I’ve been building up a useful index (index JSON at end of post) for some of the travel-sample bucket data including: review content, hotel location, cleanliness ratings and dates. It took me a while to get a couple of these figured out (thx @sreek), so thought I’d share it back to the forums for reference.
It includes custom date parser:
And note that cleanliness is numeric.
You can do a ton of interesting stuff with this index including date ranges:
{
“query”: {
“start”: “2014-10-12”,
“end”: “2015-10-09”,
“field”: “reviews.date”
}
}
… geospatial bounding boxes:
{
“query”: {
“top_left”: [-2.235143, 53.482358],
“bottom_right”: [ 29, 40],
“field”: “geo”
}
}
And all types of facet summaries:
Term facet:
{
“query”: {
“query”:“horrible experience”
},
“facets”: {
“type”: {
“size”: 5,
“field”: “type”
}
}
}
Numeric ranges:
{
“query”: {
“query”:“rustic style”
},
“facets”: {
“reviews.ratings.cleanliness”: {
“size”: 5,
“field”: “reviews.ratings.cleanliness”,
“numeric_ranges”: [{“name”:“high”,“min”:3},{“name”:“low”,“max”:2}]
}
}
}
Date ranges:
{
“query”: {
“query”:“horrible experience”
},
"facets": {
"reviews.date": {
"size": 5,
"field": "reviews.date",
"date_ranges": [{"name":"recent","start":"2013-01-01"},{"name":"old","start":"2001-01-01"}]
}
}
}
JSON Index definition:
{
"name": "hotels",
"type": "fulltext-index",
"params": {
"doc_config": {
"docid_prefix_delim": "",
"docid_regexp": "",
"mode": "type_field",
"type_field": "type"
},
"mapping": {
"analysis": {
"analyzers": {
"letterAnalyzer": {
"tokenizer": "letter",
"type": "custom"
}
},
"date_time_parsers": {
"custom_date": {
"layouts": [
"2006-01-02 15:04:05 +0300"
],
"type": "flexiblego"
}
}
},
"default_analyzer": "standard",
"default_datetime_parser": "dateTimeOptional",
"default_field": "_all",
"default_mapping": {
"dynamic": true,
"enabled": false
},
"default_type": "_default",
"docvalues_dynamic": true,
"index_dynamic": true,
"store_dynamic": false,
"type_field": "_type",
"types": {
"hotel": {
"dynamic": true,
"enabled": true,
"properties": {
"reviews": {
"dynamic": true,
"enabled": true,
"properties": {
"ratings": {
"dynamic": true,
"enabled": true,
"properties": {
"Cleanliness": {
"enabled": true,
"dynamic": false,
"fields": [
{
"docvalues": true,
"include_in_all": true,
"include_term_vectors": true,
"index": true,
"name": "cleanliness",
"store": true,
"type": "number"
}
]
}
}
},
"content": {
"enabled": true,
"dynamic": false,
"fields": [
{
"docvalues": true,
"include_in_all": true,
"include_term_vectors": true,
"index": true,
"name": "content",
"store": true,
"type": "text"
}
]
},
"date": {
"enabled": true,
"dynamic": false,
"fields": [
{
"date_format": "custom_date",
"docvalues": true,
"include_in_all": true,
"include_term_vectors": true,
"index": true,
"name": "date",
"store": true,
"type": "datetime"
}
]
}
}
},
"geo": {
"enabled": true,
"dynamic": false,
"fields": [
{
"docvalues": true,
"include_in_all": true,
"include_term_vectors": true,
"index": true,
"name": "geo",
"store": true,
"type": "geopoint"
}
]
}
}
}
}
},
"store": {
"indexType": "scorch"
}
},
"sourceType": "couchbase",
"sourceName": "travel-sample",
"sourceUUID": "",
"sourceParams": {},
"planParams": {
"maxPartitionsPerPIndex": 171,
"indexPartitions": 6,
"numReplicas": 0
},
"uuid": ""
}