hazendaz / httpunit / 656

Committed 06 Dec 2025 09:11PM UTC coverage: 80.452% (+0.02%) from 80.435%

Build # 656

Build Type

push

github

Committed by

hazendaz

Commit Message

[maven-release-plugin] prepare for next development iteration

Run Details

3213 of 4105 branches covered (78.27%)

Branch coverage included in aggregate %.

8245 of 10137 relevant lines covered (81.34%)

0.81 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

3.23

/src/main/java/com/meterware/httpunit/parsing/JTidyHTMLParser.java

/*
 * MIT License
 *
 * Copyright 2011-2025 Russell Gold
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated
 * documentation files (the "Software"), to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and
 * to permit persons to whom the Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in all copies or substantial portions
 * of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO
 * THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
 * CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
 * DEALINGS IN THE SOFTWARE.
 */
package com.meterware.httpunit.parsing;

import com.meterware.httpunit.dom.HTMLDocumentImpl;

import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.net.URL;
import java.nio.charset.StandardCharsets;

import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.html.HTMLDocument;
import org.w3c.tidy.Tidy;
import org.xml.sax.SAXException;

/**
 * The Class JTidyHTMLParser.
 */
class JTidyHTMLParser implements HTMLParser {

    @Override
    public void parse(URL pageURL, String pageText, DocumentAdapter adapter) throws IOException, SAXException {
        Document jtidyDocument = getParser(pageURL)
                .parseDOM(new ByteArrayInputStream(pageText.getBytes(StandardCharsets.UTF_8)), null);
        HTMLDocument htmlDocument = new HTMLDocumentImpl();
        NodeList nl = jtidyDocument.getChildNodes();
        for (int i = 0; i < nl.getLength(); i++) {
            Node importedNode = nl.item(i);
            if (importedNode.getNodeType() != Node.DOCUMENT_TYPE_NODE) {
                htmlDocument.appendChild(htmlDocument.importNode(importedNode, true));
            }
        }
        adapter.setDocument(htmlDocument);
    }

    @Override
    public String getCleanedText(String string) {
        return string == null ? "" : string.replace(NBSP, ' ');
    }

    @Override
    public boolean supportsPreserveTagCase() {
        return false;
    }

    @Override
    public boolean supportsForceTagCase() {
        return false;
    }

    @Override
    public boolean supportsReturnHTMLDocument() {
        return true;
    }

    @Override
    public boolean supportsParserWarnings() {
        return true;
    }

    /** The Constant NBSP. */
    private static final char NBSP = (char) 160; // non-breaking space, defined by JTidy

    /**
     * get the parser of the given url.
     *
     * @param url
     *            the url
     *
     * @return the parser
     */
    private static Tidy getParser(URL url) {
        Tidy tidy = new Tidy();
        // BR 2880636 httpunit 1.7 does not work with latest Tidy release r918
        // tidy.setCharEncoding( org.w3c.tidy.Configuration.UTF8 );
        tidy.setInputEncoding("UTF8");
        tidy.setQuiet(true);
        tidy.setShowWarnings(HTMLParserFactory.isParserWarningsEnabled());
        if (!HTMLParserFactory.getHTMLParserListeners().isEmpty()) {
            tidy.setErrout(new JTidyPrintWriter(url));
        }
        return tidy;
    }

}

1	/*
2	* MIT License
3	*
4	* Copyright 2011-2025 Russell Gold
5	*
6	* Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated
7	* documentation files (the "Software"), to deal in the Software without restriction, including without limitation
8	* the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and
9	* to permit persons to whom the Software is furnished to do so, subject to the following conditions:
10	*
11	* The above copyright notice and this permission notice shall be included in all copies or substantial portions
12	* of the Software.
13	*
14	* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO
15	* THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16	* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
17	* CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
18	* DEALINGS IN THE SOFTWARE.
19	*/
20	package com.meterware.httpunit.parsing;
21
22	import com.meterware.httpunit.dom.HTMLDocumentImpl;
23
24	import java.io.ByteArrayInputStream;
25	import java.io.IOException;
26	import java.net.URL;
27	import java.nio.charset.StandardCharsets;
28
29	import org.w3c.dom.Document;
30	import org.w3c.dom.Node;
31	import org.w3c.dom.NodeList;
32	import org.w3c.dom.html.HTMLDocument;
33	import org.w3c.tidy.Tidy;
34	import org.xml.sax.SAXException;
35
36	/**
37	* The Class JTidyHTMLParser.
38	*/
39	class JTidyHTMLParser implements HTMLParser {	1✔
40
41	@Override
42	public void parse(URL pageURL, String pageText, DocumentAdapter adapter) throws IOException, SAXException {
43	Document jtidyDocument = getParser(pageURL)	×
44	.parseDOM(new ByteArrayInputStream(pageText.getBytes(StandardCharsets.UTF_8)), null);	×
45	HTMLDocument htmlDocument = new HTMLDocumentImpl();	×
46	NodeList nl = jtidyDocument.getChildNodes();	×
47	for (int i = 0; i < nl.getLength(); i++) {	×
48	Node importedNode = nl.item(i);	×
49	if (importedNode.getNodeType() != Node.DOCUMENT_TYPE_NODE) {	×
50	htmlDocument.appendChild(htmlDocument.importNode(importedNode, true));	×
51	}
52	}
53	adapter.setDocument(htmlDocument);	×
54	}	×
55
56	@Override
57	public String getCleanedText(String string) {
58	return string == null ? "" : string.replace(NBSP, ' ');	×
59	}
60
61	@Override
62	public boolean supportsPreserveTagCase() {
63	return false;	×
64	}
65
66	@Override
67	public boolean supportsForceTagCase() {
68	return false;	×
69	}
70
71	@Override
72	public boolean supportsReturnHTMLDocument() {
73	return true;	×
74	}
75
76	@Override
77	public boolean supportsParserWarnings() {
78	return true;	×
79	}
80
81	/** The Constant NBSP. */
82	private static final char NBSP = (char) 160; // non-breaking space, defined by JTidy
83
84	/**
85	* get the parser of the given url.
86	*
87	* @param url
88	* the url
89	*
90	* @return the parser
91	*/
92	private static Tidy getParser(URL url) {
93	Tidy tidy = new Tidy();	×
94	// BR 2880636 httpunit 1.7 does not work with latest Tidy release r918
95	// tidy.setCharEncoding( org.w3c.tidy.Configuration.UTF8 );
96	tidy.setInputEncoding("UTF8");	×
97	tidy.setQuiet(true);	×
98	tidy.setShowWarnings(HTMLParserFactory.isParserWarningsEnabled());	×
99	if (!HTMLParserFactory.getHTMLParserListeners().isEmpty()) {	×
100	tidy.setErrout(new JTidyPrintWriter(url));	×
101	}
102	return tidy;	×
103	}
104
105	}

hazendaz / httpunit / 656

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous