Constant Field Values

Contents

• org.carrot2.*

org.carrot2.*

org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithmDescriptor

public final String	bindableClassName	"org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm"
public final String	description	"Unlike other algorithms in Carrot2, this one creates hard clusterings (one document belongs only to one cluster). On the other hand, the clusters are labeled only with individual words that may not always fully correspond to all documents in the cluster."
public final String	label	""
public final String	prefix	"BisectingKMeansClusteringAlgorithm"
public final String	title	"A very simple implementation of bisecting k-means clustering"

org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithmDescriptor.Keys

public static final String	CLUSTER_COUNT	"BisectingKMeansClusteringAlgorithm.clusterCount"
public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENTS	"documents"
public static final String	LABEL_COUNT	"BisectingKMeansClusteringAlgorithm.labelCount"
public static final String	MAX_ITERATIONS	"BisectingKMeansClusteringAlgorithm.maxIterations"
public static final String	PARTITION_COUNT	"BisectingKMeansClusteringAlgorithm.partitionCount"
public static final String	USE_DIMENSIONALITY_REDUCTION	"BisectingKMeansClusteringAlgorithm.useDimensionalityReduction"

org.carrot2.clustering.lingo.ClusterBuilderDescriptor

public final String	bindableClassName	"org.carrot2.clustering.lingo.ClusterBuilder"
public final String	description	""
public final String	label	""
public final String	prefix	"LingoClusteringAlgorithm"
public final String	title	"Builds cluster labels based on the reduced term-document matrix and assigns documents to the labels"

org.carrot2.clustering.lingo.ClusterBuilderDescriptor.Keys

public static final String	CLUSTER_MERGING_THRESHOLD	"LingoClusteringAlgorithm.clusterMergingThreshold"
public static final String	LABEL_ASSIGNER	"LingoClusteringAlgorithm.labelAssigner"
public static final String	PHRASE_LABEL_BOOST	"LingoClusteringAlgorithm.phraseLabelBoost"
public static final String	PHRASE_LENGTH_PENALTY_START	"LingoClusteringAlgorithm.phraseLengthPenaltyStart"
public static final String	PHRASE_LENGTH_PENALTY_STOP	"LingoClusteringAlgorithm.phraseLengthPenaltyStop"

org.carrot2.clustering.lingo.LingoClusteringAlgorithmDescriptor

public final String	bindableClassName	"org.carrot2.clustering.lingo.LingoClusteringAlgorithm"
public final String	description	"Implementation as described in: <i> \"Stanis\u0142aw Osi\u0144ski, Dawid Weiss: A Concept-Driven Algorithm for Clustering Search Results. IEEE Intelligent Systems, May/June, 3 (vol. 20), 2005, pp. 48\u201454.\"</i>."
public final String	label	""
public final String	prefix	"LingoClusteringAlgorithm"
public final String	title	"Lingo clustering algorithm"

org.carrot2.clustering.lingo.LingoClusteringAlgorithmDescriptor.Keys

public static final String	CLUSTERS	"clusters"
public static final String	DESIRED_CLUSTER_COUNT_BASE	"LingoClusteringAlgorithm.desiredClusterCountBase"
public static final String	DOCUMENTS	"documents"
public static final String	QUERY	"query"
public static final String	SCORE_WEIGHT	"LingoClusteringAlgorithm.scoreWeight"

org.carrot2.clustering.lingo.SimpleLabelAssignerDescriptor

public final String	bindableClassName	"org.carrot2.clustering.lingo.SimpleLabelAssigner"
public final String	description	"For each base vector chooses the label that maximizes the base vector--label term vector cosine similarity. Different vectors can get the same label assigned, which means the number of final labels (after duplicate removal) may be smaller than the number of base vectors on input."
public final String	label	""
public final String	prefix	""
public final String	title	"A simple and fast label assigner"

org.carrot2.clustering.lingo.UniqueLabelAssignerDescriptor

public final String	bindableClassName	"org.carrot2.clustering.lingo.UniqueLabelAssigner"
public final String	description	"For each base vector chooses the label that maximizes the base vector--label term vector cosine similarity and has not been previously selected. Once a label is selected, it will not be used to label any other vector. This algorithm does not create duplicate cluster labels, which usually means that this assignment method will create more clusters than <code>SimpleLabelAssigner</code>. This method is slightly slower than <code>SimpleLabelAssigner</code>."
public final String	label	""
public final String	prefix	""
public final String	title	"Assigns unique labels to each base vector using a greedy algorithm"

org.carrot2.clustering.stc.STCClusteringAlgorithmDescriptor

public final String	bindableClassName	"org.carrot2.clustering.stc.STCClusteringAlgorithm"
public final String	description	"Pretty much as described in: <i>Oren Zamir, Oren Etzioni, Grouper: A Dynamic Clustering Interface to Web Search Results, 1999.</i> Some liberties were taken wherever STC\'s description was not clear enough or where we thought some improvements could be made."
public final String	label	"STC Clustering"
public final String	prefix	"STCClusteringAlgorithm"
public final String	title	"Suffix Tree Clustering (STC) algorithm"

org.carrot2.clustering.stc.STCClusteringAlgorithmDescriptor.Keys

public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENT_COUNT_BOOST	"STCClusteringAlgorithm.documentCountBoost"
public static final String	DOCUMENTS	"documents"
public static final String	IGNORE_WORD_IF_IN_FEWER_DOCS	"STCClusteringAlgorithm.ignoreWordIfInFewerDocs"
public static final String	IGNORE_WORD_IF_IN_HIGHER_DOCS_PERCENT	"STCClusteringAlgorithm.ignoreWordIfInHigherDocsPercent"
public static final String	MAX_BASE_CLUSTERS	"STCClusteringAlgorithm.maxBaseClusters"
public static final String	MAX_CLUSTERS	"STCClusteringAlgorithm.maxClusters"
public static final String	MAX_DESC_PHRASE_LENGTH	"STCClusteringAlgorithm.maxDescPhraseLength"
public static final String	MAX_PHRASE_OVERLAP	"STCClusteringAlgorithm.maxPhraseOverlap"
public static final String	MAX_PHRASES	"STCClusteringAlgorithm.maxPhrases"
public static final String	MERGE_THRESHOLD	"STCClusteringAlgorithm.mergeThreshold"
public static final String	MIN_BASE_CLUSTER_SCORE	"STCClusteringAlgorithm.minBaseClusterScore"
public static final String	MIN_BASE_CLUSTER_SIZE	"STCClusteringAlgorithm.minBaseClusterSize"
public static final String	MOST_GENERAL_PHRASE_COVERAGE	"STCClusteringAlgorithm.mostGeneralPhraseCoverage"
public static final String	OPTIMAL_PHRASE_LENGTH	"STCClusteringAlgorithm.optimalPhraseLength"
public static final String	OPTIMAL_PHRASE_LENGTH_DEV	"STCClusteringAlgorithm.optimalPhraseLengthDev"
public static final String	QUERY	"query"
public static final String	SINGLE_TERM_BOOST	"STCClusteringAlgorithm.singleTermBoost"

org.carrot2.clustering.synthetic.ByFieldClusteringAlgorithmDescriptor

public final String	bindableClassName	"org.carrot2.clustering.synthetic.ByFieldClusteringAlgorithm"
public final String	description	"By default the <code>Document.SOURCES</code> field is used."
public final String	label	"By Attribute Clustering"
public final String	prefix	"ByAttributeClusteringAlgorithm"
public final String	title	"Clusters documents into a flat structure based on the values of some field of the documents"

org.carrot2.clustering.synthetic.ByFieldClusteringAlgorithmDescriptor.Keys

public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENTS	"documents"
public static final String	FIELD_NAME	"ByAttributeClusteringAlgorithm.fieldName"

org.carrot2.clustering.synthetic.ByUrlClusteringAlgorithmDescriptor

public final String	bindableClassName	"org.carrot2.clustering.synthetic.ByUrlClusteringAlgorithm"
public final String	description	"<code>Document.CONTENT_URL</code> property will be used to obtain a document\'s URL. <p> Groups at the top level of the hierarchy will correspond to the last segments of the URLs, usually domain suffixes, such as \".com\" or \".co.uk\". Subgroups will be created based on further segments of the URLs, very often domains subdomains, e.g. \"yahoo.com\", \"bbc.co.uk\" and then e.g. \"mail.yahoo.com\", \"news.yahoo.com\". The \"www\" segment of the URLs will be ignored. <p> Clusters will be ordered by size (number of documents) descendingly; in case of equal sizes, alphabetically by URL, see <code>Cluster.BY_REVERSED_SIZE_AND_LABEL_COMPARATOR</code>."
public final String	label	"By URL Clustering"
public final String	prefix	""
public final String	title	"Hierarchically clusters documents according to their content URLs"

org.carrot2.clustering.synthetic.ByUrlClusteringAlgorithmDescriptor.Keys

public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENTS	"documents"

org.carrot2.core.Cluster

public static final String	OTHER_TOPICS	"other-topics"
public static final String	OTHER_TOPICS_LABEL	"Other Topics"
public static final String	SCORE	"score"

org.carrot2.core.Document

public static final String	CLICK_URL	"click-url"
public static final String	CONTENT_URL	"url"
public static final String	LANGUAGE	"language"
public static final String	PARTITIONS	"partitions"
public static final String	SCORE	"score"
public static final String	SIZE	"size"
public static final String	SOURCES	"sources"
public static final String	SUMMARY	"snippet"
public static final String	THUMBNAIL_URL	"thumbnail-url"
public static final String	TITLE	"title"

org.carrot2.core.attribute.AttributeNames

public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENTS	"documents"
public static final String	PROCESSING_RESULT_TITLE	"processing-result.title"
public static final String	PROCESSING_TIME_ALGORITHM	"processing-time-algorithm"
public static final String	PROCESSING_TIME_SOURCE	"processing-time-source"
public static final String	PROCESSING_TIME_TOTAL	"processing-time-total"
public static final String	QUERY	"query"
public static final String	RESULTS	"results"
public static final String	RESULTS_TOTAL	"results-total"
public static final String	START	"start"

org.carrot2.core.attribute.CommonAttributesDescriptor

public final String	bindableClassName	"org.carrot2.core.attribute.CommonAttributes"
public final String	description	"Extracted for consistency."
public final String	label	""
public final String	prefix	""
public final String	title	"Attributes shared and inherited by many clustering algorithms"

org.carrot2.core.attribute.CommonAttributesDescriptor.Keys

public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENTS	"documents"
public static final String	PROCESSING_RESULT_TITLE	"processing-result.title"
public static final String	PROCESSING_TIME_ALGORITHM	"processing-time-algorithm"
public static final String	PROCESSING_TIME_SOURCE	"processing-time-source"
public static final String	PROCESSING_TIME_TOTAL	"processing-time-total"
public static final String	QUERY	"query"
public static final String	RESULTS	"results"
public static final String	RESULTS_TOTAL	"results-total"
public static final String	START	"start"

org.carrot2.matrix.factorization.IterativeMatrixFactorizationFactory

protected static final int	DEFAULT_K	15
protected static final int	DEFAULT_MAX_ITERATIONS	15
protected static final boolean	DEFAULT_ORDERED	true
protected static final double	DEFAULT_STOP_THRESHOLD	-1.0

org.carrot2.matrix.factorization.KMeansMatrixFactorization

protected static final int	DEFAULT_MAX_ITERATIONS	15
protected static final boolean	DEFAULT_ORDERED	false

org.carrot2.matrix.factorization.LocalNonnegativeMatrixFactorization

protected static final int	DEFAULT_MAX_ITERATIONS	15
protected static final boolean	DEFAULT_ORDERED	false

org.carrot2.matrix.factorization.NonnegativeMatrixFactorizationED

protected static final int	DEFAULT_MAX_ITERATIONS	15
protected static final boolean	DEFAULT_ORDERED	false

org.carrot2.matrix.factorization.NonnegativeMatrixFactorizationKL

protected static final int	DEFAULT_MAX_ITERATIONS	15
protected static final boolean	DEFAULT_ORDERED	false

org.carrot2.matrix.factorization.PartialSingularValueDecomposition

protected static final int

DEFAULT_K

-1

org.carrot2.matrix.factorization.PartialSingularValueDecompositionFactory

protected static final int

DEFAULT_K

-1

org.carrot2.output.metrics.ClusteringMetricsCalculatorDescriptor

public final String	bindableClassName	"org.carrot2.output.metrics.ClusteringMetricsCalculator"
public final String	description	""
public final String	label	""
public final String	prefix	""
public final String	title	"Calculates a set of quality metrics for clusters"

org.carrot2.output.metrics.ContaminationMetric

public static final String

CONTAMINATION

"contamination"

org.carrot2.output.metrics.ContaminationMetricDescriptor

public final String	bindableClassName	"org.carrot2.output.metrics.ContaminationMetric"
public final String	description	"If a cluster groups documents found in the same <code>Document.PARTITIONS</code>, its contamination is 0. If a cluster groups an equally distributed mix of all partitions, its contamination is 1.0. For a full definition, please see section 4.4.1 of <a href=\"http://project.carrot2.org/publications/osinski04-dimensionality.pdf\">this work</a>. <p> Contamination is calculated for top-level clusters only, taking into account documents from the cluster and all subclusters. Finally, contamination will be calculated only if all input documents have non-blank <code>Document.PARTITIONS</code>s. </p>"
public final String	label	""
public final String	prefix	""
public final String	title	"Computes cluster contamination"

org.carrot2.output.metrics.ContaminationMetricDescriptor.Keys

public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENTS	"documents"
public static final String	ENABLED	"org.carrot2.output.metrics.ContaminationMetric.enabled"
public static final String	WEIGHTED_AVERAGE_CONTAMINATION	"org.carrot2.output.metrics.ContaminationMetric.weightedAverageContamination"

org.carrot2.output.metrics.IdealPartitioningBasedMetricDescriptor

public final String	bindableClassName	"org.carrot2.output.metrics.IdealPartitioningBasedMetric"
public final String	description	""
public final String	label	""
public final String	prefix	""
public final String	title	"A base class for metrics based on some reference partitioning"

org.carrot2.output.metrics.IdealPartitioningBasedMetricDescriptor.Keys

public static final String

PARTITION_ID_FIELD_NAME

"org.carrot2.output.metrics.IdealPartitioningBasedMetric.partitionIdFieldName"

org.carrot2.output.metrics.NormalizedMutualInformationMetricDescriptor

public final String	bindableClassName	"org.carrot2.output.metrics.NormalizedMutualInformationMetric"
public final String	description	"<p> Metrics will be calculated only if all input documents have non-blank <code>Document.PARTITIONS</code>. </p>"
public final String	label	""
public final String	prefix	""
public final String	title	"Computes Normalized Mutual Information (NMI) metric for the cluster set"

org.carrot2.output.metrics.NormalizedMutualInformationMetricDescriptor.Keys

public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENTS	"documents"
public static final String	ENABLED	"org.carrot2.output.metrics.NormalizedMutualInformationMetric.enabled"
public static final String	NORMALIZED_MUTUAL_INFORMATION	"org.carrot2.output.metrics.NormalizedMutualInformationMetric.normalizedMutualInformation"

org.carrot2.output.metrics.PrecisionRecallMetric

public static final String

BEST_F_MEASURE_PARTITION

"best-f-measure-partition"

org.carrot2.output.metrics.PrecisionRecallMetricDescriptor

public final String	bindableClassName	"org.carrot2.output.metrics.PrecisionRecallMetric"
public final String	description	"<p> Metrics will be calculated only if all input documents have non-blank <code>Document.PARTITIONS</code>. </p>"
public final String	label	""
public final String	prefix	""
public final String	title	"Computes precision, recall and F-metric for all partitions against the provided clusters"

org.carrot2.output.metrics.PrecisionRecallMetricDescriptor.Keys

public static final String	CLUSTERS	"clusters"
public static final String	DOCUMENTS	"documents"
public static final String	ENABLED	"org.carrot2.output.metrics.PrecisionRecallMetric.enabled"
public static final String	F_MEASURE_BY_PARTITION	"org.carrot2.output.metrics.PrecisionRecallMetric.fMeasureByPartition"
public static final String	PRECISION_BY_PARTITION	"org.carrot2.output.metrics.PrecisionRecallMetric.precisionByPartition"
public static final String	RECALL_BY_PARTITION	"org.carrot2.output.metrics.PrecisionRecallMetric.recallByPartition"
public static final String	WEIGHTED_AVERAGE_F_MEASURE	"org.carrot2.output.metrics.PrecisionRecallMetric.weightedAverageFMeasure"
public static final String	WEIGHTED_AVERAGE_PRECISION	"org.carrot2.output.metrics.PrecisionRecallMetric.weightedAveragePrecision"
public static final String	WEIGHTED_AVERAGE_RECALL	"org.carrot2.output.metrics.PrecisionRecallMetric.weightedAverageRecall"

org.carrot2.source.MultipageSearchEngineDescriptor

public final String	bindableClassName	"org.carrot2.source.MultipageSearchEngine"
public final String	description	"This class implements helper methods for concurrent querying of search services that limit the number of search results returned in one request."
public final String	label	""
public final String	prefix	""
public final String	title	"A base class facilitating implementation of <code>IDocumentSource</code>s wrapping external search engines with remote/ network-based interfaces"

org.carrot2.source.MultipageSearchEngineDescriptor.Keys

public static final String

SEARCH_MODE

"search-mode"

org.carrot2.source.SearchEngineBaseDescriptor

public final String	bindableClassName	"org.carrot2.source.SearchEngineBase"
public final String	description	"The base class defines the common attribute fields used by more specific base classes and concrete implementations."
public final String	label	""
public final String	prefix	"SearchEngineBase"
public final String	title	"A base class facilitating implementation of <code>IDocumentSource</code>s wrapping external search engines with remote/ network-based interfaces"

org.carrot2.source.SearchEngineBaseDescriptor.Keys

public static final String	COMPRESSED	"SearchEngineBase.compressed"
public static final String	DOCUMENTS	"documents"
public static final String	QUERY	"query"
public static final String	RESULTS	"results"
public static final String	RESULTS_TOTAL	"results-total"
public static final String	START	"start"

org.carrot2.source.SearchEngineResponse

public static final String	COMPRESSION_KEY	"compression"
public static final String	RESULTS_TOTAL_KEY	"resultsTotal"

org.carrot2.source.SearchEngineStatsDescriptor

public final String	bindableClassName	"org.carrot2.source.SearchEngineStats"
public final String	description	""
public final String	label	""
public final String	prefix	"SearchEngineStats"
public final String	title	"Usage statistics for an instance of <code>MultipageSearchEngine</code>"

org.carrot2.source.SearchEngineStatsDescriptor.Keys

public static final String	PAGE_REQUESTS	"SearchEngineStats.pageRequests"
public static final String	QUERIES	"SearchEngineStats.queries"

org.carrot2.source.SimpleSearchEngineDescriptor

public final String	bindableClassName	"org.carrot2.source.SimpleSearchEngine"
public final String	description	"This implementation assumes that all requested results can be fetched from the search engine using one request."
public final String	label	""
public final String	prefix	""
public final String	title	"A base class facilitating implementation of <code>IDocumentSource</code>s wrapping external search engines with remote/ network-based interfaces"

org.carrot2.source.ambient.AmbientDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.ambient.AmbientDocumentSource"
public final String	description	"Ambient (AMBIgous ENTries) is a data set designed for evaluating subtopic information retrieval. It consists of 44 topics, each with a set of subtopics and a list of 100 ranked documents. For more information, please see <a href=\"http://credo.fub.it/ambient/\">Ambient home page</a>."
public final String	label	""
public final String	prefix	"AmbientDocumentSource"
public final String	title	"Serves documents from the Ambient test set"

org.carrot2.source.ambient.AmbientDocumentSourceDescriptor.Keys

public static final String	RESULTS	"results"
public static final String	RESULTS_TOTAL	"results-total"
public static final String	TOPIC	"AmbientDocumentSource.topic"

org.carrot2.source.ambient.FubDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.ambient.FubDocumentSource"
public final String	description	""
public final String	label	""
public final String	prefix	"FubDocumentSource"
public final String	title	"A base document source for test collections developed at Fondazione Ugo Bordoni"

org.carrot2.source.ambient.FubDocumentSourceDescriptor.Keys

public static final String	DOCUMENTS	"documents"
public static final String	MIN_TOPIC_SIZE	"FubDocumentSource.minTopicSize"
public static final String	QUERY	"query"
public static final String	TOPIC_IDS	"FubDocumentSource.topicIds"

org.carrot2.source.ambient.Odp239DocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.ambient.Odp239DocumentSource"
public final String	description	"For more details, please see: http://credo.fub.it/odp239/."
public final String	label	""
public final String	prefix	"Odp239DocumentSource"
public final String	title	"Serves documents from the ODP239 test set"

org.carrot2.source.ambient.Odp239DocumentSourceDescriptor.Keys

public static final String	RESULTS	"results"
public static final String	RESULTS_TOTAL	"results-total"
public static final String	TOPIC	"Odp239DocumentSource.topic"

org.carrot2.source.etools.EToolsDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.etools.EToolsDocumentSource"
public final String	description	"For commercial licensing of the eTools feed, please e-mail: <code>contact@comcepta.com</code>."
public final String	label	""
public final String	prefix	"EToolsDocumentSource"
public final String	title	"A Carrot2 input component for the eTools service (http://www.etools.ch)"

org.carrot2.source.etools.EToolsDocumentSourceDescriptor.Keys

public static final String	COUNTRY	"EToolsDocumentSource.country"
public static final String	DATA_SOURCES	"EToolsDocumentSource.dataSources"
public static final String	LANGUAGE	"EToolsDocumentSource.language"
public static final String	PARTNER_ID	"EToolsDocumentSource.partnerId"
public static final String	SAFE_SEARCH	"EToolsDocumentSource.safeSearch"
public static final String	SERVICE_URL_BASE	"EToolsDocumentSource.serviceUrlBase"
public static final String	TIMEOUT	"EToolsDocumentSource.timeout"

org.carrot2.source.google.GoogleDesktopDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.google.GoogleDesktopDocumentSource"
public final String	description	""
public final String	label	""
public final String	prefix	"GoogleDesktopDocumentSource"
public final String	title	"Fetches documents from an instance of Google Desktop search engine"

org.carrot2.source.google.GoogleDesktopDocumentSourceDescriptor.Keys

public static final String	KEEP_HIGHLIGHTS	"GoogleDesktopDocumentSource.keepHighlights"
public static final String	QUERY_URL	"GoogleDesktopDocumentSource.queryUrl"

org.carrot2.source.google.GoogleDocumentSource

public static final String

CARROTSEARCH_API_KEY

"ABQIAAAA_XmITjrzoipJYoBApAgGJhS8yIvkL4-1sNwOJWkV7nbkjq_Z_BQW0-uzOh5lKXRtEXQDTGbzIEz06Q"

org.carrot2.source.google.GoogleDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.google.GoogleDocumentSource"
public final String	description	"Please note that this document source cannot deliver more than 32 search results."
public final String	label	""
public final String	prefix	"GoogleDocumentSource"
public final String	title	"A <code>IDocumentSource</code> fetching search results from Google JSON API"

org.carrot2.source.google.GoogleDocumentSourceDescriptor.Keys

public static final String	API_KEY	"GoogleDocumentSource.apiKey"
public static final String	KEEP_HIGHLIGHTS	"GoogleDocumentSource.keepHighlights"
public static final String	REFERER	"GoogleDocumentSource.referer"
public static final String	SERVICE_URL	"GoogleDocumentSource.serviceUrl"

org.carrot2.source.idol.IdolDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.idol.IdolDocumentSource"
public final String	description	"Please note that you will need to install an XSLT stylesheet in your IDOL instance that transforms the search results into the OpenSearch format. The XSLT stylesheet is available under the <tt>org.carrot2.source.idol</tt> package, next to the binaries of this class. <p> Based on code donated by Julien Nioche. Autonomy IDOL support contributed by James Sealey. </p>"
public final String	label	""
public final String	prefix	"IdolDocumentSource"
public final String	title	"A <code>IDocumentSource</code> fetching <code>Document</code>s (search results) from an IDOL Search Engine"

org.carrot2.source.idol.IdolDocumentSourceDescriptor.Keys

public static final String	IDOL_SERVER_NAME	"IdolDocumentSource.idolServerName"
public static final String	IDOL_SERVER_PORT	"IdolDocumentSource.idolServerPort"
public static final String	MAXIMUM_RESULTS	"IdolDocumentSource.maximumResults"
public static final String	MIN_SCORE	"IdolDocumentSource.minScore"
public static final String	OTHER_SEARCH_ATTRIBUTES	"IdolDocumentSource.otherSearchAttributes"
public static final String	RESULTS_PER_PAGE	"IdolDocumentSource.resultsPerPage"
public static final String	USER_AGENT	"IdolDocumentSource.userAgent"
public static final String	USER_NAME	"IdolDocumentSource.userName"
public static final String	XSL_TEMPLATE_NAME	"IdolDocumentSource.xslTemplateName"

org.carrot2.source.lucene.LuceneDocumentSource

public static final String

LUCENE_DOCUMENT_FIELD

"luceneDocument"

org.carrot2.source.lucene.LuceneDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.lucene.LuceneDocumentSource"
public final String	description	"The index should be binary-compatible with the Lucene version actually imported by this plugin."
public final String	label	""
public final String	prefix	"LuceneDocumentSource"
public final String	title	"A <code>IDocumentSource</code> fetching <code>Document</code>s from a local Apache Lucene index"

org.carrot2.source.lucene.LuceneDocumentSourceDescriptor.Keys

public static final String	ANALYZER	"LuceneDocumentSource.analyzer"
public static final String	DIRECTORY	"LuceneDocumentSource.directory"
public static final String	DOCUMENTS	"documents"
public static final String	FIELD_MAPPER	"LuceneDocumentSource.fieldMapper"
public static final String	KEEP_LUCENE_DOCUMENTS	"LuceneDocumentSource.keepLuceneDocuments"
public static final String	QUERY	"query"
public static final String	RESULTS	"results"
public static final String	RESULTS_TOTAL	"results-total"

org.carrot2.source.lucene.SimpleFieldMapperDescriptor

public final String	bindableClassName	"org.carrot2.source.lucene.SimpleFieldMapper"
public final String	description	""
public final String	label	""
public final String	prefix	""
public final String	title	"A simple <code>IFieldMapper</code> with one-to-one mapping between the default title, url and summary fields"

org.carrot2.source.lucene.SimpleFieldMapperDescriptor.Keys

public static final String	CONTENT_FIELD	"org.carrot2.source.lucene.SimpleFieldMapper.contentField"
public static final String	CONTEXT_FRAGMENTS	"org.carrot2.source.lucene.SimpleFieldMapper.contextFragments"
public static final String	FORMATTER	"org.carrot2.source.lucene.SimpleFieldMapper.formatter"
public static final String	FRAGMENT_JOIN	"org.carrot2.source.lucene.SimpleFieldMapper.fragmentJoin"
public static final String	SEARCH_FIELDS	"org.carrot2.source.lucene.SimpleFieldMapper.searchFields"
public static final String	TITLE_FIELD	"org.carrot2.source.lucene.SimpleFieldMapper.titleField"
public static final String	URL_FIELD	"org.carrot2.source.lucene.SimpleFieldMapper.urlField"

org.carrot2.source.microsoft.Bing2DocumentSource

public static final String	CARROTSEARCH_APPID	"2679A5C568DC48B57628500D4024F83AD859633C"
protected static final int	MAX_CONCURRENT_THREADS	10

org.carrot2.source.microsoft.Bing2DocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.microsoft.Bing2DocumentSource"
public final String	description	"We model this into separate subclasses, specific to a particular request type (web, image, news). In theory one could request web and news results at once, but in practice this is difficult when paging is also needed (because they have different limits)."
public final String	label	""
public final String	prefix	"Bing2DocumentSource"
public final String	title	"A base <code>IDocumentSource</code> serving requests to Microsoft Bing API, version 2"

org.carrot2.source.microsoft.Bing2DocumentSourceDescriptor.Keys

public static final String	ADULT	"Bing2DocumentSource.adult"
public static final String	APPID	"Bing2DocumentSource.appid"
public static final String	MARKET	"Bing2DocumentSource.market"
public static final String	OPTIONS	"Bing2DocumentSource.options"

org.carrot2.source.microsoft.Bing2ImageDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.microsoft.Bing2ImageDocumentSource"
public final String	description	""
public final String	label	""
public final String	prefix	"Bing2ImageDocumentSource"
public final String	title	"Image search document source fetching from Bing using Bing2 API"

org.carrot2.source.microsoft.Bing2NewsDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.microsoft.Bing2NewsDocumentSource"
public final String	description	""
public final String	label	""
public final String	prefix	"Bing2NewsDocumentSource"
public final String	title	"News search specific document source fetching from Bing using Bing2 API"

org.carrot2.source.microsoft.Bing2NewsDocumentSourceDescriptor.Keys

public static final String

SORT_ORDER

"Bing2NewsDocumentSource.sortOrder"

org.carrot2.source.microsoft.Bing2WebDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.microsoft.Bing2WebDocumentSource"
public final String	description	""
public final String	label	""
public final String	prefix	"Bing2WebDocumentSource"
public final String	title	"Web search specific document source fetching from Bing using Bing2 API"

org.carrot2.source.microsoft.Bing2WebDocumentSourceDescriptor.Keys

public static final String	FILE_TYPES	"Bing2WebDocumentSource.fileTypes"
public static final String	SITE	"Bing2WebDocumentSource.site"
public static final String	WEB_OPTIONS	"Bing2WebDocumentSource.webOptions"

org.carrot2.source.opensearch.OpenSearchDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.opensearch.OpenSearchDocumentSource"
public final String	description	"<p> Based on code donated by Julien Nioche."
public final String	label	""
public final String	prefix	"OpenSearchDocumentSource"
public final String	title	"A <code>IDocumentSource</code> fetching <code>Document</code>s (search results) from an OpenSearch feed"

org.carrot2.source.opensearch.OpenSearchDocumentSourceDescriptor.Keys

public static final String	FEED_URL_PARAMS	"OpenSearchDocumentSource.feedUrlParams"
public static final String	FEED_URL_TEMPLATE	"OpenSearchDocumentSource.feedUrlTemplate"
public static final String	MAXIMUM_RESULTS	"OpenSearchDocumentSource.maximumResults"
public static final String	RESULTS_PER_PAGE	"OpenSearchDocumentSource.resultsPerPage"
public static final String	USER_AGENT	"OpenSearchDocumentSource.userAgent"

org.carrot2.source.pubmed.PubMedDocumentSource

public static final String	E_FETCH_URL	"http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi"
public static final String	E_SEARCH_URL	"http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
public static final int	PUBMED_TIMEOUT	24000

org.carrot2.source.pubmed.PubMedDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.pubmed.PubMedDocumentSource"
public final String	description	""
public final String	label	""
public final String	prefix	"PubMedDocumentSource"
public final String	title	"Performs searches on the PubMed database using its on-line e-utilities: http://eutils.ncbi.nlm.nih.gov/entrez/query/static/eutils_help.html"

org.carrot2.source.pubmed.PubMedDocumentSourceDescriptor.Keys

public static final String

MAX_RESULTS

"PubMedDocumentSource.maxResults"

org.carrot2.source.solr.SolrDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.solr.SolrDocumentSource"
public final String	description	""
public final String	label	""
public final String	prefix	"SolrDocumentSource"
public final String	title	"Fetches documents from an instance of Solr"

org.carrot2.source.solr.SolrDocumentSourceDescriptor.Keys

public static final String	SERVICE_URL_BASE	"SolrDocumentSource.serviceUrlBase"
public static final String	SOLR_SUMMARY_FIELD_NAME	"SolrDocumentSource.solrSummaryFieldName"
public static final String	SOLR_TITLE_FIELD_NAME	"SolrDocumentSource.solrTitleFieldName"
public static final String	SOLR_URL_FIELD_NAME	"SolrDocumentSource.solrUrlFieldName"

org.carrot2.source.xml.RemoteXmlSimpleSearchEngineBaseDescriptor

public final String	bindableClassName	"org.carrot2.source.xml.RemoteXmlSimpleSearchEngineBase"
public final String	description	"The XSLT stylesheet will be loaded once during component initialization and cached for all further requests."
public final String	label	""
public final String	prefix	""
public final String	title	"A base class for implementing data sources based on XML/XSLT"

org.carrot2.source.xml.XmlDocumentSourceDescriptor

public final String	bindableClassName	"org.carrot2.source.xml.XmlDocumentSource"
public final String	description	"For additional flexibility, an XSLT stylesheet can be applied to the XML stream before it is deserialized into Carrot2 data."
public final String	label	""
public final String	prefix	"XmlDocumentSource"
public final String	title	"Fetches documents from XML files and streams"

org.carrot2.source.xml.XmlDocumentSourceDescriptor.Keys

public static final String	DOCUMENTS	"documents"
public static final String	QUERY	"query"
public static final String	READ_ALL	"XmlDocumentSource.readAll"
public static final String	RESULTS	"results"
public static final String	TITLE	"processing-result.title"
public static final String	XML	"XmlDocumentSource.xml"
public static final String	XML_PARAMETERS	"XmlDocumentSource.xmlParameters"
public static final String	XSLT	"XmlDocumentSource.xslt"
public static final String	XSLT_PARAMETERS	"XmlDocumentSource.xsltParameters"

org.carrot2.source.xml.XmlDocumentSourceHelperDescriptor

public final String	bindableClassName	"org.carrot2.source.xml.XmlDocumentSourceHelper"
public final String	description	"This helper does note expose any attributes, so that different implementations can decide which attributes they expose."
public final String	label	""
public final String	prefix	"XmlDocumentSourceHelper"
public final String	title	"Exposes the common functionality a <code>IDocumentSource</code> based on XML/XSLT is likely to need"

org.carrot2.source.xml.XmlDocumentSourceHelperDescriptor.Keys

public static final String

TIMEOUT

"XmlDocumentSourceHelper.timeout"

org.carrot2.text.analysis.ITokenizer

public static final short	TF_COMMON_WORD	4096
public static final short	TF_QUERY_WORD	8192
public static final short	TF_SEPARATOR_DOCUMENT	512
public static final short	TF_SEPARATOR_FIELD	1024
public static final short	TF_SEPARATOR_SENTENCE	256
public static final short	TF_TERMINATOR	2048
public static final int	TT_ACRONYM	5
public static final int	TT_BARE_URL	7
public static final int	TT_EMAIL	4
public static final int	TT_EOF	-1
public static final int	TT_FILE	8
public static final int	TT_FULL_URL	6
public static final int	TT_HYPHTERM	9
public static final int	TT_NUMERIC	2
public static final int	TT_PUNCTUATION	3
public static final int	TT_TERM	1
public static final int	TYPE_MASK	15

org.carrot2.text.clustering.MultilingualClusteringDescriptor

public final String	bindableClassName	"org.carrot2.text.clustering.MultilingualClustering"
public final String	description	"The helper partitions the input documents by <code>org.carrot2.core.Document.LANGUAGE</code>, clusters each such monolingual partition separately and then aggregates the partial cluster lists based on the selected <code>LanguageAggregationStrategy</code>."
public final String	label	""
public final String	prefix	"MultilingualClustering"
public final String	title	"A helper for clustering multilingual collections of documents"

org.carrot2.text.clustering.MultilingualClusteringDescriptor.Keys

public static final String	DEFAULT_LANGUAGE	"MultilingualClustering.defaultLanguage"
public static final String	LANGUAGE_AGGREGATION_STRATEGY	"MultilingualClustering.languageAggregationStrategy"

org.carrot2.text.linguistic.DefaultLexicalDataFactoryDescriptor

public final String	bindableClassName	"org.carrot2.text.linguistic.DefaultLexicalDataFactory"
public final String	description	"Resources are read from disk, cached and shared between <b>all</b> threads using this class. Additional attributes control resource reloading and merging: <code>org.carrot2.text.linguistic.DefaultLexicalDataFactory.resourceLookup</code>, <code>org.carrot2.text.linguistic.DefaultLexicalDataFactory.reloadResources</code>, <code>org.carrot2.text.linguistic.DefaultLexicalDataFactory.mergeResources</code>."
public final String	label	""
public final String	prefix	""
public final String	title	"The default management of lexical resources"

org.carrot2.text.linguistic.DefaultLexicalDataFactoryDescriptor.Keys

public static final String	MERGE_RESOURCES	"merge-resources"
public static final String	RELOAD_RESOURCES	"reload-resources"
public static final String	RESOURCE_LOOKUP	"resource-lookup"

org.carrot2.text.linguistic.DefaultStemmerFactoryDescriptor

public final String	bindableClassName	"org.carrot2.text.linguistic.DefaultStemmerFactory"
public final String	description	""
public final String	label	""
public final String	prefix	""
public final String	title	""

org.carrot2.text.linguistic.DefaultTokenizerFactoryDescriptor

public final String	bindableClassName	"org.carrot2.text.linguistic.DefaultTokenizerFactory"
public final String	description	""
public final String	label	""
public final String	prefix	""
public final String	title	""

org.carrot2.text.linguistic.LexicalDataLoaderDescriptor

public final String	bindableClassName	"org.carrot2.text.linguistic.LexicalDataLoader"
public final String	description	""
public final String	label	""
public final String	prefix	""
public final String	title	"Common attributes related to loading and caching of lexical resources"

org.carrot2.text.linguistic.LexicalDataLoaderDescriptor.Keys

public static final String	RELOAD_RESOURCES	"reload-resources"
public static final String	RESOURCE_LOOKUP	"resource-lookup"

org.carrot2.text.preprocessing.CaseNormalizerDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.CaseNormalizer"
public final String	description	"The aim of case normalization is to find the most frequently appearing variants of words in terms of case. For example, if in the input documents <i>MacOS</i> appears 20 times, <i>Macos</i> 5 times and <i>macos</i> 2 times, case normalizer will select <i>MacOS</i> to represent all variants and assign the aggregated term frequency of 27 to it. <p> This class saves the following results to the <code>PreprocessingContext</code>: <ul> <li><code>AllTokens.wordIndex</code></li> <li><code>AllWords.image</code></li> <li><code>AllWords.tf</code></li> <li><code>AllWords.tfByDocument</code></li> </ul> <p> This class requires that <code>Tokenizer</code> be invoked first."
public final String	label	""
public final String	prefix	"CaseNormalizer"
public final String	title	"Performs case normalization and calculates a number of frequency statistics for words"

org.carrot2.text.preprocessing.CaseNormalizerDescriptor.Keys

public static final String

DF_THRESHOLD

"CaseNormalizer.dfThreshold"

org.carrot2.text.preprocessing.DocumentAssignerDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.DocumentAssigner"
public final String	description	"For each label candidate from <code>AllLabels.featureIndex</code> an <code>BitSet</code> with the assigned documents is constructed. The assignment algorithm is rather simple: in order to be assigned to a label, a document must contain at least one occurrence of each non-stop word from the label. <p> This class saves the following results to the <code>PreprocessingContext</code> : <ul> <li><code>AllLabels.documentIndices</code></li> </ul> <p> This class requires that <code>Tokenizer</code>, <code>CaseNormalizer</code>, <code>StopListMarker</code>, <code>PhraseExtractor</code> and <code>LabelFilterProcessor</code> be invoked first."
public final String	label	""
public final String	prefix	"DocumentAssigner"
public final String	title	"Assigns document to label candidates"

org.carrot2.text.preprocessing.DocumentAssignerDescriptor.Keys

public static final String	EXACT_PHRASE_ASSIGNMENT	"DocumentAssigner.exactPhraseAssignment"
public static final String	MIN_CLUSTER_SIZE	"DocumentAssigner.minClusterSize"

org.carrot2.text.preprocessing.LabelFilterProcessorDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.LabelFilterProcessor"
public final String	description	"Filtering is applied to <code>AllWords</code> and <code>AllPhrases</code>, the results are saved to <code>AllLabels</code>. Currently, the following filters are applied: <ol> <li><code>StopWordLabelFilter</code></li> <li><code>CompleteLabelFilter</code></li> </ol> This class saves the following results to the <code>PreprocessingContext</code>: <ul> <li><code>AllLabels.featureIndex</code></li> </ul> <p> This class requires that <code>Tokenizer</code>, <code>CaseNormalizer</code>, <code>StopListMarker</code> and <code>PhraseExtractor</code> be invoked first."
public final String	label	""
public final String	prefix	"LabelFilterProcessor"
public final String	title	"Applies basic filtering to words and phrases to produce candidates for cluster labels"

org.carrot2.text.preprocessing.LabelFormatterDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.LabelFormatter"
public final String	description	""
public final String	label	""
public final String	prefix	""
public final String	title	"Formats cluster labels for final rendering"

org.carrot2.text.preprocessing.LanguageModelStemmerDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.LanguageModelStemmer"
public final String	description	"<p> This class saves the following results to the <code>PreprocessingContext</code>: <ul> <li><code>AllWords.stemIndex</code></li> <li><code>AllStems.image</code></li> <li><code>AllStems.mostFrequentOriginalWordIndex</code></li> <li><code>AllStems.tf</code></li> <li><code>AllStems.tfByDocument</code></li> <li><code>AllWords.type</code> is populated with <code>ITokenizer.TF_QUERY_WORD</code></li> </ul> This class requires that <code>Tokenizer</code> and <code>CaseNormalizer</code> be invoked first."
public final String	label	""
public final String	prefix	"LanguageModelStemmer"
public final String	title	"Applies stemming to words and calculates a number of frequency statistics for stems"

org.carrot2.text.preprocessing.PhraseExtractorDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.PhraseExtractor"
public final String	description	"A frequent phrase is a sequence of words that appears in the documents more than once. This phrase extractor aggregates different inflection variants of phrase words into one phrase, returning the most frequent variant. For example, if phrase <i>computing science</i> appears 2 times and <i>computer sciences</i> appears 4 times, the latter will be returned with aggregated frequency of 6. <p> This class saves the following results to the <code>PreprocessingContext</code>: <ul> <li><code>AllPhrases.wordIndices</code></li> <li><code>AllPhrases.tf</code></li> <li><code>AllPhrases.tfByDocument</code></li> <li><code>AllTokens.suffixOrder</code></li> <li><code>AllTokens.lcp</code></li> </ul> <p> This class requires that <code>Tokenizer</code>, <code>CaseNormalizer</code> and <code>LanguageModelStemmer</code> be invoked first."
public final String	label	""
public final String	prefix	"PhraseExtractor"
public final String	title	"Extracts frequent phrases from the provided document"

org.carrot2.text.preprocessing.PhraseExtractorDescriptor.Keys

public static final String

DF_THRESHOLD

"PhraseExtractor.dfThreshold"

org.carrot2.text.preprocessing.StopListMarkerDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.StopListMarker"
public final String	description	"<p> This class saves the following results to the <code>PreprocessingContext</code>: <ul> <li><code>AllWords.type</code></li> </ul> <p> This class requires that <code>Tokenizer</code> and <code>CaseNormalizer</code> be invoked first."
public final String	label	""
public final String	prefix	"StopListMarker"
public final String	title	"Marks stop words based on the current language model"

org.carrot2.text.preprocessing.TokenizerDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.Tokenizer"
public final String	description	"<p> This class saves the following results to the <code>PreprocessingContext</code>: <ul> <li><code>AllTokens.image</code></li> <li><code>AllTokens.documentIndex</code></li> <li><code>AllTokens.fieldIndex</code></li> <li><code>AllTokens.type</code></li> </ul>"
public final String	label	""
public final String	prefix	"Tokenizer"
public final String	title	"Performs tokenization of documents"

org.carrot2.text.preprocessing.TokenizerDescriptor.Keys

public static final String

DOCUMENT_FIELDS

"Tokenizer.documentFields"

org.carrot2.text.preprocessing.filter.CompleteLabelFilterDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.filter.CompleteLabelFilter"
public final String	description	"<p> See <a href=\"http://project.carrot2.org/publications/osinski-2003-lingo.pdf\">this document</a>, page 31 for a definition of a complete phrase."
public final String	label	""
public final String	prefix	"CompleteLabelFilter"
public final String	title	"A filter that removes \"incomplete\" labels"

org.carrot2.text.preprocessing.filter.CompleteLabelFilterDescriptor.Keys

public static final String	ENABLED	"CompleteLabelFilter.enabled"
public static final String	LABEL_OVERRIDE_THRESHOLD	"CompleteLabelFilter.labelOverrideThreshold"

org.carrot2.text.preprocessing.filter.GenitiveLabelFilterDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.filter.GenitiveLabelFilter"
public final String	description	""
public final String	label	""
public final String	prefix	"GenitiveLabelFilter"
public final String	title	"Accepts labels that do not end in words in the Saxon Genitive form (e.g. \"Threatening the Country\'s\")"

org.carrot2.text.preprocessing.filter.GenitiveLabelFilterDescriptor.Keys

public static final String

ENABLED

"GenitiveLabelFilter.enabled"

org.carrot2.text.preprocessing.filter.MinLengthLabelFilterDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.filter.MinLengthLabelFilter"
public final String	description	""
public final String	label	""
public final String	prefix	"MinLengthLabelFilter"
public final String	title	"Accepts labels whose length in characters is greater or equal to the provided value"

org.carrot2.text.preprocessing.filter.MinLengthLabelFilterDescriptor.Keys

public static final String

ENABLED

"MinLengthLabelFilter.enabled"

org.carrot2.text.preprocessing.filter.NumericLabelFilterDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.filter.NumericLabelFilter"
public final String	description	""
public final String	label	""
public final String	prefix	"NumericLabelFilter"
public final String	title	"Accepts labels that do not consist only of numeric tokens and start with a non-numeric token"

org.carrot2.text.preprocessing.filter.NumericLabelFilterDescriptor.Keys

public static final String

ENABLED

"NumericLabelFilter.enabled"

org.carrot2.text.preprocessing.filter.QueryLabelFilterDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.filter.QueryLabelFilter"
public final String	description	""
public final String	label	""
public final String	prefix	"QueryLabelFilter"
public final String	title	"Accepts labels that do not consist only of query words"

org.carrot2.text.preprocessing.filter.QueryLabelFilterDescriptor.Keys

public static final String

ENABLED

"QueryLabelFilter.enabled"

org.carrot2.text.preprocessing.filter.StopLabelFilterDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.filter.StopLabelFilter"
public final String	description	""
public final String	label	""
public final String	prefix	"StopLabelFilter"
public final String	title	"Accepts labels that are not declared as stop labels in the stoplabels.<lang> files"

org.carrot2.text.preprocessing.filter.StopLabelFilterDescriptor.Keys

public static final String

ENABLED

"StopLabelFilter.enabled"

org.carrot2.text.preprocessing.filter.StopWordLabelFilterDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.filter.StopWordLabelFilter"
public final String	description	""
public final String	label	""
public final String	prefix	"StopWordLabelFilter"
public final String	title	"Accepts words that are not stop words and phrases that do not start nor end in a stop word"

org.carrot2.text.preprocessing.filter.StopWordLabelFilterDescriptor.Keys

public static final String

ENABLED

"StopWordLabelFilter.enabled"

org.carrot2.text.preprocessing.pipeline.BasicPreprocessingPipelineDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.pipeline.BasicPreprocessingPipeline"
public final String	description	"The preprocessing consists of the following steps: <ol> <li><code>Tokenizer.tokenize(PreprocessingContext)</code></li> <li><code>CaseNormalizer.normalize(PreprocessingContext)</code></li> <li><code>LanguageModelStemmer.stem(PreprocessingContext)</code></li> <li><code>StopListMarker.mark(PreprocessingContext)</code></li> </ol>"
public final String	label	""
public final String	prefix	"PreprocessingPipeline"
public final String	title	"Performs basic preprocessing steps on the provided documents"

org.carrot2.text.preprocessing.pipeline.BasicPreprocessingPipelineDescriptor.Keys

public static final String	LEXICAL_DATA_FACTORY	"PreprocessingPipeline.lexicalDataFactory"
public static final String	STEMMER_FACTORY	"PreprocessingPipeline.stemmerFactory"
public static final String	TOKENIZER_FACTORY	"PreprocessingPipeline.tokenizerFactory"

org.carrot2.text.preprocessing.pipeline.CompletePreprocessingPipelineDescriptor

public final String	bindableClassName	"org.carrot2.text.preprocessing.pipeline.CompletePreprocessingPipeline"
public final String	description	"The preprocessing consists of the following steps: <ol> <li><code>Tokenizer.tokenize(PreprocessingContext)</code></li> <li><code>CaseNormalizer.normalize(PreprocessingContext)</code></li> <li><code>LanguageModelStemmer.stem(PreprocessingContext)</code></li> <li><code>StopListMarker.mark(PreprocessingContext)</code></li> <li><code>PhraseExtractor.extractPhrases(PreprocessingContext)</code></li> <li><code>LabelFilterProcessor.process(PreprocessingContext)</code></li> <li><code>DocumentAssigner.assign(PreprocessingContext)</code></li> </ol>"
public final String	label	""
public final String	prefix	"PreprocessingPipeline"
public final String	title	"Performs a complete preprocessing on the provided documents"

org.carrot2.text.suffixtree.SuffixTree

public static final int

NO_EDGE

-1

org.carrot2.text.vsm.TermDocumentMatrixBuilderDescriptor

public final String	bindableClassName	"org.carrot2.text.vsm.TermDocumentMatrixBuilder"
public final String	description	""
public final String	label	""
public final String	prefix	"TermDocumentMatrixBuilder"
public final String	title	"Builds a term document matrix based on the provided <code>PreprocessingContext</code>"

org.carrot2.text.vsm.TermDocumentMatrixBuilderDescriptor.Keys

public static final String	MAX_WORD_DF	"TermDocumentMatrixBuilder.maxWordDf"
public static final String	MAXIMUM_MATRIX_SIZE	"TermDocumentMatrixBuilder.maximumMatrixSize"
public static final String	TERM_WEIGHTING	"TermDocumentMatrixBuilder.termWeighting"
public static final String	TITLE_WORDS_BOOST	"TermDocumentMatrixBuilder.titleWordsBoost"

org.carrot2.text.vsm.TermDocumentMatrixReducerDescriptor

public final String	bindableClassName	"org.carrot2.text.vsm.TermDocumentMatrixReducer"
public final String	description	""
public final String	label	""
public final String	prefix	"TermDocumentMatrixReducer"
public final String	title	"Reduces the dimensionality of a term-document matrix using a matrix factorization algorithm"

org.carrot2.text.vsm.TermDocumentMatrixReducerDescriptor.Keys

public static final String	FACTORIZATION_FACTORY	"TermDocumentMatrixReducer.factorizationFactory"
public static final String	FACTORIZATION_QUALITY	"TermDocumentMatrixReducer.factorizationQuality"

org.carrot2.util.RollingWindowAverage

public static final int	MILLIS	1
public static final int	MINUTE	60000
public static final int	SECOND	1000

org.carrot2.util.httpclient.HttpClientFactory

public static final int

DEFAULT_TIMEOUT

8000

org.carrot2.util.xslt.TemplatesPool

public static final String

TEMPLATE_CACHING_PROPERTY

"template.caching"

org.carrot2.util.xsltfilter.XSLTFilterConstants

public static final String	NO_XSLT_PROCESSING	"xslt.filter:disable"
public static final String	XSLT_PARAMS_MAP	"xslt.filter:stylesheet-params"