All Downloads are FREE. Search and download functionalities are using the official Maven repository.

com.topologi.diffx.xml.esc.XMLEscapeASCII Maven / Gradle / Ivy

Go to download

docx4j is a library which helps you to work with the Office Open XML file format as used in docx documents, pptx presentations, and xlsx spreadsheets.

The newest version!
/*
 * This file is part of the DiffX library.
 *
 * For licensing information please see the file license.txt included in the release.
 * A copy of this licence can also be found at
 *   http://www.opensource.org/licenses/artistic-license-2.0.php
 */
package com.topologi.diffx.xml.esc;

/**
 * A singleton for escaping XML data when using the 'ASCII' encoding.
 *
 * @author  Christophe Lauret
 * @version 16 January 2007
 */
public final class XMLEscapeASCII extends XMLEscapeBase implements XMLEscape {

  /**
   * A static instance of the UTF8 escape class.
   */
  public static final XMLEscape ASCII_ESCAPE = new XMLEscapeASCII();

  /**
   * The encoding used for this instance.
   */
  private static final String ENCODING = "ASCII";

  /**
   * Prevent creation of instances
   */
  private XMLEscapeASCII() {
    super(ENCODING);
  }

  /**
   * Replaces '<', '&', '"' and '\'' as well an any character that is not part of
   * the standard unicode range.
   *
   * 
   * Char ::= #x9 | #xA | #xD |
   *          [#x20-#xD7FF] |
   *          [#xE000-#xFFFD] |
   *          [#x10000-#x10FFFF]
   * 
* * {@inheritDoc} */ @Override public String toAttributeValue(char[] ch, int off, int len) { // process the rest StringBuffer out = new StringBuffer(len + len / 10); for (int i = off; i < off+len; i++) { // 0x00 to 0x1F if (ch[i] < 0x20) { // tabs, new lines and line feeds: preserve if (ch[i] == 0x09 || ch[i] == 0x0A || ch[i] == 0x0D) { out.append(ch[i]); } else { doNothing(); // 0x20 to 0x7F } } else if (ch[i] < 0x80) { switch (ch[i]) { case '&' : out.append("&"); break; case '<' : out.append("<"); break; case '"' : out.append("""); break; case '\'' : out.append("'"); break; // output by default default: out.append(ch[i]); } // control characters (C1): prune } else if (ch[i] < 0xA0) { doNothing(); // all other characters: use numerical character entity } else { out.append("&#x").append((int)ch[i]).append(';'); } } return out.toString(); } /** * Replace characters which are invalid in element values, * by the corresponding entity in a given String. * *

these characters are:
*

    *
  • '&' by the ampersand entity "&amp"
  • *
  • '<' by the entity "&lt;"
  • *
*

* *

Empty strings or null return respectively * "" and null. * *

Note: this function assumes that there are no entities in * the given String. If there are existing entities, then the * ampersand character will be escaped by the ampersand entity. * * {@inheritDoc} */ @Override public String toElementText(char[] ch, int off, int len) { // process the rest StringBuffer out = new StringBuffer(len + len / 10); for (int i = off; i < off+len; i++) { // 0x00 to 0x1F if (ch[i] < 0x20) { // tabs, new lines and line feeds: preserve if (ch[i] == 0x09 || ch[i] == 0x0A || ch[i] == 0x0D) { out.append(ch[i]); } else { doNothing(); // 0x20 to 0x7F } } else if (ch[i] < 0x80) { switch (ch[i]) { case '&' : out.append("&"); break; case '<' : out.append("<"); break; // output by default default: out.append(ch[i]); } // control characters (C1): prune } else if (ch[i] < 0xA0) { doNothing(); // all other characters: use numerical character entity } else { out.append("&#x").append((int)ch[i]).append(';'); } } return out.toString(); } /** * Does nothing. */ private void doNothing() { } }





© 2015 - 2024 Weber Informatics LLC | Privacy Policy