org.wandora.application.tools.extractors.tagthe

Class AbstractTagtheExtractor

java.lang.Object

org.wandora.application.tools.AbstractWandoraTool

org.wandora.application.tools.extractors.AbstractExtractor

org.wandora.application.tools.extractors.tagthe.AbstractTagtheExtractor

All Implemented Interfaces:

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

Direct Known Subclasses:

TagtheExtractor

public abstract class AbstractTagtheExtractor
extends AbstractExtractor

Author:

akivela

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
private java.lang.String[]	contentTypes
protected java.lang.String	defaultEncoding
static java.lang.String	DOCUMENT_SI
static java.lang.String	LANG
static java.lang.String	SOURCE_SI
static java.lang.String	TAGTHE_SI
static java.lang.String	TAGTHE_TERM_SI
static java.lang.String	TAGTHE_TERM_TYPE_SI
static java.lang.String	TOPIC_SI
static java.lang.String	WEB_SERVICE_URL

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
AbstractTagtheExtractor()

Method Summary

Modifier and Type	Method and Description
abstract boolean	_extractTopicsFrom(java.io.InputStream in, TopicMap topicMap)
java.lang.String	doBrowserExtract(BrowserExtractRequest request, Wandora wandora)
void	fillDocumentTopic(Topic textTopic, TopicMap topicMap, java.lang.String content)
java.lang.String[]	getContentTypes() Returns an array of String containing the content-types this ContentHandler can process.
Topic	getDocumentType(TopicMap tm)
protected java.lang.String	getFileContents(java.io.File file)
javax.swing.Icon	getIcon() All tools may have identifying graphic icon used within tool GUI elements.
protected Topic	getOrCreateTopic(TopicMap tm, java.lang.String si)
protected Topic	getOrCreateTopic(TopicMap tm, java.lang.String si, java.lang.String bn)
Topic	getSourceType(TopicMap tm)
protected java.lang.String	getStringFromDocument(org.w3c.dom.Document doc)
Topic	getTagtheClass(TopicMap tm)
Topic	getTermTopic(java.lang.String term, java.lang.String type, TopicMap tm)
Topic	getTermType(java.lang.String type, TopicMap tm)
Topic	getTermTypeType(TopicMap tm)
Topic	getTopicType(TopicMap tm)
WandoraToolType	getType() Tool type is used to categorize tools.
Topic	getWandoraClass(TopicMap tm)
boolean	isConfigurable() Whether this tool is configurable.
protected void	makeSubclassOf(TopicMap tm, Topic t, Topic superclass)
java.lang.String	solveTitle(java.lang.String content)
boolean	useURLCrawler()

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

_extractTopicsFrom, _extractTopicsFrom, _extractTopicsFrom, acceptBrowserExtractRequest, addCrawlerUrl, browserExtractorConsumesPlainText, buildSI, buildSL, clearMasterSubject, createAssociation, createAssociation, createTopic, createTopic, createTopic, createTopic, createTopic, createTopic, createTopic, croppedFilename, croppedFilename, croppedUrlString, croppedUrlString, dropExtract, dropExtract, dropExtract, execute, extractTopicsFrom, extractTopicsFrom, extractTopicsFrom, extractTopicsFrom, extractTopicsFromText, getBrowserExtractorName, getCrawlerMode, getDescription, getExtractorType, getForceContent, getForceFiles, getForceUrls, getGUIText, getGUIText, getInterruptsHandled, getMasterSubject, getName, 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, 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, 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

defaultEncoding

protected java.lang.String defaultEncoding

LANG

public static java.lang.String LANG

WEB_SERVICE_URL

public static final java.lang.String WEB_SERVICE_URL

See Also:

Constant Field Values

SOURCE_SI

public static final java.lang.String SOURCE_SI

See Also:

Constant Field Values

DOCUMENT_SI

public static final java.lang.String DOCUMENT_SI

See Also:

Constant Field Values

TOPIC_SI

public static final java.lang.String TOPIC_SI

See Also:

Constant Field Values

TAGTHE_SI

public static final java.lang.String TAGTHE_SI

See Also:

Constant Field Values

TAGTHE_TERM_SI

public static final java.lang.String TAGTHE_TERM_SI

See Also:

Constant Field Values

TAGTHE_TERM_TYPE_SI

public static final java.lang.String TAGTHE_TERM_TYPE_SI

See Also:

Constant Field Values

contentTypes

private final java.lang.String[] contentTypes

Constructor Detail

AbstractTagtheExtractor

public AbstractTagtheExtractor()

Method Detail

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.

getType

public WandoraToolType getType()

Description copied from class: AbstractWandoraTool

Tool type is used to categorize tools. Tool type has no real effect today, it is merely an informative property of a tool.

Specified by:

getType in interface WandoraTool

Overrides:

getType in class AbstractExtractor

Returns:

Tool's type object.

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

isConfigurable

public boolean isConfigurable()

Description copied from class: AbstractWandoraTool

Whether this tool is configurable. Configurable tools will provide an interface to configure themselves. To make a configurable tool you will need to:

• Implement isConfigurable method and return true there.
• Implement initialize method to initialize the tool with saved options.
• Implement configure method to provide the user interface for configuration and then save the new options.
• Implement writeOptions method to save the current options.

Specified by:

isConfigurable in interface WandoraTool

Overrides:

isConfigurable in class AbstractWandoraTool

Returns:

true if the tool is configurable.

doBrowserExtract

public java.lang.String doBrowserExtract(BrowserExtractRequest request,
                                         Wandora wandora)
                                  throws TopicMapException

Specified by:

doBrowserExtract in interface BrowserPluginExtractor

Overrides:

doBrowserExtract in class AbstractExtractor

Throws:

TopicMapException

_extractTopicsFrom

public abstract boolean _extractTopicsFrom(java.io.InputStream in,
                                           TopicMap topicMap)
                                    throws java.lang.Exception

Throws:

java.lang.Exception

solveTitle

public java.lang.String solveTitle(java.lang.String content)

fillDocumentTopic

public void fillDocumentTopic(Topic textTopic,
                              TopicMap topicMap,
                              java.lang.String content)

getTermTypeType

public Topic getTermTypeType(TopicMap tm)
                      throws TopicMapException

Throws:

TopicMapException

getTermType

public Topic getTermType(java.lang.String type,
                         TopicMap tm)
                  throws TopicMapException

Throws:

TopicMapException

getTermTopic

public Topic getTermTopic(java.lang.String term,
                          java.lang.String type,
                          TopicMap tm)
                   throws TopicMapException

Throws:

TopicMapException

getTagtheClass

public Topic getTagtheClass(TopicMap tm)
                     throws TopicMapException

Throws:

TopicMapException

getWandoraClass

public Topic getWandoraClass(TopicMap tm)
                      throws TopicMapException

Throws:

TopicMapException

getTopicType

public Topic getTopicType(TopicMap tm)
                   throws TopicMapException

Throws:

TopicMapException

getSourceType

public Topic getSourceType(TopicMap tm)
                    throws TopicMapException

Throws:

TopicMapException

getDocumentType

public Topic getDocumentType(TopicMap tm)
                      throws TopicMapException

Throws:

TopicMapException

getOrCreateTopic

protected Topic getOrCreateTopic(TopicMap tm,
                                 java.lang.String si)
                          throws TopicMapException

Throws:

TopicMapException

getOrCreateTopic

protected Topic getOrCreateTopic(TopicMap tm,
                                 java.lang.String si,
                                 java.lang.String bn)
                          throws TopicMapException

Throws:

TopicMapException

makeSubclassOf

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

Throws:

TopicMapException

getStringFromDocument

protected java.lang.String getStringFromDocument(org.w3c.dom.Document doc)

getFileContents

protected java.lang.String getFileContents(java.io.File file)
                                    throws java.io.IOException,
                                           java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException