Created
August 4, 2012 03:59
-
-
Save briandonahue/3254252 to your computer and use it in GitHub Desktop.
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
using System; | |
using System.Collections.Generic; | |
using System.Configuration; | |
using System.Globalization; | |
using System.IO; | |
using Hercules.Infrastructure.Search.Mapping; | |
using Lucene.Net.Analysis.Standard; | |
using Lucene.Net.Index; | |
using Lucene.Net.QueryParsers; | |
using Lucene.Net.Search; | |
using Lucene.Net.Store; | |
using Version = Lucene.Net.Util.Version; | |
using Hercules.Infrastructure; | |
using System.Linq; | |
namespace Hercules.Infrastructure.Search.QueryMaps | |
{ | |
public abstract class QueryMapBase<T> : IQueryMapper<T> where T : ISearchCriteria | |
{ | |
readonly string baseIndexPath = ConfigurationManager.AppSettings["LuceneIndexDirectory"]; | |
readonly FSDirectory indexDir; | |
IndexReader reader; | |
protected QueryMapBase() | |
{ | |
var indexPath = Path.Combine(baseIndexPath, typeof (T).Name.Replace("SearchCriteria", "")); | |
indexDir = FSDirectory.Open(new DirectoryInfo(indexPath)); | |
reader = IndexReader.Open(indexDir, true); | |
} | |
public abstract Lucene.Net.Search.Query Map(T criteria); | |
protected void AddPrefixQuery(string fieldName, string text, BooleanQuery query) | |
{ | |
if (query == null) return; | |
if (string.IsNullOrEmpty(text)) return; | |
query.Add(new PrefixQuery(new Term(fieldName, text.ToLower())), | |
BooleanClause.Occur.MUST); | |
} | |
protected void AddPrefixQueries(string fieldName, IEnumerable<string> keywords, BooleanQuery query) | |
{ | |
if (query == null || keywords.IsNullOrEmpty()) return; | |
var statusQuery = new BooleanQuery(); | |
keywords.Each(keyword => | |
{ | |
foreach (string term in keyword.ToLower(CultureInfo.InvariantCulture).Split(' ')) | |
{ | |
statusQuery.Add(new PrefixQuery(new Term(fieldName, term)), | |
BooleanClause.Occur.SHOULD); | |
} | |
}); | |
query.Add(statusQuery, BooleanClause.Occur.MUST); | |
} | |
protected void AddPhraseQuery(string fieldName, string phrase, BooleanQuery query) | |
{ | |
if (query == null || string.IsNullOrEmpty(phrase)) return; | |
// if only one term, a prefix query will suffice | |
var terms = phrase.ToLower().Split(' '); | |
if (terms.Count() == 1) | |
{ | |
AddPrefixQuery(fieldName, phrase, query); | |
return; | |
} | |
// if multiple terms, we want to match phrase with wildcard, such as "wall street jou*" | |
// The process for doing this in Lucene is horrid: | |
// Taken mostly from http://stackoverflow.com/questions/5075304/how-to-use-a-multiphrasequery | |
var phraseQuery = new MultiPhraseQuery(); | |
// Add all but last term as regular terms | |
terms.Take(terms.Count() - 1).Each(t => phraseQuery.Add(new Term(fieldName, t))); | |
// get last term, and retrieve ALL matching terms, and add as an OR block | |
var lastTermText = terms.Last(); | |
var lastTerm = new Term(fieldName, lastTermText); | |
var termEnum = reader.Terms(lastTerm); | |
var fuzzyTerms = new List<Term>(); | |
do { | |
var currTerm = termEnum.Term(); | |
if (currTerm.Field() != fieldName || !currTerm.Text().StartsWith(lastTermText)) break; | |
fuzzyTerms.Add(termEnum.Term()); | |
} while (termEnum.Next()); | |
// add the original term, mostly in case no terms matched, Lucene throws an error | |
fuzzyTerms.Add(lastTerm); | |
phraseQuery.Add(fuzzyTerms.ToArray()); | |
query.Add(phraseQuery, BooleanClause.Occur.MUST); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment