001    /*
002     * Copyright (c) 2004 World Wide Web Consortium,
003     *
004     * (Massachusetts Institute of Technology, European Research Consortium for
005     * Informatics and Mathematics, Keio University). All Rights Reserved. This
006     * work is distributed under the W3C(r) Software License [1] in the hope that
007     * it will be useful, but WITHOUT ANY WARRANTY; without even the implied
008     * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
009     *
010     * [1] http://www.w3.org/Consortium/Legal/2002/copyright-software-20021231
011     */
012    
013    package org.w3c.dom;
014    
015    /**
016     * CDATA sections are used to escape blocks of text containing characters that
017     * would otherwise be regarded as markup. The only delimiter that is
018     * recognized in a CDATA section is the "]]>" string that ends the CDATA
019     * section. CDATA sections cannot be nested. Their primary purpose is for
020     * including material such as XML fragments, without needing to escape all
021     * the delimiters.
022     * <p>The <code>CharacterData.data</code> attribute holds the text that is
023     * contained by the CDATA section. Note that this <em>may</em> contain characters that need to be escaped outside of CDATA sections and
024     * that, depending on the character encoding ("charset") chosen for
025     * serialization, it may be impossible to write out some characters as part
026     * of a CDATA section.
027     * <p>The <code>CDATASection</code> interface inherits from the
028     * <code>CharacterData</code> interface through the <code>Text</code>
029     * interface. Adjacent <code>CDATASection</code> nodes are not merged by use
030     * of the <code>normalize</code> method of the <code>Node</code> interface.
031     * <p> No lexical check is done on the content of a CDATA section and it is
032     * therefore possible to have the character sequence <code>"]]&gt;"</code>
033     * in the content, which is illegal in a CDATA section per section 2.7 of [<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>]. The
034     * presence of this character sequence must generate a fatal error during
035     * serialization or the cdata section must be splitted before the
036     * serialization (see also the parameter <code>"split-cdata-sections"</code>
037     * in the <code>DOMConfiguration</code> interface).
038     * <p ><b>Note:</b> Because no markup is recognized within a
039     * <code>CDATASection</code>, character numeric references cannot be used as
040     * an escape mechanism when serializing. Therefore, action needs to be taken
041     * when serializing a <code>CDATASection</code> with a character encoding
042     * where some of the contained characters cannot be represented. Failure to
043     * do so would not produce well-formed XML.
044     * <p ><b>Note:</b> One potential solution in the serialization process is to
045     * end the CDATA section before the character, output the character using a
046     * character reference or entity reference, and open a new CDATA section for
047     * any further characters in the text node. Note, however, that some code
048     * conversion libraries at the time of writing do not return an error or
049     * exception when a character is missing from the encoding, making the task
050     * of ensuring that data is not corrupted on serialization more difficult.
051     * <p>See also the <a href='http://www.w3.org/TR/2004/REC-DOM-Level-3-Core-20040407'>Document Object Model (DOM) Level 3 Core Specification</a>.
052     */
053    public interface CDATASection extends Text {
054    }