Skip to content
Snippets Groups Projects
Commit 879398ed authored by Paweł Walkowiak's avatar Paweł Walkowiak
Browse files

Create doc builder

parent 6ab51adb
Branches
1 merge request!1Support xml
Pipeline #10753 failed with stage
in 54 seconds
......@@ -75,6 +75,10 @@ public class Converter extends Worker {
Logger.getLogger(Converter.class.getName()).log(Level.INFO, "Input file: " + fileIn);
File file = new File(fileIn);
TikaInputStream inS;
DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
Document doc = builder.parse(file);
try {
Metadata metadata = new Metadata();
metadata.set("Content-Encoding", "CP1250");
......@@ -114,8 +118,8 @@ public class Converter extends Worker {
Logger.getLogger(Converter.class.getName()).log(Level.WARNING, "Problems in Tika processing " + ex.getMessage() , ex.getMessage());
if (ex.getMessage().contains("XML parse error")) {
try {
DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
Document doc = builder.parse(file);
// DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
// Document doc = builder.parse(file);
doc.getDocumentElement().normalize();
Logger.getLogger(Converter.class.getName()).log(Level.INFO, "Root element :" + doc.getDocumentElement().getNodeName() + " " + doc.getDocumentElement().getTextContent());
Logger.getLogger(Converter.class.getName()).log(Level.INFO, "Child element :" + doc.getDocumentElement().getChildNodes().item(0).getTextContent());
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment