Explanation of elasticsearch analysis with differents filters

elasticsearch_analysis

GET /timeline/event/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "terms": {
            "author_uuid": [
              {
                "uuid": "c6c99520-1d8b-45d5-a851-2bc159817af6"
              },
              {
                "uuid": "3dcfb094-6ac8-4295-af0c-9dd8d744293c"
              }
            ]
          }
        },
        {
          "terms": {
            "namespace": [
              "news",
              "advert",
              "event"
            ]
          }
        }
      ]
    }
  },
  "sort": {
    "last_activity": "desc"
  },
  "size": 30,
  "from": 0
}

GET /timeline/event/_search
{
  "size": 120, 
  "query": {
    "match_all": {}
  },
  "sort": {
    "last_activity": "desc"
  }
}

# ANALYSER STANDARD

GET /my_index/_analyze?analyzer=standard&text="Y a de l'eau dans le gaz MR WI-FI."

# FILTER ELISION

PUT /my_index
{
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "filter": {
        "my_filter_elision": {
          "type": "elision",
          "articles": [
            "l",
            "m",
            "t",
            "qu",
            "n",
            "s",
            "j",
            "d"
          ]
        }
      },
      "analyzer": {
        "my_analizer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "my_filter_elision"
          ]
        }
      }
    }
  }
}

GET /my_index/_analyze?analyzer=my_analizer&text="Y a de l'eau dans le gaz MR PowerShot."

DELETE  /my_index

# FILTER LOWERCASE

PUT /my_index
{
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "analyzer": {
        "my_analizer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "lowercase",
            "elision"
          ]
        }
      }
    }
  }
}

GET /my_index/_analyze?analyzer=my_analizer&text="Y a de l'eau dans le gaz MR WI-FI."

DELETE  /my_index

# FILTER STOPWORD

PUT /my_index
{
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "filter": {
        "my_stop_word" : {
          "type": "stop",
          "stopwords": "_french_"
        }
      }, 
      "analyzer": {
        "my_analizer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "lowercase",
            "elision",
            "my_stop_word"
          ]
        }
      }
    }
  }
}

GET /my_index/_analyze?analyzer=my_analizer&text="Y a de l'eau dans le gaz MR WI-FI."

DELETE  /my_index

# FILTER WORD DELIMITER

PUT /my_index
{
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "filter": {
        "my_stop_word" : {
          "type": "stop",
          "stopwords": "_french_"
        }
      }, 
      "analyzer": {
        "my_analizer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "lowercase",
            "elision",
            "my_stop_word",
            "word_delimiter"
          ]
        }
      }
    }
  }
}

GET /my_index/_analyze?analyzer=my_analizer&text="Y a de l'eau dans le gaz MR PowerShot."

DELETE  /my_index

# FILTER WORD DELIMITER (GOOD ORDER)

PUT /my_index
{
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "filter": {
        "my_stop_word" : {
          "type": "stop",
          "stopwords": "_french_"
        }
      }, 
      "analyzer": {
        "my_analizer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "my_stop_word",
            "elision",
            "word_delimiter",
            "lowercase"
          ]
        }
      }
    }
  }
}

GET /my_index/_analyze?analyzer=my_analizer&text="Y a de l'eau dans le gaz MR PowerShot chevaux."

DELETE  /my_index

# SNOWBALL

PUT /my_index
{
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "filter": {
        "my_stop_word" : {
          "type": "stop",
          "stopwords": "_french_"
        },
        "my_snowball" : {
          "type" : "snowball",
          "language": "French"
        }
      }, 
      "analyzer": {
        "my_analizer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "my_stop_word",
            "elision",
            "word_delimiter",
            "lowercase",
            "my_snowball"
          ]
        }
      }
    }
  }
}

GET /my_index/_analyze?analyzer=my_analizer&text="Y a de maisons méchamment l'eau dans le gaz MR PowerShot chevaux."

DELETE  /my_index

# asciifolding 

PUT /my_index
{
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "filter": {
        "my_stop_word" : {
          "type": "stop",
          "stopwords": "_french_"
        },
        "my_snowball" : {
          "type" : "snowball",
          "language": "French"
        },
        "my_edge_ngram": { 
            "type":     "edge_ngram",
            "min_gram": 3,
            "max_gram": 10
        }
      }, 
      "analyzer": {
        "my_analizer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "my_stop_word",
            "elision",
            "word_delimiter",
            "lowercase",
            "my_snowball",
            "asciifolding"
          ]
        }
      }
    }
  }
}

GET /my_index/_analyze?analyzer=my_analizer&text="Il faut être comme sera on est mais ne pas être ce que nous fûmes"

DELETE  /my_index

# EDGE GRAM 

PUT /my_index
{
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "filter": {
        "my_stop_word" : {
          "type": "stop",
          "stopwords": "_french_"
        },
        "my_snowball" : {
          "type" : "snowball",
          "language": "French"
        },
        "my_edge_ngram": { 
            "type":     "edge_ngram",
            "min_gram": 2,
            "max_gram": 10
        }
      }, 
      "analyzer": {
        "my_analizer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "my_stop_word",
            "elision",
            "word_delimiter",
            "lowercase",
            "my_snowball",
            "asciifolding",
            "my_edge_ngram"
          ]
        }
      }
    }
  }
}


GET /my_index/_analyze?analyzer=my_analizer&text="Y a de l'eau dans le gaz MR PowerShot chevaux."

# INDEX DATA

PUT /my_index/_mapping/my_type
{
    "my_type": {
        "properties": {
            "name": {
                "type":     "string",
                "analyzer": "my_analizer"
            }
        }
    }
}

POST /my_index/my_type/_bulk
{"index":{"_id":1}}
{"name": "Mes amis les chevaux"}
{"index":{"_id":2}}
{"name":"Nous étions bonnes quand on étais jeunes"}
{"index":{"_id":3}}
{"name":"Guillaume est amoureux de game of throne et d'un cheval"}
{"index":{"_id":4}}
{"name":"Maxime est un petit jeunot mais son esprit est bon"}
{"index":{"_id":5}}
{"name":"Il faut être comme on est mais ne pas être ce que nous fûmes"}

GET /my_index/my_type/_search
{
    "query": {
      "match_all": {}
    }
}

GET /my_index/_analyze?analyzer=my_analizer&text="Nous étions bonnes quand on étais jeunes"

# QUERY DATA

GET /my_index/my_type/_search
{
    "query": {
        "match": {
            "name": "jeunot"
        }
    }
}

# QUERY DATA WITH STANDARD ANALIZER

GET /my_index/my_type/_search
{
    "query": {
        "match": {
            "name": {
                "query":    "jeun",
                "analyzer": "standard" 
            }
        }
    }
}

# QUERY DATA WITH STANDARD ANALIZER

GET /my_index/my_type/_search?explain
{
    "query": {
        "match": {
            "name": {
                "query":    "cheval",
                "analyzer": "standard" 
            }
        }
    }
}