Merge pull request #210 from CDRH/elasticsearch_upgrade

Elasticsearch upgrade
CDRH · Mar 23, 2023 · 8a99138 · 8a99138
2 parents 2df4dde + f982173
commit 8a99138
Show file tree

Hide file tree

Showing 6 changed files with 71 additions and 58 deletions.
diff --git a/lib/config/es_api_schemas/2.0.yml b/lib/config/es_api_schemas/2.0.yml
@@ -1,37 +1,38 @@
 # compatible with Apium v2.0
 settings:
-  analysis:
-    char_filter:
-      escapes:
-        type: mapping
-        mappings:
-          - "<em> => "
-          - "</em> => "
-          - "<u> => "
-          - "</u> => "
-          - "<strong> => "
-          - "</strong> => "
-          - "- => "
-          - "& => "
-          - ": => "
-          - "; => "
-          - ", => "
-          - ". => "
-          - "$ => "
-          - "@ => "
-          - "~ => "
-          - "\" => "
-          - "' => "
-          - "[ => "
-          - "] => "
-    normalizer:
-      keyword_normalized:
-        type: custom
-        char_filter:
-          - escapes
-        filter:
-          - asciifolding
-          - lowercase
+  settings:
+    analysis:
+      char_filter:
+        escapes:
+          type: mapping
+          mappings:
+            - "<em> => "
+            - "</em> => "
+            - "<u> => "
+            - "</u> => "
+            - "<strong> => "
+            - "</strong> => "
+            - "- => "
+            - "& => "
+            - ": => "
+            - "; => "
+            - ", => "
+            - ". => "
+            - "$ => "
+            - "@ => "
+            - "~ => "
+            - "\" => "
+            - "' => "
+            - "[ => "
+            - "] => "
+      normalizer:
+        keyword_normalized:
+          type: custom
+          char_filter:
+            - escapes
+          filter:
+            - asciifolding
+            - lowercase
 mappings:
   properties:
     identifier:

diff --git a/lib/datura/elasticsearch/alias.rb b/lib/datura/elasticsearch/alias.rb
@@ -20,7 +20,7 @@ def self.add
         { add: { alias: ali, index: idx } }
       ]
     }
-    RestClient.post(base_url, data.to_json, { content_type: :json }) { |res, req, result|
+    RestClient.post(base_url, data.to_json, @auth_header.merge({ content_type: :json })) { |res, req, result|
       if result.code == "200"
         puts res
         puts "Successfully added alias #{ali}. Current alias list:"
@@ -40,15 +40,15 @@ def self.delete
 
     url = File.join(options["es_path"], idx, "_alias", ali)
 
-    res = JSON.parse(RestClient.delete(url))
+    res = JSON.parse(RestClient.delete(url, @auth_header))
     puts JSON.pretty_generate(res)
     list
   end
 
   def self.list
     options = Datura::Options.new({}).all
 
-    res = RestClient.get(File.join(options["es_path"], "_aliases"))
+    res = RestClient.get(File.join(options["es_path"], "_aliases"), )
     JSON.pretty_generate(JSON.parse(res))
   end
 

diff --git a/lib/datura/elasticsearch/data.rb b/lib/datura/elasticsearch/data.rb
@@ -47,7 +47,7 @@ def self.clear_all(options)
     if confirm == "Yes I'm sure"
       url = File.join(options["es_path"], options["es_index"], "_doc", "_delete_by_query?pretty=true")
       json = { "query" => { "match_all" => {} } }
-      RestClient.post(url, json.to_json, { content_type: :json }) { |res, req, result|
+      RestClient.post(url, json.to_json, @auth_header.merge({ content_type: :json })) { |res, req, result|
         if result.code == "200"
           puts res
         else
@@ -66,7 +66,7 @@ def self.clear_index(options)
 
     if confirmation
       data = self.build_clear_data(options)
-      RestClient.post(url, data.to_json, { content_type: :json }) { |res, req, result|
+      RestClient.post(url, data.to_json, @auth_header.merge({ content_type: :json })) { |res, req, result|
         if result.code == "200"
           puts res
         else

diff --git a/lib/datura/elasticsearch/index.rb b/lib/datura/elasticsearch/index.rb
@@ -1,6 +1,7 @@
 require "json"
 require "rest-client"
 require "yaml"
+require "base64"
 
 require_relative "./../elasticsearch.rb"
 
@@ -21,10 +22,11 @@ def initialize(options = nil, schema_mapping: false)
 
     @index_url = File.join(@options["es_path"], @options["es_index"])
     @pretty_url = "#{@index_url}?pretty=true"
-    @mapping_url = File.join(@index_url, "_mapping", "_doc?pretty=true")
+    @mapping_url = File.join(@index_url, "_mapping?pretty=true")
 
     # yaml settings (if exist) and mappings
     @requested_schema = YAML.load_file(@options["es_schema"])
+    @auth_header = Datura::Helpers.construct_auth_header(@options)
     # if requested, grab the mapping currently associated with this index
     # otherwise wait until after the requested schema is loaded
     get_schema_mapping if schema_mapping
@@ -33,17 +35,16 @@ def initialize(options = nil, schema_mapping: false)
   def create
     json = @requested_schema["settings"].to_json
     puts "Creating ES index for API version #{@options["api_version"]}: #{@pretty_url}"
-
     if json && json != "null"
-      RestClient.put(@pretty_url, json, { content_type: :json }) { |res, req, result|
+      RestClient.put(@pretty_url, json, @auth_header.merge({ content_type: :json })) { |res, req, result|
         if result.code == "200"
           puts res
         else
           raise "#{result.code} error creating Elasticsearch index: #{res}"
         end
       }
     else
-      RestClient.put(@pretty_url, nil) { |res, req, result|
+      RestClient.put(@pretty_url, nil, @auth_header) { |res, req, result|
         if result.code == "200"
           puts res
         else
@@ -56,15 +57,15 @@ def create
   def delete
     puts "Deleting #{@options["es_index"]} via url #{@pretty_url}"
 
-    RestClient.delete(@pretty_url) { |res, req, result|
+    RestClient.delete(@pretty_url, @auth_header) { |res, req, result|
       if result.code != "200"
         raise "#{result.code} error deleting Elasticsearch index: #{res}"
       end
     }
   end
 
   def get_schema
-    RestClient.get(@mapping_url) { |res, req, result|
+    RestClient.get(@mapping_url, @auth_header) { |res, req, result|
       if result.code == "200"
         JSON.parse(res)
       else
@@ -77,13 +78,13 @@ def get_schema_mapping
     # if mapping has not already been set, get the schema and manipulate
     if !defined?(@schema_mapping)
       @schema_mapping = {
-        "dyanmic" => nil,  # /regex|regex/
+        "dynamic" => nil,  # /regex|regex/
         "fields" => [],    # [ fields ]
         "nested" => {}     # { field: [ nested_fields ] }
       }
 
       schema = get_schema[@options["es_index"]]
-      doc = schema["mappings"]["_doc"]
+      doc = schema["mappings"]
       doc["properties"].each do |field, value|
         @schema_mapping["fields"] << field
         if value["type"] == "nested"
@@ -92,12 +93,14 @@ def get_schema_mapping
       end
 
       regex_pieces = []
-      doc["dynamic_templates"].each do |template|
-        mapping = template.map { |k,v| v["match"] }.first
-        # dynamic fields are listed like *_k and will need
-        # to be converted to ^.*_k$, then combined into a mega-regex
-        es_match = mapping.sub("*", ".*")
-        regex_pieces << es_match
+      if doc["dynamic_templates"]
+        doc["dynamic_templates"].each do |template|
+          mapping = template.map { |k,v| v["match"] }.first
+          # dynamic fields are listed like *_k and will need
+          # to be converted to ^.*_k$, then combined into a mega-regex
+          es_match = mapping.sub("*", ".*")
+          regex_pieces << es_match
+        end
       end
       if !regex_pieces.empty?
         regex_joined = regex_pieces.join("|")
@@ -111,7 +114,7 @@ def set_schema
     json = @requested_schema["mappings"].to_json
 
     puts "Setting schema: #{@mapping_url}"
-    RestClient.put(@mapping_url, json, { content_type: :json }) { |res, req, result|
+    RestClient.put(@mapping_url, json, @auth_header.merge({ content_type: :json })) { |res, req, result|
       if result.code == "200"
         puts res
       else
@@ -206,9 +209,10 @@ def self.clear_all(options)
     puts "Type: 'Yes I'm sure'"
     confirm = STDIN.gets.chomp
     if confirm == "Yes I'm sure"
-      url = File.join(options["es_path"], options["es_index"], "_doc", "_delete_by_query?pretty=true")
+      url = File.join(options["es_path"], options["es_index"], "_delete_by_query?pretty=true")
+      auth_header = Datura::Helpers.construct_auth_header(options)
       json = { "query" => { "match_all" => {} } }
-      RestClient.post(url, json.to_json, { content_type: :json }) { |res, req, result|
+      RestClient.post(url, json.to_json, auth_header.merge({ content_type: :json })) { |res, req, result|
         if result.code == "200"
           puts res
         else
@@ -222,13 +226,14 @@ def self.clear_all(options)
   end
 
   def self.clear_index(options)
-    url = File.join(options["es_path"], options["es_index"], "_doc", "_delete_by_query?pretty=true")
+    url = File.join(options["es_path"], options["es_index"], "_delete_by_query?pretty=true")
     confirmation = self.confirm_clear(options, url)
 
     if confirmation
       data = self.build_clear_data(options)
-      RestClient.post(url, data.to_json, { content_type: :json }) { |res, req, result|
-        if result.code == "200"
+      auth_header = Datura::Helpers.construct_auth_header(options)
+      RestClient.post(url, data.to_json, auth_header.merge({content_type: :json })) { |res, req, result|
+        if result.code == "200" || result.code == "201"
           puts res
         else
           raise "#{result.code} error when clearing index: #{res}"

diff --git a/lib/datura/file_type.rb b/lib/datura/file_type.rb
@@ -30,6 +30,7 @@ def initialize(location, options)
     @out_html = File.join(output, "html")
     @out_iiif = File.join(output, "iiif")
     @out_solr = File.join(output, "solr")
+    @auth_header = Datura::Helpers.construct_auth_header(options)
     Datura::Helpers.make_dirs(@out_es, @out_html, @out_iiif, @out_solr)
     # script locations set in child classes
   end
@@ -68,7 +69,7 @@ def post_es(es)
           # NOTE: If you need to do partial updates rather than replacement of doc
           # you will need to add _update at the end of this URL
           begin
-            RestClient.put("#{es.index_url}/_doc/#{id}", doc.to_json, {:content_type => :json } )
+            RestClient.put("#{es.index_url}/_doc/#{id}", doc.to_json, @auth_header.merge({:content_type => :json }) )
           rescue => e
             error = "Error transforming or posting to ES for #{self.filename(false)}: #{e}"
           end

diff --git a/lib/datura/helpers.rb b/lib/datura/helpers.rb
@@ -171,4 +171,10 @@ def self.should_update?(file, since_date=nil)
     end
   end
 
+  def self.construct_auth_header(options)
+    username = options["es_user"]
+    password = options["es_password"]
+    { "Authorization" => "Basic #{Base64::encode64("#{username}:#{password}")}" }
+  end
+
 end