Used Ruff to reformat

.github/workflows/lint.yml

@@ -0,0 +1,30 @@
+name: Lint
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Setup Python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Install Ruff
+        run: |
+          python -m pip install --upgrade pip
+          pip install ruff
+
+      - name: Lint with Ruff
+        run: |
+          ruff check . --output-format=github
+
+      - name: Check formatting with Ruff
+        run: |
+          ruff format --check .

CHANGELOG.md

@@ -1,14 +1,17 @@
 # Changelog for ppx
 
 ## [1.4.0]
+### Changed
+- Linting and formatting is now performed with Ruff.
+
 ### Fixed
 - Fixed MassIVE FTP URLs using the MassIVE PROXI API.
 - Fixed PRIDE FTP URLs... again.
 - Updated unit tests with new PRIDE FTP URLs.
 
 ## [1.3.0] - 2022-04-39
 ### Added
-- Support for cloud provider destinations. Thanks @sooheon! 
+- Support for cloud provider destinations. Thanks @sooheon!
 
 ## [1.2.6] - 2022-03-16
 ### Fixed
@@ -47,25 +50,25 @@
 
 ## [1.2.0] - 2021-09-14
 ### Added
-- New `timeout` parameter for most functions and classes. This specifies the 
+- New `timeout` parameter for most functions and classes. This specifies the
   maximum amount of time to wait for a response from the server.
 
 ### Changed
 - The backend for MassIVE now uses the GNPS API to list files and projects,
-  only falling back to scraping the FTP server on failure. This should make 
+  only falling back to scraping the FTP server on failure. This should make
   it much faster. Thanks @mwang87!
 - Files and projects are now returned in sorted order.
 
 ### Fixed
-- Poor connections with PRIDE were leading to a number of occasional errors. 
-  Multiple reconnect attempts are now tried for a wider variety of FTP 
+- Poor connections with PRIDE were leading to a number of occasional errors.
+  Multiple reconnect attempts are now tried for a wider variety of FTP
   operations.
 
 ## [1.1.1] - 2021-07-02
 ### Fixed
 - Downloading files is now more robust. ppx will now retry FTP connections up
   to 10 times if the connection was dropped or refused.
-- Partial downloads are now continued automatically by comparing the local 
+- Partial downloads are now continued automatically by comparing the local
   file size to the remote file size.
 
 ## [1.1.0] - 2021-05-18
@@ -75,26 +78,25 @@
   instead. **Note that this may change the number, identity, and order of the
   file that were previously returned for PRIDE projects!**
 - Small documentation updates.
-  
+
 ### Added
-- Caching of the remote files and directories found for a project. If a 
+- Caching of the remote files and directories found for a project. If a
   project's `fetch` attribute is `False`, then we'll rely on this cached
   data, so long as it is available. Setting `fetch=True` will always refresh
   the data from the repository.
 
-## [1.0.0] - 2021-05-14  
-### Changed  
+## [1.0.0] - 2021-05-14
+### Changed
 - **We did a complete rework of the API!** This will break nearly all previous
   code using ppx, but greatly improves its versatility.
   See the [docs](https://ppx.readthedocs.io) for more details
 - Updated the build to align with
   [PEP517](https://www.python.org/dev/peps/pep-0517/)
-  
+
 ### Added
-- A command line interface for downloading files from PRIDE and MassIVE 
+- A command line interface for downloading files from PRIDE and MassIVE
   projects.
 - Additional unit tests.
 - A ppx logo
 - This changelog.
 - ppx is now available on bioconda!
-

ppx/__init__.py

@@ -1,4 +1,5 @@
 """See the README for detailed documentation and examples."""
+
 try:
     from importlib.metadata import PackageNotFoundError, version
 

ppx/config.py

@@ -1,4 +1,5 @@
 """This module contains the configuration details for ppx"""
+
 import logging
 import os
 from pathlib import Path
@@ -43,7 +44,8 @@ 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

ppx/factory.py

@@ -2,6 +2,7 @@
 
 This is the foundation of the ppx package.
 """
+
 import logging
 import re
 from urllib.parse import urlparse
@@ -78,11 +79,11 @@ def id(self):
 
     def find(self):
         """Find the dataset at the partner repository"""
-        kwargs = dict(
-            local=self._local,
-            fetch=self._fetch,
-            timeout=self._timeout,
-        )
+        kwargs = {
+            "local": self._local,
+            "fetch": self._fetch,
+            "timeout": self._timeout,
+        }
 
         if self._repo == "PRIDE":
             return PrideProject(self._repo_id, **kwargs)
@@ -164,7 +165,7 @@ def find_project(identifier, local=None, repo=None, fetch=False, timeout=10.0):
         repo = str(repo).lower()
 
     # User-specified:
-    kwargs = dict(local=local, fetch=fetch, timeout=timeout)
+    kwargs = {"local": local, "fetch": fetch, "timeout": timeout}
     if repo == "pride":
         return PrideProject(identifier, **kwargs)
 

ppx/ftp.py

@@ -1,4 +1,5 @@
 """General utilities for working with the repository FTP sites."""
+
 import logging
 import re
 import socket

ppx/massive.py

@@ -1,4 +1,5 @@
 """MassIVE datasets."""
+
 import logging
 import re
 import socket
@@ -50,12 +51,12 @@ class MassiveProject(BaseProject):
     def __init__(self, msv_id, local=None, fetch=False, timeout=10.0):
         """Instantiate a MSVDataset object"""
         super().__init__(msv_id, local, fetch, timeout)
-        self._params = dict(
-            _stream="on",
-            _sort="filepath",
-            dataset__exact=self.id,
-            _size="max",
-        )
+        self._params = {
+            "_stream": "on",
+            "_sort": "filepath",
+            "dataset__exact": self.id,
+            "_size": "max",
+        }
 
     def _validate_id(self, identifier):
         """Validate a MassIVE identifier.
@@ -143,7 +144,9 @@ def remote_files(self, glob=None):
         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,
@@ -211,7 +214,7 @@ def list_projects(timeout=10.0):
 
     """
     url = "https://gnps-datasetcache.ucsd.edu/datasette/database.csv"
-    params = dict(sql="select distinct dataset from filename", _size="max")
+    params = {"sql": "select distinct dataset from filename", "_size": "max"}
     try:
         res = requests.get(url, params, timeout=timeout).text.splitlines()[1:]
         res.sort()

ppx/ppx.py

@@ -1,4 +1,5 @@
 """The command line entry point for ppx"""
+
 import logging
 import sys
 from argparse import ArgumentParser
@@ -11,17 +12,20 @@
 
 def get_parser():
     """Parse the command line arguments"""
-    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."""
+    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."""
 
     epilog = "More documentation and examples at: https://ppx.readthedocs.io"
     parser = ArgumentParser(description=desc, epilog=epilog)
 
     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(
@@ -79,7 +83,9 @@ 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()
@@ -95,16 +101,21 @@ def main():
             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:

ppx/pride.py

@@ -1,4 +1,5 @@
 """A class for PRIDE datasets"""
+
 import json
 import re
 

ppx/project.py

@@ -1,4 +1,5 @@
 """A base dataset class"""
+
 from abc import ABC, abstractmethod
 from pathlib import Path
 
@@ -239,7 +240,9 @@ def download(self, files, force_=False, silent=False):
                 f"{', '.join(missing)}"
             )
 
-        return self._parser.download(files, self.local, force_=force_, silent=silent)
+        return self._parser.download(
+            files, self.local, force_=force_, silent=silent
+        )
 
 
 def cache(files, cache_file, fetch):

setup.py

@@ -1,4 +1,5 @@
 """Setup ppx"""
+
 import setuptools
 
 setuptools.setup()

tests/conftest.py

@@ -7,6 +7,7 @@
 - A mock FTP server response from PRIDE
 - A mock FTP server response from MassIVE
 """
+
 import ftplib
 import json
 import socket

tests/system_tests/test_cli.py

@@ -1,4 +1,5 @@
 """Test the command line interface"""
+
 import subprocess
 
 PXID = "PXD000001"

tests/unit_tests/test_cloud.py

@@ -1,4 +1,5 @@
 """Test using cloud locations"""
+
 from cloudpathlib import CloudPath
 
 import ppx

tests/unit_tests/test_config.py

@@ -1,4 +1,5 @@
 """Test the configuration"""
+
 from pathlib import Path
 
 import pytest

tests/unit_tests/test_download.py

@@ -2,6 +2,7 @@
 
 These tests are in a separate file because they all require internet access.
 """
+
 from ftplib import FTP, error_temp
 
 import pytest

tests/unit_tests/test_find_project.py

@@ -1,4 +1,5 @@
 """Test finding projects"""
+
 import pytest
 from requests.exceptions import ConnectTimeout, ReadTimeout
 

tests/unit_tests/test_list_projects.py

@@ -1,4 +1,5 @@
 """Test that the list_projects() functions work"""
+
 import pytest
 import requests
 

tests/unit_tests/test_massive.py

@@ -1,4 +1,5 @@
 """Test MassIVE functionality w/o internet access"""
+
 import shutil
 from pathlib import Path