gistfile1.sh

# Have an index created with "no_stopwords" analyzer

curl -XPUT 'http://localhost:9200/my_twitter1/' -d '
{
    "settings": {
        "number_of_shards": 1,
        "number_of_replicas": 0,
        "analysis" : {
            "analyzer" : {
                "no_stopwords" : {
                    "type" : "standard",
                    "stopwords" : "_none_"
                }
            }
        }
    },
    "mappings": {
        "tweet" : {
            "_all" : {"type" : "string", "null_value" : "na", "index" : "analyzed", "analyzer" : "no_stopwords"},
            "properties" : {
                "user" : {"type" : "string", "index" : "not_analyzed"},
                "message" : {"type" : "string", "null_value" : "na", "index" : "analyzed", "analyzer" : "no_stopwords"},
                "postDate" : {"type" : "date"}
            }
        }
    }
}'

# But that can be annoying to set on each field, i.e. we want the no_stopword analyzer to be the default (and then we don't have to specify it in the mappings):

curl -XPUT 'http://localhost:9200/my_twitter1/' -d '
{
    "settings": {
        "number_of_shards": 1,
        "number_of_replicas": 0,
        "analysis" : {
            "analyzer" : {
                "default" : {
                    "type" : "standard",
                    "stopwords" : "_none_"
                }
            }
        }
    },
    "mappings": {
        "tweet" : {
            "_all" : {"type" : "string", "null_value" : "na", "index" : "analyzed"},
            "properties" : {
                "user" : {"type" : "string", "index" : "not_analyzed"},
                "message" : {"type" : "string", "null_value" : "na", "index" : "analyzed"},
                "postDate" : {"type" : "date"}
            }
        }
    }
}'