Add config validation

nad_ch/application/data_reader.py

@@ -27,6 +27,26 @@ def read_column_map(self) -> dict[any]:
                 )
         return column_map_config
 
+    def validate_column_map(self):
+        column_map = self.column_map["data_column_mapping"]
+        column_map_reverse = {}
+
+        for key, values in column_map.items():
+            for value in values:
+                value_lcase = value.lower()
+                if value_lcase in column_map_reverse:
+                    column_map_reverse[value_lcase].append(key)
+                else:
+                    column_map_reverse[value_lcase] = [key]
+        duplicates = {k: v for k, v in column_map_reverse.items() if len(v) > 1}
+        if duplicates:
+            duplicate_nad_fields = ", ".join(
+                [" & ".join(nad_fields) for nad_fields in list(duplicates.values())]
+            )
+            raise Exception(
+                f"Duplicate inputs found for destination fields: {duplicate_nad_fields}"
+            )
+
     def rename_columns(self, gdf: GeoDataFrame) -> GeoDataFrame:
         column_map = self.column_map["data_column_mapping"]
         original_names = {col.lower(): col for col in gdf.columns}

nad_ch/application/nad_column_maps/testprovider1.yaml

@@ -25,6 +25,7 @@ data_column_mapping:
     - AREASQMETER
   COL_2:
     - TRACT
+    - Pacific
   COL_20:
     - Shape_Length
   COL_21:
@@ -39,6 +40,7 @@ data_column_mapping:
     - TOTPOP
   COL_6:
     - POPDENS
+    - totPop
   COL_7:
     - RACEBASE
   COL_8:

tests/application/test_data_reader.py

@@ -6,6 +6,7 @@
 )
 import pickle
 from pandas.testing import assert_frame_equal
+import pytest
 
 TEST_DATA_DIR = "tests/test_data"
 
@@ -36,6 +37,19 @@ def test_read_column_map():
     )
 
 
+def test_validate_column_map():
+    with pytest.raises(Exception) as exc:
+        reader = DataReader("testprovider1")
+        reader.validate_column_map()
+    assert (
+        str(exc.value)
+        == "Duplicate inputs found for destination fields: COL_13 & COL_2, COL_5 & COL_6"
+    )
+
+    reader = DataReader("testprovider2")
+    reader.validate_column_map()
+
+
 def test_read_file_in_batches_shape():
     file_path = os.path.join(
         TEST_DATA_DIR, "shapefiles/usa-major-cities/usa-major-cities.shp"

tests/test_data/config_baselines.py

@@ -96,14 +96,14 @@
         "COL_17": ["LASTEDITOR"],
         "COL_18": ["AGEMAJOR"],
         "COL_19": ["AREASQMETER"],
-        "COL_2": ["TRACT"],
+        "COL_2": ["TRACT", "Pacific"],
         "COL_20": ["Shape_Length"],
         "COL_21": ["Shape_Area"],
         "COL_22": ["geometry"],
         "COL_3": ["STFID"],
         "COL_4": ["BLOCK"],
         "COL_5": ["TOTPOP"],
-        "COL_6": ["POPDENS"],
+        "COL_6": ["POPDENS", "totPop"],
         "COL_7": ["RACEBASE"],
         "COL_8": ["WHITE"],
         "COL_9": ["BLACK"],