hazendaz / httpunit / 755

Committed 14 Feb 2026 07:14PM UTC coverage: 80.526%. Remained the same

Build # 755

Build Type

push

github

Committed by

hazendaz

Commit Message

[ci] Fix badge

Run Details

3213 of 4105 branches covered (78.27%)

Branch coverage included in aggregate %.

8245 of 10124 relevant lines covered (81.44%)

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

/*
 * SPDX-License-Identifier: MIT
 * See LICENSE file for details.
 *
 * Copyright 2000-2026 Russell Gold
 * Copyright 2021-2000 hazendaz
 */
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	* SPDX-License-Identifier: MIT
3	* See LICENSE file for details.
4	*
5	* Copyright 2000-2026 Russell Gold
6	* Copyright 2021-2000 hazendaz
7	*/
8	package com.meterware.httpunit.parsing;
9
10	import com.meterware.httpunit.dom.HTMLDocumentImpl;
11
12	import java.io.ByteArrayInputStream;
13	import java.io.IOException;
14	import java.net.URL;
15	import java.nio.charset.StandardCharsets;
16
17	import org.w3c.dom.Document;
18	import org.w3c.dom.Node;
19	import org.w3c.dom.NodeList;
20	import org.w3c.dom.html.HTMLDocument;
21	import org.w3c.tidy.Tidy;
22	import org.xml.sax.SAXException;
23
24	/**
25	* The Class JTidyHTMLParser.
26	*/
27	class JTidyHTMLParser implements HTMLParser {	1✔
28
29	@Override
30	public void parse(URL pageURL, String pageText, DocumentAdapter adapter) throws IOException, SAXException {
31	Document jtidyDocument = getParser(pageURL)	×
32	.parseDOM(new ByteArrayInputStream(pageText.getBytes(StandardCharsets.UTF_8)), null);	×
33	HTMLDocument htmlDocument = new HTMLDocumentImpl();	×
34	NodeList nl = jtidyDocument.getChildNodes();	×
35	for (int i = 0; i < nl.getLength(); i++) {	×
36	Node importedNode = nl.item(i);	×
37	if (importedNode.getNodeType() != Node.DOCUMENT_TYPE_NODE) {	×
38	htmlDocument.appendChild(htmlDocument.importNode(importedNode, true));	×
39	}
40	}
41	adapter.setDocument(htmlDocument);	×
42	}	×
43
44	@Override
45	public String getCleanedText(String string) {
46	return string == null ? "" : string.replace(NBSP, ' ');	×
47	}
48
49	@Override
50	public boolean supportsPreserveTagCase() {
51	return false;	×
52	}
53
54	@Override
55	public boolean supportsForceTagCase() {
56	return false;	×
57	}
58
59	@Override
60	public boolean supportsReturnHTMLDocument() {
61	return true;	×
62	}
63
64	@Override
65	public boolean supportsParserWarnings() {
66	return true;	×
67	}
68
69	/** The Constant NBSP. */
70	private static final char NBSP = (char) 160; // non-breaking space, defined by JTidy
71
72	/**
73	* get the parser of the given url.
74	*
75	* @param url
76	* the url
77	*
78	* @return the parser
79	*/
80	private static Tidy getParser(URL url) {
81	Tidy tidy = new Tidy();	×
82	// BR 2880636 httpunit 1.7 does not work with latest Tidy release r918
83	// tidy.setCharEncoding( org.w3c.tidy.Configuration.UTF8 );
84	tidy.setInputEncoding("UTF8");	×
85	tidy.setQuiet(true);	×
86	tidy.setShowWarnings(HTMLParserFactory.isParserWarningsEnabled());	×
87	if (!HTMLParserFactory.getHTMLParserListeners().isEmpty()) {	×
88	tidy.setErrout(new JTidyPrintWriter(url));	×
89	}
90	return tidy;	×
91	}
92
93	}

hazendaz / httpunit / 755

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