Add drop_bucket function

Signed-off-by: Israel Blancas <[email protected]>

Author: iblancasa

.chloggen/40280.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: transformprocessor
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add support to drop_bucket OTTL function. 
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [40280]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [user]

processor/transformprocessor/CONTRIBUTING.md

@@ -12,7 +12,7 @@ New functions must update the appropriate registry.  For common functions, updat
 
 Unit tests must be added for all new functions.  Unit test files must start with `func_` and end in `_test`.  Unit tests must be placed in the same directory as the function.  Functions that are not specific to a pipeline should be tested independently of any specific pipeline. Functions that are specific to a pipeline should be tests against that pipeline.
 
-All new functions should have integration tests added to any usable pipeline's `processing_test.go` tests.  The purpose of these tests is not to test the function's logic, but its ability to be used within a specific pipeline.  
+All new functions should have integration tests added to any usable pipeline's `processor_tests.go` tests.  The purpose of these tests is not to test the function's logic, but its ability to be used within a specific pipeline.  
 
 ## New Values
 

processor/transformprocessor/README.md

@@ -261,6 +261,7 @@ In addition to the common OTTL functions, the processor defines its own function
 - [aggregate_on_attributes](#aggregate_on_attributes)
 - [convert_exponential_histogram_to_histogram](#convert_exponential_histogram_to_histogram)
 - [aggregate_on_attribute_value](#aggregate_on_attribute_value)
+- [drop_bucket](#drop_bucket)
 
 ### convert_sum_to_gauge
 
@@ -582,6 +583,19 @@ statements:
 
 To aggregate only using a specified set of attributes, you can use `keep_matching_keys`.
 
+### drop_bucket
+
+`drop_bucket(pattern)`
+
+The `drop_bucket` function removes histogram buckets whose bounds match the provided regex pattern.
+
+`pattern` is a string containing a valid regular expression to match against bucket bounds.
+
+Examples:
+
+- `drop_bucket("^10$") where metric.name == "http_request_duration"` - Remove the bucket with bound exactly equal to 10
+- `drop_bucket("^(5|20)$") where metric.name == "request_size"` - Remove buckets with bounds 5 and 20
+- `drop_bucket("^1.*") where metric.name == "latency"` - Remove all buckets with bounds starting with 1
 
 ## Examples
 

processor/transformprocessor/internal/metrics/func_drop_bucket.go

@@ -0,0 +1,100 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package metrics // import "github.com/open-telemetry/opentelemetry-collector-contrib/processor/transformprocessor/internal/metrics"
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"regexp"
+	"strconv"
+
+	"go.opentelemetry.io/collector/pdata/pmetric"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl/contexts/ottlmetric"
+)
+
+type DropBucketArguments struct {
+	Pattern string
+}
+
+func newDropBucketFactory() ottl.Factory[ottlmetric.TransformContext] {
+	return ottl.NewFactory(
+		"drop_bucket",
+		&DropBucketArguments{},
+		createDropBucketFunction,
+	)
+}
+
+func createDropBucketFunction(_ ottl.FunctionContext, oArgs ottl.Arguments) (ottl.ExprFunc[ottlmetric.TransformContext], error) {
+	args, ok := oArgs.(*DropBucketArguments)
+
+	if !ok {
+		return nil, errors.New("DropBucketFactory args must be of type *DropBucketArguments[K]")
+	}
+
+	return dropBucketFunc(args.Pattern), nil
+}
+
+func dropBucketFunc(pattern string) ottl.ExprFunc[ottlmetric.TransformContext] {
+	return func(_ context.Context, tCtx ottlmetric.TransformContext) (any, error) {
+		metric := tCtx.GetMetric()
+		if metric.Type() != pmetric.MetricTypeHistogram {
+			return nil, nil
+		}
+
+		compiledPattern, err := regexp.Compile(pattern)
+		if err != nil {
+			return nil, fmt.Errorf("the regex pattern supplied to drop_bucket is not a valid pattern: %w", err)
+		}
+
+		dps := metric.Histogram().DataPoints()
+		for i := 0; i < dps.Len(); i++ {
+			hdp := dps.At(i)
+			bounds := hdp.ExplicitBounds()
+			counts := hdp.BucketCounts()
+
+			boundsSlice := bounds.AsRaw()
+			countsSlice := counts.AsRaw()
+
+			countsToRemove := make(map[int]bool)
+			idx := 1
+
+			newBounds := RemoveIfFloat64(boundsSlice, func(bound float64, _ int) bool {
+				defer func() {
+					idx++
+				}()
+				if compiledPattern.MatchString(strconv.FormatFloat(bound, 'f', -1, 64)) {
+					countsToRemove[idx] = true
+					return true
+				}
+
+				return false
+			})
+
+			if len(countsToRemove) == 0 {
+				continue
+			}
+
+			count := uint64(0)
+			newCounts := RemoveIfUint64(countsSlice, func(c uint64, idx int) bool {
+				if countsToRemove[idx] {
+					return true
+				}
+				count += c
+				return false
+			})
+
+			hdp.ExplicitBounds().FromRaw(newBounds)
+			hdp.BucketCounts().FromRaw(newCounts)
+			hdp.SetCount(count)
+
+			// Remove sum since it would be incorrect after removing buckets
+			hdp.RemoveSum()
+		}
+
+		return nil, nil
+	}
+}