Search in sources :

Example 1 with UpdateDataSetCacheKey

use of org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey in project data-prep by Talend.

the class DataSetServiceTest method updateRawContentShouldCheckAvailableSpaceEvenIfTheSizeIsNotProvidedByFrontEnd.

@Test
public void updateRawContentShouldCheckAvailableSpaceEvenIfTheSizeIsNotProvidedByFrontEnd() throws Exception {
    // given
    final String datasetId = createCSVDataSet(this.getClass().getResourceAsStream("../avengers.csv"), "dataset2");
    Mockito.reset(quotaService);
    Mockito.when(quotaService.getAvailableSpace()).thenReturn(10L);
    // when
    final Response response = // 
    given().body(IOUtils.toString(this.getClass().getResourceAsStream(TAGADA_CSV), UTF_8)).when().put("/datasets/{id}/raw", datasetId);
    // then
    assertEquals(413, response.getStatusCode());
    assertFalse(cacheManager.has(new UpdateDataSetCacheKey(datasetId)));
}
Also used : Response(com.jayway.restassured.response.Response) UpdateDataSetCacheKey(org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey) Matchers.containsString(org.hamcrest.Matchers.containsString) Matchers.isEmptyString(org.hamcrest.Matchers.isEmptyString) DataSetBaseTest(org.talend.dataprep.dataset.DataSetBaseTest) Test(org.junit.Test)

Example 2 with UpdateDataSetCacheKey

use of org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey in project data-prep by Talend.

the class DataSetServiceTest method updateRawContentShouldCheckDataSetSize.

@Test
public void updateRawContentShouldCheckDataSetSize() throws Exception {
    // given
    final String datasetId = createCSVDataSet(this.getClass().getResourceAsStream("../avengers.csv"), "dataset2");
    Mockito.reset(quotaService);
    TDPException exception = new TDPException(DataSetErrorCodes.MAX_STORAGE_MAY_BE_EXCEEDED);
    doThrow(exception).when(quotaService).checkIfAddingSizeExceedsAvailableStorage(Math.abs(113L - 298L));
    // when
    final Response response = // 
    given().body(IOUtils.toString(this.getClass().getResourceAsStream(TAGADA_CSV), UTF_8)).when().queryParam("size", 113).put("/datasets/{id}/raw", datasetId);
    // then
    assertEquals(413, response.getStatusCode());
    assertFalse(cacheManager.has(new UpdateDataSetCacheKey(datasetId)));
}
Also used : TDPException(org.talend.dataprep.exception.TDPException) Response(com.jayway.restassured.response.Response) UpdateDataSetCacheKey(org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey) Matchers.containsString(org.hamcrest.Matchers.containsString) Matchers.isEmptyString(org.hamcrest.Matchers.isEmptyString) DataSetBaseTest(org.talend.dataprep.dataset.DataSetBaseTest) Test(org.junit.Test)

Example 3 with UpdateDataSetCacheKey

use of org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey in project data-prep by Talend.

the class DataSetService method updateRawDataSet.

/**
 * Updates a data set content and metadata. If no data set exists for given id, data set is silently created.
 *
 * @param dataSetId The id of data set to be updated.
 * @param name The new name for the data set. Empty name (or <code>null</code>) does not update dataset name.
 * @param dataSetContent The new content for the data set. If empty, existing content will <b>not</b> be replaced.
 * For delete operation, look at {@link #delete(String)}.
 */
@RequestMapping(value = "/datasets/{id}/raw", method = PUT)
@ApiOperation(value = "Update a data set by id", notes = "Update a data set content based on provided id and PUT body. Id should be a UUID returned by the list operation. Not valid or non existing data set id returns empty content. For documentation purposes, body is typed as 'text/plain' but operation accepts binary content too.")
@Timed
@VolumeMetered
public String updateRawDataSet(// 
@PathVariable(value = "id") @ApiParam(name = "id", value = "Id of the data set to update") String dataSetId, // 
@RequestParam(value = "name", required = false) @ApiParam(name = "name", value = "New value for the data set name") String name, // 
@RequestParam(value = "size", required = false) @ApiParam(name = "size", value = "The size of the dataSet") Long size, @ApiParam(value = "content") InputStream dataSetContent) {
    LOG.debug("updating dataset content #{}", dataSetId);
    if (name != null) {
        checkDataSetName(name);
    }
    DataSetMetadata currentDataSetMetadata = dataSetMetadataRepository.get(dataSetId);
    if (currentDataSetMetadata == null) {
        return create(name, null, size, TEXT_PLAIN_VALUE, dataSetContent);
    } else {
        // just like the creation, let's make sure invalid size forbids dataset creation
        if (size != null && size < 0) {
            LOG.warn("invalid size provided {}", size);
            throw new TDPException(UNSUPPORTED_CONTENT);
        }
        final UpdateDataSetCacheKey cacheKey = new UpdateDataSetCacheKey(currentDataSetMetadata.getId());
        final DistributedLock lock = dataSetMetadataRepository.createDatasetMetadataLock(currentDataSetMetadata.getId());
        try {
            lock.lock();
            // check the size if it's available (quick win)
            if (size != null && size > 0) {
                quotaService.checkIfAddingSizeExceedsAvailableStorage(Math.abs(size - currentDataSetMetadata.getDataSetSize()));
            }
            final DataSetMetadataBuilder datasetBuilder = metadataBuilder.metadata().id(currentDataSetMetadata.getId());
            datasetBuilder.copyNonContentRelated(currentDataSetMetadata);
            datasetBuilder.modified(System.currentTimeMillis());
            if (!StringUtils.isEmpty(name)) {
                datasetBuilder.name(name);
            }
            final DataSetMetadata updatedDataSetMetadata = datasetBuilder.build();
            // Save data set content into cache to make sure there's enough space in the content store
            final long maxDataSetSizeAllowed = getMaxDataSetSizeAllowed();
            final StrictlyBoundedInputStream sizeCalculator = new StrictlyBoundedInputStream(dataSetContent, maxDataSetSizeAllowed);
            try (OutputStream cacheEntry = cacheManager.put(cacheKey, TimeToLive.DEFAULT)) {
                IOUtils.copy(sizeCalculator, cacheEntry);
            }
            // once fully copied to the cache, we know for sure that the content store has enough space, so let's copy
            // from the cache to the content store
            PipedInputStream toContentStore = new PipedInputStream();
            PipedOutputStream fromCache = new PipedOutputStream(toContentStore);
            Runnable r = () -> {
                try (final InputStream input = cacheManager.get(cacheKey)) {
                    IOUtils.copy(input, fromCache);
                    // it's important to close this stream, otherwise the piped stream will never close
                    fromCache.close();
                } catch (IOException e) {
                    throw new TDPException(UNABLE_TO_CREATE_OR_UPDATE_DATASET, e);
                }
            };
            executor.execute(r);
            contentStore.storeAsRaw(updatedDataSetMetadata, toContentStore);
            // update the dataset metadata with its new size
            updatedDataSetMetadata.setDataSetSize(sizeCalculator.getTotal());
            dataSetMetadataRepository.save(updatedDataSetMetadata);
            // publishing update event
            publisher.publishEvent(new DatasetUpdatedEvent(updatedDataSetMetadata));
        } catch (StrictlyBoundedInputStream.InputStreamTooLargeException e) {
            LOG.warn("Dataset update {} cannot be done, new content is too big", currentDataSetMetadata.getId());
            throw new TDPException(MAX_STORAGE_MAY_BE_EXCEEDED, e, build().put("limit", e.getMaxSize()));
        } catch (IOException e) {
            LOG.error("Error updating the dataset", e);
            throw new TDPException(UNABLE_TO_CREATE_OR_UPDATE_DATASET, e);
        } finally {
            dataSetContentToNull(dataSetContent);
            // whatever the outcome the cache needs to be cleaned
            if (cacheManager.has(cacheKey)) {
                cacheManager.evict(cacheKey);
            }
            lock.unlock();
        }
        // Content was changed, so queue events (format analysis, content indexing for search...)
        analyzeDataSet(currentDataSetMetadata.getId(), true, emptyList());
        return currentDataSetMetadata.getId();
    }
}
Also used : DataSetMetadataBuilder(org.talend.dataprep.dataset.DataSetMetadataBuilder) PipedInputStream(java.io.PipedInputStream) StrictlyBoundedInputStream(org.talend.dataprep.dataset.store.content.StrictlyBoundedInputStream) InputStream(java.io.InputStream) PipedOutputStream(java.io.PipedOutputStream) NullOutputStream(org.apache.commons.io.output.NullOutputStream) OutputStream(java.io.OutputStream) PipedOutputStream(java.io.PipedOutputStream) PipedInputStream(java.io.PipedInputStream) IOException(java.io.IOException) DataSetMetadata(org.talend.dataprep.api.dataset.DataSetMetadata) TDPException(org.talend.dataprep.exception.TDPException) DistributedLock(org.talend.dataprep.lock.DistributedLock) StrictlyBoundedInputStream(org.talend.dataprep.dataset.store.content.StrictlyBoundedInputStream) DatasetUpdatedEvent(org.talend.dataprep.dataset.event.DatasetUpdatedEvent) UpdateDataSetCacheKey(org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey) VolumeMetered(org.talend.dataprep.metrics.VolumeMetered) Timed(org.talend.dataprep.metrics.Timed) ApiOperation(io.swagger.annotations.ApiOperation) RequestMapping(org.springframework.web.bind.annotation.RequestMapping)

Example 4 with UpdateDataSetCacheKey

use of org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey in project data-prep by Talend.

the class DataSetServiceTest method copyDataSetShouldCheckIfThereIsEnoughSpaceAvailable.

@Test
public void copyDataSetShouldCheckIfThereIsEnoughSpaceAvailable() throws Exception {
    // given
    final String datasetId = createCSVDataSet(this.getClass().getResourceAsStream("../avengers.csv"), "dataset2");
    Mockito.reset(quotaService);
    Mockito.when(quotaService.getAvailableSpace()).thenReturn(10L);
    // when
    final Response response = // 
    given().queryParam("copyName", // 
    "copy").post("/datasets/{id}/copy", datasetId);
    // then
    assertEquals(413, response.getStatusCode());
    assertFalse(cacheManager.has(new UpdateDataSetCacheKey(datasetId)));
}
Also used : Response(com.jayway.restassured.response.Response) UpdateDataSetCacheKey(org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey) Matchers.containsString(org.hamcrest.Matchers.containsString) Matchers.isEmptyString(org.hamcrest.Matchers.isEmptyString) DataSetBaseTest(org.talend.dataprep.dataset.DataSetBaseTest) Test(org.junit.Test)

Aggregations

UpdateDataSetCacheKey (org.talend.dataprep.dataset.service.cache.UpdateDataSetCacheKey)4 Response (com.jayway.restassured.response.Response)3 Matchers.containsString (org.hamcrest.Matchers.containsString)3 Matchers.isEmptyString (org.hamcrest.Matchers.isEmptyString)3 Test (org.junit.Test)3 DataSetBaseTest (org.talend.dataprep.dataset.DataSetBaseTest)3 TDPException (org.talend.dataprep.exception.TDPException)2 ApiOperation (io.swagger.annotations.ApiOperation)1 IOException (java.io.IOException)1 InputStream (java.io.InputStream)1 OutputStream (java.io.OutputStream)1 PipedInputStream (java.io.PipedInputStream)1 PipedOutputStream (java.io.PipedOutputStream)1 NullOutputStream (org.apache.commons.io.output.NullOutputStream)1 RequestMapping (org.springframework.web.bind.annotation.RequestMapping)1 DataSetMetadata (org.talend.dataprep.api.dataset.DataSetMetadata)1 DataSetMetadataBuilder (org.talend.dataprep.dataset.DataSetMetadataBuilder)1 DatasetUpdatedEvent (org.talend.dataprep.dataset.event.DatasetUpdatedEvent)1 StrictlyBoundedInputStream (org.talend.dataprep.dataset.store.content.StrictlyBoundedInputStream)1 DistributedLock (org.talend.dataprep.lock.DistributedLock)1