public class TextWiseClassifier extends AbstractExtractor
Modifier and Type | Class and Description |
---|---|
private static class |
TextWiseClassifier.TextWiseResultParser |
Modifier and Type | Field and Description |
---|---|
private static java.lang.String |
API_ADDRESS |
protected java.lang.String |
CLASSIFICATION_SI |
private java.lang.String |
contentType |
private java.lang.String[] |
contentTypes |
private java.lang.String |
defaultEncoding |
protected java.lang.String |
DIMENSION_SI |
protected java.lang.String |
DOCUMENT_SI |
protected java.lang.String |
ROOT_SI |
protected java.lang.String |
SOURCE_SI |
private java.lang.String |
token |
protected java.lang.String |
TOPIC_SI |
static boolean |
USE_WEIGHTS |
protected java.lang.String |
WEIGHT_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_EXTRACTOR
CLOSE, EXECUTE, INVISIBLE, VISIBLE, WAIT
RETURN_ERROR, RETURN_INFO
Constructor and Description |
---|
TextWiseClassifier()
Creates a new instance of TextWiseClassifier
|
Modifier and Type | Method and Description |
---|---|
boolean |
_extractTopicsFrom(java.io.File file,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.io.InputStream in,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.lang.String in,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.net.URL url,
TopicMap topicMap) |
java.lang.String |
doBrowserExtract(BrowserExtractRequest request,
Wandora wandora) |
void |
fillDocumentTopic(Topic textTopic,
TopicMap topicMap,
java.lang.String content) |
Topic |
getClassificationType(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.
|
Topic |
getDimensionTopic(java.lang.String dimension,
TopicMap tm) |
Topic |
getDimensionType(TopicMap tm) |
Topic |
getDocumentType(TopicMap tm) |
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 |
getOrCreateTopic(TopicMap tm,
java.lang.String si) |
protected Topic |
getOrCreateTopic(TopicMap tm,
java.lang.String si,
java.lang.String bn) |
Topic |
getSourceType(TopicMap tm) |
Topic |
getTextWiseClass(TopicMap tm) |
Topic |
getTopicType(TopicMap tm) |
Topic |
getWandoraClass(TopicMap tm) |
Topic |
getWeightTopic(java.lang.String weight,
TopicMap tm) |
Topic |
getWeightType(TopicMap tm) |
protected void |
makeSubclassOf(TopicMap tm,
Topic t,
Topic superclass) |
java.lang.String |
solveTitle(java.lang.String content) |
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, 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, useTempTopicMap, useURLCrawler
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
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
configure, execute, execute, getContext, getToolMenuItem, hlog, initialize, isConfigurable, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLogger, writeOptions
forceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setState
public static final boolean USE_WEIGHTS
private static final java.lang.String API_ADDRESS
protected java.lang.String ROOT_SI
protected java.lang.String DIMENSION_SI
protected java.lang.String CLASSIFICATION_SI
protected java.lang.String WEIGHT_SI
protected java.lang.String TOPIC_SI
protected java.lang.String SOURCE_SI
protected java.lang.String DOCUMENT_SI
private java.lang.String contentType
private java.lang.String defaultEncoding
private java.lang.String token
private final java.lang.String[] contentTypes
public TextWiseClassifier()
public java.lang.String getName()
AbstractWandoraTool
getName
in interface WandoraTool
getName
in class AbstractExtractor
public java.lang.String getDescription()
AbstractWandoraTool
getDescription
in interface WandoraTool
getDescription
in class AbstractExtractor
public javax.swing.Icon getIcon()
AbstractWandoraTool
getIcon
should return Icon
object of
the tool.getIcon
in interface WandoraTool
getIcon
in class AbstractExtractor
public java.lang.String[] getContentTypes()
Handler
ContentHandler
can process.getContentTypes
in interface Handler
getContentTypes
in class AbstractExtractor
public java.lang.String doBrowserExtract(BrowserExtractRequest request, Wandora wandora) throws TopicMapException
doBrowserExtract
in interface BrowserPluginExtractor
doBrowserExtract
in class AbstractExtractor
TopicMapException
public boolean _extractTopicsFrom(java.net.URL url, TopicMap topicMap) throws java.lang.Exception
_extractTopicsFrom
in class AbstractExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.io.File file, TopicMap topicMap) throws java.lang.Exception
_extractTopicsFrom
in class AbstractExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.io.InputStream in, TopicMap topicMap) throws java.lang.Exception
java.lang.Exception
public boolean _extractTopicsFrom(java.lang.String in, TopicMap topicMap) throws java.lang.Exception
_extractTopicsFrom
in class AbstractExtractor
java.lang.Exception
public java.lang.String solveTitle(java.lang.String content)
public void fillDocumentTopic(Topic textTopic, TopicMap topicMap, java.lang.String content)
public Topic getDimensionTopic(java.lang.String dimension, TopicMap tm) throws TopicMapException
TopicMapException
public Topic getDimensionType(TopicMap tm) throws TopicMapException
TopicMapException
public Topic getWeightTopic(java.lang.String weight, TopicMap tm) throws TopicMapException
TopicMapException
public Topic getWeightType(TopicMap tm) throws TopicMapException
TopicMapException
public Topic getTextWiseClass(TopicMap tm) throws TopicMapException
TopicMapException
public Topic getWandoraClass(TopicMap tm) throws TopicMapException
TopicMapException
public Topic getClassificationType(TopicMap tm) throws TopicMapException
TopicMapException
public Topic getTopicType(TopicMap tm) throws TopicMapException
TopicMapException
public Topic getSourceType(TopicMap tm) throws TopicMapException
TopicMapException
public Topic getDocumentType(TopicMap tm) throws TopicMapException
TopicMapException
protected Topic getOrCreateTopic(TopicMap tm, java.lang.String si) throws TopicMapException
TopicMapException
protected Topic getOrCreateTopic(TopicMap tm, java.lang.String si, java.lang.String bn) throws TopicMapException
TopicMapException
protected void makeSubclassOf(TopicMap tm, Topic t, Topic superclass) throws TopicMapException
TopicMapException
Copyright 2004-2015 Wandora Team