From 9d7a52b780053bb4d8c1ac3a0ba31fdc73b5d296 Mon Sep 17 00:00:00 2001
From: pwalkow <pawel.walkowiak@hotmail.com>
Date: Tue, 4 Jul 2023 11:25:37 +0200
Subject: [PATCH] set ins encoding

---
 module/src/main/java/pl/clarin/any2txt/Converter.java | 1 +
 1 file changed, 1 insertion(+)

diff --git a/module/src/main/java/pl/clarin/any2txt/Converter.java b/module/src/main/java/pl/clarin/any2txt/Converter.java
index c0b1a48..5200153 100644
--- a/module/src/main/java/pl/clarin/any2txt/Converter.java
+++ b/module/src/main/java/pl/clarin/any2txt/Converter.java
@@ -93,6 +93,7 @@ public class Converter extends Worker {
                 try {
                     DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
                     DocumentBuilder loader = factory.newDocumentBuilder();
+                    ins.setEncoding("UTF-8");
                     Document document = loader.parse(inS);
 
                     DocumentTraversal trav = (DocumentTraversal) document;
-- 
GitLab