improve utf8 detction with confidence

JabRef · Dec 29, 2024 · 0714b66 · 0714b66
1 parent 4b7ac10
commit 0714b66
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/src/main/java/org/jabref/logic/importer/Importer.java b/src/main/java/org/jabref/logic/importer/Importer.java
@@ -121,7 +121,8 @@ protected static Charset getCharset(BufferedInputStream bufferedInputStream) {
                 return defaultCharSet;
             }
 
-            if (Arrays.stream(matches).anyMatch(charset -> "ASCII".equals(charset.getName()))) {
+            // if we have utf8 with 100 confidence we
+            if (Arrays.stream(matches).anyMatch(charset -> "ASCII".equals(charset.getName()) || ("UTF-8".equals(charset.getName()) && charset.getConfidence() == 100))) {
                 return defaultCharSet;
             }