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.

1 files changed, 28 insertions, 2 deletions

diff --git a/contrib/gcc-changelog/git_commit.py b/contrib/gcc-changelog/git_commit.py
index bd8c1ff..d1646bd 100755
--- a/contrib/gcc-changelog/git_commit.py
+++ b/contrib/gcc-changelog/git_commit.py
@@ -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()