Jordan Lewallen
Reputation: 1851
Elasticsearch ngram tokenizer returns all results regardless of query input
I am trying to build a query to search for records in the following format: TR000002_1_2020.
Users should be able to search for results the following ways:
TR000002 or 2_1_2020 or TR000002_1_2020 or 2020. I figured an ngram tokenization query would be best suited for my needs. I am using Elasticsearch 6.8 so I cannot use the built in Search-As-You-Type introduced in E7.
Here's my implementation I followed from docs here. The only thing I modified was EdgeNGram -> NGram as the user can search from any point of the text.
My Analysis block looks like this:
.Analysis(a => a
.Analyzers(aa => aa
.Custom("autocomplete", ca => ca
.Tokenizer("autocomplete")
.Filters(new string[] {
"lowercase"
})
)
.Custom("autocomplete_search", ca => ca
.Tokenizer("lowercase")
)
)
.Tokenizers(t => t
.NGram("autocomplete", e => e
.MinGram(2)
.MaxGram(16)
.TokenChars(new TokenChar[] {
TokenChar.Letter,
TokenChar.Digit,
TokenChar.Punctuation,
TokenChar.Symbol
})
)
)
)
Then in my mapping I define:
.Text(t => t
.Name(tr => tr.TestRecordId)
.Analyzer("autocomplete")
.SearchAnalyzer("autocomplete_search")
)
When I search for TR000002, my query returns all results instead of just the records that contain those specific characters. What am I doing wrong? Is there a better tokenizer for this specific use case? Thanks!
EDIT: Here's a sample of what is returned:
{
"took" : 5,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : 27,
"max_score" : 0.105360515,
"hits" : [
{
"_index" : "test-records-development-09-09-2020-02-00-00",
"_type" : "testrecorddto",
"_id" : "3",
"_score" : 0.105360515,
"_source" : {
"id" : 3,
"testRecordId" : "TR000002_1_2020",
"type" : 0,
"typeName" : "TIDCo60",
"missionId" : 1,
"mission" : {
"missionId" : 1,
"name" : "[REDACTED]",
"mRPLUsername" : "[REDACTED]",
"missionRadiationPartsLead" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"missionInstruments" : [
{
"missionId" : 1,
"instrumentId" : 1,
"cognizantEngineerUsername" : "[REDACTED]",
"instrument" : {
"intstrumentId" : 1,
"name" : "Instrument"
},
"cognizantEngineer" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
}
},
{
"missionId" : 1,
"instrumentId" : 2,
"instrument" : {
"intstrumentId" : 2,
"name" : "Instrument 2"
}
}
]
},
"procurementPartId" : 2,
"procurementPart" : {
"procurementPartId" : 2,
"partNumber" : "procurement part",
"part" : {
"partId" : 1,
"manufacturer" : "Texas Instruments",
"genericPartNumber" : "123",
"description" : "description",
"partTechnology" : "Part Tech"
}
},
"testStatusId" : 12,
"testStatus" : {
"testStatusId" : 12,
"name" : "Complete: Postponed Until Further Notice"
},
"discriminator" : "SingleEventEffectsRecord",
"testRecordServiceOrders" : [
{
"testRecordId" : 3,
"serviceOrderId" : 9,
"serviceOrder" : {
"serviceOrderId" : 9,
"serviceOrderNumber" : "105702"
}
}
],
"rtdbFiles" : [ ],
"personnelGroups" : [
{
"personnelGroupUsers" : [ ]
},
{
"personnelGroupUsers" : [ ]
}
],
"testRecordTestSubTypes" : [ ],
"testRecordTestFacilityConditions" : [ ],
"testRecordFollowers" : [ ],
"isDeleted" : false,
"sEETestRates" : [ ]
}
},
{
"_index" : "test-records-development-09-09-2020-02-00-00",
"_type" : "testrecorddto",
"_id" : "11",
"_score" : 0.105360515,
"_source" : {
"id" : 11,
"testRecordId" : "TR000011_1_2020",
"type" : 0,
"typeName" : "TIDCo60",
"missionId" : 1,
"mission" : {
"missionId" : 1,
"name" : "[REDACTED]",
"mRPLUsername" : "[REDACTED]",
"missionRadiationPartsLead" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"missionInstruments" : [
{
"missionId" : 1,
"instrumentId" : 1,
"cognizantEngineerUsername" : "[REDACTED]",
"instrument" : {
"intstrumentId" : 1,
"name" : "Instrument"
},
"cognizantEngineer" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
}
},
{
"missionId" : 1,
"instrumentId" : 2,
"instrument" : {
"intstrumentId" : 2,
"name" : "Instrument 2"
}
}
]
},
"procurementPartId" : 2,
"procurementPart" : {
"procurementPartId" : 2,
"partNumber" : "procurement part",
"part" : {
"partId" : 1,
"manufacturer" : "Texas Instruments",
"genericPartNumber" : "123",
"description" : "description",
"partTechnology" : "Part Tech"
}
},
"testStatusId" : 1,
"testStatus" : {
"testStatusId" : 1,
"name" : "Active"
},
"discriminator" : "TotalIonizingDoseRecord",
"creatorUsername" : "[REDACTED]",
"creator" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"testRecordServiceOrders" : [ ],
"partLDC" : "12",
"waferLot" : "1",
"rtdbFiles" : [ ],
"personnelGroups" : [
{
"personnelGroupUsers" : [ ]
}
],
"testRecordTestSubTypes" : [ ],
"testRecordTestFacilityConditions" : [ ],
"testRecordFollowers" : [ ],
"isDeleted" : false,
"testStartDate" : "2020-07-30T00:00:00",
"actualCompletionDate" : "2020-07-31T00:00:00"
}
},
{
"_index" : "test-records-development-09-09-2020-02-00-00",
"_type" : "testrecorddto",
"_id" : "17",
"_score" : 0.105360515,
"_source" : {
"id" : 17,
"testRecordId" : "TR000017_1_2020",
"type" : 0,
"typeName" : "TIDCo60",
"missionId" : 1,
"mission" : {
"missionId" : 1,
"name" : "[REDACTED]",
"mRPLUsername" : "[REDACTED]",
"missionRadiationPartsLead" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"missionInstruments" : [
{
"missionId" : 1,
"instrumentId" : 1,
"cognizantEngineerUsername" : "[REDACTED]",
"instrument" : {
"intstrumentId" : 1,
"name" : "Instrument"
},
"cognizantEngineer" : {
"username" : "lewallen",
"displayName" : "[REDACTED]"
}
},
{
"missionId" : 1,
"instrumentId" : 2,
"instrument" : {
"intstrumentId" : 2,
"name" : "Instrument 2"
}
}
]
},
"procurementPartId" : 2,
"procurementPart" : {
"procurementPartId" : 2,
"partNumber" : "procurement part",
"part" : {
"partId" : 1,
"manufacturer" : "Texas Instruments",
"genericPartNumber" : "123",
"description" : "description",
"partTechnology" : "Part Tech"
}
},
"testStatusId" : 1,
"testStatus" : {
"testStatusId" : 1,
"name" : "Active"
},
"discriminator" : "TotalIonizingDoseRecord",
"creatorUsername" : "[REDACTED]",
"creator" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"testRecordServiceOrders" : [ ],
"rtdbFiles" : [ ],
"personnelGroups" : [
{
"personnelGroupUsers" : [ ]
}
],
"testRecordTestSubTypes" : [ ],
"testRecordTestFacilityConditions" : [ ],
"testRecordFollowers" : [ ],
"isDeleted" : false
}
},
Also here's what shows for mapping:
"testRecordId" : {
"type" : "text",
"analyzer" : "autocomplete",
"search_analyzer" : "autocomplete_search"
},
I guess I should also mention, I've been testing this query in the console like so:
GET test-records-development/_search
{
"query": {
"match": {
"testRecordId": {
"query": "TR000002_1_2020"
}
}
}
}
EDIT 2: Added API response from index _settings endpoint:
{
"test-records-development-09-09-2020-02-00-00" : {
"settings" : {
"index" : {
"number_of_shards" : "5",
"provided_name" : "test-records-development-09-09-2020-02-00-00",
"creation_date" : "1599617013874",
"analysis" : {
"analyzer" : {
"autocomplete" : {
"filter" : [
"lowercase"
],
"type" : "custom",
"tokenizer" : "autocomplete"
},
"autocomplete_search" : {
"type" : "custom",
"tokenizer" : "lowercase"
}
},
"tokenizer" : {
"autocomplete" : {
"token_chars" : [
"letter",
"digit",
"punctuation",
"symbol"
],
"min_gram" : "2",
"type" : "ngram",
"max_gram" : "16"
}
}
},
"number_of_replicas" : "0",
"uuid" : "FSeCa0YwRCOJVbjfxYGkig",
"version" : {
"created" : "6080199"
}
}
}
}
}
Upvotes: 0
Views: 583
Answers (1)
Amit
Reputation: 32376
As I don't have the analyzer setting access in JSON format,I can't confirm it but most probably issue is with your search analyzer autocomplete_search which is creating search time tokens which are matching the index time tokens.
For example: you are searching for TR000002_1_2020 and if it creates 2020 as a token and for document containing TR000011_1_2020 also creates a 2020 token than your query will match it.
You can use the analyze API to check the generated tokens based on a analyzer and as mentioned earlier mostly there is some tokens which are matching as shown above.
Upvotes: 1
Related Questions
- elasticsearch ngram analyzer/tokenizer not working?
- Can't get proper result from elasticsearch based on query and document tokenization
- Token Chars Mapping to Ngram Filter ElasticSearch NEST
- Query elasticsearch to make all analyzed ngram tokens to match
- Elasticsearch - Analyser creating the right tokens but query is not matching
- Ngram Tokenizer on field, not on query
- ElasticSearch does not respect Max NGram length while using NGram Tokenizer
- issue with edge_ngram tokenizer IN Elastic search
- ElasticSearch - Problems with edgeNGram tokenizer
- Elasticsearch index tokenizer keyword not working