Merge pull request #80 from UMCUGenetics/feature/gendercheckY

Feature/gendercheckY

clarity_epp.py

@@ -115,10 +115,16 @@ def export_removed_samples(args):
     clarity_epp.export.sample.removed_samples(lims, args.output_file)
 
 
-def export_sample_indications(args):
-    """Export sample indication table."""
-    clarity_epp.export.sample.sample_indications(
-        lims, args.output_file, args.artifact_name, args.sequencing_run, args.sequencing_run_project
+def export_sample_udf(args):
+    "Export sample udf table."""
+    clarity_epp.export.sample.sample_udf(
+        lims,
+        args.output_file,
+        args.artifact_name,
+        args.sequencing_run,
+        args.sequencing_run_project,
+        args.udf,
+        args.column_name
     )
 
 
@@ -335,16 +341,18 @@ def placement_pipetting(args):
     )
     parser_export_removed_samples.set_defaults(func=export_removed_samples)
 
-    parser_export_sample_indications = subparser_export.add_parser(
-        'sample_indications', help='Export sample indication table.', parents=[output_parser]
+    parser_export_sample_udf = subparser_export.add_parser(
+        'sample_udf', help='Export sample udf table.', parents=[output_parser]
     )
-    parser_export_sample_indications_group = parser_export_sample_indications.add_mutually_exclusive_group(required=True)
-    parser_export_sample_indications_group.add_argument('-a', '--artifact_name', help='Artifact name')
-    parser_export_sample_indications_group.add_argument('-r', '--sequencing_run', help='Sequencing run name')
-    parser_export_sample_indications.add_argument(
+    parser_export_sample_udf_group = parser_export_sample_udf.add_mutually_exclusive_group(required=True)
+    parser_export_sample_udf_group.add_argument('-a', '--artifact_name', help='Artifact name')
+    parser_export_sample_udf_group.add_argument('-r', '--sequencing_run', help='Sequencing run name')
+    parser_export_sample_udf.add_argument(
         '-p', '--sequencing_run_project',  nargs='?', help='Sequencing run project name'
     )
-    parser_export_sample_indications.set_defaults(func=export_sample_indications)
+    parser_export_sample_udf.add_argument('-u', '--udf', help='udf to query')
+    parser_export_sample_udf.add_argument('-c', '--column_name', help='naming of column')
+    parser_export_sample_udf.set_defaults(func=export_sample_udf)
 
     parser_export_sample_related_mip = subparser_export.add_parser(
         'sample_related_mip', help='Export related mip samples.', parents=[output_parser]

clarity_epp/export/ped.py

@@ -33,7 +33,7 @@ def create_file(lims, process_id, output_file):
                 ped_sample['sex'] = 0
 
             # Determine affection
-            ped_sample['affection'] = 0  # unkown
+            ped_sample['affection'] = 0  # unknown
             if 'Bevestiging diagnose' in sample.udf['Dx Onderzoeksreden']:
                 ped_sample['affection'] = 2  # affected
             elif 'Informativiteitstest' in sample.udf['Dx Onderzoeksreden']:

clarity_epp/export/sample.py

@@ -124,8 +124,8 @@ def removed_samples(lims, output_file):
                 ))
 
 
-def sample_indications(lims, output_file, artifact_name=None, sequencing_run=None, sequencing_run_project=None):
-    """Export table with sample indications. Lookup samples by sample name or sequencing run (project)."""
+def get_samples(lims, artifact_name=None, sequencing_run=None, sequencing_run_project=None):
+    """Lookup samples by sample name or sequencing run (project)."""
     samples = []
 
     # Get samples by artifact_name
@@ -142,22 +142,28 @@ def sample_indications(lims, output_file, artifact_name=None, sequencing_run=Non
         artifacts = lims.get_artifacts(type='Analyte', udf=udf_query)
         samples = {artifact.name: artifact.samples[0] for artifact in artifacts}
 
+    return samples
+
+
+def sample_udf(lims, output_file, artifact_name=None, sequencing_run=None, sequencing_run_project=None, udf=None, column_name=None):
+    """Export table with sample udf."""
+    samples = get_samples(lims, artifact_name, sequencing_run, sequencing_run_project)
     # Write result
     if samples:
-        output_file.write('Sample\tIndication\n')
+        output_file.write(f'Sample\t{column_name}\n')
         for sample_name, sample in samples.items():
-            if 'Dx Onderzoeksindicatie' in sample.udf:
+            if udf in sample.udf:
                 output_file.write(
-                    '{sample}\t{indication}\n'.format(
+                    '{sample}\t{udf_value}\n'.format(
                         sample=sample_name,
-                        indication=sample.udf['Dx Onderzoeksindicatie'].split(';')[0]  # select newest indication
+                        udf_value=sample.udf[udf].split(';')[0]  # select newest udf value
                     )
                 )
             else:
                 output_file.write(
-                    '{sample}\t{indication}\n'.format(
+                    '{sample}\t{udf_value}\n'.format(
                         sample=sample_name,
-                        indication='unkown_indication'
+                        udf_value='unknown'
                     )
                 )
     else:

requirements.txt

@@ -1,3 +1,5 @@
 genologics==0.3.20
 argparse==1.4.0
-xmltodict==0.12.0
+xmltodict==0.12.0
+pytest==7.0.1
+pytest-mock==3.6.1

tests/test_export_sample.py

@@ -0,0 +1,49 @@
+import sys
+
+from clarity_epp.export import sample
+
+
+class MyMock:
+    def __init__(self, udf):
+        self.udf = udf
+
+
+def test_sample_udf_withudf(mocker, capsys):
+    # Test output for sample with known udf in database
+    patched_clarity_epp = mocker.patch(
+        'clarity_epp.export.sample.get_samples',
+        return_value=samples_mock
+    )
+    sample.sample_udf("lims", sys.stdout, udf=udf_value, column_name=column_name)
+    captured = capsys.readouterr()
+    assert captured.out == f"Sample\t{column_name}\n{sample_name}\t{geslacht}\n"
+
+
+def test_sample_udf_withoutudf(mocker, capsys):
+    # Test output for sample with no known udf in database
+    patched_clarity_epp = mocker.patch(
+        'clarity_epp.export.sample.get_samples',
+        return_value=samples_mock
+    )
+    sample.sample_udf("lims", sys.stdout, udf="udf2", column_name=column_name)
+    captured = capsys.readouterr()
+    assert captured.out == f"Sample\t{column_name}\n{sample_name}\tunknown\n"
+
+
+def test_sample_udf_nosamples(mocker, capsys):
+    # Test output for sample not known in database
+    patched_clarity_epp = mocker.patch(
+        'clarity_epp.export.sample.get_samples',
+        return_value=None
+    )
+    sample.sample_udf("lims", sys.stdout)
+    captured = capsys.readouterr()
+    assert captured.out == "no_sample_found\n"
+
+
+column_name = "test_column"
+sample_name = "test_sample"
+udf_value = "Dx geslacht"
+geslacht = "Vrouw"
+samples_mock = {}
+samples_mock[sample_name] = MyMock({udf_value: geslacht})