Examples with Analyzer org.talend.dataquality.common.inference.Analyzer used on opensource projects

Example 6 with Analyzer

use of org.talend.dataquality.common.inference.Analyzer in project data-prep by Talend.

the class SchemaAnalysis method analyze.

@Override
public void analyze(String dataSetId) {
    if (StringUtils.isEmpty(dataSetId)) {
        throw new IllegalArgumentException("Data set id cannot be null or empty.");
    }
    DistributedLock datasetLock = repository.createDatasetMetadataLock(dataSetId);
    datasetLock.lock();
    try {
        DataSetMetadata metadata = repository.get(dataSetId);
        if (metadata == null) {
            LOGGER.info("Unable to analyze schema of data set #{}: seems to be removed.", dataSetId);
            return;
        }
        // Schema analysis
        try (Stream<DataSetRow> stream = store.stream(metadata, 100)) {
            LOGGER.info("Analyzing schema in dataset #{}...", dataSetId);
            // Configure analyzers
            final List<ColumnMetadata> columns = metadata.getRowMetadata().getColumns();
            try (Analyzer<Analyzers.Result> analyzer = analyzerService.schemaAnalysis(columns)) {
                // Determine schema for the content.
                stream.limit(100).map(row -> row.toArray(DataSetRow.SKIP_TDP_ID)).forEach(analyzer::analyze);
                // Find the best suitable type
                adapter.adapt(columns, analyzer.getResult());
                LOGGER.info("Analyzed schema in dataset #{}.", dataSetId);
                metadata.getLifecycle().schemaAnalyzed(true);
                repository.save(metadata);
            }
        } catch (Exception e) {
            LOGGER.error("Unable to analyse schema for dataset " + dataSetId + ".", e);
            TDPException.rethrowOrWrap(e, UNABLE_TO_ANALYZE_COLUMN_TYPES);
        }
    } finally {
        datasetLock.unlock();
    }
}