add lint, changelog reminder, black and isort

.github/workflows/keep_a_changelog.yml

@@ -0,0 +1,15 @@
+name: "Changelog Reminder"
+on:
+  pull_request:
+      types: [opened, synchronize, reopened, ready_for_review, labeled, unlabeled]
+
+jobs:
+  # Enforces the update of a changelog file on every pull request
+  changelog:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: dangoslen/changelog-enforcer@v3
+      with:
+        changeLogPath: 'CHANGELOG.md'
+        skipLabels: 'Skip-Changelog'

.github/workflows/linting_only.yml

@@ -0,0 +1,47 @@
+name: Lint files - no fixing
+
+# This will check linting in local PRs
+on: ["push", "pull_request"]
+
+jobs:
+  build:
+
+    name: Lint-only
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.11]
+
+    steps:
+
+    # Check out Scout code
+    - name: Check out git repository
+      uses: actions/checkout@v4
+
+    # Set up python
+    - name: Set up Python ${{ matrix.python-version}}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version}}
+
+    - name: Install Python Dependencies
+      run: |
+        pip install black flake8 isort
+
+    - name: Run linters
+      uses: wearerequired/lint-action@v2
+      # Let linters fix problems if they can
+      with:
+        github_token: ${{ secrets.github_token }}
+        auto_fix: false
+        # Enable linters
+        black: true
+        black_args: "--check -l 100"
+        # stop the build if there are Python syntax errors or undefined names
+        flake8: true
+        flake8_args: "chanjo/ --count --select=E9,F63,F7,F82 --show-source --statistics"
+
+    - name: Run isort
+      uses: jamescurtin/isort-action@master
+      with:
+          configuration: "--check-only --diff -m 3 --tc --fgw 0 --up -n -l 100"

CHANGELOG.md

@@ -5,6 +5,8 @@ This project adheres to [Semantic Versioning](http://semver.org/).
 ## [4.7.1] - 2024-06-05
 ### Fixed
 - Added `cryptography` module among the dependencies
+- Refactored to allow later python versions than 3.8 (pkg_resources to importlib, os.path and path.py to pathlib, distutils to shutil) [#262](https://github.com/Clinical-Genomics/chanjo/pull/262)
+- Updated actions to use python 3.11, add changelog reminder, add linting, format for linters
 
 ## [4.7] - 2024-05-22
 ### Added

chanjo/__init__.py

@@ -8,6 +8,7 @@
 :licence: MIT, see LICENCE for more details
 """
 import logging
+
 try:
     from importlib.metadata import version
 except ImportError:  # Backport support for importlib metadata on Python 3.7
@@ -23,18 +24,18 @@
                             /___/
 """
 
-__title__ = 'chanjo'
-__summary__ = 'coverage analysis tool for clinical sequencing'
-__uri__ = 'http://www.chanjo.co/'
+__title__ = "chanjo"
+__summary__ = "coverage analysis tool for clinical sequencing"
+__uri__ = "http://www.chanjo.co/"
 
 __version__ = version(__title__)
-__codename__ = 'Optimistic Otter'
+__codename__ = "Optimistic Otter"
 
-__author__ = 'Robin Andeer'
-__email__ = '[email protected]'
+__author__ = "Robin Andeer"
+__email__ = "[email protected]"
 
-__license__ = 'MIT'
-__copyright__ = 'Copyright 2016 Robin Andeer'
+__license__ = "MIT"
+__copyright__ = "Copyright 2016 Robin Andeer"
 
 # the user should dictate what happens when a logging event occurs
 logging.getLogger(__name__).addHandler(logging.NullHandler())

chanjo/calculate.py

@@ -6,7 +6,6 @@
 
 
 class CalculateMixin:
-
     """Methods for calculating various metrics."""
 
     def mean(self, sample_ids=None):
@@ -39,16 +38,21 @@ def gene_metrics(self, *genes):
     def sample_coverage(self, sample_ids: list, genes: list) -> dict:
         """Calculate coverage for samples."""
         with self.begin() as session:
-            query = session.query(
-                TranscriptStat.sample_id.label('sample_id'),
-                func.avg(TranscriptStat.mean_coverage).label('mean_coverage'),
-                func.avg(TranscriptStat.completeness_10).label('mean_completeness'),
-            ).join(
-                Transcript,
-            ).filter(
-                Transcript.gene_id.in_(genes),
-                TranscriptStat.sample_id.in_(sample_ids),
-            ).group_by(TranscriptStat.sample_id)
+            query = (
+                session.query(
+                    TranscriptStat.sample_id.label("sample_id"),
+                    func.avg(TranscriptStat.mean_coverage).label("mean_coverage"),
+                    func.avg(TranscriptStat.completeness_10).label("mean_completeness"),
+                )
+                .join(
+                    Transcript,
+                )
+                .filter(
+                    Transcript.gene_id.in_(genes),
+                    TranscriptStat.sample_id.in_(sample_ids),
+                )
+                .group_by(TranscriptStat.sample_id)
+            )
 
             data = {
                 result.sample_id: {

chanjo/cli/__init__.py

@@ -1,7 +1,7 @@
 from .base import root
 from .calculate import calculate
-from .sex import sex
-from .load import link, load
-from .sambamba import sambamba
 from .db import db_cmd
 from .init import init
+from .load import link, load
+from .sambamba import sambamba
+from .sex import sex

chanjo/cli/base.py

@@ -6,6 +6,7 @@
 """
 import logging
 import os
+
 try:
     from importlib.metadata import entry_points
 except ImportError:  # Backport support for importlib metadata on Python 3.7
@@ -15,19 +16,20 @@
 import coloredlogs
 import yaml
 
-from chanjo import __version__, __title__
+from chanjo import __title__, __version__
 
 LOG = logging.getLogger(__name__)
 
-COMMAND_GROUP_KEY = 'chanjo.subcommands.4'
+COMMAND_GROUP_KEY = "chanjo.subcommands.4"
+
 
 class EntryPointsCLI(click.MultiCommand):
     """Add sub-commands dynamically to a CLI via entry points."""
 
     def _iter_commands(self):
         """Iterate over all sub-commands as defined by the entry point."""
         # Get all entry points for the specified group
-        if hasattr(entry_points(), 'select'):
+        if hasattr(entry_points(), "select"):
             # Python >3.10, importlib
             eps = entry_points(group=COMMAND_GROUP_KEY)
         else:
@@ -49,16 +51,17 @@ def get_command(self, ctx, name):
 
 
 @click.group(cls=EntryPointsCLI)
-@click.option('-c', '--config', default='./chanjo.yaml',
-              type=click.Path(), help='path to config file')
-@click.option('-d', '--database', help='path/URI of the SQL database')
-@click.option('-l', '--log-level', default='INFO')
-@click.option('--log-file', type=click.File('a'))
+@click.option(
+    "-c", "--config", default="./chanjo.yaml", type=click.Path(), help="path to config file"
+)
+@click.option("-d", "--database", help="path/URI of the SQL database")
+@click.option("-l", "--log-level", default="INFO")
+@click.option("--log-file", type=click.File("a"))
 @click.version_option(__version__, prog_name=__title__)
 @click.pass_context
 def root(context, config, database, log_level, log_file):
     """Clinical sequencing coverage analysis tool."""
-    logout = log_file or click.get_text_stream('stderr')
+    logout = log_file or click.get_text_stream("stderr")
     coloredlogs.install(level=log_level, stream=logout)
     LOG.debug("version %s", __version__)
 
@@ -68,7 +71,7 @@ def root(context, config, database, log_level, log_file):
             context.obj = yaml.safe_load(conf_handle)
     else:
         context.obj = {}
-    context.obj['database'] = (database or context.obj.get('database'))
+    context.obj["database"] = database or context.obj.get("database")
 
     # Update the context with new defaults from the config file
     context.default_map = context.obj

chanjo/cli/calculate.py

@@ -1,11 +1,12 @@
 """Functions for calculating operations on database"""
+
 import json
 import logging
 
 import click
 
 from chanjo.store.api import ChanjoDB
-from chanjo.store.constants import STAT_COLUMNS, OMIM_GENE_IDS
+from chanjo.store.constants import OMIM_GENE_IDS, STAT_COLUMNS
 
 LOG = logging.getLogger(__name__)
 
@@ -23,30 +24,30 @@ def dump_json(data, pretty=False):
 @click.pass_context
 def calculate(context):
     """Calculate statistics across samples."""
-    context.obj['db'] = ChanjoDB(uri=context.obj['database'])
+    context.obj["db"] = ChanjoDB(uri=context.obj["database"])
 
 
 @calculate.command()
-@click.option('-p', '--pretty', is_flag=True)
-@click.option('-s', '--sample', multiple=True, help='sample to limit query to')
+@click.option("-p", "--pretty", is_flag=True)
+@click.option("-s", "--sample", multiple=True, help="sample to limit query to")
 @click.pass_context
 def mean(context, sample, pretty):
     """Calculate mean statistics."""
-    query = context.obj['db'].mean(sample_ids=sample)
-    columns = ['sample_id'] + STAT_COLUMNS
+    query = context.obj["db"].mean(sample_ids=sample)
+    columns = ["sample_id"] + STAT_COLUMNS
     for result in query:
         row = {column: value for column, value in zip(columns, result)}
         click.echo(dump_json(row, pretty=pretty))
 
 
 @calculate.command()
-@click.option('-p', '--pretty', is_flag=True, help="Print in pretty format")
-@click.option('-s', '--sample', multiple=True, type=str, help="Sample to get coverage for")
-@click.option('-o', '--omim', is_flag=True, help="Use genes in the OMIM panel")
-@click.option('-f', '--gene-file',
-              type=click.Path(exists=True),
-              help="File with row separated gene IDs")
-@click.argument('genes', nargs=-1)
+@click.option("-p", "--pretty", is_flag=True, help="Print in pretty format")
+@click.option("-s", "--sample", multiple=True, type=str, help="Sample to get coverage for")
+@click.option("-o", "--omim", is_flag=True, help="Use genes in the OMIM panel")
+@click.option(
+    "-f", "--gene-file", type=click.Path(exists=True), help="File with row separated gene IDs"
+)
+@click.argument("genes", nargs=-1)
 @click.pass_context
 def coverage(context, pretty, sample, omim, gene_file, genes):
     """Calculate coverage for sample on specified genes"""
@@ -55,5 +56,5 @@ def coverage(context, pretty, sample, omim, gene_file, genes):
     if gene_file:
         with open(gene_file) as file_handle:
             genes = file_handle.read().strip().split("\n")
-    query = context.obj['db'].sample_coverage(sample_ids=sample, genes=list(genes))
+    query = context.obj["db"].sample_coverage(sample_ids=sample, genes=list(genes))
     click.echo(dump_json(query, pretty=pretty))

chanjo/cli/db.py

@@ -59,9 +59,7 @@ def samples(context, group_id, sample_id, pretty):
     indent = None
     if pretty:
         indent = 4
-    click.echo(
-        json.dumps([dict(result) for result in query], default=str, indent=indent)
-    )
+    click.echo(json.dumps([dict(result) for result in query], default=str, indent=indent))
 
 
 @db_cmd.command()
@@ -75,9 +73,7 @@ def transcripts(context, sample_id, pretty):
     indent = None
     if pretty:
         indent = 4
-    click.echo(
-        json.dumps([dict(result) for result in query], default=str, indent=indent)
-    )
+    click.echo(json.dumps([dict(result) for result in query], default=str, indent=indent))
 
 
 @db_cmd.command()

chanjo/cli/init.py

@@ -1,36 +1,36 @@
 # -*- coding: utf-8 -*-
 import codecs
-from shutil import which
 import logging
+from pathlib import Path
+from shutil import which
 
 import click
-from pathlib import Path
 import yaml
 
+from chanjo.init.bootstrap import BED_NAME, DB_NAME, pull
+from chanjo.init.demo import DEMO_BED_NAME, setup_demo
 from chanjo.store.api import ChanjoDB
-from chanjo.init.bootstrap import pull, BED_NAME, DB_NAME
-from chanjo.init.demo import setup_demo, DEMO_BED_NAME
 
 LOG = logging.getLogger(__name__)
 
 
 @click.command()
-@click.option('-f', '--force', is_flag=True, help='overwrite existing files')
-@click.option('-d', '--demo', is_flag=True, help='copy demo files')
-@click.option('-a', '--auto', is_flag=True)
-@click.argument('root_dir', default='.', required=False)
+@click.option("-f", "--force", is_flag=True, help="overwrite existing files")
+@click.option("-d", "--demo", is_flag=True, help="copy demo files")
+@click.option("-a", "--auto", is_flag=True)
+@click.argument("root_dir", default=".", required=False)
 @click.pass_context
 def init(context, force, demo, auto, root_dir):
     """Bootstrap a new chanjo setup."""
     is_bootstrapped = False
     root_path = Path(root_dir)
 
     LOG.info("setting up chanjo under: %s", root_path)
-    db_uri = context.obj.get('database')
+    db_uri = context.obj.get("database")
     db_uri = db_uri or "sqlite:///{}".format(root_path.joinpath(DB_NAME).resolve())
 
     # test setup of sambamba
-    sambamba_bin = which('sambamba')
+    sambamba_bin = which("sambamba")
     if sambamba_bin is None:  # pragma: no cover
         LOG.warning("'sambamba' command not found")
     else:
@@ -44,7 +44,7 @@ def init(context, force, demo, auto, root_dir):
         chanjo_db = ChanjoDB(db_uri)
         chanjo_db.set_up()
         is_bootstrapped = True
-    elif auto or click.confirm('Bootstrap HGNC transcript BED?'):
+    elif auto or click.confirm("Bootstrap HGNC transcript BED?"):
         pull(root_dir, force=force)
 
         LOG.info("configure new chanjo database: %s", db_uri)
@@ -54,13 +54,13 @@ def init(context, force, demo, auto, root_dir):
 
     # setup config file
     root_path.mkdir(parents=True, exist_ok=True)
-    conf_path = root_path.joinpath('chanjo.yaml')
-    with open(conf_path, 'w') as conf_handle:
-        data = {'database': db_uri}
+    conf_path = root_path.joinpath("chanjo.yaml")
+    with open(conf_path, "w") as conf_handle:
+        data = {"database": db_uri}
         LOG.info("writing config file: %s", conf_path)
         yaml.dump(data, conf_handle, default_flow_style=False)
 
     if is_bootstrapped:
-        click.echo('Chanjo bootstrap successful! Now run: ')
+        click.echo("Chanjo bootstrap successful! Now run: ")
         bed_path = root_path.joinpath(DEMO_BED_NAME if demo else BED_NAME)
         click.echo("chanjo --config {} link {}".format(conf_path, bed_path))