| icetindil | 82838a2 | 2013-10-11 16:41:18 -0700 | [diff] [blame^] | 1 | #!/bin/bash |
| 2 | # |
| 3 | # Copyright 2010-2011 The Regents of the University of California |
| 4 | # |
| 5 | # Licensed under the Apache License, Version 2.0 (the "License"); you |
| 6 | # may not use this file except in compliance with the License. You |
| 7 | # may obtain a copy of the License at |
| 8 | # |
| 9 | # http://www.apache.org/licenses/LICENSE-2.0 |
| 10 | # |
| 11 | # Unless required by applicable law or agreed to in writing, software |
| 12 | # distributed under the License is distributed on an "AS IS"; BASIS, |
| 13 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or |
| 14 | # implied. See the License for the specific language governing |
| 15 | # permissions and limitations under the License. |
| 16 | # |
| 17 | # Author: Rares Vernica <rares (at) ics.uci.edu> |
| 18 | |
| 19 | DIR=`dirname $0`; if [ "${DIR:0:1}" == "." ]; then DIR=`pwd`"${DIR:1}"; fi |
| 20 | source $DIR/conf.sh |
| 21 | |
| 22 | ARGS=1 # Required number of arguments |
| 23 | E_BADARGS=85 # Wrong number of arguments passed to script. |
| 24 | if [ $# -lt "$ARGS" ] |
| 25 | then |
| 26 | echo "Usage: `basename $0` dataset" |
| 27 | echo "Example: `basename $0` dblp-small" |
| 28 | exit $E_BADARGS |
| 29 | fi |
| 30 | |
| 31 | $SSJOIN/tokenizer $DATA/$1/raw-000/part-00000 $2 |
| 32 | mkdir $DATA/$1/$IN |
| 33 | mv $DATA/$1/raw-000/part-00000.bin $DATA/$1/$IN/part-00000 |
| 34 | |