This is an automated email from the ASF dual-hosted git repository.
agrove pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-datafusion-python.git
The following commit(s) were added to refs/heads/main by this push:
new 3711c73 Add Python script for generating changelog (#383)
3711c73 is described below
commit 3711c73f2bb2bf01cd1c6fd50d0264825d2fd821
Author: Andy Grove <[email protected]>
AuthorDate: Fri May 19 08:57:53 2023 -0600
Add Python script for generating changelog (#383)
---
dev/release/README.md | 39 ++++++++-----
dev/release/generate-changelog.md | 114 ++++++++++++++++++++++++++++++++++++++
2 files changed, 138 insertions(+), 15 deletions(-)
diff --git a/dev/release/README.md b/dev/release/README.md
index 1ba44fb..e85b288 100644
--- a/dev/release/README.md
+++ b/dev/release/README.md
@@ -56,28 +56,37 @@ Before creating a new release:
- a PR should be created and merged to update the major version number of the
project
- A new release branch should be created, such as `branch-0.8`
-### Update CHANGELOG.md
+### Change Log
-Define release branch (e.g. `branch-0.8`), base version tag (e.g. `0.7.0`) and
future version tag (e.g. `0.9.0`). Commits
-between the base version tag and the release branch will be used to populate
the changelog content.
+We maintain a `CHANGELOG.md` so our users know what has been changed between
releases.
+
+The changelog is generated using a Python script:
```bash
-# create the changelog
-CHANGELOG_GITHUB_TOKEN=<TOKEN>
./dev/release/update_change_log-datafusion-python.sh main 0.8.0 0.7.0
-# review change log / edit issues and labels if needed, rerun until you are
happy with the result
-git commit -a -m 'Create changelog for release'
+$ GITHUB_TOKEN=<TOKEN> ./dev/release/generate-changelog.py
apache/arrow-datafusion-python 24.0.0 HEAD > dev/changelog/25.0.0.md
+```
+
+This script creates a changelog from GitHub PRs based on the labels associated
with them as well as looking for
+titles starting with `feat:`, `fix:`, or `docs:` . The script will produce
output similar to:
+
```
+Fetching list of commits between 24.0.0 and HEAD
+Fetching pull requests
+Categorizing pull requests
+Generating changelog content
+```
+
+This process is not fully automated, so there are some additional manual steps:
-_If you see the error `"You have exceeded a secondary rate limit"` when
running this script, try reducing the CPU
-allocation to slow the process down and throttle the number of GitHub requests
made per minute, by modifying the
-value of the `--cpus` argument in the `update_change_log.sh` script._
+- Add the ASF header to the generated file
+- Add a link to this changelog from the top-level `/datafusion/CHANGELOG.md`
+- Add the following content (copy from the previous version's changelog and
update as appropriate:
-You can add `invalid` or `development-process` label to exclude items from
-release notes.
+```
+## [24.0.0](https://github.com/apache/arrow-datafusion-python/tree/24.0.0)
(2023-05-06)
-Send a PR to get these changes merged into the release branch (e.g.
`branch-0.8`). If new commits that could change the
-change log content landed in the release branch before you could merge the PR,
you need to rerun the changelog update
-script to regenerate the changelog and update the PR accordingly.
+[Full
Changelog](https://github.com/apache/arrow-datafusion-python/compare/23.0.0...24.0.0)
+```
### Preparing a Release Candidate
diff --git a/dev/release/generate-changelog.md
b/dev/release/generate-changelog.md
new file mode 100644
index 0000000..caa6ae6
--- /dev/null
+++ b/dev/release/generate-changelog.md
@@ -0,0 +1,114 @@
+#!/usr/bin/env python
+
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You 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.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import argparse
+import sys
+from github import Github
+import os
+import re
+
+
+def print_pulls(repo_name, title, pulls):
+if len(pulls) > 0:
+print("**{}:**".format(title))
+print()
+for (pull, commit) in pulls:
+url = "https://github.com/{}/pull/{}".format(repo_name, pull.number)
+print("- {} [#{}]({}) ({})".format(pull.title, pull.number, url,
commit.author.login))
+print()
+
+
+def generate_changelog(repo, repo_name, tag1, tag2):
+
+ # get a list of commits between two tags
+ print(f"Fetching list of commits between {tag1} and {tag2}",
file=sys.stderr)
+ comparison = repo.compare(tag1, tag2)
+
+ # get the pull requests for these commits
+ print("Fetching pull requests", file=sys.stderr)
+ unique_pulls = []
+ all_pulls = []
+ for commit in comparison.commits:
+ pulls = commit.get_pulls()
+ for pull in pulls:
+ # there can be multiple commits per PR if squash merge is not
being used and
+ # in this case we should get all the author names, but for now
just pick one
+ if pull.number not in unique_pulls:
+ unique_pulls.append(pull.number)
+ all_pulls.append((pull, commit))
+
+ # we split the pulls into categories
+ #TODO: make categories configurable
+ breaking = []
+ bugs = []
+ docs = []
+ enhancements = []
+
+ # categorize the pull requests based on GitHub labels
+ print("Categorizing pull requests", file=sys.stderr)
+ for (pull, commit) in all_pulls:
+
+ # see if PR title uses Conventional Commits
+ cc_type = ''
+ cc_scope = ''
+ cc_breaking = ''
+ parts = re.findall(r'^([a-z]+)(\([a-z]+\))?(!)?:', pull.title)
+ if len(parts) == 1:
+ parts_tuple = parts[0]
+ cc_type = parts_tuple[0] # fix, feat, docs, chore
+ cc_scope = parts_tuple[1] # component within project
+ cc_breaking = parts_tuple[2] == '!'
+
+ labels = [label.name for label in pull.labels]
+ #print(pull.number, labels, parts, file=sys.stderr)
+ if 'api change' in labels or cc_breaking:
+ breaking.append((pull, commit))
+ elif 'bug' in labels or cc_type == 'fix':
+ bugs.append((pull, commit))
+ elif 'enhancement' in labels or cc_type == 'feat':
+ enhancements.append((pull, commit))
+ elif 'documentation' in labels or cc_type == 'docs':
+ docs.append((pull, commit))
+
+ # produce the changelog content
+ print("Generating changelog content", file=sys.stderr)
+ print_pulls(repo_name, "Breaking changes", breaking)
+ print_pulls(repo_name, "Implemented enhancements", enhancements)
+ print_pulls(repo_name, "Fixed bugs", bugs)
+ print_pulls(repo_name, "Documentation updates", docs)
+ print_pulls(repo_name, "Merged pull requests", all_pulls)
+
+
+def cli(args=None):
+"""Process command line arguments."""
+if not args:
+args = sys.argv[1:]
+
+ parser = argparse.ArgumentParser()
+ parser.add_argument("project", help="The project name e.g.
apache/arrow-datafusion-python")
+ parser.add_argument("tag1", help="The previous release tag")
+ parser.add_argument("tag2", help="The current release tag")
+ args = parser.parse_args()
+
+ token = os.getenv("GITHUB_TOKEN")
+
+ g = Github(token)
+ repo = g.get_repo(args.project)
+ generate_changelog(repo, args.project, args.tag1, args.tag2)
+
+if __name__ == "__main__":
+cli()
\ No newline at end of file
