Merge pull request #180 from executablebooks/prek

Update pre commit config and moved to an active mirror for prettier

Author: nabobalis

.github/workflows/tests.yaml

@@ -25,22 +25,19 @@ jobs:
 
     steps:
       - uses: actions/checkout@v7
-      - uses: actions/setup-python@v7
-        with:
-          python-version: "3.14"
 
-      # ref: https://github.com/pre-commit/action
-      - uses: pre-commit/action@v3.0.1
+      # ref: https://github.com/j178/prek-action
+      - uses: j178/prek-action@4e14d07f9231acabce116ccfca13b13dd9755ece # v3.0.0
       - name: Help message if pre-commit fail
         if: ${{ failure() }}
         run: |
-          echo "You can install pre-commit hooks to automatically run formatting"
-          echo "on each commit with:"
-          echo "    pre-commit install"
+          echo "You can install pre-commit hooks (with prek or pre-commit) to"
+          echo "automatically run formatting on each commit with:"
+          echo "    prek install"
           echo "or you can run by hand on staged files with"
-          echo "    pre-commit run"
+          echo "    prek run"
           echo "or after-the-fact on already committed files with"
-          echo "    pre-commit run --all-files"
+          echo "    prek run --all-files"
 
   tests:
     runs-on: ubuntu-24.04

.pre-commit-config.yaml

@@ -11,22 +11,22 @@
 repos:
   # Autoformat: Python code
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: f0fe93c067104b76ffb58852abe79673a8429bd1 # frozen: v0.11.8
+    rev: v0.16.7
     hooks:
-      - id: ruff
+      - id: ruff-check
         args: ["--fix", "--show-fixes", "--exit-non-zero-on-fix"]
       - id: ruff-format
 
   # Autoformat: markdown, yaml
-  - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: 787fb9f542b140ba0b2aced38e6a3e68021647a3 # frozen: v3.5.3
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: v3.9.6
     hooks:
       - id: prettier
         exclude: tests/.*
 
   # Misc...
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: 3e8a8703264a2f4a69428a0aa4dcb512790b2c8c # v6.0.0
+    rev: v6.0.0 # v6.0.0
     # ref: https://github.com/pre-commit/pre-commit-hooks#hooks-available
     hooks:
       # Sanity checks

docs/example_cache.ipynb

@@ -18,8 +18,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from github_activity.cache import get_cache_stats, load_from_cache\n",
     "from github_activity.github_activity import get_activity\n",
-    "from github_activity.cache import load_from_cache, get_cache_stats\n",
     "\n",
     "activity = get_activity(\"jupyter/repo2docker\", \"2019\", cache=True)"
    ]

docs/use.md

@@ -266,7 +266,7 @@ df = get_activity(
     until="2023-12-31",
     auth="your-github-token",
     kind=None,
-    cache=None
+    cache=None,
 )
 ```
 
@@ -277,5 +277,5 @@ There are some helper functions for this. For example, to extract nested comment
 from github_activity import get_activity, extract_comments
 
 df = get_activity(...)
-comments_df = extract_comments(df['comments'])
+comments_df = extract_comments(df["comments"])
 ```

github_activity/__init__.py

@@ -1,4 +1,4 @@
 __version__ = "1.1.7"
-__all__ = ["get_activity", "generate_activity_md"]
+__all__ = ["generate_activity_md", "get_activity"]
 
-from .github_activity import get_activity, generate_activity_md
+from .github_activity import generate_activity_md, get_activity

github_activity/cache.py

@@ -19,7 +19,7 @@ def _cache_data(query_data, path_cache):
         path_repo_cache.mkdir(parents=True, exist_ok=True)
 
         # First pull issues
-        def _categorize_item(item):
+        def _categorize_item(item, repo=repo):
             if f"{repo}/issues" in item:
                 out = "issue"
             else:

github_activity/cli.py

@@ -2,14 +2,14 @@
 import json
 import os
 import sys
-from subprocess import PIPE
-from subprocess import run
+from subprocess import PIPE, run
 
-from .git import _git_installed_check
-from .git import _git_toplevel_path
-from .github_activity import _parse_target
-from .github_activity import generate_activity_md
-from .github_activity import generate_all_activity_md
+from .git import _git_installed_check, _git_toplevel_path
+from .github_activity import (
+    _parse_target,
+    generate_activity_md,
+    generate_all_activity_md,
+)
 
 DESCRIPTION = "Generate a markdown changelog of GitHub activity within a date window."
 
@@ -191,7 +191,7 @@ def main():
     if not args.target:
         err = "Could not automatically detect remote, and none was given."
         try:
-            out = run("git remote -v".split(), stdout=PIPE)
+            out = run(["git", "remote", "-v"], stdout=PIPE, check=False)
             remotes = out.stdout.decode().split("\n")
             remotes = [ii for ii in remotes if ii]
             remotes = {
@@ -214,16 +214,16 @@ def main():
         except Exception:
             raise ValueError(err)
 
-    common_kwargs = dict(
-        kind=args.kind,
-        auth=args.auth,
-        tags=tags,
-        include_issues=bool(args.include_issues),
-        include_opened=bool(args.include_opened),
-        strip_brackets=bool(args.strip_brackets),
-        branch=args.branch,
-        ignored_contributors=args.ignore_contributor,
-    )
+    common_kwargs = {
+        "kind": args.kind,
+        "auth": args.auth,
+        "tags": tags,
+        "include_issues": bool(args.include_issues),
+        "include_opened": bool(args.include_opened),
+        "strip_brackets": bool(args.strip_brackets),
+        "branch": args.branch,
+        "ignored_contributors": args.ignore_contributor,
+    }
 
     # Wrap in a try/except so we don't have an ugly stack trace if there's an error
     try:

github_activity/github_activity.py

@@ -10,9 +10,7 @@
 import sys
 from collections import OrderedDict
 from json import loads
-from subprocess import CalledProcessError
-from subprocess import PIPE
-from subprocess import run
+from subprocess import PIPE, CalledProcessError, run
 from tempfile import TemporaryDirectory
 
 import dateutil.parser
@@ -25,7 +23,6 @@
 from .cache import _cache_data
 from .graphql import GitHubGraphQlQuery
 
-
 # The tags and description to use in creating subsets of PRs
 TAGS_METADATA_BASE = OrderedDict(
     [
@@ -175,7 +172,9 @@ def get_activity(
     if auth is None:
         # Attempt to use the gh cli if installed
         try:
-            p = run(["gh", "auth", "token"], text=True, capture_output=True)
+            p = run(
+                ["gh", "auth", "token"], text=True, capture_output=True, check=False
+            )
             auth = p.stdout.strip()
         except CalledProcessError:
             print(
@@ -270,7 +269,7 @@ def generate_all_activity_md(
     include_opened=False,
     strip_brackets=False,
     branch=None,
-    ignored_contributors: list[str] = None,
+    ignored_contributors: list[str] | None = None,
 ):
     """Generate a full markdown changelog of GitHub activity of a repo based on release tags.
 
@@ -316,10 +315,12 @@ def generate_all_activity_md(
     # Get the sha and tag name for each tag in the target repo
     with TemporaryDirectory() as td:
         subprocess.run(
-            shlex.split(f"git clone https://github.com/{target} repo"), cwd=td
+            shlex.split(f"git clone https://github.com/{target} repo"),
+            cwd=td,
+            check=False,
         )
         repo = os.path.join(td, "repo")
-        subprocess.run(shlex.split("git fetch origin --tags"), cwd=repo)
+        subprocess.run(shlex.split("git fetch origin --tags"), cwd=repo, check=False)
 
         cmd = 'git log --tags --simplify-by-decoration --pretty="format:%h | %D"'
         data = (
@@ -402,8 +403,7 @@ def add(self, contributor):
     def __iter__(self):
         if self.author:
             yield self.author
-        for item in sorted(self.other - {self.author}):
-            yield item
+        yield from sorted(self.other - {self.author})
 
 
 def generate_activity_md(
@@ -418,7 +418,7 @@ def generate_activity_md(
     strip_brackets=False,
     heading_level=1,
     branch=None,
-    ignored_contributors: list[str] = None,
+    ignored_contributors: list[str] | None = None,
 ):
     """Generate a markdown changelog of GitHub activity within a date window.
 
@@ -536,12 +536,10 @@ def ignored_user(username):
             return True
 
         # Check against user-specified ignored contributors
-        if ignored_contributors and any(
-            fnmatch.fnmatch(username, user) for user in ignored_contributors
-        ):
-            return True
-
-        return False
+        return bool(
+            ignored_contributors
+            and any(fnmatch.fnmatch(username, user) for user in ignored_contributors)
+        )
 
     def filter_ignored(userlist):
         return {user for user in userlist if not ignored_user(user)}
@@ -617,7 +615,7 @@ def filter_ignored(userlist):
     comment_contributors = comment_contributor_counts[
         comment_contributor_counts >= comment_others_cutoff
     ].index.tolist()
-    all_contributors |= set(c for c in comment_contributors if isinstance(c, str))
+    all_contributors |= {c for c in comment_contributors if isinstance(c, str)}
 
     closed_mask, opened_mask = _activity_window_masks(
         data, data.since_dt_str, data.until_dt_str, data.since_is_git_ref
@@ -646,7 +644,7 @@ def filter_ignored(userlist):
     # Add any contributors to a merged PR to our contributors list
     # Filter out NaN values and non-strings
     pr_contributors = closed_prs["contributors"].explode().unique().tolist()
-    all_contributors |= set(c for c in pr_contributors if isinstance(c, str))
+    all_contributors |= {c for c in pr_contributors if isinstance(c, str)}
 
     # Define categories for a few labels
     if tags is None:
@@ -660,7 +658,7 @@ def filter_ignored(userlist):
     tags_metadata = {key: val for key, val in TAGS_METADATA_BASE.items() if key in tags}
 
     # Initialize our tags with empty metadata
-    for key, vals in tags_metadata.items():
+    for vals in tags_metadata.values():
         vals.update(
             {
                 "mask": None,
@@ -673,14 +671,18 @@ def filter_ignored(userlist):
     # Track which PRs have already been assigned to prevent duplicates
     assigned_prs = set()
 
-    for kind, kindmeta in tags_metadata.items():
+    for kindmeta in tags_metadata.values():
         # First find the PRs based on tag
         mask = closed_prs["labels"].map(
-            lambda a: any(ii == jj for ii in kindmeta["tags"] for jj in a)
+            lambda a, kindmeta=kindmeta: any(
+                ii == jj for ii in kindmeta["tags"] for jj in a
+            )
         )
         # Now find PRs based on prefix
         mask_pre = closed_prs["title"].map(
-            lambda title: any(f"{ipre}:" in title for ipre in kindmeta["pre"])
+            lambda title, kindmeta=kindmeta: any(
+                f"{ipre}:" in title for ipre in kindmeta["pre"]
+            )
         )
         mask = mask | mask_pre
 
@@ -705,39 +707,39 @@ def filter_ignored(userlist):
 
     # Add some optional kinds of PRs / issues
     tags_metadata.update(
-        dict(others={"description": other_description, "md": [], "data": others})
+        {"others": {"description": other_description, "md": [], "data": others}}
     )
     if include_issues:
         tags_metadata.update(
-            dict(
-                closed_issues={
+            {
+                "closed_issues": {
                     "description": "Closed issues",
                     "md": [],
                     "data": closed_issues,
                 }
-            )
+            }
         )
         if include_opened:
             tags_metadata.update(
-                dict(
-                    opened_issues={
+                {
+                    "opened_issues": {
                         "description": "Opened issues",
                         "md": [],
                         "data": opened_issues,
                     }
-                )
+                }
             )
     if include_opened:
         tags_metadata.update(
-            dict(opened_prs={"description": "Opened PRs", "md": [], "data": opened_prs})
+            {"opened_prs": {"description": "Opened PRs", "md": [], "data": opened_prs}}
         )
 
     # Generate the markdown
     prs = tags_metadata
 
     extra_head = "#" * (heading_level - 1)
 
-    for kind, items in prs.items():
+    for items in prs.values():
         n_orgs = len(items["data"]["org"].unique())
         for org, idata in items["data"].groupby("org"):
             if n_orgs > 1:
@@ -794,7 +796,7 @@ def filter_ignored(userlist):
         "",
         f"([full changelog]({changelog_url}))",
     ]
-    for kind, info in prs.items():
+    for info in prs.values():
         if len(info["md"]) > 0:
             md += [""]
             md.append(f"{extra_head}## {info['description']}")
@@ -943,9 +945,7 @@ def _get_datetime_and_type(org, repo, datetime_or_git_ref, auth):
             return (dt, False)
         except Exception:
             raise ValueError(
-                "{0} not found as a ref or valid date format".format(
-                    datetime_or_git_ref
-                )
+                f"{datetime_or_git_ref} not found as a ref or valid date format"
             )
 
 
@@ -981,7 +981,7 @@ def _get_latest_release_tag(org, repo):
     ]
     print(f"Auto-detecting latest release tag for: {org}/{repo}", file=sys.stderr)
     print(f"Running command: {' '.join(cmd)}", file=sys.stderr)
-    out = run(cmd, stdout=PIPE)
+    out = run(cmd, stdout=PIPE, check=False)
     try:
         json = out.stdout.decode()
         release_data = loads(json)
@@ -998,6 +998,6 @@ def _get_latest_release_tag(org, repo):
             f"Error getting latest release tag for {org}/{repo}: {e}", file=sys.stderr
         )
         print("Reverting to using latest local git tag...", file=sys.stderr)
-        out = run("git describe --tags".split(), stdout=PIPE)
+        out = run(["git", "describe", "--tags"], stdout=PIPE, check=False)
         tag = out.stdout.decode().rsplit("-", 2)[0]
         return tag