Try SpotterManage Elasticsearch Transform Jobs.
| "added in version" 0.0.1 of community.elastic"
Authors: Rhys Campbell (@rhysmeister)
Install with ansible-galaxy collection install community.elastic:==1.1.2
collections:
- name: community.elastic
version: 1.1.2Manage Elasticsearch Transform Jobs.
- name: Create a transform job with a pivot
community.elastic.elastic_transform:
name: ecommerce_transform1
state: present
source:
index: "kibana_sample_data_ecommerce"
query: {
"term": {
"geoip.continent_name": {
"value": "Asia"
}
}
}
pivot:
group_by: {
"customer_id": {
"terms": {
"field": "customer_id"
}
}
}
aggregations: {
"max_price": {
"max": {
"field": "taxful_total_price"
}
}
}
description: "Maximum priced ecommerce data by customer_id in Asia"
dest:
index: "kibana_sample_data_ecommerce_transform1"
pipeline: "add_timestamp_pipeline"
frequency: "5m"
sync: {
"time": {
"field": "order_date",
"delay": "60s"
}
}
- name: Delete a transform job called ecommerce_transform1
community.elastic.elastic_transform:
name: ecommerce_transform1
state: absent
- name: Start a transform job called ecommerce_transform1
community.elastic.elastic_transform:
name: ecommerce_transform1
state: started
- name: Stop a transform job called ecommerce_transform1
community.elastic.elastic_transform:
name: ecommerce_transform1
state: stopped
dest:
description:
- The destination for the transform.
suboptions:
index:
description:
- The destination index for the transform.
required: true
type: str
pipeline:
description:
- The unique identifier for a pipeline.
required: false
type: str
type: dict
name:
aliases:
- transform_id
description:
- The name of the transform job
required: true
type: str
sync:
description:
- Defines the properties transforms require to run continuously.
suboptions:
time:
description:
- Specifies that the transform uses a time field to synchronize the source and
destination indices.
required: true
suboptions:
delay:
default: 60s
description:
- The time delay between the current time and the latest input data time.
type: str
field:
description:
- The date field that is used to identify new documents in the source.
required: true
type: str
type: dict
type: dict
pivot:
description:
- The pivot method transforms the data by aggregating and grouping it.
- These objects define the group by fields and the aggregation to reduce the data.
suboptions:
aggregations:
aliases:
- aggs
description:
- Defines how to aggregate the grouped data.
type: dict
group_by:
aliases:
- groupby
description:
- Defines how to group the data.
- More than one grouping can be defined per pivot.
type: dict
type: dict
state:
choices:
- present
- absent
- started
- stopped
default: present
description:
- State of the transform job
type: str
cafile:
description:
- Path to ca file
type: str
latest:
description:
- The latest method transforms the data by finding the latest document for each unique
key.
suboptions:
sort:
description:
- Specifies the date field that is used to identify the latest documents.
type: str
unique_key:
description:
- Specifies an array of one or more fields that are used to group the data.
elements: str
type: list
type: dict
source:
description:
- The source of the data for the transform.
suboptions:
index:
description:
- The source indices for the transform.
- It can be a single index, an index pattern (for example, "my-index-*"), \ an
array of indices (for example, ["my-index-000001", "my-index-000002"]), \ or
an array of index patterns (for example, ["my-index-*", "my-other-index-*"].
required: true
type: raw
query:
description:
- A query clause that retrieves a subset of data from the source index.
type: dict
type: dict
timeout:
default: 30
description:
- Response timeout in seconds.
type: int
settings:
description:
- Defines optional transform settings.
suboptions:
dates_as_epoch_millis:
default: false
description:
- Defines if dates in the ouput should be written as ISO formatted string (default)
or as millis since epoch.
type: bool
docs_per_second:
default: null
description:
- Specifies a limit on the number of input documents per second.
type: float
max_page_search_size:
default: 500
description:
- Defines the initial page size to use for the composite aggregation for each
checkpoint.
type: int
type: dict
frequency:
default: 1m
description:
- The interval between checks for changes in the source indices when the transform
is running continuously.
- Also determines the retry interval in the event of transient failures while the
transform is searching or indexing.
type: str
login_port:
default: 9200
description:
- The Elastic server port to login to.
required: false
type: int
login_user:
description:
- The Elastic user to login with.
- Required when I(login_password) is specified.
required: false
type: str
auth_method:
choices:
- ''
- http_auth
default: ''
description:
- Authentication Method.
type: str
auth_scheme:
choices:
- http
- https
default: http
description:
- Authentication scheme.
type: str
description:
description:
- A description of the transform job.
type: str
login_hosts:
default: localhost
description:
- The Elastic hosts to connect to.
elements: str
required: false
type: list
login_password:
description:
- The password used to authenticate with.
- Required when I(login_user) is specified.
required: false
type: str
defer_validation:
default: false
description:
- When true, deferrable validations are not run.
type: bool
connection_options:
default: []
description:
- Additional connection options for Elasticsearch
elements: dict
type: list