Created
March 20, 2023 08:54
-
-
Save kid-cavaquinho/c5099781136a425aa3e43ce570bd8c7a to your computer and use it in GitHub Desktop.
elasticsearch normalizer and analyzers
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
PUT index-test | |
{ | |
"settings": { | |
"analysis": { | |
"normalizer": { | |
"my_normalizer": { | |
"type": "custom", | |
"char_filter": [], | |
"filter": ["lowercase", "asciifolding"] | |
} | |
} | |
} | |
}, | |
"mappings": { | |
"properties": { | |
"foo": { | |
"type": "keyword", | |
"normalizer": "my_normalizer" | |
} | |
} | |
} | |
} | |
PUT /test_index | |
{ | |
"settings": { | |
"index": { | |
"analysis": { | |
"filter": { | |
"my_graph_synonyms": { | |
"type": "synonym_graph", | |
"synonyms": [ | |
"baaar, bar" | |
] | |
} | |
}, | |
"analyzer": { | |
"custom_index_time_analyzer": { | |
"tokenizer": "keyword", | |
"filter": [ | |
"lowercase", | |
"stemmer", | |
"asciifolding" | |
] | |
}, | |
"search_index_time_analyzer": { | |
"tokenizer": "keyword", | |
"filter": [ | |
"lowercase", | |
"stemmer", | |
"asciifolding", | |
"my_graph_synonyms" | |
] | |
} | |
} | |
} | |
} | |
}, | |
"mappings": { | |
"properties": { | |
"foo": { | |
"type": "text", | |
"analyzer": "custom_index_time_analyzer", | |
"search_analyzer": "search_index_time_analyzer" | |
} | |
} | |
} | |
} | |
POST test_index/_bulk | |
{"index":{"_id":"1"}} | |
{"foo":"bar"} | |
{"index":{"_id":"2"}} | |
{"foo":"Bar"} | |
{"index":{"_id":"3"}} | |
{"foo":"zas"} | |
{"index":{"_id":"4"}} | |
{"foo":"pas"} | |
{"index":{"_id":"5"}} | |
{"foo":"tas"} | |
{"index":{"_id":"6"}} | |
{"foo":"barry"} | |
{"index":{"_id":"7"}} | |
{"foo":"bãr"} | |
POST test_index/_refresh | |
# outputs 2 results | |
GET test_index/_search | |
{ | |
"query": { | |
"term": { | |
"foo": "bar" | |
} | |
} | |
} | |
#outputs 2 results using synonym graph | |
GET test_index/_search | |
{ | |
"query": { | |
"match": { | |
"foo": "baaar" | |
} | |
} | |
} | |
#outputs 2 results | |
GET test_index/_search | |
{ | |
"query": { | |
"match_phrase": { | |
"foo": { | |
"query": "bar" | |
} | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment