contrib/gcc-changelog: Check that PR in subject is in changelog

This patch checks that a '[PRnnnn]' and '(PRnnnn)' also appears as PR in the
changelog part of the commit message.  And it does likewise for 'PR comp/nnnn'
except that then also the component name is checked.  (Note that the reverse
is permitted, i.e. PR(s) only appearing in the changelog.)
To avoid false positives, PR numbers in the subject line are ignored,
if 'revert' appears.
Additionally, reject commits with a nonempty second line.

contrib/ChangeLog:

	* gcc-changelog/git_commit.py (pr_regex): Add ?P<pr> for group('pr').
	(subject_pr_regex, subject_pr2_regex): New.
	(GitInfo.__init__, GitCommit.parse_changelog): Check subject PRs.
	* gcc-changelog/git_email.py (SUBJECT_PREFIX, subject_patch_regex): New.
	(GitEmail.__init__): Parse 'Subject:' and pass it to GitInfo.
	* gcc-changelog/test_email.py (test_pr_only_in_subject,
	test_wrong_pr_comp_in_subject, test_copyright_years): New.
	* gcc-changelog/test_patches.txt (0030-PR-c-92746, pr-check1.patch):
	Update to avoid triggering the new check.
	(0001-rs6000-Support-doubleword, pr-wrong-comp.patch,
	copyright-years.patch): New.
This commit is contained in:
Tobias Burnus 2021-06-13 07:46:54 +02:00
parent 8b8c391279
commit d554f43c98
4 changed files with 120 additions and 5 deletions

View File

@ -156,7 +156,9 @@ author_line_regex = \
re.compile(r'^(?P<datetime>\d{4}-\d{2}-\d{2})\ {2}(?P<name>.* <.*>)')
additional_author_regex = re.compile(r'^\t(?P<spaces>\ *)?(?P<name>.* <.*>)')
changelog_regex = re.compile(r'^(?:[fF]or +)?([a-z0-9+-/]*)ChangeLog:?')
pr_regex = re.compile(r'\tPR (?P<component>[a-z+-]+\/)?([0-9]+)$')
subject_pr_regex = re.compile(r'(^|\W)PR\s+(?P<component>[a-zA-Z+-]+)/(?P<pr>\d{4,7})')
subject_pr2_regex = re.compile(r'[(\[]PR\s*(?P<pr>\d{4,7})[)\]]')
pr_regex = re.compile(r'\tPR (?P<component>[a-z+-]+\/)?(?P<pr>[0-9]+)$')
dr_regex = re.compile(r'\tDR ([0-9]+)$')
star_prefix_regex = re.compile(r'\t\*(?P<spaces>\ *)(?P<content>.*)')
end_of_location_regex = re.compile(r'[\[<(:]')
@ -298,6 +300,7 @@ class GitCommit:
self.top_level_authors = []
self.co_authors = []
self.top_level_prs = []
self.subject_prs = set()
self.cherry_pick_commit = None
self.revert_commit = None
self.commit_to_info_hook = commit_to_info_hook
@ -307,6 +310,9 @@ class GitCommit:
if self.info.lines and self.info.lines[0] == 'Update copyright years.':
return
if self.info.lines and len(self.info.lines) > 1 and self.info.lines[1]:
self.errors.append(Error('Expected empty second line in commit message', info.lines[0]))
# Identify first if the commit is a Revert commit
for line in self.info.lines:
m = revert_regex.match(line)
@ -316,6 +322,19 @@ class GitCommit:
if self.revert_commit:
self.info = self.commit_to_info_hook(self.revert_commit)
# The following happens for get_email.py:
if not self.info:
return
# Extract PR numbers form the subject line
# Match either [PRnnnn] / (PRnnnn) or PR component/nnnn
if self.info.lines and not self.revert_commit:
self.subject_prs = {m.group('pr') for m in subject_pr2_regex.finditer(info.lines[0])}
for m in subject_pr_regex.finditer(info.lines[0]):
if not m.group('component') in bug_components:
self.errors.append(Error('invalid PR component in subject', info.lines[0]))
self.subject_prs.add(m.group('pr'))
# Allow complete deletion of ChangeLog files in a commit
project_files = [f for f in self.info.modified_files
if (self.is_changelog_filename(f[0], allow_suffix=True) and f[1] != 'D')
@ -346,6 +365,9 @@ class GitCommit:
if not self.errors:
self.check_mentioned_files()
self.check_for_correct_changelog()
if self.subject_prs:
self.errors.append(Error('PR %s in subject but not in changelog' %
', '.join(self.subject_prs), self.info.lines[0]))
@property
def success(self):
@ -460,7 +482,9 @@ class GitCommit:
else:
author_tuple = (m.group('name'), None)
elif pr_regex.match(line):
component = pr_regex.match(line).group('component')
m = pr_regex.match(line)
component = m.group('component')
pr = m.group('pr')
if not component:
self.errors.append(Error('missing PR component', line))
continue
@ -469,6 +493,8 @@ class GitCommit:
continue
else:
pr_line = line.lstrip()
if pr in self.subject_prs:
self.subject_prs.remove(pr)
elif dr_regex.match(line):
pr_line = line.lstrip()

View File

@ -17,6 +17,7 @@
# <http://www.gnu.org/licenses/>. */
import os
import re
import sys
from itertools import takewhile
@ -28,6 +29,8 @@ from unidiff import PatchSet, PatchedFile
DATE_PREFIX = 'Date: '
FROM_PREFIX = 'From: '
SUBJECT_PREFIX = 'Subject: '
subject_patch_regex = re.compile(r'^\[PATCH( \d+/\d+)?\] ')
unidiff_supports_renaming = hasattr(PatchedFile(), 'is_rename')
@ -37,7 +40,9 @@ class GitEmail(GitCommit):
diff = PatchSet.from_filename(filename)
date = None
author = None
subject = ''
subject_last = False
with open(self.filename, 'r') as f:
lines = f.read().splitlines()
lines = list(takewhile(lambda line: line != '---', lines))
@ -46,8 +51,21 @@ class GitEmail(GitCommit):
date = parse(line[len(DATE_PREFIX):])
elif line.startswith(FROM_PREFIX):
author = GitCommit.format_git_author(line[len(FROM_PREFIX):])
elif line.startswith(SUBJECT_PREFIX):
subject = line[len(SUBJECT_PREFIX):]
subject_last = True
elif subject_last and line.startswith(' '):
subject += line
elif line == '':
break
else:
subject_last = False
if subject:
subject = subject_patch_regex.sub('', subject)
header = list(takewhile(lambda line: line != '', lines))
body = lines[len(header) + 1:]
# Note: commit message consists of email subject, empty line, email body
message = [subject] + lines[len(header):]
modified_files = []
for f in diff:
@ -67,7 +85,7 @@ class GitEmail(GitCommit):
else:
t = 'M'
modified_files.append((target if t != 'D' else source, t))
git_info = GitInfo(None, date, author, body, modified_files)
git_info = GitInfo(None, date, author, message, modified_files)
super().__init__(git_info,
commit_to_info_hook=lambda x: None)

View File

@ -427,3 +427,16 @@ class TestGccChangelog(unittest.TestCase):
def test_multi_same_file(self):
email = self.from_patch_glob('0001-OpenMP-Fix-SIMT')
assert email.errors[0].message == 'same file specified multiple times'
def test_pr_only_in_subject(self):
email = self.from_patch_glob('0001-rs6000-Support-doubleword')
assert (email.errors[0].message ==
'PR 100085 in subject but not in changelog')
def test_wrong_pr_comp_in_subject(self):
email = self.from_patch_glob('pr-wrong-comp.patch')
assert email.errors[0].message == 'invalid PR component in subject'
def test_copyright_years(self):
email = self.from_patch_glob('copyright-years.patch')
assert not email.errors

View File

@ -1461,6 +1461,7 @@ Subject: [PATCH 0030/2034] PR c++/92746 - ICE with noexcept of function
Another place that needs to specially handle Concepts TS function-style
concepts.
PR c++/92746
* except.c (check_noexcept_r): Handle concept-check.
---
gcc/cp/ChangeLog | 3 +++
@ -1977,7 +1978,7 @@ index aac31d02b6c..56c470f6ecf 100644
From 5194b51ed9714808d88827531e91474895b6c706 Mon Sep 17 00:00:00 2001
From: Jason Merrill <jason@redhat.com>
Date: Thu, 16 Jan 2020 16:55:39 -0500
Subject: [PATCH 0121/2034] PR c++/93286 - ICE with __is_constructible and
Subject: [PATCH 0121/2034] PR c++/12345 - ICE with __is_constructible and
variadic template.
Here we had been recursing in tsubst_copy_and_build if type2 was a TREE_LIST
@ -3406,3 +3407,60 @@ index 00000000000..21540512e23
+
--
2.25.1
=== 0001-rs6000-Support-doubleword ===
From f700e4b0ee3ef53b48975cf89be26b9177e3a3f3 Mon Sep 17 00:00:00 2001
From: Xionghu Luo <luoxhu@linux.ibm.com>
Date: Tue, 8 Jun 2021 21:48:12 -0500
Subject: [PATCH] rs6000: Support doubleword swaps removal in rot64 load store
[PR100085]
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/pr100085.c: New test.
---
diff --git a/gcc/testsuite/gcc.target/powerpc/pr100085.c b/gcc/testsuite/gcc.target/powerpc/pr100085.c
new file mode 100644
index 00000000000..7d8b147b127
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr100085.c
@@ -0,0 +1,1 @@
+
--
2.25.1
=== pr-wrong-comp.patch ===
From 5194b51ed9714808d88827531e91474895b6c706 Mon Sep 17 00:00:00 2001
From: Jason Merrill <jason@redhat.com>
Date: Thu, 16 Jan 2020 16:55:39 -0500
Subject: [PATCH 0121/2034] PR some/93286 - ICE with __is_constructible and
variadic template.
gcc/testsuite/ChangeLog:
PR c++/93286
* gcc.target/powerpc/pr100085.c: New test.
---
diff --git a/gcc/testsuite/gcc.target/powerpc/pr100085.c b/gcc/testsuite/gcc.target/powerpc/pr100085.c
new file mode 100644
index 00000000000..7d8b147b127
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr100085.c
@@ -0,0 +1,1 @@
+
--
2.25.1
==== copyright-years.patch ===
From 99dee82307f1e163e150c9c810452979994047ce Mon Sep 17 00:00:00 2001
From: Jakub Jelinek <jakub@redhat.com>
Date: Mon, 4 Jan 2021 10:26:59 +0100
Subject: [PATCH] Update copyright years.
---
diff --git a/lto-plugin/lto-plugin.c b/lto-plugin/lto-plugin.c
new file mode 100644
index 6f67552d075..32478f070e8 100644
--- a/lto-plugin/lto-plugin.c
+++ b/lto-plugin/lto-plugin.c
@@ -0,0 +1,1 @@
+
--
2.25.1