The XML driver can be configured so that it supports hierarchical-formatted documents. In this case, the driver assumes that the document that it is accessing can contain more than one table. The driver scans the document to locate all tables; the available tables are visible through a SQLTables operation. Then, the driver does a second scan to gather each table’s column information and to determine a data type for each column.First, the XML driver returns two tables: "purchaseOrder" and "items." Two tables are returned because two items are found for a single purchase order. The XML driver found commonality of child elements.Second, the XML driver determines which columns are in a specific table. An _ID column, which is essentially a primary key, is automatically generated for each table. If a table is determined to be a child of another table, then it is given a second generated column. The name of this column is prefixed with the parent table’s name and ends with _ID, for example, _purchaseOrder_ID.Consider the previous example document. The items table will receive two generated columns, _ID and _purchaseOrder_ID, which are assigned an integer data type. The purchaseOrder table receives only the _ID column, because it does not have a parent table.