public abstract class AbstractMillionFirstStepsExtractor extends AbstractExtractor
Modifier and Type | Field and Description |
---|---|
static java.lang.String |
ARKID_SI |
static java.lang.String |
AUTHOR_SI |
static java.lang.String |
BASE_SI |
static java.lang.String |
BL_DLS_SI |
static java.lang.String |
BOOK_SI |
static java.lang.String |
BRITISH_LIBRARY_SI |
static java.lang.String |
CORPORATE_SI |
static java.lang.String |
DATE_SI |
static java.lang.String |
DATEFIELD_SI |
protected static java.lang.String |
defaultEncoding |
protected static java.lang.String |
defaultLang |
static java.lang.String |
EDITION_SI |
static java.lang.String |
IMAGE_SI |
static java.lang.String |
IMAGEIDX_SI |
static java.lang.String |
ISSUANCE_SI |
static java.lang.String |
LANG_SI |
static java.lang.String |
ORDER_SI |
static java.lang.String |
PAGE_SI |
static java.lang.String |
PDF_SI |
static java.lang.String |
PLACE_SI |
static java.lang.String |
PUBLISHER_SI |
static java.lang.String |
ROLE_SI |
static java.lang.String |
SHELFMARK_SI |
static java.lang.String |
TITLE_SI |
static java.lang.String |
VOLUME_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 |
---|
AbstractMillionFirstStepsExtractor() |
Modifier and Type | Method and Description |
---|---|
protected java.lang.String |
doUrl(java.net.URL url) |
static Topic |
getArkIdTypeTopic(TopicMap tm) |
static Topic |
getATopic(java.lang.String str,
java.lang.String si,
java.lang.String type,
TopicMap tm) |
static Topic |
getATypeTopic(java.lang.String si,
java.lang.String type,
TopicMap tm) |
static Topic |
getAuthorTopic(java.lang.String author,
TopicMap tm) |
static Topic |
getAuthorTypeTopic(TopicMap tm) |
static Topic |
getBLDLSIdTypeTopic(TopicMap tm) |
static Topic |
getBookTopic(java.lang.String book,
TopicMap tm) |
static Topic |
getBookTypeTopic(TopicMap tm) |
static Topic |
getBritishLibraryTypeTopic(TopicMap tm) |
static Topic |
getCorporateTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getCorporateTypeTopic(TopicMap tm) |
static Topic |
getDatefieldTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getDatefieldTypeTopic(TopicMap tm) |
static Topic |
getDateTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getDateTypeTopic(TopicMap tm) |
java.lang.String |
getDescription()
AdminToolManager views tool descriptions while user browses available
tools and build user customizable GUI elements such as Tools menu.
|
static Topic |
getEditionTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getEditionTypeTopic(TopicMap tm) |
javax.swing.Icon |
getIcon()
All tools may have identifying graphic icon used within tool GUI elements.
|
static Topic |
getImageIdxTypeTopic(TopicMap tm) |
static Topic |
getImageTopic(java.lang.String str,
java.lang.String sl,
TopicMap tm) |
static Topic |
getImageTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getImageTypeTopic(TopicMap tm) |
static Topic |
getIssuanceTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getIssuanceTypeTopic(TopicMap tm) |
protected static Topic |
getLangTopic(TopicMap tm) |
java.lang.String |
getName()
Tools name represent the tool in UI unless the tool has been given
explicitly another GUI name.
|
protected static Topic |
getOrCreateTopic(TopicMap tm,
java.lang.String si) |
protected static Topic |
getOrCreateTopic(TopicMap tm,
java.lang.String si,
java.lang.String bn) |
static Topic |
getOrderTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getOrderTypeTopic(TopicMap tm) |
static Topic |
getPageTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getPageTypeTopic(TopicMap tm) |
static Topic |
getPDFTypeTopic(TopicMap tm) |
static Topic |
getPlaceTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getPlaceTypeTopic(TopicMap tm) |
static Topic |
getPublisherTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getPublisherTypeTopic(TopicMap tm) |
static Topic |
getRoleTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getRoleTypeTopic(TopicMap tm) |
static Topic |
getShelfmarkTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getShelfmarkTypeTopic(TopicMap tm) |
static Topic |
getTitleTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getTitleTypeTopic(TopicMap tm) |
static Topic |
getVolumeTopic(java.lang.String str,
TopicMap tm) |
static Topic |
getVolumeTypeTopic(TopicMap tm) |
protected static Topic |
getWandoraClassTopic(TopicMap tm) |
protected static void |
makeSubclassOf(TopicMap tm,
Topic t,
Topic superclass) |
boolean |
runInOwnThread()
Whether or not this tool should fork own thread.
|
boolean |
useTempTopicMap() |
boolean |
useURLCrawler() |
_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, getContentTypes, getCrawlerMode, getExtractorType, getForceContent, getForceFiles, getForceUrls, getGUIText, getGUIText, getInterruptsHandled, getMasterSubject, getType, getWandora, handle, handleContent, handleCustomType, handleFiles, handleForcedContent, handleInterrupt, handleStringContent, handleUrls, initializeCustomType, instantDropHandle, makeSubclassOfWandoraClass, setData, setDisplayName, setForceContent, setForceFiles, setForceUrls, setMasterSubject, setMasterSubject, setTopicMap, setupCrawler, setWandora, takeNap, urlEncode
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
protected static java.lang.String defaultEncoding
protected static java.lang.String defaultLang
public static final java.lang.String LANG_SI
public static final java.lang.String BRITISH_LIBRARY_SI
public static final java.lang.String BASE_SI
public static final java.lang.String BOOK_SI
public static final java.lang.String AUTHOR_SI
public static final java.lang.String CORPORATE_SI
public static final java.lang.String TITLE_SI
public static final java.lang.String PLACE_SI
public static final java.lang.String DATE_SI
public static final java.lang.String DATEFIELD_SI
public static final java.lang.String PUBLISHER_SI
public static final java.lang.String EDITION_SI
public static final java.lang.String ISSUANCE_SI
public static final java.lang.String SHELFMARK_SI
public static final java.lang.String IMAGE_SI
public static final java.lang.String IMAGEIDX_SI
public static final java.lang.String ROLE_SI
public static final java.lang.String ORDER_SI
public static final java.lang.String ARKID_SI
public static final java.lang.String BL_DLS_SI
public static final java.lang.String PAGE_SI
public static final java.lang.String VOLUME_SI
public static final java.lang.String PDF_SI
protected static Topic getLangTopic(TopicMap tm) throws TopicMapException
TopicMapException
protected static Topic getWandoraClassTopic(TopicMap tm) throws TopicMapException
TopicMapException
protected static Topic getOrCreateTopic(TopicMap tm, java.lang.String si) throws TopicMapException
TopicMapException
protected static Topic getOrCreateTopic(TopicMap tm, java.lang.String si, java.lang.String bn) throws TopicMapException
TopicMapException
protected static void makeSubclassOf(TopicMap tm, Topic t, Topic superclass) throws TopicMapException
TopicMapException
public static Topic getBritishLibraryTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getATopic(java.lang.String str, java.lang.String si, java.lang.String type, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getATypeTopic(java.lang.String si, java.lang.String type, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getBookTopic(java.lang.String book, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getBookTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getArkIdTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getBLDLSIdTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getPDFTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getImageIdxTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getAuthorTopic(java.lang.String author, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getAuthorTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getCorporateTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getCorporateTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getTitleTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getTitleTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getPageTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getPageTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getVolumeTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getVolumeTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getPlaceTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getPlaceTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getDatefieldTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getDatefieldTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getDateTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getDateTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getPublisherTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getPublisherTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getEditionTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getEditionTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getIssuanceTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getIssuanceTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getShelfmarkTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getShelfmarkTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getImageTopic(java.lang.String str, java.lang.String sl, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getImageTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getImageTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getOrderTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getOrderTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getRoleTopic(java.lang.String str, TopicMap tm) throws TopicMapException
TopicMapException
public static Topic getRoleTypeTopic(TopicMap tm) throws TopicMapException
TopicMapException
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 boolean runInOwnThread()
AbstractWandoraTool
runInOwnThread
in class AbstractExtractor
public boolean useTempTopicMap()
useTempTopicMap
in class AbstractExtractor
public boolean useURLCrawler()
useURLCrawler
in class AbstractExtractor
protected java.lang.String doUrl(java.net.URL url) throws java.io.IOException
java.io.IOException
Copyright 2004-2015 Wandora Team