当前位置: 首页>>代码示例>>Java>>正文

Java Highlighter.setTextFragmenter方法代码示例

本文整理汇总了Java中org.apache.lucene.search.highlight.Highlighter.setTextFragmenter方法的典型用法代码示例。如果您正苦于以下问题：Java Highlighter.setTextFragmenter方法的具体用法？Java Highlighter.setTextFragmenter怎么用？Java Highlighter.setTextFragmenter使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.apache.lucene.search.highlight.Highlighter的用法示例。


在下文中一共展示了Highlighter.setTextFragmenter方法的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。

示例1: getHighlightString

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public static String getHighlightString (String text, String keyword) throws IOException {
       TermQuery query = new TermQuery(new Term("f", keyword));
QueryScorer scorer = new QueryScorer(query);
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">","</span>");
Highlighter highlighter = new Highlighter(formatter, scorer);
Fragmenter fragmenter = new SimpleFragmenter(50);
highlighter.setTextFragmenter(fragmenter);
TokenStream tokenStream = new StandardAnalyzer(Version.LUCENE_20).tokenStream("f", new StringReader(text));
//String result = highlighter.getBestFragments(tokenStream, text, 30, "...");

StringBuilder writer = new StringBuilder("");
writer.append("<html>");
writer.append("<style>\n" +
	".highlight {\n" +
	" background: yellow;\n" +
	"}\n" +
	"</style>");
writer.append("<body>");
writer.append("");
writer.append("</body></html>");

return ( writer.toString() );
   }
开发者ID:CoEIA，项目名称:DEM，代码行数:24，代码来源:TextHighlighter.java

示例2: searToHighlighterCss

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
/**
 * ����
 * @param analyzer
 * @param searcher
 * @throws IOException
 * @throws InvalidTokenOffsetsException
 */
public void searToHighlighterCss(Analyzer analyzer,IndexSearcher searcher) throws IOException, InvalidTokenOffsetsException{  
       Term term =new Term("Content", new String("免费".getBytes(),"GBK"));//��ѯ��������˼����Ҫ�����Ա�Ϊ���������  
       TermQuery query =new TermQuery(term);  
       TopDocs docs =searcher.search(query, 10);//����  
         
       /**�Զ����ע�����ı���ǩ*/  
       SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"hightlighterCss\">","</span>");  
       /**����QueryScorer*/  
       QueryScorer scorer=new QueryScorer(query);  
       /**����Fragmenter*/  
       Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);  
       Highlighter highlight=new Highlighter(formatter,scorer);  
       highlight.setTextFragmenter(fragmenter);  
       
       for(ScoreDoc doc:docs.scoreDocs){//��ȡ���ҵ��ĵ����������
           Document document =searcher.doc(doc.doc);
           String value = document.getField("Content").toString();
           TokenStream tokenStream = analyzer.tokenStream("Content", new StringReader(value));    
           String str1 = highlight.getBestFragment(tokenStream, value);    
           System.out.println(str1);
       }  
   }
开发者ID:Smalinuxer，项目名称:Rearchor，代码行数:30，代码来源:TestHighLight.java

示例3: highlight

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
@Override
public String highlight(String locale, boolean useStopWords, String query, String content, String pre, String post, int preview) {
    Analyzer analyzer = termAnalyzers.findAnalyzer(locale, useStopWords);
    QueryParser parser = new QueryParser(defaultField, analyzer);

    String summary = null;
    try {
        SimpleHTMLFormatter formatter = new SimpleHTMLFormatter(pre, post);
        Highlighter hg = new Highlighter(formatter, new QueryTermScorer(parser.parse(query)));
        hg.setMaxDocCharsToAnalyze(preview);
        hg.setTextFragmenter(new SimpleFragmenter(100));

        TokenStream tokens = TokenSources.getTokenStream(defaultField, content, analyzer);
        summary = hg.getBestFragments(tokens, content, 4, " ... ");
    } catch (InvalidTokenOffsetsException | IOException | ParseException ex) {
        LOG.error("Failed to highlight", ex);
    }

    return StringUtils.isBlank(summary) ? null : summary;
}
开发者ID:jivesoftware，项目名称:miru，代码行数:21，代码来源:LuceneBackedQueryParser.java

示例4: highlightField

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
/**
 * This method intended for use with
 * <tt>testHighlightingWithDefaultField()</tt>
 */
private String highlightField(Query query, String fieldName,
    String text) throws IOException, InvalidTokenOffsetsException {
  TokenStream tokenStream = new MockAnalyzer(random(), MockTokenizer.SIMPLE,
      true, MockTokenFilter.ENGLISH_STOPSET, true).tokenStream(fieldName,
      new StringReader(text));
  // Assuming "<B>", "</B>" used to highlight
  SimpleHTMLFormatter formatter = new SimpleHTMLFormatter();
  MyQueryScorer scorer = new MyQueryScorer(query, fieldName, FIELD_NAME);
  Highlighter highlighter = new Highlighter(formatter, scorer);
  highlighter.setTextFragmenter(new SimpleFragmenter(Integer.MAX_VALUE));

  String rv = highlighter.getBestFragments(tokenStream, text, 1,
      "(FIELD TEXT TRUNCATED)");
  return rv.length() == 0 ? text : rv;
}
开发者ID:pkarmstr，项目名称:NYBC，代码行数:20，代码来源:HighlightCustomQueryTest.java

示例5: testHits

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public void testHits() throws Exception {
    IndexSearcher searcher = new IndexSearcher(TestUtil.getBookIndexDirectory());
    TermQuery query = new TermQuery(new Term("title", "action"));
    TopDocs hits = searcher.search(query, 10);

    QueryScorer scorer = new QueryScorer(query, "title");
    Highlighter highlighter = new Highlighter(scorer);
    highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer));

    Analyzer analyzer = new SimpleAnalyzer();

    for (ScoreDoc sd : hits.scoreDocs) {
        StoredDocument doc = searcher.doc(sd.doc);
        String title = doc.get("title");

        TokenStream stream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), sd.doc, "title", doc,
                analyzer);
        String fragment = highlighter.getBestFragment(stream, title);

        LOGGER.info(fragment);
    }
}
开发者ID:xuzhikethinker，项目名称:t4f-data，代码行数:23，代码来源:HighlightTest.java

示例6: displayHtmlHighlight

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
static String displayHtmlHighlight(Query query, Analyzer analyzer, String fieldName, String fieldContent,
		int fragmentSize) throws IOException, InvalidTokenOffsetsException {
	Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter("<font color='red'>", "</font>"),
			new QueryScorer(query));
	Fragmenter fragmenter = new SimpleFragmenter(fragmentSize);
	highlighter.setTextFragmenter(fragmenter);
	return highlighter.getBestFragment(analyzer, fieldName, fieldContent);
}
开发者ID:tedyli，项目名称:Tedyli-Searcher，代码行数:9，代码来源:Searcher.java

示例7: search

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public static void search(String indexDir, String q) throws Exception {
  Directory dir = FSDirectory.open(Paths.get(indexDir));
  IndexReader reader = DirectoryReader.open(dir);
  IndexSearcher is = new IndexSearcher(reader);
  // Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
  SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
  QueryParser parser = new QueryParser("desc", analyzer);
  Query query = parser.parse(q);

  long start = System.currentTimeMillis();
  TopDocs hits = is.search(query, 10);
  long end = System.currentTimeMillis();
  System.out.println("匹配 " + q + " ，总共花费" + (end - start) + "毫秒" + "查询到" + hits.totalHits + "个记录");

  QueryScorer scorer = new QueryScorer(query);
  Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
  SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
  Highlighter highlighter = new Highlighter(simpleHTMLFormatter, scorer);
  highlighter.setTextFragmenter(fragmenter);
  for (ScoreDoc scoreDoc : hits.scoreDocs) {
    Document doc = is.doc(scoreDoc.doc);
    System.out.println(doc.get("city"));
    System.out.println(doc.get("desc"));
    String desc = doc.get("desc");
    if (desc != null) {
      TokenStream tokenStream = analyzer.tokenStream("desc", new StringReader(desc));
      System.out.println(highlighter.getBestFragment(tokenStream, desc));
    }
  }
  reader.close();
}
开发者ID:MiniPa，项目名称:cjs_ssms，代码行数:32，代码来源:SearcherTest.java

示例8: HighlightingHelper

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
HighlightingHelper(Query query, Analyzer analyzer) {
  this.analyzer = analyzer;

  Formatter formatter = new SimpleHTMLFormatter();
  Encoder encoder = new MinimalHTMLEncoder();
  scorer = new QueryScorer(query);
  highlighter = new Highlighter(formatter, encoder, scorer);

  fragmentLength = DEFAULT_FRAGMENT_LENGTH;
  Fragmenter fragmenter = new SimpleSpanFragmenter(scorer, fragmentLength);
  highlighter.setTextFragmenter(fragmenter);
}
开发者ID:lukhnos，项目名称:lucenestudy，代码行数:13，代码来源:HighlightingHelper.java

示例9: highlightField

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
/**
 * This method intended for use with
 * <tt>testHighlightingWithDefaultField()</tt>
 */
private String highlightField(Query query, String fieldName,
    String text) throws IOException, InvalidTokenOffsetsException {
  TokenStream tokenStream = new MockAnalyzer(random(), MockTokenizer.SIMPLE,
      true, MockTokenFilter.ENGLISH_STOPSET).tokenStream(fieldName, text);
  // Assuming "<B>", "</B>" used to highlight
  SimpleHTMLFormatter formatter = new SimpleHTMLFormatter();
  MyQueryScorer scorer = new MyQueryScorer(query, fieldName, FIELD_NAME);
  Highlighter highlighter = new Highlighter(formatter, scorer);
  highlighter.setTextFragmenter(new SimpleFragmenter(Integer.MAX_VALUE));

  String rv = highlighter.getBestFragments(tokenStream, text, 1,
      "(FIELD TEXT TRUNCATED)");
  return rv.length() == 0 ? text : rv;
}
开发者ID:europeana，项目名称:search，代码行数:19，代码来源:HighlightCustomQueryTest.java

示例10: createHighlighter

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
protected Highlighter createHighlighter(org.apache.lucene.search.Query luceneQuery) {
	SimpleHTMLFormatter format = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
	Highlighter highlighter = new Highlighter(format, new QueryScorer(luceneQuery));// 高亮
	// highlighter.setTextFragmenter(new
	// SimpleFragmenter(Integer.MAX_VALUE));
	highlighter.setTextFragmenter(new SimpleFragmenter(200));
	return highlighter;
}
开发者ID:mixaceh，项目名称:openyu-commons，代码行数:9，代码来源:CommonDaoSupporter.java

示例11: getResult

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public String getResult(String fieldName, String fieldValue) throws Exception{
    BuguIndex index = BuguIndex.getInstance();
    QueryParser parser = new QueryParser(index.getVersion(), fieldName, index.getAnalyzer());
    Query query = parser.parse(keywords);
    TokenStream tokens = index.getAnalyzer().tokenStream(fieldName, new StringReader(fieldValue));
    QueryScorer scorer = new QueryScorer(query, fieldName);
    Highlighter highlighter = new Highlighter(formatter, scorer);
    highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer));
    return highlighter.getBestFragments(tokens, fieldValue, maxFragments, "...");
}
开发者ID:xbwen，项目名称:bugu-mongo，代码行数:11，代码来源:BuguHighlighter.java

示例12: testHighlighting

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public void testHighlighting() throws Exception {
    String text = "The quick brown fox jumps over the lazy dog";

    TermQuery query = new TermQuery(new Term("field", "fox"));

    TokenStream tokenStream = new SimpleAnalyzer().tokenStream("field", new StringReader(text));

    QueryScorer scorer = new QueryScorer(query, "field");
    Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
    Highlighter highlighter = new Highlighter(scorer);
    highlighter.setTextFragmenter(fragmenter);
    assertEquals("The quick brown <B>fox</B> jumps over the lazy dog",
            highlighter.getBestFragment(tokenStream, text));
}
开发者ID:xuzhikethinker，项目名称:t4f-data，代码行数:15，代码来源:HighlightTest.java

示例13: searchData

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
private String searchData(String key) throws IOException, ParseException, InvalidTokenOffsetsException {
	Directory directory = FSDirectory.open(new File(filePath));
	IndexSearcher indexSearcher = new IndexSearcher(directory);
	
	QueryParser queryParser = new QueryParser(Version.LUCENE_31, "foods",
			new SmartChineseAnalyzer(Version.LUCENE_31, true));
	//queryParser.setDefaultOperator(Operator.AND);

	Query query = queryParser.parse(key);
	TopDocs docs = indexSearcher.search(query, 10);
	
	QueryScorer queryScorer = new QueryScorer(query, "foods");
	Highlighter highlighter = new Highlighter(queryScorer);
	highlighter.setTextFragmenter(new SimpleSpanFragmenter(queryScorer));


	List<SearchResult> searchResults = new ArrayList<SearchResult>();
	
	if (docs != null) {
		for (ScoreDoc scoreDoc : docs.scoreDocs) {
			Document doc = indexSearcher.doc(scoreDoc.doc);
			TokenStream tokenStream = TokenSources.getAnyTokenStream(
					indexSearcher.getIndexReader(), scoreDoc.doc, "foods", doc, 
					new SmartChineseAnalyzer(Version.LUCENE_31, true));
			SearchResult searchResult = new SearchResult();
			searchResult.setRestaurantId(Long.valueOf(doc.get("id")));
			searchResult.setRestaurantName(doc.get("restaurant_name"));
			searchResult.setKey(key);
			searchResult.setFoods(Arrays.asList(highlighter.
					getBestFragment(tokenStream, doc.get("foods")).split(" ")));
			searchResults.add(searchResult);
		}
	} else {
		searchResults = null;
	}
	
	indexSearcher.close();
	directory.close();
	
	return new Gson().toJson(searchResults);
}
开发者ID:tensorchen，项目名称:rrs，代码行数:42，代码来源:SearchController.java

示例14: main

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
	if (args.length != 0) {
		QUERY = args[0];
	}
	// 将庖丁封装成符合Lucene要求的Analyzer规范
	Analyzer analyzer = new PaodingAnalyzer();
	
	//读取本类目录下的text.txt文件
	String content = ContentReader.readText(English.class);

	//接下来是标准的Lucene建立索引和检索的代码
	Directory ramDir = new RAMDirectory();
	IndexWriter writer = new IndexWriter(ramDir, analyzer);
	Document doc = new Document();
	Field fd = new Field(FIELD_NAME, content, Field.Store.YES,
			Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
	doc.add(fd);
	writer.addDocument(doc);
	writer.optimize();
	writer.close();

	IndexReader reader = IndexReader.open(ramDir);
	String queryString = QUERY;
	QueryParser parser = new QueryParser(FIELD_NAME, analyzer);
	Query query = parser.parse(queryString);
	Searcher searcher = new IndexSearcher(ramDir);
	query = query.rewrite(reader);
	System.out.println("Searching for: " + query.toString(FIELD_NAME));
	Hits hits = searcher.search(query);

	BoldFormatter formatter = new BoldFormatter();
	Highlighter highlighter = new Highlighter(formatter, new QueryScorer(
			query));
	highlighter.setTextFragmenter(new SimpleFragmenter(50));
	for (int i = 0; i < hits.length(); i++) {
		String text = hits.doc(i).get(FIELD_NAME);
		int maxNumFragmentsRequired = 5;
		String fragmentSeparator = "...";
		TermPositionVector tpv = (TermPositionVector) reader
				.getTermFreqVector(hits.id(i), FIELD_NAME);
		TokenStream tokenStream = TokenSources.getTokenStream(tpv);
		String result = highlighter.getBestFragments(tokenStream, text,
				maxNumFragmentsRequired, fragmentSeparator);
		System.out.println("\n" + result);
	}
	reader.close();
}
开发者ID:no8899，项目名称:paoding-for-lucene-2.4，代码行数:48，代码来源:English.java

示例15: main

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
	if (args.length != 0) {
		QUERY = args[0];
	}
	// 将庖丁封装成符合Lucene要求的Analyzer规范
	Analyzer analyzer = new PaodingAnalyzer();
	
	//读取本类目录下的text.txt文件
	String content = ContentReader.readText(Chinese.class);

	//接下来是标准的Lucene建立索引和检索的代码
	Directory ramDir = new RAMDirectory();
	IndexWriter writer = new IndexWriter(ramDir, analyzer);
	Document doc = new Document();
	Field fd = new Field(FIELD_NAME, content, Field.Store.YES,
			Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
	doc.add(fd);
	writer.addDocument(doc);
	writer.optimize();
	writer.close();

	IndexReader reader = IndexReader.open(ramDir);
	String queryString = QUERY;
	QueryParser parser = new QueryParser(FIELD_NAME, analyzer);
	Query query = parser.parse(queryString);
	Searcher searcher = new IndexSearcher(ramDir);
	query = query.rewrite(reader);
	System.out.println("Searching for: " + query.toString(FIELD_NAME));
	Hits hits = searcher.search(query);

	BoldFormatter formatter = new BoldFormatter();
	Highlighter highlighter = new Highlighter(formatter, new QueryScorer(
			query));
	highlighter.setTextFragmenter(new SimpleFragmenter(50));
	for (int i = 0; i < hits.length(); i++) {
		String text = hits.doc(i).get(FIELD_NAME);
		int maxNumFragmentsRequired = 5;
		String fragmentSeparator = "...";
		TermPositionVector tpv = (TermPositionVector) reader
				.getTermFreqVector(hits.id(i), FIELD_NAME);
		TokenStream tokenStream = TokenSources.getTokenStream(tpv);
		String result = highlighter.getBestFragments(tokenStream, text,
				maxNumFragmentsRequired, fragmentSeparator);
		System.out.println("\n" + result);
	}
	reader.close();
}
开发者ID:no8899，项目名称:paoding-for-lucene-2.4，代码行数:48，代码来源:Chinese.java


注：本文中的org.apache.lucene.search.highlight.Highlighter.setTextFragmenter方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。