Added initial ES configuration.

README.md

@@ -1,2 +1,59 @@
 # vivo-es
-Configuration for ElasticSearch index used by VIVO
+Configuration for Elasticsearch/OpenSearch index used by VIVO
+
+# How to setup?
+
+## Build the Docker Image:
+
+```
+sudo docker build -t vivo-elasticsearch -f elasticsearch/Dockerfile .
+```
+if you want to use OpenSearch:
+```
+sudo docker build -t vivo-opensearch -f opensearch/Dockerfile .
+```
+
+## Run the Container:
+
+```
+docker run -p 9200:9200 -p 9300:9300 --name vivo_es vivo-elasticsearch
+```
+if you built OpenSearch image:
+```
+docker run -p 9200:9200 -p 9300:9300 --name vivo_os vivo-opensearch
+```
+
+This setup will start Elasticsearch/OpenSearch, expose it on localhost:9200, and create the vivo index with the specified mapping by loading the configuration from index-config.json.
+
+## Alternatively - Run Elasticsearch locally
+
+1. Download Elasticsearch (suited for your platform) from the [official website](https://www.elastic.co/downloads/elasticsearch).
+2. Run `bin/elasticsearch` (or `bin\elasticsearch.bat` on Windows) to start Elasticsearch [with security enabled](https://www.elastic.co/guide/en/elasticsearch/reference/current/configuring-stack-security.html).
+3. Create `vivo` index by running:
+
+```
+curl -k -u '<ES_USERNAME>:<ES_PASSWORD>' -X PUT "https://localhost:9200/vivo" -H 'Content-Type: application/json' -d index-config.json
+```
+
+## Alternatively - Run OpenSearch locally
+
+1. Download OpenSearch (suited for your platform) from the [official website](https://opensearch.org/versions/opensearch-2-18-0.html).
+2. Run `./opensearch` (or `./opensearch.bat` on Windows) to start OpenSearch [with security enabled](https://opensearch.org/docs/latest/security/).
+3. Create `vivo` index by running:
+
+```
+curl -k -u '<OS_USERNAME>:<OS_PASSWORD>' -X PUT "https://localhost:9200/vivo" -H 'Content-Type: application/json' -d index-config.json
+```
+
+# Adding security
+By default, docker configuration sets up Elasticsearch/OpenSearch without any security measures. A configuration like that is only viable if you are running your ES/OS instance inside of an internal local-area network without exposing it to the internet. If you need to expose your ES/OS instance to the internet you MUST activate necessary security mesures.
+
+In order to setup security (SSL + basic authentication) you have to do the following steps:
+
+- Comment-out or remove the following line from the Dockerfile `ENV xpack.security.enabled=false` for Elasticsearch or `ENV plugins.security.disabled=true` for OpenSearch. If you use OS, you have to provide an initial administrator password through `OPENSEARCH_INITIAL_ADMIN_PASSWORD` variable.
+
+- Build the image and run the respected container as explained above
+
+- If you are using ES, upon startup, the script will generate a new secure password for you to use when connecting to the instance. Find the console output that looks like this: `The new password for the elastic user is: <PASSWORD_VALUE>` and save the password value, you cannot access it later. Keep in mind that, at this moment, VIVO only supports basic authentication for ES/OS (API key authentication will be added in the future).
+
+- Then, simply use your new password (username is always `elastic`/`admin`) to connect to your ES/OS instance (respectfully) from VIVO application.

elasticsearch/Dockerfile

@@ -0,0 +1,19 @@
+FROM docker.elastic.co/elasticsearch/elasticsearch:8.9.0
+
+# Simple, single node deployment
+ENV discovery.type=single-node
+ENV ES_JAVA_OPTS="-Xms512m -Xmx512m"
+ENV xpack.security.enabled=false
+
+# VIVO index name
+ENV INDEX_NAME="vivo"
+
+# Default es username
+ENV ES_USERNAME="elastic"
+
+EXPOSE 9200 9300
+
+COPY ./elasticsearch/setup-index.sh /usr/share/elasticsearch/setup-index.sh
+COPY index-config.json /usr/share/elasticsearch/index-config.json
+
+CMD ["sh", "-c", "/usr/local/bin/docker-entrypoint.sh & sleep 15 && sh /usr/share/elasticsearch/setup-index.sh && wait"]

elasticsearch/setup-index.sh

@@ -0,0 +1,48 @@
+#!/bin/bash
+
+
+if [ -f /usr/share/elasticsearch/setup_done.flag ]; then
+    echo "Setup has already been completed, skipping setup."
+    exit 0
+fi
+
+
+SSL_ENABLED=$(curl -sk -X GET "https://localhost:9200")
+
+if [ -z "$SSL_ENABLED" ]; then
+    echo "SSL not enabled, falling back to HTTP..."
+    SSL_ENABLED="false"
+else
+    SSL_ENABLED="true"
+    echo "SSL is enabled"
+fi
+
+if [ "$SSL_ENABLED" == "true" ]; then
+    ES_URL="https://localhost:9200"
+else
+    ES_URL="http://localhost:9200"
+fi
+
+
+ES_PASSWORD=$( /usr/share/elasticsearch/bin/elasticsearch-reset-password -u $ES_USERNAME --url $ES_URL --batch 2>&1 | grep -oP '(?<=New value: ).*' )
+
+echo "The new password for the [$ES_USERNAME] user is: $ES_PASSWORD"
+
+
+AUTH=""
+if [[ -n "$ES_USERNAME" && -n "$ES_PASSWORD" ]]; then
+    AUTH="-u $ES_USERNAME:$ES_PASSWORD"
+fi
+
+
+until curl -k -s $AUTH -X GET "$ES_URL"; do
+    echo "Waiting for Elasticsearch to start..."
+    sleep 5
+done
+
+echo "Elasticsearch is up..."
+
+
+curl -k $AUTH -X PUT "$ES_URL/$INDEX_NAME" -H 'Content-Type: application/json' -d @/usr/share/elasticsearch/index-config.json
+
+touch /usr/share/elasticsearch/setup_done.flag

index-config.json

@@ -0,0 +1,181 @@
+{
+  "settings":{
+     "index":{
+        "analysis":{
+           "tokenizer":{
+              "keyword_tokenizer":{
+                 "type":"keyword"
+              },
+              "whitespace_tokenizer":{
+                 "type":"whitespace"
+              }
+           },
+           "filter":{
+              "lowercase_filter":{
+                 "type":"lowercase"
+              },
+              "edgengram_filter":{
+                 "type":"edge_ngram",
+                 "min_gram":2,
+                 "max_gram":25
+              },
+              "word_delimiter_filter":{
+                 "type":"word_delimiter",
+                 "generate_word_parts":true,
+                 "generate_number_parts":true,
+                 "catenate_words":false,
+                 "catenate_numbers":false,
+                 "catenate_all":false,
+                 "split_on_case_change":true
+              },
+              "porter_stem_filter":{
+                 "type":"snowball",
+                 "language":"English"
+              }
+           },
+           "analyzer":{
+              "default":{
+                 "type":"english"
+              },
+              "edgengram_untokenized":{
+                 "type":"custom",
+                 "tokenizer":"keyword_tokenizer",
+                 "filter":[
+                    "lowercase_filter",
+                    "edgengram_filter"
+                 ]
+              },
+              "edgengram_untokenized_query":{
+                 "type":"custom",
+                 "tokenizer":"keyword_tokenizer",
+                 "filter":[
+                    "lowercase_filter"
+                 ]
+              },
+              "edgengram_stemmed":{
+                 "type":"custom",
+                 "tokenizer":"whitespace_tokenizer",
+                 "filter":[
+                    "word_delimiter_filter",
+                    "lowercase_filter",
+                    "porter_stem_filter",
+                    "edgengram_filter"
+                 ]
+              },
+              "edgengram_stemmed_query":{
+                 "type":"custom",
+                 "tokenizer":"whitespace_tokenizer",
+                 "filter":[
+                    "word_delimiter_filter",
+                    "lowercase_filter",
+                    "porter_stem_filter"
+                 ]
+              }
+           }
+        }
+     }
+  },
+  "mappings":{
+     "dynamic_templates":[
+        {
+           "field_sort_template":{
+              "match":"*_label_sort",
+              "mapping":{
+                 "type":"text",
+                 "fields":{
+                    "keyword":{
+                       "type":"keyword"
+                    }
+                 },
+                 "fielddata":true
+              }
+           }
+        },
+        {
+           "field_ss_template":{
+              "match":"*_ss",
+              "mapping":{
+                 "type":"text",
+                 "fields":{
+                    "keyword":{
+                       "type":"keyword",
+                       "ignore_above":256
+                    }
+                 },
+                 "fielddata":true
+              }
+           }
+        },
+        {
+           "date_range_template":{
+              "match":"*_drsim",
+              "mapping":{
+                 "type":"date_range",
+                 "format":"strict_date_optional_time||epoch_millis"
+              }
+           }
+        }
+     ],
+     "properties":{
+        "ALLTEXT":{
+           "type":"text",
+           "analyzer":"english",
+           "fields":{
+              "keyword":{
+                 "type":"keyword",
+                 "ignore_above":256
+              }
+           }
+        },
+        "ALLTEXTUNSTEMMED":{
+           "type":"text",
+           "analyzer":"standard"
+        },
+        "DocId":{
+           "type":"keyword"
+        },
+        "classgroup":{
+           "type":"keyword"
+        },
+        "type":{
+           "type":"keyword"
+        },
+        "mostSpecificTypeURIs":{
+           "type":"keyword"
+        },
+        "indexedTime":{
+           "type":"long"
+        },
+        "nameRaw":{
+           "type":"keyword"
+        },
+        "URI":{
+           "type":"keyword"
+        },
+        "THUMBNAIL":{
+           "type":"integer"
+        },
+        "THUMBNAIL_URL":{
+           "type":"keyword"
+        },
+        "nameLowercaseSingleValued":{
+           "type":"text",
+           "analyzer":"standard",
+           "fielddata":true
+        },
+        "BETA":{
+           "type":"float"
+        },
+        "acNameUntokenized":{
+           "type":"text",
+           "analyzer":"edgengram_untokenized",
+           "search_analyzer":"edgengram_untokenized_query"
+        },
+        "acNameStemmed":{
+           "type":"text",
+           "analyzer":"edgengram_stemmed",
+           "search_analyzer":"edgengram_stemmed_query"
+        }
+     }
+  }
+}

opensearch/Dockerfile

@@ -0,0 +1,22 @@
+FROM opensearchproject/opensearch:2.18.0
+
+# Simple, single node deployment
+ENV discovery.type=single-node
+ENV OPENSEARCH_JAVA_OPTS="-Xms512m -Xmx512m"
+ENV plugins.security.disabled=true
+
+# VIVO index name
+ENV INDEX_NAME="vivo"
+
+# Default OpenSearch username
+ENV OS_USERNAME="admin"
+
+# Provide strong initial password
+ENV OPENSEARCH_INITIAL_ADMIN_PASSWORD="<STRONG_PASSWORD>"
+
+EXPOSE 9200 9300
+
+COPY /opensearch/setup-index.sh /usr/share/opensearch/setup-index.sh
+COPY index-config.json /usr/share/opensearch/index-config.json
+
+CMD ["sh", "-c", "/usr/share/opensearch/opensearch-docker-entrypoint.sh & sleep 15 && sh /usr/share/opensearch/setup-index.sh && wait"]

opensearch/setup-index.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+
+
+if [ -f /usr/share/opensearch/setup_done.flag ]; then
+    echo "Setup has already been completed, skipping setup."
+    exit 0
+fi
+
+
+SSL_ENABLED=$(curl -sk -X GET "https://localhost:9200")
+
+if [ -z "$SSL_ENABLED" ]; then
+    echo "SSL not enabled, falling back to HTTP..."
+    SSL_ENABLED="false"
+else
+    SSL_ENABLED="true"
+    echo "SSL is enabled"
+fi
+
+if [ "$SSL_ENABLED" == "true" ]; then
+    OS_URL="https://localhost:9200"
+else
+    OS_URL="http://localhost:9200"
+fi
+
+
+AUTH="-u $OS_USERNAME:$OPENSEARCH_INITIAL_ADMIN_PASSWORD"
+
+until curl -k -s $AUTH -X GET "$OS_URL"; do
+    echo "Waiting for OpenSearch to start..."
+    sleep 5
+done
+
+echo "OpenSearch is up..."
+
+
+curl -k $AUTH -X PUT "$OS_URL/$INDEX_NAME" -H 'Content-Type: application/json' -d @/usr/share/opensearch/index-config.json
+
+touch /usr/share/opensearch/setup_done.flag