Index / Add danish language. (geonetwork#7697)

Co-authored-by: Jose García <[email protected]>

Author: fxprunayre

docs/manual/docs/customizing-application/configuring-search-fields.md

@@ -248,4 +248,45 @@ By default, the search score is defined as (see `web-ui/src/main/resources/catal
 
 ## Language analyzer
 
+
 By default a `standard` analyzer is used. If the catalog content is english, it may make sense to change the analyzer to `english`. To customize the analyzer see `web/src/main/webResources/WEB-INF/data/config/index/records.json`
+
+To add a new language, check first if Elasticsearch provides a specific analyzer for that language (see https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-lang-analyzer.html). Then configure fields that are multilingual 
+in `records.json` (eg. adding Danish):
+
+* If the field is used for full text search, use the language analyzer:
+
+```json
+{
+  "textField": {
+    "match": "*Object",
+    "mapping": {
+      "type": "object",
+      "properties": {
+        "default": {},
+        ...
+        "langdan": {
+            "type": "text",
+            "analyzer": "danish"
+        },
+```
+
+* If the field is a keyword like organisation name or tag field use type `keyword` (which is required for computing aggregations)
+
+```json
+{
+  "tag": {
+    "match": "th_*",
+    "mapping": {
+      "type": "object",
+      "copy_to": ["tag"],
+      "properties": {
+        "default": {},
+        ...
+        "langdan": {
+            "type": "keyword",
+            "copy_to": [
+            "any.langdan"
+            ]
+        },
+```

web/src/main/webResources/WEB-INF/data/config/index/records.json

@@ -1085,6 +1085,10 @@
                 "type": "keyword",
                 "copy_to": ["any.langdut", "organisationName.langdut"]
               },
+              "langdan": {
+                "type": "keyword",
+                "copy_to": ["any.langdan", "organisationName.langdan"]
+              },
               "langspa": {
                 "type": "keyword",
                 "copy_to": ["any.langspa", "organisationName.langspa"]
@@ -1172,6 +1176,19 @@
                   }
                 }
               },
+              "langdan": {
+                "type": "text",
+                "analyzer": "danish",
+                "copy_to": [
+                  "any.langdan"
+                ],
+                "fields": {
+                  "keyword": {
+                    "type": "keyword",
+                    "ignore_above": ${es.index.ignore_above}
+                  }
+                }
+              },
               "langita": {
                 "type": "text",
                 "analyzer": "italian",
@@ -1286,6 +1303,12 @@
                   "any.langdut"
                 ]
               },
+              "langdan": {
+                "type": "keyword",
+                "copy_to": [
+                  "any.langdan"
+                ]
+              },
               "langita": {
                 "type": "keyword",
                 "copy_to": ["any.langita"]
@@ -1471,6 +1494,10 @@
             "type": "text",
             "analyzer": "dutch"
           },
+          "langdan": {
+            "type": "text",
+            "analyzer": "danish"
+          },
           "langita": {
             "type": "text",
             "analyzer": "italian"
@@ -1513,6 +1540,12 @@
               "any.langdut"
               ]
           },
+          "langdan": {
+            "type": "keyword",
+            "copy_to": [
+              "any.langdan"
+              ]
+          },
           "langita": {
             "type": "keyword",
             "copy_to": ["any.langita"]
@@ -2045,6 +2078,9 @@
           "langdut": {
             "type": "keyword"
           },
+          "langdan": {
+            "type": "keyword"
+          },
           "langspa": {
             "type": "keyword"
           }