package utils;
import java.io.IOException;
import java.nio.file.Paths;
import java.text.ParseException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexReaderContext;
import org.apache.lucene.index.LeafReader;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.MultiFields;
import org.apache.lucene.index.PostingsEnum;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.Terms;
import org.apache.lucene.index.TermsEnum;
import org.apache.lucene.queryparser.ext.Extensions.Pair;
import org.apache.lucene.search.DocIdSetIterator;
import org.apache.lucene.search.similarities.TFIDFSimilarity;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.NIOFSDirectory;
import org.apache.lucene.util.BytesRef;
public class TF_IDF {
String index="D:\\alia\\aila20-task-data\\aila20-task1\\dataset\\index_q";
public List<List<Pair<String,Double>>> tfidf() {
List<List<Pair<String,Double>>> ret=new ArrayList<>();
try {
Directory dir=new NIOFSDirectory(Paths.get(index));
IndexReader ir=DirectoryReader.open(dir);
for(int i=1;i<ir.maxDoc();i++) {
List<Pair<String,Double>> newmap=new ArrayList<>();
Terms terms=ir.getTermVector(i, "content");
TermsEnum p=terms.iterator();
BytesRef tmp=null;
PostingsEnum posting=null;
int k=0;
while((tmp=p.next())!=null) {
posting=p.postings(posting,PostingsEnum.ALL);
posting.nextDoc();
newmap.add(new Pair<String, Double>(new String(tmp.bytes, tmp.offset, tmp.length), ((double)posting.freq()/terms.size())));
}
ret.add(newmap);
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return ret;
}
}
最新版luence中求index tf值的实现
最新推荐文章于 2021-02-21 22:09:23 发布