@Override
public String getSnippet(
Query query,
String field,
String s,
int maxNumFragments,
int fragmentLength,
String fragmentSuffix,
Formatter formatter)
throws IOException {
QueryScorer queryScorer = new QueryScorer(query, field);
Highlighter highlighter = new Highlighter(formatter, queryScorer);
highlighter.setTextFragmenter(new SimpleFragmenter(fragmentLength));
TokenStream tokenStream = getAnalyzer().tokenStream(field, new UnsyncStringReader(s));
try {
String snippet =
highlighter.getBestFragments(tokenStream, s, maxNumFragments, fragmentSuffix);
if (Validator.isNotNull(snippet)
&& !StringUtil.endsWith(snippet, fragmentSuffix)
&& !s.equals(snippet)) {
snippet = snippet.concat(fragmentSuffix);
}
return snippet;
} catch (InvalidTokenOffsetsException itoe) {
throw new IOException(itoe);
}
}
/**
* 设置关键字高亮
*
* @param query 查询对象
* @param list 设置高亮的内容列表
* @param subLength 截取长度
* @param fields 字段名
*/
public List<T> keywordsHighlight(
BooleanQuery query, List<T> list, int subLength, String... fields) {
Analyzer analyzer = new IKAnalyzer();
Formatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>");
Highlighter highlighter = new Highlighter(formatter, new QueryScorer(query));
highlighter.setTextFragmenter(new SimpleFragmenter(subLength));
for (T entity : list) {
try {
for (String field : fields) {
String text = StringUtils.replaceHtml((String) Reflections.invokeGetter(entity, field));
// 设置高亮字段
String description = highlighter.getBestFragment(analyzer, field, text);
if (description != null) {
Reflections.invokeSetter(entity, fields[0], description);
break;
}
Reflections.invokeSetter(entity, fields[0], StringUtils.abbr(text, subLength * 2));
}
} catch (IOException e) {
e.printStackTrace();
} catch (InvalidTokenOffsetsException e) {
e.printStackTrace();
}
}
return list;
}
/**
* Return a {@link org.apache.lucene.search.highlight.Highlighter} appropriate for this field.
*
* @param query The current Query
* @param fieldName The name of the field
* @param request The current SolrQueryRequest
*/
protected Highlighter getHighlighter(Query query, String fieldName, SolrQueryRequest request) {
SolrParams params = request.getParams();
Highlighter highlighter =
new Highlighter(
getFormatter(fieldName, params),
getEncoder(fieldName, params),
getQueryScorer(query, fieldName, request));
highlighter.setTextFragmenter(getFragmenter(fieldName, params));
return highlighter;
}
/**
* Annoncements adapter
*
* @param hg
* @param a
* @param ann
* @return
* @throws Exception
*/
public SearchResultWH makeHW(Highlighter hg, Analyzer a, Announce ann) throws Exception {
String s = "";
{
String text = ann.getITopDescription() + "";
TokenStream tokenStream = a.tokenStream("topdescription", new StringReader(text));
s +=
cP(
"Совпадения в заголовке объявления",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
}
{
String text = ann.getIDescription() + "";
TokenStream tokenStream = a.tokenStream("description", new StringReader(text));
s +=
cP(
"Совпадения в тексте объявления",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
}
String metatexts = "";
{
String text = ann.getMeta_keywords() + "";
TokenStream tokenStream = a.tokenStream("meta_keywords", new StringReader(text));
metatexts +=
cPmeta(
"Совпадения в keywords",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
text = ann.getMeta_description() + "";
tokenStream = a.tokenStream("meta_description", new StringReader(text));
metatexts +=
cPmeta(
"Совпадения в description",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
text = ann.getMeta_subject() + "";
tokenStream = a.tokenStream("meta_subject", new StringReader(text));
metatexts +=
cPmeta(
"Совпадения в subject",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
}
SearchResultWH swh = new SearchResultWH(ann, "Announce", s, metatexts);
return swh;
}
/**
* @Title: createHighlighter @Description: 创建高亮器
*
* @param query 索引查询对象
* @param prefix 高亮前缀字符串
* @param stuffix 高亮后缀字符串
* @param fragmenterLength 摘要最大长度
* @return
*/
public static Highlighter createHighlighter(
Query query, String prefix, String stuffix, int fragmenterLength) {
Formatter formatter =
new SimpleHTMLFormatter(
(prefix == null || prefix.trim().length() == 0) ? "<font color=\"red\">" : prefix,
(stuffix == null || stuffix.trim().length() == 0) ? "</font>" : stuffix);
Scorer fragmentScorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(formatter, fragmentScorer);
Fragmenter fragmenter = new SimpleFragmenter(fragmenterLength <= 0 ? 50 : fragmenterLength);
highlighter.setTextFragmenter(fragmenter);
return highlighter;
}
public static String hightlightFeild(
Highlighter highlighter, Analyzer analyzer, Document doc, String feild) {
String docContent = doc.get(feild);
try {
String hc = highlighter.getBestFragment(analyzer, feild, docContent);
if (hc == null) {
if (docContent.length() >= 50) {
hc = docContent.substring(0, 50);
} else {
hc = docContent;
}
}
doc.getField(feild).setValue(hc);
// System.out.println(hc);
return hc;
} catch (InvalidTokenOffsetsException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return docContent;
}
/**
* Return a phrase {@link org.apache.lucene.search.highlight.Highlighter} appropriate for this
* field.
*
* @param query The current Query
* @param fieldName The name of the field
* @param request The current SolrQueryRequest
* @param tokenStream document text CachingTokenStream
* @throws IOException
*/
protected Highlighter getPhraseHighlighter(
Query query, String fieldName, SolrQueryRequest request, CachingTokenFilter tokenStream)
throws IOException {
SolrParams params = request.getParams();
Highlighter highlighter = null;
highlighter =
new Highlighter(
getFormatter(fieldName, params),
getEncoder(fieldName, params),
getSpanQueryScorer(query, fieldName, tokenStream, request));
highlighter.setTextFragmenter(getFragmenter(fieldName, params));
return highlighter;
}
public void heighlight(String field, String searchText) {
String text =
"In this section we'll show you how to make the simplest "
+ "programmatic query, searching for a single term, and then "
+ "we'll see how to use QueryParser to accept textual queries. "
+ "In the sections that follow, we’ll take this simple example "
+ "further by detailing all the query types built into Lucene. "
+ "We begin with the simplest search of all: searching for all "
+ "documents that contain a single term.";
Analyzer analyzer = new StandardAnalyzer();
QueryParser queryParser = new QueryParser(field, analyzer);
try {
Query query = queryParser.parse(searchText);
SimpleHTMLFormatter formatter =
new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>");
TokenStream tokens = analyzer.tokenStream("f", new StringReader(text));
QueryScorer scorer = new QueryScorer(query, "f");
Highlighter highlighter = new Highlighter(formatter, scorer);
highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer));
String result = highlighter.getBestFragments(tokens, text, 3, "...");
FileWriter writer = new FileWriter("/home/venugopal/Downloads/Lucene/lia/highter.html"); // #8
writer.write("<html>"); // #8
writer.write(
"<style>\n"
+ // #8
".highlight {\n"
+ // #8
" background: yellow;\n"
+ // #8
"}\n"
+ // #8
"</style>"); // #8
writer.write("<body>"); // #8
writer.write(result); // #8
writer.write("</body></html>"); // #8
writer.close();
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (InvalidTokenOffsetsException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
/**
* @param query 索引查询对象
* @param prefix 高亮前缀
* @param suffix 高亮后缀
* @param fragmenterLength 摘要最大长度
* @param ifCustom 是否自定义Highlighter
* @return
* @author huangzhiqian
* @date 2015年12月11日
*/
public static Highlighter createHighlighter(
Query query, String prefix, String suffix, int fragmenterLength, boolean ifCustom) {
Formatter formatter =
new SimpleHTMLFormatter(
(prefix == null || prefix.trim().length() == 0) ? "<font color=\"blue\">" : prefix,
(suffix == null || suffix.trim().length() == 0) ? "</font>" : suffix);
Scorer fragmentScorer = new QueryScorer(query);
Highlighter highlighter = null;
if (ifCustom) {
highlighter = new CusHzqHighlighter(formatter, fragmentScorer);
} else {
highlighter = new Highlighter(formatter, fragmentScorer);
}
Fragmenter fragmenter = new SimpleFragmenter(fragmenterLength <= 0 ? 50 : fragmenterLength);
highlighter.setTextFragmenter(fragmenter);
return highlighter;
}
/**
* 高亮设置
*
* @param query
* @param doc
* @param field
* @return
*/
private String toHighlighter(Analyzer analyzer, Query query, Document doc) {
String field = "text";
try {
SimpleHTMLFormatter simpleHtmlFormatter =
new SimpleHTMLFormatter("<font color=\"red\">", "</font>");
Highlighter highlighter = new Highlighter(simpleHtmlFormatter, new QueryScorer(query));
TokenStream tokenStream1 = analyzer.tokenStream("text", new StringReader(doc.get(field)));
String highlighterStr = highlighter.getBestFragment(tokenStream1, doc.get(field));
return highlighterStr == null ? doc.get(field) : highlighterStr;
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (InvalidTokenOffsetsException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return null;
}
private String doHighlightQuery(
Query query, String fieldName, String text, String openMark, String closeMark) {
try {
SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter(openMark, closeMark);
Highlighter highlighter =
new Highlighter(htmlFormatter, new QueryScorer(query, fieldName, this.env.defaultField));
highlighter.setTextFragmenter(new NullFragmenter());
String str =
highlighter.getBestFragment(
this.env.indexAnalyzer,
"".equals(fieldName) ? this.env.defaultField : fieldName,
text);
return null != str ? str : text;
} catch (Exception x) {
logger.error("Caught an exception:", x);
}
return text;
}
/**
* Visa adapter
*
* @param hg
* @param a
* @param ann
* @return
* @throws Exception
*/
public SearchResultWH makeHW(Highlighter hg, Analyzer a, Visa v) throws Exception {
String s = "";
String text = v.getIDescription() + "";
TokenStream tokenStream = a.tokenStream("description", new StringReader(text));
s +=
cP(
"Совпадения в описании",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
String metatexts = "";
{
text = v.getMeta_keywords() + "";
tokenStream = a.tokenStream("meta_keywords", new StringReader(text));
metatexts +=
cPmeta(
"Совпадения в keywords",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
text = v.getMeta_description() + "";
tokenStream = a.tokenStream("meta_description", new StringReader(text));
metatexts +=
cPmeta(
"Совпадения в description",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
text = v.getMeta_subject() + "";
tokenStream = a.tokenStream("meta_subject", new StringReader(text));
metatexts +=
cPmeta(
"Совпадения в subject",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
}
SearchResultWH swh = new SearchResultWH(v, "Visa", s, metatexts);
return swh;
}
/**
* Public image adapter
*
* @param hg
* @param a
* @param pi
* @return
* @throws Exception
*/
public SearchResultWH makeHW(Highlighter hg, Analyzer a, PublicImage pi) throws Exception {
String text = pi.getDescription() + "";
TokenStream tokenStream = a.tokenStream("description", new StringReader(text));
String s =
cP(
"Совпадения в описании",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
SearchResultWH swh = new SearchResultWH(pi, "PublicImage", s);
return swh;
}
/**
* Any text adapter
*
* @param hg
* @param a
* @param ann
* @return
* @throws Exception
*/
public SearchResultWH makeHW(Highlighter hg, Analyzer a, AnyText t) throws Exception {
String s = "";
String text = t.getIDescription() + "";
TokenStream tokenStream = a.tokenStream("anytext", new StringReader(text));
s +=
cP(
"Совпадения в тексте",
hg.getBestFragments(tokenStream, text, MAX_NUM_FRAGMENTS_REQUIRED, "... "));
SearchResultWH swh = new SearchResultWH(t, "AnyText", s);
return swh;
}
protected String retrieveResultSummary(
Document document, Highlighter highlighter, StandardAnalyzer analyzer)
throws InvalidTokenOffsetsException, IOException {
String content = document.get(FIELD_TOPIC_CONTENT);
TokenStream tokenStream = analyzer.tokenStream(FIELD_TOPIC_CONTENT, new StringReader(content));
String summary = highlighter.getBestFragments(tokenStream, content, 3, "...");
if (StringUtils.isBlank(summary) && !StringUtils.isBlank(content)) {
summary = StringEscapeUtils.escapeHtml(content.substring(0, Math.min(200, content.length())));
if (Math.min(200, content.length()) == 200) {
summary += "...";
}
}
return summary;
}
public String getSnippet(int index) throws Exception {
StandardAnalyzer analyzer = new StandardAnalyzer();
QueryParser qp = new QueryParser(FieldType.TEXT.toString(), analyzer);
SchemaObjectInfo info = getResult(index);
String text = info.getTextDescription();
String label = info.getLabel().toLowerCase();
// remove abundant labels
if (!label.equals("")) {
while (text.indexOf(label) == 0) text = text.substring(label.length()).trim();
}
if (keyword != null) {
try {
Highlighter hl = new Highlighter(new QueryScorer(qp.parse(keyword)));
TokenStream ts = analyzer.tokenStream(text, new StringReader(text));
String snippet = hl.getBestFragment(ts, text);
if (snippet != null) return snippet;
} catch (Exception e) {
// e.printStackTrace();
}
}
return text;
}
/**
* @param key 搜索内容所在的字段名称
* @param value 所要搜索的内容
* @throws CorruptIndexException
* @throws IOException
* @throws ParseException
*/
public static void search(String key, String value)
throws CorruptIndexException, IOException, ParseException {
IndexSearcher searcher;
// 创建QueryParser对象,第一个参数表示Lucene的版本,第二个表示搜索Field的字段,第三个表示搜索使用分词器
// Analyzer analyzer = new IKAnalyzer(); //new StandardAnalyzer(Version.LUCENE_36)
// QueryParser qp = new QueryParser(Version.LUCENE_36, key,analyzer);
searcher = new IndexSearcher(IndexReader.open(FSDirectory.open(new File(PATH))));
searcher.setSimilarity(new IKSimilarity());
Query query = IKQueryParser.parse(key, value);
// Query tq = qp.parse(value);
TopDocs topDocs = searcher.search(query, 10000);
// searcher.search(query, results); // new function
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
System.out.println("命中：" + topDocs.totalHits);
Formatter formatter = new SimpleHTMLFormatter("<font color='red'>", "</font>");
Scorer fragmentScorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(formatter, fragmentScorer);
Fragmenter fragmenter = new SimpleFragmenter(50);
highlighter.setTextFragmenter(fragmenter);
Analyzer analyzer = new IKAnalyzer();
for (int i = 0; i < scoreDocs.length; i++) {
ScoreDoc scoreDoc = topDocs.scoreDocs[i];
int docSn = scoreDoc.doc; // 文档内部编号
Document doc = searcher.doc(docSn); // 根据文档编号取出文档
hightlightFeild(highlighter, analyzer, doc, "name");
hightlightFeild(highlighter, analyzer, doc, "address");
hightlightFeild(highlighter, analyzer, doc, "datatype");
// scoreDocs[i].
System.out.println("name:" + doc.get("name")); // new function
System.out.println("address:" + doc.get("address"));
System.out.println("datatype:" + doc.get("datatype"));
System.out.println("geom:" + doc.get("geom"));
}
}
/**
* @Title: highlight @Description: 生成高亮文本
*
* @param document 索引文档对象
* @param highlighter 高亮器
* @param analyzer 索引分词器
* @param field 高亮字段
* @return
* @throws IOException
* @throws InvalidTokenOffsetsException
*/
public static String highlight(
Document document, Highlighter highlighter, Analyzer analyzer, String field)
throws IOException {
List<IndexableField> list = document.getFields();
for (IndexableField fieldable : list) {
String fieldValue = fieldable.stringValue();
if (fieldable.name().equals(field)) {
try {
fieldValue = highlighter.getBestFragment(analyzer, field, fieldValue);
} catch (InvalidTokenOffsetsException e) {
fieldValue = fieldable.stringValue();
}
return (fieldValue == null || fieldValue.trim().length() == 0)
? fieldable.stringValue()
: fieldValue;
}
}
return null;
}
@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,
StoredDocument 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;
}
};
}
public Search search(String queryString)
throws ParseException, IOException, InvalidTokenOffsetsException {
List<Result> finalRes = new ArrayList<Result>();
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);
Directory indexDir = FSDirectory.open(new File(pathOfIndex));
Date inizio = new Date();
IndexReader reader = DirectoryReader.open(indexDir);
IndexSearcher indexSearcher = new IndexSearcher(reader);
QueryParser queryParser = new QueryParser(Version.LUCENE_47, "words", analyzer);
Query query = queryParser.parse(queryString);
TopDocs hits = indexSearcher.search(query, reader.maxDoc());
// TopDocs hitsSuggested= new TopDocs();
int numberOfResults = hits.totalHits;
Date fine = new Date();
long time = fine.getTime() - inizio.getTime();
SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter();
Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(query));
// Estraggo gli snippet
for (int i = 0; i < hits.totalHits; i++) {
int id = hits.scoreDocs[i].doc;
Document doc = indexSearcher.doc(id);
String text = doc.get("words");
// MoreLikeThis mlt = new MoreLikeThis(reader);
// Query querySuggested = mlt.like(hits.scoreDocs[i].doc);
// hitsSuggested = indexSearcher.search(querySuggested, reader.maxDoc());
//
TokenStream tokenStream =
TokenSources.getAnyTokenStream(indexSearcher.getIndexReader(), id, "words", analyzer);
TextFragment[] frag = highlighter.getBestTextFragments(tokenStream, text, false, 4);
Result r = new Result();
r.setTitle(doc.get("title"));
String path = doc.get("path");
r.setPath(path);
r.setScore(hits.scoreDocs[i].score);
String snippet = "";
for (int j = 0; j < frag.length; j++) {
if ((frag[j] != null) && (frag[j].getScore() > 0)) {
snippet += frag[j].toString();
}
}
String snippet1 = snippet.replace("<B>", "<b>");
String snippetFinal = snippet1.replace("</B>", "</b>");
r.setSnippet(snippetFinal);
finalRes.add(r);
}
reader.close();
String suggestedQuery = null;
if (numberOfResults < minimumHits || hits.scoreDocs[0].score < minimumScore) {
suggestedQuery = DidYouMean.suggest(queryString, indexDir);
}
Search searchRes = new Search(finalRes, time, queryString, suggestedQuery);
return searchRes;
}
/**
* Searches pages using a particular combination of flags.
*
* @param query The query to perform in Lucene query language
* @param flags A set of flags
* @return A Collection of SearchResult instances
* @throws ProviderException if there is a problem with the backend
*/
public Collection findPages(String query, int flags) throws ProviderException {
IndexSearcher searcher = null;
ArrayList<SearchResult> list = null;
Highlighter highlighter = null;
try {
String[] queryfields = {
LUCENE_PAGE_CONTENTS, LUCENE_PAGE_NAME, LUCENE_AUTHOR, LUCENE_ATTACHMENTS
};
QueryParser qp =
new MultiFieldQueryParser(Version.LUCENE_36, queryfields, getLuceneAnalyzer());
// QueryParser qp = new QueryParser( LUCENE_PAGE_CONTENTS, getLuceneAnalyzer() );
Query luceneQuery = qp.parse(query);
if ((flags & FLAG_CONTEXTS) != 0) {
highlighter =
new Highlighter(
new SimpleHTMLFormatter("<span class=\"searchmatch\">", "</span>"),
new SimpleHTMLEncoder(),
new QueryScorer(luceneQuery));
}
try {
File dir = new File(m_luceneDirectory);
Directory luceneDir = new SimpleFSDirectory(dir, null);
IndexReader reader = IndexReader.open(luceneDir);
searcher = new IndexSearcher(reader);
} catch (Exception ex) {
log.info("Lucene not yet ready; indexing not started", ex);
return null;
}
ScoreDoc[] hits = searcher.search(luceneQuery, MAX_SEARCH_HITS).scoreDocs;
list = new ArrayList<SearchResult>(hits.length);
for (int curr = 0; curr < hits.length; curr++) {
int docID = hits[curr].doc;
Document doc = searcher.doc(docID);
String pageName = doc.get(LUCENE_ID);
WikiPage page = m_engine.getPage(pageName, WikiPageProvider.LATEST_VERSION);
if (page != null) {
if (page instanceof Attachment) {
// Currently attachments don't look nice on the search-results page
// When the search-results are cleaned up this can be enabled again.
}
int score = (int) (hits[curr].score * 100);
// Get highlighted search contexts
String text = doc.get(LUCENE_PAGE_CONTENTS);
String[] fragments = new String[0];
if (text != null && highlighter != null) {
TokenStream tokenStream =
getLuceneAnalyzer().tokenStream(LUCENE_PAGE_CONTENTS, new StringReader(text));
fragments = highlighter.getBestFragments(tokenStream, text, MAX_FRAGMENTS);
}
SearchResult result = new SearchResultImpl(page, score, fragments);
list.add(result);
} else {
log.error(
"Lucene found a result page '"
+ pageName
+ "' that could not be loaded, removing from Lucene cache");
pageRemoved(new WikiPage(m_engine, pageName));
}
}
} catch (IOException e) {
log.error("Failed during lucene search", e);
} catch (ParseException e) {
log.info("Broken query; cannot parse query ", e);
throw new ProviderException(
"You have entered a query Lucene cannot process: " + e.getMessage());
} catch (InvalidTokenOffsetsException e) {
log.error("Tokens are incompatible with provided text ", e);
} finally {
if (searcher != null) {
try {
searcher.close();
} catch (IOException e) {
log.error(e);
}
}
}
return list;
}
private void doHighlightingByHighlighter(
Query query,
SolrQueryRequest req,
NamedList docSummaries,
int docId,
Document doc,
String fieldName)
throws IOException {
final SolrIndexSearcher searcher = req.getSearcher();
final IndexSchema schema = searcher.getSchema();
// TODO: Currently in trunk highlighting numeric fields is broken (Lucene) -
// so we disable them until fixed (see LUCENE-3080)!
// BEGIN: Hack
final SchemaField schemaField = schema.getFieldOrNull(fieldName);
if (schemaField != null
&& ((schemaField.getType() instanceof org.apache.solr.schema.TrieField)
|| (schemaField.getType() instanceof org.apache.solr.schema.TrieDateField))) return;
// END: Hack
SolrParams params = req.getParams();
IndexableField[] docFields = doc.getFields(fieldName);
List<String> listFields = new ArrayList<String>();
for (IndexableField field : docFields) {
listFields.add(field.stringValue());
}
// preserve order of values in a multiValued list
boolean preserveMulti = params.getFieldBool(fieldName, HighlightParams.PRESERVE_MULTI, false);
String[] docTexts = (String[]) listFields.toArray(new String[listFields.size()]);
// according to Document javadoc, doc.getValues() never returns null. check empty instead of
// null
if (docTexts.length == 0) return;
TokenStream tstream = null;
int numFragments = getMaxSnippets(fieldName, params);
boolean mergeContiguousFragments = isMergeContiguousFragments(fieldName, params);
String[] summaries = null;
List<TextFragment> frags = new ArrayList<TextFragment>();
TermOffsetsTokenStream tots = null; // to be non-null iff we're using TermOffsets optimization
TokenStream tvStream =
TokenSources.getTokenStreamWithOffsets(searcher.getIndexReader(), docId, fieldName);
if (tvStream != null) {
tots = new TermOffsetsTokenStream(tvStream);
}
for (int j = 0; j < docTexts.length; j++) {
if (tots != null) {
// if we're using TermOffsets optimization, then get the next
// field value's TokenStream (i.e. get field j's TokenStream) from tots:
tstream = tots.getMultiValuedTokenStream(docTexts[j].length());
} else {
// fall back to analyzer
tstream = createAnalyzerTStream(schema, fieldName, docTexts[j]);
}
int maxCharsToAnalyze =
params.getFieldInt(
fieldName, HighlightParams.MAX_CHARS, Highlighter.DEFAULT_MAX_CHARS_TO_ANALYZE);
Highlighter highlighter;
if (Boolean.valueOf(req.getParams().get(HighlightParams.USE_PHRASE_HIGHLIGHTER, "true"))) {
if (maxCharsToAnalyze < 0) {
tstream = new CachingTokenFilter(tstream);
} else {
tstream = new CachingTokenFilter(new OffsetLimitTokenFilter(tstream, maxCharsToAnalyze));
}
// get highlighter
highlighter = getPhraseHighlighter(query, fieldName, req, (CachingTokenFilter) tstream);
// after highlighter initialization, reset tstream since construction of highlighter already
// used it
tstream.reset();
} else {
// use "the old way"
highlighter = getHighlighter(query, fieldName, req);
}
if (maxCharsToAnalyze < 0) {
highlighter.setMaxDocCharsToAnalyze(docTexts[j].length());
} else {
highlighter.setMaxDocCharsToAnalyze(maxCharsToAnalyze);
}
try {
TextFragment[] bestTextFragments =
highlighter.getBestTextFragments(
tstream, docTexts[j], mergeContiguousFragments, numFragments);
for (int k = 0; k < bestTextFragments.length; k++) {
if (preserveMulti) {
if (bestTextFragments[k] != null) {
frags.add(bestTextFragments[k]);
}
} else {
if ((bestTextFragments[k] != null) && (bestTextFragments[k].getScore() > 0)) {
frags.add(bestTextFragments[k]);
}
}
}
} catch (InvalidTokenOffsetsException e) {
throw new SolrException(SolrException.ErrorCode.SERVER_ERROR, e);
}
}
// sort such that the fragments with the highest score come first
if (!preserveMulti) {
Collections.sort(
frags,
new Comparator<TextFragment>() {
@Override
public int compare(TextFragment arg0, TextFragment arg1) {
return Math.round(arg1.getScore() - arg0.getScore());
}
});
}
// convert fragments back into text
// TODO: we can include score and position information in output as snippet attributes
if (frags.size() > 0) {
ArrayList<String> fragTexts = new ArrayList<String>();
for (TextFragment fragment : frags) {
if (preserveMulti) {
if (fragment != null) {
fragTexts.add(fragment.toString());
}
} else {
if ((fragment != null) && (fragment.getScore() > 0)) {
fragTexts.add(fragment.toString());
}
}
if (fragTexts.size() >= numFragments && !preserveMulti) break;
}
summaries = fragTexts.toArray(new String[0]);
if (summaries.length > 0) docSummaries.add(fieldName, summaries);
}
// no summeries made, copy text from alternate field
if (summaries == null || summaries.length == 0) {
alternateField(docSummaries, params, doc, fieldName);
}
}
private void doHighlightingByHighlighter(
Query query,
SolrQueryRequest req,
NamedList docSummaries,
int docId,
Document doc,
String fieldName)
throws IOException {
SolrParams params = req.getParams();
String[] docTexts = doc.getValues(fieldName);
// according to Document javadoc, doc.getValues() never returns null. check empty instead of
// null
if (docTexts.length == 0) return;
SolrIndexSearcher searcher = req.getSearcher();
IndexSchema schema = searcher.getSchema();
TokenStream tstream = null;
int numFragments = getMaxSnippets(fieldName, params);
boolean mergeContiguousFragments = isMergeContiguousFragments(fieldName, params);
String[] summaries = null;
List<TextFragment> frags = new ArrayList<TextFragment>();
TermOffsetsTokenStream tots = null; // to be non-null iff we're using TermOffsets optimization
try {
TokenStream tvStream =
TokenSources.getTokenStream(searcher.getIndexReader(), docId, fieldName);
if (tvStream != null) {
tots = new TermOffsetsTokenStream(tvStream);
}
} catch (IllegalArgumentException e) {
// No problem. But we can't use TermOffsets optimization.
}
for (int j = 0; j < docTexts.length; j++) {
if (tots != null) {
// if we're using TermOffsets optimization, then get the next
// field value's TokenStream (i.e. get field j's TokenStream) from tots:
tstream = tots.getMultiValuedTokenStream(docTexts[j].length());
} else {
// fall back to analyzer
tstream = createAnalyzerTStream(schema, fieldName, docTexts[j]);
}
Highlighter highlighter;
if (Boolean.valueOf(req.getParams().get(HighlightParams.USE_PHRASE_HIGHLIGHTER, "true"))) {
// TODO: this is not always necessary - eventually we would like to avoid this wrap
// when it is not needed.
tstream = new CachingTokenFilter(tstream);
// get highlighter
highlighter = getPhraseHighlighter(query, fieldName, req, (CachingTokenFilter) tstream);
// after highlighter initialization, reset tstream since construction of highlighter already
// used it
tstream.reset();
} else {
// use "the old way"
highlighter = getHighlighter(query, fieldName, req);
}
int maxCharsToAnalyze =
params.getFieldInt(
fieldName, HighlightParams.MAX_CHARS, Highlighter.DEFAULT_MAX_CHARS_TO_ANALYZE);
if (maxCharsToAnalyze < 0) {
highlighter.setMaxDocCharsToAnalyze(docTexts[j].length());
} else {
highlighter.setMaxDocCharsToAnalyze(maxCharsToAnalyze);
}
try {
TextFragment[] bestTextFragments =
highlighter.getBestTextFragments(
tstream, docTexts[j], mergeContiguousFragments, numFragments);
for (int k = 0; k < bestTextFragments.length; k++) {
if ((bestTextFragments[k] != null) && (bestTextFragments[k].getScore() > 0)) {
frags.add(bestTextFragments[k]);
}
}
} catch (InvalidTokenOffsetsException e) {
throw new SolrException(SolrException.ErrorCode.SERVER_ERROR, e);
}
}
// sort such that the fragments with the highest score come first
Collections.sort(
frags,
new Comparator<TextFragment>() {
public int compare(TextFragment arg0, TextFragment arg1) {
return Math.round(arg1.getScore() - arg0.getScore());
}
});
// convert fragments back into text
// TODO: we can include score and position information in output as snippet attributes
if (frags.size() > 0) {
ArrayList<String> fragTexts = new ArrayList<String>();
for (TextFragment fragment : frags) {
if ((fragment != null) && (fragment.getScore() > 0)) {
fragTexts.add(fragment.toString());
}
if (fragTexts.size() >= numFragments) break;
}
summaries = fragTexts.toArray(new String[0]);
if (summaries.length > 0) docSummaries.add(fieldName, summaries);
}
// no summeries made, copy text from alternate field
if (summaries == null || summaries.length == 0) {
alternateField(docSummaries, params, doc, fieldName);
}
}
public Vector<Hashtable<String, String>> query(String s, String subject, String from, String to)
throws CorruptIndexException, IOException, ParseException, InvalidTokenOffsetsException {
WhitespaceAnalyzer analyzer = new WhitespaceAnalyzer(Version.LUCENE_36);
QueryParser parser = new QueryParser(Version.LUCENE_36, "segmented", analyzer);
// s = Lucene.client.autoSegment(s);
// System.out.println(s);
String[] sprite = s.split(" ");
ScoreDoc[] docs;
String q = "";
if (from.length() == 14 && to.length() == 14) {
q += "post_date:[" + from + " TO " + to + "] AND ";
} else if (from.length() == 14) {
q += "post_date:[" + from + " TO " + "21000000000000" + "] AND ";
} else if (to.length() == 14) {
q += "post_date:[" + "20000000000000" + " TO " + to + "] AND ";
}
if (subject.length() == 0) q += s;
else {
if (!subject.equals("all")) q += s + " AND subject:" + subject;
else q += s;
}
if (subject.length() == 0) docs = this.search(searcher, parser.parse(q));
else docs = this.search(searcher, parser.parse(q + " AND sub_score:[0070 TO 1000]"));
Vector<Hashtable<String, String>> result = new Vector<>();
System.out.println(q);
System.out.println(docs.length);
SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter();
Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(parser.parse(s)));
// id score search
for (int i = 0; i < 100 && i < docs.length; ++i) {
Document doc = searcher.doc(docs[i].doc);
String docResult = "";
Hashtable<String, String> ret = new Hashtable<>();
// docResult +="doc="+docs[i].doc+" score="+docs[i].score + "\n";
TokenStream Stream =
TokenSources.getAnyTokenStream(
searcher.getIndexReader(), docs[i].doc, "post_content", analyzer);
TextFragment[] frag;
String content = doc.get("post_content");
for (String tmp : sprite) {
content = content.replaceAll(tmp, " " + tmp + " ");
}
// System.out.println(content);
////////// 주석
docResult += highlighter.getBestFragment(analyzer, "", content);
/*
frag = highlighter.getBestTextFragments(Stream, content, false, 100);
for (int j = 0; j < frag.length; j++) {
if ((frag[j] != null) && (frag[j].getScore() > 0)) {
docResult+=(frag[j].toString());
}
}
*/
docResult = docResult.replaceAll(" (<B>.*?</B>) ", "$1");
// System.out.println(docResult);
try {
// System.out.println(safe_get(doc,"sub_score"));
// ret.put("id", safe_get(doc,"id"));
ret.put("content", docResult);
ret.put("url", safe_get(doc, "url"));
ret.put("date", safe_get(doc, "post_date"));
ret.put("id", safe_get(doc, "post_title"));
ret.put("sub_score", safe_get(doc, "sub_score"));
ret.put("subject", safe_get(doc, "subject"));
ret.put("score", Float.toString(docs[i].score));
result.add(ret);
} catch (Exception err) {
result.add(ret);
continue;
}
}
return result;
}
/**
* @param currentPageNum
* @return
* @throws Exception
*/
public List<DocumentEntity> getResult(int currentPageNum) throws Exception {
List<DocumentEntity> list = new ArrayList<DocumentEntity>();
directory = FSDirectory.open(new File(SystemConstant.indexDir));
reader = DirectoryReader.open(directory);
IndexSearcher searcher = new IndexSearcher(reader);
// 高亮显示设置
Highlighter highlighter = null;
SimpleHTMLFormatter simpleHTMLFormatter =
new SimpleHTMLFormatter("<font color='red'><b>", "</b></font>");
Highlighter highlighterTitle = null;
SimpleHTMLFormatter formatTitle = new SimpleHTMLFormatter("<FONT color=#c60a00>", "</FONT>");
ScoreDoc[] hits = this.getScoreDocs();
Query query = this.getQuery();
highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query));
highlighterTitle = new Highlighter(formatTitle, new QueryScorer(query));
highlighter.setTextFragmenter(new SimpleFragmenter(200)); // 这个200是指定关键字字符串的context
// 的长度，你可以自己设定，因为不可能返回整篇正文内容
Document doc;
String fileName = "";
int totalNumber = currentPageNum * eachePageNum;
if (totalNumber > hits.length) totalNumber = hits.length;
for (int i = (currentPageNum - 1) * eachePageNum; i < totalNumber; i++) {
// 打印文档的内容
doc = searcher.doc(hits[i].doc);
// System.out.println(doc.toString());
// if(this.docType.equals(doc.get("type"))){
// 高亮出显示
DocumentEntity docEntity = new DocumentEntity();
TokenStream tokenStream =
new PaodingAnalyzer().tokenStream("contents", new StringReader(doc.get("contents")));
docEntity.setContents(highlighter.getBestFragment(tokenStream, doc.get("contents")));
// System.out.println("----------"+i+"----------");
// System.out.println(docEntity.getContents());
fileName = doc.get("fileName");
tokenStream = new PaodingAnalyzer().tokenStream("fileName", new StringReader(fileName));
// 需要注意：在处理时如果文本检索结果中不包含对应的关键字返回一个null
String forMatt = highlighterTitle.getBestFragment(tokenStream, fileName);
if (forMatt == null) docEntity.setFilename(fileName);
else docEntity.setFilename(forMatt);
String type1 = doc.get("type");
docEntity.setType(type1);
docEntity.setId(doc.get("id"));
if ("pdf".equalsIgnoreCase(type1)) {
fileName = SystemConstant.CONTEXT + SystemConstant.PDFdir + fileName + "." + type1;
docEntity.setOriginalFileName(fileName);
} else if ("doc".equalsIgnoreCase(type1)) {
fileName = SystemConstant.CONTEXT + SystemConstant.Docdir + fileName + "." + type1;
docEntity.setOriginalFileName(fileName);
}
// System.out.println(docEntity.getType());
list.add(docEntity);
// System.out.println(docEntity.getFilename());
// System.out.println("--------------------"+doc.get("fileName"));
// }//end for if
// else continue;
} // end for
return list;
}
public String getContext(String sample) throws IOException {
String result = "";
try {
String highlight_query_str = cfg.searchField + ":" + cfg.quotes + sample + cfg.quotes;
String query_str = "padded_length:[" + String.format("%09d", cfg.minDocLen) + " TO *]";
if (cfg.enableTitleSearch) {
query_str +=
" AND (title:"
+ cfg.quotes
+ sample
+ cfg.quotes
+ " OR "
+ cfg.searchField
+ ":"
+ cfg.quotes
+ sample
+ cfg.quotes
+ ")";
} else {
query_str += " AND (" + cfg.searchField + ":" + cfg.quotes + sample + cfg.quotes + ")";
}
Query query = parser.parse(query_str);
Query highlight_query = parser.parse(highlight_query_str);
if (cfg.debug == true) System.out.println("Searching (" + query + ").....");
TopDocs topDocs = searcher.search(query, cfg.maxHits != 0 ? cfg.maxHits : Integer.MAX_VALUE);
if (topDocs.totalHits > 0) {
ScoreDoc[] hits = topDocs.scoreDocs;
if (cfg.debug == true) System.out.println("Results (" + hits.length + ") :)");
String data;
int indx;
SimpleHTMLFormatter htmlFormatter = null;
Highlighter highlighter = null;
if (cfg.displayHighlights) {
htmlFormatter = new SimpleHTMLFormatter();
highlighter = new Highlighter(htmlFormatter, new QueryScorer(highlight_query));
}
for (int i = 0; i < hits.length; i++) {
if (cfg.displayDID) {
result += String.format("\t%d", hits[i].doc);
}
if (cfg.displayScore) {
result += String.format("\t%f", hits[i].score);
}
if (cfg.displayLen) {
result += "\t" + indexReader.document(hits[i].doc).getField("length").stringValue();
}
if (cfg.displayTitle) {
data = indexReader.document(hits[i].doc).getField("title").stringValue();
if (cfg.removeParen && (indx = data.indexOf(" (")) != -1)
data =
indexReader
.document(hits[i].doc)
.getField("title")
.stringValue()
.substring(0, indx);
result += "\t" + data;
}
if (cfg.displayTxt || cfg.displayHighlights) {
String text = indexReader.document(hits[i].doc).getField("text").stringValue();
if (cfg.displayTxt) result += "\t" + text;
if (cfg.displayHighlights) {
TokenStream tokenStream =
TokenSources.getAnyTokenStream(
searcher.getIndexReader(), hits[i].doc, "text", stdAnalyzer);
TextFragment[] frag;
try {
frag = highlighter.getBestTextFragments(tokenStream, text, false, 10);
for (int j = 0; j < frag.length; j++) {
if ((frag[j] != null) && (frag[j].getScore() > 0)) {
result += "\t" + (frag[j].toString());
}
}
} catch (InvalidTokenOffsetsException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} // highlighter.getBestFragments(tokenStream, text, 3, "...");
}
}
if (cfg.displayCategories) {
IndexableField categories[] = indexReader.document(hits[i].doc).getFields("category");
for (int j = 0;
j < categories.length && (cfg.numCategories == 0 || j < cfg.numCategories);
j++) {
result += "\t" + categories[j].stringValue();
}
}
result += System.lineSeparator() + System.lineSeparator() + System.lineSeparator();
}
} else if (cfg.debug == true) System.out.println("No results found :(");
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} //
return result;
}
@SuppressWarnings("resource")
public static String getTextAbstract(String title, String content) {
try {
content = getTextFromHtml(content);
org.apache.lucene.search.Query q = IKQueryParser.parse("CONTENT", title);
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("", "");
Highlighter highlighter = new Highlighter(formatter, new QueryScorer(q));
highlighter.setTextFragmenter(new SimpleFragmenter(200));
org.apache.lucene.analysis.TokenStream tokenStream =
(new IKAnalyzer()).tokenStream("CONTENT", new StringReader(content));
String tmp = highlighter.getBestFragment(tokenStream, content);
if (HtmlStringUtil.isNotEmpty(tmp)) content = tmp.trim();
} catch (Exception e) {
e.printStackTrace();
}
int start = 0;
int end = 0;
boolean startFlag = true;
for (int i = 0; i < content.length(); i++) {
char c = content.charAt(i);
if (startFlag) {
if (Character.isWhitespace(c)
|| Character.isISOControl(c)
|| c == ','
|| c == '，'
|| c == '”'
|| c == '’'
|| c == '.'
|| c == '。'
|| c == '>'
|| c == '?'
|| c == '？'
|| c == ' '
|| c == ' '
|| c == ' '
|| c == '!'
|| c == '！'
|| c == ';'
|| c == '；'
|| c == ':'
|| c == '：'
|| c == ']'
|| c == '］') continue;
start = i;
startFlag = false;
}
if (!startFlag)
if (c == '.' || c == '。' || c == '?' || c == '？' || c == '!' || c == '！' || c == ' '
|| c == ' ' || c == ' ') {
if (i < 8) start = i + 1;
end = i;
if (i != content.length() - 1
&& (content.charAt(i + 1) == '”' || content.charAt(i + 1) == '’')) end = i + 1;
} else {
if ((c == ',' || c == '，' || c == '>' || c == '》' || c == '、') && i < 2) start = i + 1;
if (c == '’' || c == '”')
if (i != content.length() - 1) {
char next = content.charAt(i + 1);
if (next != ',' && next == '，' && next == '、' && next == ';' && next == '；')
end = i + 1;
} else {
end = i;
}
}
}
if (end != 0 && end > start) {
content = content.substring(start, end + 1).trim();
start = 0;
for (int i = 0; i < content.length(); i++) {
char c = content.charAt(i);
if ((c == '.' || c == '。' || c == '?' || c == '？' || c == '!' || c == '！' || c == ' '
|| c == ' ' || c == ' ')
&& i < 8) start = i + 1;
}
if (start != 0) content = content.substring(start);
end = 0;
if (HtmlStringUtil.isNotEmpty(content)) {
char c = content.charAt(content.length() - 1);
if (c != '.' && c != '。' && c != '?' && c != '？' && c != '!' && c != '！') {
for (int i = content.length() - 2; i > 0; i--) {
c = content.charAt(i);
if (c != ';' && c != '；' && c != ',' && c != '，' && c != '>' && c != '》') continue;
end = i;
break;
}
}
}
if (end != 0) content = content.substring(0, end);
}
return content;
}
/**
* Serch method
*
* @param f
* @param luquery
* @param entities
* @return
* @throws Exception
*/
@Transactional(propagation = Propagation.REQUIRED)
public List<SearchResultWH> searchWH(
String[] f,
String luquery,
String hgQuery,
SortField[] sortFields,
int firstResult,
int maxResults,
Class<?>... entities)
throws Exception {
// create FullTextEntityManager ----------------------------
FullTextEntityManager fullTextEntityManager =
org.hibernate.search.jpa.Search.getFullTextEntityManager(entityManager);
StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_31);
// ---------------------------------------------------------
QueryParser parser = new MultiFieldQueryParser(Version.LUCENE_31, f, analyzer);
org.apache.lucene.search.Query query = parser.parse(luquery.trim());
System.out.println("QUERY: " + query + " entitys size:" + entities.length);
// wrap Lucene query in a javax.persistence.Query
// javax.persistence.Query persistenceQuery = fullTextEntityManager
// .createFullTextQuery(query, entities);
org.hibernate.search.jpa.FullTextQuery persistenceQuery =
fullTextEntityManager.createFullTextQuery(query, entities);
// org.apache.lucene.search.Sort sort = new Sort(
// new SortField("title", SortField.STRING));
if (sortFields != null && sortFields.length > 0) {
persistenceQuery.setSort(new Sort(sortFields));
System.out.println("Sort setted");
}
if (firstResult >= 0) {
persistenceQuery.setFirstResult(firstResult);
persistenceQuery.setMaxResults(maxResults);
}
// execute search
@SuppressWarnings("unchecked")
List<Object> result = persistenceQuery.getResultList();
// ---------------------------------------------------------------
QueryScorer qs = null;
if (hgQuery != null && hgQuery.trim().length() > 0) { // Если запрос для
// подсветки
// специфичный
qs = new QueryScorer(parser.parse(hgQuery.trim()));
} else {
qs = new QueryScorer(query);
}
Highlighter highlighter =
new Highlighter(
new Formatter() {
String preTag = "<font color=\"red\"><b>";
String postTag = "</b></font>";
@Override
public String highlightTerm(String originalText, TokenGroup tokenGroup) {
StringBuffer returnBuffer;
if (tokenGroup.getTotalScore() > 0) {
returnBuffer = new StringBuffer();
returnBuffer.append(preTag);
returnBuffer.append(originalText);
returnBuffer.append(postTag);
return returnBuffer.toString();
}
return originalText;
}
},
qs);
highlighter.setTextFragmenter(new SimpleFragmenter(150));
// ---------------------------------------------------------------
List<SearchResultWH> listWH = new ArrayList<SearchResultWH>();
for (Object o : result) {
if (o instanceof Hotel) {
Hotel h = (Hotel) o;
h.getResortTypes().size(); // LAZY load
listWH.add(makeHW(highlighter, analyzer, h));
} else if (o instanceof ResortType) {
listWH.add(makeHW(highlighter, analyzer, (ResortType) o));
} else if (o instanceof PublicImage) {
listWH.add(makeHW(highlighter, analyzer, (PublicImage) o));
} else if (o instanceof FileResourse) {
listWH.add(makeHW(highlighter, analyzer, (FileResourse) o));
} else if (o instanceof News) {
listWH.add(makeHW(highlighter, analyzer, (News) o));
} else if (o instanceof Announce) {
listWH.add(makeHW(highlighter, analyzer, (Announce) o));
} else if (o instanceof Location) {
listWH.add(makeHW(highlighter, analyzer, (Location) o));
} else if (o instanceof LType) {
listWH.add(makeHW(highlighter, analyzer, (LType) o));
} else if (o instanceof AnyText) {
listWH.add(makeHW(highlighter, analyzer, (AnyText) o));
} else if (o instanceof Visa) {
listWH.add(makeHW(highlighter, analyzer, (Visa) o));
}
}
return listWH;
}