[
https://issues.apache.org/jira/browse/NUTCH-1129?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16321925#comment-16321925
]
ASF GitHub Bot commented on NUTCH-1129:
---------------------------------------
nmaro commented on a change in pull request #205: WIP: NUTCH-1129 microdata for
Nutch 1.x
URL: https://github.com/apache/nutch/pull/205#discussion_r160901970
##########
File path:
src/plugin/any23/src/java/org/apache/nutch/any23/Any23ParseFilter.java
##########
@@ -0,0 +1,175 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.nutch.any23;
+
+import java.io.*;
+import java.net.URISyntaxException;
+import java.nio.charset.Charset;
+import java.util.Set;
+import java.util.TreeSet;
+import java.util.Collections;
+
+import org.apache.any23.Any23;
+import org.apache.any23.extractor.ExtractionException;
+import org.apache.any23.writer.BenchmarkTripleHandler;
+import org.apache.any23.writer.NTriplesWriter;
+import org.apache.any23.writer.TripleHandler;
+import org.apache.any23.writer.TripleHandlerException;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.parse.HTMLMetaTags;
+import org.apache.nutch.parse.HtmlParseFilter;
+import org.apache.nutch.parse.Parse;
+import org.apache.nutch.parse.ParseResult;
+import org.apache.nutch.protocol.Content;
+import org.ccil.cowan.tagsoup.XMLWriter;
+import org.ccil.cowan.tagsoup.jaxp.SAXParserImpl;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import org.w3c.dom.DocumentFragment;
+import org.xml.sax.InputSource;
+import org.xml.sax.SAXException;
+import org.xml.sax.XMLReader;
+
+/**
+ * <p>This implementation of {@link org.apache.nutch.parse.HtmlParseFilter}
+ * uses the <a href="http://any23.apache.org";>Apache Any23</a> library
+ * for parsing and extracting structured data in RDF format from a
+ * variety of Web documents. The supported formats can be found at <a
href="http://any23.apache.org";>Apache Any23</a>.
+ * <p>In this implementation triples are written as Notation3 e.g.
+ * <code><http://www.bbc.co.uk/news/scotland/>
<http://iptc.org/std/rNews/2011-10-07#datePublished> "2014/03/31
13:53:03"@en-gb .</code>
+ * and triples are identified within output triple streams by the presence of
'\n'.
+ * The presence of the '\n' is a characteristic specific to N3 serialization
in Any23.
+ * In order to use another/other writers implementing the
+ * <a
href="http://any23.apache.org/apidocs/index.html?org/apache/any23/writer/TripleHandler.html";>TripleHandler</a>
+ * interface, we will most likely need to identify an alternative data
characteristic
+ * which we can use to split triples streams.</p>
+ * <p>
+ */
+public class Any23ParseFilter implements HtmlParseFilter {
+
+ /** Logging instance */
+ public static final Logger LOG =
LoggerFactory.getLogger(Any23ParseFilter.class);
+
+ private Configuration conf = null;
+
+ /**
+ * Constant identifier used as a Key for writing and reading
+ * triples to and from the metadata Map field.
+ */
+ public final static String ANY23_TRIPLES = "Any23-Triples";
+
+ public static final String ANY_23_EXTRACTORS_CONF = "any23.extractors";
+
+ private static class Any23Parser {
+
+ Set<String> triples = null;
+
+ Any23Parser(String url, String htmlContent, String... extractorNames)
throws TripleHandlerException {
+ triples = new TreeSet<String>();
+ try {
+ parse(url, htmlContent, extractorNames);
+ } catch (URISyntaxException e) {
+ throw new RuntimeException(e.getReason());
+ } catch (IOException e) {
+ e.printStackTrace();
+ }
+ }
+
+ /**
+ * Maintains a {@link java.util.Set} containing the triples
+ * @return a {@link java.util.Set} of triples.
+ */
+ private Set<String> getTriples() {
+ return triples;
+ }
+
+ private void parse(String url, String htmlContent, String...
extractorNames) throws URISyntaxException, IOException, TripleHandlerException {
+ Any23 any23 = new Any23(extractorNames);
+ any23.setMIMETypeDetector(null);
+
+ try {
+ // Fix input to avoid extraction error
(https://github.com/semarglproject/semargl/issues/37#issuecomment-69381281)
Review comment:
I'm going to ignore this within the scope of this merge request as we
already invested many hours into it.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
> Any23 Nutch plugin
> ------------------
>
> Key: NUTCH-1129
> URL: https://issues.apache.org/jira/browse/NUTCH-1129
> Project: Nutch
> Issue Type: New Feature
> Components: parser
> Reporter: Lewis John McGibbney
> Assignee: Lewis John McGibbney
> Priority: Minor
> Fix For: 2.5
>
> Attachments: NUTCH-1129.patch
>
>
> This plugin should build on the Any23 library to provide us with a plugin
> which extracts RDF data from HTTP and file resources. Although as of writing
> Any23 not part of the ASF, the project is working towards integration into
> the Apache Incubator. Once the project proves its value, this would be an
> excellent addition to the Nutch 1.X codebase.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
