elasticsearch - complex querying - elasticsearch

Question

I am using the jdbc river and I can create the following index:
curl -XPUT 'localhost:9201/_river/email/_meta' -d '{
"type" : "jdbc",
"jdbc" : {
"strategy":"simple",
"poll":"10",
"driver" : "org.postgresql.Driver",
"url" : "jdbc:postgresql://localhost:5432/api_development",
"username" : "paulcowan",
"password" : "",
"sql" : "SELECT id, subject, body, personal, sent_at, read_by, account_id, sender_user_id, sender_contact_id, html, folder, draft FROM emails"
},
"index" : {
"index" : "email",
"type" : "jdbc"
},
"mappings" : {
"email" : {
"properties" : {
"account_id" : { "type" : "integer" },
"subject" : { "type" : "string" },
"body" : { "type" : "string" },
"html" : { "type" : "string" },
"folder" : { "type" : "string", "index" : "not_analyzed" },
"id" : { "type" : "integer" }
}
}
}
}'
I can run basic queries using curl like this:
curl -XGET 'http://localhost:9201/email/jdbc/_search?pretty&q=fullcontact'
I get back results
But what I want to do is restrict the results to a particular email account_id and a particular email, I run the following query:
curl -XGET 'http://localhost:9201/email/jdbc/_search' -d '{
"query": {
"filtered": {
"filter": {
"and": [
{
"term": {
"folder": "INBOX"
}
},
{
"term": {
"account_id": 1
}
}
]
},
"query": {
"query_string": {
"query": "fullcontact*"
}
}
}
}
}'
I get the following results:
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 0,
"max_score": null,
"hits": []
}
}
Can anyone tell me what is wrong with my query?

Answer 1

It turns out that you need to use the type_mapping section to specify a field is not_analyzed in the jdbc river the normal mappings node is ignored.
Below is how it turned out:
curl -XPUT 'localhost:9200/_river/your_index/_meta' -d '{
"type" : "jdbc",
"jdbc" : {
"strategy":"simple",
"poll":"10",
"driver" : "org.postgresql.Driver",
"url" : "jdbc:postgresql://localhost:5432/api_development",
"username" : "user",
"password" : "your_password",
"sql" : "SELECT field_one, field_two, field_three, the_rest FROM blah"
},
"index" : {
"index" : "your_index",
"type" : "jdbc",
"type_mapping": "{\"your_index\" : {\"properties\" : {\"field_two\":{\"type\":\"string\",\"index\":\"not_analyzed\"}}}}"
}
}'
Strangely or annoyingly, the type_mapping section, takes a json encoded string and not a normal json node:
I can check the mappings by running:
# check mappings
curl -XGET 'http://localhost:9200/your_index/jdbc/_mapping?pretty=true'
Which should give something like:
{
"jdbc" : {
"properties" : {
"field_one" : {
"type" : "long"
},
"field_two" : {
"type" : "string",
"index" : "not_analyzed",
"omit_norms" : true,
"index_options" : "docs"
},
"field_three" : {
"type" : "string"
}
}
}
}