Last active
August 29, 2015 14:28
-
-
Save vince-geekcore/c084fa22aad345f06049 to your computer and use it in GitHub Desktop.
Lucene.NET HitHighlighter (with Boolean Query) could be used in combination with Sitecore.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/// <summary> | |
/// Uses Lucene Contrib Highlighter to create search highlight based on an index field/string with all content | |
/// This code requires Lucene 3.0.3.0 DLL from Nuget and is not supported with the Sitecore7 Lucene DLL out of the box. | |
/// This is pure Lucene code and does not use any Sitecore namespaces. | |
/// Adding Try/catch is advised. searchQuery = searchterm/keyword(s) | |
/// </summary> | |
private string GenerateHighlightText(string pageContent, string searchQuery) | |
{ | |
var analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30); | |
// Create Wildcard query using the BooleanQuery for multiple words. | |
var booleanQuery = new BooleanQuery(); | |
var segments = searchQuery.ToLower().Split(new[] { " " }, StringSplitOptions.RemoveEmptyEntries); | |
foreach (var segment in segments) | |
{ | |
var wildcardQuery = new WildcardQuery(new Lucene.Net.Index.Term("", segment + "*")); | |
booleanQuery.Add(new BooleanClause(wildcardQuery, Occur.SHOULD)); | |
} | |
IFormatter formatter = new SimpleHTMLFormatter("<strong>", "</strong>"); | |
// set max size for every segment | |
var fragmenter = new SimpleFragmenter(132); | |
var scorer = new QueryScorer(booleanQuery); | |
var highlighter = new Highlighter(formatter, scorer) { TextFragmenter = fragmenter }; | |
// remove html tags from content | |
string rawPageContent = StringUtil.RemoveTags(pageContent); | |
// get highlighted fragments | |
TokenStream stream = analyzer.TokenStream("", new StringReader(rawPageContent)); | |
string highlightedFragment = highlighter.GetBestFragments(stream, rawPageContent, 3, "..."); | |
if (!string.IsNullOrWhiteSpace(highlightedFragment)) | |
{ | |
return new HtmlString(highlightedFragment); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment