#! /bin/sh
set -e

#http://www.debian.org/mirror/anonftpsync

# This script originates from http://www.debian.org/mirror/anonftpsync

# CVS: cvs.debian.org:/cvs/webwml - webwml/english/mirror/anonftpsync
# Version: $Id: anonftpsync,v 1.27 2007/05/20 10:48:27 joy Exp $ 

# Note: You MUST have rsync 2.6.4 or newer, which is available in sarge
# and all newer Debian releases, or at http://rsync.samba.org/

# Note: You need to install the package procmail, it contains 
# /usr/bin/lockfile, which is needed by this script.

# Don't forget:
# chmod u+x anonftpsync

# Set the variables below to fit your site. You can then use cron to have
# this script run daily to automatically update your copy of the archive.

# TO is the destination for the base of the Debian mirror directory
# (the dir that holds dists/ and ls-lR).
# (mandatory)

TO=/mnt/mirror/source

# RSYNC_HOST is the site you have chosen from the mirrors file.
# (http://www.debian.org/mirror/list-full)
# (mandatory)

RSYNC_HOST=ftp.mirror.ac.uk


# RSYNC_DIR is the directory given in the "Packages over rsync:" line of
# the mirrors file for the site you have chosen to mirror.
# (mandatory)

RSYNC_DIR=ftp.debian.org/debian/

# LOGDIR is the directory where the logs will be written to
# (mandatory)

LOGDIR=/mnt/mirror/logs

# ARCH_EXCLUDE can be used to exclude a complete architecture from
# mirrorring. Please use as space seperated list.
# Possible values are:
# alpha, amd64, arm, hppa, hurd-i386, i386, ia64, m68k, mipsel, mips, powerpc, s390, sh and sparc
#
# There is one special value: source
# This is not an architecture but will exclude all source code in /pool
#
# eg.
ARCH_EXCLUDE="alpha arm hppa hurd-i386 amd64 i386 powerpc ia64 m68k mipsel mips s390 sparc all"
# 
# With a blank ARCH_EXCLUDE you will mirror all available architectures
# (optional)

#ARCH_EXCLUDE=

# EXCLUDE is a list of parameters listing patterns that rsync will exclude, in
# addition to the architectures excluded by ARCH_EXCLUDE.
#
# Use ARCH_EXCLUDE to exclude specific architectures or all sources
#
# --exclude stable, testing, unstable options DON'T remove the packages of
# the given distribution. If you want do so, use debmirror instead.
#
# The following example would exclude mostly everything:
EXCLUDE="\
   --exclude testing/ --exclude unstable/ \
   --exclude /contrib/ --exclude /non-free/ \
 "

# With a blank EXCLUDE you will mirror the entire archive, except the
# architectures excluded by ARCH_EXCLUDE.
# (optional)


# MAILTO is the address to send logfiles to;
# if it is not defined, no mail will be sent
# (optional)

MAILTO=

# There should be no need to edit anything below this point, unless there
# are problems.

#-----------------------------------------------------------------------------#

# Check for some environment variables
if [ -z $TO ] || [ -z $RSYNC_HOST ] || [ -z $RSYNC_DIR ] || [ -z $LOGDIR ]; then
	echo "One of the following variables seems to be empty:"
	echo "TO, RSYNC_HOST, RSYNC_DIR or LOGDIR"
	exit 2
fi

if ! [ -d ${TO}/project/trace/ ]; then
	# we are running mirror script for the first time
	umask 002
	mkdir -p ${TO}/project/trace
fi

# Note: on some non-Debian systems, hostname doesn't accept -f option.
# If that's the case on your system, make sure hostname prints the full
# hostname, and remove the -f option. If there's no hostname command,
# explicitly replace `hostname -f` with the hostname.

HOSTNAME=`hostname -f`

# The hostname must match the "Site" field written in the list of mirrors.
# If hostname doesn't returns the correct value, fill and uncomment below 
# HOSTNAME=mirror.domain.tld
 
LOCK="${TO}/Archive-Update-in-Progress-${HOSTNAME}"

# The temp directory used by rsync --delay-updates is not
# world-readable remotely. It must be excluded to avoid errors. 
TMP_EXCLUDE="--exclude .~tmp~/"

# Exclude architectures defined in $ARCH_EXCLUDE
for ARCH in $ARCH_EXCLUDE; do
	EXCLUDE=$EXCLUDE"\
		--exclude binary-$ARCH/ \
		--exclude disks-$ARCH/ \
		--exclude installer-$ARCH/ \
		--exclude Contents-$ARCH.gz \
		--exclude Contents-$ARCH.diff/ \
		--exclude *_$ARCH.deb \
		--exclude *_$ARCH.udeb "
	if [ "$ARCH" == "source" ]; then
		SOURCE_EXCLUDE="\
		--exclude *.tar.gz \
		--exclude *.diff.gz \
		--exclude *.dsc "
	fi
done

# Logfile
LOGFILE=$LOGDIR/debian-mirror.log

# Get in the right directory and set the umask to be group writable
# 
cd $HOME
umask 002

# Check to see if another sync is in progress
if lockfile -! -l 43200 -r 0 "$LOCK"; then
  echo ${HOSTNAME} is unable to start rsync, lock file exists
  exit 1
fi
# Note: on some non-Debian systems, trap doesn't accept "exit" as signal
# specification. If that's the case on your system, try using "0".
trap "rm -f $LOCK > /dev/null 2>&1" exit

set +e

# First sync /pool
rsync --recursive --links --hard-links --times --verbose \
     $TMP_EXCLUDE $EXCLUDE $SOURCE_EXCLUDE \
     $RSYNC_HOST::$RSYNC_DIR/pool/ $TO/pool/ >> $LOGFILE 2>&1
result=$?

if [ 0 = $result ]; then
	# Now sync the remaining stuff
	rsync --recursive --links --hard-links --times --verbose --delay-updates --delete-after \
	     --exclude "Archive-Update-in-Progress-${HOSTNAME}" \
	     --exclude "project/trace/${HOSTNAME}" \
	     $TMP_EXCLUDE $EXCLUDE $SOURCE_EXCLUDE \
	     $RSYNC_HOST::$RSYNC_DIR $TO >> $LOGFILE 2>&1

	LANG=C date -u > "${TO}/project/trace/${HOSTNAME}"
else
	echo "ERROR: Help, something weird happened" | tee -a $LOGFILE
	echo "mirroring /pool exited with exitcode" $result | tee -a $LOGFILE
fi


if ! [ -z $MAILTO ]; then
	mail -s "debian archive synced" $MAILTO < $LOGFILE
fi

savelog $LOGFILE