idl.tmt.representation
Class IndexedCollection

java.lang.Object
  |
  +--idl.tmt.representation.IndexedCollection

All Implemented Interfaces:

java.io.Serializable

public class IndexedCollection

extends java.lang.Object

implements java.io.Serializable

A class that allows us manage a collection of terms and documents

Author:

miles

See Also:

Serialized Form

Field Summary

(package private) java.lang.String	collectionName
(package private) DocumentIDMapper	docList
(package private) java.util.LinkedList	documentClassifications
(package private) java.util.HashMap	documentIndex
(package private) java.util.HashMap	invertedIndex
(package private) TmtMatrix	matrix
private static java.lang.String	SUFFIX
(package private) TermList	termList
(package private) java.util.LinkedList	transformations
(package private) URLMapper	urlMap

Constructor Summary

IndexedCollection(java.lang.String collectionName)

IndexedCollection(TermList terms, DocumentIDMapper docIDMapper, URLMapper ul, TmtMatrix mat)

Method Summary

void	addDocumentClassification(DocumentClassification dc)
private void	createDocumentIndex()
java.io.File	getDocFile(int docID)
java.util.ArrayList	getDocTermIDs(int docID)
java.util.ArrayList	getDocTerms(int docID)
java.util.List	getDocumentClassifications()
DocumentIDMapper	getDocumentIDMapper()
TmtMatrix	getMatrix()
int	getNumDocs()
int	getNumTerms()
java.net.URL	getRemoteURL(java.io.File docFile)
java.lang.String	getTerm(int termID)
java.util.ArrayList	getTermDocs(int termID)
TermList	getTermList()
URLMapper	getURLMapper()
void	printCollectionStats()
private void	readCollection()
private void	saveCollection() writes all known information about this collection to disk
void	saveCollection(java.lang.String collectionName)
void	setDocumentIDMapper(DocumentIDMapper d)
void	setMatrix(TmtMatrix m)
void	setTermList(TermList t)
void	setURLMapper(URLMapper u)

Methods inherited from class java.lang.Object

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

Field Detail

SUFFIX

private static final java.lang.String SUFFIX

collectionName

java.lang.String collectionName

transformations

java.util.LinkedList transformations

termList

TermList termList

docList

DocumentIDMapper docList

urlMap

URLMapper urlMap

documentIndex

java.util.HashMap documentIndex

invertedIndex

java.util.HashMap invertedIndex

matrix

TmtMatrix matrix

documentClassifications

java.util.LinkedList documentClassifications

Constructor Detail

IndexedCollection

public IndexedCollection(java.lang.String collectionName)
                  throws java.io.FileNotFoundException,
                         java.io.IOException,
                         java.lang.ClassNotFoundException

IndexedCollection

public IndexedCollection(TermList terms,
                         DocumentIDMapper docIDMapper,
                         URLMapper ul,
                         TmtMatrix mat)

Method Detail

saveCollection

public void saveCollection(java.lang.String collectionName)
                    throws java.io.IOException

saveCollection

private void saveCollection()
                     throws java.io.IOException

writes all known information about this collection to disk

Parameters:

myTerms - a TermList mapping termIDs to Strings

myDocs - a DocIDMapper

myMatrix - a document-term matrix (hopefully sparse)

readCollection

private void readCollection()
                     throws java.io.FileNotFoundException,
                            java.io.IOException,
                            java.lang.ClassNotFoundException

getNumTerms

public int getNumTerms()

getNumDocs

public int getNumDocs()

getDocFile

public java.io.File getDocFile(int docID)

getRemoteURL

public java.net.URL getRemoteURL(java.io.File docFile)

getDocTermIDs

public java.util.ArrayList getDocTermIDs(int docID)

getDocTerms

public java.util.ArrayList getDocTerms(int docID)

getTermDocs

public java.util.ArrayList getTermDocs(int termID)

getTerm

public java.lang.String getTerm(int termID)

getMatrix

public TmtMatrix getMatrix()

setMatrix

public void setMatrix(TmtMatrix m)

setDocumentIDMapper

public void setDocumentIDMapper(DocumentIDMapper d)

getDocumentIDMapper

public DocumentIDMapper getDocumentIDMapper()

setURLMapper

public void setURLMapper(URLMapper u)

getURLMapper

public URLMapper getURLMapper()

setTermList

public void setTermList(TermList t)

getTermList

public TermList getTermList()

createDocumentIndex

private void createDocumentIndex()

addDocumentClassification

public void addDocumentClassification(DocumentClassification dc)

getDocumentClassifications

public java.util.List getDocumentClassifications()

printCollectionStats

public void printCollectionStats()