dataLocation, org.apache.hadoop.io.Text term) Build a key from the given row, dataLocation, and term
static boolean[]	decodeBooleans(String flags) Decode the encoded NOT flags into a boolean array
static org.apache.hadoop.io.Text[]	decodeColumns(String columns) Decode the encoded columns into a Text array
static org.apache.hadoop.io.Text[]	decodeTermValues(String terms) Decode the encoded terms into a Text array
org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>	deepCopy(org.apache.accumulo.core.iterators.IteratorEnvironment env)
static String	encodeBooleans(boolean[] flags) Encode an array of booleans denoted which columns are NOT'ed
static String	encodeColumns(org.apache.hadoop.io.Text[] columns) Encode a Text array of all the columns to intersect on
static String	encodeTermValues(org.apache.hadoop.io.Text[] terms) Encode a Text array of all of the terms to intersect on.
protected org.apache.hadoop.io.Text	getDataLocation(org.apache.accumulo.core.data.Key key) Returns the given key's dataLocation
protected org.apache.hadoop.io.Text	getDocID(org.apache.accumulo.core.data.Key key) Returns the given key's DocID
protected org.apache.hadoop.io.Text	getPartition(org.apache.accumulo.core.data.Key key)
protected org.apache.hadoop.io.Text	getTerm(org.apache.accumulo.core.data.Key key) Returns the given key's term
org.apache.accumulo.core.data.Key	getTopKey()
org.apache.accumulo.core.data.Value	getTopValue()
protected String	getUID(org.apache.accumulo.core.data.Key key) Returns the given key's UID
boolean	hasTop()
void	init(org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> source, Map<String,String> options, org.apache.accumulo.core.iterators.IteratorEnvironment env)
boolean	jump(org.apache.accumulo.core.data.Key jumpKey)
void	next()
void	seek(org.apache.accumulo.core.data.Range range, Collection<org.apache.accumulo.core.data.ByteSequence> seekColumnFamilies, boolean inclusive)
static String	stringTopKey(org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> iter)

Methods inherited from class java.lang.Object

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

Field Detail

columnFamiliesOptionName

public static final String columnFamiliesOptionName

See Also:

Constant Field Values

termValuesOptionName

public static final String termValuesOptionName

See Also:

Constant Field Values

notFlagsOptionName

public static final String notFlagsOptionName

See Also:

Constant Field Values

log

protected static final org.apache.log4j.Logger log

emptyByteArray

protected final byte[] emptyByteArray

value

protected org.apache.accumulo.core.data.Value value

nullText

protected org.apache.hadoop.io.Text nullText

Constructor Detail

AndIterator

public AndIterator()

Empty default constructor

AndIterator

public AndIterator(AndIterator other,
           org.apache.accumulo.core.iterators.IteratorEnvironment env)

Method Detail

stringTopKey

public static String stringTopKey(org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> iter)

encodeColumns

public static String encodeColumns(org.apache.hadoop.io.Text[] columns)

Encode a Text array of all the columns to intersect on

Parameters:

columns - The columns to be encoded

Returns:

A Base64 encoded string (using a \n delimiter) of all columns to intersect on.

encodeTermValues

public static String encodeTermValues(org.apache.hadoop.io.Text[] terms)

Encode a Text array of all of the terms to intersect on. The terms should match the columns in a one-to-one manner

Parameters:

terms - The terms to be encoded

Returns:

A Base64 encoded string (using a \n delimiter) of all terms to intersect on.

encodeBooleans

public static String encodeBooleans(boolean[] flags)

Encode an array of booleans denoted which columns are NOT'ed

Parameters:

flags - The array of NOTs

Returns:

A base64 encoded string of which columns are NOT'ed

decodeColumns

public static org.apache.hadoop.io.Text[] decodeColumns(String columns)

Decode the encoded columns into a Text array

Parameters:

columns - The Base64 encoded String of the columns

Returns:

A Text array of the decoded columns

decodeTermValues

public static org.apache.hadoop.io.Text[] decodeTermValues(String terms)

Decode the encoded terms into a Text array

Parameters:

terms - The Base64 encoded String of the terms

Returns:

A Text array of decoded terms.

decodeBooleans

public static boolean[] decodeBooleans(String flags)

Decode the encoded NOT flags into a boolean array

Parameters:

flags -

Returns:

A boolean array of decoded NOT flags

getPartition

protected org.apache.hadoop.io.Text getPartition(org.apache.accumulo.core.data.Key key)

getDataLocation

protected org.apache.hadoop.io.Text getDataLocation(org.apache.accumulo.core.data.Key key)

Returns the given key's dataLocation

Parameters:

key -

Returns:

The given key's dataLocation

getTerm

protected org.apache.hadoop.io.Text getTerm(org.apache.accumulo.core.data.Key key)

Returns the given key's term

Parameters:

key -

Returns:

The given key's term

getDocID

protected org.apache.hadoop.io.Text getDocID(org.apache.accumulo.core.data.Key key)

Returns the given key's DocID

Parameters:

key -

Returns:

The given key's DocID

getUID

protected String getUID(org.apache.accumulo.core.data.Key key)

Returns the given key's UID

Parameters:

key -

Returns:

The given key's UID

buildKey

protected org.apache.accumulo.core.data.Key buildKey(org.apache.hadoop.io.Text row,
                                         org.apache.hadoop.io.Text dataLocation)

Build a key from the given row and dataLocation

Parameters:

row - The desired row

dataLocation - The desired dataLocation

Returns:

A Key object built from the given row and dataLocation.

buildKey

protected org.apache.accumulo.core.data.Key buildKey(org.apache.hadoop.io.Text row,
                                         org.apache.hadoop.io.Text dataLocation,
                                         org.apache.hadoop.io.Text term)

Build a key from the given row, dataLocation, and term

Parameters:

row - The desired row

dataLocation - The desired dataLocation

term - The desired term

Returns:

A Key object built from the given row, dataLocation, and term.

buildFollowingPartitionKey

protected org.apache.accumulo.core.data.Key buildFollowingPartitionKey(org.apache.accumulo.core.data.Key key)

Return the key that directly follows the given key

Parameters:

key - The key who will be directly before the returned key

Returns:

The key directly following the given key.

deepCopy

public org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> deepCopy(org.apache.accumulo.core.iterators.IteratorEnvironment env)

Specified by:

deepCopy in interface org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

getTopKey

public org.apache.accumulo.core.data.Key getTopKey()

Specified by:

getTopKey in interface org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

getTopValue

public org.apache.accumulo.core.data.Value getTopValue()

Specified by:

getTopValue in interface org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

hasTop

public boolean hasTop()

Specified by:

hasTop in interface org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

next

public void next()
          throws IOException

Specified by:

next in interface org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

Throws:

IOException

advanceToIntersection

protected void advanceToIntersection()
                              throws IOException

Throws:

IOException

init

public void init(org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> source,
        Map<String,String> options,
        org.apache.accumulo.core.iterators.IteratorEnvironment env)
          throws IOException

Specified by:

init in interface org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

Throws:

IOException

seek

public void seek(org.apache.accumulo.core.data.Range range,
        Collection<org.apache.accumulo.core.data.ByteSequence> seekColumnFamilies,
        boolean inclusive)
          throws IOException

Specified by:

seek in interface org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value>

Throws:

IOException

addSource

public void addSource(org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> source,
             org.apache.accumulo.core.iterators.IteratorEnvironment env,
             org.apache.hadoop.io.Text term,
             boolean notFlag)

addSource

public void addSource(org.apache.accumulo.core.iterators.SortedKeyValueIterator<org.apache.accumulo.core.data.Key,org.apache.accumulo.core.data.Value> source,
             org.apache.accumulo.core.iterators.IteratorEnvironment env,
             org.apache.hadoop.io.Text dataLocation,
             org.apache.hadoop.io.Text term,
             boolean notFlag)

jump

public boolean jump(org.apache.accumulo.core.data.Key jumpKey)
             throws IOException

Throws:

IOException