#ifndef DOMWriter_HEADER_GUARD_ #define DOMWriter_HEADER_GUARD_ /* * Copyright 2002,2004 The Apache Software Foundation. * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ /* * $Id: DOMWriter.hpp,v 1.11 2004/09/08 13:55:39 peiyongz Exp $ * $Log: DOMWriter.hpp,v $ * Revision 1.11 2004/09/08 13:55:39 peiyongz * Apache License Version 2.0 * * Revision 1.10 2003/03/07 19:59:09 tng * [Bug 11692] Unimplement the hidden constructors and assignment operator to remove warnings from gcc. * * Revision 1.9 2002/11/27 18:46:39 tng * Documentation: clarify that DOMWriter::writeToString always returns string in UTF-16 * * Revision 1.8 2002/11/04 15:09:25 tng * C++ Namespace Support. * * Revision 1.7 2002/08/22 15:04:57 tng * Remove unused parameter variables in inline functions. * * Revision 1.6 2002/06/25 16:04:49 tng * DOM L3: add function release(). * * Revision 1.5 2002/06/06 20:53:07 tng * Documentation Fix: Update the API Documentation for DOM headers * * Revision 1.4 2002/06/03 22:33:21 peiyongz * DOMWriter: constants moved to XMLUni * * Revision 1.3 2002/05/31 20:59:40 peiyongz * Add "introduced in DOM3" * * Revision 1.2 2002/05/30 16:25:33 tng * Fix doxygen warning message. * * Revision 1.1 2002/05/28 22:38:55 peiyongz * DOM3 Save Interface: DOMWriter/DOMWriterFilter * */ /** * * DOMWriter provides an API for serializing (writing) a DOM document out in * an XML document. The XML data is written to an output stream, the type of * which depends on the specific language bindings in use. During * serialization of XML data, namespace fixup is done when possible. *

DOMWriter accepts any node type for serialization. For * nodes of type Document or Entity, well formed * XML will be created if possible. The serialized output for these node * types is either as a Document or an External Entity, respectively, and is * acceptable input for an XML parser. For all other types of nodes the * serialized form is not specified, but should be something useful to a * human for debugging or diagnostic purposes. Note: rigorously designing an * external (source) form for stand-alone node types that don't already have * one defined in seems a bit much to take on here. *

Within a Document or Entity being serialized, Nodes are processed as * follows Documents are written including an XML declaration and a DTD * subset, if one exists in the DOM. Writing a document node serializes the * entire document. Entity nodes, when written directly by * writeNode defined in the DOMWriter interface, * output the entity expansion but no namespace fixup is done. The resulting * output will be valid as an external entity. Entity References nodes are * serializes as an entity reference of the form * "&entityName;") in the output. Child nodes (the * expansion) of the entity reference are ignored. CDATA sections * containing content characters that can not be represented in the * specified output encoding are handled according to the * "split-cdata-sections" feature.If the feature is true, CDATA * sections are split, and the unrepresentable characters are serialized as * numeric character references in ordinary content. The exact position and * number of splits is not specified. If the feature is false, * unrepresentable characters in a CDATA section are reported as errors. The * error is not recoverable - there is no mechanism for supplying * alternative characters and continuing with the serialization. All other * node types (DOMElement, DOMText, etc.) are serialized to their corresponding * XML source form. *

Within the character data of a document (outside of markup), any * characters that cannot be represented directly are replaced with * character references. Occurrences of '<' and '&' are replaced by * the predefined entities &lt; and &amp. The other predefined * entities (&gt, &apos, etc.) are not used; these characters can be * included directly. Any character that can not be represented directly in * the output character encoding is serialized as a numeric character * reference. *

Attributes not containing quotes are serialized in quotes. Attributes * containing quotes but no apostrophes are serialized in apostrophes * (single quotes). Attributes containing both forms of quotes are * serialized in quotes, with quotes within the value represented by the * predefined entity &quot;. Any character that can not be represented * directly in the output character encoding is serialized as a numeric * character reference. *

Within markup, but outside of attributes, any occurrence of a character * that cannot be represented in the output character encoding is reported * as an error. An example would be serializing the element * <LaCaņada/> with the encoding="us-ascii". *

When requested by setting the normalize-characters feature * on DOMWriter, all data to be serialized, both markup and * character data, is W3C Text normalized according to the rules defined in * . The W3C Text normalization process affects only the data as it is being * written; it does not alter the DOM's view of the document after * serialization has completed. *

Namespaces are fixed up during serialization, the serialization process * will verify that namespace declarations, namespace prefixes and the * namespace URIs associated with Elements and Attributes are consistent. If * inconsistencies are found, the serialized form of the document will be * altered to remove them. The algorithm used for doing the namespace fixup * while seralizing a document is a combination of the algorithms used for * lookupNamespaceURI and lookupNamespacePrefix . previous paragraph to be * defined closer here. *

Any changes made affect only the namespace prefixes and declarations * appearing in the serialized data. The DOM's view of the document is not * altered by the serialization operation, and does not reflect any changes * made to namespace declarations or prefixes in the serialized output. *

While serializing a document the serializer will write out * non-specified values (such as attributes whose specified is * false) if the output-default-values feature is * set to true. If the output-default-values flag * is set to false and the use-abstract-schema * feature is set to true the abstract schema will be used to * determine if a value is specified or not, if * use-abstract-schema is not set the specified * flag on attribute nodes is used to determine if attribute values should * be written out. *

Ref to Core spec (1.1.9, XML namespaces, 5th paragraph) entity ref * description about warning about unbound entity refs. Entity refs are * always serialized as &foo;, also mention this in the load part of * this spec. *

When serializing a document the DOMWriter checks to see if the document * element in the document is a DOM Level 1 element or a DOM Level 2 (or * higher) element (this check is done by looking at the localName of the * root element). If the root element is a DOM Level 1 element then the * DOMWriter will issue an error if a DOM Level 2 (or higher) element is * found while serializing. Likewise if the document element is a DOM Level * 2 (or higher) element and the DOMWriter sees a DOM Level 1 element an * error is issued. Mixing DOM Level 1 elements with DOM Level 2 (or higher) * is not supported. *

DOMWriters have a number of named features that can be * queried or set. The name of DOMWriter features must be valid * XML names. Implementation specific features (extensions) should choose an * implementation dependent prefix to avoid name collisions. *

Here is a list of properties that must be recognized by all * implementations. *

*
"normalize-characters"
*
*
*
true
*
[ * optional] (default) Perform the W3C Text Normalization of the characters * in document as they are written out. Only the characters being written * are (potentially) altered. The DOM document itself is unchanged.
*
* false
*
[required] do not perform character normalization.
*
*
* "split-cdata-sections"
*
*
*
true
*
[required] (default) * Split CDATA sections containing the CDATA section termination marker * ']]>' or characters that can not be represented in the output * encoding, and output the characters using numeric character references. * If a CDATA section is split a warning is issued.
*
false
*
[ * required] Signal an error if a CDATASection contains an * unrepresentable character.
*
*
"validation"
*
*
*
true
*
[ * optional] Use the abstract schema to validate the document as it is being * serialized. If validation errors are found the error handler is notified * about the error. Setting this state will also set the feature * use-abstract-schema to true.
*
false
*
[ * required] (default) Don't validate the document as it is being * serialized.
*
*
"expand-entity-references"
*
*
*
true
*
[ * optional] Expand EntityReference nodes when serializing.
*
* false
*
[required] (default) Serialize all * EntityReference nodes as XML entity references.
*
*
* "whitespace-in-element-content"
*
*
*
true
*
[required] ( * default) Output all white spaces in the document.
*
false
*
[ * optional] Only output white space that is not within element content. The * implementation is expected to use the * isWhitespaceInElementContent flag on Text nodes * to determine if a text node should be written out or not.
*
*
* "discard-default-content"
*
*
*
true
*
[required] (default * ) Use whatever information available to the implementation (i.e. XML * schema, DTD, the specified flag on Attr nodes, * and so on) to decide what attributes and content should be serialized or * not. Note that the specified flag on Attr nodes * in itself is not always reliable, it is only reliable when it is set to * false since the only case where it can be set to * false is if the attribute was created by a Level 1 * implementation.
*
false
*
[required] Output all attributes and * all content.
*
*
"format-canonical"
*
*
*
true
*
[optional] * This formatting writes the document according to the rules specified in . * Setting this feature to true will set the feature "format-pretty-print" * to false.
*
false
*
[required] (default) Don't canonicalize the * output.
*
*
"format-pretty-print"
*
*
*
true
*
[optional] * Formatting the output by adding whitespace to produce a pretty-printed, * indented, human-readable form. The exact form of the transformations is * not specified by this specification. Setting this feature to true will * set the feature "format-canonical" to false.
*
false
*
[required] * (default) Don't pretty-print the result.
*
*
*

See also the Document Object Model (DOM) Level 3 Abstract Schemas and Load * and Save Specification. * * @since DOM Level 3 */ #include #include #include #include XERCES_CPP_NAMESPACE_BEGIN class CDOM_EXPORT DOMWriter { protected : // ----------------------------------------------------------------------- // Hidden constructors // ----------------------------------------------------------------------- /** @name Hidden constructors */ //@{ DOMWriter() {}; //@} private: // ----------------------------------------------------------------------- // Unimplemented constructors and operators // ----------------------------------------------------------------------- /** @name Unimplemented constructors and operators */ //@{ DOMWriter(const DOMWriter &); DOMWriter & operator = (const DOMWriter &); //@} public: // ----------------------------------------------------------------------- // All constructors are hidden, just the destructor is available // ----------------------------------------------------------------------- /** @name Destructor */ //@{ /** * Destructor * */ virtual ~DOMWriter() {}; //@} // ----------------------------------------------------------------------- // Virtual DOMWriter interface // ----------------------------------------------------------------------- /** @name Functions introduced in DOM Level 3 */ //@{ // ----------------------------------------------------------------------- // Feature methods // ----------------------------------------------------------------------- /** * Query whether setting a feature to a specific value is supported. *
The feature name has the same form as a DOM hasFeature string. * *

"Experimental - subject to change"

* * @param featName The feature name, which is a DOM has-feature style string. * @param state The requested state of the feature (true or * false). * @return true if the feature could be successfully set to * the specified value, or false if the feature is not * recognized or the requested value is not supported. The value of * the feature itself is not changed. * @since DOM Level 3 */ virtual bool canSetFeature(const XMLCh* const featName , bool state) const = 0; /** * Set the state of a feature. *
The feature name has the same form as a DOM hasFeature string. *
It is possible for a DOMWriter to recognize a feature * name but to be unable to set its value. * *

"Experimental - subject to change"

* * @param featName The feature name. * @param state The requested state of the feature (true or * false). * @exception DOMException * Raise a NOT_SUPPORTED_ERR exception when the DOMWriter * recognizes the feature name but cannot set the requested value. *
Raise a NOT_FOUND_ERR When the DOMWriter does not * recognize the feature name. * @see getFeature * @since DOM Level 3 */ virtual void setFeature(const XMLCh* const featName , bool state) = 0; /** * Look up the value of a feature. *
The feature name has the same form as a DOM hasFeature string * @param featName The feature name, which is a string with DOM has-feature * syntax. * @return The current state of the feature (true or * false). * @exception DOMException * Raise a NOT_FOUND_ERR When the DOMWriter does not * recognize the feature name. * *

"Experimental - subject to change"

* * @see setFeature * @since DOM Level 3 */ virtual bool getFeature(const XMLCh* const featName) const = 0; // ----------------------------------------------------------------------- // Setter methods // ----------------------------------------------------------------------- /** * The character encoding in which the output will be written. *
The encoding to use when writing is determined as follows: If the * encoding attribute has been set, that value will be used.If the * encoding attribute is null or empty, but the item to be * written includes an encoding declaration, that value will be used.If * neither of the above provides an encoding name, a default encoding of * "UTF-8" will be used. *
The default value is null. * *

"Experimental - subject to change"

* * @param encoding The character encoding in which the output will be written. * @see getEncoding * @since DOM Level 3 */ virtual void setEncoding(const XMLCh* const encoding) = 0; /** * The end-of-line sequence of characters to be used in the XML being * written out. The only permitted values are these: *
*
null
*
* Use a default end-of-line sequence. DOM implementations should choose * the default to match the usual convention for text files in the * environment being used. Implementations must choose a default * sequence that matches one of those allowed by 2.11 "End-of-Line * Handling".
*
CR
*
The carriage-return character (#xD).
*
CR-LF
*
The * carriage-return and line-feed characters (#xD #xA).
*
LF
*
The line-feed * character (#xA).
*
*
The default value for this attribute is null. * *

"Experimental - subject to change"

* * @param newLine The end-of-line sequence of characters to be used. * @see getNewLine * @since DOM Level 3 */ virtual void setNewLine(const XMLCh* const newLine) = 0; /** * The error handler that will receive error notifications during * serialization. The node where the error occured is passed to this * error handler, any modification to nodes from within an error * callback should be avoided since this will result in undefined, * implementation dependent behavior. * *

"Experimental - subject to change"

* * @param errorHandler The error handler to be used. * @see getErrorHandler * @since DOM Level 3 */ virtual void setErrorHandler(DOMErrorHandler *errorHandler) = 0; /** * When the application provides a filter, the serializer will call out * to the filter before serializing each Node. Attribute nodes are never * passed to the filter. The filter implementation can choose to remove * the node from the stream or to terminate the serialization early. * *

"Experimental - subject to change"

* * @param filter The writer filter to be used. * @see getFilter * @since DOM Level 3 */ virtual void setFilter(DOMWriterFilter *filter) = 0; // ----------------------------------------------------------------------- // Getter methods // ----------------------------------------------------------------------- /** * Return the character encoding in which the output will be written. * *

"Experimental - subject to change"

* * @return The character encoding used. * @see setEncoding * @since DOM Level 3 */ virtual const XMLCh* getEncoding() const = 0; /** * Return the end-of-line sequence of characters to be used in the XML being * written out. * *

"Experimental - subject to change"

* * @return The end-of-line sequence of characters to be used. * @see setNewLine * @since DOM Level 3 */ virtual const XMLCh* getNewLine() const = 0; /** * Return the error handler that will receive error notifications during * serialization. * *

"Experimental - subject to change"

* * @return The error handler to be used. * @see setErrorHandler * @since DOM Level 3 */ virtual DOMErrorHandler* getErrorHandler() const = 0; /** * Return the WriterFilter used. * *

"Experimental - subject to change"

* * @return The writer filter used. * @see setFilter * @since DOM Level 3 */ virtual DOMWriterFilter* getFilter() const = 0; // ----------------------------------------------------------------------- // Write methods // ----------------------------------------------------------------------- /** * Write out the specified node as described above in the description of * DOMWriter. Writing a Document or Entity node produces a * serialized form that is well formed XML. Writing other node types * produces a fragment of text in a form that is not fully defined by * this document, but that should be useful to a human for debugging or * diagnostic purposes. * *

"Experimental - subject to change"

* * @param destination The destination for the data to be written. * @param nodeToWrite The Document or Entity node to * be written. For other node types, something sensible should be * written, but the exact serialized form is not specified. * @return Returns true if node was * successfully serialized and false in case a failure * occured and the failure wasn't canceled by the error handler. * @exception DOMSystemException * This exception will be raised in response to any sort of IO or system * error that occurs while writing to the destination. It may wrap an * underlying system exception. * @since DOM Level 3 */ virtual bool writeNode(XMLFormatTarget* const destination , const DOMNode &nodeToWrite) = 0; /** * Serialize the specified node as described above in the description of * DOMWriter. The result of serializing the node is * returned as a string. Writing a Document or Entity node produces a * serialized form that is well formed XML. Writing other node types * produces a fragment of text in a form that is not fully defined by * this document, but that should be useful to a human for debugging or * diagnostic purposes. * *

"Experimental - subject to change"

* * @param nodeToWrite The node to be written. * @return Returns the serialized data, or null in case a * failure occured and the failure wasn't canceled by the error * handler. The returned string is always in UTF-16. * The encoding information available in DOMWriter is ignored in writeToString(). * @since DOM Level 3 */ virtual XMLCh* writeToString(const DOMNode &nodeToWrite) = 0; //@} // ----------------------------------------------------------------------- // Non-standard Extension // ----------------------------------------------------------------------- /** @name Non-standard Extension */ //@{ /** * Called to indicate that this Writer is no longer in use * and that the implementation may relinquish any resources associated with it. * * Access to a released object will lead to unexpected result. */ virtual void release() = 0; //@} }; XERCES_CPP_NAMESPACE_END #endif