fix: Thermo Fisher Scientific SkanIt - error detecing plate word matching

src/allotropy/parsers/thermo_skanit/constants.py

@@ -8,3 +8,5 @@
     "Ctrl": SampleRoleType.control_sample_role,
 }
 DEVICE_TYPE = "plate reader"
+
+PLATE_IDENTIFIER_PATTERN = r"\b(?:\w+\s+)?plate(?:\s+\d+)?\b"

src/allotropy/parsers/thermo_skanit/thermo_skanit_structure.py

@@ -19,7 +19,11 @@
 )
 from allotropy.exceptions import AllotropyParserError
 from allotropy.parsers.constants import NEGATIVE_ZERO, NOT_APPLICABLE
-from allotropy.parsers.thermo_skanit.constants import DEVICE_TYPE, SAMPLE_ROLE_MAPPINGS
+from allotropy.parsers.thermo_skanit.constants import (
+    DEVICE_TYPE,
+    PLATE_IDENTIFIER_PATTERN,
+    SAMPLE_ROLE_MAPPINGS,
+)
 from allotropy.parsers.utils.pandas import df_to_series_data, parse_header_row
 from allotropy.parsers.utils.uuids import random_uuid_str
 from allotropy.parsers.utils.values import try_float_or_none
@@ -443,8 +447,11 @@ def identify_data_and_sample_dfs(
                     reading_samples = False
                     continue
 
-            if "Plate" in row_str:
-                plate_match = re.search(r"Plate\s*(\d+)", row_str)
+            if "plate" in row_str.lower():
+                # Match "Plate 1", "Blank plate", "gch - Plate", etc.
+                plate_match = re.search(
+                    PLATE_IDENTIFIER_PATTERN, row_str, re.IGNORECASE
+                )
                 if plate_match:
                     current_plate_id = plate_match.group(0)
                     if current_plate_id not in plates_dict:

tests/parsers/thermo_skanit/testdata/skanit_different_plate_pattern.json

@@ -0,0 +1,112 @@
+{
+    "$asm.manifest": "http://purl.allotrope.org/manifests/plate-reader/REC/2025/03/plate-reader.manifest",
+    "plate reader aggregate document": {
+        "plate reader document": [
+            {
+                "measurement aggregate document": {
+                    "measurement document": [
+                        {
+                            "device control aggregate document": {
+                                "device control document": [
+                                    {
+                                        "device type": "plate reader",
+                                        "detection type": "Absorbance",
+                                        "detector wavelength setting": {
+                                            "value": 260.0,
+                                            "unit": "nm"
+                                        },
+                                        "custom information document": {
+                                            "Plate adapter name": "96-well adapter for plate without lid",
+                                            "Optical response compensation": "Yes",
+                                            "Plate adapter number": 2.0
+                                        }
+                                    }
+                                ]
+                            },
+                            "measurement identifier": "THERMO_SKANIT_TEST_ID_0",
+                            "sample document": {
+                                "location identifier": "A2",
+                                "sample identifier": "Blank1",
+                                "sample role type": "blank role",
+                                "well plate identifier": "Blank plate"
+                            },
+                            "absorbance": {
+                                "value": 0.0499,
+                                "unit": "mAU"
+                            },
+                            "experimental data identifier": "4-8-24 BD final"
+                        }
+                    ],
+                    "measurement time": "2024-05-08T15:54:50+00:00",
+                    "plate well count": {
+                        "value": 96,
+                        "unit": "#"
+                    },
+                    "container type": "well plate"
+                }
+            },
+            {
+                "measurement aggregate document": {
+                    "measurement document": [
+                        {
+                            "device control aggregate document": {
+                                "device control document": [
+                                    {
+                                        "device type": "plate reader",
+                                        "detection type": "Absorbance",
+                                        "detector wavelength setting": {
+                                            "value": 260.0,
+                                            "unit": "nm"
+                                        },
+                                        "custom information document": {
+                                            "Plate adapter name": "96-well adapter for plate without lid",
+                                            "Optical response compensation": "Yes",
+                                            "Plate adapter number": 2.0
+                                        }
+                                    }
+                                ]
+                            },
+                            "measurement identifier": "THERMO_SKANIT_TEST_ID_1",
+                            "sample document": {
+                                "location identifier": "A2",
+                                "sample identifier": "Un0001",
+                                "sample role type": "unknown sample role",
+                                "well plate identifier": "Sample Plate"
+                            },
+                            "absorbance": {
+                                "value": 0.058,
+                                "unit": "mAU"
+                            },
+                            "experimental data identifier": "4-8-24 BD final"
+                        }
+                    ],
+                    "measurement time": "2024-05-08T15:54:50+00:00",
+                    "plate well count": {
+                        "value": 96,
+                        "unit": "#"
+                    },
+                    "container type": "well plate"
+                }
+            }
+        ],
+        "data system document": {
+            "ASM file identifier": "skanit_different_plate_pattern.json",
+            "data system instance identifier": "N/A",
+            "UNC path": "tests/parsers/thermo_skanit/testdata/skanit_different_plate_pattern.xlsx",
+            "file name": "skanit_different_plate_pattern.xlsx",
+            "ASM converter name": "allotropy_thermo_fisher_scientific_skanit",
+            "ASM converter version": "0.1.109",
+            "software name": "SkanIt Software 7.0.2 RE for Microplate Readers RE",
+            "software version": "7.0.2.5",
+            "custom information document": {
+                "Dispenser": "No",
+                "ESW version": "1.00.38"
+            }
+        },
+        "device system document": {
+            "device identifier": "Varioskan LUX",
+            "model number": "Varioskan LUX",
+            "equipment serial number": "3020-83152"
+        }
+    }
+}

tests/parsers/thermo_skanit/thermo_skanit_structure_test.py

@@ -1,9 +1,13 @@
+import re
+
 import pandas as pd
+import pytest
 
 from allotropy.allotrope.models.shared.components.plate_reader import SampleRoleType
 from allotropy.allotrope.schema_mappers.adm.plate_reader.rec._2025._03.plate_reader import (
     MeasurementType,
 )
+from allotropy.parsers.thermo_skanit.constants import PLATE_IDENTIFIER_PATTERN
 from allotropy.parsers.thermo_skanit.thermo_skanit_structure import (
     DataThermoSkanIt,
     DataWell,
@@ -201,3 +205,35 @@ def test_create_skanit_data() -> None:
     skanit_data = DataThermoSkanIt.create(sheet_data=sheet_data, file_path="abc")
     assert len(skanit_data.measurement_groups) == 96
     assert skanit_data.metadata.equipment_serial_number == "3020-81776"
+
+
+@pytest.mark.parametrize(
+    "input_string,expected_match",
+    [
+        ("Plate 1", "Plate 1"),
+        ("Plate 2", "Plate 2"),
+        ("Plate 123", "Plate 123"),
+        ("Blank plate", "Blank plate"),
+        ("Sample Plate", "Sample Plate"),
+        ("blank plate", "blank plate"),
+        ("SAMPLE PLATE", "SAMPLE PLATE"),
+        ("plate", "plate"),
+    ],
+)
+def test_plate_identifier_regex_matching(
+    input_string: str, expected_match: str | None
+) -> None:
+    """Test that the plate identifier regex correctly matches valid plate names."""
+    match = re.search(PLATE_IDENTIFIER_PATTERN, input_string, re.IGNORECASE)
+
+    if expected_match is None:
+        assert (
+            match is None
+        ), f"Expected no match for '{input_string}', but got '{match.group(0) if match else None}'"
+    else:
+        assert (
+            match is not None
+        ), f"Expected to match '{expected_match}' in '{input_string}', but got no match"
+        assert (
+            match.group(0) == expected_match
+        ), f"Expected '{expected_match}', but got '{match.group(0)}'"