Added test for assay column matching

Added 'FAILED' to LZ status that is okay for usage
Linting

cubi_tk/snappy/itransfer_common.py

@@ -489,11 +489,13 @@ def get_landing_zone_uuid_by_path(self, lz_irods_path, project_uuid, assay_uuid=
             existing_lzs = list(filter(lambda x: x.assay == assay_uuid, existing_lzs))
 
         matching_lzs = list(filter(lambda x: x.irods_path == lz_irods_path, existing_lzs))
-        if matching_lzs and matching_lzs[0].status == 'ACTIVE':
+        if matching_lzs and matching_lzs[0].status in ("ACTIVE", "FAILED"):
             lz_uuid = matching_lzs[0].sodar_uuid
         else:
-            msg = "Could not find an active LZ with the given path. Please review input: {0}".format(
-                lz_irods_path
+            msg = (
+                "Could not find an active LZ with the given path. Please review input: {0}".format(
+                    lz_irods_path
+                )
             )
             logger.error(msg)
             raise ParameterException(msg)

tests/conftest.py

@@ -74,3 +74,26 @@ def my_exists(self):
 def my_get_sodar_info(_self):
     """Method is used to patch cubi_tk.snappy.itransfer_common.SnappyItransferCommandBase.get_sodar_info"""
     return "466ab946-ce6a-4c78-9981-19b79e7bbe86", "/irods/dest"
+
+
+def my_sodar_api_export(n_assays=1):
+    """Return contents for api.samplesheet.export"""
+    assay = textwrap.dedent(
+        """
+        Sample Name\tProtocol REF\tParameter Value[Concentration measurement]\tPerformer\tDate\tExtract Name\tCharacteristics[Concentration]\tUnit\tTerm Source REF\tTerm Accession Number\tProtocol REF\tParameter Value[Provider name]\tParameter Value[Provider contact]\tParameter Value[Provider project ID]\tParameter Value[Provider sample ID]\tParameter Value[Provider QC status]\tParameter Value[Requestor contact]\tParameter Value[Requestor project]\tParameter Value[Requestor sample ID]\tParameter Value[Concentration measurement]\tParameter Value[Library source]\tParameter Value[Library strategy]\tParameter Value[Library selection]\tParameter Value[Library layout]\tParameter Value[Library kit]\tComment[Library kit catalogue ID]\tParameter Value[Target insert size]\tParameter Value[Wet-lab insert size]\tParameter Value[Barcode kit]\tParameter Value[Barcode kit catalogue ID]\tParameter Value[Barcode name]\tParameter Value[Barcode sequence]\tPerformer\tDate\tLibrary Name\tCharacteristics[Folder name]\tCharacteristics[Concentration]\tUnit\tTerm Source REF\tTerm Accession Number\tProtocol REF\tParameter Value[Platform]\tParameter Value[Instrument model]\tParameter Value[Base quality encoding]\tParameter Value[Center name]\tParameter Value[Center contact]\tPerformer\tDate\tRaw Data File
+        Sample1-N1\tNucleic acid extraction WES\t\t\t\tSample1-N1-DNA1\t\t\t\t\tLibrary construction WES\t\t\t\t\t\t\t\t\t\tGENOMIC\tWXS\tHybrid Selection\tPAIRED\tAgilent SureSelect Human All Exon V7\t\t\t\t\t\t\t\t\t\tSample1-N1-DNA1-WES1\tFolder1\t\t\t\t\tNucleic acid sequencing WES\tILLUMINA\tIllumina NovaSeq 6000\tPhred+33
+        Sample2-N1\tNucleic acid extraction WES\t\t\t\tSample2-N1-DNA1\t\t\t\t\tLibrary construction WES\t\t\t\t\t\t\t\t\t\tGENOMIC\tWXS\tHybrid Selection\tPAIRED\tAgilent SureSelect Human All Exon V7\t\t\t\t\t\t\t\t\t\tSample2-N1-DNA1-WES1\tFolder2\t\t\t\t\tNucleic acid sequencing WES\tILLUMINA\tIllumina NovaSeq 6000\tPhred+33
+        Sample3-N1\tNucleic acid extraction WES\t\t\t\tSample3-N1-DNA1\t\t\t\t\tLibrary construction WES\t\t\t\t\t\t\t\t\t\tGENOMIC\tWXS\tHybrid Selection\tPAIRED\tAgilent SureSelect Human All Exon V7\t\t\t\t\t\t\t\t\t\tSample3-N1-DNA1-WES1\tFolder3\t\t\t\t\tNucleic acid sequencing WES\tILLUMINA\tIllumina NovaSeq 6000\tPhred+33
+        """
+    ).lstrip()
+
+    isa_dict = {
+        "investigation": {"path": "i_Investigation.txt", "tsv": None},
+        "studies": {"s_Study_0.txt": {"tsv": None}},
+        "assays": {"a_name_0": {"tsv": assay}},
+    }
+    if n_assays > 1:
+        for i in range(1, n_assays):
+            isa_dict["assays"]["a_name_%d" % i] = {"tsv": assay}
+
+    return isa_dict

tests/test_sodar_ingest_fastq.py

@@ -6,14 +6,19 @@
 import json
 import os
 import re
+import unittest
 from unittest import mock
+from unittest.mock import patch
 
 from pyfakefs import fake_filesystem, fake_pathlib
 import pytest
 
 from cubi_tk.__main__ import main, setup_argparse
+from cubi_tk.exceptions import ParameterException
+from cubi_tk.sodar.ingest_fastq import SodarIngestFastq
 
-from .conftest import my_get_sodar_info
+from .conftest import my_get_sodar_info, my_sodar_api_export
+from .factories import InvestigationFactory
 
 
 def test_run_sodar_ingest_fastq_help(capsys):
@@ -57,6 +62,68 @@ def test_run_sodar_ingest_fastq_src_regex():
         assert res.groupdict()["sample"] == expected_sample
 
 
+@patch("cubi_tk.sodar.ingest_fastq.api.samplesheet.retrieve")
+@patch("cubi_tk.sodar.ingest_fastq.api.samplesheet.export")
+def test_run_sodar_ingest_fastq_get_match_to_collection_mapping(mock_api_export, mock_api_retrieve):
+    # Patched sodar API call
+    mock_api_export.return_value = my_sodar_api_export()
+
+    # Instantiate SodarIngestFastq (seems to require args?)
+    landing_zone_uuid = "466ab946-ce6a-4c78-9981-19b79e7bbe86"
+    project_uuid = "466ab946-ce6a-4c78-9981-19b79e7bbe86"
+    fake_base_path = "/base/path"
+    argv = [
+        "--verbose",
+        "sodar",
+        "ingest-fastq",
+        "--num-parallel-transfers",
+        "0",
+        "--sodar-api-token",
+        "XXXX",
+        "--yes",
+        fake_base_path,
+        landing_zone_uuid,
+    ]
+
+    parser, _subparsers = setup_argparse()
+    args = parser.parse_args(argv)
+    ingestfastq = SodarIngestFastq(args)
+
+    # test to get expected dict
+    expected = {
+        "Folder1": "Sample1-N1-DNA1-WES1",
+        "Folder2": "Sample2-N1-DNA1-WES1",
+        "Folder3": "Sample3-N1-DNA1-WES1",
+    }
+
+    assert expected == ingestfastq.get_match_to_collection_mapping(project_uuid, "Folder name")
+    assert expected == ingestfastq.get_match_to_collection_mapping(
+        project_uuid, "Folder name", "Library Name"
+    )
+
+    # Test for alternative collection column
+    expected2 = {
+        "Folder1": "Sample1-N1-DNA1",
+        "Folder2": "Sample2-N1-DNA1",
+        "Folder3": "Sample3-N1-DNA1",
+    }
+    assert expected2 == ingestfastq.get_match_to_collection_mapping(
+        project_uuid, "Folder name", "Extract Name"
+    )
+
+    # Test for missing column
+    with unittest.TestCase.assertRaises(unittest.TestCase, ParameterException):
+        ingestfastq.get_match_to_collection_mapping(project_uuid, "Typo-Column")
+
+    # Test with additional assay
+    mock_api_export.return_value = my_sodar_api_export(2)
+    mock_api_retrieve.return_value = InvestigationFactory()
+    assay_uuid = list(mock_api_retrieve.return_value.studies["s_Study_0"].assays.keys())[0]
+    ingestfastq.args.assay = assay_uuid
+
+    assert expected == ingestfastq.get_match_to_collection_mapping(project_uuid, "Folder name")
+
+
 def test_run_sodar_ingest_fastq_smoke_test(mocker, requests_mock):
     # --- setup arguments
     irods_path = "/irods/dest"