feat: Migrate biorad_bioplex_manager to use SeriesData.get_unread (#1100)

Co-authored-by: joshua-benchling <jherna@benchling.com>

Author: oscar-castro-bl

src/allotropy/allotrope/schema_mappers/adm/multi_analyte_profiling/benchling/_2024/_09/multi_analyte_profiling.py

@@ -70,6 +70,7 @@ class Analyte:
     statistics: list[StatisticsDocument] | None = None
     statistic_datum_role: TStatisticDatumRole | None = None
     fluorescence: float | None = None
+    custom_info: dict[str, Any] | None = None
 
 
 @dataclass(frozen=True)
@@ -253,42 +254,45 @@ def _get_measurement_document(
             assay_bead_count=TQuantityValueNumber(value=measurement.assay_bead_count),
             analyte_aggregate_document=AnalyteAggregateDocument(
                 analyte_document=[
-                    AnalyteDocumentItem(
-                        analyte_identifier=analyte.identifier,
-                        analyte_name=analyte.name,
-                        assay_bead_identifier=analyte.assay_bead_identifier,
-                        assay_bead_count=TQuantityValueNumber(
-                            value=analyte.assay_bead_count
-                        ),
-                        fluorescence=quantity_or_none(
-                            TQuantityValueRelativeFluorescenceUnit,
-                            analyte.fluorescence,
-                            has_statistic_datum_role=analyte.statistic_datum_role,
-                        ),
-                        statistics_aggregate_document=(
-                            StatisticsAggregateDocument(
-                                statistics_document=[
-                                    StatisticsDocumentItem(
-                                        statistical_feature=statistic.statistical_feature,
-                                        statistic_dimension_aggregate_document=StatisticDimensionAggregateDocument(
-                                            statistic_dimension_document=[
-                                                StatisticDimensionDocumentItem(
-                                                    statistical_value=TQuantityValueModel(
-                                                        value=dimension.value,
-                                                        unit=dimension.unit,
-                                                        has_statistic_datum_role=dimension.statistic_datum_role,
-                                                    ),
-                                                )
-                                                for dimension in statistic.statistic_dimensions
-                                            ]
-                                        ),
-                                    )
-                                    for statistic in analyte.statistics
-                                ]
-                            )
-                            if analyte.statistics
-                            else None
+                    add_custom_information_document(
+                        AnalyteDocumentItem(
+                            analyte_identifier=analyte.identifier,
+                            analyte_name=analyte.name,
+                            assay_bead_identifier=analyte.assay_bead_identifier,
+                            assay_bead_count=TQuantityValueNumber(
+                                value=analyte.assay_bead_count
+                            ),
+                            fluorescence=quantity_or_none(
+                                TQuantityValueRelativeFluorescenceUnit,
+                                analyte.fluorescence,
+                                has_statistic_datum_role=analyte.statistic_datum_role,
+                            ),
+                            statistics_aggregate_document=(
+                                StatisticsAggregateDocument(
+                                    statistics_document=[
+                                        StatisticsDocumentItem(
+                                            statistical_feature=statistic.statistical_feature,
+                                            statistic_dimension_aggregate_document=StatisticDimensionAggregateDocument(
+                                                statistic_dimension_document=[
+                                                    StatisticDimensionDocumentItem(
+                                                        statistical_value=TQuantityValueModel(
+                                                            value=dimension.value,
+                                                            unit=dimension.unit,
+                                                            has_statistic_datum_role=dimension.statistic_datum_role,
+                                                        ),
+                                                    )
+                                                    for dimension in statistic.statistic_dimensions
+                                                ]
+                                            ),
+                                        )
+                                        for statistic in analyte.statistics
+                                    ]
+                                )
+                                if analyte.statistics
+                                else None
+                            ),
                         ),
+                        custom_info_doc=analyte.custom_info,
                     )
                     for analyte in measurement.analytes
                 ]

src/allotropy/parsers/biorad_bioplex_manager/biorad_bioplex_manager_parser.py

@@ -33,7 +33,11 @@ def create_data(self, named_file_contents: NamedFileContents) -> Data:
 
         samples_dict = SampleMetadata.create_samples(reader["Samples"])
         # Only parse system-level metadata once, from the first well.
-        system_metadata = SystemMetadata.create(reader["Wells"][0])
+        wells = reader["Wells"].findall("Well")
+        system_metadata = SystemMetadata.create(wells[0])
+        plate_dimensions = reader["PlateDimensions"]
+        plate_well_count = plate_dimensions.get_attr("TotalWells")
+        plate_dimensions.get_unread()
 
         return Data(
             create_metadata(
@@ -44,12 +48,12 @@ def create_data(self, named_file_contents: NamedFileContents) -> Data:
                     well,
                     samples_dict[well.name],
                     system_metadata,
-                    experimental_data_id=reader["NativeDocumentLocation"].text,
-                    experiment_type=reader["Description"].text,
-                    plate_well_count=int(
-                        reader.get_attribute("PlateDimensions", "TotalWells")
-                    ),
+                    experimental_data_id=reader[
+                        "NativeDocumentLocation"
+                    ].get_text_or_none(),
+                    experiment_type=reader["Description"].get_text_or_none(),
+                    plate_well_count=int(plate_well_count),
                 )
-                for well in [Well.create(well_xml) for well_xml in reader["Wells"]]
+                for well in [Well.create(well_xml) for well_xml in wells]
             ],
         )

src/allotropy/parsers/biorad_bioplex_manager/biorad_bioplex_manager_reader.py

@@ -7,15 +7,23 @@
 )
 from allotropy.named_file_contents import NamedFileContents
 from allotropy.parsers.biorad_bioplex_manager import constants
+from allotropy.parsers.utils.strict_xml_element import StrictXmlElement
 
 
 class BioradBioplexReader:
     def __init__(self, named_file_contents: NamedFileContents) -> None:
         contents = named_file_contents.contents.read()
+        # Ensure contents is bytes for StrictXmlElement.create_from_bytes()
+        if isinstance(contents, str):
+            contents = contents.encode("utf-8")
         try:
-            xml_tree = Et.ElementTree(Et.fromstring(contents))  # noqa: S314
-            self.root = xml_tree.getroot()
-            self.children = {child.tag: child for child in self.root}
+            self.root = StrictXmlElement.create_from_bytes(contents)
+            # Create a mapping of child tags to StrictXmlElement objects
+            self.children = {}
+            for child_tag in constants.EXPECTED_TAGS:
+                child_element = self.root.find_or_none(child_tag)
+                if child_element is not None:
+                    self.children[child_tag] = child_element
         except Et.ParseError as err:
             # Return all expected tags if XML parsing fails
             msg = "Error parsing xml"
@@ -31,12 +39,12 @@ def _validate(self) -> None:
             msg = f"Missing expected tags in xml: {missing_tags}"
             raise AllotropeConversionError(msg)
 
-    def __getitem__(self, child_tag: str) -> Et.Element:
+    def __getitem__(self, child_tag: str) -> StrictXmlElement:
         return get_key_or_error("child tag of root", child_tag, self.children)
 
     def get_attribute(self, child_tag: str, attribute: str) -> str:
         try:
-            return self[child_tag].attrib[attribute]
-        except KeyError as e:
-            msg = f"Unable to find '{attribute}' in {self[child_tag].attrib}"
+            return self[child_tag].get_attr(attribute)
+        except Exception as e:
+            msg = f"Unable to find '{attribute}' in {self[child_tag].element.attrib}"
             raise AllotropeConversionError(msg) from e