4 Overview of Transforming Data

About Data Transformation in Oracle Warehouse Builder

After you import your source data and define the target, you can consider how to transform the source data into the output desired for the target. In Oracle Warehouse Builder, you specify how to transform the data by designing mappings in the Mapping Editor. A mapping is an Oracle Warehouse Builder entity that describes the sequence of operations required to extract data from sources, transform the data, and load the data into one or more targets.

The fundamental unit of design for a mapping is the operator. You use an operator to represent each distinct operation you want to perform in the mapping. Operations include extracting data, loading data, and transforming data (aggregating, joining, performing a lookup, and so on). To indicate the order of operations, you connect the mappings with data flow connections.

To specify data transformation in a mapping, select from the many prebuilt transformation operators or design a new transformation. The prebuilt transformation operators enable commonly performed operations such as filtering, joining, and sorting. Oracle Warehouse Builder also includes prebuilt operators for complex operations such as merging data, cleansing data, or profiling data. If none of the prebuilt transformation operators meet your needs, you can design a new one. You can design the new transformation operator based on the Oracle Database library of PL/SQL functions, procedures, package functions, and package procedures.

Extraction and loading operations are represented by any of the numerous source and target operators. For example, a Table operator represents a table and a Flat File operator represents a flat file. Whether that operator specifies an extraction or loading operation depends on how you connect the operator relative to other operators in the mapping.

An important distinction to understand is the difference between the operator in the mapping and the object it represents. The operator and the object are separate entities until you bind the two. For example, when you add a table operator to a mapping, you can bind that operator to a specific table in the repository. With the operator bound to the table, you can synchronize changing definitions between the two. If the table operator represents a target and you change the operator in the mapping, then you can propagate those changes back to the table in the repository. If the operator represents a source that incurred a change in its metadata definition, then you can reimport the table in the Design Center and then propagate those changes to the table operator in the Mapping Editor.

About Mappings

Mappings describe a series of operations that extract data from sources, transform it, and load it into targets. They provide a visual representation of the flow of the data and the operations performed on the data. When you design a mapping in Oracle Warehouse Builder, you use the Mapping Editor interface. Alternatively, you can create and define mappings using OMB*Plus, the scripting interface for Oracle Warehouse Builder as described in Oracle Warehouse Builder API and Scripting Reference.

Based on the ETL logic that you define in a mapping, Oracle Warehouse Builder generates the code required to implement your design. Oracle Warehouse Builder can generate code for the following languages:

• PL/SQL mappings, see "PL/SQL Mappings"

• SQL*Loader mappings, see "SQL*Loader Mappings"

• SAP ABAP mappings, see "SAP ABAP Mappings"

• Code Template mappings, "Code Template (CT) Mappings"

About Using Operators

The basic design element for a mapping is the operator. Use operators to represent sources and targets in the data flow. Also use operators to define how to transform the data from source to target. The operators that you select as sources affect how you design the mapping. Based on the operators that you select, Oracle Warehouse Builder assigns the mapping to one of the following mapping generation languages. Each of these code languages require you to adhere to certain rules when designing a mapping.

• SQL

  For mappings that contains code templates, Oracle Warehouse Builder generates SQL code.

• PL/SQL

  For all mappings that do not contain either a Flat File operator as a source or a SAP/R3 source, Oracle Warehouse Builder generates PL/SQL code. Design considerations for PL/SQL mappings depend upon whether you specify a row-based or set-based operating mode as described in Chapter 10, "Understanding Performance and Advanced ETL Concepts".

• SQL*Loader

  When you define a Flat File operator as a source, Oracle Warehouse Builder generates SQL*Loader code. To design a SQL*Loader mapping correctly, follow the guidelines described in "Flat File Source Operators".

• ABAP

  When you define a SAP/R3 source, Oracle Warehouse Builder generates ABAP code. For mapping design considerations for SAP sources, see "Creating SAP Extraction Mappings".

Types of Operators

As you design a mapping, you select operators from the Mapping Editor palette and drag them onto the canvas.

This section introduces the types of operators and refers you to other chapters in this manual for detailed information.

• "Source and Target Operators": These operators represent Oracle Database objects, flat files, remote sources or targets, and non-Oracle sources and targets.

• Remote and Non-Oracle Source and Target Operators: The special requirements for using these operators are discussed in "Using Remote and non-Oracle Source and Target Operators".

• "Transformation Operators": These operators transform data.

• "Pre/Post Processing Operators": These operators call a function or procedure before or after executing a mapping.

• "Pluggable Mapping Operators": These are mappings that function as operators in other mappings.

• "Real-time Data Warehousing Operators": These operators are used in creating realtime and batch mappings.

Source and Target Operators

Use source and target operators to represent relational database objects and flat file objects.

Table 4-1 lists each source and target operator alphabetically and gives a brief description. For more information about these operators, see Chapter 25, "Source and Target Operators".

Table 4-1 Source and Target Operators

Icon	Operator Name	Description
	Constant	Produces a single output group that can contain one or more constant attributes.
	Construct Object	Produces object types and collection types.
	Cube	Represents a cube that you previously defined.
	Data Generator	Provides information such as record number, system date, and sequence values.
	Dimension	Represents a dimension that you previously defined.
	Expand Object	Expands an object type to obtain the individual attributes that comprise the object type.
	External Table	Represents an external table that you previously defined or imported.
	Flat File	Represents a flat file that you previously defined or imported.
	Materialized View	Represents a materialized view that you previously defined
	Queue	Represents an advanced queue that you previously defined.
	Sequence	Generates sequential numbers that increment for each row.
	Table	Represents a table that you previously defined or imported.
	Varray Iterator	Iterates through the values in the table type.
	View	Represents a view that you previously defined or imported.

Transformation Operators

To transform your source data, use data flow operators in your mapping.

Table 4-2 lists each data flow operator alphabetically and gives a brief description. For more information about these operators, see Chapter 26, "Data Flow Operators", Chapter 22, "Name and Address Cleansing", and Chapter 23, "Matching, Merging, and Deduplication".

Table 4-2 Data Flow Operators

Icon	Operator Name	Description
	Aggregator	Performs data aggregations, such as SUM and AVG, and provides an output row set with aggregated data.
	Anydata Cast	Converts an object of type Sys.AnyData to either a primary type or to a user-defined type.
	Deduplicator	Removes duplicate data in a source by placing a DISTINCT clause in the select code represented by the mapping.
	Expression	Enables you to write SQL expressions that define nonprocedural algorithms for one output parameter of the operator. The expression text can contain combinations of input parameter names, variable names, and library functions.
	Filter	Conditionally filters out rows from a row set.
	Joiner	Joins multiple row sets from different sources with different cardinalities and produces a single output row set.
	Lookup	Performs a lookup of data from a lookup object such as a table, view, materialized view, external table, cube, or dimension.
	Match Merge	Data quality operator that identifies matching records and merges them into a single record.
	Name and Address	Identifies and corrects errors and inconsistencies in name and address source data.
	Pivot	Transforms a single row of attributes into multiple rows. Use this operator to transform data that contained across attributes instead of rows.
	Set Operation	Performs union, union all, intersect, and minus operations in a mapping.
	Sorter	Sorts attributes in ascending or descending order.
	Splitter operator	Splits a single input row set into several output row sets using a boolean split condition.
	Subquery Filter	filter rows based on the results of a subquery.
	Table Function	Enables you to develop custom code to manipulate a set of input rows and return a set of output rows of the same or different cardinality that can be queried like a physical table.
	Transformation	Transforms the attribute value data of rows within a row set using a PL/SQL function or procedure.
	Unpivot	Converts multiple input rows into one output row. It enables you to extract from a source and produce one row from a set of source rows that are grouped by attributes in the source data.

Pre/Post Processing Operators

Use Pre/Post Processing operators to perform processing before or after executing a mapping. The Mapping parameter operator is used to provide values to and from a mapping.

Table 4-3 lists the Pre/Post Processing operators and the Mapping Parameter operators and gives a brief description. For more details about these operators, see Chapter 26, "Data Flow Operators".

Table 4-3 Pre/Post Processing Operators

Icon	Operator	Description
	Mapping Input Parameter	Passes parameter values into a mapping.
	Mapping Output Parameter	Sends values out of a mapping.
	Post-Mapping Process	Calls a function or procedure after executing a mapping.
	Pre-Mapping Process	Calls a function or procedure before executing a mapping.

Pluggable Mapping Operators

A pluggable mapping is a reusable grouping of mapping operators that behaves as a single operator.

Table 4-4 lists the Pluggable Mapping operators and gives a brief description. For more information, see Chapter 26, "Data Flow Operators".

Table 4-4 Pluggable Mapping Operators

Icon	Operator	Description
	Pluggable Mapping	Represents a reusable mapping.
	Pluggable Mapping Input Signature	A combination of input attributes that flow into the pluggable mapping.
	Pluggable Mapping Output Signature	A combination of output attributes that flow out of the pluggable mapping.

Real-time Data Warehousing Operators

Real-time data warehousing operators enable you to use queues to perform Change Data Capture. You can create mappings that capture changes in source objects and then apply them to target tables.

Table 4-5 lists the real-time data warehousing operators.

Table 4-5 Pluggable Mapping Operators

Icon	Operator	Description
	LCR Cast	Expands an LCR (Logical Change Record) object into its constituent columns.
	LCR Splitter	Directs changes to different tables along data flow paths.

About Transformations

Transformations are PL/SQL functions, procedures, packages, and types that enable you to transform data. You use transformations when designing mappings and process flows that define ETL processes. Transformations are stored in Oracle Warehouse Builder workspace and can be used in the project in which they are defined. Transformation packages are deployed at the package level but run at the transformation level.

About Transformation Libraries

A transformation library consists of a set of reusable transformations. Each time you create a repository, Oracle Warehouse Builder creates a Transformation Library containing transformation operations for that repository. This library contains the standard public Oracle Predefined library and an additional library for each Oracle module defined within the project.

Transformation libraries are available under the Public Transformations node of the Globals Navigator in the Design Center.