Question

我想为我的用户提供搜索引擎。让我们说用户类是：

public class User
{
    public string Code { get; set; }
    public string Name { get; set; }
}

我的数据库中有这样的用户：

(1) new User { Code = "XW1234", Name = "John Doe" }, 
(2) new User { Code = "AD4567", Name = "Jane Doe" }

所以：当我的查询是：＆＃34; doe＆＃34; （注意小写）我想看（1）和（2）当我的查询是：＆＃34; 4＆＃34;我想看（1）和（2）当我的查询是：＆＃34; x＆＃34;我想看（1）当我的查询是：＆＃34; ja＆＃34;我想看（2）我希望在SQL中与like %doe%类似地工作。请不要介意查询长度 - 我最少使用3个字母。这只是一个例子。

我有一个带通配符的解决方案 - 工作但性能很差。

我试图配置索引以使用ngram tokenizer但没有成功 - 我收到了一个空集合。

我也检查了这个（＆＃34;以＆＃34;方法开始）： https://www.elastic.co/guide/en/elasticsearch/guide/current/_index_time_search_as_you_type.html 没有成功。

请提供C＃代码。我不知道我是否正确翻译了弹性搜索jsons。

修改根据第一条评论我尝试了这个：

private const string DefaultIndexName = "test";
private const string ElasticSearchServerUri = @"http://192.168.99.100:32769";

private static readonly IndexName UsersIndexName = "users";

public IElasticClient CreateElasticClient()
{
    var settings = CreateConnectionSettings();

    var client = new ElasticClient(settings);

    var studentsIndexDescriptor = new CreateIndexDescriptor(UsersIndexName)
        .Mappings(ms => ms
            .Map<User>(m => m
                .Properties(ps => ps
                    .String(s => s
                        .Name(n => n.Code)
                        .Analyzer("substring_analyzer")))));
    client.CreateIndex(UsersIndexName, descriptor => studentsIndexDescriptor
        .Settings(s => s
            .Analysis(a => a
                .Analyzers(analyzer => analyzer
                    .Custom("substring_analyzer", analyzerDescriptor => analyzerDescriptor.Tokenizer("standard").Filters("lowercase", "substring")))
                .TokenFilters(tf => tf
                    .NGram("substring", filterDescriptor => filterDescriptor.MinGram(2).MaxGram(15))))));

    return client;
}

private static ConnectionSettings CreateConnectionSettings()
{
    var uri = new Uri(ElasticSearchServerUri);
    var settings = new ConnectionSettings(uri);
    settings
        .DefaultIndex(DefaultIndexName);

    return settings;
}

我使用了这个查询：

public IEnumerable<User> Search(string query)
{
    var result = elasticClient.Search<User>(descriptor => descriptor
        .Query(q => q
            .QueryString(queryDescriptor => queryDescriptor.Query(query).Fields(fs => fs.Fields(f1 => f1.Code)))));
    return result.Documents;
}

没有工作。

我尝试过代码：＆＃34; 1234＆＃34;和＆＃34; 5678＆＃34;。我尝试用＆＃34; 23＆＃34;，＆＃34; 5＆＃34; - 没有结果。当我搜索＆＃34; 1234＆＃34; - 它返回正确的用户。

Answer 1

我怀疑你的代码：

为用户编制索引时，不指定users索引，因此将用户编入索引为默认索引。
搜索时，不指定users索引，因此将查询默认索引test。此索引包含索引文档，但code字段未使用substring_analyzer进行分析，因为此分析在users索引中定义。

NEST在ConnectionSettings，.InferMappingFor<T>()上提供配置选项，以将特定POCO类型与特定索引名称相关联;如果未在请求中指定并且优先于默认索引，则将使用此索引。

var uri = new Uri(ElasticSearchServerUri);
var settings = new ConnectionSettings(uri)
    .DefaultIndex(DefaultIndexName)
    .InferMappingFor<User>(d => d
        .IndexName(UsersIndexName)
    );

您的其余代码是正确的。这是一个完整的工作示例

private const string DefaultIndexName = "test";
private const string ElasticSearchServerUri = @"http://localhost:9200";
private const string UsersIndexName = "users";

void Main()
{
    var client = CreateElasticClient();

    var users = new[] {
        new User { Code = "XW1234", Name = "John Doe" },
        new User { Code = "AD4567", Name = "Jane Doe" }
    };

    client.IndexMany(users);

    // refresh the index after indexing so that the documents are immediately 
    // available for search. This is good for testing, 
    // but avoid doing it in production.
    client.Refresh(UsersIndexName);

    var result = client.Search<User>(descriptor => descriptor
        .Query(q => q
            .QueryString(queryDescriptor => queryDescriptor
                .Query("1234")
                .Fields(fs => fs
                    .Fields(f1 => f1.Code)
                )
            )
        )
    );

    // outputs 1
    Console.WriteLine(result.Total);
}

public class User
{
    public string Code { get; set; }
    public string Name { get; set; }
}

public IElasticClient CreateElasticClient()
{
    var settings = CreateConnectionSettings();
    var client = new ElasticClient(settings);

    // this is here so that the example can be re-run.
    // Remove this!
    if (client.IndexExists(UsersIndexName).Exists)
    {
        client.DeleteIndex(UsersIndexName);
    }

    client.CreateIndex(UsersIndexName, descriptor => descriptor
        .Mappings(ms => ms
            .Map<User>(m => m
                .AutoMap()
                .Properties(ps => ps
                    .String(s => s
                        .Name(n => n.Code)
                        .Analyzer("substring_analyzer")
                    )
                )
            )
        )
        .Settings(s => s
            .Analysis(a => a
                .Analyzers(analyzer => analyzer
                    .Custom("substring_analyzer", analyzerDescriptor => analyzerDescriptor
                        .Tokenizer("standard")
                        .Filters("lowercase", "substring")
                    )
                )
                .TokenFilters(tf => tf
                    .NGram("substring", filterDescriptor => filterDescriptor
                        .MinGram(2)
                        .MaxGram(15)
                    )
                )
            )
        )
    );

    return client;
}

private static ConnectionSettings CreateConnectionSettings()
{
    var uri = new Uri(ElasticSearchServerUri);
    var settings = new ConnectionSettings(uri)
        .DefaultIndex(DefaultIndexName)
        .InferMappingFor<User>(d => d
            .IndexName(UsersIndexName)
        );

    return settings;
}

Elasticsearch NEST：不带通配符的部分/全文搜索

1 个答案: