public class WebThesaurusMap extends java.lang.Object implements IThesaurusMap<java.lang.String,java.lang.String>
Constructor and Description |
---|
WebThesaurusMap() |
WebThesaurusMap(java.io.File dbConfigurationFile) |
WebThesaurusMap(java.io.File dbConfigurationFile,
java.io.File tunnelConfigurationFile) |
WebThesaurusMap(java.lang.String dbConfigurationFile) |
Modifier and Type | Method and Description |
---|---|
boolean |
connect()
Connects to the data source
|
void |
destroy()
Ends the connection to the data source
|
java.lang.Long |
getContextsCount(java.lang.String key)
Get the context count from the corpus
|
java.util.Map<java.lang.String,java.lang.Double> |
getContextsTermScores(java.lang.String key)
Get all term-context scores for a given context
|
java.util.Map<java.lang.String,java.lang.Double> |
getContextsTermScores(java.lang.String key,
double threshold)
Get all term-context scores for a given context, using a score threshold
|
java.util.Map<java.lang.String,java.lang.Double> |
getContextsTermScores(java.lang.String key,
int numberOfEntries)
Get the top n term-context scores for a given context
|
java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>> |
getIsas(java.lang.String key)
Get all senses for the input term, using the standard sense type
|
java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>> |
getIsas(java.lang.String key,
java.lang.String type)
Get all senses for the input term, with a specified sense type
|
java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>> |
getSenseCUIs(java.lang.String key)
Get all senses for the input term, using the standard sense type
|
java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>> |
getSenseCUIs(java.lang.String key,
java.lang.String type)
Get all senses for the input term, with a specified sense type
|
java.util.Map<java.lang.Integer,java.util.List<java.lang.String>> |
getSenses(java.lang.String key)
Get all senses for the input term, using the standard sense type
|
java.util.Map<java.lang.Integer,java.util.List<java.lang.String>> |
getSenses(java.lang.String key,
java.lang.String type)
Get all senses for the input term, with a specified sense type
|
java.lang.String[] |
getSensesTypes()
Get all possible sense types available
|
java.util.Map<java.lang.String,java.lang.Double> |
getSimilarContexts(java.lang.String values)
Get a list of all similar contexts for a given context
|
java.util.Map<java.lang.String,java.lang.Double> |
getSimilarContexts(java.lang.String values,
double threshold)
Get a list of all similar contexts for a given context, minimal similarity score is specified
|
java.util.Map<java.lang.String,java.lang.Double> |
getSimilarContexts(java.lang.String values,
int numberOfEntries)
Get a list of all similar contexts for a given context, maximal number is specified
|
java.util.Map<java.lang.String,java.lang.Double> |
getSimilarTerms(java.lang.String key)
Get a list of all similar terms for a given term.
|
java.util.Map<java.lang.String,java.lang.Double> |
getSimilarTerms(java.lang.String key,
double threshold)
Get a list of similar terms for a given term, minimal similarity score is specified
|
java.util.Map<java.lang.String,java.lang.Double> |
getSimilarTerms(java.lang.String key,
int numberOfEntries)
Get a list of similar terms for a given term, maximal number is specified
|
java.lang.Double |
getSimilarTermScore(java.lang.String t1,
java.lang.String t2)
Retrieve the similarity score between two terms.
|
java.lang.String |
getStandardSense()
Get the name of the standard sense inventory type
|
java.util.Map<java.lang.String,java.lang.Double> |
getStringDoubleMap(java.util.List<org.apache.pig.impl.util.Pair<java.lang.String,java.lang.Double>> set) |
java.lang.Long |
getTermContextsCount(java.lang.String key,
java.lang.String val)
Get the term-context count from the corpus
|
java.lang.Double |
getTermContextsScore(java.lang.String key,
java.lang.String val)
Get the significance score of a term-context combination
|
java.util.Map<java.lang.String,java.lang.Double> |
getTermContextsScores(java.lang.String key)
Get all term-context scores for a given term
|
java.util.Map<java.lang.String,java.lang.Double> |
getTermContextsScores(java.lang.String key,
double threshold)
Get all term-context scores for a given term, using a score threshold
|
java.util.Map<java.lang.String,java.lang.Double> |
getTermContextsScores(java.lang.String key,
int numberOfEntries)
Get the top n term-context scores for a given term
|
java.lang.Long |
getTermCount(java.lang.String key)
Get the term count from the corpus
|
java.lang.String[] |
isContextsContained(java.lang.String... key)
Checks which contexts from the input list are contained in the resource
|
boolean |
isContextsContained(java.lang.String key)
Checks whether the context is contained in the resource
|
java.lang.String[] |
isTermContained(java.lang.String... key)
Checks whether a list of terms is contained in the resource
|
boolean |
isTermContained(java.lang.String key)
Checks whether the term is contained in the resource
|
public WebThesaurusMap(java.io.File dbConfigurationFile)
public WebThesaurusMap(java.lang.String dbConfigurationFile)
public WebThesaurusMap(java.io.File dbConfigurationFile, java.io.File tunnelConfigurationFile)
public WebThesaurusMap()
public boolean connect()
IThesaurus
connect
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
public void destroy()
IThesaurus
destroy
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
public java.lang.Long getTermCount(java.lang.String key)
IThesaurus
getTermCount
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termpublic java.lang.Long getContextsCount(java.lang.String key)
IThesaurus
getContextsCount
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input contextpublic java.lang.Long getTermContextsCount(java.lang.String key, java.lang.String val)
IThesaurus
getTermContextsCount
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termval
- the input contextpublic java.lang.Double getTermContextsScore(java.lang.String key, java.lang.String val)
IThesaurus
getTermContextsScore
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termval
- the input contextpublic java.util.Map<java.lang.String,java.lang.Double> getSimilarTerms(java.lang.String key)
IThesaurus
getSimilarTerms
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termpublic java.util.Map<java.lang.String,java.lang.Double> getSimilarTerms(java.lang.String key, int numberOfEntries)
IThesaurus
getSimilarTerms
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termnumberOfEntries
- the maximal number of items to retrievepublic java.util.Map<java.lang.String,java.lang.Double> getSimilarTerms(java.lang.String key, double threshold)
IThesaurus
getSimilarTerms
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termthreshold
- the minimal similarity scorepublic java.util.Map<java.lang.String,java.lang.Double> getSimilarContexts(java.lang.String values)
IThesaurus
getSimilarContexts
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
values
- the input contextpublic java.util.Map<java.lang.String,java.lang.Double> getSimilarContexts(java.lang.String values, int numberOfEntries)
IThesaurus
getSimilarContexts
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
values
- the input contextnumberOfEntries
- the maximal number of items to retrievepublic java.util.Map<java.lang.String,java.lang.Double> getSimilarContexts(java.lang.String values, double threshold)
IThesaurus
getSimilarContexts
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
values
- the input contextthreshold
- the minimal similarity scorepublic java.util.Map<java.lang.String,java.lang.Double> getTermContextsScores(java.lang.String key)
IThesaurus
getTermContextsScores
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termpublic java.util.Map<java.lang.String,java.lang.Double> getTermContextsScores(java.lang.String key, int numberOfEntries)
IThesaurus
getTermContextsScores
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termnumberOfEntries
- the maximum number of entries to returnpublic java.util.Map<java.lang.String,java.lang.Double> getTermContextsScores(java.lang.String key, double threshold)
IThesaurus
getTermContextsScores
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termthreshold
- the minimal significance scorepublic java.util.Map<java.lang.String,java.lang.Double> getStringDoubleMap(java.util.List<org.apache.pig.impl.util.Pair<java.lang.String,java.lang.Double>> set)
public java.util.Map<java.lang.Integer,java.util.List<java.lang.String>> getSenses(java.lang.String key, java.lang.String type)
IThesaurus
getSenses
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termtype
- the required sense typepublic java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>> getIsas(java.lang.String key, java.lang.String type)
IThesaurus
getIsas
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termtype
- the required sense typepublic java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>> getSenseCUIs(java.lang.String key, java.lang.String type)
IThesaurus
getSenseCUIs
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termtype
- the required sense typepublic java.lang.Double getSimilarTermScore(java.lang.String t1, java.lang.String t2)
IThesaurus
getSimilarTermScore
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
t1
- term1t2
- term2public java.util.Map<java.lang.String,java.lang.Double> getContextsTermScores(java.lang.String key)
IThesaurus
getContextsTermScores
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input contextpublic java.util.Map<java.lang.String,java.lang.Double> getContextsTermScores(java.lang.String key, int numberOfEntries)
IThesaurus
getContextsTermScores
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input contextnumberOfEntries
- the maximum number of entries to returnpublic java.util.Map<java.lang.String,java.lang.Double> getContextsTermScores(java.lang.String key, double threshold)
IThesaurus
getContextsTermScores
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input contextthreshold
- the minimal significance scorepublic java.util.Map<java.lang.Integer,java.util.List<java.lang.String>> getSenses(java.lang.String key)
IThesaurus
getSenses
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termpublic java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>> getIsas(java.lang.String key)
IThesaurus
getIsas
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termpublic java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>> getSenseCUIs(java.lang.String key)
IThesaurus
getSenseCUIs
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input termpublic java.lang.String[] getSensesTypes()
IThesaurus
getSensesTypes
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
public java.lang.String getStandardSense()
IThesaurus
getStandardSense
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
public boolean isTermContained(java.lang.String key)
IThesaurus
isTermContained
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- input termpublic java.lang.String[] isTermContained(java.lang.String... key)
IThesaurus
isTermContained
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- list of input terms that should be checkedpublic boolean isContextsContained(java.lang.String key)
IThesaurus
isContextsContained
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- the input contextpublic java.lang.String[] isContextsContained(java.lang.String... key)
IThesaurus
isContextsContained
in interface IThesaurus<java.lang.String,java.lang.String,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.String,java.lang.Double>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>,java.util.Map<java.lang.Integer,java.util.List<java.lang.String>>,java.util.Map<java.lang.Integer,java.util.Map<java.lang.String,java.lang.Double>>>
key
- list of contexts that are checked