killed off a redundant important, getting documentation rolling

This commit is contained in:
Chris Allen 2014-04-13 20:00:28 -05:00
parent 8c8892f34b
commit 1aea945f12
2 changed files with 205 additions and 2 deletions

View File

@ -5,14 +5,218 @@
* Elasticsearch client and query DSL for Haskell
** Why?
Because you're tired of obnoxious errors like [this](http://i.imgur.com/FKtZYIP.png) and want types to guide your use of the API.
** Stability
Bloodhound is alpha at the moment. The library works fine, but I don't want to mislead anyone into thinking the API is final or stable. I wouldn't call the library "complete" or representative of everything you can do in Elasticsearch but being personally familiar with multiple clients in other languages I think the story there is good.
Bloodhound is alpha at the moment. The library works fine, but I don't want to mislead anyone into thinking the API is final or stable. I wouldn't call the library "complete" or representative of everything you can do in Elasticsearch but being compared to clients in other languages the story here so far is good.
* Examples
** Index Operations
*** Create Index
#+BEGIN_SRC haskell
-- Formatted for use in ghci, so there are "let"s in front of the decls.
-- :set -XDeriveGeneric
import Database.Bloodhound.Client
import Data.Aeson
import Data.Either (Either(..))
import Data.Maybe (fromJust)
import Data.Time.Calendar (Day(..))
import Data.Time.Clock (secondsToDiffTime, UTCTime(..))
import Data.Text (Text)
import GHC.Generics (Generic)
import Network.HTTP.Conduit
import qualified Network.HTTP.Types.Status as NHTS
-- no trailing slashes in servers, library handles building the path.
let testServer = (Server "http://localhost:9200")
let testIndex = IndexName "twitter"
let testMapping = MappingName "tweet"
-- defaultIndexSettings is exported by Database.Bloodhound.Client as well.
let defaultIndexSettings = IndexSettings (ShardCount 3) (ReplicaCount 2)
-- createIndex returns IO Reply
-- response :: Reply, Reply is a synonym for Network.HTTP.Conduit.Response
response <- createIndex testServer defaultIndexSettings testIndex
#+END_SRC
*** Delete Index
#+BEGIN_SRC haskell
-- response :: Reply
response <- deleteIndex testServer testIndex
-- print response if it was a success
Response {responseStatus = Status {statusCode = 200, statusMessage = "OK"}, responseVersion = HTTP/1.1, responseHeaders = [("Content-Type","application/json; charset=UTF-8"),("Content-Length","21")], responseBody = "{\"acknowledged\":true}", responseCookieJar = CJ {expose = []}, responseClose' = ResponseClose}
-- if the index to be deleted didn't exist anyway
Response {responseStatus = Status {statusCode = 404, statusMessage = "Not Found"}, responseVersion = HTTP/1.1, responseHeaders = [("Content-Type","application/json; charset=UTF-8"),("Content-Length","65")], responseBody = "{\"error\":\"IndexMissingException[[twitter] missing]\",\"status\":404}", responseCookieJar = CJ {expose = []}, responseClose' = ResponseClose}
#+END_SRC
*** Refresh Index
**** Note, you *have* to do this if you expect to read what you just wrote
#+BEGIN_SRC haskell
resp <- refreshIndex testServer testIndex
-- print resp on success
Response {responseStatus = Status {statusCode = 200, statusMessage = "OK"}, responseVersion = HTTP/1.1, responseHeaders = [("Content-Type","application/json; charset=UTF-8"),("Content-Length","50")], responseBody = "{\"_shards\":{\"total\":10,\"successful\":5,\"failed\":0}}", responseCookieJar = CJ {expose = []}, responseClose' = ResponseClose}
#+END_SRC
** Mapping Operations
*** Create Mapping
#+BEGIN_SRC haskell
-- don't forget imports and the like at the top.
data TweetMapping = TweetMapping deriving (Eq, Show)
-- I know writing the JSON directly/manually sucks.
-- I don't have a real data type for Mappings yet.
-- Let me know if this is something you need.
:{
instance ToJSON TweetMapping where
toJSON TweetMapping =
object ["tweet" .=
object ["properties" .=
object ["location" .=
object ["type" .= ("geo_point" :: Text)]]]]
:}
resp <- createMapping testServer testIndex testMapping TweetMapping
#+END_SRC
*** Delete Mapping
#+BEGIN_SRC haskell
resp <- deleteMapping testServer testIndex testMapping
#+END_SRC
** Document Operations
*** Indexing Documents
#+BEGIN_SRC haskell
-- don't forget the imports and derive generic setting for ghci at the beginning of the examples.
:{
data Location = Location { lat :: Double
, lon :: Double } deriving (Eq, Generic, Show)
data Tweet = Tweet { user :: Text
, postDate :: UTCTime
, message :: Text
, age :: Int
, location :: Location } deriving (Eq, Generic, Show)
exampleTweet = Tweet { user = "bitemyapp"
, postDate = UTCTime
(ModifiedJulianDay 55000)
(secondsToDiffTime 10)
, message = "Use haskell!"
, age = 10000
, location = Location 40.12 (-71.34) }
-- automagic (generic) derivation of instances because we're lazy.
instance ToJSON Tweet
instance FromJSON Tweet
instance ToJSON Location
instance FromJSON Location
:}
-- Should be able to toJSON and encode the data structures like this:
-- λ> toJSON $ Location 10.0 10.0
-- Object fromList [("lat",Number 10.0),("lon",Number 10.0)]
-- λ> encode $ Location 10.0 10.0
-- "{\"lat\":10,\"lon\":10}"
resp <- indexDocument testServer testIndex testMapping exampleTweet (DocId "1")
-- print resp on success
Response {responseStatus = Status {statusCode = 200, statusMessage = "OK"}, responseVersion = HTTP/1.1, responseHeaders = [("Content-Type","application/json; charset=UTF-8"),("Content-Length","75")], responseBody = "{\"_index\":\"twitter\",\"_type\":\"tweet\",\"_id\":\"1\",\"_version\":2,\"created\":false}", responseCookieJar = CJ {expose = []}, responseClose' = ResponseClose}
#+END_SRC
*** Deleting Documents
#+BEGIN_SRC haskell
resp <- deleteDocument testServer testIndex testMapping (DocId "1")
#+END_SRC
*** Getting Documents
#+BEGIN_SRC haskell
-- n.b., you'll need the earlier imports. responseBody is from http-conduit
resp <- getDocument testServer testIndex testMapping (DocId "1")
-- responseBody :: Response body -> body
let body = responseBody resp
-- you have two options, you use decode and just get Maybe (EsResult Tweet)
-- or you can use eitherDecode and get Either String (EsResult Tweet)
let maybeResult = decode body :: Maybe (EsResult Tweet)
-- the explicit typing is so Aeson knows how to parse the JSON.
-- use either if you want to know why something failed to parse.
-- (string errors, sadly)
let eitherResult = decode body :: Either String (EsResult Tweet)
-- print eitherResult should look like:
Right (EsResult {_index = "twitter", _type = "tweet", _id = "1", _version = 2, found = Just True, _source = Tweet {user = "bitemyapp", postDate = 2009-06-18 00:00:10 UTC, message = "Use haskell!", age = 10000, location = Location {lat = 40.12, lon = -71.34}}})
-- _source in EsResult is parametric, we dispatch the type by passing in what we expect (Tweet) as a parameter to EsResult.
#+END_SRC
** Search
*** Querying
*** Filtering
* Possible future functionality
** Node discovery and failover
Might require TCP support.
** Support for TCP access to Elasticsearch
Pretend to be a transport client?
** Bulk cluster-join merge
Might require making a lucene index on disk with the appropriate format.
** GeoShapeFilter
http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/query-dsl-geo-shape-filter.html

View File

@ -4,7 +4,6 @@ module Main where
import Database.Bloodhound.Client
import Data.Aeson
import Data.DeriveTH
import Data.Either (Either(..))
import Data.Maybe (fromJust)
import Data.Time.Calendar (Day(..))