elasticsearch-api 8.18.0 → 9.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d92d90d78651e26eacae85b93d362209401741be16833772f8905b5c6a4017d5
-  data.tar.gz: 43657d27a5e30b001cdf5356ec2779a75afecd10f52599f847593acf3f05f8b0
+  metadata.gz: 1b6b96fb592177062e080e5f81e8a67b67421c5d11bde2decbec398460b16a8d
+  data.tar.gz: 540e10412256da73a2311f659edc6930e2205f94691fbe28ee0d87cce8de67f9
 SHA512:
-  metadata.gz: 59844d5a5485c499a4d0be5b05c9fe829aef551ad9bf3be0fd5686e309ef0a471b4cb2abebef192889a2a7dd0b05a1d4a78a224f7bf225b7e494877225b2b869
-  data.tar.gz: 3d7ca26d37d4ce2d2cfaa3b45143153abd2cd5577531837f72cd00da75f334e9abafe1b22463bf9731480e53c96f8b85a7e4be7c71b848d4d25964f5d2dd0e09
+  metadata.gz: 8802233dfefffa10fbb544ced7c3b624fc9dae6d3ad4f53a8ba3cf940040ad441622e5dbc80615beb08f4142f7be5c0c42ba09bb6b4d6219a7a26c04ec1a957b
+  data.tar.gz: dc84cd9102676845afe5fc1e8e420122ee4121d8ce34fa8aec565e517b57032adc395b1ba1496c5331bc6777cf9700c867964d5146d806d59620f6f52f56703b

data/README.md

@@ -4,7 +4,7 @@
 
 **Refer to the [official documentation on Elasticsearch API](https://www.elastic.co/guide/en/elasticsearch/client/ruby-api/current/api.html).**
 
-The `elasticsearch-api` library provides a Ruby implementation of the [Elasticsearch](http://elasticsearch.com) REST API. It does not provide an Elasticsearch client; see the [`elastic-transport`](https://github.com/elastic/elastic-transport-ruby/) library.
+The `elasticsearch-api` library provides a Ruby implementation of the [Elasticsearch](http://elasticsearch.com) REST API. It does not provide an Elasticsearch client. See [elasticsearch](https://github.com/elastic/elasticsearch-ruby) and the [`elastic-transport`](https://github.com/elastic/elastic-transport-ruby/) libraries for a full Elasticsearch client and HTTP transport layer respectively.
 
 We follow Ruby’s own maintenance policy and officially support all currently maintained versions per [Ruby Maintenance Branches](https://www.ruby-lang.org/en/downloads/branches/).
 
@@ -15,17 +15,21 @@ Language clients are forward compatible; meaning that clients support communicat
 
 Refer to [CONTRIBUTING](https://github.com/elastic/elasticsearch-ruby/blob/main/CONTRIBUTING.md).
 
-We run the test suite for Elasticsearch's Rest API tests. You can read more about this in [the test runner README](https://github.com/elastic/elasticsearch-ruby/tree/main/api-spec-testing#rest-api-yaml-test-runner).
+Use `bundle exec rake test:unit` to run Unit tests. Add the environment variable `COVERAGE` to see Simplecov test coverage.
 
-The `rest_api` task needs the test files from Elasticsearch. You can run the rake task to download the test artifacts in the root folder of the project. You can pass in a version to the task as a parameter:
+The integration tests on this project run the [Elasticsearch Client tests](https://github.com/elastic/elasticsearch-clients-tests/) with the [Elasticsearch Tests Runner](https://github.com/elastic/es-test-runner-ruby/) library. You can run a docker container with Elasticsearch with a Rake task from the root directory of this project:
 
-`rake download_artifacts[8.5.0-SNAPSHOT]`
+```bash
+$ rake es:up
+```
 
-Or it can get the version from a running cluster to determine which version and build hash of Elasticsearch to use and test against:
+This will start whatever version of Elasticsearch is set in the Buildkite pipeline file (`../.buildkite/pipeline.yml`) with security enabled. You can also specify a version and a suite ('free' or 'platinum' for security disabled/enabled):
 
-`TEST_ES_SERVER=http://localhost:9200 rake es:download_artifacts`
+```bash
+$ rake es:start[version,suite] # e.g. rake es:start[9.0.0-SNAPSHOT, free]
+```
 
-This will download the necessary files used for the integration tests to `./tmp`.
+You can run the integration tests with `bundle exec rake test:integration`.
 
 ### Code generation
 

data/elasticsearch-api.gemspec

@@ -34,51 +34,36 @@ Gem::Specification.new do |s|
     'source_code_uri' => 'https://github.com/elastic/elasticsearch-ruby/tree/main/elasticsearch-api',
     'bug_tracker_uri' => 'https://github.com/elastic/elasticsearch-ruby/issues'
   }
-  s.files         = `git ls-files`.split($/)
-  s.executables   = s.files.grep(%r{^bin/}) { |f| File.basename(f) }
-  s.test_files    = s.files.grep(%r{^(test|spec|features)/})
+  s.files = `git ls-files`.split($/).reject do |file|
+    file.match(/^utils\/|^spec\/|^api-spec-testing\/|^Gemfile|^Rakefile/)
+  end
   s.require_paths = ['lib']
-
   s.extra_rdoc_files  = ['README.md', 'LICENSE.txt']
   s.rdoc_options      = ['--charset=UTF-8']
 
-  s.required_ruby_version = '>= 2.5'
-
+  s.required_ruby_version = '>= 2.6' # For compatibility with JRuby 9.3
   s.add_dependency 'multi_json'
 
   s.add_development_dependency 'ansi'
   s.add_development_dependency 'bundler'
   s.add_development_dependency 'elasticsearch'
   s.add_development_dependency 'elasticsearch-test-runner' unless defined?(JRUBY_VERSION) && JRUBY_VERSION <= '9.4'
-  s.add_development_dependency 'minitest'
-  s.add_development_dependency 'minitest-reporters', '>= 1.6'
-  s.add_development_dependency 'mocha'
   s.add_development_dependency 'pry'
   s.add_development_dependency 'rake'
-  s.add_development_dependency 'shoulda-context'
   s.add_development_dependency 'yard'
 
   # Gems for testing integrations
   s.add_development_dependency 'concurrent-ruby', '1.3.4' if defined? JRUBY_VERSION && JRUBY_VERSION < '9.4'
-  s.add_development_dependency 'jsonify'
+  s.add_development_dependency 'activesupport'
   s.add_development_dependency 'hashie'
-  # Temporary support for Ruby 2.6, since it's EOL March 2022:
-  if RUBY_VERSION < '2.7.0'
-    s.add_development_dependency 'jbuilder', '< 7.0.0'
-  else
-    s.add_development_dependency 'activesupport'
-    s.add_development_dependency 'jbuilder'
-  end
+  s.add_development_dependency 'jbuilder'
+  s.add_development_dependency 'jsonify'
 
   s.add_development_dependency 'cane'
   s.add_development_dependency 'escape_utils' unless defined? JRUBY_VERSION
-
   s.add_development_dependency 'require-prof' unless defined?(JRUBY_VERSION) || defined?(Rubinius)
   s.add_development_dependency 'ruby-prof' unless defined?(JRUBY_VERSION) || defined?(Rubinius)
   s.add_development_dependency 'simplecov'
-
-  s.add_development_dependency 'test-unit', '~> 2'
-
   s.description = <<-DESC.gsub(/^    /, '')
     Ruby API for Elasticsearch. See the `elasticsearch` gem for full integration.
   DESC

data/lib/elasticsearch/api/actions/async_search/delete.rb

@@ -15,19 +15,22 @@
 # specific language governing permissions and limitations
 # under the License.
 #
-# Auto generated from build hash f284cc16f4d4b4289bc679aa1529bb504190fe80
-# @see https://github.com/elastic/elasticsearch/tree/main/rest-api-spec
-#
+# This code was automatically generated from the Elasticsearch Specification
+# See https://github.com/elastic/elasticsearch-specification
+# See Elasticsearch::ES_SPECIFICATION_COMMIT for commit hash.
 module Elasticsearch
   module API
     module AsyncSearch
       module Actions
-        # Deletes an async search by ID. If the search is still running, the search request will be cancelled. Otherwise, the saved search results are deleted.
+        # Delete an async search.
+        # If the asynchronous search is still running, it is cancelled.
+        # Otherwise, the saved search results are deleted.
+        # If the Elasticsearch security features are enabled, the deletion of a specific async search is restricted to: the authenticated user that submitted the original search request; users that have the +cancel_task+ cluster privilege.
         #
-        # @option arguments [String] :id The async search ID
+        # @option arguments [String] :id A unique identifier for the async search. (*Required*)
         # @option arguments [Hash] :headers Custom HTTP headers
         #
-        # @see https://www.elastic.co/guide/en/elasticsearch/reference/8.17/async-search.html
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-async-search-submit
         #
         def delete(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'async_search.delete' }
@@ -47,7 +50,7 @@ module Elasticsearch
           _id = arguments.delete(:id)
 
           method = Elasticsearch::API::HTTP_DELETE
-          path   = "_async_search/#{Utils.__listify(_id)}"
+          path   = "_async_search/#{Utils.listify(_id)}"
           params = {}
 
           Elasticsearch::API::Response.new(

data/lib/elasticsearch/api/actions/async_search/get.rb

@@ -15,22 +15,30 @@
 # specific language governing permissions and limitations
 # under the License.
 #
-# Auto generated from build hash f284cc16f4d4b4289bc679aa1529bb504190fe80
-# @see https://github.com/elastic/elasticsearch/tree/main/rest-api-spec
-#
+# This code was automatically generated from the Elasticsearch Specification
+# See https://github.com/elastic/elasticsearch-specification
+# See Elasticsearch::ES_SPECIFICATION_COMMIT for commit hash.
 module Elasticsearch
   module API
     module AsyncSearch
       module Actions
-        # Retrieves the results of a previously submitted async search request given its ID.
+        # Get async search results.
+        # Retrieve the results of a previously submitted asynchronous search request.
+        # If the Elasticsearch security features are enabled, access to the results of a specific async search is restricted to the user or API key that submitted it.
         #
-        # @option arguments [String] :id The async search ID
-        # @option arguments [Time] :wait_for_completion_timeout Specify the time that the request should block waiting for the final response
-        # @option arguments [Time] :keep_alive Specify the time interval in which the results (partial or final) for this search will be available
+        # @option arguments [String] :id A unique identifier for the async search. (*Required*)
+        # @option arguments [Time] :keep_alive The length of time that the async search should be available in the cluster.
+        #  When not specified, the +keep_alive+ set with the corresponding submit async request will be used.
+        #  Otherwise, it is possible to override the value and extend the validity of the request.
+        #  When this period expires, the search, if still running, is cancelled.
+        #  If the search is completed, its saved results are deleted.
         # @option arguments [Boolean] :typed_keys Specify whether aggregation and suggester names should be prefixed by their respective types in the response
+        # @option arguments [Time] :wait_for_completion_timeout Specifies to wait for the search to be completed up until the provided timeout.
+        #  Final results will be returned if available before the timeout expires, otherwise the currently available results will be returned once the timeout expires.
+        #  By default no timeout is set meaning that the currently available results will be returned without any additional wait.
         # @option arguments [Hash] :headers Custom HTTP headers
         #
-        # @see https://www.elastic.co/guide/en/elasticsearch/reference/8.17/async-search.html
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-async-search-submit
         #
         def get(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'async_search.get' }
@@ -50,7 +58,7 @@ module Elasticsearch
           _id = arguments.delete(:id)
 
           method = Elasticsearch::API::HTTP_GET
-          path   = "_async_search/#{Utils.__listify(_id)}"
+          path   = "_async_search/#{Utils.listify(_id)}"
           params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(

data/lib/elasticsearch/api/actions/async_search/status.rb

@@ -15,20 +15,25 @@
 # specific language governing permissions and limitations
 # under the License.
 #
-# Auto generated from build hash f284cc16f4d4b4289bc679aa1529bb504190fe80
-# @see https://github.com/elastic/elasticsearch/tree/main/rest-api-spec
-#
+# This code was automatically generated from the Elasticsearch Specification
+# See https://github.com/elastic/elasticsearch-specification
+# See Elasticsearch::ES_SPECIFICATION_COMMIT for commit hash.
 module Elasticsearch
   module API
     module AsyncSearch
       module Actions
-        # Retrieves the status of a previously submitted async search request given its ID.
+        # Get the async search status.
+        # Get the status of a previously submitted async search request given its identifier, without retrieving search results.
+        # If the Elasticsearch security features are enabled, the access to the status of a specific async search is restricted to:
+        # * The user or API key that submitted the original async search request.
+        # * Users that have the +monitor+ cluster privilege or greater privileges.
         #
-        # @option arguments [String] :id The async search ID
-        # @option arguments [Time] :keep_alive Specify the time interval in which the results (partial or final) for this search will be available
+        # @option arguments [String] :id A unique identifier for the async search. (*Required*)
+        # @option arguments [Time] :keep_alive The length of time that the async search needs to be available.
+        #  Ongoing async searches and any saved search results are deleted after this period. Server default: 5d.
         # @option arguments [Hash] :headers Custom HTTP headers
         #
-        # @see https://www.elastic.co/guide/en/elasticsearch/reference/8.17/async-search.html
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-async-search-submit
         #
         def status(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'async_search.status' }
@@ -48,7 +53,7 @@ module Elasticsearch
           _id = arguments.delete(:id)
 
           method = Elasticsearch::API::HTTP_GET
-          path   = "_async_search/status/#{Utils.__listify(_id)}"
+          path   = "_async_search/status/#{Utils.listify(_id)}"
           params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(

data/lib/elasticsearch/api/actions/async_search/submit.rb

@@ -15,63 +15,70 @@
 # specific language governing permissions and limitations
 # under the License.
 #
-# Auto generated from build hash f284cc16f4d4b4289bc679aa1529bb504190fe80
-# @see https://github.com/elastic/elasticsearch/tree/main/rest-api-spec
-#
+# This code was automatically generated from the Elasticsearch Specification
+# See https://github.com/elastic/elasticsearch-specification
+# See Elasticsearch::ES_SPECIFICATION_COMMIT for commit hash.
 module Elasticsearch
   module API
     module AsyncSearch
       module Actions
-        # Executes a search request asynchronously.
+        # Run an async search.
+        # When the primary sort of the results is an indexed field, shards get sorted based on minimum and maximum value that they hold for that field. Partial results become available following the sort criteria that was requested.
+        # Warning: Asynchronous search does not support scroll or search requests that include only the suggest section.
+        # By default, Elasticsearch does not allow you to store an async search response larger than 10Mb and an attempt to do this results in an error.
+        # The maximum allowed size for a stored async search response can be set by changing the +search.max_async_search_response_size+ cluster level setting.
         #
-        # @option arguments [List] :index A comma-separated list of index names to search; use `_all` or empty string to perform the operation on all indices
-        # @option arguments [Time] :wait_for_completion_timeout Specify the time that the request should block waiting for the final response
-        # @option arguments [Boolean] :keep_on_completion Control whether the response should be stored in the cluster if it completed within the provided [wait_for_completion] time (default: false)
-        # @option arguments [Time] :keep_alive Update the time interval in which the results (partial or final) for this search will be available
-        # @option arguments [Number] :batched_reduce_size The number of shard results that should be reduced at once on the coordinating node. This value should be used as the granularity at which progress results will be made available.
-        # @option arguments [Boolean] :request_cache Specify if request cache should be used for this request or not, defaults to true
+        # @option arguments [String, Array] :index A comma-separated list of index names to search; use +_all+ or empty string to perform the operation on all indices
+        # @option arguments [Time] :wait_for_completion_timeout Blocks and waits until the search is completed up to a certain timeout.
+        #  When the async search completes within the timeout, the response won’t include the ID as the results are not stored in the cluster. Server default: 1s.
+        # @option arguments [Time] :keep_alive Specifies how long the async search needs to be available.
+        #  Ongoing async searches and any saved search results are deleted after this period. Server default: 5d.
+        # @option arguments [Boolean] :keep_on_completion If +true+, results are stored for later retrieval when the search completes within the +wait_for_completion_timeout+.
+        # @option arguments [Boolean] :allow_no_indices Whether to ignore if a wildcard indices expression resolves into no concrete indices. (This includes +_all+ string or when no indices have been specified)
+        # @option arguments [Boolean] :allow_partial_search_results Indicate if an error should be returned if there is a partial search failure or timeout
         # @option arguments [String] :analyzer The analyzer to use for the query string
         # @option arguments [Boolean] :analyze_wildcard Specify whether wildcard and prefix queries should be analyzed (default: false)
-        # @option arguments [Boolean] :ccs_minimize_roundtrips When doing a cross-cluster search, setting it to true may improve overall search latency, particularly when searching clusters with a large number of shards. However, when set to true, the progress of searches on the remote clusters will not be received until the search finishes on all clusters.
-        # @option arguments [String] :default_operator The default operator for query string query (AND or OR) (options: AND, OR)
+        # @option arguments [Integer] :batched_reduce_size Affects how often partial results become available, which happens whenever shard results are reduced.
+        #  A partial reduction is performed every time the coordinating node has received a certain number of new shard responses (5 by default). Server default: 5.
+        # @option arguments [Boolean] :ccs_minimize_roundtrips The default value is the only supported value.
+        # @option arguments [String] :default_operator The default operator for query string query (AND or OR)
         # @option arguments [String] :df The field to use as default where no field prefix is given in the query string
+        # @option arguments [String, Array<String>] :docvalue_fields A comma-separated list of fields to return as the docvalue representation of a field for each hit
+        # @option arguments [String, Array<String>] :expand_wildcards Whether to expand wildcard expression to concrete indices that are open, closed or both.
         # @option arguments [Boolean] :explain Specify whether to return detailed information about score computation as part of a hit
-        # @option arguments [List] :stored_fields A comma-separated list of stored fields to return as part of a hit
-        # @option arguments [List] :docvalue_fields A comma-separated list of fields to return as the docvalue representation of a field for each hit
-        # @option arguments [Number] :from Starting offset (default: 0)
-        # @option arguments [Boolean] :ignore_unavailable Whether specified concrete indices should be ignored when unavailable (missing or closed)
         # @option arguments [Boolean] :ignore_throttled Whether specified concrete, expanded or aliased indices should be ignored when throttled
-        # @option arguments [Boolean] :allow_no_indices Whether to ignore if a wildcard indices expression resolves into no concrete indices. (This includes `_all` string or when no indices have been specified)
-        # @option arguments [String] :expand_wildcards Whether to expand wildcard expression to concrete indices that are open, closed or both. (options: open, closed, hidden, none, all)
+        # @option arguments [Boolean] :ignore_unavailable Whether specified concrete indices should be ignored when unavailable (missing or closed)
         # @option arguments [Boolean] :lenient Specify whether format-based query failures (such as providing text to a numeric field) should be ignored
+        # @option arguments [Integer] :max_concurrent_shard_requests The number of concurrent shard requests per node this search executes concurrently. This value should be used to limit the impact of the search on the cluster in order to limit the number of concurrent shard requests
         # @option arguments [String] :preference Specify the node or shard the operation should be performed on (default: random)
-        # @option arguments [Boolean] :rest_total_hits_as_int Indicates whether hits.total should be rendered as an integer or an object in the rest search response
-        # @option arguments [String] :q Query in the Lucene query string syntax
-        # @option arguments [List] :routing A comma-separated list of specific routing values
-        # @option arguments [String] :search_type Search operation type (options: query_then_fetch, dfs_query_then_fetch)
-        # @option arguments [Number] :size Number of hits to return (default: 10)
-        # @option arguments [List] :sort A comma-separated list of <field>:<direction> pairs
-        # @option arguments [List] :_source True or false to return the _source field or not, or a list of fields to return
-        # @option arguments [List] :_source_excludes A list of fields to exclude from the returned _source field
-        # @option arguments [List] :_source_includes A list of fields to extract and return from the _source field
-        # @option arguments [Number] :terminate_after The maximum number of documents to collect for each shard, upon reaching which the query execution will terminate early.
-        # @option arguments [List] :stats Specific 'tag' of the request for logging and statistical purposes
-        # @option arguments [String] :suggest_field Specify which field to use for suggestions
-        # @option arguments [String] :suggest_mode Specify suggest mode (options: missing, popular, always)
-        # @option arguments [Number] :suggest_size How many suggestions to return in response
-        # @option arguments [String] :suggest_text The source text for which the suggestions should be returned
+        # @option arguments [Boolean] :request_cache Specify if request cache should be used for this request or not, defaults to true Server default: true.
+        # @option arguments [String] :routing A comma-separated list of specific routing values
+        # @option arguments [String] :search_type Search operation type
+        # @option arguments [Array<String>] :stats Specific 'tag' of the request for logging and statistical purposes
+        # @option arguments [String, Array<String>] :stored_fields A comma-separated list of stored fields to return as part of a hit
+        # @option arguments [String] :suggest_field Specifies which field to use for suggestions.
+        # @option arguments [String] :suggest_mode Specify suggest mode
+        # @option arguments [Integer] :suggest_size How many suggestions to return in response
+        # @option arguments [String] :suggest_text The source text for which the suggestions should be returned.
+        # @option arguments [Integer] :terminate_after The maximum number of documents to collect for each shard, upon reaching which the query execution will terminate early.
         # @option arguments [Time] :timeout Explicit operation timeout
+        # @option arguments [Boolean, Integer] :track_total_hits Indicate if the number of documents that match the query should be tracked. A number can also be specified, to accurately track the total hit count up to the number.
         # @option arguments [Boolean] :track_scores Whether to calculate and return scores even if they are not used for sorting
-        # @option arguments [Boolean|long] :track_total_hits Indicate if the number of documents that match the query should be tracked. A number can also be specified, to accurately track the total hit count up to the number.
-        # @option arguments [Boolean] :allow_partial_search_results Indicate if an error should be returned if there is a partial search failure or timeout
         # @option arguments [Boolean] :typed_keys Specify whether aggregation and suggester names should be prefixed by their respective types in the response
+        # @option arguments [Boolean] :rest_total_hits_as_int Indicates whether hits.total should be rendered as an integer or an object in the rest search response
         # @option arguments [Boolean] :version Specify whether to return document version as part of a hit
+        # @option arguments [Boolean, String, Array<String>] :_source True or false to return the _source field or not, or a list of fields to return
+        # @option arguments [String, Array<String>] :_source_excludes A list of fields to exclude from the returned _source field
+        # @option arguments [String, Array<String>] :_source_includes A list of fields to extract and return from the _source field
         # @option arguments [Boolean] :seq_no_primary_term Specify whether to return sequence number and primary term of the last modification of each hit
-        # @option arguments [Number] :max_concurrent_shard_requests The number of concurrent shard requests per node this search executes concurrently. This value should be used to limit the impact of the search on the cluster in order to limit the number of concurrent shard requests
+        # @option arguments [String] :q Query in the Lucene query string syntax
+        # @option arguments [Integer] :size Number of hits to return (default: 10)
+        # @option arguments [Integer] :from Starting offset (default: 0)
+        # @option arguments [String] :sort A comma-separated list of <field>:<direction> pairs
         # @option arguments [Hash] :headers Custom HTTP headers
-        # @option arguments [Hash] :body The search definition using the Query DSL
+        # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/guide/en/elasticsearch/reference/8.17/async-search.html
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-async-search-submit
         #
         def submit(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'async_search.submit' }
@@ -84,13 +91,13 @@ module Elasticsearch
           arguments = arguments.clone
           headers = arguments.delete(:headers) || {}
 
-          body   = arguments.delete(:body)
+          body = arguments.delete(:body)
 
           _index = arguments.delete(:index)
 
           method = Elasticsearch::API::HTTP_POST
           path   = if _index
-                     "#{Utils.__listify(_index)}/_async_search"
+                     "#{Utils.listify(_index)}/_async_search"
                    else
                      '_async_search'
                    end

data/lib/elasticsearch/api/actions/bulk.rb

@@ -15,33 +15,122 @@
 # specific language governing permissions and limitations
 # under the License.
 #
-# Auto generated from build hash f284cc16f4d4b4289bc679aa1529bb504190fe80
-# @see https://github.com/elastic/elasticsearch/tree/main/rest-api-spec
-#
+# This code was automatically generated from the Elasticsearch Specification
+# See https://github.com/elastic/elasticsearch-specification
+# See Elasticsearch::ES_SPECIFICATION_COMMIT for commit hash.
 module Elasticsearch
   module API
     module Actions
-      # Allows to perform multiple index/update/delete operations in a single request.
+      # Bulk index or delete documents.
+      # Perform multiple +index+, +create+, +delete+, and +update+ actions in a single request.
+      # This reduces overhead and can greatly increase indexing speed.
+      # If the Elasticsearch security features are enabled, you must have the following index privileges for the target data stream, index, or index alias:
+      # * To use the +create+ action, you must have the +create_doc+, +create+, +index+, or +write+ index privilege. Data streams support only the +create+ action.
+      # * To use the +index+ action, you must have the +create+, +index+, or +write+ index privilege.
+      # * To use the +delete+ action, you must have the +delete+ or +write+ index privilege.
+      # * To use the +update+ action, you must have the +index+ or +write+ index privilege.
+      # * To automatically create a data stream or index with a bulk API request, you must have the +auto_configure+, +create_index+, or +manage+ index privilege.
+      # * To make the result of a bulk operation visible to search using the +refresh+ parameter, you must have the +maintenance+ or +manage+ index privilege.
+      # Automatic data stream creation requires a matching index template with data stream enabled.
+      # The actions are specified in the request body using a newline delimited JSON (NDJSON) structure:
+      # +
+      # action_and_meta_data\n
+      # optional_source\n
+      # action_and_meta_data\n
+      # optional_source\n
+      # ....
+      # action_and_meta_data\n
+      # optional_source\n
+      # +
+      # The +index+ and +create+ actions expect a source on the next line and have the same semantics as the +op_type+ parameter in the standard index API.
+      # A +create+ action fails if a document with the same ID already exists in the target
+      # An +index+ action adds or replaces a document as necessary.
+      # NOTE: Data streams support only the +create+ action.
+      # To update or delete a document in a data stream, you must target the backing index containing the document.
+      # An +update+ action expects that the partial doc, upsert, and script and its options are specified on the next line.
+      # A +delete+ action does not expect a source on the next line and has the same semantics as the standard delete API.
+      # NOTE: The final line of data must end with a newline character (+\n+).
+      # Each newline character may be preceded by a carriage return (+\r+).
+      # When sending NDJSON data to the +_bulk+ endpoint, use a +Content-Type+ header of +application/json+ or +application/x-ndjson+.
+      # Because this format uses literal newline characters (+\n+) as delimiters, make sure that the JSON actions and sources are not pretty printed.
+      # If you provide a target in the request path, it is used for any actions that don't explicitly specify an +_index+ argument.
+      # A note on the format: the idea here is to make processing as fast as possible.
+      # As some of the actions are redirected to other shards on other nodes, only +action_meta_data+ is parsed on the receiving node side.
+      # Client libraries using this protocol should try and strive to do something similar on the client side, and reduce buffering as much as possible.
+      # There is no "correct" number of actions to perform in a single bulk request.
+      # Experiment with different settings to find the optimal size for your particular workload.
+      # Note that Elasticsearch limits the maximum size of a HTTP request to 100mb by default so clients must ensure that no request exceeds this size.
+      # It is not possible to index a single document that exceeds the size limit, so you must pre-process any such documents into smaller pieces before sending them to Elasticsearch.
+      # For instance, split documents into pages or chapters before indexing them, or store raw binary data in a system outside Elasticsearch and replace the raw data with a link to the external system in the documents that you send to Elasticsearch.
+      # **Client suppport for bulk requests**
+      # Some of the officially supported clients provide helpers to assist with bulk requests and reindexing:
+      # * Go: Check out +esutil.BulkIndexer+
+      # * Perl: Check out +Search::Elasticsearch::Client::5_0::Bulk+ and +Search::Elasticsearch::Client::5_0::Scroll+
+      # * Python: Check out +elasticsearch.helpers.*+
+      # * JavaScript: Check out +client.helpers.*+
+      # * .NET: Check out +BulkAllObservable+
+      # * PHP: Check out bulk indexing.
+      # **Submitting bulk requests with cURL**
+      # If you're providing text file input to +curl+, you must use the +--data-binary+ flag instead of plain +-d+.
+      # The latter doesn't preserve newlines. For example:
+      # +
+      # $ cat requests
+      # { "index" : { "_index" : "test", "_id" : "1" } }
+      # { "field1" : "value1" }
+      # $ curl -s -H "Content-Type: application/x-ndjson" -XPOST localhost:9200/_bulk --data-binary "@requests"; echo
+      # {"took":7, "errors": false, "items":[{"index":{"_index":"test","_id":"1","_version":1,"result":"created","forced_refresh":false}}]}
+      # +
+      # **Optimistic concurrency control**
+      # Each +index+ and +delete+ action within a bulk API call may include the +if_seq_no+ and +if_primary_term+ parameters in their respective action and meta data lines.
+      # The +if_seq_no+ and +if_primary_term+ parameters control how operations are run, based on the last modification to existing documents. See Optimistic concurrency control for more details.
+      # **Versioning**
+      # Each bulk item can include the version value using the +version+ field.
+      # It automatically follows the behavior of the index or delete operation based on the +_version+ mapping.
+      # It also support the +version_type+.
+      # **Routing**
+      # Each bulk item can include the routing value using the +routing+ field.
+      # It automatically follows the behavior of the index or delete operation based on the +_routing+ mapping.
+      # NOTE: Data streams do not support custom routing unless they were created with the +allow_custom_routing+ setting enabled in the template.
+      # **Wait for active shards**
+      # When making bulk calls, you can set the +wait_for_active_shards+ parameter to require a minimum number of shard copies to be active before starting to process the bulk request.
+      # **Refresh**
+      # Control when the changes made by this request are visible to search.
+      # NOTE: Only the shards that receive the bulk request will be affected by refresh.
+      # Imagine a +_bulk?refresh=wait_for+ request with three documents in it that happen to be routed to different shards in an index with five shards.
+      # The request will only wait for those three shards to refresh.
+      # The other two shards that make up the index do not participate in the +_bulk+ request at all.
       #
-      # @option arguments [String] :index Default index for items which don't provide one
-      # @option arguments [String] :wait_for_active_shards Sets the number of shard copies that must be active before proceeding with the bulk operation. Defaults to 1, meaning the primary shard only. Set to `all` for all shard copies, otherwise set to any non-negative value less than or equal to the total number of copies for the shard (number of replicas + 1)
-      # @option arguments [String] :refresh If `true` then refresh the affected shards to make this operation visible to search, if `wait_for` then wait for a refresh to make this operation visible to search, if `false` (the default) then do nothing with refreshes. (options: true, false, wait_for)
-      # @option arguments [String] :routing Specific routing value
-      # @option arguments [Time] :timeout Explicit operation timeout
-      # @option arguments [String] :type Default document type for items which don't provide one
-      # @option arguments [List] :_source True or false to return the _source field or not, or default list of fields to return, can be overridden on each sub-request
-      # @option arguments [List] :_source_excludes Default list of fields to exclude from the returned _source field, can be overridden on each sub-request
-      # @option arguments [List] :_source_includes Default list of fields to extract and return from the _source field, can be overridden on each sub-request
-      # @option arguments [String] :pipeline The pipeline id to preprocess incoming documents with
-      # @option arguments [Boolean] :require_alias Sets require_alias for all incoming documents. Defaults to unset (false)
-      # @option arguments [Boolean] :require_data_stream When true, requires the destination to be a data stream (existing or to-be-created). Default is false
-      # @option arguments [Boolean] :list_executed_pipelines Sets list_executed_pipelines for all incoming documents. Defaults to unset (false)
-      # @option arguments [Boolean] :include_source_on_error True or false if to include the document source in the error message in case of parsing errors. Defaults to true.
+      # @option arguments [String] :index The name of the data stream, index, or index alias to perform bulk actions on.
+      # @option arguments [Boolean] :include_source_on_error True or false if to include the document source in the error message in case of parsing errors. Server default: true.
+      # @option arguments [Boolean] :list_executed_pipelines If +true+, the response will include the ingest pipelines that were run for each index or create.
+      # @option arguments [String] :pipeline The pipeline identifier to use to preprocess incoming documents.
+      #  If the index has a default ingest pipeline specified, setting the value to +_none+ turns off the default ingest pipeline for this request.
+      #  If a final pipeline is configured, it will always run regardless of the value of this parameter.
+      # @option arguments [String] :refresh If +true+, Elasticsearch refreshes the affected shards to make this operation visible to search.
+      #  If +wait_for+, wait for a refresh to make this operation visible to search.
+      #  If +false+, do nothing with refreshes.
+      #  Valid values: +true+, +false+, +wait_for+. Server default: false.
+      # @option arguments [String] :routing A custom value that is used to route operations to a specific shard.
+      # @option arguments [Boolean, String, Array<String>] :_source Indicates whether to return the +_source+ field (+true+ or +false+) or contains a list of fields to return.
+      # @option arguments [String, Array<String>] :_source_excludes A comma-separated list of source fields to exclude from the response.
+      #  You can also use this parameter to exclude fields from the subset specified in +_source_includes+ query parameter.
+      #  If the +_source+ parameter is +false+, this parameter is ignored.
+      # @option arguments [String, Array<String>] :_source_includes A comma-separated list of source fields to include in the response.
+      #  If this parameter is specified, only these source fields are returned.
+      #  You can exclude fields from this subset using the +_source_excludes+ query parameter.
+      #  If the +_source+ parameter is +false+, this parameter is ignored.
+      # @option arguments [Time] :timeout The period each action waits for the following operations: automatic index creation, dynamic mapping updates, and waiting for active shards.
+      #  The default is +1m+ (one minute), which guarantees Elasticsearch waits for at least the timeout before failing.
+      #  The actual wait time could be longer, particularly when multiple waits occur. Server default: 1m.
+      # @option arguments [Integer, String] :wait_for_active_shards The number of shard copies that must be active before proceeding with the operation.
+      #  Set to +all+ or any positive integer up to the total number of shards in the index (+number_of_replicas+1+).
+      #  The default is +1+, which waits for each primary shard to be active. Server default: 1.
+      # @option arguments [Boolean] :require_alias If +true+, the request's actions must target an index alias.
+      # @option arguments [Boolean] :require_data_stream If +true+, the request's actions must target a data stream (existing or to be created).
       # @option arguments [Hash] :headers Custom HTTP headers
-      # @option arguments [String|Array] :body The operation definition and data (action-data pairs), separated by newlines. Array of Strings, Header/Data pairs,
-      # or the conveniency "combined" format can be passed, refer to Elasticsearch::API::Utils.__bulkify documentation.
+      # @option arguments [String|Array] :body operations. Array of Strings, Header/Data pairs, or the conveniency "combined" format can be passed, refer to Elasticsearch::API::Utils.bulkify documentation.
       #
-      # @see https://www.elastic.co/guide/en/elasticsearch/reference/8.17/docs-bulk.html
+      # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-bulk
       #
       def bulk(arguments = {})
         request_opts = { endpoint: arguments[:endpoint] || 'bulk' }
@@ -56,25 +145,27 @@ module Elasticsearch
         arguments = arguments.clone
         headers = arguments.delete(:headers) || {}
 
-        body   = arguments.delete(:body)
+        body = arguments.delete(:body)
 
         _index = arguments.delete(:index)
 
         method = Elasticsearch::API::HTTP_POST
         path   = if _index
-                   "#{Utils.__listify(_index)}/_bulk"
+                   "#{Utils.listify(_index)}/_bulk"
                  else
                    '_bulk'
                  end
         params = Utils.process_params(arguments)
 
         payload = if body.is_a? Array
-                    Elasticsearch::API::Utils.__bulkify(body)
+                    Elasticsearch::API::Utils.bulkify(body)
                   else
                     body
                   end
 
-        headers.merge!('Content-Type' => 'application/x-ndjson')
+        headers.merge!({
+                         'Content-Type' => 'application/vnd.elasticsearch+x-ndjson; compatible-with=9'
+                       })
         Elasticsearch::API::Response.new(
           perform_request(method, path, params, payload, headers, request_opts)
         )