public abstract class AbstractBossExtractor extends AbstractExtractor
| Modifier and Type | Field and Description |
|---|---|
private static java.lang.String |
appid |
static java.lang.String |
BOSS_CONTENTTYPE_SI |
static java.lang.String |
BOSS_DATETIME_SI |
static java.lang.String |
BOSS_DESCRIPTION_SI |
static java.lang.String |
BOSS_FILESIZE_SI |
static java.lang.String |
BOSS_HEIGHT_SI |
static java.lang.String |
BOSS_IMAGERESULT_SI |
static java.lang.String |
BOSS_ROOT |
static java.lang.String |
BOSS_TITLE_SI |
static java.lang.String |
BOSS_WEBRESULT_SI |
static java.lang.String |
BOSS_WIDTH_SI |
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 |
QUERY_SI |
static java.lang.String |
SOURCE_SI |
static java.lang.String |
TOPIC_SI |
static java.lang.String |
WEB_SERVICE_URL |
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 |
|---|
AbstractBossExtractor() |
| 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 |
fillQueryTopic(Topic queryTopic,
TopicMap topicMap,
java.lang.String query) |
void |
forgetAuthorization() |
Topic |
getBossClass(TopicMap tm) |
java.lang.String[] |
getContentTypes()
Returns an array of String containing the content-types this
ContentHandler can process. |
Topic |
getContentTypeType(TopicMap tm) |
Topic |
getDateTimeTopic(java.lang.String datetime,
TopicMap tm) |
Topic |
getDateTimeType(TopicMap tm) |
Topic |
getDescriptionTopic(java.lang.String description,
TopicMap tm) |
Topic |
getDescriptionType(TopicMap tm) |
Topic |
getDocumentType(TopicMap tm) |
protected java.lang.String |
getFileContents(java.io.File file) |
Topic |
getFileSizeType(TopicMap tm) |
Topic |
getHeightType(TopicMap tm) |
javax.swing.Icon |
getIcon()
All tools may have identifying graphic icon used within tool GUI elements.
|
Topic |
getImageSearchResultTopic(TopicMap tm,
java.lang.String title,
java.lang.String url,
java.lang.String width,
java.lang.String height,
java.lang.String contentType,
java.lang.String fileSize) |
Topic |
getImageSearchResultType(TopicMap tm) |
protected Topic |
getOrCreateTopic(TopicMap tm,
java.lang.String si) |
protected Topic |
getOrCreateTopic(TopicMap tm,
java.lang.String si,
java.lang.String bn) |
Topic |
getQueryType(TopicMap tm) |
Topic |
getSourceType(TopicMap tm) |
protected java.lang.String |
getStringFromDocument(org.w3c.dom.Document doc) |
Topic |
getTitleTopic(java.lang.String title,
TopicMap tm) |
Topic |
getTitleType(TopicMap tm) |
Topic |
getTopicType(TopicMap tm) |
WandoraToolType |
getType()
Tool type is used to categorize tools.
|
Topic |
getWandoraClass(TopicMap tm) |
Topic |
getWebSearchResultTopic(TopicMap tm,
java.lang.String title,
java.lang.String description,
java.lang.String url,
java.lang.String datetime) |
Topic |
getWebSearchResultType(TopicMap tm) |
Topic |
getWidthType(TopicMap tm) |
boolean |
isConfigurable()
Whether this tool is configurable.
|
protected void |
makeSubclassOf(TopicMap tm,
Topic t,
Topic superclass) |
protected java.lang.String |
solveAppId() |
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, useTempTopicMapaddUndoMarker, 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, solveNameForTopicMapclone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitexecute, execute, getContext, getToolMenuItem, hlog, initialize, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLoggerforceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setStateprotected 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 BOSS_ROOT
public static final java.lang.String QUERY_SI
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 BOSS_TITLE_SI
public static final java.lang.String BOSS_DESCRIPTION_SI
public static final java.lang.String BOSS_DATETIME_SI
public static final java.lang.String BOSS_WIDTH_SI
public static final java.lang.String BOSS_HEIGHT_SI
public static final java.lang.String BOSS_CONTENTTYPE_SI
public static final java.lang.String BOSS_FILESIZE_SI
public static final java.lang.String BOSS_WEBRESULT_SI
public static final java.lang.String BOSS_IMAGERESULT_SI
private final java.lang.String[] contentTypes
private static java.lang.String appid
public javax.swing.Icon getIcon()
AbstractWandoraToolgetIcon should return Icon object of
the tool.getIcon in interface WandoraToolgetIcon in class AbstractExtractorpublic WandoraToolType getType()
AbstractWandoraToolTool 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 WandoraToolgetType in class AbstractExtractorpublic java.lang.String[] getContentTypes()
HandlerContentHandler can process.getContentTypes in interface HandlergetContentTypes in class AbstractExtractorpublic boolean useURLCrawler()
useURLCrawler in class AbstractExtractorpublic boolean isConfigurable()
AbstractWandoraToolisConfigurable in interface WandoraToolisConfigurable in class AbstractWandoraToolpublic void configure(Wandora admin, Options options, java.lang.String prefix) throws TopicMapException
AbstractWandoraToolconfigure in interface WandoraToolconfigure in class AbstractWandoraToolTopicMapExceptionpublic void writeOptions(Wandora admin, Options options, java.lang.String prefix)
AbstractWandoraToolwriteOptions in interface WandoraToolwriteOptions in class AbstractWandoraToolpublic abstract boolean _extractTopicsFrom(java.io.InputStream in,
TopicMap topicMap)
throws java.lang.Exception
java.lang.Exceptionpublic void fillQueryTopic(Topic queryTopic, TopicMap topicMap, java.lang.String query)
public java.lang.String solveTitle(java.lang.String content)
public Topic getWebSearchResultTopic(TopicMap tm, java.lang.String title, java.lang.String description, java.lang.String url, java.lang.String datetime) throws TopicMapException
TopicMapExceptionpublic Topic getImageSearchResultTopic(TopicMap tm, java.lang.String title, java.lang.String url, java.lang.String width, java.lang.String height, java.lang.String contentType, java.lang.String fileSize) throws TopicMapException
TopicMapExceptionpublic Topic getTitleTopic(java.lang.String title, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDescriptionTopic(java.lang.String description, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDateTimeTopic(java.lang.String datetime, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getTitleType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDescriptionType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDateTimeType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getWidthType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getHeightType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getContentTypeType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getFileSizeType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getWandoraClass(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getTopicType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getSourceType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDocumentType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getBossClass(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getQueryType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getWebSearchResultType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getImageSearchResultType(TopicMap tm) 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 void makeSubclassOf(TopicMap tm, Topic t, Topic superclass) throws TopicMapException
TopicMapExceptionprotected 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.IOExceptionjava.io.FileNotFoundExceptionCopyright 2004-2015 Wandora Team