| Oracle FAQ | Your Portal to the Oracle Knowledge Grid | |
 |
 | |||
| Oracle FAQ | Your Portal to the Oracle Knowledge Grid | |
|
| |||
Home -> Community -> Usenet -> c.d.o.tools -> Re: Large XML Data, Parsing, JDBC, RMI, 2 Oracle DB
Hi, this is the parsing program. It doesn;t do any Thread yet. Can anyone suggest a better way to do it with thread ? Thanks again
import oracle.xml.parser.v2.*;
import oracle.jdbc.driver.*;
import java.io.*; import java.net.*; import java.util.*; import java.util.Date; import java.text.*; import java.sql.*; import java.rmi.*;
import javax.naming.*;
import javax.sql.*;
public class DataParsing implements XMLToken {
static XMLTokenizer parser = null;
static int num = 0, i = 0, count = 0;
static String rElement, thisElement, thisAtt, caseID, s;
static StringBuffer sbuffer;
static StringBuffer[] between = new StringBuffer[10];
static Connection conn = null;
static PreparedStatement pstmt = null;
static ResultSet rs = null;
static PrintWriter debug;
static DataInsert insertDB = null;
//private Thread myThread;
static public void main(String[] args) throws IOException, Exception {
try
{
insertDB = (DataInsert)Naming.lookup(args[0]);
doParse("file.xml");
}catch(Exception e) {
e.printStackTrace();
}
if(myThread == null)
{
myThread = new Thread(this);
myThread.start();
}
URL url = createURL(arg);
parser = new XMLTokenizer((XMLToken)new DataParsing());
parser.setToken (STagName, true);
parser.setToken (EmptyElemTag, true);
parser.setToken (STag, true);
parser.setToken (ETag, true);
parser.setToken (ETagName, true);
parser.setToken (Attribute, true);
parser.setToken (AttName, true);
parser.setToken (AttValue, true);
parser.setToken (Reference, true);
parser.setToken (Comment, true);
parser.setToken (CharData, true);
parser.setToken (CDSect, true);
parser.setToken (PI, true);
parser.setToken (PITarget, true);
parser.setToken (XMLDecl, true);
parser.setToken (TextDecl, true);
parser.setToken (DTDName, true);
parser.setToken (AttListDecl, true);
parser.setToken (elementdecl, true);
parser.setToken (ElemDeclName, true);
parser.setToken (EntityDecl, true);
parser.setToken (EntityDeclName, true);
parser.setToken (EntityValue, true);
parser.setToken (NotationDecl, true);
parser.setToken (ExternalID, true);
try {
parser.tokenize (url);
} catch (SAXException e) {
//System.out.println (e.getMessage());
}
// This is read by doParse(arg)
public void token(int token, String value)
{
switch (token) {
case XMLToken.STagName:
thisElement = value; // set current element
if(value.equals (rElement)) {
parser.setToken (Comment, false);
parser.setToken (CharData, false);
parser.setToken (CDSect, false);
parser.setToken (PI, false);
}
break;
case XMLToken.ETagName:
if(value.equals (rElement)){
parser.setToken (Comment, true);
parser.setToken (CharData, true);
parser.setToken (CDSect, true);
parser.setToken (PI, true);
}
break;
case XMLToken.CharData:
if (thisElement.equals("Title"))
{
try
{
insertDB.Title(caseID,value);
}catch(SQLException sqle){
sqle.printStackTrace();
}catch(RemoteException rme){
rme.printStackTrace();
}
}
if (thisElement.equals("Description"))
{
try{
insertDB.Description(caseID,value);
}catch(SQLException sqle){
sqle.printStackTrace();
}catch(RemoteException rme){
rme.printStackTrace();
}
}
case XMLToken.AttName:
thisAtt = value; // set current attribute
break;
case XMLToken.AttValue:
sbuffer = new StringBuffer(value);
s = new String(sbuffer.substring(1, sbuffer.length()-1));
if(thisElement.equals("Case"))
{
if(thisAtt.equals("ID"))
{
caseID = s;
}
}
break;
default:
break;
}
static public URL createURL(String fileName) {
URL url = null;
try {
url = new URL(fileName);
} catch (MalformedURLException ex) {
File f = new File(fileName);
try
{
String path = f.getAbsolutePath();
// This is a bunch of weird code that is required to
// make a valid URL on the Windows platform, due
// to inconsistencies in what getAbsolutePath returns.
String fs = System.getProperty("file.separator");
if (fs.length() == 1)
{
char sep = fs.charAt(0);
if (sep != '/')
path = path.replace(sep, '/');
if (path.charAt(0) != '/')
path = '/' + path;
}
path = "file://" + path;
url = new URL(path);
}
catch (MalformedURLException e)
{
System.out.println("Cannot create url for:" + fileName);
System.exit(0);
}
}
return url;
}
©Ø
In article <tlilner8k3pd5d_at_corp.supernews.com>, "Raden Java" <radenjava_at_theglobe.com.invalide> wrote:
> Hi, > > I'm trying to insert a large of data over 25,000,000 elements in xml > format to 2 different Oracle Database on 2 different server. > > I'm currently working on 4 machines, machine A 1 and 2 is a database > running Oracle 9i, machine B is a parsing machine (8 CPU Solaris), and > machine C is where the RMI Connection to Database. > > What, I'm doing right now is I'm parsing every elements from the files > using Oracle Parser and insert it to database using jdbc. But the > program isn;t using all of the cpus because it's only capable to Parse > and insert around 18,000 elements / hour, 432,000 elements in 1 day. > So to parse all of data it will take around 57 days ? It should be > something wrong here, but I don't have any clue on how to get through > it. > > My only thought is to modified the parsing program, to utilize the 8 > cpus resources. > > Can someone guide me how to find resource in Parallelism, so the Parsing > program will utilize the SMP. > > Or if anyone have some advice on the best way to implement it, I really > appreciate it. > > ThanksReceived on Sat Jul 21 2001 - 13:54:46 CDT
 |
 |