gpt4 book ai didi

c# - 使用 Apache Lucene 进行搜索

转载 作者:太空狗 更新时间:2023-10-29 18:00:03 26 4
gpt4 key购买 nike

我一直在尝试实现 Lucene 来加快我网站上的搜索速度。

我的代码目前可以运行,但是,我认为我没有正确使用 Lucene。现在,我的搜索查询是 productName:asterisk(input)asterisk - 我无法想象这是你应该做的来找到 productName 包含的所有产品输入。我认为这与我将字段保存到文档的方式有关。

我的代码:

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
};

}

}
}

我如何调用 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;
}
}

}

如有任何帮助,我们将不胜感激。

产品输入列表示例: ProductList

查询:从产品中选择 Product.ID、Product.Description、Product.Name

期望的结果: DesiredResults

等效于 SQL Server 查询:SELECT Product.ID、Product.Description、Product.Name FROM Product WHERE Product.Name LIKE '%Zelf%' OR Product.Description LIKE '%Zelf%'

基本上,Zelf 是输入。我想找到包含输入字符串的产品描述或产品名称的所有匹配项。

最佳答案

ucene not allows使用?或 * 作为搜索词的起始符号。为了克服这个问题,您需要在索引中存储从单词的任何位置到结束位置的子字符串。例如。对于单词测试,你应该放在索引中

test
est
st
t

我建议为此使用单独的字段。 Java 示例,如果您有一个短字段,其中包含一个单词,例如产品名称。

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);
}

在此之后,您可以使用以下查询字符串productNameSearch:(input)asterisk 或使用 PrefixQuery用于搜索包含 input 的产品名称。

如果您的字段中有多个单词,并且输入的长度足够合理,那么最好为该字段添加 NGramTokenFilter .如果您的输入字符串有从 n 到 m 的限制,您应该创建一个具有 n minGram 和 m maxGramm 的 NGram token 过滤器。如果你有单词 test 并且你将 2 到 3 个限制在你的索引词中

te
tes
es
est
st

之后你可以通过字符串搜索

ngrammField:(输入)

关于c# - 使用 Apache Lucene 进行搜索,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/33825369/

26 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com