strip topup libraries

Author: williamputraintan

lib/workload/stateless/stacks/sample-sheet-check/sample-sheet-check-lambda/src/samplesheet.py

@@ -174,7 +174,7 @@ def set_metadata_row_for_sample(self, metadata_df):
         """
         library_id_column_var = METADATA_COLUMN_NAMES["library_id"]
         sample_id_column_var = METADATA_COLUMN_NAMES["sample_id"]
-        library_id_var = self.library_id
+        library_id_var = SAMPLE_REGEX_OBJS["topup"].sub('', self.library_id)
         sample_id_var = self.sample_id
 
         # Query for specific dataframe value
@@ -457,27 +457,25 @@ def set_metadata_from_api(self, auth_header):
         library_id_array = []
 
         for sample in self:
-            library_id_array.append(sample.library_id)
 
             # check that the primary library for the topup exists
             if SAMPLE_REGEX_OBJS["topup"].search(sample.library_id) is not None:
                 logger.info("{} is a top up sample. Investigating the previous sample".format(sample.unique_id))
                 orig_unique_id = SAMPLE_REGEX_OBJS["topup"].sub('', sample.unique_id)
-
                 unique_id_regex_obj = SAMPLE_REGEX_OBJS["unique_id"].match(orig_unique_id)
 
                 # Sample ID is the first group and the library ID is the second group
                 topup_sample_id = unique_id_regex_obj.group(1)
                 topup_library_id = unique_id_regex_obj.group(2)
-
                 # Appending these original sample/library id to the search query
                 library_id_array.append(topup_library_id)
+            else:
+                library_id_array.append(sample.library_id)
 
         try:
             metadata_response = get_metadata_record_from_array_of_field_name(auth_header=auth_header,
                                                                              field_name='library_id',
                                                                              value_list=library_id_array)
-
         except Exception as e:
             raise ApiCallError("Fail to fetch metadata api for library id in the sample sheet")
 

lib/workload/stateless/stacks/sample-sheet-check/sample-sheet-check-lambda/src/v2_samplesheet_builder.py

@@ -21,7 +21,7 @@
     V2_SAMPLESHEET_BCLCONVERT_ADAPTER_SETTINGS_BY_ASSAY_TYPE,
     V2_ADAPTER_SETTINGS, V2_DATA_ROWS, V2_SAMPLESHEET_GLOBAL_SETTINGS, V2_SAMPLESHEET_DATA_SETTINGS,
     V2_BCLCONVERT_BASESPACE_URN, V2_BCLCONVERT_BASESPACE_SOFTWARE_VERSION,
-    EXPERIMENT_REGEX_STR
+    EXPERIMENT_REGEX_STR, SAMPLE_REGEX_OBJS
 )
 from v2_samplesheet_maker.functions.v2_samplesheet_writer import v2_samplesheet_writer
 
@@ -46,7 +46,8 @@ def get_bclconvert_adapter_setting_by_type_and_assay(sample_type: str, sample_as
             if setting_value is not None:
                 return setting_value
     else:
-        logger.debug(f"Could not get the bclconvert settings for this type / assay combination '{sample_type}' / '{sample_assay}'")
+        logger.debug(
+            f"Could not get the bclconvert settings for this type / assay combination '{sample_type}' / '{sample_assay}'")
 
 
 def get_bclconvert_settings_by_library_id(library_id: str, samplesheet: SampleSheet) -> Dict:
@@ -259,11 +260,11 @@ def get_bclconvert_data_list(samplesheet: SampleSheet) -> List:
     for index, data_row in samplesheet.data.iterrows():
         # Drop datadict
         data_dict = dict(data_row)
-
+        library_id = SAMPLE_REGEX_OBJS["topup"].sub('', data_dict["Sample_Name"])
         # Add bclconvert settings
         data_dict.update(
             get_bclconvert_settings_by_library_id(
-                library_id=data_dict["Sample_Name"],
+                library_id=library_id,
                 samplesheet=samplesheet
             )
         )