public abstract class AbstractZemantaExtractor extends AbstractExtractor
| Modifier and Type | Field and Description |
|---|---|
private static java.lang.String |
apikey |
private java.lang.String[] |
contentTypes |
protected java.lang.String |
defaultEncoding |
static java.lang.String |
DOCUMENT_SI |
protected boolean |
EXTRACT_RELEVANCE |
static java.lang.String |
LANG |
static java.lang.String |
SOURCE_SI |
static java.lang.String |
TOPIC_SI |
static java.lang.String |
ZEMANTA_ARTICLE_SI |
static java.lang.String |
ZEMANTA_ARTICLE_TITLE_SI |
static java.lang.String |
ZEMANTA_CATEGORIZATION_SI |
static java.lang.String |
ZEMANTA_CATEGORY_SI |
static java.lang.String |
ZEMANTA_CONFIDENCE_SI |
static java.lang.String |
ZEMANTA_DATE_SI |
static java.lang.String |
ZEMANTA_IMAGE_ATTRIBUTION_SI |
static java.lang.String |
ZEMANTA_IMAGE_DESCRIPTION_SI |
static java.lang.String |
ZEMANTA_IMAGE_LICENSE_SI |
static java.lang.String |
ZEMANTA_IMAGE_SI |
static java.lang.String |
ZEMANTA_KEYWORD_SI |
static java.lang.String |
ZEMANTA_LARGE_IMAGE_SI |
static java.lang.String |
ZEMANTA_LINK_ANCHOR_SI |
static java.lang.String |
ZEMANTA_LINK_SI |
static java.lang.String |
ZEMANTA_LINK_TITLE_SI |
static java.lang.String |
ZEMANTA_LINK_TYPE_SI |
static java.lang.String |
ZEMANTA_LINK_URL_SI |
static java.lang.String |
ZEMANTA_MEDIUM_IMAGE_SI |
static java.lang.String |
ZEMANTA_PUBLISHED_DATE_SI |
static java.lang.String |
ZEMANTA_RELEVANCE_SI |
static java.lang.String |
ZEMANTA_SCHEMA_SI |
static java.lang.String |
ZEMANTA_SI |
static java.lang.String |
ZEMANTA_SMALL_IMAGE_SI |
static java.lang.String |
ZEMANTA_URL |
static java.lang.String |
ZEMANTA_ZEMIFIED_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 |
|---|
AbstractZemantaExtractor() |
| 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.
|
java.lang.String |
doBrowserExtract(BrowserExtractRequest request,
Wandora wandora) |
void |
fillDocumentTopic(Topic textTopic,
TopicMap topicMap,
java.lang.String content) |
void |
forgetAuthorization() |
Topic |
getArticleTitleTopic(java.lang.String str,
TopicMap tm) |
Topic |
getArticleTitleType(TopicMap tm) |
Topic |
getArticleTopic(java.lang.String url,
TopicMap tm) |
Topic |
getArticleType(TopicMap tm) |
private Topic |
getATopic(java.lang.String str,
java.lang.String si,
Topic type,
TopicMap tm) |
Topic |
getCategorizationTopic(java.lang.String str,
TopicMap tm) |
Topic |
getCategorizationType(TopicMap tm) |
Topic |
getCategoryTopic(java.lang.String str,
TopicMap tm) |
Topic |
getCategoryType(TopicMap tm) |
Topic |
getConfidenceTopic(java.lang.String str,
TopicMap tm) |
Topic |
getConfidenceType(TopicMap tm) |
java.lang.String[] |
getContentTypes()
Returns an array of String containing the content-types this
ContentHandler can process. |
Topic |
getDateTopic(java.lang.String str,
TopicMap tm) |
Topic |
getDateType(TopicMap tm) |
Topic |
getDefaultLangType(TopicMap tm) |
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.
|
Topic |
getImageAttributionType(TopicMap tm) |
Topic |
getImageDescriptionType(TopicMap tm) |
Topic |
getImageLicenseType(TopicMap tm) |
Topic |
getImageTopic(java.lang.String url,
TopicMap tm) |
Topic |
getImageType(TopicMap tm) |
Topic |
getKeywordTopic(java.lang.String str,
TopicMap tm) |
Topic |
getKeywordType(TopicMap tm) |
Topic |
getLargeImageType(TopicMap tm) |
Topic |
getLinkAnchorTopic(java.lang.String str,
TopicMap tm) |
Topic |
getLinkAnchorType(TopicMap tm) |
Topic |
getLinkTitleTopic(java.lang.String str,
TopicMap tm) |
Topic |
getLinkTitleType(TopicMap tm) |
Topic |
getLinkType(TopicMap tm) |
Topic |
getLinkTypeTopic(java.lang.String str,
TopicMap tm) |
Topic |
getLinkTypeType(TopicMap tm) |
Topic |
getLinkUrlTopic(java.lang.String url,
TopicMap tm) |
Topic |
getLinkUrlType(TopicMap tm) |
Topic |
getMediumImageType(TopicMap tm) |
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 |
getPublishedDateType(TopicMap tm) |
Topic |
getRelevanceTopic(java.lang.String str,
TopicMap tm) |
Topic |
getRelevanceType(TopicMap tm) |
Topic |
getSchemaTopic(java.lang.String str,
TopicMap tm) |
Topic |
getSchemaType(TopicMap tm) |
Topic |
getSmallImageType(TopicMap tm) |
Topic |
getSourceType(TopicMap tm) |
protected java.lang.String |
getStringFromDocument(org.w3c.dom.Document doc) |
Topic |
getTopicType(TopicMap tm) |
WandoraToolType |
getType()
Tool type is used to categorize tools.
|
private Topic |
getUTopic(java.lang.String si,
Topic type,
TopicMap tm) |
Topic |
getWandoraClass(TopicMap tm) |
Topic |
getZemantaType(TopicMap tm) |
Topic |
getZemifiedTopic(java.lang.String str,
TopicMap tm) |
Topic |
getZemifiedType(TopicMap tm) |
boolean |
isConfigurable()
Whether this tool is configurable.
|
protected void |
makeSubclassOf(TopicMap tm,
Topic t,
Topic superclass) |
static java.lang.String |
sendRequest(java.net.URL url,
java.lang.String data,
java.lang.String ctype,
java.lang.String method) |
java.lang.String |
solveAPIKey() |
java.lang.String |
solveAPIKey(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, 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 boolean EXTRACT_RELEVANCE
protected java.lang.String defaultEncoding
public static java.lang.String LANG
public static final java.lang.String ZEMANTA_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 ZEMANTA_SI
public static final java.lang.String ZEMANTA_IMAGE_SI
public static final java.lang.String ZEMANTA_LARGE_IMAGE_SI
public static final java.lang.String ZEMANTA_MEDIUM_IMAGE_SI
public static final java.lang.String ZEMANTA_SMALL_IMAGE_SI
public static final java.lang.String ZEMANTA_IMAGE_DESCRIPTION_SI
public static final java.lang.String ZEMANTA_IMAGE_ATTRIBUTION_SI
public static final java.lang.String ZEMANTA_IMAGE_LICENSE_SI
public static final java.lang.String ZEMANTA_KEYWORD_SI
public static final java.lang.String ZEMANTA_CATEGORY_SI
public static final java.lang.String ZEMANTA_CATEGORIZATION_SI
public static final java.lang.String ZEMANTA_CONFIDENCE_SI
public static final java.lang.String ZEMANTA_RELEVANCE_SI
public static final java.lang.String ZEMANTA_SCHEMA_SI
public static final java.lang.String ZEMANTA_LINK_SI
public static final java.lang.String ZEMANTA_LINK_ANCHOR_SI
public static final java.lang.String ZEMANTA_LINK_URL_SI
public static final java.lang.String ZEMANTA_LINK_TYPE_SI
public static final java.lang.String ZEMANTA_LINK_TITLE_SI
public static final java.lang.String ZEMANTA_ARTICLE_SI
public static final java.lang.String ZEMANTA_ARTICLE_TITLE_SI
public static final java.lang.String ZEMANTA_DATE_SI
public static final java.lang.String ZEMANTA_PUBLISHED_DATE_SI
public static final java.lang.String ZEMANTA_ZEMIFIED_SI
private final java.lang.String[] contentTypes
private static java.lang.String apikey
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 java.lang.String doBrowserExtract(BrowserExtractRequest request, Wandora wandora) throws TopicMapException
doBrowserExtract in interface BrowserPluginExtractordoBrowserExtract in class AbstractExtractorTopicMapExceptionpublic static java.lang.String sendRequest(java.net.URL url,
java.lang.String data,
java.lang.String ctype,
java.lang.String method)
throws java.io.IOException
java.io.IOExceptionpublic 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 java.lang.String solveTitle(java.lang.String content)
public void fillDocumentTopic(Topic textTopic, TopicMap topicMap, java.lang.String content)
public Topic getKeywordTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getCategoryTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getConfidenceTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getRelevanceTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getSchemaTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getCategorizationTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkUrlTopic(java.lang.String url, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkAnchorTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkTypeTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkTitleTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getZemifiedTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDateTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getArticleTopic(java.lang.String url, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getArticleTitleTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getImageTopic(java.lang.String url, TopicMap tm) throws TopicMapException
TopicMapExceptionprivate Topic getATopic(java.lang.String str, java.lang.String si, Topic type, TopicMap tm) throws TopicMapException
TopicMapExceptionprivate Topic getUTopic(java.lang.String si, Topic type, TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getImageType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLargeImageType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getMediumImageType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getSmallImageType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDefaultLangType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getImageDescriptionType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getImageLicenseType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getImageAttributionType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getArticleType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getArticleTitleType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDateType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getPublishedDateType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getZemifiedType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkTitleType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkTypeType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkAnchorType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getLinkUrlType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getRelevanceType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getConfidenceType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getSchemaType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getCategorizationType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getKeywordType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getCategoryType(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 getZemantaType(TopicMap tm) throws TopicMapException
TopicMapExceptionpublic Topic getDocumentType(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 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
TopicMapExceptionpublic java.lang.String solveAPIKey(Wandora wandora)
public java.lang.String solveAPIKey()
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