Creating JavaScript sweep action handler to download document content

Edit online

Adapt the following item in the JavaScript example:

Output directory: Change the output directory in the script. Because the JavaScript code is run on a Content Platform Engine server, the content download directory that you specify must satisfy the following requirements:

  • It exists on the server as an existing local directory or a mapped network directory
  • It is one to which the server has write permissions.
  • It is accessible to the Datacap application that reads the files from this location during the scan task.
JavaScript sweep action script:
importPackage(Packages.com.filenet.api.core);
importPackage(Packages.com.filenet.api.constants);
importPackage(Packages.com.filenet.api.exception);
importPackage(Packages.com.filenet.api.sweep);
importPackage(Packages.com.filenet.api.engine);

/* Implement for custom job and queue sweeps. */
function onSweep(sweepObject, sweepItems) {
  var hcc = HandlerCallContext.getInstance();
  hcc.traceDetail("Entering DatacapSweepHandler.onSweep");
  hcc.traceDetail("sweepObject = " +
    sweepObject.getProperties().getIdValue(PropertyNames.ID) +
    ", sweepItems.length = " + sweepItems.length);

  /* Iterate the sweepItems */
  idx = 0;
  for (idx = 0; idx < sweepItems.length; idx++) {
   /* At the top of your loop, always check to make sure 
    * that the server is not shutting down. 
    * If it is, clean up and return control to the server.
    */
    if (hcc != null && hcc.isShuttingDown()) {
      throw new EngineRuntimeException(ExceptionCode.E_BACKGROUND_TASK_TERMINATED,
        this.constructor.name + " is terminating prematurely because the server is shutting down");
    } 

    var item = sweepItems[idx].getTarget();
    hcc.traceDetail("sweepItems[" + idx + "]= " + item.getProperties().getIdValue("ID"));

    try {
      var CEObject = Document(item);
      var celist = CEObject.get_ContentElements();
      var docID = CEObject.getProperties().getIdValue("ID");
      for (i = 0; i < celist.size(); i++)
      {   
        var ce  = celist.get(i);
        var folderName = "X://sweep"; /* output directory */       
        this._downloadContent(folderName, docID, ce);
      }

      /* Set outcome to PROCESSED if item processed successfully.*/
      sweepItems[idx].setOutcome(SweepItemOutcome.PROCESSED,
        "item processed by " + this.constructor.name);
    }
    /* Set failure status on objects that fail to process.*/
    catch (ioe) {
      sweepItems[idx].setOutcome(SweepItemOutcome.FAILED, "DatacapSweepHandler: " +
        ioe.rhinoException.getMessage());
    }
  }
  hcc.traceDetail("Exiting DatacapSweepHandler.onSweep");
}

/* private function to download content elements. 
 * the folderName should use the forward slash "/" as path separator.
 * If the file exists it will be overwritten. 
 */
function _downloadContent(folderName, docID, ct)
{
    var out = new java.io.FileOutputStream(folderName + "//" + docID +"."+ ct.get_RetrievalName());
    var docLen = ct.get_ContentSize().intValue();
    var buf = java.lang.reflect.Array.newInstance(java.lang.Byte.TYPE, docLen);
    var stream = ct.accessContentStream();
 
    stream.read(buf, 0, docLen);
    out.write(buf);
    out.flush();
    stream.close();
    out.close();   
}

/* Called automatically when the handler is invoked by a custom sweep job 
* or sweep policy. Specify properties required by the handler, if any.
* If you return an empty array, then all properties are fetched.
*/
function getRequiredProperties() {
  var pnames = [];
  return pnames.toString();  
}

/* Implement for custom sweep policies. 
* This method is not implemented because this is an example of a custom sweep job.  
*/
function onPolicySweep (sweepObject, policyObject, sweepItems) 
{}

Go to next step