[gentoo-portage-dev] [PATCH 3 of 3] repoman: update copyright on modified files

[Fabian Groffen <grobian@gentoo.org>]

To retain the behaviour of echangelog, update the copyrights on modified
files (mostly ebuilds) when necessary.  We also use this to update the
ChangeLog's copyright.

diff --git a/pym/repoman/utilities.py b/pym/repoman/utilities.py
--- a/pym/repoman/utilities.py
+++ b/pym/repoman/utilities.py
@@ -523,9 +523,84 @@
 
 	return outvcs
 
+def update_copyrights(pkgdir, files, year, pretend):
+	"""
+	Check list of files for Copyright statements, and update them to
+	year.  The patterns used for replacing copyrights are taken from
+	echangelog.  Only the first lines of each file that start with a
+	hash ('#') are considered, until a line is found that doesn't start
+	with a hash.
+	patches and diffs (identified by .patch and .diff) are excluded
+	"""
+
+	for fn in files:
+		if fn.endswith('.diff') or fn.endswith('.patch'):
+			continue
+
+		fn_path = os.path.join(pkgdir, fn)
+		try:
+			fn_hdl = io.open(_unicode_encode(fn_path,
+				encoding=_encodings['fs'], errors='strict'),
+				mode='r', encoding=_encodings['repo.content'], errors='replace')
+		except EnvironmentError:
+			continue
+
+		orig_header = []
+		new_header = []
+
+		for line in fn_hdl:
+			line_strip = line.strip()
+			orig_header.append(line)
+			if not line_strip or line_strip[:1] != '#':
+				new_header.append(line)
+				break
+
+			# these two regexes are taken from
+			# echangelog update_copyright()
+			line = re.sub(r'^(# Copyright \d+) ',
+				r'\1-%s ' % year, line)
+			line = re.sub(r'^(# Copyright) \d\d\d\d-\d\d\d\d',
+				r'\1 1999-%s' % year, line)
+			new_header.append(line)
+
+		difflines = 0
+		for line in difflib.unified_diff(orig_header, new_header,
+				fromfile=fn_path, tofile=fn_path, n=0):
+			util.writemsg_stdout(line, noiselevel=-1)
+			difflines += 1
+		util.writemsg_stdout("\n", noiselevel=-1)
+
+		# unified diff has three lines to start with
+		if difflines > 3 and not pretend:
+			# write new file with changed header
+			f, fnnew_path = mkstemp()
+			f = io.open(f, mode='w', encoding=_encodings['repo.content'],
+				errors='backslashreplace')
+			for line in new_header:
+				f.write(line);
+			for line in fn_hdl:
+				f.write(line)
+			f.close()
+			try:
+				fn_stat = os.stat(fn_path)
+			except OSError:
+				fn_stat = None
+
+			shutil.move(fnnew_path, fn_path)
+
+			if fn_stat is None:
+				util.apply_permissions(fn_path, mode=0o644)
+			else:
+				util.apply_stat_permissions(fn_path, fn_stat)
+		fn_hdl.close()
+
 def UpdateChangeLog(pkgdir, category, package, new, removed, changed, \
 		msg, pretend, repodir):
-	""" Write an entry to an existing ChangeLog, or create a new one. """
+	"""
+	Write an entry to an existing ChangeLog, or create a new one.
+	Updates copyright year on changed files, and updates the header of
+	ChangeLog with the contents of skel.ChangeLog.
+	"""
 
 	# figure out who to write as
 	if 'GENTOO_COMMITTER_NAME' in os.environ and \
@@ -548,6 +623,12 @@
 		logging.critical(err)
 		return None
 
+	year = time.strftime('%Y')
+	date = time.strftime('%d %b %Y')
+
+	# check modified files and the ChangeLog for copyright updates
+	update_copyrights(pkgdir, new + changed + ['ChangeLog'], year, pretend)
+
 	cl_path = os.path.join(pkgdir, 'ChangeLog')
 	clold_lines = []
 	clnew_lines = []
@@ -578,7 +659,8 @@
 	# construct correct header first
 	try:
 		if clold_file is not None:
-			# retain header from old ChangeLog
+			# retain header from old ChangeLog, its copyright has
+			# already been updated by update_copyrights
 			for line in clold_file:
 				line_strip = line.strip()
 				clold_lines.append(line)
@@ -597,7 +679,7 @@
 				line = line.replace('<CATEGORY>', category)
 				line = line.replace('<PACKAGE_NAME>', package)
 				line = re.sub(r'^(# Copyright \d\d\d\d)-\d\d\d\d ',
-					r'\1-%s ' % time.strftime('%Y'), line)
+					r'\1-%s ' % year, line)
 				clnew_lines.append(line)
 			clnew_lines.append(_unicode_decode('\n'))
 			clskel_file.close()
@@ -651,7 +733,7 @@
 		if clold_file is not None:
 			# clold_lines may contain a saved non-header line
 			# that we want to write first.
-			if clold_lines[-1].strip():
+			if len(clold_lines) > 0 and clold_lines[-1].strip():
 				f.write(clold_lines[-1])
 
 			for line in clold_file: