Example usage for javax.swing.text.html HTMLDocument getText

List of usage examples for javax.swing.text.html HTMLDocument getText

  1. HOME
  2. Java
  3. javax
  4. javax.swing.text.html.*
  5. HTMLDocument
  6. getText

Introduction

In this page you can find the example usage for javax.swing.text.html HTMLDocument getText.

Prototype

public String getText(int offset, int length) throws BadLocationException

Source Link

Document

Gets a sequence of text from the document.

Usage

From source file:MainClass.java

public static void main(String args[]) throws Exception {
    URL url = new URL("http://www.java2s.com");
    URLConnection connection = url.openConnection();
    InputStream is = connection.getInputStream();
    InputStreamReader isr = new InputStreamReader(is);
    BufferedReader br = new BufferedReader(isr);

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);// ww w. j  av  a  2  s. c om

    for (HTMLDocument.Iterator iterator = htmlDoc.getIterator(HTML.Tag.A); iterator.isValid(); iterator
            .next()) {

        AttributeSet attributes = iterator.getAttributes();
        String srcString = (String) attributes.getAttribute(HTML.Attribute.HREF);
        System.out.print(srcString);
        int startOffset = iterator.getStartOffset();
        int endOffset = iterator.getEndOffset();
        int length = endOffset - startOffset;
        String text = htmlDoc.getText(startOffset, length);
        System.out.println(" - " + text);
    }
}

From source file:MainClass.java

public static void main(String args[]) throws Exception {
    URL url = new URL("http://www.google.com");
    URLConnection connection = url.openConnection();
    InputStream is = connection.getInputStream();
    InputStreamReader isr = new InputStreamReader(is);
    BufferedReader br = new BufferedReader(isr);

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);//  w w w.  j a  v a 2  s. com

    for (HTMLDocument.Iterator iterator = htmlDoc.getIterator(HTML.Tag.A); iterator.isValid(); iterator
            .next()) {

        AttributeSet attributes = iterator.getAttributes();
        String srcString = (String) attributes.getAttribute(HTML.Attribute.HREF);
        System.out.print(srcString);
        int startOffset = iterator.getStartOffset();
        int endOffset = iterator.getEndOffset();
        int length = endOffset - startOffset;
        String text = htmlDoc.getText(startOffset, length);
        System.out.println(" - " + text);
    }
}

From source file:MainClass.java

public static void main(String args[]) throws Exception {
    URL url = new URL("http://www.google.com");
    URLConnection connection = url.openConnection();
    InputStream is = connection.getInputStream();
    InputStreamReader isr = new InputStreamReader(is);
    BufferedReader br = new BufferedReader(isr);

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);/* w  w  w  . j  ava 2 s  . c o m*/

    for (HTMLDocument.Iterator iterator = htmlDoc.getIterator(HTML.Tag.A); iterator.isValid(); iterator
            .next()) {

        AttributeSet attributes = iterator.getAttributes();
        String srcString = (String) attributes.getAttribute(HTML.Attribute.HREF);
        System.out.print(srcString);
        int startOffset = iterator.getStartOffset();
        int endOffset = iterator.getEndOffset();
        int length = endOffset - startOffset;
        String text = htmlDoc.getText(startOffset, length);
        System.out.println("  " + text);
    }
}

From source file:DocumentIteratorExample.java

public static void main(String args[]) throws Exception {
    URL url = new URL("http://www.java2s.com");
    URLConnection connection = url.openConnection();
    InputStream is = connection.getInputStream();
    InputStreamReader isr = new InputStreamReader(is);
    BufferedReader br = new BufferedReader(isr);

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);//from   ww  w. jav  a2s .  co  m

    for (HTMLDocument.Iterator iterator = htmlDoc.getIterator(HTML.Tag.A); iterator.isValid(); iterator
            .next()) {

        AttributeSet attributes = iterator.getAttributes();
        String srcString = (String) attributes.getAttribute(HTML.Attribute.HREF);
        System.out.print(srcString);
        int startOffset = iterator.getStartOffset();
        int endOffset = iterator.getEndOffset();
        int length = endOffset - startOffset;
        String text = htmlDoc.getText(startOffset, length);
        System.out.println(" - " + text);
    }
    System.exit(0);
}

From source file:MainClass.java

public static void main(String args[]) throws Exception {
    URL url = new URL("http://www.java2s.com");
    URLConnection connection = url.openConnection();
    InputStream is = connection.getInputStream();
    InputStreamReader isr = new InputStreamReader(is);
    BufferedReader br = new BufferedReader(isr);

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);/*from   w ww  .  java  2 s  . co  m*/

    ElementIterator iterator = new ElementIterator(htmlDoc);
    Element element;
    while ((element = iterator.next()) != null) {
        AttributeSet attributes = element.getAttributes();
        Object name = attributes.getAttribute(StyleConstants.NameAttribute);
        if ((name instanceof HTML.Tag) && (name == HTML.Tag.H1)) {
            StringBuffer text = new StringBuffer();
            int count = element.getElementCount();
            for (int i = 0; i < count; i++) {
                Element child = element.getElement(i);
                AttributeSet childAttributes = child.getAttributes();
                if (childAttributes.getAttribute(StyleConstants.NameAttribute) == HTML.Tag.CONTENT) {
                    int startOffset = child.getStartOffset();
                    int endOffset = child.getEndOffset();
                    int length = endOffset - startOffset;
                    text.append(htmlDoc.getText(startOffset, length));
                }
            }
            System.out.println(name + ": " + text.toString());
        }
    }
}

From source file:MainClass.java

public static void main(String args[]) throws Exception {
    URL url = new URL("http://www.google.com");
    URLConnection connection = url.openConnection();
    InputStream is = connection.getInputStream();
    InputStreamReader isr = new InputStreamReader(is);
    BufferedReader br = new BufferedReader(isr);

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);/*from   w w w . j a  v  a2  s  .  co  m*/

    Element element;
    ElementIterator iterator = new ElementIterator(htmlDoc);
    while ((element = iterator.next()) != null) {
        AttributeSet attributes = element.getAttributes();
        Object name = attributes.getAttribute(StyleConstants.NameAttribute);

        if ((name instanceof HTML.Tag) && (name == HTML.Tag.H1 || name == HTML.Tag.H2 || name == HTML.Tag.P)) {
            // Build up content text as it may be within multiple elements
            int count = element.getElementCount();
            for (int i = 0; i < count; i++) {
                Element child = element.getElement(i);
                AttributeSet childAttributes = child.getAttributes();
                if (childAttributes.getAttribute(StyleConstants.NameAttribute) == HTML.Tag.CONTENT) {
                    int startOffset = child.getStartOffset();
                    int endOffset = child.getEndOffset();
                    int length = endOffset - startOffset;
                    System.out.println(htmlDoc.getText(startOffset, length));
                }
            }
        }
    }
}

From source file:ElementIteratorExample.java

public static void main(String args[]) throws Exception {

    if (args.length != 1) {
        System.err.println("Usage: java ElementIteratorExample input-URL");
    }//w ww  . ja  v  a 2s  . c  om

    // Load HTML file synchronously
    URL url = new URL(args[0]);
    URLConnection connection = url.openConnection();
    InputStream is = connection.getInputStream();
    InputStreamReader isr = new InputStreamReader(is);
    BufferedReader br = new BufferedReader(isr);

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);

    // Parse
    ElementIterator iterator = new ElementIterator(htmlDoc);
    Element element;
    while ((element = iterator.next()) != null) {
        AttributeSet attributes = element.getAttributes();
        Object name = attributes.getAttribute(StyleConstants.NameAttribute);
        if ((name instanceof HTML.Tag)
                && ((name == HTML.Tag.H1) || (name == HTML.Tag.H2) || (name == HTML.Tag.H3))) {
            // Build up content text as it may be within multiple elements
            StringBuffer text = new StringBuffer();
            int count = element.getElementCount();
            for (int i = 0; i < count; i++) {
                Element child = element.getElement(i);
                AttributeSet childAttributes = child.getAttributes();
                if (childAttributes.getAttribute(StyleConstants.NameAttribute) == HTML.Tag.CONTENT) {
                    int startOffset = child.getStartOffset();
                    int endOffset = child.getEndOffset();
                    int length = endOffset - startOffset;
                    text.append(htmlDoc.getText(startOffset, length));
                }
            }
            System.out.println(name + ": " + text.toString());
        }
    }
    System.exit(0);
}

From source file:com.hexidec.ekit.action.ListAutomationAction.java

public void actionPerformed(ActionEvent ae) {
    try {// w w w .j  a v a  2  s  .co  m
        JEditorPane jepEditor = (JEditorPane) (parentEkit.getTextPane());
        String selTextBase = jepEditor.getSelectedText();
        int textLength = -1;
        if (selTextBase != null) {
            textLength = selTextBase.length();
        }
        if (selTextBase == null || textLength < 1) {
            int pos = parentEkit.getCaretPosition();
            parentEkit.setCaretPosition(pos);
            if (ae.getActionCommand() != "newListPoint") {
                if (htmlUtilities.checkParentsTag(HTML.Tag.OL) || htmlUtilities.checkParentsTag(HTML.Tag.UL)) {
                    revertList(htmlUtilities.getListItemContainer());
                    return;
                }
            }
            String sListType = (baseTag == HTML.Tag.OL ? "ol" : "ul");
            StringBuffer sbNew = new StringBuffer();
            if (htmlUtilities.checkParentsTag(baseTag)) {
                sbNew.append("<li></li>");
                insertHTML(parentEkit.getTextPane(), parentEkit.getExtendedHtmlDoc(),
                        parentEkit.getTextPane().getCaretPosition(), sbNew.toString(), 0, 0, HTML.Tag.LI);
            } else {
                boolean isLast = false;
                int caretPos = parentEkit.getCaretPosition();
                if (caretPos == parentEkit.getExtendedHtmlDoc().getLength()) {
                    isLast = true;
                }
                sbNew.append("<" + sListType + "><li></li></" + sListType + ">"
                        + (isLast ? "<p style=\"margin-top: 0\">&nbsp;</p>" : ""));
                insertHTML(parentEkit.getTextPane(), parentEkit.getExtendedHtmlDoc(),
                        parentEkit.getTextPane().getCaretPosition(), sbNew.toString(), 0, 0,
                        (sListType.equals("ol") ? HTML.Tag.OL : HTML.Tag.UL));
                if (true) {
                    parentEkit.setCaretPosition(caretPos + 1);
                }
            }
            parentEkit.refreshOnUpdate();
        } else {
            if (htmlUtilities.checkParentsTag(HTML.Tag.OL) || htmlUtilities.checkParentsTag(HTML.Tag.UL)) {
                revertList(htmlUtilities.getListItemContainer());
                return;
            } else {
                String sListType = (baseTag == HTML.Tag.OL ? "ol" : "ul");
                HTMLDocument htmlDoc = (HTMLDocument) (jepEditor.getDocument());
                int iStart = jepEditor.getSelectionStart();
                int iEnd = jepEditor.getSelectionEnd();
                String selText = htmlDoc.getText(iStart, iEnd - iStart);
                /*
                for(int ch = 0; ch < selText.length(); ch++)
                {
                   Element elem = htmlDoc.getCharacterElement(iStart + ch);
                   log.debug("elem " + ch + ": " + elem.getName());
                   log.debug("char " + ch + ": " + selText.charAt(ch) + " [" + Character.getNumericValue(selText.charAt(ch)) + "]");
                   if(Character.getNumericValue(selText.charAt(ch)) < 0)
                   {
                      log.debug("  is space?    " + ((selText.charAt(ch) == '\u0020') ? "YES" : "---"));
                      log.debug("  is return?   " + ((selText.charAt(ch) == '\r') ? "YES" : "---"));
                      log.debug("  is newline?  " + ((selText.charAt(ch) == '\n') ? "YES" : "---"));
                      log.debug("  is nextline? " + ((selText.charAt(ch) == '\u0085') ? "YES" : "---"));
                      log.debug("  is linesep?  " + ((selText.charAt(ch) == '\u2028') ? "YES" : "---"));
                      log.debug("  is parasep?  " + ((selText.charAt(ch) == '\u2029') ? "YES" : "---"));
                      log.debug("  is verttab?  " + ((selText.charAt(ch) == '\u000B') ? "YES" : "---"));
                      log.debug("  is formfeed? " + ((selText.charAt(ch) == '\u000C') ? "YES" : "---"));
                   }
                }
                */
                StringBuffer sbNew = new StringBuffer();
                sbNew.append("<" + sListType + ">");
                // tokenize on known linebreaks if present, otherwise manually parse on <br> break tags
                if ((selText.indexOf("\r") > -1) || (selText.indexOf("\n") > -1)) {
                    String sToken = ((selText.indexOf("\r") > -1) ? "\r" : "\n");
                    StringTokenizer stTokenizer = new StringTokenizer(selText, sToken);
                    while (stTokenizer.hasMoreTokens()) {
                        sbNew.append("<li>");
                        sbNew.append(stTokenizer.nextToken());
                        sbNew.append("</li>");
                    }
                } else {
                    StringBuffer sbItem = new StringBuffer();
                    for (int ch = 0; ch < selText.length(); ch++) {
                        String elem = (htmlDoc.getCharacterElement(iStart + ch) != null
                                ? htmlDoc.getCharacterElement(iStart + ch).getName().toLowerCase()
                                : "[null]");
                        if (elem.equals("br") && sbItem.length() > 0) {
                            sbNew.append("<li>");
                            sbNew.append(sbItem.toString());
                            sbNew.append("</li>");
                            sbItem.delete(0, sbItem.length());
                        } else {
                            sbItem.append(selText.charAt(ch));
                        }
                    }
                }
                sbNew.append("</" + sListType + ">");
                htmlDoc.remove(iStart, iEnd - iStart);
                insertHTML(jepEditor, htmlDoc, iStart, sbNew.toString(), 1, 1, null);
            }
        }
    } catch (BadLocationException ble) {
    }
}

From source file:org.deegree.tools.metadata.InspireValidator.java

/**
 * parse INSPIRE metadata validator response and print out result onto the console
 * /*from w w  w . j  a  va 2s  . c o m*/
 * @param response
 * @throws IOException
 * @throws IllegalStateException
 */
private void parseServiceResponse(HttpResponse response) throws Exception {
    String s = FileUtils.readTextFile(((BasicHttpResponse) response).getEntity().getContent()).toString();
    if (response.getStatusLine().getStatusCode() != 200) {
        outputWriter.println(s);
        outputWriter.println();
        return;
    }
    s = "<html><head></head><body>" + s + "</body></html>";
    BufferedReader br = new BufferedReader(new StringReader(s));

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);

    // Parse
    ElementIterator iterator = new ElementIterator(htmlDoc);
    Element element;
    while ((element = iterator.next()) != null) {
        AttributeSet attributes = element.getAttributes();
        Object name = attributes.getAttribute(StyleConstants.NameAttribute);
        if ((name instanceof HTML.Tag) && ((name == HTML.Tag.IMPLIED))) {
            // Build up content text as it may be within multiple elements
            StringBuffer text = new StringBuffer();
            int count = element.getElementCount();
            for (int i = 0; i < count; i++) {
                Element child = element.getElement(i);
                AttributeSet childAttributes = child.getAttributes();
                if (childAttributes.getAttribute(StyleConstants.NameAttribute) == HTML.Tag.CONTENT) {
                    int startOffset = child.getStartOffset();
                    int endOffset = child.getEndOffset();
                    int length = endOffset - startOffset;
                    text.append(htmlDoc.getText(startOffset, length));
                }
            }
            outputWriter.println(text.toString());
        }
    }
    outputWriter.println("---------------------------------------------------------------------");
    outputWriter.println();
}