createIndexWriter();// 生成indexWriter对象
for (Article article : list) {
Document document = new Document();// 生成Document对象
Field field = new Field("articleId", String.valueOf(article.getArticleId()), Field.Store.YES, Field.Index.NO);
Field field2 = new Field("articleName", article.getArticleName(),Field.Store.YES, Field.Index.ANALYZED);
Field field3 = new Field("articleContent", article.getArticleContent(), Field.Store.YES, Field.Index.NO);
document.add(field);
document.add(field2);
document.add(field3);
try {
indexWriter.addDocument(document);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
closeIndexWriter(indexWriter);
}
/**
* 函数功能：建立对文章的高亮显示查询
*
*/
public void createHightLightIndex(List
createIndexWriter();// 生成indexWriter对象
System.out.println("createHightLightIndex list length" + list.size());
for (LogQueryTemp logQuery : list) {
Document document = new Document();// 生成Document对象
Field field = new Field("articleId", String.valueOf(logQuery.getArticleId()), Field.Store.YES, Field.Index.NO);
Field field2 = new Field("articleName", logQuery.getArticleName(),Field.Store.YES, Field.Index.ANALYZED);
Field field3 = new Field("articleKindName", logQuery.getArticleKindName(), Field.Store.YES, Field.Index.NO);
Field field4 = new Field("writeTime", logQuery.getWriteTime(),Field.Store.YES, Field.Index.NO);
Field field5 = new Field("articleContent", logQuery.getArticleContent(), Field.Store.YES, Field.Index.ANALYZED);
document.add(field);
document.add(field2);
document.add(field3);
document.add(field4);
document.add(field5);
try {
indexWriter.addDocument(document);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
closeIndexWriter(indexWriter);
}
/**
* 函数功能：建立查询图片的索引（主要是对图片的描述建立索引）
*
*/
public void createPicIndex(List
createIndexWriter();// 生成indexWriter对象
for (PicQueryTemp picQuery : list) {
Document document = new Document();// 生成Document对象
Field field = new Field("picId", String.valueOf(picQuery.getPicId()), Field.Store.YES,Field.Index.NO);
Field field2 = new Field("picGroupId", String.valueOf(picQuery.getPicGroupId()), Field.Store.YES, Field.Index.NO);
Field field3 = new Field("picName", picQuery.getPicName(),Field.Store.YES, Field.Index.NO);
Field field4 = new Field("pictureDetail", picQuery.getPictureDetail(), Field.Store.YES, Field.Index.ANALYZED);
document.add(field);
document.add(field2);
document.add(field3);
document.add(field4);
try {
indexWriter.addDocument(document);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
closeIndexWriter(indexWriter);
}
/**
* 函数功能 ：关闭indexWriter
*
* @param indexWriter
*/
public void closeIndexWriter(IndexWriter indexWriter) {
try {
indexWriter.optimize();
indexWriter.close();
date2 = new Date();
System.out.println("建立索引总共用了:" + (date2.getTime() - date.getTime())
+ "毫秒");
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 函数功能:生成indexWriter对象
*/
public void createIndexWriter() {
try {
boolean flag = true;
// 如果已存在索引,则追加索引
if (IndexReader.indexExists(indexPath)) {
flag = false;
}
indexWriter = new IndexWriter(indexPath, new StandardAnalyzer(),
flag, IndexWriter.MaxFieldLength.LIMITED);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 函数功能:查询文章的索引
*/
public List
List
System.out.println("查询内容为:" + findContent);
try {
dir = FSDirectory.getDirectory(indexPath);
searcher = new IndexSearcher(dir);
QueryParser parser = new QueryParser("articleName",
new StandardAnalyzer());
try {
Query query = parser.parse(findContent);// 根据查询内容进行查询
TopDocs topDocs = searcher.search(query, 5);
ScoreDoc[] hits = topDocs.scoreDocs;
for (int i = 0; i < hits.length; i++) {
int DocId = hits[i].doc;
Article article = new Article();
Document doc = searcher.doc(DocId);
article.setArticleId(Integer.parseInt(doc.get("articleId")));
article.setArticleName(doc.get("articleName"));
article.setArticleContent(doc.get("articleContent"));
list2.add(article);
}
Date date3 = new Date();
System.out.println("查询总共花的时间为:"+ (date3.getTime() - date2.getTime()) + "毫秒");
} catch (ParseException e) {
e.printStackTrace();
}
} catch (IOException e) {
e.printStackTrace();
}
return list2;
}
/**
* 函数功能:通过booleanQuery方法进行查询索引
*/
public List
String findContent) {
List
LuceneJEAnalyzerText jeAnalyzer = new LuceneJEAnalyzerText(indexPath);
BooleanQuery booleanQuery = new BooleanQuery();
try {
dir = FSDirectory.getDirectory(indexPath);
searcher = new IndexSearcher(dir);
String[] str = jeAnalyzer.createAnalyzer(findContent).split(",");
for (int i = 0; i < str.length; i++) {
booleanQuery.add(
new TermQuery(new Term("articleName", str[i])),
BooleanClause.Occur.SHOULD);
}
// QueryParser parser = new QueryParser("articleName", new
// StandardAnalyzer());
// Query query = parser.parse(findContent);//根据查询内容进行查询
TopDocs topDocs = searcher.search(booleanQuery, 3);
ScoreDoc[] hits = topDocs.scoreDocs;
for (int i = 0; i < hits.length; i++) {
int DocId = hits[i].doc;
Article article = new Article();
Document doc = searcher.doc(DocId);
article.setArticleId(Integer.parseInt(doc.get("articleId")));
article.setArticleName(doc.get("articleName"));
// article.setArticleContent(doc.get("articleContent"));
list2.add(article);
// list2.add(doc.get("sname"));
}
if (hits.length > 0) {
list2.remove(0);
}
Date date3 = new Date();
System.out.println("查询总共花的时间为:"
+ (date3.getTime() - date2.getTime()) + "毫秒");
} catch (IOException e) {
e.printStackTrace();
}
return list2;
}
/**
* 函数功能:高亮显示查询
*
* @param fieldName
* @param keyword
* @throws CorruptIndexException
* @throws IOException
* @throws ParseException
*/
public List
List
LuceneJEAnalyzerText jeAnalyzer = new LuceneJEAnalyzerText(indexPath);
System.out.println("查询内容为:" + findContent);
BooleanQuery booleanQuery = new BooleanQuery();
try {
dir = FSDirectory.getDirectory(indexPath);
searcher = new IndexSearcher(dir);
String[] str = jeAnalyzer.createAnalyzer(findContent).split(",");
for (int i = 0; i < str.length; i++) {
booleanQuery.add(new TermQuery(
new Term("pictureDetail", str[i])),
BooleanClause.Occur.SHOULD);
}
TopDocs topDocs = searcher.search(booleanQuery, 12);
ScoreDoc[] hits = topDocs.scoreDocs;
for (int i = 0; i < hits.length; i++) {
int DocId = hits[i].doc;
PicQueryTemp picQuery = new PicQueryTemp();
Document doc = searcher.doc(DocId);
picQuery.setPicGroupId(Integer.parseInt(doc.get("picGroupId")));
picQuery.setPicId(Integer.parseInt(doc.get("picId")));
picQuery.setPicName(doc.get("picName"));
picQuery.setPictureDetail(doc.get("pictureDetail"));
list2.add(picQuery);
// list2.add(doc.get("sname"));
}
Date date3 = new Date();
System.out.println("查询总共花的时间为:"
+ (date3.getTime() - date2.getTime()) + "毫秒");
} catch (IOException e) {
e.printStackTrace();
}
return list2;
}
/**函数功能：主要对文章的索引进行查询，主要是查询文章的内容和标题
* @param keyword
* @param startIndex
* @param endIndex
* @return
* @throws CorruptIndexException
* @throws IOException
* @throws ParseException
*/
public List
int endIndex) throws CorruptIndexException, IOException,
ParseException {
List
searcher = new IndexSearcher(indexPath);
Analyzer analyzer = new MMAnalyzer();
// QueryParser queryParse = new QueryParser(fieldName, analyzer);
// Query query = queryParse.parse(keyword);
LuceneJEAnalyzerText jeAnalyzer = new LuceneJEAnalyzerText(indexPath);
BooleanQuery booleanQuery = new BooleanQuery();
try {
dir = FSDirectory.getDirectory(indexPath);
searcher = new IndexSearcher(dir);
String[] str = jeAnalyzer.createAnalyzer(keyword).split(",");
for (int j = 0; j < str.length; j++) {
booleanQuery.add(new TermQuery(new Term("articleContent",str[j])), BooleanClause.Occur.SHOULD);
booleanQuery.add(new TermQuery(new Term("articleName", str[j])),BooleanClause.Occur.SHOULD);
}
Hits hits = searcher.search(booleanQuery);
if (endIndex >= hits.length()) {
endIndex = hits.length() - 1;
}
for (int i = startIndex; i <= endIndex; i++) {
LogQueryTemp logQuery = new LogQueryTemp();
Document doc = hits.doc(i);
String text = doc.get("articleContent");
String text2 = doc.get("articleName");
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(booleanQuery));
// 设置被高亮的文本返回的摘要的文本大小
Fragmenter fragmenter = new SimpleFragmenter(350);// 默认是50个字符，修改为350个字符
highlighter.setTextFragmenter(fragmenter);
String highLightText = highlighter.getBestFragment(analyzer,
"articleContent", text);
String highLightText2 = highlighter.getBestFragment(analyzer,
"articleName", text2);
if (highLightText2 != null) {
logQuery.setArticleName(highLightText2);
} else {
logQuery.setArticleName(doc.get("articleName"));
}
if (highLightText != null) {
logQuery.setArticleContent(highLightText);
} else {
logQuery.setArticleContent(doc.get("articleContent"));
}
logQuery.setArticleId(doc.get("articleId"));
logQuery.setIsMywrite(keyword);
logQuery.setArticleKindName(doc.get("articleKindName"));
logQuery.setWriteTime(doc.get("writeTime"));
listlog.add(logQuery);
}
searcher.close();
} catch (IOException ex) {
ex.printStackTrace();
}
return listlog;
}
}