Search in sources :

Example 1 with Flag

use of org.talend.dataprep.api.dataset.row.Flag in project data-prep by Talend.

the class TransformationService method getSemanticDomains.

/**
 * Return the semantic domains for the given parameters.
 *
 * @param metadata the dataset metadata.
 * @param columnId the column id to analyze.
 * @param records the dataset records.
 * @return the semantic domains for the given parameters.
 * @throws IOException can happen...
 */
private List<SemanticDomain> getSemanticDomains(DataSetMetadata metadata, String columnId, InputStream records) throws IOException {
    // copy the column metadata and set the semantic domain forced flag to false to make sure the statistics adapter set all
    // available domains
    final ColumnMetadata columnMetadata = // 
    column().copy(// 
    metadata.getRowMetadata().getById(columnId)).semanticDomainForce(// 
    false).build();
    final Analyzer<Analyzers.Result> analyzer = analyzerService.build(columnMetadata, SEMANTIC);
    analyzer.init();
    try (final JsonParser parser = mapper.getFactory().createParser(new InputStreamReader(records, UTF_8))) {
        final DataSet dataSet = mapper.readerFor(DataSet.class).readValue(parser);
        dataSet.getRecords().map(// 
        r -> r.get(columnId)).forEach(analyzer::analyze);
        analyzer.end();
    }
    final List<Analyzers.Result> analyzerResult = analyzer.getResult();
    statisticsAdapter.adapt(singletonList(columnMetadata), analyzerResult);
    return columnMetadata.getSemanticDomains();
}
Also used : VolumeMetered(org.talend.dataprep.metrics.VolumeMetered) LocaleContextHolder(org.springframework.context.i18n.LocaleContextHolder) StringUtils(org.apache.commons.lang.StringUtils) ContentCacheKey(org.talend.dataprep.cache.ContentCacheKey) TdqCategories(org.talend.dataquality.semantic.broadcast.TdqCategories) Autowired(org.springframework.beans.factory.annotation.Autowired) ApiParam(io.swagger.annotations.ApiParam) PreviewParameters(org.talend.dataprep.transformation.preview.api.PreviewParameters) ExportFormatMessage(org.talend.dataprep.format.export.ExportFormatMessage) ActionContext(org.talend.dataprep.transformation.api.action.context.ActionContext) Collections.singletonList(java.util.Collections.singletonList) ScopeCategory(org.talend.dataprep.transformation.actions.category.ScopeCategory) Valid(javax.validation.Valid) SemanticDomain(org.talend.dataprep.api.dataset.statistics.SemanticDomain) BeanConversionService(org.talend.dataprep.conversions.BeanConversionService) GetPrepMetadataAsyncCondition(org.talend.dataprep.async.conditional.GetPrepMetadataAsyncCondition) TaskExecutor(org.springframework.core.task.TaskExecutor) DataSet(org.talend.dataprep.api.dataset.DataSet) ExportParametersUtil(org.talend.dataprep.api.export.ExportParametersUtil) StepDiff(org.talend.dataprep.api.preparation.StepDiff) PreparationDetailsGet(org.talend.dataprep.command.preparation.PreparationDetailsGet) HEAD(org.talend.dataprep.api.export.ExportParameters.SourceType.HEAD) APPLICATION_OCTET_STREAM_VALUE(org.springframework.http.MediaType.APPLICATION_OCTET_STREAM_VALUE) Resource(javax.annotation.Resource) StreamingResponseBody(org.springframework.web.servlet.mvc.method.annotation.StreamingResponseBody) JSON(org.talend.dataprep.transformation.format.JsonFormat.JSON) PreparationGetContentUrlGenerator(org.talend.dataprep.async.result.PreparationGetContentUrlGenerator) SecurityProxy(org.talend.dataprep.security.SecurityProxy) Stream(java.util.stream.Stream) Builder.column(org.talend.dataprep.api.dataset.ColumnMetadata.Builder.column) org.springframework.web.bind.annotation(org.springframework.web.bind.annotation) GZIPOutputStream(java.util.zip.GZIPOutputStream) DynamicType(org.talend.dataprep.transformation.api.action.dynamic.DynamicType) RunnableAction(org.talend.dataprep.transformation.actions.common.RunnableAction) Analyzers(org.talend.dataquality.common.inference.Analyzers) java.util(java.util) TransformationErrorCodes(org.talend.dataprep.exception.error.TransformationErrorCodes) GenericParameter(org.talend.dataprep.transformation.api.action.dynamic.GenericParameter) Configuration(org.talend.dataprep.transformation.api.transformer.configuration.Configuration) PreviewConfiguration(org.talend.dataprep.transformation.api.transformer.configuration.PreviewConfiguration) AnalyzerService(org.talend.dataprep.quality.AnalyzerService) TransformationMetadataCacheKey(org.talend.dataprep.cache.TransformationMetadataCacheKey) PrepMetadataExecutionIdGenerator(org.talend.dataprep.async.generator.PrepMetadataExecutionIdGenerator) PREPARATION_DOES_NOT_EXIST(org.talend.dataprep.exception.error.PreparationErrorCodes.PREPARATION_DOES_NOT_EXIST) Api(io.swagger.annotations.Api) Preparation(org.talend.dataprep.api.preparation.Preparation) ActionRegistry(org.talend.dataprep.transformation.pipeline.ActionRegistry) GetPrepContentAsyncCondition(org.talend.dataprep.async.conditional.GetPrepContentAsyncCondition) TransformationContext(org.talend.dataprep.transformation.api.action.context.TransformationContext) AggregationService(org.talend.dataprep.transformation.aggregation.AggregationService) NullOutputStream(org.apache.commons.io.output.NullOutputStream) StatisticsAdapter(org.talend.dataprep.dataset.StatisticsAdapter) DataSetGetMetadata(org.talend.dataprep.command.dataset.DataSetGetMetadata) Timed(org.talend.dataprep.metrics.Timed) ColumnMetadata(org.talend.dataprep.api.dataset.ColumnMetadata) DataSetGet(org.talend.dataprep.command.dataset.DataSetGet) AggregationResult(org.talend.dataprep.transformation.aggregation.api.AggregationResult) LoggerFactory(org.slf4j.LoggerFactory) Flag(org.talend.dataprep.api.dataset.row.Flag) SEMANTIC(org.talend.dataprep.quality.AnalyzerService.Analysis.SEMANTIC) ActionParser(org.talend.dataprep.transformation.api.action.ActionParser) CacheKeyGenerator(org.talend.dataprep.cache.CacheKeyGenerator) ApiOperation(io.swagger.annotations.ApiOperation) DataSetMetadata(org.talend.dataprep.api.dataset.DataSetMetadata) ExportParameters(org.talend.dataprep.api.export.ExportParameters) PrepMetadataGetContentUrlGenerator(org.talend.dataprep.async.result.PrepMetadataGetContentUrlGenerator) MediaType(org.springframework.http.MediaType) PublicAPI(org.talend.dataprep.security.PublicAPI) RequestMethod(org.springframework.web.bind.annotation.RequestMethod) Collectors(java.util.stream.Collectors) ContentCache(org.talend.dataprep.cache.ContentCache) UNEXPECTED_EXCEPTION(org.talend.dataprep.exception.error.TransformationErrorCodes.UNEXPECTED_EXCEPTION) TransformerFactory(org.talend.dataprep.transformation.api.transformer.TransformerFactory) CommonErrorCodes(org.talend.dataprep.exception.error.CommonErrorCodes) Analyzer(org.talend.dataquality.common.inference.Analyzer) ActionDefinition(org.talend.dataprep.api.action.ActionDefinition) PreparationExportStrategy(org.talend.dataprep.transformation.service.export.PreparationExportStrategy) RowMetadata(org.talend.dataprep.api.dataset.RowMetadata) ExportFormat(org.talend.dataprep.format.export.ExportFormat) TDPException(org.talend.dataprep.exception.TDPException) JsonErrorCodeDescription(org.talend.dataprep.exception.json.JsonErrorCodeDescription) ExceptionContext.build(org.talend.daikon.exception.ExceptionContext.build) ExportParametersExecutionIdGenerator(org.talend.dataprep.async.generator.ExportParametersExecutionIdGenerator) ExceptionContext(org.talend.daikon.exception.ExceptionContext) org.talend.dataprep.async(org.talend.dataprep.async) Suggestion(org.talend.dataprep.transformation.api.transformer.suggestion.Suggestion) SuggestionEngine(org.talend.dataprep.transformation.api.transformer.suggestion.SuggestionEngine) Logger(org.slf4j.Logger) LocaleContextHolder.getLocale(org.springframework.context.i18n.LocaleContextHolder.getLocale) JsonParser(com.fasterxml.jackson.core.JsonParser) UTF_8(java.nio.charset.StandardCharsets.UTF_8) Step(org.talend.dataprep.api.preparation.Step) APPLICATION_JSON_VALUE(org.springframework.http.MediaType.APPLICATION_JSON_VALUE) ApplicationContext(org.springframework.context.ApplicationContext) ActionForm(org.talend.dataprep.api.action.ActionForm) AggregationParameters(org.talend.dataprep.transformation.aggregation.api.AggregationParameters) java.io(java.io) TdqCategoriesFactory(org.talend.dataquality.semantic.broadcast.TdqCategoriesFactory) ColumnMetadata(org.talend.dataprep.api.dataset.ColumnMetadata) DataSet(org.talend.dataprep.api.dataset.DataSet) AggregationResult(org.talend.dataprep.transformation.aggregation.api.AggregationResult) JsonParser(com.fasterxml.jackson.core.JsonParser)

Aggregations

JsonParser (com.fasterxml.jackson.core.JsonParser)1 Api (io.swagger.annotations.Api)1 ApiOperation (io.swagger.annotations.ApiOperation)1 ApiParam (io.swagger.annotations.ApiParam)1 java.io (java.io)1 UTF_8 (java.nio.charset.StandardCharsets.UTF_8)1 java.util (java.util)1 Collections.singletonList (java.util.Collections.singletonList)1 Collectors (java.util.stream.Collectors)1 Stream (java.util.stream.Stream)1 GZIPOutputStream (java.util.zip.GZIPOutputStream)1 Resource (javax.annotation.Resource)1 Valid (javax.validation.Valid)1 NullOutputStream (org.apache.commons.io.output.NullOutputStream)1 StringUtils (org.apache.commons.lang.StringUtils)1 Logger (org.slf4j.Logger)1 LoggerFactory (org.slf4j.LoggerFactory)1 Autowired (org.springframework.beans.factory.annotation.Autowired)1 ApplicationContext (org.springframework.context.ApplicationContext)1 LocaleContextHolder (org.springframework.context.i18n.LocaleContextHolder)1