util

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

val APPLICATION_LABEL_FIELD: String

val DNS_RESOURCE_RECORD_TYPE_FIELD: String

lazy val MOTHRA_COLLECTORS_DF: Option[DataFrame]

val ORGANIZATION_LABEL_FIELD: String

val TLS_CIPHER_SUITE_FIELD: String

val app_label_name: Column

def app_labels(labels: Any*): Column

def append_collection_labels(df: DataFrame, attributes: String*): DataFrame

Append one or more collection attribute labels to a dataframe based on the observationDomainid and vlanId fields in the data.

final def asInstanceOf[T0]: T0

def clone(): AnyRef

def collect_column(df: DataFrame, c: Column): Array[Any]

An array containing the values of a column expression of a dataframe.

def collect_column(df: DataFrame): Array[Any]

An array containing the values from the first column of a dataframe.

def collection_labels(attribute: String, labels: String*): Column

Given the name of a collection attribute and a set of matching labels, produce a filter expression that can be used to filter a DataFrame for * flows matching the given labels.

def collector_labels(labels: String*): Column

Given a set of collector labels, returns a set of filter expressions for filtering records from those collectors.

def compare_field(field: String, condition: String, value: Any): Column

Convenience method for building filter conditions using comparison operators.

def count_by_collection_labels(df: DataFrame, attributes: String*): DataFrame

Group data by one or more collection attributes and count the number of flows within each group.

def dateRange(from: LocalDate, to: LocalDate, step: Integer = 1): Iterator[LocalDate]

def department_labels(labels: String*): Column

Given a set of department labels, returns a set of filter expressions for filtering records from those departments.

val dns_rr_types: Column

val dns_rr_types_udf: UserDefinedFunction

val email_addr: UserDefinedFunction

val email_addrs: UserDefinedFunction

val email_display: UserDefinedFunction

val email_displays: UserDefinedFunction

val email_domain: UserDefinedFunction

val email_domains: UserDefinedFunction

val email_header_addrs: UserDefinedFunction

val email_header_displays: UserDefinedFunction

val email_header_domains: UserDefinedFunction

val email_header_mailboxes: UserDefinedFunction

val email_mailbox: UserDefinedFunction

val email_mailboxes: UserDefinedFunction

def enclave_labels(labels: String*): Column

Given a set of enclave labels, returns a set of filter expressions for filtering records from those enclaves.

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def filter_array_field_list(df: DataFrame, field: String, list: Seq[Any]): DataFrame

def filter_by_field(df: DataFrame, field: String, condition: String, value: Any): DataFrame

Filter a DataFrame on the passed field, value and condition.

def filter_by_times(df: DataFrame, start: String, end: String): DataFrame

Return a DataFrame containing only flows starting at or after the passed start time before or at the passed end time.

def filter_field_list(df: DataFrame, field: String, list: Seq[Any]): DataFrame

This function filters and returns a DataFrame based on whether the value or values in the given field of the DataFrame are contained in the given list.

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

def ip_is_external(a: Any): Column

True if the input is a string representing an IP address not in the internal set.

def ip_is_internal(a: Any): Column

True if the input is a string representing an IP address in the internal set.

final def isInstanceOf[T0]: Boolean

def load_csv_file(filepath: String): DataFrame

Import data from a CSV file and return a DataFrame containing the imported data.

def load_hive_table(tablename: String): DataFrame

Import data from a CSV file and return a DataFrame containing the imported data.

def load_ipset(infile: String): DataFrame

Load a SiLK IPset file into a DataFrame of individual IP addresses.

def load_ipset_blocks(infile: String): DataFrame

Load a SiLK IPset file into a DataFrame of IP address blocks.

def make_timestamp(t: Timestamp): Timestamp

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def organization_labels(labels: String*): Column

Given a set of organization labels, returns a set of filter expressions for filtering records from those organizations.

def save_csv_file(df: DataFrame, outfile: String): Unit

Write data in an existing DataFrame to a CSV file.

def save_hive_table(df: DataFrame, tablename: String): Unit

Write data in an existing DataFrame to a Hive table.

def save_ipset(outfile: String, df: DataFrame): Unit

Save a DataFrame of IP addresses or blocks as a SiLK IPset file.

def sip_dip_direction(sip: Any, dip: Any): Column

If both arguments are strings parsable as IP addresses, and if the first argument (sip) represents the initiator of a connection and the second argument (dip) represents the recipient of a connection, returns:

val ssl_rewrite_col: UserDefinedFunction

def ssl_rewrite_df(df: DataFrame): DataFrame

def stime_date(date: String): Column

Given a string in the form of yyyy-mm-dd representing a date, returns a filter expression that can be used to filter a DataFrame for records with a start time on that date.

def stime_range(begin: String = null, end: String = null): Column

Given string arguments representing the begin and end of a time range, returns a filter expression that can be used to filter a DataFrame for records with a start time within that range.

final def synchronized[T0](arg0: ⇒ T0): T0

val tls_cipher_descs: Column

val tls_cipher_descs_udf: UserDefinedFunction

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

def withSensorIds[T](input: Dataset[T], sensorIds: Seq[Int]): Dataset[T]

val yaf_ssl_object_type: UserDefinedFunction

def make_timestamp(s: String): Timestamp