Fix most linting errors

docs/conf.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 #
 # Configuration file for the Sphinx documentation builder.
 #
@@ -13,8 +12,8 @@
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
 import os
-import sys
 import subprocess
+import sys
 
 sys.path.insert(0, os.path.abspath(".."))
 

ppx/__init__.py

@@ -1,23 +1,22 @@
 """See the README for detailed documentation and examples."""
 try:
-    from importlib.metadata import version, PackageNotFoundError
+    from importlib.metadata import PackageNotFoundError, version
 
     try:
         __version__ = version(__name__)
     except PackageNotFoundError:
         pass
 
 except ImportError:
-    from pkg_resources import get_distribution, DistributionNotFound
+    from pkg_resources import DistributionNotFound, get_distribution
 
     try:
         __version__ = get_distribution(__name__).version
     except DistributionNotFound:
         pass
 
-from . import pride
-from . import massive
+from . import massive, pride
+from .config import get_data_dir, set_data_dir
 from .factory import find_project
-from .pride import PrideProject
 from .massive import MassiveProject
-from .config import get_data_dir, set_data_dir
+from .pride import PrideProject

ppx/config.py

@@ -1,6 +1,6 @@
 """This module contains the configuration details for ppx"""
-import os
 import logging
+import os
 from pathlib import Path
 
 from cloudpathlib import AnyPath
@@ -14,6 +14,7 @@ class PPXConfig:
     Attributes
     ----------
     path : pathlib.Path object
+
     """
 
     def __init__(self):
@@ -42,8 +43,7 @@ def path(self, path):
             path = self._resolve_path(path)
             if not path.exists():
                 raise FileNotFoundError(
-                    f"The specified directory or bucket ({path}) "
-                    "does not exist."
+                    f"The specified directory or bucket ({path}) " "does not exist."
                 )
 
         self._path = path
@@ -61,6 +61,7 @@ def _resolve_path(path):
         -------
         Path or CloudPath
             The resolved path.
+
         """
         path = AnyPath(path)
         try:
@@ -83,6 +84,7 @@ def set_data_dir(path=None):
     ----------
     path : str or pathlib.Path object, optional
         The path for ppx to use as its data directory.
+
     """
     config.path = path
 

ppx/factory.py

@@ -1,15 +1,15 @@
+"""The PXDataset class and its associated methods.
+
+This is the foundation of the ppx package.
 """
-This module contains the PXDataset class and its associated methods,
-which are the foundation of the ppx package.
-"""
-import re
 import logging
+import re
 from urllib.parse import urlparse
 
 import requests
 
-from .pride import PrideProject
 from .massive import MassiveProject
+from .pride import PrideProject
 
 LOGGER = logging.getLogger(__name__)
 
@@ -29,6 +29,7 @@ class PXDFactory:
         Should ppx check the remote repository for updated metadata?
     timeout : float, optional
         The maximum amount of time to wait for a server response.
+
     """
 
     rest = "http://proteomecentral.proteomexchange.org/cgi/GetDataset"
@@ -156,6 +157,7 @@ def find_project(identifier, local=None, repo=None, fetch=False, timeout=10.0):
     -------
     :py:class:`~ppx.PrideProject` or :py:class:`~ppx.MassiveProject`
         An object to interact with the project data in the repository.
+
     """
     identifier = str(identifier).upper()
     if repo is not None:

ppx/ftp.py

@@ -2,7 +2,7 @@
 import logging
 import re
 import socket
-from ftplib import FTP, error_temp, error_perm
+from ftplib import FTP, error_perm, error_temp
 from functools import partial
 
 from cloudpathlib import CloudPath
@@ -51,6 +51,7 @@ class FTPParser:
         The maximum number of reconnects to attempt during downloads.
     timeout : float, optional
         The maximum amount of time to wait for a response from the server.
+
     """
 
     def __init__(self, url, max_depth=4, max_reconnects=10, timeout=10.0):
@@ -97,9 +98,9 @@ def _with_reconnects(self, func, *args, **kwargs):
                 return func(*args, **kwargs)
 
             except (
+                TimeoutError,
                 ConnectionRefusedError,
                 ConnectionResetError,
-                socket.timeout,
                 socket.gaierror,
                 socket.herror,
                 error_temp,
@@ -131,6 +132,7 @@ def _download_file(self, remote_file, out_file, force_, silent):
             Disable the progress bar?
         force_ : bool
             Force the file to be redownloaded, even if it exists.
+
         """
         self.connect()
         size = self.connection.size(remote_file)
@@ -182,6 +184,7 @@ def open_(out_file, force_):
         -------
         file object
             The opened for the file.
+
         """
         open_kwargs = {"mode": "wb+" if force_ else "ab+"}
         if isinstance(out_file, CloudPath):
@@ -200,6 +203,7 @@ def _transfer_file(self, fname, fhandle, pbar):
             The opened file object where the data will be written.
         pbar : tqdm.tqdm
             The tqdm progress bar to update.
+
         """
         write = partial(write_file, fhandle=fhandle, pbar=pbar)
         self.connection.retrbinary(f"RETR {fname}", write, rest=fhandle.tell())
@@ -243,6 +247,7 @@ def download(self, files, dest_dir, force_=False, silent=False):
             Force the files to be redownloaded, even they already exist.
         silent : bool
             Disable the progress bar?
+
         """
         files = listify(files)
         out_files = []
@@ -302,13 +307,14 @@ def parse_response(conn):
 
     Parameters
     ----------
-    url : str
-        The url of the FTP server.
+    conn : Connection
+        The FTP server connection
 
     Returns
     -------
     files : list of str
     directories : list of str
+
     """
     lines = []
     conn.dir(lines.append)
@@ -341,6 +347,7 @@ def parse_line(line):
         The file or directory name.
     date : date
         The modification date.
+
     """
     match = UNIX.fullmatch(line)
     is_dir = match[1] == "d" or match[1] == "l"

ppx/massive.py

@@ -1,8 +1,8 @@
 """MassIVE datasets."""
+import logging
 import re
 import socket
-import logging
-import xml.etree.ElementTree as ET
+import xml.etree.ElementTree as ET  # noqa: N817
 from pathlib import Path
 
 import requests
@@ -41,6 +41,7 @@ class MassiveProject(BaseProject):
     metadata : dict
     fetch : bool
     timeout : float
+
     """
 
     _api = "https://gnps-datasetcache.ucsd.edu/datasette/database/filename.csv"
@@ -68,6 +69,7 @@ def _validate_id(self, identifier):
         -------
         str
             The validated identifier.
+
         """
         identifier = str(identifier).upper()
         if not re.match("(MSV|RMSV)[0-9]{9}", identifier):
@@ -82,8 +84,6 @@ def url(self):
             return self._url
 
         res = requests.get(self._proxy_api + self.id, timeout=self.timeout)
-        print(res)
-        print(res.json())
         for link in res.json()["datasetLink"]:
             if link["accession"] == "MS:1002852":
                 self._url = link["value"]
@@ -138,18 +138,17 @@ def remote_files(self, glob=None):
         -------
         list of str
             The remote files available for this project.
+
         """
         if self.fetch or self._remote_files is None:
             try:
                 info = self.file_info().splitlines()[1:]
-                self._remote_files = [
-                    r.split(",")[0].split("/", 1)[1] for r in info
-                ]
+                self._remote_files = [r.split(",")[0].split("/", 1)[1] for r in info]
                 assert self._remote_files
             except (
+                TimeoutError,
                 ConnectionRefusedError,
                 ConnectionResetError,
-                socket.timeout,
                 socket.gaierror,
                 socket.herror,
                 EOFError,
@@ -173,6 +172,7 @@ def file_info(self):
         -------
         str
             Information about the files in a CSV format.
+
         """
         file_info_path = self.local / ".file_info.csv"
         if file_info_path.exists() and not self.fetch:
@@ -208,6 +208,7 @@ def list_projects(timeout=10.0):
     -------
     list of str
         A list of MassIVE identifiers.
+
     """
     url = "https://gnps-datasetcache.ucsd.edu/datasette/database.csv"
     params = dict(sql="select distinct dataset from filename", _size="max")
@@ -217,9 +218,9 @@ def list_projects(timeout=10.0):
         return res
 
     except (
+        TimeoutError,
         ConnectionRefusedError,
         ConnectionResetError,
-        socket.timeout,
         socket.gaierror,
         socket.herror,
         EOFError,

ppx/ppx.py

@@ -1,18 +1,17 @@
 """The command line entry point for ppx"""
-import sys
 import logging
-from pathlib import Path
+import sys
 from argparse import ArgumentParser
+from pathlib import Path
 
-from . import __version__
-from . import find_project
+from . import __version__, find_project
 
 LOGGER = logging.getLogger(__name__)
 
 
 def get_parser():
     """Parse the command line arguments"""
-    desc = f"""Use this command line utility to download files from the PRIDE and MassIVE
+    desc = """Use this command line utility to download files from the PRIDE and MassIVE
     proteomics repositories. The paths to the downloaded files are written to
     stdout."""
 
@@ -22,10 +21,7 @@ def get_parser():
     parser.add_argument(
         "identifier",
         type=str,
-        help=(
-            "The ProteomeXchange, PRIDE, or MassIVE identifier for the "
-            "project."
-        ),
+        help=("The ProteomeXchange, PRIDE, or MassIVE identifier for the " "project."),
     )
 
     parser.add_argument(
@@ -83,9 +79,7 @@ def get_parser():
 
 def main():
     """Run ppx"""
-    logging.basicConfig(
-        level=logging.INFO, format="[%(levelname)s]: %(message)s"
-    )
+    logging.basicConfig(level=logging.INFO, format="[%(levelname)s]: %(message)s")
 
     parser = get_parser()
     args = parser.parse_args()
@@ -96,26 +90,21 @@ def main():
         matches = set()
         passed = []
         for pat in args.files:
-            pat_match = set(f for f in remote_files if Path(f).match(pat))
+            pat_match = {f for f in remote_files if Path(f).match(pat)}
             passed.append(bool(pat_match))
             matches.update(pat_match)
 
         if not all(passed):
-            failed = "  \n".join(
-                [f for f, p in zip(args.files, passed) if not p]
-            )
+            failed = "  \n".join([f for f, p in zip(args.files, passed) if not p])
 
             raise FileNotFoundError(
-                "Unable to find one or more of the files or patterns:"
-                f"\n  {failed}"
+                "Unable to find one or more of the files or patterns:" f"\n  {failed}"
             )
 
     else:
         matches = remote_files
 
-    LOGGER.info(
-        "Downloading %i files from %s...", len(matches), args.identifier
-    )
+    LOGGER.info("Downloading %i files from %s...", len(matches), args.identifier)
     downloaded = proj.download(matches)
 
     for local_file in downloaded: