org.wandora.application.tools.extractors.umbel

Class AbstractUmbelExtractor

java.lang.Object

org.wandora.application.tools.AbstractWandoraTool

org.wandora.application.tools.extractors.AbstractExtractor

org.wandora.application.tools.extractors.umbel.AbstractUmbelExtractor

All Implemented Interfaces:

java.io.Serializable, java.lang.Runnable, BrowserPluginExtractor, DropExtractor, WandoraTool, WandoraToolLogger, Handler, InterruptHandler, TopicMapLogger

Direct Known Subclasses:

AbstractUmbelRelationExtractor, UmbelGetConcept

public abstract class AbstractUmbelExtractor
extends AbstractExtractor

Author:

akivela

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static boolean	ADD_DISTANCE_AS_PLAYER
private java.lang.String[]	contentTypes
protected static java.lang.String	csvEncoding
protected static char	csvLineSeparator
protected static char	csvStringCharacter
protected static char	csvValueSeparator
static int	FILE_CONTAINS_PLAIN_UMBEL_CONCEPT
static int	FILE_CONTAINS_UMBEL_CONCEPT_URLS
static int	FILE_IS_CSV_OF_UMBEL_CONCEPTS
static int	fileProcessor
static int	filterDistancesBelow
static boolean	getOnlyImmediateNeighbours
static java.lang.String	LANG
static java.lang.String	UMBEL_ALT_LABEL_URI
static java.lang.String	UMBEL_BROADER_NARROWER_TYPE_NAME
static java.lang.String	UMBEL_BROADER_NARROWER_TYPE_SI
static java.lang.String	UMBEL_BROADER_TYPE_NAME
static java.lang.String	UMBEL_BROADER_TYPE_SI
static java.lang.String[]	UMBEL_BROADER_URI
static java.lang.String	UMBEL_CONCEPT_STRING_SPLITTER
static java.lang.String	UMBEL_CONCEPT_TYPE_NAME
static java.lang.String	UMBEL_CONCEPT_TYPE_SI
static java.lang.String	UMBEL_CONCEPT_URI_BASE
static java.lang.String	UMBEL_DEFINITION_URI
static java.lang.String	UMBEL_DISJOINT_TYPE_NAME
static java.lang.String	UMBEL_DISJOINT_TYPE_SI
static java.lang.String[]	UMBEL_DISJOINT_URI
static java.lang.String	UMBEL_DISTANCE_TYPE_NAME
static java.lang.String	UMBEL_DISTANCE_TYPE_SI
static java.lang.String	UMBEL_NARROWER_TYPE_NAME
static java.lang.String	UMBEL_NARROWER_TYPE_SI
static java.lang.String[]	UMBEL_NARROWER_URI
static java.lang.String	UMBEL_PREF_LABEL_URI
static java.lang.String	UMBEL_SUBCLASS_TYPE_NAME
static java.lang.String	UMBEL_SUBCLASS_TYPE_SI
static java.lang.String[]	UMBEL_SUBCLASS_URI
static java.lang.String	UMBEL_SUPER_TYPE_URI_BASE
static java.lang.String	UMBEL_SUPERCLASS_SUBCLASS_TYPE_NAME
static java.lang.String	UMBEL_SUPERCLASS_SUBCLASS_TYPE_SI
static java.lang.String	UMBEL_SUPERCLASS_TYPE_NAME
static java.lang.String	UMBEL_SUPERCLASS_TYPE_SI
static java.lang.String[]	UMBEL_SUPERCLASS_URI
static java.lang.String	UMBEL_TYPE_NAME
static java.lang.String	UMBEL_TYPE_SI
static java.lang.String	UMBEL_TYPE_TYPE_NAME
static java.lang.String	UMBEL_TYPE_TYPE_SI
static java.lang.String[]	UMBEL_TYPE_URI
static boolean	useXTMSuperclassSubclassTopics

Fields inherited from class org.wandora.application.tools.extractors.AbstractExtractor

CUSTOM_EXTRACTOR, DONE_FAILED, DONE_MANY, DONE_ONE, EXACTLY_GIVEN_URLS, FILE_EXTRACTOR, FILE_PATTERN, GIVEN_URLS_AND_ALL_CRAWLED_DOCUMENTS, GIVEN_URLS_AND_CRAWLED_DOCUMENTS_IN_URL_DOMAIN, GIVEN_URLS_AND_LINKED_DOCUMENTS, GIVEN_URLS_AND_URL_BELOW, INFO_WAIT_WHILE_WORKING, LOG_TITLE, POINT_START_URL_TEXT, RAW_EXTRACTOR, SELECT_DIALOG_TITLE, STRING_EXTRACTOR_NOT_SUPPORTED_MESSAGE, URL_EXTRACTOR

Fields inherited from interface org.wandora.application.WandoraToolLogger

CLOSE, EXECUTE, INVISIBLE, VISIBLE, WAIT

Fields inherited from interface org.wandora.application.tools.browserextractors.BrowserPluginExtractor

RETURN_ERROR, RETURN_INFO

Constructor Summary

Constructors

Constructor and Description
AbstractUmbelExtractor()

Method Summary

Modifier and Type	Method and Description
boolean	_extractTopicsFrom(java.io.File file, TopicMap topicMap)
boolean	_extractTopicsFrom(java.net.URL url, TopicMap topicMap)
protected boolean	equalsAny(java.lang.String a, java.lang.String[] b)
abstract java.lang.String	getApiRequestUrlFor(java.lang.String str)
protected Tuples.T3<Topic,Topic,Topic>	getAssociationTopicsForUmbelPredicate(java.lang.String predicate, TopicMap tm)
protected Topic	getBroaderNarrowerTypeTopic(TopicMap topicMap)
protected Topic	getBroaderTypeTopic(TopicMap topicMap)
protected Topic	getConceptTopic(java.lang.String si, java.lang.String label, TopicMap topicMap)
protected Topic	getConceptTopic(java.lang.String si, TopicMap topicMap)
protected Topic	getConceptTypeTopic(TopicMap topicMap)
java.lang.String[]	getContentTypes() Returns an array of String containing the content-types this ContentHandler can process.
java.lang.String	getDescription() AdminToolManager views tool descriptions while user browses available tools and build user customizable GUI elements such as Tools menu.
protected Topic	getDisjointTypeTopic(TopicMap topicMap)
protected Topic	getDistanceTopic(int distance, TopicMap topicMap)
protected Topic	getDistanceTypeTopic(TopicMap topicMap)
int	getExtractorType()
javax.swing.Icon	getIcon() All tools may have identifying graphic icon used within tool GUI elements.
java.lang.String	getName() Tools name represent the tool in UI unless the tool has been given explicitly another GUI name.
protected Topic	getNarrowerTypeTopic(TopicMap topicMap)
protected Topic	getSubclassTypeTopic(TopicMap topicMap)
protected Topic	getSuperclassSubclassTypeTopic(TopicMap topicMap)
protected Topic	getSuperclassTypeTopic(TopicMap topicMap)
protected Topic	getTopic(java.lang.String si, java.lang.String name, TopicMap topicMap)
protected Topic	getTopic(java.lang.String si, TopicMap topicMap)
protected Topic	getTypeTypeTopic(TopicMap topicMap)
java.lang.String	getUmbelConceptURI(java.lang.String label)
protected Topic	getUmbelTypeTopic(TopicMap topicMap)
protected boolean	isURL(java.lang.String u)
protected org.json.JSONObject	performRequest(java.lang.String urlStr, java.lang.String concept)
protected java.lang.String	robustGet(org.json.JSONObject json, java.lang.String key)
protected int	robustGetInt(org.json.JSONObject json, java.lang.String key)
boolean	useURLCrawler()

Methods inherited from class org.wandora.application.tools.extractors.AbstractExtractor

_extractTopicsFrom, acceptBrowserExtractRequest, addCrawlerUrl, browserExtractorConsumesPlainText, buildSI, buildSL, clearMasterSubject, createAssociation, createAssociation, createTopic, createTopic, createTopic, createTopic, createTopic, createTopic, createTopic, croppedFilename, croppedFilename, croppedUrlString, croppedUrlString, doBrowserExtract, dropExtract, dropExtract, dropExtract, execute, extractTopicsFrom, extractTopicsFrom, extractTopicsFrom, extractTopicsFrom, extractTopicsFromText, getBrowserExtractorName, getCrawlerMode, getForceContent, getForceFiles, getForceUrls, getGUIText, getGUIText, getInterruptsHandled, getMasterSubject, getType, getWandora, handle, handleContent, handleCustomType, handleFiles, handleForcedContent, handleInterrupt, handleStringContent, handleUrls, initializeCustomType, instantDropHandle, makeSubclassOfWandoraClass, runInOwnThread, setData, setDisplayName, setForceContent, setForceFiles, setForceUrls, setMasterSubject, setMasterSubject, setTopicMap, setupCrawler, setWandora, takeNap, urlEncode, useTempTopicMap

Methods inherited from class org.wandora.application.tools.AbstractWandoraTool

addUndoMarker, addUndoMarker, allowMultipleInvocations, clearAllThreads, clearThreads, clearThreads, clearToolLock, clearToolLock, clearToolLocks, configure, execute, execute, forceStop, forceStop, getContext, getCurrentLogger, getDefaultLogger, getHistory, getLastLogger, getState, getThreads, getThreads, getToolMenuItem, getToolMenuItem, getTopicName, hlog, initialize, interruptAllThreads, interruptThreads, interruptThreads, isConfigurable, isRunning, isRunning, lockLog, log, log, log, log, requiresRefresh, run, setContext, setDefaultLogger, setLogTitle, setProgress, setProgressMax, setState, setToolLogger, singleLog, singleLog, singleLog, solveContextTopicMap, solveNameForTopicMap, writeOptions

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.wandora.application.WandoraTool

configure, execute, execute, getContext, getToolMenuItem, hlog, initialize, isConfigurable, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLogger, writeOptions

Methods inherited from interface org.wandora.application.WandoraToolLogger

forceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setState

Methods inherited from interface java.lang.Runnable

run

Field Detail

UMBEL_CONCEPT_STRING_SPLITTER

public static final java.lang.String UMBEL_CONCEPT_STRING_SPLITTER

See Also:

Constant Field Values

FILE_CONTAINS_UMBEL_CONCEPT_URLS

public static final int FILE_CONTAINS_UMBEL_CONCEPT_URLS

See Also:

Constant Field Values

FILE_CONTAINS_PLAIN_UMBEL_CONCEPT

public static final int FILE_CONTAINS_PLAIN_UMBEL_CONCEPT

See Also:

Constant Field Values

FILE_IS_CSV_OF_UMBEL_CONCEPTS

public static final int FILE_IS_CSV_OF_UMBEL_CONCEPTS

See Also:

Constant Field Values

fileProcessor

public static int fileProcessor

ADD_DISTANCE_AS_PLAYER

public static boolean ADD_DISTANCE_AS_PLAYER

filterDistancesBelow

public static int filterDistancesBelow

getOnlyImmediateNeighbours

public static boolean getOnlyImmediateNeighbours

useXTMSuperclassSubclassTopics

public static boolean useXTMSuperclassSubclassTopics

csvStringCharacter

protected static char csvStringCharacter

csvLineSeparator

protected static char csvLineSeparator

csvValueSeparator

protected static char csvValueSeparator

csvEncoding

protected static java.lang.String csvEncoding

LANG

public static java.lang.String LANG

UMBEL_CONCEPT_URI_BASE

public static final java.lang.String UMBEL_CONCEPT_URI_BASE

See Also:

Constant Field Values

UMBEL_SUPER_TYPE_URI_BASE

public static final java.lang.String UMBEL_SUPER_TYPE_URI_BASE

See Also:

Constant Field Values

UMBEL_TYPE_SI

public static final java.lang.String UMBEL_TYPE_SI

See Also:

Constant Field Values

UMBEL_TYPE_NAME

public static final java.lang.String UMBEL_TYPE_NAME

See Also:

Constant Field Values

UMBEL_CONCEPT_TYPE_SI

public static final java.lang.String UMBEL_CONCEPT_TYPE_SI

See Also:

Constant Field Values

UMBEL_CONCEPT_TYPE_NAME

public static final java.lang.String UMBEL_CONCEPT_TYPE_NAME

See Also:

Constant Field Values

UMBEL_BROADER_NARROWER_TYPE_SI

public static final java.lang.String UMBEL_BROADER_NARROWER_TYPE_SI

See Also:

Constant Field Values

UMBEL_BROADER_NARROWER_TYPE_NAME

public static final java.lang.String UMBEL_BROADER_NARROWER_TYPE_NAME

See Also:

Constant Field Values

UMBEL_NARROWER_TYPE_SI

public static final java.lang.String UMBEL_NARROWER_TYPE_SI

See Also:

Constant Field Values

UMBEL_NARROWER_TYPE_NAME

public static final java.lang.String UMBEL_NARROWER_TYPE_NAME

See Also:

Constant Field Values

UMBEL_BROADER_TYPE_SI

public static final java.lang.String UMBEL_BROADER_TYPE_SI

See Also:

Constant Field Values

UMBEL_BROADER_TYPE_NAME

public static final java.lang.String UMBEL_BROADER_TYPE_NAME

See Also:

Constant Field Values

UMBEL_SUPERCLASS_SUBCLASS_TYPE_SI

public static final java.lang.String UMBEL_SUPERCLASS_SUBCLASS_TYPE_SI

See Also:

Constant Field Values

UMBEL_SUPERCLASS_SUBCLASS_TYPE_NAME

public static final java.lang.String UMBEL_SUPERCLASS_SUBCLASS_TYPE_NAME

See Also:

Constant Field Values

UMBEL_SUBCLASS_TYPE_SI

public static final java.lang.String UMBEL_SUBCLASS_TYPE_SI

See Also:

Constant Field Values

UMBEL_SUBCLASS_TYPE_NAME

public static final java.lang.String UMBEL_SUBCLASS_TYPE_NAME

See Also:

Constant Field Values

UMBEL_SUPERCLASS_TYPE_SI

public static final java.lang.String UMBEL_SUPERCLASS_TYPE_SI

See Also:

Constant Field Values

UMBEL_SUPERCLASS_TYPE_NAME

public static final java.lang.String UMBEL_SUPERCLASS_TYPE_NAME

See Also:

Constant Field Values

UMBEL_TYPE_TYPE_SI

public static final java.lang.String UMBEL_TYPE_TYPE_SI

See Also:

Constant Field Values

UMBEL_TYPE_TYPE_NAME

public static final java.lang.String UMBEL_TYPE_TYPE_NAME

See Also:

Constant Field Values

UMBEL_DISTANCE_TYPE_SI

public static final java.lang.String UMBEL_DISTANCE_TYPE_SI

See Also:

Constant Field Values

UMBEL_DISTANCE_TYPE_NAME

public static final java.lang.String UMBEL_DISTANCE_TYPE_NAME

See Also:

Constant Field Values

UMBEL_DISJOINT_TYPE_SI

public static final java.lang.String UMBEL_DISJOINT_TYPE_SI

See Also:

Constant Field Values

UMBEL_DISJOINT_TYPE_NAME

public static final java.lang.String UMBEL_DISJOINT_TYPE_NAME

See Also:

Constant Field Values

UMBEL_PREF_LABEL_URI

public static final java.lang.String UMBEL_PREF_LABEL_URI

See Also:

Constant Field Values

UMBEL_ALT_LABEL_URI

public static final java.lang.String UMBEL_ALT_LABEL_URI

See Also:

Constant Field Values

UMBEL_DEFINITION_URI

public static final java.lang.String UMBEL_DEFINITION_URI

See Also:

Constant Field Values

UMBEL_SUBCLASS_URI

public static final java.lang.String[] UMBEL_SUBCLASS_URI

UMBEL_SUPERCLASS_URI

public static final java.lang.String[] UMBEL_SUPERCLASS_URI

UMBEL_NARROWER_URI

public static final java.lang.String[] UMBEL_NARROWER_URI

UMBEL_BROADER_URI

public static final java.lang.String[] UMBEL_BROADER_URI

UMBEL_TYPE_URI

public static final java.lang.String[] UMBEL_TYPE_URI

UMBEL_DISJOINT_URI

public static final java.lang.String[] UMBEL_DISJOINT_URI

contentTypes

private final java.lang.String[] contentTypes

Constructor Detail

AbstractUmbelExtractor

public AbstractUmbelExtractor()

Method Detail

getName

public java.lang.String getName()

Description copied from class: AbstractWandoraTool

Tools name represent the tool in UI unless the tool has been given explicitly another GUI name. All tools should override this method and return a valid string representing name of the tool.

Specified by:

getName in interface WandoraTool

Overrides:

getName in class AbstractExtractor

Returns:

String representing tool's name.

getDescription

public java.lang.String getDescription()

Description copied from class: AbstractWandoraTool

AdminToolManager views tool descriptions while user browses available tools and build user customizable GUI elements such as Tools menu. By default description equals the tool name. All tools should override this method.

Specified by:

getDescription in interface WandoraTool

Overrides:

getDescription in class AbstractExtractor

Returns:

String representing tool's description.

getIcon

public javax.swing.Icon getIcon()

Description copied from class: AbstractWandoraTool

All tools may have identifying graphic icon used within tool GUI elements. getIcon should return Icon object of the tool.

Specified by:

getIcon in interface WandoraTool

Overrides:

getIcon in class AbstractExtractor

Returns:

icon for the tool.

getContentTypes

public java.lang.String[] getContentTypes()

Description copied from interface: Handler

Returns an array of String containing the content-types this ContentHandler can process.

Specified by:

getContentTypes in interface Handler

Overrides:

getContentTypes in class AbstractExtractor

Returns:

String array representing content types.

useURLCrawler

public boolean useURLCrawler()

Overrides:

useURLCrawler in class AbstractExtractor

getExtractorType

public int getExtractorType()

Overrides:

getExtractorType in class AbstractExtractor

getApiRequestUrlFor

public abstract java.lang.String getApiRequestUrlFor(java.lang.String str)

_extractTopicsFrom

public boolean _extractTopicsFrom(java.net.URL url,
                                  TopicMap topicMap)
                           throws java.lang.Exception

Specified by:

_extractTopicsFrom in class AbstractExtractor

Throws:

java.lang.Exception

_extractTopicsFrom

public boolean _extractTopicsFrom(java.io.File file,
                                  TopicMap topicMap)
                           throws java.lang.Exception

Specified by:

_extractTopicsFrom in class AbstractExtractor

Throws:

java.lang.Exception

getUmbelConceptURI

public java.lang.String getUmbelConceptURI(java.lang.String label)

performRequest

protected org.json.JSONObject performRequest(java.lang.String urlStr,
                                             java.lang.String concept)

robustGet

protected java.lang.String robustGet(org.json.JSONObject json,
                                     java.lang.String key)

robustGetInt

protected int robustGetInt(org.json.JSONObject json,
                           java.lang.String key)

getConceptTopic

protected Topic getConceptTopic(java.lang.String si,
                                TopicMap topicMap)

getConceptTopic

protected Topic getConceptTopic(java.lang.String si,
                                java.lang.String label,
                                TopicMap topicMap)

isURL

protected boolean isURL(java.lang.String u)

getUmbelTypeTopic

protected Topic getUmbelTypeTopic(TopicMap topicMap)
                           throws TopicMapException

Throws:

TopicMapException

getBroaderNarrowerTypeTopic

protected Topic getBroaderNarrowerTypeTopic(TopicMap topicMap)
                                     throws TopicMapException

Throws:

TopicMapException

getNarrowerTypeTopic

protected Topic getNarrowerTypeTopic(TopicMap topicMap)
                              throws TopicMapException

Throws:

TopicMapException

getBroaderTypeTopic

protected Topic getBroaderTypeTopic(TopicMap topicMap)
                             throws TopicMapException

Throws:

TopicMapException

getDisjointTypeTopic

protected Topic getDisjointTypeTopic(TopicMap topicMap)
                              throws TopicMapException

Throws:

TopicMapException

getTypeTypeTopic

protected Topic getTypeTypeTopic(TopicMap topicMap)
                          throws TopicMapException

Throws:

TopicMapException

getSuperclassSubclassTypeTopic

protected Topic getSuperclassSubclassTypeTopic(TopicMap topicMap)
                                        throws TopicMapException

Throws:

TopicMapException

getSubclassTypeTopic

protected Topic getSubclassTypeTopic(TopicMap topicMap)
                              throws TopicMapException

Throws:

TopicMapException

getSuperclassTypeTopic

protected Topic getSuperclassTypeTopic(TopicMap topicMap)
                                throws TopicMapException

Throws:

TopicMapException

getConceptTypeTopic

protected Topic getConceptTypeTopic(TopicMap topicMap)
                             throws TopicMapException

Throws:

TopicMapException

getDistanceTopic

protected Topic getDistanceTopic(int distance,
                                 TopicMap topicMap)
                          throws TopicMapException

Throws:

TopicMapException

getDistanceTypeTopic

protected Topic getDistanceTypeTopic(TopicMap topicMap)
                              throws TopicMapException

Throws:

TopicMapException

getTopic

protected Topic getTopic(java.lang.String si,
                         java.lang.String name,
                         TopicMap topicMap)

getTopic

protected Topic getTopic(java.lang.String si,
                         TopicMap topicMap)

getAssociationTopicsForUmbelPredicate

protected Tuples.T3<Topic,Topic,Topic> getAssociationTopicsForUmbelPredicate(java.lang.String predicate,
                                                                             TopicMap tm)

equalsAny

protected boolean equalsAny(java.lang.String a,
                            java.lang.String[] b)