Created
September 10, 2013 00:58
-
-
Save scottrice10/6503652 to your computer and use it in GitHub Desktop.
Here is a mapping I used to index ~75,000 health provider documents from npiapi.com, a web service providing NPI health provider records in json. Lines 4 and 5: Per recommendations on the Elasticsearch Google Group and by a gist written by Shay Bannon about peak indexing performance, I set a high number of shards and 0 replicas to increase index…
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
| curl -XPUT 'localhost:9200/doctors_index' -d ' | |
| { | |
| "settings": { | |
| "number_of_shards": 16, | |
| "number_of_replicas": 0, | |
| "index.refresh_interval": 120, | |
| "analysis": { | |
| "analyzer": { | |
| "autocomplete": { | |
| "type": "custom", | |
| "tokenizer": "standard", | |
| "filter": ["standard", "lowercase", "kstem", "edgeNGram"] | |
| }, | |
| "post_title": { | |
| "filter": ["standard", "lowercase", "asciifolding"], | |
| "type": "custom", | |
| "tokenizer": "standard" | |
| } | |
| }, | |
| "filter" : { | |
| "ngram" : { | |
| "type": "edgeNGram", | |
| "min_gram": 2, | |
| "max_gram": 15 | |
| } | |
| } | |
| } | |
| }, | |
| "mappings": { | |
| "doctors" : { | |
| "index_analyzer" : "standard", | |
| "search_analyzer" : "standard", | |
| "_timestamp" : { "enabled" : true }, | |
| "properties": { | |
| "names": { | |
| "properties": { | |
| "name_suffix": { | |
| "type": "string" | |
| }, | |
| "name_prefix": { | |
| "type": "string" | |
| }, | |
| "first_name": { | |
| "type": "multi_field", | |
| "path": "just_name", | |
| "fields": { | |
| "first_name": { | |
| "type": "string" | |
| }, | |
| "post_title": { | |
| "type": "string", | |
| "analyzer": "post_title", | |
| "similarity": "BM25" | |
| }, | |
| "autocomplete": { | |
| "analyzer": "autocomplete", | |
| "type": "string" | |
| } | |
| } | |
| }, | |
| "organization_name_type": { | |
| "type": "string" | |
| }, | |
| "middle_name": { | |
| "type": "string" | |
| }, | |
| "primary": { | |
| "type": "string" | |
| }, | |
| "last_name": { | |
| "type": "multi_field", | |
| "path": "just_name", | |
| "fields": { | |
| "first_name": { | |
| "type": "string" | |
| }, | |
| "post_title": { | |
| "type": "string", | |
| "analyzer": "post_title", | |
| "similarity": "BM25" | |
| }, | |
| "autocomplete": { | |
| "analyzer": "autocomplete", | |
| "type": "string" | |
| } | |
| } | |
| }, | |
| "gender": { | |
| "type": "string" | |
| }, | |
| "organization_name": { | |
| "type": "string" | |
| }, | |
| "credential": { | |
| "type": "string" | |
| } | |
| } | |
| }, | |
| "official": { | |
| "properties": { | |
| "name_suffix": { | |
| "type": "string" | |
| }, | |
| "name_prefix": { | |
| "type": "string" | |
| }, | |
| "first_name": { | |
| "type": "string" | |
| }, | |
| "title": { | |
| "type": "string" | |
| }, | |
| "middle_name": { | |
| "type": "string" | |
| }, | |
| "last_name": { | |
| "type": "string" | |
| }, | |
| "telephone": { | |
| "type": "string" | |
| }, | |
| "credential": { | |
| "type": "string" | |
| } | |
| } | |
| }, | |
| "addresses": { | |
| "properties": { | |
| "street2": { | |
| "type": "string" | |
| }, | |
| "street1": { | |
| "type": "string" | |
| }, | |
| "fax": { | |
| "type": "string" | |
| }, | |
| "postal_code": { | |
| "type": "long" | |
| }, | |
| "state": { | |
| "type": "string" | |
| }, | |
| "type": { | |
| "type": "string" | |
| }, | |
| "telephone": { | |
| "type": "string" | |
| }, | |
| "country_code": { | |
| "type": "string" | |
| }, | |
| "city": { | |
| "type": "string" | |
| } | |
| } | |
| }, | |
| "entity_type": { | |
| "type": "string" | |
| }, | |
| "last_update_date": { | |
| "type": "string" | |
| }, | |
| "taxonomies": { | |
| "properties": { | |
| "code": { | |
| "type": "string" | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| ' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment