-
Notifications
You must be signed in to change notification settings - Fork 3.4k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[release] Add script to gather PRs for a release (#11987)
Co-authored-by: driazati <driazati@users.noreply.github.com>
- Loading branch information
Showing
6 changed files
with
509 additions
and
7 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| *.md | ||
| !README.md | ||
| *.csv | ||
| *.pkl | ||
|
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,43 @@ | ||
| <!--- 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. --> | ||
|
|
||
| These scripts can be helpful when creating release notes. | ||
|
|
||
| ```bash | ||
| # example: create a csv file of all PRs since the v0.8 and v0.9.0 releases | ||
| # the result will be in 2 CSV files based on the --threshold arg (small PRs vs large PRs) | ||
| export GITHUB_TOKEN=<github oauth token> | ||
| python release/gather_prs.py --from-commit $(git rev-parse v0.9.0) --to-commit $(git merge-base origin/main v0.8.0) | ||
| ``` | ||
|
|
||
| You can then import this CSV into a collaborative spreadsheet editor to distribute the work of categorizing PRs for the notes. Once done, you can download the resulting CSV and convert it to readable release notes. | ||
|
|
||
| ```bash | ||
| # example: use a csv of cateogrized PRs to create a markdown file | ||
| python make_notes.py --notes-csv categorized_prs.csv > out.md | ||
| ``` | ||
|
|
||
| You can also create a list of RFCs | ||
|
|
||
| ```bash | ||
| git clone https://github.com/apache/tvm-rfcs.git | ||
|
|
||
| # example: list RFCs since a specific commit in the tvm-rfcs repo | ||
| python list_rfcs.py --since-commit <hash> --rfcs-repo ./tvm-rfcs > rfc.md | ||
| ``` | ||
|
|
||
| Finally, combine `rfc.md` and `out.md` along with some prose to create the final release notes. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,216 @@ | ||
| #!/usr/bin/env python3 | ||
| # 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 os | ||
| import pickle | ||
| from pathlib import Path | ||
| import csv | ||
| import sys | ||
| from typing import Callable, Dict, List, Any | ||
|
|
||
| REPO_ROOT = Path(__file__).resolve().parent.parent.parent.parent | ||
| sys.path.append(str(REPO_ROOT / "tests" / "scripts")) | ||
|
|
||
| from git_utils import git, GitHubRepo | ||
| from github_tag_teams import tags_from_title | ||
|
|
||
| GITHUB_TOKEN = os.environ["GITHUB_TOKEN"] | ||
|
|
||
|
|
||
| PRS_QUERY = """ | ||
| query ($owner: String!, $name: String!, $after: String, $pageSize: Int!) { | ||
| repository(owner: $owner, name: $name) { | ||
| defaultBranchRef { | ||
| name | ||
| target { | ||
| ... on Commit { | ||
| oid | ||
| history(after: $after, first: $pageSize) { | ||
| pageInfo { | ||
| hasNextPage | ||
| endCursor | ||
| } | ||
| nodes { | ||
| oid | ||
| committedDate | ||
| associatedPullRequests(first: 1) { | ||
| nodes { | ||
| number | ||
| additions | ||
| changedFiles | ||
| deletions | ||
| author { | ||
| login | ||
| } | ||
| title | ||
| body | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| """ | ||
|
|
||
|
|
||
| def append_and_save(items, file): | ||
| if not file.exists(): | ||
| data = [] | ||
| else: | ||
| with open(file, "rb") as f: | ||
| data = pickle.load(f) | ||
|
|
||
| data += items | ||
| with open(file, "wb") as f: | ||
| pickle.dump(data, f) | ||
|
|
||
|
|
||
| def fetch_pr_data(args, cache): | ||
| github = GitHubRepo(user=user, repo=repo, token=GITHUB_TOKEN) | ||
|
|
||
| if args.from_commit is None or args.to_commit is None: | ||
| print("--from-commit and --to-commit must be specified if --skip-query is not used") | ||
| exit(1) | ||
|
|
||
| i = 0 | ||
| page_size = 80 | ||
| cursor = f"{args.from_commit} {i}" | ||
|
|
||
| while True: | ||
| r = github.graphql( | ||
| query=PRS_QUERY, | ||
| variables={ | ||
| "owner": user, | ||
| "name": repo, | ||
| "after": cursor, | ||
| "pageSize": page_size, | ||
| }, | ||
| ) | ||
| data = r["data"]["repository"]["defaultBranchRef"]["target"]["history"] | ||
| if not data["pageInfo"]["hasNextPage"]: | ||
| break | ||
| cursor = data["pageInfo"]["endCursor"] | ||
| results = data["nodes"] | ||
|
|
||
| to_add = [] | ||
| stop = False | ||
| for r in results: | ||
| if r["oid"] == args.to_commit: | ||
| print(f"Found {r['oid']}, stopping") | ||
| stop = True | ||
| break | ||
| else: | ||
| to_add.append(r) | ||
|
|
||
| oids = [r["oid"] for r in to_add] | ||
| print(oids) | ||
| append_and_save(to_add, cache) | ||
| if stop: | ||
| break | ||
| print(i) | ||
| i += page_size | ||
|
|
||
|
|
||
| def write_csv( | ||
| filename: str, data: List[Dict[str, Any]], filter: Callable[[Dict[str, Any]], bool] | ||
| ) -> None: | ||
| with open(filename, "w", newline="") as csvfile: | ||
| writer = csv.writer(csvfile, quotechar='"') | ||
| writer.writerow( | ||
| ( | ||
| "category", | ||
| "description", | ||
| "date", | ||
| "number", | ||
| "author", | ||
| "tags", | ||
| "title", | ||
| "additions", | ||
| "deletions", | ||
| "changed files", | ||
| ) | ||
| ) | ||
| for item in data: | ||
| pr = item["associatedPullRequests"]["nodes"][0] | ||
| if not filter(pr): | ||
| continue | ||
| tags = tags_from_title(pr["title"]) | ||
| actual_tags = [] | ||
| for t in tags: | ||
| items = [x.strip() for x in t.split(",")] | ||
| actual_tags += items | ||
| tags = actual_tags | ||
| tags = [t.lower() for t in tags] | ||
| category = "" | ||
| if len(tags) == 1: | ||
| category = tags[0] | ||
| writer.writerow( | ||
| ( | ||
| category, | ||
| "", | ||
| item["committedDate"], | ||
| f'https://github.com/apache/tvm/pull/{pr["number"]}', | ||
| pr["author"]["login"], | ||
| ", ".join(tags), | ||
| pr["title"], | ||
| pr["additions"], | ||
| pr["deletions"], | ||
| pr["changedFiles"], | ||
| ) | ||
| ) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| help = "List out commits with attached PRs since a certain commit" | ||
| parser = argparse.ArgumentParser(description=help) | ||
| parser.add_argument("--from-commit", help="commit to start checking PRs from") | ||
| parser.add_argument("--to-commit", help="commit to stop checking PRs from") | ||
| parser.add_argument( | ||
| "--threshold", default=150, help="sum of additions + deletions to consider large" | ||
| ) | ||
| parser.add_argument( | ||
| "--skip-query", action="store_true", help="don't query GitHub and instead use cache file" | ||
| ) | ||
| args = parser.parse_args() | ||
| user = "apache" | ||
| repo = "tvm" | ||
| threshold = int(args.threshold) | ||
|
|
||
| cache = Path("out.pkl") | ||
| if not args.skip_query: | ||
| fetch_pr_data(args, cache) | ||
|
|
||
| with open(cache, "rb") as f: | ||
| data = pickle.load(f) | ||
|
|
||
| print(f"Found {len(data)} PRs") | ||
|
|
||
| write_csv( | ||
| filename="out-large.csv", | ||
| data=data, | ||
| filter=lambda pr: pr["additions"] + pr["deletions"] > threshold, | ||
| ) | ||
| write_csv( | ||
| filename="out-small.csv", | ||
| data=data, | ||
| filter=lambda pr: pr["additions"] + pr["deletions"] <= threshold, | ||
| ) |
Oops, something went wrong.