org.apache.beam.sdk.options.Default Java Examples

/**
 * The class responsible for staging resources to be accessible by workers during job execution.
 * If stager has not been set explicitly, an instance of this class will be created and used as
 * the resource stager.
 */
@Description(
    "The class of the stager that should be created and used to stage resources. "
        + "If stager has not been set explicitly, an instance of the this class will be created "
        + "and used as the resource stager.")
@Default.Class(GcsStager.class)
Class<? extends Stager> getStagerClass();
 

@Description(
    "Csv format according to Apache Commons CSV format. Default is: Apache Commons CSV"
        + " default\n"
        + "https://static.javadoc.io/org.apache.commons/commons-csv/1.7/org/apache/commons/csv/CSVFormat.html#DEFAULT\n"
        + "Must match format names exactly found at: "
        + "https://static.javadoc.io/org.apache.commons/commons-csv/1.7/org/apache/commons/csv/CSVFormat.Predefined.html")
@Default.String("Default")
String getCsvFormat();
 

@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("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();
 

/**
 * The credential instance that should be used to authenticate against AWS services. The option
 * value must contain a "@type" field and an AWS Credentials Provider class as the field value.
 * Refer to {@link DefaultAWSCredentialsProviderChain} Javadoc for usage help.
 *
 * <p>For example, to specify the AWS key ID and secret, specify the following: <code>
 * {"@type" : "AWSStaticCredentialsProvider", "awsAccessKeyId" : "key_id_value",
 * "awsSecretKey" : "secret_value"}
 * </code>
 */
@Description(
    "The credential instance that should be used to authenticate "
        + "against AWS services. The option value must contain \"@type\" field "
        + "and an AWS Credentials Provider class name as the field value. "
        + "Refer to DefaultAWSCredentialsProviderChain Javadoc for usage help. "
        + "For example, to specify the AWS key ID and secret, specify the following: "
        + "{\"@type\": \"AWSStaticCredentialsProvider\", "
        + "\"awsAccessKeyId\":\"<key_id>\", \"awsSecretKey\":\"<secret_key>\"}")
@Default.InstanceFactory(AwsUserCredentialsFactory.class)
AWSCredentialsProvider getAwsCredentialsProvider();
 

@Description(
    "Fixed window size in seconds (default 60) to apply before aggregating the numerical value of "
        + "features and exporting the aggregated values as metrics. Refer to "
        + "feast/ingestion/transform/metrics/WriteFeatureValueMetricsDoFn.java"
        + "for the metric nameas and types used.")
@Default.Integer(60)
int getWindowSizeInSecForFeatureValueMetric();
 

@Description(
    "Flag indicating whether result of GBK needs to be re-iterable. Re-iterable result implies that all values for a single key must fit in memory as we currently do not support spilling to disk.")
@Default.Boolean(false)
Boolean getReIterableGroupByKeyResult();
 

@Description("Max records per micro-batch. For streaming sources only.")
@Default.Long(-1)
Long getMaxRecordsPerBatch();
 

@Description(
    "Size of S3 upload chunks; max upload object size is this value multiplied by 10000;"
        + "default is 64MB, or 5MB in memory-constrained environments. Must be at least 5MB.")
@Default.InstanceFactory(S3UploadBufferSizeBytesFactory.class)
Integer getS3UploadBufferSizeBytes();
 

@Description("The beam sink class to which the metrics will be pushed")
@Default.InstanceFactory(NoOpMetricsSink.class)
Class<? extends MetricsSink> getMetricsSink();
 

@Description("Database name to connect to. Optional.")
@Default.String("")
String getDatabase();
 

@Description("The config for state to be durable")
@Default.Boolean(false)
Boolean getStateDurable();
 

@Description("Column delimiter of the data files. The default value is comma.")
@Default.Character(',')
ValueProvider<Character> getColumnDelimiter();
 

@Description("Numeric value of allowed data lateness, in minutes")
@Default.Integer(120)
Integer getAllowedLateness();
 

@Description("The output suffix for TFRecord Files")
@Default.String(".tfrecord")
ValueProvider<String> getOutputSuffix();
 

@Description("Kafka topic")
@Validation.Required
@Default.String("test")
String getKafkaTopic();
 

/**
 * Instance of a pipeline resources detection algorithm. If not set explicitly, a default
 * implementation will be used.
 */
@JsonIgnore
@Description(
    "Instance of a pipeline resources detection algorithm. If not set explicitly, a default implementation will be used")
@Default.InstanceFactory(PipelineResourcesDetectorFactory.class)
PipelineResourcesDetector getPipelineResourcesDetector();
 

@Description("Cloud Spanner API endpoint")
@Default.String("https://batch-spanner.googleapis.com")
ValueProvider<String> getSpannerHost();
 

@Description("The Bigtable table ID in the instance.")
@Default.String("bigtable-table")
String getBigtableTableId();
 

@Description("The filename prefix of the files to write to.")
@Default.String("output")
ValueProvider<String> getOutputFilenamePrefix();
 

@Description(
    "Sets the number of times that failed tasks are re-executed. "
        + "A value of zero effectively disables fault tolerance. A value of -1 indicates "
        + "that the system default value (as defined in the configuration) should be used.")
@Default.Integer(-1)
Integer getNumberOfExecutionRetries();
 

@Description("Query for the pipeline input.  Must return exactly one result")
@Default.String(RECORD_QUERY)
String getInput();
 

@Description("Numeric value of month to filter on")
@Default.Integer(MONTH_TO_FILTER)
Integer getMonthFilter();
 

@Description("The maximum time to wait for the sub-process to complete")
@Default.Integer(3600)
Integer getWaitTime();
 

@Description("The class that determines the strategy for calculating the similarity of alleles.")
@Default.Class(SharedMinorAllelesCalculatorFactory.class)
Class<? extends CallSimilarityCalculatorFactory> getCallSimilarityCalculatorFactory();
 

@Description("Numeric value of fixed window duration for team analysis, in minutes")
@Default.Integer(60)
Integer getTeamWindowDuration();
 

@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("String containing comma separated arguments for the JobServer.")
@Default.InstanceFactory(DefaultJobServerConfigFactory.class)
String[] getJobServerConfig();
 

@Description("Prefix used for the BigQuery table names")
@Default.String("game_stats")
String getGameStatsTablePrefix();
 

@Description("The maximum number of elements in a bundle.")
@Default.Long(1)
long getMaxBundleSize();