eva-sub-cli 0.5.3__tar.gz → 0.6.1__tar.gz

eva_sub_cli-0.6.1/.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-0.5.3 → eva_sub_cli-0.6.1}/.github/workflows/tests.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.9]
+        python-version: ["3.9", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v2

{eva_sub_cli-0.5.3/eva_sub_cli.egg-info → eva_sub_cli-0.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.5.3
+Version: 0.6.1
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console

{eva_sub_cli-0.5.3 → eva_sub_cli-0.6.1}/docker/Dockerfile

@@ -6,9 +6,7 @@ ENV NXF_VER=23.10.0
 WORKDIR /opt
 
 # Install JAVA and Node
-RUN apt update && apt install -y default-jdk build-essential \
-    && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
-    && apt install -y nodejs
+RUN apt update && apt install -y default-jdk nodejs npm
 
 # Install VCF validator
 RUN curl -LJo /usr/local/bin/vcf_validator  https://github.com/EBIvariation/vcf-validator/releases/download/v${vcf_validator_version}/vcf_validator_linux \

{eva_sub_cli-0.5.3 → eva_sub_cli-0.6.1}/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-0.5.3 → eva_sub_cli-0.6.1}/docs/validation_overview.md

@@ -25,7 +25,7 @@ Key points to note before validating your metadata spreadsheet with the eva-sub-
 - Any pre-registered projects and samples must be released and not kept in private status.
 - Sample names in the spreadsheet must match those in the VCF file.
 - Analysis aliases must match across the sheets (Analysis, Sample, and File sheets).
-- Use the Hold Date field in the Project sheet for data that needs to be kept under embargo.
+- Use the Hold Date field in the Project sheet for data that needs to be kept under embargo. The Hold Date cannot be more than 2 years in the future.
 
 Common errors seen with metadata checks:
 

{eva_sub_cli-0.5.3 → eva_sub_cli-0.6.1}/eva_sub_cli/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.5.3'
-__version_tuple__ = version_tuple = (0, 5, 3)
+__version__ = version = '0.6.1'
+__version_tuple__ = version_tuple = (0, 6, 1)
 
-__commit_id__ = commit_id = 'gc81081e35'
+__commit_id__ = commit_id = 'g13513250e'

eva_sub_cli-0.6.1/eva_sub_cli/call_home.py

@@ -0,0 +1,118 @@
+import os
+import traceback
+import uuid
+from datetime import datetime, timezone
+
+import requests
+from ebi_eva_common_pyutils.config import WritableConfig
+from ebi_eva_common_pyutils.logger import logging_config as log_cfg
+
+from eva_sub_cli import __version__, SUB_CLI_CONFIG_FILE, ROOT_DIR
+from eva_sub_cli.submission_ws import _submission_ws_base_url
+
+logger = log_cfg.get_logger(__name__)
+
+CALL_HOME_PATH = 'call-home/events'
+DEPLOYMENT_ID_DIR = os.path.join(os.path.expanduser('~'), '.eva-sub-cli')
+DEPLOYMENT_ID_FILE = os.path.join(DEPLOYMENT_ID_DIR, 'deployment_id')
+
+EVENT_START = 'START'
+EVENT_VALIDATION_COMPLETED = 'VALIDATION_COMPLETED'
+EVENT_END = 'END'
+EVENT_FAILURE = 'FAILURE'
+
+
+def _get_call_home_url():
+    return os.path.join(_submission_ws_base_url(), CALL_HOME_PATH)
+
+
+def _get_or_create_deployment_id():
+    try:
+        if os.path.isfile(DEPLOYMENT_ID_FILE):
+            with open(DEPLOYMENT_ID_FILE, 'r') as f:
+                deployment_id = f.read().strip()
+            if deployment_id:
+                return deployment_id
+        deployment_id = str(uuid.uuid4())
+        os.makedirs(DEPLOYMENT_ID_DIR, exist_ok=True)
+        with open(DEPLOYMENT_ID_FILE, 'w') as f:
+            f.write(deployment_id)
+        return deployment_id
+    except Exception:
+        logger.debug('Failed to read or create deployment ID file, using transient ID')
+        return str(uuid.uuid4())
+
+
+def _get_or_create_run_id(submission_dir):
+    try:
+        config_path = os.path.join(submission_dir, SUB_CLI_CONFIG_FILE)
+        config = WritableConfig(config_path)
+        run_id = config.get('run_id')
+        if run_id:
+            return str(run_id)
+        run_id = str(uuid.uuid4())
+        config.set('run_id', value=run_id)
+        config.write()
+        return run_id
+    except Exception:
+        logger.debug('Failed to read or create run ID in config, using transient ID')
+        return str(uuid.uuid4())
+
+
+class CallHomeClient:
+
+    def __init__(self, submission_dir, executor, tasks):
+        self.start_time = datetime.now(timezone.utc)
+        self.deployment_id = _get_or_create_deployment_id()
+        self.run_id = _get_or_create_run_id(submission_dir)
+        self.executor = executor
+        self.tasks = tasks
+
+    def _build_payload(self, event_type, **kwargs):
+        now = datetime.now(timezone.utc)
+        if event_type == EVENT_START:
+            runtime_seconds = 0
+        else:
+            elapsed = now - self.start_time
+            runtime_seconds = int(elapsed.total_seconds())
+        payload = {
+            'deploymentId': self.deployment_id,
+            'runId': self.run_id,
+            'eventType': event_type,
+            'cliVersion': __version__,
+            'createdAt': now.isoformat(),
+            'runtimeSeconds': runtime_seconds,
+            'executor': self.executor,
+            'tasks': self.tasks,
+        }
+        if kwargs:
+            payload.update(kwargs)
+        return payload
+
+    def _send_event(self, event_type, **kwargs):
+        try:
+            payload = self._build_payload(event_type, **kwargs)
+            requests.post(_get_call_home_url(), json=payload, timeout=5)
+        except Exception:
+            logger.debug('Failed to send %s call-home event', event_type)
+
+    def send_start(self):
+        self._send_event(EVENT_START)
+
+    def send_validation_completed(self, validation_result: dict):
+        self._send_event(EVENT_VALIDATION_COMPLETED, validation_result=validation_result)
+
+    def send_end(self):
+        self._send_event(EVENT_END)
+
+    def send_failure(self, exception=None):
+        kwargs = {}
+        if exception is not None:
+            kwargs['exceptionMessage'] = str(exception)
+            stack_trace = ''.join(
+                traceback.format_exception(type(exception), exception, exception.__traceback__)
+            )
+            # Remove the location of the file to preserve anonymity in case usernames are in the path
+            stack_trace = stack_trace.replace(ROOT_DIR, '')
+            kwargs['exceptionStacktrace'] = stack_trace
+        self._send_event(EVENT_FAILURE, **kwargs)

eva_sub_cli-0.6.1/eva_sub_cli/etc/call_home_payload_schema.json

@@ -0,0 +1,73 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "Call-Home Event Payload",
+  "description": "Payload sent by the eva-sub-cli to the submission WS /call-home endpoint for usage telemetry.",
+  "type": "object",
+  "properties": {
+    "deploymentId": {
+      "type": "string",
+      "format": "uuid",
+      "description": "Persistent UUID identifying a unique CLI installation. Stored at ~/.eva-sub-cli/deployment_id."
+    },
+    "runId": {
+      "type": "string",
+      "format": "uuid",
+      "description": "Persistent UUID identifying a submission directory run. Stored in the .eva_sub_cli_config.yml file within the submission directory."
+    },
+    "eventType": {
+      "type": "string",
+      "enum": ["START", "VALIDATION_COMPLETED", "END", "FAILURE"],
+      "description": "Type of lifecycle event. START is sent when main() begins, VALIDATION_COMPLETED after validation finishes, END when the program completes, FAILURE on any error."
+    },
+    "cliVersion": {
+      "type": "string",
+      "description": "Version of the eva-sub-cli package (e.g. '0.5.3')."
+    },
+    "createdAt": {
+      "type": "string",
+      "format": "date-time",
+      "description": "ISO 8601 UTC timestamp of when the event was created."
+    },
+    "runtimeSeconds": {
+      "type": "integer",
+      "minimum": 0,
+      "description": "Elapsed wall-clock seconds since the CLI started. Always 0 for START events."
+    },
+    "executor": {
+      "type": "string",
+      "enum": ["native", "docker"],
+      "description": "Execution backend selected for validation."
+    },
+    "tasks": {
+      "type": "array",
+      "items": {
+        "type": "string",
+        "enum": ["validate", "submit"]
+      },
+      "description": "List of tasks requested by the user."
+    },
+    "validation_result": {
+      "type": "object",
+      "description": "Outcome of the validation step. Only present in VALIDATION_COMPLETED events."
+    },
+    "exceptionMessage": {
+      "type": "string",
+      "description": "The exception message string. Only present in FAILURE events when an exception was caught."
+    },
+    "exceptionStacktrace": {
+      "type": "string",
+      "description": "Full Python stacktrace of the exception. Only present in FAILURE events when an exception was caught."
+    }
+  },
+  "required": [
+    "deploymentId",
+    "runId",
+    "eventType",
+    "cliVersion",
+    "createdAt",
+    "runtimeSeconds",
+    "executor",
+    "tasks"
+  ],
+  "additionalProperties": true
+}

{eva_sub_cli-0.5.3 → eva_sub_cli-0.6.1}/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-0.5.3 → eva_sub_cli-0.6.1}/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-0.5.3 → eva_sub_cli-0.6.1}/eva_sub_cli/executables/cli.py

@@ -19,10 +19,12 @@ from eva_sub_cli.exceptions.metadata_template_version_exception import MetadataT
     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.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
 from eva_sub_cli.validators.validator import ALL_VALIDATION_TASKS
 
+logger = logging_config.get_logger(__name__)
 
 def validate_command_line_arguments(args, argparser):
     fail = False
@@ -107,42 +109,74 @@ def main():
     else:
         logging_config.add_stdout_handler(logging.INFO)
 
+    # Initialize call-home
+    call_home = None
+    try:
+        call_home = CallHomeClient(
+            submission_dir=args.submission_dir,
+            executor=args.executor,
+            tasks=args.tasks
+        )
+        call_home.send_start()
+    except Exception:
+        pass
+
+    caught_exception = None
     try:
         # lock the submission directory
         with DirLock(os.path.join(args.submission_dir)) as lock:
             # Create the log file
             logging_config.add_file_handler(os.path.join(args.submission_dir, 'eva_submission.log'), logging.DEBUG)
             # Pass on all the arguments to the orchestrator
-            orchestrator.orchestrate_process(**args.__dict__)
-    except DirLockError:
+            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.')
+        caught_exception = dle
         exit_status = 65
     except FileNotFoundError as fne:
         print(fne)
+        caught_exception = fne
         exit_status = 66
     except SubmissionNotFoundException as snfe:
         print(f'{snfe}. Please contact EVA Helpdesk')
+        caught_exception = snfe
         exit_status = 67
     except SubmissionStatusException as sse:
         print(f'{sse}. Please try again later. If the problem persists, please contact EVA Helpdesk')
+        caught_exception = sse
         exit_status = 68
     except MetadataTemplateVersionException as mte:
         print(mte)
+        caught_exception = mte
         exit_status = 69
     except MetadataTemplateVersionNotFoundException as mte:
         print(mte)
+        caught_exception = mte
         exit_status = 70
     except SubmissionUploadException as sue:
         print(sue)
+        caught_exception = sue
         exit_status = 71
     except HTTPError as http_err:
         print(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
     except Exception as ex:
         print(ex)
+        caught_exception = ex
         exit_status = 73
+
+    if caught_exception:
+        logger.exception(caught_exception)
+
+    if call_home is not None:
+        if exit_status == 0:
+            call_home.send_end()
+        else:
+            call_home.send_failure(caught_exception)
+
     return exit_status

{eva_sub_cli-0.5.3 → eva_sub_cli-0.6.1}/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-0.5.3 → eva_sub_cli-0.6.1}/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-0.5.3 → eva_sub_cli-0.6.1}/eva_sub_cli/nextflow/validation.nf

@@ -105,20 +105,31 @@ workflow {
 	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)
 	}
 }
 
@@ -294,6 +305,7 @@ 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 +313,9 @@ 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 +376,7 @@ 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 +384,9 @@ 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-0.5.3 → eva_sub_cli-0.6.1}/eva_sub_cli/orchestrator.py

@@ -299,7 +299,7 @@ def check_validation_required(tasks, sub_config, username=None, password=None):
 
 def orchestrate_process(submission_dir, metadata_json, metadata_xlsx,
                         tasks, executor, validation_tasks=ALL_VALIDATION_TASKS, username=None, password=None,
-                        shallow_validation=False, nextflow_config=None, **kwargs):
+                        shallow_validation=False, nextflow_config=None, call_home=None, **kwargs):
     # load config
     config_file_path = os.path.join(submission_dir, SUB_CLI_CONFIG_FILE)
     sub_config = WritableConfig(config_file_path, version=__version__)
@@ -341,6 +341,8 @@ def orchestrate_process(submission_dir, metadata_json, metadata_xlsx,
                                         nextflow_config=nextflow_config)
         with validator:
             validator.validate_and_report()
+            if call_home:
+                call_home.send_validation_completed(validator.results)
             if not metadata_json:
                 metadata_json = os.path.join(validator.output_dir, 'metadata.json')
             sub_config.set('metadata_json', value=metadata_json)

{eva_sub_cli-0.5.3 → eva_sub_cli-0.6.1}/eva_sub_cli/report.py

@@ -17,16 +17,16 @@ def get_logo_data():
 
 def generate_report(validation_results, validation_date, submission_dir, vcf_fasta_analysis_mapping, project_title,
                     consent_statement_required, subdir, template_file):
-
-    from eva_sub_cli.validators.validator import RUN_STATUS_KEY, PASS
+    from eva_sub_cli.validators.validator import RUN_STATUS_KEY, TRIM_DOWN, PASS
 
     results_for_report = {k: v for k, v in validation_results.items() if k != 'ready_for_submission_to_eva'}
+    non_file_keys = {RUN_STATUS_KEY, PASS, TRIM_DOWN}
     vcf_files = sorted(set([file_name
                             for check in results_for_report if check in ["vcf_check", "assembly_check"]
                             for file_name in results_for_report[check]
-                            if file_name not in {RUN_STATUS_KEY, PASS}
+                            if file_name not in non_file_keys
                             ]))
-    fasta_files = sorted([file_name for file_name in results_for_report['fasta_check'] if file_name not in {RUN_STATUS_KEY, PASS}])
+    fasta_files = sorted([file_name for file_name in results_for_report['fasta_check'] if file_name not in non_file_keys])
     template = Environment(
         loader=FileSystemLoader(os.path.join(current_dir, 'jinja_templates', subdir))
     ).get_template(template_file)