I've been trying to implement Lucene to make the searching on my website faster.
My code currently works, however, I think I am not correctly making use of Lucene. Right now, my search query is productName:asterisk(input)asterisk
- I can't imagine this is what you're supposed to do to find all products where productName
contains input
. I think it has something to do with the way I save the fields to a document.
My code:
LuceneHelper.cs
using System;
using System.Collections;
using System.Collections.Generic;
using System.Data.Entity.Migrations.Model;
using System.Linq;
using System.Threading.Tasks;
using Lucene.Net;
using Lucene.Net.Analysis;
using Lucene.Net.Analysis.Standard;
using Lucene.Net.Documents;
using Lucene.Net.Index;
using Lucene.Net.QueryParsers;
using Lucene.Net.Search;
using Lucene.Net.Store;
using Rentpro.Models;
using RentPro.Models.Tables;
using RentProModels.Models;
namespace RentPro.Helpers
{
public class LuceneHelper
{
private const Lucene.Net.Util.Version Version = Lucene.Net.Util.Version.LUCENE_30;
private bool IndicesInitialized;
private List<Language> Languages = new List<Language>();
public void BuildIndices(DB db)
{
Languages = GetLanguages(db);
Analyzer analyzer = new StandardAnalyzer(Version);
List<Product> allProducts = db.GetAllProducts(true, false);
foreach (Language l in Languages)
{
BuildIndicesForLanguage(allProducts, analyzer, l.ID);
}
IndicesInitialized = true;
}
private void BuildIndicesForLanguage(List<Product> products, Analyzer analyzer, int id = 0)
{
using (
IndexWriter indexWriter = new IndexWriter(GetDirectory(id), analyzer,
IndexWriter.MaxFieldLength.UNLIMITED))
{
var x = products.Count;
foreach (Product p in products)
{
SearchProduct product = SearchProduct.FromProduct(p, id);
Document document = new Document();
Field productIdField = new Field("productId", product.ID.ToString(), Field.Store.YES, Field.Index.NO);
Field productTitleField = new Field("productName", product.Name, Field.Store.YES, Field.Index.ANALYZED);
Field productDescriptionField = new Field("productDescription", product.Description, Field.Store.YES, Field.Index.ANALYZED);
Field productCategoryField = new Field("productCategory", product.Category, Field.Store.YES, Field.Index.ANALYZED);
Field productCategorySynonymField = new Field("productCategorySynonym", product.CategorySynonym, Field.Store.YES, Field.Index.ANALYZED);
Field productImageUrlField = new Field("productImageUrl", product.ImageUrl, Field.Store.YES, Field.Index.NO);
Field productTypeField = new Field("productType", product.Type, Field.Store.YES, Field.Index.NO);
Field productDescriptionShortField = new Field("productDescriptionShort", product.DescriptionShort, Field.Store.YES, Field.Index.NO);
Field productPriceField = new Field("productPrice", product.Price, Field.Store.YES, Field.Index.NO);
document.Add(productIdField);
document.Add(productTitleField);
document.Add(productDescriptionField);
document.Add(productCategoryField);
document.Add(productCategorySynonymField);
document.Add(productImageUrlField);
document.Add(productTypeField);
document.Add(productDescriptionShortField);
document.Add(productPriceField);
indexWriter.AddDocument(document);
}
indexWriter.Optimize();
indexWriter.Commit();
}
}
public List<SearchProduct> Search(string input)
{
if (!IndicesInitialized)
{
BuildIndices(new DB());
return Search(input);
}
IndexReader reader = IndexReader.Open(GetCurrentDirectory(), true);
Searcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new StandardAnalyzer(Version);
TopScoreDocCollector collector = TopScoreDocCollector.Create(100, true);
MultiFieldQueryParser parser = new MultiFieldQueryParser(Version,
new[] { "productDescription", "productCategory", "productCategorySynonym", "productName" }, analyzer)
{
AllowLeadingWildcard = true
};
searcher.Search(parser.Parse("*" + input + "*"), collector);
ScoreDoc[] hits = collector.TopDocs().ScoreDocs;
List<int> productIds = new List<int>();
List<SearchProduct> results = new List<SearchProduct>();
foreach (ScoreDoc scoreDoc in hits)
{
Document document = searcher.Doc(scoreDoc.Doc);
int productId = int.Parse(document.Get("productId"));
if (!productIds.Contains(productId))
{
productIds.Add(productId);
SearchProduct result = new SearchProduct
{
ID = productId,
Description = document.Get("productDescription"),
Name = document.Get("productName"),
Category = document.Get("productCategory"),
CategorySynonym = document.Get("productCategorySynonym"),
ImageUrl = document.Get("productImageUrl"),
Type = document.Get("productType"),
DescriptionShort = document.Get("productDescriptionShort"),
Price = document.Get("productPrice")
};
results.Add(result);
}
}
reader.Dispose();
searcher.Dispose();
analyzer.Dispose();
return results;
}
private string GetDirectoryPath(int languageId = 1)
{
return GetDirectoryPath(Languages.SingleOrDefault(x => x.ID == languageId).UriPart);
}
private string GetDirectoryPath(string languageUri)
{
return AppDomain.CurrentDomain.BaseDirectory + @"\App_Data\LuceneIndices\" + languageUri;
}
private List<Language> GetLanguages(DB db)
{
return db.Languages.ToList();
}
private int GetCurrentLanguageId()
{
return Translator.GetCurrentLanguageID();
}
private FSDirectory GetCurrentDirectory()
{
return FSDirectory.Open(GetDirectoryPath(GetCurrentLanguageId()));
}
private FSDirectory GetDirectory(int languageId)
{
return FSDirectory.Open(GetDirectoryPath(languageId));
}
}
public class SearchProduct
{
public int ID { get; set; }
public string Description { get; set; }
public string Name { get; set; }
public string ImageUrl { get; set; }
public string Type { get; set; }
public string DescriptionShort { get; set; }
public string Price { get; set; }
public string Category { get; set; }
public string CategorySynonym { get; set; }
public static SearchProduct FromProduct(Product p, int languageId)
{
return new SearchProduct()
{
ID = p.ID,
Description = p.GetText(languageId, ProductLanguageType.Description),
Name = p.GetText(languageId),
ImageUrl =
p.Images.Count > 0
? "/Company/" + Settings.Get("FolderName") + "/Pictures/Products/100x100/" +
p.Images.Single(x => x.Type == "Main").Url
: "",
Type = p is HuurProduct ? "HuurProduct" : "KoopProduct",
DescriptionShort = p.GetText(languageId, ProductLanguageType.DescriptionShort),
Price = p is HuurProduct ? ((HuurProduct)p).CalculatedPrice(1, !Settings.GetBool("BTWExLeading")).ToString("0.00") : "",
Category = p.Category.Name,
CategorySynonym = p.Category.Synonym
};
}
}
}
How I call the LuceneHelper:
public ActionResult Lucene(string SearchString, string SearchOrderBy, int? page, int? amount)
{
List<SearchProduct> searchResults = new List<SearchProduct>();
if (!SearchString.IsNullOrWhiteSpace())
{
LuceneHelper lucene = new LuceneHelper();
searchResults = lucene.Search(SearchString);
}
return View(new LuceneSearchResultsVM(db, SearchString, searchResults, SearchOrderBy, page ?? 1, amount ?? 10));
}
LuceneSearchResultsVM:
using System;
using System.Collections.Generic;
using System.Linq;
using System.Linq.Dynamic;
using System.Web;
using RentPro.Models.Tables;
using System.Linq.Expressions;
using System.Reflection;
using Microsoft.Ajax.Utilities;
using Rentpro.Models;
using RentPro.Helpers;
using RentProModels.Models;
namespace RentPro.ViewModels
{
public class LuceneSearchResultsVM
{
public List<SearchProduct> SearchProducts { get; set; }
public bool BTWActive { get; set; }
public bool BTWEXInput { get; set; }
public bool BTWShow { get; set; }
public bool BTWExLeading { get; set; }
public string FolderName { get; set; }
public string CurrentSearchString { get; set; }
public string SearchOrderBy { get; set; }
public int Page;
public int Amount;
public String SearchQueryString {
get
{
return Translator.Translate("Zoekresultaten voor") + ": " + CurrentSearchString + " (" +
SearchProducts.Count + " " + Translator.Translate("resultaten") + " - " +
Translator.Translate("pagina") + " " + Page + " " + Translator.Translate("van") + " " +
CalculateAmountOfPages() + ")";
}
set { }
}
public LuceneSearchResultsVM(DB db, string queryString, List<SearchProduct> results, string searchOrderBy, int page, int amt)
{
BTWActive = Settings.GetBool("BTWActive");
BTWEXInput = Settings.GetBool("BTWEXInput");
BTWShow = Settings.GetBool("BTWShow");
BTWExLeading = Settings.GetBool("BTWExLeading");
FolderName = Settings.Get("FolderName");
SearchProducts = results;
CurrentSearchString = queryString;
if (searchOrderBy.IsNullOrWhiteSpace())
{
searchOrderBy = "Name";
}
SearchOrderBy = searchOrderBy;
Amount = amt == 0 ? 10 : amt;
int maxPages = CalculateAmountOfPages();
Page = page > maxPages ? maxPages : page;
SearchLog.MakeEntry(queryString, SearchProducts.Count(), db, HttpContext.Current.Request.UserHostAddress);
}
public List<SearchProduct> GetOrderedList()
{
List<SearchProduct> copySearchProductList = new List<SearchProduct>(SearchProducts);
copySearchProductList = copySearchProductList.Skip((Page - 1) * Amount).Take(Amount).ToList();
switch (SearchOrderBy)
{
case "Price":
copySearchProductList.Sort(new PriceSorter());
break;
case "DateCreated":
return copySearchProductList; //TODO
default:
return copySearchProductList.OrderBy(n => n.Name).ToList();
}
return copySearchProductList;
}
public int CalculateAmountOfPages()
{
int items = SearchProducts.Count;
return items / Amount + (items % Amount > 0 ? 1 : 0);
}
}
public class PriceSorter : IComparer<SearchProduct>
{
public int Compare(SearchProduct x, SearchProduct y)
{
if (x == null || x.Price == "") return 1;
if (y == null || y.Price == "") return -1;
decimal priceX = decimal.Parse(x.Price);
decimal priceY = decimal.Parse(y.Price);
return priceX > priceY ? 1 : priceX == priceY ? 0 : -1;
}
}
}
Any help would be greatly appreciated.
Example input list of products:
Query:
SELECT Product.ID, Product.Decription, Product.Name FROM Product
Desired results:
SQL Server query equivalent:
SELECT Product.ID, Product.Decription, Product.Name FROM Product WHERE Product.Name LIKE '%Zelf%' OR Product.Decription LIKE '%Zelf%'
Basically, Zelf
is the input. I want to find all matches with product descriptions or product names that contain the input string.
Apache Lucene™ is a high-performance, full-featured search engine library written entirely in Java. It is a technology suitable for nearly any application that requires structured search, full-text search, faceting, nearest-neighbor search across high-dimensionality vectors, spell correction or query suggestions.
Despite these open-source bona fides, it's still surprising to see someone at Google adopting Solr, an open-source search server based on Apache Lucene, for its All for Good site. Google is the world's search market leader by a very long stretch.
Lucene is able to achieve fast search responses because, instead of searching the text directly, it searches an index instead. This would be the equivalent of retrieving pages in a book related to a keyword by searching the index at the back of a book, as opposed to searching the words in each page of the book.
ucene not allows to use ? or * as starting symbols of the searching term. To overcome this issue you need to store in your index a sub-strings from any position of word to it end position. E.g. for word test you should put to index
test
est
st
t
I recommend to use separate field for that. Java example for case if you have a short field with one word like a product name.
for(int i = 0; i < product.SafeName.length()-1; i++){
Field productTitleSearchField = new Field("productNameSearch", product.SafeName.substring(i, product.SafeName.length()), Field.Store.NO, Field.Index.ANALYZED);
}
After this you can use following query string
productNameSearch:(input)asterisk
or use a PrefixQuery for searching product names containing input
.
In case if you have several words in you field and for you will be enough to have some reasonable length of your input, then it will better to add for this field a NGramTokenFilter. You if have limit on your input string from n to m you should create a NGram Token Filter with n minGram and m maxGramm. If you has word test
and you limit 2 to 3 you will have in your index words
te
tes
es
est
st
After this you can search via string
ngrammField:(input)
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With