EVA-4248: Validate project title and desciption lengths

eva_sub_cli/etc/eva_schema.json

@@ -89,12 +89,14 @@
             "title": {
               "type": "string",
               "description": "Title of the project",
-              "maxLength": 500
+              "minLength": 20,
+              "maxLength": 250
             },
             "description": {
               "type": "string",
               "description": "Description of the project",
-              "maxLength": 5000
+              "minLength": 20,
+              "maxLength": 4000
             },
             "centre": {
               "type": "string",

tests/resources/EVA_Submission_test.json

@@ -18,7 +18,7 @@
     }
   ],
   "project": {
-    "title": "Example Project",
+    "title": "Example Project Title",
     "description": "An example project for demonstration purposes",
     "centre": "University of Example",
     "taxId": 9606,

tests/resources/EVA_Submission_test_with_asm_report.json

@@ -20,7 +20,7 @@
     }
   ],
   "project": {
-    "title": "Example Project",
+    "title": "Example Project Title",
     "projectAlias": "EP",
     "description": "An example project for demonstration purposes",
     "centre": "University of Example",

tests/resources/EVA_Submission_test_with_non_vcf_files.json

@@ -18,7 +18,7 @@
     }
   ],
   "project": {
-    "title": "Example Project",
+    "title": "Example Project Title",
     "description": "An example project for demonstration purposes",
     "centre": "University of Example",
     "taxId": 9606,

tests/resources/metadata_with_filename.json

@@ -1,7 +1,7 @@
 {
   "submitterDetails": [],
   "project": {
-    "title": "Example Project",
+    "title": "Example Project Title",
     "description": "An example project for demonstration purposes",
     "centre": "University of Example",
     "taxId": 9606,

tests/resources/validation_reports/expected_metadata_json_report.txt

@@ -72,7 +72,7 @@ For requirements, please refer to the EVA website (https://www.ebi.ac.uk/eva/?Su
 VCF VALIDATION RESULTS
 Checks whether each file is compliant with the VCF specification (http://samtools.github.io/hts-specs/VCFv4.4.pdf).
 Also checks whether the variants' reference alleles match against the reference assembly.
-ASSEMBLY CHECK RESULTS
+    ASSEMBLY CHECK
             ❌ input_fail.vcf: 26/36 (72.22%)
             First 10 errors per category are below. Full report: /path/to/assembly_failed/report
                 Parsing error: The assembly checking could not be completed: Contig 'chr23' not found in assembly report
@@ -86,7 +86,7 @@ ASSEMBLY CHECK RESULTS
                 Mismatch error: Chromosome 1, position 35819, reference allele 'T' does not match the reference sequence, expected 'a'
                 Mismatch error: Chromosome 1, position 35822, reference allele 'T' does not match the reference sequence, expected 'c'
             ✔ input_passed.vcf: 247/247 (100.0%)
-VCF VALIDATION RESULTS
+    VCF CHECK
 		❌ input_fail.vcf: 1 critical errors, 1 non-critical errors
             First 10 errors per category are below. Full report: /path/to/vcf_failed/report
                 Critical error: Line 4: Error in meta-data section.

tests/resources/validation_reports/expected_metadata_xlsx_report.txt

@@ -66,7 +66,7 @@ For requirements, please refer to the EVA website (https://www.ebi.ac.uk/eva/?Su
 VCF VALIDATION RESULTS
 Checks whether each file is compliant with the VCF specification (http://samtools.github.io/hts-specs/VCFv4.4.pdf).
 Also checks whether the variants' reference alleles match against the reference assembly.
-ASSEMBLY CHECK RESULTS
+    ASSEMBLY CHECK
             ❌ input_fail.vcf: 26/36 (72.22%)
             First 10 errors per category are below. Full report: /path/to/assembly_failed/report
                 Parsing error: The assembly checking could not be completed: Contig 'chr23' not found in assembly report
@@ -80,7 +80,7 @@ ASSEMBLY CHECK RESULTS
                 Mismatch error: Chromosome 1, position 35819, reference allele 'T' does not match the reference sequence, expected 'a'
                 Mismatch error: Chromosome 1, position 35822, reference allele 'T' does not match the reference sequence, expected 'c'
             ✔ input_passed.vcf: 247/247 (100.0%)
-VCF VALIDATION RESULTS
+    VCF CHECK
 		❌ input_fail.vcf: 1 critical errors, 1 non-critical errors
             First 10 errors per category are below. Full report: /path/to/vcf_failed/report
                 Critical error: Line 4: Error in meta-data section.

tests/resources/validation_reports/expected_report_metadata_json_crashed.txt

@@ -32,9 +32,9 @@ For requirements, please refer to the EVA website (https://www.ebi.ac.uk/eva/?Su
 VCF VALIDATION RESULTS
 Checks whether each file is compliant with the VCF specification (http://samtools.github.io/hts-specs/VCFv4.4.pdf).
 Also checks whether the variants' reference alleles match against the reference assembly.
-ASSEMBLY CHECK RESULTS
+    ASSEMBLY CHECK
 ❗ Assembly check did not complete successfully. Check the logs for more information.
-VCF VALIDATION RESULTS
+    VCF CHECK
 ❗ VCF check did not complete successfully. Check the logs for more information.
 -
 SAMPLE NAME CONCORDANCE CHECK

tests/resources/validation_reports/expected_report_metadata_json_process_not_run.txt

@@ -32,9 +32,9 @@ For requirements, please refer to the EVA website (https://www.ebi.ac.uk/eva/?Su
 VCF VALIDATION RESULTS
 Checks whether each file is compliant with the VCF specification (http://samtools.github.io/hts-specs/VCFv4.4.pdf).
 Also checks whether the variants' reference alleles match against the reference assembly.
-ASSEMBLY CHECK RESULTS
+    ASSEMBLY CHECK
 ⏸ Process not run yet
-VCF VALIDATION RESULTS
+    VCF CHECK
 ⏸ Process not run yet
 -
 SAMPLE NAME CONCORDANCE CHECK

tests/resources/validation_reports/expected_shallow_metadata_xlsx_report.txt

@@ -75,7 +75,7 @@ For requirements, please refer to the EVA website (https://www.ebi.ac.uk/eva/?Su
 VCF VALIDATION RESULTS
 Checks whether each file is compliant with the VCF specification (http://samtools.github.io/hts-specs/VCFv4.4.pdf).
 Also checks whether the variants' reference alleles match against the reference assembly.
-ASSEMBLY CHECK RESULTS
+    ASSEMBLY CHECK
             ❌ input_fail.vcf: 26/36 (72.22%)
             First 10 errors per category are below. Full report: /path/to/assembly_failed/report
                 Parsing error: The assembly checking could not be completed: Contig 'chr23' not found in assembly report
@@ -89,7 +89,7 @@ ASSEMBLY CHECK RESULTS
                 Mismatch error: Chromosome 1, position 35819, reference allele 'T' does not match the reference sequence, expected 'a'
                 Mismatch error: Chromosome 1, position 35822, reference allele 'T' does not match the reference sequence, expected 'c'
             ✔ input_passed.vcf: 247/247 (100.0%)
-VCF VALIDATION RESULTS
+    VCF CHECK
 		❌ input_fail.vcf: 1 critical errors, 1 non-critical errors
             First 10 errors per category are below. Full report: /path/to/vcf_failed/report
                 Critical error: Line 4: Error in meta-data section.

tests/resources/validation_reports/validation_output/other_validations/metadata_validation.txt

@@ -13,7 +13,7 @@
 /project/title
 	should have required property 'title'
 /project/description
-	must NOT have more than 5000 characters
+	must NOT have more than 4000 characters
 /project/taxId
         must have required property 'taxId'
 /project/holdDate

tests/test_orchestrator.py

@@ -25,7 +25,7 @@
 
 
 class TestOrchestrator(unittest.TestCase):
-    project_title = 'Example Project'
+    project_title = 'Example Project Title'
     resource_dir = os.path.join(os.path.dirname(__file__), 'resources')
     test_sub_dir = os.path.join(resource_dir, 'test_sub_dir')
     config_file = os.path.join(test_sub_dir, SUB_CLI_CONFIG_FILE)
@@ -97,7 +97,7 @@ def test_remove_non_vcf_files_from_metadata_xlsx(self):
     def test_get_project_title_and_create_vcf_files_mapping(self):
         project_title, mapping_file = get_project_title_and_create_vcf_files_mapping(
             self.test_sub_dir, self.metadata_json_with_non_vcf_files, None, None)
-        assert project_title == 'Example Project'
+        assert project_title == 'Example Project Title'
         with open(mapping_file, 'r') as f:
             reader = csv.reader(f)
             next(reader)

tests/test_validator.py

@@ -58,7 +58,7 @@
         'json_errors': [
             {'property': '/files', 'description': "should have required property 'files'"},
             {'property': '/project/title', 'description': "should have required property 'title'"},
-            {'property': '/project/description', 'description': 'must NOT have more than 5000 characters'},
+            {'property': '/project/description', 'description': 'must NOT have more than 4000 characters'},
             {'property': '/project/taxId', 'description': "must have required property 'taxId'"},
             {'property': '/project/holdDate', 'description': 'must match format "date"'},
             {'property': '/analysis/0/description',
@@ -469,7 +469,7 @@ def test__collect_validation_workflow_results_with_metadata_xlsx(self):
             {'sheet': 'Project', 'row': 3, 'column': 'Project Title',
              'description': 'Column "Project Title" is not populated'},
             {'sheet': 'Project', 'row': 3, 'column': 'Description',
-             'description': 'must NOT have more than 5000 characters'},
+             'description': 'must NOT have more than 4000 characters'},
             {'sheet': 'Project', 'row': 3, 'column': 'Taxonomy ID',
              'description': 'Column "Taxonomy ID" is not populated'},
             {'sheet': 'Project', 'row': 3, 'column': 'Hold Date',
@@ -509,7 +509,7 @@ def test_parse_biovalidator_validation_results(self):
         assert self.validator.results['metadata_check']['json_errors'] == [
             {'property': '/files', 'description': "should have required property 'files'"},
             {'property': '/project/title', 'description': "should have required property 'title'"},
-            {'property': '/project/description', 'description': 'must NOT have more than 5000 characters'},
+            {'property': '/project/description', 'description': 'must NOT have more than 4000 characters'},
             {'property': '/project/taxId', 'description': "must have required property 'taxId'"},
             {'property': '/project/holdDate', 'description': 'must match format "date"'},
             {'property': '/analysis/0/description', 'description': "should have required property 'description'"},

tests/test_xlsx2json.py

@@ -225,7 +225,7 @@ def get_expected_json(self):
                 }
             ],
             "project": {
-                "title": "Example Project",
+                "title": "Example Project Title",
                 "description": "An example project for demonstration purposes",
                 "centre": "University of Example",
                 "taxId": 9606,