Laboratoire ICAR » Plateforme TXM

package org.txm.scripts.test

println "Pre-balisage du discours direct"

List<String> containers = ["p","ab"]; // elements qui contiennent des <s>

File infile = new File(System.getProperty("user.home"), "TXM-SRC/quote-orig/perceval2.xml")

File outfile = new File(System.getProperty("user.home"), "TXM-SRC/quote-orig/perceval2-q.xml")

def doc = new XmlParser().parse (infile)

List<Node> nodesToInspect = doc.text.body.div

// nodesToInspect << doc.text.body.div // on en rajoute

/*************************/

new org.txm.importer.EncodeTEIQuotes(nodesToInspect, containers, "\"", "pon");

//copy the doc in "outfile" File

String encoding = "UTF-8"

OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream(outfile) , encoding);

//writer.write("<?xml version=\"1.0\" encoding=\""+encoding+"\"?>");

//writer.write ("<?xml-stylesheet type=\"text/css\" href=\"tei-graal.css\"?>\n")

def pwriter = new PrintWriter(writer, true)

XmlNodePrinter xmlwriter = new XmlNodePrinter(pwriter)

xmlwriter.setPreserveWhitespace(false)

xmlwriter.print(doc)

pwriter.close()

writer.close()

xmlwriter = null

//println "write output file "+outfile

//update counts

if(outfile.exists())

{

        String txtid = org.txm.importer.WordCounter.findTextId(infile, "s"); // retrouve l'id du text qui a été concaténé aux id des S originels (ex : s19_12 >> 19)

        new org.txm.importer.WordCounter(outfile, "s", txtid);

        new org.txm.importer.WordCounter(outfile, "q", txtid);

}