incrementalsaxsource_filter.java

来自「JAVA 所有包」· Java 代码 · 共 806 行 · 第 1/2 页

  	if(null!=clientDTDHandler)
	  	clientDTDHandler.notationDecl(a,b,c);
  }
  public void unparsedEntityDecl(String a, String b, String c, String d)  throws SAXException
  {
  	if(null!=clientDTDHandler)
	  	clientDTDHandler.unparsedEntityDecl(a,b,c,d);
  }
  
  //
  // ErrorHandler support.
  //
  // PROBLEM: Xerces is apparently _not_ calling the ErrorHandler for
  // exceptions thrown by the ContentHandler, which prevents us from
  // handling this properly when running in filtering mode with Xerces
  // as our event source.  It's unclear whether this is a Xerces bug
  // or a SAX design flaw.
  // 
  // %REVIEW% Current solution: In filtering mode, it is REQUIRED that
  // event source make sure this method is invoked if the event stream
  // abends before endDocument is delivered. If that means explicitly calling
  // us in the exception handling code because it won't be delivered as part
  // of the normal SAX ErrorHandler stream, that's fine; Not Our Problem.
  //
  public void error(SAXParseException exception) throws SAXException
  {
    if(null!=clientErrorHandler)
      clientErrorHandler.error(exception);
  }
  
  public void fatalError(SAXParseException exception) throws SAXException
  {
    // EXCEPTION: In this case we need to run the event BEFORE we yield --
    // just as with endDocument, this terminates the event stream.
    if(null!=clientErrorHandler)
      clientErrorHandler.error(exception);

    eventcounter=0;     
    co_yield(false);

  }
  
  public void warning(SAXParseException exception) throws SAXException
  {
    if(null!=clientErrorHandler)
      clientErrorHandler.error(exception);
  }
  

  //
  // coroutine support
  //

  public int getSourceCoroutineID() {
    return fSourceCoroutineID;
  }
  public int getControllerCoroutineID() {
    return fControllerCoroutineID;
  }

  /** @return the CoroutineManager this CoroutineFilter object is bound to.
   * If you're using the do...() methods, applications should only
   * need to talk to the CoroutineManager once, to obtain the
   * application's Coroutine ID.
   * */
  public CoroutineManager getCoroutineManager()
  {
    return fCoroutineManager;
  }

  /** <p>In the SAX delegation code, I've inlined the count-down in
   * the hope of encouraging compilers to deliver better
   * performance. However, if we subclass (eg to directly connect the
   * output to a DTM builder), that would require calling super in
   * order to run that logic... which seems inelegant.  Hence this
   * routine for the convenience of subclasses: every [frequency]
   * invocations, issue a co_yield.</p>
   *
   * @param moreExepected Should always be true unless this is being called
   * at the end of endDocument() handling.
   * */
  protected void count_and_yield(boolean moreExpected) throws SAXException
  {
    if(!moreExpected) eventcounter=0;
    
    if(--eventcounter<=0)
      {
        co_yield(true);
        eventcounter=frequency;
      }
  }

  /**
   * co_entry_pause is called in startDocument() before anything else
   * happens. It causes the filter to wait for a "go ahead" request
   * from the controller before delivering any events. Note that
   * the very first thing the controller tells us may be "I don't
   * need events after all"!
   */
  private void co_entry_pause() throws SAXException
  {
    if(fCoroutineManager==null)
    {
      // Nobody called init()? Do it now...
      init(null,-1,-1);
    }

    try
    {
      Object arg=fCoroutineManager.co_entry_pause(fSourceCoroutineID);
      if(arg==Boolean.FALSE)
        co_yield(false);
    }
    catch(NoSuchMethodException e)
    {
      // Coroutine system says we haven't registered. That's an
      // application coding error, and is unrecoverable.
      if(DEBUG) e.printStackTrace();
      throw new SAXException(e);
    }
  }

  /**
   * Co_Yield handles coroutine interactions while a parse is in progress.
   *
   * When moreRemains==true, we are pausing after delivering events, to
   * ask if more are needed. We will resume the controller thread with 
   *   co_resume(Boolean.TRUE, ...)
   * When control is passed back it may indicate
   *      Boolean.TRUE    indication to continue delivering events
   *      Boolean.FALSE   indication to discontinue events and shut down.
   * 
   * When moreRemains==false, we shut down immediately without asking the
   * controller's permission. Normally this means end of document has been
   * reached.
   *
   * Shutting down a IncrementalSAXSource_Filter requires terminating the incoming
   * SAX event stream. If we are in control of that stream (if it came
   * from an XMLReader passed to our startReader() method), we can do so
   * very quickly by throwing a reserved exception to it. If the stream is
   * coming from another source, we can't do that because its caller may
   * not be prepared for this "normal abnormal exit", and instead we put
   * ourselves in a "spin" mode where events are discarded.
   */
  private void co_yield(boolean moreRemains) throws SAXException
  {
    // Horrendous kluge to run filter to completion. See below.
    if(fNoMoreEvents)
      return;

    try // Coroutine manager might throw no-such.
    {
      Object arg=Boolean.FALSE;
      if(moreRemains)
      {
        // Yield control, resume parsing when done
        arg = fCoroutineManager.co_resume(Boolean.TRUE, fSourceCoroutineID,
                                          fControllerCoroutineID);
        
      }

      // If we're at end of document or were told to stop early
      if(arg==Boolean.FALSE)
      {
        fNoMoreEvents=true;
        
        if(fXMLReader!=null)    // Running under startParseThread()
          throw new StopException(); // We'll co_exit from there.
        
        // Yield control. We do NOT expect anyone to ever ask us again.
        fCoroutineManager.co_exit_to(Boolean.FALSE, fSourceCoroutineID,
                                     fControllerCoroutineID);
      }
    }
    catch(NoSuchMethodException e)
    {
      // Shouldn't happen unless we've miscoded our coroutine logic
      // "Shut down the garbage smashers on the detention level!"
      fNoMoreEvents=true;
      fCoroutineManager.co_exit(fSourceCoroutineID);
      throw new SAXException(e);
    }
  }

  //
  // Convenience: Run an XMLReader in a thread
  //

  /** Launch a thread that will run an XMLReader's parse() operation within
   *  a thread, feeding events to this IncrementalSAXSource_Filter. Mostly a convenience
   *  routine, but has the advantage that -- since we invoked parse() --
   *  we can halt parsing quickly via a StopException rather than waiting
   *  for the SAX stream to end by itself.
   *
   * @throws SAXException is parse thread is already in progress
   * or parsing can not be started.
   * */
  public void startParse(InputSource source) throws SAXException
  {
    if(fNoMoreEvents)
      throw new SAXException(XMLMessages.createXMLMessage(XMLErrorResources.ER_INCRSAXSRCFILTER_NOT_RESTARTABLE, null)); //"IncrmentalSAXSource_Filter not currently restartable.");
    if(fXMLReader==null)
      throw new SAXException(XMLMessages.createXMLMessage(XMLErrorResources.ER_XMLRDR_NOT_BEFORE_STARTPARSE, null)); //"XMLReader not before startParse request");

    fXMLReaderInputSource=source;
    
    // Xalan thread pooling...
    // com.sun.org.apache.xalan.internal.transformer.TransformerImpl.runTransformThread(this);
    ThreadControllerWrapper.runThread(this, -1);
  }
  
  /* Thread logic to support startParseThread()
   */
  public void run()
  {
    // Guard against direct invocation of start().
    if(fXMLReader==null) return;

    if(DEBUG)System.out.println("IncrementalSAXSource_Filter parse thread launched");

    // Initially assume we'll run successfully.
    Object arg=Boolean.FALSE;

    // For the duration of this operation, all coroutine handshaking
    // will occur in the co_yield method. That's the nice thing about
    // coroutines; they give us a way to hand off control from the
    // middle of a synchronous method.
    try
    {
      fXMLReader.parse(fXMLReaderInputSource);
    }
    catch(IOException ex)
    {
      arg=ex;
    }
    catch(StopException ex)
    {
      // Expected and harmless
      if(DEBUG)System.out.println("Active IncrementalSAXSource_Filter normal stop exception");
    }
    catch (SAXException ex)
    {
      Exception inner=ex.getException();
      if(inner instanceof StopException){
        // Expected and harmless
        if(DEBUG)System.out.println("Active IncrementalSAXSource_Filter normal stop exception");
      }
      else
      {
        // Unexpected malfunction
        if(DEBUG)
        {
          System.out.println("Active IncrementalSAXSource_Filter UNEXPECTED SAX exception: "+inner);
          inner.printStackTrace();
        }                
        arg=ex;
      }
    } // end parse
    
    // Mark as no longer running in thread.
    fXMLReader=null;

    try
    {
      // Mark as done and yield control to the controller coroutine
      fNoMoreEvents=true;
      fCoroutineManager.co_exit_to(arg, fSourceCoroutineID,
                                   fControllerCoroutineID);
    }
    catch(java.lang.NoSuchMethodException e)
    {
      // Shouldn't happen unless we've miscoded our coroutine logic
      // "CPO, shut down the garbage smashers on the detention level!"
      e.printStackTrace(System.err);
      fCoroutineManager.co_exit(fSourceCoroutineID);
    }
  }

  /** Used to quickly terminate parse when running under a
      startParse() thread. Only its type is important. */
  class StopException extends RuntimeException
  {
          static final long serialVersionUID = -1129245796185754956L;
  }

  /** deliverMoreNodes() is a simple API which tells the coroutine
   * parser that we need more nodes.  This is intended to be called
   * from one of our partner routines, and serves to encapsulate the
   * details of how incremental parsing has been achieved.
   *
   * @param parsemore If true, tells the incremental filter to generate
   * another chunk of output. If false, tells the filter that we're
   * satisfied and it can terminate parsing of this document.
   *
   * @return Boolean.TRUE if there may be more events available by invoking
   * deliverMoreNodes() again. Boolean.FALSE if parsing has run to completion (or been
   * terminated by deliverMoreNodes(false). Or an exception object if something
   * malfunctioned. %REVIEW% We _could_ actually throw the exception, but
   * that would require runinng deliverMoreNodes() in a try/catch... and for many
   * applications, exception will be simply be treated as "not TRUE" in
   * any case.
   * */
  public Object deliverMoreNodes(boolean parsemore)
  {
    // If parsing is already done, we can immediately say so
    if(fNoMoreEvents)
      return Boolean.FALSE;

    try 
    {
      Object result =
        fCoroutineManager.co_resume(parsemore?Boolean.TRUE:Boolean.FALSE,
                                    fControllerCoroutineID, fSourceCoroutineID);
      if(result==Boolean.FALSE)
        fCoroutineManager.co_exit(fControllerCoroutineID);

      return result;
    }
      
    // SHOULD NEVER OCCUR, since the coroutine number and coroutine manager
    // are those previously established for this IncrementalSAXSource_Filter...
    // So I'm just going to return it as a parsing exception, for now.
    catch(NoSuchMethodException e)
      {
        return e;
      }
  }
  

  //================================================================
  /** Simple unit test. Attempt coroutine parsing of document indicated
   * by first argument (as a URI), report progress.
   */
    /*
  public static void _main(String args[])
  {
    System.out.println("Starting...");

    org.xml.sax.XMLReader theSAXParser=
      new com.sun.org.apache.xerces.internal.parsers.SAXParser();
  

    for(int arg=0;arg<args.length;++arg)
    {
      // The filter is not currently designed to be restartable
      // after a parse has ended. Generate a new one each time.
      IncrementalSAXSource_Filter filter=
        new IncrementalSAXSource_Filter();
      // Use a serializer as our sample output
      com.sun.org.apache.xml.internal.serialize.XMLSerializer trace;
      trace=new com.sun.org.apache.xml.internal.serialize.XMLSerializer(System.out,null);
      filter.setContentHandler(trace);
      filter.setLexicalHandler(trace);

      try
      {
        InputSource source = new InputSource(args[arg]);
        Object result=null;
        boolean more=true;

        // init not issued; we _should_ automagically Do The Right Thing

        // Bind parser, kick off parsing in a thread
        filter.setXMLReader(theSAXParser);
        filter.startParse(source);
      
        for(result = filter.deliverMoreNodes(more);
            (result instanceof Boolean && ((Boolean)result)==Boolean.TRUE);
            result = filter.deliverMoreNodes(more))
        {
          System.out.println("\nSome parsing successful, trying more.\n");
          
          // Special test: Terminate parsing early.
          if(arg+1<args.length && "!".equals(args[arg+1]))
          {
            ++arg;
            more=false;
          }
          
        }
      
        if (result instanceof Boolean && ((Boolean)result)==Boolean.FALSE)
        {
          System.out.println("\nFilter ended (EOF or on request).\n");
        }
        else if (result == null) {
          System.out.println("\nUNEXPECTED: Filter says shut down prematurely.\n");
        }
        else if (result instanceof Exception) {
          System.out.println("\nFilter threw exception:");
          ((Exception)result).printStackTrace();
        }
      
      }
      catch(SAXException e)
      {
        e.printStackTrace();
      }
    } // end for
  }
    */  
} // class IncrementalSAXSource_Filter