Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-1114: Updated example 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@608126 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Grant Ingersoll 2008-01-02 15:30:40 +00:00
parent 0ae1e1a905
commit ed893f770c
1 changed files with 28 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
contrib/highlighter/src/java/org/apache/lucene/search/highlight/package.html
View File

@ -10,19 +10,34 @@ Fragmenter, FragmentScorer, Formatter classes.
<h2>Example Usage</h2>
<pre>
IndexSearcher searcher = new IndexSearcher(ramDir);
Query query = QueryParser.parse("Kenne*", FIELD_NAME, analyzer);
query = query.rewrite(reader); //required to expand search terms
//... Above, create documents with two fields, one with term vectors (tv) and one without (notv)
IndexSearcher searcher = new IndexSearcher(directory);
QueryParser parser = new QueryParser("notv", analyzer);
Query query = parser.parse("million");
//query = query.rewrite(reader); //required to expand search terms
Hits hits = searcher.search(query);
Highlighter highlighter = new Highlighter(this, new QueryScorer(query));
for (int i = 0; i &lt; hits.length(); i++)
{
String text = hits.doc(i).get(FIELD_NAME);
TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, new StringReader(text));
// Get 3 best fragments and seperate with a "..."
String result = highlighter.getBestFragments(tokenStream, text, 3, "...");
System.out.println(result);
SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter();
Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(query));
for (int i = 0; i < 10; i++) {
String text = hits.doc(i).get("notv");
TokenStream tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), hits.id(i), "notv", analyzer);
TextFragment[] frag = highlighter.getBestTextFragments(tokenStream, text, false, 10);//highlighter.getBestFragments(tokenStream, text, 3, "...");
for (int j = 0; j < frag.length; j++) {
if ((frag[j] != null) && (frag[j].getScore() > 0)) {
System.out.println((frag[j].toString()));
}
}
//Term vector
text = hits.doc(i).get("tv");
tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), hits.id(i), "tv", analyzer);
frag = highlighter.getBestTextFragments(tokenStream, text, false, 10);
for (int j = 0; j < frag.length; j++) {
if ((frag[j] != null) && (frag[j].getScore() > 0)) {
System.out.println((frag[j].toString()));
}
}
System.out.println("-------------");
}
</pre>