feat(SIMPL-24642): migrate tests from 3 source repos with updated imports

tests/dataframe_level_anonymisation/config_models/__init__.py

@@ -0,0 +1 @@
+

tests/dataframe_level_anonymisation/config_models/test_base_config.py

@@ -0,0 +1,54 @@
+import pytest
+from pydantic import ValidationError
+
+from template_code_location.dataframe_level_anonymisation.config_models.base_config import BaseConfiguration
+
+
+def test_valid_configuration_with_overrides():
+    cfg = BaseConfiguration(
+        ident=["id"],
+        quasi_identifiers=["age"],
+        supp_level=10.0,
+        generalisation_hierarchies={"age": "age_hierarchy"},
+    )
+    assert cfg.ident == ["id"]
+    assert cfg.quasi_identifiers == ["age"]
+    assert cfg.supp_level == 10.0
+    assert cfg.generalisation_hierarchies == {"age": "age_hierarchy"}
+
+
+def test_default_values_are_loaded():
+    cfg = BaseConfiguration()
+    assert cfg.ident == ["Name"]
+    assert cfg.quasi_identifiers == ["Age"]
+    assert cfg.supp_level == 50.0
+    assert cfg.generalisation_hierarchies == {"Age": "simpl_age"}
+
+
+def test_missing_ident_raises_error():
+    with pytest.raises(ValidationError):
+        BaseConfiguration(
+            ident=[]
+        )
+
+
+def test_missing_quasi_ident_raises_error():
+    with pytest.raises(ValidationError):
+        BaseConfiguration(
+            quasi_identifiers=[]
+        )
+
+
+def test_overlap_between_ident_and_quasi_identifiers():
+    with pytest.raises(ValidationError):
+        BaseConfiguration(
+            ident=["age"],
+            quasi_identifiers=["age"]
+        )
+
+
+def test_supp_level_bounds():
+    with pytest.raises(ValidationError):
+        BaseConfiguration(
+            supp_level=150.0  # fuori range
+        )

tests/dataframe_level_anonymisation/config_models/test_hierarchies.py

@@ -0,0 +1,48 @@
+from template_code_location.dataframe_level_anonymisation.config_models.hierarchies import (
+    simpl_age,
+    simpl_age2,
+    simpl_gender,
+    get_all_hierarchies,
+)
+
+
+def test_simpl_age_structure():
+    assert isinstance(simpl_age, dict)
+    assert 0 in simpl_age
+    assert isinstance(simpl_age[0], list)
+    # verify first level contains 100 ages
+    assert len(simpl_age[0]) == 100
+    assert simpl_age[0][0] == 0
+    assert simpl_age[0][-1] == 99
+
+
+def test_simpl_age2_structure():
+    assert isinstance(simpl_age2, dict)
+    assert 0 in simpl_age2
+    assert 1 in simpl_age2
+    assert isinstance(simpl_age2[0], list)
+    assert isinstance(simpl_age2[1], list)
+
+
+def test_simpl_gender_structure():
+    assert isinstance(simpl_gender, dict)
+    assert 0 in simpl_gender
+    assert 1 in simpl_gender
+    assert simpl_gender[0] == ["M", "F", "O"]
+    assert simpl_gender[1] == ["*", "*", "*"]
+
+
+def test_get_all_hierarchies():
+    hier = get_all_hierarchies()
+
+    # the function should return dicts only
+    assert isinstance(hier, dict)
+
+    # ensure expected dicts are included
+    assert "simpl_age" in hier
+    assert "simpl_age2" in hier
+    assert "simpl_gender" in hier
+
+    # ensure the values returned are references to the actual dicts
+    assert hier["simpl_age"] is simpl_age
+    assert hier["simpl_gender"] is simpl_gender

tests/dataframe_level_anonymisation/config_models/test_k_anonymity_config.py

@@ -0,0 +1,41 @@
+import pytest
+from pydantic import ValidationError
+
+from template_code_location.dataframe_level_anonymisation.config_models.k_anonymity_configuration import (
+    KAnonymityConfiguration,
+)
+
+
+def test_valid_k_anonymity_config_with_overrides():
+    cfg = KAnonymityConfiguration(
+        ident=["id"],
+        quasi_identifiers=["age"],
+        supp_level=5.0,
+        generalisation_hierarchies={"age": "age_hier"},
+        k=3,
+        sensitive_attributes=["disease"],
+    )
+    assert cfg.k == 3
+    assert cfg.sensitive_attributes == ["disease"]
+    assert cfg.generalisation_hierarchies == {"age": "age_hier"}
+
+
+def test_default_values_are_loaded():
+    cfg = KAnonymityConfiguration(
+        ident=["id"],
+        quasi_identifiers=["age"],
+        generalisation_hierarchies={"age": "age_hier"}
+    )
+    assert cfg.k == 3
+    assert cfg.sensitive_attributes == ["Disease"]
+
+
+def test_invalid_k_value_raises_error():
+    with pytest.raises(ValidationError):
+        KAnonymityConfiguration(
+            ident=["id"],
+            quasi_identifiers=["age"],
+            generalisation_hierarchies={"age": "age_hier"},
+            k=1,  # invalid, must be >= 2
+            sensitive_attributes=["disease"],
+        )

tests/dataframe_level_anonymisation/config_models/test_l_diversity_config.py

@@ -0,0 +1,44 @@
+import pytest
+from pydantic import ValidationError
+
+from template_code_location.dataframe_level_anonymisation.config_models.l_diversity_configuration import (
+    LDiversityConfiguration,
+)
+
+
+def test_valid_l_diversity_config_with_overrides():
+    cfg = LDiversityConfiguration(
+        ident=["id"],
+        quasi_identifiers=["age"],
+        supp_level=5.0,
+        generalisation_hierarchies={"age": "age_hier"},
+        k=3,
+        l=2,
+        sensitive_attribute="disease",
+    )
+    assert cfg.k == 3
+    assert cfg.l == 2
+    assert cfg.sensitive_attribute == "disease"
+
+
+def test_default_values_are_loaded():
+    cfg = LDiversityConfiguration(
+        ident=["id"],
+        quasi_identifiers=["age"],
+        generalisation_hierarchies={"age": "age_hier"}
+    )
+    assert cfg.k == 2
+    assert cfg.l == 3
+    assert cfg.sensitive_attribute == "Disease"
+
+
+def test_invalid_l_value_raises_error():
+    with pytest.raises(ValidationError):
+        LDiversityConfiguration(
+            ident=["id"],
+            quasi_identifiers=["age"],
+            generalisation_hierarchies={"age": "age_hier"},
+            k=3,
+            l=0,  # invalid, must be >= 1
+            sensitive_attribute="disease",
+        )

tests/dataframe_level_anonymisation/config_models/test_t_closeness_config.py

@@ -0,0 +1,56 @@
+import pytest
+from pydantic import ValidationError
+
+from template_code_location.dataframe_level_anonymisation.config_models.t_closeness_configuration import (
+    TClosenessConfiguration,
+)
+
+
+def test_valid_t_closeness_config_with_overrides():
+    cfg = TClosenessConfiguration(
+        ident=["id"],
+        quasi_identifiers=["age"],
+        supp_level=5.0,
+        generalisation_hierarchies={"age": "age_hier"},
+        k=3,
+        t=0.4,
+        sensitive_attribute="disease",
+    )
+    assert cfg.k == 3
+    assert cfg.t == 0.4
+    assert cfg.sensitive_attribute == "disease"
+
+
+def test_default_values_are_loaded():
+    cfg = TClosenessConfiguration(
+        ident=["id"],
+        quasi_identifiers=["age"],
+        generalisation_hierarchies={"age": "age_hier"}
+    )
+    assert cfg.k == 2
+    assert cfg.t == 0.5
+    assert cfg.sensitive_attribute == "Disease"
+
+
+def test_invalid_t_value_low():
+    with pytest.raises(ValidationError):
+        TClosenessConfiguration(
+            ident=["id"],
+            quasi_identifiers=["age"],
+            generalisation_hierarchies={"age": "age_hier"},
+            k=3,
+            t=-0.1,  # invalid
+            sensitive_attribute="disease",
+        )
+
+
+def test_invalid_t_value_high():
+    with pytest.raises(ValidationError):
+        TClosenessConfiguration(
+            ident=["id"],
+            quasi_identifiers=["age"],
+            generalisation_hierarchies={"age": "age_hier"},
+            k=3,
+            t=2.0,  # invalid > 1
+            sensitive_attribute="disease",
+        )