Merge branch 'main' into s3exporter-canned-acl

Author: kevthompson

.chloggen/k8sattributes-fix-filter-labels-bug.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: bug_fix
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: k8sattributes
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Fix bug where `Filters.Labels` failed with when the `exists` or `not-exists` operations were used.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [37913]
+
+# (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: []

CHANGELOG-API.md

@@ -514,9 +514,9 @@ If you are looking for user-facing changes, check out [CHANGELOG.md](./CHANGELOG
 ### 🚩 Deprecations 🚩
 
 - `pkg/stanza`: Deprecate 'helper.EncodingConfig' and 'helper.NewEncodingConfig' (#25846)
-- `pkg/stanza`: Deprecate encoding related elements of helper pacakge, in favor of new decoder package (#26019)
+- `pkg/stanza`: Deprecate encoding related elements of helper package, in favor of new decoder package (#26019)
   Includes the following deprecations | - Decoder - NewDecoder - LookupEncoding - IsNop
-- `pkg/stanza`: Deprecate tokenization related elements of helper pacakge, in favor of new tokenize package (#25914)
+- `pkg/stanza`: Deprecate tokenization related elements of helper package, in favor of new tokenize package (#25914)
   Includes the following deprecations | - Flusher - FlusherConfig - NewFlusherConfig - Multiline - MultilineConfig - NewMultilineConfig - NewLineStartSplitFunc - NewLineEndSplitFunc - NewNewlineSplitFunc - Splitter - SplitterConfig - NewSplitterConfig - SplitNone
 
 ### 💡 Enhancements 💡

CHANGELOG.md

@@ -110,7 +110,7 @@ If you are looking for developer-facing changes, check out [CHANGELOG-API.md](./
 - `otlpjsonfilereceiver`: Include file attributes and append it to the log record (#36641)
 - `routingconnector`: The connector splits the original payload so that it may be emitted in parts to each route. (#37390)
 - `pkg/stanza`: Fix default source identifier in recombine operator (#37210)
-  Its defualt value is now aligned with the semantic conventions: `attributes["log.file.path"]`
+  Its default value is now aligned with the semantic conventions: `attributes["log.file.path"]`
 
 - `tailsamplingprocessor`: Fixed sampling decision metrics `otelcol_processor_tail_sampling_sampling_trace_dropped_too_early` and `otelcol_processor_tail_sampling_sampling_policy_evaluation_error_total`, these were sometimes overcounted. (#37212)
   As a result of this change non-zero values of `otelcol_processor_tail_sampling_sampling_trace_dropped_too_early`
@@ -789,7 +789,7 @@ arrow.waiter_limit -> admission.waiter_limit
 
 ### 🚀 New components 🚀
 
-- `azurelogs_translater`: Adds a new translater that converts Azure EventHub logs to OpenTelemetry logs used by the Azure Events Hub receiver. (#39704)
+- `azurelogs_translator`: Adds a new translator that converts Azure EventHub logs to OpenTelemetry logs used by the Azure Events Hub receiver. (#39704)
 - `dorisexporter`: logs implementation (#33479)
 - `dorisexporter`: traces implementation (#33479)
 

pkg/batchperresourceattr/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [atoulme, dmitryax]

pkg/batchpersignal/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [jpkrohling]

pkg/core/xidutils/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [odubajDT]

pkg/experimentalmetricmetadata/metadata.yaml

@@ -1,4 +1,5 @@
 status:
+  class: pkg
   codeowners:
     active: [dmitryax]
     emeritus: [rmfitzpatrick]

pkg/pdatatest/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [djaglowski, fatsheep9146]

pkg/pdatautil/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [dmitryax]

pkg/resourcetotelemetry/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [mx-psi]

pkg/stanza/docs/operators/key_value_parser.md

@@ -8,7 +8,7 @@ The `key_value_parser` operator parses the string-type field selected by `parse_
 | ---              | ---                 | ---                                                                                                                                                                                                                                       |
 | `id`             | `key_value_parser`  | A unique identifier for the operator.                                                                                                                                                                                                     |
 | `delimiter`      | `=`                 | The delimiter used for splitting a value into a key value pair.                                                                                                                                                                           |
-| `pair_delimiter` |                     | The delimiter used for seperating key value pairs, defaults to whitespace.                                                                                                                                                                |
+| `pair_delimiter` |                     | The delimiter used for separating key value pairs, defaults to whitespace.                                                                                                                                                                |
 | `output`         | Next in pipeline    | The connected operator(s) that will receive all outbound entries.                                                                                                                                                                         |
 | `parse_from`     | `body`              | A [field](../types/field.md) that indicates the field to be parsed into key value pairs.                                                                                                                                               |
 | `parse_to`       | `attributes`        | A [field](../types/field.md) that indicates the field to be parsed as into key value pairs.                                                                                                                                            |

pkg/stanza/docs/operators/noop.md

@@ -30,4 +30,4 @@ operators:
 
 #### Why is this necessary?
 
-The last operator is always responsible for emitting logs from the receiver. In non-linear pipelines, it is sometimes necessary to explictly direct logs to the final operator. In many such cases, the final operator performs some work. However, if no more work is required, the `noop` operator can serve as a final operator.
+The last operator is always responsible for emitting logs from the receiver. In non-linear pipelines, it is sometimes necessary to explicitly direct logs to the final operator. In many such cases, the final operator performs some work. However, if no more work is required, the `noop` operator can serve as a final operator.

pkg/stanza/docs/operators/syslog_input.md

@@ -26,7 +26,7 @@ TCP Configuration:
 ```yaml
 - type: syslog_input
   tcp:
-     listen_adress: "0.0.0.0:54526"
+     listen_address: "0.0.0.0:54526"
   syslog:
      protocol: rfc5424
 ```
@@ -36,7 +36,7 @@ UDP Configuration:
 ```yaml
 - type: syslog_input
   udp:
-     listen_adress: "0.0.0.0:54526"
+     listen_address: "0.0.0.0:54526"
   syslog:
      protocol: rfc3164
      location: UTC

pkg/stanza/docs/operators/udp_input.md

@@ -66,7 +66,7 @@ Configuration:
 
 ```yaml
 - type: udp_input
-  listen_adress: "0.0.0.0:54526"
+  listen_address: "0.0.0.0:54526"
 ```
 
 Send a log:

pkg/stanza/docs/types/entry.md

@@ -36,4 +36,4 @@ Represented in `json` format, an entry may look like the following:
 }
 ```
 
-Throughout the documentation, `json` format is used to represent entries. Fields are typically ommitted unless relevant to the behavior being described.
+Throughout the documentation, `json` format is used to represent entries. Fields are typically omitted unless relevant to the behavior being described.

pkg/stanza/docs/types/operators.md

@@ -104,7 +104,7 @@ receivers:
         value: baz
 ```
 
-### Emitting from a reciever
+### Emitting from a receiver
 
 By default, the last operator in a sequence will emit logs from the receiver.
 

pkg/stanza/docs/types/severity.md

@@ -13,7 +13,7 @@ Parser operators can parse a severity and attach the resulting value to a log en
 | `parse_from`     | required  | The [field](../types/field.md) from which the value will be parsed. |
 | `preset`         | `default` | A predefined set of values that should be interpretted at specific severity levels. |
 | `mapping`        |           | A custom set of values that should be interpretted at designated severity levels. |
-| `overwrite_text` | `false`   | If `true`, the severity text will be set to the [recommeneded short name](https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/logs/data-model.md#displaying-severity) corresponding to the severity number. |
+| `overwrite_text` | `false`   | If `true`, the severity text will be set to the [recommended short name](https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/logs/data-model.md#displaying-severity) corresponding to the severity number. |
 
 Note that by default the severity _text_ will be set to the original value which was interpreted into a severity number. In order to set the severity text to a standard short name (e.g. `ERROR`, `INFO3`, etc.), set `overwrite_text` to `true`.
 

pkg/stanza/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [djaglowski]

pkg/translator/azure/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [open-telemetry/collector-approvers, atoulme, cparkins]

pkg/translator/azurelogs/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: "pkg"
   codeowners:
     active: [atoulme, cparkins, MikeGoldsmith]

pkg/translator/jaeger/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: "pkg"
   codeowners:
     active: [open-telemetry/collector-approvers, frzifus]

pkg/translator/loki/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: "pkg"
   codeowners:
     active: [gouthamve, mar4uk]

pkg/translator/opencensus/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: "pkg"
   codeowners:
     active: [open-telemetry/collector-approvers]

pkg/translator/prometheus/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: "pkg"
   codeowners:
     active: [dashpole, bertysentry, ArthurSens]

pkg/translator/prometheusremotewrite/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: "pkg"
   codeowners:
     active: [Aneurysm9, dashpole]

pkg/translator/skywalking/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: pkg
   codeowners:
     active: [JaredTan95]

pkg/winperfcounters/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: "pkg"
   codeowners:
     active: [dashpole, Mrod1598, alxbl, pjanotti]

pkg/xk8stest/metadata.yaml

@@ -1,3 +1,4 @@
 status:
+  class: "pkg"
   codeowners:
     active: [crobert-1]

processor/k8sattributesprocessor/internal/kube/client.go

@@ -946,10 +946,27 @@ func (c *WatchClient) shouldIgnorePod(pod *api_v1.Pod) bool {
 	return false
 }
 
+var singleValueOperators = map[selection.Operator]int{
+	selection.Equals:       1,
+	selection.DoubleEquals: 1,
+	selection.NotEquals:    1,
+	selection.GreaterThan:  1,
+	selection.LessThan:     1,
+}
+
 func selectorsFromFilters(filters Filters) (labels.Selector, fields.Selector, error) {
 	labelSelector := labels.Everything()
 	for _, f := range filters.Labels {
-		r, err := labels.NewRequirement(f.Key, f.Op, []string{f.Value})
+		if f.Op == selection.In || f.Op == selection.NotIn {
+			return nil, nil, fmt.Errorf("label filters don't support operator: '%s'", f.Op)
+		}
+
+		var vals []string
+		if _, ok := singleValueOperators[f.Op]; ok {
+			vals = []string{f.Value}
+		}
+
+		r, err := labels.NewRequirement(f.Key, f.Op, vals)
 		if err != nil {
 			return nil, nil, err
 		}

processor/k8sattributesprocessor/internal/kube/client_test.go

@@ -1358,7 +1358,7 @@ func TestFilters(t *testing.T) {
 		}, {
 			name: "labels-and-fields",
 			filters: Filters{
-				Labels: []FieldFilter{
+				Labels: []LabelFilter{
 					{
 						Key:   "k1",
 						Value: "v1",
@@ -1841,24 +1841,69 @@ func TestErrorSelectorsFromFilters(t *testing.T) {
 	tests := []struct {
 		name    string
 		filters Filters
+		wantErr bool
 	}{
 		{
 			name: "label/invalid-op",
 			filters: Filters{
-				Labels: []FieldFilter{{Op: "invalid-op"}},
+				Labels: []LabelFilter{{Op: "invalid-op"}},
 			},
+			wantErr: true,
+		},
+		{
+			name: "label/equals",
+			filters: Filters{
+				Labels: []LabelFilter{{Key: "app", Op: selection.Equals, Value: "test"}},
+			},
+		},
+		{
+			name: "label/not-equals",
+			filters: Filters{
+				Labels: []LabelFilter{{Key: "app", Op: selection.NotEquals, Value: "test"}},
+			},
+		},
+		{
+			name: "label/exists",
+			filters: Filters{
+				Labels: []LabelFilter{{Key: "app", Op: selection.Exists}},
+			},
+		},
+		{
+			name: "label/does-not-exist",
+			filters: Filters{
+				Labels: []LabelFilter{{Key: "app", Op: selection.DoesNotExist}},
+			},
+		},
+		{
+			name: "label/in",
+			filters: Filters{
+				Labels: []LabelFilter{{Key: "app", Op: selection.In}},
+			},
+			wantErr: true,
+		},
+		{
+			name: "label/not-in",
+			filters: Filters{
+				Labels: []LabelFilter{{Key: "app", Op: selection.NotIn}},
+			},
+			wantErr: true,
 		},
 		{
 			name: "fields/invalid-op",
 			filters: Filters{
 				Fields: []FieldFilter{{Op: selection.Exists}},
 			},
+			wantErr: true,
 		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			_, _, err := selectorsFromFilters(tt.filters)
-			assert.Error(t, err)
+			if tt.wantErr {
+				assert.Error(t, err)
+			} else {
+				assert.NoError(t, err)
+			}
 		})
 	}
 }

processor/k8sattributesprocessor/internal/kube/informer_test.go

@@ -49,7 +49,7 @@ func Test_informerListFuncWithSelectors(t *testing.T) {
 				Op:    selection.Equals,
 			},
 		},
-		Labels: []FieldFilter{
+		Labels: []LabelFilter{
 			{
 				Key:   "lk1",
 				Value: "lv1",
@@ -86,7 +86,7 @@ func Test_informerWatchFuncWithSelectors(t *testing.T) {
 				Op:    selection.Equals,
 			},
 		},
-		Labels: []FieldFilter{
+		Labels: []LabelFilter{
 			{
 				Key:   "lk1",
 				Value: "lv1",

processor/k8sattributesprocessor/internal/kube/kube.go

@@ -176,7 +176,7 @@ type Filters struct {
 	Node      string
 	Namespace string
 	Fields    []FieldFilter
-	Labels    []FieldFilter
+	Labels    []LabelFilter
 }
 
 // FieldFilter represents exactly one filter by field rule.
@@ -192,6 +192,24 @@ type FieldFilter struct {
 	Op selection.Operator
 }
 
+// LabelFilter represents exactly one filter by label rule.
+type LabelFilter struct {
+	// Key matches the label name.
+	Key string
+	// Value matches the label value.
+	Value string
+	// Op determines the matching operation.
+	// The following operations are supported,
+	//	- Exists
+	// 	- DoesNotExist
+	//	- Equals
+	//	- DoubleEquals
+	//	- NotEquals
+	//	- GreaterThan
+	//	- LessThan
+	Op selection.Operator
+}
+
 // ExtractionRules is used to specify the information that needs to be extracted
 // from pods and added to the spans as tags.
 type ExtractionRules struct {