įigure 2-3 OHSCDA ETL in Multi-source Integrationĭescription of "Figure 2-3 OHSCDA ETL in Multi-source Integration" Multi-source integration is described in detail in Chapter 3, "Multi-Source Integration". Figure 2-3 illustrates how OHSCDA's ETL architecture expands to support multi-source integration. To address this, OHSCDA provides a multi-source integration capability. If data is loaded from more than one data source, it is necessary to integrate the data, by identifying and merging duplicate source records. The execution of the mappings is under the control of the Oracle DAC. It provides SDE to stage data for these tables from Oracle Clinical and Siebel Clinical database. OHSCDA provides SIL for each of its warehouse tables. The result is that dimension D1 can be queried as one of the dimensions in the star-schema centered on fact F1. The second part (4b) represents the setting of the values of each record's foreign key to dimension D1. The first part (4a) represents the copy, transformation, and derivation of the staged data for the fact. Mapping 4, the SIL that loads fact F1 into the warehouse target table for the fact, has two components. The Mappings are executed in the order indicated by the numbers. This part is called the SIL, for Source-Independent Load.įigure 2-2 shows the ETL process for extracting data from two tables (one dimension D1 and one fact F1) in one source application database.ĭescription of "Figure 2-2 ETL for One Source Database"Įach numbered arrow represents the execution of a Mapping. The second mapping for the given warehouse table reads from its Staging table and writes to the final warehouse table. For a given warehouse table, there must be one SDE for each supported source application. Records in the Staging table have a common format, regardless of the source from which they were extracted. This mapping is referred to as SDE, for Source-Dependent Extract. The first part is a mapping that reads from a specific application's database and writes to a common warehouse Staging table. Because data can be extracted from databases managed by different applications, the ETL mappings to load any given warehouse table is composed of two parts. A mapping is a program that selects data from one or more tables, performs transformations and derivations on the data, and inserts or updates the results in a target table. In OHSCDA, ETL is performed by execution of Informatica Mappings. OHSCDA supports the extraction of data from one or more transactional application source databases. Description of "Figure 2-1 ETL Architecture"
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |