Examples with DatasetUpdatedEvent org.talend.dataprep.dataset.event.DatasetUpdatedEvent used on opensource projects

Example 1 with DatasetUpdatedEvent

use of org.talend.dataprep.dataset.event.DatasetUpdatedEvent in project data-prep by Talend.

the class TransformAPITest method testShouldEvictPreparationCacheOnDataSetUpdate.

@Test
public void testShouldEvictPreparationCacheOnDataSetUpdate() throws Exception {
    // given
    final String preparationId = testClient.createPreparationFromFile("dataset/dataset_TDP-2165.csv", "testDataset", home.getId());
    testClient.applyAction(preparationId, IOUtils.toString(this.getClass().getResourceAsStream("transformation/TDP-2165.json"), UTF_8));
    testClient.getPreparation(preparationId);
    final Preparation preparation = preparationRepository.get(preparationId, Preparation.class);
    final TransformationCacheKey transformationCacheKey = // 
    cacheKeyGenerator.generateContentKey(// 
    preparation.getDataSetId(), // 
    preparationId, // 
    preparation.getHeadId(), // 
    "JSON", // 
    HEAD, // no filter
    "");
    assertTrue(contentCache.has(transformationCacheKey));
    // when
    context.publishEvent(new DatasetUpdatedEvent(dataSetMetadataRepository.get(preparation.getDataSetId())));
    // then
    assertFalse(contentCache.has(transformationCacheKey));
}

Example 2 with DatasetUpdatedEvent

use of org.talend.dataprep.dataset.event.DatasetUpdatedEvent 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();
    }
}

Example 3 with DatasetUpdatedEvent

use of org.talend.dataprep.dataset.event.DatasetUpdatedEvent in project data-prep by Talend.

the class DatasetUpdateListener method onUpdate.

@EventListener
public void onUpdate(DatasetUpdatedEvent event) {
    // when we update a dataset we need to clean cache
    final DataSetMetadata dataSetMetadata = event.getSource();
    final ContentCacheKey sampleKey = () -> "dataset-sample_" + dataSetMetadata.getId();
    LOGGER.debug("Evicting sample cache entry for #{}", dataSetMetadata.getId());
    publisher.publishEvent(new CleanCacheEvent(sampleKey));
    LOGGER.debug("Evicting sample cache entry for #{} done.", dataSetMetadata.getId());
    LOGGER.debug("Evicting transformation cache entry for dataset #{}", dataSetMetadata.getId());
    publisher.publishEvent(new CleanCacheEvent(new ContentCacheKey() {

        @Override
        public String getKey() {
            return dataSetMetadata.getId();
        }

        @Override
        public Predicate<String> getMatcher() {
            String regex = ".*_" + getKey() + "_.*";
            // Build regular expression matcher
            final Pattern pattern = Pattern.compile(regex);
            return str -> pattern.matcher(str).matches();
        }
    }, Boolean.TRUE));
    LOGGER.debug("Evicting transformation cache entry for dataset  #{} done.", dataSetMetadata.getId());
}

Example 4 with DatasetUpdatedEvent

use of org.talend.dataprep.dataset.event.DatasetUpdatedEvent in project data-prep by Talend.

the class DataSetService method updateDataSet.

/**
 * Updates a data set metadata. If no data set exists for given id, a {@link TDPException} is thrown.
 *
 * @param dataSetId The id of data set to be updated.
 * @param dataSetMetadata 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}", method = PUT)
@ApiOperation(value = "Update a data set metadata by id", notes = "Update a data set metadata according to the content of the PUT body. Id should be a UUID returned by the list operation. Not valid or non existing data set id return an error response.")
@Timed
public void updateDataSet(@PathVariable(value = "id") @ApiParam(name = "id", value = "Id of the data set to update") String dataSetId, @RequestBody DataSetMetadata dataSetMetadata) {
    if (dataSetMetadata != null && dataSetMetadata.getName() != null) {
        checkDataSetName(dataSetMetadata.getName());
    }
    final DistributedLock lock = dataSetMetadataRepository.createDatasetMetadataLock(dataSetId);
    lock.lock();
    try {
        DataSetMetadata metadataForUpdate = dataSetMetadataRepository.get(dataSetId);
        if (metadataForUpdate == null) {
            // No need to silently create the data set metadata: associated content will most likely not exist.
            throw new TDPException(DataSetErrorCodes.DATASET_DOES_NOT_EXIST, build().put("id", dataSetId));
        }
        LOG.debug("updateDataSet: {}", dataSetMetadata);
        publisher.publishEvent(new DatasetUpdatedEvent(dataSetMetadata));
        // 
        // Only part of the metadata can be updated, so the original dataset metadata is loaded and updated
        // 
        DataSetMetadata original = metadataBuilder.metadata().copy(metadataForUpdate).build();
        try {
            // update the name
            metadataForUpdate.setName(dataSetMetadata.getName());
            // update the sheet content (in case of a multi-sheet excel file)
            if (metadataForUpdate.getSchemaParserResult() != null) {
                Optional<Schema.SheetContent> sheetContentFound = metadataForUpdate.getSchemaParserResult().getSheetContents().stream().filter(sheetContent -> dataSetMetadata.getSheetName().equals(sheetContent.getName())).findFirst();
                if (sheetContentFound.isPresent()) {
                    List<ColumnMetadata> columnMetadatas = sheetContentFound.get().getColumnMetadatas();
                    if (metadataForUpdate.getRowMetadata() == null) {
                        metadataForUpdate.setRowMetadata(new RowMetadata(emptyList()));
                    }
                    metadataForUpdate.getRowMetadata().setColumns(columnMetadatas);
                }
                metadataForUpdate.setSheetName(dataSetMetadata.getSheetName());
                metadataForUpdate.setSchemaParserResult(null);
            }
            // Location updates
            metadataForUpdate.setLocation(dataSetMetadata.getLocation());
            // update parameters & encoding (so that user can change import parameters for CSV)
            metadataForUpdate.getContent().setParameters(dataSetMetadata.getContent().getParameters());
            metadataForUpdate.setEncoding(dataSetMetadata.getEncoding());
            // update limit
            final Optional<Long> newLimit = dataSetMetadata.getContent().getLimit();
            newLimit.ifPresent(limit -> metadataForUpdate.getContent().setLimit(limit));
            // Validate that the new data set metadata and removes the draft status
            final String formatFamilyId = dataSetMetadata.getContent().getFormatFamilyId();
            if (formatFamilyFactory.hasFormatFamily(formatFamilyId)) {
                FormatFamily format = formatFamilyFactory.getFormatFamily(formatFamilyId);
                try {
                    DraftValidator draftValidator = format.getDraftValidator();
                    DraftValidator.Result result = draftValidator.validate(dataSetMetadata);
                    if (result.isDraft()) {
                        // This is not an exception case: data set may remain a draft after update (although rather
                        // unusual)
                        LOG.warn("Data set #{} is still a draft after update.", dataSetId);
                        return;
                    }
                    // Data set metadata to update is no longer a draft
                    metadataForUpdate.setDraft(false);
                } catch (UnsupportedOperationException e) {
                // no need to validate draft here
                }
            }
            // update schema
            formatAnalyzer.update(original, metadataForUpdate);
            // save the result
            dataSetMetadataRepository.save(metadataForUpdate);
            // all good mate!! so send that to jms
            // Asks for a in depth schema analysis (for column type information).
            analyzeDataSet(dataSetId, true, singletonList(FormatAnalysis.class));
        } catch (TDPException e) {
            throw e;
        } catch (Exception e) {
            throw new TDPException(UNABLE_TO_CREATE_OR_UPDATE_DATASET, e);
        }
    } finally {
        lock.unlock();
    }
}