本文整理汇总了Java中org.apache.lucene.search.highlight.Highlighter类的典型用法代码示例。如果您正苦于以下问题:Java Highlighter类的具体用法?Java Highlighter怎么用?Java Highlighter使用的例子?那么, 这里精选的类代码示例或许可以为您提供帮助。
Highlighter类属于org.apache.lucene.search.highlight包,在下文中一共展示了Highlighter类的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() );
}
示例2: searToHighlighterCss
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的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);
}
}
示例3: highlight
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的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;
}
示例4: highlightField
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的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;
}
示例5: testHits
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的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);
}
}
示例6: displayHtmlHighlight
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的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);
}
示例7: search
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的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();
}
示例8: search
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的package包/类
@Override
@SuppressWarnings("unchecked")
public List<Post> search(Paging paging, String q) throws Exception {
FullTextSession fullTextSession = Search.getFullTextSession(super.session());
SearchFactory sf = fullTextSession.getSearchFactory();
QueryBuilder qb = sf.buildQueryBuilder().forEntity(PostPO.class).get();
org.apache.lucene.search.Query luceneQuery = qb.keyword().onFields("title","summary","tags").matching(q).createQuery();
FullTextQuery query = fullTextSession.createFullTextQuery(luceneQuery);
query.setFirstResult(paging.getFirstResult());
query.setMaxResults(paging.getMaxResults());
StandardAnalyzer standardAnalyzer = new StandardAnalyzer();
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span style='color:red;'>", "</span>");
QueryScorer queryScorer = new QueryScorer(luceneQuery);
Highlighter highlighter = new Highlighter(formatter, queryScorer);
List<PostPO> list = query.list();
List<Post> rets = new ArrayList<>(list.size());
for (PostPO po : list) {
Post m = BeanMapUtils.copy(po, 0);
// 处理高亮
String title = highlighter.getBestFragment(standardAnalyzer, "title", m.getTitle());
String summary = highlighter.getBestFragment(standardAnalyzer, "summary", m.getSummary());
if (StringUtils.isNotEmpty(title)) {
m.setTitle(title);
}
if (StringUtils.isNotEmpty(summary)) {
m.setSummary(summary);
}
rets.add(m);
}
paging.setTotalCount(query.getResultSize());
return rets;
}
示例9: performHighlighting
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的package包/类
/**
* Performs highlighting for a given query and a given document.
*
* @param indexSearcher the IndexSearcher performing the query
* @param query the Tripod LuceneQuery
* @param scoreDoc the Lucene ScoreDoc
* @param doc the Lucene Document
* @param highlighter the Highlighter to use
* @param result the QueryResult to add the highlights to
* @throws IOException if an error occurs performing the highlighting
* @throws InvalidTokenOffsetsException if an error occurs performing the highlighting
*/
protected void performHighlighting(final IndexSearcher indexSearcher, final Query query, final ScoreDoc scoreDoc,
final Document doc, final Highlighter highlighter, final QR result)
throws IOException, InvalidTokenOffsetsException {
if (query.getHighlightFields() == null || query.getHighlightFields().isEmpty()) {
return;
}
final List<Highlight> highlights = new ArrayList<>();
final List<String> hlFieldNames = getHighlightFieldNames(query, doc);
// process each field to highlight on
for (String hlField : hlFieldNames) {
final String text = doc.get(hlField);
if (StringUtils.isEmpty(text)) {
continue;
}
final List<String> snippets = new ArrayList<>();
final Fields tvFields = indexSearcher.getIndexReader().getTermVectors(scoreDoc.doc);
final int maxStartOffset = highlighter.getMaxDocCharsToAnalyze() -1;
// get the snippets for the given field
final TokenStream tokenStream = TokenSources.getTokenStream(hlField, tvFields, text, analyzer, maxStartOffset);
final TextFragment[] textFragments = highlighter.getBestTextFragments(tokenStream, text, false, 10);
for (TextFragment textFragment : textFragments) {
if (textFragment != null && textFragment.getScore() > 0) {
snippets.add(textFragment.toString());
}
}
// if we have snippets then add a highlight result to the QueryResult
if (snippets.size() > 0) {
highlights.add(new Highlight(hlField, snippets));
}
}
result.setHighlights(highlights);
}
示例10: HighlightingHelper
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的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);
}
示例11: highlightField
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的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;
}
示例12: setup
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的package包/类
@Override
public void setup() throws Exception {
super.setup();
//check to make sure either the doc is being stored
PerfRunData data = getRunData();
if (data.getConfig().get("doc.stored", false) == false){
throw new Exception("doc.stored must be set to true");
}
maxDocCharsToAnalyze = data.getConfig().get("highlighter.maxDocCharsToAnalyze", Highlighter.DEFAULT_MAX_CHARS_TO_ANALYZE);
}
示例13: getBenchmarkHighlighter
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的package包/类
@Override
protected BenchmarkHighlighter getBenchmarkHighlighter(Query q){
highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
highlighter.setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
return new BenchmarkHighlighter(){
@Override
public int doHighlight(IndexReader reader, int doc, String field,
Document document, Analyzer analyzer, String text) throws Exception {
TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
return frag != null ? frag.length : 0;
}
};
}
示例14: getBenchmarkHighlighter
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的package包/类
@Override
public BenchmarkHighlighter getBenchmarkHighlighter(Query q) {
highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
return new BenchmarkHighlighter() {
@Override
public int doHighlight(IndexReader reader, int doc, String field, Document document, Analyzer analyzer, String text) throws Exception {
TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
numHighlightedResults += frag != null ? frag.length : 0;
return frag != null ? frag.length : 0;
}
};
}
示例15: createContextSummary
import org.apache.lucene.search.highlight.Highlighter; //导入依赖的package包/类
public static String createContextSummary(Object highlighter, Analyzer analyzer, String text, int maxNumFragments,String defaultValue) throws IOException {
if(!(highlighter instanceof Highlighter) || analyzer==null || StringUtil.isEmpty(text))
return defaultValue;
TokenStream tokenStream = analyzer.tokenStream("", new StringReader(text));
return ((Highlighter)highlighter).getBestFragments(tokenStream, text, maxNumFragments, "...");
}