style: apply style black, flake8, isort (biocommons#108)

Also includes this as a check in CI.

.github/workflows/ci.yml

@@ -17,7 +17,45 @@ jobs:
         env:
           GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
 
+  linting:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v1
+
+      - name: Install Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.8"
+
+      - name: Install dependencies
+        run: |
+            # Install / update package management tools
+            pip install -U pip setuptools
+            # Test dependencies
+            pip install -U pytest pytest-cov pytest-vcr black==23.3.0 flake8>=6.0,<7.0 isort>=5.0,<6.0
+            # Dump installed packages and versions
+            pip freeze
+
+      - name: Run linting tools
+        run: |
+          black -l 120 --check --diff .
+          isort --profile=black --check --diff .
+          flake8 src tests docs setup.py
+
+      - name: Comment PR
+        if: github.event_name == 'pull_request' && failure()
+        uses: marocchino/sticky-pull-request-comment@v1.1.0
+        with:
+          message: |
+            - Please format your Python code with [black](https://black.readthedocs.io): `make black`
+            - Please organize your imports [isorts](https://isort.readthedocs.io): `make isort`
+            - Please ensure that your code passes [flake8](https://flake8.pycqa.org/en/latest/): `make flake8`
+
+            You can trigger all lints locally by running `black -l 120 --check . && isort --profile=black --check . && flake8 src tests docs setup.py`
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
   testing:
+    needs: linting
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -36,12 +74,17 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
 
-      - name: Install system dependencies
+      - name: Install dependencies
         run: |
           sudo apt install libhts-dev libhts3 libhtscodecs-dev libhtscodecs2 tabix
+          # Install / update package management tools.
           pip install -U pip setuptools
-          pip install -U pytest pytest-cov pytest-vcr
+          # Test dependencies
+          pip install -U pytest pytest-cov pytest-vcr black==23.3.0 flake8>=6.0,<7.0 isort>=5.0,<6.0
+          # Install the local package itself in editable mode.
           pip install -e .
+          # Dump installed packages and versions
+          pip freeze
 
       - name: Run tests
         run: |

.gitignore

@@ -1,3 +1,7 @@
+# Editors
+.*.sw?
+*~
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

docs/utils.py

@@ -1,13 +1,11 @@
+import math
 from base64 import urlsafe_b64decode, urlsafe_b64encode
 from binascii import hexlify, unhexlify
-import datetime
-import math
-import sys
 
 
 def _format_time(timespan, precision=3):
     """Formats the timespan in a human readable form
-    
+
     >>> _format_time(0.35)
     '350 ms'
 
@@ -26,21 +24,21 @@ def _format_time(timespan, precision=3):
     if timespan >= 60.0:
         # we have more than a minute, format that in a human readable form
         # Idea from http://snipplr.com/view/5713/
-        parts = [("d", 60*60*24),("h", 60*60),("min", 60), ("s", 1)]
+        parts = [("d", 60 * 60 * 24), ("h", 60 * 60), ("min", 60), ("s", 1)]
         time = []
         leftover = timespan
         for suffix, length in parts:
             value = int(leftover / length)
             if value > 0:
                 leftover = leftover % length
-                time.append(u'%s%s' % (str(value), suffix))
+                time.append(u"%s%s" % (str(value), suffix))
             if leftover < 1:
                 break
         return " ".join(time)
 
-    units = [u"s", u"ms", u"us", u"ns"]  # the save value   
+    units = [u"s", u"ms", u"us", u"ns"]  # the save value
     scaling = [1, 1e3, 1e6, 1e9]
-        
+
     if timespan > 0.0:
         order = min(-int(math.floor(math.log10(timespan)) // 3), 3)
     else:
@@ -51,6 +49,6 @@ def _format_time(timespan, precision=3):
 def hex_to_base64url(s):
     return urlsafe_b64encode(unhexlify(s)).decode("ascii")
 
+
 def base64url_to_hex(s):
     return hexlify(urlsafe_b64decode(s)).decode("ascii")
-

fixes/fixer

@@ -8,14 +8,13 @@ This script isn't for general users
 
 import argparse
 import logging
-import sqlite3
 import os
+import sqlite3
 import sys
 
 import coloredlogs
 import yaml
 
-
 _logger = logging.getLogger()
 
 fixes_dir = os.path.dirname(sys.argv[0])

misc/rsync-log-summary

@@ -11,7 +11,6 @@ import sys
 import coloredlogs
 from dateutil.parser import parse
 
-
 _logger = logging.getLogger(__name__)
 
 # e.g., 2016/08/31 01:24:34 [32383] rsync on seqrepo/ from ec2-....compute.amazonaws.com (52.34.43.195)

misc/threading-verification.py

@@ -22,9 +22,9 @@
 
 
 import os
-from multiprocessing import Process, Queue
 import sqlite3
 import sys
+from multiprocessing import Process, Queue
 
 from biocommons.seqrepo import SeqRepo
 
@@ -37,7 +37,7 @@ def fetch_in_thread(sr, nsa):
     def fetch_seq(q, nsa):
         pid, ppid = os.getpid(), os.getppid()
         q.put((pid, ppid, sr[nsa]))
-    
+
     q = Queue()
     p = Process(target=fetch_seq, args=(q, nsa))
     p.start()
@@ -46,9 +46,9 @@ def fetch_seq(q, nsa):
 
     assert pid != ppid, "sequence was not fetched from thread"
     return pid, ppid, seq
-
 
-def make_seqrepo(writeable):    
+
+def make_seqrepo(writeable):
     sr = SeqRepo("/tmp/sr", writeable=True)
     sr.store("SMELLASSWEET", [{"namespace": "en", "alias": "rose"}, {"namespace": "fr", "alias": "rose"}])
 
@@ -70,6 +70,6 @@ def _test(sr):
     print("sys.platform: " + sys.platform)
     print("sys.version: " + sys.version.replace("\n", " "))
     print("sqlite3.sqlite_version: " + sqlite3.sqlite_version)
-    
+
     _test(make_seqrepo(writeable=False))
     _test(make_seqrepo(writeable=True))

sbin/get-sequence-urls

@@ -15,9 +15,9 @@ import logging
 import re
 import sys
 from urllib.request import urljoin, urlopen
-from requests_html import HTMLSession, HTML
 
 import coloredlogs
+from requests_html import HTML, HTMLSession
 
 _logger = logging.getLogger(__name__)
 

setup.cfg

@@ -103,6 +103,5 @@ all_files  = 1
 max-line-length = 120
 exclude = tests/*
 max-complexity = 10
-ignore = E129,E221,E241,E251,E303,W291
-
+ignore = E203, E266, E501, W503
 

setup.py

@@ -1,2 +1,3 @@
 from setuptools import setup
+
 setup(use_scm_version=True)

src/biocommons/__init__.py

@@ -1,3 +1,4 @@
 # pragma: nocover
 import pkg_resources
+
 pkg_resources.declare_namespace(__name__)

src/biocommons/seqrepo/__init__.py

@@ -2,24 +2,24 @@
 from __future__ import absolute_import, division, print_function, unicode_literals
 
 import logging
-import pkg_resources
 import warnings
 
+import pkg_resources
+
 _logger = logging.getLogger(__name__)
 
-from ._versionwarning import *
+from ._versionwarning import *  # noqa; F403
 
 try:
     __version__ = pkg_resources.get_distribution(__name__).version
-except pkg_resources.DistributionNotFound as e:    # pragma: no cover
+except pkg_resources.DistributionNotFound:  # pragma: no cover
     warnings.warn("can't get __version__ because %s package isn't installed" % __package__, Warning)
     __version__ = None
 
 _logger.info(__name__ + " " + __version__)
 
 
-from .seqrepo import SeqRepo
-
+from .seqrepo import SeqRepo  # noqa: F401, E402
 
 # <LICENSE>
 # Copyright 2016 biocommons.fastadir Contributors (https://github.com/biocommons/biocommons.fastadir/)

src/biocommons/seqrepo/_internal/logging_support.py

@@ -1,5 +1,3 @@
-import logging
-
 class DuplicateFilter:
     """
     Filters away duplicate log messages.