feat: add stage 1 and 2 validation tests

data-pipeline/tests/fixtures/annotated.fixture.json

@@ -0,0 +1,170 @@
+[
+  {
+    "_fixture": "noun_with_cefr_vote",
+    "source_id": "ili:i100955",
+    "pos": "noun",
+    "translations": { "en": ["grain"], "de": ["Korn", "Kornbrand"] },
+    "glosses": { "en": ["a cereal grass"], "de": ["ein Getreidegras"] },
+    "examples": {
+      "en": [
+        { "text": "wheat is a grain that is grown in Kansas", "source": "omw" }
+      ]
+    },
+    "votes": { "en": { "grain": { "cefr_source": "B1" } } }
+  },
+  {
+    "_fixture": "verb_no_votes_no_translations",
+    "source_id": "ili:i21779",
+    "pos": "verb",
+    "translations": { "en": ["respire"] },
+    "glosses": {
+      "en": [
+        "undergo the biomedical and metabolic processes of respiration by taking up oxygen and producing carbon monoxide"
+      ]
+    },
+    "examples": {},
+    "votes": {}
+  },
+  {
+    "_fixture": "verb_with_cefr_vote_all_languages",
+    "source_id": "ili:i21778",
+    "pos": "verb",
+    "translations": {
+      "en": ["breathe", "take a breath", "respire", "suspire"],
+      "it": ["respirare"],
+      "es": ["aspirar", "respirar"],
+      "de": ["Luft holen", "hauchen", "Luft bekommen", "Luft kriegen", "atmen"],
+      "fr": ["inspirer", "respirer"]
+    },
+    "glosses": {
+      "en": ["draw air into, and expel out of, the lungs"],
+      "de": ["Luft in die Lunge saugen und aus ihr ausstoßen"]
+    },
+    "examples": {
+      "en": [
+        {
+          "text": "I can breathe better when the air is clean",
+          "source": "omw"
+        },
+        { "text": "The patient is respiring", "source": "omw" }
+      ]
+    },
+    "votes": { "en": { "breathe": { "cefr_source": "A1" } } }
+  },
+  {
+    "_fixture": "adjective_all_languages_multiple_translations",
+    "source_id": "ili:i10007",
+    "pos": "adjective",
+    "translations": {
+      "en": ["possible"],
+      "it": [
+        "attuabile",
+        "effettuabile",
+        "eseguibile",
+        "fattibile",
+        "operabile",
+        "possibile",
+        "producibile",
+        "realizzabile"
+      ],
+      "es": ["posible"],
+      "de": [
+        "möglich",
+        "denkbar",
+        "eventuell",
+        "möglicherweise",
+        "allfällig",
+        "etwaig",
+        "gegebenenfalls",
+        "eventuell"
+      ],
+      "fr": ["possible", "éventuel"]
+    },
+    "glosses": {
+      "en": ["capable of happening or existing"],
+      "de": ["in der Lage, zu geschehen oder zu existieren"]
+    },
+    "examples": {
+      "en": [
+        { "text": "a breakthrough may be possible next year", "source": "omw" },
+        { "text": "anything is possible", "source": "omw" },
+        { "text": "warned of possible consequences", "source": "omw" }
+      ]
+    },
+    "votes": { "en": { "possible": { "cefr_source": "A2" } } }
+  },
+  {
+    "_fixture": "adjective_multiple_de_votes_cefr_examples",
+    "source_id": "ili:i10000",
+    "pos": "adjective",
+    "translations": {
+      "en": ["negative"],
+      "de": [
+        "dürftig",
+        "zu wünschen übrig lassen",
+        "schlecht",
+        "widrig",
+        "ungut",
+        "lausig",
+        "negativ",
+        "von Nachteil",
+        "schädlich",
+        "nachteilig",
+        "ungünstig"
+      ],
+      "fr": ["négatif", "strictement négatif"]
+    },
+    "glosses": { "en": ["less than zero"], "de": ["kleiner als Null"] },
+    "examples": {
+      "en": [{ "text": "a negative number", "source": "omw" }],
+      "de": [
+        { "text": "Die Beweise waren dürftig.", "source": "cefr" },
+        { "text": "Das Wetter ist heute schlecht.", "source": "cefr" },
+        {
+          "text": "Trotz widriger Umstände haben sie es geschafft.",
+          "source": "cefr"
+        },
+        {
+          "text": "Er hatte ein ungutes Gefühl bei der Sache.",
+          "source": "cefr"
+        },
+        { "text": "Er hat eine sehr negative Einstellung.", "source": "cefr" },
+        {
+          "text": "Rauchen ist schädlich für die Gesundheit.",
+          "source": "cefr"
+        },
+        {
+          "text": "Diese Entscheidung könnte nachteilig sein.",
+          "source": "cefr"
+        },
+        {
+          "text": "Das Wetter ist heute ungünstig für einen Ausflug.",
+          "source": "cefr"
+        }
+      ]
+    },
+    "votes": {
+      "de": {
+        "dürftig": { "cefr_source": "C1" },
+        "schlecht": { "cefr_source": "A1" },
+        "widrig": { "cefr_source": "C1" },
+        "ungut": { "cefr_source": "B2" },
+        "negativ": { "cefr_source": "A2" },
+        "schädlich": { "cefr_source": "B1" },
+        "nachteilig": { "cefr_source": "B1" },
+        "ungünstig": { "cefr_source": "B2" }
+      }
+    }
+  },
+  {
+    "_fixture": "adverb_no_votes",
+    "source_id": "ili:i18157",
+    "pos": "adverb",
+    "translations": { "en": ["a cappella"], "es": ["a capella"] },
+    "glosses": { "en": ["without musical accompaniment"] },
+    "examples": {
+      "en": [{ "text": "they performed a cappella", "source": "omw" }]
+    },
+    "votes": {}
+  }
+]

data-pipeline/tests/fixtures/conflicts.fixture.json

@@ -0,0 +1,4 @@
+[
+  { "word": "macht", "pos": "noun", "language": "de", "levels": ["A2", "B1"] },
+  { "word": "bleiche", "pos": "noun", "language": "de", "levels": ["B2", "B1"] }
+]