@Description( "The shard template of the output file. Specified as repeating sequences " + "of the letters 'S' or 'N' (example: SSS-NNN). These are replaced with the " + "shard number, or number of shards respectively") @Default.String("W-P-SS-of-NN") ValueProvider<String> getOutputShardTemplate();
@Description("The Google Genomics reference set id to use for the annotation set." + "Only used when --bamInput is used. Defaults to \"EMWV_ZfLxrDY-wE\" for hg19.") @Default.String("EMWV_ZfLxrDY-wE") String getReferenceSetId(); void setReferenceSetId(String referenceSetId);
@Validation.Required @Description("The ID of the Google Genomics Dataset that the output AnnotationSet will be " + "posted to.") @Default.String("") String getOutputDatasetId();
@Description("A comma delimited list of the IDs of the Google Genomics ReadGroupSets this " + "pipeline is working with. Default (empty) indicates all ReadGroupSets in InputDatasetId." + " This or InputDatasetId must be set. InputDatasetId overrides " + "ReadGroupSetIds (if InputDatasetId is set, this field will be ignored).") @Default.String("") String getReadGroupSetIds();
@Description("Path of the file to read from") @Default.String( "gs://apache-beam-samples/traffic_sensor/" + "Freeways-5Minaa2010-01-01_to_2010-02-15_test2.csv") String getInputFile();
@Description( "String representation of the first minute after which to generate results," + "in the format: yyyy-MM-dd-HH-mm . This time should be in PST." + "Any input data timestamped prior to that minute won't be included in the sums.") @Default.String("1970-01-01-00-00") String getStartMin();
@Description("The filename prefix of the files to write to.") @Default.String("output") @Required ValueProvider<String> getOutputFilenamePrefix(); void setOutputFilenamePrefix(ValueProvider<String> value);
@Description("The ID of the Google Genomics Dataset that the pipeline will get its input reads" + " from. Default (empty) means to use ReadGroupSetIds instead. This or ReadGroupSetIds" + " must be set. InputDatasetId overrides ReadGroupSetIds (if this field is set, " + "ReadGroupSetIds will be ignored). All of the referenceSetIds for all ReadGroupSets in" + " this Dataset must be the same for the purposes of setting the referenceSetId" + " of the output AnnotationSet." + " Use one of --bamInput, --inputDatasetId, or --readGroupSetIds.") @Default.String("") String getInputDatasetId();
@Description("A comma delimited list of the IDs of the Google Genomics ReadGroupSets this " + "pipeline is working with. Default (empty) indicates all ReadGroupSets in InputDatasetId." + " This or InputDatasetId must be set. InputDatasetId overrides ReadGroupSetIds " + "(if InputDatasetId is set, this field will be ignored). All of the referenceSetIds for" + " all ReadGroupSets in this list must be the same for the purposes of setting the" + " referenceSetId of the output AnnotationSet." + " Use one of --bamInput, --inputDatasetId, or --readGroupSetIds.") @Default.String("") String getReadGroupSetIds();
@Description("Cloud storage prefix containing BAM and BAI files from which to read or a path " + "to a local file containing the newline-separated prefixes." + " Use one of --bamInput, --inputDatasetId, or --readGroupSetIds.") @Default.String("") String getBamInput(); void setBamInput(String value);
@Description("The ID of the Google Genomics Dataset that the pipeline will get its input reads" + " from. Default (empty) means to use ReadGroupSetIds and VariantSetIds instead. This or" + " ReadGroupSetIds and VariantSetIds must be set. InputDatasetId overrides" + " ReadGroupSetIds and VariantSetIds (if this field is set, ReadGroupSetIds and" + " VariantSetIds will be ignored).") @Default.String("") String getInputDatasetId();
@Description( "The window duration in which data will be written. Defaults to 5m. " + "Allowed formats are: " + "Ns (for seconds, example: 5s), " + "Nm (for minutes, example: 12m), " + "Nh (for hours, example: 2h).") @Default.String("5m") String getWindowDuration();
@Description("The IDs of the Google Genomics transcript sets this pipeline is working with, " + "comma delimited. Defaults to UCSC refGene (hg19).") @Default.String("CIjfoPXj9LqPlAEQ5vnql4KewYuSAQ") String getTranscriptSetIds(); void setTranscriptSetIds(String transcriptSetIds);
@Description("The ID of the Google Genomics VariantSet this pipeline is working with." + " It assumes the variant set has INFO field 'AF' from which it retrieves the" + " allele frequency for the variant, such as 1,000 Genomes phase 1 or phase 3 variants." + " Defaults to the 1,000 Genomes phase 1 VariantSet with id " + DEFAULT_VARIANTSET + ".") @Default.String(DEFAULT_VARIANTSET) String getVariantSetId(); void setVariantSetId(String variantSetId);
@Description( "Provide errors store options as a json string containing key-values. Options required" + "depend on the type of store set.") @Default.String("{}") String getErrorsStoreOptions();
/** * By default, this example reads from a public dataset containing the text of King Lear. Set * this option to choose a different input file or glob. */ @Description("Path of the file to read from") @Default.String("gs://apache-beam-samples/shakespeare/kinglear.txt") String getInputFile();
@Description("Path of the file to read from") @Default.String( "gs://apache-beam-samples/traffic_sensor/" + "Freeways-5Minaa2010-01-01_to_2010-02-15_test2.csv") String getInputFile();
@Description("Path to the data file(s) containing game data.") // The default maps to two large Google Cloud Storage files (each ~12GB) holding two subsequent // day's worth (roughly) of data. @Default.String("gs://apache-beam-samples/game/gaming_data*.csv") String getInput();
/** * The root URL for the Dataflow API. {@code dataflowEndpoint} can override this value if it * contains an absolute URL, otherwise {@code apiRootUrl} will be combined with {@code * dataflowEndpoint} to generate the full URL to communicate with the Dataflow API. */ @Description( "The root URL for the Dataflow API. dataflowEndpoint can override this " + "value if it contains an absolute URL, otherwise apiRootUrl will be combined with " + "dataflowEndpoint to generate the full URL to communicate with the Dataflow API.") @Default.String(Dataflow.DEFAULT_ROOT_URL) String getApiRootUrl();
/** * Set csvDelimiter optional parameter to specify the CSV delimiter. Default delimiter is set to a * comma. */ @Description( "Set csvDelimiter optional parameter to specify the CSV delimiter. Default delimiter is set" + " to a comma.") @Default.String(",") String getCsvDelimiter();