Merge pull request #44 from cfpb/features/33_add_validation_id

Task 33, adding validation id

src/tests/test_checks.py

@@ -0,0 +1,27 @@
+import pytest
+
+from validator.checks import SBLCheck
+
+
+class TestSBLCheck:
+    def test_no_id_check(self):
+        with pytest.raises(Exception) as exc:
+            SBLCheck(lambda: True, warning=True, name="Just a Warning")
+
+        assert "Each check must be assigned a `name` and an `id`." in str(exc.value)
+        assert exc.type == ValueError
+
+    def test_no_name_check(self):
+        with pytest.raises(Exception) as exc:
+            SBLCheck(lambda: True, id="00000", warning=True)
+
+        assert "Each check must be assigned a `name` and an `id`." in str(exc.value)
+        assert exc.type == ValueError
+
+    def test_name_and_id_check(self):
+        raised = False
+        try:
+            SBLCheck(lambda: True, id="00000", warning=True, name="Just a Warning")
+        except ValueError:
+            raised = True
+        assert raised is False

src/validator/checks.py

@@ -14,7 +14,7 @@
         name="Just a Warning"
     )
     
-    error_check_implied = SBLCheck(lambda: Truename="Error Check")
+    error_check_implied = SBLCheck(lambda: True, name="Error Check")
     
     error_check_explicit = SBLCheck(
         lambda: True,
@@ -32,31 +32,37 @@
 
 
 class SBLCheck(Check):
-    """A custom Pandera.Check subclasss that requires a `name` be
+    """A custom Pandera.Check subclasss that requires a `name` and an `id` be
     specified. Additionally, an attribute named `warning` is added to
     the class to enable distinction between warnings and errors. The
     default value of warning is `False` which corresponds to an error.
 
     Don't use this class directly. Make use of the SBLErrorCheck and
     SBLWarningCheck subclasses below."""
 
-    def __init__(self, check_fn: Callable, warning=False, *args, **kwargs):
-        """Custom init method that verifies the presence of `name` in
+    def __init__(
+        self, check_fn: Callable, id: str = None, warning=False, *args, **kwargs
+    ):
+        """Custom init method that verifies the presence of `name` and `id` in
         kwargs creates a custom class attribute called `warning`. All
         other initializaiton is handled by the parent Check class.
 
         Args:
             check_fn (Callable): A function which evaluates the validity
                 of the column(s) being tested.
+            id (str, required): Each check mut have an id.
             warning (bool, optional): Boolean specifying whether to
                 treat the check as a warning rather than an error.
 
         Raises:
-            ValueError: Raised if `name` not supplied in kwargs.
+            ValueError: Raised if `name` not supplied in kwargs and if id is not
+            supplied or None.
         """
 
-        if "name" not in kwargs:
-            raise ValueError("Each check must be assigned a `name`.")
+        self.id = id
+
+        if "name" not in kwargs or id is None:
+            raise ValueError("Each check must be assigned a `name` and an `id`.")
 
         # if warning==False treat check as an error check
         self.warning = warning
@@ -67,10 +73,3 @@ def __init__(self, check_fn: Callable, warning=False, *args, **kwargs):
     def get_backend(cls, check_obj: Any) -> Type[BaseCheckBackend]:
         """Assume Pandas DataFrame and return PandasCheckBackend"""
         return PandasCheckBackend
-
-
-if __name__ == "__main__":
-    warning_check = SBLCheck(lambda: True, warning=True, name="Just a Warning")
-
-    error_check_implied = SBLCheck(lambda: True, name="Error Check")
-    error_check_explicit = SBLCheck(lambda: True, warning=False, name="Also an Error")

src/validator/create_schemas.py

@@ -24,20 +24,24 @@ def print_schema_errors(errors: SchemaErrors, phase: str):
     for error in errors.schema_errors:
         # Name of the column in the dataframe being checked
         schema_error = error["error"]
-        column_name = schema_error.schema.name
+        check_id = "n/a"
 
         # built in checks such as unique=True are different than custom
         # checks unfortunately so the name needs to be accessed differently
         try:
             check_name = schema_error.check.name
+            check_id = schema_error.check.id
             # This will either be a boolean series or a single bool
             check_output = schema_error.check_output
         except AttributeError:
             check_name = schema_error.check
             # this is just a string that we'd need to parse manually
             check_output = schema_error.args[0]
 
-        print(f"{phase} Validation `{check_name}` failed for column `{column_name}`")
+        print(
+            f"{phase} Validation `{check_name}` with id: `{check_id}` "
+            "failed for column `{column_name}`"
+        )
         print(check_output)
         print("")