feat: update dummy dataset fetchers

Author: wiebe-vandendriessche

internal/fetcher/dummy_dataset_api_fetcher.go

@@ -12,13 +12,19 @@ func (f *DummyDatasetAPIFetcher) Fetch(ctx context.Context, datasetID string) (*
 	return &DatasetAPIResponse{
 		ID:          datasetID,
 		Author:      "huggingface",
-		Tags:        []string{"dataset", "benchmark"},
+		SHA:         "abc123def456789012345678901234567890abcd",
+		LastMod:     "2024-01-15T10:30:00.000Z",
+		CreatedAt:   "2023-06-01T08:00:00.000Z",
+		UsedStorage: 1024000,
+		Tags:        []string{"dataset", "benchmark", "text-classification"},
 		Description: "Dummy dataset for testing: " + datasetID,
 		Downloads:   100000,
 		Likes:       500,
 		CardData: map[string]any{
-			"language": "en",
-			"license":  "cc0-1.0",
+			"language":        "en",
+			"license":         "cc0-1.0",
+			"task_categories": []interface{}{"text-classification", "text-generation"},
+			"tags":            []interface{}{"sentiment-analysis", "benchmark"},
 		},
 	}, nil
 }

internal/fetcher/dummy_dataset_readme_fetcher.go

@@ -18,10 +18,26 @@ func (f *DummyDatasetReadmeFetcher) Fetch(ctx context.Context, datasetID string)
 		License:            "cc0-1.0",
 		Tags:               []string{"dataset", "test"},
 		Language:           []string{"en"},
-		AnnotationCreators: []string{"huggingface"},
-		CuratedBy:          "Dummy Curator",
-		FundedBy:           "Test Foundation",
-		SharedBy:           "Test Team",
-		DatasetDescription: "A dummy dataset for testing dataset component building",
+		AnnotationCreators: []string{"Test Annotator", "Secondary Annotator"},
+		Configs: []DatasetConfig{
+			{
+				Name: "default",
+				DataFiles: []DatasetDataFile{
+					{Split: "train", Path: "data/train.csv"},
+					{Split: "test", Path: "data/test.csv"},
+				},
+			},
+		},
+		DatasetDescription:    "A dummy dataset for testing dataset component building with comprehensive metadata",
+		CuratedBy:             "Dummy Curator",
+		FundedBy:              "Test Foundation",
+		SharedBy:              "Test Team",
+		RepositoryURL:         "https://huggingface.co/datasets/" + datasetID,
+		PaperURL:              "https://arxiv.org/abs/2401.12345",
+		DemoURL:               "https://huggingface.co/spaces/demo/" + datasetID,
+		OutOfScopeUse:         "This dataset should not be used for production systems without proper validation",
+		PersonalSensitiveInfo: "This dataset may contain synthetic personal information for testing purposes",
+		BiasRisksLimitations:  "Dataset may contain inherent biases from the synthetic generation process",
+		DatasetCardContact:    "[email protected]",
 	}, nil
 }