1 /*
2 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
3 *
4 * This code is free software; you can redistribute it and/or modify it
5 * under the terms of the GNU General Public License version 2 only, as
6 * published by the Free Software Foundation. Oracle designates this
7 * particular file as subject to the "Classpath" exception as provided
8 * by Oracle in the LICENSE file that accompanied this code.
9 *
10 * This code is distributed in the hope that it will be useful, but WITHOUT
11 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
12 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
13 * version 2 for more details (a copy is included in the LICENSE file that
14 * accompanied this code).
15 *
16 * You should have received a copy of the GNU General Public License version
17 * 2 along with this work; if not, write to the Free Software Foundation,
18 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
19 *
20 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
21 * or visit www.oracle.com if you need additional information or have any
22 * questions.
23 */
24
25 /*
26 * This file is available under and governed by the GNU General Public
27 * License version 2 only, as published by the Free Software Foundation.
28 * However, the following notice accompanied the original version of this
29 * file and, per its terms, should not be removed:
30 *
31 * Copyright (c) 2004 World Wide Web Consortium,
32 *
33 * (Massachusetts Institute of Technology, European Research Consortium for
34 * Informatics and Mathematics, Keio University). All Rights Reserved. This
35 * work is distributed under the W3C(r) Software License [1] in the hope that
36 * it will be useful, but WITHOUT ANY WARRANTY; without even the implied
37 * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
38 *
39 * [1] http://www.w3.org/Consortium/Legal/2002/copyright-software-20021231
40 */
41
42 package org.w3c.dom;
43
44 /**
45 * The <code>Text</code> interface inherits from <code>CharacterData</code>
46 * 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
47 * markup inside an element's content, the text is contained in a single
48 * object implementing the <code>Text</code> interface that is the only
49 * child of the element. If there is markup, it is parsed into the
50 * information items (elements, comments, etc.) and <code>Text</code> nodes
51 * that form the list of children of the element.
52 * <p>When a document is first made available via the DOM, there is only one
53 * <code>Text</code> node for each block of text. Users may create adjacent
54 * <code>Text</code> nodes that represent the contents of a given element
55 * without any intervening markup, but should be aware that there is no way
56 * to represent the separations between these nodes in XML or HTML, so they
57 * will not (in general) persist between DOM editing sessions. The
58 * <code>Node.normalize()</code> method merges any such adjacent
59 * <code>Text</code> objects into a single node for each block of text.
60 * <p> No lexical check is done on the content of a <code>Text</code> node
61 * and, depending on its position in the document, some characters must be
62 * escaped during serialization using character references; e.g. the
63 * characters "<&" if the textual content is part of an element or of
64 * an attribute, the character sequence "]]>" when part of an element,
65 * the quotation mark character " or the apostrophe character ' when part of
66 * an attribute.
67 * <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>.
68 */
69 public interface Text extends CharacterData {
70 /**
71 * Breaks this node into two nodes at the specified <code>offset</code>,
72 * keeping both in the tree as siblings. After being split, this node
73 * will contain all the content up to the <code>offset</code> point. A
74 * new node of the same type, which contains all the content at and
75 * after the <code>offset</code> point, is returned. If the original
76 * node had a parent node, the new node is inserted as the next sibling
77 * of the original node. When the <code>offset</code> is equal to the
78 * length of this node, the new node has no data.
79 * @param offset The 16-bit unit offset at which to split, starting from
80 * <code>0</code>.
81 * @return The new node, of the same type as this node.
82 * @exception DOMException
83 * INDEX_SIZE_ERR: Raised if the specified offset is negative or greater
84 * than the number of 16-bit units in <code>data</code>.
85 * <br>NO_MODIFICATION_ALLOWED_ERR: Raised if this node is readonly.
86 */
87 public Text splitText(int offset)
88 throws DOMException;
89
90 /**
91 * Returns whether this text node contains <a href='http://www.w3.org/TR/2004/REC-xml-infoset-20040204#infoitem.character'>
92 * element content whitespace</a>, often abusively called "ignorable whitespace". The text node is
93 * determined to contain whitespace in element content during the load
94 * of the document or if validation occurs while using
95 * <code>Document.normalizeDocument()</code>.
96 * @since DOM Level 3
97 */
98 public boolean isElementContentWhitespace();
99
100 /**
101 * Returns all text of <code>Text</code> nodes logically-adjacent text
102 * nodes to this node, concatenated in document order.
103 * <br>For instance, in the example below <code>wholeText</code> on the
104 * <code>Text</code> node that contains "bar" returns "barfoo", while on
105 * the <code>Text</code> node that contains "foo" it returns "barfoo".
106 *
107 * <pre>
108 * +-----+
109 * | <p> |
110 * +-----+
111 * /\
112 * / \
113 * /-----\ +-------+
114 * | bar | | &ent; |
115 * \-----/ +-------+
116 * |
117 * |
118 * /-----\
119 * | foo |
120 * \-----/
121 * </pre>
122 * <em>Figure: barTextNode.wholeText value is "barfoo"</em>
123 *
124 * @since DOM Level 3
125 */
126 public String getWholeText();
127
128 /**
129 * Replaces the text of the current node and all logically-adjacent text
130 * nodes with the specified text. All logically-adjacent text nodes are
131 * removed including the current node unless it was the recipient of the
132 * replacement text.
133 * <p>This method returns the node which received the replacement text.
134 * The returned node is:</p>
135 * <ul>
136 * <li><code>null</code>, when the replacement text is
137 * the empty string;
138 * </li>
139 * <li>the current node, except when the current node is
140 * read-only;
141 * </li>
142 * <li> a new <code>Text</code> node of the same type (
143 * <code>Text</code> or <code>CDATASection</code>) as the current node
144 * inserted at the location of the replacement.
145 * </li>
146 * </ul>
147 * <p>For instance, in the above example calling
148 * <code>replaceWholeText</code> on the <code>Text</code> node that
149 * contains "bar" with "yo" in argument results in the following:</p>
150 *
151 * <pre>
152 * +-----+
153 * | <p> |
154 * +-----+
155 * |
156 * |
157 * /-----\
158 * | yo |
159 * \-----/
160 * </pre>
161 * <em>Figure: barTextNode.replaceWholeText("yo") modifies the
162 * textual content of barTextNode with "yo"</em>
163 *
164 * <p>Where the nodes to be removed are read-only descendants of an
165 * <code>EntityReference</code>, the <code>EntityReference</code> must
166 * be removed instead of the read-only nodes. If any
167 * <code>EntityReference</code> to be removed has descendants that are
168 * not <code>EntityReference</code>, <code>Text</code>, or
169 * <code>CDATASection</code> nodes, the <code>replaceWholeText</code>
170 * method must fail before performing any modification of the document,
171 * raising a <code>DOMException</code> with the code
172 * <code>NO_MODIFICATION_ALLOWED_ERR</code>.</p>
173 * <p>For instance, in the example below calling
174 * <code>replaceWholeText</code> on the <code>Text</code> node that
175 * contains "bar" fails, because the <code>EntityReference</code> node
176 * "ent" contains an <code>Element</code> node which cannot be removed.</p>
177 * @param content The content of the replacing <code>Text</code> node.
178 * @return The <code>Text</code> node created with the specified content.
179 * @exception DOMException
180 * NO_MODIFICATION_ALLOWED_ERR: Raised if one of the <code>Text</code>
181 * nodes being replaced is readonly.
182 * @since DOM Level 3
183 */
184 public Text replaceWholeText(String content)
185 throws DOMException;
186
187 }