From e862358d901c22b0ca6ccb5da6e475dfc62eb921 Mon Sep 17 00:00:00 2001
From: Robert Stephan <robert.stephan@uni-rostock.de>
Date: Mon, 20 Jul 2026 18:15:04 +0200
Subject: [PATCH] MCR-3774 add TikaMapping to collect metadata into one Solr
 field

---
 .../file/tika/MCRCollectingTikaMapper.java    | 47 +++++++++++++++++++
 .../index/file/tika/MCRSimpleTikaMapper.java  |  5 +-
 .../solr/config/solr/main/solr-schema.json    |  6 +++
 3 files changed, 56 insertions(+), 2 deletions(-)
 create mode 100644 mycore-solr/src/main/java/org/mycore/solr/index/file/tika/MCRCollectingTikaMapper.java

diff --git a/mycore-solr/src/main/java/org/mycore/solr/index/file/tika/MCRCollectingTikaMapper.java b/mycore-solr/src/main/java/org/mycore/solr/index/file/tika/MCRCollectingTikaMapper.java
new file mode 100644
index 0000000000..8b94871c94
--- /dev/null
+++ b/mycore-solr/src/main/java/org/mycore/solr/index/file/tika/MCRCollectingTikaMapper.java
@@ -0,0 +1,47 @@
+/*
+ * This file is part of ***  M y C o R e  ***
+ * See https://www.mycore.de/ for details.
+ *
+ * MyCoRe is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * MyCoRe is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with MyCoRe.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+package org.mycore.solr.index.file.tika;
+
+import org.apache.solr.common.SolrInputDocument;
+
+import com.fasterxml.jackson.databind.node.ValueNode;
+
+/**
+ * A simple implementation of the MCRTikaMapper interface. 
+ * This implementation converts JSON key and value of a Tika metadata field 
+ * into a property-like ('key=value') string and stores it into the Solr field `tika_metadata`;
+ * If the property "StripNamespace" is set to true, the namespace of the key is removed before mapping.
+ * If the property "MultiValueField" is set to true, the values are added as multi value fields, otherwise the values
+ * will be concatenated to a single string with newlines.
+ *
+ * @author Robert Stephan
+ */
+public class MCRCollectingTikaMapper extends MCRSimpleTikaMapper implements MCRTikaMapper {
+
+    private static final String SOLR_FIELD_4_TIKA_METADATA = "tika_metadata";
+
+    @Override
+    protected void mapValueNode(SolrInputDocument document, ValueNode vn, String simplifiedKey) {
+        String value = getValueNodeAsString(vn);
+        if (value == null || value.isEmpty()) {
+            return;
+        }
+        document.addField(SOLR_FIELD_4_TIKA_METADATA, simplifiedKey + "=" + value);
+    }
+}
diff --git a/mycore-solr/src/main/java/org/mycore/solr/index/file/tika/MCRSimpleTikaMapper.java b/mycore-solr/src/main/java/org/mycore/solr/index/file/tika/MCRSimpleTikaMapper.java
index 751cf28d71..0fd5652285 100644
--- a/mycore-solr/src/main/java/org/mycore/solr/index/file/tika/MCRSimpleTikaMapper.java
+++ b/mycore-solr/src/main/java/org/mycore/solr/index/file/tika/MCRSimpleTikaMapper.java
@@ -26,6 +26,7 @@
 
 import com.fasterxml.jackson.core.TreeNode;
 import com.fasterxml.jackson.databind.node.ArrayNode;
+import com.fasterxml.jackson.databind.node.TextNode;
 import com.fasterxml.jackson.databind.node.ValueNode;
 
 /**
@@ -104,11 +105,11 @@ private void mapArrayNode(SolrInputDocument document, ArrayNode an, String simpl
                     sb.append(getValueNodeAsString(vn));
                 }
             });
-            document.addField(simplifiedKey, sb.toString());
+            mapValueNode(document, new TextNode(sb.toString()), simplifiedKey);
         }
     }
 
-    private void mapValueNode(SolrInputDocument document, ValueNode vn, String simplifiedKey) {
+    protected void mapValueNode(SolrInputDocument document, ValueNode vn, String simplifiedKey) {
         String value = getValueNodeAsString(vn);
         if (value == null || value.isEmpty()) {
             return;
diff --git a/mycore-solr/src/main/resources/components/solr/config/solr/main/solr-schema.json b/mycore-solr/src/main/resources/components/solr/config/solr/main/solr-schema.json
index e32ebac7ed..c8c0204e99 100644
--- a/mycore-solr/src/main/resources/components/solr/config/solr/main/solr-schema.json
+++ b/mycore-solr/src/main/resources/components/solr/config/solr/main/solr-schema.json
@@ -739,6 +739,12 @@
       "type": "boolean"
     }
   },
+  {
+    "add-field": {
+      "name": "tika_metadata",
+      "type": "strings"
+    }
+  },
   {
     "add-field": {
       "name": "tika_has_error",