Return-Path: 
 <lucene-user-return-9910-apmail-jakarta-lucene-user-archive=jakarta.apache.org@jakarta.apache.org>
Delivered-To: apmail-jakarta-lucene-user-archive@www.apache.org
Received: (qmail 57875 invoked from network); 24 Aug 2004 17:19:32 -0000
Received: from hermes.apache.org (HELO mail.apache.org) (209.237.227.199)
  by minotaur-2.apache.org with SMTP; 24 Aug 2004 17:19:32 -0000
Received: (qmail 83199 invoked by uid 500); 24 Aug 2004 17:19:02 -0000
Delivered-To: apmail-jakarta-lucene-user-archive@jakarta.apache.org
Received: (qmail 83156 invoked by uid 500); 24 Aug 2004 17:19:02 -0000
Mailing-List: contact lucene-user-help@jakarta.apache.org; run by ezmlm
Precedence: bulk
List-Unsubscribe: <mailto:lucene-user-unsubscribe@jakarta.apache.org>
List-Subscribe: <mailto:lucene-user-subscribe@jakarta.apache.org>
List-Help: <mailto:lucene-user-help@jakarta.apache.org>
List-Post: <mailto:lucene-user@jakarta.apache.org>
List-Id: "Lucene Users List" <lucene-user.jakarta.apache.org>
Reply-To: "Lucene Users List" <lucene-user@jakarta.apache.org>
Delivered-To: mailing list lucene-user@jakarta.apache.org
Received: (qmail 83030 invoked by uid 99); 24 Aug 2004 17:19:00 -0000
X-ASF-Spam-Status: No, hits=1.6 required=10.0
	tests=DNS_FROM_RFC_ABUSE,HTML_40_50,HTML_MESSAGE,MSGID_FROM_MTA_HEADER,RCVD_IN_NJABL_PROXY,RCVD_IN_SORBS_MISC
X-Spam-Check-By: apache.org
Received: from [203.199.83.28] (HELO rediffmail.com) (203.199.83.28)
  by apache.org (qpsmtpd/0.27.1) with SMTP; Tue, 24 Aug 2004 10:18:59 -0700
Received: (qmail 11129 invoked by uid 510); 24 Aug 2004 13:55:09 -0000
Date: 24 Aug 2004 13:55:09 -0000
Message-ID: <20040824135509.11128.qmail@webmail18.rediffmail.com>
Received: from unknown (61.11.82.240) by rediffmail.com via HTTP;
 24 aug 2004 13:55:09 -0000
MIME-Version: 1.0
From: "sivalingam T" <thangasival@rediffmail.com>
Reply-To: "sivalingam T" <thangasival@rediffmail.com>
To: lucene-user@jakarta.apache.org
Cc: viji_anbumani@yahoo.com
Subject: PDF indexing
Content-type: multipart/alternative;
	boundary="Next_1093355709---0-203.199.83.28-11108"
X-Virus-Checked: Checked
X-Spam-Rating: minotaur-2.apache.org 1.6.2 0/1000/N

--Next_1093355709---0-203.199.83.28-11108
Content-type: text/plain;
	charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline

 =A0Hi=0A=0AI have written one files for PDF Indexing. Here I have written =
as follows ..  =0A=0AThis is my IndexPDF file.=0A=0Aimport org.apache.lucen=
e.analysis.standard.StandardAnalyzer;=0Aimport org.apache.lucene.document.D=
ocument;=0Aimport org.apache.lucene.index.IndexReader;=0Aimport org.apache.=
lucene.index.IndexWriter;=0Aimport org.apache.lucene.index.Term;=0Aimport o=
rg.apache.lucene.index.TermEnum;=0A=0Aimport org.pdfbox.searchengine.lucene=
.LucenePDFDocument;=0A=0Aimport java.io.File;=0Aimport java.util.Date;=0Aim=
port java.util.Arrays;=0A=0Aclass IndexPDF {=0A  private static boolean del=
eting =3D false;       // true during deletion pass=0A  private static Inde=
xReader reader;            // existing index=0A  private static IndexWriter=
 writer;            // new index being built=0A  private static TermEnum ui=
dIter;            // document id iterator=0A=0A  public static void main(St=
ring[] argv) {=0A    try {=0A      String index =3D "index";=0A      boolea=
n create =3D false;=0A      File root =3D null;=0A=0A      String usage =3D=
 "IndexHTML [-create] [-index <index>] <root_directory>";=0A=0A      if (ar=
gv.length =3D=3D 0) {=0A     System.err.println("Usage: " + usage);=0A     =
return;=0A      }=0A=0A      for (int i =3D 0; i < argv.length; i++) {=0A  =
   if (argv[i].equals("-index")) {            // parse -index option=0A    =
   index =3D argv[++i];=0A     } else if (argv[i].equals("-create")) {     =
  // parse -create option=0A       create =3D true;=0A     } else if (i !=
=3D argv.length-1) {=0A       System.err.println("Usage: " + usage);=0A    =
   return;=0A     } else=0A       root =3D new File(argv[i]);=0A      }=0A=
=0A      Date start =3D new Date();=0A=0A      if (!create) {              =
        // delete stale docs=0A     deleting =3D true;=0A     indexDocs(roo=
t, index, create);=0A      }=0A=0A      writer =3D new IndexWriter(index, n=
ew StandardAnalyzer(), create);=0A      writer.maxFieldLength =3D 1000000;=
=0A=0A      indexDocs(root, index, create);            // add new docs=0A=
=0A      System.out.println("Optimizing index...");=0A      writer.optimize=
();=0A      writer.close();=0A=0A      Date end =3D new Date();=0A=0A      =
System.out.print(end.getTime() - start.getTime());=0A      System.out.print=
ln(" total milliseconds");=0A=0A    } catch (Exception e) {=0A      System.=
out.println(" caught a " + e.getClass() +=0A                "\n with messag=
e: " + e.getMessage());=0A    }=0A  }=0A=0A  /* Walk directory hierarchy in=
 uid order, while keeping uid iterator from=0A  /* existing index in sync. =
 Mismatches indicate one of: (a) old documents to=0A  /* be deleted; (b) un=
changed documents, to be left alone; or (c) new=0A  /* documents, to be ind=
exed.=0A  */=0A=0A  private static void indexDocs(File file, String index, =
boolean create)=0A      throws Exception {=0A    if (!create) {            =
          // incrementally update=0A=0A      reader =3D IndexReader.open(in=
dex);            // open existing index=0A      uidIter =3D reader.terms(ne=
w Term("uid", "")); // init uid iterator=0A=0A      indexDocs(file);=0A=0A =
     if (deleting) {                      // delete rest of stale docs=0A  =
   while (uidIter.term() !=3D null && uidIter.term().field() =3D=3D "uid") =
{=0A       System.out.println("deleting " +=0A                   HTMLDocume=
nt.uid2url(uidIter.term().text()));=0A       reader.delete(uidIter.term());=
=0A       uidIter.next();=0A     }=0A     deleting =3D false;=0A      }=0A=
=0A      uidIter.close();                      // close uid iterator=0A    =
  reader.close();                      // close existing index=0A=0A    } e=
lse                           // don't have exisiting=0A      indexDocs(fil=
e);=0A  }=0A=0A  private static void indexDocs(File file) throws Exception=
=0A  {=0A    if (file.isDirectory())=0A     {                 // if a direc=
tory=0A      String[] files =3D file.list();            // list its files=
=0A      Arrays.sort(files);                 // sort the files=0A      for =
(int i =3D 0; i < files.length; i++)=0A          {  // recursively index th=
em=0A     indexDocs(new File(file, files[i]));=0A          }=0A=0A    } =0A=
     if ((file.getPath().endsWith(".pdf" )) || (file.getPath().endsWith(".P=
DF" )))=0A    {=0A            System.out.println( "Indexing PDF document: "=
 + file );=0A            try=0A               {=0A               //Document=
 doc =3D LucenePDFDocument.getDocument( file );=0A            writer.addDoc=
ument(LucenePDFDocument.getDocument( file));=0A               }=0A         =
      catch(Exception e)=0A               {}=0A    }=0A      =0A  }=0A  =0A=
}=0A=0Awhen i use the following commands, the exceptions are thrown if anyb=
ody know please inform me.=0A=0A=0AC:\>java org.apache.lucene.demo.IndexPDF=
 -create -index c:\lucene\pdf c:\pdfs\Words.pdf=0A=0AIndexing PDF document:=
 c:\pdfs\Words.pdf=0AException in thread "main" java.lang.NoClassDefFoundEr=
ror: org/apache/log4j/Cate=0Agory=0A        at org.pdfbox.searchengine.luce=
ne.LucenePDFDocument.addContent(LucenePDF=0ADocument.java:197)=0A        at=
 org.pdfbox.searchengine.lucene.LucenePDFDocument.getDocument(LucenePD=0AFD=
ocument.java:118)=0A        at org.apache.lucene.demo.IndexPDF.indexDocs(Un=
known Source)=0A        at org.apache.lucene.demo.IndexPDF.indexDocs(Unknow=
n Source)=0A        at org.apache.lucene.demo.IndexPDF.main(Unknown Source)=
=0A=0A=0A=0AThanks.=0A=0A=0A=0A=0A=0A=0AWith Warm Regards,=0D=0ASivalingam.=
T=0D=0A=0D=0ASai Eswar Innovations (P) Ltd,=0D=0AChennai-92
--Next_1093355709---0-203.199.83.28-11108--