OraOLEDB is compatible with OLE DB Services that are available in OLE DB version 2.0 and later. OLE DB Services contains useful services such as automatic transaction enlistment, Client Cursor Engine (CCE), connection and session pooling, which can enhance application performance, and others.

OLE DB Services can be used with OraOLEDB through C++/COM or ADO.

By default, the OLEDB_SERVICES registry entry for OraOLEDB is set, under the CLSID of OraOLEDB, to 0xffffffff (that is, -1), which enables all services. Certain OLE DB Services can also be disabled or enabled programmatically through the DBPROP_INIT_OLEDBSERVICES property setting.

OraOLEDB offers provider-specific connection string attributes, which are set in the same way as the Provider and User ID are set. The provider-specific connection string attributes are:

• CacheType - specifies the type of cache used to store the rowset data on the client. See "OraOLEDB-Specific Connection String Attributes for Rowsets".

• ChunkSize - specifies the size of LONG or LONG RAW column data stored in the provider's cache. See "OraOLEDB-Specific Connection String Attributes for Rowsets".

• DistribTX - enables or disables distributed transaction enlistment capability. See "Distributed Transactions".

• FetchSize - specifies the size of the fetch array in rows. See "OraOLEDB-Specific Connection String Attributes for Rowsets".

• OLEDB.NET - enables or disables compatibility with OLEDB.NET Data Provider. See "OLEDB.NET Data Provider Compatibility".

• OSAuthent - specifies whether operating system authentication will be used when connecting to an Oracle Database. See "Operating System Authentication".

• PLSQLRSet - enables or disables the return of a rowset from PL/SQL stored procedures. See "OraOLEDB Custom Properties for Commands".

• PwdChgDlg - enables or disables displaying the password change dialog box when the password expires. See "Password Expiration".

• UseSessionFormat - specifies whether to use the default NLS session formats or let OraOLEDB override some of these formats for the duration of the session. Valid values are 0 (FALSE) and 1 (TRUE). The default is FALSE which lets OraOLEDB override some of the default NLS session formats. If the value is TRUE, OraOLEDB uses the default NLS session formats.

  Note that this connection attribute does not appear under the \\HKEY_LOCAL_ MACHINE\SOFTWARE\ORACLE\KEY_HOMENAME\OLEDB registry key.

• VCharNull - enables or disables the NULL termination of VARCHAR2 OUT parameters from stored procedures.

• SPPrmDefVal - specifies whether to use the default value or a NULL value if the application has not specified a stored procedure parameter value.

• NDataType - specifies whether any of the parameters bound to the command are of N data types, which include NCHAR, NVARCHAR2, or NCLOB. See "NDatatype".

  Note that this connection attribute does not appear under the \\HKEY_LOCAL_ MACHINE\SOFTWARE\ORACLE\KEY_HOMENAME\OLEDB registry key.

• SPPrmsLOB - specifies whether one or more parameters bound to the stored procedures are of LOB data type, which include CLOB, BLOB, or NCLOB. See "SPPrmsLOB".

  Note that this connection attribute does not appear under the \\HKEY_LOCAL_ MACHINE\SOFTWARE\ORACLE\KEY_HOMENAME\OLEDB registry key.

• StmtCacheSize – specifies the maximum number of statements that can be cached. See "Statement Caching".

• MetaDataCacheSize - specifies the maximum number of SELECT statements for which the metadata can be cached. See "Metadata Caching".

• DeferUpdChk - specifies whether or not to defer the updateability check to support updating read-only disconnected rowsets. See DeferUpdChk under "OraOLEDB-Specific Connection String Attributes for Rowsets".

• DBNotifications - specifies whether or not to subscribe to the high availability events. See "Enhanced Failover Capability".

• DBNotificationPort - specifies the port number, which is opened to listen to the Database notifications. See "Enhanced Failover Capability".

The default values for these attributes are located under the \\HKEY_LOCAL_ MACHINE\SOFTWARE\ORACLE\KEY_HOMENAME\OLEDB registry key, where KEY_HOMENAME is the Oracle home.

The registry default values are read by OraOLEDB from the registry when the provider is loaded into memory. If Oracle-specific connection string attributes are not provided at connection time, then the default registry values are used. However, if the attributes are provided, then these new values override the default registry values.

These attributes can be set by setting the DBPROP_INIT_PROVIDERSTRING property, provided in the DBPROPSET_DBINIT property set. For example:

"FetchSize=100;CacheType=Memory;OSAuthent=0;PLSQLRSet=1;StmtCacheSize=10;"

The DistribTX attribute specifies whether sessions are enabled to enlist in distributed transactions. Valid values are 0 (disabled) and 1 (enabled). The default is 1 which indicates that sessions are enabled for distributed transaction enlistments.

Applications using Microsoft Distributed Transaction Coordinator must have DistribTX set to 1, the default.

Sessions enabled for distributed transaction enlistments cannot run statements that use the direct path load and parallel DML capabilities of the Oracle database. Such statements are executed as conventional path serial statements.

This feature enhances failover capability.

These connection string attributes support enhanced failover capability.

• DBNotifications

  The DBNotifications attribute specifies whether or not to subscribe to high availability events. Valid values are 0 (FALSE) and 1 (TRUE). The default is FALSE, which indicates that OraOLEDB does not subscribe to high availability events. If this attribute is not provided at the connection time, then the default registry value is used.

• DBNotificationPort

  The DBNotificationPort attribute specifies the port number, which is used to listen to the database notifications. The valid value is an unsigned integer.

  DBNotificationPort is effective only if the DBNotifications attribute is set to TRUE, either through the connection string attribute or by registry entry. The default for the DBNotificationPort attribute is 0, which implies that OraOLEDB opens a valid port randomly. OraOLEDB does not validate the port number, so it is the responsibility of the application to specify a valid port number.

The OSAuthent attribute specifies whether operating system authentication will be used when connecting to an Oracle Database. Valid values are 0 (disabled) and 1(enabled). The default is 0, which indicates that operating system authentication is not used.

Operating system authentication is the feature by which Oracle uses the security mechanisms of the operating system to authorize users.

After the Windows client has been set up properly for operating system authentication, this feature may be enabled by OraOLEDB clients by setting any of the following:

• DBPROP_AUTH_USERNAME to /

• DBPROP_INIT_PROVIDERSTRING to OSAuthent=1;

• OSAuthent in the registry to 1

Oracle provides a Password Expiration feature which allows database administrators to force users to change their passwords regularly. The PwdChgDlg attribute enables or disables the displaying of the password change dialog box, whenever a logon fails due to an expired password. When enabled, the provider displays the dialog box to change the password. When disabled, the logon fails with an error message. The valid values are 0 (disabled) and 1 (enabled). The default is 1 (enabled).

Dim con As New ADODB.Connection
con.ConnectionString = "Provider=OraOLEDB.Oracle;Data Source=MyOraDb;" & _
                     "User ID=scott;Password=tiger;"
con.Open

Dim con As New ADODB.Connection
con.Provider = "OraOLEDB.Oracle"
con.Open "MyOraDb", "scott", "tiger"

Dim con As New ADODB.Connection
con.Provider = "OraOLEDB.Oracle"
con.ConnectionString = "FetchSize=200;CacheType=Memory;" & _
                       "OSAuthent=0;PLSQLRSet=1;Data Source=MyOraDb;" & _
                       "User ID=scott;Password=tiger;"
con.Open

Dim con As New ADODB.Connection
con.Provider = "OraOLEDB.Oracle"
con.Open "MyOraDb", "/", ""

Dim con As New ADODB.Connection
con.Provider = "OraOLEDB.Oracle"
con.ConnectionString = "Data Source=MyOraDb;OSAuthent=1;"
con.Open

The VCharNull attribute enables or disables the NULL termination of VARCHAR2 OUT parameters from stored procedures. Valid values are 0 (disabled) and 1 (enabled). The default is 1, which indicates that VARCHAR2 OUT parameters are NULL terminated. A value of 0 indicates that VARCHAR2 OUT parameters are padded with spaces.

The default value for this attribute is located under the \\HKEY_LOCAL_ MACHINE\SOFTWARE\ORACLE\KEY_HOMENAME\OLEDB registry key, where HOMENAME is the Oracle home. If this attribute is not provided at the connection time, then the default registry value is used.

Note that with this connection attribute enabled, applications need to pad the stored procedure IN and IN OUT CHAR parameters with spaces explicitly, if the parameter is to be used in a WHERE clause.

The SPPrmDefVal attribute specifies whether to use the default value or a NULL value if the application has not specified a stored procedure parameter value. Valid values are 0 (FALSE) and 1 (TRUE). The default is FALSE, which enables OraOLEDB to pass a NULL value. If the value is TRUE, then OraOLEDB uses the default value.

The default value for this attribute is located under the \\HKEY_LOCAL_ MACHINE\SOFTWARE\ORACLE\KEY_HOMENAME\OLEDB registry key. If this attribute is not provided at connection time, then the default registry value is used.

OraOLEDB supports local and distributed transactions, which provide explicit commit and abort transactional operations.

OraOLEDB does not support nested transactions. In addition, a local transaction cannot be started if the session is currently enlisted in a distributed transaction. This also applies to distributed transactions if the session is currently enlisted in a local transaction.

When executing an Oracle PL/SQL stored procedure using a command, use Oracle native syntax or the ODBC procedure call escape sequence in the command text:

• Oracle native syntax: BEGIN credit_account(123, 40); END;

• ODBC syntax: {CALL credit_account(123, 40)}

OraOLEDB validates and fetches the metadata only for SELECT SQL statements.

When using Oracle ANSI SQL, parameters in the command text are preceded by a colon. In ODBC SQL, parameters are indicated by a question mark (?).

OraOLEDB supports input, output, and input and output parameters for PL/SQL stored procedures and stored functions. OraOLEDB supports input parameters for SQL statements.

OraOLEDB custom properties for commands are grouped under the custom property set ORAPROPSET_COMMANDS. It provides these properties:

Dim objRes As NEW ADODB.Recordset
Dim objCon As NEW ADODB.Connection
Dim objCmd As NEW ADODB.Command
....
objCmd.ActiveConnection = objCon
objCmd.CommandType = adCmdText

' Enabling the PLSQLRSet property indicates to the provider
' that the command returns one or more rowsets
objCmd.Properties("PLSQLRSet") = TRUE

' Assume Employees.GetEmpRecords() has a REF CURSOR as
' one of the arguments
objCmd.CommandText = "{ CALL Employees.GetEmpRecords(?,?) }"

' Execute the SQL
set objRes = objCmd.Execute

' It is a good idea to disable the property after execute as the
' same command object may be used for a different SQL statement
objCmd.Properties("PLSQLRSet") = FALSE

Dim objCon As NEW ADODB.Connection
Dim objCmd As NEW ADODB.Command
Dim prEmpno As NEW ADODB.Parameter
Dim prEname As NEW ADODB.Parameter
...
objCmd.ActiveConnection = objCon
objCmd.CommandType = adCmdText

' Create and append the parameters to the command object
Set prEmpno = objCmd.CreateParameter("prEmpno", adSmallInt, adParamInput, ,8521)
' prEname is bound to a NVARCHAR2 column in the EMP table
Set prEname = objCmd.CreateParameter("prEname", adBSTR, adParamInput, , "Joe")
objCmd.Parameters.Append prEmpno
objCmd.Parameters.Append prEname

' Enabling the NDatatype property indicates to the provider
' that one or more of the bound parameters is of N datatype
objCmd.Properties("NDatatype") = TRUE

' Assume column ENAME in table EMP is of NVARCHAR2 type
objCmd.CommandText = "INSERT INTO EMP (EMPNO, ENAME) VALUES (?, ?)"

' Execute the SQL
objCmd.Execute

' It is a good idea to disable the property after execute as the same command
' object may be used for a different SQL statement 
objCmd.Properties("NDatatype") = FALSE

Dim objCon As NEW ADODB.Connection
Dim objCmd As NEW ADODB.Command
Dim prCLOB As NEW ADODB.Parameter
...
objCmd.ActiveConnection = objCon
objCmd.CommandType = adCmdText

' Create and append the parameters to the command object
Set prCLOB = objCmd.CreateParameter("prCLOB", adLongVarchar, adParamOutput, _
                                                10000)
objCmd.Parameters.Append prCLOB

' Enabling the SPPrmsLOB property indicates to the provider
' that one or more of the bound parameters is of LOB data type
objCmd.Properties("SPPrmsLOB") = TRUE

' Assume the Stored Procedure requires a CLOB parameter
objCmd.CommandText = "{ call storedproc(?) }"

'Execute the SQL
objCmd.Execute

' It is a good idea to disable the property after execute as the
' same command object may be used for a different SQL statement 
objCmd.Properties("SPPrmsLOB") = FALSE

Dim objCon As NEW ADODB.Connection
Dim objCmd As NEW ADODB.Command
... 

' Statement caching is enabled by setting the 'StmtCacheSize'
' connection string attribute to a value greater than zero
objCon.ConnectionString = "StmtCacheSize=10;Data Source=MyOraDb;" & _                        "User ID=scott;Password=tiger;"
objCon.Open
objCmd.ActiveConnection = objCon
objCmd.CommandType = adCmdText
objCmd.CommandText = "SELECT * FROM EMP"

' "SELECT * FROM EMP" statement would be added to the statement cache because
' StmtCacheSize connection string attribute value is greater than 0 and 
' AddToStmtCache property value is TRUE by default.
objCmd.Execute

' Do not add "SELECT * FROM DEPT" to the statement cache
objCmd.CommandText = "SELECT * FROM DEPT"
objCmd.Properties("AddToStmtCache") = FALSE

' "SELECT * FROM DEPT" statement would not be added to the statement cache
objCmd.Execute

Oracle Provider for OLE DB allows consumers to execute a PL/SQL stored procedure with an argument of REF CURSOR type or a stored function returning a REF CURSOR value.

OraOLEDB returns a rowset for the REF CURSOR bind variable. Because there is no predefined data type for REF CURSOR in the OLE DB specification, the consumer must not bind this parameter.

If the PL/SQL stored procedure has one or more arguments of REF CURSOR type, OraOLEDB binds these arguments and returns a rowset for each argument of REF CURSOR type.

If the PL/SQL stored function returns a REF CURSOR or has an argument of REF CURSOR type, OraOLEDB binds these and returns a rowset for each REF CURSOR type.

To use this feature, stored procedures or functions must be called in the ODBC procedure call escape sequence.

The stored procedure or function being called could be either standalone or packaged. However, the REF CURSOR being returned must be explicitly defined in a package in the database.

OraOLEDB supports returning more than one rowset from a stored procedure. Consumers can use this feature to access all the REF CURSORs being returned by a stored procedure.

CREATE OR REPLACE PACKAGE Employees AS  
  TYPE empcur IS REF CURSOR; 
 
  PROCEDURE GetEmpRecords(p_cursor OUT empcur,
                          q_cursor OUT empcur,
                          indeptno IN NUMBER,
                          p_errorcode OUT NUMBER);
 
  FUNCTION GetDept(inempno IN NUMBER,  
                   p_errorcode OUT NUMBER)  
    RETURN empcur; 
END Employees; 

CREATE OR REPLACE PACKAGE BODY Employees AS 
 
  PROCEDURE GetEmpRecords(p_cursor OUT empcur, 
                          q_cursor OUT empcur, 
                          indeptno IN NUMBER,  
                          p_errorcode OUT NUMBER) IS  
  BEGIN   
    p_errorcode := 0;  
    OPEN p_cursor FOR  
      SELECT *  
      FROM emp  
      WHERE deptno = indeptno  
      ORDER BY empno;  

OPEN q_cursor FOR  
      SELECT empno 
      FROM emp  
      WHERE deptno = indeptno  
      ORDER BY empno; 
 
  EXCEPTION  
    WHEN OTHERS THEN  
      p_errorcode:= SQLCODE;  
 
  END GetEmpRecords;  
 
  FUNCTION GetDept(inempno IN NUMBER,  
                   p_errorcode OUT NUMBER)  
    RETURN empcur IS  
      p_cursor empcur;  
  BEGIN   
    p_errorcode := 0;  
    OPEN p_cursor FOR  
      SELECT deptno  
      FROM emp  
      WHERE empno = inempno;  
    RETURN (p_cursor);  
 
  EXCEPTION  
    WHEN OTHERS THEN  
      p_errorcode:= SQLCODE; 
 
  END GetDept;   
 
END Employees; 

Dim Con   As New ADODB.Connection
Dim Rst1  As New ADODB.Recordset 
Dim Rst2  As New ADODB.Recordset 
Dim Rst3  As New ADODB.Recordset 
Dim Cmd   As New ADODB.Command 
Dim Prm1  As New ADODB.Parameter 
Dim Prm2  As New ADODB.Parameter 

Con.Provider = "OraOLEDB.Oracle"
Con.ConnectionString = "Data Source=MyOraDb;" & _
                       "User ID=scott;Password=tiger;"
Con.Open
Cmd.ActiveConnection = Con

' Although Employees.GetEmpRecords() takes four parameters, only 
' two need to be bound because Ref cursor parameters are automatically 
' bound by the provider. 

Set Prm1 = Cmd.CreateParameter("Prm1", adSmallInt, adParamInput, , 30)
Cmd.Parameters.Append Prm1 
Set Prm2 = Cmd.CreateParameter("Prm2", adSmallInt, adParamOutput) 
Cmd.Parameters.Append Prm2 

' Enable PLSQLRSet property
Cmd.Properties ("PLSQLRSet") = TRUE  

' Stored Procedures returning resultsets must be called using the 
' ODBC escape sequence for calling stored procedures. 
Cmd.CommandText = "{CALL Employees.GetEmpRecords(?, ?)}" 

' Get the first recordset
Set Rst1 = Cmd.Execute 

' Disable PLSQLRSet property
Cmd.Properties("PLSQLRSet") = FALSE 

' Get the second recordset
Set Rst2 = Rst1.NextRecordset

' Just as in a stored procedure, the REF CURSOR return value must  
' not be bound in a stored function. 
Prm1.Value = 7839
Prm2.Value = 0

' Enable PLSQLRSet property
Cmd.Properties("PLSQLRSet") = TRUE 

' Stored Functions returning resultsets must be called using the 
' ODBC escape sequence for calling stored functions. 
Cmd.CommandText = "{CALL Employees.GetDept(?, ?)}" 

' Get the rowset
Set Rst3 = Cmd.Execute   

' Disable PLSQLRSet
Cmd.Properties ("PLSQLRSet") = FALSE

' Clean up
Rst1.Close
Rst2.Close
Rst3.Close

Statement caching eliminates the need to parse each SQL or PL/SQL statement before execution, by caching server cursors created during the initial statement execution. Subsequent executions of the same statement can reuse the parsed information from the cursor, and then execute the statement without reparsing, for better performance.

To see performance gains from statement caching, Oracle recommends caching only those statements that will be repeatedly executed. Furthermore, SQL or PL/SQL statements should use parameters rather than literal values. This will enable you to take full advantage of statement caching. This is because parsed information from parameterized statements can be reused, even if the parameter values change in subsequent executions. However, if the literal values in the statements are different, the parsed information cannot be reused unless the subsequent statements also have the same literal values.

This feature minimizes the retrieval of metadata for SELECT statements by caching the metadata during the initial statement execution. Subsequent executions of the same statement can reuse the cached metadata information for better performance. To see performance gains from metadata caching, Oracle recommends caching only those statements that are executed repeatedly.

The Cancel method cancels the OraOLEDB command currently being executed. This method can be useful when the application needs to cancel a long running command during times of heavy network traffic or heavy server use.

Alternatively, by using the CommandTimeout property, developers can set a limit to the time that a command executes before OraOLEDB attempts to cancel it. OraOLEDB requires setting the EnableCmdTimeout registry value to 1 to enable CommandTimeout.

When using OLE DB, the default DPBROP_COMMANDTIMEOUT is 0 seconds. When using ADO, the default CommandTimeout property is 30 seconds.

OraOLEDB supports both immediate and deferred update mode. However, insert and update operations cannot be deferred when the operation changes a nonscalar column, such as LONG, BLOB, or CLOB. When nonscalar column values are changed in a deferred update mode, the entire row is transmitted to the database as though the operation was in an immediate update mode. In addition, these operations cannot be undone with the Undo method (ADO) or IRowsetUpdate::Undo(). However, if they are in a transaction, they can be rolled back with RollbackTrans method (ADO) or ITransactionLocal::Abort().

Rowsets created using queries with joins are updatable by OraOLEDB only with the Client Cursor Engine enabled. C/C++ OLE DB consumers must enable this service to make these rowsets updatable. ADO consumers must specify the CursorLocation as adUseClient to make these rowsets updatable.

For example:

Dim objCon As New ADODB.Connection
Dim objRst As New ADODB.Recordset

objCon.Provider = "OraOLEDB.Oracle"
objCon.Open "MyOraDb", "scott", "tiger"
objRst.CursorLocation = adUseClient       'ADO Client Cursor
objRst.Open "select ename, dname " & _
       "from emp, dept " & _
       "where emp.deptno = dept.deptno", _
       objCon, adOpenStatic, adLockOptimistic, adCmdText


'Recordset created is updatable. Please note that CursorLocation 
'needs to be explicitly set to adUseClient for this join recordset
'to be updatable.

If DBPROP_SERVERDATAONINSERT (Server Data on Insert) is set to TRUE using OraOLEDB, the consumer can obtain defaults, sequences, and triggered column values from newly inserted and updated rows, if the insert and update operations are made through the rowset.

Having DBPROP_SERVERDATAONINSERT set to TRUE may degrade performance for both insert and update executions using a rowset because OraOLEDB fetches row data from the database for the newly inserted and updated row. However, if DBPROP_SERVERDATAONINSERT is set to its default value of FALSE, only the explicitly provided values for insert and update operations are returned when column values are requested for those rows.

If the base table from which the rowset was created does not contain any defaults, sequences, or triggers, then it is highly recommended that DBPROP_SERVERDATAONINSERT retain its default value of FALSE.

The DBPROP_SERVERDATAONINSERT property does not affect the performance of insert and update operations using the command object.

OraOLEDB only supports searches performed on CHAR, DATE, FLOAT, NUMBER, RAW, and VARCHAR2 columns. Otherwise, DB_E_NOTSUPPORTED is returned.

When a search is done with a NULL value, only the DBCOMPAREOPS_EQ and DBCOMPAREOPS_NE compare operations are supported. Otherwise, DB_E_NOTSUPPORTED is returned.

OraOLEDB-specific connection string attributes which affect the performance of the rowset are:

• CacheType - specifies the type of caching used by the provider to store rowset data. OraOLEDB provides two caching mechanisms:

  • Memory - The provider stores all the rowset data in-memory. This caching mechanism provides better performance at the expense of higher memory utilization. The default is Memory.

  • File - The provider stores all the rowset data on disk. This caching mechanism limits memory consumption at the expense of performance.

• ChunkSize - This attribute specifies the size, in bytes, of the data in LONG and LONG RAW columns fetched and stored in the provider cache. Providing a high value for this attribute improves performance, but requires more memory to store the data in the rowset. Valid values are 1 to 65535. The default is 100.

• FetchSize - specifies the number of rows the provider will fetch at a time (fetch array). It must be set on the basis of data size and the response time of the network. If the value is set too high, then this could result in more wait time during the execution of the query. If the value is set too low, then this could result in many more round trips to the database. Valid values are 1 to 429,496, and 296. The default is 100.

• DeferUpdChk - The DeferUpdChk attribute specifies whether or not to defer the updateability check. This supports updating ADO read-only disconnected rowsets. Valid values are 0 (FALSE) and 1 (TRUE). The default is FALSE, which implies that OraOLEDB does not defer the check. If this attribute is not provided at the connection time, then the default registry value is used.

The default attribute values are set in the registry. The following ADO code example overrides the default attribute values:

Dim con As ADODB.Connection
Set con = NEW ADODB.Connection
con.ConnectionString = "Provider=OraOLEDB.Oracle;User ID=scott;" & _
                          "Password=tiger;Data Source=MyOraDB;" & _
                          "FetchSize=200;CacheType=File;"
con.Open

Setting the ADO Rowset property LockType to adLockPessimistic is not supported by Oracle Provider for OLE DB. If LockType is set to adLockPessimistic, then OraOLEDB behaves similar to when set as adLockOptimistic. This behavior occurs because OraOLEDB does not perform explicit locks on the rows being modified. However, when new data is submitted to the database, the database only performs the update if the rowset data was not already updated by another user, which means that dirty writes are not allowed. LockType values adLockReadOnly, adLockBatchOptimistic, and adLockOptimistic are supported by OraOLEDB.

Setting ADO Rowset property CursorType to adOpenKeyset or adOpenDynamic is not supported by Oracle Provider for OLE DB. OraOLEDB does not support either of the two as Oracle supports Statement Level Read Consistency, which ensures that the data returned by a query contains only committed data as of the time the query was executed. CursorType values adOpenStatic and adOpenForwardOnly are supported by OraOLEDB.

The schema rowsets available through Oracle Provider for OLE DB are:

• DBSCHEMA_COLUMNS

• DBSCHEMA_INDEXES

• DBSCHEMA_SCHEMATA

• DBSCHEMA_VIEWS

• DBSCHEMA_TABLES

• DBSCHEMA_PROVIDER_TYPES (forward scroll only)

• DBSCHEMA_FOREIGN_KEYS

• DBSCHEMA_PRIMARY_KEYS

• DBSCHEMA_PROCEDURES

• DBSCHEMA_PROCEDURE_PARAMETERS

The date format for the Oracle session cannot be set using the ALTER SESSION SET NLS_DATE_FORMAT command. In Visual Basic, date formats are controlled by the Regional Settings properties in Windows Control Panel. For more information on Visual Basic date formats, refer to your Visual Basic documentation.

For Oracle Provider for OLE DB, if the Connection property UseSessionFormat is FALSE, which is a default value, then NLS_DATE_FORMAT is fixed for the session to 'YYYY-MM-DD HH24:MI:SS' by the provider. If you pass the date to Oracle Database as a string, the date must be in the 'YYYY-MM-DD HH24:MI:SS' format. If UseSessionFormat is TRUE, then NLS_DATE_FORMAT is not fixed by Oracle Provider for OLE DB and the default session NLS_DATE_FORMAT is used. For example:

SELECT * FROM EMP WHERE HIREDATE > '1981-06-15 17:32:12'

To use a different format, you need to use the SQL function, TO_DATE(), to specify the format for dates passed as strings. For example:

SELECT * FROM EMP WHERE HIREDATE > TO_DATE('15-JUN-81', 'DD-MON-YY')

However, for dates passed as parameters, the date format is controlled by ADO, which is controlled by the Regional Settings in Windows Control Panel. In this case, TO_DATE() should not be used. For example:

Private Sub Command1_Click()
  Dim objCon As New ADODB.Connection
  Dim objCmd As New ADODB.Command
  Dim objRst  As New ADODB.Recordset
  Dim pDate As New ADODB.Parameter

  objCon.Provider = "OraOLEDB.Oracle"
  objCon.Open "MyOraDb", "scott", "tiger"
  Set pDate = objCmd.CreateParameter("pDate", adDate, adParamInput)
  objCmd.Parameters.Append pDate
  objCmd.CommandText = _
         "SELECT * FROM EMP WHERE HIREDATE > ?"
  objCmd.ActiveConnection = objCon
  objCmd.CommandType = adCmdText
  pDate.Value = "06/15/1981"
  Set objRst = objCmd.Execute

    ...
End Sub

The names of all objects (tables, columns, views, and so forth) in Oracle Database are case-sensitive. This allows the two objects EMP and emp to exist in the same namespace in the database.

The query, SELECT ename FROM emp, executes correctly even though the table name is EMP (all uppercase) in the database. However, if you want to specify object names in mixed case, you can do so by enclosing the name in double quotes. For example:

SELECT ename FROM "Emp"

will execute successfully if the table name in the database is Emp. Double quotes preserve the case of the object names in Oracle Database.

BINARY_FLOAT is a single-precision floating point data type (4 bytes), which is mapped to OLE DB DBTYPE_R4.

BINARY_DOUBLE is a double-precision floating point data type (8 bytes), which is mapped to OLE DB DBTYPE_R8.

This section discusses the Timestamp data types and then provides the following:

• Sample data illustrating insertion and retrieval operations using each of the Timestamp data types.

• A Visual Basic code example using the Timestamp data types.

Timestamp data types are mapped to the OLE DB DBTYPE_DBTIMESTAMP. The OLE DB DBTYPE_DBTIMESTAMP data type does not have TIME ZONE information.

The Timestamp data types include:

• TIMESTAMP

• TIMESTAMP WITH TIME ZONE

• TIMESTAMP WITH LOCAL TIME ZONE

...
Dim DT As Date 
 DT = Now() 
con.ConnectionString = "Provider=OraOLEDB.Oracle.1;User ID=user_name;" & _
    "Password=pwd;Data Source=Oracle;" 
con.Open 
'Must use adUseServer 
rec.CursorLocation = adUseServer 
rec.ActiveConnection = con 
rec.Open "select timestamp_column from test_table", con, adOpenDynamic,_
    adLockOptimistic 
rec.AddNew Array("timestamp_column"), Array(DT) 
 
update data 
rec.Update Array("timestamp_column"), Array("07/07/07 07:17:17 AM") 
...

The INTERVAL data types are mapped to OLE DB DBTYPE_STR data type. The INTERVAL data types include:

• INTERVAL YEAR TO MONTH

• INTERVAL DAY TO SECOND

For the INTERVAL YEAR TO MONTH column, the maximum year_precision is 9 and the default is 2. For INTERVAL DAY TO SECOND column, the maximum day_precision is 9 and the default is 2 and the maximum fractional_seconds_precision is 9, the default is 6.

...
con.ConnectionString = "Provider=OraOLEDB.Oracle.1;User ID=user_name;"& _
     "Password=pwd;Data Source=Oracle;" 
con.Open 
'no restriction on using adUseServer or adUseClient 
rec.CursorLocation = adUseServer 
rec.ActiveConnection = con 
rec.Open "select * from test_table2", con, adOpenDynamic, adLockOptimistic 
rec.AddNew Array("year_to_month_column", "day_to_second_column"), _
    Array("8-1", "3 20:30:10.12")   
 
'update data 
rec.Update Array("year_to_month_column", "day_to_second_column"), _
     Array("2-3", "7 10:20:30.123456")
... 

The Oracle Databases store the Unicode data in the UTF-8 encoding scheme, which is an ASCII compatible multibyte encoding of Unicode. Microsoft Windows uses the UTF-16 encoding, which is a 2-byte fixed-width encoding scheme. OraOLEDB transparently converts the data between the two encoding schemes allowing the consumers to deal with only UTF-16.

OraOLEDB works in two modes, Unicode mode and nonUnicode mode. When the client character set is not a superset of the server character set or the database character set is a multibyte character set, OraOLEDB automatically enables the Unicode mode. In this mode, OraOLEDB stores the data in its cache in the UTF-16 encoding scheme. The user should ensure that the database's character set is AL32UTF8 to prevent any data loss.

If the client character set is a superset of the server's, then the provider operates in the nonUnicode mode. This mode provides slightly better performance as it does not have to deal with larger character buffers required by the UTF-16 encoding.

The detection of the client's and the server's character set is performed during logon.

See "Data Type Mappings in Rowsets and Parameters" for further information.

To prevent any data loss, the database character set should be AL32UTF8. Other than this, there is no other setup required for Unicode support.