Hi THere
In the absense of documentation, I am trying to convert an EmailFilter
class to Lucene 3.0. Its not working! Obviously, my understanding of the
new token filter mechanism is misguided.
Can someone in the know help me out for a sec and let me know where I am
going wrong. Thanks.
import org.apache.commons.logging.*;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import java.io.IOException;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.Stack;
/* Many thanks to Michael J. Prichard" <michael_prich...@mac.com> for his
* original the email filter code. It is rewritten. */
public class EmailFilter extends TokenFilter implements Serializable {
public EmailFilter(TokenStream in) {
super(in);
}
public final boolean incrementToken() throws java.io.IOException {
if (!input.incrementToken()) {
return false;
}
TermAttribute termAtt = (TermAttribute)
input.getAttribute(TermAttribute.class);
char[] buffer = termAtt.termBuffer();
final int bufferLength = termAtt.termLength();
String emailAddress = new String(buffer, 0,bufferLength);
emailAddress = emailAddress.replaceAll("<", "");
emailAddress = emailAddress.replaceAll(">", "");
emailAddress = emailAddress.replaceAll("\"", "");
String [] parts = extractEmailParts(emailAddress);
clearAttributes();
for (int i = 0; i < parts.length; i++) {
if (parts[i]!=null) {
TermAttribute newTermAttribute =
addAttribute(TermAttribute.class);
newTermAttribute.setTermBuffer(parts[i]);
newTermAttribute.setTermLength(parts[i].length());
}
}
return true;
}
private String[] extractWhitespaceParts(String email) {
String[] whitespaceParts = email.split(" ");
ArrayList<String> partsList = new ArrayList<String>();
for (int i=0; i < whitespaceParts.length; i++) {
partsList.add(whitespaceParts[i]);
}
return whitespaceParts;
}
private String[] extractEmailParts(String email) {
if (email.indexOf('@')==-1)
return extractWhitespaceParts(email);
ArrayList<String> partsList = new ArrayList<String>();
String[] whitespaceParts = extractWhitespaceParts(email);
for (int w=0;w<whitespaceParts.length;w++) {
if (whitespaceParts[w].indexOf('@')==-1)
partsList.add(whitespaceParts[w]);
else {
partsList.add(whitespaceParts[w]);
String[] splitOnAmpersand = whitespaceParts[w].split("@");
try {
partsList.add(splitOnAmpersand[0]);
partsList.add(splitOnAmpersand[1]);
} catch (ArrayIndexOutOfBoundsException ae) {}
if (splitOnAmpersand.length > 0) {
String[] splitOnDot = splitOnAmpersand[0].split("\\.");
for (int i=0; i < splitOnDot.length; i++) {
partsList.add(splitOnDot[i]);
}
}
if (splitOnAmpersand.length > 1) {
String[] splitOnDot = splitOnAmpersand[1].split("\\.");
for (int i=0; i < splitOnDot.length; i++) {
partsList.add(splitOnDot[i]);
}
if (splitOnDot.length > 2) {
String domain = splitOnDot[splitOnDot.length-2]
+ "." + splitOnDot[splitOnDot.length-1];
partsList.add(domain);
}
}
}
}
return partsList.toArray(new String[0]);
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: java-user-unsubscr...@lucene.apache.org
For additional commands, e-mail: java-user-h...@lucene.apache.org
