contenthandlerimpl.java

xbrlapi的源码

package org.xbrlapi.SAXHandlers;

import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.HashMap;
import java.util.Stack;

import org.apache.log4j.Logger;
import org.apache.xerces.parsers.XMLGrammarPreparser;
import org.apache.xerces.util.XMLResourceIdentifierImpl;
import org.apache.xerces.xni.XMLResourceIdentifier;
import org.apache.xerces.xni.grammars.XMLGrammarDescription;
import org.apache.xerces.xni.grammars.XSGrammar;
import org.apache.xerces.xni.parser.XMLEntityResolver;
import org.apache.xerces.xni.parser.XMLInputSource;
import org.apache.xerces.xs.StringList;
import org.apache.xerces.xs.XSElementDeclaration;
import org.apache.xerces.xs.XSModel;
import org.apache.xerces.xs.XSNamespaceItem;
import org.apache.xerces.xs.XSNamespaceItemList;
import org.xbrlapi.Fragment;
import org.xbrlapi.impl.ArcroleTypeImpl;
import org.xbrlapi.impl.ConceptImpl;
import org.xbrlapi.impl.ContextImpl;
import org.xbrlapi.impl.ElementDeclarationImpl;
import org.xbrlapi.impl.EntityImpl;
import org.xbrlapi.impl.FragmentImpl;
import org.xbrlapi.impl.InstanceImpl;
import org.xbrlapi.impl.LanguageImpl;
import org.xbrlapi.impl.LinkbaseImpl;
import org.xbrlapi.impl.NonNumericItemImpl;
import org.xbrlapi.impl.PeriodImpl;
import org.xbrlapi.impl.ReferencePartDeclarationImpl;
import org.xbrlapi.impl.ReferencePartImpl;
import org.xbrlapi.impl.RoleTypeImpl;
import org.xbrlapi.impl.ScenarioImpl;
import org.xbrlapi.impl.SchemaImpl;
import org.xbrlapi.impl.SegmentImpl;
import org.xbrlapi.impl.SimpleNumericItemImpl;
import org.xbrlapi.impl.TupleImpl;
import org.xbrlapi.impl.UnitImpl;
import org.xbrlapi.impl.UsedOnImpl;
import org.xbrlapi.impl.XlinkDocumentationImpl;
import org.xbrlapi.loader.Loader;
import org.xbrlapi.utilities.Constants;
import org.xbrlapi.utilities.GrammarCacheImpl;
import org.xbrlapi.utilities.XBRLException;
import org.xbrlapi.xlink.XLinkException;
import org.xbrlapi.xlink.handler.XBRLXLinkHandlerImpl;
import org.xbrlapi.xmlbase.BaseURLSAXResolver;
import org.xbrlapi.xmlbase.BaseURLSAXResolverImpl;
import org.xbrlapi.xmlbase.XMLBaseException;
import org.xml.sax.Attributes;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.helpers.DefaultHandler;

/**
 * SAX content handler used in construction of an XBRL 
 * Discoverable Taxonomy Set (DTS).
 * The content handler is responsible for building up the XBRL
 * XML fragments as they are parsed and then passing them over
 * to the underlying data representation for storage.
 * 
 * The content handler needs to be supplied with a variety of helpers
 * to assist with data storage and XLink processing. These are 
 * supplied to the constructor by the loader.
 * 
 * @author Geoffrey Shuetrim ([e-mail])
 */

public class ContentHandlerImpl extends DefaultHandler {

	protected static Logger logger = Logger.getLogger(ContentHandlerImpl.class);	
    /**
     * The DTS loader that uses this content handler 
     * to process discovered XML
     */
    private Loader loader = null;
	    
    /**
     * The XML Schema model if parsing an XML Schema.
     */
    private XSModel model = null;
    
    /**
     * The URL of the document being parsed.  This is used to
     * recover the XML Schema model for the document if required.
     */
    private URL url = null;
    
    /**
     * The target namespace of an XML Schema.
     */
    private String targetNamespace = null;
    
    /**
     * State information to help find tuples in XBRL instances.
     */
    private boolean parsingAnXBRLInstance = false;
    private boolean canBeATuple = false;

    /**
     * State information to help find reference parts.
     * TODO Find reference parts using XML Schema substitution group information.
     */
    private boolean parsingAReferenceResource = false;
    
    /**
     * SAX parsing locator - providing information for use in
     * error reporting.
     */
    Locator locator = null;
    
    /**
     * Element depth of the tree being parsed.  This is used to 
     * ensure that the loader knows when a fragment has finished 
     * being built.  This starts at 0 and is incremented for each
     * startElement event and decremented for each end element 
     * event.
     * TODO eliminate depth from the SAX content handler in favour of the ElementState.
     */
    long depth = 0;
    
    /**
     * Data required to track the element scheme XPointer 
     * expressions that can be used to identify XBRL fragments.
     */
    ElementState state = new ElementState();
    
    /**
     * String representation of the XML document - for documents supplied as such.
     */
    String xml = null;

    /**
     * The namespace map stack for tracking namespaces.
     */
    Stack<HashMap<String,String>> nsStack = new Stack<HashMap<String,String>>();
    
    /**
     * Creates the content handler, starting out by
     * identifying the DTS structure that the content
     * handler is discovering.
     * @param loader The DTS loader that is using this content handler.
     * @param url The URL of the document being parsed.
     * @throws XBRLException if any of the parameters
     * are null.
     */
	public ContentHandlerImpl(Loader loader, URL url) throws XBRLException {
		
		super();
		if (loader == null) {
			throw new XBRLException("The loader must not be null.");
		}
		if (url == null) {
			throw new XBRLException("The url must not be null.");
		}
		this.loader = loader;
		this.url = url;
		
	    nsStack.push(new HashMap<String,String>());
		
	}
	
    /**
     * Creates the content handler, starting out by
     * identifying the data structure that the content
     * handler is discovering.
     * @param loader The data loader that is using this content handler.
     * @param url The URL of the document being parsed.
     * @param xml The string representation of the document being parsed.
     * @throws XBRLException if any of the parameters
     * are null.
     */
	public ContentHandlerImpl(Loader loader, URL url, String xml) throws XBRLException {

		this(loader, url);
		this.xml = xml;
		
	}	
    
    private Loader getLoader() {
    	return loader;
    }
    
    private long getDepth() {
    	return depth;
    }

    private ElementState getState() {
    	return state;
    }
    
    /**
     * The locator for a document is stored as part of the DTSImpl object
     * to facilitate resolution of CacheURLImpl's relative to that location.
     */
    public void setDocumentLocator(Locator l)
    {
    	this.locator = l;
    }
    
    private XBRLXLinkHandlerImpl getXLinkHandler() throws SAXException {
    	try {
    		return (XBRLXLinkHandlerImpl) this.getLoader().getXlinkProcessor().getXLinkHandler();
    	} catch (ClassCastException e) {
    		throw new SAXException("The XBRL API is not using the XBRL XLink Handler implementation.");
    	}
    }
    
    BaseURLSAXResolver baseURLSAXResolver = null;
    /**
     * On starting to parse a document the Base URL resolver is set up with the document's system ID;
     */
    public void startDocument() throws SAXException 
	{
    	// Get the XLink handler
    	XBRLXLinkHandlerImpl xbrlXlinkHandler = getXLinkHandler();

    	// Set the base URL resolver for this document
    	try {
    		// TODO Can we use the url property of the content handler instead of the loader document URL?
    		String thisDocumentURL = this.getLoader().getDocumentURL();
    		this.baseURLSAXResolver = new BaseURLSAXResolverImpl(new URL(thisDocumentURL));
    		xbrlXlinkHandler.setBaseURLSAXResolver(this.baseURLSAXResolver);
    	} catch (MalformedURLException e) {
    		throw new SAXException("The docment has a malformed URL specified by the locator's System ID.");
    	}
    	
    	
    	
    }
    
    /**
     * The end of the document triggers stepping out of the document's 
     * container element
     */
    public void endDocument() throws SAXException 
    {
    }
    
    /**
     * All element processing is done by the DTSImpl object.
     * The only activities specific to this content handler relate
     * to the specific treatment of extended links, locators and arcs.
     */
    @SuppressWarnings("unchecked")
    public void startElement( String namespaceURI, String lName, String qName, Attributes attrs) throws SAXException 
	{
    	
    	// Update element depth and child count.
    	depth++;
    	
    	try {
    		getLoader().incrementChildren();
    	} catch (XBRLException e) {
    		throw new SAXException("Could not record a new child for the fragment being parsed.",e);
    	}
    	
    	// Update the information about the state of the current element
    	state = new ElementState(state);
    	
    	// Stash new URLs in xsi:schemaLocation attributes if desired
    	if (getLoader().useSchemaLocationAttributes()) {
    		String schemaLocations = attrs.getValue(Constants.XMLSchemaInstanceNamespace,"schemaLocation");
    		if (schemaLocations != null) {
        		logger.debug("Processing schema locations: " + schemaLocations);
    			String[] fields = schemaLocations.trim().split("\\s+");
    			for (int i=1; i<fields.length; i=i+2) {
    		    	try {
    					URL url = new URL(this.baseURLSAXResolver.getBaseURL(),fields[i]);
       					logger.debug("Working on: " + url);
       					getLoader().stashURL(url);
    		    	} catch (MalformedURLException e) {
    		    		logger.warn("Ignoring malformed XSI schemaLocation URL in: " + schemaLocations);