ElasticSearch Settings file

gistfile1.txt

{
	"mappings": {
		"properties": {
			"searchable_text": {
				"type": "multi_field",
				"fields": {
					"full_words": {
						"type": "string",
						"store": "yes",
						"index": "analyzed",
						"term_vector": "with_positions_offsets",
						"analyzer": "transcript_analyzer",
						"boost": 2.0,
						"similarity": "BM25"
					},

					"ngrams": {
						"type": "string",
						"store": "yes",
						"index": "analyzed",
						"term_vector": "with_positions_offsets",
						"analyzer": "ngram_analyzer",
						"boost": 1.0,
						"similarity": "BM25"
					}
				}
			},

			"display_name": {
				"type": "multi_field",
				"fields": {

					"depth_search": {
						"type": "string",
						"store": "yes",
						"index": "analyzed",
						"term_vector": "with_positions_offsets",
						"analyzer": "depth_analyzer",
						"boost": 1.0,
						"similarity": "BM25"
					},

					"breadth_search": {
						"type": "string",
						"store": "yes",
						"index": "analyzed",
						"term_vector": "with_positions_offsets",
						"analyzer": "breadth_analyzer",
						"boost": 2.0,
						"similarity": "BM25"
					}
				},

				"id": {
					"type": "string",
					"store": "true"
				},

				"hash": {
					"type": "string",
					"store": "true"
				},
				
				"thumbnail": {
					"type": "binary"
				},

                "course_id": {
                    "type": "string",
                    "store": "true"
                }
			}
		}
	},

	"settings": {
		"analysis":{
		    "analyzer": {

		        "transcript_analyzer": {
		            "type": "custom",
		            "tokenizer": "standard",
		            "filter": ["asciifolding", "custom_word_delimiter", "lowercase", "custom_stemmer", "shingle",
		            		    "custom_phonetic"]
		        },

		        "ngram_analyzer": {
		        	"type": "custom",
		        	"tokenizer": "standard",
		        	"filter": ["asciifolding", "word_delimiter", "lowercase", "custom_stemmer", "custom_phonetic"]
		        },

		        "depth_analyzer": {
		        	"type": "custom",
		        	"tokenizer": "standard",
		        	"filter": ["custom_word_delimiter", "lowercase", "shingle", "custom_phonetic"]
		        },

		        "breadth_analyzer": {
		        	"type": "custom",
		        	"tokenizer": "standard",
		        	"filter": ["asciifolding", "lowercase", "custom_phonetic"]
		        }
		    },

		    "filter" : {

		    	"custom_phonetic": {
		    		"type": "phonetic",
		    		"encoder": "doublemetaphone",
		    		"replace": false
		    	},

		        "custom_stemmer": {
		            "type": "stemmer",
		            "name": "minimal_english"
		        }
		    }
		}
	}
}