Feature/pdct 1453 update budget type checker to allow floats as well …

…as ints (#17)

* fix: add float to typing check for funding figures

* style : make outputs a bit more clearer

* Bump version to 0.1.12

---------

Co-authored-by: Osneil Drakes <[email protected]>

gcf_data_mapper/parsers/family.py

@@ -1,4 +1,4 @@
-from typing import Any, Iterable, Optional
+from typing import Any, Iterable, Optional, Union
 
 import click
 import pandas as pd
@@ -57,13 +57,15 @@ def calculate_status(row: pd.Series) -> Optional[str]:
     return None
 
 
-def get_budgets(funding_list: list[dict], source: str) -> Optional[list[int]]:
+def get_budgets(
+    funding_list: list[dict], source: str
+) -> Optional[list[Union[int, float]]]:
     """Get the budget amount from the row based on the funding source.
 
     :param list[dict] row: A list of all the funding information, represented in dictionaries
     :param str source: The funding source to retrieve the budget from.
 
-    :return Optional[list[int]]: A list of budget amounts corresponding to the source,
+    :return Optional[list[Union[int, float]]: A list of budget amounts corresponding to the source,
         or [0] if the source is not found.
     """
 
@@ -75,7 +77,7 @@ def get_budgets(funding_list: list[dict], source: str) -> Optional[list[int]]:
     ]
 
     # Check for any invalid values
-    if any(not isinstance(budget, (int)) for budget in budgets):
+    if any(not isinstance(budget, (int, float)) for budget in budgets):
         click.echo("🛑 Funding entries does not have valid int budget values")
         return None
 
@@ -164,16 +166,18 @@ def map_family_data(
     """
 
     family_metadata = map_family_metadata(row)
+    projects_id = row.at[FamilyColumnsNames.PROJECTS_ID.value]
 
     # When processing the family metadata if there are any empty/falsy values we return None
     # and skip the row. Therefore we don't want to process the rest of the family data so we
     # return None in this conditional.
     if family_metadata is None:
-        click.echo("🛑 Skipping row as family metadata has missing information")
+        click.echo(
+            f"🛑 Skipping row as family metadata has missing information, ProjectsID : {projects_id}"
+        )
         return None
 
     approved_ref = row.at[FamilyColumnsNames.APPROVED_REF.value]
-    projects_id = row.at[FamilyColumnsNames.PROJECTS_ID.value]
     summary = row.at[FamilyColumnsNames.SUMMARY.value]
     title = row.at[FamilyColumnsNames.TITLE.value]
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gcf-data-mapper"
-version = "0.1.11"
+version = "0.1.12"
 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/family/conftest.py

@@ -192,7 +192,7 @@ def mock_family_row_no_entities_no_regions():
 
 
 @pytest.fixture()
-def mock_family_row_with_non_int_budget_values():
+def mock_family_row_with_non_int_non_float_budget_values():
     yield pd.Series(
         {
             "ProjectsID": 3,
@@ -214,8 +214,8 @@ def mock_family_row_with_non_int_budget_values():
                 },
                 {
                     "Source": "Co-Financing",
-                    "Budget": 620000.20,
-                    "BudgetUSDeq": 620000.50,
+                    "Budget": "620000.20",
+                    "BudgetUSDeq": "620000.50",
                 },
             ],
             "ResultAreas": [

tests/unit_tests/parsers/family/test_map_family.py

@@ -152,15 +152,16 @@ def test_skips_processing_row_if_row_contains_empty_values(
 
 
 def test_skips_processing_row_if_family_metadata_has_missing_data(
-    mock_family_row_no_result_areas, capsys
+    mock_family_row_no_result_areas: pd.Series, capsys
 ):
+    projects_id = mock_family_row_no_result_areas.ProjectsID
     family_data = map_family_data(mock_family_row_no_result_areas)
     assert family_data is None
     captured = capsys.readouterr()
     # We have two outputs, one from map_family_metadata pointing to the missing data and the second
     # from map_family_data informing that the row is being skipped
     map_family_data_output = captured.out.strip().split("\n")
     assert (
-        "🛑 Skipping row as family metadata has missing information"
+        f"🛑 Skipping row as family metadata has missing information, ProjectsID : {projects_id}"
         == map_family_data_output[1]
     )

tests/unit_tests/parsers/family/test_map_family_metadata.py

@@ -129,9 +129,9 @@ def test_returns_expected_value_when_parsing_budget_data(
 
 
 def test_map_family_metadata_returns_none_if_budget_does_not_contain_valid_int_types(
-    mock_family_row_with_non_int_budget_values: pd.Series,
+    mock_family_row_with_non_int_non_float_budget_values: pd.Series,
 ):
-    result = map_family_metadata(mock_family_row_with_non_int_budget_values)
+    result = map_family_metadata(mock_family_row_with_non_int_non_float_budget_values)
     assert result is None