[
https://issues.apache.org/jira/browse/BEAM-3429?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Matt Darwin updated BEAM-3429:
------------------------------
Description:
I think I have found a bug in TextIO, in the way it handles URIs. I am told
that the TextIO.Write.to(String) method should take a URI string, but this
doesn't seem to work for me.
Test case inline:
{code:java}
import static org.junit.Assert.assertFalse;
import static org.junit.Assert.assertTrue;
import java.io.File;
import java.io.IOException;
import java.net.URI;
import java.nio.file.*;
import java.util.*;
import org.apache.beam.sdk.io.TextIO;
import org.apache.beam.sdk.testing.TestPipeline;
import org.apache.beam.sdk.transforms.Create;
import org.apache.beam.sdk.values.PCollection;
import org.junit.Rule;
import org.junit.Test;
public class Beam3429Test {
@Rule
public final transient TestPipeline pipeline = TestPipeline.create();
@Test
public void testBeamTextIO() throws IOException {
List<String> words = Arrays.asList("tom", "huck", "polly");
Create.Values<String> source = Create.of(words);
PCollection<String> coll = this.pipeline.apply(source);
String fileName = "test" + System.currentTimeMillis() + ".txt";
String fileURI = new File(fileName).toPath().toUri().toString();
// ie file:///full/unix/path/to/test.file
coll.apply(TextIO.write().to(fileURI));
//test passes if we use the line below instead of the above
// coll.apply(TextIO.write().to(fileName));
pipeline.run();
//read all sharded files:
Path dir = Paths.get(URI.create(fileURI)).getParent();
List<Path> files = new ArrayList<>();
Files.newDirectoryStream(dir, new DirectoryStream.Filter<Path>() {
@Override public boolean accept(Path entry) throws IOException {
return entry.toString().contains(fileName);
}
}).forEach(path -> files.add(path));
assertFalse("no files produced!", files.isEmpty());
List<String> fileContents = new ArrayList<>();
for (Path f : files) {
fileContents.addAll(Files.readAllLines(f));
}
assertTrue(fileContents.contains("tom"));
assertTrue(fileContents.contains("polly"));
}
}
{code}
was:
I think I have found a bug in TextIO, in the way it handles URIs. I am told
that the TextIO.Write.to(String) method should take a URI string, but this
doesn't seem to work for me.
Test case inline:
{code:java}
@Test
public void testBeamTextIO() throws IOException {
List<String> words = Arrays.asList("tom", "huck", "polly");
Create.Values<String> source = Create.of(words);
PCollection<String> coll = this.pipeline.apply(source);
String fileName = "test" + System.currentTimeMillis() + ".txt";
String fileURI = new File(fileName).toPath().toUri().toString();
// ie file:///full/unix/path/to/test.file
coll.apply(TextIO.write().to(fileURI));
//test passes if we use the line below instead of the above
// coll.apply(TextIO.write().to(fileName));
pipeline.run();
//read all sharded files:
Path dir = Paths.get(URI.create(fileURI)).getParent();
List<Path> files = new ArrayList<>();
Files.newDirectoryStream(dir, new DirectoryStream.Filter<Path>() {
@Override public boolean accept(Path entry) throws IOException {
return entry.toString().contains(fileName);
}
}).forEach(path -> files.add(path));
assertFalse("no files produced!", files.isEmpty());
List<String> fileContents = new ArrayList<>();
for (Path f : files) {
fileContents.addAll(Files.readAllLines(f));
}
assertTrue(fileContents.contains("tom"));
assertTrue(fileContents.contains("polly"));
}
{code}
> TextIO.Write not handling URI properly
> --------------------------------------
>
> Key: BEAM-3429
> URL: https://issues.apache.org/jira/browse/BEAM-3429
> Project: Beam
> Issue Type: Bug
> Components: beam-model
> Affects Versions: 2.2.0
> Environment: Mac OS X
> Reporter: Matt Darwin
> Assignee: Kenneth Knowles
>
> I think I have found a bug in TextIO, in the way it handles URIs. I am told
> that the TextIO.Write.to(String) method should take a URI string, but this
> doesn't seem to work for me.
> Test case inline:
> {code:java}
> import static org.junit.Assert.assertFalse;
> import static org.junit.Assert.assertTrue;
> import java.io.File;
> import java.io.IOException;
> import java.net.URI;
> import java.nio.file.*;
> import java.util.*;
> import org.apache.beam.sdk.io.TextIO;
> import org.apache.beam.sdk.testing.TestPipeline;
> import org.apache.beam.sdk.transforms.Create;
> import org.apache.beam.sdk.values.PCollection;
> import org.junit.Rule;
> import org.junit.Test;
> public class Beam3429Test {
> @Rule
> public final transient TestPipeline pipeline = TestPipeline.create();
> @Test
> public void testBeamTextIO() throws IOException {
> List<String> words = Arrays.asList("tom", "huck", "polly");
> Create.Values<String> source = Create.of(words);
> PCollection<String> coll = this.pipeline.apply(source);
> String fileName = "test" + System.currentTimeMillis() + ".txt";
> String fileURI = new File(fileName).toPath().toUri().toString();
> // ie file:///full/unix/path/to/test.file
> coll.apply(TextIO.write().to(fileURI));
> //test passes if we use the line below instead of the above
> // coll.apply(TextIO.write().to(fileName));
> pipeline.run();
> //read all sharded files:
> Path dir = Paths.get(URI.create(fileURI)).getParent();
> List<Path> files = new ArrayList<>();
> Files.newDirectoryStream(dir, new DirectoryStream.Filter<Path>() {
> @Override public boolean accept(Path entry) throws IOException {
> return entry.toString().contains(fileName);
> }
> }).forEach(path -> files.add(path));
> assertFalse("no files produced!", files.isEmpty());
> List<String> fileContents = new ArrayList<>();
> for (Path f : files) {
> fileContents.addAll(Files.readAllLines(f));
> }
> assertTrue(fileContents.contains("tom"));
> assertTrue(fileContents.contains("polly"));
> }
> }
> {code}
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
