From 07793b9c94c9fcf75f6f1797b9999da0b876dbf2 Mon Sep 17 00:00:00 2001 From: Thad Hughes Date: Sat, 15 Dec 2012 15:34:20 -0800 Subject: [PATCH] Fixed URL encoding in goldens. --- data/downloadInputs.sh | 34 +- testdata/goldens/SingleLang_DE.quickdic.text | 1582 +++++------ testdata/goldens/SingleLang_EN.quickdic.text | 2430 ++++++++--------- testdata/goldens/SingleLang_IT.quickdic.text | 325 +-- testdata/goldens/testItConj.html | 2 +- .../wiktionary.WholeSection.DE.quickdic.text | 56 +- .../wiktionary.WholeSection.EN.quickdic.text | 2430 ++++++++--------- .../wiktionary.WholeSection.IT.quickdic.text | 1030 +++---- testdata/outputs/testItConj.html | 2 +- 9 files changed, 3949 insertions(+), 3942 deletions(-) diff --git a/data/downloadInputs.sh b/data/downloadInputs.sh index 5e7990f..9db64a0 100755 --- a/data/downloadInputs.sh +++ b/data/downloadInputs.sh @@ -8,42 +8,42 @@ echo "Note that unzipping is slow." L=en echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" -WIKI=${L}wiktionary-20120930-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120930/${WIKI}.bz2 -bunzip2 ${WIKI}.bz2 -mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +WIKI=${L}wiktionary-20121208-pages-articles.xml +#curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20121208/${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 ${CHEMNITZ} inputs/ +#curl --remote-name http://ftp.tu-chemnitz.de/pub/Local/urz/ding/de-en-devel/${CHEMNITZ}.gz +#gunzip ${CHEMNITZ}.gz +#mv ${CHEMNITZ} inputs/ L=fr echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" -WIKI=${L}wiktionary-20120926-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120926/${WIKI}.bz2 -bunzip2 ${WIKI}.bz2 -mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +WIKI=${L}wiktionary-20121204-pages-articles.xml +#curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20121204/${WIKI}.bz2 +#bunzip2 ${WIKI}.bz2 +#mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml L=it echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" -WIKI=${L}wiktionary-20120926-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120926/${WIKI}.bz2 +WIKI=${L}wiktionary-20121213-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20121213/${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-20120928-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120928/${WIKI}.bz2 +WIKI=${L}wiktionary-20121206-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20121206/${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-20120924-pages-articles.xml -curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20120924/${WIKI}.bz2 +WIKI=${L}wiktionary-20121210-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20121210/${WIKI}.bz2 bunzip2 ${WIKI}.bz2 mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml diff --git a/testdata/goldens/SingleLang_DE.quickdic.text b/testdata/goldens/SingleLang_DE.quickdic.text index 9f3d706..4e2ada4 100644 --- a/testdata/goldens/SingleLang_DE.quickdic.text +++ b/testdata/goldens/SingleLang_DE.quickdic.text @@ -18,8 +18,8 @@ HtmlEntry: Aal <<<

Bedeutungen

-

Verkleinerungsformen

-