org.wandora.application.tools.extractors

Class GellishExtractor

java.lang.Object

org.wandora.application.tools.AbstractWandoraTool

org.wandora.application.tools.extractors.AbstractExtractor

org.wandora.application.tools.extractors.GellishExtractor

All Implemented Interfaces:

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

public class GellishExtractor
extends AbstractExtractor
implements WandoraTool

Author:

akivela

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static boolean	CONNECT_TO_WANDORA_CLASS
static java.lang.String	DEFAULT_LANG
static boolean	EXTRACT_EXTRAS
java.lang.String	locatorPrefix
static boolean	REMOVE_SPACES_IN_IDS

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
GellishExtractor() Creates a new instance of GellishExtractor

Method Summary

Modifier and Type	Method and Description
boolean	_extractTopicsFrom(java.io.BufferedReader breader, TopicMap topicMap)
boolean	_extractTopicsFrom(java.io.File thesaurusFile, TopicMap topicMap)
boolean	_extractTopicsFrom(java.lang.String str, TopicMap topicMap)
boolean	_extractTopicsFrom(java.net.URL url, TopicMap topicMap)
protected boolean	associationExists(Topic t1, Topic t2, Topic at)
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	getGellishClassTopic(TopicMap tm)
java.lang.String	getGUIText(int textType)
java.lang.String	getName() Tools name represent the tool in UI unless the tool has been given explicitly another GUI name.
protected Topic	getOrCreateConceptTopic(TopicMap tm, java.lang.String id, java.lang.String name)
protected Topic	getOrCreateTopic(TopicMap topicmap, Locator si, java.lang.String baseName, java.lang.String displayName)
protected Topic	getOrCreateTopic(TopicMap topicmap, Locator si, java.lang.String baseName, java.lang.String displayName, Topic typeTopic)
protected Topic	getOrCreateTopic(TopicMap topicmap, java.lang.String si, java.lang.String baseName, java.lang.String displayName)
protected java.lang.String	getToken(int i, java.lang.String[] arr)
protected boolean	isValid(java.lang.String str)
protected Locator	makeSI(java.lang.String str)
protected Locator	makeSI(java.lang.String prefix, java.lang.String str)
protected Locator	makeSI(java.lang.String prefix, java.lang.String str, java.lang.String postfix)
protected void	makeSubclassOf(TopicMap tm, Topic t, Topic superclass)
protected void	makeSubclassOfGellish(TopicMap tm, Topic subclass)
protected java.lang.String	removeSpacesIn(java.lang.String str)
boolean	useTempTopicMap()

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

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, getContentTypes, getCrawlerMode, getExtractorType, getForceContent, getForceFiles, getForceUrls, getGUIText, getIcon, 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, useURLCrawler

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, execute, getContext, getIcon, getToolMenuItem, getType, 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

locatorPrefix

public java.lang.String locatorPrefix

DEFAULT_LANG

public static java.lang.String DEFAULT_LANG

EXTRACT_EXTRAS

public static boolean EXTRACT_EXTRAS

REMOVE_SPACES_IN_IDS

public static boolean REMOVE_SPACES_IN_IDS

CONNECT_TO_WANDORA_CLASS

public static boolean CONNECT_TO_WANDORA_CLASS

Constructor Detail

GellishExtractor

public GellishExtractor()

Creates a new instance of GellishExtractor

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.

getGUIText

public java.lang.String getGUIText(int textType)

Overrides:

getGUIText in class AbstractExtractor

_extractTopicsFrom

public boolean _extractTopicsFrom(java.lang.String str,
                                  TopicMap topicMap)
                           throws java.lang.Exception

Specified by:

_extractTopicsFrom in class AbstractExtractor

Throws:

java.lang.Exception

_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 thesaurusFile,
                                  TopicMap topicMap)
                           throws java.lang.Exception

Specified by:

_extractTopicsFrom in class AbstractExtractor

Throws:

java.lang.Exception

_extractTopicsFrom

public boolean _extractTopicsFrom(java.io.BufferedReader breader,
                                  TopicMap topicMap)
                           throws java.lang.Exception

Throws:

java.lang.Exception

getToken

protected java.lang.String getToken(int i,
                                    java.lang.String[] arr)

isValid

protected boolean isValid(java.lang.String str)

removeSpacesIn

protected java.lang.String removeSpacesIn(java.lang.String str)

associationExists

protected boolean associationExists(Topic t1,
                                    Topic t2,
                                    Topic at)

getOrCreateConceptTopic

protected Topic getOrCreateConceptTopic(TopicMap tm,
                                        java.lang.String id,
                                        java.lang.String name)

getOrCreateTopic

protected Topic getOrCreateTopic(TopicMap topicmap,
                                 java.lang.String si,
                                 java.lang.String baseName,
                                 java.lang.String displayName)

getOrCreateTopic

protected Topic getOrCreateTopic(TopicMap topicmap,
                                 Locator si,
                                 java.lang.String baseName,
                                 java.lang.String displayName)

getOrCreateTopic

protected Topic getOrCreateTopic(TopicMap topicmap,
                                 Locator si,
                                 java.lang.String baseName,
                                 java.lang.String displayName,
                                 Topic typeTopic)

makeSI

protected Locator makeSI(java.lang.String str)

makeSI

protected Locator makeSI(java.lang.String prefix,
                         java.lang.String str)

makeSI

protected Locator makeSI(java.lang.String prefix,
                         java.lang.String str,
                         java.lang.String postfix)

makeSubclassOfGellish

protected void makeSubclassOfGellish(TopicMap tm,
                                     Topic subclass)
                              throws TopicMapException

Throws:

TopicMapException

makeSubclassOf

protected void makeSubclassOf(TopicMap tm,
                              Topic t,
                              Topic superclass)
                       throws TopicMapException

Throws:

TopicMapException

getGellishClassTopic

protected Topic getGellishClassTopic(TopicMap tm)
                              throws TopicMapException

Throws:

TopicMapException

useTempTopicMap

public boolean useTempTopicMap()

Overrides:

useTempTopicMap in class AbstractExtractor