#!/bin/sh
# $Header: /upc/share/CVS/ldm5/scour/scour.in,v 1.1 2002/10/14 21:42:01 steve Exp $
# Deletes old data files.
#
# Recursively deletes files older than a specified number of days from a
# specified set of directories.  The directories, retention time in days,
# and an optional shell filename pattern appear, separated by tab characters
# one directory per line, in a configuration file named on the command line.
#
# If no files have been written under a directory since the last time scour was
# run, it will skip deleting old files and log an error message instead.
#
# WARNING: scour follows symbolic links, so don't put symbolic links to
# directories you don't want scoured under data directories.

PATH=/bin:/usr/bin
CONFFILE=/home/dataman/bin/scour.conf			# default, if no args
VERBOSEFLAG=
DEBUGFLAG=
ERRS=
LOGGER=echo
TZ=UTC0 export TZ
LOG_LDM=local0

while [ "$1" != "" ]
do
	case "$1" in
	-v)
		VERBOSEFLAG=1
		;;
	-x)
		DEBUGFLAG=1
		;;
	-l)						# logs to syslogd
		LOGGER="logger -t `basename $0` -p $LOG_LDM.notice"
		;;
	-*)
		$LOGGER "unrecognized flag ($1)"
		ERRS=1
		;;
	*)
		if [ $# -ne 1 ]
		then
			$LOGGER "only 1 conf file argument permitted"
			ERRS=1
		fi
		CONFFILE=$1
		;;
	esac
	shift
done

if [ "$ERRS" != "" ]
then
	$LOGGER "usage: `basename $0` [-l] [-v] [-x] [config-file]"
	exit 1
fi

if [ "$VERBOSEFLAG" != "" ]
then
	$LOGGER "Starting Up"
fi

while read dir age pattern; do
    if [ x$dir = x ]	# ignore blank lines
    then
        continue
    fi

    case $dir in
      \#*) 		# ignore comments
	continue
	;;
      *)
	if [ x$pattern = x ]
	then
		pattern="*"
	fi

	# handle ~user expansion for home directory of user
	rdir=`echo echo $dir | csh -f`
	if [ $? != 0 ]; then
	    $LOGGER "directory $dir does not exist, skipping"
	    continue
	fi

	# expand symbolic link, since find doesn't follow symbolic links
	edir=`cd $rdir && /bin/pwd`
	if [ $? != 0 ]; then
	    $LOGGER "directory $dir does not exist, skipping"
	    continue
	fi

	if [ "$DEBUGFLAG" != "" ]
	then
	    echo "dir=$dir age=$age pattern=$pattern edir=$edir"
	fi

	# if either "$edir/.scour$pattern" doesn't exist yet OR
        #           there are files newer than "$edir/.scour$pattern"
	# then
	#     delete old files and create "$edir/.scour$pattern"
        # else
	#     skip deletions and log message

	if  [ ! -f "$edir/.scour$pattern" ] || \
	    (cd $edir; find . -newer "$edir/.scour$pattern" -print) | grep -s .
	then
            # find has a non-intuitive interpretation of age, subtract 1
            FINDAGE=`echo $age 1 - p|dc`
            if [ "$VERBOSEFLAG" != "" ]
            then
                    BEFORE=`du -s $edir|sed 's/^ *\([0-9]*\).*/\1/'`
            fi
            (cd $edir; \
             find . -type f -mtime +$FINDAGE -name "$pattern" -exec rm -f {} \;) \
             && touch "$edir/.scour$pattern"
            if [ "$VERBOSEFLAG" != "" ]
            then
                AFTER=`du -s $edir|sed 's/^ *\([0-9]*\).*/\1/'`
                # set DELETED to max(0, BEFORE - AFTER)
                DELETED=`echo $BEFORE $AFTER|\
                         sed 's/\([0-9]*\) \([0-9]*\).*/b=\1;a=\2;d=0;if(a<b)d=b-a;d/'|\
                             bc`
                $LOGGER "$DELETED blocks from $edir/$pattern ( > $age days old)"
            fi
	else
	    $LOGGER "skipping, no recent files in $edir/$pattern"
	fi
	;;
    esac
done < $CONFFILE

if [ "$VERBOSEFLAG" != "" ]
then
	$LOGGER exiting ...
fi