eva-sub-cli 0.6.0__tar.gz → 0.6.2__tar.gz

eva_sub_cli-0.6.2/.github/workflows/integration-tests.yml

@@ -0,0 +1,56 @@
+name: Integration tests
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main]
+
+env:
+  VCF_VALIDATOR_VERSION: "0.10.2"
+  NXF_VER: "23.10.0"
+
+jobs:
+  integration-tests:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install Java and Node
+        run: sudo apt update && sudo apt install -y default-jdk nodejs npm git curl
+
+      - name: Install vcf-validator and vcf-assembly-checker
+        run: |
+          curl -LJo /usr/local/bin/vcf_validator \
+            https://github.com/EBIvariation/vcf-validator/releases/download/v${VCF_VALIDATOR_VERSION}/vcf_validator_linux
+          curl -LJo /usr/local/bin/vcf_assembly_checker \
+            https://github.com/EBIvariation/vcf-validator/releases/download/v${VCF_VALIDATOR_VERSION}/vcf_assembly_checker_linux
+          chmod 755 /usr/local/bin/vcf_validator /usr/local/bin/vcf_assembly_checker
+
+      - name: Install biovalidator
+        run: |
+          git clone https://github.com/elixir-europe/biovalidator.git
+          cd biovalidator
+          npm install
+          sudo npm link
+
+      - name: Install Nextflow
+        run: |
+          curl -L "https://github.com/nextflow-io/nextflow/releases/download/v${NXF_VER}/nextflow-${NXF_VER}-all" | bash
+          sudo mv nextflow /usr/local/bin/
+
+      - name: Install Python dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest
+          python -m pip install .
+
+      - name: Run integration tests
+        run: |
+          PYTHONPATH=. pytest tests -m integration

{eva_sub_cli-0.6.0/eva_sub_cli.egg-info → eva_sub_cli-0.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.6.0
+Version: 0.6.2
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/docker/Dockerfile

@@ -1,4 +1,4 @@
-FROM --platform=linux/amd64 python:3.10
+FROM python:3.10
 
 ENV vcf_validator_version=0.10.2
 ENV NXF_VER=23.10.0

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/docs/input_file_overview.md

@@ -98,7 +98,8 @@ alias, which is a shortened identifier you must provide for each analysis.
 
 This is where you describe the biological samples used for your analyses. Each row describes one sample and must include
 the Analysis Alias to indicate which analysis it belongs to, and "Sample Name in VCF" which is the exact name of the 
-sample as it appears in the VCF file.
+sample as it appears in the VCF file. If you are submitting a VCF without sample names (containing only allele frequencies),
+then you can omit the "Sample Name in VCF" column.
 
 We accept preregistered samples, which should be provided using BioSamples sample or sampleset accessions. Please
 ensure these are publicly accessible, as otherwise EVA will not be able to validate them.

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.6.0'
-__version_tuple__ = version_tuple = (0, 6, 0)
+__version__ = version = '0.6.2'
+__version_tuple__ = version_tuple = (0, 6, 2)
 
-__commit_id__ = commit_id = 'g9b7431423'
+__commit_id__ = commit_id = 'g1dbfe4351'

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli/etc/eva_schema.json

@@ -318,7 +318,6 @@
           {
             "required": [
               "analysisAlias",
-              "sampleInVCF",
               "bioSampleObject"
             ]
           }
@@ -334,7 +333,7 @@
           },
           "sampleInVCF": {
             "type": "string",
-            "description": "Sample Name used in the VCF file"
+            "description": "Sample Name used in the VCF file. It is a required field when genotypes are provided."
           },
           "bioSampleAccession": {
             "type": "string",

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/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-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli/executables/check_metadata_semantics.py

@@ -1,18 +1,23 @@
 import argparse
 import json
 
+import yaml
+
 from eva_sub_cli.semantic_metadata import SemanticMetadataChecker
 
 
 def main():
     arg_parser = argparse.ArgumentParser(description='Perform semantic checks on the metadata')
     arg_parser.add_argument('--metadata_json', required=True, dest='metadata_json', help='EVA metadata json file')
+    arg_parser.add_argument('--evidence_type_results', required=True, dest='evidence_type_results', help='Results of the evidence check')
     arg_parser.add_argument('--output_yaml', required=True, dest='output_yaml',
                             help='Path to the location of the results')
     args = arg_parser.parse_args()
 
     with open(args.metadata_json) as open_json:
         metadata = json.load(open_json)
-        checker = SemanticMetadataChecker(metadata)
-        checker.check_all()
-        checker.write_result_yaml(args.output_yaml)
+    with open(args.evidence_type_results) as open_yaml:
+        evidence_type_results = yaml.safe_load(open_yaml)
+    checker = SemanticMetadataChecker(metadata, evidence_type_results)
+    checker.check_all()
+    checker.write_result_yaml(args.output_yaml)

eva_sub_cli-0.6.2/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-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli/executables/samples_checker.py

@@ -54,7 +54,7 @@ def compare_names_in_files_and_samples(sample_name_in_analysis, sample_name_per_
             more_metadata_submitted_files)
 
 
-def compare_all_analysis(metadata, files_per_analysis):
+def compare_all_analysis(metadata, files_per_analysis, evidence_type_results):
     overall_differences = False
     results_per_analysis_alias = {}
     all_analysis_alias = set(metadata.samples_per_analysis) | set(files_per_analysis)
@@ -65,7 +65,7 @@ def compare_all_analysis(metadata, files_per_analysis):
             for file_path in files_per_analysis.get(analysis_alias, [])
         }
 
-        if need_to_check_samples(sample_name_per_file):
+        if need_to_check_samples(evidence_type_results, analysis_alias):
             (
                 has_difference, more_per_submitted_files_metadata,
                 more_submitted_files_metadata, more_metadata_submitted_files
@@ -89,13 +89,9 @@ def compare_all_analysis(metadata, files_per_analysis):
     return overall_differences, results_per_analysis_alias
 
 
-def need_to_check_samples(sample_name_per_file):
-    no_samples_in_vcf = all(len(v) == 0 for v in sample_name_per_file.values())
-    if no_samples_in_vcf:
-        evidence_types_for_vcf_files = [detect_vcf_evidence_type(vcf_file) for vcf_file in sample_name_per_file.keys()]
-        if set(evidence_types_for_vcf_files) == {'allele_frequency'}:
-            return False
-
+def need_to_check_samples(evidence_type_results, analysis_alias):
+    if evidence_type_results.get(analysis_alias, {}).get('evidence_type') == 'allele_frequency':
+        return False
     return True
 
 
@@ -107,14 +103,16 @@ def write_result_yaml(output_yaml, overall_differences, results_per_analysis_ali
         }, stream=open_yaml)
 
 
-def check_sample_name_concordance(metadata_json, vcf_files, output_yaml):
+def check_sample_name_concordance(metadata_json, vcf_files, output_yaml, evidence_type_result_file):
     """
     Take the metadata following EVA standard and formatted in JSON then compare the sample names in it to the ones
     found in the VCF files
     """
     metadata = EvaMetadataJson(metadata_json)
+    with open(evidence_type_result_file) as open_yaml:
+        evidence_type_results = yaml.safe_load(open_yaml)
     file_path_per_analysis = associate_vcf_path_with_analysis(metadata, vcf_files)
-    overall_differences, results_per_analysis_alias = compare_all_analysis(metadata, file_path_per_analysis)
+    overall_differences, results_per_analysis_alias = compare_all_analysis(metadata, file_path_per_analysis, evidence_type_results)
     write_result_yaml(output_yaml, overall_differences, results_per_analysis_alias)
 
 
@@ -127,7 +125,10 @@ def main():
                             help='Path to the vcf files to compare to the metadata')
     arg_parser.add_argument('--output_yaml', required=True, dest='output_yaml',
                             help='Path to the location of the results')
+    arg_parser.add_argument('--evidence_type_results', required=True, dest='evidence_type_results',
+                            help='Results of the evidence check')
+
 
     args = arg_parser.parse_args()
     logging_config.add_stdout_handler()
-    check_sample_name_concordance(args.metadata_json, args.vcf_files, args.output_yaml)
+    check_sample_name_concordance(args.metadata_json, args.vcf_files, args.output_yaml, args.evidence_type_results)

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli/executables/xlsx2json.py

@@ -225,8 +225,9 @@ class XlsxParser:
         return str(value)
 
     def get_sample_data_with_split_analysis_alias(self, data, analysis_alias, sample_name_in_vcf):
-        analysis_alias_list = data[analysis_alias].split(',')
-        sample_in_vcf_val = data[sample_name_in_vcf]
+        analysis_alias_val = data.get(analysis_alias)
+        analysis_alias_list = analysis_alias_val.split(',') if analysis_alias_val else []
+        sample_in_vcf_val = data.get(sample_name_in_vcf)
         return {analysis_alias: analysis_alias_list, sample_name_in_vcf: sample_in_vcf_val}
 
     def get_sample_json_data(self):
@@ -245,8 +246,8 @@ class XlsxParser:
                 sample_data.update(bioSampleAccession=json_value[bio_sample_acc])
                 sample_json[json_key].append(sample_data)
             else:
-                json_value.pop(analysis_alias)
-                json_value.pop(sample_name_in_vcf)
+                json_value.pop(analysis_alias, None)
+                json_value.pop(sample_name_in_vcf, None)
 
                 biosample_obj = self.get_biosample_object(json_value)
                 sample_data.update(bioSampleObject=biosample_obj)

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/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-0.6.0 → eva_sub_cli-0.6.2}/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 = ""
@@ -98,27 +99,41 @@ 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())
 
 	// Task-specific processing
+	evidence_type_results = null
+
     if (params.tasks.contains(VCF_CHECK)) {
         check_vcf_valid(vcf_and_ref_ch)
         evidence_type_check(metadata_json, vcf_files.collect())
+        evidence_type_results = evidence_type_check.out.evidence_type_checker_yml
 	}
 	if (params.tasks.contains(ASSEMBLY_CHECK)) {
 		check_vcf_reference(vcf_and_ref_ch)
 		insdc_checker(metadata_json, fasta_to_vcfs)
 	}
 	if (params.tasks.contains(METADATA_CHECK)) {
+	    if (!evidence_type_results) {
+            evidence_type_check(metadata_json, vcf_files.collect())
+            evidence_type_results = evidence_type_check.out.evidence_type_checker_yml
+	    }
 		metadata_json_validation(metadata_json)
-		metadata_semantic_check(metadata_json)
+		metadata_semantic_check(metadata_json, evidence_type_results)
 	}
 	if (params.tasks.contains(SAMPLE_CHECK)) {
-		sample_name_concordance(metadata_json, vcf_files.collect())
+	    if (!evidence_type_results){
+            evidence_type_check(metadata_json, vcf_files.collect())
+            evidence_type_results = evidence_type_check.out.evidence_type_checker_yml
+	    }
+		sample_name_concordance(metadata_json, vcf_files.collect(), evidence_type_results)
 	}
 }
 
@@ -166,6 +181,7 @@ 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
     """
@@ -195,6 +211,7 @@ 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
     """
@@ -263,6 +280,28 @@ 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'
@@ -294,6 +333,7 @@ process sample_name_concordance {
     input:
     path(metadata_json)
     path(vcf_files)
+    path(evidence_type_results)
 
     output:
     path "sample_checker.yml", emit: sample_checker_yml
@@ -301,7 +341,9 @@ process sample_name_concordance {
 
     script:
     """
-    $params.python_scripts.samples_checker --metadata_json $metadata_json --vcf_files $vcf_files --output_yaml sample_checker.yml > sample_checker.log 2>&1
+    $params.python_scripts.samples_checker --metadata_json $metadata_json \
+        --vcf_files $vcf_files --output_yaml sample_checker.yml \
+        --evidence_type_results $evidence_type_results > sample_checker.log 2>&1
     """
 }
 
@@ -362,6 +404,7 @@ process metadata_semantic_check {
 
     input:
     path(metadata_json)
+    path(evidence_type_results)
 
     output:
     path "metadata_semantic_check.yml", emit: metadata_semantic_check_yml
@@ -369,6 +412,9 @@ process metadata_semantic_check {
 
     script:
     """
-    $params.python_scripts.semantic_checker --metadata_json $metadata_json --output_yaml metadata_semantic_check.yml > semantic_checker.log 2>&1
+    $params.python_scripts.semantic_checker \
+    --metadata_json $metadata_json \
+    --evidence_type_results $evidence_type_results \
+    --output_yaml metadata_semantic_check.yml > semantic_checker.log 2>&1
     """
 }

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli/semantic_metadata.py

@@ -20,6 +20,7 @@ PROJECT_ACCESSION_KEY = 'projectAccession'
 PARENT_PROJECT_KEY = 'parentProject'
 CHILD_PROJECTS_KEY = 'childProjects'
 PEER_PROJECTS_KEY = 'peerProjects'
+SAMPLE_IN_VCF_KEY = 'sampleInVCF'
 BIOSAMPLE_OBJECT_KEY = 'bioSampleObject'
 BIOSAMPLE_ACCESSION_KEY = 'bioSampleAccession'
 CHARACTERISTICS_KEY = 'characteristics'
@@ -40,9 +41,10 @@ def cast_list(l, type_to_cast=str):
 
 class SemanticMetadataChecker(AppLogger):
 
-    def __init__(self, metadata, sample_checklist='ERC000011'):
+    def __init__(self, metadata, evidence_type_results, sample_checklist='ERC000011'):
         self.sample_checklist = sample_checklist
         self.metadata = metadata
+        self.evidence_type_results = evidence_type_results
         self.errors = []
         # Caches whether taxonomy code is valid or not, and maps to scientific name if valid
         self.taxonomy_valid = {}
@@ -60,6 +62,7 @@ class SemanticMetadataChecker(AppLogger):
         self.check_all_analysis_run_accessions()
         self.check_analysis_alias_coherence()
         self.check_all_analysis_contain_samples()
+        self.check_all_samples_have_sample_in_vcf()
         self.check_hold_date()
 
     def check_hold_date(self):
@@ -316,3 +319,14 @@ class SemanticMetadataChecker(AppLogger):
                 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.')
+
+    def check_all_samples_have_sample_in_vcf(self):
+        for idx, sample in enumerate(self.metadata[SAMPLE_KEY]):
+            json_path = f'/{SAMPLE_KEY}/{idx}/{SAMPLE_IN_VCF_KEY}'
+            analysis_aliases = sample.get(ANALYSIS_ALIAS_KEY, [])
+            if any([self.evidence_type_results.get(analysis_alias, {}).get('evidence_type') != 'allele_frequency' for
+                        analysis_alias in analysis_aliases]):
+                # SampleInVCF is required
+                if sample.get(SAMPLE_IN_VCF_KEY) is None or sample.get(SAMPLE_IN_VCF_KEY) == '':
+                    self.add_error(json_path, f'{SAMPLE_IN_VCF_KEY} must be provided when Genotypes are present in the VCF file')
+

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/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 = 'v0.0.11'
+default_container_tag = 'v0.0.13'
 container_validation_dir = '/opt/vcf_validation'
 container_validation_output_dir = 'vcf_validation_output'
 

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli/validators/validator.py

@@ -3,17 +3,18 @@ import csv
 import datetime
 import logging
 import os
+import shutil
 from functools import lru_cache, cached_property
 
 import yaml
 from ebi_eva_common_pyutils.command_utils import run_command_with_output
 from ebi_eva_common_pyutils.config import WritableConfig
-from ebi_eva_common_pyutils.logger import logging_config, AppLogger
+from ebi_eva_common_pyutils.logger import AppLogger
 from packaging import version
 
 import eva_sub_cli
 from eva_sub_cli import ETC_DIR, SUB_CLI_CONFIG_FILE, __version__
-from eva_sub_cli.file_utils import backup_file_or_directory, resolve_single_file_path
+from eva_sub_cli.file_utils import resolve_single_file_path
 from eva_sub_cli.metadata import EvaMetadataJson
 from eva_sub_cli.report import generate_html_report, generate_text_report
 from eva_sub_cli.validators.validation_results_parsers import parse_assembly_check_log, parse_assembly_check_report, \
@@ -43,7 +44,6 @@ RUN_STATUS_KEY = 'run_status'
 PASS = 'pass'
 
 
-
 class Validator(AppLogger):
 
     def __init__(self, mapping_file, submission_dir, project_title=None, metadata_json=None, metadata_xlsx=None,
@@ -54,6 +54,7 @@ class Validator(AppLogger):
         self.tasks = validation_tasks
         self.submission_dir = submission_dir
         self.output_dir = os.path.join(submission_dir, VALIDATION_OUTPUT_DIR)
+        self.nextflow_work_dir = os.path.join(self.submission_dir, 'work') # Default location when we chdir in self.submission_dir
         self.validation_result_file = os.path.join(submission_dir, VALIDATION_RESULTS_FILE)
         self.mapping_file = mapping_file
         vcf_files, fasta_files = self._find_vcf_and_fasta_files()
@@ -130,20 +131,22 @@ class Validator(AppLogger):
         raise NotImplementedError
 
     def set_up_output_dir(self):
-        if os.path.exists(self.output_dir):
-            backup_file_or_directory(self.output_dir, max_backups=9)
-        os.makedirs(self.output_dir, exist_ok=True)
+        if not os.path.exists(self.output_dir):
+            os.makedirs(self.output_dir, exist_ok=True)
 
     def clean_up_output_dir(self):
         # Move intermediate validation outputs into a subdir except metadata.json
         subdir = os.path.join(self.output_dir, 'other_validations')
-        os.mkdir(subdir)
+        os.makedirs(subdir, exist_ok=True)
         for file_name in os.listdir(self.output_dir):
-            if file_name == 'metadata.json':
+            if file_name in ['metadata.json', 'report.txt', 'report.html']:
                 continue
             file_path = os.path.join(self.output_dir, file_name)
             if os.path.isfile(file_path):
                 os.rename(file_path, os.path.join(subdir, file_name))
+        # Remove the nextflow work directory if it exists
+        if os.path.exists(self.nextflow_work_dir):
+            shutil.rmtree(self.nextflow_work_dir)
 
     @staticmethod
     def _validation_file_path_for(file_path):
@@ -210,7 +213,6 @@ class Validator(AppLogger):
                 del self.results[SHALLOW_VALIDATION]['required']
             del self.results[SHALLOW_VALIDATION]['requested']
 
-
     def _collect_validation_workflow_results(self):
         # Collect information from the output and summarise in the config
         if self.shallow_validation:
@@ -550,7 +552,7 @@ class Validator(AppLogger):
                     file_path_2_file_size[vcf_file] = file_size
                     file_name_2_file_size[os.path.basename(vcf_file)] = file_size
         else:
-            error_txt =  f"Cannot locate file_info.txt at {os.path.join(self.output_dir, 'other_validations', 'file_info.txt')}"
+            error_txt = f"Cannot locate file_info.txt at {os.path.join(self.output_dir, 'other_validations', 'file_info.txt')}"
             self.error(error_txt)
             raise FileNotFoundError(error_txt)
 

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2/eva_sub_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.6.0
+Version: 0.6.2
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli.egg-info/SOURCES.txt

@@ -6,6 +6,7 @@ pytest.ini
 requirements.txt
 setup.cfg
 setup.py
+.github/workflows/integration-tests.yml
 .github/workflows/publish.yml
 .github/workflows/publish_docs.yml
 .github/workflows/tests.yml
@@ -58,6 +59,7 @@ eva_sub_cli/executables/check_fasta_insdc.py
 eva_sub_cli/executables/check_metadata_semantics.py
 eva_sub_cli/executables/cli.py
 eva_sub_cli/executables/evidence_type_checker.py
+eva_sub_cli/executables/format_metadata.py
 eva_sub_cli/executables/samples_checker.py
 eva_sub_cli/executables/trim_down.py
 eva_sub_cli/executables/xlsx2json.py
@@ -90,7 +92,9 @@ tests/test_cli.py
 tests/test_docker_validator.py
 tests/test_evidence_type_checker.py
 tests/test_file_utils.py
+tests/test_format_metadata.py
 tests/test_metadata.py
+tests/test_native_validator_sample_in_vcf.py
 tests/test_orchestrator.py
 tests/test_report.py
 tests/test_samples_checker.py
@@ -108,6 +112,7 @@ tests/resources/EVA_Submission_test_V2.xlsx
 tests/resources/EVA_Submission_test_fails.xlsx
 tests/resources/EVA_Submission_test_version_missing.xlsx
 tests/resources/EVA_Submission_test_with_asm_report.json
+tests/resources/EVA_Submission_test_with_links.xlsx
 tests/resources/EVA_Submission_test_with_non_vcf_files.json
 tests/resources/EVA_Submission_test_with_non_vcf_files.xlsx
 tests/resources/EVA_Submission_test_with_project_accession.json
@@ -119,10 +124,18 @@ tests/resources/assembly_reports/input_passed.txt
 tests/resources/fasta_files/Saccharomyces_cerevisiae_I.fa
 tests/resources/fasta_files/input_passed.fa
 tests/resources/fasta_files/multi_seq.fa
+tests/resources/sample_checker/evidence_type.yaml
 tests/resources/sample_checker/example1.vcf.gz
 tests/resources/sample_checker/example2.vcf
 tests/resources/sample_checker/example3.vcf
 tests/resources/sample_checker/metadata.json
+tests/resources/sample_in_vcf_check/allele_freq.vcf
+tests/resources/sample_in_vcf_check/fake_fasta.fa
+tests/resources/sample_in_vcf_check/genotype.vcf
+tests/resources/sample_in_vcf_check/metadata_af_no_sample_in_vcf.json
+tests/resources/sample_in_vcf_check/metadata_af_with_sample_in_vcf.json
+tests/resources/sample_in_vcf_check/metadata_genotype_no_sample_in_vcf.json
+tests/resources/sample_in_vcf_check/metadata_genotype_with_sample_in_vcf.json
 tests/resources/validation_reports/expected_metadata_json_report.html
 tests/resources/validation_reports/expected_metadata_json_report.txt
 tests/resources/validation_reports/expected_metadata_xlsx_report.html

{eva_sub_cli-0.6.0 → eva_sub_cli-0.6.2}/eva_sub_cli.egg-info/entry_points.txt

@@ -3,6 +3,7 @@ check_fasta_insdc.py = eva_sub_cli.executables.check_fasta_insdc:main
 check_metadata_semantics.py = eva_sub_cli.executables.check_metadata_semantics:main
 eva-sub-cli.py = eva_sub_cli.executables.cli:main
 evidence_type_checker.py = eva_sub_cli.executables.evidence_type_checker:main
+format_metadata.py = eva_sub_cli.executables.format_metadata:main
 samples_checker.py = eva_sub_cli.executables.samples_checker:main
 trim_down.py = eva_sub_cli.executables.trim_down:main
 xlsx2json.py = eva_sub_cli.executables.xlsx2json:main