Examples with MaxSizeSplitHintSpec org.apache.druid.data.input.MaxSizeSplitHintSpec used on opensource projects

Example 6 with MaxSizeSplitHintSpec

use of org.apache.druid.data.input.MaxSizeSplitHintSpec in project druid by druid-io.

the class LocalInputSourceTest method testCreateSplitsRespectingSplitHintSpec.

@Test
public void testCreateSplitsRespectingSplitHintSpec() {
    final long fileSize = 15;
    final HumanReadableBytes maxSplitSize = new HumanReadableBytes(50L);
    final List<File> files = mockFiles(10, fileSize);
    final LocalInputSource inputSource = new LocalInputSource(null, null, files);
    final List<InputSplit<List<File>>> splits = inputSource.createSplits(new NoopInputFormat(), new MaxSizeSplitHintSpec(maxSplitSize, null)).collect(Collectors.toList());
    Assert.assertEquals(4, splits.size());
    Assert.assertEquals(3, splits.get(0).get().size());
    Assert.assertEquals(3, splits.get(1).get().size());
    Assert.assertEquals(3, splits.get(2).get().size());
    Assert.assertEquals(1, splits.get(3).get().size());
}

Example 7 with MaxSizeSplitHintSpec

use of org.apache.druid.data.input.MaxSizeSplitHintSpec in project druid by druid-io.

the class CombiningInputSourceTest method testEstimateNumSplits.

@Test
public void testEstimateNumSplits() {
    final File file = EasyMock.niceMock(File.class);
    EasyMock.expect(file.length()).andReturn(5L).anyTimes();
    EasyMock.replay(file);
    final TestFileInputSource fileSource = new TestFileInputSource(generateFiles(3));
    final TestUriInputSource uriInputSource = new TestUriInputSource(ImmutableList.of(URI.create("http://test.com/http-test1"), URI.create("http://test.com/http-test2"), URI.create("http://test.com/http-test3")));
    final CombiningInputSource combiningInputSource = new CombiningInputSource(ImmutableList.of(fileSource, uriInputSource));
    Assert.assertEquals(combiningInputSource.estimateNumSplits(new NoopInputFormat(), new MaxSizeSplitHintSpec(new HumanReadableBytes(5L), null)), 6);
}

Example 8 with MaxSizeSplitHintSpec

use of org.apache.druid.data.input.MaxSizeSplitHintSpec in project druid by druid-io.

the class OssInputSourceTest method testCreateSplitsWithSplitHintSpecRespectingHint.

@Test
public void testCreateSplitsWithSplitHintSpecRespectingHint() {
    EasyMock.reset(OSSCLIENT);
    expectListObjects(PREFIXES.get(0), ImmutableList.of(EXPECTED_URIS.get(0)), CONTENT);
    expectListObjects(PREFIXES.get(1), ImmutableList.of(EXPECTED_URIS.get(1)), CONTENT);
    EasyMock.replay(OSSCLIENT);
    OssInputSource inputSource = new OssInputSource(OSSCLIENT, INPUT_DATA_CONFIG, null, PREFIXES, null, null);
    Stream<InputSplit<List<CloudObjectLocation>>> splits = inputSource.createSplits(new JsonInputFormat(JSONPathSpec.DEFAULT, null, null), new MaxSizeSplitHintSpec(new HumanReadableBytes(CONTENT.length * 3L), null));
    Assert.assertEquals(ImmutableList.of(EXPECTED_URIS.stream().map(CloudObjectLocation::new).collect(Collectors.toList())), splits.map(InputSplit::get).collect(Collectors.toList()));
    EasyMock.verify(OSSCLIENT);
}

Example 9 with MaxSizeSplitHintSpec

use of org.apache.druid.data.input.MaxSizeSplitHintSpec in project druid by druid-io.

the class OssInputSourceTest method testWithPrefixesSplit.

@Test
public void testWithPrefixesSplit() {
    EasyMock.reset(OSSCLIENT);
    expectListObjects(PREFIXES.get(0), ImmutableList.of(EXPECTED_URIS.get(0)), CONTENT);
    expectListObjects(PREFIXES.get(1), ImmutableList.of(EXPECTED_URIS.get(1)), CONTENT);
    EasyMock.replay(OSSCLIENT);
    OssInputSource inputSource = new OssInputSource(OSSCLIENT, INPUT_DATA_CONFIG, null, PREFIXES, null, null);
    Stream<InputSplit<List<CloudObjectLocation>>> splits = inputSource.createSplits(new JsonInputFormat(JSONPathSpec.DEFAULT, null, null), new MaxSizeSplitHintSpec(null, 1));
    Assert.assertEquals(EXPECTED_COORDS, splits.map(InputSplit::get).collect(Collectors.toList()));
    EasyMock.verify(OSSCLIENT);
}

Example 10 with MaxSizeSplitHintSpec

use of org.apache.druid.data.input.MaxSizeSplitHintSpec in project druid by druid-io.

the class GoogleCloudStorageInputSourceTest method testWithPrefixesSplit.

@Test
public void testWithPrefixesSplit() throws IOException {
    EasyMock.reset(STORAGE);
    EasyMock.reset(INPUT_DATA_CONFIG);
    addExpectedPrefixObjects(PREFIXES.get(0), ImmutableList.of(EXPECTED_URIS.get(0)));
    addExpectedPrefixObjects(PREFIXES.get(1), ImmutableList.of(EXPECTED_URIS.get(1)));
    EasyMock.expect(INPUT_DATA_CONFIG.getMaxListingLength()).andReturn(MAX_LISTING_LENGTH);
    EasyMock.replay(STORAGE);
    EasyMock.replay(INPUT_DATA_CONFIG);
    GoogleCloudStorageInputSource inputSource = new GoogleCloudStorageInputSource(STORAGE, INPUT_DATA_CONFIG, null, PREFIXES, null);
    Stream<InputSplit<List<CloudObjectLocation>>> splits = inputSource.createSplits(new JsonInputFormat(JSONPathSpec.DEFAULT, null, null), new MaxSizeSplitHintSpec(null, 1));
    Assert.assertEquals(EXPECTED_OBJECTS, splits.map(InputSplit::get).collect(Collectors.toList()));
}