public abstract class AbstractYahooTermExtractor extends AbstractExtractor
Modifier and Type | Field and Description |
---|---|
private static java.lang.String |
appid |
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 |
TOPIC_SI |
static java.lang.String |
WEB_SERVICE_URL |
static java.lang.String |
YAHOO_TERM_SI |
static java.lang.String |
YAHOO_TERM_TYPE_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 |
---|
AbstractYahooTermExtractor() |
Modifier and Type | Method and Description |
---|---|
abstract boolean |
_extractTopicsFrom(java.io.InputStream in,
TopicMap topicMap) |
void |
configure(Wandora admin,
Options options,
java.lang.String prefix)
If the tool is configurable, shows an user interface to configure the tool.
|
void |
fillDocumentTopic(Topic textTopic,
TopicMap topicMap,
java.lang.String content) |
void |
forgetAuthorization() |
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 |
getTermTopic(java.lang.String term,
TopicMap tm) |
Topic |
getTermType(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 |
solveAppId() |
java.lang.String |
solveAppId(Wandora wandora) |
java.lang.String |
solveTitle(java.lang.String content) |
boolean |
useURLCrawler() |
void |
writeOptions(Wandora admin,
Options options,
java.lang.String prefix)
If the tool is configurable, saves all current tool options.
|
_extractTopicsFrom, _extractTopicsFrom, _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, 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
addUndoMarker, addUndoMarker, allowMultipleInvocations, clearAllThreads, clearThreads, clearThreads, clearToolLock, clearToolLock, clearToolLocks, 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
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
execute, execute, getContext, getToolMenuItem, hlog, initialize, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLogger
forceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setState
protected java.lang.String defaultEncoding
public static java.lang.String LANG
public static final java.lang.String WEB_SERVICE_URL
public static final java.lang.String SOURCE_SI
public static final java.lang.String DOCUMENT_SI
public static final java.lang.String TOPIC_SI
public static final java.lang.String YAHOO_TERM_SI
public static final java.lang.String YAHOO_TERM_TYPE_SI
private final java.lang.String[] contentTypes
private static java.lang.String appid
public javax.swing.Icon getIcon()
AbstractWandoraTool
getIcon
should return Icon
object of
the tool.getIcon
in interface WandoraTool
getIcon
in class AbstractExtractor
public WandoraToolType getType()
AbstractWandoraTool
Tool type is used to categorize tools. Tool type has no real effect today, it is merely an informative property of a tool.
getType
in interface WandoraTool
getType
in class AbstractExtractor
public java.lang.String[] getContentTypes()
Handler
ContentHandler
can process.getContentTypes
in interface Handler
getContentTypes
in class AbstractExtractor
public boolean useURLCrawler()
useURLCrawler
in class AbstractExtractor
public boolean isConfigurable()
AbstractWandoraTool
isConfigurable
in interface WandoraTool
isConfigurable
in class AbstractWandoraTool
public void configure(Wandora admin, Options options, java.lang.String prefix) throws TopicMapException
AbstractWandoraTool
configure
in interface WandoraTool
configure
in class AbstractWandoraTool
TopicMapException
public void writeOptions(Wandora admin, Options options, java.lang.String prefix)
AbstractWandoraTool
writeOptions
in interface WandoraTool
writeOptions
in class AbstractWandoraTool
public abstract boolean _extractTopicsFrom(java.io.InputStream in, TopicMap topicMap) throws java.lang.Exception
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 getTermType(TopicMap tm) throws TopicMapException
TopicMapException
public Topic getTermTopic(java.lang.String term, TopicMap tm) throws TopicMapException
TopicMapException
public Topic getWandoraClass(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
public java.lang.String solveAppId(Wandora wandora)
public java.lang.String solveAppId()
public void forgetAuthorization()
protected java.lang.String getStringFromDocument(org.w3c.dom.Document doc)
protected java.lang.String getFileContents(java.io.File file) throws java.io.IOException, java.io.FileNotFoundException
java.io.IOException
java.io.FileNotFoundException
Copyright 2004-2015 Wandora Team