public class FileBasedSink extends Object implements org.dice_research.squirrel.sink.Sink
| Modifier and Type | Class and Description |
|---|---|
protected static class |
FileBasedSink.StreamStatus |
| Modifier and Type | Field and Description |
|---|---|
static org.apache.jena.riot.Lang |
DEFAULT_OUTPUT_LANG |
private static org.slf4j.Logger |
LOGGER |
protected File |
outputDirectory
Directory to which the files of this sink are written.
|
protected org.apache.jena.riot.Lang |
outputLang
Language used for the output files.
|
protected Map<String,FileBasedSink.StreamStatus> |
streamMapping
Synchronized mapping of crawled URIs to their output stream.
|
protected boolean |
useCompression
Flag whether a compression algorithm should be used.
|
| Constructor and Description |
|---|
FileBasedSink(File outputDirectory,
boolean useCompression) |
FileBasedSink(File outputDirectory,
org.apache.jena.riot.Lang outputLang,
boolean useCompression) |
| Modifier and Type | Method and Description |
|---|---|
void |
addData(org.dice_research.squirrel.data.uri.CrawleableUri uri,
InputStream is) |
void |
addQuad(org.dice_research.squirrel.data.uri.CrawleableUri uri,
org.apache.jena.sparql.core.Quad quad) |
void |
addTriple(org.dice_research.squirrel.data.uri.CrawleableUri uri,
org.apache.jena.graph.Triple triple) |
void |
closeSinkForUri(org.dice_research.squirrel.data.uri.CrawleableUri uri) |
void |
flushMetadata() |
static String |
generateFileName(org.dice_research.squirrel.data.uri.CrawleableUri uri,
org.apache.jena.riot.Lang outputLang,
boolean useCompression) |
private FileBasedSink.StreamStatus |
getStream(org.dice_research.squirrel.data.uri.CrawleableUri uri) |
void |
openSinkForUri(org.dice_research.squirrel.data.uri.CrawleableUri uri) |
private static final org.slf4j.Logger LOGGER
public static final org.apache.jena.riot.Lang DEFAULT_OUTPUT_LANG
protected File outputDirectory
protected boolean useCompression
protected Map<String,FileBasedSink.StreamStatus> streamMapping
protected org.apache.jena.riot.Lang outputLang
public FileBasedSink(File outputDirectory, boolean useCompression)
public FileBasedSink(File outputDirectory, org.apache.jena.riot.Lang outputLang, boolean useCompression)
public void addTriple(org.dice_research.squirrel.data.uri.CrawleableUri uri,
org.apache.jena.graph.Triple triple)
addTriple in interface org.dice_research.squirrel.sink.triplebased.TripleBasedSinkpublic void flushMetadata()
flushMetadata in interface org.dice_research.squirrel.sink.Sinkpublic void addData(org.dice_research.squirrel.data.uri.CrawleableUri uri,
InputStream is)
addData in interface org.dice_research.squirrel.sink.UnstructuredDataSinkpublic void openSinkForUri(org.dice_research.squirrel.data.uri.CrawleableUri uri)
openSinkForUri in interface org.dice_research.squirrel.sink.SinkBaseprivate FileBasedSink.StreamStatus getStream(org.dice_research.squirrel.data.uri.CrawleableUri uri)
public void closeSinkForUri(org.dice_research.squirrel.data.uri.CrawleableUri uri)
closeSinkForUri in interface org.dice_research.squirrel.sink.SinkBasepublic static String generateFileName(org.dice_research.squirrel.data.uri.CrawleableUri uri, org.apache.jena.riot.Lang outputLang, boolean useCompression)
public void addQuad(org.dice_research.squirrel.data.uri.CrawleableUri uri,
org.apache.jena.sparql.core.Quad quad)
addQuad in interface org.dice_research.squirrel.sink.quadbased.QuadBasedSinkCopyright © 2017–2020. All rights reserved.