X-Git-Url: http://gitweb.fperrin.net/?p=DictionaryPC.git;a=blobdiff_plain;f=data%2FdownloadInputs.sh;h=0929f63687146349e7ae8a5511183e31eeba9acb;hp=b5640b7778928fd1c1519fe42a65799f75fb89ad;hb=ee1dbfb669462305a1c07e4d804a90af79f5d39f;hpb=aad37bfcc3c1a1772d5fba894d7471c2b09b64ee diff --git a/data/downloadInputs.sh b/data/downloadInputs.sh index b5640b7..0929f63 100755 --- a/data/downloadInputs.sh +++ b/data/downloadInputs.sh @@ -10,49 +10,42 @@ L=en echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" WIKI=${L}wiktionary-latest-pages-articles.xml curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 -bunzip2 ${WIKI}.bz2 -mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2 echo "Downloading from: http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/" CHEMNITZ=de-en.txt curl -L --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 +mv ${CHEMNITZ}.gz inputs/de-en_chemnitz.txt.gz L=fr echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" WIKI=${L}wiktionary-latest-pages-articles.xml curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 -bunzip2 --force ${WIKI}.bz2 -mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2 L=it echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" WIKI=${L}wiktionary-latest-pages-articles.xml curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 -bunzip2 ${WIKI}.bz2 -mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2 L=de echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" WIKI=${L}wiktionary-latest-pages-articles.xml curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 -bunzip2 ${WIKI}.bz2 -mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2 L=es echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" WIKI=${L}wiktionary-latest-pages-articles.xml curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 -bunzip2 ${WIKI}.bz2 -mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2 L=pt echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" WIKI=${L}wiktionary-latest-pages-articles.xml curl -L --remote-name http://dumps.wikimedia.org/${L}wiktionary/latest/${WIKI}.bz2 -bunzip2 ${WIKI}.bz2 -mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +mv ${WIKI}.bz2 inputs/${L}wiktionary-pages-articles.xml.bz2 echo "Done. Now run WiktionarySplitter to split apart enwiktionary."