Add trim report output

internal/cli/trim_test.go

@@ -8,6 +8,7 @@ import (
 	"testing"
 
 	"gitea.maximumdirect.net/eric/seriatim/internal/config"
+	"gitea.maximumdirect.net/eric/seriatim/internal/report"
 	"gitea.maximumdirect.net/eric/seriatim/schema"
 )
 
@@ -221,6 +222,125 @@ func TestTrimRejectsNonSeriatimInputArtifacts(t *testing.T) {
 	}
 }
 
+func TestTrimReportFileContainsAuditFields(t *testing.T) {
+	dir := t.TempDir()
+	input := writeTrimFullFixture(t, dir, "input.json")
+	output := filepath.Join(dir, "trimmed.json")
+	reportPath := filepath.Join(dir, "trim-report.json")
+
+	err := executeTrim(
+		"--input-file", input,
+		"--output-file", output,
+		"--report-file", reportPath,
+		"--remove", "4,2",
+	)
+	if err != nil {
+		t.Fatalf("trim failed: %v", err)
+	}
+
+	var rpt report.Report
+	readJSON(t, reportPath, &rpt)
+	if len(rpt.Events) == 0 {
+		t.Fatal("expected report events")
+	}
+	if !hasReportEvent(rpt, "trim", "trim", "trimmed 4 input segment(s) into 2 output segment(s) with mode=remove") {
+		t.Fatal("expected trim summary event")
+	}
+	if !hasReportEvent(rpt, "trim", "validate-output", "validated 2 output segment(s)") {
+		t.Fatal("expected validation event")
+	}
+
+	audit := extractTrimAuditEvent(t, rpt)
+	if audit.Operation != "trim" {
+		t.Fatalf("operation = %q, want trim", audit.Operation)
+	}
+	if audit.InputFile != input {
+		t.Fatalf("input_file = %q, want %q", audit.InputFile, input)
+	}
+	if audit.OutputFile != output {
+		t.Fatalf("output_file = %q, want %q", audit.OutputFile, output)
+	}
+	if audit.InputSchema != config.OutputSchemaFull || audit.OutputSchema != config.OutputSchemaFull {
+		t.Fatalf("schemas = %q -> %q, want full -> full", audit.InputSchema, audit.OutputSchema)
+	}
+	if audit.Mode != "remove" {
+		t.Fatalf("mode = %q, want remove", audit.Mode)
+	}
+	if audit.Selector != "4,2" {
+		t.Fatalf("selector = %q, want %q", audit.Selector, "4,2")
+	}
+	assertIntSliceEqual(t, audit.SelectedIDs, []int{2, 4})
+	if audit.AllowEmpty {
+		t.Fatal("allow_empty should be false")
+	}
+	if audit.InputSegmentCount != 4 || audit.RetainedSegmentCount != 2 || audit.RemovedSegmentCount != 2 {
+		t.Fatalf("counts = input:%d retained:%d removed:%d, want 4/2/2", audit.InputSegmentCount, audit.RetainedSegmentCount, audit.RemovedSegmentCount)
+	}
+	assertIntSliceEqual(t, audit.RemovedInputIDs, []int{2, 4})
+	if len(audit.OldToNewIDMapping) != 2 {
+		t.Fatalf("mapping length = %d, want 2", len(audit.OldToNewIDMapping))
+	}
+	if audit.OldToNewIDMapping[0].OldID != 1 || audit.OldToNewIDMapping[0].NewID != 1 {
+		t.Fatalf("mapping[0] = %#v, want old_id=1 new_id=1", audit.OldToNewIDMapping[0])
+	}
+	if audit.OldToNewIDMapping[1].OldID != 3 || audit.OldToNewIDMapping[1].NewID != 2 {
+		t.Fatalf("mapping[1] = %#v, want old_id=3 new_id=2", audit.OldToNewIDMapping[1])
+	}
+	if !audit.OverlapGroupsRecomputed {
+		t.Fatal("expected overlap_groups_recomputed=true for full schema trim")
+	}
+}
+
+func TestTrimReportOldToNewMappingIsDeterministicSorted(t *testing.T) {
+	dir := t.TempDir()
+	input := writeTrimFullFixture(t, dir, "input.json")
+	output := filepath.Join(dir, "trimmed.json")
+	reportPath := filepath.Join(dir, "trim-report.json")
+
+	err := executeTrim(
+		"--input-file", input,
+		"--output-file", output,
+		"--report-file", reportPath,
+		"--keep", "4,1,3",
+	)
+	if err != nil {
+		t.Fatalf("trim failed: %v", err)
+	}
+
+	var rpt report.Report
+	readJSON(t, reportPath, &rpt)
+	audit := extractTrimAuditEvent(t, rpt)
+	if len(audit.OldToNewIDMapping) != 3 {
+		t.Fatalf("mapping length = %d, want 3", len(audit.OldToNewIDMapping))
+	}
+	for index, expectedOld := range []int{1, 3, 4} {
+		if audit.OldToNewIDMapping[index].OldID != expectedOld {
+			t.Fatalf("mapping[%d].old_id = %d, want %d", index, audit.OldToNewIDMapping[index].OldID, expectedOld)
+		}
+	}
+}
+
+func TestTrimNoReportFileWhenOmitted(t *testing.T) {
+	dir := t.TempDir()
+	input := writeTrimFullFixture(t, dir, "input.json")
+	output := filepath.Join(dir, "trimmed.json")
+	reportPath := filepath.Join(dir, "trim-report.json")
+
+	err := executeTrim(
+		"--input-file", input,
+		"--output-file", output,
+		"--keep", "1",
+	)
+	if err != nil {
+		t.Fatalf("trim failed: %v", err)
+	}
+
+	_, statErr := os.Stat(reportPath)
+	if !os.IsNotExist(statErr) {
+		t.Fatalf("expected no report file at %q, got err=%v", reportPath, statErr)
+	}
+}
+
 func executeTrim(args ...string) error {
 	cmd := NewRootCommand()
 	cmd.SetArgs(append([]string{"trim"}, args...))
@@ -299,3 +419,31 @@ func assertSequentialIDs(t *testing.T, ids []int) {
 		}
 	}
 }
+
+func extractTrimAuditEvent(t *testing.T, rpt report.Report) trimAuditReport {
+	t.Helper()
+
+	for _, event := range rpt.Events {
+		if event.Stage == "trim" && event.Module == "trim-audit" {
+			var audit trimAuditReport
+			if err := json.Unmarshal([]byte(event.Message), &audit); err != nil {
+				t.Fatalf("decode trim audit event: %v", err)
+			}
+			return audit
+		}
+	}
+	t.Fatal("missing trim-audit event")
+	return trimAuditReport{}
+}
+
+func assertIntSliceEqual(t *testing.T, got []int, want []int) {
+	t.Helper()
+	if len(got) != len(want) {
+		t.Fatalf("slice length = %d, want %d", len(got), len(want))
+	}
+	for index := range got {
+		if got[index] != want[index] {
+			t.Fatalf("slice[%d] = %d, want %d (full got=%v, want=%v)", index, got[index], want[index], got, want)
+		}
+	}
+}