From: Thad Hughes Date: Sun, 16 Dec 2012 00:02:53 +0000 (-0800) Subject: Update to latest wiktionaries, update unit tests, der-top/mid/bottom. X-Git-Url: http://gitweb.fperrin.net/?p=DictionaryPC.git;a=commitdiff_plain;h=2bd62e0aab9c5ce70506cbd1b5de7b21feee1cf4 Update to latest wiktionaries, update unit tests, der-top/mid/bottom. --- diff --git a/data/downloadInputs.sh b/data/downloadInputs.sh index 9db64a0..442920a 100755 --- a/data/downloadInputs.sh +++ b/data/downloadInputs.sh @@ -9,22 +9,22 @@ echo "Note that unzipping is slow." L=en echo "Downloading from: http://dumps.wikimedia.org/${L}wiktionary/" WIKI=${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 +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=${L}wiktionary-20121204-pages-articles.xml -#curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20121204/${WIKI}.bz2 -#bunzip2 ${WIKI}.bz2 -#mv ${WIKI} inputs/${L}wiktionary-pages-articles.xml +curl --remote-name http://dumps.wikimedia.org/${L}wiktionary/20121204/${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/" diff --git a/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java b/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java index a0c04c5..361473e 100644 --- a/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java +++ b/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java @@ -268,13 +268,10 @@ public class WiktionarySplitter extends org.xml.sax.helpers.DefaultHandler { } } - public void parse(final File file) throws ParserConfigurationException, SAXException, IOException { final SAXParser parser = SAXParserFactoryImpl.newInstance().newSAXParser(); parser.parse(file, this); } - - } diff --git a/src/com/hughes/android/dictionary/parser/wiktionary/EnFunctionCallbacks.java b/src/com/hughes/android/dictionary/parser/wiktionary/EnFunctionCallbacks.java index 58ff72e..41ee89f 100644 --- a/src/com/hughes/android/dictionary/parser/wiktionary/EnFunctionCallbacks.java +++ b/src/com/hughes/android/dictionary/parser/wiktionary/EnFunctionCallbacks.java @@ -78,6 +78,10 @@ class EnFunctionCallbacks { callbacks.put("rel-mid3", callback); callbacks.put("rel-mid4", callback); callbacks.put("rel-bottom", callback); + callbacks.put("der-top", callback); + callbacks.put("der-mid", callback); + callbacks.put("der-mid3", callback); + callbacks.put("der-bottom", callback); callback = new AppendName(); callbacks.put("...", callback); diff --git a/testdata/goldens/SingleLang_DE.quickdic.text b/testdata/goldens/SingleLang_DE.quickdic.text index 4e2ada4..6ddeb4b 100644 --- a/testdata/goldens/SingleLang_DE.quickdic.text +++ b/testdata/goldens/SingleLang_DE.quickdic.text @@ -308,13 +308,13 @@ HtmlEntry: August <<<

Bedeutungen

+{Abkürzungen} +

Herkunft

-{Abkürzungen} -

Synonyme