Skip to content

Commit 483ffa8

Browse files
kkasunpererakkasunperera
committed
Adding methods to query Wik revision history
ReadXMLFile class parse the out put results XML file and count the number of revisions
1 parent 022a693 commit 483ffa8

File tree

3 files changed

+293
-0
lines changed

3 files changed

+293
-0
lines changed

‎WikipediaCategoryProcessor/src/main/java/org/dbpedia/kasun/wikiquery/ReadXMLFile.java‎

Lines changed: 134 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,134 @@
1+
/*
2+
* To change this template, choose Tools | Templates
3+
* and open the template in the editor.
4+
*/
5+
/**
6+
*
7+
* Date Author Changes Sep 10, 2013 Kasun Perera Created
8+
*
9+
*/
10+
package org.dbpedia.kasun.wikiquery;
11+
12+
13+
/**
14+
* TODO- describe the purpose of the class
15+
*
16+
*/
17+
import javax.xml.parsers.DocumentBuilderFactory;
18+
import javax.xml.parsers.DocumentBuilder;
19+
import org.w3c.dom.Document;
20+
import org.w3c.dom.NodeList;
21+
import org.w3c.dom.Node;
22+
import org.w3c.dom.Element;
23+
import java.io.File;
24+
import java.io.UnsupportedEncodingException;
25+
import java.net.URLEncoder;
26+
27+
public class ReadXMLFile
28+
{
29+
30+
public static void ReadFile( String filename )
31+
{
32+
//public static void ReadFile(File fXmlFile) {
33+
try
34+
{
35+
36+
File fXmlFile = new File( filename );
37+
DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();
38+
DocumentBuilder dBuilder = dbFactory.newDocumentBuilder();
39+
Document doc = dBuilder.parse( fXmlFile );
40+
41+
//optional, but recommended
42+
//read this - http://stackoverflow.com/questions/13786607/normalization-in-dom-parsing-with-java-how-does-it-work
43+
doc.getDocumentElement().normalize();
44+
45+
System.out.println( "Root element :" + doc.getDocumentElement().getNodeName() );
46+
47+
NodeList nList = doc.getElementsByTagName( "rev" );
48+
49+
System.out.println( "----------------------------" );
50+
51+
for ( int temp = 0; temp < nList.getLength(); temp++ )
52+
{
53+
54+
Node nNode = nList.item( temp );
55+
56+
System.out.println( "Current Element :" + nNode.getNodeName() );
57+
58+
if ( nNode.getNodeType() == Node.ELEMENT_NODE )
59+
{
60+
61+
62+
Element eElement = (Element) nNode;
63+
64+
System.out.println( "Revision22222 id : " + eElement.getAttribute( "revid" ) );
65+
// System.out.println("First Name : " + eElement.getElementsByTagName("firstname").item(0).getTextContent());
66+
// System.out.println("Last Name : " + eElement.getElementsByTagName("lastname").item(0).getTextContent());
67+
// System.out.println("Nick Name : " + eElement.getElementsByTagName("nickname").item(0).getTextContent());
68+
// System.out.println("Salary : " + eElement.getElementsByTagName("salary").item(0).getTextContent());
69+
70+
}
71+
}
72+
} catch ( Exception e )
73+
{
74+
e.printStackTrace();
75+
}
76+
}
77+
78+
public static int ReadFile( Document doc ,String urlParameters, String url) throws UnsupportedEncodingException
79+
{
80+
81+
int numberOfRevisions=0;
82+
//public static void ReadFile(File fXmlFile) {
83+
try
84+
{
85+
doc.getDocumentElement().normalize();
86+
87+
// System.out.println( "Root element :" + doc.getDocumentElement().getNodeName() );
88+
89+
NodeList continueNodeList = doc.getElementsByTagName( "revisions" );
90+
if ( continueNodeList.getLength() > 0 )
91+
{
92+
Node continueNode = continueNodeList.item( 0 );
93+
94+
Element continueElement = (Element) continueNode;
95+
// String urlParameters = "fName=" + URLEncoder.encode( "???", "UTF-8" ) + "&lName=" + URLEncoder.encode( "???", "UTF-8" );
96+
// String url = "http://en.wikipedia.org/w/api.php?action=query&format=xml&prop=revisions&titles=Mother&rvlimit=max&rvstart=20130604000000&rvcontinue="+continueElement.getAttribute( "rvcontinue" );
97+
98+
// System.out.println("Calling recursive function using rivision Id "+ continueElement.getAttribute( "rvcontinue" ));
99+
numberOfRevisions=ReadFile(RevisionHistory.excutePost( url+ "&rvcontinue="+continueElement.getAttribute( "rvcontinue" ), urlParameters ),urlParameters, url );
100+
101+
// System.out.println( "Continue revision Id : " + continueElement.getAttribute( "rvcontinue" ) );
102+
}
103+
104+
NodeList nList = doc.getElementsByTagName( "rev" );
105+
106+
// System.out.println( "number of nodes" + nList.getLength());
107+
/*
108+
for ( int temp = 0; temp < nList.getLength(); temp++ )
109+
{
110+
111+
Node nNode = nList.item( temp );
112+
113+
// System.out.println( "\nCurrent Element :" + nNode.getNodeName() + " count: " + temp );
114+
115+
if ( nNode.getNodeType() == Node.ELEMENT_NODE )
116+
{
117+
118+
Element eElement = (Element) nNode;
119+
120+
System.out.println( "Revision id : " + eElement.getAttribute( "revid" ) );
121+
122+
}
123+
}
124+
*/
125+
126+
return numberOfRevisions+ nList.getLength();
127+
} catch ( Exception e )
128+
{
129+
e.printStackTrace();
130+
return 0;
131+
132+
}
133+
}
134+
}

‎WikipediaCategoryProcessor/src/main/java/org/dbpedia/kasun/wikiquery/RevisionHistory.java‎

Lines changed: 110 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,110 @@
1+
/*
2+
* To change this template, choose Tools | Templates
3+
* and open the template in the editor.
4+
*/
5+
/**
6+
*
7+
* Date Author Changes Sep 10, 2013 Kasun Perera Created
8+
*
9+
*/
10+
package org.dbpedia.kasun.wikiquery;
11+
12+
13+
import java.io.*;
14+
import java.net.HttpURLConnection;
15+
import java.net.URL;
16+
import org.w3c.dom.Document;
17+
import javax.xml.parsers.DocumentBuilder;
18+
import javax.xml.parsers.DocumentBuilderFactory;
19+
20+
/**
21+
* TODO- describe the purpose of the class
22+
*
23+
*/
24+
public class RevisionHistory
25+
{
26+
27+
// public static String excutePost( String targetURL, String urlParameters )
28+
public static Document excutePost( String targetURL, String urlParameters )
29+
{
30+
URL url;
31+
HttpURLConnection connection = null;
32+
try
33+
{
34+
//Create connection
35+
url = new URL( targetURL );
36+
connection = (HttpURLConnection) url.openConnection();
37+
connection.setRequestMethod( "GET" );
38+
connection.setRequestProperty( "Accept", "application/xml" );
39+
40+
//connection.setRequestProperty( "Content-Length", ""+ Integer.toString( urlParameters.getBytes().length ) );
41+
// connection.setRequestProperty( "Content-Language", "en-US" );
42+
43+
connection.setUseCaches( false );
44+
connection.setDoInput( true );
45+
connection.setDoOutput( true );
46+
47+
//Send request
48+
DataOutputStream wr = new DataOutputStream(
49+
connection.getOutputStream() );
50+
wr.writeBytes( urlParameters );
51+
wr.flush();
52+
wr.close();
53+
54+
//Get Response
55+
InputStream is = connection.getInputStream();
56+
57+
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
58+
DocumentBuilder db = dbf.newDocumentBuilder();
59+
Document doc = (Document) db.parse(is);
60+
61+
62+
/*
63+
BufferedReader rd = new BufferedReader( new InputStreamReader( is ) );
64+
String line;
65+
66+
67+
// Create temp file.
68+
File temp = File.createTempFile( "pattern", ".xml" );
69+
70+
// Delete temp file when program exits.
71+
temp.deleteOnExit();
72+
73+
// Write to temp file
74+
BufferedWriter out = new BufferedWriter( new FileWriter( temp ) );
75+
76+
77+
78+
StringBuffer response = new StringBuffer();
79+
while ( ( line = rd.readLine() ) != null )
80+
{
81+
out.write( line + "\n" );
82+
83+
System.out.println( line + "\n" );
84+
response.append( line + "\n" );
85+
// response.append( '\r' );
86+
}
87+
rd.close();
88+
out.close();
89+
90+
91+
*/
92+
return doc;
93+
// return response.toString();
94+
95+
} catch ( Exception e )
96+
{
97+
98+
e.printStackTrace();
99+
return null;
100+
101+
} finally
102+
{
103+
104+
if ( connection != null )
105+
{
106+
connection.disconnect();
107+
}
108+
}
109+
}
110+
}

‎WikipediaCategoryProcessor/src/main/java/org/dbpedia/kasun/wikiquery/WikiQuery.java‎

Lines changed: 49 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,49 @@
1+
/*
2+
* To change this template, choose Tools | Templates
3+
* and open the template in the editor.
4+
*/
5+
6+
7+
8+
/**
9+
* KarshaAnnotate- Annotation tool for financial documents
10+
*
11+
*
12+
* Date Author Changes
13+
* Sep 10, 2013 Kasun Perera Created
14+
*
15+
*/
16+
17+
package org.dbpedia.kasun.wikiquery;
18+
19+
20+
import java.io.FileNotFoundException;
21+
import java.io.IOException;
22+
import java.io.UnsupportedEncodingException;
23+
import java.net.URLEncoder;
24+
25+
26+
27+
/**
28+
* TODO- describe the purpose of the class
29+
*
30+
*/
31+
public class WikiQuery {
32+
33+
public static void main(String[] args ) throws UnsupportedEncodingException {
34+
35+
int pageId=83430;
36+
37+
String urlParameters = "fName=" + URLEncoder.encode("???", "UTF-8") + "&lName=" + URLEncoder.encode("???", "UTF-8");
38+
//timestamp June 4th, 2013 00:00:00 UTC=20130604000000
39+
// String url="http://en.wikipedia.org/w/api.php?action=query&format=xml&prop=revisions&titles=Mother&rvlimit=max&rvstart=20130604000000";
40+
String url="http://en.wikipedia.org/w/api.php?action=query&format=xml&prop=revisions&pageids="+pageId+"&rvlimit=max&rvstart=20130604000000";
41+
42+
//pageid
43+
// RevisionHistory.excutePost( url, urlParameters );
44+
// ReadXMLFile.ReadFile( "C:\\Users\\lsf\\Documents\\NetBeansProjects\\WikipediaCategoryProcessor\\api.xml");
45+
int totalRevisions= ReadXMLFile.ReadFile(RevisionHistory.excutePost( url, urlParameters ),urlParameters,url);
46+
System.out.println("totalRevisions "+ totalRevisions);
47+
}
48+
49+
}

0 commit comments

Comments
 (0)