configure coreNLP tokenization to group hyphaneted words

src/Gargantext/Core/Text/Terms/Multi/PosTagging.hs

@@ -82,7 +82,7 @@ corenlp' :: ( FromJSON a
           => URI -> Lang -> p -> IO (Response a)
 corenlp' uri lang txt = do
   req <- parseRequest $
-         "POST " <> show (uri { uriQuery = "?properties=" <> (BSL.unpack $ encode $ toJSON $ Map.fromList properties) })
+         "POST " <> show (uri { uriQuery = "?properties=" <> BSL.unpack (encode $ toJSON $ Map.fromList properties) })
    -- curl -XPOST 'http://localhost:9000/?properties=%7B%22annotators%22:%20%22tokenize,ssplit,pos,ner%22,%20%22outputFormat%22:%20%22json%22%7D' -d 'hello world, hello' | jq .
   --   printDebug "[corenlp] sending body" $ (cs txt :: ByteString)
   catch (httpJSON $ setRequestBodyLBS (cs txt) req) $ \e ->
@@ -97,7 +97,7 @@ corenlp' uri lang txt = do
     properties_ :: [(Text, Text)]
     properties_ = case lang of
 -- TODO: Add: Aeson.encode $ Aeson.toJSON $ Map.fromList [()] instead of these hardcoded JSON strings
-            EN -> [ ("annotators", "tokenize,ssplit,pos,ner" ) ]
+            EN -> [ ("annotators", "tokenize,ssplit,pos,ner" ), ("tokenize.options", "splitHyphenated=false") ]
             FR -> [ ("annotators", "tokenize,ssplit,pos,lemma,ner")
                   -- , ("parse.model", "edu/stanford/nlp/models/lexparser/frenchFactored.ser.gz")
                   , ("pos.model", "edu/stanford/nlp/models/pos-tagger/models/french.tagger")