[extension/azure_encoding] Implement general Azure Resource Log parsing functionality

.chloggen/feat_azureencoding-logs-general.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. receiver/filelog)
+component: extension/azure_encoding
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Implement general Azure Resource Log parsing functionality
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [41725]
+
+# (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: []

extension/encoding/azureencodingextension/README.md

@@ -142,6 +142,8 @@ Currently supported following Azure Resource Logs export formats:
 
 Currently only subset of available Azure Resource Logs Categories properly translated using OpenTelemetry SemConv.
 
+[Transformation rules from Azure Resource Logs fields to OpenTelemetry](./internal/unmarshaler/logs/README.md).
+
 Unsupported Categories simply copies attributes from "properties" field of incoming Azure Log Record to OpenTelemetry Log Attributes as a strings.
 
 ***time_formats (Optional)***

extension/encoding/azureencodingextension/extension.go

@@ -22,15 +22,16 @@ var (
 )
 
 type azureExtension struct {
-	config *Config
+	config         *Config
+	logUnmarshaler plog.Unmarshaler
 }
 
 func (*azureExtension) UnmarshalTraces(_ []byte) (ptrace.Traces, error) {
 	return ptrace.Traces{}, errors.New("not implemented yet")
 }
 
-func (*azureExtension) UnmarshalLogs(_ []byte) (plog.Logs, error) {
-	return plog.Logs{}, errors.New("not implemented yet")
+func (ex *azureExtension) UnmarshalLogs(buf []byte) (plog.Logs, error) {
+	return ex.logUnmarshaler.UnmarshalLogs(buf)
 }
 
 func (*azureExtension) UnmarshalMetrics(_ []byte) (pmetric.Metrics, error) {

extension/encoding/azureencodingextension/factory.go

@@ -11,6 +11,7 @@ import (
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding/azureencodingextension/internal/metadata"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding/azureencodingextension/internal/unmarshaler"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding/azureencodingextension/internal/unmarshaler/logs"
 )
 
 func NewFactory() extension.Factory {
@@ -22,11 +23,17 @@ func NewFactory() extension.Factory {
 	)
 }
 
-func createExtension(_ context.Context, _ extension.Settings, cfg component.Config) (extension.Extension, error) {
+func createExtension(_ context.Context, settings extension.Settings, cfg component.Config) (extension.Extension, error) {
 	config := cfg.(*Config)
 
 	return &azureExtension{
 		config: config,
+		logUnmarshaler: logs.NewAzureResourceLogsUnmarshaler(
+			settings.BuildInfo,
+			settings.Logger,
+			config.Format,
+			config.Logs,
+		),
 	}, nil
 }
 

extension/encoding/azureencodingextension/go.mod

@@ -3,7 +3,12 @@ module github.com/open-telemetry/opentelemetry-collector-contrib/extension/encod
 go 1.24.0
 
 require (
+	github.com/goccy/go-json v0.10.5
+	github.com/json-iterator/go v1.1.12
 	github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding v0.140.1
+	github.com/open-telemetry/opentelemetry-collector-contrib/pkg/golden v0.140.1
+	github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest v0.140.1
+	github.com/relvacode/iso8601 v1.7.0
 	github.com/stretchr/testify v1.11.1
 	go.opentelemetry.io/collector/component v1.46.1-0.20251120204106-2e9c82787618
 	go.opentelemetry.io/collector/component/componenttest v0.140.1-0.20251120204106-2e9c82787618
@@ -12,39 +17,46 @@ require (
 	go.opentelemetry.io/collector/extension v1.46.1-0.20251120204106-2e9c82787618
 	go.opentelemetry.io/collector/extension/extensiontest v0.140.1-0.20251120204106-2e9c82787618
 	go.opentelemetry.io/collector/pdata v1.46.1-0.20251120204106-2e9c82787618
+	go.opentelemetry.io/otel v1.38.0
 	go.uber.org/goleak v1.3.0
+	go.uber.org/zap v1.27.0
 )
 
 require (
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
 	github.com/gobwas/glob v0.2.3 // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/hashicorp/go-version v1.7.0 // indirect
-	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/knadh/koanf/maps v0.1.2 // indirect
 	github.com/knadh/koanf/providers/confmap v1.0.0 // indirect
 	github.com/knadh/koanf/v2 v2.3.0 // indirect
 	github.com/mitchellh/copystructure v1.2.0 // indirect
 	github.com/mitchellh/reflectwalk v1.0.2 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.3-0.20250322232337-35a7c28c31ee // indirect
+	github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.140.1 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
 	go.opentelemetry.io/collector/featuregate v1.46.1-0.20251120204106-2e9c82787618 // indirect
 	go.opentelemetry.io/collector/pdata/pprofile v0.140.1-0.20251120204106-2e9c82787618 // indirect
-	go.opentelemetry.io/otel v1.38.0 // indirect
 	go.opentelemetry.io/otel/metric v1.38.0 // indirect
 	go.opentelemetry.io/otel/sdk v1.38.0 // indirect
 	go.opentelemetry.io/otel/sdk/metric v1.38.0 // indirect
 	go.opentelemetry.io/otel/trace v1.38.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
-	go.uber.org/zap v1.27.0 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/sys v0.37.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )
 
 replace github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding => ../
+
+replace github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil => ../../../pkg/pdatautil
+
+replace github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest => ../../../pkg/pdatatest
+
+replace github.com/open-telemetry/opentelemetry-collector-contrib/pkg/golden => ../../../pkg/golden

extension/encoding/azureencodingextension/internal/unmarshaler/helpers.go

@@ -3,9 +3,106 @@
 
 package unmarshaler // import "github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding/azureencodingextension/internal/unmarshaler"
 
+import (
+	"encoding/json"
+	"fmt"
+	"time"
+
+	"github.com/relvacode/iso8601"
+	"go.opentelemetry.io/collector/pdata/pcommon"
+)
+
 type RecordsBatchFormat string
 
+// Supported wrapper formats of Azure Logs Records batch
 const (
 	FormatEventHub    RecordsBatchFormat = "eventhub"
 	FormatBlobStorage RecordsBatchFormat = "blobstorage"
 )
+
+// JSON Path expressions that matches specific wrapper format
+const (
+	// As exported to Azure Event Hub, e.g. `{"records": [ {...}, {...} ]}`
+	JSONPathEventHubLogRecords = "$.records[*]"
+	// As exported to Azure Blob Storage, e.g. `[ {...}, {...} ]`
+	JSONPathBlobStorageLogRecords = "$[*]"
+)
+
+// Commonly used attributes non-SemConv attributes across all telemetry signals
+const (
+	AttributeAzureCategory      = "azure.category"
+	AttributeAzureOperationName = "azure.operation.name"
+)
+
+const originalSuffix = ".original"
+
+// AsTimestamp tries to parse a string with timestamp into OpenTelemetry
+// using provided list of formats layouts.
+// If not formats provided or parsing using them failed - will use an ISO8601 parser.
+// If the string cannot be parsed, it will return zero and the error.
+func AsTimestamp(s string, formats ...string) (pcommon.Timestamp, error) {
+	var err error
+	var t time.Time
+
+	// Try parsing with provided formats first
+	for _, format := range formats {
+		if t, err = time.Parse(format, s); err == nil {
+			return pcommon.Timestamp(t.UnixNano()), nil
+		}
+	}
+
+	// Fallback to ISO 8601 parsing if no format matches
+	if t, err = iso8601.ParseString(s); err == nil {
+		return pcommon.Timestamp(t.UnixNano()), nil
+	}
+
+	return 0, err
+}
+
+// AttrPutStrIf is a helper function to set a string attribute
+// only if the value is not empty
+func AttrPutStrIf(attrs pcommon.Map, attrKey, attrValue string) {
+	if attrValue != "" {
+		attrs.PutStr(attrKey, attrValue)
+	}
+}
+
+// AttrPutStrPtrIf is a helper function to set a string attribute
+// only if the value exists and is not empty
+func AttrPutStrPtrIf(attrs pcommon.Map, attrKey string, attrValue *string) {
+	if attrValue != nil && *attrValue != "" {
+		attrs.PutStr(attrKey, *attrValue)
+	}
+}
+
+// AttrPutIntNumberIf is a helper function to set an int64 attribute with defined key,
+// trying to parse it from json.Number value
+// If parsing failed - no attribute will be set
+func AttrPutIntNumberIf(attrs pcommon.Map, attrKey string, attrValue json.Number) {
+	if i, err := attrValue.Int64(); err == nil {
+		attrs.PutInt(attrKey, i)
+	}
+}
+
+// AttrPutIntNumberPtrIf is a same function as AttrPutIntNumberIf but
+// accepts a pointer to json.Number instead of value
+func AttrPutIntNumberPtrIf(attrs pcommon.Map, attrKey string, attrValue *json.Number) {
+	if attrValue != nil {
+		AttrPutIntNumberIf(attrs, attrKey, *attrValue)
+	}
+}
+
+// attrPutMap is a helper function to set a map attribute with defined key,
+// trying to parse it from raw value
+// If parsing failed - no attribute will be set
+func AttrPutMapIf(attrs pcommon.Map, attrKey string, attrValue any) {
+	if attrKey == "" || attrValue == nil {
+		return
+	}
+
+	if err := attrs.PutEmpty(attrKey).FromRaw(attrValue); err != nil {
+		// Failed to parse - put string representation of the attrValue
+		attrs.Remove(attrKey)
+		attrs.PutStr(attrKey+originalSuffix, fmt.Sprintf("%v", attrValue))
+	}
+}