public class HdtBasedSink extends FileBasedSink
Modifier and Type | Class and Description |
---|---|
protected class |
HdtBasedSink.HDTParser |
FileBasedSink.StreamStatus
Modifier and Type | Field and Description |
---|---|
private ExecutorService |
EXECUTION_SERVICE |
protected String |
inputType
input type for parsing the file
|
private static org.slf4j.Logger |
LOGGER |
protected FileOutputStream |
out
outputstream for Metadata
|
protected File |
outputDirectory |
DEFAULT_OUTPUT_LANG, outputLang, streamMapping, useCompression
Constructor and Description |
---|
HdtBasedSink(File outputDirectory)
Creates a temp file for the FileBasedsink storage
|
Modifier and Type | Method and Description |
---|---|
void |
addData(org.dice_research.squirrel.data.uri.CrawleableUri uri,
InputStream stream) |
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)
Recovers the temp file generated and parse it to hdt
|
void |
openSinkForUri(org.dice_research.squirrel.data.uri.CrawleableUri uri) |
addQuad, flushMetadata, generateFileName
private static final org.slf4j.Logger LOGGER
private final ExecutorService EXECUTION_SERVICE
protected File outputDirectory
protected String inputType
protected FileOutputStream out
public HdtBasedSink(File outputDirectory) throws IOException
outputDirectory
- IOException
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.TripleBasedSink
addTriple
in class FileBasedSink
public void openSinkForUri(org.dice_research.squirrel.data.uri.CrawleableUri uri)
openSinkForUri
in interface org.dice_research.squirrel.sink.SinkBase
openSinkForUri
in class FileBasedSink
public void closeSinkForUri(org.dice_research.squirrel.data.uri.CrawleableUri uri)
closeSinkForUri
in interface org.dice_research.squirrel.sink.SinkBase
closeSinkForUri
in class FileBasedSink
public void addData(org.dice_research.squirrel.data.uri.CrawleableUri uri, InputStream stream)
addData
in interface org.dice_research.squirrel.sink.UnstructuredDataSink
addData
in class FileBasedSink
Copyright © 2017–2020. All rights reserved.