eva-sub-cli 0.4.14__tar.gz → 0.5.0__tar.gz

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.4.14
+Version: 0.5.0
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/docker/Dockerfile

@@ -1,7 +1,7 @@
 FROM python:3.10
 
 ENV vcf_validator_version=0.10.2
-ENV NXF_VER=22.10.6
+ENV NXF_VER=23.10.0
 
 WORKDIR /opt
 

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.4.14'
-__version_tuple__ = version_tuple = (0, 4, 14)
+__version__ = version = '0.5.0'
+__version_tuple__ = version_tuple = (0, 5, 0)
 
-__commit_id__ = commit_id = 'g1808b05b1'
+__commit_id__ = commit_id = 'g1b663fd41'

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/etc/eva_schema.json

@@ -64,66 +64,81 @@
       }
     },
     "project": {
-      "type": "object",
-      "description": "General information about the Project",
-      "required": [
-        "title",
-        "description",
-        "taxId",
-        "centre"
-      ],
-      "properties": {
-        "title": {
-          "type": "string",
-          "description": "Title of the project",
-          "maxLength": 500
-        },
-        "description": {
-          "type": "string",
-          "description": "Description of the project",
-          "maxLength": 5000
-        },
-        "centre": {
-          "type": "string",
-          "description": "Centre, institute or company submitting the project"
-        },
-        "taxId": {
-          "type": "number",
-          "description": "Taxonomy ID of the species associated with the project (found here: http://www.ncbi.nlm.nih.gov/taxonomy)"
-        },
-        "publications": {
-          "type": "array",
-          "items": true
-        },
-        "parentProject": {
-          "$ref": "#/definitions/projectAccession"
-        },
-        "childProjects": {
-          "type": "array",
-          "items": {
-            "$ref": "#/definitions/projectAccession"
-          }
-        },
-        "peerProjects": {
-          "type": "array",
-          "items": {
-            "$ref": "#/definitions/projectAccession"
+      "oneOf": [
+        {
+          "type": "object",
+          "required": [
+            "projectAccession"
+          ],
+          "properties": {
+            "projectAccession": {
+              "$ref": "#/definitions/projectAccession"
+            }
           }
         },
-        "links": {
-          "type": "array",
-          "items": {
-            "type": "string"
+        {
+          "type": "object",
+          "description": "General information about the Project",
+          "required": [
+            "title",
+            "description",
+            "taxId",
+            "centre"
+          ],
+          "properties": {
+            "title": {
+              "type": "string",
+              "description": "Title of the project",
+              "maxLength": 500
+            },
+            "description": {
+              "type": "string",
+              "description": "Description of the project",
+              "maxLength": 5000
+            },
+            "centre": {
+              "type": "string",
+              "description": "Centre, institute or company submitting the project"
+            },
+            "taxId": {
+              "type": "number",
+              "description": "Taxonomy ID of the species associated with the project (found here: http://www.ncbi.nlm.nih.gov/taxonomy)"
+            },
+            "publications": {
+              "type": "array",
+              "items": true
+            },
+            "parentProject": {
+              "$ref": "#/definitions/projectAccession"
+            },
+            "childProjects": {
+              "type": "array",
+              "items": {
+                "$ref": "#/definitions/projectAccession"
+              }
+            },
+            "peerProjects": {
+              "type": "array",
+              "items": {
+                "$ref": "#/definitions/projectAccession"
+              }
+            },
+            "links": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            },
+            "holdDate": {
+              "type": "string",
+              "format": "date",
+              "examples": [
+                "2018-11-13"
+              ]
+            }
           }
-        },
-        "holdDate": {
-          "type": "string",
-          "format": "date",
-          "examples": [
-            "2018-11-13"
-          ]
         }
-      }
+      ]
     },
     "analysis": {
       "type": "array",

eva_sub_cli-0.5.0/eva_sub_cli/etc/spreadsheet2json_conf.yaml

@@ -0,0 +1,139 @@
+#Configuration for defining which fields in which worksheets to be parsed in an Excel file
+#
+#At the top level, "worksheets" defines a list of worksheets (titles) to be parsed.
+#Then for each worksheet, you define which fields to be parsed from this worksheet.
+#These fields are either "required", "optional" and/or header_row. "required" fields must be found
+#in the worksheet so that this worksheet is valid. Otherwise this worksheet is not
+#valid. The field names must match those values in the header row in the worksheet.
+#
+#This is a YAML file
+
+# List of worksheets to be parsed.
+worksheets:
+  Submitter Details: submitterDetails
+  Project: project
+  Analysis: analysis
+  Sample: sample
+  Files: files
+
+Submitter Details:
+  required:
+    Last Name: lastName
+    First Name: firstName
+    Email Address: email
+    Laboratory: laboratory
+    Center: centre
+  optional:
+    Address: address
+
+# List of field for Projects
+Project:
+  header_row: 3
+  optional:
+    Project Accession: projectAccession
+    Project Title: title
+    Description: description
+    Center: centre
+    Taxonomy ID: taxId
+    Publication(s): publications
+    Parent Project: parentProject
+    Child Project(s): childProjects
+    Peer Project(s): peerProjects
+    Link(s): links
+    Hold Date: holdDate
+    Collaborator(s): collaborators
+    Strain: strain
+    Breed: breed
+    Broker: broker
+  cast:
+    Publication(s): list
+    Child Project(s): list
+    Peer Project(s): list
+    Link(s): list
+    Hold Date: date
+    Taxonomy ID: integer
+
+Analysis:
+  required:
+    Analysis Title: analysisTitle
+    Analysis Alias: analysisAlias
+    Description: description
+    Experiment Type: experimentType
+    Reference: referenceGenome
+  optional:
+    Reference Fasta Path: referenceFasta
+    Platform: platform
+    Software: software
+    Pipeline Description: pipelineDescriptions
+    Imputation: imputation
+    Phasing: phasing
+    Centre: centre
+    Date: date
+    Link(s): links
+    Run Accession(s): runAccessions
+  cast:
+    Run Accession(s): list
+    Imputation: boolean
+    Phasing: boolean
+    Date: date
+    Software: list
+
+Sample:
+  header_row: 3
+  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
+    Title: title
+    Description: description
+    Unique Name: uniqueName
+    Prefix: prefix
+    Subject: subject
+    Derived From: derivedFrom
+    Taxonomy ID: taxId
+    Scientific Name: scientific name
+    Common Name: commonName
+    mating_type: mating_type
+    sex: sex
+    population: population
+    cell_type: cell_type
+    dev_stage: dev_stage
+    germline: germline
+    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: 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: sub_species
+    variety: variety
+    sub_strain: sub_strain
+    cell_line: cell_line
+    serotype: serotype
+    serovar: serovar
+  cast:
+    collection_date: date
+    Taxonomy ID: integer
+
+
+Files:
+  required:
+    Analysis Alias: analysisAlias
+    File Name: fileName

eva_sub_cli-0.4.14/eva_sub_cli/etc/spreadsheet2json_conf.yaml → eva_sub_cli-0.5.0/eva_sub_cli/etc/spreadsheet2json_conf_V2.yaml

@@ -50,6 +50,8 @@ Project:
     Peer Project(s): list
     Link(s): list
     Hold Date: date
+    Taxonomy ID: integer
+
 
 Analysis:
   required:
@@ -127,12 +129,12 @@ Sample:
     serotype: serotype
     serovar: serovar
   cast:
-    Sample ID: string
-    BioSample Name: string
     collection_date: date
+    Taxonomy ID: integer
+
 
 
 Files:
   required:
     Analysis Alias: analysisAlias
-    File Name: fileName
+    File Name: fileName

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/executables/cli.py

@@ -151,4 +151,7 @@ def main():
     except MetadataTemplateVersionNotFoundException as mte:
         print(mte)
         exit_status = 70
+    except Exception as ex:
+        print(ex)
+        exit_status = 71
     return exit_status

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/executables/xlsx2json.py

@@ -103,9 +103,7 @@ class XlsxParser:
     @staticmethod
     def cast_value(value, type_name):
         # Do not cast None values
-        if type_name and value is not None:
-            if type_name == 'string':
-                return str(value)
+        if value is not None:
             if type_name == 'boolean':
                 return str(value).lower() in ['true', '1', "'1'", 't', 'y', 'yes']
             if type_name == 'list':
@@ -114,6 +112,10 @@ class XlsxParser:
                 return [v for v in split_values if v]
             if type_name == 'date':
                 return XlsxParser.serialize(value)
+            if type_name == 'integer':
+                return int(value)
+            # Default any value is cast to string
+            return str(value)
         return value
 
     @staticmethod
@@ -179,15 +181,20 @@ class XlsxParser:
         return rows
 
     def get_project_json_data(self):
+        json_key = self.xlsx_conf[WORKSHEETS_KEY_NAME][PROJECT]
+
         project_data = self.get_rows()
         if len(project_data) > 1:
             logger.warning(f"{PROJECT} worksheet expects a single row of info but more than one found in the file. "
                            f"Only the first row's data will be taken into consideration")
+        elif len(project_data) == 0:
+            logger.error(f"{PROJECT} worksheet expects a single row of info but no info is found in the file.")
+            self.add_error(f"{PROJECT} worksheet expects a single row of info but no info is found in the file.")
+            return {json_key: {}}
 
         first_row = project_data[0]
         first_row.pop('row_num')
 
-        json_key = self.xlsx_conf[WORKSHEETS_KEY_NAME][PROJECT]
         json_value = {self.translate_header(PROJECT, k): v for k, v in first_row.items() if v is not None}
         return {json_key: json_value}
 

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/jinja_templates/html/file_validation.html

@@ -20,7 +20,7 @@
         {% set row_class = "report-section fail collapsible" %}
     {% elif error_count > 0 %}
         {% set expand_icon = "▶" %}
-        {% set icon = "❌" %}
+        {% set icon = "❗" %}
         {% set row_class = "report-section warn collapsible" %}
     {% else %}
         {% set icon = "✔" %}

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/jinja_templates/text/file_validation.txt

@@ -13,8 +13,10 @@
 {% macro vcf_check(vcf_check_result) %}
     {% set critical_count = vcf_check_result.get("critical_count", 0) %}
     {% set error_count = vcf_check_result.get("error_count", 0) %}
-    {% if critical_count > 0 or error_count > 0 %}
+    {% if critical_count > 0 %}
         {% set icon = "\u274C" %}
+     {% elif error_count > 0 %}
+        {% set icon = "\u26A0" %}
     {% else %}
         {% set icon = "\u2714" %}
     {% endif %}

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/nextflow/validation.nf

@@ -7,10 +7,11 @@ def helpMessage() {
     Validate a set of VCF files and metadata to check if they are valid to be submitted to EVA.
 
     Inputs:
-            --vcf_files_mapping     csv file with the mappings for vcf files, fasta and assembly report
-            --output_dir            output_directory where the reports will be output
-            --metadata_json         Json file describing the project, analysis, samples and files
-            --metadata_xlsx         Excel file describing the project, analysis, samples and files
+            --vcf_files_mapping         csv file with the mappings for vcf files, fasta and assembly report
+            --output_dir                output_directory where the reports will be output
+            --metadata_json             Json file describing the project, analysis, samples and files
+            --metadata_xlsx             Excel file describing the project, analysis, samples and files
+            --conversion_configuration_name  Name of the configuration file for converting metadata_xlsx to metadata_json. This is only needed if you are working with metadata spreadsheet and not json
     """
 }
 
@@ -44,16 +45,18 @@ params.shallow_validation = false
 if (params.help) exit 0, helpMessage()
 
 // Test input files
-if (!params.vcf_files_mapping || !params.output_dir || (!params.metadata_json && !params.metadata_xlsx)) {
+if (!params.vcf_files_mapping || !params.output_dir || (!params.metadata_json && !params.metadata_xlsx) || (!params.metadata_json && params.metadata_xlsx && !params.conversion_configuration_name)) {
     if (!params.vcf_files_mapping)      log.warn('Provide a csv file with the mappings (vcf, fasta, assembly report) --vcf_files_mapping')
-    if (!params.metadata_xlsx)           log.warn('Provide a json file with the metadata description of the project and analysis --metadata_json')
     if (!params.output_dir)             log.warn('Provide an output directory where the reports will be copied using --output_dir')
     if (!params.metadata_json && !params.metadata_xlsx)   log.warn('Provide a json or Excel file with the metadata description of the project and analysis --metadata_json or --metadata_xlsx')
+    if (params.metadata_xlsx && !params.conversion_configuration_name)   log.warn('Provide a name of the configuration file to convert the metadata xlsx file to json --params.conversion_configuration_name')
     exit 1, helpMessage()
 }
 
 schema_dir = file(projectDir).parent + '/etc'
-conversion_configuration = schema_dir + '/spreadsheet2json_conf.yaml'
+conversion_configuration = "${schema_dir}/$params.conversion_configuration_name"
+
+
 
 def joinBasePath(path) {
     if (path){
@@ -240,7 +243,6 @@ process convert_xlsx_2_json {
 
     script:
     metadata_json = metadata_xlsx.getBaseName() + '.json'
-
     """
     $params.python_scripts.xlsx2json --metadata_xlsx $metadata_xlsx --metadata_json metadata.json --errors_yaml metadata_conversion_errors.yml --conversion_configuration $conversion_configuration > xlsx2json.log 2>&1
     """

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/orchestrator.py

@@ -25,6 +25,7 @@ from eva_sub_cli.metadata import EvaMetadataJson
 from eva_sub_cli.submission_ws import SubmissionWSClient
 from eva_sub_cli.submit import StudySubmitter, SUB_CLI_CONFIG_KEY_SUBMISSION_ID, \
     SUB_CLI_CONFIG_KEY_SUBMISSION_UPLOAD_URL
+from eva_sub_cli.utils import get_project_title_from_ena
 from eva_sub_cli.validators.docker_validator import DockerValidator
 from eva_sub_cli.validators.native_validator import NativeValidator
 from eva_sub_cli.validators.validator import READY_FOR_SUBMISSION_TO_EVA
@@ -47,7 +48,7 @@ def get_vcf_files(mapping_file):
 
 
 def get_project_title_and_create_vcf_files_mapping(submission_dir, vcf_files, reference_fasta,
-                                                   metadata_json, metadata_xlsx):
+                                                   metadata_json, metadata_xlsx, metadata_xlsx_version):
     """
     Get project title and mapping between VCF files and reference FASTA files, from three sources: command line
         arguments, metadata JSON file, or metadata XLSX file.
@@ -57,6 +58,7 @@ def get_project_title_and_create_vcf_files_mapping(submission_dir, vcf_files, re
     :param reference_fasta: Reference FASTA from command line, if present
     :param metadata_json: Metadata JSON from command line, if present
     :param metadata_xlsx: Metadata XLSX from command line, if present
+    :param metadata_xlsx_version: Version of metadata XLSX
     :return: Project title and path to the mapping file
     """
     mapping_file = os.path.join(submission_dir, 'vcf_mapping_file.csv')
@@ -71,11 +73,11 @@ def get_project_title_and_create_vcf_files_mapping(submission_dir, vcf_files, re
             if metadata_json:
                 project_title, _ = get_project_and_vcf_fasta_mapping_from_metadata_json(metadata_json, False)
             elif metadata_xlsx:
-                project_title, _ = get_project_and_vcf_fasta_mapping_from_metadata_xlsx(metadata_xlsx, False)
+                project_title, _ = get_project_and_vcf_fasta_mapping_from_metadata_xlsx(metadata_xlsx, metadata_xlsx_version, False)
         elif metadata_json:
             project_title, vcf_files_mapping = get_project_and_vcf_fasta_mapping_from_metadata_json(metadata_json, True)
         elif metadata_xlsx:
-            project_title, vcf_files_mapping = get_project_and_vcf_fasta_mapping_from_metadata_xlsx(metadata_xlsx, True)
+            project_title, vcf_files_mapping = get_project_and_vcf_fasta_mapping_from_metadata_xlsx(metadata_xlsx, metadata_xlsx_version, True)
 
         # Filter out non-vcf files
         vcf_files_mapping = [(vcf, fasta, report) for vcf, fasta, report in vcf_files_mapping if is_vcf_file(vcf)]
@@ -109,6 +111,10 @@ def get_project_and_vcf_fasta_mapping_from_metadata_json(metadata_json, mapping_
     metadata = EvaMetadataJson(metadata_json)
 
     project_title = metadata.project.get('title')
+    if not project_title:
+        project_accession = metadata.project.get('projectAccession')
+        if project_accession:
+            project_title = get_project_title_from_ena(project_accession)
 
     vcf_fasta_report_mapping = []
     if mapping_req:
@@ -168,7 +174,7 @@ def get_metadata_xlsx_template_link():
         return 'https://raw.githubusercontent.com/EBIvariation/eva-sub-cli/main/eva_sub_cli/etc/EVA_Submission_template.xlsx'
 
 
-def verify_metadata_xlsx_version(metadata_xlsx, min_req_version):
+def verify_and_get_metadata_xlsx_version(metadata_xlsx, min_req_version):
     workbook = load_workbook(metadata_xlsx)
     instructions_sheet = workbook['PLEASE READ FIRST']
     xlsx_sheet_version_value = instructions_sheet[3][0].value
@@ -184,15 +190,27 @@ def verify_metadata_xlsx_version(metadata_xlsx, min_req_version):
             f"No version information found in metadata xlsx sheet {metadata_xlsx}. "
             f"Please download the correct template from EVA github project {get_metadata_xlsx_template_link()}")
 
+    return xlsx_version
 
-def get_project_and_vcf_fasta_mapping_from_metadata_xlsx(metadata_xlsx, mapping_req=False):
+
+def get_project_and_vcf_fasta_mapping_from_metadata_xlsx(metadata_xlsx, metadata_xlsx_version, mapping_req=False):
     workbook = load_workbook(metadata_xlsx)
 
     project_sheet = workbook['Project']
     project_headers = {}
-    for cell in project_sheet[1]:
-        project_headers[cell.value] = cell.column
-    project_title = project_sheet.cell(row=2, column=project_headers['Project Title']).value
+
+    if version.parse(metadata_xlsx_version) < version.parse('3.0.0'):
+        for cell in project_sheet[1]:
+            project_headers[cell.value] = cell.column
+        project_title = project_sheet.cell(row=2, column=project_headers['Project Title']).value
+    else:
+        for cell in project_sheet[3]:
+            project_headers[cell.value] = cell.column
+        project_title = project_sheet.cell(row=4, column=project_headers['Project Title']).value
+        if not project_title:
+            project_accession = project_sheet.cell(row=4, column=project_headers['Project Accession']).value
+            if project_accession:
+                project_title = get_project_title_from_ena(project_accession)
 
     vcf_fasta_report_mapping = []
     if mapping_req:
@@ -273,14 +291,15 @@ def orchestrate_process(submission_dir, vcf_files, reference_fasta, metadata_jso
 
     if metadata_json:
         metadata_json = os.path.abspath(metadata_json)
+    metadata_xlsx_version = None
     if metadata_xlsx:
         metadata_xlsx = os.path.abspath(metadata_xlsx)
         # check metadata xlsx version is not lower than the required min metadata template version
-        verify_metadata_xlsx_version(metadata_xlsx, MINIMUM_METADATA_XLSX_TEMPLATE_VERSION)
+        metadata_xlsx_version = verify_and_get_metadata_xlsx_version(metadata_xlsx, MINIMUM_METADATA_XLSX_TEMPLATE_VERSION)
 
     # Get the provided Project Title and VCF files mapping (VCF, Fasta and Report)
     project_title, vcf_files_mapping = get_project_title_and_create_vcf_files_mapping(
-        submission_dir, vcf_files, reference_fasta, metadata_json, metadata_xlsx
+        submission_dir, vcf_files, reference_fasta, metadata_json, metadata_xlsx, metadata_xlsx_version
     )
     vcf_files = get_vcf_files(vcf_files_mapping)
 
@@ -290,12 +309,13 @@ def orchestrate_process(submission_dir, vcf_files, reference_fasta, metadata_jso
     if VALIDATE in tasks:
         if executor == DOCKER:
             validator = DockerValidator(vcf_files_mapping, submission_dir, project_title, metadata_json, metadata_xlsx,
-                                        shallow_validation=shallow_validation, submission_config=sub_config)
+                                        metadata_xlsx_version, shallow_validation=shallow_validation,
+                                        submission_config=sub_config)
         # default to native execution
         else:
             validator = NativeValidator(vcf_files_mapping, submission_dir, project_title, metadata_json, metadata_xlsx,
-                                        shallow_validation=shallow_validation, submission_config=sub_config,
-                                        nextflow_config=nextflow_config)
+                                        metadata_xlsx_version, shallow_validation=shallow_validation,
+                                        submission_config=sub_config, nextflow_config=nextflow_config)
         with validator:
             validator.validate_and_report()
             if not metadata_json:

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/semantic_metadata.py

@@ -4,12 +4,11 @@ from copy import deepcopy
 from datetime import datetime
 
 import yaml
-from requests import HTTPError
-
-from retry import retry
 from ebi_eva_common_pyutils.biosamples_communicators import NoAuthHALCommunicator
 from ebi_eva_common_pyutils.ena_utils import download_xml_from_ena, get_scientific_name_and_common_name
 from ebi_eva_common_pyutils.logger import AppLogger
+from requests import HTTPError
+from retry import retry
 
 from eva_sub_cli.date_utils import check_date
 
@@ -17,6 +16,7 @@ PROJECT_KEY = 'project'
 ANALYSIS_KEY = 'analysis'
 SAMPLE_KEY = 'sample'
 FILES_KEY = 'files'
+PROJECT_ACCESSION_KEY = 'projectAccession'
 PARENT_PROJECT_KEY = 'parentProject'
 CHILD_PROJECTS_KEY = 'childProjects'
 PEER_PROJECTS_KEY = 'peerProjects'
@@ -29,7 +29,8 @@ ANALYSIS_ALIAS_KEY = 'analysisAlias'
 ANALYSIS_RUNS_KEY = 'runAccessions'
 
 # Samples created before this date are not required to have collection date or geographic location
-threshold_2023 = datetime(2023,1,1)
+threshold_2023 = datetime(2023, 1, 1)
+
 
 def cast_list(l, type_to_cast=str):
     for e in l:
@@ -62,6 +63,8 @@ class SemanticMetadataChecker(AppLogger):
     def check_all_project_accessions(self):
         """Check that ENA project accessions exist and are public."""
         project = self.metadata[PROJECT_KEY]
+        if PROJECT_ACCESSION_KEY in project:
+            self.check_project_accession(project[PROJECT_ACCESSION_KEY], f'/{PROJECT_KEY}/{PROJECT_ACCESSION_KEY}')
         if PARENT_PROJECT_KEY in project:
             self.check_project_accession(project[PARENT_PROJECT_KEY], f'/{PROJECT_KEY}/{PARENT_PROJECT_KEY}')
         for idx, accession in enumerate(project.get(CHILD_PROJECTS_KEY, [])):
@@ -225,9 +228,9 @@ class SemanticMetadataChecker(AppLogger):
     def _should_bypass_error(self, sample_data, error):
         try:
             try:
-                created_dated = datetime.strptime(sample_data['create'],'%Y-%m-%dT%H:%M:%S.%fZ')
+                created_dated = datetime.strptime(sample_data['create'], '%Y-%m-%dT%H:%M:%S.%fZ')
             except ValueError:
-                created_dated = datetime.strptime(sample_data['create'],'%Y-%m-%dT%H:%M:%SZ')
+                created_dated = datetime.strptime(sample_data['create'], '%Y-%m-%dT%H:%M:%SZ')
             if created_dated < threshold_2023 and (
                     'collection date' in error or
                     'geographic location (country and/or sea)' in error
@@ -300,4 +303,5 @@ class SemanticMetadataChecker(AppLogger):
             analysis_alias = analysis.get(ANALYSIS_ALIAS_KEY)
             if analysis_alias and analysis_alias not in sample_analysis_aliases_set:
                 json_path = f'/{ANALYSIS_KEY}/{idx}'
-                self.add_error(property=json_path, description=f'No sample found for the analysis. Should have at the least one sample.')
+                self.add_error(property=json_path,
+                               description=f'No sample found for the analysis. Should have at the least one sample.')

{eva_sub_cli-0.4.14 → eva_sub_cli-0.5.0}/eva_sub_cli/submit.py

@@ -103,9 +103,10 @@ class StudySubmitter(AppLogger):
             return
 
         # upload submission
-        self.info(f'Upload data')
+        self.info(f'Start Uploading data')
         self._upload_submission()
+        self.info(f'Data Uploaded successfully')
 
         # Complete the submission
-        self.info(f'Complete submission')
         self._complete_submission()
+        self.info(f'Submission completed successfully')