Add distclean.sh - a little script to check set of distfiles against currently

installed ports collection and prompt to remove unmatching entries (i.e.
distfiles that doesn't have corresponding md5 file).

Hardly requiested by:	will

2 files changed, 71 insertions, 5 deletions

diff --git a/Tools/scripts/README b/Tools/scripts/README
index 738c54f4f98f..79fa0191277c 100644
--- a/Tools/scripts/README
+++ b/Tools/scripts/README
@@ -4,7 +4,9 @@ addport	- future replacement for easy-import
 
 consistency-check -  check whether all your ports are installed properly,
                      what files have changed, and what new files there are
-
+distclean - compare md5 sums of distfiles in ports/distfiles with currently
+            installed ports collection in ports/* and prompt to remove
+            unmatched entries
 getpr   - downloads a problem report from GNATS and attempts to extract
           the patch, shar, uuencoded file from it.
           this probably needs to be checked for potential security problems.
@@ -41,12 +43,21 @@ getpr, prpatch and prdone are used as so:
 	<this will attempt to fill out the cvs log message, check in the
 	 port and edit-pr the problem report so you can close it>
 
-NOTE: These scripts need work and are *NOT* safe to use unless you know
-      what they do.  Use at your own risk.  Patches would be great, but
-      I'd prefer they pass through me.
-
 ----------------------------------------------------------------------
 
 checksum is a script that allows checking of ports to see if their checksums
 match, and if they don't, give a diff against the older version to try and
 discover why the checksum didn't match.
+
+----------------------------------------------------------------------
+
+distclean is a script that allows to compare md5 checksums of distfiles in
+ports/distfiles with list of all md5 sums listed in "md5" files in the ports
+collection. After comparing, utility will prompt to remove distfiles which
+doesn't have associated md5 entry (most likely outdated distfiles).
+
+----------------------------------------------------------------------
+
+NOTE: These scripts need work and are *NOT* safe to use unless you know
+      what they do.  Use at your own risk.  Patches would be great, but
+      I'd prefer they pass through me.
diff --git a/Tools/scripts/distclean.sh b/Tools/scripts/distclean.sh
new file mode 100755
index 000000000000..89081be401ad
--- /dev/null
+++ b/Tools/scripts/distclean.sh
@@ -0,0 +1,55 @@
+#!/bin/sh
+
+# distclean
+
+# Compare distfiles in /usr/ports/distfiles
+# with currently instaled ports collection
+# and removes outdated files
+
+#
+# ----------------------------------------------------------------------------
+# "THE BEER-WARE LICENSE" (Revision 42, (c) Poul-Henning Kamp):
+# Maxim Sobolev <sobomax@altavista.net wrote this file.  As long as you retain
+# this notice you can do whatever you want with this stuff. If we meet some
+# day, and you think this stuff is worth it, you can buy me a beer in return.
+#
+# Maxim Sobolev
+# ----------------------------------------------------------------------------
+#
+
+
+PATH=/sbin:/bin:/usr/bin
+
+echo "Distfiles clean utility v0.40 by Maxim Sobolev <sobomax@altavista.net>."
+echo "Assumes that your ports in /usr/ports and distfiles in /usr/ports/distfiles."
+echo ""
+
+umask 077
+
+FN_PORTS=`mktemp -t dclean` || exit 1
+FN_DISTFILES=`mktemp -t dclean` || exit 1
+FN_RESULTS_SCRIPT=`mktemp -t dclean` || exit 1
+
+echo -n "Building ports md5 index..."
+find /usr/ports -name "md5" -type f | xargs cat | grep "^MD5 ("| sort | uniq > $FN_PORTS
+echo "Done."
+P_MD5_COUNT=`wc -l $FN_PORTS | sed "s| $FN_PORTS|| ; s| ||g"`
+echo "Found $P_MD5_COUNT md5 entries in your ports directory."
+
+echo -n "Building distfiles md5 index..."
+find -H /usr/ports/distfiles -type f | xargs md5 | sed 's|/usr/ports/distfiles/||' | sort > $FN_DISTFILES
+echo "Done."
+D_MD5_COUNT=`wc -l $FN_DISTFILES | sed "s| $FN_DISTFILES|| ; s| ||g"`
+echo "Found $D_MD5_COUNT distfile(s) in your distfiles directory."
+
+echo -n "Comparing results..."
+diff -d $FN_DISTFILES $FN_PORTS | grep "^<" | sed 's|.*(|rm -i /usr/ports/distfiles/| ; s|).*||' > $FN_RESULTS_SCRIPT
+echo "Done."
+R_MD5_COUNT=`wc -l $FN_RESULTS_SCRIPT | sed "s| $FN_RESULTS_SCRIPT|| ; s| ||g"`
+echo "$R_MD5_COUNT distfile(s) doesn't have corresponding md5 entries in ports directory."
+/bin/sh $FN_RESULTS_SCRIPT
+
+echo -n "Finishing..."
+rm -f $FN_RESULTS_SCRIPT $FN_PORTS $FN_DISTFILES
+echo "Done."
+