Upgrade to Pro — share decks privately, control downloads, hide ads and more …

From A to JSON - an overview of Elasticsearch

Boaz Leskes
January 09, 2014

From A to JSON - an overview of Elasticsearch

A talk I gave at the Jan 9th 2014 010Dev meetup

It gives an overview of Elasticsearch with some extra attention to the new features in the 1.0 release

Boaz Leskes

January 09, 2014
Tweet

More Decks by Boaz Leskes

Other Decks in Technology

Transcript

  1. Update a document... $ curl -X PUT localhost:9200/products/product/1 -d '{

    "title" : "Welcome to the breakfast. Bon appetite!” }'
  2. {
 "id" : "abc123",
 
 "title" : "A JSON Document",


    
 "body" : "A JSON document is a ...",
 
 "published_on" : "2013/06/27 10:00:00", ! "featured" : true,
 
 "tags" : ["search", "json"],
 
 "author" : {
 "first_name" : "Clara",
 "last_name" : "Rice",
 "email" : "[email protected]"
 }
 } Documents as JSON Data structure with basic types, arrays and deep hierarchies
  3. Terms apple apple iphone Phrases "apple iphone" Proximity "apple safari"~5

    Fuzzy apple~0.8 Wildcards app* *pp* Boosting apple^10 safari Range [2011/05/01 TO 2011/05/31] [java TO json] Boolean apple AND NOT iphone +apple -iphone (apple OR iphone) AND NOT review Fields title:iphone^15 OR body:iphone published_on:[2011/05/01 TO "2011/05/27 10:00:00"] http://lucene.apache.org/core/4_5_0/queryparser... $ curl -X GET "http://localhost:9200/_search?q=<YOUR QUERY>"
  4. curl -X GET localhost:9200/articles/_search -d '{
 "query" : {
 "filtered"

    : {
 "query" : {
 "bool" : {
 
 "must" : {
 "match" : {
 "author.first_name" : {
 "query" : "claire",
 "fuzziness" : 0.1
 }
 }
 },
 
 "must" : {
 "multi_match" : {
 "query" : "elasticsearch",
 "fields" : ["title^10", "body"]
 }
 }
 }
 
 },
 
 "filter": {
 "and" : [
 { "terms" : { "tags" : ["search"] } },
 { "range" : { "published_on": {"from": "2013"} } },
 { "term" : { "featured" : true } }
 ]
 }
 }
 }
 }' JSON-based Query DSL
  5. curl -X GET localhost:9200/articles/_search -d '{
 "query" : {
 "filtered"

    : {
 "query" : {
 "bool" : {
 
 "must" : {
 "match" : {
 "author.first_name" : {
 "query" : "claire",
 "fuzziness" : 0.1
 }
 }
 },
 
 "must" : {
 "multi_match" : {
 "query" : "elasticsearch",
 "fields" : ["title^10", "body"]
 }
 }
 }
 
 },
 
 "filter": {
 "and" : [
 { "terms" : { "tags" : ["search"] } },
 { "range" : { "published_on": {"from": "2013"} } },
 { "term" : { "featured" : true } }
 ]
 }
 }
 }
 }' JSON-based Query DSL 
 
 
 

  6. curl -X GET localhost:9200/articles/_search -d '{
 "query" : {
 "filtered"

    : {
 "query" : {
 "bool" : {
 
 "must" : {
 "match" : {
 "author.first_name" : {
 "query" : "claire",
 "fuzziness" : 0.1
 }
 }
 },
 
 "must" : {
 "multi_match" : {
 "query" : "elasticsearch",
 "fields" : ["title^10", "body"]
 }
 }
 }
 
 },
 
 "filter": {
 "and" : [
 { "terms" : { "tags" : ["search"] } },
 { "range" : { "published_on": {"from": "2013"} } },
 { "term" : { "featured" : true } }
 ]
 }
 }
 }
 }' JSON-based Query DSL 
 
 
 

  7. curl -X GET localhost:9200/articles/_search -d '{
 "query" : {
 "filtered"

    : {
 "query" : {
 "bool" : {
 
 "must" : {
 "match" : {
 "author.first_name" : {
 "query" : "claire",
 "fuzziness" : 0.1
 }
 }
 },
 
 "must" : {
 "multi_match" : {
 "query" : "elasticsearch",
 "fields" : ["title^10", "body"]
 }
 }
 }
 
 },
 
 "filter": {
 "and" : [
 { "terms" : { "tags" : ["search"] } },
 { "range" : { "published_on": {"from": "2013"} } },
 { "term" : { "featured" : true } }
 ]
 }
 }
 }
 }' JSON-based Query DSL 
 
 
 

  8. curl -X GET localhost:9200/articles/_search -d '{
 "query" : {
 "filtered"

    : {
 "query" : {
 "bool" : {
 
 "must" : {
 "match" : {
 "author.first_name" : {
 "query" : "claire",
 "fuzziness" : 0.1
 }
 }
 },
 
 "must" : {
 "multi_match" : {
 "query" : "elasticsearch",
 "fields" : ["title^10", "body"]
 }
 }
 }
 
 },
 
 "filter": {
 "and" : [
 { "terms" : { "tags" : ["search"] } },
 { "range" : { "published_on": {"from": "2013"} } },
 { "term" : { "featured" : true } }
 ]
 }
 }
 }
 }' JSON-based Query DSL 
 
 
 

  9. “Find all articles with ‘search’ in their title or body,

    give matches in titles higher score” Full-text Search “Find all articles from year 2013 tagged ‘search’” Structured Search See custom_score and custom_filters_score queries Custom Scoring
  10. Fetch document field ➝ Pick configured analyzer ➝ Parse text

    into tokens ➝ Apply token filters ➝ Store into index How Search Engine Works? Result Results Query How Users See Search?
  11. Mapping curl -X PUT localhost:9200/articles/_mapping -d '{
 "article" : {


    "properties" : {
 "title" : {
 "type" : "string",
 "analyzer" : "english"
 }
 }
 }
 }' Configuring document properties for the search engine
  12. curl -X POST 'localhost:9200/articles/_search?search_type=count&pretty' -d '{
 "facets": {
 "tag-cloug": {


    "terms" : {
 "field" : "tags"
 }
 }
 }
 }'
 “Tag Cloud” With the terms Facet "facets" : { "tag-cloug" : { "terms" : [ { "term" : "ruby", "count" : 3 }, { "term" : "java", "count" : 2 }, ... } ] } } Simplest “map/reduce” aggregation: document count per tag
  13. curl -X GET 'localhost:9200/scores/_search/?search_type=count&pretty' -d '{
 "facets": {
 "scores-per-subject" :

    {
 "terms_stats" : {
 "key_field" : "subject",
 "value_field" : "score"
 }
 }
 }
 }'
 Statistics on Student Scores With the terms_stats Facet "facets" : { "scores-per-subject" : { "_type" : "terms_stats", "missing" : 0, "terms" : [ { "term" : "math", "count" : 4, "total_count" : 4, "min" : 25.0, "max" : 92.0, "total" : 267.0, "mean" : 66.75 }, ... ] } } Aggregating statistics per subject
  14. curl -X GET 'localhost:9200/scores/_search/?search_type=count&pretty' -d '{
 "query" : {
 "match"

    : {
 "student" : "john"
 }
 },
 "facets": {
 "scores-per-subject" : {
 "terms_stats" : {
 "key_field" : "subject",
 "value_field" : "score"
 }
 }
 }
 }'
 Statistics on Student Scores With the terms_stats Facet "facets" : { "scores-per-subject" : { "_type" : "terms_stats", "missing" : 0, "terms" : [ { "term" : "math", "count" : 1, "total_count" : 1, "min" : 85.0, "max" : 85.0, "total" : 85.0, "mean" : 85.0 }, ... ] } } Realtime filtering with queries and filters
  15. Above & Beyond Bulk operations (For indexing and search operations)

    Percolator (“reversed search” — alerts, classification, …) Suggesters (“Did you mean …?”) Index aliases (Grouping, filtering or “renaming” of indices) Index templates (Automatic index configuration) Monitoring API (Amount of memory used, number of operations, …) …
  16. curl -X GET 'localhost:9200/scores/_search/?search_type=count&pretty' -d '{
 "query" : {
 "match"

    : {
 "student" : "john"
 }
 },
 "aggs": {
 "scores-per-subject" : {
 "terms" : { "field" : “subject” }, "aggs" : { “avg_score” : { "avg" : { "field" : "score"
 } } } }
 }
 }'
 "aggregations" : { "scores-per-subject" : { "terms" : [ { "term" : "math", "doc_count" : 1, "avg_score" : { “value": 85.0 } }, ... ] } }
  17. curl -X GET 'localhost:9200/scores/_search/?search_type=count&pretty' -d '{
 "query" : {
 "match"

    : {
 "student" : "john"
 }
 },
 "aggs": {
 "scores-per-subject" : {
 "terms" : { "field" : “subject” }, "aggs" : { "avg_score_by_year”: { “date_histogram”: { "field" : "date", "interval" : "year", "format" : "yyyy" } } "aggs": { "avg_score" : { "avg": { "field" : "score"
 } } } } } }
 }
 }'
 "aggregations" : { "scores-per-subject" : { "terms" : [ { "term" : "math", "doc_count" : 1, "avg_score_by_year" : [{ "key_as_string": "2013", "avg_score": { “value”: 85.0 } }… ] }, ... ] } }
  18. curl -XPUT “localhost:9200/twitter/.percolator/es-tweets” -d ‘{ “query”: { “match”: { “body”:

    “elasticsearch” } } }’ $ curl -XGET “localhost:9200/twitter/_percolate” -d ‘{ “doc”: { “body”: “#elasticsearch is awesome” “nick”: “@imotov” “name”: “Igor Motov” “date”: “2013-11-03” } }’ { … “matches”: [ { “_index”: “twitter”, “_id”: “es-tweets” } ] }
  19. Backup, 0.90 style 1. disable flush 2. find all primary

    shard location (optional) 3. copy files from primary shards (rsync) 4. enable flush
  20. Backup, 0.90 style 1. close the index (shutdown the cluster)

    2. find all existing index shards 3. replace all index shards with data from backup 4. open the index (start the cluster)
  21. A curl -XPUT 'http://localhost:9200/a/' -d '{
 "settings" : {
 "index"

    : {
 "number_of_shards" : 3,
 "number_of_replicas" : 1
 }
 }
 }'
 Index is partitioned into 3 primary shards, each is duplicated in 1 replica shard A1 A2 A3 Replicas Primaries A1' A2' A3'
  22. 1 node 2 nodes 3 nodes Demo "index.routing.allocation.exclude.name" : "Node1"

    "cluster.routing.allocation.exclude.name" : "Node3" ...