Created
February 24, 2021 16:15
-
-
Save dainiusjocas/c9a2bca9c3870c4c23592d56b7abba2f to your computer and use it in GitHub Desktop.
Phrase query examples when implemented as shingles
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
DELETE /phrases-shingle-example | |
PUT /phrases-shingle-example | |
{ | |
"settings": { | |
"analysis": { | |
"filter": { | |
"my_shingle_filter": { | |
"type": "shingle", | |
"min_shingle_size": 2, | |
"max_shingle_size": 2, | |
"output_unigrams": false | |
} | |
}, | |
"analyzer": { | |
"rebuilt_shingle": { | |
"tokenizer": "standard", | |
"filter": [ | |
"lowercase", | |
"asciifolding", | |
"my_shingle_filter" | |
] | |
} | |
} | |
} | |
}, | |
"mappings": { | |
"properties": { | |
"title": { | |
"type": "text", | |
"analyzer": "standard", | |
"fields": { | |
"shingle": { | |
"type": "text", | |
"analyzer": "rebuilt_shingle" | |
} | |
} | |
} | |
} | |
} | |
} | |
# Have a look at the tokens after analysis | |
POST phrases-shingle-example/_analyze | |
{ | |
"field": "title.shingle", | |
"text": ["Raudona gėlėta suknelė"] | |
} | |
POST /phrases-shingle-example/_doc/1 | |
{"title":"Raudona gėlėta suknelė"} | |
POST /phrases-shingle-example/_doc/2 | |
{"title":"Gėlėta raudona suknelė"} | |
POST /phrases-shingle-example/_doc/3 | |
{"title":"Raudona suknelė"} | |
POST /phrases-shingle-example/_doc/4 | |
{"title":"Raudonos suknelės"} | |
GET phrases-shingle-example/_refresh | |
# two hits | |
GET /phrases-shingle-example/_search | |
{ | |
"query": { | |
"bool": { | |
"must": [ | |
{ | |
"match": { | |
"title.shingle": { | |
"query": "raudona suknele", | |
"_name": "phrase" | |
} | |
} | |
} | |
] | |
} | |
} | |
} | |
# The same two hits despite the fact that "neriniuota" is mentioned | |
GET /phrases-shingle-example/_search | |
{ | |
"query": { | |
"bool": { | |
"must": [ | |
{ | |
"match": { | |
"title.shingle": { | |
"query": "raudona suknele neriniuota", | |
"_name": "phrase" | |
} | |
} | |
} | |
] | |
} | |
} | |
} | |
# No hits at all because of "neriniuota" and "operator and", | |
# which enforces that all tokens from the query must be present in the document | |
GET /phrases-shingle-example/_search | |
{ | |
"query": { | |
"bool": { | |
"must": [ | |
{ | |
"match": { | |
"title.shingle": { | |
"query": "raudona suknele neriniuota", | |
"_name": "phrase", | |
"operator": "and" | |
} | |
} | |
} | |
] | |
} | |
} | |
} | |
# No hits at all because of "neriniuota" and minimum should match | |
# as an alternative to "operator and" | |
GET /phrases-shingle-example/_search | |
{ | |
"query": { | |
"bool": { | |
"must": [ | |
{ | |
"match": { | |
"title.shingle": { | |
"query": "raudona suknele neriniuota", | |
"_name": "phrase", | |
"minimum_should_match": "100%" | |
} | |
} | |
} | |
] | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment