X-Git-Url: http://gitweb.fperrin.net/?a=blobdiff_plain;f=data%2FdownloadInputs.sh;h=3135eb04bbd6f35ed20e1a6b9ebc548fd147e7a8;hb=7148490a04873235017badb0a42b01c80bf81fad;hp=c0cc8ee11ea90887daa271042459b0e1bd269db8;hpb=482bc692ba8274fdcd36efd8714aaedee778300a;p=DictionaryPC.git diff --git a/data/downloadInputs.sh b/data/downloadInputs.sh index c0cc8ee..3135eb0 100755 --- a/data/downloadInputs.sh +++ b/data/downloadInputs.sh @@ -2,52 +2,51 @@ OLD_DIR=`pwd` DIR=`dirname $0` - cd $DIR -echo "Downloading from: http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/" -CHEMNITZ=de-en.txt -#curl --remote-name http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/${CHEMNITZ}.gz -#gunzip ${CHEMNITZ}.gz -#mv ${CHEMNITZ} inputs/ - echo "Note that unzipping is slow." L=en echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" -WIKI=${L}wiktionary-20111224-pages-articles.xml -#curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20111224/${WIKI}.bz2 -#bunzip2 ${WIKI}.bz2 -#mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +WIKI=${L}wiktionary-latest-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 +bunzip2 ${WIKI}.bz2 +mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml + +echo "Downloading from: http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/" +CHEMNITZ=de-en.txt +curl --remote-name http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/${CHEMNITZ}.gz +gunzip ${CHEMNITZ}.gz +mv ${CHEMNITZ} inputs/de-en_chemnitz.txt L=fr echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" -WIKI=${L}wiktionary-20120106-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120106/${WIKI}.bz2 -bunzip2 ${WIKI}.bz2 +WIKI=${L}wiktionary-latest-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 +bunzip2 --force ${WIKI}.bz2 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml L=it echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" -WIKI=${L}wiktionary-20120110-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120110/${WIKI}.bz2 +WIKI=${L}wiktionary-latest-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 bunzip2 ${WIKI}.bz2 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml L=de echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" -WIKI=${L}wiktionary-20120111-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120111/${WIKI}.bz2 +WIKI=${L}wiktionary-latest-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 bunzip2 ${WIKI}.bz2 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml L=es echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" -WIKI=${L}wiktionary-20120108-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120108/${WIKI}.bz2 +WIKI=${L}wiktionary-latest-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 bunzip2 ${WIKI}.bz2 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml -echo "Done. Now run WiktionarySplitter to spit apart enwiktionary." +echo "Done. Now run WiktionarySplitter to split apart enwiktionary." cd $OLD_DIR