dtm.java

JAVA 所有包

/*
 * Copyright 1999-2004 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: DTM.java,v 1.2.4.1 2005/09/15 08:14:51 suresh_emailid Exp $
 */
package com.sun.org.apache.xml.internal.dtm;

import javax.xml.transform.SourceLocator;

import com.sun.org.apache.xml.internal.utils.XMLString;

/**
 * <code>DTM</code> is an XML document model expressed as a table
 * rather than an object tree. It attempts to provide an interface to
 * a parse tree that has very little object creation. (DTM
 * implementations may also support incremental construction of the
 * model, but that's hidden from the DTM API.)
 *
 * <p>Nodes in the DTM are identified by integer "handles".  A handle must
 * be unique within a process, and carries both node identification and
 * document identification.  It must be possible to compare two handles
 * (and thus their nodes) for identity with "==".</p>
 *
 * <p>Namespace URLs, local-names, and expanded-names can all be
 * represented by and tested as integer ID values.  An expanded name
 * represents (and may or may not directly contain) a combination of
 * the URL ID, and the local-name ID.  Note that the namespace URL id
 * can be 0, which should have the meaning that the namespace is null.
 * For consistancy, zero should not be used for a local-name index. </p>
 *
 * <p>Text content of a node is represented by an index and length,
 * permitting efficient storage such as a shared FastStringBuffer.</p>
 *
 * <p>The model of the tree, as well as the general navigation model,
 * is that of XPath 1.0, for the moment.  The model will eventually be
 * adapted to match the XPath 2.0 data model, XML Schema, and
 * InfoSet.</p>
 *
 * <p>DTM does _not_ directly support the W3C's Document Object
 * Model. However, it attempts to come close enough that an
 * implementation of DTM can be created that wraps a DOM and vice
 * versa.</p>
 *
 * <p><strong>Please Note:</strong> The DTM API is still
 * <strong>Subject To Change.</strong> This wouldn't affect most
 * users, but might require updating some extensions.</p>
 *
 * <p> The largest change being contemplated is a reconsideration of
 * the Node Handle representation.  We are still not entirely sure
 * that an integer packed with two numeric subfields is really the
 * best solution. It has been suggested that we move up to a Long, to
 * permit more nodes per document without having to reduce the number
 * of slots in the DTMManager. There's even been a proposal that we
 * replace these integers with "cursor" objects containing the
 * internal node id and a pointer to the actual DTM object; this might
 * reduce the need to continuously consult the DTMManager to retrieve
 * the latter, and might provide a useful "hook" back into normal Java
 * heap management.  But changing this datatype would have huge impact
 * on Xalan's internals -- especially given Java's lack of C-style
 * typedefs -- so we won't cut over unless we're convinced the new
 * solution really would be an improvement!</p>
 * */
public interface DTM
{

  /**
   * Null node handles are represented by this value.
   */
  public static final int NULL = -1;

  // These nodeType mnemonics and values are deliberately the same as those
  // used by the DOM, for convenient mapping
  //
  // %REVIEW% Should we actually define these as initialized to,
  // eg. org.w3c.dom.Document.ELEMENT_NODE?

  /**
   * The node is a <code>Root</code>.
   */
  public static final short ROOT_NODE = 0;
  
  /**
   * The node is an <code>Element</code>.
   */
  public static final short ELEMENT_NODE = 1;

  /**
   * The node is an <code>Attr</code>.
   */
  public static final short ATTRIBUTE_NODE = 2;

  /**
   * The node is a <code>Text</code> node.
   */
  public static final short TEXT_NODE = 3;

  /**
   * The node is a <code>CDATASection</code>.
   */
  public static final short CDATA_SECTION_NODE = 4;

  /**
   * The node is an <code>EntityReference</code>.
   */
  public static final short ENTITY_REFERENCE_NODE = 5;

  /**
   * The node is an <code>Entity</code>.
   */
  public static final short ENTITY_NODE = 6;

  /**
   * The node is a <code>ProcessingInstruction</code>.
   */
  public static final short PROCESSING_INSTRUCTION_NODE = 7;

  /**
   * The node is a <code>Comment</code>.
   */
  public static final short COMMENT_NODE = 8;

  /**
   * The node is a <code>Document</code>.
   */
  public static final short DOCUMENT_NODE = 9;

  /**
   * The node is a <code>DocumentType</code>.
   */
  public static final short DOCUMENT_TYPE_NODE = 10;

  /**
   * The node is a <code>DocumentFragment</code>.
   */
  public static final short DOCUMENT_FRAGMENT_NODE = 11;

  /**
   * The node is a <code>Notation</code>.
   */
  public static final short NOTATION_NODE = 12;

  /**
   * The node is a <code>namespace node</code>. Note that this is not
   * currently a node type defined by the DOM API.
   */
  public static final short NAMESPACE_NODE = 13;
  
  /**
   * The number of valid nodetypes.
   */
  public static final short  NTYPES = 14;

  // ========= DTM Implementation Control Functions. ==============
  // %TBD% RETIRED -- do via setFeature if needed. Remove from impls.
  // public void setParseBlockSize(int blockSizeSuggestion);

  /**
   * Set an implementation dependent feature.
   * <p>
   * %REVIEW% Do we really expect to set features on DTMs?
   *
   * @param featureId A feature URL.
   * @param state true if this feature should be on, false otherwise.
   */
  public void setFeature(String featureId, boolean state);

  /**
   * Set a run time property for this DTM instance.
   *
   * @param property a <code>String</code> value
   * @param value an <code>Object</code> value
   */
  public void setProperty(String property, Object value);

  // ========= Document Navigation Functions =========

  /**
   * This returns a stateless "traverser", that can navigate over an
   * XPath axis, though not in document order.
   *
   * @param axis One of Axes.ANCESTORORSELF, etc.
   *
   * @return A DTMAxisIterator, or null if the givin axis isn't supported.
   */
  public DTMAxisTraverser getAxisTraverser(final int axis);

  /**
   * This is a shortcut to the iterators that implement
   * XPath axes.
   * Returns a bare-bones iterator that must be initialized
   * with a start node (using iterator.setStartNode()).
   *
   * @param axis One of Axes.ANCESTORORSELF, etc.
   *
   * @return A DTMAxisIterator, or null if the givin axis isn't supported.
   */
  public DTMAxisIterator getAxisIterator(final int axis);

  /**
   * Get an iterator that can navigate over an XPath Axis, predicated by
   * the extended type ID.
   *
   * @param axis
   * @param type An extended type ID.
   *
   * @return A DTMAxisIterator, or null if the givin axis isn't supported.
   */
  public DTMAxisIterator getTypedAxisIterator(final int axis, final int type);

  /**
   * Given a node handle, test if it has child nodes.
   * <p> %REVIEW% This is obviously useful at the DOM layer, where it
   * would permit testing this without having to create a proxy
   * node. It's less useful in the DTM API, where
   * (dtm.getFirstChild(nodeHandle)!=DTM.NULL) is just as fast and
   * almost as self-evident. But it's a convenience, and eases porting
   * of DOM code to DTM.  </p>
   *
   * @param nodeHandle int Handle of the node.
   * @return int true if the given node has child nodes.
   */
  public boolean hasChildNodes(int nodeHandle);

  /**
   * Given a node handle, get the handle of the node's first child.
   *
   * @param nodeHandle int Handle of the node.
   * @return int DTM node-number of first child,
   * or DTM.NULL to indicate none exists.
   */
  public int getFirstChild(int nodeHandle);

  /**
   * Given a node handle, get the handle of the node's last child.
   *
   * @param nodeHandle int Handle of the node.
   * @return int Node-number of last child,
   * or DTM.NULL to indicate none exists.
   */
  public int getLastChild(int nodeHandle);

  /**
   * Retrieves an attribute node by local name and namespace URI
   *
   * %TBD% Note that we currently have no way to support
   * the DOM's old getAttribute() call, which accesses only the qname.
   *
   * @param elementHandle Handle of the node upon which to look up this attribute.
   * @param namespaceURI The namespace URI of the attribute to
   *   retrieve, or null.
   * @param name The local name of the attribute to
   *   retrieve.
   * @return The attribute node handle with the specified name (
   *   <code>nodeName</code>) or <code>DTM.NULL</code> if there is no such
   *   attribute.
   */
  public int getAttributeNode(int elementHandle, String namespaceURI,
                              String name);

  /**
   * Given a node handle, get the index of the node's first attribute.
   *
   * @param nodeHandle int Handle of the node.
   * @return Handle of first attribute, or DTM.NULL to indicate none exists.
   */
  public int getFirstAttribute(int nodeHandle);

  /**
   * Given a node handle, get the index of the node's first namespace node.
   *
   * @param nodeHandle handle to node, which should probably be an element
   *                   node, but need not be.
   *
   * @param inScope true if all namespaces in scope should be
   *                   returned, false if only the node's own
   *                   namespace declarations should be returned.
   * @return handle of first namespace,
   * or DTM.NULL to indicate none exists.
   */
  public int getFirstNamespaceNode(int nodeHandle, boolean inScope);

  /**
   * Given a node handle, advance to its next sibling.
   * @param nodeHandle int Handle of the node.
   * @return int Node-number of next sibling,
   * or DTM.NULL to indicate none exists.
   */
  public int getNextSibling(int nodeHandle);

  /**
   * Given a node handle, find its preceeding sibling.
   * WARNING: DTM implementations may be asymmetric; in some,
   * this operation has been resolved by search, and is relatively expensive.
   *
   * @param nodeHandle the id of the node.
   * @return int Node-number of the previous sib,
   * or DTM.NULL to indicate none exists.
   */
  public int getPreviousSibling(int nodeHandle);

  /**
   * Given a node handle, advance to the next attribute. If an
   * element, we advance to its first attribute; if an attr, we advance to
   * the next attr of the same element.
   *
   * @param nodeHandle int Handle of the node.
   * @return int DTM node-number of the resolved attr,
   * or DTM.NULL to indicate none exists.
   */