test: add step count preservation tests for SchemaOrg → Cooklang conversion

Adds checkStepCount helper that verifies the number of instructions in
the parsed schema.org recipe matches the number of SecStep items in
the Method section of the resulting Cooklang Recipe. Tests both
fried-rice (4 steps) and carrot-risotto (7 steps).

test/Roux/SchemaOrgSpec.hs

@@ -1,7 +1,7 @@
 module Roux.SchemaOrgSpec (spec) where
 
 import Data.Aeson (Value, decodeStrict)
-import Data.CookLang (Duration (..), Metadata (..), Recipe (..))
+import Data.CookLang (Duration (..), Metadata (..), Recipe (..), Section (..), SectionBodyItem (..))
 import Data.List.NonEmpty (toList)
 import Data.Maybe (fromJust, isJust)
 import Data.Text (Text)
@@ -66,34 +66,68 @@ spec = describe "SchemaOrg" $ do
         it "human-readable -> Nothing" $ chk "20 minutes" Nothing
 
     describe "schemaOrgToCooklang" $ do
-        it "converts fried-rice schema.org recipe to Cooklang" $ do
+        let loadRecipeFile :: FilePath -> IO (Maybe SchemaOrgRecipe)
-            html <- readFile "test-data/fried-rice.html"
+            loadRecipeFile path = do
-            let decoded = tryDecode (T.pack html)
+                html <- readFile path
-                recipe = parseSchemaOrgRecipe (fromJust decoded)
+                let decoded = tryDecode (T.pack html)
-            case recipe of
+                pure (parseSchemaOrgRecipe =<< decoded)
-                Just r -> case schemaOrgToCooklang r of
-                    Right cook -> do
-                        metaTitle (recipeMetadata cook) `shouldBe` Just "Fried Rice"
-                        metaSource (recipeMetadata cook) `shouldBe` Just "https://cooking.nytimes.com/recipes/12177-fried-rice"
-                        metaCourse (recipeMetadata cook) `shouldBe` Just "one pot, side dish"
-                        metaCuisine (recipeMetadata cook) `shouldBe` Just "asian"
-                        metaTotalTime (recipeMetadata cook) `shouldBe` Just (Duration 20 (Just "minutes"))
-                        metaTags (recipeMetadata cook) `shouldBe` ["egg", "rice", "vegetarian"]
-                        metaDescription (recipeMetadata cook) `shouldSatisfy` isJust
-                        let sections = toList (recipeSections cook)
-                        length sections `shouldBe` 2
-                    Left err -> fail err
-                Nothing -> fail "Failed to parse schema.org recipe"
 
-        it "converts carrot-risotto schema.org recipe to Cooklang" $ do
+        let countMethodSteps :: Recipe -> Int
-            html <- readFile "test-data/carrot-risotto.html"
+            countMethodSteps recipe =
-            let decoded = tryDecode (T.pack html)
+                let sections = toList (recipeSections recipe)
-                recipe = parseSchemaOrgRecipe (fromJust decoded)
+                 in case filter (\s -> sectionName s == Just "Method") sections of
-            case recipe of
+                        [s] ->
-                Just r -> case schemaOrgToCooklang r of
+                            let bodyItems = toList (sectionBody s)
-                    Right cook -> do
+                             in length [() | SecStep _ <- bodyItems]
-                        metaTitle (recipeMetadata cook) `shouldBe` Just "Carrot Risotto With Chile Crisp"
+                        _ -> 0
-                        metaAuthor (recipeMetadata cook) `shouldBe` Just "Alexa Weibel"
+
-                        metaTags (recipeMetadata cook) `shouldSatisfy` (not . null)
+        let checkStepCount :: FilePath -> String -> Int -> Spec
-                    Left err -> fail err
+            checkStepCount path label expectedSteps = it ("preserves " <> label <> " step count in Cooklang conversion") $ do
-                Nothing -> fail "Failed to parse schema.org recipe"
+                mRecipe <- loadRecipeFile path
+                case mRecipe of
+                    Nothing -> fail "Failed to parse schema.org recipe"
+                    Just r -> do
+                        let rawInstructions = soRecipeInstructions r
+                        length rawInstructions `shouldBe` expectedSteps
+                        case schemaOrgToCooklang r of
+                            Left err -> fail err
+                            Right cook -> do
+                                let cookSteps = countMethodSteps cook
+                                cookSteps `shouldBe` expectedSteps
+
+        let checkMetadata :: FilePath -> String -> (SchemaOrgRecipe -> IO ()) -> Spec
+            checkMetadata path label checks = it ("converts " <> label <> " schema.org recipe to Cooklang") $ do
+                mRecipe <- loadRecipeFile path
+                case mRecipe of
+                    Nothing -> fail "Failed to parse schema.org recipe"
+                    Just r -> do
+                        checks r
+                        case schemaOrgToCooklang r of
+                            Left err -> fail err
+                            Right _ -> pure ()
+
+        checkStepCount "test-data/fried-rice.html" "fried-rice" 4
+
+        checkStepCount "test-data/carrot-risotto.html" "carrot-risotto" 7
+
+        checkMetadata "test-data/fried-rice.html" "fried-rice" $ \r ->
+            case schemaOrgToCooklang r of
+                Left err -> fail err
+                Right cook -> do
+                    metaTitle (recipeMetadata cook) `shouldBe` Just "Fried Rice"
+                    metaSource (recipeMetadata cook) `shouldBe` Just "https://cooking.nytimes.com/recipes/12177-fried-rice"
+                    metaCourse (recipeMetadata cook) `shouldBe` Just "one pot, side dish"
+                    metaCuisine (recipeMetadata cook) `shouldBe` Just "asian"
+                    metaTotalTime (recipeMetadata cook) `shouldBe` Just (Duration 20 (Just "minutes"))
+                    metaTags (recipeMetadata cook) `shouldBe` ["egg", "rice", "vegetarian"]
+                    metaDescription (recipeMetadata cook) `shouldSatisfy` isJust
+                    let sections = toList (recipeSections cook)
+                    length sections `shouldBe` 2
+
+        checkMetadata "test-data/carrot-risotto.html" "carrot-risotto" $ \r ->
+            case schemaOrgToCooklang r of
+                Left err -> fail err
+                Right cook -> do
+                    metaTitle (recipeMetadata cook) `shouldBe` Just "Carrot Risotto With Chile Crisp"
+                    metaAuthor (recipeMetadata cook) `shouldBe` Just "Alexa Weibel"
+                    metaTags (recipeMetadata cook) `shouldSatisfy` (not . null)