Created
July 18, 2011 09:19
-
-
Save clintongormley/1088986 to your computer and use it in GitHub Desktop.
Create index for partial matching of names in ElasticSearch
This file contains hidden or 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
| # First, create the synonyms file /opt/elasticsearch/name_synonyms.txt | |
| # with the contents: | |
| # | |
| # rob,bob => robert | |
| # | |
| ## CREATE THE INDEX WITH ANALYZERS AND MAPPINGS | |
| curl -XPUT 'http://127.0.0.1:9200/test/?pretty=1' -d ' | |
| { | |
| "mappings" : { | |
| "member" : { | |
| "properties" : { | |
| "location" : { | |
| "type" : "geo_point" | |
| }, | |
| "member_id" : { | |
| "type" : "string", | |
| "analyzer" : "simple" | |
| }, | |
| "birthday" : { | |
| "format" : "yyyy-MM-dd", | |
| "type" : "date" | |
| }, | |
| "last_name" : { | |
| "fields" : { | |
| "metaphone" : { | |
| "type" : "string", | |
| "analyzer" : "name_metaphone" | |
| }, | |
| "partial" : { | |
| "search_analyzer" : "full_name", | |
| "index_analyzer" : "partial_name", | |
| "type" : "string" | |
| }, | |
| "last_name" : { | |
| "type" : "string", | |
| "analyzer" : "full_name" | |
| } | |
| }, | |
| "type" : "multi_field" | |
| }, | |
| "first_name" : { | |
| "fields" : { | |
| "metaphone" : { | |
| "type" : "string", | |
| "analyzer" : "name_metaphone" | |
| }, | |
| "partial" : { | |
| "search_analyzer" : "full_name", | |
| "index_analyzer" : "partial_name", | |
| "type" : "string" | |
| }, | |
| "first_name" : { | |
| "type" : "string", | |
| "analyzer" : "full_name" | |
| } | |
| }, | |
| "type" : "multi_field" | |
| } | |
| } | |
| } | |
| }, | |
| "settings" : { | |
| "analysis" : { | |
| "filter" : { | |
| "name_synonyms" : { | |
| "type" : "synonym", | |
| "synonyms_path" : "/opt/elasticsearch/name_synonyms.txt" | |
| }, | |
| "name_ngrams" : { | |
| "side" : "front", | |
| "max_gram" : 10, | |
| "min_gram" : 1, | |
| "type" : "edgeNGram" | |
| }, | |
| "name_metaphone" : { | |
| "replace" : false, | |
| "encoder" : "metaphone", | |
| "type" : "phonetic" | |
| } | |
| }, | |
| "analyzer" : { | |
| "full_name" : { | |
| "filter" : [ | |
| "standard", | |
| "lowercase", | |
| "asciifolding" | |
| ], | |
| "type" : "custom", | |
| "tokenizer" : "standard" | |
| }, | |
| "name_metaphone" : { | |
| "filter" : [ | |
| "name_metaphone" | |
| ], | |
| "type" : "custom", | |
| "tokenizer" : "standard" | |
| }, | |
| "partial_name" : { | |
| "filter" : [ | |
| "standard", | |
| "lowercase", | |
| "asciifolding", | |
| "name_synonyms", | |
| "name_ngrams" | |
| ], | |
| "type" : "custom", | |
| "tokenizer" : "standard" | |
| } | |
| } | |
| } | |
| } | |
| } | |
| ' | |
| ### INDEX SAMPLE DATA | |
| # [Mon Jul 18 11:50:54 2011] Protocol: http, Server: 192.168.5.103:9200 | |
| curl -XPOST 'http://127.0.0.1:9200/_bulk?pretty=1' -d ' | |
| {"index" : {"_index" : "test", "_type" : "member"}} | |
| {"location" : [51.50853, -0.12574], "member_id" : "ABC-1234", "birthday" : "1970-10-24", "last_name" : "Smith", "first_name" : "Robert"} | |
| {"index" : {"_index" : "test", "_type" : "member"}} | |
| {"location" : [53.41667, -2.25], "member_id" : "ABC-1235", "birthday" : "1975-11-03", "last_name" : "Jones", "first_name" : "Robin"} | |
| {"index" : {"_index" : "test", "_type" : "member"}} | |
| {"location" : [41.3873, 2.1762], "member_id" : "ABC-1235", "birthday" : "1975-11-03", "last_name" : "Sánchez", "first_name" : "Jordi"} | |
| ' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Does this below index configuration correct?
{
"mappings":{
"inventory_record":{
"properties":{
"column_1":{
"fields":{
"metaphone":{ "type":"string", "analyzer":"data_metaphone" },
"partial":{ "search_analyzer":"full_data", "index_analyzer":"partial_data", "type":"string" },
"column_1":{ "type":"string", "analyzer":"full_data" }
}
"type" : "multi_field",
"path": "just_name",
}
}
}
},
"settings":{
"number_of_shards":3,
"analysis":
{
"filter":{
"data_ngrams":
{
"side":"front",
"max_gram":10,
"min_gram":1,
"type":"edgeNGram"
},
"data_metaphone":
{
"replace":false,
"encoder":"metaphone",
"type":"phonetic"
}
},
"analyzer":{
"full_data":
{
"filter":[
"standard",
"lowercase",
"asciifolding"
],
"type":"custom",
"tokenizer":"standard"
},
"data_metaphone":{
"filter":[
"data_metaphone"
],
"type":"custom",
"tokenizer":"standard"
},
"partial_data":{
"filter":[
"standard",
"lowercase",
"asciifolding",
"data_ngrams"
],
"type":"custom",
"tokenizer":"standard"
}
}
}
}
}