Module: Elasticsearch::API::Actions
- Included in:
- Elasticsearch::API
- Defined in:
- lib/elasticsearch/api/actions/get.rb,
lib/elasticsearch/api/actions/bulk.rb,
lib/elasticsearch/api/actions/info.rb,
lib/elasticsearch/api/actions/mget.rb,
lib/elasticsearch/api/actions/ping.rb,
lib/elasticsearch/api/actions/count.rb,
lib/elasticsearch/api/actions/index.rb,
lib/elasticsearch/api/actions/create.rb,
lib/elasticsearch/api/actions/delete.rb,
lib/elasticsearch/api/actions/exists.rb,
lib/elasticsearch/api/actions/scroll.rb,
lib/elasticsearch/api/actions/search.rb,
lib/elasticsearch/api/actions/update.rb,
lib/elasticsearch/api/actions/explain.rb,
lib/elasticsearch/api/actions/msearch.rb,
lib/elasticsearch/api/actions/reindex.rb,
lib/elasticsearch/api/actions/rank_eval.rb,
lib/elasticsearch/api/actions/field_caps.rb,
lib/elasticsearch/api/actions/get_script.rb,
lib/elasticsearch/api/actions/get_source.rb,
lib/elasticsearch/api/actions/put_script.rb,
lib/elasticsearch/api/actions/search_mvt.rb,
lib/elasticsearch/api/actions/terms_enum.rb,
lib/elasticsearch/api/actions/termvectors.rb,
lib/elasticsearch/api/actions/clear_scroll.rb,
lib/elasticsearch/api/actions/mtermvectors.rb,
lib/elasticsearch/api/actions/delete_script.rb,
lib/elasticsearch/api/actions/exists_source.rb,
lib/elasticsearch/api/actions/health_report.rb,
lib/elasticsearch/api/actions/search_shards.rb,
lib/elasticsearch/api/actions/delete_by_query.rb,
lib/elasticsearch/api/actions/search_template.rb,
lib/elasticsearch/api/actions/update_by_query.rb,
lib/elasticsearch/api/actions/msearch_template.rb,
lib/elasticsearch/api/actions/get_script_context.rb,
lib/elasticsearch/api/actions/open_point_in_time.rb,
lib/elasticsearch/api/actions/reindex_rethrottle.rb,
lib/elasticsearch/api/actions/close_point_in_time.rb,
lib/elasticsearch/api/actions/get_script_languages.rb,
lib/elasticsearch/api/actions/render_search_template.rb,
lib/elasticsearch/api/actions/scripts_painless_execute.rb,
lib/elasticsearch/api/actions/delete_by_query_rethrottle.rb,
lib/elasticsearch/api/actions/update_by_query_rethrottle.rb
Instance Method Summary collapse
-
#bulk(arguments = {}) ⇒ Object
Bulk index or delete documents.
-
#clear_scroll(arguments = {}) ⇒ Object
Clear a scrolling search.
-
#close_point_in_time(arguments = {}) ⇒ Object
Close a point in time.
-
#count(arguments = {}) ⇒ Object
Count search results.
-
#create(arguments = {}) ⇒ Object
Create a new document in the index.
-
#delete(arguments = {}) ⇒ Object
Delete a document.
-
#delete_by_query(arguments = {}) ⇒ Object
Delete documents.
-
#delete_by_query_rethrottle(arguments = {}) ⇒ Object
Throttle a delete by query operation.
-
#delete_script(arguments = {}) ⇒ Object
Delete a script or search template.
-
#exists(arguments = {}) ⇒ Object
(also: #exists?)
Check a document.
-
#exists_source(arguments = {}) ⇒ Object
(also: #exists_source?)
Check for a document source.
-
#explain(arguments = {}) ⇒ Object
Explain a document match result.
-
#field_caps(arguments = {}) ⇒ Object
Get the field capabilities.
-
#get(arguments = {}) ⇒ Object
Get a document by its ID.
-
#get_script(arguments = {}) ⇒ Object
Get a script or search template.
-
#get_script_context(arguments = {}) ⇒ Object
Get script contexts.
-
#get_script_languages(arguments = {}) ⇒ Object
Get script languages.
-
#get_source(arguments = {}) ⇒ Object
Get a document’s source.
-
#health_report(arguments = {}) ⇒ Object
Get the cluster health.
-
#index(arguments = {}) ⇒ Object
Create or update a document in an index.
-
#info(arguments = {}) ⇒ Object
Get cluster info.
-
#mget(arguments = {}) ⇒ Object
Get multiple documents.
-
#msearch(arguments = {}) ⇒ Object
Run multiple searches.
-
#msearch_template(arguments = {}) ⇒ Object
Run multiple templated searches.
-
#mtermvectors(arguments = {}) ⇒ Object
Get multiple term vectors.
-
#open_point_in_time(arguments = {}) ⇒ Object
Open a point in time.
-
#ping(arguments = {}) ⇒ Object
Ping the cluster.
-
#put_script(arguments = {}) ⇒ Object
Create or update a script or search template.
-
#rank_eval(arguments = {}) ⇒ Object
Evaluate ranked search results.
-
#reindex(arguments = {}) ⇒ Object
Reindex documents.
-
#reindex_rethrottle(arguments = {}) ⇒ Object
Throttle a reindex operation.
-
#render_search_template(arguments = {}) ⇒ Object
Render a search template.
-
#scripts_painless_execute(arguments = {}) ⇒ Object
Run a script.
-
#scroll(arguments = {}) ⇒ Object
Run a scrolling search.
-
#search(arguments = {}) ⇒ Object
Run a search.
-
#search_mvt(arguments = {}) ⇒ Object
Search a vector tile.
-
#search_shards(arguments = {}) ⇒ Object
Get the search shards.
-
#search_template(arguments = {}) ⇒ Object
Run a search with a search template.
-
#terms_enum(arguments = {}) ⇒ Object
Get terms in an index.
-
#termvector(arguments = {}) ⇒ Object
Deprecated: Use the plural version, #termvectors.
-
#termvectors(arguments = {}) ⇒ Object
Get term vector information.
-
#update(arguments = {}) ⇒ Object
Update a document.
-
#update_by_query(arguments = {}) ⇒ Object
Update documents.
-
#update_by_query_rethrottle(arguments = {}) ⇒ Object
Throttle an update by query operation.
Instance Method Details
#bulk(arguments = {}) ⇒ Object
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 thecreate_doc
,create
,index
, orwrite
index privilege. Data streams support only thecreate
action. -
To use the
index
action, you must have thecreate
,index
, orwrite
index privilege. -
To use the
delete
action, you must have thedelete
orwrite
index privilege. -
To use the
update
action, you must have theindex
orwrite
index privilege. -
To automatically create a data stream or index with a bulk API request, you must have the
auto_configure
,create_index
, ormanage
index privilege. -
To make the result of a bulk operation visible to search using the
refresh
parameter, you must have themaintenance
ormanage
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_datan optional_sourcen action_and_meta_datan optional_sourcen .… action_and_meta_datan optional_sourcen + 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
andSearch::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 “errors”: false, “items”:} + **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.
135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
# File 'lib/elasticsearch/api/actions/bulk.rb', line 135 def bulk(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'bulk' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = if _index "#{Utils.listify(_index)}/_bulk" else '_bulk' end params = Utils.process_params(arguments) payload = if body.is_a? Array Elasticsearch::API::Utils.bulkify(body) else body end 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) ) end |
#clear_scroll(arguments = {}) ⇒ Object
Clear a scrolling search. Clear the search context and results for a scrolling search.
*Deprecation notice*: A scroll id can be quite large and should be specified as part of the body Deprecated since version 7.0.0
40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
# File 'lib/elasticsearch/api/actions/clear_scroll.rb', line 40 def clear_scroll(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'clear_scroll' } arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _scroll_id = arguments.delete(:scroll_id) method = Elasticsearch::API::HTTP_DELETE path = '_search/scroll' params = Utils.process_params(arguments) if Array(arguments[:ignore]).include?(404) Utils.rescue_from_not_found do Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end else Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end end |
#close_point_in_time(arguments = {}) ⇒ Object
Close a point in time. A point in time must be opened explicitly before being used in search requests. The keep_alive
parameter tells Elasticsearch how long it should persist. A point in time is automatically closed when the keep_alive
period has elapsed. However, keeping points in time has a cost; close them as soon as they are no longer required for search requests.
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
# File 'lib/elasticsearch/api/actions/close_point_in_time.rb', line 35 def close_point_in_time(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'close_point_in_time' } arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) method = Elasticsearch::API::HTTP_DELETE path = '_pit' params = {} Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#count(arguments = {}) ⇒ Object
Count search results. Get the number of documents matching a query. The query can be provided either by using a simple query string as a parameter, or by defining Query DSL within the request body. The query is optional. When no query is provided, the API uses match_all
to count all the documents. The count API supports multi-target syntax. You can run a single count API search across multiple data streams and indices. The operation is broadcast across all shards. For each shard ID group, a replica is chosen and the search is run against it. This means that replicas increase the scalability of the count.
70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
# File 'lib/elasticsearch/api/actions/count.rb', line 70 def count(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'count' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = if _index "#{Utils.listify(_index)}/_count" else '_count' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#create(arguments = {}) ⇒ Object
Create a new document in the index. You can index a new JSON document with the /<target>/_doc/ or /<target>/_create/<_id> APIs Using _create
guarantees that the document is indexed only if it does not already exist. It returns a 409 response when a document with a same ID already exists in the index. To update an existing document, you must use the /<target>/_doc/ API. If the Elasticsearch security features are enabled, you must have the following index privileges for the target data stream, index, or index alias:
-
To add a document using the PUT /<target>/_create/<_id> or POST /<target>/_create/<_id> request formats, you must have the
create_doc
,create
,index
, orwrite
index privilege. -
To automatically create a data stream or index with this API request, you must have the
auto_configure
,create_index
, ormanage
index privilege.
Automatic data stream creation requires a matching index template with data stream enabled. **Automatically create data streams and indices** If the request’s target doesn’t exist and matches an index template with a data_stream
definition, the index operation automatically creates the data stream. If the target doesn’t exist and doesn’t match a data stream template, the operation automatically creates the index and applies any matching index templates. NOTE: Elasticsearch includes several built-in index templates. To avoid naming collisions with these templates, refer to index pattern documentation. If no mapping exists, the index operation creates a dynamic mapping. By default, new fields and objects are automatically added to the mapping if needed. Automatic index creation is controlled by the action.auto_create_index
setting. If it is true
, any index can be created automatically. You can modify this setting to explicitly allow or block automatic creation of indices that match specified patterns or set it to false
to turn off automatic index creation entirely. Specify a comma-separated list of patterns you want to allow or prefix each pattern with +++ or -
to indicate whether it should be allowed or blocked. When a list is specified, the default behaviour is to disallow. NOTE: The action.auto_create_index
setting affects the automatic creation of indices only. It does not affect the creation of data streams. Routing By default, shard placement — or routing — is controlled by using a hash of the document’s ID value. For more explicit control, the value fed into the hash function used by the router can be directly specified on a per-operation basis using the routing
parameter. When setting up explicit mapping, you can also use the _routing
field to direct the index operation to extract the routing value from the document itself. This does come at the (very minimal) cost of an additional document parsing pass. If the _routing
mapping is defined and set to be required, the index operation will fail if no routing value is provided or extracted. NOTE: Data streams do not support custom routing unless they were created with the allow_custom_routing
setting enabled in the template. Distributed The index operation is directed to the primary shard based on its route and performed on the actual node containing this shard. After the primary shard completes the operation, if needed, the update is distributed to applicable replicas. **Active shards** To improve the resiliency of writes to the system, indexing operations can be configured to wait for a certain number of active shard copies before proceeding with the operation. If the requisite number of active shard copies are not available, then the write operation must wait and retry, until either the requisite shard copies have started or a timeout occurs. By default, write operations only wait for the primary shards to be active before proceeding (that is to say wait_for_active_shards
is 1
). This default can be overridden in the index settings dynamically by setting index.write.wait_for_active_shards
. To alter this behavior per operation, use the wait_for_active_shards request parameter. Valid values are all or any positive integer up to the total number of configured copies per shard in the index (which is number_of_replicas+1). Specifying a negative value or a number greater than the number of shard copies will throw an error. For example, suppose you have a cluster of three nodes, A, B, and C and you create an index index with the number of replicas set to 3 (resulting in 4 shard copies, one more copy than there are nodes). If you attempt an indexing operation, by default the operation will only ensure the primary copy of each shard is available before proceeding. This means that even if B and C went down and A hosted the primary shard copies, the indexing operation would still proceed with only one copy of the data. If wait_for_active_shards
is set on the request to 3
(and all three nodes are up), the indexing operation will require 3 active shard copies before proceeding. This requirement should be met because there are 3 active nodes in the cluster, each one holding a copy of the shard. However, if you set wait_for_active_shards
to all
(or to 4
, which is the same in this situation), the indexing operation will not proceed as you do not have all 4 copies of each shard active in the index. The operation will timeout unless a new node is brought up in the cluster to host the fourth copy of the shard. It is important to note that this setting greatly reduces the chances of the write operation not writing to the requisite number of shard copies, but it does not completely eliminate the possibility, because this check occurs before the write operation starts. After the write operation is underway, it is still possible for replication to fail on any number of shard copies but still succeed on the primary. The _shards
section of the API response reveals the number of shard copies on which replication succeeded and failed.
115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
# File 'lib/elasticsearch/api/actions/create.rb', line 115 def create(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'create' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _id = arguments.delete(:id) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_PUT path = "#{Utils.listify(_index)}/_create/#{Utils.listify(_id)}" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#delete(arguments = {}) ⇒ Object
Delete a document. Remove a JSON document from the specified index. NOTE: You cannot send deletion requests directly to a data stream. To delete a document in a data stream, you must target the backing index containing the document. **Optimistic concurrency control** Delete operations can be made conditional and only be performed if the last modification to the document was assigned the sequence number and primary term specified by the if_seq_no
and if_primary_term
parameters. If a mismatch is detected, the operation will result in a VersionConflictException
and a status code of 409
. Versioning Each document indexed is versioned. When deleting a document, the version can be specified to make sure the relevant document you are trying to delete is actually being deleted and it has not changed in the meantime. Every write operation run on a document, deletes included, causes its version to be incremented. The version number of a deleted document remains available for a short time after deletion to allow for control of concurrent operations. The length of time for which a deleted document’s version remains available is determined by the index.gc_deletes
index setting. Routing If routing is used during indexing, the routing value also needs to be specified to delete a document. If the _routing
mapping is set to required
and no routing value is specified, the delete API throws a RoutingMissingException
and rejects the request. For example: + DELETE /my-index-000001/_doc/1?routing=shard-1 + This request deletes the document with ID 1, but it is routed based on the user. The document is not deleted if the correct routing is not specified. Distributed The delete operation gets hashed into a specific shard ID. It then gets redirected into the primary shard within that ID group and replicated (if needed) to shard replicas within that ID group.
71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
# File 'lib/elasticsearch/api/actions/delete.rb', line 71 def delete(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'delete' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _id = arguments.delete(:id) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_DELETE path = "#{Utils.listify(_index)}/_doc/#{Utils.listify(_id)}" params = Utils.process_params(arguments) if Array(arguments[:ignore]).include?(404) Utils.rescue_from_not_found do Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end else Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end end |
#delete_by_query(arguments = {}) ⇒ Object
Delete documents. Deletes documents that match the specified query. If the Elasticsearch security features are enabled, you must have the following index privileges for the target data stream, index, or alias:
-
read
-
delete
orwrite
You can specify the query criteria in the request URI or the request body using the same syntax as the search API. When you submit a delete by query request, Elasticsearch gets a snapshot of the data stream or index when it begins processing the request and deletes matching documents using internal versioning. If a document changes between the time that the snapshot is taken and the delete operation is processed, it results in a version conflict and the delete operation fails. NOTE: Documents with a version equal to 0 cannot be deleted using delete by query because internal versioning does not support 0 as a valid version number. While processing a delete by query request, Elasticsearch performs multiple search requests sequentially to find all of the matching documents to delete. A bulk delete request is performed for each batch of matching documents. If a search or bulk request is rejected, the requests are retried up to 10 times, with exponential back off. If the maximum retry limit is reached, processing halts and all failed requests are returned in the response. Any delete requests that completed successfully still stick, they are not rolled back. You can opt to count version conflicts instead of halting and returning by setting conflicts
to proceed
. Note that if you opt to count version conflicts the operation could attempt to delete more documents from the source than max_docs
until it has successfully deleted max_docs documents, or it has gone through every document in the source query. **Throttling delete requests** To control the rate at which delete by query issues batches of delete operations, you can set requests_per_second
to any positive decimal number. This pads each batch with a wait time to throttle the rate. Set requests_per_second
to -1
to disable throttling. Throttling uses a wait time between batches so that the internal scroll requests can be given a timeout that takes the request padding into account. The padding time is the difference between the batch size divided by the requests_per_second
and the time spent writing. By default the batch size is 1000
, so if requests_per_second
is set to 500
: + target_time = 1000 / 500 per second = 2 seconds wait_time = target_time - write_time = 2 seconds - .5 seconds = 1.5 seconds + Since the batch is issued as a single _bulk
request, large batch sizes cause Elasticsearch to create many requests and wait before starting the next set. This is “bursty” instead of “smooth”. Slicing Delete by query supports sliced scroll to parallelize the delete process. This can improve efficiency and provide a convenient way to break the request down into smaller parts. Setting slices
to auto
lets Elasticsearch choose the number of slices to use. This setting will use one slice per shard, up to a certain limit. If there are multiple source data streams or indices, it will choose the number of slices based on the index or backing index with the smallest number of shards. Adding slices to the delete by query operation creates sub-requests which means it has some quirks:
-
You can see these requests in the tasks APIs. These sub-requests are “child” tasks of the task for the request with slices.
-
Fetching the status of the task for the request with slices only contains the status of completed slices.
-
These sub-requests are individually addressable for things like cancellation and rethrottling.
-
Rethrottling the request with
slices
will rethrottle the unfinished sub-request proportionally. -
Canceling the request with
slices
will cancel each sub-request. -
Due to the nature of
slices
each sub-request won’t get a perfectly even portion of the documents. All documents will be addressed, but some slices may be larger than others. Expect larger slices to have a more even distribution. -
Parameters like
requests_per_second
andmax_docs
on a request withslices
are distributed proportionally to each sub-request. Combine that with the earlier point about distribution being uneven and you should conclude that usingmax_docs
withslices
might not result in exactlymax_docs
documents being deleted. -
Each sub-request gets a slightly different snapshot of the source data stream or index though these are all taken at approximately the same time.
If you’re slicing manually or otherwise tuning automatic slicing, keep in mind that:
-
Query performance is most efficient when the number of slices is equal to the number of shards in the index or backing index. If that number is large (for example, 500), choose a lower number as too many
slices
hurts performance. Settingslices
higher than the number of shards generally does not improve efficiency and adds overhead. -
Delete performance scales linearly across available resources with the number of slices.
Whether query or delete performance dominates the runtime depends on the documents being reindexed and cluster resources. **Cancel a delete by query operation** Any delete by query can be canceled using the task cancel API. For example: + POST _tasks/r1A2WoRbTwKZ516z6NEs5A:36619/_cancel + The task ID can be found by using the get tasks API. Cancellation should happen quickly but might take a few seconds. The get task status API will continue to list the delete by query task until this task checks that it has been cancelled and terminates itself.
143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
# File 'lib/elasticsearch/api/actions/delete_by_query.rb', line 143 def delete_by_query(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'delete_by_query' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = "#{Utils.listify(_index)}/_delete_by_query" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#delete_by_query_rethrottle(arguments = {}) ⇒ Object
Throttle a delete by query operation. Change the number of requests per second for a particular delete by query operation. Rethrottling that speeds up the query takes effect immediately but rethrotting that slows down the query takes effect after completing the current batch to prevent scroll timeouts.
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
# File 'lib/elasticsearch/api/actions/delete_by_query_rethrottle.rb', line 35 def delete_by_query_rethrottle(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'delete_by_query_rethrottle' } defined_params = [:task_id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'task_id' missing" unless arguments[:task_id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _task_id = arguments.delete(:task_id) method = Elasticsearch::API::HTTP_POST path = "_delete_by_query/#{Utils.listify(_task_id)}/_rethrottle" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#delete_script(arguments = {}) ⇒ Object
Delete a script or search template. Deletes a stored script or search template.
38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
# File 'lib/elasticsearch/api/actions/delete_script.rb', line 38 def delete_script(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'delete_script' } defined_params = [:id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _id = arguments.delete(:id) method = Elasticsearch::API::HTTP_DELETE path = "_scripts/#{Utils.listify(_id)}" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#exists(arguments = {}) ⇒ Object Also known as: exists?
Check a document. Verify that a document exists. For example, check to see if a document with the _id
0 exists: + HEAD my-index-000001/_doc/0 + If the document exists, the API returns a status code of 200 - OK. If the document doesn’t exist, the API returns 404 - Not Found. **Versioning support** You can use the version
parameter to check the document only if its current version is equal to the specified one. Internally, Elasticsearch has marked the old document as deleted and added an entirely new document. The old version of the document doesn’t disappear immediately, although you won’t be able to access it. Elasticsearch cleans up deleted documents in the background as you continue to index more data.
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
# File 'lib/elasticsearch/api/actions/exists.rb', line 68 def exists(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'exists' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _id = arguments.delete(:id) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_HEAD path = "#{Utils.listify(_index)}/_doc/#{Utils.listify(_id)}" params = Utils.process_params(arguments) Utils.rescue_from_not_found do perform_request(method, path, params, body, headers, request_opts).status == 200 end end |
#exists_source(arguments = {}) ⇒ Object Also known as: exists_source?
Check for a document source. Check whether a document source exists in an index. For example: + HEAD my-index-000001/_source/1 + A document’s source is not available if it is disabled in the mapping.
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
# File 'lib/elasticsearch/api/actions/exists_source.rb', line 51 def exists_source(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'exists_source' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _id = arguments.delete(:id) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_HEAD path = "#{Utils.listify(_index)}/_source/#{Utils.listify(_id)}" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#explain(arguments = {}) ⇒ Object
Explain a document match result. Get information about why a specific document matches, or doesn’t match, a query. It computes a score explanation for a query and a specific document.
59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
# File 'lib/elasticsearch/api/actions/explain.rb', line 59 def explain(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'explain' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _id = arguments.delete(:id) _index = arguments.delete(:index) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = "#{Utils.listify(_index)}/_explain/#{Utils.listify(_id)}" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#field_caps(arguments = {}) ⇒ Object
Get the field capabilities. Get information about the capabilities of fields among multiple indices. For data streams, the API returns field capabilities among the stream’s backing indices. It returns runtime fields like any other field. For example, a runtime field with a type of keyword is returned the same as any other field that belongs to the keyword
family.
48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
# File 'lib/elasticsearch/api/actions/field_caps.rb', line 48 def field_caps(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'field_caps' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = if _index "#{Utils.listify(_index)}/_field_caps" else '_field_caps' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#get(arguments = {}) ⇒ Object
Get a document by its ID. Get a document and its source or stored fields from an index. By default, this API is realtime and is not affected by the refresh rate of the index (when data will become visible for search). In the case where stored fields are requested with the stored_fields
parameter and the document has been updated but is not yet refreshed, the API will have to parse and analyze the source to extract the stored fields. To turn off realtime behavior, set the realtime
parameter to false. **Source filtering** By default, the API returns the contents of the _source
field unless you have used the stored_fields
parameter or the _source
field is turned off. You can turn off _source
retrieval by using the _source
parameter: + GET my-index-000001/_doc/0?_source=false + If you only need one or two fields from the _source
, use the _source_includes
or _source_excludes
parameters to include or filter out particular fields. This can be helpful with large documents where partial retrieval can save on network overhead Both parameters take a comma separated list of fields or wildcard expressions. For example: + GET my-index-000001/_doc/0?_source_includes=*.id&_source_excludes=entities + If you only want to specify includes, you can use a shorter notation: + GET my-index-000001/_doc/0?_source=*.id + Routing If routing is used during indexing, the routing value also needs to be specified to retrieve a document. For example: + GET my-index-000001/_doc/2?routing=user1 + This request gets the document with ID 2, but it is routed based on the user. The document is not fetched if the correct routing is not specified. Distributed The GET operation is hashed into a specific shard ID. It is then redirected to one of the replicas within that shard ID and returns the result. The replicas are the primary shard and its replicas within that shard ID group. This means that the more replicas you have, the better your GET scaling will be. **Versioning support** You can use the version
parameter to retrieve the document only if its current version is equal to the specified one. Internally, Elasticsearch has marked the old document as deleted and added an entirely new document. The old version of the document doesn’t disappear immediately, although you won’t be able to access it. Elasticsearch cleans up deleted documents in the background as you continue to index more data.
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
# File 'lib/elasticsearch/api/actions/get.rb', line 99 def get(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'get' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _id = arguments.delete(:id) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_GET path = "#{Utils.listify(_index)}/_doc/#{Utils.listify(_id)}" params = Utils.process_params(arguments) if Array(arguments[:ignore]).include?(404) Utils.rescue_from_not_found do Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end else Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end end |
#get_script(arguments = {}) ⇒ Object
Get a script or search template. Retrieves a stored script or search template.
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
# File 'lib/elasticsearch/api/actions/get_script.rb', line 35 def get_script(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'get_script' } defined_params = [:id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _id = arguments.delete(:id) method = Elasticsearch::API::HTTP_GET path = "_scripts/#{Utils.listify(_id)}" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#get_script_context(arguments = {}) ⇒ Object
Get script contexts. Get a list of supported script contexts and their methods.
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
# File 'lib/elasticsearch/api/actions/get_script_context.rb', line 31 def get_script_context(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'get_script_context' } arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil method = Elasticsearch::API::HTTP_GET path = '_script_context' params = {} Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#get_script_languages(arguments = {}) ⇒ Object
Get script languages. Get a list of available script types, languages, and contexts.
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
# File 'lib/elasticsearch/api/actions/get_script_languages.rb', line 31 def get_script_languages(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'get_script_languages' } arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil method = Elasticsearch::API::HTTP_GET path = '_script_language' params = {} Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#get_source(arguments = {}) ⇒ Object
Get a document’s source. Get the source of a document. For example: + GET my-index-000001/_source/1 + You can use the source filtering parameters to control which parts of the _source
are returned: + GET my-index-000001/_source/1/?_source_includes=*.id&_source_excludes=entities +
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
# File 'lib/elasticsearch/api/actions/get_source.rb', line 54 def get_source(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'get_source' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _id = arguments.delete(:id) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_GET path = "#{Utils.listify(_index)}/_source/#{Utils.listify(_id)}" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#health_report(arguments = {}) ⇒ Object
Get the cluster health. Get a report with the health status of an Elasticsearch cluster. The report contains a list of indicators that compose Elasticsearch functionality. Each indicator has a health status of: green, unknown, yellow or red. The indicator will provide an explanation and metadata describing the reason for its current health status. The cluster’s status is controlled by the worst indicator status. In the event that an indicator’s status is non-green, a list of impacts may be present in the indicator result which detail the functionalities that are negatively affected by the health issue. Each impact carries with it a severity level, an area of the system that is affected, and a simple description of the impact on the system. Some health indicators can determine the root cause of a health problem and prescribe a set of steps that can be performed in order to improve the health of the system. The root cause and remediation steps are encapsulated in a diagnosis. A diagnosis contains a cause detailing a root cause analysis, an action containing a brief description of the steps to take to fix the problem, the list of affected resources (if applicable), and a detailed step-by-step troubleshooting guide to fix the diagnosed problem. NOTE: The health indicators perform root cause analysis of non-green health statuses. This can be computationally expensive when called frequently. When setting up automated polling of the API for health status, set verbose to false to disable the more expensive analysis logic.
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
# File 'lib/elasticsearch/api/actions/health_report.rb', line 46 def health_report(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'health_report' } defined_params = [:feature].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _feature = arguments.delete(:feature) method = Elasticsearch::API::HTTP_GET path = if _feature "_health_report/#{Utils.listify(_feature)}" else '_health_report' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#index(arguments = {}) ⇒ Object
Create or update a document in an index. Add a JSON document to the specified data stream or index and make it searchable. If the target is an index and the document already exists, the request updates the document and increments its version. NOTE: You cannot use this API to send update requests for existing documents in a data stream. If the Elasticsearch security features are enabled, you must have the following index privileges for the target data stream, index, or index alias:
-
To add or overwrite a document using the PUT /<target>/_doc/<_id> request format, you must have the
create
,index
, orwrite
index privilege. -
To add a document using the POST /<target>/_doc/ request format, you must have the
create_doc
,create
,index
, orwrite
index privilege. -
To automatically create a data stream or index with this API request, you must have the
auto_configure
,create_index
, ormanage
index privilege.
Automatic data stream creation requires a matching index template with data stream enabled. NOTE: Replica shards might not all be started when an indexing operation returns successfully. By default, only the primary is required. Set wait_for_active_shards
to change this default behavior. **Automatically create data streams and indices** If the request’s target doesn’t exist and matches an index template with a data_stream
definition, the index operation automatically creates the data stream. If the target doesn’t exist and doesn’t match a data stream template, the operation automatically creates the index and applies any matching index templates. NOTE: Elasticsearch includes several built-in index templates. To avoid naming collisions with these templates, refer to index pattern documentation. If no mapping exists, the index operation creates a dynamic mapping. By default, new fields and objects are automatically added to the mapping if needed. Automatic index creation is controlled by the action.auto_create_index
setting. If it is true
, any index can be created automatically. You can modify this setting to explicitly allow or block automatic creation of indices that match specified patterns or set it to false
to turn off automatic index creation entirely. Specify a comma-separated list of patterns you want to allow or prefix each pattern with +++ or -
to indicate whether it should be allowed or blocked. When a list is specified, the default behaviour is to disallow. NOTE: The action.auto_create_index
setting affects the automatic creation of indices only. It does not affect the creation of data streams. **Optimistic concurrency control** Index operations can be made conditional and only be performed if the last modification to the document was assigned the sequence number and primary term specified by the if_seq_no
and if_primary_term
parameters. If a mismatch is detected, the operation will result in a VersionConflictException
and a status code of 409
. Routing By default, shard placement — or routing — is controlled by using a hash of the document’s ID value. For more explicit control, the value fed into the hash function used by the router can be directly specified on a per-operation basis using the routing
parameter. When setting up explicit mapping, you can also use the _routing
field to direct the index operation to extract the routing value from the document itself. This does come at the (very minimal) cost of an additional document parsing pass. If the _routing
mapping is defined and set to be required, the index operation will fail if no routing value is provided or extracted. NOTE: Data streams do not support custom routing unless they were created with the allow_custom_routing
setting enabled in the template. Distributed The index operation is directed to the primary shard based on its route and performed on the actual node containing this shard. After the primary shard completes the operation, if needed, the update is distributed to applicable replicas. **Active shards** To improve the resiliency of writes to the system, indexing operations can be configured to wait for a certain number of active shard copies before proceeding with the operation. If the requisite number of active shard copies are not available, then the write operation must wait and retry, until either the requisite shard copies have started or a timeout occurs. By default, write operations only wait for the primary shards to be active before proceeding (that is to say wait_for_active_shards
is 1
). This default can be overridden in the index settings dynamically by setting index.write.wait_for_active_shards
. To alter this behavior per operation, use the wait_for_active_shards request parameter. Valid values are all or any positive integer up to the total number of configured copies per shard in the index (which is number_of_replicas+1). Specifying a negative value or a number greater than the number of shard copies will throw an error. For example, suppose you have a cluster of three nodes, A, B, and C and you create an index index with the number of replicas set to 3 (resulting in 4 shard copies, one more copy than there are nodes). If you attempt an indexing operation, by default the operation will only ensure the primary copy of each shard is available before proceeding. This means that even if B and C went down and A hosted the primary shard copies, the indexing operation would still proceed with only one copy of the data. If wait_for_active_shards
is set on the request to 3
(and all three nodes are up), the indexing operation will require 3 active shard copies before proceeding. This requirement should be met because there are 3 active nodes in the cluster, each one holding a copy of the shard. However, if you set wait_for_active_shards
to all
(or to 4
, which is the same in this situation), the indexing operation will not proceed as you do not have all 4 copies of each shard active in the index. The operation will timeout unless a new node is brought up in the cluster to host the fourth copy of the shard. It is important to note that this setting greatly reduces the chances of the write operation not writing to the requisite number of shard copies, but it does not completely eliminate the possibility, because this check occurs before the write operation starts. After the write operation is underway, it is still possible for replication to fail on any number of shard copies but still succeed on the primary. The _shards
section of the API response reveals the number of shard copies on which replication succeeded and failed. **No operation (noop) updates** When updating a document by using this API, a new version of the document is always created even if the document hasn’t changed. If this isn’t acceptable use the _update
API with detect_noop
set to true
. The detect_noop
option isn’t available on this API because it doesn’t fetch the old source and isn’t able to compare it against the new source. There isn’t a definitive rule for when noop updates aren’t acceptable. It’s a combination of lots of factors like how frequently your data source sends updates that are actually noops and how many queries per second Elasticsearch runs on the shard receiving the updates. Versioning Each indexed document is given a version number. By default, internal versioning is used that starts at 1 and increments with each update, deletes included. Optionally, the version number can be set to an external value (for example, if maintained in a database). To enable this functionality, version_type
should be set to external
. The value provided must be a numeric, long value greater than or equal to 0, and less than around 9.2e18+. NOTE: Versioning is completely real time, and is not affected by the near real time aspects of search operations. If no version is provided, the operation runs without any version checks. When using the external version type, the system checks to see if the version number passed to the index request is greater than the version of the currently stored document. If true, the document will be indexed and the new version number used. If the value provided is less than or equal to the stored document’s version number, a version conflict will occur and the index operation will fail. For example: “‘ PUT my-index-000001/_doc/1?version=2&version_type=external {
"user": {
"id": "elkbee"
}
} In this example, the operation will succeed since the supplied version of 2 is higher than the current document version of 1. If the document was already updated and its version was set to 2 or higher, the indexing command will fail and result in a conflict (409 HTTP status code). A nice side effect is that there is no need to maintain strict ordering of async indexing operations run as a result of changes to a source database, as long as version numbers from the source database are used. Even the simple case of updating the Elasticsearch index using data from a database is simplified if external versioning is used, as only the latest version will be used if the index operations arrive out of order.
146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 |
# File 'lib/elasticsearch/api/actions/index.rb', line 146 def index(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'index' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _id = arguments.delete(:id) _index = arguments.delete(:index) method = _id ? Elasticsearch::API::HTTP_PUT : Elasticsearch::API::HTTP_POST path = if _index && _id "#{Utils.listify(_index)}/_doc/#{Utils.listify(_id)}" else "#{Utils.listify(_index)}/_doc" end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#info(arguments = {}) ⇒ Object
Get cluster info. Get basic build, version, and cluster information.
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
# File 'lib/elasticsearch/api/actions/info.rb', line 31 def info(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'info' } arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil method = Elasticsearch::API::HTTP_GET path = '' params = {} Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#mget(arguments = {}) ⇒ Object
Get multiple documents. Get multiple JSON documents by ID from one or more indices. If you specify an index in the request URI, you only need to specify the document IDs in the request body. To ensure fast responses, this multi get (mget) API responds with partial results if one or more shards fail. **Filter source fields** By default, the _source
field is returned for every document (if stored). Use the _source
and _source_include
or source_exclude
attributes to filter what fields are returned for a particular document. You can include the _source
, _source_includes
, and _source_excludes
query parameters in the request URI to specify the defaults to use when there are no per-document instructions. **Get stored fields** Use the stored_fields
attribute to specify the set of stored fields you want to retrieve. Any requested fields that are not stored are ignored. You can include the stored_fields
query parameter in the request URI to specify the defaults to use when there are no per-document instructions.
57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
# File 'lib/elasticsearch/api/actions/mget.rb', line 57 def mget(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'mget' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = if _index "#{Utils.listify(_index)}/_mget" else '_mget' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#msearch(arguments = {}) ⇒ Object
Run multiple searches. The format of the request is similar to the bulk API format and makes use of the newline delimited JSON (NDJSON) format. The structure is as follows: + headern bodyn headern bodyn + This structure is specifically optimized to reduce parsing if a specific search ends up redirected to another node. IMPORTANT: 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 requests to this endpoint the Content-Type
header should be set to application/x-ndjson
.
63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
# File 'lib/elasticsearch/api/actions/msearch.rb', line 63 def msearch(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'msearch' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = if _index "#{Utils.listify(_index)}/_msearch" else '_msearch' end params = Utils.process_params(arguments) if body.is_a?(Array) && body.any? { |d| d.key? :search } payload = body.each_with_object([]) do |item, sum| = item data = .delete(:search) sum << sum << data end.map { |item| Elasticsearch::API.serializer.dump(item) } payload << '' unless payload.empty? payload = payload.join("\n") elsif body.is_a?(Array) payload = body.map { |d| d.is_a?(String) ? d : Elasticsearch::API.serializer.dump(d) } payload << '' unless payload.empty? payload = payload.join("\n") else payload = body end 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) ) end |
#msearch_template(arguments = {}) ⇒ Object
Run multiple templated searches. Run multiple templated searches with a single request. If you are providing a text file or text input to curl
, use the --data-binary
flag instead of -d
to preserve newlines. For example: + $ cat requests { “index”: “my-index” } { “id”: “my-search-template”, “params”: { “query_string”: “hello world”, “from”: 0, “size”: 10 }} { “index”: “my-other-index” } { “id”: “my-other-search-template”, “params”: { “query_type”: “match_all” }} $ curl -H “Content-Type: application/x-ndjson” -XGET localhost:9200/_msearch/template –data-binary “@requests”; echo +
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
# File 'lib/elasticsearch/api/actions/msearch_template.rb', line 51 def msearch_template(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'msearch_template' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = if _index "#{Utils.listify(_index)}/_msearch/template" else '_msearch/template' end params = Utils.process_params(arguments) if body.is_a?(Array) payload = body.map { |d| d.is_a?(String) ? d : Elasticsearch::API.serializer.dump(d) } payload << '' unless payload.empty? payload = payload.join("\n") else payload = body end 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) ) end |
#mtermvectors(arguments = {}) ⇒ Object
Get multiple term vectors. Get multiple term vectors with a single request. You can specify existing documents by index and ID or provide artificial documents in the body of the request. You can specify the index in the request body or request URI. The response contains a docs
array with all the fetched termvectors. Each element has the structure provided by the termvectors API. **Artificial documents** You can also use mtermvectors
to generate term vectors for artificial documents provided in the body of the request. The mapping used is determined by the specified _index
.
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
# File 'lib/elasticsearch/api/actions/mtermvectors.rb', line 54 def mtermvectors(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'mtermvectors' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = if _index "#{Utils.listify(_index)}/_mtermvectors" else '_mtermvectors' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#open_point_in_time(arguments = {}) ⇒ Object
Open a point in time. A search request by default runs against the most recent visible data of the target indices, which is called point in time. Elasticsearch pit (point in time) is a lightweight view into the state of the data as it existed when initiated. In some cases, it’s preferred to perform multiple search requests using the same point in time. For example, if refreshes happen between search_after
requests, then the results of those requests might not be consistent as changes happening between searches are only visible to the more recent point in time. A point in time must be opened explicitly before being used in search requests. A subsequent search request with the pit
parameter must not specify index
, routing
, or preference
values as these parameters are copied from the point in time. Just like regular searches, you can use from
and size
to page through point in time search results, up to the first 10,000 hits. If you want to retrieve more hits, use PIT with search_after
. IMPORTANT: The open point in time request and each subsequent search request can return different identifiers; always use the most recently received ID for the next search request. When a PIT that contains shard failures is used in a search request, the missing are always reported in the search response as a NoShardAvailableActionException
exception. To get rid of these exceptions, a new PIT needs to be created so that shards missing from the previous PIT can be handled, assuming they become available in the meantime. **Keeping point in time alive** The keep_alive
parameter, which is passed to a open point in time request and search request, extends the time to live of the corresponding point in time. The value does not need to be long enough to process all data — it just needs to be long enough for the next request. Normally, the background merge process optimizes the index by merging together smaller segments to create new, bigger segments. Once the smaller segments are no longer needed they are deleted. However, open point-in-times prevent the old segments from being deleted since they are still in use. TIP: Keeping older segments alive means that more disk space and file handles are needed. Ensure that you have configured your nodes to have ample free file handles. Additionally, if a segment contains deleted or updated documents then the point in time must keep track of whether each document in the segment was live at the time of the initial search request. Ensure that your nodes have sufficient heap space if you have many open point-in-times on an index that is subject to ongoing deletes or updates. Note that a point-in-time doesn’t prevent its associated indices from being deleted. You can check how many point-in-times (that is, search contexts) are open with the nodes stats API.
69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
# File 'lib/elasticsearch/api/actions/open_point_in_time.rb', line 69 def open_point_in_time(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'open_point_in_time' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = "#{Utils.listify(_index)}/_pit" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#ping(arguments = {}) ⇒ Object
Ping the cluster. Get information about whether the cluster is running.
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
# File 'lib/elasticsearch/api/actions/ping.rb', line 31 def ping(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'ping' } arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil method = Elasticsearch::API::HTTP_HEAD path = '' params = {} begin perform_request(method, path, params, body, headers, request_opts).status == 200 rescue Exception => e raise e unless e.class.to_s =~ /NotFound|ConnectionFailed/ || e. =~ /Not *Found|404|ConnectionFailed/i false end end |
#put_script(arguments = {}) ⇒ Object
Create or update a script or search template. Creates or updates a stored script or search template.
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
# File 'lib/elasticsearch/api/actions/put_script.rb', line 42 def put_script(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'put_script' } defined_params = [:id, :context].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _id = arguments.delete(:id) _context = arguments.delete(:context) method = Elasticsearch::API::HTTP_PUT path = if _id && _context "_scripts/#{Utils.listify(_id)}/#{Utils.listify(_context)}" else "_scripts/#{Utils.listify(_id)}" end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#rank_eval(arguments = {}) ⇒ Object
Evaluate ranked search results. Evaluate the quality of ranked search results over a set of typical search queries.
39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
# File 'lib/elasticsearch/api/actions/rank_eval.rb', line 39 def rank_eval(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'rank_eval' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = if _index "#{Utils.listify(_index)}/_rank_eval" else '_rank_eval' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#reindex(arguments = {}) ⇒ Object
Reindex documents. Copy documents from a source to a destination. You can copy all documents to the destination index or reindex a subset of the documents. The source can be any existing index, alias, or data stream. The destination must differ from the source. For example, you cannot reindex a data stream into itself. IMPORTANT: Reindex requires _source
to be enabled for all documents in the source. The destination should be configured as wanted before calling the reindex API. Reindex does not copy the settings from the source or its associated template. Mappings, shard counts, and replicas, for example, must be configured ahead of time. If the Elasticsearch security features are enabled, you must have the following security privileges:
-
The
read
index privilege for the source data stream, index, or alias. -
The
write
index privilege for the destination data stream, index, or index alias. -
To automatically create a data stream or index with a reindex API request, you must have the
auto_configure
,create_index
, ormanage
index privilege for the destination data stream, index, or alias. -
If reindexing from a remote cluster, the
source.remote.user
must have themonitor
cluster privilege and theread
index privilege for the source data stream, index, or alias.
If reindexing from a remote cluster, you must explicitly allow the remote host in the reindex.remote.whitelist
setting. Automatic data stream creation requires a matching index template with data stream enabled. The dest
element can be configured like the index API to control optimistic concurrency control. Omitting version_type
or setting it to internal
causes Elasticsearch to blindly dump documents into the destination, overwriting any that happen to have the same ID. Setting version_type
to external
causes Elasticsearch to preserve the version
from the source, create any documents that are missing, and update any documents that have an older version in the destination than they do in the source. Setting op_type
to create
causes the reindex API to create only missing documents in the destination. All existing documents will cause a version conflict. IMPORTANT: Because data streams are append-only, any reindex request to a destination data stream must have an op_type
of create
. A reindex can only add new documents to a destination data stream. It cannot update existing documents in a destination data stream. By default, version conflicts abort the reindex process. To continue reindexing if there are conflicts, set the conflicts
request body property to proceed
. In this case, the response includes a count of the version conflicts that were encountered. Note that the handling of other error types is unaffected by the conflicts
property. Additionally, if you opt to count version conflicts, the operation could attempt to reindex more documents from the source than max_docs
until it has successfully indexed max_docs
documents into the target or it has gone through every document in the source query. NOTE: The reindex API makes no effort to handle ID collisions. The last document written will “win” but the order isn’t usually predictable so it is not a good idea to rely on this behavior. Instead, make sure that IDs are unique by using a script. **Running reindex asynchronously** If the request contains wait_for_completion=false, Elasticsearch performs some preflight checks, launches the request, and returns a task you can use to cancel or get the status of the task. Elasticsearch creates a record of this task as a document at _tasks/<task_id>. **Reindex from multiple sources** If you have many sources to reindex it is generally better to reindex them one at a time rather than using a glob pattern to pick up multiple sources. That way you can resume the process if there are any errors by removing the partially completed source and starting over. It also makes parallelizing the process fairly simple: split the list of sources to reindex and run each list in parallel. For example, you can use a bash script like this: + for index in i1 i2 i3 i4 i5; do
curl -HContent-Type:application/json -XPOST localhost:9200/_reindex?pretty -d'{
"source": {
"index": "'$index'"
},
"dest": {
"index": "'$index'-reindexed"
}
}'
done + Throttling Set requests_per_second
to any positive decimal number (1.4
, 6
, 1000
, for example) to throttle the rate at which reindex issues batches of index operations. Requests are throttled by padding each batch with a wait time. To turn off throttling, set requests_per_second
to -1
. The throttling is done by waiting between batches so that the scroll that reindex uses internally can be given a timeout that takes into account the padding. The padding time is the difference between the batch size divided by the requests_per_second
and the time spent writing. By default the batch size is 1000
, so if requests_per_second
is set to 500
: + target_time = 1000 / 500 per second = 2 seconds wait_time = target_time - write_time = 2 seconds - .5 seconds = 1.5 seconds + Since the batch is issued as a single bulk request, large batch sizes cause Elasticsearch to create many requests and then wait for a while before starting the next set. This is “bursty” instead of “smooth”. Slicing Reindex supports sliced scroll to parallelize the reindexing process. This parallelization can improve efficiency and provide a convenient way to break the request down into smaller parts. NOTE: Reindexing from remote clusters does not support manual or automatic slicing. You can slice a reindex request manually by providing a slice ID and total number of slices to each request. You can also let reindex automatically parallelize by using sliced scroll to slice on _id
. The slices
parameter specifies the number of slices to use. Adding slices
to the reindex request just automates the manual process, creating sub-requests which means it has some quirks:
-
You can see these requests in the tasks API. These sub-requests are “child” tasks of the task for the request with slices.
-
Fetching the status of the task for the request with
slices
only contains the status of completed slices. -
These sub-requests are individually addressable for things like cancellation and rethrottling.
-
Rethrottling the request with
slices
will rethrottle the unfinished sub-request proportionally. -
Canceling the request with
slices
will cancel each sub-request. -
Due to the nature of
slices
, each sub-request won’t get a perfectly even portion of the documents. All documents will be addressed, but some slices may be larger than others. Expect larger slices to have a more even distribution. -
Parameters like
requests_per_second
andmax_docs
on a request withslices
are distributed proportionally to each sub-request. Combine that with the previous point about distribution being uneven and you should conclude that usingmax_docs
withslices
might not result in exactlymax_docs
documents being reindexed. -
Each sub-request gets a slightly different snapshot of the source, though these are all taken at approximately the same time.
If slicing automatically, setting slices
to auto
will choose a reasonable number for most indices. If slicing manually or otherwise tuning automatic slicing, use the following guidelines. Query performance is most efficient when the number of slices is equal to the number of shards in the index. If that number is large (for example, 500
), choose a lower number as too many slices will hurt performance. Setting slices higher than the number of shards generally does not improve efficiency and adds overhead. Indexing performance scales linearly across available resources with the number of slices. Whether query or indexing performance dominates the runtime depends on the documents being reindexed and cluster resources. **Modify documents during reindexing** Like _update_by_query
, reindex operations support a script that modifies the document. Unlike _update_by_query
, the script is allowed to modify the document’s metadata. Just as in _update_by_query
, you can set ctx.op
to change the operation that is run on the destination. For example, set ctx.op
to noop
if your script decides that the document doesn’t have to be indexed in the destination. This “no operation” will be reported in the noop
counter in the response body. Set ctx.op
to delete
if your script decides that the document must be deleted from the destination. The deletion will be reported in the deleted
counter in the response body. Setting ctx.op
to anything else will return an error, as will setting any other field in ctx
. Think of the possibilities! Just be careful; you are able to change:
-
_id
-
_index
-
_version
-
_routing
Setting _version
to null
or clearing it from the ctx
map is just like not sending the version in an indexing request. It will cause the document to be overwritten in the destination regardless of the version on the target or the version type you use in the reindex API. **Reindex from remote** Reindex supports reindexing from a remote Elasticsearch cluster. The host
parameter must contain a scheme, host, port, and optional path. The username
and password
parameters are optional and when they are present the reindex operation will connect to the remote Elasticsearch node using basic authentication. Be sure to use HTTPS when using basic authentication or the password will be sent in plain text. There are a range of settings available to configure the behavior of the HTTPS connection. When using Elastic Cloud, it is also possible to authenticate against the remote cluster through the use of a valid API key. Remote hosts must be explicitly allowed with the reindex.remote.whitelist
setting. It can be set to a comma delimited list of allowed remote host and port combinations. Scheme is ignored; only the host and port are used. For example: + reindex.remote.whitelist: [otherhost:9200, another:9200, 127.0.10.*:9200, localhost:*“] + The list of allowed hosts must be configured on any nodes that will coordinate the reindex. This feature should work with remote clusters of any version of Elasticsearch. This should enable you to upgrade from any version of Elasticsearch to the current version by reindexing from a cluster of the old version. WARNING: Elasticsearch does not support forward compatibility across major versions. For example, you cannot reindex from a 7.x cluster into a 6.x cluster. To enable queries sent to older versions of Elasticsearch, the query
parameter is sent directly to the remote host without validation or modification. NOTE: Reindexing from remote clusters does not support manual or automatic slicing. Reindexing from a remote server uses an on-heap buffer that defaults to a maximum size of 100mb. If the remote index includes very large documents you’ll need to use a smaller batch size. It is also possible to set the socket read timeout on the remote connection with the socket_timeout
field and the connection timeout with the connect_timeout
field. Both default to 30 seconds. **Configuring SSL parameters** Reindex from remote supports configurable SSL settings. These must be specified in the elasticsearch.yml
file, with the exception of the secure settings, which you add in the Elasticsearch keystore. It is not possible to configure SSL in the body of the reindex request.
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
# File 'lib/elasticsearch/api/actions/reindex.rb', line 180 def reindex(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'reindex' } raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) method = Elasticsearch::API::HTTP_POST path = '_reindex' params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#reindex_rethrottle(arguments = {}) ⇒ Object
Throttle a reindex operation. Change the number of requests per second for a particular reindex operation. For example: + POST _reindex/r1A2WoRbTwKZ516z6NEs5A:36619/_rethrottle?requests_per_second=-1 + Rethrottling that speeds up the query takes effect immediately. Rethrottling that slows down the query will take effect after completing the current batch. This behavior prevents scroll timeouts.
41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
# File 'lib/elasticsearch/api/actions/reindex_rethrottle.rb', line 41 def reindex_rethrottle(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'reindex_rethrottle' } defined_params = [:task_id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'task_id' missing" unless arguments[:task_id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _task_id = arguments.delete(:task_id) method = Elasticsearch::API::HTTP_POST path = "_reindex/#{Utils.listify(_task_id)}/_rethrottle" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#render_search_template(arguments = {}) ⇒ Object
Render a search template. Render a search template as a search request body.
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
# File 'lib/elasticsearch/api/actions/render_search_template.rb', line 34 def render_search_template(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'render_search_template' } defined_params = [:id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _id = arguments.delete(:id) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = if _id "_render/template/#{Utils.listify(_id)}" else '_render/template' end params = {} Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#scripts_painless_execute(arguments = {}) ⇒ Object
Run a script. Runs a script and returns a result. Use this API to build and test scripts, such as when defining a script for a runtime field. This API requires very few dependencies and is especially useful if you don’t have permissions to write documents on a cluster. The API uses several contexts, which control how scripts are run, what variables are available at runtime, and what the return type is. Each context requires a script, but additional parameters depend on the context you’re using for that script. This functionality is Experimental and may be changed or removed completely in a future release. Elastic will take a best effort approach to fix any issues, but experimental features are not subject to the support SLA of official GA features.
40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
# File 'lib/elasticsearch/api/actions/scripts_painless_execute.rb', line 40 def scripts_painless_execute(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'scripts_painless_execute' } arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = '_scripts/painless/_execute' params = {} Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#scroll(arguments = {}) ⇒ Object
Run a scrolling search. IMPORTANT: The scroll API is no longer recommend for deep pagination. If you need to preserve the index state while paging through more than 10,000 hits, use the search_after
parameter with a point in time (PIT). The scroll API gets large sets of results from a single scrolling search request. To get the necessary scroll ID, submit a search API request that includes an argument for the scroll
query parameter. The scroll
parameter indicates how long Elasticsearch should retain the search context for the request. The search response returns a scroll ID in the _scroll_id
response body parameter. You can then use the scroll ID with the scroll API to retrieve the next batch of results for the request. If the Elasticsearch security features are enabled, the access to the results of a specific scroll ID is restricted to the user or API key that submitted the search. You can also use the scroll API to specify a new scroll parameter that extends or shortens the retention period for the search context. IMPORTANT: Results from a scrolling search reflect the state of the index at the time of the initial search request. Subsequent indexing or document changes only affect later search and scroll requests.
*Deprecation notice*: A scroll id can be quite large and should be specified as part of the body Deprecated since version 7.0.0
48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
# File 'lib/elasticsearch/api/actions/scroll.rb', line 48 def scroll(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'scroll' } arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _scroll_id = arguments.delete(:scroll_id) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = '_search/scroll' params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#search(arguments = {}) ⇒ Object
Run a search. Get search hits that match the query defined in the request. You can provide search queries using the q
query string parameter or the request body. If both are specified, only the query parameter is used. If the Elasticsearch security features are enabled, you must have the read index privilege for the target data stream, index, or alias. For cross-cluster search, refer to the documentation about configuring CCS privileges. To search a point in time (PIT) for an alias, you must have the read
index privilege for the alias’s data streams or indices. **Search slicing** When paging through a large number of documents, it can be helpful to split the search into multiple slices to consume them independently with the slice
and pit
properties. By default the splitting is done first on the shards, then locally on each shard. The local splitting partitions the shard into contiguous ranges based on Lucene document IDs. For instance if the number of shards is equal to 2 and you request 4 slices, the slices 0 and 2 are assigned to the first shard and the slices 1 and 3 are assigned to the second shard. IMPORTANT: The same point-in-time ID should be used for all slices. If different PIT IDs are used, slices can overlap and miss documents. This situation can occur because the splitting criterion is based on Lucene document IDs, which are not stable across changes to the index.
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 |
# File 'lib/elasticsearch/api/actions/search.rb', line 155 def search(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'search' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = if _index "#{Utils.listify(_index)}/_search" else '_search' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#search_mvt(arguments = {}) ⇒ Object
Search a vector tile. Search a vector tile for geospatial values. Before using this API, you should be familiar with the Mapbox vector tile specification. The API returns results as a binary mapbox vector tile. Internally, Elasticsearch translates a vector tile search API request into a search containing:
-
A
geo_bounding_box
query on the <field>. The query uses the <zoom>/<x>/<y> tile as a bounding box. -
A
geotile_grid
orgeohex_grid
aggregation on the <field>. Thegrid_agg
parameter determines the aggregation type. The aggregation uses the <zoom>/<x>/<y> tile as a bounding box. -
Optionally, a
geo_bounds
aggregation on the <field>. The search only includes this aggregation if theexact_bounds
parameter istrue
. -
If the optional parameter
with_labels
istrue
, the internal search will include a dynamic runtime field that calls thegetLabelPosition
function of the geometry doc value. This enables the generation of new point features containing suggested geometry labels, so that, for example, multi-polygons will have only one label.
For example, Elasticsearch may translate a vector tile search API request with a grid_agg
argument of geotile
and an exact_bounds
argument of true
into the following search + GET my-index/_search {
"size": 10000,
"query": {
"geo_bounding_box": {
"my-geo-field": {
"top_left": {
"lat": -40.979898069620134,
"lon": -45
},
"bottom_right": {
"lat": -66.51326044311186,
"lon": 0
}
}
}
},
"aggregations": {
"grid": {
"geotile_grid": {
"field": "my-geo-field",
"precision": 11,
"size": 65536,
"bounds": {
"top_left": {
"lat": -40.979898069620134,
"lon": -45
},
"bottom_right": {
"lat": -66.51326044311186,
"lon": 0
}
}
}
},
"bounds": {
"geo_bounds": {
"field": "my-geo-field",
"wrap_longitude": false
}
}
}
} + The API returns results as a binary Mapbox vector tile. Mapbox vector tiles are encoded as Google Protobufs (PBF). By default, the tile contains three layers:
-
A
hits
layer containing a feature for each <field> value matching thegeo_bounding_box
query. -
An
aggs
layer containing a feature for each cell of thegeotile_grid
orgeohex_grid
. The layer only contains features for cells with matching data. -
A meta layer containing:
-
A feature containing a bounding box. By default, this is the bounding box of the tile.
-
Value ranges for any sub-aggregations on the
geotile_grid
orgeohex_grid
. -
Metadata for the search.
-
The API only returns features that can display at its zoom level. For example, if a polygon feature has no area at its zoom level, the API omits it. The API returns errors as UTF-8 encoded JSON. IMPORTANT: You can specify several options for this API as either a query parameter or request body parameter. If you specify both parameters, the query parameter takes precedence. **Grid precision for geotile** For a grid_agg
of geotile
, you can use cells in the aggs
layer as tiles for lower zoom levels. grid_precision
represents the additional zoom levels available through these cells. The final precision is computed by as follows: <zoom> grid_precision+. For example, if <zoom> is 7 and grid_precision
is 8, then the geotile_grid
aggregation will use a precision of 15. The maximum final precision is 29. The grid_precision
also determines the number of cells for the grid as follows: (2^grid_precision) x (2^grid_precision). For example, a value of 8 divides the tile into a grid of 256 x 256 cells. The aggs
layer only contains features for cells with matching data. **Grid precision for geohex** For a grid_agg
of geohex
, Elasticsearch uses <zoom> and grid_precision
to calculate a final precision as follows: <zoom> grid_precision+. This precision determines the H3 resolution of the hexagonal cells produced by the geohex
aggregation. The following table maps the H3 resolution for each precision. For example, if <zoom> is 3 and grid_precision
is 3, the precision is 6. At a precision of 6, hexagonal cells have an H3 resolution of 2. If <zoom> is 3 and grid_precision
is 4, the precision is 7. At a precision of 7, hexagonal cells have an H3 resolution of 3. | Precision | Unique tile bins | H3 resolution | Unique hex bins | Ratio | | ——— | —————- | ————- | —————-| —– | | 1 | 4 | 0 | 122 | 30.5 | | 2 | 16 | 0 | 122 | 7.625 | | 3 | 64 | 1 | 842 | 13.15625 | | 4 | 256 | 1 | 842 | 3.2890625 | | 5 | 1024 | 2 | 5882 | 5.744140625 | | 6 | 4096 | 2 | 5882 | 1.436035156 | | 7 | 16384 | 3 | 41162 | 2.512329102 | | 8 | 65536 | 3 | 41162 | 0.6280822754 | | 9 | 262144 | 4 | 288122 | 1.099098206 | | 10 | 1048576 | 4 | 288122 | 0.2747745514 | | 11 | 4194304 | 5 | 2016842 | 0.4808526039 | | 12 | 16777216 | 6 | 14117882 | 0.8414913416 | | 13 | 67108864 | 6 | 14117882 | 0.2103728354 | | 14 | 268435456 | 7 | 98825162 | 0.3681524172 | | 15 | 1073741824 | 8 | 691776122 | 0.644266719 | | 16 | 4294967296 | 8 | 691776122 | 0.1610666797 | | 17 | 17179869184 | 9 | 4842432842 | 0.2818666889 | | 18 | 68719476736 | 10 | 33897029882 | 0.4932667053 | | 19 | 274877906944 | 11 | 237279209162 | 0.8632167343 | | 20 | 1099511627776 | 11 | 237279209162 | 0.2158041836 | | 21 | 4398046511104 | 12 | 1660954464122 | 0.3776573213 | | 22 | 17592186044416 | 13 | 11626681248842 | 0.6609003122 | | 23 | 70368744177664 | 13 | 11626681248842 | 0.165225078 | | 24 | 281474976710656 | 14 | 81386768741882 | 0.2891438866 | | 25 | 1125899906842620 | 15 | 569707381193162 | 0.5060018015 | | 26 | 4503599627370500 | 15 | 569707381193162 | 0.1265004504 | | 27 | 18014398509482000 | 15 | 569707381193162 | 0.03162511259 | | 28 | 72057594037927900 | 15 | 569707381193162 | 0.007906278149 | | 29 | 288230376151712000 | 15 | 569707381193162 | 0.001976569537 | Hexagonal cells don’t align perfectly on a vector tile. Some cells may intersect more than one vector tile. To compute the H3 resolution for each precision, Elasticsearch compares the average density of hexagonal bins at each resolution with the average density of tile bins at each zoom level. Elasticsearch uses the H3 resolution that is closest to the corresponding geotile density.
178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 |
# File 'lib/elasticsearch/api/actions/search_mvt.rb', line 178 def search_mvt(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'search_mvt' } defined_params = [:index, :field, :zoom, :x, :y].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'field' missing" unless arguments[:field] raise ArgumentError, "Required argument 'zoom' missing" unless arguments[:zoom] raise ArgumentError, "Required argument 'x' missing" unless arguments[:x] raise ArgumentError, "Required argument 'y' missing" unless arguments[:y] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) _field = arguments.delete(:field) _zoom = arguments.delete(:zoom) _x = arguments.delete(:x) _y = arguments.delete(:y) method = Elasticsearch::API::HTTP_POST path = "#{Utils.listify(_index)}/_mvt/#{Utils.listify(_field)}/#{Utils.listify(_zoom)}/#{Utils.listify(_x)}/#{Utils.listify(_y)}" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#search_shards(arguments = {}) ⇒ Object
Get the search shards. Get the indices and shards that a search request would be run against. This information can be useful for working out issues or planning optimizations with routing and shard preferences. When filtered aliases are used, the filter is returned as part of the indices
section. If the Elasticsearch security features are enabled, you must have the view_index_metadata
or manage
index privilege for the target data stream, index, or alias.
52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
# File 'lib/elasticsearch/api/actions/search_shards.rb', line 52 def search_shards(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'search_shards' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_GET path = if _index "#{Utils.listify(_index)}/_search_shards" else '_search_shards' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#search_template(arguments = {}) ⇒ Object
Run a search with a search template.
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 |
# File 'lib/elasticsearch/api/actions/search_template.rb', line 54 def search_template(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'search_template' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = if _index "#{Utils.listify(_index)}/_search/template" else '_search/template' end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#terms_enum(arguments = {}) ⇒ Object
Get terms in an index. Discover terms that match a partial string in an index. This API is designed for low-latency look-ups used in auto-complete scenarios.
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
# File 'lib/elasticsearch/api/actions/terms_enum.rb', line 36 def terms_enum(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'terms_enum' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end path = "#{Utils.listify(_index)}/_terms_enum" params = {} Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#termvector(arguments = {}) ⇒ Object
Deprecated: Use the plural version, #termvectors
111 112 113 114 |
# File 'lib/elasticsearch/api/actions/termvectors.rb', line 111 def termvector(arguments = {}) warn '[DEPRECATION] `termvector` is deprecated. Please use the plural version, `termvectors` instead.' termvectors(arguments.merge(endpoint: '_termvector')) end |
#termvectors(arguments = {}) ⇒ Object
Get term vector information. Get information and statistics about terms in the fields of a particular document. You can retrieve term vectors for documents stored in the index or for artificial documents passed in the body of the request. You can specify the fields you are interested in through the fields
parameter or by adding the fields to the request body. For example: + GET /my-index-000001/_termvectors/1?fields=message + Fields can be specified using wildcards, similar to the multi match query. Term vectors are real-time by default, not near real-time. This can be changed by setting realtime
parameter to false
. You can request three types of values: _term information_, _term statistics_, and _field statistics_. By default, all term information and field statistics are returned for all fields but term statistics are excluded. **Term information**
-
term frequency in the field (always returned)
-
term positions (+positions: true+)
-
start and end offsets (+offsets: true+)
-
term payloads (+payloads: true+), as base64 encoded bytes
If the requested information wasn’t stored in the index, it will be computed on the fly if possible. Additionally, term vectors could be computed for documents not even existing in the index, but instead provided by the user.
71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
# File 'lib/elasticsearch/api/actions/termvectors.rb', line 71 def termvectors(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'termvectors' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) _id = arguments.delete(:id) method = if body Elasticsearch::API::HTTP_POST else Elasticsearch::API::HTTP_GET end arguments.delete(:endpoint) path = if _index && _id "#{Utils.listify(_index)}/_termvectors/#{Utils.listify(_id)}" else "#{Utils.listify(_index)}/_termvectors" end params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#update(arguments = {}) ⇒ Object
Update a document. Update a document by running a script or passing a partial document. If the Elasticsearch security features are enabled, you must have the index
or write
index privilege for the target index or index alias. The script can update, delete, or skip modifying the document. The API also supports passing a partial document, which is merged into the existing document. To fully replace an existing document, use the index API. This operation:
-
Gets the document (collocated with the shard) from the index.
-
Runs the specified script.
-
Indexes the result.
The document must still be reindexed, but using this API removes some network roundtrips and reduces chances of version conflicts between the GET and the index operation. The _source
field must be enabled to use this API. In addition to _source
, you can access the following variables through the ctx
map: _index
, _type
, _id
, _version
, _routing
, and _now
(the current timestamp).
66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
# File 'lib/elasticsearch/api/actions/update.rb', line 66 def update(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'update' } defined_params = [:index, :id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'body' missing" unless arguments[:body] raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] raise ArgumentError, "Required argument 'id' missing" unless arguments[:id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _id = arguments.delete(:id) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = "#{Utils.listify(_index)}/_update/#{Utils.listify(_id)}" params = Utils.process_params(arguments) if Array(arguments[:ignore]).include?(404) Utils.rescue_from_not_found do Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end else Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end end |
#update_by_query(arguments = {}) ⇒ Object
Update documents. Updates documents that match the specified query. If no query is specified, performs an update on every document in the data stream or index without modifying the source, which is useful for picking up mapping changes. If the Elasticsearch security features are enabled, you must have the following index privileges for the target data stream, index, or alias:
-
read
-
index
orwrite
You can specify the query criteria in the request URI or the request body using the same syntax as the search API. When you submit an update by query request, Elasticsearch gets a snapshot of the data stream or index when it begins processing the request and updates matching documents using internal versioning. When the versions match, the document is updated and the version number is incremented. If a document changes between the time that the snapshot is taken and the update operation is processed, it results in a version conflict and the operation fails. You can opt to count version conflicts instead of halting and returning by setting conflicts
to proceed
. Note that if you opt to count version conflicts, the operation could attempt to update more documents from the source than max_docs
until it has successfully updated max_docs
documents or it has gone through every document in the source query. NOTE: Documents with a version equal to 0 cannot be updated using update by query because internal versioning does not support 0 as a valid version number. While processing an update by query request, Elasticsearch performs multiple search requests sequentially to find all of the matching documents. A bulk update request is performed for each batch of matching documents. Any query or update failures cause the update by query request to fail and the failures are shown in the response. Any update requests that completed successfully still stick, they are not rolled back. **Throttling update requests** To control the rate at which update by query issues batches of update operations, you can set requests_per_second
to any positive decimal number. This pads each batch with a wait time to throttle the rate. Set requests_per_second
to -1
to turn off throttling. Throttling uses a wait time between batches so that the internal scroll requests can be given a timeout that takes the request padding into account. The padding time is the difference between the batch size divided by the requests_per_second
and the time spent writing. By default the batch size is 1000, so if requests_per_second
is set to 500
: + target_time = 1000 / 500 per second = 2 seconds wait_time = target_time - write_time = 2 seconds - .5 seconds = 1.5 seconds + Since the batch is issued as a single _bulk request, large batch sizes cause Elasticsearch to create many requests and wait before starting the next set. This is “bursty” instead of “smooth”. Slicing Update by query supports sliced scroll to parallelize the update process. This can improve efficiency and provide a convenient way to break the request down into smaller parts. Setting slices
to auto
chooses a reasonable number for most data streams and indices. This setting will use one slice per shard, up to a certain limit. If there are multiple source data streams or indices, it will choose the number of slices based on the index or backing index with the smallest number of shards. Adding slices
to _update_by_query
just automates the manual process of creating sub-requests, which means it has some quirks:
-
You can see these requests in the tasks APIs. These sub-requests are “child” tasks of the task for the request with slices.
-
Fetching the status of the task for the request with
slices
only contains the status of completed slices. -
These sub-requests are individually addressable for things like cancellation and rethrottling.
-
Rethrottling the request with
slices
will rethrottle the unfinished sub-request proportionally. -
Canceling the request with slices will cancel each sub-request.
-
Due to the nature of slices each sub-request won’t get a perfectly even portion of the documents. All documents will be addressed, but some slices may be larger than others. Expect larger slices to have a more even distribution.
-
Parameters like
requests_per_second
andmax_docs
on a request with slices are distributed proportionally to each sub-request. Combine that with the point above about distribution being uneven and you should conclude that usingmax_docs
withslices
might not result in exactlymax_docs
documents being updated. -
Each sub-request gets a slightly different snapshot of the source data stream or index though these are all taken at approximately the same time.
If you’re slicing manually or otherwise tuning automatic slicing, keep in mind that:
-
Query performance is most efficient when the number of slices is equal to the number of shards in the index or backing index. If that number is large (for example, 500), choose a lower number as too many slices hurts performance. Setting slices higher than the number of shards generally does not improve efficiency and adds overhead.
-
Update performance scales linearly across available resources with the number of slices.
Whether query or update performance dominates the runtime depends on the documents being reindexed and cluster resources. **Update the document source** Update by query supports scripts to update the document source. As with the update API, you can set ctx.op
to change the operation that is performed. Set ctx.op = “noop” if your script decides that it doesn’t have to make any changes. The update by query operation skips updating the document and increments the noop
counter. Set ctx.op = “delete” if your script decides that the document should be deleted. The update by query operation deletes the document and increments the deleted
counter. Update by query supports only index
, noop
, and delete
. Setting ctx.op
to anything else is an error. Setting any other field in ctx
is an error. This API enables you to only modify the source of matching documents; you cannot move them.
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 |
# File 'lib/elasticsearch/api/actions/update_by_query.rb', line 155 def update_by_query(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'update_by_query' } defined_params = [:index].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'index' missing" unless arguments[:index] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = arguments.delete(:body) _index = arguments.delete(:index) method = Elasticsearch::API::HTTP_POST path = "#{Utils.listify(_index)}/_update_by_query" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |
#update_by_query_rethrottle(arguments = {}) ⇒ Object
Throttle an update by query operation. Change the number of requests per second for a particular update by query operation. Rethrottling that speeds up the query takes effect immediately but rethrotting that slows down the query takes effect after completing the current batch to prevent scroll timeouts.
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
# File 'lib/elasticsearch/api/actions/update_by_query_rethrottle.rb', line 35 def update_by_query_rethrottle(arguments = {}) request_opts = { endpoint: arguments[:endpoint] || 'update_by_query_rethrottle' } defined_params = [:task_id].each_with_object({}) do |variable, set_variables| set_variables[variable] = arguments[variable] if arguments.key?(variable) end request_opts[:defined_params] = defined_params unless defined_params.empty? raise ArgumentError, "Required argument 'task_id' missing" unless arguments[:task_id] arguments = arguments.clone headers = arguments.delete(:headers) || {} body = nil _task_id = arguments.delete(:task_id) method = Elasticsearch::API::HTTP_POST path = "_update_by_query/#{Utils.listify(_task_id)}/_rethrottle" params = Utils.process_params(arguments) Elasticsearch::API::Response.new( perform_request(method, path, params, body, headers, request_opts) ) end |