All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.apache.xerces.impl.xs.opti.SchemaDOM Maven / Gradle / Ivy

Go to download

Xerces2 is the next generation of high performance, fully compliant XML parsers in the Apache Xerces family. This new version of Xerces introduces the Xerces Native Interface (XNI), a complete framework for building parser components and configurations that is extremely modular and easy to program. The Apache Xerces2 parser is the reference implementation of XNI but other parser components, configurations, and parsers can be written using the Xerces Native Interface. For complete design and implementation documents, refer to the XNI Manual. Xerces2 is a fully conforming XML Schema 1.0 processor. A partial experimental implementation of the XML Schema 1.1 Structures and Datatypes Working Drafts (December 2009) and an experimental implementation of the XML Schema Definition Language (XSD): Component Designators (SCD) Candidate Recommendation (January 2010) are provided for evaluation. For more information, refer to the XML Schema page. Xerces2 also provides a complete implementation of the Document Object Model Level 3 Core and Load/Save W3C Recommendations and provides a complete implementation of the XML Inclusions (XInclude) W3C Recommendation. It also provides support for OASIS XML Catalogs v1.1. Xerces2 is able to parse documents written according to the XML 1.1 Recommendation, except that it does not yet provide an option to enable normalization checking as described in section 2.13 of this specification. It also handles namespaces according to the XML Namespaces 1.1 Recommendation, and will correctly serialize XML 1.1 documents if the DOM level 3 load/save APIs are in use.

The newest version!
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You 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.
 */

package org.apache.xerces.impl.xs.opti;

import java.util.ArrayList;
import java.util.Enumeration;

import org.apache.xerces.util.XMLSymbols;
import org.apache.xerces.xni.NamespaceContext;
import org.apache.xerces.xni.QName;
import org.apache.xerces.xni.XMLAttributes;
import org.apache.xerces.xni.XMLString;
import org.w3c.dom.Attr;
import org.w3c.dom.DOMImplementation;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;

/**
 * @xerces.internal  
 * 
 * @author Rahul Srivastava, Sun Microsystems Inc.
 * @author Sandy Gao, IBM
 *
 * @version $Id: SchemaDOM.java 982713 2010-08-05 17:54:01Z mrglavas $
 */
public class SchemaDOM extends DefaultDocument {
    
    static final int relationsRowResizeFactor = 15;
    static final int relationsColResizeFactor = 10;
    
    NodeImpl[][] relations;
    // parent must be an element in this scheme
    ElementImpl parent;
    int currLoc;
    int nextFreeLoc;
    boolean hidden;
    boolean inCDATA;
    
    // for annotation support:
    private StringBuffer fAnnotationBuffer = null;
    
    public SchemaDOM() {
        reset();
    }
    
    
    public ElementImpl startElement(QName element, XMLAttributes attributes,
            int line, int column, int offset) {
        ElementImpl node = new ElementImpl(line, column, offset);
        processElement(element, attributes, node);
        // now the current node added, becomes the parent
        parent = node;
        return node;
    }
    
    public ElementImpl emptyElement(QName element, XMLAttributes attributes,
            int line, int column, int offset) {
        ElementImpl node = new ElementImpl(line, column, offset);
        processElement(element, attributes, node);
        return node;
    }
    
    public ElementImpl startElement(QName element, XMLAttributes attributes,
            int line, int column) {
        return startElement(element, attributes, line, column, -1);
    }
    
    public ElementImpl emptyElement(QName element, XMLAttributes attributes,
            int line, int column) {
        return emptyElement(element, attributes, line, column, -1);
    }
    
    private void processElement(QName element, XMLAttributes attributes, ElementImpl node) {
        
        // populate node
        node.prefix = element.prefix;
        node.localpart = element.localpart;
        node.rawname = element.rawname;
        node.uri = element.uri;
        node.schemaDOM = this;
        
        // set the attributes
        Attr[] attrs = new Attr[attributes.getLength()];
        for (int i=0; i 0) {
            fAnnotationBuffer.append(text.ch, text.offset, text.length);
        }
        fAnnotationBuffer.append("-->");
    }
    
    // note that this will only be called within appinfo/documentation
    void processingInstruction(String target, XMLString data) {
        fAnnotationBuffer.append(" 0) {
            fAnnotationBuffer.append(' ').append(data.ch, data.offset, data.length);
        }
        fAnnotationBuffer.append("?>");
    }
    
    // note that this will only be called within appinfo/documentation
    void characters(XMLString text) {
        
        // escape characters if necessary
        if (!inCDATA) {
            final StringBuffer annotationBuffer = fAnnotationBuffer;
            for (int i = text.offset; i < text.offset+text.length; ++i) {
                char ch = text.ch[i];
                if (ch == '&') {
                    annotationBuffer.append("&");
                } 
                else if (ch == '<') {
                    annotationBuffer.append("<");
                }
                // character sequence "]]>" cannot appear in content, 
                // therefore we should escape '>'.
                else if (ch == '>') {
                    annotationBuffer.append(">");
                }
                // If CR is part of the document's content, it
                // must not be printed as a literal otherwise
                // it would be normalized to LF when the document
                // is reparsed.
                else if (ch == '\r') {
                    annotationBuffer.append("
");
                }
                else {
                    annotationBuffer.append(ch);
                }
            }
        }
        else {
            fAnnotationBuffer.append(text.ch, text.offset, text.length);
        }
    }
    
    // note that this will only be called within appinfo/documentation
    void charactersRaw(String text) {
        fAnnotationBuffer.append(text);
    }
    
    void endAnnotation(QName elemName, ElementImpl annotation) {
        fAnnotationBuffer.append("\n");
        annotation.fAnnotation = fAnnotationBuffer.toString();
        // apparently, there is no sensible way of resetting these things
        fAnnotationBuffer = null;
    }
    
    void endAnnotationElement(QName elemName) {
        endAnnotationElement(elemName.rawname);
    }
    
    void endAnnotationElement(String elemRawName) {
        fAnnotationBuffer.append("");
    }
    
    void endSyntheticAnnotationElement(QName elemName, boolean complete) {
        endSyntheticAnnotationElement(elemName.rawname, complete);
    }
    
    void endSyntheticAnnotationElement(String elemRawName, boolean complete) {
        if(complete) {
            fAnnotationBuffer.append("\n");
            // note that this is always called after endElement on 's
            // child and before endElement on annotation.
            // hence, we must make this the child of the current
            // parent's only child.
            parent.fSyntheticAnnotation = fAnnotationBuffer.toString();
            
            // apparently, there is no sensible way of resetting
            // these things
            fAnnotationBuffer = null;
        } else      //capturing character calls
            fAnnotationBuffer.append("");
    }
    
    void startAnnotationCDATA() {
        inCDATA = true;
        fAnnotationBuffer.append("");
        inCDATA = false;
    }
    
    private void resizeRelations() {
        NodeImpl[][] temp = new NodeImpl[relations.length+relationsRowResizeFactor][];
        System.arraycopy(relations, 0, temp, 0, relations.length);
        for (int i = relations.length ; i < temp.length ; i++) {
            temp[i] = new NodeImpl[relationsColResizeFactor];
        }
        relations = temp;
    }
    
    private void resizeRelations(int i) {
        NodeImpl[] temp = new NodeImpl[relations[i].length+relationsColResizeFactor];
        System.arraycopy(relations[i], 0, temp, 0, relations[i].length);
        relations[i] = temp;
    }
    
    
    public void reset() {
        
        // help out the garbage collector
        if(relations != null) 
            for(int i=0; i");
            depth+=4;
            for (Node child = node.getFirstChild(); child != null; child = child.getNextSibling()) {
                traverse(child, depth);
            }
            depth-=4;
            indent(depth);
            System.out.println("");
        }
        else {
            System.out.println("/>");
        }
    }
    
    public static void indent(int amount) {
        for (int i = 0; i < amount; i++) {
            System.out.print(' ');
        }
    }
    
    // org.w3c.dom methods
    public Element getDocumentElement() {
        // this returns a parent node, known to be an ElementImpl
        return (ElementImpl)relations[0][1];
    }
    
    public DOMImplementation getImplementation() {
        return SchemaDOMImplementation.getDOMImplementation();
    }
    
    // commence the serialization of an annotation
    void startAnnotation(QName elemName, XMLAttributes attributes,
            NamespaceContext namespaceContext) {
        startAnnotation(elemName.rawname, attributes, namespaceContext);
    }
    void startAnnotation(String elemRawName, XMLAttributes attributes,
            NamespaceContext namespaceContext) {
        if(fAnnotationBuffer == null) fAnnotationBuffer = new StringBuffer(256);
        fAnnotationBuffer.append("<").append(elemRawName).append(" ");
        
        // attributes are a bit of a pain.  To get this right, we have to keep track
        // of the namespaces we've seen declared, then examine the namespace context
        // for other namespaces so that we can also include them.
        // optimized for simplicity and the case that not many
        // namespaces are declared on this annotation...
        ArrayList namespaces = new ArrayList();
        for (int i = 0; i < attributes.getLength(); ++i) {
            String aValue = attributes.getValue(i);
            String aPrefix = attributes.getPrefix(i);
            String aQName = attributes.getQName(i);
            // if it's xmlns:* or xmlns, must be a namespace decl
            if (aPrefix == XMLSymbols.PREFIX_XMLNS || aQName == XMLSymbols.PREFIX_XMLNS) {
                namespaces.add(aPrefix == XMLSymbols.PREFIX_XMLNS ? 
                        attributes.getLocalName(i) : XMLSymbols.EMPTY_STRING);
            }
            fAnnotationBuffer.append(aQName).append("=\"").append(processAttValue(aValue)).append("\" ");
        }
        // now we have to look through currently in-scope namespaces to see what
        // wasn't declared here
        Enumeration currPrefixes = namespaceContext.getAllPrefixes();
        while(currPrefixes.hasMoreElements()) {
            String prefix = (String)currPrefixes.nextElement();
            String uri = namespaceContext.getURI(prefix);
            if (uri == null) {
                uri = XMLSymbols.EMPTY_STRING;
            }
            if (!namespaces.contains(prefix)) {
                // have to declare this one
                if(prefix == XMLSymbols.EMPTY_STRING) {
                    fAnnotationBuffer.append("xmlns").append("=\"").append(processAttValue(uri)).append("\" ");
                }
                else {
                    fAnnotationBuffer.append("xmlns:").append(prefix).append("=\"").append(processAttValue(uri)).append("\" ");
                }
            }
        }
        fAnnotationBuffer.append(">\n");
    }
    void startAnnotationElement(QName elemName, XMLAttributes attributes) {
        startAnnotationElement(elemName.rawname, attributes);
    }
    void startAnnotationElement(String elemRawName, XMLAttributes attributes) {
        fAnnotationBuffer.append("<").append(elemRawName);
        for(int i=0; i");
    }
    
    private static String processAttValue(String original) {
        final int length = original.length();
        // normally, nothing will happen
        for (int i = 0; i < length; ++i) {
            char currChar = original.charAt(i);
            if (currChar == '"' || currChar == '<' || currChar == '&' ||
                    currChar == 0x09 || currChar == 0x0A || currChar == 0x0D) {
                return escapeAttValue(original, i);
            }
        }
        return original;
    }
    
    private static String escapeAttValue(String original, int from) {
        int i;
        final int length = original.length();
        StringBuffer newVal = new StringBuffer(length);
        newVal.append(original.substring(0, from));
        for (i = from; i < length; ++i) {
            char currChar = original.charAt(i);
            if (currChar == '"') {
                newVal.append(""");
            } 
            else if (currChar == '<') {
                newVal.append("<");
            }
            else if (currChar == '&') {
                newVal.append("&");
            }
            // Must escape 0x09, 0x0A and 0x0D if they appear in attribute
            // value so that they may be round-tripped. They would otherwise
            // be transformed to a 0x20 during attribute value normalization.
            else if (currChar == 0x09) {
                newVal.append("	");
            }
            else if (currChar == 0x0A) {
                newVal.append("
");
            }
            else if (currChar == 0x0D) {
                newVal.append("
");
            }
            else {
                newVal.append(currChar);
            }
        }
        return newVal.toString();
    }
}




© 2015 - 2024 Weber Informatics LLC | Privacy Policy