Loading... (original) (raw)

Issue with Java version 6u41

Using HTMLEditorKit to parse pre-existing HTML. If we parse this
document, it works as expected:

But if we don't have the tag, then we get only a handleEndOfLineString
callback, and do not get the actual text. This is the example document:
/ at start is bad

Testcase:
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLDocument;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.DTD;
import javax.swing.text.html.parser.DocumentParser;
import javax.swing.text.html.parser.Entity;
import javax.swing.text.html.parser.ParserDelegator;
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;

/**
* Bug in Parser when the document starts with a slash.
*/
public class ParserTest {
public static void main(String[] args) throws IOException {

doTest( "/ at start is bad" );
doTest( "/ at start inside body is okay" );
}

private static void doTest(String text) throws IOException {
System.out.println( "doTest: " + text );
ParserCB cb = new ParserCB();
HTMLEditorKit htmlKit = new HTMLEditorKit();
HTMLDocument htmlDoc = (HTMLDocument)
htmlKit.createDefaultDocument();

htmlDoc.getParser().parse(new StringReader(text), cb, true);
System.out.println();
}

private static class ParserCB extends HTMLEditorKit.ParserCallback {
@Override
public void handleComment(char[] data, int pos) {
System.out.println("handleComment: " + new String(data) );
}

@Override
public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int
pos) {
System.out.println("handleStartTag: " + t );
}

@Override
public void handleEndTag(HTML.Tag t, int pos) {
System.out.println("handleEndTag: " + t );
}

@Override
public void handleSimpleTag(HTML.Tag t, MutableAttributeSet a, int
pos) {
System.out.println("handleSimpleTag: " + t );
}

@Override
public void handleError(String errorMsg, int pos) {
System.out.println("handleError: " + errorMsg );
}

@Override
public void handleEndOfLineString(String eol) {
System.out.println("handleEndOfLineString: " + eol );
}

@Override
public void handleText(char[] data, int pos) {
System.out.println("handleText: " + new String(data));
}
}
}

Output from the test case:
doTest: / at start is bad
handleEndOfLineString:

doTest: / at start inside body is okay
handleStartTag: html
handleStartTag: head
handleEndTag: head
handleStartTag: body
handleText: / at start inside body is okay
handleEndTag: body
handleEndTag: html
handleEndOfLineString: