Lucene + Sen combined to implement a simple query engine (Japanese)

Related materials: http://ultimania.org/sen/

Perl5.6 to reduce: http://www.activestate.com/store/download.aspx? Prdguid = 81fbce82-6bd5-49bc-a915-08d58c2648ca
Ant1.5 reduction: http://ant.apache.org/bindownload.cgi
Note) Ant-dperl. bin = D:/Java/perl/bin/perl.exe
: Https://sen.dev.java.net/servlets/ProjectDocumentList? Folderid = 755 & expandfolder = 755 & folderid = 0

The Code is as follows:

Package demo;

Import java. Io. bufferedreader;
Import java. Io. ioexception;
Import java. Io. inputstreamreader;

Import org. Apache. Lucene. analysis. analyzer;
Import org. Apache. Lucene. analysis. Ja. japaneseanalyzer;
Import org.apache.e.doc ument. Document;
Import org.apache.e.doc ument. field;
Import org. Apache. Lucene. Index. indexwriter;
Import org. Apache. Lucene. queryparser. parseexception;
Import org. Apache. Lucene. queryparser. queryparser;
Import org. Apache. Lucene. Search. Hits;
Import org. Apache. Lucene. Search. indexsearcher;
Import org. Apache. Lucene. Search. query;
Import org. Apache. Lucene. Store. Directory;
Import org. Apache. Lucene. Store. fsdirectory;
Import org. Apache. Lucene. Store. ramdirectory;

Public class hellolucene ...{

Private Static final string field_content = "content ";

Private Static final string sen_xml_path = "D:/Java/sen-1.2.2.1/CONF/SEN. xml ";

Private Static final directory = new ramdirectory ();

Private Static final analyzer = new japaneseanalyzer (sen_xml_path );

Private Static final queryparser QP = new queryparser (field_content, analyzer );



Private Static final string [] Contents = ...{

"カツオ ", "サザはワ", "ワ ", "ワ ",

"カオは ", "サエは ", "ワカ ",

"マスはサ ", "", "タち ",

"サザとマ ", "", "",

"マス ", "カオは ", ""

};



Public static void main (string [] ARGs) throws ioexception, parseexception ...{

Makeindex ();

Backupindex ();

Bufferedreader BR = new bufferedreader (New inputstreamreader (system. In ));

String q = NULL;

While (q = NULL |! Q. Equals ("Q "))...{

System. Out. Print ("Q already asked)> ");

System. Out. Flush ();

Q = Br. Readline ();

If (! Q. Equals ("Q "))

Searchindex (Q );

}

BR. Close ();

If (directory! = NULL)

Directory. Close ();

}



Private Static void makeindex () throws ioexception ...{

Indexwriter writer = new indexwriter (directory, analyzer, true );

For (INT I = 0; I <contents. length; I ++ )...{

Document Doc = new document ();

Doc. Add (new field (field_content, contents [I], field. Store. Yes, field. Index. tokenized ));

Writer. adddocument (DOC );

}

Writer. Close ();

}



Private Static void searchindex (final string q) throws ioexception, parseexception ...{

Indexsearcher searcher = new indexsearcher (directory );

Query query = QP. parse (Q );

Hits hits = searcher. Search (query );

Int length = hits. Length ();

System. Out. println (integer. tostring (length) +. ");

For (INT I = 0; I <length; I ++ )...{

Document Doc = hits.doc (I );

System. Out. println ("" + Doc. Get (field_content ));

}

Searcher. Close ();

}



Private Static void backupindex () throws ioexception ...{

Directory persistent = fsdirectory. getdirectory ("Index ");

Directory. Copy (directory, persistent, false );

Persistent. Close ();

}
}

References:

Http://lucene.jugem.jp /? Month = 200703

Http://www.geocities.jp/another4000yrs/lucene/

Http://repository.kulib.kyoto-u.ac.jp/dspace-memo/japanization.html

Http://lucene.jugem.jp /? Eid = 53

Http://lucene.jugem.jp /? Eid = 97

Http://www.getopt.org/luke/

Chinese:

Http://www.javaeye.com/topic/49441? Page = 6

Http://blog.cnblog.org/archives/2005/07/luceneaecee.html

Http://blog.csdn.net/ugg/archive/2007/03/06/1522624.aspx

Http://www.ideagrace.com/html/doc/2007/02/07/08630.html