Merge "yum-minimal: strip locale archive"

elements/yum-minimal/pre-install.d/03-yum-cleanup

@@ -22,8 +22,59 @@ set -eu
 set -o pipefail
 
 # effectively: febootstrap-minimize --keep-zoneinfo --keep-rpmdb --keep-services "$target"
-# locales
-rm -rf /usr/{{lib,share}/locale,{lib,lib64}/gconv,bin/localedef,sbin/build-locale-archive}
+
+# Fedora 24 has a much better way to handle just installing some
+# languages; see bug.  We should support that at the right time.
+if [[ $DISTRO_NAME == "fedora" && $DIB_RELEASE -gt 23 ]]; then
+    echo "Locale support for Fedora 24 is incomplete"
+    echo " see: https://bugs.launchpad.net/diskimage-builder/+bug/1571488"
+    die "Cannot cleanup locales on > Fedora 23"
+fi
+
+# Stripping *all* locales is a bad idea.  For now, we take the
+# suggestion in [1] for reducing this
+# [1] https://bugzilla.redhat.com/show_bug.cgi?id=156477
+
+if [ ! -f /usr/lib/locale/locale-archive ]; then
+    die "locale-archive not found?  Can not do cleanup."
+fi
+
+# now the archive has everything in it, and is about 100MiB.  Strip it
+# to just en_US (basically, this is the locale we support if you ssh
+# in, other than POSIX)
+localedef --delete-from-archive \
+    $(localedef --list-archive | grep -v '^en_US' | xargs)
+
+# This removes the locales from the archive index but doesn't rebuild
+# the file, so it is still the same size (maybe it is sparse?
+# presumably as it's mmapped you don't want to fiddle with the offsets
+# of locales in the archive on a live system.  We are not live).
+
+# build-locale-archive is a tool provided by the RH packaging of
+# glibc.  Documentation is scarce, but it takes the pre-built locales
+# in the tmpl file and creates an archive.  It seems originally the
+# installer would set some flags to rpm to tell the package what
+# languages to pick out of the template, but along the way, this was
+# reverted to install them (size considered less important than locale
+# support).
+
+# We hack this by moving the locale-archive we've removed the extra
+# locales from to the template, then re-run the build.
+mv /usr/lib/locale/locale-archive /usr/lib/locale/locale-archive.tmpl
+
+# rebuild archive from template
+/usr/sbin/build-locale-archive
+
+# leave empty template behind as package does.  I think this stops
+# upgrades redoing things
+echo > /usr/locale/locale-archive.tmpl
+
+# remove the unnecessary source locale files and iconv files
+pushd /usr/share/locale
+find . ! -name 'locale.alias' -delete
+popd
+rm -rf {lib.lib64}/gconv
+
 # docs
 rm -rf /usr/share/{doc,info,gnome/help}
 # cracklib