-
Notifications
You must be signed in to change notification settings - Fork 43
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
6 changed files
with
176 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
94 changes: 94 additions & 0 deletions
94
runner/src/main/java/org/ananas/runner/paginator/files/GCSPaginator.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,94 @@ | ||
package org.ananas.runner.paginator.files; | ||
|
||
import com.google.api.gax.paging.Page; | ||
import com.google.cloud.storage.*; | ||
import org.ananas.runner.kernel.paginate.AutoDetectedSchemaPaginator; | ||
import org.ananas.runner.kernel.paginate.Paginator; | ||
import org.ananas.runner.model.steps.files.JsonPaginator; | ||
import org.ananas.runner.model.steps.files.TextPaginator; | ||
import org.apache.beam.sdk.schemas.Schema; | ||
import org.apache.beam.sdk.values.Row; | ||
|
||
import java.util.Map; | ||
|
||
public class GCSPaginator extends AutoDetectedSchemaPaginator { | ||
|
||
private String format; | ||
private Paginator paginator; | ||
|
||
public GCSPaginator(String id, | ||
String type, | ||
Map<String, Object> config, | ||
Schema schema) { | ||
super(id, type, config, schema); | ||
} | ||
|
||
@Override | ||
public Iterable<Row> iterateRows(Integer page, Integer pageSize) { | ||
|
||
return paginator.paginateRows( | ||
page == null ? 0 : Integer.valueOf(page), | ||
pageSize == null ? 1000 : Integer.valueOf(pageSize)).getRight(); | ||
} | ||
|
||
@Override | ||
public Schema autodetect() { | ||
if (format.toLowerCase().equals("csv")) { | ||
return ((CSVPaginator)paginator).autodetect(); | ||
} | ||
return this.schema;//already autodetected | ||
} | ||
|
||
@Override | ||
public void parseConfig(Map<String, Object> config) { | ||
System.out.println("Hey ho " + config); | ||
this.format = (String)config.get("format"); | ||
String bucketName = (String)config.get("bucket"); | ||
String prefix = (String)config.get("path"); | ||
System.out.println("Hey ho " + prefix); | ||
|
||
//get bucket | ||
BucketInfo.Builder builder = Bucket.newBuilder(bucketName); | ||
|
||
// Instantiates a client | ||
Storage storage = StorageOptions.getDefaultInstance().getService(); | ||
|
||
// The name for the new bucket | ||
//String bucketName = "id5"; | ||
//String prefix = "appnexus/20180802"; | ||
|
||
// Creates the new bucket | ||
Page<Blob> l = storage.list(bucketName, Storage.BlobListOption.prefix(prefix)); | ||
|
||
String url = null; | ||
|
||
if (l.hasNextPage()) { | ||
throw new IllegalArgumentException("There is no files in this bucket"); | ||
} | ||
|
||
for (Blob b : l.iterateAll()) { | ||
url = b.getMediaLink(); | ||
this.config.put("path", url); | ||
break; | ||
} | ||
|
||
this.config.put("path", url); | ||
|
||
switch (format.toLowerCase()) { | ||
case "csv": | ||
paginator = new CSVPaginator(this.id, this.type, this.config, schema); | ||
break; | ||
case "json": | ||
paginator = new JsonPaginator(this.id, url); | ||
break; | ||
case "text": | ||
paginator = new TextPaginator(this.id, url); | ||
break; | ||
default: | ||
throw new IllegalArgumentException("Unsupported format " + format); | ||
} | ||
} | ||
|
||
|
||
|
||
} |
53 changes: 53 additions & 0 deletions
53
runner/src/main/java/org/ananas/runner/steprunner/files/GCSConnector.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,53 @@ | ||
package org.ananas.runner.steprunner.files; | ||
|
||
import org.ananas.runner.kernel.ConnectorStepRunner; | ||
import org.ananas.runner.kernel.model.Step; | ||
import org.ananas.runner.kernel.model.StepType; | ||
import org.ananas.runner.kernel.paginate.AutoDetectedSchemaPaginator; | ||
import org.ananas.runner.kernel.paginate.PaginatorFactory; | ||
import org.ananas.runner.steprunner.files.csv.BeamTextCSVCustomTable; | ||
import org.apache.beam.sdk.Pipeline; | ||
import org.apache.beam.sdk.schemas.Schema; | ||
import org.apache.beam.sdk.transforms.Create; | ||
import org.apache.beam.sdk.values.PCollection; | ||
import org.apache.beam.sdk.values.Row; | ||
import org.apache.commons.lang3.tuple.MutablePair; | ||
|
||
public class GCSConnector extends ConnectorStepRunner { | ||
|
||
private static final long serialVersionUID = -6637097842918012864L; | ||
|
||
public GCSConnector(Pipeline pipeline, Step step, boolean doSampling, boolean isTest) { | ||
super(pipeline, step, doSampling, isTest); | ||
} | ||
|
||
public void build() { | ||
System.out.println(step.config); | ||
//GCSStepConfig config = new GCSStepConfig(StepType.Connector, step.config); | ||
|
||
Schema schema = step.getBeamSchema(); | ||
|
||
AutoDetectedSchemaPaginator paginator = | ||
PaginatorFactory.of(stepId, step.metadataId, step.type, step.config, schema) | ||
.buildPaginator(); | ||
schema = paginator.getSchema(); | ||
|
||
if (schema == null || step.forceAutoDetectSchema()) { | ||
// find the paginator bind to it | ||
|
||
} | ||
|
||
this.stepId = stepId; | ||
|
||
Integer page = 1; | ||
Integer pageSize = 100; | ||
|
||
MutablePair<Schema, Iterable<Row>> c = paginator.paginateRows(page, pageSize); | ||
|
||
|
||
Create.Values<Row> o = Create.of(c.getRight()); | ||
this.output = this.pipeline.apply(o); | ||
this.output.setRowSchema(schema); | ||
} | ||
} | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters