Feature/pdct 1418 Make skeleton for GCF event data (#10)

* Add events skeleton

* Check events df has required fields

* Move has_required_fields into separate helpers file

* Add tests for has_required_fields helper

* Add typehints for has_required_fields tests

* Raise an attribute error if required fields not present

* Bump to 0.1.6

* Add raise in docstring for verify_required_fields_present

gcf_data_mapper/cli.py

@@ -7,6 +7,7 @@
 
 from gcf_data_mapper.parsers.collection import collection
 from gcf_data_mapper.parsers.document import document
+from gcf_data_mapper.parsers.event import event
 from gcf_data_mapper.parsers.family import family
 from gcf_data_mapper.read import read
 
@@ -91,7 +92,7 @@ def wrangle_to_json(
         "collections": collection(debug),
         "families": family(project_info, debug),
         "documents": document(doc_info, debug),
-        "events": [],
+        "events": event(project_info, debug),
     }
 
 

gcf_data_mapper/parsers/event.py

@@ -0,0 +1,32 @@
+from enum import Enum
+from typing import Any, Optional
+
+import click
+import pandas as pd
+
+from gcf_data_mapper.parsers.helpers import verify_required_fields_present
+
+
+class RequiredColumns(Enum):
+    APPROVED = "ApprovalDate"
+    UNDER_IMPLEMENTATION = "StartDate"
+    COMPLETED = "DateCompletion"
+
+
+def event(projects_data: pd.DataFrame, debug: bool) -> list[Optional[dict[str, Any]]]:
+    """Map the GCF event info to new structure.
+
+    :param pd.DataFrame projects_data: The MCF and GCF project data,
+        joined on FP num.
+    :param bool debug: Whether debug mode is on.
+    :return list[Optional[dict[str, Any]]]: A list of GCF families in
+        the 'destination' format described in the GCF Data Mapper Google
+        Sheet.
+    """
+    if debug:
+        click.echo("📝 Wrangling GCF event data.")
+
+    required_fields = set(str(e.value) for e in RequiredColumns)
+    verify_required_fields_present(projects_data, required_fields)
+
+    return []

gcf_data_mapper/parsers/helpers.py

@@ -0,0 +1,22 @@
+import pandas as pd
+
+
+def verify_required_fields_present(
+    data: pd.DataFrame, required_fields: set[str]
+) -> bool:
+    """Map the GCF event info to new structure.
+
+    :param pd.DataFrame data: The DataFrame to check.
+    :param set[str] required_fields: The required DataFrame columns.
+    :param bool debug: Whether debug mode is on.
+    :raise AttributeError if any of the required fields are missing.
+    :return bool: True if the DataFrame contains the required fields.
+    """
+    cols = set(data.columns)
+    diff = set(required_fields).difference(cols)
+    if diff == set():
+        return True
+    raise AttributeError(
+        f"Required fields '{str(diff)}' not present in df columns '"
+        f"{cols if cols != set() else r'{}'}'"
+    )

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gcf-data-mapper"
-version = "0.1.5"
+version = "0.1.6"
 description = "A CLI tool to wrangle GCF data into format recognised by the bulk-import tool."
 authors = ["CPR-dev-team <[email protected]>"]
 license = "Apache-2.0"

tests/unit_tests/parsers/event/conftest.py

@@ -0,0 +1,31 @@
+import pandas as pd
+import pytest
+
+
+@pytest.fixture(
+    params=[
+        {
+            "col1": ["record1"],
+        },
+        {
+            "ApprovalDate": ["some_approval"],
+        },
+        {
+            "ApprovalDate": ["some_ref"],
+            "StartDate": ["some_start"],
+        },
+    ]
+)
+def required_cols_missing(request):
+    yield pd.DataFrame(request.param)
+
+
+@pytest.fixture()
+def valid_data():
+    yield pd.DataFrame(
+        {
+            "ApprovalDate": ["some_approval"],
+            "StartDate": ["some_start"],
+            "DateCompletion": ["some_end"],
+        }
+    )

tests/unit_tests/parsers/event/test_event.py

@@ -0,0 +1,13 @@
+import pytest
+
+from gcf_data_mapper.parsers.event import event
+
+
+def test_returns_empty_when_cols_missing(required_cols_missing):
+    with pytest.raises(AttributeError):
+        event(required_cols_missing, debug=False)
+
+
+def test_success_with_valid_data(valid_data):
+    event_data = event(valid_data, debug=False)
+    assert event_data == []

tests/unit_tests/parsers/helpers/test_verify_required_fields_present.py

@@ -0,0 +1,60 @@
+import pandas as pd
+import pytest
+
+from gcf_data_mapper.parsers.helpers import verify_required_fields_present
+
+
+@pytest.mark.parametrize(
+    ("test_df", "expected_fields", "expected_error"),
+    [
+        (
+            pd.DataFrame(
+                {
+                    "fruits": ["apple", "banana", "cherry"],
+                }
+            ),
+            set(["fruits", "vegetables"]),
+            "Required fields '{'vegetables'}' not present in df columns '{'fruits'}'",
+        ),
+        (
+            pd.DataFrame(),
+            set(["cars"]),
+            "Required fields '{'cars'}' not present in df columns '{}'",
+        ),
+    ],
+)
+def test_returns_false_when_missing_fields(
+    test_df: pd.DataFrame, expected_fields: set[str], expected_error: str
+):
+    with pytest.raises(AttributeError) as e:
+        verify_required_fields_present(test_df, expected_fields)
+    assert str(e.value) == expected_error
+
+
+@pytest.mark.parametrize(
+    ("test_df", "expected_fields"),
+    [
+        (
+            pd.DataFrame(
+                {
+                    "fruits": ["date", "elderberry", "fig"],
+                    "vegetables": ["asparagus", "beetroot", "carrot"],
+                }
+            ),
+            set(["fruits", "vegetables"]),
+        ),
+        (
+            pd.DataFrame(
+                {
+                    "cars": ["Ford", "Renault", "Audi"],
+                }
+            ),
+            set(["cars"]),
+        ),
+    ],
+)
+def test_returns_true_when_no_missing_fields(
+    test_df: pd.DataFrame, expected_fields: set[str]
+):
+    return_value = verify_required_fields_present(test_df, expected_fields)
+    assert return_value is True