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 * The <code>Text</code> interface inherits from <code>CharacterData</code>
017 * and represents the textual content (termed <a href='http://www.w3.org/TR/2004/REC-xml-20040204#syntax'>character data</a> in XML) of an <code>Element</code> or <code>Attr</code>. If there is no
018 * markup inside an element's content, the text is contained in a single
019 * object implementing the <code>Text</code> interface that is the only
020 * child of the element. If there is markup, it is parsed into the
021 * information items (elements, comments, etc.) and <code>Text</code> nodes
022 * that form the list of children of the element.
023 * <p>When a document is first made available via the DOM, there is only one
024 * <code>Text</code> node for each block of text. Users may create adjacent
025 * <code>Text</code> nodes that represent the contents of a given element
026 * without any intervening markup, but should be aware that there is no way
027 * to represent the separations between these nodes in XML or HTML, so they
028 * will not (in general) persist between DOM editing sessions. The
029 * <code>Node.normalize()</code> method merges any such adjacent
030 * <code>Text</code> objects into a single node for each block of text.
031 * <p> No lexical check is done on the content of a <code>Text</code> node
032 * and, depending on its position in the document, some characters must be
033 * escaped during serialization using character references; e.g. the
034 * characters "<&" if the textual content is part of an element or of
035 * an attribute, the character sequence "]]>" when part of an element,
036 * the quotation mark character " or the apostrophe character ' when part of
037 * an attribute.
038 * <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>.
039 */
040 public interface Text extends CharacterData {
041 /**
042 * Breaks this node into two nodes at the specified <code>offset</code>,
043 * keeping both in the tree as siblings. After being split, this node
044 * will contain all the content up to the <code>offset</code> point. A
045 * new node of the same type, which contains all the content at and
046 * after the <code>offset</code> point, is returned. If the original
047 * node had a parent node, the new node is inserted as the next sibling
048 * of the original node. When the <code>offset</code> is equal to the
049 * length of this node, the new node has no data.
050 * @param offset The 16-bit unit offset at which to split, starting from
051 * <code>0</code>.
052 * @return The new node, of the same type as this node.
053 * @exception DOMException
054 * INDEX_SIZE_ERR: Raised if the specified offset is negative or greater
055 * than the number of 16-bit units in <code>data</code>.
056 * <br>NO_MODIFICATION_ALLOWED_ERR: Raised if this node is readonly.
057 */
058 public Text splitText(int offset)
059 throws DOMException;
060
061 /**
062 * Returns whether this text node contains <a href='http://www.w3.org/TR/2004/REC-xml-infoset-20040204#infoitem.character'>
063 * element content whitespace</a>, often abusively called "ignorable whitespace". The text node is
064 * determined to contain whitespace in element content during the load
065 * of the document or if validation occurs while using
066 * <code>Document.normalizeDocument()</code>.
067 * @since DOM Level 3
068 */
069 public boolean isElementContentWhitespace();
070
071 /**
072 * Returns all text of <code>Text</code> nodes logically-adjacent text
073 * nodes to this node, concatenated in document order.
074 * <br>For instance, in the example below <code>wholeText</code> on the
075 * <code>Text</code> node that contains "bar" returns "barfoo", while on
076 * the <code>Text</code> node that contains "foo" it returns "barfoo".
077 * @since DOM Level 3
078 */
079 public String getWholeText();
080
081 /**
082 * Replaces the text of the current node and all logically-adjacent text
083 * nodes with the specified text. All logically-adjacent text nodes are
084 * removed including the current node unless it was the recipient of the
085 * replacement text.
086 * <br>This method returns the node which received the replacement text.
087 * The returned node is:
088 * <ul>
089 * <li><code>null</code>, when the replacement text is
090 * the empty string;
091 * </li>
092 * <li>the current node, except when the current node is
093 * read-only;
094 * </li>
095 * <li> a new <code>Text</code> node of the same type (
096 * <code>Text</code> or <code>CDATASection</code>) as the current node
097 * inserted at the location of the replacement.
098 * </li>
099 * </ul>
100 * <br>For instance, in the above example calling
101 * <code>replaceWholeText</code> on the <code>Text</code> node that
102 * contains "bar" with "yo" in argument results in the following:
103 * <br>Where the nodes to be removed are read-only descendants of an
104 * <code>EntityReference</code>, the <code>EntityReference</code> must
105 * be removed instead of the read-only nodes. If any
106 * <code>EntityReference</code> to be removed has descendants that are
107 * not <code>EntityReference</code>, <code>Text</code>, or
108 * <code>CDATASection</code> nodes, the <code>replaceWholeText</code>
109 * method must fail before performing any modification of the document,
110 * raising a <code>DOMException</code> with the code
111 * <code>NO_MODIFICATION_ALLOWED_ERR</code>.
112 * <br>For instance, in the example below calling
113 * <code>replaceWholeText</code> on the <code>Text</code> node that
114 * contains "bar" fails, because the <code>EntityReference</code> node
115 * "ent" contains an <code>Element</code> node which cannot be removed.
116 * @param content The content of the replacing <code>Text</code> node.
117 * @return The <code>Text</code> node created with the specified content.
118 * @exception DOMException
119 * NO_MODIFICATION_ALLOWED_ERR: Raised if one of the <code>Text</code>
120 * nodes being replaced is readonly.
121 * @since DOM Level 3
122 */
123 public Text replaceWholeText(String content)
124 throws DOMException;
125
126 }