Dear Wiki user, You have subscribed to a wiki page or wiki category on "Nutch Wiki" for change notification.
The "WritingPluginExample" page has been changed by LewisJohnMcgibbney: http://wiki.apache.org/nutch/WritingPluginExample?action=diff&rev1=19&rev2=20 {{{ <?xml version="1.0" encoding="UTF-8"?> <plugin - id="recommended" - name="Recommended Parser/Filter" + id="urlmeta" + name="URL Meta Indexing Filter" - version="0.0.1" + version="1.0.0" - provider-name="nutch.org"> + provider-name="sgonyea"> + <runtime> - <!-- As defined in build.xml this plugin will end up bundled as recommended.jar --> - <library name="recommended.jar"> + <library name="urlmeta.jar"> <export name="*"/> </library> </runtime> - <!-- The RecommendedParser extends the HtmlParseFilter to grab the contents of - any recommended meta tags --> - <extension id="org.apache.nutch.parse.recommended.recommendedfilter" - name="Recommended Parser" - point="org.apache.nutch.parse.HtmlParseFilter"> - <implementation id="RecommendedParser" - class="org.apache.nutch.parse.recommended.RecommendedParser"/> + <requires> + <import plugin="nutch-extensionpoints"/> + </requires> + + <extension id="org.apache.nutch.indexer.urlmeta" + name="URL Meta Indexing Filter" + point="org.apache.nutch.indexer.IndexingFilter"> + <implementation id="indexer-urlmeta" + class="org.apache.nutch.indexer.urlmeta.URLMetaIndexingFilter"/> </extension> + <extension id="org.apache.nutch.scoring.urlmeta" + name="URL Meta Scoring Filter" - - <!-- TheRecommendedIndexer extends the IndexingFilter in order to add the contents - of the recommended meta tags (as found by the RecommendedParser) to the lucene - index. --> - <extension id="org.apache.nutch.parse.recommended.recommendedindexer" - name="Recommended identifier filter" - point="org.apache.nutch.indexer.IndexingFilter"> + point="org.apache.nutch.scoring.ScoringFilter"> - <implementation id="RecommendedIndexer" - class="org.apache.nutch.parse.recommended.RecommendedIndexer"/> + <implementation id="scoring-urlmeta" + class="org.apache.nutch.scoring.urlmeta.URLMetaScoringFilter" /> </extension> - - <!-- The RecommendedQueryFilter gets called when you perform a search. It runs a - search for the user's query against the recommended fields. In order to get - add this to the list of filters that gets run by default, you have to use - "fields=DEFAULT". --> - <extension id="org.apache.nutch.parse.recommended.recommendedSearcher" - name="Recommended Search Query Filter" - point="org.apache.nutch.searcher.QueryFilter"> - <implementation id="RecommendedQueryFilter" - class="org.apache.nutch.parse.recommended.RecommendedQueryFilter" - fields="DEFAULT"/> - </extension> - </plugin> }}} + == Build.xml == In its simplest form: {{{ <?xml version="1.0"?> - <project name="recommended" default="jar"> + <project name="recommended" default="jar-core"> <import file="../build-plugin.xml"/> </project> }}} + == The HTML Parser Extension == This is the source code for the HTML Parser extension. It tries to grab the contents of the recommended meta tag and add them to the document being parsed.

