Switched from using setup.py to pyproject.toml

Added build dependency to setuptools_scm
Use setuptools_scm to set the version

.github/workflows/tests.yml

@@ -24,7 +24,7 @@ jobs:
         python -m pip install --upgrade pip
         pip install flake8 pytest
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-        python setup.py install
+        python -m pip install .
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names

.gitignore

@@ -130,3 +130,6 @@ dmypy.json
 
 # PyCharm
 .idea/
+
+#setuptools_scm version file
+_version.py

docker/Dockerfile

@@ -25,4 +25,4 @@ RUN curl -L "https://github.com/nextflow-io/nextflow/releases/download/v${NXF_VE
 
 COPY . /opt/
 
-RUN pip install .
+RUN python -m pip install .

eva_sub_cli/__init__.py

@@ -7,12 +7,21 @@
 ETC_DIR = os.path.join(PACKAGE_DIR, 'etc')
 LSRI_CLIENT_ID = "aa0fcc42-096a-4f9d-b871-aceb1a97d174"
 
-__version__ = open(os.path.join(PACKAGE_DIR, 'VERSION')).read().strip()
-
 SUB_CLI_CONFIG_FILE = ".eva_sub_cli_config.yml"
 
 # Environment variable
 SUBMISSION_WS_VAR = 'SUBMISSION_WS_URL'
 ENA_WEBIN_ACCOUNT_VAR = 'ENA_WEBIN_ACCOUNT'
 ENA_WEBIN_PASSWORD_VAR = 'ENA_WEBIN_PASSWORD'
 
+
+try:
+    # If setuptools_scm is installed we can get the version directly from it
+    from setuptools_scm import get_version
+    __version__ = get_version(root='..', relative_to=__file__)
+    del get_version
+except:
+    # otherwise assume that we're working in a deployed instance which should have the _version file
+    from ._version import version as __version__
+
+

bin/check_fasta_insdc.py → eva_sub_cli/executables/check_fasta_insdc.py

@@ -1,5 +1,3 @@
-#!/usr/bin/env python
-
 import argparse
 import gzip
 import hashlib
@@ -186,6 +184,3 @@ def main():
     results = assess_fasta(args.input_fasta, analyses, metadata_insdc)
     write_result_yaml(args.output_yaml, results)
 
-
-if __name__ == "__main__":
-    main()

bin/check_metadata_semantics.py → eva_sub_cli/executables/check_metadata_semantics.py

@@ -16,7 +16,3 @@ def main():
         checker = SemanticMetadataChecker(metadata)
         checker.check_all()
         checker.write_result_yaml(args.output_yaml)
-
-
-if __name__ == "__main__":
-    main()

bin/eva-sub-cli.py → eva_sub_cli/executables/cli.py

@@ -1,6 +1,6 @@
-#!/usr/bin/env python
 import sys
 
+import eva_sub_cli
 from eva_sub_cli.exceptions.submission_not_found_exception import SubmissionNotFoundException
 from eva_sub_cli.exceptions.submission_status_exception import SubmissionStatusException
 
@@ -36,15 +36,9 @@ def validate_command_line_arguments(args, argparser):
         sys.exit(1)
 
 
-def get_version():
-    base_dir = os.path.abspath(os.path.dirname(main.__file__))
-    version = open(os.path.join(base_dir, 'VERSION')).read().strip()
-    return f'{version}'
-
-
-if __name__ == "__main__":
+def main():
     argparser = ArgumentParser(prog='eva-sub-cli', description='EVA Submission CLI - validate and submit data to EVA')
-    argparser.add_argument('--version', action='version', version=f'%(prog)s {get_version()}')
+    argparser.add_argument('--version', action='version', version=f'%(prog)s {eva_sub_cli.__version__}')
     argparser.add_argument('--submission_dir', required=True, type=str,
                            help='Full path to the directory where all processing will be done '
                                 'and submission info is/will be stored')

bin/samples_checker.py → eva_sub_cli/executables/samples_checker.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 import argparse
 import gzip
 import json
@@ -149,7 +148,3 @@ def main():
     args = arg_parser.parse_args()
     logging_config.add_stdout_handler()
     check_sample_name_concordance(args.metadata_json, args.vcf_files, args.output_yaml)
-
-
-if __name__ == "__main__":
-    main()

bin/xlsx2json.py → eva_sub_cli/executables/xlsx2json.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 import argparse
 import datetime
 import json
@@ -368,7 +367,3 @@ def main():
         parser.add_error(e)
     finally:
         parser.save_errors(args.errors_yaml)
-
-
-if __name__ == "__main__":
-    main()

eva_sub_cli/jinja_templates/html_report.html

@@ -42,6 +42,7 @@
         </div>
     <div class="title">
         <h1>Validation Report</h1>
+        <h6>eva-sub-cli v{{cli_version}}</h6>
     </div>
 </header>
 

eva_sub_cli/report.py

@@ -3,6 +3,8 @@
 
 from jinja2 import Environment, FileSystemLoader
 
+import eva_sub_cli
+
 current_dir = os.path.dirname(__file__)
 
 
@@ -22,6 +24,7 @@ def generate_html_report(validation_results, validation_date, submission_dir, vc
         loader=FileSystemLoader(os.path.join(current_dir, 'jinja_templates'))
     ).get_template('html_report.html')
     rendered_template = template.render(
+        cli_version=eva_sub_cli.__version__,
         logo_data=get_logo_data(),
         project_title=project_title,
         validation_date=validation_date,

eva_sub_cli/validators/validator.py

@@ -580,7 +580,6 @@ def get_vcf_fasta_analysis_mapping(self):
         else:
             self.error('Error building validation report : Metadata file not present')
 
-
     def create_reports(self):
         report_html = generate_html_report(self.results, self.validation_date, self.submission_dir,
                                            self.get_vcf_fasta_analysis_mapping(), self.project_title)

pyproject.toml

@@ -0,0 +1,50 @@
+[build-system]
+requires = [
+    "setuptools >= 64",
+    "setuptools_scm[toml] >= 8",
+    "setuptools_scm_git_archive",
+    "wheel >= 0.29.0",
+]
+build-backend = 'setuptools.build_meta'
+
+[project]
+name = 'eva_sub_cli'
+description = 'EBI EVA - validation and submission command line tool'
+dynamic = ["version", 'requires-python']
+readme = 'README.md'
+classifiers = [
+    'Development Status :: 5 - Production/Stable',
+    'Environment :: Console',
+    'Intended Audience :: Science/Research',
+    'Natural Language :: English',
+    'Operating System :: POSIX :: Linux',
+    'Operating System :: MacOS :: MacOS X',
+    'Programming Language :: Python :: 3.6',
+    'Programming Language :: Python :: 3.7',
+    'Programming Language :: Python :: 3.8',
+    'Programming Language :: Python :: 3.9',
+    'Programming Language :: Python :: 3.10',
+    'Topic :: Scientific/Engineering :: Bio-Informatics',
+    'Topic :: Communications :: File Sharing',
+    'License :: OSI Approved :: Apache',
+]
+[project.scripts]
+'eva-sub-cli.py'='eva_sub_cli.executables.cli:main'
+'check_fasta_insdc.py'='eva_sub_cli.executables.check_fasta_insdc:main'
+'check_metadata_semantics.py'='eva_sub_cli.executables.check_metadata_semantics:main'
+'samples_checker.py'='eva_sub_cli.executables.samples_checker:main'
+'xlsx2json.py'='eva_sub_cli.executables.xlsx2json:main'
+
+[tool.setuptools]
+packages = ['eva_sub_cli', 'eva_sub_cli.executables']
+
+[tool.setuptools.package-data]
+'eva_sub_cli'=['nextflow/*', 'etc/*', 'jinja_templates/*']
+
+[tool.setuptools.dynamic]
+dependencies = {file = 'requirements.txt'}
+
+
+[tool.setuptools_scm]
+write_to = 'eva_sub_cli/_version.py'
+

setup.cfg

@@ -1,5 +1,3 @@
-[metadata]
-description-file = README.md
 
 [zest.releaser]
 tag-format = v{version}
@@ -12,3 +10,11 @@ ignore =
     tests/*/*/*/*
     .gitlab-ci.yml
 
+[options]
+zip_safe = False
+platforms = any
+include_package_data = True
+python_requires = >=3.6
+setup_requires =
+    setuptools_scm
+

setup.py

@@ -1,30 +1,36 @@
 import glob
 from distutils.core import setup
 from os.path import join, abspath, dirname
-from setuptools import find_packages
-
-base_dir = abspath(dirname(__file__))
-requirements_txt = join(base_dir, 'requirements.txt')
-requirements = [l.strip() for l in open(requirements_txt) if l and not l.startswith('#')]
 
-version = open(join(base_dir, 'eva_sub_cli', 'VERSION')).read().strip()
+import setuptools
+from setuptools import find_packages
+#
+# base_dir = abspath(dirname(__file__))
+# requirements_txt = join(base_dir, 'requirements.txt')
+# requirements = [l.strip() for l in open(requirements_txt) if l and not l.startswith('#')]
+#
+# version = open(join(base_dir, 'eva_sub_cli', 'VERSION')).read().strip()
+#
+# setup(
+#     name='eva_sub_cli',
+#     packages=find_packages(),
+#     package_data={'eva_sub_cli': ['nextflow/*', 'etc/*', 'VERSION', 'jinja_templates/*']},
+#     use_scm_version={'write_to': 'eva_sub_cli/_version.py'},
+#     license='Apache',
+#     description='EBI EVA - validation and submission command line tool',
+#     url='https://github.com/EBIvariation/eva-sub-cli',
+#     keywords=['ebi', 'eva', 'python', 'submission', 'validation'],
+#     install_requires=requirements,
+#     setup_requires=['setuptools_scm'],
+#     classifiers=[
+#         'Development Status :: 5 - Production/Stable',
+#         'Intended Audience :: Science/Research',
+#         'Topic :: Communications :: File Sharing',
+#         'License :: OSI Approved :: Apache Software License',
+#         'Programming Language :: Python :: 3'
+#     ],
+#     scripts=glob.glob(join(dirname(__file__), 'bin', '*.py'))
+# )
 
-setup(
-    name='eva_sub_cli',
-    packages=find_packages(),
-    package_data={'eva_sub_cli': ['nextflow/*', 'etc/*', 'VERSION', 'jinja_templates/*']},
-    version=version,
-    license='Apache',
-    description='EBI EVA - validation and submission command line tool',
-    url='https://github.com/EBIvariation/eva-sub-cli',
-    keywords=['ebi', 'eva', 'python', 'submission', 'validation'],
-    install_requires=requirements,
-    classifiers=[
-        'Development Status :: 5 - Production/Stable',
-        'Intended Audience :: Science/Research',
-        'Topic :: Communications :: File Sharing',
-        'License :: OSI Approved :: Apache Software License',
-        'Programming Language :: Python :: 3'
-    ],
-    scripts=glob.glob(join(dirname(__file__), 'bin', '*.py'))
-)
+if __name__ == "__main__":
+    setuptools.setup()

tests/test_check_fasta_insdc.py

@@ -5,7 +5,7 @@
 import pytest
 import requests as requests
 
-from bin.check_fasta_insdc import assess_fasta, get_analyses_and_reference_genome_from_metadata
+from eva_sub_cli.executables.check_fasta_insdc import assess_fasta, get_analyses_and_reference_genome_from_metadata
 
 
 class TestFastaChecker(TestCase):
@@ -20,8 +20,8 @@ def test_get_analysis_and_reference_genome_from_metadata(self):
 
     def test_assess_fasta_is_insdc(self):
         input_fasta = os.path.join(self.resource_dir, 'fasta_files', 'Saccharomyces_cerevisiae_I.fa')
-        with patch('bin.check_fasta_insdc.get_refget_metadata', autospec=True) as m_get_refget, \
-                patch('bin.check_fasta_insdc._get_containing_assemblies_paged', autospec=True) as m_get_assemblies:
+        with patch('eva_sub_cli.executables.check_fasta_insdc.get_refget_metadata', autospec=True) as m_get_refget, \
+                patch('eva_sub_cli.executables.check_fasta_insdc._get_containing_assemblies_paged', autospec=True) as m_get_assemblies:
             m_get_refget.return_value = {'sequence_name': 'chr1'}
             m_get_assemblies.return_value = {'GCA_000146045.2'}
             results = assess_fasta(input_fasta, ['analysis'], None)
@@ -30,8 +30,8 @@ def test_assess_fasta_is_insdc(self):
                 'sequences': [{'sequence_name': 'I', 'sequence_md5': '6681ac2f62509cfc220d78751b8dc524', 'insdc': True}],
                 'possible_assemblies': {'GCA_000146045.2'}
             }
-        with patch('bin.check_fasta_insdc.get_refget_metadata', autospec=True) as m_get_refget, \
-                patch('bin.check_fasta_insdc._get_containing_assemblies_paged', autospec=True) as m_get_assemblies:
+        with patch('eva_sub_cli.executables.check_fasta_insdc.get_refget_metadata', autospec=True) as m_get_refget, \
+                patch('eva_sub_cli.executables.check_fasta_insdc._get_containing_assemblies_paged', autospec=True) as m_get_assemblies:
             m_get_refget.return_value = None
             m_get_assemblies.return_value = set()
             results = assess_fasta(input_fasta, ['analysis'], None)
@@ -42,8 +42,8 @@ def test_assess_fasta_is_insdc(self):
 
     def test_assess_fasta_matches_metadata(self):
         input_fasta = os.path.join(self.resource_dir, 'fasta_files', 'Saccharomyces_cerevisiae_I.fa')
-        with patch('bin.check_fasta_insdc.get_refget_metadata', autospec=True) as m_get_refget, \
-                patch('bin.check_fasta_insdc._get_containing_assemblies_paged', autospec=True) as m_get_assemblies:
+        with patch('eva_sub_cli.executables.check_fasta_insdc.get_refget_metadata', autospec=True) as m_get_refget, \
+                patch('eva_sub_cli.executables.check_fasta_insdc._get_containing_assemblies_paged', autospec=True) as m_get_assemblies:
             m_get_refget.return_value = {'sequence_name': 'I'}
             m_get_assemblies.return_value = {'GCA_000146045.2'}
             results = assess_fasta(input_fasta, ['analysis'], 'GCA_000146045.2')
@@ -69,8 +69,8 @@ def test_assess_fasta_matches_metadata(self):
 
     def test_assess_fasta_http_error(self):
         input_fasta = os.path.join(self.resource_dir, 'fasta_files', 'Saccharomyces_cerevisiae_I.fa')
-        with patch('bin.check_fasta_insdc.get_refget_metadata', autospec=True) as m_get_refget, \
-                patch('bin.check_fasta_insdc._get_containing_assemblies_paged', autospec=True) as m_get_assemblies:
+        with patch('eva_sub_cli.executables.check_fasta_insdc.get_refget_metadata', autospec=True) as m_get_refget, \
+                patch('eva_sub_cli.executables.check_fasta_insdc._get_containing_assemblies_paged', autospec=True) as m_get_assemblies:
             m_get_refget.return_value = {'sequence_name': 'I'}
             m_get_assemblies.side_effect = requests.HTTPError('500 Internal Server Error')
             results = assess_fasta(input_fasta, ['analysis'], None)

tests/test_report.py

@@ -2,6 +2,7 @@
 import datetime
 from unittest import TestCase
 
+import eva_sub_cli
 from eva_sub_cli.report import generate_html_report
 
 validation_results = {
@@ -190,7 +191,10 @@ def test_generate_html_report(self):
             open_file.write(report)
 
         with open(self.expected_report) as open_html:
-            assert report == open_html.read()
+            expected_report_text = open_html.read()
+            # Inject the version in the expected report
+            expected_report_text = expected_report_text.replace('cligeneratedversion', eva_sub_cli.__version__)
+            assert report == expected_report_text
 
         # Remove output file if assert passes
         if os.path.exists('report.html'):

tests/test_samples_checker.py

@@ -3,7 +3,7 @@
 
 import yaml
 
-from bin.samples_checker import check_sample_name_concordance
+from eva_sub_cli.executables.samples_checker import check_sample_name_concordance
 
 
 class TestSampleChecker(TestCase):

tests/test_xlsx2json.py

@@ -6,7 +6,7 @@
 import yaml
 
 from eva_sub_cli import ETC_DIR
-from bin.xlsx2json import XlsxParser, create_xls_template_from_yaml
+from eva_sub_cli.executables.xlsx2json import XlsxParser, create_xls_template_from_yaml
 
 
 class TestXlsReader(TestCase):