org.wandora.application.tools.extractors.mediawikiapi

Class MediaWikiAPIPageExtractor

java.lang.Object

org.wandora.application.tools.AbstractWandoraTool

org.wandora.application.tools.extractors.AbstractExtractor

org.wandora.application.tools.extractors.mediawikiapi.AbstractMediaWikiAPIExtractor

org.wandora.application.tools.extractors.mediawikiapi.MediaWikiAPIPageExtractor

All Implemented Interfaces:

java.io.Serializable, java.lang.Runnable, BrowserPluginExtractor, DropExtractor, WandoraTool, WandoraToolLogger, Handler, InterruptHandler, TopicMapLogger

public class MediaWikiAPIPageExtractor
extends AbstractMediaWikiAPIExtractor

Author:

Eero

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
private java.lang.String	baseURL
private java.lang.String[]	contentTypes
private boolean	crawlClasses
private WandoraToolLogger	logger
private int	nExtracted
private int	progress
private java.lang.String[]	qType
private java.lang.String	queryURL

Fields inherited from class org.wandora.application.tools.extractors.mediawikiapi.AbstractMediaWikiAPIExtractor

CONTENT_TYPE_SI, LANG_SI, PAGE_SI, SI_ROOT

Fields inherited from class org.wandora.application.tools.extractors.AbstractExtractor

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

Fields inherited from interface org.wandora.application.WandoraToolLogger

CLOSE, EXECUTE, INVISIBLE, VISIBLE, WAIT

Fields inherited from interface org.wandora.application.tools.browserextractors.BrowserPluginExtractor

RETURN_ERROR, RETURN_INFO

Constructor Summary

Constructors

Constructor and Description
MediaWikiAPIPageExtractor(java.lang.String baseURL, java.lang.String[] qType, boolean crawl)

Method Summary

Modifier and Type	Method and Description
boolean	_extractTopicsFrom(java.io.File f, TopicMap t)
boolean	_extractTopicsFrom(java.lang.String str, TopicMap t)
boolean	_extractTopicsFrom(java.net.URL u, TopicMap t)
private void	continueExtraction(org.wandora.dep.json.JSONObject contObject, TopicMap t)
private boolean	extractTopicsFromString(java.lang.String str, TopicMap t)
private boolean	extractTopicsFromURL(java.net.URL u, TopicMap t)
private java.lang.String	getArticleBody(java.lang.String title)
private java.util.List<java.lang.String>	getArticleClasses(java.lang.String title)
private java.util.HashMap<java.lang.String,java.lang.String>	getArticleInfo(java.lang.String title)
protected java.lang.String	getBaseUrl()
java.lang.String[]	getContentTypes() Returns an array of String containing the content-types this ContentHandler can process.
protected java.lang.String	getQueryUrl()
protected void	incrementExtractions()
private org.wandora.dep.json.JSONObject	parse(org.wandora.dep.json.JSONObject body, TopicMap tm)
private void	parsePage(org.wandora.dep.json.JSONObject page, TopicMap tm)
private void	parsePage(java.lang.String title, TopicMap tm)
private void	printError(org.wandora.dep.json.JSONObject body)
private void	printWarnings(org.wandora.dep.json.JSONObject body)
boolean	runInOwnThread() Whether or not this tool should fork own thread.
protected void	setQueryUrl(java.lang.String u)
boolean	useURLCrawler()

Methods inherited from class org.wandora.application.tools.extractors.mediawikiapi.AbstractMediaWikiAPIExtractor

getContentTypeTopic, getLangTopic, getLangTopic, getMediaWikiClass, getOrCreateTopic, getOrCreateTopic, getWandoraClassTopic, makeSubclassOf

Methods inherited from class org.wandora.application.tools.extractors.AbstractExtractor

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, getIcon, getInterruptsHandled, getMasterSubject, getName, 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, useTempTopicMap

Methods inherited from class org.wandora.application.tools.AbstractWandoraTool

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

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.wandora.application.WandoraTool

configure, execute, execute, getContext, getToolMenuItem, hlog, initialize, isConfigurable, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLogger, writeOptions

Methods inherited from interface org.wandora.application.WandoraToolLogger

forceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setState

Methods inherited from interface java.lang.Runnable

run

Field Detail

nExtracted

private int nExtracted

baseURL

private java.lang.String baseURL

queryURL

private java.lang.String queryURL

crawlClasses

private boolean crawlClasses

qType

private java.lang.String[] qType

progress

private int progress

logger

private WandoraToolLogger logger

contentTypes

private final java.lang.String[] contentTypes

Constructor Detail

MediaWikiAPIPageExtractor

MediaWikiAPIPageExtractor(java.lang.String baseURL,
                          java.lang.String[] qType,
                          boolean crawl)

Method Detail

useURLCrawler

public boolean useURLCrawler()

Overrides:

useURLCrawler in class AbstractExtractor

runInOwnThread

public boolean runInOwnThread()

Description copied from class: AbstractWandoraTool

Whether or not this tool should fork own thread. If own thread is allowed, the execution of the tool return immediately. If own thread is not allowed the thread entering initial execute method is used. Extending classes should override this method.

Overrides:

runInOwnThread in class AbstractExtractor

Returns:

true if the tool should should be ran in separate thread.

setQueryUrl

protected void setQueryUrl(java.lang.String u)

getBaseUrl

protected java.lang.String getBaseUrl()

getQueryUrl

protected java.lang.String getQueryUrl()

incrementExtractions

protected void incrementExtractions()

getContentTypes

public java.lang.String[] getContentTypes()

Description copied from interface: Handler

Returns an array of String containing the content-types this ContentHandler can process.

Specified by:

getContentTypes in interface Handler

Overrides:

getContentTypes in class AbstractExtractor

Returns:

String array representing content types.

_extractTopicsFrom

public boolean _extractTopicsFrom(java.io.File f,
                                  TopicMap t)
                           throws java.lang.Exception

Specified by:

_extractTopicsFrom in class AbstractExtractor

Throws:

java.lang.Exception

_extractTopicsFrom

public boolean _extractTopicsFrom(java.net.URL u,
                                  TopicMap t)
                           throws java.lang.Exception

Specified by:

_extractTopicsFrom in class AbstractExtractor

Throws:

java.lang.Exception

_extractTopicsFrom

public boolean _extractTopicsFrom(java.lang.String str,
                                  TopicMap t)
                           throws java.lang.Exception

Specified by:

_extractTopicsFrom in class AbstractExtractor

Throws:

java.lang.Exception

extractTopicsFromString

private boolean extractTopicsFromString(java.lang.String str,
                                        TopicMap t)

extractTopicsFromURL

private boolean extractTopicsFromURL(java.net.URL u,
                                     TopicMap t)

continueExtraction

private void continueExtraction(org.wandora.dep.json.JSONObject contObject,
                                TopicMap t)
                         throws java.lang.Exception

Throws:

java.lang.Exception

parse

private org.wandora.dep.json.JSONObject parse(org.wandora.dep.json.JSONObject body,
                                              TopicMap tm)
                                       throws org.wandora.dep.json.JSONException,
                                              TopicMapException,
                                              java.io.IOException

Throws:

org.wandora.dep.json.JSONException

TopicMapException

java.io.IOException

parsePage

private void parsePage(org.wandora.dep.json.JSONObject page,
                       TopicMap tm)
                throws org.wandora.dep.json.JSONException,
                       TopicMapException,
                       java.io.IOException

Throws:

org.wandora.dep.json.JSONException

TopicMapException

java.io.IOException

parsePage

private void parsePage(java.lang.String title,
                       TopicMap tm)
                throws org.wandora.dep.json.JSONException,
                       TopicMapException,
                       java.io.IOException

Throws:

org.wandora.dep.json.JSONException

TopicMapException

java.io.IOException

getArticleBody

private java.lang.String getArticleBody(java.lang.String title)
                                 throws java.io.IOException

Throws:

java.io.IOException

getArticleInfo

private java.util.HashMap<java.lang.String,java.lang.String> getArticleInfo(java.lang.String title)
                                                                     throws java.io.IOException

Throws:

java.io.IOException

getArticleClasses

private java.util.List<java.lang.String> getArticleClasses(java.lang.String title)
                                                    throws java.io.IOException

Throws:

java.io.IOException

printError

private void printError(org.wandora.dep.json.JSONObject body)
                 throws org.wandora.dep.json.JSONException

Throws:

org.wandora.dep.json.JSONException

printWarnings

private void printWarnings(org.wandora.dep.json.JSONObject body)
                    throws org.wandora.dep.json.JSONException

Throws:

org.wandora.dep.json.JSONException