Can you suggest how do I build a query based on multiple filter.
Currently, I want to implement a search functionality using the following filters:
ProductName
Countries (array)
Cities (array)
The requirements is that, when counties or cities has no selected value, the query assumes that you are searching all countries and cities.
If there are selected counties and cities, then the result should be base on the selected counties and cities.
I have the query below to start with.
static void Main(string[] args)
{
var uri = new Uri("http://localhost:9200");
var connectionPool = new SingleNodeConnectionPool(uri);
var settings = new ConnectionSettings(connectionPool);
var client = new ElasticClient(settings);
if (counties.Count > 0)
{
foreach(string country in counties)
{
// Add a query to be added in client.Search
}
}
if (cities.Count > 0)
{
foreach(string city in cities)
{
// Add a query to be added in client.Search
}
}
client.Search<Product>(s => s
.Query(q => q
.Bool(b => b
.Must(mu => mu
.Match(m => m
.Field(f => f.ProductName)
.Query("some text")
),
.
)
)
)
);
}
I just answer my own question. Currently, I came with this approach.
var sd = new SearchDescriptor<object>();
var qc = new QueryContainer();
var qd = new QueryContainerDescriptor<object>();
sd.From(0);
sd.Size(100);
sd.Index("Products");
sd.Type("Product");
if (!string.IsNullOrEmpty(title))
{
qc = qd.Match(m1 => m1
.Field("title")
.Query(title)
);
}
if (countries.Count > 0)
{
qc = qd.Terms(t => t
.Field("country")
.Terms(countries.ToArray())
);
}
if (cities.Count > 0)
{
qc = qd.Terms(t => t
.Field("city")
.Terms(cities.ToArray())
);
}
sd.Query(q => q
.Bool(b => b
.Must(qc)
)
);
var result = client.Search<object>(s => s = sd);
You can use the terms query:
{
"query": {
"bool": {
"must": [
{ "match": { "field": "productName", "query": "some text"}},
// Only add this filter if the array is not empty
{ "terms": { "Country": ["Canada", "France"]}},
// Same here
{ "terms": { "City": ["Ottawa", "Paris"]}},
]
}
}
}
Related
I have a query and want to do a search by multiple fields in case if no result by uuid need to do the same by parentUuid:
C# query:
return new NestedQuery
{
Path = Infer.Field<ElasticDocument>(t => t.KeywordFields),
Query = new BoolQuery
{
Filter = new List<QueryContainer>
{
new TermsQuery
{
Field = Infer.Field<ElasticDocument>(t => t.KeywordFields),
Terms = new List<string>
{
"term2"
},
Boost = 10
}
},
Should = new List<QueryContainer>
{
new TermQuery
{
Field = Infer.Field<ElasticDocument>(t => t.KeywordFields.First().UUID),
Value = filter.UUID
},
new TermQuery
{
Field = Infer.Field<ElasticDocument>(t => t.KeywordFields.First().ParentUUID),
Value = filter.UUID
},
}
}
};
example of documents:
"keywordFields": [
{
"value": "term1",
"uuid": "bf18ee9f-7592-488d-7985-2b9fe8b878ca",
"parentUUID": null
},
{
"value": "term2",
"uuid": "079205ed-30df-08f6-02a1-9caf093c3be0",
"parentUUID": "103d6061-cb99-4fba-8118-2ea501e4425d"
}
]
How to update the query to use or condition in case if no result by 'UUID' then let's do it by ParentUUID?
Try to combine bool query:
nested1 = new NestedQuery {
Path = Infer.Field<ElasticDocument>(t => t.KeywordFields),
Query = new BoolQuery {
Filter = new List<QueryContainer>
{
new TermsQuery {
Field = Infer.Field<ElasticDocument>(t => t.KeywordFields),
Terms = new List<string>
{
"term2"
},
Boost = 10
}
}
}
};
nested2 = new NestedQuery {
Path = Infer.Field<ElasticDocument>(t => t.KeywordFields),
Query = new BoolQuery {
Filter = new List<QueryContainer>
{
new TermsQuery {
Field = Infer.Field<ElasticDocument>(t => t.KeywordFields),
Terms = new List<string>
{
"term2"
},
Boost = 10
}
},
Should = new List<QueryContainer>
{
new BoolQuery {
MustNot = new List<QueryContainer> {
new TermQuery
{
Field = Infer.Field<ElasticDocument>(t => t.KeywordFields.First().UUID),
Value = filter.UUID
}
},
Must = new List<QueryContainer> {
new TermQuery
{
Field = Infer.Field<ElasticDocument>(t => t.KeywordFields.First().parentUUID),
Value = filter.UUID
}
}
}
}
}
};
And should nested1 with nested2
note: not IDE for this edit, the nested2 query could be simplify for sure.
We are using a filter as per following:
filters.Add(fq => fq
.Term(t => t
.Field(f => f.LocalityId)
.Value(locationParams[2])) || fq
.GeoShape(g => g
.Field("locationShape")
.Relation(GeoShapeRelation.Within)
.IndexedShape(f => f
.Id(searchCriteria.spLocationId)
.Index(indexName)
.Path("geometry")
)
)
);
However, if the geometry field is missing, Elasticsearch throws an exception.
Is there anyway to avoid this by using a default (Null Value) in the mapping or any other way.
It is not possible to avoid the exception in this case. Elasticsearch assumes that the parameters that the user provides to a pre-indexed shape are valid.
Ideally, the values supplied to the indexed shape should be constrained in a manner that prevents an end user from supplying invalid values. If that is unfeasible, you could run a bool query with filter clauses of exists query and ids query on the indexName index before adding the indexed shape geoshape query filter to the search request.
For example
private static void Main()
{
var documentsIndex = "documents";
var shapesIndex = "shapes";
var host = "localhost";
var pool = new SingleNodeConnectionPool(new Uri($"http://{host}:9200"));
var settings = new ConnectionSettings(pool)
.DefaultMappingFor<Document>(m => m.IndexName(documentsIndex))
.DefaultMappingFor<Shape>(m => m.IndexName(shapesIndex));
var client = new ElasticClient(settings);
if (client.Indices.Exists(documentsIndex).Exists)
client.Indices.Delete(documentsIndex);
client.Indices.Create(documentsIndex, c => c
.Map<Document>(m => m
.AutoMap()
)
);
if (client.Indices.Exists(shapesIndex).Exists)
client.Indices.Delete(shapesIndex);
client.Indices.Create(shapesIndex, c => c
.Map<Shape>(m => m
.AutoMap()
)
);
client.Bulk(b => b
.IndexMany(new [] {
new Document
{
Id = 1,
LocalityId = 1,
LocationShape = GeoWKTReader.Read("POLYGON ((30 20, 20 15, 20 25, 30 20))")
},
new Document
{
Id = 2,
LocalityId = 2
},
})
.IndexMany(new []
{
new Shape
{
Id = 1,
Geometry = GeoWKTReader.Read("POLYGON ((20 35, 10 30, 10 10, 30 5, 45 20, 20 35))")
}
})
.Refresh(Refresh.WaitFor)
);
var shapeId = 1;
var searchResponse = client.Search<Shape>(s => s
.Size(0)
.Query(q => +q
.Ids(i => i.Values(shapeId)) && +q
.Exists(e => e.Field("geometry"))
)
);
Func<QueryContainerDescriptor<Document>, QueryContainer> geoShapeQuery = q => q;
if (searchResponse.Total == 1)
geoShapeQuery = q => +q
.GeoShape(g => g
.Field("locationShape")
.Relation(GeoShapeRelation.Within)
.IndexedShape(f => f
.Id(shapeId)
.Index(shapesIndex)
.Path("geometry")
)
);
client.Search<Document>(s => s
.Query(q => +q
.Term(t => t
.Field(f => f.LocalityId)
.Value(2)
) || geoShapeQuery(q)
)
);
}
public class Document
{
public int Id { get; set; }
public int LocalityId { get; set; }
public IGeoShape LocationShape { get; set; }
}
public class Shape
{
public int Id { get; set; }
public IGeoShape Geometry { get; set; }
}
If var shapeId = 1; is changed to var shapeId = 2; then the geoshape query is not added to the filter clauses when searching on the documents index.
I try to build an elasticsearch request with a must and a should request
my target request is this bellow:
POST /index/type/_search
{
"query": {
"bool" : {
"must" : {
"match":{"field1":{"query":"word1"}}
},
"should":{
"match":{"field2":{"query":"word2"}}
}
}
}}
I wrote:
var queryContainer = new QueryContainer();
queryContainer &= new MatchQuery() { Field = "field1", Query = "word1" };
queryContainer |= new MatchQuery() { Field = "field2", Query = "word2"};
var searchRequest = new SearchRequest<type>
{
Query = queryContainer
};
but it produces me :
POST /index/type/_search
{
"query":{
"bool":{
"should":[
{"match":{"field1":{"query":"word1"}}},
{"match":{"field2":{"query":"word2"}}}]
}
}
}
Do you know what should I write when building my QueryContainer?
Using operator overloading here is not that helpful; I think in this case, constructing the bool query is clearer
Object Initializer Syntax
var searchRequest = new SearchRequest<Document>()
{
Query = new BoolQuery
{
Must = new QueryContainer[] { new MatchQuery() { Field = "field1", Query = "word1" } },
Should = new QueryContainer[] { new MatchQuery() { Field = "field2", Query = "word2" } }
}
};
client.Search<Document>(searchRequest);
or Fluent API
client.Search<Document>(s => s
.Query(q => q
.Bool(b => b
.Must(fi => fi
.Match(m => m
.Field("field2")
.Query("word2")
)
)
.Should(sh => sh
.Match(m => m
.Field("field1")
.Query("word1")
)
)
)
)
);
I have 2 Types in one index and both have Suggest field (as required )
public class LegalAreaSearchModel : LegalAreaModel
{
public SuggestField Suggest
{
get
{
List<string> input = new List<string>();
string[] childArea = !string.IsNullOrEmpty(this.LegalArea) ? this.LegalArea.Split(' ') : new string[] { "" };
string[] ParentArea = !string.IsNullOrEmpty(this.Parent) ? this.Parent.Split(' ') : new string[] { "" };
input.AddRange(childArea);
input.AddRange(ParentArea);
return
new SuggestField
{
Input = input,
Output = this.LegalArea,
Payload = new
{
Id = this.RowId,
Name = !string.IsNullOrEmpty(this.Parent) ? this.Parent + "/" + this.LegalArea : this.LegalArea,
Type = "Specialization"
},
Weight = !string.IsNullOrEmpty(this.LegalArea) ? this.LegalArea.Length : 0
};
}
}
}
AND
public class LegalDocumentSearchModel : LegalDocumentModel
{
public LegalDocumentSearchModel()
{
//this = ObjectCopier.Clone<LegalDocumentSearchModel>(legalDocumentSearchModel);
SupplierDetails = new List<LegalDocumentSupplierDetailForSearch>();
CategoryDetails = new List<CategoryDetails>();
}
[Nested()]
public List<LegalDocumentSupplierDetailForSearch> SupplierDetails { get; set; }
[Nested()]
public List<CategoryDetails> CategoryDetails { get; set; }
public SuggestField Suggest
{
get
{
return
new SuggestField
{
Input = new List<string>(!string.IsNullOrEmpty(this.Name) ? this.Name.Split(' ') : new string[] { "" }) { this.Name },
Output = this.Name,
Payload = new
{
Id = this.RowId,
SEOFriendlyURLName = !string.IsNullOrEmpty(this.SEOFriendlyURLName) ? string.Concat(this.SEOFriendlyURLName) : string.Empty,
Name = this.Name,
ProductType = this.ProductType,
Description = this.Description
},
Weight = !string.IsNullOrEmpty(this.Description) ? this.Description.Length : 0
};
}
}
}
public class LegalDocumentSupplierDetailForSearch
{
public string PinCode { get; set; }
public string Lattitude { get; set; }
public string Longitude { get; set; }
}
public class CategoryDetails
{
public int CategoryId { get; set; }
public string CategoryName { get; set; }
}
now my search is as follows
List<AdvocateListingSuggestionModel> lsResult = new List<AdvocateListingSuggestionModel>();
var result = _searchProvider.Client.Suggest<LegalAreaSearchModel>(s => s
.Index(SearchConfigurationManager.DefaultSearchIndex)
.Completion("ml-la-suggestions", c => c
.Text(Search)
.Field(p => p.Suggest)
.Fuzzy(fz => fz
.Fuzziness(Fuzziness.Auto))
)
);
I am getting result from other type as well(mix) of both how can we restrict result from only one type
Type1.LegalAreaSearchModel
Type 2.LegalDocumentSearchModel
my index creation is as follows
public static bool CheckForIndex(ElasticSearchProvider searchProvider)
{
Nest.IndexExistsRequest idr = new Nest.IndexExistsRequest(Nest.Indices.Index(new Nest.IndexName() { Name = SearchConfigurationManager.DefaultSearchIndex }));
var indxres = searchProvider.Client.IndexExists(idr);
if (!indxres.Exists)
{
searchProvider.Client.CreateIndex(SearchConfigurationManager.DefaultSearchIndex, i => i
.Settings(s => s
.NumberOfShards(2)
.NumberOfReplicas(0)
.Analysis(analysis => analysis
.Tokenizers(tokenizers => tokenizers
.Pattern("ml-id-tokenizer", p => p.Pattern(#"\W+"))
)
.TokenFilters(tokenfilters => tokenfilters
.WordDelimiter("ml-id-words", wd => wd
.SplitOnCaseChange()
.PreserveOriginal()
.SplitOnNumerics()
.GenerateNumberParts(false)
.GenerateWordParts()
)
)
.Analyzers(analyzers => analyzers
.Custom("ml-id-analyzer", c => c
.Tokenizer("ml-id-tokenizer")
.Filters("ml-id-words", "lowercase")
)
.Custom("ml-id-keyword", c => c
.Tokenizer("keyword")
.Filters("lowercase")
)
)
)
));
}
return true;
}
Creatining Document Type as follows
public bool CreateDocumentIndex()
{
bool retVal = false;
if (Common.CheckForIndex(_searchProvider))
{
var res = _searchProvider.Client.Map<LegalDocumentSearchModel>(m =>
m.Index(SearchConfigurationManager.DefaultSearchIndex)
.Type(this.type)
.AutoMap()
.Properties(ps => ps
.String(s => s
.Name(p => p.Id)
.Analyzer("ml-id-analyzer")
.Fields(f => f
.String(p => p.Name("keyword").Analyzer("ml-id-keyword"))
.String(p => p.Name("raw").Index(FieldIndexOption.NotAnalyzed))
)
)
.Completion(c => c
.Name(p => p.Suggest)
.Payloads()
)
));
retVal = res.IsValid;
}
return retVal;
}
creating LegalArea Type as follows
public bool CreateLegalAreaIndex()
{
bool retVal = false;
if (Common.CheckForIndex(_searchProvider))
{
var res = _searchProvider.Client.Map<LegalAreaSearchModel>(m =>
m.Index(SearchConfigurationManager.DefaultSearchIndex)
.Type(this.type)
.AutoMap()
.Properties(ps => ps
.String(s => s
.Name(p => p.Id)
.Analyzer("ml-id-analyzer")
.Fields(f => f
.String(p => p.Name("keyword").Analyzer("ml-id-keyword"))
.String(p => p.Name("raw").Index(FieldIndexOption.NotAnalyzed))
)
)
.Completion(c => c
.Name(p => p.Suggest)
.Payloads()
)
));
retVal = res.IsValid;
}
return retVal;
}
now when i am running legal area suggestions as follows
public List<AdvocateListingSuggestionModel> LegalAreaSuggestion(string Search)
{
List<AdvocateListingSuggestionModel> lsResult = new List<AdvocateListingSuggestionModel>();
var result = _searchProvider.Client.Suggest<LegalAreaSearchModel>(s => s
.Index(SearchConfigurationManager.DefaultSearchIndex)
.Completion("ml-la-suggestions", c => c
.Text(Search)
.Field(p => p.Suggest)
.Fuzzy(fz => fz
.Fuzziness(Fuzziness.Auto))
)
);
if (result.IsValid)
{
lsResult = result.Suggestions["ml-la-suggestions"]
.FirstOrDefault()
.Options
.Select(suggest => suggest.Payload<AdvocateListingSuggestionModel>()).ToList();
}
return lsResult;
}
I am getting results of LegalDocumentSearchModel as well.pls advise
Thanks
Suggesters work at the index level, that is, one Finite State Transducer (FST) is created for a field per index so if you have two types with the same field name in the same index (both fields must be of the same type), both types will have data represented in the one FST.
We can see this with a simple example. Here we have two types with completion fields that we're going to index into the same index
public class Band
{
public int Id { get; set;}
public CompletionField<object> Suggest { get; set;}
}
public class Sport
{
public int Id { get; set;}
public CompletionField<object> Suggest { get; set; }
}
void Main()
{
var pool = new SingleNodeConnectionPool(new Uri("http://localhost:9200"));
var defaultIndex = "default-index";
var connectionSettings = new ConnectionSettings(pool)
.DefaultIndex(defaultIndex);
var client = new ElasticClient(connectionSettings);
// just so we can re-run this example...
if (client.IndexExists(defaultIndex).Exists)
client.DeleteIndex(defaultIndex);
client.CreateIndex(defaultIndex, ci => ci
.Mappings(m => m
.Map<Band>(l => l
.AutoMap()
.Properties(p => p
.Completion(c => c
.Name(n => n.Suggest)
)
)
)
.Map<Sport>(l => l
.AutoMap()
.Properties(p => p
.Completion(c => c
.Name(n => n.Suggest)
)
)
)
)
);
var bands = new List<Band>
{
new Band { Id = 1, Suggest = new CompletionField<object> { Input = new [] {"Bowling for Soup"} } },
new Band { Id = 2, Suggest = new CompletionField<object> { Input = new [] {"Fastball"} } },
new Band { Id = 3, Suggest = new CompletionField<object> { Input = new [] {"Dropkick Murphys"} } },
new Band { Id = 4, Suggest = new CompletionField<object> { Input = new [] {"Yellowcard"} } },
new Band { Id = 5, Suggest = new CompletionField<object> { Input = new [] {"American Football"} } },
};
client.IndexMany(bands);
var sports = new List<Sport>
{
new Sport { Id = 1, Suggest = new CompletionField<object> { Input = new [] {"Bowling"} } },
new Sport { Id = 2, Suggest = new CompletionField<object> { Input = new [] {"Football"} } },
new Sport { Id = 3, Suggest = new CompletionField<object> { Input = new [] {"Baseball"} } },
new Sport { Id = 4, Suggest = new CompletionField<object> { Input = new [] {"Table Tennis"} } },
new Sport { Id = 5, Suggest = new CompletionField<object> { Input = new [] {"American Football"} } },
};
client.IndexMany(sports);
client.Refresh(defaultIndex);
var suggestResponse = client.Suggest<Band>(s => s
.Completion("suggestion", cs => cs
.Text("Bo")
.Field(f => f.Suggest)
)
);
}
We get back the following from our suggest call
{
"_shards" : {
"total" : 5,
"successful" : 5,
"failed" : 0
},
"suggestion" : [ {
"text" : "Bo",
"offset" : 0,
"length" : 2,
"options" : [ {
"text" : "Bowling",
"score" : 1.0
}, {
"text" : "Bowling for Soup",
"score" : 1.0
} ]
} ]
}
We get a suggestion of both a Band type and a Sport type in the results. Perhaps not what we expected or wanted, but that's how suggesters work. Note that in the .Suggest<T>() call, the type T is used to provide strongly typed access to properties that may be used in the query. In this example, the .Suggest field of type Band.
The recommended solution here is to have separate indices for different types; you can still query across multiple indices when you need to and avoid the pitfalls that can come with having multiple types in the same index.
With that aside, you can get this to work by using a Context Suggester and taking advantage of category context for the completion type mapping. Ideally, you want to use a field that exists within the document for the category to afford you flexibility in the category, but you can however use a metadata field if you want to. I recommend investigating and researching approaches for your domain.
With our previous example, if we now include category context in the mapping (same code as before but with this updated mapping)
client.CreateIndex(defaultIndex, ci => ci
.Mappings(m => m
.Map<Band>(l => l
.AutoMap()
.Properties(p => p
.Completion(c => c
.Name(n => n.Suggest)
.Context(sc => sc
.Category("type", csc => csc
// recommend that you use another field on
// the document here instead of a metadata field
.Field("_type")
)
)
)
)
)
.Map<Sport>(l => l
.AutoMap()
.Properties(p => p
.Completion(c => c
.Name(n => n.Suggest)
.Context(sc => sc
.Category("type", csc => csc
// recommend that you use another field on
// the document here instead of a metadata field
.Field("_type")
)
)
)
)
)
)
);
And use category context whilst searching
var suggestResponse = client.Suggest<Band>(s => s
.Completion("suggestion", cs => cs
.Text("Bo")
.Field(f => f.Suggest)
.Context(d => d.Add("type", "band"))
)
);
then we get the desired result
{
"_shards" : {
"total" : 5,
"successful" : 5,
"failed" : 0
},
"suggestion" : [ {
"text" : "Bo",
"offset" : 0,
"length" : 2,
"options" : [ {
"text" : "Bowling for Soup",
"score" : 1.0
} ]
} ]
}
I am writing a query in nest for elasticsearch that matches to a list of countries - it cutrrently matches whenever any of the countries in the list is present in ESCountryDescription (a list of countries). I only want to match when all of the countries in CountryList match ESCountryDescription. I believe that I need to use MinimumShouldMatch as in this example http://www.elastic.co/guide/en/elasticsearch/reference/0.90/query-dsl-terms-query.html
a.Terms(t => t.ESCountryDescription, CountryList)
But I cannot find a way of adding MinimumShouldMatch into my query above.
You can apply MinimumShouldMatch patameter in TermsDescriptor. Here is an example:
var lookingFor = new List<string> { "netherlands", "poland" };
var searchResponse = client.Search<IndexElement>(s => s
.Query(q => q
.TermsDescriptor(t => t.OnField(f => f.Countries).MinimumShouldMatch("100%").Terms(lookingFor))));
or
var lookingFor = new List<string> { "netherlands", "poland" };
var searchResponse = client.Search<IndexElement>(s => s
.Query(q => q
.TermsDescriptor(t => t.OnField(f => f.Countries).MinimumShouldMatch(lookingFor.Count).Terms(lookingFor))));
And this is the whole example
class Program
{
public class IndexElement
{
public int Id { get; set; }
[ElasticProperty(Index = FieldIndexOption.NotAnalyzed)]
public List<string> Countries { get; set; }
}
static void Main(string[] args)
{
var indexName = "sampleindex";
var uri = new Uri("http://localhost:9200");
var settings = new ConnectionSettings(uri).SetDefaultIndex(indexName).EnableTrace(true);
var client = new ElasticClient(settings);
client.DeleteIndex(indexName);
client.CreateIndex(
descriptor =>
descriptor.Index(indexName)
.AddMapping<IndexElement>(
m => m.MapFromAttributes()));
client.Index(new IndexElement {Id = 1, Countries = new List<string> {"poland", "germany", "france"}});
client.Index(new IndexElement {Id = 2, Countries = new List<string> {"poland", "france"}});
client.Index(new IndexElement {Id = 3, Countries = new List<string> {"netherlands"}});
client.Refresh();
var lookingFor = new List<string> { "germany" };
var searchResponse = client.Search<IndexElement>(s => s
.Query(q => q
.TermsDescriptor(t => t.OnField(f => f.Countries).MinimumShouldMatch("100%").Terms(lookingFor))));
}
}
Regarding your problem
For terms: "netherlands" you will get document with Id 3
For terms: "poland" and "france" you will get documents with Id 1 and 2
For terms: "germany" you will get document with Id 1
For terms: "poland", "france" and "germany" you will get document
with Id 1
I hope this is your point.
Instead of doing
.Query(q => q
.Terms(t => t.ESCountryDescription, CountryList))
You can use the command below
.Query(q => q
.TermsDescriptor(td => td
.OnField(t => t.ESCountryDescription)
.MinimumShouldMatch(x)
.Terms(CountryList)))
See this for unit tests in elasticsearch-net Github repository.