| GET / | |
| #### 1ST PART CRUD | |
| DELETE villes | |
| PUT villes | |
| { | |
| "settings": { | |
| "number_of_shards": 1 | |
| } | |
| } | |
| PUT villes/_doc/cergy | |
| { | |
| "message": "Ici c'est Cergy" | |
| } | |
| GET villes/_doc/cergy | |
| PUT villes/_doc/cergy | |
| { | |
| "message": "Ici c'est Cergy", | |
| "meteo": "nuageux" | |
| } | |
| GET villes/_doc/cergy | |
| DELETE villes/_doc/cergy | |
| GET villes/_doc/cergy | |
| POST villes/_doc/ | |
| { | |
| "message": "Ici c'est Cergy", | |
| "meteo": "nuageux", | |
| "nom": "Cergy" | |
| } | |
| # Just one or two | |
| POST villes/_doc/ | |
| { | |
| "message": "Ici c'est Cergy Pontoise", | |
| "meteo": "nuageux", | |
| "nom": "Cergy Pontoise" | |
| } | |
| POST villes/_doc/ | |
| { | |
| "message": "Ici c'est Lille", | |
| "meteo": "beau", | |
| "nom": "Lille" | |
| } | |
| # Look at inelastic for meteo field | |
| #### SEARCH | |
| GET villes/_search | |
| GET villes/_search | |
| { | |
| "query": { | |
| "match": { | |
| "message": "cergy" | |
| } | |
| } | |
| } | |
| GET villes/_search | |
| { | |
| "query": { | |
| "match": { | |
| "message": "CERGY!" | |
| } | |
| } | |
| } | |
| GET villes/_search | |
| { | |
| "query": { | |
| "match": { | |
| "message": "cergy pontoise" | |
| } | |
| } | |
| } | |
| #### 2nd Part: INJECTOR | |
| # Inject data | |
| # Run aggregations | |
| # Play in Kibana | |
| # Show monitoring | |
| # Scale Out | |
| GET person/_search?track_total_hits=true | |
| # Back To Slides | |
| #### 3RD PART ANALYZE | |
| POST _analyze | |
| { | |
| "text": [ "The quick brown fox jumps over the lazy Dog!" ] | |
| } | |
| POST _analyze | |
| { | |
| "analyzer": "english", | |
| "text": [ "The quick brown fox jumps over the lazy Dog!" ] | |
| } | |
| # Start with ... And add the other filters | |
| POST _analyze | |
| { | |
| "tokenizer": "standard", | |
| "filter": [ | |
| "lowercase" | |
| ], | |
| "text": [ "L'éléphant est ROSE et il trompe énormément !" ] | |
| } | |
| POST _analyze | |
| { | |
| "explain": true, | |
| "tokenizer": "standard", | |
| "filter": [ | |
| "lowercase", | |
| {"type": "stop", "stopwords": [ "_french_" ]}, | |
| {"type": "elision", "articles" : ["l", "m", "t", "qu", "n", "s", "j"]}, | |
| {"type": "stemmer", "name": "light_french"}, | |
| "asciifolding" | |
| ], | |
| "text": [ "L'éléphant est ROSE et il trompe énormément !" ] | |
| } | |
| POST _analyze | |
| { | |
| "analyzer": "french", | |
| "text": [ "L'éléphant est ROSE et il trompe énormément !" ] | |
| } | |
| ## Not so light | |
| POST _analyze | |
| { | |
| "tokenizer": "standard", | |
| "filter": [ | |
| "lowercase", | |
| {"type": "stop", "stopwords": [ "_french_" ]}, | |
| {"type": "elision", "articles" : ["l", "m", "t", "qu", "n", "s", "j"]}, | |
| {"type": "stemmer", "name": "french"}, | |
| "asciifolding" | |
| ], | |
| "text": [ "L'éléphant est ROSE et il trompe énormément !" ] | |
| } | |
| POST _analyze | |
| { | |
| "tokenizer": "standard", | |
| "filter": [ | |
| "lowercase", | |
| {"type": "stop", "stopwords": [ "_french_" ]}, | |
| {"type": "elision", "articles" : ["l", "m", "t", "qu", "n", "s", "j"]}, | |
| {"type": "stemmer", "name": "french"}, | |
| "asciifolding" | |
| ], | |
| "text": [ "Des éléphantes" ] | |
| } | |
| ## Bizarre ? | |
| POST _analyze | |
| { | |
| "analyzer": "french", | |
| "text": [ "Un avion" ] | |
| } | |
| POST _analyze | |
| { | |
| "analyzer": "french", | |
| "text": [ "Des avions" ] | |
| } | |
| ## Ngrams | |
| POST _analyze | |
| { | |
| "tokenizer": "standard", | |
| "filter": [ | |
| {"type": "edgeNGram", "min_gram" : 2, "max_gram" : 5} | |
| ], | |
| "text": [ "eleph" ] | |
| } | |
| POST _analyze | |
| { | |
| "tokenizer": "standard", | |
| "filter": [ | |
| {"type": "nGram", "min_gram" : 2, "max_gram" : 3} | |
| ], | |
| "text": [ "eleph" ] | |
| } | |
| DELETE mon_index | |
| PUT mon_index | |
| { | |
| "settings": { | |
| "number_of_shards": 1, | |
| "number_of_replicas": 0, | |
| "analysis": { | |
| "analyzer": { | |
| "francais": { | |
| "type": "custom", | |
| "tokenizer": "standard", | |
| "filter": [ | |
| "lowercase", | |
| "stop_francais", | |
| "fr_stemmer", | |
| "asciifolding", | |
| "elision" | |
| ] | |
| }, | |
| "autocomplete": { | |
| "type": "custom", | |
| "tokenizer": "standard", | |
| "filter": [ | |
| "elision", | |
| "lowercase", | |
| "asciifolding", | |
| "autocomplete" | |
| ] | |
| } | |
| }, | |
| "filter": { | |
| "stop_francais": { | |
| "type": "stop", | |
| "stopwords": [ | |
| "_french_", | |
| "twitter" | |
| ] | |
| }, | |
| "fr_stemmer": { | |
| "type": "stemmer", | |
| "name": "french" | |
| }, | |
| "elision": { | |
| "type": "elision", | |
| "articles": [ | |
| "l", | |
| "m", | |
| "t", | |
| "qu", | |
| "n", | |
| "s", | |
| "j", | |
| "d", | |
| "lorsqu" | |
| ] | |
| }, | |
| "autocomplete": { | |
| "type": "edgeNGram", | |
| "min_gram": 2, | |
| "max_gram": 5 | |
| } | |
| } | |
| } | |
| }, | |
| "mappings": { | |
| "properties": { | |
| "description": { | |
| "type": "text", | |
| "analyzer": "francais" | |
| }, | |
| "username": { | |
| "type": "text", | |
| "analyzer": "autocomplete", | |
| "search_analyzer": "simple" | |
| }, | |
| "city": { | |
| "type": "text", | |
| "analyzer": "francais", | |
| "fields": { | |
| "ngram": { | |
| "type": "text", | |
| "analyzer": "autocomplete", | |
| "search_analyzer": "simple" | |
| }, | |
| "raw": { | |
| "type": "keyword" | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| POST mon_index/_analyze | |
| { | |
| "text": [ "Cergy", "Cénac" ], | |
| "analyzer": "autocomplete" | |
| } | |
| POST mon_index/_analyze | |
| { | |
| "text": [ "Cer" ], | |
| "analyzer": "autocomplete" | |
| } | |
| POST mon_index/_analyze | |
| { | |
| "text": [ "Cer" ], | |
| "analyzer": "simple" | |
| } | |
| POST mon_index/_analyze | |
| { | |
| "text": [ "J'habite à Cergy" ], | |
| "analyzer": "francais" | |
| } | |