[jboss-cvs] jboss-portal/cms/src/main/org/jboss/portal/test/cms ...

[Roy Russo]

  User: russo   
  Date: 06/08/22 16:08:23

  Added:       cms/src/main/org/jboss/portal/test/cms  TestRegEx.java
  Log:
  JBPORTAL-937 - done.
  
  Revision  Changes    Path
  1.1      date: 2006/08/22 20:08:23;  author: russo;  state: Exp;jboss-portal/cms/src/main/org/jboss/portal/test/cms/TestRegEx.java
  
  Index: TestRegEx.java
  ===================================================================
  /*
  * JBoss, Home of Professional Open Source
  * Copyright 2005, JBoss Inc., and individual contributors as indicated
  * by the @authors tag. See the copyright.txt in the distribution for a
  * full listing of individual contributors.
  *
  * This is free software; you can redistribute it and/or modify it
  * under the terms of the GNU Lesser General Public License as
  * published by the Free Software Foundation; either version 2.1 of
  * the License, or (at your option) any later version.
  *
  * This software is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  * Lesser General Public License for more details.
  *
  * You should have received a copy of the GNU Lesser General Public
  * License along with this software; if not, write to the Free
  * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
  * 02110-1301 USA, or see the FSF site: http://www.fsf.org.
  */
  package org.jboss.portal.test.cms;
  
  import junit.framework.TestCase;
  import org.jboss.portal.cms.util.FileUtil;
  
  import java.io.BufferedReader;
  import java.io.FileReader;
  import java.util.regex.Matcher;
  import java.util.regex.Pattern;
  
  /**
   * Tests for the CMS Regex when retrieving stored content.
   *
   * @author <a href="mailto:roy at jboss.org">Roy Russo</a>
   */
  public class TestRegEx extends TestCase
  {
  
     String HTMLHeaderFile = "resources/test/jcr/headerpage.html";
     String HTMLHeaderFile_Good = "resources/test/jcr/headerpage_good.html";
  
     private static final String URI_schemeRegex = "[a-z][-+.0-9a-z]*:";
  
     /**
      * For our purposes, ignore URIs that start with a scheme idicator,
      * a slash (indicating an absolute path), or a hash sign (# = ASCII hex 23).
      */
     private static final String URI_ignoreRegex = "" + URI_schemeRegex + "|/|\\x23";
  
     private static final String
           regex = "((?:href|src)\\s*=\\s*)               # Capture preliminaries in $1.  \n"
                   + "(?:                                   # First look for URL in quotes. \n"
                   + "   ([\"\'])                           #   Capture open quote in $2.   \n"
                   + "   (?!" + URI_ignoreRegex + ")        #   If it isn't absolute...     \n"
                   + "   /?(.+?)                              #    ...capture URL in $3       \n"
                   + "   \\2                                #   Match the closing quote     \n"
                   + " |                                    # Look for non-quoted URL.      \n"
                   + "   (?![\"\']|" + URI_ignoreRegex + ") #   If it isn't absolute...     \n"
                   + "   /?([^\\s>]+)                         #    ...capture URL in $4       \n"
                   + ")";
  
     /**
      * Removes header content, and leaves content between body tags
      */
     private static final String HTMLStripperRegex = "(.*<body[^>]*>(.+)</body>.*)";
     //private static final String HTMLStripperRegex = "(.*<body[^>]*>(.+)</body>.*')";
  
     private static final Pattern RELATIVE_URI_PATTERN = Pattern.compile(regex, Pattern.MULTILINE | Pattern.CASE_INSENSITIVE | Pattern.COMMENTS);
  
     private static final Pattern STRIP_TAGS_PATTERN = Pattern.compile(HTMLStripperRegex, Pattern.DOTALL | Pattern.CASE_INSENSITIVE);
  
     public void setUp() throws Exception
     {
        super.setUp();
     }
  
     /**
      * Tests HTML rewriting of header content and links in CMSPortlet.
      *
      * @throws Exception
      */
     public void testHTMLPageHeaderRewrite() throws Exception
     {
        String fileHTML = "";
        StringBuffer fileData = new StringBuffer(1000);
        BufferedReader reader = new BufferedReader(new FileReader(HTMLHeaderFile));
        char[] buffer = new char[1024];
        int count = 0;
        while((count = reader.read(buffer)) != -1)
        {
           String read = String.valueOf(buffer, 0, count);
           fileData.append(read);
           buffer = new char[1024];
        }
        reader.close();
        fileHTML = fileData.toString();
  
        // begin cleaner
        String CleanHTML = "";
        Matcher h = STRIP_TAGS_PATTERN.matcher(fileHTML);
        while(h.find())
        {
           CleanHTML = h.group(2);
        }
        // begin modifying links
        StringBuffer stringbuffer = new StringBuffer();
        Matcher m = RELATIVE_URI_PATTERN.matcher(CleanHTML);
        while(m.find())
        {
           String relURI = m.group(3) != null ? m.group(3) : m.group(4);
           String absoluteURI = this.buildURL("/" + relURI);
           m.appendReplacement(stringbuffer, "$1$2" + FileUtil.cleanDoubleSlashes(absoluteURI) + "$2");
        }
        m.appendTail(stringbuffer);
        CleanHTML = stringbuffer.toString();
  
        /* Assert */
        String goodHTML = "";
        fileData = new StringBuffer(1000);
        reader = new BufferedReader(new FileReader(HTMLHeaderFile_Good));
        buffer = new char[1024];
        count = 0;
        while((count = reader.read(buffer)) != -1)
        {
           String read = String.valueOf(buffer, 0, count);
           fileData.append(read);
           buffer = new char[1024];
        }
        reader.close();
        goodHTML = fileData.toString();
  
        assertEquals("RegEx failed to match!", CleanHTML, goodHTML);
     }
  
     protected void tearDown() throws Exception
     {
        super.tearDown();
     }
  
     /**
      * Faking it.
      */
     private String buildURL(String path)
     {
        return "http://localhost:8080/portal/content" + path;
     }
  }