[pkg/stanza] Revert recombine operator 'overwrite_with' change (open-…

…telemetry#32146)

Effectively reverts open-telemetry#30786, due to error pointed out by @yutingcaicyt
[here](open-telemetry#30786 (comment)).

.chloggen/pkg-stanza-revert-overwrite-with.yaml

@@ -0,0 +1,30 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: breaking
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: pkg/stanza
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Revert recombine operator's 'overwrite_with' default value.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [30783]
+
+# (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: |
+    Restores the previous the default value of `oldest`, meaning that the recombine operator will emit the
+    first entry from each batch (with the recombined field). This fixes the bug introduced by 30783 and restores
+    the default setting so as to effectively cancel out the bug for users who were not using this setting.
+    For users who were explicitly setting `overwrite_with`, this corrects the intended behavior.
+# 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: []

pkg/stanza/operator/transformer/recombine/config.go

@@ -38,7 +38,7 @@ func NewConfigWithID(operatorID string) *Config {
 		MaxBatchSize:      1000,
 		MaxSources:        1000,
 		CombineWith:       defaultCombineWith,
-		OverwriteWith:     "newest",
+		OverwriteWith:     "oldest",
 		ForceFlushTimeout: 5 * time.Second,
 		SourceIdentifier:  entry.NewAttributeField("file.path"),
 	}
@@ -94,12 +94,12 @@ func (c *Config) Build(logger *zap.SugaredLogger) (operator.Operator, error) {
 		return nil, fmt.Errorf("missing required argument 'combine_field'")
 	}
 
-	var overwriteWithOldest bool
+	var overwriteWithNewest bool
 	switch c.OverwriteWith {
 	case "newest":
-		overwriteWithOldest = false
+		overwriteWithNewest = true
 	case "oldest", "":
-		overwriteWithOldest = true
+		overwriteWithNewest = false
 	default:
 		return nil, fmt.Errorf("invalid value '%s' for parameter 'overwrite_with'", c.OverwriteWith)
 	}
@@ -110,7 +110,7 @@ func (c *Config) Build(logger *zap.SugaredLogger) (operator.Operator, error) {
 		prog:                prog,
 		maxBatchSize:        c.MaxBatchSize,
 		maxSources:          c.MaxSources,
-		overwriteWithOldest: overwriteWithOldest,
+		overwriteWithNewest: overwriteWithNewest,
 		batchMap:            make(map[string]*sourceBatch),
 		batchPool: sync.Pool{
 			New: func() any {

pkg/stanza/operator/transformer/recombine/transformer.go

@@ -26,7 +26,7 @@ type Transformer struct {
 	prog                *vm.Program
 	maxBatchSize        int
 	maxSources          int
-	overwriteWithOldest bool
+	overwriteWithNewest bool
 	combineField        entry.Field
 	combineWith         string
 	ticker              *time.Ticker
@@ -154,7 +154,7 @@ func (t *Transformer) addToBatch(ctx context.Context, e *entry.Entry, source str
 		batch = t.addNewBatch(source, e)
 	} else {
 		batch.numEntries++
-		if t.overwriteWithOldest {
+		if t.overwriteWithNewest {
 			batch.baseEntry = e
 		}
 	}

pkg/stanza/operator/transformer/recombine/transformer_test.go

@@ -123,12 +123,12 @@ func TestTransformer(t *testing.T) {
 				return cfg
 			}(),
 			[]*entry.Entry{
-				entryWithBody(t1, "test1"),
-				entryWithBody(t2, "test2"),
-				entryWithBody(t2, "test1"),
+				entryWithBodyAttr(t1, "test1", map[string]string{"base": "false"}),
+				entryWithBodyAttr(t2, "test2", map[string]string{"base": "true"}),
+				entryWithBodyAttr(t2, "test1", map[string]string{"base": "false"}),
 			},
 			[]*entry.Entry{
-				entryWithBody(t1, "test1\ntest2"),
+				entryWithBodyAttr(t2, "test1\ntest2", map[string]string{"base": "true"}),
 			},
 		},
 		{
@@ -142,12 +142,12 @@ func TestTransformer(t *testing.T) {
 				return cfg
 			}(),
 			[]*entry.Entry{
-				entryWithBody(t1, "test1"),
-				entryWithBody(t2, "test2"),
-				entryWithBody(t2, "test1"),
+				entryWithBodyAttr(t1, "test1", map[string]string{"base": "true"}),
+				entryWithBodyAttr(t2, "test2", map[string]string{"base": "false"}),
+				entryWithBodyAttr(t2, "test1", map[string]string{"base": "true"}),
 			},
 			[]*entry.Entry{
-				entryWithBody(t2, "test1\ntest2"),
+				entryWithBodyAttr(t1, "test1\ntest2", map[string]string{"base": "true"}),
 			},
 		},
 		{
@@ -157,7 +157,7 @@ func TestTransformer(t *testing.T) {
 				cfg.CombineField = entry.NewBodyField()
 				cfg.IsFirstEntry = "$body == 'test1'"
 				cfg.OutputIDs = []string{"fake"}
-				cfg.OverwriteWith = "newest"
+				cfg.OverwriteWith = "oldest"
 				cfg.ForceFlushTimeout = 10 * time.Millisecond
 				return cfg
 			}(),
@@ -177,7 +177,7 @@ func TestTransformer(t *testing.T) {
 				cfg.CombineField = entry.NewBodyField()
 				cfg.IsFirstEntry = "body == 'start'"
 				cfg.OutputIDs = []string{"fake"}
-				cfg.OverwriteWith = "oldest"
+				cfg.OverwriteWith = "newest"
 				cfg.ForceFlushTimeout = 10 * time.Millisecond
 				return cfg
 			}(),
@@ -286,7 +286,7 @@ func TestTransformer(t *testing.T) {
 				cfg.CombineField = entry.NewBodyField("message")
 				cfg.CombineWith = ""
 				cfg.IsLastEntry = "body.logtag == 'F'"
-				cfg.OverwriteWith = "oldest"
+				cfg.OverwriteWith = "newest"
 				cfg.OutputIDs = []string{"fake"}
 				return cfg
 			}(),
@@ -380,7 +380,7 @@ func TestTransformer(t *testing.T) {
 				cfg.IsLastEntry = "body == 'end'"
 				cfg.OutputIDs = []string{"fake"}
 				cfg.MaxSources = 1
-				cfg.OverwriteWith = "oldest"
+				cfg.OverwriteWith = "newest"
 				cfg.ForceFlushTimeout = 10 * time.Millisecond
 				return cfg
 			}(),