eva-sub-cli 0.6.1__tar.gz → 0.6.3__tar.gz

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/.github/workflows/integration-tests.yml

@@ -6,6 +6,9 @@ on:
   pull_request:
     branches: [ main]
 
+permissions:
+  contents: read
+
 env:
   VCF_VALIDATOR_VERSION: "0.10.2"
   NXF_VER: "23.10.0"

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/.github/workflows/publish.yml

@@ -5,12 +5,15 @@ on:
     tags:
       - '**'
 
+permissions:
+  contents: read
+
 jobs:
   test:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.9"]
+        python-version: ["3.11"]
     steps:
     - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
@@ -38,7 +41,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: '3.9'
+        python-version: '3.11'
         cache: pip
         cache-dependency-path: '**/pyproject.toml'
     - name: Install dependencies

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/.github/workflows/tests.yml

@@ -4,14 +4,17 @@ on:
   push:
     branches: [ main ]
   pull_request:
-    branches: [ main, add-validation-tasks ]
+    branches: [ main ]
+
+permissions:
+  contents: read
 
 jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.9", "3.11", "3.12"]
+        python-version: ["3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v2

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/.github/workflows/trigger-eva-sub-cli-integration-tests.yml

@@ -4,6 +4,9 @@ on:
   push:
     branches: [main]
 
+permissions:
+  contents: read
+
 jobs:
   trigger-integration-tests:
     runs-on: ubuntu-latest

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.6.1
+Version: 0.6.3
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
@@ -19,7 +19,7 @@ Classifier: License :: OSI Approved :: Apache Software License
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: ebi_eva_common_pyutils==0.*,>=0.7.4
+Requires-Dist: ebi_eva_common_pyutils>=0.7.4
 Requires-Dist: jinja2==3.*,>=3.0.0
 Requires-Dist: jsonschema==4.*
 Requires-Dist: openpyxl==3.*

eva_sub_cli-0.6.3/eva_sub_cli/_version.py

@@ -0,0 +1,24 @@
+# file generated by vcs-versioning
+# don't change, don't track in version control
+from __future__ import annotations
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+version: str
+__version__: str
+__version_tuple__: tuple[int | str, ...]
+version_tuple: tuple[int | str, ...]
+commit_id: str | None
+__commit_id__: str | None
+
+__version__ = version = '0.6.3'
+__version_tuple__ = version_tuple = (0, 6, 3)
+
+__commit_id__ = commit_id = 'g1c826d931'

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/etc/spreadsheet2json_conf.yaml

@@ -77,6 +77,7 @@ Analysis:
     Phasing: boolean
     Date: date
     Software: list
+    Link(s): list
 
 Sample:
   header_row: 3

eva_sub_cli-0.6.3/eva_sub_cli/exceptions.py

@@ -0,0 +1,40 @@
+class NoVcfsFoundException(Exception):
+    def __init__(self, message):
+        self.message = message
+        super().__init__(self.message)
+
+
+class InvalidFileTypeError(Exception):
+    def __init__(self, message):
+        self.message = message
+        super().__init__(self.message)
+
+
+class MetadataTemplateVersionException(Exception):
+    def __init__(self, message):
+        self.message = message
+        super().__init__(self.message)
+
+
+class MetadataTemplateVersionNotFoundException(Exception):
+    def __init__(self, message):
+        self.message = message
+        super().__init__(self.message)
+
+
+class SubmissionNotFoundException(Exception):
+    def __init__(self, message):
+        self.message = message
+        super().__init__(self.message)
+
+
+class SubmissionStatusException(Exception):
+    def __init__(self, message):
+        self.message = message
+        super().__init__(self.message)
+
+
+class SubmissionUploadException(Exception):
+    def __init__(self, message):
+        self.message = message
+        super().__init__(self.message)

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/executables/cli.py

@@ -2,8 +2,6 @@ import sys
 
 from requests import HTTPError
 
-from eva_sub_cli.exceptions.submission_upload_exception import SubmissionUploadException
-
 if not sys.warnoptions:
     import warnings
     warnings.simplefilter("ignore")
@@ -15,10 +13,8 @@ from ebi_eva_common_pyutils.logger import logging_config
 
 import eva_sub_cli
 from eva_sub_cli import orchestrator
-from eva_sub_cli.exceptions.metadata_template_version_exception import MetadataTemplateVersionException, \
-    MetadataTemplateVersionNotFoundException
-from eva_sub_cli.exceptions.submission_status_exception import SubmissionStatusException
-from eva_sub_cli.exceptions.submission_not_found_exception import SubmissionNotFoundException
+from eva_sub_cli.exceptions import MetadataTemplateVersionException, MetadataTemplateVersionNotFoundException, \
+    SubmissionStatusException, SubmissionNotFoundException, SubmissionUploadException, NoVcfsFoundException
 from eva_sub_cli.call_home import CallHomeClient
 from eva_sub_cli.file_utils import is_submission_dir_writable, DirLockError, DirLock
 from eva_sub_cli.orchestrator import VALIDATE, SUBMIT, DOCKER, NATIVE
@@ -130,48 +126,50 @@ def main():
             # Pass on all the arguments to the orchestrator
             orchestrator.orchestrate_process(call_home=call_home, **args.__dict__)
     except DirLockError as dle:
-        print(f'Could not acquire the lock file for {args.submission_dir} because another process is using this '
-              f'directory or a previous process did not terminate correctly. '
-              f'If the problem persists, remove the lock file manually.')
+        logger.exception(f'Could not acquire the lock file for {args.submission_dir} because another process is using '
+                         f'this directory or a previous process did not terminate correctly. '
+                         f'If the problem persists, remove the lock file manually.')
         caught_exception = dle
         exit_status = 65
     except FileNotFoundError as fne:
-        print(fne)
+        logger.exception(fne)
         caught_exception = fne
         exit_status = 66
+    except NoVcfsFoundException as nvfe:
+        logger.exception(f'{nvfe}. Please ensure that you have listed VCF files in the metadata (.vcf or .vcf.gz file '
+                         f'extension), and that you have not modified the metadata template in any way.')
+        caught_exception = nvfe
+        exit_status = 67
     except SubmissionNotFoundException as snfe:
-        print(f'{snfe}. Please contact EVA Helpdesk')
+        logger.exception(f'{snfe}. Please contact EVA Helpdesk')
         caught_exception = snfe
-        exit_status = 67
+        exit_status = 68
     except SubmissionStatusException as sse:
-        print(f'{sse}. Please try again later. If the problem persists, please contact EVA Helpdesk')
+        logger.exception(f'{sse}. Please try again later. If the problem persists, please contact EVA Helpdesk')
         caught_exception = sse
-        exit_status = 68
+        exit_status = 69
     except MetadataTemplateVersionException as mte:
-        print(mte)
+        logger.exception(mte)
         caught_exception = mte
-        exit_status = 69
+        exit_status = 70
     except MetadataTemplateVersionNotFoundException as mte:
-        print(mte)
+        logger.exception(mte)
         caught_exception = mte
-        exit_status = 70
+        exit_status = 71
     except SubmissionUploadException as sue:
-        print(sue)
+        logger.exception(sue)
         caught_exception = sue
-        exit_status = 71
+        exit_status = 72
     except HTTPError as http_err:
-        print(http_err)
+        logger.exception(http_err)
         if http_err.response is not None and http_err.response.text:
             print(http_err.response.text)
         caught_exception = http_err
-        exit_status = 72
+        exit_status = 73
     except Exception as ex:
-        print(ex)
+        logger.exception(ex)
         caught_exception = ex
-        exit_status = 73
-
-    if caught_exception:
-        logger.exception(caught_exception)
+        exit_status = 74
 
     if call_home is not None:
         if exit_status == 0:

eva_sub_cli-0.6.3/eva_sub_cli/executables/format_metadata.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+import argparse
+import json
+import shutil
+
+from ebi_eva_common_pyutils.logger import logging_config
+logger = logging_config.get_logger(__name__)
+
+def format_experiment_type(json_file_input, json_file_output):
+    try:
+        with open(json_file_input, 'r') as input:
+            json_data = json.load(input)
+
+        for analysis_item in json_data.get("analysis", []):
+            original_experiment_type = analysis_item.get("experimentType", "")
+            logger.info(f"Formatting metadata - experiment type to capitalized - {original_experiment_type}")
+            experiment_type_capital = original_experiment_type.capitalize()
+            analysis_item["experimentType"] = experiment_type_capital or ""
+
+        with open(json_file_output, 'w') as output:
+            json.dump(json_data, output, indent=4)
+        return json_file_output
+
+    except (FileNotFoundError, json.JSONDecodeError, KeyError) as e:
+        # if the try block fails, copy the input file (because nextflow is expecting the output file).
+        logger.error(f"Failed to process JSON: {e}")
+        shutil.copy(json_file_input, json_file_output)
+        return None
+
+
+def main():
+    arg_parser = argparse.ArgumentParser(
+        description='Formats experiment type for the metadata.')
+    arg_parser.add_argument('--metadata_json_input', required=True, dest='metadata_json_input',
+                            help='EVA metadata json file INPUT')
+    arg_parser.add_argument('--metadata_json_output', required=True, dest='metadata_json_output',
+                            help='EVA metadata json file OUTPUT')
+    args = arg_parser.parse_args()
+    format_experiment_type(args.metadata_json_input, args.metadata_json_output)
+
+if __name__ == "__main__":
+    main()

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/executables/xlsx2json.py

@@ -9,8 +9,6 @@ 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'
@@ -259,8 +257,7 @@ class XlsxParser:
         # If the file could not be loaded at all, return without generating JSON.
         if not self.file_loaded:
             return
-        # Include which version of the EVA schema we are using
-        json_data = {'$schema': self.get_json_schema_link()}
+        json_data = {}
         for title in self.xlsx_conf[WORKSHEETS_KEY_NAME]:
             self.active_worksheet = title
             if title == PROJECT:
@@ -281,13 +278,6 @@ 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, {}):

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/file_utils.py

@@ -1,7 +1,6 @@
 import glob
 import gzip
 import os
-import shutil
 import time
 from itertools import groupby
 
@@ -132,28 +131,6 @@ def _assess_vcf_evidence_type_manual(vcf_file):
         open_file.close()
 
 
-def backup_file_or_directory(file_name, max_backups=None):
-    """
-    Rename a file or directory by adding a '.1' at the end. If the '.1' file exists it move it to a '.2' and so on.
-    Keep at most the specified number of backups, if None will keep all.
-    """
-    suffix = 1
-    backup_name = f'{file_name}.{suffix}'
-    while os.path.exists(backup_name):
-        suffix += 1
-        backup_name = f'{file_name}.{suffix}'
-
-    for i in range(suffix, 1, -1):
-        if max_backups and i > max_backups:
-            if os.path.isfile(file_name):
-                os.remove(f'{file_name}.{i - 1}')
-            else:
-                shutil.rmtree(f'{file_name}.{i - 1}')
-        else:
-            os.rename(f'{file_name}.{i - 1}', f'{file_name}.{i}')
-    os.rename(file_name, file_name + '.1')
-
-
 def open_gzip_if_required(input_file, mode='r'):
     """Open a file in read mode using gzip if the file extension says .gz"""
     if input_file.endswith('.gz'):

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/nextflow/validation.nf

@@ -42,7 +42,8 @@ params.python_scripts = [
     "fasta_checker": "check_fasta_insdc.py",
     "xlsx2json": "xlsx2json.py",
     "semantic_checker": "check_metadata_semantics.py",
-    "trim_down": "trim_down.py"
+    "trim_down": "trim_down.py",
+    "format_metadata": "format_metadata.py"
 ]
 // prefix to prepend to all provided path
 params.base_dir = ""
@@ -66,7 +67,6 @@ schema_dir = file(projectDir).parent + '/etc'
 conversion_configuration = "${schema_dir}/$params.conversion_configuration_name"
 
 
-
 def joinBasePath(path) {
     if (path) {
         return params.base_dir + '/' + path
@@ -98,8 +98,11 @@ workflow {
 		convert_xlsx_2_json(joinBasePath(params.metadata_xlsx))
 		metadata_json = convert_xlsx_2_json.out.metadata_json
 	} else {
-		metadata_json = joinBasePath(params.metadata_json)
+		metadata_json = file(joinBasePath(params.metadata_json), checkIfExists:true)
 	}
+
+    metadata_json_format(metadata_json)
+    metadata_json = metadata_json_format.out.metadata_formatted_json
 	// File size and MD5
 	generate_file_size_and_md5_digests(vcf_files)
 	collect_file_size_and_md5(generate_file_size_and_md5_digests.out.file_size_and_digest_info.collect())
@@ -177,6 +180,7 @@ process check_vcf_valid {
     """
     trap 'if [[ \$? == 1 ]]; then exit 0; fi' EXIT
 
+    rm -rf ${output_dir}/vcf_format
     mkdir -p vcf_format
     $params.executable.vcf_validator -i $vcf -r text -o vcf_format --require-evidence > vcf_format/${vcf}.vcf_format.log 2>&1
     """
@@ -206,6 +210,7 @@ process check_vcf_reference {
     """
     trap 'if [[ \$? == 1 || \$? == 139 ]]; then exit 0; fi' EXIT
 
+    rm -rf ${output_dir}/assembly_check
     mkdir -p assembly_check
     $params.executable.vcf_assembly_checker -i $vcf -f $fasta $report_opt -r summary,text  -o assembly_check --require-genbank > assembly_check/${vcf}.assembly_check.log 2>&1
     """
@@ -274,6 +279,28 @@ process convert_xlsx_2_json {
     """
 }
 
+process metadata_json_format {
+
+    label 'short_time', 'small_mem'
+
+    publishDir output_dir,
+            overwrite: true,
+            mode: "copy"
+
+    input:
+    path(metadata_json)
+
+    output:
+    path "metadata_formatted.log", emit: metadata_formatted
+    path "metadata_formatted_case_insensitive.json", emit: metadata_formatted_json
+
+    script:
+    def output_json = "metadata_formatted_case_insensitive.json"
+    """
+    $params.python_scripts.format_metadata --metadata_json_input $metadata_json --metadata_json_output $output_json > metadata_formatted.log 2>&1
+    """
+}
+
 process metadata_json_validation {
 
     label 'short_time', 'small_mem'

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/orchestrator.py

@@ -9,23 +9,18 @@ from ebi_eva_common_pyutils.config import WritableConfig
 from ebi_eva_common_pyutils.logger import logging_config
 from openpyxl.reader.excel import load_workbook
 from packaging import version
-from requests import HTTPError
-from retry import retry
 
-import eva_sub_cli
 from eva_sub_cli import MINIMUM_METADATA_XLSX_TEMPLATE_VERSION
 from eva_sub_cli import SUB_CLI_CONFIG_FILE, __version__
-from eva_sub_cli.exceptions.invalid_file_type_exception import InvalidFileTypeError
-from eva_sub_cli.exceptions.metadata_template_version_exception import MetadataTemplateVersionException, \
-    MetadataTemplateVersionNotFoundException
-from eva_sub_cli.exceptions.submission_not_found_exception import SubmissionNotFoundException
-from eva_sub_cli.exceptions.submission_status_exception import SubmissionStatusException
+from eva_sub_cli.exceptions import InvalidFileTypeError, MetadataTemplateVersionException, \
+    MetadataTemplateVersionNotFoundException, SubmissionNotFoundException, SubmissionStatusException, \
+    NoVcfsFoundException
 from eva_sub_cli.file_utils import is_vcf_file
 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.utils import get_project_title_from_ena, get_metadata_xlsx_template_link
 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, ALL_VALIDATION_TASKS
@@ -115,6 +110,8 @@ def validate_vcf_mapping(vcf_mapping):
     :param vcf_mapping: iterable of triples (VCF file path, reference FASTA path, optional assembly report path)
     :return:
     """
+    if len(vcf_mapping) == 0:
+        raise NoVcfsFoundException('No VCF files detected in metadata')
     for vcf_file, fasta_file, report_file in vcf_mapping:
         if not (vcf_file and os.path.isfile(vcf_file)):
             raise FileNotFoundError(f'The variant file {vcf_file} does not exist, please check the file path.')
@@ -154,46 +151,6 @@ def get_project_and_vcf_fasta_mapping_from_metadata_json(metadata_json):
     return project_title, vcf_fasta_report_mapping
 
 
-def get_sub_cli_version():
-    if version.parse(eva_sub_cli.__version__).is_devrelease:
-        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:
-            minor -= 1
-            patch = 0
-        elif major > 0:
-            major -= 1
-            minor = 0
-            patch = 0
-        return f"{major}.{minor}.{patch}"
-    else:
-        return version.parse(eva_sub_cli.__version__).base_version
-
-
-@retry(exceptions=(HTTPError,), tries=3, delay=2, backoff=1.2, jitter=(1, 3))
-def get_sub_cli_github_tags():
-    url = f"https://api.github.com/repos/EBIvariation/eva-sub-cli/tags"
-    response = requests.get(url)
-    if response.status_code == 200:
-        tags = [tag["name"][1:] for tag in response.json()]
-        return tags
-    else:
-        return []
-
-
-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/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'
-
-
 def verify_and_get_metadata_xlsx_version(metadata_xlsx, min_req_version):
     workbook = load_workbook(metadata_xlsx)
     instructions_sheet = workbook['PLEASE READ FIRST']

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/semantic_metadata.py

@@ -93,9 +93,13 @@ class SemanticMetadataChecker(AppLogger):
             self.check_taxonomy_code(project[TAX_ID_KEY], f'/{PROJECT_KEY}/{TAX_ID_KEY}')
         # Check sample taxonomies for novel samples
         for idx, sample in enumerate(self.metadata[SAMPLE_KEY]):
-            if BIOSAMPLE_OBJECT_KEY in sample and TAX_ID_KEY in sample[BIOSAMPLE_OBJECT_KEY][CHARACTERISTICS_KEY]:
-                self.check_taxonomy_code(sample[BIOSAMPLE_OBJECT_KEY][CHARACTERISTICS_KEY][TAX_ID_KEY][0]['text'],
-                                         f'/{SAMPLE_KEY}/{idx}/{BIOSAMPLE_OBJECT_KEY}/{CHARACTERISTICS_KEY}/{TAX_ID_KEY}')
+            if BIOSAMPLE_OBJECT_KEY in sample:
+                if TAX_ID_KEY in sample[BIOSAMPLE_OBJECT_KEY][CHARACTERISTICS_KEY]:
+                    self.check_taxonomy_code(sample[BIOSAMPLE_OBJECT_KEY][CHARACTERISTICS_KEY][TAX_ID_KEY][0]['text'],
+                                             f'/{SAMPLE_KEY}/{idx}/{BIOSAMPLE_OBJECT_KEY}/{CHARACTERISTICS_KEY}/{TAX_ID_KEY}')
+                else:
+                    self.add_error(f'/{SAMPLE_KEY}/{idx}/{BIOSAMPLE_OBJECT_KEY}/{CHARACTERISTICS_KEY}/{TAX_ID_KEY}',
+                                   f"must have required property '{TAX_ID_KEY}'")
 
     def check_uniqueness_analysis_alias(self):
         analyses = self.metadata[ANALYSIS_KEY]

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/submission_ws.py

@@ -7,7 +7,7 @@ from retry import retry
 
 from eva_sub_cli import SUBMISSION_WS_VAR
 from eva_sub_cli.auth import get_auth
-from eva_sub_cli.exceptions.submission_upload_exception import SubmissionUploadException
+from eva_sub_cli.exceptions import SubmissionUploadException
 
 DEFAULT_SUBMISSION_WS_URL = 'https://www.ebi.ac.uk/eva/webservices/submission-ws/v1/'
 

eva_sub_cli-0.6.3/eva_sub_cli/utils.py

@@ -0,0 +1,72 @@
+import requests
+from packaging import version
+from requests import HTTPError
+from retry import retry
+
+import eva_sub_cli
+from ebi_eva_common_pyutils.ena_utils import download_xml_from_ena
+
+
+def get_project_title_from_ena(project_accession):
+    try:
+        xml_root = download_xml_from_ena(f'https://www.ebi.ac.uk/ena/browser/api/xml/{project_accession}')
+        project_title = next(iter(xml_root.xpath('/PROJECT_SET/PROJECT/TITLE/text()')), None)
+    except HTTPError as e:
+        # We cannot currently differentiate between the service returning an error and the accession not existing
+        raise Exception(f"{project_accession} does not exist in ENA or is private")
+    except Exception as e:
+        raise Exception(f'Unexpected error occurred while getting project details from ENA for {project_accession}')
+
+    if not project_title:
+        raise Exception(f"{project_accession} does not exist in ENA or is private")
+
+    return project_title
+
+
+def get_sub_cli_version():
+    if version.parse(eva_sub_cli.__version__).is_devrelease:
+        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:
+            minor -= 1
+            patch = 0
+        elif major > 0:
+            major -= 1
+            minor = 0
+            patch = 0
+        return f"{major}.{minor}.{patch}"
+    else:
+        return version.parse(eva_sub_cli.__version__).base_version
+
+
+@retry(exceptions=(HTTPError,), tries=3, delay=2, backoff=1.2, jitter=(1, 3))
+def get_sub_cli_github_tags():
+    url = f"https://api.github.com/repos/EBIvariation/eva-sub-cli/tags"
+    response = requests.get(url)
+    if response.status_code == 200:
+        tags = [tag["name"][1:] for tag in response.json()]
+        return tags
+    else:
+        return []
+
+
+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/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'
+
+
+def get_json_schema_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/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'

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.3}/eva_sub_cli/validators/docker_validator.py

@@ -9,7 +9,7 @@ from retry import retry
 from eva_sub_cli.validators.validator import Validator, ALL_VALIDATION_TASKS
 
 default_container_image = 'ebivariation/eva-sub-cli'
-default_container_tag = 'v0.0.12'
+default_container_tag = 'v0.0.13'
 container_validation_dir = '/opt/vcf_validation'
 container_validation_output_dir = 'vcf_validation_output'