edu.stanford.nlp.patterns

Class LuceneSentenceIndex<E extends Pattern>

java.lang.Object

edu.stanford.nlp.patterns.SentenceIndex<E>

edu.stanford.nlp.patterns.LuceneSentenceIndex<E>

public class LuceneSentenceIndex<E extends Pattern>
extends SentenceIndex<E>

To create a lucene inverted index from tokens to sentence ids. (Right now it is not storing all core tokens although some functions might suggest that.)

Author:

Sonal Gupta on 10/14/14.

Constructor Summary

Constructors

Constructor and Description
LuceneSentenceIndex(java.util.Properties props, java.util.Set<java.lang.String> stopWords, java.lang.String indexDirStr, java.util.function.Function<CoreLabel,java.util.Map<java.lang.String,java.lang.String>> transformer)

Method Summary

Modifier and Type	Method and Description
protected void	add(java.util.List<CoreLabel> tokens, java.lang.String sentid, boolean addProcessedText)
void	add(java.util.Map<java.lang.String,DataInstance> sentences, boolean addProcessedText) addProcessedText is true when inserting sentences for the first time
static LuceneSentenceIndex	createIndex(java.util.Map<java.lang.String,java.util.List<CoreLabel>> sentences, java.util.Properties props, java.util.Set<java.lang.String> stopWords, java.lang.String indexDiskDir, java.util.function.Function<CoreLabel,java.util.Map<java.lang.String,java.lang.String>> transformer)
void	finishUpdating()
void	listAllDocuments()
static LuceneSentenceIndex	loadIndex(java.util.Properties props, java.util.Set<java.lang.String> stopwords, java.lang.String dir, java.util.function.Function<CoreLabel,java.util.Map<java.lang.String,java.lang.String>> transformSentenceToString)
java.util.Map<E,java.util.Set<java.lang.String>>	queryIndex(java.util.Collection<E> patterns)
void	saveIndex(java.lang.String dir)
void	update(java.util.List<CoreLabel> tokens, java.lang.String sentid)

Methods inherited from class edu.stanford.nlp.patterns.SentenceIndex

createIndex, loadIndex, setUp, size

Methods inherited from class java.lang.Object

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

Constructor Detail

LuceneSentenceIndex

public LuceneSentenceIndex(java.util.Properties props,
                           java.util.Set<java.lang.String> stopWords,
                           java.lang.String indexDirStr,
                           java.util.function.Function<CoreLabel,java.util.Map<java.lang.String,java.lang.String>> transformer)

Method Detail

add

public void add(java.util.Map<java.lang.String,DataInstance> sentences,
                boolean addProcessedText)

Description copied from class: SentenceIndex

addProcessedText is true when inserting sentences for the first time

Specified by:

add in class SentenceIndex<E extends Pattern>

queryIndex

public java.util.Map<E,java.util.Set<java.lang.String>> queryIndex(java.util.Collection<E> patterns)

Specified by:

queryIndex in class SentenceIndex<E extends Pattern>

listAllDocuments

public void listAllDocuments()
                      throws java.io.IOException

Throws:

java.io.IOException

add

protected void add(java.util.List<CoreLabel> tokens,
                   java.lang.String sentid,
                   boolean addProcessedText)

Specified by:

add in class SentenceIndex<E extends Pattern>

finishUpdating

public void finishUpdating()

Specified by:

finishUpdating in class SentenceIndex<E extends Pattern>

update

public void update(java.util.List<CoreLabel> tokens,
                   java.lang.String sentid)

Specified by:

update in class SentenceIndex<E extends Pattern>

saveIndex

public void saveIndex(java.lang.String dir)

Specified by:

saveIndex in class SentenceIndex<E extends Pattern>

createIndex

public static LuceneSentenceIndex createIndex(java.util.Map<java.lang.String,java.util.List<CoreLabel>> sentences,
                                              java.util.Properties props,
                                              java.util.Set<java.lang.String> stopWords,
                                              java.lang.String indexDiskDir,
                                              java.util.function.Function<CoreLabel,java.util.Map<java.lang.String,java.lang.String>> transformer)

loadIndex

public static LuceneSentenceIndex loadIndex(java.util.Properties props,
                                            java.util.Set<java.lang.String> stopwords,
                                            java.lang.String dir,
                                            java.util.function.Function<CoreLabel,java.util.Map<java.lang.String,java.lang.String>> transformSentenceToString)