public class CrawlingActivity extends Object implements Serializable
Modifier and Type | Class and Description |
---|---|
static class |
CrawlingActivity.CrawlingURIState |
Modifier and Type | Field and Description |
---|---|
private String |
activityUri
A unique id.
|
private Calendar |
dateEnded
When the activity has ended.
|
private Calendar |
dateStarted
When the activity has started.
|
private long |
numberOfTriples |
private Map<String,org.apache.jena.rdf.model.Resource> |
outputResource
The URIs of the resources generated by this activity as well as their type as
RDF Resource.
|
private static long |
serialVersionUID |
private CrawlingActivity.CrawlingURIState |
state
The crawling state of the uri.
|
private List<String> |
steps |
private org.dice_research.squirrel.data.uri.CrawleableUri |
uri
The uri for the crawling activity.
|
private String |
workerUri
URI of the worker assigned carrying out this activity.
|
Constructor and Description |
---|
CrawlingActivity(org.dice_research.squirrel.data.uri.CrawleableUri uri,
String workerUri)
Constructor.
|
Modifier and Type | Method and Description |
---|---|
void |
addOutputResource(String outputResource,
org.apache.jena.rdf.model.Resource resourceType) |
void |
addStep(Class<?> clazz,
String... actions) |
void |
finishActivity(org.dice_research.squirrel.sink.Sink sink)
Finish the crawling activity and send data to sink
|
org.dice_research.squirrel.data.uri.CrawleableUri |
getCrawleableUri() |
long |
getNumberOfTriples() |
CrawlingActivity.CrawlingURIState |
getState() |
protected String |
getStepsAsString() |
org.dice_research.squirrel.data.uri.CrawleableUri |
getUri() |
org.apache.jena.rdf.model.Model |
prepareMetadataModel()
Prepare the metadata model and returns it.
|
void |
setNumberOfTriples(long numberOfTriples) |
void |
setState(CrawlingActivity.CrawlingURIState state) |
private static final long serialVersionUID
private String activityUri
private Calendar dateStarted
private Calendar dateEnded
private org.dice_research.squirrel.data.uri.CrawleableUri uri
private Map<String,org.apache.jena.rdf.model.Resource> outputResource
private CrawlingActivity.CrawlingURIState state
private String workerUri
private long numberOfTriples
public CrawlingActivity(org.dice_research.squirrel.data.uri.CrawleableUri uri, String workerUri)
uri
- the URI, which was crawledworkerUri
- URI of the Worker
that crawled the URIpublic void setState(CrawlingActivity.CrawlingURIState state)
public void finishActivity(org.dice_research.squirrel.sink.Sink sink)
public org.apache.jena.rdf.model.Model prepareMetadataModel()
protected String getStepsAsString()
public CrawlingActivity.CrawlingURIState getState()
public org.dice_research.squirrel.data.uri.CrawleableUri getCrawleableUri()
public org.dice_research.squirrel.data.uri.CrawleableUri getUri()
public void setNumberOfTriples(long numberOfTriples)
public long getNumberOfTriples()
public void addOutputResource(String outputResource, org.apache.jena.rdf.model.Resource resourceType)
Copyright © 2017–2020. All rights reserved.