chore: Refactor custom data block in roche bioht parser (#1089)

Author: nathan-stender

src/allotropy/parsers/roche_cedex_bioht/roche_cedex_bioht_structure.py

@@ -75,48 +75,40 @@ def create(data: SeriesData) -> RawMeasurement:
         if error == BELOW_TEST_RANGE:
             error = data.get(str, "original concentration value", error)
 
-        custom_info = data.get_custom_keys(
-            {"detection kit", "detection kit range", "analyte code"}
-        )
-        custom_info["record type"] = data.get(str, "row type", None)
-        data.mark_read(
-            {
-                "sample identifier",
-                "batch identifier",
-                "col4",
-                "col5",
-                "col6",
-                "col8",
-                "col10",
-                "col11",
-                "col12",
-                "col13",
-                "original concentration value",
-                "sample role type",
-            }
-        )
-
-        if error:
-            custom_info["flag"] = error
-
-        measurement = RawMeasurement(
+        return RawMeasurement(
             data[str, "analyte name"],
             data[str, "measurement time"],
             value,
             unit,
             data[str, "analyte code"],
             error,
-            {},
+            custom_info=dict(
+                sorted(
+                    {
+                        **{
+                            # analyte code is read to generate the analyte id, but is not saved to a field, so include in custom data.
+                            "analyte code": data.get(str, "analyte code"),
+                            "record type": data.get(str, "row type"),
+                            "flag": error or None,
+                        },
+                        **data.get_unread(
+                            skip={
+                                # Sample and batch identifier are read in groupby operation.
+                                "sample identifier",
+                                "batch identifier",
+                                # Read by reader
+                                "sample role type",
+                                # Only read if there is an error.
+                                "original concentration value",
+                                # Skip unidentified columns (col1, col2, etc)
+                                r"col[\d]+",
+                            }
+                        ),
+                    }.items()
+                )
+            ),
         )
 
-        if isinstance(measurement.custom_info, dict):
-            custom_info.update(data.get_unread())
-            custom_info_sorted = dict(sorted(custom_info.items()))
-
-            measurement.custom_info.update(custom_info_sorted)
-
-        return measurement
-
     @staticmethod
     def _get_value_and_unit(value: JsonFloat, unit: str) -> tuple[JsonFloat, str]:
         multiplier = 1.0

tests/parsers/roche_cedex_bioht/roche_cedex_bioht_structure_test.py

@@ -113,7 +113,7 @@ def test_create_measurements() -> None:
                 "g/L",
                 "LAC2B",
                 None,
-                {"analyte code": "LAC2B", "record type": None},
+                {"analyte code": "LAC2B", "record type": None, "flag": None},
             ),
             "glutamine_GLN2B": RawMeasurement(
                 "glutamine",
@@ -122,7 +122,7 @@ def test_create_measurements() -> None:
                 "mmol/L",
                 "GLN2B",
                 None,
-                {"analyte code": "GLN2B", "record type": None},
+                {"analyte code": "GLN2B", "record type": None, "flag": None},
             ),
             "osmolality_OSM2B": RawMeasurement(
                 "osmolality",
@@ -131,7 +131,7 @@ def test_create_measurements() -> None:
                 "mosm/kg",
                 "OSM2B",
                 None,
-                {"analyte code": "OSM2B", "record type": None},
+                {"analyte code": "OSM2B", "record type": None, "flag": None},
             ),
         }
     }
@@ -162,7 +162,7 @@ def test_create_measurements_more_than_one_measurement_docs() -> None:
                 "g/L",
                 "LAC2B",
                 None,
-                {"analyte code": "LAC2B", "record type": None},
+                {"analyte code": "LAC2B", "record type": None, "flag": None},
             ),
             "glutamine_GLN2B": RawMeasurement(
                 "glutamine",
@@ -171,7 +171,7 @@ def test_create_measurements_more_than_one_measurement_docs() -> None:
                 "mmol/L",
                 "GLN2B",
                 None,
-                {"analyte code": "GLN2B", "record type": None},
+                {"analyte code": "GLN2B", "record type": None, "flag": None},
             ),
         },
         "2021-05-21T16:57:51+00:00": {
@@ -182,7 +182,7 @@ def test_create_measurements_more_than_one_measurement_docs() -> None:
                 "mmol/L",
                 "GLN2B",
                 None,
-                {"analyte code": "GLN2B", "record type": None},
+                {"analyte code": "GLN2B", "record type": None, "flag": None},
             ),
         },
     }
@@ -242,7 +242,7 @@ def test_create_sample() -> None:
                 "g/L",
                 "LAC2B",
                 None,
-                {"analyte code": "LAC2B", "record type": None},
+                {"analyte code": "LAC2B", "record type": None, "flag": None},
             ),
             "glutamine_GLN2B": RawMeasurement(
                 "glutamine",
@@ -251,7 +251,7 @@ def test_create_sample() -> None:
                 "mmol/L",
                 "GLN2B",
                 None,
-                {"analyte code": "GLN2B", "record type": None},
+                {"analyte code": "GLN2B", "record type": None, "flag": None},
             ),
         }
     }