object ParquetUtils extends Logging
- Alphabetic
- By Inheritance
- ParquetUtils
- Logging
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @native() @throws( ... )
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
def
generatePartitionStructs(partitionSchema: Option[StructType]): Seq[StructField]
Given a partition schema transform it to an equivalent partition schema where each partition column name was transformed to
virtual_<partition_column_name>
Given a partition schema transform it to an equivalent partition schema where each partition column name was transformed to
virtual_<partition_column_name>
- partitionSchema
the partition schema to transform
- returns
the transformed partition schema fields
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
getColumnName(idx: Index, version: Long = ...): String
returns the column name for the specified index and version
returns the column name for the specified index and version
- idx
the index for which the column name needs to created
- version
version number, the metadata spec of which will determine the column name
- def getColumnNameForCols(cols: Seq[String], idxName: String, version: Long = ...): String
-
def
getIndexSchema(index: Index, translators: Seq[ParquetMetaDataTranslator]): Option[DataType]
Given an index and schema translator tries searching for the first available translation.
Given an index and schema translator tries searching for the first available translation. to a native DataFrame schema. if no translation is found return None
- index
the index to translate
- translators
the list of available translators
- returns
the DataType associated with the translation
- def getMdVersionStatus(version: Long): MetadataVersionStatus
- def getMdVersionStatusFromDf(df: DataFrame): MetadataVersionStatus
-
def
getPartitionColName(partCol: String): String
given a column name adds
virtual_
before it done to avoid aliasing existing columns in the datagiven a column name adds
virtual_
before it done to avoid aliasing existing columns in the data- partCol
the partition column to handle
- returns
virtual_<column_name>
-
def
getVersion(schema: StructType): Long
retrieves the version number from a metadata DataFrame Schema, returns 0 if the version is not explicitly defined (files without version number are implicitly declared version 0).
retrieves the version number from a metadata DataFrame Schema, returns 0 if the version is not explicitly defined (files without version number are implicitly declared version 0). the function assumes the
obj_name
column exists in the schema.- schema
- the schema of the metadata df
-
def
getVersion(df: DataFrame): Long
retrieves the version number from a Metadata DataFrame, returns 0 if the version is not explicitly defined (files without version number are implicitly declared version 0).
retrieves the version number from a Metadata DataFrame, returns 0 if the version is not explicitly defined (files without version number are implicitly declared version 0). the function assumes the
obj_name
column exists in the schema. -
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
def
initializeLogIfNecessary(isInterpreter: Boolean): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
def
isTraceEnabled(): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
def
log: Logger
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logName: String
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
- def mdFileToDF(session: SparkSession, mdPath: String): DataFrame
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
def
replaceReferences(expr: Expression, mapping: Map[String, String]): Expression
Replaces attribute references names in the given expression according to the given mapping
Replaces attribute references names in the given expression according to the given mapping
- expr
the expression to replace
- mapping
a mapping from attribute name to new attribute name
- returns
the new expresion with attribute references replaced with the given mapping
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @native() @throws( ... )