Hi Justin, A shot in the dark: You could create a collection reader that works similarly to org.apache.ctakes.core.cr.FilesInDirectoryCollectionReader , but instead of grabbing all of the files in a directory it grabs all the records parsed from a single .xml and runs a pipeline per record. Basically, swap a directory for an .xml, a text file for an xml element containing a record. Somebody out there might have something that already does as much.
Sean -----Original Message----- From: Justin Zhang [mailto:justinzhang...@gmail.com] Sent: Wednesday, August 05, 2015 6:40 PM To: u...@ctakes.apache.org; dev@ctakes.apache.org Subject: how to run i2b2 data Hello everyone, I am running ctakes with i2b2 data https://urldefense.proofpoint.com/v2/url?u=https-3A__www.i2b2.org_NLP_DataSets_Main.php&d=BQIBaQ&c=qS4goWBT7poplM69zy_3xhKwEW14JZMSdioCoppxeFU&r=fs67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4gTao&m=IygWj6YGkcjofGRbrDiFJacJHMaBveHR9qzY0VD1AAE&s=swpt3QP4-B392iLlJ9wypBwD17tRDOCxPdSZOW1rS8s&e= In each xml file, there are multiple patient records. I am able to separate each patient into single files and process them with "runCPE.sh" Is there a way to convert this single xml file into the format "ctakes" accepted, and process as a single input file, and generate a single output file (results labelled by patient id). For example, each patient id has a "smoking status". Thanks, -- Justin