有的应用有些要求,对于某类型的内容即使满足条件了,但是也不能被搜索出来,lucene中提供了过滤器的功能,
通过自定义的过滤器继承Filter,从 而实现特定的过滤功能。Filter是一种过滤行为BitSet是一种位集合队列,
这个队列中只有两种取值,TRUE或FALSE,LUCENE以这两种取值代表文档是否被过 滤,也就是说,LUCENE返回结果时,
会首先遍历BITSET,仅将那些对应值为TRUE的文档返回。
public interface FilterAccessor {
public String[] values();
public String getField();
public boolean set();
}
public class MyIDFilter extends Filter {
private FilterAccessor accessor;
public MyIDFilter(FilterAccessor accessor) {
this.accessor = accessor;
}
@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
//创建一个bit,默认所有的元素都是0,表示都不显示
OpenBitSet obs = new OpenBitSet(reader.maxDoc());
if(accessor.set()) {
set(reader,obs);
} else {
clear(reader, obs);
}
return obs;
}
private void set(IndexReader reader,OpenBitSet obs) {
try {
int[] docs = new int[1];
int [] freqs = new int[1];
//获取id所在的doc的位置,并且将其设置为0
for(String delId:accessor.values()) {
//获取TermDocs
TermDocs tds = reader.termDocs(new Term(accessor.getField(),delId));
//会见查询出来的对象的位置存储到docs中,出现的频率存储到freqs中,返回获取的条数
int count = tds.read(docs, freqs);
if(count==1) {
obs.set(docs[0]);
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
private void clear(IndexReader reader,OpenBitSet obs) {
try {
//先把元素填满,整个集合设置为TRUE,表示当前集合内的所有文档都是可以被检索到的
obs.set(0,reader.maxDoc());
int[] docs = new int[1];
int [] freqs = new int[1];
for(String delId:accessor.values()) {
//获取TermDocs
TermDocs tds = reader.termDocs(new Term(accessor.getField(),delId));
//会见查询出来的对象的位置存储到docs中,出现的频率存储到freqs中,返回获取的条数
int count = tds.read(docs, freqs);
if(count==1) {
//将这个位置的元素删除
obs.clear(docs[0]);
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
}
public void searchByCustomFilter() {
try {
IndexSearcher searcher = new IndexSearcher(IndexReader.open(FileIndexUtils.getDirectory()));
Query q = new TermQuery(new Term("content","java"));
TopDocs tds = null;
tds = searcher.search(q, new MyIDFilter(new FilterAccessor() {
@Override
public String[] values() {
return new String[]{"Ant.she","Ant.txt","java.txt"};
}
@Override
public boolean set() {
return true;
}
@Override
public String getField() {
return "filename";
}
}),200);
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss");
for(ScoreDoc sd:tds.scoreDocs) {
Document d = searcher.doc(sd.doc);
System.out.println(sd.doc+":("+sd.score+")" +
"["+d.get("filename")+"【"+d.get("path")+"】--->"+
d.get("size")+"------------>"+d.get("id"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}