org.archive.util.binsearch

Class SortedTextFile

java.lang.Object

org.archive.util.binsearch.SortedTextFile

Direct Known Subclasses:

CDXFile

public class SortedTextFile
extends java.lang.Object

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	SortedTextFile.CachedStringIterator
static class	SortedTextFile.DefaultComparator
static class	SortedTextFile.NumericComparator

Field Summary

Fields

Modifier and Type	Field and Description
protected int	binsearchBlockSize
static java.util.Comparator<java.lang.String>	defaultComparator
protected SeekableLineReaderFactory	factory
static java.util.Comparator<java.lang.String>	numericComparator

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	SortedTextFile()
	SortedTextFile(SeekableLineReaderFactory factory)
	SortedTextFile(java.lang.String filename)
	SortedTextFile(java.lang.String filename, boolean useNio)

Method Summary

Modifier and Type	Method and Description
long	binaryFindOffset(SeekableLineReader slr, java.lang.String key, java.util.Comparator<java.lang.String> comparator)
int	getBinsearchBlockSize()
java.lang.String	getLastLine(SeekableLineReader slr)
java.lang.String[]	getNthSplit(java.lang.String start, java.lang.String end, int split, int numSplits)
java.lang.String[]	getRange(java.lang.String start, java.lang.String end)
CloseableIterator<java.lang.String>	getRecordIterator(long offset)
CloseableIterator<java.lang.String>	getRecordIterator(java.lang.String prefix)
CloseableIterator<java.lang.String>	getRecordIterator(java.lang.String prefix, boolean lessThan)
CloseableIterator<java.lang.String>	getRecordIteratorLT(java.lang.String prefix)
SeekableLineReader	getSLR()
CloseableIterator<java.lang.String>	getSplitIterator(java.lang.String start, java.lang.String end, int numSplits)
long[]	getStartEndOffsets(SeekableLineReader slr, java.lang.String start, java.lang.String end)
void	reloadFactory()
void	setBinsearchBlockSize(int binsearchBlockSize)
protected void	setFactory(SeekableLineReaderFactory factory)

Methods inherited from class java.lang.Object

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

Field Detail

numericComparator

public static final java.util.Comparator<java.lang.String> numericComparator

defaultComparator

public static final java.util.Comparator<java.lang.String> defaultComparator

factory

protected SeekableLineReaderFactory factory

binsearchBlockSize

protected int binsearchBlockSize

Constructor Detail

SortedTextFile

public SortedTextFile(SeekableLineReaderFactory factory)

SortedTextFile

public SortedTextFile(java.lang.String filename)
               throws java.io.IOException

Throws:

java.io.IOException

SortedTextFile

public SortedTextFile(java.lang.String filename,
                      boolean useNio)
               throws java.io.IOException

Throws:

java.io.IOException

SortedTextFile

protected SortedTextFile()

Method Detail

setFactory

protected void setFactory(SeekableLineReaderFactory factory)

reloadFactory

public void reloadFactory()

getBinsearchBlockSize

public int getBinsearchBlockSize()

setBinsearchBlockSize

public void setBinsearchBlockSize(int binsearchBlockSize)

getRecordIteratorLT

public CloseableIterator<java.lang.String> getRecordIteratorLT(java.lang.String prefix)
                                                        throws java.io.IOException

Throws:

java.io.IOException

getRecordIterator

public CloseableIterator<java.lang.String> getRecordIterator(java.lang.String prefix)
                                                      throws java.io.IOException

Throws:

java.io.IOException

getSLR

public SeekableLineReader getSLR()
                          throws java.io.IOException

Throws:

java.io.IOException

getRecordIterator

public CloseableIterator<java.lang.String> getRecordIterator(long offset)
                                                      throws java.io.IOException

Throws:

java.io.IOException

getRecordIterator

public CloseableIterator<java.lang.String> getRecordIterator(java.lang.String prefix,
                                                             boolean lessThan)
                                                      throws java.io.IOException

Throws:

java.io.IOException

binaryFindOffset

public long binaryFindOffset(SeekableLineReader slr,
                             java.lang.String key,
                             java.util.Comparator<java.lang.String> comparator)
                      throws java.io.IOException

Throws:

java.io.IOException

getStartEndOffsets

public long[] getStartEndOffsets(SeekableLineReader slr,
                                 java.lang.String start,
                                 java.lang.String end)
                          throws java.io.IOException

Throws:

java.io.IOException

getSplitIterator

public CloseableIterator<java.lang.String> getSplitIterator(java.lang.String start,
                                                            java.lang.String end,
                                                            int numSplits)
                                                     throws java.io.IOException

Throws:

java.io.IOException

getRange

public java.lang.String[] getRange(java.lang.String start,
                                   java.lang.String end)
                            throws java.io.IOException

Throws:

java.io.IOException

getNthSplit

public java.lang.String[] getNthSplit(java.lang.String start,
                                      java.lang.String end,
                                      int split,
                                      int numSplits)
                               throws java.io.IOException

Throws:

java.io.IOException

getLastLine

public java.lang.String getLastLine(SeekableLineReader slr)
                             throws java.io.IOException

Throws:

java.io.IOException