]> gitweb.fperrin.net Git - DictionaryPC.git/blob - data/downloadInputs.sh
Attempt at using maven for compilation
[DictionaryPC.git] / data / downloadInputs.sh
1 #!/bin/bash -e
2
3 OLD_DIR=`pwd`
4 DIR=`dirname $0`
5 cd $DIR
6
7 echo "Note that unzipping is slow."
8
9 L=en
10 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
11 WIKI=${L}wiktionary-latest-pages-articles.xml
12 curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2
13 mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2
14
15 echo "Downloading from: http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/"
16 CHEMNITZ=de-en.txt
17 curl -L --remote-name http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/${CHEMNITZ}.gz
18 mv ${CHEMNITZ}.gz inputs/de-en_chemnitz.txt.gz
19
20 L=fr
21 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
22 WIKI=${L}wiktionary-latest-pages-articles.xml
23 curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2
24 mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2
25
26 L=it
27 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
28 WIKI=${L}wiktionary-latest-pages-articles.xml
29 curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2
30 mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2
31
32 L=de
33 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
34 WIKI=${L}wiktionary-latest-pages-articles.xml
35 curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2
36 mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2
37
38 L=es
39 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
40 WIKI=${L}wiktionary-latest-pages-articles.xml
41 curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2
42 mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2
43
44 L=pt
45 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
46 WIKI=${L}wiktionary-latest-pages-articles.xml
47 curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2
48 mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2
49
50 echo "Done.  Now run WiktionarySplitter to split apart enwiktionary."
51
52 cd $OLD_DIR