/**
* 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;
}
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;
}
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();
}
}
/**
* 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;
}
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;
}