organize properties as required

Author: oscar-castro-bl

src/allotropy/allotrope/schema_mappers/adm/plate_reader/benchling/_2023/_09/plate_reader.py

@@ -86,6 +86,7 @@ class ImageFeature:
     feature: str
     result: float | InvalidJsonFloat
     data_sources: list[DataSource] | None = None
+    custom_info: dict[str, Any] | None = None
 
 
 @dataclass(frozen=True)
@@ -561,15 +562,18 @@ def _get_processed_data_aggregate_document(
                     processed_data_identifier=data.identifier,
                     image_feature_aggregate_document=ImageFeatureAggregateDocument(
                         image_feature_document=[
-                            ImageFeatureDocumentItem(
-                                image_feature_identifier=image_feature.identifier,
-                                image_feature_name=image_feature.feature,
-                                image_feature_result=TQuantityValueUnitless(
-                                    value=image_feature.result
-                                ),
-                                data_source_aggregate_document=self._get_data_source_aggregate_document(
-                                    image_feature.data_sources
+                            add_custom_information_document(
+                                ImageFeatureDocumentItem(
+                                    image_feature_identifier=image_feature.identifier,
+                                    image_feature_name=image_feature.feature,
+                                    image_feature_result=TQuantityValueUnitless(
+                                        value=image_feature.result
+                                    ),
+                                    data_source_aggregate_document=self._get_data_source_aggregate_document(
+                                        image_feature.data_sources
+                                    ),
                                 ),
+                                image_feature.custom_info,
                             )
                             for image_feature in data.features
                         ]

src/allotropy/parsers/ctl_immunospot/ctl_immunospot_reader.py

@@ -202,8 +202,6 @@ def _read_plate_data_7_0_38(self, reader: CsvReader) -> list[pd.DataFrame]:
         return plates
 
     def _read_header(self, reader: CsvReader) -> SeriesData:
-        lines = [line.strip() for line in reader.pop_until_empty(EMPTY_STR_OR_CSV_LINE)]
-
         def fix_line(line: str) -> str:
             # Add missing key for file path line.
             if line.endswith(".txt") or line.endswith(".xls"):
@@ -213,13 +211,45 @@ def fix_line(line: str) -> str:
                 line = f"Review Date: {date_str}"
             return line.strip()
 
-        lines = [fix_line(line) for raw_line in lines for line in raw_line.split(";")]
+        def split_multi_key_line(line: str) -> list[str]:
+            """Split lines that contain multiple key-value pairs into separate lines."""
+            line = line.strip().strip('"').strip()  # Clean up quotes and whitespace
+
+            # Case 1: Parenthetical format: (Auto Areas: Estimated, Manual Areas: Normalized)
+            if line.startswith("(") and line.endswith(")") and "," in line:
+                return [pair.strip() for pair in line[1:-1].split(",")]
+
+            # Case 2: Tab-separated format: Assay: 1\t\t\t\t\t\tEdge Compensation Level: 1.0
+            if "\t" in line and line.count(":") > 1:
+                return [
+                    part.strip()
+                    for part in line.split("\t")
+                    if part.strip() and ":" in part
+                ]
+
+            return [line]
+
+        def process_lines(raw_lines: list[str]) -> list[str]:
+            """Process a list of raw lines and return split/fixed lines."""
+            processed = []
+            for raw_line in raw_lines:
+                for line in raw_line.split(";"):
+                    fixed_line = fix_line(line)
+                    processed.extend(split_multi_key_line(fixed_line))
+            return processed
+
+        # Process initial header lines
+        lines = [line.strip() for line in reader.pop_until_empty(EMPTY_STR_OR_CSV_LINE)]
+        all_lines = process_lines(lines)
+
+        # Process additional header lines if they exist
         reader.drop_empty(EMPTY_STR_OR_CSV_LINE)
         if ":" in (reader.get() or ""):
-            lines.extend(list(reader.pop_until_empty(EMPTY_STR_OR_CSV_LINE)))
+            additional_lines = list(reader.pop_until_empty(EMPTY_STR_OR_CSV_LINE))
+            all_lines.extend(process_lines(additional_lines))
 
         df = read_csv(
-            StringIO("\n".join(lines)),
+            StringIO("\n".join(all_lines)),
             sep=r"^([^:]+):\s+",
             header=None,
             engine="python",

src/allotropy/parsers/ctl_immunospot/ctl_immunospot_structure.py

@@ -33,8 +33,14 @@ def _create_measurement(
     well_plate_identifier: str,
     plate_data: dict[str, pd.DataFrame],
     histograms: dict[str, tuple[list[float], list[float]]],
+    header_data: dict[str, float | str | None],
 ) -> Measurement:
     location_identifier = f"{well_row}{well_col}"
+    image_custom_info = {
+        "Min. SpotSize": header_data.pop("Min. SpotSize", None),
+        "Max. SpotSize": header_data.pop("Max. SpotSize", None),
+        "Spot Separation": header_data.pop("Spot Separation", None),
+    }
     return Measurement(
         type_=MeasurementType.OPTICAL_IMAGING,
         device_type=constants.DEVICE_TYPE,
@@ -50,6 +56,7 @@ def _create_measurement(
                     identifier=random_uuid_str(),
                     feature=name,
                     result=float(data[well_col][well_row]),
+                    custom_info=image_custom_info,
                 )
                 for name, data in plate_data.items()
             ],
@@ -77,6 +84,7 @@ def _create_measurement(
         ]
         if histograms and location_identifier in histograms
         else None,
+        device_control_custom_info=header_data,
     )
 
 
@@ -94,16 +102,23 @@ def create_measurement_groups(
         round_to_nearest_well_count(first_plate.size),
         f"Unable to determine valid plate count from dataframe of size: {first_plate.size}",
     )
+    measurement_time = header[str, ("Counted", "Review Date")]
+    analyst = header[str, "Authenticated user"]
+    custom_info = {
+        "Assay": header.get(str, "Assay"),
+    }
+    header_data = header.get_unread()
     return [
         MeasurementGroup(
             plate_well_count=plate_well_count,
-            measurement_time=header[str, ("Counted", "Review Date")],
-            analyst=header[str, "Authenticated user"],
+            measurement_time=measurement_time,
+            analyst=analyst,
             measurements=[
                 _create_measurement(
-                    row, col, well_plate_identifier, plate_data, histograms
+                    row, col, well_plate_identifier, plate_data, histograms, header_data
                 )
             ],
+            custom_info=custom_info,
         )
         for row in first_plate.index
         for col in first_plate.columns
@@ -128,5 +143,4 @@ def create_metadata(header: SeriesData) -> Metadata:
             re.match(r"^ImmunoSpot ([\d\.]+)$", header[str, "Software version"]),
             msg="Unable to parse software version",
         ).group(1),
-        custom_info=header.get_unread(),
     )