Merge remote-tracking branch 'origin/main'

k8s/dataverse/Chart.yaml

@@ -15,10 +15,10 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.7.0
+version: 0.9.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "6.3.0"
+appVersion: "6.5.0"

k8s/dataverse/README.md

@@ -14,7 +14,10 @@ Postgres is configured to automatically create and store a logical backup in S3.
 
 Before running the script, you must set these env variables:
 
+- `SOURCE_DATAVERSE_NAME`, the deployment name of the source Dataverse
+- `SOURCE_DATAVERSE_CONTEXT`, the Kubernetes context name of the source Dataverse
 - `DESTINATION_DATAVERSE_NAME`, the deployment name of the destination Dataverse
+- `DESTINATION_DATAVERSE_CONTEXT`, the Kubernetes context name of the destination Dataverse
 - `LOGICAL_BACKUP_S3_BUCKET`, the S3 bucket where the backup is located
 - `SCOPE` and `LOGICAL_BACKUP_S3_BUCKET_SCOPE_SUFFIX`, define the directory inside the S3 bucket where the backup is
    located
@@ -23,6 +26,11 @@ Before running the script, you must set these env variables:
 The values for `LOGICAL_BACKUP_S3_BUCKET`, `SCOPE` and `LOGICAL_BACKUP_S3_BUCKET_SCOPE_SUFFIX` can be found using
 `kubectl describe pod` on one of the backup job pods.
 
+Since reindexing the entire Dataverse database into the Solr index may take a long time depending on the number of
+datasets, the script also creates and loads a backup of the Solr index instead.
+If you don't have a lot of datasets and prefer reindexing, you can comment out the script section responsible for
+Solr backup creation and loading, and comment in the section for reindexing.
+
 ### Creating a database backup
 
 1. Login into the postgres pod and create and compress a logical backup.
@@ -35,28 +43,4 @@ The values for `LOGICAL_BACKUP_S3_BUCKET`, `SCOPE` and `LOGICAL_BACKUP_S3_BUCKET
 
 2. Copy the logical backup to your local computer
 
-   `kubectl cp $POSTGRES_POD_NAME:/tmp/jd.dump.gz ./jd.dump.gz`
-
-## Solr
-
-If you want to avoid a re-index (which may take a long time), you can also create and restore Solr backups.
-
-### Creating a Solr backup
-
-```
-$ kubectl exec -it $SOURCE_DATAVERSE_DEPLOYMENT_NAME-solr-0 -- bash
-# curl localhost:8983/solr/collection1/replication?command=backup
-# curl localhost:8983/solr/collection1/replication?command=details
-$ kubectl cp $SOURCE_DATAVERSE_DEPLOYMENT_NAME-solr-0:/var/solr/data/collection1/data/$SNAPSHOT_FILE_NAME $SNAPSHOT_FILE_NAME
-```
-
-Note: replace `$SNAPSHOT_FILE_NAME` with the name given by `curl localhost:8983/solr/collection1/replication?command=details`.
-
-### Restoring a Solr backup
-
-```
-$ kubectl cp $SNAPSHOT_FILE_NAME $DESTINATION_DATAVERSE_DEPLOYMENT_NAME-solr-0:/var/solr/data/collection1/data
-$ kubectl exec -it $DESTINATION_DATAVERSE_DEPLOYMENT_NAME-solr-0 -- bash
-# curl localhost:8983/solr/collection1/replication?command=restore
-# curl localhost:8983/solr/collection1/replication?command=restorestatus
-```
+   `kubectl cp $POSTGRES_POD_NAME:/tmp/jd.dump.gz ./jd.dump.gz`

k8s/dataverse/persona/nfdi4health/generate-permalink.sql

@@ -1,47 +1,33 @@
--- A script for creating, through a database stored procedure, sequential
--- 8 character identifiers from a base36 representation of current timestamp.
--- Adapted from: https://guides.dataverse.org/en/latest/_downloads/772201110a1c1b429e7c3336b6e9d36d/identifier_from_timestamp.sql
+-- Adapted from: https://github.com/IQSS/dataverse/blob/a36db2d7df0d9976c00179b82f11cfb338a6cfc8/doc/sphinx-guides/source/_static/util/createsequence.sql
 
-CREATE OR REPLACE FUNCTION base36_encode(
-  IN digits bigint, IN min_width int = 0)
-RETURNS varchar AS $$
+DO $$
 DECLARE
-chars char[];
-    ret varchar;
-    val bigint;
+last_val bigint;
 BEGIN
-    chars := ARRAY[
-      '0','1','2','3','4','5','6','7','8','9',
-      'A','B','C','D','E','F','G','H','I','J',
-      'K','L','M','N','O','P','Q','R','S','T',
-      'U','V','W','X','Y','Z'];
-    val := digits;
-    ret := '';
-    IF val < 0 THEN
-        val := val * -1;
-END IF;
-    WHILE val != 0 LOOP
-        ret := chars[(val % 36)+1] || ret;
-        val := val / 36;
-END LOOP;
+    -- Get the last value of the existing sequence
+    SELECT last_value INTO last_val FROM dvobject_id_seq;
 
-    IF min_width > 0 AND char_length(ret) < min_width THEN
-        ret := lpad(ret, min_width, '0');
-END IF;
+    -- Create the new sequence with the desired start and min values
+    EXECUTE format('
+            CREATE SEQUENCE datasetidentifier_seq
+            INCREMENT BY 1
+            MINVALUE %s
+            MAXVALUE 9223372036854775807
+            CACHE 1
+        ', last_val + 1);
+END $$;
 
-RETURN ret;
-END;
-$$ LANGUAGE plpgsql IMMUTABLE;
+ALTER TABLE datasetidentifier_seq OWNER TO "dataverse";
 
+-- And now create a PostgreSQL FUNCTION, for JPA to
+-- access as a NamedStoredProcedure:
 
 CREATE OR REPLACE FUNCTION generateIdentifierFromStoredProcedure()
 RETURNS varchar AS $$
 DECLARE
-curr_time_msec bigint;
-    identifier varchar;
+identifier varchar;
 BEGIN
-    curr_time_msec := extract(epoch from now())*1000;
-    identifier := base36_encode(curr_time_msec);
+    identifier := nextval('datasetidentifier_seq')::varchar;
 RETURN identifier;
 END;
 $$ LANGUAGE plpgsql IMMUTABLE;

k8s/dataverse/persona/nfdi4health/init.sh

@@ -22,10 +22,6 @@ echo "# hide progress meter
 # fail script on server error
 --fail-with-body" > ~/.curlrc
 
-echo "Configuring PID permalink generator function"
-PGPASSWORD=$DATAVERSE_DB_PASSWORD psql -h $DATAVERSE_DB_HOST -U $DATAVERSE_DB_USER < /scripts/bootstrap/nfdi4health/generate-permalink.sql
-echo
-
 echo "Setting superuser status"
 curl -X PUT "${DATAVERSE_URL}/api/admin/superuser/dataverseAdmin" -d true
 echo
@@ -141,6 +137,12 @@ while IFS= read -r DATAVERSE; do
   fi
 done <<< "${DATAVERSES}"
 
+# This should be done after creating dataverses if we want a chance of keeping the database IDs and Permalink IDs of our
+# datasets in sync
+echo "Configuring PID permalink generator function"
+PGPASSWORD=$DATAVERSE_DB_PASSWORD psql -h $DATAVERSE_DB_HOST -U $DATAVERSE_DB_USER < /scripts/bootstrap/nfdi4health/generate-permalink.sql
+echo
+
 # Last step as existence of one block is the indicator for a complete bootstrapped installation
 echo "Load custom metadata blocks"
 #curl -X POST -H "Content-type: text/tab-separated-values" $DATAVERSE_HOST/api/admin/datasetfield/load --upload-file customMDS.tsv

k8s/dataverse/persona/nfdi4health/schema.xml

@@ -142,6 +142,7 @@
 
     <field name="dvName" type="text_en" stored="true" indexed="true" multiValued="false"/>
     <field name="dvAlias" type="text_en" stored="true" indexed="true" multiValued="false"/>
+    <field name="dvParentAlias" type="text_en" stored="true" indexed="true" multiValued="false"/>
     <field name="dvAffiliation" type="text_en" stored="true" indexed="true" multiValued="false"/>
     <field name="dvDescription" type="text_en" stored="true" indexed="true" multiValued="false"/>
 
@@ -205,6 +206,7 @@
     <field name="entityId" type="plong" stored="true" indexed="true" multiValued="false"/>
 
     <field name="datasetVersionId" type="plong" stored="true" indexed="true" multiValued="false"/>
+    <field name="datasetType" type="string" stored="true" indexed="true" multiValued="false"/>
 
     <!-- Added for Dataverse 4.0 alpha 1 to sort by name  -->
     <!-- https://redmine.hmdc.harvard.edu/issues/3482 -->
@@ -232,6 +234,7 @@
     <field name="datasetValid" type="boolean" stored="true" indexed="true" multiValued="false"/>
 
     <field name="license" type="string" stored="true" indexed="true" multiValued="false"/>
+    <field name="fileCount" type="plong" stored="true" indexed="true" multiValued="false"/>
 
     <!--
         METADATA SCHEMA FIELDS
@@ -481,6 +484,7 @@
     <field name="productionPlace" type="text_en" multiValued="true" stored="true" indexed="true"/>
     <field name="publication" type="text_en" multiValued="true" stored="true" indexed="true"/>
     <field name="publicationCitation" type="text_en" multiValued="true" stored="true" indexed="true"/>
+    <field name="publicationRelationType" type="text_en" multiValued="true" stored="true" indexed="true"/>
     <field name="publicationIDNumber" type="text_en" multiValued="true" stored="true" indexed="true"/>
     <field name="publicationIDType" type="text_en" multiValued="true" stored="true" indexed="true"/>
     <field name="publicationURL" type="text_en" multiValued="true" stored="true" indexed="true"/>
@@ -645,6 +649,7 @@
     <copyField source="dvAlias" dest="_text_" maxChars="3000"/>
     <copyField source="dvAffiliation" dest="_text_" maxChars="3000"/>
     <copyField source="dsPersistentId" dest="_text_" maxChars="3000"/>
+    <copyField source="datasetType" dest="_text_" maxChars="3000"/>
     <!-- copyField commands copy one field to another at the time a document
         is added to the index.  It's used either to index the same field differently,
         or to add multiple fields to the same field for easier/faster searching.  -->
@@ -940,6 +945,7 @@
     <copyField source="productionPlace" dest="_text_" maxChars="3000"/>
     <copyField source="publication" dest="_text_" maxChars="3000"/>
     <copyField source="publicationCitation" dest="_text_" maxChars="3000"/>
+    <copyField source="publicationRelationType" dest="_text_" maxChars="3000"/>
     <copyField source="publicationIDNumber" dest="_text_" maxChars="3000"/>
     <copyField source="publicationIDType" dest="_text_" maxChars="3000"/>
     <copyField source="publicationURL" dest="_text_" maxChars="3000"/>

k8s/dataverse/templates/dataverse-pod.yaml

@@ -97,26 +97,18 @@ spec:
             - name: DATAVERSE_PID_PROVIDERS
               value: "fake,csh,ctgov,euctr,per,isrctn,ctri,jprn,actrn,drks"
             - name: DATAVERSE_PID_DEFAULT_PROVIDER
-              value: "fake"
-            - name: DATAVERSE_PID_FAKE_TYPE
-              value: "FAKE"
-            - name: DATAVERSE_PID_FAKE_LABEL
-              value: "Fake DOI Provider"
-            - name: DATAVERSE_PID_FAKE_SHOULDER
-              value: "FK2/"
-            - name: DATAVERSE_PID_FAKE_AUTHORITY
-              value: "10.5072"
+              value: "csh"
             - name: DATAVERSE_PID_CSH_TYPE
               value: "perma"
             - name: DATAVERSE_PID_CSH_LABEL
               value: "Permalink Provider"
             - name: DATAVERSE_PID_CSH_AUTHORITY
               value: {{.Values.dataverse.pid.permalink.authority}}
             - name: DATAVERSE_PID_CSH_SHOULDER
-              value: {{.Values.dataverse.pid.permalink.shoulder}}
-            - name: DATAVERSE_PID_CSH_BASE_URL
+              value: ""
+            - name: DATAVERSE_PID_CSH_PERMALINK_BASE_URL
               value: {{.Values.dataverse.pid.permalink.base_url}}
-            - name: DATAVERSE_PID_CSH_SEPARATOR
+            - name: DATAVERSE_PID_CSH_PERMALINK_SEPARATOR
               value: {{.Values.dataverse.pid.permalink.separator | quote}}
             - name: DATAVERSE_PID_CSH_IDENTIFIER_GENERATION_STYLE
               value: "storedProcGenerated"

k8s/dataverse/values.yaml

@@ -24,5 +24,5 @@ dataverse:
       base_url:
       separator:
 images:
-  backend: ghcr.io/nfdi4health/csh-ui/dataverse:6.3
-  configbaker: ghcr.io/nfdi4health/csh-ui/dataverse-baker:6.3
+  backend: ghcr.io/nfdi4health/csh-ui/dataverse:6.5
+  configbaker: ghcr.io/nfdi4health/csh-ui/dataverse-baker:6.5

scripts/load_dataverse_backup.sh

@@ -1,5 +1,14 @@
 #!/bin/bash
 
+LOGICAL_BACKUP_S3_BUCKET=
+SCOPE=
+LOGICAL_BACKUP_S3_BUCKET_SCOPE_SUFFIX=
+S3_CONFIG_FILE=
+SOURCE_DATAVERSE_NAME=
+SOURCE_DATAVERSE_CONTEXT=
+DESTINATION_DATAVERSE_NAME=
+DESTINATION_DATAVERSE_CONTEXT=
+
 S3_CONFIG_FILE="${S3_CONFIG_FILE:-'~/.s3cfg'}"
 
 # Computed from env variables above
@@ -11,13 +20,13 @@ echo "Downloading backup from S3..."
 s3cmd get $LAST_BACKUP_FILE . -c $S3_CONFIG_FILE --skip-existing
 
 echo "Copying backup to postgres pod..."
-kubectl cp $(basename $LAST_BACKUP_FILE) $POSTGRES_POD_NAME:/tmp/
+kubectl cp $(basename $LAST_BACKUP_FILE) $POSTGRES_POD_NAME:/tmp/ --context $DESTINATION_DATAVERSE_CONTEXT
 
 echo "Unzipping backup..."
-kubectl exec $POSTGRES_POD_NAME -- gunzip /tmp/$(basename $LAST_BACKUP_FILE)
+kubectl exec $POSTGRES_POD_NAME --context $DESTINATION_DATAVERSE_CONTEXT -- gunzip /tmp/$(basename $LAST_BACKUP_FILE)
 
 echo "Emptying database..."
-kubectl exec $POSTGRES_POD_NAME -- psql -P pager=off -U dataverse -c "-- Recreate the schema
+kubectl exec $POSTGRES_POD_NAME --context $DESTINATION_DATAVERSE_CONTEXT -- psql -P pager=off -U dataverse -c "-- Recreate the schema
 DROP SCHEMA public CASCADE;
 CREATE SCHEMA public;
 
@@ -27,35 +36,94 @@ GRANT ALL ON SCHEMA public TO public;"
 # source: https://stackoverflow.com/a/61221726
 
 echo "Loading backup into database..."
-kubectl exec $POSTGRES_POD_NAME -- psql -P pager=off -U dataverse -f /tmp/$(basename $LAST_BACKUP_FILE .gz) template1
+kubectl exec $POSTGRES_POD_NAME --context $DESTINATION_DATAVERSE_CONTEXT -- psql -P pager=off -U dataverse -f /tmp/$(basename $LAST_BACKUP_FILE .gz) template1
 
 
 echo "Updating database passwords..."
-kubectl get secret | grep ${DESTINATION_DATAVERSE_NAME}-dataverse-postgres.credentials.postgresql.acid.zalan.do | awk '{print $1}' | while read SECRET; do kubectl exec $POSTGRES_POD_NAME -- psql -P pager=off -U dataverse -c "ALTER USER $(echo $SECRET | awk -F. '{print $1}') WITH PASSWORD '$(kubectl get secrets/$SECRET -o=jsonpath="{.data.password}" | base64 -d)';"; done
+kubectl get secret --context $DESTINATION_DATAVERSE_CONTEXT | grep ${DESTINATION_DATAVERSE_NAME}-dataverse-postgres.credentials.postgresql.acid.zalan.do | awk '{print $1}' | while read SECRET; do kubectl exec $POSTGRES_POD_NAME --context $DESTINATION_DATAVERSE_CONTEXT -- psql -P pager=off -U dataverse -c "ALTER USER $(echo $SECRET | awk -F. '{print $1}') WITH PASSWORD '$(kubectl get secrets/$SECRET -o=jsonpath="{.data.password}" --context $DESTINATION_DATAVERSE_CONTEXT | base64 -d)';"; done
 
 echo "Restarting dataverse pod..."
-kubectl delete pod $DATAVERSE_POD_NAME
-kubectl wait --for=condition=Ready --timeout=-1s pod/$DATAVERSE_POD_NAME
-
+kubectl delete pod $DATAVERSE_POD_NAME --context $DESTINATION_DATAVERSE_CONTEXT
+kubectl wait --for=condition=Ready --timeout=-1s --context $DESTINATION_DATAVERSE_CONTEXT pod/$DATAVERSE_POD_NAME
+#
+## NOTE: The following block is commented out because it's no longer feasible time-wise to reindex Dataverse after
+# loading a backup. Since we have over 25,000 datasets, it takes too long.
+# Instead, we also load a backup for the Solr index.
 # Using port 8081 because 8080 is often already used if currently developing with Dataverse
-DATAVERSE_LOCAL_PORT=8081
-DATAVERSE_REMOTE_PORT=8080
-
-echo "Starting re-index..."
-kubectl port-forward $DATAVERSE_POD_NAME $DATAVERSE_LOCAL_PORT:$DATAVERSE_REMOTE_PORT >/dev/null &
-PORT_FORWARD_PID=$!
-# Kill the port-forward when this script exits
-trap '{
-    kill $PORT_FORWARD_PID 2>/dev/null
-}' EXIT
-# Wait for port to be available
-while ! nc -vz localhost $DATAVERSE_LOCAL_PORT >/dev/null 2>&1; do
-    sleep 0.1
+#DATAVERSE_LOCAL_PORT=8086
+#DATAVERSE_REMOTE_PORT=8080
+#
+#echo "Starting re-index..."
+#kubectl port-forward $DATAVERSE_POD_NAME $DATAVERSE_LOCAL_PORT:$DATAVERSE_REMOTE_PORT >/dev/null &
+#PORT_FORWARD_PID=$!
+## Kill the port-forward when this script exits
+#trap '{
+#    kill $PORT_FORWARD_PID 2>/dev/null
+#}' EXIT
+## Wait for port to be available
+#while ! nc -vz localhost $DATAVERSE_LOCAL_PORT >/dev/null 2>&1; do
+#    sleep 0.1
+#done
+#curl http://localhost:$DATAVERSE_LOCAL_PORT/api/admin/index/clear
+#echo
+#curl http://localhost:$DATAVERSE_LOCAL_PORT/api/admin/index
+#echo
+
+echo "Checking age of latest backup of source Solr..."
+SOLR_BACKUP_RESPONSE=$(kubectl exec -it ${SOURCE_DATAVERSE_NAME}-dataverse-solr-0 --context $SOURCE_DATAVERSE_CONTEXT --container solr -- curl localhost:8983/solr/collection1/replication?command=details)
+SOLR_BACKUP_STATUS=$(echo $SOLR_BACKUP_RESPONSE | jq -r '.details.backup.status')
+if [[ "$SOLR_BACKUP_STATUS" == "success" ]]; then
+    SOLR_BACKUP_TIMESTAMP=$(echo $SOLR_BACKUP_RESPONSE | jq -r '.details.backup.snapshotCompletedAt')
+
+    SOLR_BACKUP_TIMESTAMP_DATE=$(echo $SOLR_BACKUP_TIMESTAMP | cut -d'T' -f1)
+    SOLR_BACKUP_TIMESTAMP_HOUR=$(echo $SOLR_BACKUP_TIMESTAMP | cut -d'T' -f2 | cut -d':' -f1)
+
+    CURRENT_DATE=$(date -u +"%Y-%m-%d")
+    CURRENT_HOUR=$(date -u +"%H")
+
+    if [[ "$SOLR_BACKUP_TIMESTAMP_DATE" == "$CURRENT_DATE" && "$SOLR_BACKUP_TIMESTAMP_HOUR" == "$CURRENT_HOUR" ]]; then
+        # The timestamp is within the current hour
+        echo "Backup is not too old."
+    else
+        echo "Backup is too old. Creating backup of source Solr..."
+        kubectl exec ${SOURCE_DATAVERSE_NAME}-dataverse-solr-0 --context $SOURCE_DATAVERSE_CONTEXT --container solr -- curl -s "localhost:8983/solr/collection1/replication?command=backup&numberToKeep=1"; echo
+        while true; do
+            SOLR_BACKUP_RESPONSE=$(kubectl exec ${SOURCE_DATAVERSE_NAME}-dataverse-solr-0 --context $SOURCE_DATAVERSE_CONTEXT --container solr -- curl localhost:8983/solr/collection1/replication?command=details)
+            SOLR_BACKUP_STATUS=$(echo $SOLR_BACKUP_RESPONSE | jq -r '.details.backup.status')
+            echo $SOLR_BACKUP_STATUS
+            if [[ "$SOLR_BACKUP_STATUS" == "success" ]]; then
+                break
+            fi
+            echo "Waiting for Solr backup to be completed..."
+            sleep 1
+        done
+    fi
+fi
+
+SOLR_BACKUP_NAME=$(echo $SOLR_BACKUP_RESPONSE | jq -r '.details.backup.directoryName')
+
+if kubectl exec ${DESTINATION_DATAVERSE_NAME}-dataverse-solr-0 --container solr --context $DESTINATION_DATAVERSE_CONTEXT -- sh -c "[ -d /var/solr/data/collection1/data/${SOLR_BACKUP_NAME} ]"; then
+    echo "Backup was already copied to destination Solr."
+else
+    echo "Copying completed backup ${SOLR_BACKUP_NAME} to destination Solr... (this may take some time)"
+    kubectl exec ${SOURCE_DATAVERSE_NAME}-dataverse-solr-0 --container solr --context $SOURCE_DATAVERSE_CONTEXT -- tar -zcf /tmp/${SOLR_BACKUP_NAME}.tar.gz -C /var/solr/data/collection1/data/ ${SOLR_BACKUP_NAME} > /dev/null
+    kubectl cp ${SOURCE_DATAVERSE_NAME}-dataverse-solr-0:/tmp/${SOLR_BACKUP_NAME}.tar.gz ${SOLR_BACKUP_NAME}.tar.gz --container solr --context $SOURCE_DATAVERSE_CONTEXT --retries=-1 > /dev/null
+    kubectl cp ${SOLR_BACKUP_NAME}.tar.gz ${DESTINATION_DATAVERSE_NAME}-dataverse-solr-0:/tmp/ --container solr --context $DESTINATION_DATAVERSE_CONTEXT --retries=-1 > /dev/null
+    kubectl exec ${DESTINATION_DATAVERSE_NAME}-dataverse-solr-0 --container solr --context $DESTINATION_DATAVERSE_CONTEXT -- rm -r /var/solr/data/collection1/data/snapshot.*
+    kubectl exec ${DESTINATION_DATAVERSE_NAME}-dataverse-solr-0 --container solr --context $DESTINATION_DATAVERSE_CONTEXT -- tar -zxf /tmp/${SOLR_BACKUP_NAME}.tar.gz -C /var/solr/data/collection1/data/
+fi
+
+kubectl exec ${DESTINATION_DATAVERSE_NAME}-dataverse-solr-0 --context $DESTINATION_DATAVERSE_CONTEXT --container solr -- curl -s "localhost:8983/solr/collection1/replication?command=restore" > /dev/null
+
+while true; do
+    SOLR_BACKUP_LOAD_RESPONSE=$(kubectl exec -t ${DESTINATION_DATAVERSE_NAME}-dataverse-solr-0 --context $DESTINATION_DATAVERSE_CONTEXT --container solr -- curl -s "localhost:8983/solr/collection1/replication?command=restorestatus")
+    SOLR_BACKUP_LOAD_STATUS=$(echo $SOLR_BACKUP_LOAD_RESPONSE | jq -r '.restorestatus.status')
+    if [[ "$SOLR_BACKUP_LOAD_STATUS" == "success" ]]; then
+        break
+    fi
+    echo "Waiting for Solr backup to be loaded..."
+    sleep 3
 done
-curl http://localhost:$DATAVERSE_LOCAL_PORT/api/admin/index/clear
-echo
-curl http://localhost:$DATAVERSE_LOCAL_PORT/api/admin/index
-echo
 
 echo
-echo "Done! Please wait for the re-indexing to finish, then the backup loading will be complete."
+echo "Done! Backup loading complete."