Line	Hits	Note	Source
1			/*
2			* $Id: HtmlCleaner.java 1011 2008-06-16 17:57:36Z amandel $
3			*
4			* Copyright 2006, The jCoderZ.org Project. All rights reserved.
5			*
6			* Redistribution and use in source and binary forms, with or without
7			* modification, are permitted provided that the following conditions are
8			* met:
9			*
10			* * Redistributions of source code must retain the above copyright
11			* notice, this list of conditions and the following disclaimer.
12			* * Redistributions in binary form must reproduce the above
13			* copyright notice, this list of conditions and the following
14			* disclaimer in the documentation and/or other materials
15			* provided with the distribution.
16			* * Neither the name of the jCoderZ.org Project nor the names of
17			* its contributors may be used to endorse or promote products
18			* derived from this software without specific prior written
19			* permission.
20			*
21			* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS "AS IS" AND
22			* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23			* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
24			* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS AND CONTRIBUTORS
25			* BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
26			* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
27			* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
28			* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
29			* WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
30			* OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
31			* ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32			*/
33			package org.jcoderz.commons.doclet;
34
35			import java.io.ByteArrayInputStream;
36			import java.io.ByteArrayOutputStream;
37			import java.io.InputStream;
38			import java.io.PrintWriter;
39			import java.io.StringWriter;
40			import java.util.logging.Level;
41			import java.util.logging.Logger;
42
43			import org.w3c.tidy.Configuration;
44			import org.w3c.tidy.Tidy;
45
46			/**
47			* This class provides an easy interface to jTidy to clean up
48			* html fragments as used within javadoc.
49			*
50			* @author Andreas Mandel
51			*/
52	100		public class HtmlCleaner
53			{
54			/** The full qualified name of this class. */
55	75		private static final String CLASSNAME = HtmlCleaner.class.getName();
56
57			/** The logger to use. */
58	100		private static final Logger logger = Logger.getLogger(CLASSNAME);
59
60			private static final String FIX_HEADER
61			= "<html><head><title>clean</title></head><body>";
62
63			private static final String FIX_FOOTER
64			= "</body></html>";
65
66	100		private String mWarnings = "";
67	100		private boolean mHasErrors = false;
68
69			/**
70			* Converts the given HTML fragment string into wellformed xhtml.
71			* @param in the html fragment to be cleaned up.
72			* @return a cleaned up wellformed xhtml version of the in string.
73			*/
74			public String clean (CharSequence in)
75			{
76	100		if (logger.isLoggable(Level.FINER))
77			{
78	100		logger.entering(CLASSNAME, "clean(CharSequence)", in);
79			}
80	100		mHasErrors = false;
81	100		final Tidy tidy = new Tidy();
82	100		final String inData = FIX_HEADER + in + FIX_FOOTER;
83	100		final StringWriter err = new StringWriter();
84	100		String result = null;
85			try
86			{
87	100		tidy.setCharEncoding(Configuration.UTF8);
88	100		tidy.setMakeClean(true);
89	100		tidy.setXmlOut(true);
90	100		tidy.setRawOut(true);
91	100		tidy.setNumEntities(true);
92	100		tidy.setWraplen(0); // do not care about line length
93			// tidy.setOnlyErrors(true);
94	100		tidy.setErrout(new PrintWriter(err));
95
96	100		final InputStream inStream = new ByteArrayInputStream(
97			inData.getBytes("utf-8"));
98
99	100		final ByteArrayOutputStream out = new ByteArrayOutputStream();
100
101	100		tidy.parse(inStream, out);
102
103	100		final String resultString = new String(out.toByteArray(), "utf-8");
104
105	100		final int start = resultString.indexOf("<body>");
106	100		final int end = resultString.lastIndexOf("</body>");
107
108	100		if (start != -1 && end != -1)
109			{
110	100		result = resultString.substring(
111			start + "<body>\n".length(), end).trim();
112			}
113			else
114			{
115	100		result = "Invalid HTML could not be parsed.";
116			}
117
118	100		if (tidy.getParseWarnings() == 0 && tidy.getParseErrors() == 0)
119			{
120	100		mWarnings = "";
121			}
122			else
123			{
124	100		mWarnings = err.toString();
125			}
126	100		mHasErrors = (tidy.getParseErrors() == 0);
127			}
128	0		catch (Exception ex)
129			{
130	0		result = "Invalid HTML could not be parsed.";
131	0		err.write(result);
132	0		err.write("Got exception:");
133	0		err.write(ex.toString());
134	0		ex.printStackTrace(new PrintWriter(err));
135	0		mWarnings = err.toString();
136	0		logger.log(Level.FINER,
137			"Could not handle html fragment. '" + in + "'." , ex);
138	0		mHasErrors = true;
139	100		}
140	100		if (logger.isLoggable(Level.FINER))
141			{
142	100		logger.exiting(CLASSNAME, "clean(CharSequence)", result);
143			}
144	100		return result;
145			}
146
147			/**
148			* Returns the warnings encountered during last clean.
149			* @return the warnings encountered during last clean.
150			*/
151			public String getWarnings ()
152			{
153	100		return mWarnings;
154			}
155
156		(1)	public boolean hasErrors ()
157			{
158	0		return mHasErrors;
159			}
160			}
161

Findings in this File

(1)

156

Missing a Javadoc comment.

Project Report: fawkez

Packagesummary org.jcoderz.commons.doclet

org.jcoderz.commons.doclet.HtmlCleaner

Findings in this File