elastic search analyzer examples for email addresses

basic.json

# curl -XGET 'localhost:9200/test/_analyze?pretty=true&analyzer=standard' -d '[email protected]'
{
  "tokens" : [ {
    "token" : "john.smith",
    "start_offset" : 0,
    "end_offset" : 10,
    "type" : "<ALPHANUM>",
    "position" : 1
  }, {
    "token" : "example",
    "start_offset" : 11,
    "end_offset" : 18,
    "type" : "<ALPHANUM>",
    "position" : 2
  }, {
    "token" : "one.com",
    "start_offset" : 19,
    "end_offset" : 26,
    "type" : "<ALPHANUM>",
    "position" : 3
  } ]
}


# curl -XGET 'localhost:9200/test/_analyze?pretty=true&analyzer=simple' -d '[email protected]'
{
  "tokens" : [ {
    "token" : "john",
    "start_offset" : 0,
    "end_offset" : 4,
    "type" : "word",
    "position" : 1
  }, {
    "token" : "smith",
    "start_offset" : 5,
    "end_offset" : 10,
    "type" : "word",
    "position" : 2
  }, {
    "token" : "example",
    "start_offset" : 11,
    "end_offset" : 18,
    "type" : "word",
    "position" : 3
  }, {
    "token" : "one",
    "start_offset" : 19,
    "end_offset" : 22,
    "type" : "word",
    "position" : 4
  }, {
    "token" : "com",
    "start_offset" : 23,
    "end_offset" : 26,
    "type" : "word",
    "position" : 5
  } ]
}


# curl -XGET 'localhost:9200/test/_analyze?pretty=true&analyzer=whitespace' -d '[email protected]'
{
  "tokens" : [ {
    "token" : "[email protected]",
    "start_offset" : 0,
    "end_offset" : 26,
    "type" : "word",
    "position" : 1
  } ]
}

stopwords-examples.json

# curl -XGET 'localhost:9200/test/_analyze?pretty=true&analyzer=standard' -d '[email protected]'
{
  "tokens" : [ {
    "token" : "john.smith",
    "start_offset" : 0,
    "end_offset" : 10,
    "type" : "<ALPHANUM>",
    "position" : 1
  }, {
    "token" : "example.com",
    "start_offset" : 14,
    "end_offset" : 25,
    "type" : "<ALPHANUM>",
    "position" : 3
  } ]
}


# curl -XGET 'localhost:9200/test/_analyze?pretty=true&analyzer=simple' -d '[email protected]'
{
  "tokens" : [ {
    "token" : "john",
    "start_offset" : 0,
    "end_offset" : 4,
    "type" : "word",
    "position" : 1
  }, {
    "token" : "smith",
    "start_offset" : 5,
    "end_offset" : 10,
    "type" : "word",
    "position" : 2
  }, {
    "token" : "an",
    "start_offset" : 11,
    "end_offset" : 13,
    "type" : "word",
    "position" : 3
  }, {
    "token" : "example",
    "start_offset" : 14,
    "end_offset" : 21,
    "type" : "word",
    "position" : 4
  }, {
    "token" : "com",
    "start_offset" : 22,
    "end_offset" : 25,
    "type" : "word",
    "position" : 5
  } ]
}