processors:
  metricstransform:
  # transforms is a list of transformations with each element transforming a metric selected by metric name
    transforms:
    
        # SPECIFY WHICH METRIC(S) TO MATCH
        
        # include specifies the metric name used to determine which metric(s) to operate on
      - include: <metric_name>
        # match_type specifies whether the include name should be used as a strict match or regexp match, default = strict
        match_type: {strict, regexp}
    
        # experimental_match_labels specifies the label set against which the metric filter will work. If experimental_match_labels is specified, transforms will only be applied to those metrics which 
        # have the provided metric label values. This works for both strict and regexp match_type. This is an experimental feature.
        experimental_match_labels: {<label1>: <label_value1>, <label2>: <label_value2>}
        
        # SPECIFY THE ACTION TO TAKE ON THE MATCHED METRIC(S)
        
        # action specifies if the operations (specified below) are performed on metrics in place (update), on an inserted clone (insert), or on a new combined metric (combine)
        action: {update, insert, combine}
        
        # SPECIFY HOW TO TRANSFORM THE METRIC GENERATED AS A RESULT OF APPLYING THE ABOVE ACTION
        
        # new_name specifies the updated name of the metric; if action is insert or combine, new_name is required
        new_name: <new_metric_name_inserted>
        # aggregation_type defines how combined data points will be aggregated; if action is combine, aggregation_type is required
        aggregation_type: {sum, mean, min, max, count, median}
        # submatch_case specifies the case that should be used when adding label values based on regexp submatches when performing a combine action; leave blank to use the submatch value as is
        submatch_case: {lower, upper}
        # operations contain a list of operations that will be performed on the resulting metric(s)
        operations:
            # action defines the type of operation that will be performed, see examples below for more details
          - action: {add_label, update_label, delete_label_value, toggle_scalar_data_type, experimental_scale_value, aggregate_labels, aggregate_label_values}
            # label specifies the label to operate on
            label: <label>
            # new_label specifies the updated name of the label; if action is add_label, new_label is required
            new_label: <new_label>
            # aggregated_values contains a list of label values that will be aggregated; if action is aggregate_label_values, aggregated_values is required
            aggregated_values: [values...]
            # new_value specifies the updated name of the label value; if action is add_label or aggregate_label_values, new_value is required
            new_value: <new_value>
            # label_value specifies the label value for which points should be deleted; if action is delete_label_value, label_value is required
            label_value: <label_value>
            # label_set contains a list of labels that will remain after aggregation; if action is aggregate_labels, label_set is required
            label_set: [labels...]
            # aggregation_type defines how data points will be aggregated; if action is aggregate_labels or aggregate_label_values, aggregation_type is required
            aggregation_type: {sum, mean, min, max, count, median}
            # experimental_scale specifies the scalar to apply to values. Scaling exponential histograms inherently involves some loss of accuracy. 
            experimental_scale: <scalar>
            # value_actions contain a list of operations that will be performed on the selected label
            value_actions:
                # value specifies the value to operate on
              - value: <current_label_value>
                # new_value specifies the updated value
                new_value: <new_label_value>

include: host.cpu.usage
action: insert
new_name: host.cpu.utilization
operations:
  ...

# create host.cpu.utilization from host.cpu.usage where we have metric label "container=my_container"
include: host.cpu.usage
action: insert
new_name: host.cpu.utilization
match_type: strict
experimental_match_labels: {"container": "my_container"}
operations:
  ...

# create host.cpu.utilization from host.cpu.usage where we have metric label pod with non-empty values
include: host.cpu.usage
action: insert
new_name: host.cpu.utilization
match_type: regexp
experimental_match_labels: {"pod": "(.|\\s)*\\S(.|\\s)*"}
operations:
  ...

# rename system.cpu.usage to system.cpu.usage_time
include: system.cpu.usage
action: update
new_name: system.cpu.usage_time

# rename all system.cpu metrics to system.processor.*.stat
# instead of regular $ use double dollar $$. Because $ is treated as a special character.
# wrap the group name/number with braces
include: ^system\.cpu\.(.*)$$
match_type: regexp
action: update
new_name: system.processor.$${1}.stat

# for system.cpu.usage_time, add label `version` with value `opentelemetry collector vX.Y.Z` to all points
include: system.cpu.usage
action: update
operations:
  - action: add_label
    new_label: version
    new_value: opentelemetry collector {{version}}

# for all system metrics, add label `version` with value `opentelemetry collector vX.Y.Z` to all points
include: ^system\.
match_type: regexp
action: update
operations:
  - action: add_label
    new_label: version
    new_value: opentelemetry collector {{version}}

# for system.cpu.usage_time, rename the label state to cpu_state
include: system.cpu.usage
action: update
operations:
  - action: update_label
    label: state
    new_label: cpu_state

# for all system.cpu metrics, rename the label state to cpu_state
include: ^system\.cpu\.
action: update
operations:
  - action: update_label
    label: state
    new_label: cpu_state

# rename the label value slab_reclaimable to sreclaimable, slab_unreclaimable to sunreclaimable
include: system.memory.usage
action: update
operations:
  - action: update_label
    label: state
    value_actions:
      - value: slab_reclaimable
        new_value: sreclaimable
      - value: slab_unreclaimable
        new_value: sunreclaimable

# deletes all data points with the label value 'idle' of the label 'state'
include: system.cpu.usage
action: update
operations:
  - action: delete_label_value
    label: state
    label_value: idle

# toggle the datatype of cpu usage from int (the default) to double
include: system.cpu.usage
action: update
operations:
  - action: toggle_scalar_data_type

# experimental_scale CPU usage from seconds to milliseconds
include: system.cpu.usage
action: update
operations:
  - action: experimental_scale_value
    experimental_scale: 1000

# aggregate away all labels except `state` using summation
include: system.cpu.usage
action: update
operations:
  - action: aggregate_labels
    label_set: [ state ]
    aggregation_type: sum

# aggregate data points with state label value slab_reclaimable & slab_unreclaimable using summation into slab
include: system.memory.usage
action: update
operations:
  - action: aggregate_label_values
    label: state
    aggregated_values: [ slab_reclaimable, slab_unreclaimable ]
    new_value: slab 
    aggregation_type: sum

# convert a set of metrics for each http_method into a single metric with an http_method label, i.e.
#
# Web Service (*)/Total Delete Requests     iis.requests{http_method=delete}
# Web Service (*)/Total Get Requests     >  iis.requests{http_method=get}
# Web Service (*)/Total Post Requests       iis.requests{http_method=post}
include: ^Web Service \(\*\)/Total (?P<http_method>.*) Requests$
match_type: regexp
action: combine
new_name: iis.requests
submatch_case: lower
operations:
  ...

# Group metrics from one single ResourceMetrics and report them as multiple ResourceMetrics.
# 
# ex: Consider pod and container metrics collected from Kubernetes. Both the metrics are recorded under one ResourceMetric
# applying this transformation will result in two separate ResourceMetric packets with corresponding resource labels in the resource headers
#
# instead of regular $ use double dollar $$. Because $ is treated as a special character.


- include: ^k8s\.pod\.(.*)$$
  match_type: regexp
  action: group
  group_resource_labels: {"resource.type": "k8s.pod", "source": "kubelet"}
- include: ^container\.(.*)$$
  match_type: regexp
  action: group
  group_resource_labels: {"resource.type": "container", "source": "kubelet"}