U+0085 control character breaks PICA line parsing #277

pkiraly · Jun 2, 2023 · 66dc6db · 66dc6db
1 parent 1026631
commit 66dc6db
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/main/java/de/gwdg/metadataqa/marc/utils/pica/reader/model/PicaLine.java b/src/main/java/de/gwdg/metadataqa/marc/utils/pica/reader/model/PicaLine.java
@@ -15,7 +15,7 @@
 public class PicaLine {
   private static final Logger logger = Logger.getLogger(PicaLine.class.getCanonicalName());
 
-  private static final Pattern LINE = Pattern.compile("^(SET:|Eingabe:|Warnung:|[0-2]\\d\\d[A-Z@])(\\/(\\d\\d+))? (.*)$", Pattern.MULTILINE);
+  private static final Pattern LINE = Pattern.compile("^(SET:|Eingabe:|Warnung:|[0-2]\\d\\d[A-Z@])(\\/(\\d\\d+))? ((\\u0085|.)*+)$", Pattern.MULTILINE);
   private static Map<String, String> quotedSeparatorMap = new HashMap<>();
   public static final String DEFAULT_SEPARATOR = "$";
   private static final String SET = "SET";