Merge branch 'patch-2' into 'dev'

Patch 2

See merge request !6

README.md

-# halCrawler
+# HAL API Crawler
+
+## API documentation
+
+## Base website
+https://api.archives-ouvertes.fr/docs
+
+## Usage
+### Entry function
+The basic entry point of this crawler is the function `HAL.` `getMetadataWith`.
+
+This function take a `Text` representing the query you want to run on hal
+and a `Maybe Int` representing the maximum number of result you want to get.
+### Return Type
+The return type is a bit more tricky, it's **either** a `ClientError` or a `HAL.Client` `Response Corpus`.
+In the usage it's exactly working as the other crawler `Documents` type, but it facilitate on the implementation side.
+
+`Response x` represent a collection of `x` and the number of `x` returned.
+
+` HAL.Doc.Corpus.` `Corpus` is a simple type that contain every informations we need (id,title,abstract,publicationDate,sources).
+
+### Exemple
+Here is a basic main using the entry point of the crawler and printing the 5 first documents.
+```hs
+{-# LANGUAGE OverloadedStrings #-}
+
+module Main where
+
+import Network.HTTP.Client (newManager)
+import Network.HTTP.Client.TLS (tlsManagerSettings)
+import Servant.Client
+
+import HAL (getMetadataWith)
+import HAL.Client
+import HAL.Doc
+import Tree
+
+main :: IO ()
+main = do
+  res <- getMetadataWith "artificial intelligence" (Just 10)
+  case res of
+    (Left  err) -> print err
+    (Right val) -> print $ take 5 $ _docs val
+```
+ 

app/Main.hs

@@ -6,15 +6,14 @@ import Network.HTTP.Client (newManager)
 import Network.HTTP.Client.TLS (tlsManagerSettings)
 import Servant.Client
 
-import HAL (runSearchRequest)
+import HAL (getMetadataWith)
 import HAL.Client
 import HAL.Doc
 import Tree
 
 main :: IO ()
 main = do
-  manager' <- newManager tlsManagerSettings
-  res <- runSearchRequest $ ["ia"]
+  res <- getMetadataWith "artificial intelligence" (Just 10)
   case res of
-    (Left err) -> print err
+    (Left  err) -> print err
     (Right val) -> print $ _docs val

src/HAL.hs

@@ -13,6 +13,15 @@ import Servant.Client (BaseUrl(..), Scheme(..), ClientM, ClientError, runClientM
 import HAL.Client
 import HAL.Doc.Corpus
 
+
+getMetadataWith :: Text -> Maybe Int -> IO (Either ClientError (Response Corpus))
+getMetadataWith q l = do
+  manager' <- newManager tlsManagerSettings
+  runHalAPIClient $ search (Just requestedFields) [q] Nothing l Nothing
+
+requestedFields :: Text
+requestedFields = "docid,title_s,abstract_s,submittedDate_s,source_s,authFullName_s,authOrganism_s"
+
 runHalAPIClient :: ClientM (Response Corpus) -> IO (Either ClientError (Response Corpus))
 runHalAPIClient cmd = do
   manager' <- newManager tlsManagerSettings
@@ -20,8 +29,8 @@ runHalAPIClient cmd = do
 
 runStructureRequest :: Maybe Text -> IO (Either ClientError (Response Corpus))
 runStructureRequest rq =
-  runHalAPIClient $ structure (Just "docid,title_s,abstract_s,submittedDate_s,source_s,authFullName_s,authOrganism_s") rq (Just 10000)
+  runHalAPIClient $ structure (Just requestedFields) rq (Just 10000)
 
 runSearchRequest :: [Text] -> IO (Either ClientError (Response Corpus))
 runSearchRequest rq =
-  runHalAPIClient $ search (Just "docid,title_s,abstract_s,submittedDate_s,source_s,authFullName_s,authOrganism_s") rq Nothing Nothing Nothing
+  runHalAPIClient $ search (Just requestedFields) rq Nothing Nothing Nothing