/** 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 - <A>Revision<\a> 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];
assertEquals("Tag Contents", html, tag.toHtml());
assertEquals("Node 0 should have one child", 1, tag.getChildren().size());
assertTrue("The child should be a string node", tag.getChildren().elementAt(0) instanceof Text);
Text stringNode = (Text) tag.getChildren().elementAt(0);
assertEquals("Text Contents", "Revision", stringNode.getText());
}
public void testErroneousLinkBug() throws ParserException {
createParser(
"Site Comments?<br>"
+ "<a href=\"mailto:[email protected]?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);
}
/**
* 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 String getText() {
return delegate.getText();
}
@Override
public void visitStringNode(Text string) {
Element parent = getParent(string.getParent());
parent.setInnerText(string.getText());
}
