]> gitweb.fperrin.net Git - DictionaryPC.git/blob - data/downloadInputs.sh
Better downloading, fix Builder.
[DictionaryPC.git] / data / downloadInputs.sh
1 #!/bin/bash -e
2
3 OLD_DIR=`pwd`
4 DIR=`dirname $0`
5
6 cd $DIR
7
8 echo "Downloading from: http://dumps.wikimedia.org/enwiktionary/"
9 WIKI=enwiktionary-20111224-pages-articles.xml
10 curl --remote-name http://dumps.wikimedia.org/enwiktionary/20111224/${WIKI}.bz2
11 echo "Unzipping... this is slow."
12 bunzip2 ${WIKI}.bz2
13 mv ${WIKI} inputs/
14
15 echo "Downloading from: http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/"
16 CHEMNITZ=de-en.txt
17 curl --remote-name http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/${CHEMNITZ}.gz
18 gunzip ${CHEMNITZ}.gz
19 mv ${CHEMNITZ} inputs/
20
21 echo "Done.  Now run WiktionarySplitter to spit apart enwiktionary."
22
23 cd $OLD_DIR