linktagtest.java

html to xml convertor

    {
        LinkTag link;

        createParser ("<A HREF='http://www.someurl.com'>Try http.</A>","http://sourceforge.net");
        parseAndAssertNodeCount (1);
        assertTrue ("Node should be a LinkTag", node[0] instanceof LinkTag);
        link = (LinkTag)node[0];
        assertTrue("This is a http link : "+link.getLink(),link.isHTTPLink());
    }

    public void testRelativeTypeHttpLink() throws ParserException
    {
        LinkTag link;

        createParser ("<A HREF='somePage.html'>Try relative http.</A>","http://sourceforge.net");
        parseAndAssertNodeCount (1);
        assertTrue ("Node should be a LinkTag", node[0] instanceof LinkTag);
        link = (LinkTag)node[0];
        assertTrue("This relative link is also a http link : "+link.getLink(),link.isHTTPLink());
    }
    
    public void testTypeNonHttp() throws ParserException
    {
        LinkTag link;

        createParser ("<A HREF='ftp://www.someurl.com'>Try non-http.</A>","http://sourceforge.net");
        parseAndAssertNodeCount (1);
        assertTrue ("Node should be a LinkTag", node[0] instanceof LinkTag);
        link = (LinkTag)node[0];
        assertTrue("This is not a http link : "+link.getLink(),!link.isHTTPLink());
    }

    public void testTypeHttpLikeLink() throws ParserException
    {
        LinkTag link;

        createParser ("<A HREF='http://'>Try basic http.</A>","http://sourceforge.net");
        parseAndAssertNodeCount (1);
        assertTrue ("Node should be a LinkTag", node[0] instanceof LinkTag);
        link = (LinkTag)node[0];
        assertTrue("This is a http link",link.isHTTPLikeLink());
        
        createParser ("<A HREF='https://www.someurl.com'>Try https.</A>","http://sourceforge.net");
        parseAndAssertNodeCount (1);
        assertTrue ("Node should be a LinkTag", node[0] instanceof LinkTag);
        link = (LinkTag)node[0];
        assertTrue("This is a https link",link.isHTTPLikeLink());
    }

    /**
     * Test mail link.
     * Bug #738504 MailLink != HTTPLink
     */
    public void testMailToIsNotAHTTPLink () throws ParserException
    {
        LinkTag link;

        createParser ("<A HREF='mailto:[e-mail]'>Derrick</A>","http://sourceforge.net");
        parseAndAssertNodeCount (1);
        assertTrue ("Node should be a LinkTag", node[0] instanceof LinkTag);
        link = (LinkTag)node[0];
        assertTrue ("bug #738504 MailLink != HTTPLink", !link.isHTTPLink ());
        assertTrue ("bug #738504 MailLink != HTTPSLink", !link.isHTTPSLink ());
    }

    /**
     * Bug #784767 irc://server/channel urls are HTTPLike?
     */
    public void testIrcIsNotAHTTPLink () throws ParserException
    {
        LinkTag link;

        createParser ("<A HREF='irc://server/channel'>Try irc.</A>","http://sourceforge.net");
        parseAndAssertNodeCount (1);
        assertTrue ("Node should be a LinkTag", node[0] instanceof LinkTag);
        link = (LinkTag)node[0];
        assertTrue("This is not a http link", !link.isHTTPLikeLink ());
    }

    public void testAccessKey() throws ParserException {
        createParser("<a href=\"http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph\" accessKey=1>Click Here</A>");
        parseAndAssertNodeCount(1);
        assertTrue("The node should be a link tag",node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag)node[0];
        assertEquals("Link URL of link tag","http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph",linkTag.getLink());
        assertEquals("Link Text of link tag","Click Here",linkTag.getLinkText());
        assertEquals("Access key","1",linkTag.getAccessKey());
    }

    public void testErroneousLinkBug() throws ParserException {
        createParser(
            "Site Comments?<br>" +
                "<a href=\"mailto:[e-mail]?subject=Site Comments\">" +
                    "Mail Us" +
                "<a>"
        );
        parseAndAssertNodeCount(4);
        // The first node should be a Text
        assertTrue("First node should be a Text",node[0] instanceof Text);
        Text stringNode = (Text)node[0];
        assertEquals("Text of the Text","Site Comments?",stringNode.getText());
        assertTrue("Second node should be a tag",node[1] instanceof Tag);
        assertTrue("Third node should be a link",node[2] instanceof LinkTag);
        // LinkScanner.evaluate() says no HREF means it isn't a link:
        assertTrue("Fourth node should be a tag",node[3] instanceof Tag); 
    }

    /**
     * Test case based on a report by Raghavender Srimantula, of the parser giving out of memory exceptions. Found to occur
     * on the following piece of html
     * <pre>
     * <a href=s/8741><img src="http://us.i1.yimg.com/us.yimg.com/i/i16/mov_popc.gif" height=16 width=16 border=0></img></td><td nowrap> &nbsp;
     * <a href=s/7509>
     * </pre>
     */
    public void testErroneousLinkBugFromYahoo2() throws ParserException {
        String link = "<a href=s/8741>" +
                "<img src=\"http://us.i1.yimg.com/us.yimg.com/i/i16/mov_popc.gif\" height=16 width=16 border=0>";
        createParser(
            "<td>" +
                link +
            "</td>" +
            "<td nowrap> &nbsp;\n"+
                "<a href=s/7509><b>Yahoo! Movies</b></a>" +
            "</td>","http://www.yahoo.com");
        NodeList linkNodes = parser.extractAllNodesThatMatch (new NodeClassFilter (LinkTag.class));

        assertEquals("number of links", 2, linkNodes.size ());
        LinkTag linkTag = (LinkTag)linkNodes.elementAt (0);
        assertStringEquals("Link","http://www.yahoo.com/s/8741",linkTag.getLink());
        // Verify the link data
        assertStringEquals("Link Text","",linkTag.getLinkText());
        // Verify the reconstruction html
        assertStringEquals("toHTML",link + "</a>",linkTag.toHtml());
    }

    /**
     * Test case based on a report by Raghavender Srimantula, of the parser giving out of memory exceptions. Found to occur
     * on the following piece of html
     * <pre>
     * <a href=s/8741><img src="http://us.i1.yimg.com/us.yimg.com/i/i16/mov_popc.gif" height=16 width=16 border=0></img>This is test
     * <a href=s/7509>
     * </pre>
     */
    public void testErroneousLinkBugFromYahoo() throws ParserException {
        String link =
            "<a href=s/8741>" +
                "<img src=\"http://us.i1.yimg.com/us.yimg.com/i/i16/mov_popc.gif\" " +
                     "height=16 " +
                     "width=16 " +
                     "border=0>" +
                "This is a test\n";
        createParser(
                link +
                "<a href=s/7509>" +
                    "<b>Yahoo! Movies</b>" +
                "</a>",
            "http://www.yahoo.com"
        );
        parseAndAssertNodeCount(2);
        assertTrue("First node should be a LinkTag",node[0] instanceof LinkTag);
        assertTrue("Second node should be a LinkTag",node[1] instanceof LinkTag);
        LinkTag linkTag = (LinkTag)node[0];
        assertEquals("Link","http://www.yahoo.com/s/8741",linkTag.getLink());
        // Verify the link data
        assertEquals("Link Text","This is a test\n",linkTag.getLinkText());
        // Verify the reconstruction html
        assertStringEquals("toHTML()",link + "</a>",linkTag.toHtml());
    }

    /**
     * This is the reproduction of a bug which produces multiple text copies.
     */
    public void testExtractLinkInvertedCommasBug2() throws ParserException
    {
        createParser("<a href=\"http://cbc.ca/artsCanada/stories/greatnorth271202\" class=\"lgblacku\">Vancouver schools plan 'Great Northern Way'</a>");
        parseAndAssertNodeCount(1);
        assertTrue("The node should be a link tag",node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag)node[0];
        assertStringEquals("Extracted Text","Vancouver schools plan 'Great Northern Way'", linkTag.getLinkText ());
    }

    /**
     * Bug pointed out by Sam Joseph ([e-mail])
     * Links with spaces in them will get their spaces absorbed
     */
    public void testLinkSpacesBug() throws ParserException{
        createParser("<a href=\"http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph\">Click Here</A>");
        parseAndAssertNodeCount(1);
        assertTrue("The node should be a link tag",node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag)node[0];
        assertEquals("Link URL of link tag","http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph",linkTag.getLink());
        assertEquals("Link Text of link tag","Click Here",linkTag.getLinkText());
    }

    /**
     * Bug reported by Raj Sharma,5-Apr-2002, upon parsing
     * http://www.samachar.com, the entire page could not be picked up.
     * The problem was occurring after parsing a particular link
     * after which the parsing would not proceed. This link was spread over three lines.
     * The bug has been reproduced and fixed.
     */
    public void testMultipleLineBug() throws ParserException {
        createParser("<LI><font color=\"FF0000\" size=-1><b>Tech Samachar:</b></font><a \n"+
        "href=\"http://ads.samachar.com/bin/redirect/tech.txt?http://www.samachar.com/tech\n"+
        "nical.html\"> Journalism 3.0</a> by Rajesh Jain");
        parser.setNodeFactory (new PrototypicalNodeFactory (new LinkTag ()));
        parseAndAssertNodeCount(8);
        assertTrue("Seventh node should be a link tag",node[6] instanceof LinkTag);
        LinkTag linkTag = (LinkTag)node[6];
        String exp = new String("http://ads.samachar.com/bin/redirect/tech.txt?http://www.samachar.com/technical.html");
        //assertEquals("Length of link tag",exp.length(), linkTag.getLink().length());
        assertStringEquals("Link URL of link tag",exp,linkTag.getLink());
        assertEquals("Link Text of link tag"," Journalism 3.0",linkTag.getLinkText());
        assertTrue("Eight node should be a string node",node[7] instanceof Text);
        Text stringNode = (Text)node[7];
        assertEquals("String node contents"," by Rajesh Jain",stringNode.getText());
    }

    public void testRelativeLinkScan() throws ParserException {
        createParser("<A HREF=\"mytest.html\"> Hello World</A>","http://www.yahoo.com");
        parseAndAssertNodeCount(1);
        assertTrue("Node identified should be HTMLLinkTag",node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag)node[0];
        assertEquals("Expected Link","http://www.yahoo.com/mytest.html",linkTag.getLink());
    }

    public void testRelativeLinkScan2() throws ParserException {
        createParser("<A HREF=\"abc/def/mytest.html\"> Hello World</A>","http://www.yahoo.com");
        parseAndAssertNodeCount(1);
        assertTrue("Node identified should be HTMLLinkTag",node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag)node[0];
        assertStringEquals("Expected Link","http://www.yahoo.com/abc/def/mytest.html",linkTag.getLink());
    }

    public void testRelativeLinkScan3() throws ParserException {
        createParser("<A HREF=\"../abc/def/mytest.html\"> Hello World</A>","http://www.yahoo.com/ghi");
        parseAndAssertNodeCount(1);
        assertTrue("Node identified should be HTMLLinkTag",node[0] instanceof LinkTag);
        LinkTag linkTag = (LinkTag)node[0];
        assertStringEquals("Expected Link","http://www.yahoo.com/abc/def/mytest.html",linkTag.getLink());
    }

    /**
     * Test scan with data which is of diff nodes type
     */
    public void testScan() throws ParserException
    {
        createParser("<A HREF=\"mytest.html\"><IMG SRC=\"abcd.jpg\">Hello World</A>","http://www.yahoo.com");
        parser.setNodeFactory (
            new PrototypicalNodeFactory (
                new Tag[] {
                    new LinkTag (),
                    new ImageTag (),
                }));
        parseAndAssertNodeCount(1);
        assertTrue("Node should be a link node",node[0] instanceof LinkTag);

        LinkTag linkTag = (LinkTag)node[0];
        // Get the link data and cross-check
        Node [] dataNode= new Node[10];
        int i = 0;
        for (SimpleNodeIterator e = linkTag.children();e.hasMoreNodes();)
        {
            dataNode[i++] = e.nextNode();
        }
        assertEquals("Number of data nodes",new Integer(2),new Integer(i));
        assertTrue("First data node should be an Image Node",dataNode[0] instanceof ImageTag);
        assertTrue("Second data node shouls be a String Node",dataNode[1] instanceof Text);

        // Check the contents of each data node
        ImageTag imageTag = (ImageTag)dataNode[0];
        assertEquals("Image URL","http://www.yahoo.com/abcd.jpg",imageTag.getImageURL());
        Text stringNode = (Text)dataNode[1];
        assertEquals("String Contents","Hello World",stringNode.getText());
    }

    /**
     * A bug in the freshmeat page - really bad html
     * tag - &lt;A&gt;Revision&lt;\a&gt;
     * Reported by Mazlan Mat
     * Note: Actually, this is completely legal HTML - Derrick
     */
    public void testFreshMeatBug() throws ParserException
    {
        String html = "<a>Revision</a>";
        createParser(html,"http://www.yahoo.com");
        parseAndAssertNodeCount(1);
        assertTrue("Node 0 should be a tag",node[0] instanceof Tag);
        Tag tag = (Tag)node[0];