From 66dc6db82810f822ce946a0379be99a89f184004 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?P=C3=A9ter=20Kir=C3=A1ly?= Date: Fri, 2 Jun 2023 09:07:52 +0200 Subject: [PATCH] U+0085 control character breaks PICA line parsing #277 --- .../gwdg/metadataqa/marc/utils/pica/reader/model/PicaLine.java | 2 +- 1 file changed, 1 insertion(+), 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 index 14cff2e33..ca8f5b332 100644 --- 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 quotedSeparatorMap = new HashMap<>(); public static final String DEFAULT_SEPARATOR = "$"; private static final String SET = "SET";