[gentoo-dev] [PATCH v2 4/5] vcs-snapshot.eclass: Detect and report invalid directory structure

[Michał Górny]

Detect when the archive does not contain a single top-level directory,
and abort in that case.  Otherwise, --strip-components would result
in unpredictable mess.

Signed-off-by: Michał Górny <mgorny@g.o>
---
 eclass/vcs-snapshot.eclass | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/eclass/vcs-snapshot.eclass b/eclass/vcs-snapshot.eclass
index 312e9a4611e1..33abd9a7c190 100644
--- a/eclass/vcs-snapshot.eclass
+++ b/eclass/vcs-snapshot.eclass
@@ -1,87 +1,100 @@
 # Copyright 1999-2019 Gentoo Authors
 # Distributed under the terms of the GNU General Public License v2
 
 # @ECLASS: vcs-snapshot.eclass
 # @MAINTAINER:
 # mgorny@g.o
 # @SUPPORTED_EAPIS: 0 1 2 3 4 5 6 7
 # @BLURB: support eclass for unpacking VCS snapshot tarballs
 # @DESCRIPTION:
 # THIS ECLASS IS NOT NECESSARY FOR MODERN GITHUB AND GITLAB SNAPSHOTS.
 # THEIR DIRECTORY STRUCTURE IS ENTIRELY PREDICTABLE, SO UPDATE YOUR
 # EBUILD TO USE /ARCHIVE/ URI AND SET S IF NECESSARY.
 #
 # This eclass provides a convenience src_unpack() which does unpack all
 # the tarballs in SRC_URI to locations matching their (local) names,
 # discarding the original parent directory.
 #
 # The typical use case are VCS tag snapshots coming from BitBucket
 # (but not GitHub or GitLab).  They have hash appended to the directory
 # name which makes extracting them a painful experience.  But if you are
 # using a SRC_URI arrow to rename them (which quite likely you have to
 # do anyway), vcs-snapshot will just extract them into matching
 # directories.
 #
 # Please note that this eclass handles only tarballs (.tar, .tar.gz,
 # .tar.bz2 & .tar.xz).  For any other file format (or suffix) it will
 # fall back to regular unpack.  Support for additional formats may be
 # added in the future if necessary.
 #
 # @EXAMPLE:
 #
 # @CODE
 # EAPI=7
 # inherit vcs-snapshot
 #
 # SRC_URI="
 #    https://bitbucket.org/foo/bar/get/${PV}.tar.bz2 -> ${P}.tar.bz2
 #    https://bitbucket.org/foo/bar-otherstuff/get/${PV}.tar.bz2
 #        -> ${P}-otherstuff.tar.bz2"
 # @CODE
 #
 # and however the tarballs were originally packed, all files will appear
 # in ${WORKDIR}/${P} and ${WORKDIR}/${P}-otherstuff respectively.
 
 case ${EAPI:-0} in
 	0|1|2|3|4|5|6|7) ;;
 	*) die "vcs-snapshot.eclass API in EAPI ${EAPI} not yet established."
 esac
 
 EXPORT_FUNCTIONS src_unpack
 
 # @FUNCTION: vcs-snapshot_src_unpack
 # @DESCRIPTION:
 # Extract all the archives from ${A}. The .tar, .tar.gz, .tar.bz2
 # and .tar.xz archives will be unpacked to directories matching their
 # local names. Other archive types will be passed down to regular
 # unpack.
 vcs-snapshot_src_unpack() {
 	debug-print-function ${FUNCNAME} "${@}"
 
 	local f
 
 	for f in ${A}
 	do
 		case "${f}" in
 			*.tar|*.tar.gz|*.tar.bz2|*.tar.xz)
 				local destdir=${WORKDIR}/${f%.tar*}
 
 				debug-print "${FUNCNAME}: unpacking ${f} to ${destdir}"
 
-				# XXX: check whether the directory structure inside is
-				# fine? i.e. if the tarball has actually a parent dir.
+				local l topdirs=()
+				while read l; do
+					topdirs+=( "${l}" )
+				done < <(tar -t -f "${DISTDIR}/${f}" | cut -d/ -f1 | sort -u)
+				if [[ ${#topdirs[@]} -gt 1 ]]; then
+					eerror "The archive ${f} contains multiple or no top directory."
+					eerror "It is impossible for vcs-snapshot to unpack this correctly."
+					eerror "Top directories found:"
+					local d
+					for d in "${topdirs[@]}"; do
+						eerror "    ${d}"
+					done
+					die "${FUNCNAME}: Invalid directory structure in archive ${f}"
+				fi
+
 				mkdir "${destdir}" || die
 				# -o (--no-same-owner) to avoid restoring original owner
 				einfo "Unpacking ${f}"
 				tar -C "${destdir}" -x -o --strip-components 1 \
 					-f "${DISTDIR}/${f}" || die
 				;;
 			*)
 				debug-print "${FUNCNAME}: falling back to unpack for ${f}"
 
 				# fall back to the default method
 				unpack "${f}"
 				;;
 		esac
 	done
 }
-- 
2.22.0