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>DOMConfiguration</code> interface represents the configuration
46 * of a document and maintains a table of recognized parameters. Using the
47 * configuration, it is possible to change
48 * <code>Document.normalizeDocument()</code> behavior, such as replacing the
49 * <code>CDATASection</code> nodes with <code>Text</code> nodes or
50 * specifying the type of the schema that must be used when the validation
51 * of the <code>Document</code> is requested. <code>DOMConfiguration</code>
52 * objects are also used in [<a href='http://www.w3.org/TR/2004/REC-DOM-Level-3-LS-20040407'>DOM Level 3 Load and Save</a>]
53 * in the <code>DOMParser</code> and <code>DOMSerializer</code> interfaces.
54 * <p> The parameter names used by the <code>DOMConfiguration</code> object
55 * are defined throughout the DOM Level 3 specifications. Names are
56 * case-insensitive. To avoid possible conflicts, as a convention, names
57 * referring to parameters defined outside the DOM specification should be
58 * made unique. Because parameters are exposed as properties in names
59 * are recommended to follow the section 5.16 Identifiers of [Unicode] with the addition of the character '-' (HYPHEN-MINUS) but it is not
60 * enforced by the DOM implementation. DOM Level 3 Core Implementations are
61 * required to recognize all parameters defined in this specification. Some
62 * parameter values may also be required to be supported by the
63 * implementation. Refer to the definition of the parameter to know if a
64 * value must be supported or not.
65 * <p ><b>Note:</b> Parameters are similar to features and properties used in
66 * SAX2 [<a href='http://www.saxproject.org/'>SAX</a>].
67 * <p> The following list of parameters defined in the DOM:
68 * <dl>
69 * <dt>
70 * <code>"canonical-form"</code></dt>
71 * <dd>
72 * <dl>
73 * <dt><code>true</code></dt>
74 * <dd>[<em>optional</em>] Canonicalize the document according to the rules specified in [<a href='http://www.w3.org/TR/2001/REC-xml-c14n-20010315'>Canonical XML</a>],
75 * such as removing the <code>DocumentType</code> node (if any) from the
76 * tree, or removing superfluous namespace declarations from each element.
77 * Note that this is limited to what can be represented in the DOM; in
78 * particular, there is no way to specify the order of the attributes in the
79 * DOM. In addition, Setting this parameter to <code>true</code> will also
80 * set the state of the parameters listed below. Later changes to the state
81 * of one of those parameters will revert "canonical-form" back to
82 * <code>false</code>. Parameters set to <code>false</code>: "entities", "
83 * normalize-characters", "cdata-sections". Parameters set to
84 * <code>true</code>: "namespaces", "namespace-declarations", "well-formed",
85 * "element-content-whitespace". Other parameters are not changed unless
86 * explicitly specified in the description of the parameters.</dd>
87 * <dt>
88 * <code>false</code></dt>
89 * <dd>[<em>required</em>] (<em>default</em>)Do not canonicalize the document.</dd>
90 * </dl></dd>
91 * <dt><code>"cdata-sections"</code></dt>
92 * <dd>
93 * <dl>
94 * <dt>
95 * <code>true</code></dt>
96 * <dd>[<em>required</em>] (<em>default</em>)Keep <code>CDATASection</code> nodes in the document.</dd>
97 * <dt><code>false</code></dt>
98 * <dd>[<em>required</em>]Transform <code>CDATASection</code> nodes in the document into
99 * <code>Text</code> nodes. The new <code>Text</code> node is then combined
100 * with any adjacent <code>Text</code> node.</dd>
101 * </dl></dd>
102 * <dt>
103 * <code>"check-character-normalization"</code></dt>
104 * <dd>
105 * <dl>
106 * <dt><code>true</code></dt>
107 * <dd>[<em>optional</em>] Check if the characters in the document are <a href='http://www.w3.org/TR/2004/REC-xml11-20040204/#dt-fullnorm'>fully
108 * normalized</a>, as defined in appendix B of [<a href='http://www.w3.org/TR/2004/REC-xml11-20040204/'>XML 1.1</a>]. When a
109 * sequence of characters is encountered that fails normalization checking,
110 * an error with the <code>DOMError.type</code> equals to
111 * "check-character-normalization-failure" is issued. </dd>
112 * <dt><code>false</code></dt>
113 * <dd>[<em>required</em>] (<em>default</em>)Do not check if characters are normalized.</dd>
114 * </dl></dd>
115 * <dt><code>"comments"</code></dt>
116 * <dd>
117 * <dl>
118 * <dt>
119 * <code>true</code></dt>
120 * <dd>[<em>required</em>] (<em>default</em>)Keep <code>Comment</code> nodes in the document.</dd>
121 * <dt><code>false</code></dt>
122 * <dd>[<em>required</em>]Discard <code>Comment</code> nodes in the document.</dd>
123 * </dl></dd>
124 * <dt>
125 * <code>"datatype-normalization"</code></dt>
126 * <dd>
127 * <dl>
128 * <dt><code>true</code></dt>
129 * <dd>[<em>optional</em>] Expose schema normalized values in the tree, such as <a href='http://www.w3.org/TR/2001/REC-xmlschema-1-20010502/#key-nv'>XML
130 * Schema normalized values</a> in the case of XML Schema. Since this parameter requires to have schema
131 * information, the "validate" parameter will also be set to
132 * <code>true</code>. Having this parameter activated when "validate" is
133 * <code>false</code> has no effect and no schema-normalization will happen.
134 * <p ><b>Note:</b> Since the document contains the result of the XML 1.0
135 * processing, this parameter does not apply to attribute value
136 * normalization as defined in section 3.3.3 of [<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>] and is only
137 * meant for schema languages other than Document Type Definition (DTD). </dd>
138 * <dt>
139 * <code>false</code></dt>
140 * <dd>[<em>required</em>] (<em>default</em>) Do not perform schema normalization on the tree. </dd>
141 * </dl></dd>
142 * <dt>
143 * <code>"element-content-whitespace"</code></dt>
144 * <dd>
145 * <dl>
146 * <dt><code>true</code></dt>
147 * <dd>[<em>required</em>] (<em>default</em>)Keep all whitespaces in the document.</dd>
148 * <dt><code>false</code></dt>
149 * <dd>[<em>optional</em>] Discard all <code>Text</code> nodes that contain whitespaces in element
150 * content, as described in <a href='http://www.w3.org/TR/2004/REC-xml-infoset-20040204#infoitem.character'>
151 * [element content whitespace]</a>. The implementation is expected to use the attribute
152 * <code>Text.isElementContentWhitespace</code> to determine if a
153 * <code>Text</code> node should be discarded or not.</dd>
154 * </dl></dd>
155 * <dt><code>"entities"</code></dt>
156 * <dd>
157 * <dl>
158 * <dt>
159 * <code>true</code></dt>
160 * <dd>[<em>required</em>] (<em>default</em>)Keep <code>EntityReference</code> nodes in the document.</dd>
161 * <dt>
162 * <code>false</code></dt>
163 * <dd>[<em>required</em>] Remove all <code>EntityReference</code> nodes from the document,
164 * putting the entity expansions directly in their place. <code>Text</code>
165 * nodes are normalized, as defined in <code>Node.normalize</code>. Only <a href='http://www.w3.org/TR/2004/REC-xml-infoset-20040204/#infoitem.rse'>
166 * unexpanded entity references</a> are kept in the document. </dd>
167 * </dl>
168 * <p ><b>Note:</b> This parameter does not affect <code>Entity</code> nodes. </dd>
169 * <dt>
170 * <code>"error-handler"</code></dt>
171 * <dd>[<em>required</em>] Contains a <code>DOMErrorHandler</code> object. If an error is
172 * encountered in the document, the implementation will call back the
173 * <code>DOMErrorHandler</code> registered using this parameter. The
174 * implementation may provide a default <code>DOMErrorHandler</code> object.
175 * When called, <code>DOMError.relatedData</code> will contain the closest
176 * node to where the error occurred. If the implementation is unable to
177 * determine the node where the error occurs,
178 * <code>DOMError.relatedData</code> will contain the <code>Document</code>
179 * node. Mutations to the document from within an error handler will result
180 * in implementation dependent behavior. </dd>
181 * <dt><code>"infoset"</code></dt>
182 * <dd>
183 * <dl>
184 * <dt>
185 * <code>true</code></dt>
186 * <dd>[<em>required</em>]Keep in the document the information defined in the XML Information Set [<a href='http://www.w3.org/TR/2004/REC-xml-infoset-20040204/'>XML Information Set</a>]
187 * .This forces the following parameters to <code>false</code>: "
188 * validate-if-schema", "entities", "datatype-normalization", "cdata-sections
189 * ".This forces the following parameters to <code>true</code>: "
190 * namespace-declarations", "well-formed", "element-content-whitespace", "
191 * comments", "namespaces".Other parameters are not changed unless
192 * explicitly specified in the description of the parameters. Note that
193 * querying this parameter with <code>getParameter</code> returns
194 * <code>true</code> only if the individual parameters specified above are
195 * appropriately set.</dd>
196 * <dt><code>false</code></dt>
197 * <dd>Setting <code>infoset</code> to
198 * <code>false</code> has no effect.</dd>
199 * </dl></dd>
200 * <dt><code>"namespaces"</code></dt>
201 * <dd>
202 * <dl>
203 * <dt>
204 * <code>true</code></dt>
205 * <dd>[<em>required</em>] (<em>default</em>) Perform the namespace processing as defined in . </dd>
206 * <dt><code>false</code></dt>
207 * <dd>[<em>optional</em>] Do not perform the namespace processing. </dd>
208 * </dl></dd>
209 * <dt>
210 * <code>"namespace-declarations"</code></dt>
211 * <dd> This parameter has no effect if the
212 * parameter "namespaces" is set to <code>false</code>.
213 * <dl>
214 * <dt><code>true</code></dt>
215 * <dd>[<em>required</em>] (<em>default</em>) Include namespace declaration attributes, specified or defaulted from
216 * the schema, in the document. See also the sections "Declaring Namespaces"
217 * in [<a href='http://www.w3.org/TR/1999/REC-xml-names-19990114/'>XML Namespaces</a>]
218 * and [<a href='http://www.w3.org/TR/2004/REC-xml-names11-20040204/'>XML Namespaces 1.1</a>]
219 * .</dd>
220 * <dt><code>false</code></dt>
221 * <dd>[<em>required</em>]Discard all namespace declaration attributes. The namespace prefixes (
222 * <code>Node.prefix</code>) are retained even if this parameter is set to
223 * <code>false</code>.</dd>
224 * </dl></dd>
225 * <dt><code>"normalize-characters"</code></dt>
226 * <dd>
227 * <dl>
228 * <dt><code>true</code></dt>
229 * <dd>[<em>optional</em>] <a href='http://www.w3.org/TR/2004/REC-xml11-20040204/#dt-fullnorm'>Fully
230 * normalized</a> the characters in the document as defined in appendix B of [<a href='http://www.w3.org/TR/2004/REC-xml11-20040204/'>XML 1.1</a>]. </dd>
231 * <dt>
232 * <code>false</code></dt>
233 * <dd>[<em>required</em>] (<em>default</em>)Do not perform character normalization.</dd>
234 * </dl></dd>
235 * <dt><code>"schema-location"</code></dt>
236 * <dd>[<em>optional</em>] Represent a <code>DOMString</code> object containing a list of URIs,
237 * separated by whitespaces (characters matching the <a href='http://www.w3.org/TR/2004/REC-xml-20040204#NT-S'>nonterminal
238 * production S</a> defined in section 2.3 [<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>]), that
239 * represents the schemas against which validation should occur, i.e. the
240 * current schema. The types of schemas referenced in this list must match
241 * the type specified with <code>schema-type</code>, otherwise the behavior
242 * of an implementation is undefined. The schemas specified using this
243 * property take precedence to the schema information specified in the
244 * document itself. For namespace aware schema, if a schema specified using
245 * this property and a schema specified in the document instance (i.e. using
246 * the <code>schemaLocation</code> attribute) in a schema document (i.e.
247 * using schema <code>import</code> mechanisms) share the same
248 * <code>targetNamespace</code>, the schema specified by the user using this
249 * property will be used. If two schemas specified using this property share
250 * the same <code>targetNamespace</code> or have no namespace, the behavior
251 * is implementation dependent. If no location has been provided, this
252 * parameter is <code>null</code>.
253 * <p ><b>Note:</b> The <code>"schema-location"</code> parameter is ignored
254 * unless the "schema-type" parameter value is set. It is strongly
255 * recommended that <code>Document.documentURI</code> will be set so that an
256 * implementation can successfully resolve any external entities referenced. </dd>
257 * <dt>
258 * <code>"schema-type"</code></dt>
259 * <dd>[<em>optional</em>] Represent a <code>DOMString</code> object containing an absolute URI
260 * and representing the type of the schema language used to validate a
261 * document against. Note that no lexical checking is done on the absolute
262 * URI. If this parameter is not set, a default value may be provided by
263 * the implementation, based on the schema languages supported and on the
264 * schema language used at load time. If no value is provided, this
265 * parameter is <code>null</code>.
266 * <p ><b>Note:</b> For XML Schema [<a href='http://www.w3.org/TR/2001/REC-xmlschema-1-20010502/'>XML Schema Part 1</a>]
267 * , applications must use the value
268 * <code>"http://www.w3.org/2001/XMLSchema"</code>. For XML DTD [<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>],
269 * applications must use the value
270 * <code>"http://www.w3.org/TR/REC-xml"</code>. Other schema languages are
271 * outside the scope of the W3C and therefore should recommend an absolute
272 * URI in order to use this method. </dd>
273 * <dt><code>"split-cdata-sections"</code></dt>
274 * <dd>
275 * <dl>
276 * <dt>
277 * <code>true</code></dt>
278 * <dd>[<em>required</em>] (<em>default</em>)Split CDATA sections containing the CDATA section termination marker
279 * ']]>'. When a CDATA section is split a warning is issued with a
280 * <code>DOMError.type</code> equals to
281 * <code>"cdata-sections-splitted"</code> and
282 * <code>DOMError.relatedData</code> equals to the first
283 * <code>CDATASection</code> node in document order resulting from the split.</dd>
284 * <dt>
285 * <code>false</code></dt>
286 * <dd>[<em>required</em>]Signal an error if a <code>CDATASection</code> contains an
287 * unrepresentable character.</dd>
288 * </dl></dd>
289 * <dt><code>"validate"</code></dt>
290 * <dd>
291 * <dl>
292 * <dt><code>true</code></dt>
293 * <dd>[<em>optional</em>] Require the validation against a schema (i.e. XML schema, DTD, any
294 * other type or representation of schema) of the document as it is being
295 * normalized as defined by [<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>]. If
296 * validation errors are found, or no schema was found, the error handler is
297 * notified. Schema-normalized values will not be exposed according to the
298 * schema in used unless the parameter "datatype-normalization" is
299 * <code>true</code>. This parameter will reevaluate:
300 * <ul>
301 * <li> Attribute nodes with
302 * <code>Attr.specified</code> equals to <code>false</code>, as specified in
303 * the description of the <code>Attr</code> interface;
304 * </li>
305 * <li> The value of the
306 * attribute <code>Text.isElementContentWhitespace</code> for all
307 * <code>Text</code> nodes;
308 * </li>
309 * <li> The value of the attribute
310 * <code>Attr.isId</code> for all <code>Attr</code> nodes;
311 * </li>
312 * <li> The attributes
313 * <code>Element.schemaTypeInfo</code> and <code>Attr.schemaTypeInfo</code>.
314 * </li>
315 * </ul>
316 * <p ><b>Note:</b> "validate-if-schema" and "validate" are mutually
317 * exclusive, setting one of them to <code>true</code> will set the other
318 * one to <code>false</code>. Applications should also consider setting the
319 * parameter "well-formed" to <code>true</code>, which is the default for
320 * that option, when validating the document. </dd>
321 * <dt><code>false</code></dt>
322 * <dd>[<em>required</em>] (<em>default</em>) Do not accomplish schema processing, including the internal subset
323 * processing. Default attribute values information are kept. Note that
324 * validation might still happen if "validate-if-schema" is <code>true</code>
325 * . </dd>
326 * </dl></dd>
327 * <dt><code>"validate-if-schema"</code></dt>
328 * <dd>
329 * <dl>
330 * <dt><code>true</code></dt>
331 * <dd>[<em>optional</em>]Enable validation only if a declaration for the document element can be
332 * found in a schema (independently of where it is found, i.e. XML schema,
333 * DTD, or any other type or representation of schema). If validation is
334 * enabled, this parameter has the same behavior as the parameter "validate"
335 * set to <code>true</code>.
336 * <p ><b>Note:</b> "validate-if-schema" and "validate" are mutually
337 * exclusive, setting one of them to <code>true</code> will set the other
338 * one to <code>false</code>. </dd>
339 * <dt><code>false</code></dt>
340 * <dd>[<em>required</em>] (<em>default</em>) No schema processing should be performed if the document has a schema,
341 * including internal subset processing. Default attribute values
342 * information are kept. Note that validation must still happen if "validate
343 * " is <code>true</code>. </dd>
344 * </dl></dd>
345 * <dt><code>"well-formed"</code></dt>
346 * <dd>
347 * <dl>
348 * <dt><code>true</code></dt>
349 * <dd>[<em>required</em>] (<em>default</em>) Check if all nodes are XML well formed according to the XML version in
350 * use in <code>Document.xmlVersion</code>:
351 * <ul>
352 * <li> check if the attribute
353 * <code>Node.nodeName</code> contains invalid characters according to its
354 * node type and generate a <code>DOMError</code> of type
355 * <code>"wf-invalid-character-in-node-name"</code>, with a
356 * <code>DOMError.SEVERITY_ERROR</code> severity, if necessary;
357 * </li>
358 * <li> check if
359 * the text content inside <code>Attr</code>, <code>Element</code>,
360 * <code>Comment</code>, <code>Text</code>, <code>CDATASection</code> nodes
361 * for invalid characters and generate a <code>DOMError</code> of type
362 * <code>"wf-invalid-character"</code>, with a
363 * <code>DOMError.SEVERITY_ERROR</code> severity, if necessary;
364 * </li>
365 * <li> check if
366 * the data inside <code>ProcessingInstruction</code> nodes for invalid
367 * characters and generate a <code>DOMError</code> of type
368 * <code>"wf-invalid-character"</code>, with a
369 * <code>DOMError.SEVERITY_ERROR</code> severity, if necessary;
370 * </li>
371 * </ul></dd>
372 * <dt>
373 * <code>false</code></dt>
374 * <dd>[<em>optional</em>] Do not check for XML well-formedness. </dd>
375 * </dl></dd>
376 * </dl>
377 * <p> The resolution of the system identifiers associated with entities is
378 * done using <code>Document.documentURI</code>. However, when the feature
379 * "LS" defined in [<a href='http://www.w3.org/TR/2004/REC-DOM-Level-3-LS-20040407'>DOM Level 3 Load and Save</a>]
380 * is supported by the DOM implementation, the parameter
381 * "resource-resolver" can also be used on <code>DOMConfiguration</code>
382 * objects attached to <code>Document</code> nodes. If this parameter is
383 * set, <code>Document.normalizeDocument()</code> will invoke the resource
384 * resolver instead of using <code>Document.documentURI</code>.
385 * <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>.
386 * @since DOM Level 3
387 */
388 public interface DOMConfiguration {
389 /**
390 * Set the value of a parameter.
391 * @param name The name of the parameter to set.
392 * @param value The new value or <code>null</code> if the user wishes to
393 * unset the parameter. While the type of the value parameter is
394 * defined as <code>DOMUserData</code>, the object type must match the
395 * type defined by the definition of the parameter. For example, if
396 * the parameter is "error-handler", the value must be of type
397 * <code>DOMErrorHandler</code>.
398 * @exception DOMException
399 * NOT_FOUND_ERR: Raised when the parameter name is not recognized.
400 * <br> NOT_SUPPORTED_ERR: Raised when the parameter name is recognized
401 * but the requested value cannot be set.
402 * <br> TYPE_MISMATCH_ERR: Raised if the value type for this parameter
403 * name is incompatible with the expected value type.
404 */
405 public void setParameter(String name,
406 Object value)
407 throws DOMException;
408
409 /**
410 * Return the value of a parameter if known.
411 * @param name The name of the parameter.
412 * @return The current object associated with the specified parameter or
413 * <code>null</code> if no object has been associated or if the
414 * parameter is not supported.
415 * @exception DOMException
416 * NOT_FOUND_ERR: Raised when the parameter name is not recognized.
417 */
418 public Object getParameter(String name)
419 throws DOMException;
420
421 /**
422 * Check if setting a parameter to a specific value is supported.
423 * @param name The name of the parameter to check.
424 * @param value An object. if <code>null</code>, the returned value is
425 * <code>true</code>.
426 * @return <code>true</code> if the parameter could be successfully set
427 * to the specified value, or <code>false</code> if the parameter is
428 * not recognized or the requested value is not supported. This does
429 * not change the current value of the parameter itself.
430 */
431 public boolean canSetParameter(String name,
432 Object value);
433
434 /**
435 * The list of the parameters supported by this
436 * <code>DOMConfiguration</code> object and for which at least one value
437 * can be set by the application. Note that this list can also contain
438 * parameter names defined outside this specification.
439 */
440 public DOMStringList getParameterNames();
441
442 }