style: apply flake8, black, isort

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):
@@ -586,12 +586,14 @@ def show_status(opts):
         )
     )
     print(
-        "sequences: {ss[n_sequences]} sequences, {ss[tot_length]} residues, {ss[n_files]} files".format(
+        "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(
+        "aliases: {sa[n_aliases]} aliases, {sa[n_current]} current, "
+        "{sa[n_namespaces]} namespaces, {sa[n_sequences]} sequences".format(
             sa=sr.aliases.stats()
         )
     )
@@ -679,7 +681,7 @@ 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

src/biocommons/seqrepo/fastadir/__init__.py

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

src/biocommons/seqrepo/fastadir/fabgz.py

@@ -53,7 +53,8 @@ def _find_bgzip():
         raise RuntimeError("Didn't find version string in bgzip executable ({exe})".format(exe=exe))
     except missing_file_exception:
         raise RuntimeError(
-            "{exe} doesn't exist; you need to install htslib and tabix (See https://github.com/biocommons/biocommons.seqrepo#requirements)".format(
+            "{exe} doesn't exist; you need to install htslib and tabix "
+            "(See https://github.com/biocommons/biocommons.seqrepo#requirements)".format(
                 exe=exe
             )
         )
@@ -74,7 +75,8 @@ class FabgzReader(object):
     """
     Class that implements ContextManager and wraps a FabgzReader.
     The FabgzReader is returned when acquired in a contextmanager with statement.
-    """ 
+    """
+
     def __init__(self, filename):
         self.lock = threading.Lock()
         self._fh = FastaFile(filename)
@@ -141,8 +143,8 @@ def wrap_lines(seq, line_width):
 
         if seq_id not in self._added:
             self._fh.write(">" + seq_id + "\n")
-            for l in wrap_lines(seq, line_width):
-                self._fh.write(l + "\n")
+            for line in wrap_lines(seq, line_width):
+                self._fh.write(line + "\n")
             self._added.add(seq_id)
             _logger.debug("added seq_id {i}; length {l}".format(i=seq_id, l=len(seq)))
         return seq_id

src/biocommons/seqrepo/fastadir/fastadir.py

@@ -1,5 +1,3 @@
-import contextlib
-import threading
 import datetime
 import functools
 import importlib.resources
@@ -83,7 +81,7 @@ def __init__(self, root_dir, writeable=False, check_same_thread=True, fd_cache_s
             )
 
         if fd_cache_size == 0:
-            _logger.info(f"File descriptor caching disabled")
+            _logger.info("File descriptor caching disabled")
         else:
             _logger.warning(f"File descriptor caching enabled (size={fd_cache_size})")
 

src/biocommons/seqrepo/fastaiter/__init__.py

@@ -1 +1 @@
-from .fastaiter import FastaIter
+from .fastaiter import FastaIter  # noqa: F401

src/biocommons/seqrepo/fastaiter/fastaiter.py

@@ -8,14 +8,14 @@ def FastaIter(handle):
     for line in handle:
         if line.startswith(">"):
             if header is not None:  # not the first record
-                yield header, "".join(seq_lines)
+                yield header, "".join(seq_lines)  # noqa: F821
             seq_lines = list()
             header = line[1:].rstrip()
         else:
             if header is not None:  # not the first record
-                seq_lines.append(line.strip())
+                seq_lines.append(line.strip())  # noqa: F821
 
     if header is not None:
-        yield header, "".join(seq_lines)
+        yield header, "".join(seq_lines)  # noqa: F821
     else:  # no FASTA records in file
         return

src/biocommons/seqrepo/seqaliasdb/__init__.py

@@ -1 +1 @@
-from .seqaliasdb import SeqAliasDB
+from .seqaliasdb import SeqAliasDB  # noqa: F401

src/biocommons/seqrepo/seqaliasdb/seqaliasdb.py

@@ -1,11 +1,9 @@
-import itertools
 import logging
 import sqlite3
 
 import pkg_resources
 import yoyo
 
-from .._internal.logging_support import DuplicateFilter
 from .._internal.translate import translate_alias_records, translate_api2db
 
 _logger = logging.getLogger(__name__)
@@ -39,7 +37,8 @@ def __init__(
 
         if translate_ncbi_namespace is not None:
             _logger.warning(
-                "translate_ncbi_namespace is obsolete; translation is now automatic; this flag will be removed"
+                "translate_ncbi_namespace is obsolete; translation is now automatic; "
+                "this flag will be removed"
             )
 
         if self._writeable:
@@ -87,7 +86,8 @@ def fetch_aliases(self, seq_id, current_only=True, translate_ncbi_namespace=None
         )
         if translate_ncbi_namespace is not None:
             _logger.warning(
-                "translate_ncbi_namespace is obsolete; translation is now automatic; this flag will be removed"
+                "translate_ncbi_namespace is obsolete; translation is now automatic; "
+                "this flag will be removed"
             )
         return [dict(r) for r in self.find_aliases(seq_id=seq_id, current_only=current_only)]
 
@@ -119,7 +119,8 @@ def eq_or_like(s):
 
         if translate_ncbi_namespace is not None:
             _logger.warning(
-                "translate_ncbi_namespace is obsolete; translation is now automatic; this flag will be removed"
+                "translate_ncbi_namespace is obsolete; translation is now automatic; "
+                "this flag will be removed"
             )
 
         if namespace is not None:

src/biocommons/seqrepo/seqrepo.py

@@ -7,7 +7,7 @@
 import bioutils.digests
 from bioutils.digests import seq_seqhash as sha512t24u
 
-from .config import SEQREPO_LRU_CACHE_MAXSIZE, SEQREPO_FD_CACHE_MAXSIZE
+from .config import SEQREPO_FD_CACHE_MAXSIZE, SEQREPO_LRU_CACHE_MAXSIZE
 from .fastadir import FastaDir
 from .seqaliasdb import SeqAliasDB
 
@@ -100,7 +100,7 @@ def __init__(
         translate_ncbi_namespace=None,
         check_same_thread=False,
         use_sequenceproxy=True,
-        fd_cache_size=0
+        fd_cache_size=0,
     ):
         self._root_dir = root_dir
         self._upcase = upcase
@@ -123,7 +123,9 @@ def __init__(
             self._seq_path,
             writeable=self._writeable,
             check_same_thread=self._check_same_thread,
-            fd_cache_size=SEQREPO_FD_CACHE_MAXSIZE if SEQREPO_FD_CACHE_MAXSIZE != -1 else fd_cache_size
+            fd_cache_size=(
+                SEQREPO_FD_CACHE_MAXSIZE if SEQREPO_FD_CACHE_MAXSIZE != -1 else fd_cache_size
+            ),
         )
         self.aliases = SeqAliasDB(
             self._db_path,
@@ -133,7 +135,8 @@ def __init__(
 
         if translate_ncbi_namespace is not None:
             _logger.warn(
-                "translate_ncbi_namespace is obsolete; translation is now automatic; this flag will be removed"
+                "translate_ncbi_namespace is obsolete; translation is now automatic; "
+                "this flag will be removed"
             )
 
     def __contains__(self, nsa):
@@ -210,7 +213,7 @@ def store(self, seq, nsaliases):
 
         try:
             seqhash = sha512t24u(seq)
-        except Exception as e:
+        except Exception:
             import pprint
 
             _logger.critical("Exception raised for " + pprint.pformat(nsaliases))
@@ -253,8 +256,8 @@ def store(self, seq, nsaliases):
             n_aliases_added += len(upd_tuples)
         if (
             self._pending_sequences > ct_n_seqs
-            or self._pending_aliases > ct_n_aliases
-            or self._pending_sequences_len > ct_n_residues
+            or self._pending_aliases > ct_n_aliases  # noqa: W503
+            or self._pending_sequences_len > ct_n_residues  # noqa: W503
         ):  # pragma: no cover
             _logger.info(
                 "Hit commit thresholds ({self._pending_sequences} sequences, "
@@ -279,7 +282,8 @@ def translate_alias(
 
         if translate_ncbi_namespace is not None:
             _logger.warn(
-                "translate_ncbi_namespace is obsolete; translation is now automatic; this flag will be removed"
+                "translate_ncbi_namespace is obsolete; translation is now automatic; "
+                "this flag will be removed"
             )
         seq_id = self._get_unique_seqid(alias=alias, namespace=namespace)
         aliases = self.aliases.find_aliases(seq_id=seq_id)
@@ -297,7 +301,8 @@ def translate_identifier(
         """
         if translate_ncbi_namespace is not None:
             _logger.warn(
-                "translate_ncbi_namespace is obsolete; translation is now automatic; this flag will be removed"
+                "translate_ncbi_namespace is obsolete; translation is now automatic; "
+                "this flag will be removed"
             )
 
         namespace, alias = (