Files
pytorch/scripts/release_notes/common.py
Sam Estep 5bcbbf5373 Lint trailing newlines (#54737)
Summary:
*Context:* https://github.com/pytorch/pytorch/issues/53406 added a lint for trailing whitespace at the ends of lines. However, in order to pass FB-internal lints, that PR also had to normalize the trailing newlines in four of the files it touched. This PR adds an OSS lint to normalize trailing newlines.

The changes to the following files (made in 54847d0adb9be71be4979cead3d9d4c02160e4cd) are the only manually-written parts of this PR:

- `.github/workflows/lint.yml`
- `mypy-strict.ini`
- `tools/README.md`
- `tools/test/test_trailing_newlines.py`
- `tools/trailing_newlines.py`

I would have liked to make this just a shell one-liner like the other three similar lints, but nothing I could find quite fit the bill. Specifically, all the answers I tried from the following Stack Overflow questions were far too slow (at least a minute and a half to run on this entire repository):

- [How to detect file ends in newline?](https://stackoverflow.com/q/38746)
- [How do I find files that do not end with a newline/linefeed?](https://stackoverflow.com/q/4631068)
- [How to list all files in the Git index without newline at end of file](https://stackoverflow.com/q/27624800)
- [Linux - check if there is an empty line at the end of a file [duplicate]](https://stackoverflow.com/q/34943632)
- [git ensure newline at end of each file](https://stackoverflow.com/q/57770972)

To avoid giving false positives during the few days after this PR is merged, we should probably only merge it after https://github.com/pytorch/pytorch/issues/54967.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/54737

Test Plan:
Running the shell script from the "Ensure correct trailing newlines" step in the `quick-checks` job of `.github/workflows/lint.yml` should print no output and exit in a fraction of a second with a status of 0. That was not the case prior to this PR, as shown by this failing GHA workflow run on an earlier draft of this PR:

- https://github.com/pytorch/pytorch/runs/2197446987?check_suite_focus=true

In contrast, this run (after correcting the trailing newlines in this PR) succeeded:

- https://github.com/pytorch/pytorch/pull/54737/checks?check_run_id=2197553241

To unit-test `tools/trailing_newlines.py` itself (this is run as part of our "Test tools" GitHub Actions workflow):
```
python tools/test/test_trailing_newlines.py
```

Reviewed By: malfet

Differential Revision: D27409736

Pulled By: samestep

fbshipit-source-id: 46f565227046b39f68349bbd5633105b2d2e9b19
2021-03-30 13:09:52 -07:00

196 lines
5.0 KiB
Python

from collections import namedtuple
from os.path import expanduser
import locale
import subprocess
import re
import requests
import os
import json
categories = [
'Uncategorized',
'distributed',
'mobile',
'jit',
'visualization',
'onnx',
'caffe2',
'quantization',
'amd',
'benchmark',
'profiler',
'dispatcher',
'releng',
'fx',
'code_coverage',
'vulkan',
'skip',
'cpp_frontend',
'python_frontend',
'complex_frontend',
'vmap_frontend',
'autograd_frontend',
'build_frontend',
'memory_format_frontend',
'foreach_frontend',
]
topics = [
'bc_breaking',
'deprecations',
'new_features',
'improvements',
'bug_fixes',
'performance',
'docs',
'devs',
'Untopiced',
]
Features = namedtuple('Features', [
'title',
'body',
'pr_number',
'files_changed',
'labels',
])
def dict_to_features(dct):
return Features(
title=dct['title'],
body=dct['body'],
pr_number=dct['pr_number'],
files_changed=dct['files_changed'],
labels=dct['labels'])
def features_to_dict(features):
return dict(features._asdict())
def run(command):
"""Returns (return-code, stdout, stderr)"""
p = subprocess.Popen(command, stdout=subprocess.PIPE,
stderr=subprocess.PIPE, shell=True)
output, err = p.communicate()
rc = p.returncode
enc = locale.getpreferredencoding()
output = output.decode(enc)
err = err.decode(enc)
return rc, output.strip(), err.strip()
def commit_body(commit_hash):
cmd = f'git log -n 1 --pretty=format:%b {commit_hash}'
ret, out, err = run(cmd)
return out if ret == 0 else None
def commit_title(commit_hash):
cmd = f'git log -n 1 --pretty=format:%s {commit_hash}'
ret, out, err = run(cmd)
return out if ret == 0 else None
def commit_files_changed(commit_hash):
cmd = f'git diff-tree --no-commit-id --name-only -r {commit_hash}'
ret, out, err = run(cmd)
return out.split('\n') if ret == 0 else None
def parse_pr_number(body, commit_hash, title):
regex = r'Pull Request resolved: https://github.com/pytorch/pytorch/pull/([0-9]+)'
matches = re.findall(regex, body)
if len(matches) == 0:
if 'revert' not in title.lower() and 'updating submodules' not in title.lower():
print(f'[{commit_hash}: {title}] Could not parse PR number, ignoring PR')
return None
if len(matches) > 1:
print(f'[{commit_hash}: {title}] Got two PR numbers, using the first one')
return matches[0]
return matches[0]
def get_ghstack_token():
pattern = 'github_oauth = (.*)'
with open(expanduser('~/.ghstackrc'), 'r+') as f:
config = f.read()
matches = re.findall(pattern, config)
if len(matches) == 0:
raise RuntimeError("Can't find a github oauth token")
return matches[0]
token = get_ghstack_token()
headers = {"Authorization": f"token {token}"}
def run_query(query):
request = requests.post('https://api.github.com/graphql', json={'query': query}, headers=headers)
if request.status_code == 200:
return request.json()
else:
raise Exception("Query failed to run by returning code of {}. {}".format(request.status_code, query))
def gh_labels(pr_number):
query = f"""
{{
repository(owner: "pytorch", name: "pytorch") {{
pullRequest(number: {pr_number}) {{
labels(first: 10) {{
edges {{
node {{
name
}}
}}
}}
}}
}}
}}
"""
query = run_query(query)
edges = query['data']['repository']['pullRequest']['labels']['edges']
return [edge['node']['name'] for edge in edges]
def get_features(commit_hash, return_dict=False):
title, body, files_changed = (
commit_title(commit_hash),
commit_body(commit_hash),
commit_files_changed(commit_hash))
pr_number = parse_pr_number(body, commit_hash, title)
labels = []
if pr_number is not None:
labels = gh_labels(pr_number)
result = Features(title, body, pr_number, files_changed, labels)
if return_dict:
return features_to_dict(result)
return result
class CommitDataCache:
def __init__(self, path='results/data.json'):
self.path = path
self.data = {}
if os.path.exists(path):
self.data = self.read_from_disk()
def get(self, commit):
if commit not in self.data.keys():
# Fetch and cache the data
self.data[commit] = get_features(commit)
self.write_to_disk()
return self.data[commit]
def read_from_disk(self):
with open(self.path, 'r') as f:
data = json.load(f)
data = {commit: dict_to_features(dct)
for commit, dct in data.items()}
return data
def write_to_disk(self):
data = {commit: features._asdict() for commit, features in self.data.items()}
with open(self.path, 'w') as f:
json.dump(data, f)