Menu
▾
▴
[Archive-access-cvs] SF.net SVN: archive-access:[3607] tags/nutchwax-0_13-JIRA-WAX-75/archive/ src
|
From: <bi...@us...> - 2012-01-26 20:53:09
|
Revision: 3607
http://archive-access.svn.sourceforge.net/archive-access/?rev=3607&view=rev
Author: binzino
Date: 2012-01-26 20:53:00 +0000 (Thu, 26 Jan 2012)
Log Message:
-----------
Initial revision of NutchWAX custom version of parse-html plugin. Main diffs are not enforcing robots meta tag nor trying to process redirects.
Modified Paths:
--------------
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/plugin/build.xml
Added Paths:
-----------
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/build.xml
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/lib/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/lib/tagsoup-1.2.jar
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/lib/tagsoup.LICENSE.txt
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/plugin.xml
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/DOMBuilder.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/DOMContentUtils.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/HTMLMetaProcessor.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/HtmlParser.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/XMLCharacterRecognizer.java
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/plugin/build.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/plugin/build.xml 2012-01-26 20:51:04 UTC (rev 3606)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/plugin/build.xml 2012-01-26 20:53:00 UTC (rev 3607)
@@ -92,6 +92,7 @@
<ant dir="scoring-nutchwax" target="deploy" />
<ant dir="urlfilter-nutchwax" target="deploy" />
<ant dir="parse-pdf2" target="deploy" />
+ <ant dir="parse-html2" target="deploy" />
<ant dir="html-decorator" target="deploy" />
</target>
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/build.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/build.xml (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/build.xml 2012-01-26 20:53:00 UTC (rev 3607)
@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<!--
+ 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.
+-->
+<project name="parse-html2" default="jar-core">
+
+ <import file="../build-plugin.xml"/>
+
+</project>
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/lib/tagsoup-1.2.jar
===================================================================
(Binary files differ)
Property changes on: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/lib/tagsoup-1.2.jar
___________________________________________________________________
Added: svn:mime-type
+ application/octet-stream
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/lib/tagsoup.LICENSE.txt
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/lib/tagsoup.LICENSE.txt (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/lib/tagsoup.LICENSE.txt 2012-01-26 20:53:00 UTC (rev 3607)
@@ -0,0 +1,201 @@
+ Apache License
+ Version 2.0, January 2004
+ http://www.apache.org/licenses/
+
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+ 1. Definitions.
+
+ "License" shall mean the terms and conditions for use, reproduction,
+ and distribution as defined by Sections 1 through 9 of this document.
+
+ "Licensor" shall mean the copyright owner or entity authorized by
+ the copyright owner that is granting the License.
+
+ "Legal Entity" shall mean the union of the acting entity and all
+ other entities that control, are controlled by, or are under common
+ control with that entity. For the purposes of this definition,
+ "control" means (i) the power, direct or indirect, to cause the
+ direction or management of such entity, whether by contract or
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
+ outstanding shares, or (iii) beneficial ownership of such entity.
+
+ "You" (or "Your") shall mean an individual or Legal Entity
+ exercising permissions granted by this License.
+
+ "Source" form shall mean the preferred form for making modifications,
+ including but not limited to software source code, documentation
+ source, and configuration files.
+
+ "Object" form shall mean any form resulting from mechanical
+ transformation or translation of a Source form, including but
+ not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+ "Work" shall mean the work of authorship, whether in Source or
+ Object form, made available under the License, as indicated by a
+ copyright notice that is included in or attached to the work
+ (an example is provided in the Appendix below).
+
+ "Derivative Works" shall mean any work, whether in Source or Object
+ form, that is based on (or derived from) the Work and for which the
+ editorial revisions, annotations, elaborations, or other modifications
+ represent, as a whole, an original work of authorship. For the purposes
+ of this License, Derivative Works shall not include works that remain
+ separable from, or merely link (or bind by name) to the interfaces of,
+ the Work and Derivative Works thereof.
+
+ "Contribution" shall mean any work of authorship, including
+ the original version of the Work and any modifications or additions
+ to that Work or Derivative Works thereof, that is intentionally
+ submitted to Licensor for inclusion in the Work by the copyright owner
+ or by an individual or Legal Entity authorized to submit on behalf of
+ the copyright owner. For the purposes of this definition, "submitted"
+ means any form of electronic, verbal, or written communication sent
+ to the Licensor or its representatives, including but not limited to
+ communication on electronic mailing lists, source code control systems,
+ and issue tracking systems that are managed by, or on behalf of, the
+ Licensor for the purpose of discussing and improving the Work, but
+ excluding communication that is conspicuously marked or otherwise
+ designated in writing by the copyright owner as "Not a Contribution."
+
+ "Contributor" shall mean Licensor and any individual or Legal Entity
+ on behalf of whom a Contribution has been received by Licensor and
+ subsequently incorporated within the Work.
+
+ 2. Grant of Copyright License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ copyright license to reproduce, prepare Derivative Works of,
+ publicly display, publicly perform, sublicense, and distribute the
+ Work and such Derivative Works in Source or Object form.
+
+ 3. Grant of Patent License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ (except as stated in this section) patent license to make, have made,
+ use, offer to sell, sell, import, and otherwise transfer the Work,
+ where such license applies only to those patent claims licensable
+ by such Contributor that are necessarily infringed by their
+ Contribution(s) alone or by combination of their Contribution(s)
+ with the Work to which such Contribution(s) was submitted. If You
+ institute patent litigation against any entity (including a
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
+ or a Contribution incorporated within the Work constitutes direct
+ or contributory patent infringement, then any patent licenses
+ granted to You under this License for that Work shall terminate
+ as of the date such litigation is filed.
+
+ 4. Redistribution. You may reproduce and distribute copies of the
+ Work or Derivative Works thereof in any medium, with or without
+ modifications, and in Source or Object form, provided that You
+ meet the following conditions:
+
+ (a) You must give any other recipients of the Work or
+ Derivative Works a copy of this License; and
+
+ (b) You must cause any modified files to carry prominent notices
+ stating that You changed the files; and
+
+ (c) You must retain, in the Source form of any Derivative Works
+ that You distribute, all copyright, patent, trademark, and
+ attribution notices from the Source form of the Work,
+ excluding those notices that do not pertain to any part of
+ the Derivative Works; and
+
+ (d) If the Work includes a "NOTICE" text file as part of its
+ distribution, then any Derivative Works that You distribute must
+ include a readable copy of the attribution notices contained
+ within such NOTICE file, excluding those notices that do not
+ pertain to any part of the Derivative Works, in at least one
+ of the following places: within a NOTICE text file distributed
+ as part of the Derivative Works; within the Source form or
+ documentation, if provided along with the Derivative Works; or,
+ within a display generated by the Derivative Works, if and
+ wherever such third-party notices normally appear. The contents
+ of the NOTICE file are for informational purposes only and
+ do not modify the License. You may add Your own attribution
+ notices within Derivative Works that You distribute, alongside
+ or as an addendum to the NOTICE text from the Work, provided
+ that such additional attribution notices cannot be construed
+ as modifying the License.
+
+ You may add Your own copyright statement to Your modifications and
+ may provide additional or different license terms and conditions
+ for use, reproduction, or distribution of Your modifications, or
+ for any such Derivative Works as a whole, provided Your use,
+ reproduction, and distribution of the Work otherwise complies with
+ the conditions stated in this License.
+
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
+ any Contribution intentionally submitted for inclusion in the Work
+ by You to the Licensor shall be under the terms and conditions of
+ this License, without any additional terms or conditions.
+ Notwithstanding the above, nothing herein shall supersede or modify
+ the terms of any separate license agreement you may have executed
+ with Licensor regarding such Contributions.
+
+ 6. Trademarks. This License does not grant permission to use the trade
+ names, trademarks, service marks, or product names of the Licensor,
+ except as required for reasonable and customary use in describing the
+ origin of the Work and reproducing the content of the NOTICE file.
+
+ 7. Disclaimer of Warranty. Unless required by applicable law or
+ agreed to in writing, Licensor provides the Work (and each
+ Contributor provides its Contributions) on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+ implied, including, without limitation, any warranties or conditions
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+ PARTICULAR PURPOSE. You are solely responsible for determining the
+ appropriateness of using or redistributing the Work and assume any
+ risks associated with Your exercise of permissions under this License.
+
+ 8. Limitation of Liability. In no event and under no legal theory,
+ whether in tort (including negligence), contract, or otherwise,
+ unless required by applicable law (such as deliberate and grossly
+ negligent acts) or agreed to in writing, shall any Contributor be
+ liable to You for damages, including any direct, indirect, special,
+ incidental, or consequential damages of any character arising as a
+ result of this License or out of the use or inability to use the
+ Work (including but not limited to damages for loss of goodwill,
+ work stoppage, computer failure or malfunction, or any and all
+ other commercial damages or losses), even if such Contributor
+ has been advised of the possibility of such damages.
+
+ 9. Accepting Warranty or Additional Liability. While redistributing
+ the Work or Derivative Works thereof, You may choose to offer,
+ and charge a fee for, acceptance of support, warranty, indemnity,
+ or other liability obligations and/or rights consistent with this
+ License. However, in accepting such obligations, You may act only
+ on Your own behalf and on Your sole responsibility, not on behalf
+ of any other Contributor, and only if You agree to indemnify,
+ defend, and hold each Contributor harmless for any liability
+ incurred by, or claims asserted against, such Contributor by reason
+ of your accepting any such warranty or additional liability.
+
+ END OF TERMS AND CONDITIONS
+
+ APPENDIX: How to apply the Apache License to your work.
+
+ To apply the Apache License to your work, attach the following
+ boilerplate notice, with the fields enclosed by brackets "[]"
+ replaced with your own identifying information. (Don't include
+ the brackets!) The text should be enclosed in the appropriate
+ comment syntax for the file format. We also recommend that a
+ file or class name and description of purpose be included on the
+ same "printed page" as the copyright notice for easier
+ identification within third-party archives.
+
+ Copyright [yyyy] [name of copyright owner]
+
+ Licensed 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.
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/plugin.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/plugin.xml (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/plugin.xml 2012-01-26 20:53:00 UTC (rev 3607)
@@ -0,0 +1,47 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+ 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.
+-->
+<plugin
+ id="parse-html2"
+ name="NutchWAX Html Parse Plug-in"
+ version="1.0.0"
+ provider-name="archive.org">
+
+ <runtime>
+ <library name="parse-html2.jar">
+ <export name="*"/>
+ </library>
+ <library name="tagsoup-1.2.jar"/>
+ </runtime>
+
+ <requires>
+ <import plugin="nutch-extensionpoints"/>
+ </requires>
+
+ <extension id="org.archive.nutchwax.parse.html"
+ name="NutchWAX HTML Parser"
+ point="org.apache.nutch.parse.Parser">
+
+ <implementation id="org.archive.nutchwax.parse.html.HtmlParser"
+ class="org.archive.nutchwax.parse.html.HtmlParser">
+ <parameter name="contentType" value="text/html"/>
+ <parameter name="pathSuffix" value=""/>
+ </implementation>
+
+ </extension>
+
+</plugin>
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/DOMBuilder.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/DOMBuilder.java (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/DOMBuilder.java 2012-01-26 20:53:00 UTC (rev 3607)
@@ -0,0 +1,740 @@
+/*
+ * XXX ab...@ap...: This class is copied verbatim from Xalan-J 2.6.0
+ * XXX distribution, org.apache.xml.utils.DOMBuilder, in order to
+ * avoid dependency on Xalan.
+ */
+
+/*
+ * 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.
+ */
+/*
+ * $Id: DOMBuilder.java 823614 2009-10-09 17:02:32Z ab $
+ */
+package org.archive.nutchwax.parse.html;
+
+import java.util.Stack;
+
+import org.w3c.dom.Comment;
+import org.w3c.dom.Document;
+import org.w3c.dom.DocumentFragment;
+import org.w3c.dom.Element;
+import org.w3c.dom.Node;
+import org.w3c.dom.Text;
+import org.w3c.dom.CDATASection;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.ext.LexicalHandler;
+/**
+ * This class takes SAX events (in addition to some extra events
+ * that SAX doesn't handle yet) and adds the result to a document
+ * or document fragment.
+ */
+public class DOMBuilder
+ implements ContentHandler, LexicalHandler
+{
+
+ /** Root document */
+ public Document m_doc;
+
+ /** Current node */
+ protected Node m_currentNode = null;
+
+ /** First node of document fragment or null if not a DocumentFragment */
+ public DocumentFragment m_docFrag = null;
+
+ /** Vector of element nodes */
+ protected Stack m_elemStack = new Stack();
+
+ /**
+ * DOMBuilder instance constructor... it will add the DOM nodes
+ * to the document fragment.
+ *
+ * @param doc Root document
+ * @param node Current node
+ */
+ public DOMBuilder(Document doc, Node node)
+ {
+ m_doc = doc;
+ m_currentNode = node;
+ }
+
+ /**
+ * DOMBuilder instance constructor... it will add the DOM nodes
+ * to the document fragment.
+ *
+ * @param doc Root document
+ * @param docFrag Document fragment
+ */
+ public DOMBuilder(Document doc, DocumentFragment docFrag)
+ {
+ m_doc = doc;
+ m_docFrag = docFrag;
+ }
+
+ /**
+ * DOMBuilder instance constructor... it will add the DOM nodes
+ * to the document.
+ *
+ * @param doc Root document
+ */
+ public DOMBuilder(Document doc)
+ {
+ m_doc = doc;
+ }
+
+ /**
+ * Get the root node of the DOM being created. This
+ * is either a Document or a DocumentFragment.
+ *
+ * @return The root document or document fragment if not null
+ */
+ public Node getRootNode()
+ {
+ return (null != m_docFrag) ? (Node) m_docFrag : (Node) m_doc;
+ }
+
+ /**
+ * Get the node currently being processed.
+ *
+ * @return the current node being processed
+ */
+ public Node getCurrentNode()
+ {
+ return m_currentNode;
+ }
+
+ /**
+ * Return null since there is no Writer for this class.
+ *
+ * @return null
+ */
+ public java.io.Writer getWriter()
+ {
+ return null;
+ }
+
+ /**
+ * Append a node to the current container.
+ *
+ * @param newNode New node to append
+ */
+ protected void append(Node newNode) throws org.xml.sax.SAXException
+ {
+
+ Node currentNode = m_currentNode;
+
+ if (null != currentNode)
+ {
+ currentNode.appendChild(newNode);
+
+ // System.out.println(newNode.getNodeName());
+ }
+ else if (null != m_docFrag)
+ {
+ m_docFrag.appendChild(newNode);
+ }
+ else
+ {
+ boolean ok = true;
+ short type = newNode.getNodeType();
+
+ if (type == Node.TEXT_NODE)
+ {
+ String data = newNode.getNodeValue();
+
+ if ((null != data) && (data.trim().length() > 0))
+ {
+ throw new org.xml.sax.SAXException("Warning: can't output text before document element! Ignoring...");
+ }
+
+ ok = false;
+ }
+ else if (type == Node.ELEMENT_NODE)
+ {
+ if (m_doc.getDocumentElement() != null)
+ {
+ throw new org.xml.sax.SAXException("Can't have more than one root on a DOM!");
+ }
+ }
+
+ if (ok)
+ m_doc.appendChild(newNode);
+ }
+ }
+
+ /**
+ * Receive an object for locating the origin of SAX document events.
+ *
+ * <p>SAX parsers are strongly encouraged (though not absolutely
+ * required) to supply a locator: if it does so, it must supply
+ * the locator to the application by invoking this method before
+ * invoking any of the other methods in the ContentHandler
+ * interface.</p>
+ *
+ * <p>The locator allows the application to determine the end
+ * position of any document-related event, even if the parser is
+ * not reporting an error. Typically, the application will
+ * use this information for reporting its own errors (such as
+ * character content that does not match an application's
+ * business rules). The information returned by the locator
+ * is probably not sufficient for use with a search engine.</p>
+ *
+ * <p>Note that the locator will return correct information only
+ * during the invocation of the events in this interface. The
+ * application should not attempt to use it at any other time.</p>
+ *
+ * @param locator An object that can return the location of
+ * any SAX document event.
+ * @see org.xml.sax.Locator
+ */
+ public void setDocumentLocator(Locator locator)
+ {
+
+ // No action for the moment.
+ }
+
+ /**
+ * Receive notification of the beginning of a document.
+ *
+ * <p>The SAX parser will invoke this method only once, before any
+ * other methods in this interface or in DTDHandler (except for
+ * setDocumentLocator).</p>
+ */
+ public void startDocument() throws org.xml.sax.SAXException
+ {
+
+ // No action for the moment.
+ }
+
+ /**
+ * Receive notification of the end of a document.
+ *
+ * <p>The SAX parser will invoke this method only once, and it will
+ * be the last method invoked during the parse. The parser shall
+ * not invoke this method until it has either abandoned parsing
+ * (because of an unrecoverable error) or reached the end of
+ * input.</p>
+ */
+ public void endDocument() throws org.xml.sax.SAXException
+ {
+
+ // No action for the moment.
+ }
+
+ /**
+ * Receive notification of the beginning of an element.
+ *
+ * <p>The Parser will invoke this method at the beginning of every
+ * element in the XML document; there will be a corresponding
+ * endElement() event for every startElement() event (even when the
+ * element is empty). All of the element's content will be
+ * reported, in order, before the corresponding endElement()
+ * event.</p>
+ *
+ * <p>If the element name has a namespace prefix, the prefix will
+ * still be attached. Note that the attribute list provided will
+ * contain only attributes with explicit values (specified or
+ * defaulted): #IMPLIED attributes will be omitted.</p>
+ *
+ *
+ * @param ns The namespace of the node
+ * @param localName The local part of the qualified name
+ * @param name The element name.
+ * @param atts The attributes attached to the element, if any.
+ * @see #endElement
+ * @see org.xml.sax.Attributes
+ */
+ public void startElement(
+ String ns, String localName, String name, Attributes atts)
+ throws org.xml.sax.SAXException
+ {
+
+ Element elem;
+
+ // Note that the namespace-aware call must be used to correctly
+ // construct a Level 2 DOM, even for non-namespaced nodes.
+ if ((null == ns) || (ns.length() == 0))
+ elem = m_doc.createElementNS(null,name);
+ else
+ elem = m_doc.createElementNS(ns, name);
+
+ append(elem);
+
+ try
+ {
+ int nAtts = atts.getLength();
+
+ if (0 != nAtts)
+ {
+ for (int i = 0; i < nAtts; i++)
+ {
+
+ //System.out.println("type " + atts.getType(i) + " name " + atts.getLocalName(i) );
+ // First handle a possible ID attribute
+ if (atts.getType(i).equalsIgnoreCase("ID"))
+ setIDAttribute(atts.getValue(i), elem);
+
+ String attrNS = atts.getURI(i);
+
+ if("".equals(attrNS))
+ attrNS = null; // DOM represents no-namespace as null
+
+ // System.out.println("attrNS: "+attrNS+", localName: "+atts.getQName(i)
+ // +", qname: "+atts.getQName(i)+", value: "+atts.getValue(i));
+ // Crimson won't let us set an xmlns: attribute on the DOM.
+ String attrQName = atts.getQName(i);
+
+ // In SAX, xmlns: attributes have an empty namespace, while in DOM they should have the xmlns namespace
+ if (attrQName.startsWith("xmlns:"))
+ attrNS = "http://www.w3.org/2000/xmlns/";
+
+ // ALWAYS use the DOM Level 2 call!
+ elem.setAttributeNS(attrNS,attrQName, atts.getValue(i));
+ }
+ }
+
+ // append(elem);
+
+ m_elemStack.push(elem);
+
+ m_currentNode = elem;
+
+ // append(elem);
+ }
+ catch(java.lang.Exception de)
+ {
+ // de.printStackTrace();
+ throw new org.xml.sax.SAXException(de);
+ }
+
+ }
+
+ /**
+
+
+
+ * Receive notification of the end of an element.
+ *
+ * <p>The SAX parser will invoke this method at the end of every
+ * element in the XML document; there will be a corresponding
+ * startElement() event for every endElement() event (even when the
+ * element is empty).</p>
+ *
+ * <p>If the element name has a namespace prefix, the prefix will
+ * still be attached to the name.</p>
+ *
+ *
+ * @param ns the namespace of the element
+ * @param localName The local part of the qualified name of the element
+ * @param name The element name
+ */
+ public void endElement(String ns, String localName, String name)
+ throws org.xml.sax.SAXException
+ {
+ m_elemStack.pop();
+ m_currentNode = m_elemStack.isEmpty() ? null : (Node)m_elemStack.peek();
+ }
+
+ /**
+ * Set an ID string to node association in the ID table.
+ *
+ * @param id The ID string.
+ * @param elem The associated ID.
+ */
+ public void setIDAttribute(String id, Element elem)
+ {
+
+ // Do nothing. This method is meant to be overiden.
+ }
+
+ /**
+ * Receive notification of character data.
+ *
+ * <p>The Parser will call this method to report each chunk of
+ * character data. SAX parsers may return all contiguous character
+ * data in a single chunk, or they may split it into several
+ * chunks; however, all of the characters in any single event
+ * must come from the same external entity, so that the Locator
+ * provides useful information.</p>
+ *
+ * <p>The application must not attempt to read from the array
+ * outside of the specified range.</p>
+ *
+ * <p>Note that some parsers will report whitespace using the
+ * ignorableWhitespace() method rather than this one (validating
+ * parsers must do so).</p>
+ *
+ * @param ch The characters from the XML document.
+ * @param start The start position in the array.
+ * @param length The number of characters to read from the array.
+ * @see #ignorableWhitespace
+ * @see org.xml.sax.Locator
+ */
+ public void characters(char ch[], int start, int length) throws org.xml.sax.SAXException
+ {
+ if(isOutsideDocElem()
+ && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
+ return; // avoid DOM006 Hierarchy request error
+
+ if (m_inCData)
+ {
+ cdata(ch, start, length);
+
+ return;
+ }
+
+ String s = new String(ch, start, length);
+ Node childNode;
+ childNode = m_currentNode != null ? m_currentNode.getLastChild(): null;
+ if( childNode != null && childNode.getNodeType() == Node.TEXT_NODE ){
+ ((Text)childNode).appendData(s);
+ }
+ else{
+ Text text = m_doc.createTextNode(s);
+ append(text);
+ }
+ }
+
+ /**
+ * If available, when the disable-output-escaping attribute is used,
+ * output raw text without escaping. A PI will be inserted in front
+ * of the node with the name "lotusxsl-next-is-raw" and a value of
+ * "formatter-to-dom".
+ *
+ * @param ch Array containing the characters
+ * @param start Index to start of characters in the array
+ * @param length Number of characters in the array
+ */
+ public void charactersRaw(char ch[], int start, int length)
+ throws org.xml.sax.SAXException
+ {
+ if(isOutsideDocElem()
+ && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
+ return; // avoid DOM006 Hierarchy request error
+
+
+ String s = new String(ch, start, length);
+
+ append(m_doc.createProcessingInstruction("xslt-next-is-raw",
+ "formatter-to-dom"));
+ append(m_doc.createTextNode(s));
+ }
+
+ /**
+ * Report the beginning of an entity.
+ *
+ * The start and end of the document entity are not reported.
+ * The start and end of the external DTD subset are reported
+ * using the pseudo-name "[dtd]". All other events must be
+ * properly nested within start/end entity events.
+ *
+ * @param name The name of the entity. If it is a parameter
+ * entity, the name will begin with '%'.
+ * @see #endEntity
+ * @see org.xml.sax.ext.DeclHandler#internalEntityDecl
+ * @see org.xml.sax.ext.DeclHandler#externalEntityDecl
+ */
+ public void startEntity(String name) throws org.xml.sax.SAXException
+ {
+
+ // Almost certainly the wrong behavior...
+ // entityReference(name);
+ }
+
+ /**
+ * Report the end of an entity.
+ *
+ * @param name The name of the entity that is ending.
+ * @see #startEntity
+ */
+ public void endEntity(String name) throws org.xml.sax.SAXException{}
+
+ /**
+ * Receive notivication of a entityReference.
+ *
+ * @param name name of the entity reference
+ */
+ public void entityReference(String name) throws org.xml.sax.SAXException
+ {
+ append(m_doc.createEntityReference(name));
+ }
+
+ /**
+ * Receive notification of ignorable whitespace in element content.
+ *
+ * <p>Validating Parsers must use this method to report each chunk
+ * of ignorable whitespace (see the W3C XML 1.0 recommendation,
+ * section 2.10): non-validating parsers may also use this method
+ * if they are capable of parsing and using content models.</p>
+ *
+ * <p>SAX parsers may return all contiguous whitespace in a single
+ * chunk, or they may split it into several chunks; however, all of
+ * the characters in any single event must come from the same
+ * external entity, so that the Locator provides useful
+ * information.</p>
+ *
+ * <p>The application must not attempt to read from the array
+ * outside of the specified range.</p>
+ *
+ * @param ch The characters from the XML document.
+ * @param start The start position in the array.
+ * @param length The number of characters to read from the array.
+ * @see #characters
+ */
+ public void ignorableWhitespace(char ch[], int start, int length)
+ throws org.xml.sax.SAXException
+ {
+ if(isOutsideDocElem())
+ return; // avoid DOM006 Hierarchy request error
+
+ String s = new String(ch, start, length);
+
+ append(m_doc.createTextNode(s));
+ }
+
+ /**
+ * Tell if the current node is outside the document element.
+ *
+ * @return true if the current node is outside the document element.
+ */
+ private boolean isOutsideDocElem()
+ {
+ return (null == m_docFrag) && m_elemStack.size() == 0 && (null == m_currentNode || m_currentNode.getNodeType() == Node.DOCUMENT_NODE);
+ }
+
+ /**
+ * Receive notification of a processing instruction.
+ *
+ * <p>The Parser will invoke this method once for each processing
+ * instruction found: note that processing instructions may occur
+ * before or after the main document element.</p>
+ *
+ * <p>A SAX parser should never report an XML declaration (XML 1.0,
+ * section 2.8) or a text declaration (XML 1.0, section 4.3.1)
+ * using this method.</p>
+ *
+ * @param target The processing instruction target.
+ * @param data The processing instruction data, or null if
+ * none was supplied.
+ */
+ public void processingInstruction(String target, String data)
+ throws org.xml.sax.SAXException
+ {
+ append(m_doc.createProcessingInstruction(target, data));
+ }
+
+ /**
+ * Report an XML comment anywhere in the document.
+ *
+ * This callback will be used for comments inside or outside the
+ * document element, including comments in the external DTD
+ * subset (if read).
+ *
+ * @param ch An array holding the characters in the comment.
+ * @param start The starting position in the array.
+ * @param length The number of characters to use from the array.
+ */
+ public void comment(char ch[], int start, int length) throws org.xml.sax.SAXException
+ {
+ // tagsoup sometimes submits invalid values here
+ if (ch == null || start < 0 || length >= (ch.length - start) || length < 0) return;
+ append(m_doc.createComment(new String(ch, start, length)));
+ }
+
+ /** Flag indicating that we are processing a CData section */
+ protected boolean m_inCData = false;
+
+ /**
+ * Report the start of a CDATA section.
+ *
+ * @see #endCDATA
+ */
+ public void startCDATA() throws org.xml.sax.SAXException
+ {
+ m_inCData = true;
+ append(m_doc.createCDATASection(""));
+ }
+
+ /**
+ * Report the end of a CDATA section.
+ *
+ * @see #startCDATA
+ */
+ public void endCDATA() throws org.xml.sax.SAXException
+ {
+ m_inCData = false;
+ }
+
+ /**
+ * Receive notification of cdata.
+ *
+ * <p>The Parser will call this method to report each chunk of
+ * character data. SAX parsers may return all contiguous character
+ * data in a single chunk, or they may split it into several
+ * chunks; however, all of the characters in any single event
+ * must come from the same external entity, so that the Locator
+ * provides useful information.</p>
+ *
+ * <p>The application must not attempt to read from the array
+ * outside of the specified range.</p>
+ *
+ * <p>Note that some parsers will report whitespace using the
+ * ignorableWhitespace() method rather than this one (validating
+ * parsers must do so).</p>
+ *
+ * @param ch The characters from the XML document.
+ * @param start The start position in the array.
+ * @param length The number of characters to read from the array.
+ * @see #ignorableWhitespace
+ * @see org.xml.sax.Locator
+ */
+ public void cdata(char ch[], int start, int length) throws org.xml.sax.SAXException
+ {
+ if(isOutsideDocElem()
+ && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
+ return; // avoid DOM006 Hierarchy request error
+
+ String s = new String(ch, start, length);
+
+ // XXX ab...@ap...: modified from the original, to accomodate TagSoup.
+ Node n = m_currentNode.getLastChild();
+ if (n instanceof CDATASection)
+ ((CDATASection)n).appendData(s);
+ else if (n instanceof Comment)
+ ((Comment)n).appendData(s);
+ }
+
+ /**
+ * Report the start of DTD declarations, if any.
+ *
+ * Any declarations are assumed to be in the internal subset
+ * unless otherwise indicated.
+ *
+ * @param name The document type name.
+ * @param publicId The declared public identifier for the
+ * external DTD subset, or null if none was declared.
+ * @param systemId The declared system identifier for the
+ * external DTD subset, or null if none was declared.
+ * @see #endDTD
+ * @see #startEntity
+ */
+ public void startDTD(String name, String publicId, String systemId)
+ throws org.xml.sax.SAXException
+ {
+
+ // Do nothing for now.
+ }
+
+ /**
+ * Report the end of DTD declarations.
+ *
+ * @see #startDTD
+ */
+ public void endDTD() throws org.xml.sax.SAXException
+ {
+
+ // Do nothing for now.
+ }
+
+ /**
+ * Begin the scope of a prefix-URI Namespace mapping.
+ *
+ * <p>The information from this event is not necessary for
+ * normal Namespace processing: the SAX XML reader will
+ * automatically replace prefixes for element and attribute
+ * names when the http://xml.org/sax/features/namespaces
+ * feature is true (the default).</p>
+ *
+ * <p>There are cases, however, when applications need to
+ * use prefixes in character data or in attribute values,
+ * where they cannot safely be expanded automatically; the
+ * start/endPrefixMapping event supplies the information
+ * to the application to expand prefixes in those contexts
+ * itself, if necessary.</p>
+ *
+ * <p>Note that start/endPrefixMapping events are not
+ * guaranteed to be properly nested relative to each-other:
+ * all startPrefixMapping events will occur before the
+ * corresponding startElement event, and all endPrefixMapping
+ * events will occur after the corresponding endElement event,
+ * but their order is not guaranteed.</p>
+ *
+ * @param prefix The Namespace prefix being declared.
+ * @param uri The Namespace URI the prefix is mapped to.
+ * @see #endPrefixMapping
+ * @see #startElement
+ */
+ public void startPrefixMapping(String prefix, String uri)
+ throws org.xml.sax.SAXException
+ {
+
+ /*
+ // Not sure if this is needed or wanted
+ // Also, it fails in the stree.
+ if((null != m_currentNode)
+ && (m_currentNode.getNodeType() == Node.ELEMENT_NODE))
+ {
+ String qname;
+ if(((null != prefix) && (prefix.length() == 0))
+ || (null == prefix))
+ qname = "xmlns";
+ else
+ qname = "xmlns:"+prefix;
+
+ Element elem = (Element)m_currentNode;
+ String val = elem.getAttribute(qname); // Obsolete, should be DOM2...?
+ if(val == null)
+ {
+ elem.setAttributeNS("http://www.w3.org/XML/1998/namespace",
+ qname, uri);
+ }
+ }
+ */
+ }
+
+ /**
+ * End the scope of a prefix-URI mapping.
+ *
+ * <p>See startPrefixMapping for details. This event will
+ * always occur after the corresponding endElement event,
+ * but the order of endPrefixMapping events is not otherwise
+ * guaranteed.</p>
+ *
+ * @param prefix The prefix that was being mapping.
+ * @see #startPrefixMapping
+ * @see #endElement
+ */
+ public void endPrefixMapping(String prefix) throws org.xml.sax.SAXException{}
+
+ /**
+ * Receive notification of a skipped entity.
+ *
+ * <p>The Parser will invoke this method once for each entity
+ * skipped. Non-validating processors may skip entities if they
+ * have not seen the declarations (because, for example, the
+ * entity was declared in an external DTD subset). All processors
+ * may skip external entities, depending on the values of the
+ * http://xml.org/sax/features/external-general-entities and the
+ * http://xml.org/sax/features/external-parameter-entities
+ * properties.</p>
+ *
+ * @param name The name of the skipped entity. If it is a
+ * parameter entity, the name will begin with '%'.
+ */
+ public void skippedEntity(String name) throws org.xml.sax.SAXException{}
+}
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/DOMContentUtils.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/DOMContentUtils.java (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/DOMContentUtils.java 2012-01-26 20:53:00 UTC (rev 3607)
@@ -0,0 +1,419 @@
+/**
+ * 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.archive.nutchwax.parse.html;
+
+import java.net.URL;
+import java.net.MalformedURLException;
+import java.util.Collection;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.Stack;
+
+import org.apache.nutch.parse.Outlink;
+import org.apache.nutch.util.NodeWalker;
+import org.apache.hadoop.conf.Configuration;
+
+import org.w3c.dom.*;
+
+/**
+ * A collection of methods for extracting content from DOM trees.
+ *
+ * This class holds a few utility methods for pulling content out of
+ * DOM nodes, such as getOutlinks, getText, etc.
+ *
+ */
+public class DOMContentUtils {
+
+ public static class LinkParams {
+ public String elName;
+ public String attrName;
+ public int childLen;
+
+ public LinkParams(String elName, String attrName, int childLen) {
+ this.elName = elName;
+ this.attrName = attrName;
+ this.childLen = childLen;
+ }
+
+ public String toString() {
+ return "LP[el=" + elName + ",attr=" + attrName + ",len=" + childLen + "]";
+ }
+ }
+
+ private HashMap linkParams = new HashMap();
+ private Configuration conf;
+
+ public DOMContentUtils(Configuration conf) {
+ setConf(conf);
+ }
+
+ public void setConf(Configuration conf) {
+ // forceTags is used to override configurable tag ignoring, later on
+ Collection<String> forceTags = new ArrayList<String>(1);
+
+ this.conf = conf;
+ linkParams.clear();
+ linkParams.put("a", new LinkParams("a", "href", 1));
+ linkParams.put("area", new LinkParams("area", "href", 0));
+ if (conf.getBoolean("parser.html.form.use_action", true)) {
+ linkParams.put("form", new LinkParams("form", "action", 1));
+ if (conf.get("parser.html.form.use_action") != null)
+ forceTags.add("form");
+ }
+ linkParams.put("frame", new LinkParams("frame", "src", 0));
+ linkParams.put("iframe", new LinkParams("iframe", "src", 0));
+ linkParams.put("script", new LinkParams("script", "src", 0));
+ linkParams.put("link", new LinkParams("link", "href", 0));
+ linkParams.put("img", new LinkParams("img", "src", 0));
+
+ // remove unwanted link tags from the linkParams map
+ String[] ignoreTags = conf.getStrings("parser.html.outlinks.ignore_tags");
+ for ( int i = 0 ; ignoreTags != null && i < ignoreTags.length ; i++ ) {
+ if ( ! forceTags.contains(ignoreTags[i]) )
+ linkParams.remove(ignoreTags[i]);
+ }
+ }
+
+ /**
+ * This method takes a {@link StringBuffer} and a DOM {@link Node},
+ * and will append all the content text found beneath the DOM node to
+ * the <code>StringBuffer</code>.
+ *
+ * <p>
+ *
+ * If <code>abortOnNestedAnchors</code> is true, DOM traversal will
+ * be aborted and the <code>StringBuffer</code> will not contain
+ * any text encountered after a nested anchor is found.
+ *
+ * <p>
+ *
+ * @return true if nested anchors were found
+ */
+ public boolean getText(StringBuffer sb, Node node,
+ boolean abortOnNestedAnchors) {
+ if (getTextHelper(sb, node, abortOnNestedAnchors, 0)) {
+ return true;
+ }
+ return false;
+ }
+
+
+ /**
+ * This is a convinience method, equivalent to {@link
+ * #getText(StringBuffer,Node,boolean) getText(sb, node, false)}.
+ *
+ */
+ public void getText(StringBuffer sb, Node node) {
+ getText(sb, node, false);
+ }
+
+ // returns true if abortOnNestedAnchors is true and we find nested
+ // anchors
+ private boolean getTextHelper(StringBuffer sb, Node node,
+ boolean abortOnNestedAnchors,
+ int anchorDepth) {
+ boolean abort = false;
+ NodeWalker walker = new NodeWalker(node);
+
+ while (walker.hasNext()) {
+
+ Node currentNode = walker.nextNode();
+ String nodeName = currentNode.getNodeName();
+ short nodeType = currentNode.getNodeType();
+
+ if ("script".equalsIgnoreCase(nodeName)) {
+ walker.skipChildren();
+ }
+ if ("style".equalsIgnoreCase(nodeName)) {
+ walker.skipChildren();
+ }
+ if (abortOnNestedAnchors && "a".equalsIgnoreCase(nodeName)) {
+ anchorDepth++;
+ if (anchorDepth > 1) {
+ abort = true;
+ break;
+ }
+ }
+ if (nodeType == Node.COMMENT_NODE) {
+ walker.skipChildren();
+ }
+ if (nodeType == Node.TEXT_NODE) {
+ // cleanup and trim the value
+ String text = currentNode.getNodeValue();
+ text = text.replaceAll("\\s+", " ");
+ text = text.trim();
+ if (text.length() > 0) {
+ if (sb.length() > 0) sb.append(' ');
+ sb.append(text);
+ }
+ }
+ }
+
+ return abort;
+ }
+
+ /**
+ * This method takes a {@link StringBuffer} and a DOM {@link Node},
+ * and will append the content text found beneath the first
+ * <code>title</code> node to the <code>StringBuffer</code>.
+ *
+ * @return true if a title node was found, false otherwise
+ */
+ public boolean getTitle(StringBuffer sb, Node node) {
+
+ NodeWalker walker = new NodeWalker(node);
+
+ while (walker.hasNext()) {
+
+ Node currentNode = walker.nextNode();
+ String nodeName = currentNode.getNodeName();
+ short nodeType = currentNode.getNodeType();
+
+ if ("body".equalsIgnoreCase(nodeName)) { // stop after HEAD
+ return false;
+ }
+
+ if (nodeType == Node.ELEMENT_NODE) {
+ if ("title".equalsIgnoreCase(nodeName)) {
+ getText(sb, currentNode);
+ return true;
+ }
+ }
+ }
+
+ return false;
+ }
+
+ /** If Node contains a BASE tag then it's HREF is returned. */
+ public URL getBase(Node node) {
+
+ NodeWalker walker = new NodeWalker(node);
+
+ while (walker.hasNext()) {
+
+ Node currentNode = walker.nextNode();
+ String nodeName = currentNode.getNodeName();
+ short nodeType = currentNode.getNodeType();
+
+ // is this node a BASE tag?
+ if (nodeType == Node.ELEMENT_NODE) {
+
+ if ("body".equalsIgnoreCase(nodeName)) { // stop after HEAD
+ return null;
+ }
+
+ if ("base".equalsIgnoreCase(nodeName)) {
+ NamedNodeMap attrs = currentNode.getAttributes();
+ for (int i= 0; i < attrs.getLength(); i++ ) {
+ Node attr = attrs.item(i);
+ if ("href".equalsIgnoreCase(attr.getNodeName())) {
+ try {
+ return new URL(attr.getNodeValue());
+ } catch (MalformedURLException e) {}
+ }
+ }
+ }
+ }
+ }
+
+ // no.
+ return null;
+ }
+
+
+ private boolean hasOnlyWhiteSpace(Node node) {
+ String val= node.getNodeValue();
+ for (int i= 0; i < val.length(); i++) {
+ if (!Character.isWhitespace(val.charAt(i)))
+ return false;
+ }
+ return true;
+ }
+
+ // this only covers a few cases of empty links that are symptomatic
+ // of nekohtml's DOM-fixup process...
+ private boolean shouldThrowAwayLink(Node node, NodeList children,
+ int childLen, LinkParams params) {
+ if (childLen == 0) {
+ // this has no inner structure
+ if (params.childLen == 0) return false;
+ else return true;
+ } else if ((childLen == 1)
+ && (children.item(0).getNodeType() == Node.ELEMENT_NODE)
+ && (params.elName.equalsIgnoreCase(children.item(0).getNodeName()))) {
+ // single nested link
+ return true;
+
+ } else if (childLen == 2) {
+
+ Node c0= children.item(0);
+ Node c1= children.item(1);
+
+ if ((c0.getNodeType() == Node.ELEMENT_NODE)
+ && (params.elName.equalsIgnoreCase(c0.getNodeName()))
+ && (c1.getNodeType() == Node.TEXT_NODE)
+ && hasOnlyWhiteSpace(c1) ) {
+ // single link followed by whitespace node
+ return true;
+ }
+
+ if ((c1.getNodeType() == Node.ELEMENT_NODE)
+ && (params.elName.equalsIgnoreCase(c1.getNodeName()))
+ && (c0.getNodeType() == Node.TEXT_NODE)
+ && hasOnlyWhiteSpace(c0) ) {
+ // whitespace node followed by single link
+ return true;
+ }
+
+ } else if (childLen == 3) {
+ Node c0= children.item(0);
+ Node c1= children.item(1);
+ Node c2= children.item(2);
+
+ if ((c1.getNodeType() == Node.ELEMENT_NODE)
+ && (params.elName.equalsIgnoreCase(c1.getNodeName()))
+ && (c0.getNodeType() == Node.TEXT_NODE)
+ && (c2.getNodeType() == Node.TEXT_NODE)
+ && hasOnlyWhiteSpace(c0)
+ && hasOnlyWhiteSpace(c2) ) {
+ // single link surrounded by whitespace nodes
+ return true;
+ }
+ }
+
+ return false;
+ }
+
+ /**
+ * Handles cases where the url param information is encoded into the base
+ * url as opposed to the target.
+ * <p>
+ * If the taget contains params (i.e. ';xxxx') information then the target
+ * params information is assumed to be correct and any base params information
+ * is ignored. If the base contains params information but the tareget does
+ * not, then the params information is moved to the target allowing it to be
+ * correctly determined by the java.net.URL class.
+ *
+ * @param base The base URL.
+ * @param target The target path from the base URL.
+ *
+ * @return URL A URL with the params information correctly encoded.
+ *
+ * @throws MalformedURLException If the url is not a well formed URL.
+ */
+ private URL fixEmbeddedParams(URL base, String target)
+ throws MalformedURLException{
+
+ // the target contains params information or the base doesn't then no
+ // conversion necessary, return regular URL
+ if (target.indexOf(';') >= 0 || base.toString().indexOf(';') == -1) {
+ return new URL(base, target);
+ }
+
+ // get the base url and it params information
+ String baseURL = base.toString();
+ int startParams = baseURL.indexOf(';');
+ String params = baseURL.substring(startParams);
+
+ // if the target has a query string then put the params information after
+ // any path but before the query string, otherwise just append to the path
+ int startQS = target.indexOf('?');
+ if (startQS >= 0) {
+ target = target.substring(0, startQS) + params +
+ target.substring(startQS);
+ }
+ else {
+ target += params;
+ }
+
+ return new URL(base, target);
+ }
+
+ /**
+ * This method finds all anchors below the supplied DOM
+ * <code>node</code>, and creates appropriate {@link Outlink}
+ * records for each (relative to the supplied <code>base</code>
+ * URL), and adds them to the <code>outlinks</code> {@link
+ * ArrayList}.
+ *
+ * <p>
+ *
+ * Links without inner structure (tags, text, etc) are discarded, as
+ * are links which contain only single nested links and empty text
+ * nodes (this is a common DOM-fixup artifact, at least with
+ * nekohtml).
+ */
+ public void getOutlinks(URL base, ArrayList outlinks,
+ Node node) {
+
+ NodeWalker walker = new NodeWalker(node);
+ while (walker.hasNext()) {
+
+ Node currentNode = walker.nextNode();
+ String nodeName = currentNode.getNodeName();
+ short nodeType = currentNode.getNodeType();
+ NodeList children = currentNode.getChildNodes();
+ int childLen = (children != null) ? children.getLength() : 0;
+
+ if (nodeType == Node.ELEMENT_NODE) {
+
+ nodeName = nodeName.toLowerCase();
+ LinkParams params = (LinkParams)linkParams.get(nodeName);
+ if (params != null) {
+ if (!shouldThrowAwayLink(currentNode, children, childLen, params)) {
+
+ StringBuffer linkText = new StringBuffer();
+ getText(linkText, currentNode, true);
+
+ NamedNodeMap attrs = currentNode.getAttributes();
+ String target = null;
+ boolean noFollow = false;
+ boolean post = false;
+ for (int i= 0; i < attrs.getLength(); i++ ) {
+ Node attr = attrs.item(i);
+ String attrName = attr.getNodeName();
+ if (params.attrName.equalsIgnoreCase(attrName)) {
+ target = attr.getNodeValue();
+ } else if ("rel".equalsIgnoreCase(attrName) &&
+ "nofollow".equalsIgnoreCase(attr.getNodeValue())) {
+ noFollow = true;
+ } else if ("method".equalsIgnoreCase(attrName) &&
+ "post".equalsIgnoreCase(attr.getNodeValue())) {
+ post = true;
+ }
+ }
+ if (target != null && !noFollow && !post)
+ try {
+
+ URL url = (base.toString().indexOf(';') > 0) ?
+ fixEmbeddedParams(base, target) : new URL(base, target);
+ outlinks.add(new Outlink(url.toString(),
+ linkText.toString().trim()));
+ } catch (MalformedURLException e) {
+ // don't care
+ }
+ }
+ // this should not have any children, skip them
+ if (params.childLen == 0) continue;
+ }
+ }
+ }
+ }
+
+}
+
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/HTMLMetaProcessor.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/HTMLMetaProcessor.java (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/parse-html2/src/java/org/archive/nutchwax/parse/html/HTMLMetaProcessor.java 2012-01-26 20:53:00 UTC (rev 3607)
@@ -0,0 +1,213 @@
+/**
+ * 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.archive.nutchwax.parse.html;
+
+import java.net.URL;
+
+import org.apache.nutch.parse.HTMLMetaTags;
+import org.w3c.dom.*;
+
+/**
+ * Class for parsing META Directives from DOM trees. This class
+ * handles specifically Robots META directives (all, none, nofollow,
+ * noindex), finding BASE HREF tags, and HTTP-EQUIV no-cache
+ * instructions. All meta directives are stored in a HTMLMetaTags instance.
+ */
+public class HTMLMetaProcessor {
+
+ /**
+ * Utility class with indicators for the robots directives "noindex"
+ * and "nofollow", and HTTP-EQUIV/no-cache
+ */
+
+ /**
+ * Sets the indicators in <code>robotsMeta</code> to appropriate
+ * values, based on any META tags found under the given
+ * <code>node</code>.
+ */
+ public static final void getMetaTags (
+ HTMLMetaTags metaTags, Node node, URL currURL) {
+
+ metaTags.reset();
+ getMetaTagsHelper(metaTags, node, currURL);
+ }
+
+ private static final void getMetaTagsHelper(
+ HTMLMetaTags metaTags, Node node, URL currURL) {
+
+ if (node.getNodeType() == Node.ELEMENT_NODE) {
+
+ if ("body".equalsIgnoreCase(node.getNodeName())) {
+ // META tags should not be under body
+ return;
+ }
+
+ if ("meta".equalsIgnoreCase(node.getNodeName())) {
+ NamedNodeMap attrs = node.getAttributes();
+ Node nameNode = null;
+ Node equivNode = null;
+ Node contentNode = null;
+ // Retrieves name, http-equiv and content attribues
+ for (int i=0; i<attrs.g...
[truncated message content] |
