]> gitweb.fperrin.net Git - DictionaryPC.git/blob - data/downloadInputs.sh
Fixed combining marks on Unicode regexes.
[DictionaryPC.git] / data / downloadInputs.sh
1 #!/bin/bash -e
2
3 OLD_DIR=`pwd`
4 DIR=`dirname $0`
5 cd $DIR
6
7 echo "Downloading from: http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/"
8 CHEMNITZ=de-en.txt
9 #curl --remote-name http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/${CHEMNITZ}.gz
10 #gunzip ${CHEMNITZ}.gz
11 #mv ${CHEMNITZ} inputs/
12
13 echo "Note that unzipping is slow."
14
15 L=en
16 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
17 WIKI=${L}wiktionary-20120109-pages-articles.xml
18 #curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120109/${WIKI}.bz2
19 #bunzip2 ${WIKI}.bz2
20 #mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml
21
22 L=fr
23 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
24 WIKI=${L}wiktionary-20120106-pages-articles.xml
25 curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120106/${WIKI}.bz2
26 bunzip2 ${WIKI}.bz2
27 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml
28
29 L=it
30 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
31 WIKI=${L}wiktionary-20120110-pages-articles.xml
32 curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120110/${WIKI}.bz2
33 bunzip2 ${WIKI}.bz2
34 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml
35
36 L=de
37 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
38 WIKI=${L}wiktionary-20120111-pages-articles.xml
39 curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120111/${WIKI}.bz2
40 bunzip2 ${WIKI}.bz2
41 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml
42
43 L=es
44 echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/"
45 WIKI=${L}wiktionary-20120108-pages-articles.xml
46 curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120108/${WIKI}.bz2
47 bunzip2 ${WIKI}.bz2
48 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml
49
50 echo "Done.  Now run WiktionarySplitter to spit apart enwiktionary."
51
52 cd $OLD_DIR