feat: add SchemaOrgRecipe types and FromJSON parsing

test/Roux/SchemaOrgSpec.hs

@@ -0,0 +1,51 @@
+module Roux.SchemaOrgSpec (spec) where
+
+import qualified Data.Aeson as A
+import Data.Maybe (fromJust, isJust)
+import Data.Text (Text)
+import qualified Data.Text as T
+import qualified Data.Text.Encoding as TE
+import Test.Hspec (Spec, describe, expectationFailure, it, shouldBe, shouldSatisfy)
+
+import Roux.SchemaOrg
+
+-- | Extract the first schema.org Recipe JSON-LD from HTML.
+tryDecode :: Text -> Maybe A.Value
+tryDecode html =
+    case T.splitOn "<script type=\"application/ld+json" html of
+        (_before : rest : _) ->
+            -- Skip past the closing > of the opening script tag, which may have extra attributes
+            let afterOpenTag = T.drop 1 (T.dropWhile (/= '>') rest)
+             in case T.splitOn "</script>" afterOpenTag of
+                    (jsonContent : _) -> A.decodeStrict (TE.encodeUtf8 (T.strip jsonContent))
+                    _ -> Nothing
+        _ -> Nothing
+
+spec :: Spec
+spec = describe "SchemaOrg" $ do
+    describe "parseSchemaOrgRecipe" $ do
+        it "parses fried-rice.html embedded JSON-LD" $ do
+            html <- readFile "test-data/fried-rice.html"
+            let decoded = tryDecode (T.pack html)
+            decoded `shouldSatisfy` isJust
+            let recipe = parseSchemaOrgRecipe (fromJust decoded)
+            recipe `shouldSatisfy` isJust
+            case recipe of
+                Nothing -> expectationFailure "expected Just SchemaOrgRecipe, got Nothing"
+                Just r -> do
+                    soName r `shouldBe` "Fried Rice"
+                    soRecipeYield r `shouldBe` Just "4 to 6 servings"
+                    soTotalTime r `shouldBe` Just "PT20M"
+                    soRecipeCuisine r `shouldBe` Just "asian"
+                    length (soRecipeIngredient r) `shouldBe` 14
+                    length (soRecipeInstructions r) `shouldBe` 4
+
+        it "parses carrot-risotto.html embedded JSON-LD" $ do
+            html <- readFile "test-data/carrot-risotto.html"
+            let decoded = tryDecode (T.pack html)
+            decoded `shouldSatisfy` isJust
+            let recipe = parseSchemaOrgRecipe (fromJust decoded)
+            recipe `shouldSatisfy` isJust
+            case recipe of
+                Nothing -> expectationFailure "expected Just SchemaOrgRecipe, got Nothing"
+                Just r -> soName r `shouldBe` "Carrot Risotto With Chile Crisp"

test/Spec.hs

@@ -5,14 +5,17 @@ import Test.Tasty.Hspec (testSpec)
 
 import qualified Roux.NYTimesSpec
 import qualified Roux.ParserSpec
+import qualified Roux.SchemaOrgSpec
 
 main :: IO ()
 main = do
     parserTests <- testSpec "Parser" Roux.ParserSpec.spec
     nytTests <- testSpec "NYTimes" Roux.NYTimesSpec.spec
+    schemaOrgTests <- testSpec "SchemaOrg" Roux.SchemaOrgSpec.spec
     defaultMain $
         testGroup
             "roux-server"
             [ parserTests
             , nytTests
+            , schemaOrgTests
             ]