我正在使用以下代码创建索引:
var ElasticSettings = new ConnectionSettings(new Uri(ConnectionString))
.DefaultIndex(_IndexName)
.DefaultMappingFor<PictureObject>(M => M
.Ignore(_ => _._id)
.Ignore(_ => _.Log))
.DefaultFieldNameInferrer(_ => _);
_ElasticClient = new ElasticClient(ElasticSettings);
if (!_ElasticClient.IndexExists(_IndexName).Exists)
{
var I = _ElasticClient.CreateIndex(_IndexName, Ci => Ci
.Settings(S => S
.Analysis(A => A
.CharFilters(Cf => Cf.Mapping("expressions",
E => E.Mappings(ExpressionsList))
)
.TokenFilters(Tf => Tf.Synonym("synonyms",
Descriptor => new SynonymTokenFilter
{
Synonyms = SynonymsList,
Tokenizer = "whitespace"
})
)
.Analyzers(Analyzer => Analyzer
.Custom("index", C => C
.CharFilters("expressions")
.Tokenizer("standard")
.Filters("synonyms", "standard", "lowercase", "stop")
)
.Custom("search", C => C
.CharFilters("expressions")
.Tokenizer("standard")
.Filters("synonyms", "standard", "lowercase", "stop")
)
)
)
)
.Mappings(Mapping => Mapping
.Map<PictureObject>(Map => Map
.AutoMap()
.Properties(P => P
.Text(T => T
.Name(N => N.Title)
.Analyzer("index")
.SearchAnalyzer("search")
)
.Text(T => T
.Name(N => N.Tags)
.Analyzer("index")
.SearchAnalyzer("search")
)
)
)
)
);
我要搜索的字段是“标题”和“标签”
我的同义词是这种格式:
[“大=>大,巨大”,“小=>小,微小”,]
我的表情像:
[“暴风雨=>暴风雨”,“快乐的一天=>欢乐”,]
我正在使用以下两种方法进行测试:
var Test1 = _ElasticClient.Search<PictureObject>(S => S
.From(From)
.Size(Take)
.Query(_ => _.Fuzzy(Fuzz => Fuzz.Field(F => F.Tags).Field(T => T.Title).Value(Terms).MaxExpansions(2)))).Documents;
var resTest2 = _ElasticClient.Search<PictureObject>(S => S
.Query(_ => _.QueryString(F => F.Query(Terms)))
.From(From)
.Size(Take));
当尝试完全匹配标签字段中的术语时,这两个函数将返回不同的结果。 尝试使用同义词时,结果再次有所不同。
(最终,我也想处理拼写错误,但现在我只是使用逐字字符串进行测试)
我想念什么? (我对API仍然不太了解,因此错误可能非常明显)
编辑: 这是一个可以编译的完整示例。
namespace Test
{
using System;
using System.Collections.Generic;
using Nest;
public class MyData
{
public string Id;
public string Title;
public string Tags;
}
public static class Program
{
public static void Main()
{
const string INDEX_NAME = "testindex";
var ExpressionsList = new[]
{
"bad weather => storm",
"happy day => sun"
};
var SynonymsList = new[]
{
"big => large, huge",
"small => tiny, minuscule",
"sun => sunshine, shiny, sunny"
};
// connect
var ElasticSettings = new ConnectionSettings(new Uri("http://elasticsearch:9200"))
.DefaultIndex(INDEX_NAME)
.DefaultFieldNameInferrer(_ => _) // stop the camel case
.DefaultMappingFor<MyData>(M => M.IdProperty("Id"));
var Client = new ElasticClient(ElasticSettings);
// erase the old index, if any
if (Client.IndexExists(INDEX_NAME).Exists) Client.DeleteIndex(INDEX_NAME);
// create the index
var I = Client.CreateIndex(INDEX_NAME, Ci => Ci
.Settings(S => S
.Analysis(A => A
.CharFilters(Cf => Cf.Mapping("expressions",
E => E.Mappings(ExpressionsList))
)
.TokenFilters(Tf => Tf.Synonym("synonyms",
Descriptor => new SynonymTokenFilter
{
Synonyms = SynonymsList,
Tokenizer = "whitespace"
})
)
.Analyzers(Analyzer => Analyzer
.Custom("index", C => C
.CharFilters("expressions")
.Tokenizer("standard")
.Filters("synonyms", "standard", "lowercase", "stop")
)
.Custom("search", C => C
.CharFilters("expressions")
.Tokenizer("standard")
.Filters("synonyms", "standard", "lowercase", "stop")
)
)
)
)
.Mappings(Mapping => Mapping
.Map<MyData>(Map => Map
.AutoMap()
.Properties(P => P
.Text(T => T
.Name(N => N.Title)
.Analyzer("index")
.SearchAnalyzer("search")
)
.Text(T => T
.Name(N => N.Tags)
.Analyzer("index")
.SearchAnalyzer("search")
)
)
)
)
);
// add some data
var Data = new List<MyData>
{
new MyData { Id = "1", Title = "nice stormy weather", Tags = "storm nice" },
new MyData { Id = "2", Title = "a large storm with sunshine", Tags = "storm large sunshine" },
new MyData { Id = "3", Title = "a storm during a sunny day", Tags = "sun storm" }
};
Client.IndexMany(Data);
Client.Refresh(INDEX_NAME);
// do some queries
var TestA1 = Client.Search<MyData>(S => S.Query(_ => _.Fuzzy(Fuzz => Fuzz.Field(F => F.Tags).Field(T => T.Title).Value("stormy sunny").MaxExpansions(2)))).Documents;
var TestA2 = Client.Search<MyData>(S => S.Query(_ => _.Fuzzy(Fuzz => Fuzz.Field(F => F.Tags).Field(T => T.Title).Value("stromy sunny").MaxExpansions(2)))).Documents;
var TestB1 = Client.Search<MyData>(S => S.Query(_ => _.QueryString(F => F.Query("stormy sunny")))).Documents;
// expected to return documents 1, 2, 3 because of synonyms: sun => sunny, shiny, sunshine
var TestB2 = Client.Search<MyData>(S => S.Query(_ => _.QueryString(F => F.Query("bad weather")))).Documents;
var TestB3 = Client.Search<MyData>(S => S.Query(_ => _.QueryString(F => F.Query("a large happy day")))).Documents;
/*
* I'm expecting the fuzzy queries to handle misspellings
* Also, I'm expecting the expressions and synonyms to do the substitutions as they're written
*
* Ideally I'd like to handle:
* - expressions
* - synonyms
* - misspellings
*
* all together
*
* I have tried a lot of string examples while debugging and it's really hit or miss.
* Unfortunately, I haven't kept the strings, but it was enough to see that there is something
* wrong with my approach in this code.
*/
}
}
}
答案 0 :(得分:1)
以下是一些指导您使您走上正轨的指针
var ExpressionsList = new[] { "bad weather => storm", "happy day => sun" };
考虑是否应该将它们用作字符过滤器;它们可能是,但通常是在令牌生成器可能会错误地令牌化的地方使用字符过滤器,例如
&
时,标准令牌生成器将and
删除c#
标记为c
,理想情况下,我们希望在字符过滤器中保留并替换为csharp
也许您想对字符进行过滤,但是在多单词的情况下,最好用同义词或同义词图来处理。
index
和search
自定义分析器是相同的,您可以删除其中一个。同样,如果未明确设置,则search_analyzer
数据类型字段的text
将是已配置的analyzer
,因此可以简化一些事情。
var SynonymsList = new[] { "big => large, huge", "small => tiny, minuscule", "sun => sunshine, shiny, sunny" };
这是directional synonym map,即左侧的匹配项将被替换,右侧的所有替代项将被替换。如果所有人都应被视为相等的同义词,那么您可能就不需要方向图,即
var SynonymsList = new[]
{
"big, large, huge",
"small, tiny, minuscule",
"sun, sunshine, shiny, sunny"
};
这将返回所有3个文档,
var TestB1 = Client.Search<MyData>(S => S.Query(_ => _.QueryString(F => F.Query("stormy sunny")))).Documents; // expected to return documents 1, 2, 3 because of synonyms: sun => sunny, shiny, sunshine
.Custom("index", C => C .CharFilters("expressions") .Tokenizer("standard") .Filters("synonyms", "standard", "lowercase", "stop") ) .Custom("search", C => C .CharFilters("expressions") .Tokenizer("standard") .Filters("synonyms", "standard", "lowercase", "stop") )
令牌过滤器的顺序很重要,因此您想在小写过滤器之后的 之后运行同义词过滤器
Fuzzy queries是术语级查询,因此查询输入不会进行分析,这意味着如果您针对在索引时间分析的字段运行查询,则模糊查询输入将需要与以下项的术语输出匹配索引时分析出的文档。如果查询输入是将在索引时间标记为多个术语的查询输入,则这可能不会产生正确的结果,即模糊查询输入将被视为一个完整术语,但是目标文档字段的索引时间值可能具有被分为多个术语。
看看《权威指南》中的Fuzziness section-它适用于Elasticsearch 2.x,但在很大程度上仍与更高版本有关。您可能希望使用支持模糊性并在查询时执行分析的全文查询,例如query_string
,match
或multi_match
查询。
将它们放在一起,这是一个在开发时可以使用的示例
public class MyData
{
public string Id;
public string Title;
public string Tags;
}
public static void Main()
{
const string INDEX_NAME = "testindex";
var expressions = new[]
{
"bad weather => storm",
"happy day => sun"
};
var synonyms = new[]
{
"big, large, huge",
"small, tiny, minuscule",
"sun, sunshine, shiny, sunny"
};
// connect
var settings = new ConnectionSettings(new Uri("http://localhost:9200"))
.DefaultIndex(INDEX_NAME)
.DefaultFieldNameInferrer(s => s) // stop the camel case
.DefaultMappingFor<MyData>(m => m.IdProperty("Id"))
.DisableDirectStreaming()
.PrettyJson()
.OnRequestCompleted(callDetails =>
{
if (callDetails.RequestBodyInBytes != null)
{
Console.WriteLine(
$"{callDetails.HttpMethod} {callDetails.Uri} \n" +
$"{Encoding.UTF8.GetString(callDetails.RequestBodyInBytes)}");
}
else
{
Console.WriteLine($"{callDetails.HttpMethod} {callDetails.Uri}");
}
Console.WriteLine();
if (callDetails.ResponseBodyInBytes != null)
{
Console.WriteLine($"Status: {callDetails.HttpStatusCode}\n" +
$"{Encoding.UTF8.GetString(callDetails.ResponseBodyInBytes)}\n" +
$"{new string('-', 30)}\n");
}
else
{
Console.WriteLine($"Status: {callDetails.HttpStatusCode}\n" +
$"{new string('-', 30)}\n");
}
});
var Client = new ElasticClient(settings);
// erase the old index, if any
if (Client.IndexExists(INDEX_NAME).Exists) Client.DeleteIndex(INDEX_NAME);
// create the index
var createIndexResponse = Client.CreateIndex(INDEX_NAME, c => c
.Settings(s => s
.Analysis(a => a
.CharFilters(cf => cf
.Mapping("expressions", E => E
.Mappings(expressions)
)
)
.TokenFilters(tf => tf
.Synonym("synonyms", sy => sy
.Synonyms(synonyms)
.Tokenizer("whitespace")
)
)
.Analyzers(an => an
.Custom("index", ca => ca
.CharFilters("expressions")
.Tokenizer("standard")
.Filters("standard", "lowercase", "synonyms", "stop")
)
)
)
)
.Mappings(m => m
.Map<MyData>(mm => mm
.AutoMap()
.Properties(p => p
.Text(t => t
.Name(n => n.Title)
.Analyzer("index")
)
.Text(t => t
.Name(n => n.Tags)
.Analyzer("index")
)
)
)
)
);
// add some data
var data = new List<MyData>
{
new MyData { Id = "1", Title = "nice stormy weather", Tags = "storm nice" },
new MyData { Id = "2", Title = "a large storm with sunshine", Tags = "storm large sunshine" },
new MyData { Id = "3", Title = "a storm during a sunny day", Tags = "sun storm" }
};
Client.IndexMany(data);
Client.Refresh(INDEX_NAME);
//var query = "stormy sunny";
var query = "stromy sunny";
// var query = "bad weather";
// var query = "a large happy day";
var testA1 = Client.Search<MyData>(s => s
.Query(q => q
.MultiMatch(fu => fu
.Fields(f => f
.Field(ff => ff.Tags)
.Field(ff => ff.Title)
)
.Query(query)
.Fuzziness(Fuzziness.EditDistance(2))
)
)
).Documents;
}
我在连接设置中添加了.DisableDirectStreaming()
,.PrettyJson()
和.OnRequestCompleted(...)
处理程序,以便您可以看到写入控制台的请求和响应。这些在开发过程中很有用,但是您可能希望删除这些产品以增加生产成本。像Linqpad这样的小应用程序将有助于在这里开发:)
该示例使用multi_match
查询,并启用了模糊性,且编辑距离为2(可能想在这里使用自动模糊性,这很有意义),并在Tags
和{{ 1}}字段。返回所有三个文档以进行(misspelt)查询Title