Demo script for BBLs

bbl.json

DELETE mon_index
DELETE person

GET /

#### 1ST PART CRUD
DELETE person

# Create the first doc
PUT person/_doc/david
{
  "name" : "David Pilato"
}
GET person/_doc/david

# Update the doc
PUT person/_doc/david
{
  "name" : "David Pilato",
  "address" : {
    "city": "Cergy"
  }
}
GET person/_doc/david

# Remove the doc
DELETE person/_doc/david
GET person/_doc/david


# Create some documents (like 10)
POST person/_doc/
{
  "name" : "David Pilato",
  "comments": "Ici c'est Cergy"
}

# Create some documents (like 3)
POST person/_doc/
{
  "name" : "David Pilato",
  "comments": "Ici c'est Cergy Pontoise"
}

# Create one or 2 docs
POST person/_doc/
{
  "name" : "David Pilato",
  "comments": "Ici c'est Pontoise"
}


#### SEARCH
# Search all (and from/size)
GET person/_search






















GET person/_search
{
  "query": {
    "match": {
      "comments": "cergy"
    }
  }
}

GET person/_search
{
  "query": {
    "match": {
      "comments": "CERGY!"
    }
  }
}

GET person/_search
{
  "query": {
    "match": {
      "comments": "Cergy Pontoise"
    }
  }
}

#### 2nd Part: INJECTOR

# Inject data
# Run aggregations
# Play in Kibana
# Show monitoring 
# Scale Out


DELETE person
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": [ 
  ],
  "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"]},
    "asciifolding" ,
    {"type": "stemmer", "name": "light_french"}
  ],
  "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"]},
    "asciifolding" ,
    {"type": "stemmer", "name": "french"}
  ],
  "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"]},
    "asciifolding" ,
    {"type": "stemmer", "name": "french"}
  ],
  "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": "edge_ngram", "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": "edge_ngram",
          "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": {
          "autocomplete": {
            "type": "text",
            "analyzer": "autocomplete",
            "search_analyzer": "simple"
          },
          "keyword": {
            "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"
}