Path to .xml file is a command line argument

README.md

@@ -47,7 +47,7 @@ This repository contains the code to reproduce the results in:
 # Processing the data
 
 ## Conversion of GGPOnc corpus XML file to plain text and preprocessing
-* Run `mvn compile` before executing `mvn exec:java -Dexec.mainClass="de.hpi.guidelines.reader.CPGXMLReader"` or run `CPGXMLReader.java` (in package `de.hpi.guidelines.reader`) in Eclipse (Run As => Java Application)
+* Run `mvn compile` before executing `mvn exec:java -Dexec.mainClass="de.hpi.guidelines.reader.GGPOncXMLReader" -Dexec.args="<Path to cpg-corpus-cms.xml>"` or run `GGPOncXMLReader.java` (in package `de.hpi.guidelines.reader`) in Eclipse (Run As => Java Application)
 * Wait a minute
 * Look into the directory `/output`
 

src/main/java/de/hpi/guidelines/reader/GGPOncXMLReader.java

@@ -47,8 +47,6 @@ public class GGPOncXMLReader {
 
 	public static final Logger LOGGER = Logger.getLogger(GGPOncXMLReader.class.getName());
 
-	private static Path importFile = Paths.get("src", "main", "resources", "cpg-corpus-cms.xml");
-
 	private static final Path output = Paths.get("output-GGPOnc-data");
 	private static final Path outDirXML = Paths.get(output + File.separator + "xml");
 	private static final Path outDirTXT = Paths.get(output + File.separator + "txt");
@@ -72,9 +70,10 @@ protected void setOutputStream(OutputStream out) throws SecurityException {
 	}
 
 	public static void main(String[] args) throws Exception {
+		String importFile = args[0];
 		DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();
 		DocumentBuilder dBuilder = dbFactory.newDocumentBuilder();
-		Document doc = dBuilder.parse(importFile.toFile());
+		Document doc = dBuilder.parse(new File(importFile));
 
 		doc.getDocumentElement().normalize();