Package de.julielab.jules.ae.genemapping

Class LuceneCandidateRetrieval

java.lang.Object

de.julielab.jules.ae.genemapping.LuceneCandidateRetrieval

All Implemented Interfaces:

CandidateRetrieval

public class LuceneCandidateRetrieval
extends java.lang.Object
implements CandidateRetrieval

Field Summary

Fields

Modifier and Type	Field	Description
static org.slf4j.Logger	candidateLog
static int	JAROWINKLER_SCORER
static int	LEVENSHTEIN_SCORER
static java.lang.String	LOGGER_NAME_CANDIDATES
static int	LUCENE_SCORER
static int	MAXENT_SCORER
static java.lang.String	MAXENT_SCORER_MODEL	default model for MaxEntScorer
static java.lang.String	NAME_PRIO_DELIMITER
static int	SIMPLE_SCORER
static int	TFIDF
static int	TOKEN_JAROWINKLER_SCORER

Constructor Summary

Constructors

Constructor	Description
LuceneCandidateRetrieval(GeneMappingConfiguration config)
LuceneCandidateRetrieval(org.apache.lucene.search.IndexSearcher mentionIndexSearcher, Scorer scorer)	Deprecated.

Method Summary

Modifier and Type	Method	Description
java.util.List<SynHit>	getCandidates(GeneMention geneMention)
java.util.List<SynHit>	getCandidates(GeneMention geneMention, java.lang.String organism)
java.util.List<SynHit>	getCandidates(GeneMention geneMention, java.util.Collection<java.lang.String> organisms)
java.util.List<SynHit>	getCandidates(java.lang.String originalSearchTerm)
java.util.List<SynHit>	getCandidates(java.lang.String geneMentionText, java.lang.String organism)
java.util.List<SynHit>	getCandidates(java.lang.String geneMentionText, java.util.Collection<java.lang.String> organism)
java.util.List<SynHit>	getIndexEntries(java.util.List<java.lang.String> ids)	Retrieves the first index hit for each ID.
org.apache.lucene.search.IndexSearcher	getMentionIndexSearcher()
TermNormalizer	getNormalizer()
java.util.List<java.lang.String>	getPriorityNames(java.lang.String id, int priority)
java.util.List<java.lang.String>	getPriorityNames(java.util.List<java.lang.String> ids, int priority)
Scorer	getScorer()
java.lang.String	getScorerInfo()
int	getScorerType()
org.apache.lucene.search.spell.SpellChecker	getSpellingChecker()
java.util.List<java.lang.String>	getSynonyms(java.lang.String id)
java.lang.String	mapGeneIdToTaxId(java.lang.String geneId)
void	setNormalizer(TermNormalizer normalizer)
Scorer	setScorerType(int type)

Methods inherited from class java.lang.Object

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

Field Detail

NAME_PRIO_DELIMITER

public static final java.lang.String NAME_PRIO_DELIMITER

See Also:

Constant Field Values

LOGGER_NAME_CANDIDATES

public static final java.lang.String LOGGER_NAME_CANDIDATES

See Also:

Constant Field Values

SIMPLE_SCORER

public static final int SIMPLE_SCORER

See Also:

Constant Field Values

TOKEN_JAROWINKLER_SCORER

public static final int TOKEN_JAROWINKLER_SCORER

See Also:

Constant Field Values

MAXENT_SCORER

public static final int MAXENT_SCORER

See Also:

Constant Field Values

JAROWINKLER_SCORER

public static final int JAROWINKLER_SCORER

See Also:

Constant Field Values

LEVENSHTEIN_SCORER

public static final int LEVENSHTEIN_SCORER

See Also:

Constant Field Values

TFIDF

public static final int TFIDF

See Also:

Constant Field Values

LUCENE_SCORER

public static final int LUCENE_SCORER

See Also:

Constant Field Values

MAXENT_SCORER_MODEL

public static final java.lang.String MAXENT_SCORER_MODEL

default model for MaxEntScorer

See Also:

Constant Field Values

candidateLog

public static final org.slf4j.Logger candidateLog

Constructor Detail

LuceneCandidateRetrieval

@Deprecated
public LuceneCandidateRetrieval(org.apache.lucene.search.IndexSearcher mentionIndexSearcher,
                                Scorer scorer)
                         throws java.io.IOException

Deprecated.

Throws:

java.io.IOException

LuceneCandidateRetrieval

public LuceneCandidateRetrieval(GeneMappingConfiguration config)
                         throws GeneMappingException

Throws:

GeneMappingException

Method Detail

getNormalizer

public TermNormalizer getNormalizer()

setNormalizer

public void setNormalizer(TermNormalizer normalizer)

getScorer

public Scorer getScorer()

getMentionIndexSearcher

public org.apache.lucene.search.IndexSearcher getMentionIndexSearcher()

getSpellingChecker

public org.apache.lucene.search.spell.SpellChecker getSpellingChecker()

setScorerType

public Scorer setScorerType(int type)
                     throws GeneMappingException

Throws:

GeneMappingException

getScorerInfo

public java.lang.String getScorerInfo()

getScorerType

public int getScorerType()

getCandidates

public java.util.List<SynHit> getCandidates(java.lang.String originalSearchTerm)
                                     throws GeneCandidateRetrievalException

Specified by:

getCandidates in interface CandidateRetrieval

Throws:

GeneCandidateRetrievalException

getCandidates

public java.util.List<SynHit> getCandidates(GeneMention geneMention)
                                     throws GeneCandidateRetrievalException

Specified by:

getCandidates in interface CandidateRetrieval

Throws:

GeneCandidateRetrievalException

getCandidates

public java.util.List<SynHit> getCandidates(GeneMention geneMention,
                                            java.util.Collection<java.lang.String> organisms)
                                     throws GeneCandidateRetrievalException

Specified by:

getCandidates in interface CandidateRetrieval

Throws:

GeneCandidateRetrievalException

getCandidates

public java.util.List<SynHit> getCandidates(GeneMention geneMention,
                                            java.lang.String organism)
                                     throws GeneCandidateRetrievalException

Specified by:

getCandidates in interface CandidateRetrieval

Throws:

GeneCandidateRetrievalException

getCandidates

public java.util.List<SynHit> getCandidates(java.lang.String geneMentionText,
                                            java.lang.String organism)
                                     throws GeneCandidateRetrievalException

Specified by:

getCandidates in interface CandidateRetrieval

Throws:

GeneCandidateRetrievalException

getCandidates

public java.util.List<SynHit> getCandidates(java.lang.String geneMentionText,
                                            java.util.Collection<java.lang.String> organism)
                                     throws GeneCandidateRetrievalException

Specified by:

getCandidates in interface CandidateRetrieval

Throws:

GeneCandidateRetrievalException

mapGeneIdToTaxId

public java.lang.String mapGeneIdToTaxId(java.lang.String geneId)
                                  throws java.io.IOException

Specified by:

mapGeneIdToTaxId in interface CandidateRetrieval

Throws:

java.io.IOException

getIndexEntries

public java.util.List<SynHit> getIndexEntries(java.util.List<java.lang.String> ids)
                                       throws java.io.IOException

Description copied from interface: CandidateRetrieval

Retrieves the first index hit for each ID.

Specified by:

getIndexEntries in interface CandidateRetrieval

Parameters:

ids - The gene IDs for which to retrieve a single index hit.

Returns:

One index entry - or null - for each input ID.

Throws:

java.io.IOException - If there is an issue reading the index.

getSynonyms

public java.util.List<java.lang.String> getSynonyms(java.lang.String id)
                                             throws java.io.IOException

Specified by:

getSynonyms in interface CandidateRetrieval

Throws:

java.io.IOException

getPriorityNames

public java.util.List<java.lang.String> getPriorityNames(java.lang.String id,
                                                         int priority)
                                                  throws java.io.IOException

Throws:

java.io.IOException

getPriorityNames

public java.util.List<java.lang.String> getPriorityNames(java.util.List<java.lang.String> ids,
                                                         int priority)
                                                  throws java.io.IOException

Throws:

java.io.IOException