1 /*
2  * Copyright (c) 2004 World Wide Web Consortium,
3  *
4  * (Massachusetts Institute of Technology, European Research Consortium for
5  * Informatics and Mathematics, Keio University). All Rights Reserved. This
6  * work is distributed under the W3C(r) Software License [1] in the hope that
7  * it will be useful, but WITHOUT ANY WARRANTY; without even the implied
8  * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
9  *
10  * [1] http://www.w3.org/Consortium/Legal/2002/copyright-software-20021231
11  */
12 
13 package org.w3c.dom;
14 
15 /**
16  *  The <code>DOMConfiguration</code> interface represents the configuration
17  * of a document and maintains a table of recognized parameters. Using the
18  * configuration, it is possible to change
19  * <code>Document.normalizeDocument()</code> behavior, such as replacing the
20  * <code>CDATASection</code> nodes with <code>Text</code> nodes or
21  * specifying the type of the schema that must be used when the validation
22  * of the <code>Document</code> is requested. <code>DOMConfiguration</code>
23  * 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>]
24  *  in the <code>DOMParser</code> and <code>DOMSerializer</code> interfaces.
25  * <p> The parameter names used by the <code>DOMConfiguration</code> object
26  * are defined throughout the DOM Level 3 specifications. Names are
27  * case-insensitive. To avoid possible conflicts, as a convention, names
28  * referring to parameters defined outside the DOM specification should be
29  * made unique. Because parameters are exposed as properties in the , names
30  * are recommended to follow the section 5.16 Identifiers of [Unicode] with the addition of the character '-' (HYPHEN-MINUS) but it is not
31  * enforced by the DOM implementation. DOM Level 3 Core Implementations are
32  * required to recognize all parameters defined in this specification. Some
33  * parameter values may also be required to be supported by the
34  * implementation. Refer to the definition of the parameter to know if a
35  * value must be supported or not.
36  * <p ><b>Note:</b>  Parameters are similar to features and properties used in
37  * SAX2 [<a href='http://www.saxproject.org/'>SAX</a>].
38  * <p> The following list of parameters defined in the DOM:
39  * <dl>
40  * <dt>
41  * <code>"canonical-form"</code></dt>
42  * <dd>
43  * <dl>
44  * <dt><code>true</code></dt>
45  * <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>],
46  * such as removing the <code>DocumentType</code> node (if any) from the
47  * tree, or removing superfluous namespace declarations from each element.
48  * Note that this is limited to what can be represented in the DOM; in
49  * particular, there is no way to specify the order of the attributes in the
50  * DOM. In addition,  Setting this parameter to <code>true</code> will also
51  * set the state of the parameters listed below. Later changes to the state
52  * of one of those parameters will revert "canonical-form" back to
53  * <code>false</code>. Parameters set to <code>false</code>: "entities", "
54  * normalize-characters", "cdata-sections". Parameters set to
55  * <code>true</code>: "namespaces", "namespace-declarations", "well-formed",
56  * "element-content-whitespace". Other parameters are not changed unless
57  * explicitly specified in the description of the parameters.</dd>
58  * <dt>
59  * <code>false</code></dt>
60  * <dd>[<em>required</em>] (<em>default</em>)Do not canonicalize the document.</dd>
61  * </dl></dd>
62  * <dt><code>"cdata-sections"</code></dt>
63  * <dd>
64  * <dl>
65  * <dt>
66  * <code>true</code></dt>
67  * <dd>[<em>required</em>] (<em>default</em>)Keep <code>CDATASection</code> nodes in the document.</dd>
68  * <dt><code>false</code></dt>
69  * <dd>[<em>required</em>]Transform <code>CDATASection</code> nodes in the document into
70  * <code>Text</code> nodes. The new <code>Text</code> node is then combined
71  * with any adjacent <code>Text</code> node.</dd>
72  * </dl></dd>
73  * <dt>
74  * <code>"check-character-normalization"</code></dt>
75  * <dd>
76  * <dl>
77  * <dt><code>true</code></dt>
78  * <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
79  * 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
80  * sequence of characters is encountered that fails normalization checking,
81  * an error with the <code>DOMError.type</code> equals to
82  * "check-character-normalization-failure" is issued. </dd>
83  * <dt><code>false</code></dt>
84  * <dd>[<em>required</em>] (<em>default</em>)Do not check if characters are normalized.</dd>
85  * </dl></dd>
86  * <dt><code>"comments"</code></dt>
87  * <dd>
88  * <dl>
89  * <dt>
90  * <code>true</code></dt>
91  * <dd>[<em>required</em>] (<em>default</em>)Keep <code>Comment</code> nodes in the document.</dd>
92  * <dt><code>false</code></dt>
93  * <dd>[<em>required</em>]Discard <code>Comment</code> nodes in the document.</dd>
94  * </dl></dd>
95  * <dt>
96  * <code>"datatype-normalization"</code></dt>
97  * <dd>
98  * <dl>
99  * <dt><code>true</code></dt>
100  * <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
101  * Schema normalized values</a> in the case of XML Schema. Since this parameter requires to have schema
102  * information, the "validate" parameter will also be set to
103  * <code>true</code>. Having this parameter activated when "validate" is
104  * <code>false</code> has no effect and no schema-normalization will happen.
105  * <p ><b>Note:</b>  Since the document contains the result of the XML 1.0
106  * processing, this parameter does not apply to attribute value
107  * 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
108  * meant for schema languages other than Document Type Definition (DTD). </dd>
109  * <dt>
110  * <code>false</code></dt>
111  * <dd>[<em>required</em>] (<em>default</em>) Do not perform schema normalization on the tree. </dd>
112  * </dl></dd>
113  * <dt>
114  * <code>"element-content-whitespace"</code></dt>
115  * <dd>
116  * <dl>
117  * <dt><code>true</code></dt>
118  * <dd>[<em>required</em>] (<em>default</em>)Keep all whitespaces in the document.</dd>
119  * <dt><code>false</code></dt>
120  * <dd>[<em>optional</em>] Discard all <code>Text</code> nodes that contain whitespaces in element
121  * content, as described in <a href='http://www.w3.org/TR/2004/REC-xml-infoset-20040204#infoitem.character'>
122  * [element content whitespace]</a>. The implementation is expected to use the attribute
123  * <code>Text.isElementContentWhitespace</code> to determine if a
124  * <code>Text</code> node should be discarded or not.</dd>
125  * </dl></dd>
126  * <dt><code>"entities"</code></dt>
127  * <dd>
128  * <dl>
129  * <dt>
130  * <code>true</code></dt>
131  * <dd>[<em>required</em>] (<em>default</em>)Keep <code>EntityReference</code> nodes in the document.</dd>
132  * <dt>
133  * <code>false</code></dt>
134  * <dd>[<em>required</em>] Remove all <code>EntityReference</code> nodes from the document,
135  * putting the entity expansions directly in their place. <code>Text</code>
136  * 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'>
137  * unexpanded entity references</a> are kept in the document. </dd>
138  * </dl>
139  * <p ><b>Note:</b>  This parameter does not affect <code>Entity</code> nodes. </dd>
140  * <dt>
141  * <code>"error-handler"</code></dt>
142  * <dd>[<em>required</em>] Contains a <code>DOMErrorHandler</code> object. If an error is
143  * encountered in the document, the implementation will call back the
144  * <code>DOMErrorHandler</code> registered using this parameter. The
145  * implementation may provide a default <code>DOMErrorHandler</code> object.
146  *  When called, <code>DOMError.relatedData</code> will contain the closest
147  * node to where the error occurred. If the implementation is unable to
148  * determine the node where the error occurs,
149  * <code>DOMError.relatedData</code> will contain the <code>Document</code>
150  * node. Mutations to the document from within an error handler will result
151  * in implementation dependent behavior. </dd>
152  * <dt><code>"infoset"</code></dt>
153  * <dd>
154  * <dl>
155  * <dt>
156  * <code>true</code></dt>
157  * <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>]
158  * .This forces the following parameters to <code>false</code>: "
159  * validate-if-schema", "entities", "datatype-normalization", "cdata-sections
160  * ".This forces the following parameters to <code>true</code>: "
161  * namespace-declarations", "well-formed", "element-content-whitespace", "
162  * comments", "namespaces".Other parameters are not changed unless
163  * explicitly specified in the description of the parameters. Note that
164  * querying this parameter with <code>getParameter</code> returns
165  * <code>true</code> only if the individual parameters specified above are
166  * appropriately set.</dd>
167  * <dt><code>false</code></dt>
168  * <dd>Setting <code>infoset</code> to
169  * <code>false</code> has no effect.</dd>
170  * </dl></dd>
171  * <dt><code>"namespaces"</code></dt>
172  * <dd>
173  * <dl>
174  * <dt>
175  * <code>true</code></dt>
176  * <dd>[<em>required</em>] (<em>default</em>) Perform the namespace processing as defined in . </dd>
177  * <dt><code>false</code></dt>
178  * <dd>[<em>optional</em>] Do not perform the namespace processing. </dd>
179  * </dl></dd>
180  * <dt>
181  * <code>"namespace-declarations"</code></dt>
182  * <dd> This parameter has no effect if the
183  * parameter "namespaces" is set to <code>false</code>.
184  * <dl>
185  * <dt><code>true</code></dt>
186  * <dd>[<em>required</em>] (<em>default</em>) Include namespace declaration attributes, specified or defaulted from
187  * the schema, in the document. See also the sections "Declaring Namespaces"
188  * in [<a href='http://www.w3.org/TR/1999/REC-xml-names-19990114/'>XML Namespaces</a>]
189  *  and [<a href='http://www.w3.org/TR/2004/REC-xml-names11-20040204/'>XML Namespaces 1.1</a>]
190  * .</dd>
191  * <dt><code>false</code></dt>
192  * <dd>[<em>required</em>]Discard all namespace declaration attributes. The namespace prefixes (
193  * <code>Node.prefix</code>) are retained even if this parameter is set to
194  * <code>false</code>.</dd>
195  * </dl></dd>
196  * <dt><code>"normalize-characters"</code></dt>
197  * <dd>
198  * <dl>
199  * <dt><code>true</code></dt>
200  * <dd>[<em>optional</em>] <a href='http://www.w3.org/TR/2004/REC-xml11-20040204/#dt-fullnorm'>Fully
201  * 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>
202  * <dt>
203  * <code>false</code></dt>
204  * <dd>[<em>required</em>] (<em>default</em>)Do not perform character normalization.</dd>
205  * </dl></dd>
206  * <dt><code>"schema-location"</code></dt>
207  * <dd>[<em>optional</em>] Represent a <code>DOMString</code> object containing a list of URIs,
208  * separated by whitespaces (characters matching the <a href='http://www.w3.org/TR/2004/REC-xml-20040204#NT-S'>nonterminal
209  * production S</a> defined in section 2.3 [<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>]), that
210  * represents the schemas against which validation should occur, i.e. the
211  * current schema. The types of schemas referenced in this list must match
212  * the type specified with <code>schema-type</code>, otherwise the behavior
213  * of an implementation is undefined.  The schemas specified using this
214  * property take precedence to the schema information specified in the
215  * document itself. For namespace aware schema, if a schema specified using
216  * this property and a schema specified in the document instance (i.e. using
217  * the <code>schemaLocation</code> attribute) in a schema document (i.e.
218  * using schema <code>import</code> mechanisms) share the same
219  * <code>targetNamespace</code>, the schema specified by the user using this
220  * property will be used. If two schemas specified using this property share
221  * the same <code>targetNamespace</code> or have no namespace, the behavior
222  * is implementation dependent.  If no location has been provided, this
223  * parameter is <code>null</code>.
224  * <p ><b>Note:</b>  The <code>"schema-location"</code> parameter is ignored
225  * unless the "schema-type" parameter value is set. It is strongly
226  * recommended that <code>Document.documentURI</code> will be set so that an
227  * implementation can successfully resolve any external entities referenced. </dd>
228  * <dt>
229  * <code>"schema-type"</code></dt>
230  * <dd>[<em>optional</em>] Represent a <code>DOMString</code> object containing an absolute URI
231  * and representing the type of the schema language used to validate a
232  * document against. Note that no lexical checking is done on the absolute
233  * URI.  If this parameter is not set, a default value may be provided by
234  * the implementation, based on the schema languages supported and on the
235  * schema language used at load time. If no value is provided, this
236  * parameter is <code>null</code>.
237  * <p ><b>Note:</b>  For XML Schema [<a href='http://www.w3.org/TR/2001/REC-xmlschema-1-20010502/'>XML Schema Part 1</a>]
238  * , applications must use the value
239  * <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>],
240  * applications must use the value
241  * <code>"http://www.w3.org/TR/REC-xml"</code>. Other schema languages are
242  * outside the scope of the W3C and therefore should recommend an absolute
243  * URI in order to use this method. </dd>
244  * <dt><code>"split-cdata-sections"</code></dt>
245  * <dd>
246  * <dl>
247  * <dt>
248  * <code>true</code></dt>
249  * <dd>[<em>required</em>] (<em>default</em>)Split CDATA sections containing the CDATA section termination marker
250  * ']]&gt;'. When a CDATA section is split a warning is issued with a
251  * <code>DOMError.type</code> equals to
252  * <code>"cdata-sections-splitted"</code> and
253  * <code>DOMError.relatedData</code> equals to the first
254  * <code>CDATASection</code> node in document order resulting from the split.</dd>
255  * <dt>
256  * <code>false</code></dt>
257  * <dd>[<em>required</em>]Signal an error if a <code>CDATASection</code> contains an
258  * unrepresentable character.</dd>
259  * </dl></dd>
260  * <dt><code>"validate"</code></dt>
261  * <dd>
262  * <dl>
263  * <dt><code>true</code></dt>
264  * <dd>[<em>optional</em>] Require the validation against a schema (i.e. XML schema, DTD, any
265  * other type or representation of schema) of the document as it is being
266  * normalized as defined by [<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>]. If
267  * validation errors are found, or no schema was found, the error handler is
268  * notified. Schema-normalized values will not be exposed according to the
269  * schema in used unless the parameter "datatype-normalization" is
270  * <code>true</code>.  This parameter will reevaluate:
271  * <ul>
272  * <li> Attribute nodes with
273  * <code>Attr.specified</code> equals to <code>false</code>, as specified in
274  * the description of the <code>Attr</code> interface;
275  * </li>
276  * <li> The value of the
277  * attribute <code>Text.isElementContentWhitespace</code> for all
278  * <code>Text</code> nodes;
279  * </li>
280  * <li> The value of the attribute
281  * <code>Attr.isId</code> for all <code>Attr</code> nodes;
282  * </li>
283  * <li> The attributes
284  * <code>Element.schemaTypeInfo</code> and <code>Attr.schemaTypeInfo</code>.
285  * </li>
286  * </ul>
287  * <p ><b>Note:</b>  "validate-if-schema" and "validate" are mutually
288  * exclusive, setting one of them to <code>true</code> will set the other
289  * one to <code>false</code>. Applications should also consider setting the
290  * parameter "well-formed" to <code>true</code>, which is the default for
291  * that option, when validating the document. </dd>
292  * <dt><code>false</code></dt>
293  * <dd>[<em>required</em>] (<em>default</em>) Do not accomplish schema processing, including the internal subset
294  * processing. Default attribute values information are kept. Note that
295  * validation might still happen if "validate-if-schema" is <code>true</code>
296  * . </dd>
297  * </dl></dd>
298  * <dt><code>"validate-if-schema"</code></dt>
299  * <dd>
300  * <dl>
301  * <dt><code>true</code></dt>
302  * <dd>[<em>optional</em>]Enable validation only if a declaration for the document element can be
303  * found in a schema (independently of where it is found, i.e. XML schema,
304  * DTD, or any other type or representation of schema). If validation is
305  * enabled, this parameter has the same behavior as the parameter "validate"
306  * set to <code>true</code>.
307  * <p ><b>Note:</b>  "validate-if-schema" and "validate" are mutually
308  * exclusive, setting one of them to <code>true</code> will set the other
309  * one to <code>false</code>. </dd>
310  * <dt><code>false</code></dt>
311  * <dd>[<em>required</em>] (<em>default</em>) No schema processing should be performed if the document has a schema,
312  * including internal subset processing. Default attribute values
313  * information are kept. Note that validation must still happen if "validate
314  * " is <code>true</code>. </dd>
315  * </dl></dd>
316  * <dt><code>"well-formed"</code></dt>
317  * <dd>
318  * <dl>
319  * <dt><code>true</code></dt>
320  * <dd>[<em>required</em>] (<em>default</em>) Check if all nodes are XML well formed according to the XML version in
321  * use in <code>Document.xmlVersion</code>:
322  * <ul>
323  * <li> check if the attribute
324  * <code>Node.nodeName</code> contains invalid characters according to its
325  * node type and generate a <code>DOMError</code> of type
326  * <code>"wf-invalid-character-in-node-name"</code>, with a
327  * <code>DOMError.SEVERITY_ERROR</code> severity, if necessary;
328  * </li>
329  * <li> check if
330  * the text content inside <code>Attr</code>, <code>Element</code>,
331  * <code>Comment</code>, <code>Text</code>, <code>CDATASection</code> nodes
332  * for invalid characters and generate a <code>DOMError</code> of type
333  * <code>"wf-invalid-character"</code>, with a
334  * <code>DOMError.SEVERITY_ERROR</code> severity, if necessary;
335  * </li>
336  * <li> check if
337  * the data inside <code>ProcessingInstruction</code> nodes for invalid
338  * characters and generate a <code>DOMError</code> of type
339  * <code>"wf-invalid-character"</code>, with a
340  * <code>DOMError.SEVERITY_ERROR</code> severity, if necessary;
341  * </li>
342  * </ul></dd>
343  * <dt>
344  * <code>false</code></dt>
345  * <dd>[<em>optional</em>] Do not check for XML well-formedness. </dd>
346  * </dl></dd>
347  * </dl>
348  * <p> The resolution of the system identifiers associated with entities is
349  * done using <code>Document.documentURI</code>. However, when the feature
350  * "LS" defined in [<a href='http://www.w3.org/TR/2004/REC-DOM-Level-3-LS-20040407'>DOM Level 3 Load and Save</a>]
351  *  is supported by the DOM implementation, the parameter
352  * "resource-resolver" can also be used on <code>DOMConfiguration</code>
353  * objects attached to <code>Document</code> nodes. If this parameter is
354  * set, <code>Document.normalizeDocument()</code> will invoke the resource
355  * resolver instead of using <code>Document.documentURI</code>.
356  * <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>.
357  * @since DOM Level 3
358  */
359 public interface DOMConfiguration {
360     /**
361      * Set the value of a parameter.
362      * @param name The name of the parameter to set.
363      * @param value  The new value or <code>null</code> if the user wishes to
364      *   unset the parameter. While the type of the value parameter is
365      *   defined as <code>DOMUserData</code>, the object type must match the
366      *   type defined by the definition of the parameter. For example, if
367      *   the parameter is "error-handler", the value must be of type
368      *   <code>DOMErrorHandler</code>.
369      * @exception DOMException
370      *    NOT_FOUND_ERR: Raised when the parameter name is not recognized.
371      *   <br> NOT_SUPPORTED_ERR: Raised when the parameter name is recognized
372      *   but the requested value cannot be set.
373      *   <br> TYPE_MISMATCH_ERR: Raised if the value type for this parameter
374      *   name is incompatible with the expected value type.
375      */
setParameter(String name, Object value)376     public void setParameter(String name,
377                              Object value)
378                              throws DOMException;
379 
380     /**
381      *  Return the value of a parameter if known.
382      * @param name  The name of the parameter.
383      * @return  The current object associated with the specified parameter or
384      *   <code>null</code> if no object has been associated or if the
385      *   parameter is not supported.
386      * @exception DOMException
387      *    NOT_FOUND_ERR: Raised when the parameter name is not recognized.
388      */
getParameter(String name)389     public Object getParameter(String name)
390                                throws DOMException;
391 
392     /**
393      * Check if setting a parameter to a specific value is supported.
394      * @param name The name of the parameter to check.
395      * @param value  An object. if <code>null</code>, the returned value is
396      *   <code>true</code>.
397      * @return  <code>true</code> if the parameter could be successfully set
398      *   to the specified value, or <code>false</code> if the parameter is
399      *   not recognized or the requested value is not supported. This does
400      *   not change the current value of the parameter itself.
401      */
canSetParameter(String name, Object value)402     public boolean canSetParameter(String name,
403                                    Object value);
404 
405     /**
406      *  The list of the parameters supported by this
407      * <code>DOMConfiguration</code> object and for which at least one value
408      * can be set by the application. Note that this list can also contain
409      * parameter names defined outside this specification.
410      */
getParameterNames()411     public DOMStringList getParameterNames();
412 
413 }
414