style: apply updated style configs from template (#141)

* add flake8 config from template
* add pre-commit settings from template
* apply flake8/black/isort
* re-add linting/formatting check CI action
* update readme dev instructions

.flake8

@@ -0,0 +1,13 @@
+[flake8]
+ignore = E129,E133,E203,E221,E241,E251,E303,E266,H106,H904,W291
+max-line-length = 100
+max-complexity = 15
+hang-closing = true
+exclude =
+    .eggs
+    .tox
+    build
+    dist
+    docs/conf.py
+    tests/*
+    **/_data/migrations/*

.github/workflows/python-package.yml

@@ -4,42 +4,42 @@ on:
   push:
 
 jobs:
-  # cqa:
-  #   runs-on: ubuntu-latest
-
-  #   steps:
-  #   - uses: actions/checkout@v3
-
-  #   - name: Set up Python
-  #     uses: actions/setup-python@v4
-  #     with:
-  #       python-version: "3.10"
-  #       cache: pip
-  #       cache-dependency-path: '**/setup.cfg'
-
-  #   - name: Install test dependencies
-  #     run: |
-  #       python -m pip install --upgrade pip
-  #       pip install --use-deprecated=legacy-resolver -e .[dev]
-
-  #   - name: Lint with flake8
-  #     run: |
-  #       # stop the build if there are Python syntax errors or undefined names
-  #       flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-  #       # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-  #       flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-
-  #   - name: Format check with isort
-  #     run: |
-  #       isort --check src
-
-  #   - name: Format check with black
-  #     run: |
-  #       black --check src
-
-  #   - name: Security check with bandit
-  #     run: |
-  #       bandit -ll -r src
+  cqa:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.10"
+        cache: pip
+        cache-dependency-path: '**/setup.cfg'
+
+    - name: Install test dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install --use-deprecated=legacy-resolver -e .[dev]
+
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
+    - name: Format check with isort
+      run: |
+        isort --check src
+
+    - name: Format check with black
+      run: |
+        black --check src
+
+    - name: Security check with bandit
+      run: |
+        bandit -ll -r src
 
   test:
     runs-on: ubuntu-latest
@@ -71,7 +71,7 @@ jobs:
     - name: Test with pytest
       run: |
         make test
-        
+
   deploy:
     needs:
     # - cqa

.pre-commit-config.yaml

@@ -0,0 +1,23 @@
+repos:
+- repo: local
+  hooks:
+    -  id: flake8
+       name: flake8
+       entry: flake8
+       language: system
+       types: [python]
+    -  id: pyright
+       name: pyright
+       entry: pyright
+       language: system
+       types: [python]
+    -  id: isort
+       name: isort
+       entry: isort
+       language: system
+       types: [python]
+    -  id: black
+       name: black
+       entry: black
+       language: system
+       types: [python]

Makefile

@@ -6,7 +6,7 @@
 .SUFFIXES:
 
 
-SHELL:=bash -e -o pipefail -O globstar
+SHELL:=bash -e -o pipefail # -O globstar
 
 SELF:=$(firstword $(MAKEFILE_LIST))
 
@@ -47,6 +47,7 @@ ${VE_DIR}:
 .PHONY: develop
 develop:
 	pip install -e .[dev]
+	pre-commit install
 
 #=> install: install package
 .PHONY: install
@@ -91,6 +92,18 @@ test-%:
 tox:
 	tox
 
+#=> cqa: execute code quality tests
+cqa:
+	flake8 src --show-source --statistics
+	pyright
+	isort --check src --profile black
+	black --check src
+	bandit -ll -r src
+
+#=> reformat: reformat code
+.PHONY: reformat
+reformat:
+	pre-commit
 
 ############################################################################
 #= UTILITY TARGETS
@@ -144,13 +157,13 @@ distclean: cleanest
 
 ## <LICENSE>
 ## Copyright 2023 Source Code Committers
-## 
+##
 ## Licensed under the Apache License, Version 2.0 (the "License");
 ## you may not use this file except in compliance with the License.
 ## You may obtain a copy of the License at
-## 
+##
 ##     http://www.apache.org/licenses/LICENSE-2.0
-## 
+##
 ## Unless required by applicable law or agreed to in writing, software
 ## distributed under the License is distributed on an "AS IS" BASIS,
 ## WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

README.md

@@ -124,11 +124,11 @@ tested. Patches to get other systems working would be welcomed.
     $ pip install seqrepo
     $ sudo mkdir -p /usr/local/share/seqrepo
     $ sudo chown $USER /usr/local/share/seqrepo
-    $ seqrepo pull -i 2018-11-26 
-    $ seqrepo show-status -i 2018-11-26 
+    $ seqrepo pull -i 2018-11-26
+    $ seqrepo show-status -i 2018-11-26
     seqrepo 0.2.3.post3.dev8+nb8298bd62283
     root directory: /usr/local/share/seqrepo/2018-11-26, 7.9 GB
-    backends: fastadir (schema 1), seqaliasdb (schema 1) 
+    backends: fastadir (schema 1), seqaliasdb (schema 1)
     sequences: 773587 sequences, 93051609959 residues, 192 files
     aliases: 5579572 aliases, 5480085 current, 26 namespaces, 773587 sequences
 
@@ -187,6 +187,15 @@ Here's how to get started developing:
     source venv/bin/activate
     seqrepo --version
 
+Code reformatting:
+
+    make reformat
+
+Install pre-commit hook:
+
+    # included in `make devready`, not necessary for new installations
+    pre-commit install
+
 ## Building a docker image
 
 Docker images are available at https://hub.docker.com/r/biocommons/seqrepo.

pyproject.toml

@@ -124,11 +124,6 @@ line-length = 100
 profile = "black"
 src_paths = ["src", "tests"]
 
-# [tool.flake8]
-# flake8 does not support configuration in pyproject.toml
-# https://github.com/PyCQA/flake8/issues/234#issuecomment-812800832
-# The config in setup.cfg
-
 [tool.pyright]
 include = ["src", "tests"]
 

src/biocommons/seqrepo/_internal/logging_support.py

@@ -1,6 +1,3 @@
-import logging
-
-
 class DuplicateFilter:
     """
     Filters away duplicate log messages.

src/biocommons/seqrepo/_versionwarning.py

@@ -1,20 +1,13 @@
-"""emits a warning when imported under Python < 3.6
-
-This module may be used by other biocommons packages
-
-"""
+"""emits a warning when imported under Python < 3.9"""
 
 import logging
 import sys
 
 __all__ = []
 
-version_warning = (
-    "biocommons packages are tested and supported only on Python >= 3.6"
-    " (https://github.com/biocommons/org/wiki/Migrating-to-Python-3.6)"
-)
+version_warning = "This package is tested and supported only on Python >= 3.9."
 
 _logger = logging.getLogger(__package__)
 
-if sys.version_info < (3, 6):
+if sys.version_info < (3, 9):
     _logger.warning(version_warning)

src/biocommons/seqrepo/cli.py

@@ -20,7 +20,6 @@
 import itertools
 import logging
 import os
-import pprint
 import re
 import shutil
 import stat
@@ -30,7 +29,6 @@
 
 import bioutils.assemblies
 import bioutils.seqfetcher
-import six
 import tqdm
 
 from . import SeqRepo, __version__
@@ -62,7 +60,7 @@ def _get_remote_instances(opts):
     ]
     _logger.debug("Executing `" + " ".join(rsync_cmd) + "`")
     lines = subprocess.check_output(rsync_cmd).decode().splitlines()[1:]
-    dirs = (m.group(1) for m in (line_re.match(l) for l in lines) if m)
+    dirs = (m.group(1) for m in (line_re.match(line) for line in lines) if m)
     return sorted(list(filter(instance_name_new_re.match, dirs)))
 
 
@@ -81,12 +79,14 @@ def _latest_instance_path(opts):
 
 
 def parse_arguments():
+    epilog = (
+        f"seqrepo {__version__}"
+        "See https://github.com/biocommons/biocommons.seqrepo for more information"
+    )
     top_p = argparse.ArgumentParser(
         description=__doc__.split("\n\n")[0],
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
-        epilog="seqrepo "
-        + __version__
-        + ". See https://github.com/biocommons/biocommons.seqrepo for more information",
+        epilog=epilog,
     )
     top_p.add_argument("--dry-run", "-n", default=False, action="store_true")
     top_p.add_argument("--remote-host", default="dl.biocommons.org", help="rsync server host")
@@ -352,12 +352,12 @@ def add_assembly_names(opts):
         ]
         if not_in_seqrepo:
             _logger.warning(
-                "Assembly {an} references {n} accessions not in SeqRepo instance {opts.instance_name} (e.g., {acs})".format(
+                "Assembly {an} references {n} accessions not in SeqRepo instance "
+                "{opts.instance_name} (e.g., {acs})".format(
                     an=assy_name,
                     n=len(not_in_seqrepo),
                     opts=opts,
                     acs=", ".join(not_in_seqrepo[:5] + ["..."]),
-                    seqrepo_dir=seqrepo_dir,
                 )
             )
             if not opts.partial_load:
@@ -432,8 +432,8 @@ def _rec_iterator():
             "{ns}:{a}".format(ns=ns, a=a) for ns, aliases in sorted(nsad.items()) for a in aliases
         ]
         print(">" + " ".join(aliases))
-        for l in _wrap_lines(srec["seq"], 100):
-            print(l)
+        for line in _wrap_lines(srec["seq"], 100):
+            print(line)
 
 
 def export_aliases(opts):
@@ -477,7 +477,7 @@ def init(opts):
     seqrepo_dir = os.path.join(opts.root_directory, opts.instance_name)
     if os.path.exists(seqrepo_dir) and len(os.listdir(seqrepo_dir)) > 0:
         raise IOError("{seqrepo_dir} exists and is not empty".format(seqrepo_dir=seqrepo_dir))
-    sr = SeqRepo(seqrepo_dir, writeable=True)  # flake8: noqa
+    sr = SeqRepo(seqrepo_dir, writeable=True)  # noqa: F841
 
 
 def list_local_instances(opts):
@@ -586,14 +586,12 @@ def show_status(opts):
         )
     )
     print(
-        "sequences: {ss[n_sequences]} sequences, {ss[tot_length]} residues, {ss[n_files]} files".format(
-            ss=sr.sequences.stats()
-        )
+        "sequences: {ss[n_sequences]} sequences, {ss[tot_length]} residues, "
+        "{ss[n_files]} files".format(ss=sr.sequences.stats())
     )
     print(
-        "aliases: {sa[n_aliases]} aliases, {sa[n_current]} current, {sa[n_namespaces]} namespaces, {sa[n_sequences]} sequences".format(
-            sa=sr.aliases.stats()
-        )
+        "aliases: {sa[n_aliases]} aliases, {sa[n_current]} current, "
+        "{sa[n_namespaces]} namespaces, {sa[n_sequences]} sequences".format(sa=sr.aliases.stats())
     )
     return sr
 
@@ -679,7 +677,7 @@ def _drop_write(p):
 
 def start_shell(opts):
     seqrepo_dir = os.path.join(opts.root_directory, opts.instance_name)
-    sr = SeqRepo(seqrepo_dir)
+    sr = SeqRepo(seqrepo_dir)  # noqa: 682
     import IPython
 
     IPython.embed(

src/biocommons/seqrepo/config.py

@@ -18,5 +18,6 @@ def parse_caching_env_var(env_name: str, env_default: str) -> Optional[int]:
 
 
 SEQREPO_LRU_CACHE_MAXSIZE = parse_caching_env_var("SEQREPO_LRU_CACHE_MAXSIZE", "1000000")
-# Using a default value here of -1 to differentiate not setting this env var and an explicit None (unbounded cache)
+# Using a default value here of -1 to differentiate not setting this env var and an
+# explicit None (unbounded cache)
 SEQREPO_FD_CACHE_MAXSIZE = parse_caching_env_var("SEQREPO_FD_CACHE_MAXSIZE", "-1")

src/biocommons/seqrepo/dataproxy.py

@@ -10,7 +10,6 @@
 import logging
 import os
 from abc import ABC, abstractmethod
-from collections.abc import Sequence
 from urllib.parse import urlparse
 
 import requests
@@ -149,7 +148,7 @@ def _get_sequence(self, identifier, start=None, end=None):
         url = self.base_url + f"sequence/{identifier}"
         params = {"start": start, "end": end}
         _logger.info(f"Fetching {url} {params if (start or end) else ''}")
-        resp = requests.get(url, params=params)
+        resp = requests.get(url, params=params, timeout=60)
         if resp.status_code == 404:
             raise KeyError(identifier)
         resp.raise_for_status()
@@ -158,7 +157,7 @@ def _get_sequence(self, identifier, start=None, end=None):
     def _get_metadata(self, identifier):
         url = self.base_url + f"metadata/{identifier}"
         _logger.info("Fetching %s", url)
-        resp = requests.get(url)
+        resp = requests.get(url, timeout=60)
         if resp.status_code == 404:
             raise KeyError(identifier)
         resp.raise_for_status()

src/biocommons/seqrepo/fastadir/__init__.py

@@ -1 +1 @@
-from .fastadir import FastaDir
+from .fastadir import FastaDir  # noqa: F401