public class MadsExtractor extends AbstractExtractor
| Modifier and Type | Class and Description |
|---|---|
private class |
MadsExtractor.MadsXMLParser |
| Modifier and Type | Field and Description |
|---|---|
protected static java.lang.String |
AUTHORITY_SI |
private java.lang.String[] |
contentTypes |
private static java.lang.String |
defaultEncoding |
private static java.lang.String |
defaultLang |
protected static java.lang.String |
MADS_SI |
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_EXTRACTORCLOSE, EXECUTE, INVISIBLE, VISIBLE, WAITRETURN_ERROR, RETURN_INFO| Constructor and Description |
|---|
MadsExtractor()
Creates a new instance of MadsExtractor
|
| Modifier and Type | Method and Description |
|---|---|
boolean |
_extractTopicsFrom(java.io.File file,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(org.xml.sax.InputSource in,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.io.InputStream in,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.lang.String str,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.net.URL url,
TopicMap topicMap) |
Topic |
getAuthorityType(TopicMap tm) |
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.
|
javax.swing.Icon |
getIcon()
All tools may have identifying graphic icon used within tool GUI elements.
|
Topic |
getMadsClass(TopicMap tm) |
java.lang.String |
getName()
Tools name represent the tool in UI unless the tool has been given
explicitly another GUI name.
|
protected Topic |
getOrCreateTopic(TopicMap tm,
java.lang.String si) |
protected Topic |
getOrCreateTopic(TopicMap tm,
java.lang.String si,
java.lang.String bn) |
protected Topic |
getOrCreateTopic(TopicMap tm,
java.lang.String si,
java.lang.String bn,
Topic type) |
Topic |
getTopic(TopicMap tm,
java.lang.String str,
java.lang.String SIBase,
Topic type) |
Topic |
getWandoraClass(TopicMap tm) |
protected java.lang.String |
makeSI(java.lang.String base,
java.lang.String endPoint) |
protected void |
makeSubclassOf(TopicMap tm,
Topic t,
Topic superclass) |
boolean |
useURLCrawler() |
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, getExtractorType, 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, useTempTopicMapaddUndoMarker, 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, writeOptionsclone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitconfigure, execute, execute, getContext, getToolMenuItem, hlog, initialize, isConfigurable, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLogger, writeOptionsforceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setStateprotected static java.lang.String MADS_SI
protected static java.lang.String AUTHORITY_SI
private static java.lang.String defaultEncoding
private static java.lang.String defaultLang
private final java.lang.String[] contentTypes
public java.lang.String getName()
AbstractWandoraToolgetName in interface WandoraToolgetName in class AbstractExtractorpublic java.lang.String getDescription()
AbstractWandoraToolgetDescription in interface WandoraToolgetDescription in class AbstractExtractorpublic javax.swing.Icon getIcon()
AbstractWandoraToolgetIcon should return Icon object of
the tool.getIcon in interface WandoraToolgetIcon in class AbstractExtractorpublic java.lang.String[] getContentTypes()
HandlerContentHandler can process.getContentTypes in interface HandlergetContentTypes in class AbstractExtractorpublic boolean useURLCrawler()
useURLCrawler in class AbstractExtractorpublic boolean _extractTopicsFrom(java.net.URL url,
TopicMap topicMap)
throws java.lang.Exception
_extractTopicsFrom in class AbstractExtractorjava.lang.Exceptionpublic boolean _extractTopicsFrom(java.io.File file,
TopicMap topicMap)
throws java.lang.Exception
_extractTopicsFrom in class AbstractExtractorjava.lang.Exceptionpublic boolean _extractTopicsFrom(java.lang.String str,
TopicMap topicMap)
throws java.lang.Exception
_extractTopicsFrom in class AbstractExtractorjava.lang.Exceptionpublic boolean _extractTopicsFrom(java.io.InputStream in,
TopicMap topicMap)
throws java.lang.Exception
java.lang.Exceptionpublic boolean _extractTopicsFrom(org.xml.sax.InputSource in,
TopicMap topicMap)
throws java.lang.Exception
java.lang.Exceptionpublic Topic getAuthorityType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getMadsClass(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getWandoraClass(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getTopic(TopicMap tm, java.lang.String str, java.lang.String SIBase, Topic type) throws TopicMapException
TopicMapExceptionprotected Topic getOrCreateTopic(TopicMap tm, java.lang.String si) throws TopicMapException
TopicMapExceptionprotected Topic getOrCreateTopic(TopicMap tm, java.lang.String si, java.lang.String bn) throws TopicMapException
TopicMapExceptionprotected Topic getOrCreateTopic(TopicMap tm, java.lang.String si, java.lang.String bn, Topic type) throws TopicMapException
TopicMapExceptionprotected void makeSubclassOf(TopicMap tm, Topic t, Topic superclass) throws TopicMapException
TopicMapExceptionprotected java.lang.String makeSI(java.lang.String base,
java.lang.String endPoint)
Copyright 2004-2015 Wandora Team