[gcc r10-10258] gcc-changelog: sync from master

[gcc r10-10258] gcc-changelog: sync from master

[Martin Liska]

https://gcc.gnu.org/g:8d07c82f4ae0f5b3a024ae13434bad0d9bbc3b10

commit r10-10258-g8d07c82f4ae0f5b3a024ae13434bad0d9bbc3b10
Author: Martin Liska <mliska@suse.cz>
Date:   Mon Nov 8 12:58:28 2021 +0100

    gcc-changelog: sync from master
    
    contrib/ChangeLog:
    
            * gcc-changelog/git_check_commit.py: Sync from master.
            * gcc-changelog/git_commit.py: Likewise.
            * gcc-changelog/git_email.py: Likewise.
            * gcc-changelog/git_update_version.py: Likewise.
            * gcc-changelog/test_email.py: Likewise.
            * gcc-changelog/test_patches.txt: Likewise.

Diff:
---
 contrib/gcc-changelog/git_check_commit.py   |  4 ++
 contrib/gcc-changelog/git_commit.py         | 71 +++++++++++++++++++-----
 contrib/gcc-changelog/git_email.py          | 22 +++++++-
 contrib/gcc-changelog/git_update_version.py |  5 +-
 contrib/gcc-changelog/test_email.py         | 21 ++++++-
 contrib/gcc-changelog/test_patches.txt      | 85 ++++++++++++++++++++++++++++-
 6 files changed, 189 insertions(+), 19 deletions(-)

diff --git a/contrib/gcc-changelog/git_check_commit.py b/contrib/gcc-changelog/git_check_commit.py
index 9a4c5d448fb..d6aff3cef91 100755
--- a/contrib/gcc-changelog/git_check_commit.py
+++ b/contrib/gcc-changelog/git_check_commit.py
@@ -29,6 +29,8 @@ parser.add_argument('-g', '--git-path', default='.',
                     help='Path to git repository')
 parser.add_argument('-p', '--print-changelog', action='store_true',
                     help='Print final changelog entires')
+parser.add_argument('-v', '--verbose', action='store_true',
+                    help='Print verbose information')
 args = parser.parse_args()
 
 retval = 0
@@ -41,6 +43,8 @@ for git_commit in parse_git_revisions(args.git_path, args.revisions):
     else:
         for error in git_commit.errors:
             print('ERR: %s' % error)
+            if args.verbose and error.details:
+                print(error.details)
         retval = 1
 
 exit(retval)
diff --git a/contrib/gcc-changelog/git_commit.py b/contrib/gcc-changelog/git_commit.py
index 4958ab9c159..27a1d59b211 100755
--- a/contrib/gcc-changelog/git_commit.py
+++ b/contrib/gcc-changelog/git_commit.py
@@ -134,6 +134,7 @@ ignored_prefixes = {
     'gcc/go/gofrontend/',
     'gcc/testsuite/gdc.test/',
     'gcc/testsuite/go.test/test/',
+    'libffi/',
     'libgo/',
     'libphobos/libdruntime/',
     'libphobos/src/',
@@ -156,7 +157,9 @@ 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'[\[<(:]')
@@ -194,9 +197,10 @@ def decode_path(path):
 
 
 class Error:
-    def __init__(self, message, line=None):
+    def __init__(self, message, line=None, details=None):
         self.message = message
         self.line = line
+        self.details = details
 
     def __repr__(self):
         s = self.message
@@ -215,7 +219,7 @@ class ChangeLogEntry:
         self.lines = []
         self.files = []
         self.file_patterns = []
-        self.opened_parentheses = 0
+        self.parentheses_stack = []
 
     def parse_file_names(self):
         # Whether the content currently processed is between a star prefix the
@@ -298,6 +302,7 @@ 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 +312,9 @@ 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 +324,21 @@ 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
+
+        self.check_commit_email()
+
+        # 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')
@@ -326,9 +349,11 @@ class GitCommit:
             # All modified files are only MISC files
             return
         elif project_files:
-            self.errors.append(Error('ChangeLog, DATESTAMP, BASE-VER and '
-                                     'DEV-PHASE updates should be done '
-                                     'separately from normal commits'))
+            err = 'ChangeLog, DATESTAMP, BASE-VER and DEV-PHASE updates ' \
+                  'should be done separately from normal commits\n' \
+                  '(note: ChangeLog entries will be automatically ' \
+                  'added by a cron job)'
+            self.errors.append(Error(err))
             return
 
         all_are_ignored = (len(project_files) + len(ignored_files)
@@ -344,6 +369,9 @@ 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):
@@ -458,7 +486,9 @@ 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
@@ -467,6 +497,8 @@ 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()
 
@@ -521,7 +553,7 @@ class GitCommit:
                     m = star_prefix_regex.match(line)
                     if m:
                         if (len(m.group('spaces')) != 1 and
-                                last_entry.opened_parentheses == 0):
+                                not last_entry.parentheses_stack):
                             msg = 'one space should follow asterisk'
                             self.errors.append(Error(msg, line))
                         else:
@@ -546,13 +578,13 @@ class GitCommit:
     def process_parentheses(self, last_entry, line):
         for c in line:
             if c == '(':
-                last_entry.opened_parentheses += 1
+                last_entry.parentheses_stack.append(line)
             elif c == ')':
-                if last_entry.opened_parentheses == 0:
+                if not last_entry.parentheses_stack:
                     msg = 'bad wrapping of parenthesis'
                     self.errors.append(Error(msg, line))
                 else:
-                    last_entry.opened_parentheses -= 1
+                    del last_entry.parentheses_stack[-1]
 
     def parse_file_names(self):
         for entry in self.changelog_entries:
@@ -578,9 +610,9 @@ class GitCommit:
 
     def check_for_broken_parentheses(self):
         for entry in self.changelog_entries:
-            if entry.opened_parentheses != 0:
+            if entry.parentheses_stack:
                 msg = 'bad parentheses wrapping'
-                self.errors.append(Error(msg, entry.lines[0]))
+                self.errors.append(Error(msg, entry.parentheses_stack[-1]))
 
     def get_file_changelog_location(self, changelog_file):
         for file in self.info.modified_files:
@@ -656,9 +688,11 @@ class GitCommit:
         for file in sorted(mentioned_files - changed_files):
             msg = 'unchanged file mentioned in a ChangeLog'
             candidates = difflib.get_close_matches(file, changed_files, 1)
+            details = None
             if candidates:
                 msg += f' (did you mean "{candidates[0]}"?)'
-            self.errors.append(Error(msg, file))
+                details = '\n'.join(difflib.Differ().compare([file], [candidates[0]])).rstrip()
+            self.errors.append(Error(msg, file, details))
         for file in sorted(changed_files - mentioned_files):
             if not self.in_ignored_location(file):
                 if file in self.new_files:
@@ -775,3 +809,12 @@ class GitCommit:
         print('Errors:')
         for error in self.errors:
             print(error)
+
+    def check_commit_email(self):
+        # Parse 'Martin Liska  <mliska@suse.cz>'
+        email = self.info.author.split(' ')[-1].strip('<>')
+
+        # Verify that all characters are ASCII
+        # TODO: Python 3.7 provides a nicer function: isascii
+        if len(email) != len(email.encode()):
+            self.errors.append(Error(f'non-ASCII characters in git commit email address ({email})'))
diff --git a/contrib/gcc-changelog/git_email.py b/contrib/gcc-changelog/git_email.py
index fa62e3ad2f7..87b419cae5d 100755
--- a/contrib/gcc-changelog/git_email.py
+++ b/contrib/gcc-changelog/git_email.py
@@ -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)
 
diff --git a/contrib/gcc-changelog/git_update_version.py b/contrib/gcc-changelog/git_update_version.py
index 0508f194084..1837c1a8d7f 100755
--- a/contrib/gcc-changelog/git_update_version.py
+++ b/contrib/gcc-changelog/git_update_version.py
@@ -27,7 +27,10 @@ from git_repository import parse_git_revisions
 current_timestamp = datetime.datetime.now().strftime('%Y%m%d\n')
 
 # Skip the following commits, they cannot be correctly processed
-IGNORED_COMMITS = ('c2be82058fb40f3ae891c68d185ff53e07f14f45')
+IGNORED_COMMITS = (
+        'c2be82058fb40f3ae891c68d185ff53e07f14f45',
+        '04a040d907a83af54e0a98bdba5bfabc0ef4f700',
+        '2e96b5f14e4025691b57d2301d71aa6092ed44bc')
 
 
 def read_timestamp(path):
diff --git a/contrib/gcc-changelog/test_email.py b/contrib/gcc-changelog/test_email.py
index 7472762e66d..a4796dbbe94 100755
--- a/contrib/gcc-changelog/test_email.py
+++ b/contrib/gcc-changelog/test_email.py
@@ -258,7 +258,7 @@ class TestGccChangelog(unittest.TestCase):
         email = self.from_patch_glob('0001-Add-patch_are')
         msg = 'ChangeLog, DATESTAMP, BASE-VER and DEV-PHASE updates should ' \
               'be done separately from normal commits'
-        assert email.errors[0].message == msg
+        assert email.errors[0].message.startswith(msg)
 
     def test_strict_mode_normal_patch(self):
         email = self.get_git_email('0001-Just-test-it.patch')
@@ -415,6 +415,7 @@ class TestGccChangelog(unittest.TestCase):
     def test_multiline_bad_parentheses(self):
         email = self.from_patch_glob('0002-Wrong-macro-changelog.patch')
         assert email.errors[0].message == 'bad parentheses wrapping'
+        assert email.errors[0].line == '	* config/i386/i386.md (*fix_trunc<mode>_i387_1,'
 
     def test_changelog_removal(self):
         email = self.from_patch_glob('0001-ChangeLog-removal.patch')
@@ -427,3 +428,21 @@ 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
+
+    def test_non_ascii_email(self):
+        email = self.from_patch_glob('non-ascii-email.patch')
+        assert (email.errors[0].message ==
+                'non-ASCII characters in git commit email address (jbglaw@ług-owl.de)')
diff --git a/contrib/gcc-changelog/test_patches.txt b/contrib/gcc-changelog/test_patches.txt
index 39d40b88618..98a0d3f1ee0 100644
--- a/contrib/gcc-changelog/test_patches.txt
+++ b/contrib/gcc-changelog/test_patches.txt
@@ -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 +3407,85 @@ 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
+
+=== non-ascii-email.patch ===
+From f42e95a830ab48e59389065ce79a013a519646f1 Mon Sep 17 00:00:00 2001
+From: Jan-Benedict Glaw <jbglaw@ług-owl.de>
+Date: Mon, 13 Sep 2021 12:08:25 +0200
+Subject: [PATCH] Fix multi-statment macro
+
+INIT_CUMULATIVE_ARGS() expands to multiple statements, which will break right
+after an `if` statement. Wrap it into a block.
+
+gcc/ChangeLog:
+
+	* config/alpha/vms.h (INIT_CUMULATIVE_ARGS): Wrap multi-statment
+	define into a block.
+---
+ gcc/config/alpha/vms.h | 10 +++++++---
+ 1 file changed, 7 insertions(+), 3 deletions(-)
+
+diff --git a/gcc/config/alpha/vms.h b/gcc/config/alpha/vms.h
+index 2a9917cde62..0033b0004b3 100644
+--- a/gcc/config/alpha/vms.h
++++ b/gcc/config/alpha/vms.h
+@@ -0,0 +1,1 @@
++
+--