eva-sub-cli 0.4.12__tar.gz → 0.4.13__tar.gz

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.4.12
+Version: 0.4.13
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/eva_sub_cli/_version.py

@@ -1,7 +1,14 @@
 # file generated by setuptools-scm
 # don't change, don't track in version control
 
-__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
 
 TYPE_CHECKING = False
 if TYPE_CHECKING:
@@ -9,13 +16,19 @@ if TYPE_CHECKING:
     from typing import Union
 
     VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
 else:
     VERSION_TUPLE = object
+    COMMIT_ID = object
 
 version: str
 __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
 
-__version__ = version = '0.4.12'
-__version_tuple__ = version_tuple = (0, 4, 12)
+__version__ = version = '0.4.13'
+__version_tuple__ = version_tuple = (0, 4, 13)
+
+__commit_id__ = commit_id = 'gc6e52eaa9'

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/eva_sub_cli/etc/spreadsheet2json_conf.yaml

@@ -81,6 +81,8 @@ Sample:
   required:
     Analysis Alias: analysisAlias
     Sample Name in VCF: sampleInVCF
+  # Sample property names taken from ERC000011 where present
+  # See https://www.ebi.ac.uk/biosamples/schema-store/registry/schemas/ERC000011
   optional:
     Sample Accession: bioSampleAccession
     BioSample Name: bioSampleName
@@ -91,37 +93,37 @@ Sample:
     Subject: subject
     Derived From: derivedFrom
     Taxonomy ID: taxId
-    Scientific Name: scientificName
+    Scientific Name: scientific name
     Common Name: commonName
-    mating_type: matingType
+    mating_type: mating_type
     sex: sex
     population: population
-    cell_type: cellType
-    dev_stage: devStage
+    cell_type: cell_type
+    dev_stage: dev_stage
     germline: germline
-    tissue_lib: tissueLib
-    tissue_type: tissueType
-    bio_material: BioMaterial
-    culture_collection: cultureCollection
-    specimen_voucher: specimenVoucher
-    collected_by: collectedBy
-    collection_date: collectionDate
-    geographic location (country and/or sea): geographicLocationCountrySea
-    geographic location (region and locality): geographicLocationRegion
+    tissue_lib: tissue_lib
+    tissue_type: tissue_type
+    bio_material: bio_material
+    culture_collection: culture_collection
+    specimen_voucher: specimen_voucher
+    collected_by: collected_by
+    collection_date: collection date
+    geographic location (country and/or sea): geographic location (country and/or sea)
+    geographic location (region and locality): geographic location (region and locality)
     host: host
-    identified_by: identifiedBy
-    isolation_source: isolationSource
-    lat_lon: latLon
-    lab_host: LabHost
-    environmental_sample: environmentalSample
+    identified_by: identified_by
+    isolation_source: isolation_source
+    lat_lon: lat_lon
+    lab_host: lab_host
+    environmental_sample: environmental_sample
     cultivar: cultivar
     ecotype: ecotype
     isolate: isolate
     strain: strain
-    sub_species: subSpecies
+    sub_species: sub_species
     variety: variety
-    sub_strain: subStrain
-    cell_line: cellType
+    sub_strain: sub_strain
+    cell_line: cell_line
     serotype: serotype
     serovar: serovar
   cast:

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/eva_sub_cli/executables/xlsx2json.py

@@ -9,6 +9,8 @@ from ebi_eva_common_pyutils.logger import logging_config
 from openpyxl.reader.excel import load_workbook
 from openpyxl.workbook import Workbook
 
+from eva_sub_cli.orchestrator import get_sub_cli_version, get_sub_cli_github_tags
+
 WORKSHEETS_KEY_NAME = 'worksheets'
 REQUIRED_HEADERS_KEY_NAME = 'required'
 OPTIONAL_HEADERS_KEY_NAME = 'optional'
@@ -249,7 +251,8 @@ class XlsxParser:
         # If the file could not be loaded at all, return without generating JSON.
         if not self.file_loaded:
             return
-        json_data = {}
+        # Include which version of the EVA schema we are using
+        json_data = {'$schema': self.get_json_schema_link()}
         for title in self.xlsx_conf[WORKSHEETS_KEY_NAME]:
             self.active_worksheet = title
             if title == PROJECT:
@@ -270,6 +273,14 @@ class XlsxParser:
         with open(output_json_file, 'w') as open_file:
             json.dump(json_data, open_file, cls=DateTimeEncoder)
 
+    def get_json_schema_link(self):
+        sub_cli_version = get_sub_cli_version()
+        sub_cli_tags = get_sub_cli_github_tags()
+        if sub_cli_version in sub_cli_tags:
+            return f'https://raw.githubusercontent.com/EBIvariation/eva-sub-cli/refs/tags/v{sub_cli_version}/eva_sub_cli/etc/eva_schema.json'
+        else:
+            return 'https://raw.githubusercontent.com/EBIvariation/eva-sub-cli/main/eva_sub_cli/etc/eva_schema.json'
+
     def translate_header(self, title, header):
         if header in self.xlsx_conf[title].get(REQUIRED_HEADERS_KEY_NAME, {}):
             return self.xlsx_conf[title][REQUIRED_HEADERS_KEY_NAME][header]

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/eva_sub_cli/orchestrator.py

@@ -130,7 +130,10 @@ def get_project_and_vcf_fasta_mapping_from_metadata_json(metadata_json, mapping_
 
 def get_sub_cli_version():
     if version.parse(eva_sub_cli.__version__).is_devrelease:
-        major, minor, patch = map(int, version.parse(eva_sub_cli.__version__).base_version.split('.'))
+        version_values = [int(v) for v in version.parse(eva_sub_cli.__version__).base_version.split('.')]
+        major = version_values[0]
+        minor = version_values[1] if len(version_values) > 1 else 0
+        patch = version_values[2] if len(version_values) > 2 else 0
         if patch > 0:
             patch -= 1
         elif minor > 0:
@@ -160,7 +163,7 @@ def get_metadata_xlsx_template_link():
     sub_cli_version = get_sub_cli_version()
     sub_cli_tags = get_sub_cli_github_tags()
     if sub_cli_version in sub_cli_tags:
-        return f'https://raw.githubusercontent.com/EBIvariation/eva-sub-cli/v{sub_cli_version}/eva-sub-cli/eva_sub_cli/etc/EVA_Submission_template.xlsx'
+        return f'https://raw.githubusercontent.com/EBIvariation/eva-sub-cli/refs/tags/v{sub_cli_version}/eva_sub_cli/etc/EVA_Submission_template.xlsx'
     else:
         return 'https://raw.githubusercontent.com/EBIvariation/eva-sub-cli/main/eva_sub_cli/etc/EVA_Submission_template.xlsx'
 

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/eva_sub_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.4.12
+Version: 0.4.13
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/tests/test_check_fasta_insdc.py

@@ -132,5 +132,5 @@ class TestFastaChecker(TestCase):
     @pytest.mark.integration
     def test_get_containing_assemblies(self):
         results = get_containing_assemblies('6ac8f815bf8e845bb3031b73f812c012')
-        assert len(results) == 14
+        assert len(results) == 15
         assert 'GCA_000001405.29' in results

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/tests/test_orchestrator.py

@@ -306,7 +306,7 @@ class TestOrchestrator(unittest.TestCase):
                 patch('eva_sub_cli.orchestrator.get_sub_cli_github_tags') as sub_cli_tags:
             sub_cli_version.return_value = '1.1.6'
             sub_cli_tags.return_value = ['1.1.6']
-            assert get_metadata_xlsx_template_link() == 'https://raw.githubusercontent.com/EBIvariation/eva-sub-cli/v1.1.6/eva-sub-cli/eva_sub_cli/etc/EVA_Submission_template.xlsx'
+            assert get_metadata_xlsx_template_link() == 'https://raw.githubusercontent.com/EBIvariation/eva-sub-cli/refs/tags/v1.1.6/eva_sub_cli/etc/EVA_Submission_template.xlsx'
 
             sub_cli_version.return_value = '1.1.5'
             sub_cli_tags.return_value = ['1.1.6']

{eva_sub_cli-0.4.12 → eva_sub_cli-0.4.13}/tests/test_xlsx2json.py

@@ -55,7 +55,8 @@ class TestXlsReader(TestCase):
         with open(output_json) as open_file:
             json_data = json.load(open_file)
             # assert json file is created with expected data
-            assert sorted(json_data.keys()) == ['analysis', 'files', 'project', 'sample', 'submitterDetails']
+            assert sorted(json_data.keys()) == ['$schema', 'analysis', 'files', 'project', 'sample', 'submitterDetails']
+            json_data.pop('$schema', None)
             self.assertEqual(self.get_expected_json(), json_data)
 
         # assert json schema
@@ -94,7 +95,7 @@ class TestXlsReader(TestCase):
         assert os.path.exists(output_json)
         with open(output_json) as open_file:
             json_data = json.load(open_file)
-            assert sorted(json_data.keys()) == ['analysis', 'files', 'project', 'sample', 'submitterDetails']
+            assert sorted(json_data.keys()) == ['$schema', 'analysis', 'files', 'project', 'sample', 'submitterDetails']
             # required field taxId is missing
             assert 'taxId' not in json_data['project']
             # novel sample is missing scientific name in characteristics and sample name
@@ -220,19 +221,19 @@ class TestXlsReader(TestCase):
                             "taxId": [
                                 {"text": "9447"}
                             ],
-                            "scientificName": [
+                            "scientific name": [
                                 {"text": "Lemur catta"}
                             ],
                             "sex": [
                                 {"text": "Female"}
                             ],
-                            "tissueType": [
+                            "tissue_type": [
                                 {"text": "skin"}
                             ],
                             "species": [
                                 {"text": "Lemur catta"}
                             ],
-                            'collectionDate': [
+                            'collection date': [
                                 {'text': '2021-03-12'}
                             ]
                         }