You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@any23.apache.org by le...@apache.org on 2022/01/08 22:47:28 UTC
svn commit: r1896849 [27/33] - in /any23/site: ./ apidocs/ apidocs/org/apache/any23/ apidocs/org/apache/any23/class-use/ apidocs/org/apache/any23/cli/ apidocs/org/apache/any23/cli/class-use/ apidocs/org/apache/any23/configuration/ apidocs/org/apache/an...
Modified: any23/site/download.html
URL: http://svn.apache.org/viewvc/any23/site/download.html?rev=1896849&r1=1896848&r2=1896849&view=diff
==============================================================================
--- any23/site/download.html (original)
+++ any23/site/download.html Sat Jan 8 22:47:23 2022
@@ -1,267 +1,90 @@
<!DOCTYPE html>
<!--
- | Generated by Apache Maven Doxia at 2021-09-10
- | Rendered using Apache Maven Fluido Skin 1.3.0
+ | Generated by Apache Maven Doxia Site Renderer 1.9.2 from src/site/xdoc/download.xml.vm at 2022-01-08
+ | Rendered using Apache Maven Fluido Skin 1.10.0
-->
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
<head>
<meta charset="UTF-8" />
- <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+ <meta name="viewport" content="width=device-width, initial-scale=1" />
+ <meta name="generator" content="Apache Maven Doxia Site Renderer 1.9.2" />
<meta name="author" content="Apache Any23 Team" />
- <meta name="Date-Revision-yyyymmdd" content="20210910" />
- <meta http-equiv="Content-Language" content="en" />
<title>Apache Any23 – Apache Any23 - Download</title>
- <link rel="stylesheet" href="./css/apache-maven-fluido-1.3.0.min.css" />
+ <link rel="stylesheet" href="./css/apache-maven-fluido-1.10.0.min.css" />
<link rel="stylesheet" href="./css/site.css" />
<link rel="stylesheet" href="./css/print.css" media="print" />
+ <script src="./js/apache-maven-fluido-1.10.0.min.js"></script>
+ </head>
+ <body class="topBarDisabled">
+ <div class="container-fluid">
+ <header>
+ <div id="banner">
+ <div class="pull-left"><a href="index.html" id="bannerLeft"><img src="images/logo-any23.png" alt="Apache Any23: Anything to Triples"/></a></div>
+ <div class="pull-right"><a href="http://www.apache.org/" id="bannerRight"><img src="http://www.apache.org/images/feather-small.gif" alt="Apache Any23"/></a></div>
+ <div class="clear"><hr/></div>
+ </div>
-
- <script type="text/javascript" src="./js/apache-maven-fluido-1.3.0.min.js"></script>
-
-
- </head>
- <body class="topBarDisabled">
-
-
-
- <div class="container-fluid">
- <div id="banner">
- <div class="pull-left">
- <a href="index.html" id="bannerLeft">
- <img src="images/logo-any23.png" alt="Apache Any23: Anything to Triples"/>
- </a>
- </div>
- <div class="pull-right"> <a href="http://www.apache.org/" id="bannerRight">
- <img src="http://www.apache.org/images/feather-small.gif" alt="Apache Any23"/>
- </a>
- </div>
- <div class="clear"><hr/></div>
- </div>
-
- <div id="breadcrumbs">
- <ul class="breadcrumb">
-
-
- <li id="publishDate">Last Published: 2021-09-10</li>
- <li class="divider">|</li> <li id="projectVersion">Version: 2.6-SNAPSHOT</li>
-
-
-
-
- </ul>
- </div>
-
-
+ <div id="breadcrumbs">
+ <ul class="breadcrumb">
+ <li id="publishDate">Last Published: 2022-01-08<span class="divider">|</span>
+</li>
+ <li id="projectVersion">Version: 2.7-SNAPSHOT</li>
+ </ul>
+ </div>
+ </header>
<div class="row-fluid">
- <div id="leftColumn" class="span3">
+ <header id="leftColumn" class="span2">
+ <nav class="well sidebar-nav">
+ <ul class="nav nav-list">
+ <li class="nav-header">Apache Any23</li>
+ <li><a href="index.html" title="Introduction"><span class="none"></span>Introduction</a></li>
+ <li class="active"><a href="#"><span class="icon-chevron-down"></span>Downloads</a>
+ <ul class="nav nav-list">
+ <li><a href="download.html#Apache_Any23_Sources" title="Sources"><span class="none"></span>Sources</a></li>
+ <li><a href="download.html#Apache_Any23_Core" title="Core"><span class="none"></span>Core</a></li>
+ <li><a href="download.html#Basic_Crawler" title="Basic Crawler"><span class="none"></span>Basic Crawler</a></li>
+ <li><a href="download.html#HTML_Scraper" title="HTML Scraper"><span class="none"></span>HTML Scraper</a></li>
+ <li><a href="download.html#Office_Scraper" title="Office Scraper"><span class="none"></span>Office Scraper</a></li>
+ <li><a href="download.html#Apache_Any23_Service" title="Service"><span class="none"></span>Service</a></li>
+ </ul></li>
+ <li><a href="install.html" title="Install"><span class="none"></span>Install</a></li>
+ <li class="nav-header">Documentation</li>
+ <li><a href="getting-started.html" title="Getting Started"><span class="none"></span>Getting Started</a></li>
+ <li><a href="supported-formats.html" title="Supported Formats"><span class="none"></span>Supported Formats</a></li>
+ <li><a href="extractors.html" title="Extractors"><span class="none"></span>Extractors</a></li>
+ <li><a href="configuration.html" title="Configuration"><span class="none"></span>Configuration</a></li>
+ <li><a href="service.html" title="REST Service"><span class="none"></span>REST Service</a></li>
+ <li><a href="any23-plugins.html" title="Any23 Plugins"><span class="none"></span>Any23 Plugins</a></li>
+ <li><a href="apidocs/index.html" title="APIs Doc"><span class="none"></span>APIs Doc</a></li>
+ <li><a href="developers.html" title="Developers Guide"><span class="icon-chevron-right"></span>Developers Guide</a></li>
+ <li class="nav-header">Project Documentation</li>
+ <li><a href="project-info.html" title="Project Information"><span class="icon-chevron-right"></span>Project Information</a></li>
+ <li><a href="project-reports.html" title="Project Reports"><span class="icon-chevron-right"></span>Project Reports</a></li>
+ <li class="nav-header">Misc</li>
+ <li><a href="acknowledgements.html" title="Acknowledgements"><span class="none"></span>Acknowledgements</a></li>
+ <li><a href="poweredby.html" title="PoweredBy"><span class="none"></span>PoweredBy</a></li>
+ <li class="nav-header">ASF</li>
+ <li><a href="http://www.apache.org/foundation/how-it-works.html" class="externalLink" title="How Apache Works"><span class="none"></span>How Apache Works</a></li>
+ <li><a href="http://www.apache.org/foundation/" class="externalLink" title="Foundation"><span class="none"></span>Foundation</a></li>
+ <li><a href="http://www.apache.org/foundation/sponsorship.html" class="externalLink" title="Sponsoring Apache"><span class="none"></span>Sponsoring Apache</a></li>
+ <li><a href="http://www.apache.org/foundation/thanks.html" class="externalLink" title="Thanks"><span class="none"></span>Thanks</a></li>
+ </ul>
+ </nav>
<div class="well sidebar-nav">
-
-
- <ul class="nav nav-list">
- <li class="nav-header">Apache Any23</li>
-
- <li>
-
- <a href="index.html" title="Introduction">
- <i class="none"></i>
- Introduction</a>
- </li>
-
- <li class="active">
-
- <a href="#"><i class="icon-chevron-down"></i>Downloads</a>
- <ul class="nav nav-list">
-
- <li>
-
- <a href="download.html#Apache_Any23_Sources" title="Sources">
- <i class="none"></i>
- Sources</a>
- </li>
-
- <li>
-
- <a href="download.html#Apache_Any23_Core" title="Core">
- <i class="none"></i>
- Core</a>
- </li>
-
- <li>
-
- <a href="download.html#Basic_Crawler" title="Basic Crawler">
- <i class="none"></i>
- Basic Crawler</a>
- </li>
-
- <li>
-
- <a href="download.html#HTML_Scraper" title="HTML Scraper">
- <i class="none"></i>
- HTML Scraper</a>
- </li>
-
- <li>
-
- <a href="download.html#Office_Scraper" title="Office Scraper">
- <i class="none"></i>
- Office Scraper</a>
- </li>
-
- <li>
-
- <a href="download.html#Apache_Any23_Service" title="Service">
- <i class="none"></i>
- Service</a>
- </li>
- </ul>
- </li>
-
- <li>
-
- <a href="install.html" title="Install">
- <i class="none"></i>
- Install</a>
- </li>
- <li class="nav-header">Documentation</li>
-
- <li>
-
- <a href="getting-started.html" title="Getting Started">
- <i class="none"></i>
- Getting Started</a>
- </li>
-
- <li>
-
- <a href="supported-formats.html" title="Supported Formats">
- <i class="none"></i>
- Supported Formats</a>
- </li>
-
- <li>
-
- <a href="extractors.html" title="Extractors">
- <i class="none"></i>
- Extractors</a>
- </li>
-
- <li>
-
- <a href="configuration.html" title="Configuration">
- <i class="none"></i>
- Configuration</a>
- </li>
-
- <li>
-
- <a href="service.html" title="REST Service">
- <i class="none"></i>
- REST Service</a>
- </li>
-
- <li>
-
- <a href="any23-plugins.html" title="Any23 Plugins">
- <i class="none"></i>
- Any23 Plugins</a>
- </li>
-
- <li>
-
- <a href="apidocs/index.html" title="APIs Doc">
- <i class="none"></i>
- APIs Doc</a>
- </li>
-
- <li>
-
- <a href="developers.html" title="Developers Guide">
- <i class="icon-chevron-right"></i>
- Developers Guide</a>
- </li>
- <li class="nav-header">Project Documentation</li>
-
- <li>
-
- <a href="project-info.html" title="Project Information">
- <i class="icon-chevron-right"></i>
- Project Information</a>
- </li>
-
- <li>
-
- <a href="project-reports.html" title="Project Reports">
- <i class="icon-chevron-right"></i>
- Project Reports</a>
- </li>
- <li class="nav-header">Misc</li>
-
- <li>
-
- <a href="acknowledgements.html" title="Acknowledgements">
- <i class="none"></i>
- Acknowledgements</a>
- </li>
-
- <li>
-
- <a href="poweredby.html" title="PoweredBy">
- <i class="none"></i>
- PoweredBy</a>
- </li>
- <li class="nav-header">ASF</li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/how-it-works.html" class="externalLink" title="How Apache Works">
- <i class="none"></i>
- How Apache Works</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/" class="externalLink" title="Foundation">
- <i class="none"></i>
- Foundation</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/sponsorship.html" class="externalLink" title="Sponsoring Apache">
- <i class="none"></i>
- Sponsoring Apache</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/thanks.html" class="externalLink" title="Thanks">
- <i class="none"></i>
- Thanks</a>
- </li>
- </ul>
-
-
-
- <hr class="divider" />
-
- <div id="poweredBy">
- <div class="clear"></div>
- <div class="clear"></div>
- <div class="clear"></div>
- <a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy">
- <img class="builtBy" alt="Built by Maven" src="./images/logos/maven-feather.png" />
- </a>
- </div>
+ <hr />
+ <div id="poweredBy">
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <div class="clear"></div>
+<a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy"><img class="builtBy" alt="Built by Maven" src="./images/logos/maven-feather.png" /></a>
+ </div>
</div>
- </div>
-
-
- <div id="bodyColumn" class="span9" >
-
-
+ </header>
+ <main id="bodyColumn" class="span10" >
+
- <div class="section">
+ <section>
<h2><a name="Download_Apache_Any23"></a>Download Apache Any23</h2>
<p>Apache Any23 is distributed in several formats for your convenience. Use a source archive if you intend to build Apache Any23 yourself. Otherwise, simply pick a ready-made binary distribution and follow the installation instructions given inside the archives.</p>
@@ -276,22 +99,20 @@
<p>Apache Any23 is distributed under the <a class="externalLink" href="https://any23.apache.org/license.html"> Apache License, version 2.0</a>.</p>
-
-<div class="section">
+ <section>
<h3><a name="Apache_Any23_Maven_Artifacts"></a>Apache Any23 Maven Artifacts</h3>
-<p>You can use Any23 as a <a class="externalLink" href="https://maven.apache.org">Maven</a> dependency. See the most recent release artifacts on <a class="externalLink" href="https://search.maven.org/#search%7Cga%7C1%7Cg%3A%22org.apache.any23%22">Maven Central</a>. For example you could add the <tt>apache-any23-core</tt> artifact to your project POM as follows:</p>
- <tt>
+<p>You can use Any23 as a <a class="externalLink" href="https://maven.apache.org">Maven</a> dependency. See the most recent release artifacts on <a class="externalLink" href="https://search.maven.org/#search%7Cga%7C1%7Cg%3A%22org.apache.any23%22">Maven Central</a>. For example you could add the <code>apache-any23-core</code> artifact to your project POM as follows:</p>
+ <code>
<dependency><br />
    <groupId>org.apache.any23</groupId><br />
    <artifactId>apache-any23-core</artifactId><br />
-     <version>2.5</version><br />
+     <version>2.6</version><br />
</dependency>
- </tt>
- </div>
+ </code>
+ </section>
-
-<div class="section">
+ <section>
<h3><a name="Apache_Any23_Sources"></a>Apache Any23 Sources</h3>
<table border="0" class="table table-striped">
@@ -312,31 +133,30 @@
<tr class="b">
-<td>Apache Any23 2.5 (Source tar.gz)</td>
+<td>Apache Any23 2.6 (Source tar.gz)</td>
-<td><a class="externalLink" href="https://www.apache.org/dyn/closer.lua/any23/2.5/apache-any23-2.5-src.tar.gz"> apache-any23-2.5-src.tar.gz</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dyn/closer.lua/any23/2.6/apache-any23-2.6-src.tar.gz"> apache-any23-2.6-src.tar.gz</a></td>
-<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.5/apache-any23-2.5-src.tar.gz.asc"> apache-any23-2.5-src.tar.gz.asc</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.6/apache-any23-2.6-src.tar.gz.asc"> apache-any23-2.6-src.tar.gz.asc</a></td>
-<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.5/apache-any23-2.5-src.tar.gz.sha512"> apache-any23-2.5-src.tar.gz.sha512</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.6/apache-any23-2.6-src.tar.gz.sha512"> apache-any23-2.6-src.tar.gz.sha512</a></td>
</tr>
<tr class="a">
-<td>Apache Any23 2.5 (Source zip)</td>
+<td>Apache Any23 2.6 (Source zip)</td>
-<td><a class="externalLink" href="https://www.apache.org/dyn/closer.lua/any23/2.5/apache-any23-2.5-src.zip"> apache-any23-2.5-src.zip</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dyn/closer.lua/any23/2.6/apache-any23-2.6-src.zip"> apache-any23-2.6-src.zip</a></td>
-<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.5/apache-any23-2.5-src.zip.asc"> apache-any23-2.5-src.zip.asc</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.6/apache-any23-2.6-src.zip.asc"> apache-any23-2.6-src.zip.asc</a></td>
-<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.5/apache-any23-2.5-src.zip.sha512"> apache-any23-2.5-src.zip.sha512</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.6/apache-any23-2.6-src.zip.sha512"> apache-any23-2.6-src.zip.sha512</a></td>
</tr>
</tbody>
</table>
- </div>
+ </section>
-
-<div class="section">
+ <section>
<h3><a name="Apache_Any23_Command_Line_Interface"></a>Apache Any23 Command Line Interface</h3>
<table border="0" class="table table-striped">
@@ -357,35 +177,33 @@
<tr class="b">
-<td>Apache Any23 2.5 CLI (Binary tar.gz)</td>
+<td>Apache Any23 2.6 CLI (Binary tar.gz)</td>
-<td><a class="externalLink" href="https://www.apache.org/dyn/closer.lua/any23/2.5/apache-any23-cli-2.5.tar.gz"> apache-any23-cli-2.5.tar.gz</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dyn/closer.lua/any23/2.6/apache-any23-cli-2.6.tar.gz"> apache-any23-cli-2.6.tar.gz</a></td>
-<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.5/apache-any23-cli-2.5.tar.gz.asc"> apache-any23-cli-2.5.tar.gz.asc</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.6/apache-any23-cli-2.6.tar.gz.asc"> apache-any23-cli-2.6.tar.gz.asc</a></td>
-<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.5/apache-any23-cli-2.5.tar.gz.sha512"> apache-any23-cli-2.5.tar.gz.sha512</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.6/apache-any23-cli-2.6.tar.gz.sha512"> apache-any23-cli-2.6.tar.gz.sha512</a></td>
</tr>
<tr class="a">
-<td>Apache Any23 2.5 CLI (Binary zip)</td>
+<td>Apache Any23 2.6 CLI (Binary zip)</td>
-<td><a class="externalLink" href="https://www.apache.org/dyn/closer.lua/any23/2.5/apache-any23-cli-2.5.zip"> apache-any23-cli-2.5.zip</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dyn/closer.lua/any23/2.6/apache-any23-cli-2.6.zip"> apache-any23-cli-2.6.zip</a></td>
-<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.5/apache-any23-cli-2.5.zip.asc"> apache-any23-cli-2.5.zip.asc</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.6/apache-any23-cli-2.6.zip.asc"> apache-any23-cli-2.6.zip.asc</a></td>
-<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.5/apache-any23-cli-2.5.zip.sha512"> apache-any23-cli-2.5.zip.sha512</a></td>
+<td><a class="externalLink" href="https://www.apache.org/dist/any23/2.6/apache-any23-cli-2.6.zip.sha512"> apache-any23-cli-2.6.zip.sha512</a></td>
</tr>
</tbody>
</table>
- </div>
- </div>
+ </section>
+ </section>
-
-<div class="section">
+ <section>
<h2><a name="Apache_Any23_Plugins"></a>Apache Any23 Plugins</h2>
-
-<div class="section">
+ <section>
<h3><a name="plugins"></a>plugins</h3>
<p>Various plugins were made available for Any23 releases prior to 2.4. As of 2.4, this is not longer the case. Reasoning behind this relates to the size of the artifcts post introduction of the <a class="externalLink" href="https://github.com/apache/any23-plugins/tree/master/openie">Open Information Extraction (Open IE) module</a>. This grew the artifacts to ~1GB which became too large to distribute across the Apache global mirror network.</p>
@@ -393,15 +211,13 @@
<p>Any23 plugins can be obtained by <a class="externalLink" href="https://github.com/apache/any23-plugins">downloading and building from source</a>.</p>
<p>Plugin artifacts prior to 2.4 can be found in the <a class="externalLink" href="http://archive.apache.org/dist/any23/">Apache Any23 Artifact Archive</a>.</p>
- </div>
+ </section>
- </div>
+ </section>
-
-<div class="section">
+ <section>
<h2><a name="Apache_Any23_Service"></a>Apache Any23 Service</h2>
-
-<div class="section">
+ <section>
<h3><a name="WAR_packages"></a>WAR packages</h3>
<p>Various WAR artifacts were made available for Any23 releases prior to 2.2. Post 2.2, this is not longer the case. Reasoning behind this relates to the size of the WAR artifcts post introduction of the <a class="externalLink" href="https://github.com/apache/any23-plugins/tree/master/openie">Open Information Extraction (Open IE) module</a>. This grew the artifacts to ~1GB which became too large to distribute across the Apache global mirror network.</p>
@@ -411,58 +227,53 @@
<p>WAR artifacts prior to 2.2 can be found in the <a class="externalLink" href="http://archive.apache.org/dist/any23/">Apache Any23 Artifact Archive</a>.</p>
<p>For users merely wanting to see what the Any23 Service looks like and does, visit <b><a class="externalLink" href="http://any23.org"></a></b>.</p>
- </div>
- </div>
+ </section>
+ </section>
-
-<div class="section">
+ <section>
<h2><a name="Verify_Releases"></a>Verify Releases</h2>
-
-<div class="section">
+ <section>
<h3><a name="null"></a></h3>
<p>It is essential that you verify the integrity of the downloaded files using the PGP, and/or SHA signatures. published with every Any23 release. Please read <a class="externalLink" href="http://httpd.apache.org/dev/verification.html">Verifying Apache HTTP Server Releases</a> for more information on why you should verify our releases. We strongly recommend you verify your downloads with at least PGP Guidance for doing so is provided below.</p>
- </div>
-
-<div class="section">
+ </section>
+ <section>
<h3><a name="PGP_Signatures"></a>PGP Signatures</h3>
<p>The PGP signatures can be verified using PGP or GPG. First download the <a class="externalLink" href="https://www.apache.org/dist/any23/KEYS">KEYS</a> as well as the asc signature file for the relevant distribution. <b>N.B.</b> Make sure you get these files from the main distribution directory, rather than from a mirror. Then verify the signatures using the following example</p>
- <tt>$ gpg --import KEYS</tt><br />
- <tt>$ gpg --verify apache-any23-2.5-src.tar.gz.asc apache-any23-2.5-src.tar.gz</tt>
+ <code>$ gpg --import KEYS</code><br />
+ <code>$ gpg --verify apache-any23-2.6-src.tar.gz.asc apache-any23-2.6-src.tar.gz</code>
<p>The files in the most recent release are signed by Lewis John McGibbney (CODE SIGNING KEY) lewismc@apache.org 48BAEBF6</p>
- </div>
-
-<div class="section">
+ </section>
+ <section>
<h3><a name="SHA512_Signatures"></a>SHA512 Signatures</h3>
<p>Alternatively, you can verify the SHA512 signatures on the files. A unix program called md5 or md5sum is included in many unix distributions. Use the following example</p>
- <tt>$ sha512sum apache-any23-2.5-src.tar.gz</tt>
+ <code>$ sha512sum apache-any23-2.6-src.tar.gz</code>
-<p>... output should match the string in <b>apache-any23-2.5-src.tar.gz.sha512</b></p>
- </div>
- </div>
+<p>... output should match the string in <b>apache-any23-2.6-src.tar.gz.sha512</b></p>
+ </section>
+ </section>
- </div>
- </div>
- </div>
-
+ </main>
+ </div>
+ </div>
<hr/>
-
<footer>
- <div class="container-fluid">
- <div class="row span12">Copyright © 2010-2021
- <a href="https://www.apache.org/">The Apache Software Foundation</a>.
- All Rights Reserved.
-
+ <div class="container-fluid">
+ <div class="row-fluid">
+<div class="row span16">Apache Any23, Apache, the Apache feather logo, and the Apache Any23 project logos are trademarks of The Apache Software Foundation. All other marks mentioned may be trademarks or registered trademarks of their respective owners.
+ </div>
+ </div>
</div>
-
-
-
- </div>
</footer>
+<script>
+ if(anchors) {
+ anchors.add();
+ }
+</script>
</body>
</html>
Modified: any23/site/extractors.html
URL: http://svn.apache.org/viewvc/any23/site/extractors.html?rev=1896849&r1=1896848&r2=1896849&view=diff
==============================================================================
--- any23/site/extractors.html (original)
+++ any23/site/extractors.html Sat Jan 8 22:47:23 2022
@@ -1,223 +1,81 @@
<!DOCTYPE html>
<!--
- | Generated by Apache Maven Doxia at 2021-09-10
- | Rendered using Apache Maven Fluido Skin 1.3.0
+ | Generated by Apache Maven Doxia Site Renderer 1.9.2 from src/site/apt/extractors.apt at 2022-01-08
+ | Rendered using Apache Maven Fluido Skin 1.10.0
-->
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
<head>
<meta charset="UTF-8" />
- <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+ <meta name="viewport" content="width=device-width, initial-scale=1" />
+ <meta name="generator" content="Apache Maven Doxia Site Renderer 1.9.2" />
<meta name="author" content="The Apache Software Foundation" />
- <meta name="Date-Revision-yyyymmdd" content="20210910" />
- <meta http-equiv="Content-Language" content="en" />
<title>Apache Any23 – Apache Any23 - Extractors</title>
- <link rel="stylesheet" href="./css/apache-maven-fluido-1.3.0.min.css" />
+ <link rel="stylesheet" href="./css/apache-maven-fluido-1.10.0.min.css" />
<link rel="stylesheet" href="./css/site.css" />
<link rel="stylesheet" href="./css/print.css" media="print" />
+ <script src="./js/apache-maven-fluido-1.10.0.min.js"></script>
+ </head>
+ <body class="topBarDisabled">
+ <div class="container-fluid">
+ <header>
+ <div id="banner">
+ <div class="pull-left"><a href="index.html" id="bannerLeft"><img src="images/logo-any23.png" alt="Apache Any23: Anything to Triples"/></a></div>
+ <div class="pull-right"><a href="http://www.apache.org/" id="bannerRight"><img src="http://www.apache.org/images/feather-small.gif" alt="Apache Any23"/></a></div>
+ <div class="clear"><hr/></div>
+ </div>
-
- <script type="text/javascript" src="./js/apache-maven-fluido-1.3.0.min.js"></script>
-
-
- </head>
- <body class="topBarDisabled">
-
-
-
- <div class="container-fluid">
- <div id="banner">
- <div class="pull-left">
- <a href="index.html" id="bannerLeft">
- <img src="images/logo-any23.png" alt="Apache Any23: Anything to Triples"/>
- </a>
- </div>
- <div class="pull-right"> <a href="http://www.apache.org/" id="bannerRight">
- <img src="http://www.apache.org/images/feather-small.gif" alt="Apache Any23"/>
- </a>
- </div>
- <div class="clear"><hr/></div>
- </div>
-
- <div id="breadcrumbs">
- <ul class="breadcrumb">
-
-
- <li id="publishDate">Last Published: 2021-09-10</li>
- <li class="divider">|</li> <li id="projectVersion">Version: 2.6-SNAPSHOT</li>
-
-
-
-
- </ul>
- </div>
-
-
+ <div id="breadcrumbs">
+ <ul class="breadcrumb">
+ <li id="publishDate">Last Published: 2022-01-08<span class="divider">|</span>
+</li>
+ <li id="projectVersion">Version: 2.7-SNAPSHOT</li>
+ </ul>
+ </div>
+ </header>
<div class="row-fluid">
- <div id="leftColumn" class="span3">
+ <header id="leftColumn" class="span2">
+ <nav class="well sidebar-nav">
+ <ul class="nav nav-list">
+ <li class="nav-header">Apache Any23</li>
+ <li><a href="index.html" title="Introduction"><span class="none"></span>Introduction</a></li>
+ <li><a href="download.html" title="Downloads"><span class="icon-chevron-right"></span>Downloads</a></li>
+ <li><a href="install.html" title="Install"><span class="none"></span>Install</a></li>
+ <li class="nav-header">Documentation</li>
+ <li><a href="getting-started.html" title="Getting Started"><span class="none"></span>Getting Started</a></li>
+ <li><a href="supported-formats.html" title="Supported Formats"><span class="none"></span>Supported Formats</a></li>
+ <li class="active"><a href="#"><span class="none"></span>Extractors</a></li>
+ <li><a href="configuration.html" title="Configuration"><span class="none"></span>Configuration</a></li>
+ <li><a href="service.html" title="REST Service"><span class="none"></span>REST Service</a></li>
+ <li><a href="any23-plugins.html" title="Any23 Plugins"><span class="none"></span>Any23 Plugins</a></li>
+ <li><a href="apidocs/index.html" title="APIs Doc"><span class="none"></span>APIs Doc</a></li>
+ <li><a href="developers.html" title="Developers Guide"><span class="icon-chevron-right"></span>Developers Guide</a></li>
+ <li class="nav-header">Project Documentation</li>
+ <li><a href="project-info.html" title="Project Information"><span class="icon-chevron-right"></span>Project Information</a></li>
+ <li><a href="project-reports.html" title="Project Reports"><span class="icon-chevron-right"></span>Project Reports</a></li>
+ <li class="nav-header">Misc</li>
+ <li><a href="acknowledgements.html" title="Acknowledgements"><span class="none"></span>Acknowledgements</a></li>
+ <li><a href="poweredby.html" title="PoweredBy"><span class="none"></span>PoweredBy</a></li>
+ <li class="nav-header">ASF</li>
+ <li><a href="http://www.apache.org/foundation/how-it-works.html" class="externalLink" title="How Apache Works"><span class="none"></span>How Apache Works</a></li>
+ <li><a href="http://www.apache.org/foundation/" class="externalLink" title="Foundation"><span class="none"></span>Foundation</a></li>
+ <li><a href="http://www.apache.org/foundation/sponsorship.html" class="externalLink" title="Sponsoring Apache"><span class="none"></span>Sponsoring Apache</a></li>
+ <li><a href="http://www.apache.org/foundation/thanks.html" class="externalLink" title="Thanks"><span class="none"></span>Thanks</a></li>
+ </ul>
+ </nav>
<div class="well sidebar-nav">
-
-
- <ul class="nav nav-list">
- <li class="nav-header">Apache Any23</li>
-
- <li>
-
- <a href="index.html" title="Introduction">
- <i class="none"></i>
- Introduction</a>
- </li>
-
- <li>
-
- <a href="download.html" title="Downloads">
- <i class="icon-chevron-right"></i>
- Downloads</a>
- </li>
-
- <li>
-
- <a href="install.html" title="Install">
- <i class="none"></i>
- Install</a>
- </li>
- <li class="nav-header">Documentation</li>
-
- <li>
-
- <a href="getting-started.html" title="Getting Started">
- <i class="none"></i>
- Getting Started</a>
- </li>
-
- <li>
-
- <a href="supported-formats.html" title="Supported Formats">
- <i class="none"></i>
- Supported Formats</a>
- </li>
-
- <li class="active">
-
- <a href="#"><i class="none"></i>Extractors</a>
- </li>
-
- <li>
-
- <a href="configuration.html" title="Configuration">
- <i class="none"></i>
- Configuration</a>
- </li>
-
- <li>
-
- <a href="service.html" title="REST Service">
- <i class="none"></i>
- REST Service</a>
- </li>
-
- <li>
-
- <a href="any23-plugins.html" title="Any23 Plugins">
- <i class="none"></i>
- Any23 Plugins</a>
- </li>
-
- <li>
-
- <a href="apidocs/index.html" title="APIs Doc">
- <i class="none"></i>
- APIs Doc</a>
- </li>
-
- <li>
-
- <a href="developers.html" title="Developers Guide">
- <i class="icon-chevron-right"></i>
- Developers Guide</a>
- </li>
- <li class="nav-header">Project Documentation</li>
-
- <li>
-
- <a href="project-info.html" title="Project Information">
- <i class="icon-chevron-right"></i>
- Project Information</a>
- </li>
-
- <li>
-
- <a href="project-reports.html" title="Project Reports">
- <i class="icon-chevron-right"></i>
- Project Reports</a>
- </li>
- <li class="nav-header">Misc</li>
-
- <li>
-
- <a href="acknowledgements.html" title="Acknowledgements">
- <i class="none"></i>
- Acknowledgements</a>
- </li>
-
- <li>
-
- <a href="poweredby.html" title="PoweredBy">
- <i class="none"></i>
- PoweredBy</a>
- </li>
- <li class="nav-header">ASF</li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/how-it-works.html" class="externalLink" title="How Apache Works">
- <i class="none"></i>
- How Apache Works</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/" class="externalLink" title="Foundation">
- <i class="none"></i>
- Foundation</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/sponsorship.html" class="externalLink" title="Sponsoring Apache">
- <i class="none"></i>
- Sponsoring Apache</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/thanks.html" class="externalLink" title="Thanks">
- <i class="none"></i>
- Thanks</a>
- </li>
- </ul>
-
-
-
- <hr class="divider" />
-
- <div id="poweredBy">
- <div class="clear"></div>
- <div class="clear"></div>
- <div class="clear"></div>
- <a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy">
- <img class="builtBy" alt="Built by Maven" src="./images/logos/maven-feather.png" />
- </a>
- </div>
+ <hr />
+ <div id="poweredBy">
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <div class="clear"></div>
+<a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy"><img class="builtBy" alt="Built by Maven" src="./images/logos/maven-feather.png" /></a>
+ </div>
</div>
- </div>
-
-
- <div id="bodyColumn" class="span9" >
-
- <div class="section">
+ </header>
+ <main id="bodyColumn" class="span10" >
+<section>
<h2><a name="Apache_Any23_Extractors"></a>Apache Any23 Extractors</h2>
-<p>This page enlists all the Apache Any23 Extractors (see source code <a href="./apidocs/org/apache/any23/extractor/package-summary.html">package</a>).</p>
-<div class="section">
+<p>This page enlists all the Apache Any23 Extractors (see source code <a href="./apidocs/org/apache/any23/extractor/package-summary.html">package</a>).</p><section>
<h3><a name="Microformat_Extractors"></a>Microformat Extractors</h3>
<p>The following extractors refer to the <a class="externalLink" href="http://microformats.org/">Microformats specifications</a>.</p>
<p>Specific details about *Microformats* extractors can be found <a href="./dev-microformat-extractors.html">here</a>. In particular the *Microformats Nesting* representation policy is described <a href="./dev-microformat-extractors.html#microformat-nesting">here</a>.</p>
@@ -231,54 +89,46 @@
<p><a href="./apidocs/org/apache/any23/extractor/html/SpeciesExtractor.html">SpeciesExtractor</a></p>
<p><a href="./apidocs/org/apache/any23/extractor/html/LicenseExtractor.html">LicenseExtractor</a></p>
<p><a href="./apidocs/org/apache/any23/extractor/html/XFNExtractor.html">XFNExtractor</a></p>
-<p><a href="./apidocs/org/apache/any23/extractor/html/HRecipeExtractor.html">HRecipeExtractor</a></p></div>
-<div class="section">
+<p><a href="./apidocs/org/apache/any23/extractor/html/HRecipeExtractor.html">HRecipeExtractor</a></p></section><section>
<h3><a name="RDFa_.5B1.0_.2C_1.1.5D"></a>RDFa [1.0 , 1.1]</h3>
<p>The following extractors refer to the <a class="externalLink" href="http://www.w3.org/TR/rdfa-syntax/">RDFa 1.0</a> and <a class="externalLink" href="http://www.w3.org/TR/rdfa-core/">RDFa 1.1</a> specifications.</p>
-<p><a href="./apidocs/org/apache/any23/extractor/rdfa/RDFaExtractor.html">RDFaExtractor</a></p></div>
-<div class="section">
+<p><a href="./apidocs/org/apache/any23/extractor/rdfa/RDFaExtractor.html">RDFaExtractor</a></p></section><section>
<h3><a name="Microdata"></a>Microdata</h3>
<p>The following extractors refer to the <a class="externalLink" href="http://dev.w3.org/html5/md/">Microdata specifications</a>.</p>
-<p><a href="./apidocs/org/apache/any23/extractor/microdata/MicrodataExtractor.html">MicrodataExtractor</a></p></div>
-<div class="section">
+<p><a href="./apidocs/org/apache/any23/extractor/microdata/MicrodataExtractor.html">MicrodataExtractor</a></p></section><section>
<h3><a name="RDF"></a>RDF</h3>
<p><a href="./apidocs/org/apache/any23/extractor/rdf/RDFXMLExtractor.html">RDFXMLExtractor</a></p>
<p><a href="./apidocs/org/apache/any23/extractor/rdf/NQuadsExtractor.html">NQuadsExtractor</a></p>
<p><a href="./apidocs/org/apache/any23/extractor/rdf/TurtleExtractor.html">TurtleExtractor</a></p>
-<p><a href="./apidocs/org/apache/any23/extractor/rdf/NTriplesExtractor.html">NTriplesExtractor</a></p></div>
-<div class="section">
+<p><a href="./apidocs/org/apache/any23/extractor/rdf/NTriplesExtractor.html">NTriplesExtractor</a></p></section><section>
<h3><a name="Metadata_Extractors"></a>Metadata Extractors</h3>
<p><a href="./apidocs/org/apache/any23/extractor/html/TitleExtractor.html">TitleExtractor</a></p>
<p><a href="./apidocs/org/apache/any23/extractor/html/HTMLMetaExtractor.html">HTMLMetaExtractor</a></p>
<p><a href="./apidocs/org/apache/any23/extractor/html/HeadLinkExtractor.html">HeadLinkExtractor</a></p>
<p><a href="./apidocs/org/apache/any23/extractor/html/ICBMExtractor.html">ICBMExtractor</a></p>
-<p><a href="./apidocs/org/apache/any23/extractor/html/TurtleHTMLExtractor.html">TurtleHTMLExtractor</a></p></div>
-<div class="section">
+<p><a href="./apidocs/org/apache/any23/extractor/html/TurtleHTMLExtractor.html">TurtleHTMLExtractor</a></p></section><section>
<h3><a name="Content_Extractors"></a>Content Extractors</h3>
<p><a href="./apidocs/org/apache/any23/extractor/xpath/XPathExtractor.html">XPath Extractor</a> (<b>Experimental</b>)</p>
-<p><a href="./apidocs/org/apache/any23/extractor/csv/CSVExtractor.html">CSV Extractor</a> (See the extraction <a href="./dev-csv-extractor.html">algorithm</a>.)</p></div></div>
-<div class="section">
+<p><a href="./apidocs/org/apache/any23/extractor/csv/CSVExtractor.html">CSV Extractor</a> (See the extraction <a href="./dev-csv-extractor.html">algorithm</a>.)</p></section></section><section>
<h2><a name="Get_more_documentation"></a>Get more documentation</h2>
<p>It is possible to generate the list of all the available extractors invoking the following command:</p>
-<div class="source">
-<pre><any23-core>/bin$ any23tools ExtractorDocumentation -list</pre></div></div>
- </div>
- </div>
- </div>
-
+<div class="source"><pre class="prettyprint"><any23-core>/bin$ any23tools ExtractorDocumentation -list</pre></div></section>
+ </main>
+ </div>
+ </div>
<hr/>
-
<footer>
- <div class="container-fluid">
- <div class="row span12">Copyright © 2010-2021
- <a href="https://www.apache.org/">The Apache Software Foundation</a>.
- All Rights Reserved.
-
+ <div class="container-fluid">
+ <div class="row-fluid">
+<div class="row span16">Apache Any23, Apache, the Apache feather logo, and the Apache Any23 project logos are trademarks of The Apache Software Foundation. All other marks mentioned may be trademarks or registered trademarks of their respective owners.
+ </div>
+ </div>
</div>
-
-
-
- </div>
</footer>
+<script>
+ if(anchors) {
+ anchors.add();
+ }
+</script>
</body>
</html>
Modified: any23/site/getting-started.html
URL: http://svn.apache.org/viewvc/any23/site/getting-started.html?rev=1896849&r1=1896848&r2=1896849&view=diff
==============================================================================
--- any23/site/getting-started.html (original)
+++ any23/site/getting-started.html Sat Jan 8 22:47:23 2022
@@ -1,247 +1,103 @@
<!DOCTYPE html>
<!--
- | Generated by Apache Maven Doxia at 2021-09-10
- | Rendered using Apache Maven Fluido Skin 1.3.0
+ | Generated by Apache Maven Doxia Site Renderer 1.9.2 from src/site/apt/getting-started.apt at 2022-01-08
+ | Rendered using Apache Maven Fluido Skin 1.10.0
-->
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
<head>
<meta charset="UTF-8" />
- <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+ <meta name="viewport" content="width=device-width, initial-scale=1" />
+ <meta name="generator" content="Apache Maven Doxia Site Renderer 1.9.2" />
<meta name="author" content="The Apache Software Foundation" />
- <meta name="Date-Revision-yyyymmdd" content="20210910" />
- <meta http-equiv="Content-Language" content="en" />
<title>Apache Any23 – Apache Any23 - Getting started</title>
- <link rel="stylesheet" href="./css/apache-maven-fluido-1.3.0.min.css" />
+ <link rel="stylesheet" href="./css/apache-maven-fluido-1.10.0.min.css" />
<link rel="stylesheet" href="./css/site.css" />
<link rel="stylesheet" href="./css/print.css" media="print" />
+ <script src="./js/apache-maven-fluido-1.10.0.min.js"></script>
+ </head>
+ <body class="topBarDisabled">
+ <div class="container-fluid">
+ <header>
+ <div id="banner">
+ <div class="pull-left"><a href="index.html" id="bannerLeft"><img src="images/logo-any23.png" alt="Apache Any23: Anything to Triples"/></a></div>
+ <div class="pull-right"><a href="http://www.apache.org/" id="bannerRight"><img src="http://www.apache.org/images/feather-small.gif" alt="Apache Any23"/></a></div>
+ <div class="clear"><hr/></div>
+ </div>
-
- <script type="text/javascript" src="./js/apache-maven-fluido-1.3.0.min.js"></script>
-
-
- </head>
- <body class="topBarDisabled">
-
-
-
- <div class="container-fluid">
- <div id="banner">
- <div class="pull-left">
- <a href="index.html" id="bannerLeft">
- <img src="images/logo-any23.png" alt="Apache Any23: Anything to Triples"/>
- </a>
- </div>
- <div class="pull-right"> <a href="http://www.apache.org/" id="bannerRight">
- <img src="http://www.apache.org/images/feather-small.gif" alt="Apache Any23"/>
- </a>
- </div>
- <div class="clear"><hr/></div>
- </div>
-
- <div id="breadcrumbs">
- <ul class="breadcrumb">
-
-
- <li id="publishDate">Last Published: 2021-09-10</li>
- <li class="divider">|</li> <li id="projectVersion">Version: 2.6-SNAPSHOT</li>
-
-
-
-
- </ul>
- </div>
-
-
+ <div id="breadcrumbs">
+ <ul class="breadcrumb">
+ <li id="publishDate">Last Published: 2022-01-08<span class="divider">|</span>
+</li>
+ <li id="projectVersion">Version: 2.7-SNAPSHOT</li>
+ </ul>
+ </div>
+ </header>
<div class="row-fluid">
- <div id="leftColumn" class="span3">
+ <header id="leftColumn" class="span2">
+ <nav class="well sidebar-nav">
+ <ul class="nav nav-list">
+ <li class="nav-header">Apache Any23</li>
+ <li><a href="index.html" title="Introduction"><span class="none"></span>Introduction</a></li>
+ <li><a href="download.html" title="Downloads"><span class="icon-chevron-right"></span>Downloads</a></li>
+ <li><a href="install.html" title="Install"><span class="none"></span>Install</a></li>
+ <li class="nav-header">Documentation</li>
+ <li class="active"><a href="#"><span class="none"></span>Getting Started</a></li>
+ <li><a href="supported-formats.html" title="Supported Formats"><span class="none"></span>Supported Formats</a></li>
+ <li><a href="extractors.html" title="Extractors"><span class="none"></span>Extractors</a></li>
+ <li><a href="configuration.html" title="Configuration"><span class="none"></span>Configuration</a></li>
+ <li><a href="service.html" title="REST Service"><span class="none"></span>REST Service</a></li>
+ <li><a href="any23-plugins.html" title="Any23 Plugins"><span class="none"></span>Any23 Plugins</a></li>
+ <li><a href="apidocs/index.html" title="APIs Doc"><span class="none"></span>APIs Doc</a></li>
+ <li><a href="developers.html" title="Developers Guide"><span class="icon-chevron-right"></span>Developers Guide</a></li>
+ <li class="nav-header">Project Documentation</li>
+ <li><a href="project-info.html" title="Project Information"><span class="icon-chevron-right"></span>Project Information</a></li>
+ <li><a href="project-reports.html" title="Project Reports"><span class="icon-chevron-right"></span>Project Reports</a></li>
+ <li class="nav-header">Misc</li>
+ <li><a href="acknowledgements.html" title="Acknowledgements"><span class="none"></span>Acknowledgements</a></li>
+ <li><a href="poweredby.html" title="PoweredBy"><span class="none"></span>PoweredBy</a></li>
+ <li class="nav-header">ASF</li>
+ <li><a href="http://www.apache.org/foundation/how-it-works.html" class="externalLink" title="How Apache Works"><span class="none"></span>How Apache Works</a></li>
+ <li><a href="http://www.apache.org/foundation/" class="externalLink" title="Foundation"><span class="none"></span>Foundation</a></li>
+ <li><a href="http://www.apache.org/foundation/sponsorship.html" class="externalLink" title="Sponsoring Apache"><span class="none"></span>Sponsoring Apache</a></li>
+ <li><a href="http://www.apache.org/foundation/thanks.html" class="externalLink" title="Thanks"><span class="none"></span>Thanks</a></li>
+ </ul>
+ </nav>
<div class="well sidebar-nav">
-
-
- <ul class="nav nav-list">
- <li class="nav-header">Apache Any23</li>
-
- <li>
-
- <a href="index.html" title="Introduction">
- <i class="none"></i>
- Introduction</a>
- </li>
-
- <li>
-
- <a href="download.html" title="Downloads">
- <i class="icon-chevron-right"></i>
- Downloads</a>
- </li>
-
- <li>
-
- <a href="install.html" title="Install">
- <i class="none"></i>
- Install</a>
- </li>
- <li class="nav-header">Documentation</li>
-
- <li class="active">
-
- <a href="#"><i class="none"></i>Getting Started</a>
- </li>
-
- <li>
-
- <a href="supported-formats.html" title="Supported Formats">
- <i class="none"></i>
- Supported Formats</a>
- </li>
-
- <li>
-
- <a href="extractors.html" title="Extractors">
- <i class="none"></i>
- Extractors</a>
- </li>
-
- <li>
-
- <a href="configuration.html" title="Configuration">
- <i class="none"></i>
- Configuration</a>
- </li>
-
- <li>
-
- <a href="service.html" title="REST Service">
- <i class="none"></i>
- REST Service</a>
- </li>
-
- <li>
-
- <a href="any23-plugins.html" title="Any23 Plugins">
- <i class="none"></i>
- Any23 Plugins</a>
- </li>
-
- <li>
-
- <a href="apidocs/index.html" title="APIs Doc">
- <i class="none"></i>
- APIs Doc</a>
- </li>
-
- <li>
-
- <a href="developers.html" title="Developers Guide">
- <i class="icon-chevron-right"></i>
- Developers Guide</a>
- </li>
- <li class="nav-header">Project Documentation</li>
-
- <li>
-
- <a href="project-info.html" title="Project Information">
- <i class="icon-chevron-right"></i>
- Project Information</a>
- </li>
-
- <li>
-
- <a href="project-reports.html" title="Project Reports">
- <i class="icon-chevron-right"></i>
- Project Reports</a>
- </li>
- <li class="nav-header">Misc</li>
-
- <li>
-
- <a href="acknowledgements.html" title="Acknowledgements">
- <i class="none"></i>
- Acknowledgements</a>
- </li>
-
- <li>
-
- <a href="poweredby.html" title="PoweredBy">
- <i class="none"></i>
- PoweredBy</a>
- </li>
- <li class="nav-header">ASF</li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/how-it-works.html" class="externalLink" title="How Apache Works">
- <i class="none"></i>
- How Apache Works</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/" class="externalLink" title="Foundation">
- <i class="none"></i>
- Foundation</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/sponsorship.html" class="externalLink" title="Sponsoring Apache">
- <i class="none"></i>
- Sponsoring Apache</a>
- </li>
-
- <li>
-
- <a href="http://www.apache.org/foundation/thanks.html" class="externalLink" title="Thanks">
- <i class="none"></i>
- Thanks</a>
- </li>
- </ul>
-
-
-
- <hr class="divider" />
-
- <div id="poweredBy">
- <div class="clear"></div>
- <div class="clear"></div>
- <div class="clear"></div>
- <a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy">
- <img class="builtBy" alt="Built by Maven" src="./images/logos/maven-feather.png" />
- </a>
- </div>
+ <hr />
+ <div id="poweredBy">
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <div class="clear"></div>
+<a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy"><img class="builtBy" alt="Built by Maven" src="./images/logos/maven-feather.png" /></a>
+ </div>
</div>
- </div>
-
-
- <div id="bodyColumn" class="span9" >
-
- <div class="section">
+ </header>
+ <main id="bodyColumn" class="span10" >
+<section>
<h2><a name="Getting_started_with_Apache_Any23"></a>Getting started with <b>Apache Any23</b></h2>
<p><b>Apache Any23</b> can be used:</p>
<ul>
<li>via CLI (command line interface) from your preferred shell environment;</li>
<li>as a RESTful Webservice;</li>
-<li>as a library.</li></ul>
-<div class="section">
+<li>as a library.</li></ul><section>
<h3><a name="Apache_Any23_Modules"></a><b>Apache Any23</b> Modules</h3>
<p><b>Apache Any23</b> is composed of the following modules:</p>
<ul>
-<li><tt>api/</tt> The base API definitions e.g. The Any23 API.</li>
-<li><tt>core/</tt> The core library containing all extractor functionality.</li>
-<li><tt>cli/</tt> A command line interface enabling easy invocation of Any23 tools.</li>
-<li><tt>csvutils/</tt> Utility code for CSV extractions.</li>
-<li><tt>encoding/</tt> Characterset detection and encoding.</li>
-<li><tt>mime/</tt> Media-type detection.</li>
-<li><tt>service/</tt> The REST service.</li>
-<li><tt>plugins/</tt> The core additional plugins.</li>
-<li><tt>openie/</tt> Additional extractor logic for the <a class="externalLink" href="https://github.com/allenai/openie-standalone">Open Information Extraction (Open IE) system</a>.</li></ul></div>
-<div class="section">
+<li><code>api/</code> The base API definitions e.g. The Any23 API.</li>
+<li><code>core/</code> The core library containing all extractor functionality.</li>
+<li><code>cli/</code> A command line interface enabling easy invocation of Any23 tools.</li>
+<li><code>csvutils/</code> Utility code for CSV extractions.</li>
+<li><code>encoding/</code> Characterset detection and encoding.</li>
+<li><code>mime/</code> Media-type detection.</li>
+<li><code>service/</code> The REST service.</li>
+<li><code>plugins/</code> The core additional plugins.</li>
+<li><code>openie/</code> Additional extractor logic for the <a class="externalLink" href="https://github.com/allenai/openie-standalone">Open Information Extraction (Open IE) system</a>.</li></ul></section><section>
<h3><a name="Use_the_Apache_Any23_CLI"></a>Use the <b>Apache Any23</b> CLI</h3>
<p>The command-line tools support is provided by the <b>cli</b> module.</p>
-<p>Once <b>Apache Any23</b> has been correctly <a href="./install.html">installed</a>, if you want to use it as a command line tool, use the shell script within the <tt>cli/target/appassembler/bin/</tt> directory. These are provided both for Unix (Linux/OSX) and Windows.</p>
-<p>The <tt>any23</tt> script provides analysis, documentation, testing and debugging utilities.</p>
+<p>Once <b>Apache Any23</b> has been correctly <a href="./install.html">installed</a>, if you want to use it as a command line tool, use the shell script within the <code>cli/target/appassembler/bin/</code> directory. These are provided both for Unix (Linux/OSX) and Windows.</p>
+<p>The <code>any23</code> script provides analysis, documentation, testing and debugging utilities.</p>
<p>Simply running <i>./any23</i> without options will show the <i>usage</i> options.</p>
-<div class="source">
-<pre>$ cli/target/appassembler/bin/any23
+<div class="source"><pre class="prettyprint">$ cli/target/appassembler/bin/any23
A command must be specified.
Usage: any23 [options] [command] [command options]
@@ -319,105 +175,90 @@ Usage: any23 [options] [command] [comman
-f, --format
Vocabulary output format
Default: N-Quads (mimeTypes=application/n-quads, text/x-nquads, text/nquads; ext=nq)</pre></div>
-<p>The <tt>any23</tt> script detects a list of available utilities within the <b>core</b> and <b>plugins</b> classpath and allows to activate them.</p>
+<p>The <code>any23</code> script detects a list of available utilities within the <b>core</b> and <b>plugins</b> classpath and allows to activate them.</p>
<p>The <i>any23-core</i> CLI tools are:</p>
<ul>
-<li><tt>extractor</tt>: a utility for obtaining useful information about extractors.</li>
-<li><tt>microdata</tt>: commandline parser to extract specific Microdata content from a web page (local or remote) and produce a JSON output compliant with the Microdata specification (<a class="externalLink" href="http://www.w3.org/TR/microdata/">http://www.w3.org/TR/microdata/</a>).</li>
-<li><tt>mimes</tt>: detects the MIME Type for any HTTP / file / direct input resource.</li>
-<li><tt>verify</tt>: a utility for verifying <i>Apache Any23</i> plugins.</li>
-<li><tt>rover</tt>: the RDF extraction tool.</li>
-<li><tt>vocab</tt>: allows to dump all the <b>RDFSchema</b> vocabularies declared within Apache Any23.</li></ul>
-<div class="section">
+<li><code>extractor</code>: a utility for obtaining useful information about extractors.</li>
+<li><code>microdata</code>: commandline parser to extract specific Microdata content from a web page (local or remote) and produce a JSON output compliant with the Microdata specification (<a class="externalLink" href="http://www.w3.org/TR/microdata/">http://www.w3.org/TR/microdata/</a>).</li>
+<li><code>mimes</code>: detects the MIME Type for any HTTP / file / direct input resource.</li>
+<li><code>verify</code>: a utility for verifying <i>Apache Any23</i> plugins.</li>
+<li><code>rover</code>: the RDF extraction tool.</li>
+<li><code>vocab</code>: allows to dump all the <b>RDFSchema</b> vocabularies declared within Apache Any23.</li></ul><section>
<h4><a name="The_Rover_tool"></a>The Rover tool</h4>
<p>Rover is the main extraction tool. It allows to extract metadata from local and remote (HTTP) resources, specify a custom list of extractors, specify the desired output format and other flags to suppress noise and generate advanced reports.</p>
<p>Extract metadata from an <b>HTML</b> page:</p>
-<div class="source">
-<pre>cli$ any23 rover http://yourdomain/yourfile</pre></div>
+<div class="source"><pre class="prettyprint">cli$ any23 rover http://yourdomain/yourfile</pre></div>
<p>Extract metadata from a <b>local</b> resource:</p>
-<div class="source">
-<pre>cli$ any23 rover myfoaf.rdf</pre></div>
+<div class="source"><pre class="prettyprint">cli$ any23 rover myfoaf.rdf</pre></div>
<p>Specify the output format, use the option <b>"-f"</b> or <b>"--format"</b>: (Default output format is <b>TURTLE</b>).</p>
-<div class="source">
-<pre>cli$ any23 rover -f quad myfoaf.rdf</pre></div>
+<div class="source"><pre class="prettyprint">cli$ any23 rover -f quad myfoaf.rdf</pre></div>
<p>Filtering trivial statements</p>
<p>By default, <b>Apache Any23</b> will extract <i>HTML/head</i> meta information, such as links to <i>CSS stylesheets</i> or meta information like the author or the software used to create the <i>html</i>. Hence, if the user is only interested in the structured content from the <i>HTML/body</i> tag we offer a filter functionality, activated by the <b>"-t"</b> command line argument.</p>
-<div class="source">
-<pre>core$ any23 rover -t -f quad myfoaf.rdf</pre></div></div>
-<div class="section">
+<div class="source"><pre class="prettyprint">core$ any23 rover -t -f quad myfoaf.rdf</pre></div></section><section>
<h4><a name="The_ExtractorDocumentation_tool"></a>The ExtractorDocumentation tool</h4>
<p>The ExtractorDocumentation returns human readable information about the registered extractors.</p>
<p>List all the available extractors:</p>
-<div class="source">
-<pre>cli$ any23 extractor --list
- csv [org.apache.any23.extractor.csv.CSVExtractorFactory]
- html-embedded-jsonld [org.apache.any23.extractor.html.EmbeddedJSONLDExtractorFactory]
- html-head-icbm [org.apache.any23.extractor.html.ICBMExtractorFactory]
- html-head-links [org.apache.any23.extractor.html.HeadLinkExtractorFactory]
- html-head-meta [org.apache.any23.extractor.html.HTMLMetaExtractorFactory]
- html-head-title [org.apache.any23.extractor.html.TitleExtractorFactory]
- html-mf-adr [org.apache.any23.extractor.html.AdrExtractorFactory]
- html-mf-geo [org.apache.any23.extractor.html.GeoExtractorFactory]
- html-mf-hcalendar [org.apache.any23.extractor.html.HCalendarExtractorFactory]
- html-mf-hcard [org.apache.any23.extractor.html.HCardExtractorFactory]
- html-mf-hlisting [org.apache.any23.extractor.html.HListingExtractorFactory]
- html-mf-hrecipe [org.apache.any23.extractor.html.HRecipeExtractorFactory]
- html-mf-hresume [org.apache.any23.extractor.html.HResumeExtractorFactory]
- html-mf-hreview [org.apache.any23.extractor.html.HReviewExtractorFactory]
-html-mf-hreview-aggregate [org.apache.any23.extractor.html.HReviewAggregateExtractorFactory]
- html-mf-license [org.apache.any23.extractor.html.LicenseExtractorFactory]
- html-mf-species [org.apache.any23.extractor.html.SpeciesExtractorFactory]
- html-mf-xfn [org.apache.any23.extractor.html.XFNExtractorFactory]
- html-microdata [org.apache.any23.extractor.microdata.MicrodataExtractorFactory]
- html-rdfa11 [org.apache.any23.extractor.rdfa.RDFa11ExtractorFactory]
- html-xpath [org.apache.any23.extractor.xpath.XPathExtractorFactory]
- rdf-jsonld [org.apache.any23.extractor.rdf.JSONLDExtractorFactory]
- rdf-nq [org.apache.any23.extractor.rdf.NQuadsExtractorFactory]
- rdf-nt [org.apache.any23.extractor.rdf.NTriplesExtractorFactory]
- rdf-trix [org.apache.any23.extractor.rdf.TriXExtractorFactory]
- rdf-turtle [org.apache.any23.extractor.rdf.TurtleExtractorFactory]
- rdf-xml [org.apache.any23.extractor.rdf.RDFXMLExtractorFactory]
- yaml [org.apache.any23.extractor.yaml.YAMLExtractorFactory]</pre></div></div>
-<div class="section">
+<div class="source"><pre class="prettyprint">cli$ any23 extractor --list
+ csv [org.apache.any23.extractor.csv.CSVExtractorFactory] [text/csv;q=0.1]
+ html-embedded-jsonld [org.apache.any23.extractor.html.EmbeddedJSONLDExtractorFactory] [text/html;q=0.02, application/xhtml+xml;q=0.02]
+ html-head-icbm [org.apache.any23.extractor.html.ICBMExtractorFactory] [text/html;q=0.01, application/xhtml+xml;q=0.01]
+ html-head-links [org.apache.any23.extractor.html.HeadLinkExtractorFactory] [text/html;q=0.05, application/xhtml+xml;q=0.05]
+ html-head-meta [org.apache.any23.extractor.html.HTMLMetaExtractorFactory] [text/html;q=0.02, application/xhtml+xml;q=0.02]
+ html-head-title [org.apache.any23.extractor.html.TitleExtractorFactory] [text/html;q=0.02, application/xhtml+xml;q=0.02]
+ html-mf-adr [org.apache.any23.extractor.html.AdrExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-geo [org.apache.any23.extractor.html.GeoExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-hcalendar [org.apache.any23.extractor.html.HCalendarExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-hcard [org.apache.any23.extractor.html.HCardExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-hlisting [org.apache.any23.extractor.html.HListingExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-hrecipe [org.apache.any23.extractor.html.HRecipeExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-hresume [org.apache.any23.extractor.html.HResumeExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-hreview [org.apache.any23.extractor.html.HReviewExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+html-mf-hreview-aggregate [org.apache.any23.extractor.html.HReviewAggregateExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-license [org.apache.any23.extractor.html.LicenseExtractorFactory] [text/html;q=0.01, application/xhtml+xml;q=0.01]
+ html-mf-species [org.apache.any23.extractor.html.SpeciesExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-mf-xfn [org.apache.any23.extractor.html.XFNExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-microdata [org.apache.any23.extractor.microdata.MicrodataExtractorFactory] [text/html;q=0.1, application/xhtml+xml;q=0.1]
+ html-rdfa11 [org.apache.any23.extractor.rdfa.RDFa11ExtractorFactory] [application/xhtml+xml;q=0.3, application/html;q=0.3, text/html;q=0.3]
+ html-xpath [org.apache.any23.extractor.xpath.XPathExtractorFactory] [text/html;q=0.02, application/xhtml+xml;q=0.02]
+ ical [org.apache.any23.extractor.calendar.ICalExtractorFactory] [text/calendar]
+ jcal [org.apache.any23.extractor.calendar.JCalExtractorFactory] [application/calendar+json]
+ owl-functional [org.apache.any23.extractor.rdf.FunctionalSyntaxExtractorFactory] [text/owl-functional]
+ owl-manchester [org.apache.any23.extractor.rdf.ManchesterSyntaxExtractorFactory] [text/owl-manchester]
+ rdf-jsonld [org.apache.any23.extractor.rdf.JSONLDExtractorFactory] [application/ld+json;q=0.1]
+ rdf-nq [org.apache.any23.extractor.rdf.NQuadsExtractorFactory] [application/n-quads, text/x-nquads;q=0.1, text/rdf+nq;q=0.1, text/nq;q=0.1, text/nquads;q=0.1, text/n-quads;q=0.1]
+ rdf-nt [org.apache.any23.extractor.rdf.NTriplesExtractorFactory] [application/n-triples;q=0.1, text/nt;q=0.1, text/ntriples;q=0.1, text/plain;q=0.1]
+ rdf-trix [org.apache.any23.extractor.rdf.TriXExtractorFactory] [application/trix]
+ rdf-turtle [org.apache.any23.extractor.rdf.TurtleExtractorFactory] [text/turtle, text/rdf+n3, text/n3, application/n3, application/x-turtle, application/turtle]
+ rdf-xml [org.apache.any23.extractor.rdf.RDFXMLExtractorFactory] [application/rdf+xml, text/rdf, text/rdf+xml, application/rdf]
+ xcal [org.apache.any23.extractor.calendar.XCalExtractorFactory] [application/calendar+xml]
+ yaml [org.apache.any23.extractor.yaml.YAMLExtractorFactory] [text/x-yaml;q=0.5]</pre></div></section><section>
<h4><a name="The_MicrodataParser_tool"></a>The MicrodataParser tool</h4>
<p>The <i>MicrodataParser</i> tool allows to apply the only MicrodataExtractor on a specific input source and returns the extracted data in the JSON format declared in the Microdata specification section <a class="externalLink" href="http://www.w3.org/TR/microdata/#json">JSON</a>.</p>
-<div class="source">
-<pre>cli$ any23 microdata http://path/to/resource.html</pre></div></div>
-<div class="section">
+<div class="source"><pre class="prettyprint">cli$ any23 microdata http://path/to/resource.html</pre></div></section><section>
<h4><a name="The_VocabPrinter_tool"></a>The VocabPrinter tool</h4>
<p>The VocabPrinter Tool prints out the RDFSchema declared by all the <b>Apache Any23</b> declared vocabularies.</p>
<p>Just launch the command below to see all the managed vocabularies.</p>
-<div class="source">
-<pre>cli$ any23 vocab</pre></div>
-<p><i>NOTE</i>: <b>This tool is still in beta version.</b></p></div>
-<div class="section">
+<div class="source"><pre class="prettyprint">cli$ any23 vocab</pre></div>
+<p><i>NOTE</i>: <b>This tool is still in beta version.</b></p></section><section>
<h4><a name="The_MimeDetector_tool"></a>The MimeDetector tool</h4>
<p>The MimeDetector Tool extracts the <b>MIME Type</b> for a given source (http:// file:// inline://).</p>
<p>Examples:</p>
-<div class="source">
-<pre>cli$ any23 mimes http://www.michelemostarda.com/foaf.rdf
+<div class="source"><pre class="prettyprint">cli$ any23 mimes http://www.michelemostarda.com/foaf.rdf
application/rdf+xml</pre></div>
-<div class="source">
-<pre>cli$ any23 mimes file://../src/test/resources/application/trix/test1.trx
+<div class="source"><pre class="prettyprint">cli$ any23 mimes file://../src/test/resources/application/trix/test1.trx
application/trix</pre></div>
-<div class="source">
-<pre>cli$ any23 mimes 'inline://<http://s> <http://p> <http://o> .'
-text/n3</pre></div></div>
-<div class="section">
+<div class="source"><pre class="prettyprint">cli$ any23 mimes 'inline://<http://s> <http://p> <http://o> .'
+text/n3</pre></div></section><section>
<h4><a name="The_PluginVerifier_tool"></a>The PluginVerifier tool</h4>
<p>The PluginVerifier tool allows checking installed plugin in the specified input directory</p>
<p>Just launch the command below to sanity-check the input plugins directory</p>
-<div class="source">
-<pre>cli$ any23 verify [/path/to/plugins/dir]</pre></div></div></div>
-<div class="section">
+<div class="source"><pre class="prettyprint">cli$ any23 verify [/path/to/plugins/dir]</pre></div></section></section><section>
<h3><a name="Apache_Any23_CLI_Plugins"></a><b>Apache Any23</b> CLI <i>Plugins</i></h3>
<p>The <b>Apache Any23</b> ToolRunner CLI (<i>bin/any23</i>) supports the auto detection of Tool plugins within the classpath. For further details see <a href="./any23-plugins.html">Plugins</a> section.</p>
-<p>The default <b>any23</b> CLI plugins are enlisted below.</p>
-<div class="section">
+<p>The default <b>any23</b> CLI plugins are enlisted below.</p><section>
<h4><a name="Crawler_Plugin"></a>Crawler Plugin</h4>
<p><a name="crawler-tool">crawler-tool</a> The <i>Crawler Plugin</i> provides basic site crawling and metadata extraction capabilities.</p>
-<div class="source">
-<pre>cli$ any23 -h
+<div class="source"><pre class="prettyprint">cli$ any23 -h
[...]
crawler Any23 Crawler Command Line Tool.
Usage: crawler [options] input IRIs {<url>|<file>}+
@@ -458,36 +299,31 @@ text/n3</pre></div></div>
-sf, --storagefolder Folder used to store crawler temporary data.
Default: /var/folders/zz/9vvv_lbn1cs8dpwz859nmq080000gn/T/crawler-metadata-9ff4c650-10c2-41a1-9d99-ebeb3e7d21ce</pre></div>
<p>A usage example:</p>
-<div class="source">
-<pre>cli$ any23 crawler -s -f ntriples http://www.repubblica.it 1> out.nt 2> repubblica.log</pre></div></div></div>
-<div class="section">
+<div class="source"><pre class="prettyprint">cli$ any23 crawler -s -f ntriples http://www.repubblica.it 1> out.nt 2> repubblica.log</pre></div></section></section><section>
<h3><a name="Use_Apache_Any23_as_a_RESTful_Web_Service"></a>Use <b>Apache Any23</b> as a RESTful Web Service</h3>
<p><b>Apache Any23</b> provides a Web Service that can be used to extract <i>RDF</i> from Web documents. <b>Apache Any23</b> services can be accessed through a <a href="./service.html">RESTful API</a>.</p>
<p>Running the server</p>
-<p>The server command line tool is defined within the <b>service</b> module. Run the <tt>any23server</tt> script</p>
-<div class="source">
-<pre>service$ ./bin/any23server</pre></div>
-<p>from the command line in order to start up the server, then go to <a class="externalLink" href="http://localhost:8080/"></a> to access the web interface. A live demo version of such service is running at <a class="externalLink" href="http://any23.org/"></a>. You can also start the server from Java by running the <a href="./apidocs/org/apache/any23/servlet/Servlet.html">Apache Any23 Servlet</a> class. Maven can be used to create a WAR file for deployment into an existing servlet container such as <a class="externalLink" href="http://tomcat.apache.org/">Apache Tomcat</a>.</p></div>
-<div class="section">
+<p>The server command line tool is defined within the <b>service</b> module. Run the <code>any23server</code> script</p>
+<div class="source"><pre class="prettyprint">service$ ./bin/any23server</pre></div>
+<p>from the command line in order to start up the server, then go to <a class="externalLink" href="http://localhost:8080/"></a> to access the web interface. A live demo version of such service is running at <a class="externalLink" href="http://any23.org/"></a>. You can also start the server from Java by running the <a href="./apidocs/org/apache/any23/servlet/Servlet.html">Apache Any23 Servlet</a> class. Maven can be used to create a WAR file for deployment into an existing servlet container such as <a class="externalLink" href="http://tomcat.apache.org/">Apache Tomcat</a>.</p></section><section>
<h3><a name="Use_Apache_Any23_as_a_Library"></a>Use <b>Apache Any23</b> as a Library</h3>
-<p>See our <a href="./developers.html">Developers guide</a> for more details.</p></div></div>
- </div>
- </div>
- </div>
-
+<p>See our <a href="./developers.html">Developers guide</a> for more details.</p></section></section>
+ </main>
+ </div>
+ </div>
<hr/>
-
<footer>
- <div class="container-fluid">
- <div class="row span12">Copyright © 2010-2021
- <a href="https://www.apache.org/">The Apache Software Foundation</a>.
- All Rights Reserved.
-
+ <div class="container-fluid">
+ <div class="row-fluid">
+<div class="row span16">Apache Any23, Apache, the Apache feather logo, and the Apache Any23 project logos are trademarks of The Apache Software Foundation. All other marks mentioned may be trademarks or registered trademarks of their respective owners.
+ </div>
+ </div>
</div>
-
-
-
- </div>
</footer>
+<script>
+ if(anchors) {
+ anchors.add();
+ }
+</script>
</body>
</html>
Modified: any23/site/images/apache-maven-project-2.png
URL: http://svn.apache.org/viewvc/any23/site/images/apache-maven-project-2.png?rev=1896849&r1=1896848&r2=1896849&view=diff
==============================================================================
Binary files - no diff available.