Field fieldA = new Field("contents", fileTextA, Field.Store.YES,Field.Index.TOKENIZED);
docA.add(fieldA);
Document docB = new Document();
String fileTextB = " 数据挖掘(Data Mining)，又称为数据库中的知识发现(Knowledge Discovery in Database, KDD)，就是从大量数据中获取有效的、新颖的、潜在有用的、最终可理解的模式的非平凡过程，简单的说，数据挖掘就是从大量数据中提取或“挖掘”知识。 ";
Field fieldB = new Field("contents", fileTextB, Field.Store.YES,Field.Index.TOKENIZED);
docB.add(fieldB);
writer.addDocument(docA);
writer.addDocument(docB);
writer.optimize();
writer.close();
}
public void search(String fieldName,String keyword) throws CorruptIndexException, IOException, ParseException{
searcher = new IndexSearcher(indexPath); 数据挖掘实验室
QueryParser queryParse = new QueryParser(fieldName, analyzer);
Query query = queryParse.parse(keyword);
Hits hits = searcher.search(query);
for(int i=0;i<hits.length();i++){
Document doc = hits.doc(i);
String text = doc.get(fieldName);
//System.out.println("||||||||||||"+text);
int htmlLength = prefixHTML.length()+suffixHTML.length();
System.out.println("高亮HTML的总长度为"+htmlLength);
SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter(prefixHTML, suffixHTML);
Highlighter highlighter = new Highlighter(simpleHTMLFormatter,new QueryScorer(query));
String highLightText = highlighter.getBestFragment(analyzer,"contents",text); 数据挖掘论坛
System.out.println("★高亮显示第 "+(i+1) +" 条检索结果如下所示：");
System.out.println(highLightText);
System.out.println("显示第 "+(i+1) +" 条检索结果摘要的长度为(含高亮HTML代码)："+highLightText.length());
}
searcher.close();
}
public static void main(String[] args) {
ExtractDigest ed = new ExtractDigest();
try {
ed.createIndex();
ed.search("contents", "根据 挖掘");
} catch (CorruptIndexException e) {
|
