{,PKG_}INSTALL_MASK: python implementation

The InstallMask.match code comes from the dblink _is_install_masked
method from portage-mgorny:

https://github.com/mgorny/portage/commit/f5ac3af3216d209618a2f232b4bf720bc8b520ad

4 files changed, 152 insertions, 79 deletions

diff --git a/bin/misc-functions.sh b/bin/misc-functions.sh
index 3c01280c7..26f589915 100755
--- a/bin/misc-functions.sh
+++ b/bin/misc-functions.sh
@@ -323,72 +323,6 @@ postinst_qa_check() {
 	done < <(printf "%s\0" "${qa_checks[@]}" | LC_ALL=C sort -u -z)
 }
 
-install_mask() {
-	local root="$1"
-	shift
-	local install_mask="$*"
-
-	# We think of $install_mask as a space-separated list of
-	# globs. We don't want globbing in the "for" loop; that is, we
-	# want to keep the asterisks in the indivual entries.
-	local shopts=$-
-	set -o noglob
-	local no_inst
-	for no_inst in ${install_mask}; do
-		# Here, $no_inst is a single "entry" potentially
-		# containing a glob. From now on, we *do* want to
-		# expand it.
-		set +o noglob
-
-		# The standard case where $no_inst is something that
-		# the shell could expand on its own.
-		if [[ -e "${root}"/${no_inst} || -L "${root}"/${no_inst} ||
-			"${root}"/${no_inst} != $(echo "${root}"/${no_inst}) ]] ; then
-			__quiet_mode || einfo "Removing ${no_inst}"
-			rm -Rf "${root}"/${no_inst} >&/dev/null
-		fi
-
-		# We also want to allow the user to specify a "bare
-		# glob." For example, $no_inst="*.a" should prevent
-		# ALL files ending in ".a" from being installed,
-		# regardless of their location/depth. We achieve this
-		# by passing the pattern to `find`.
-		find "${root}" \( -path "${no_inst}" -or -name "${no_inst}" \) \
-			-print0 2> /dev/null \
-		| LC_ALL=C sort -z \
-		| while read -r -d ''; do
-			__quiet_mode || einfo "Removing /${REPLY#${root}}"
-			rm -Rf "${REPLY}" >&/dev/null
-		done
-
-	done
-	# set everything back the way we found it
-	set +o noglob
-	set -${shopts}
-}
-
-preinst_mask() {
-	if [ -z "${D}" ]; then
-		 eerror "${FUNCNAME}: D is unset"
-		 return 1
-	fi
-
-	if ! ___eapi_has_prefix_variables; then
-		local ED=${D}
-	fi
-
-	# Make sure $PWD is not ${D} so that we don't leave gmon.out files
-	# in there in case any tools were built with -pg in CFLAGS.
-	cd "${T}"
-
-	install_mask "${ED}" "${INSTALL_MASK}"
-
-	# remove share dir if unnessesary
-	if has nodoc $FEATURES || has noman $FEATURES || has noinfo $FEATURES; then
-		rmdir "${ED%/}/usr/share" &> /dev/null
-	fi
-}
-
 preinst_sfperms() {
 	if [ -z "${D}" ]; then
 		 eerror "${FUNCNAME}: D is unset"
@@ -512,13 +446,6 @@ __dyn_package() {
 	# in there in case any tools were built with -pg in CFLAGS.
 	cd "${T}" || die
 
-	if [[ -n ${PKG_INSTALL_MASK} ]] ; then
-		# The caller makes ${D} refer to a temporary copy in this
-		# case, so that this does not mask files from the normal
-		# install image.
-		install_mask "${D%/}${EPREFIX}/" "${PKG_INSTALL_MASK}"
-	fi
-
 	local tar_options=""
 	[[ $PORTAGE_VERBOSE = 1 ]] && tar_options+=" -v"
 	has xattr ${FEATURES} && [[ $(tar --help 2> /dev/null) == *--xattrs* ]] && tar_options+=" --xattrs"
diff --git a/pym/_emerge/PackagePhase.py b/pym/_emerge/PackagePhase.py
index ed8256ee0..859f254be 100644
--- a/pym/_emerge/PackagePhase.py
+++ b/pym/_emerge/PackagePhase.py
@@ -11,6 +11,8 @@ import portage
 from portage import os
 from portage import _encodings
 from portage import _unicode_encode
+from portage.util._async.AsyncFunction import AsyncFunction
+from portage.util.install_mask import install_mask_dir, InstallMask
 
 
 class PackagePhase(CompositeTask):
@@ -31,7 +33,7 @@ class PackagePhase(CompositeTask):
 				encoding=_encodings['fs'], errors='strict'),
 				mode='r', encoding=_encodings['repo.content'],
 				errors='replace') as f:
-				self._pkg_install_mask = f.read()
+				self._pkg_install_mask = InstallMask(f.read())
 		except EnvironmentError:
 			self._pkg_install_mask = None
 		if self._pkg_install_mask:
@@ -51,6 +53,15 @@ class PackagePhase(CompositeTask):
 		if self._default_exit(proc) != os.EX_OK:
 			self.wait()
 		else:
+			self._start_task(AsyncFunction(
+				target=install_mask_dir,
+				args=(self._proot, self._pkg_install_mask)),
+				self._pkg_install_mask_exit)
+
+	def _pkg_install_mask_exit(self, proc):
+		if self._default_exit(proc) != os.EX_OK:
+			self.wait()
+		else:
 			self._start_package_phase()
 
 	def _start_package_phase(self):
diff --git a/pym/portage/dbapi/vartree.py b/pym/portage/dbapi/vartree.py
index bed76d80f..378d42dc0 100644
--- a/pym/portage/dbapi/vartree.py
+++ b/pym/portage/dbapi/vartree.py
@@ -32,6 +32,7 @@ portage.proxy.lazyimport.lazyimport(globals(),
 		'grabdict,normalize_path,new_protect_filename',
 	'portage.util.digraph:digraph',
 	'portage.util.env_update:env_update',
+	'portage.util.install_mask:install_mask_dir,InstallMask',
 	'portage.util.listdir:dircache,listdir',
 	'portage.util.movefile:movefile',
 	'portage.util.path:first_existing,iter_parents',
@@ -3845,11 +3846,22 @@ class dblink(object):
 		# be useful to avoid collisions in some scenarios.
 		# We cannot detect if this is needed or not here as INSTALL_MASK can be
 		# modified by bashrc files.
-		phase = MiscFunctionsProcess(background=False,
-			commands=["preinst_mask"], phase="preinst",
-			scheduler=self._scheduler, settings=self.settings)
-		phase.start()
-		phase.wait()
+		try:
+			with io.open(_unicode_encode(os.path.join(inforoot, "INSTALL_MASK"),
+				encoding=_encodings['fs'], errors='strict'),
+				mode='r', encoding=_encodings['repo.content'],
+				errors='replace') as f:
+				install_mask = InstallMask(f.read())
+		except EnvironmentError:
+			install_mask = None
+
+		if install_mask:
+			install_mask_dir(self.settings["ED"], install_mask)
+			if any(x in self.settings.features for x in ('nodoc', 'noman', 'noinfo')):
+				try:
+					os.rmdir(os.path.join(self.settings["ED"], 'usr', 'share'))
+				except OSError:
+					pass
 
 		# We check for unicode encoding issues after src_install. However,
 		# the check must be repeated here for binary packages (it's
diff --git a/pym/portage/util/install_mask.py b/pym/portage/util/install_mask.py
new file mode 100644
index 000000000..506e63c1f
--- /dev/null
+++ b/pym/portage/util/install_mask.py
@@ -0,0 +1,123 @@
+# Copyright 2018 Gentoo Foundation
+# Distributed under the terms of the GNU General Public License v2
+
+__all__ = ['install_mask_dir', 'InstallMask']
+
+import errno
+import fnmatch
+import sys
+
+from portage import os, _unicode_decode
+from portage.exception import (
+	OperationNotPermitted, PermissionDenied, FileNotFound)
+from portage.util import normalize_path
+
+if sys.hexversion >= 0x3000000:
+	_unicode = str
+else:
+	_unicode = unicode
+
+
+class InstallMask(object):
+	def __init__(self, install_mask):
+		"""
+		@param install_mask: INSTALL_MASK value
+		@type install_mask: str
+		"""
+		self._install_mask = install_mask.split()
+
+	def match(self, path):
+		"""
+		@param path: file path relative to ${ED}
+		@type path: str
+		@rtype: bool
+		@return: True if path matches INSTALL_MASK, False otherwise
+		"""
+		ret = False
+		for pattern in self._install_mask:
+			# absolute path pattern
+			if pattern.startswith('/'):
+				# match either exact path or one of parent dirs
+				# the latter is done via matching pattern/*
+				if (fnmatch.fnmatch(path, pattern[1:])
+						or fnmatch.fnmatch(path, pattern[1:] + '/*')):
+					ret = True
+					break
+			# filename
+			else:
+				if fnmatch.fnmatch(os.path.basename(path), pattern):
+					ret = True
+					break
+		return ret
+
+
+_exc_map = {
+	errno.ENOENT: FileNotFound,
+	errno.EPERM: OperationNotPermitted,
+	errno.EACCES: PermissionDenied,
+}
+
+
+def _raise_exc(e):
+	"""
+	Wrap OSError with portage.exception wrapper exceptions, with
+	__cause__ chaining when python supports it.
+
+	@param e: os exception
+	@type e: OSError
+	@raise PortageException: portage.exception wrapper exception
+	"""
+	wrapper_cls = _exc_map.get(e.errno)
+	if wrapper_cls is None:
+		raise
+	wrapper = wrapper_cls(_unicode(e))
+	wrapper.__cause__ = e
+	raise wrapper
+
+
+def install_mask_dir(base_dir, install_mask, onerror=None):
+	"""
+	Remove files and directories matched by INSTALL_MASK.
+
+	@param base_dir: directory path corresponding to ${ED}
+	@type base_dir: str
+	@param install_mask: INSTALL_MASK configuration
+	@type install_mask: InstallMask
+	"""
+	onerror = onerror or _raise_exc
+	base_dir = normalize_path(base_dir)
+	base_dir_len = len(base_dir) + 1
+	dir_stack = []
+
+	# Remove masked files.
+	for parent, dirs, files in os.walk(base_dir, onerror=onerror):
+		try:
+			parent = _unicode_decode(parent, errors='strict')
+		except UnicodeDecodeError:
+			continue
+		dir_stack.append(parent)
+		for fname in files:
+			try:
+				fname = _unicode_decode(fname, errors='strict')
+			except UnicodeDecodeError:
+				continue
+			abs_path = os.path.join(parent, fname)
+			relative_path = abs_path[base_dir_len:]
+			if install_mask.match(relative_path):
+				try:
+					os.unlink(abs_path)
+				except OSError as e:
+					onerror(e)
+
+	# Remove masked dirs (unless non-empty due to exclusions).
+	while True:
+		try:
+			dir_path = dir_stack.pop()
+		except IndexError:
+			break
+
+		if install_mask.match(dir_path[base_dir_len:]):
+			try:
+				os.rmdir(dir_path)
+			except OSError:
+				pass