seriatim/internal/cli/trim_test.go

package cli

import (
	"encoding/json"
	"os"
	"path/filepath"
	"strings"
	"testing"

	"gitea.maximumdirect.net/eric/seriatim/internal/config"
	"gitea.maximumdirect.net/eric/seriatim/internal/report"
	"gitea.maximumdirect.net/eric/seriatim/schema"
)

func TestTrimKeepModeEndToEnd(t *testing.T) {
	dir := t.TempDir()
	input := writeTrimFullFixture(t, dir, "input.json")
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--keep", "2,4",
	)
	if err != nil {
		t.Fatalf("trim failed: %v", err)
	}

	var transcript schema.Transcript
	readJSON(t, output, &transcript)
	if len(transcript.Segments) != 2 {
		t.Fatalf("segment count = %d, want 2", len(transcript.Segments))
	}
	if transcript.Segments[0].Text != "two" || transcript.Segments[1].Text != "four" {
		t.Fatalf("unexpected kept text order: %#v", transcript.Segments)
	}
	assertSequentialIDs(t, []int{transcript.Segments[0].ID, transcript.Segments[1].ID})
}

func TestTrimRemoveModeEndToEnd(t *testing.T) {
	dir := t.TempDir()
	input := writeTrimFullFixture(t, dir, "input.json")
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--remove", "2,4",
	)
	if err != nil {
		t.Fatalf("trim failed: %v", err)
	}

	var transcript schema.Transcript
	readJSON(t, output, &transcript)
	if len(transcript.Segments) != 2 {
		t.Fatalf("segment count = %d, want 2", len(transcript.Segments))
	}
	if transcript.Segments[0].Text != "one" || transcript.Segments[1].Text != "three" {
		t.Fatalf("unexpected remaining text order: %#v", transcript.Segments)
	}
	assertSequentialIDs(t, []int{transcript.Segments[0].ID, transcript.Segments[1].ID})
}

func TestTrimMutualExclusionFailure(t *testing.T) {
	dir := t.TempDir()
	input := writeTrimFullFixture(t, dir, "input.json")
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--keep", "1",
		"--remove", "2",
	)
	if err == nil {
		t.Fatal("expected mutual exclusion error")
	}
	if !strings.Contains(err.Error(), "mutually exclusive") {
		t.Fatalf("unexpected error: %v", err)
	}
}

func TestTrimMissingSelectionFailure(t *testing.T) {
	dir := t.TempDir()
	input := writeTrimFullFixture(t, dir, "input.json")
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
	)
	if err == nil {
		t.Fatal("expected selection flag error")
	}
	if !strings.Contains(err.Error(), "exactly one of --keep or --remove is required") {
		t.Fatalf("unexpected error: %v", err)
	}
}

func TestTrimInvalidSelectedIDFailure(t *testing.T) {
	dir := t.TempDir()
	input := writeTrimFullFixture(t, dir, "input.json")
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--keep", "99",
	)
	if err == nil {
		t.Fatal("expected missing selected ID error")
	}
	if !strings.Contains(err.Error(), "does not exist") {
		t.Fatalf("unexpected error: %v", err)
	}
}

func TestTrimOmittedOutputSchemaPreservesInputSchema(t *testing.T) {
	dir := t.TempDir()
	input := writeTrimMinimalFixture(t, dir, "input-minimal.json")
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--keep", "1",
	)
	if err != nil {
		t.Fatalf("trim failed: %v", err)
	}

	var transcript schema.MinimalTranscript
	readJSON(t, output, &transcript)
	if transcript.Metadata.OutputSchema != config.OutputSchemaMinimal {
		t.Fatalf("output_schema = %q, want %q", transcript.Metadata.OutputSchema, config.OutputSchemaMinimal)
	}
	if len(transcript.Segments) != 1 || transcript.Segments[0].ID != 1 {
		t.Fatalf("unexpected minimal trim output: %#v", transcript.Segments)
	}
}

func TestTrimExplicitOutputSchemaChangesOutputSchema(t *testing.T) {
	dir := t.TempDir()
	input := writeTrimFullFixture(t, dir, "input.json")
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--keep", "1,3",
		"--output-schema", config.OutputSchemaMinimal,
	)
	if err != nil {
		t.Fatalf("trim failed: %v", err)
	}

	var transcript schema.MinimalTranscript
	readJSON(t, output, &transcript)
	if transcript.Metadata.OutputSchema != config.OutputSchemaMinimal {
		t.Fatalf("output_schema = %q, want %q", transcript.Metadata.OutputSchema, config.OutputSchemaMinimal)
	}
	if len(transcript.Segments) != 2 {
		t.Fatalf("segment count = %d, want 2", len(transcript.Segments))
	}
	assertSequentialIDs(t, []int{transcript.Segments[0].ID, transcript.Segments[1].ID})
}

func TestTrimAllowEmptyBehavior(t *testing.T) {
	dir := t.TempDir()
	input := writeTrimFullFixture(t, dir, "input.json")
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--remove", "1-4",
	)
	if err == nil {
		t.Fatal("expected empty-output error")
	}
	if !strings.Contains(err.Error(), "empty transcript") {
		t.Fatalf("unexpected error: %v", err)
	}

	err = executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--remove", "1-4",
		"--allow-empty",
	)
	if err != nil {
		t.Fatalf("trim with --allow-empty failed: %v", err)
	}

	var transcript schema.Transcript
	readJSON(t, output, &transcript)
	if len(transcript.Segments) != 0 {
		t.Fatalf("segment count = %d, want 0", len(transcript.Segments))
	}
}

func TestTrimRejectsNonSeriatimInputArtifacts(t *testing.T) {
	dir := t.TempDir()
	input := writeJSONFile(t, dir, "raw-whisperx.json", `{
		"segments": [
			{"start": 1, "end": 2, "text": "hello"}
		]
	}`)
	output := filepath.Join(dir, "trimmed.json")

	err := executeTrim(
		"--input-file", input,
		"--output-file", output,
		"--keep", "1",
	)
	if err == nil {
		t.Fatal("expected invalid artifact error")
	}
	if !strings.Contains(err.Error(), "not a valid seriatim output artifact") {
		t.Fatalf("unexpected error: %v", err)
	}
}

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...))
	return cmd.Execute()
}

func writeTrimFullFixture(t *testing.T, dir string, name string) string {
	t.Helper()

	first := 10
	second := 20
	third := 30
	fourth := 40
	value := schema.Transcript{
		Metadata: schema.Metadata{
			Application:           "seriatim",
			Version:               "v-test",
			InputReader:           "json-files",
			InputFiles:            []string{"a.json"},
			PreprocessingModules:  []string{"validate-raw"},
			PostprocessingModules: []string{"assign-ids"},
			OutputModules:         []string{"json"},
		},
		Segments: []schema.Segment{
			{ID: 1, Source: "a.json", SourceSegmentIndex: &first, SourceRef: "a.json#10", Speaker: "A", Start: 1, End: 2, Text: "one", OverlapGroupID: 9},
			{ID: 2, Source: "a.json", SourceSegmentIndex: &second, SourceRef: "a.json#20", Speaker: "B", Start: 2, End: 3, Text: "two", OverlapGroupID: 9},
			{ID: 3, Source: "a.json", SourceSegmentIndex: &third, SourceRef: "a.json#30", Speaker: "C", Start: 4, End: 5, Text: "three", OverlapGroupID: 10},
			{ID: 4, Source: "a.json", SourceSegmentIndex: &fourth, SourceRef: "a.json#40", Speaker: "D", Start: 5, End: 6, Text: "four", OverlapGroupID: 10},
		},
		OverlapGroups: []schema.OverlapGroup{
			{ID: 9, Start: 1, End: 3, Segments: []string{"a.json#10", "a.json#20"}, Speakers: []string{"A", "B"}, Class: "unknown", Resolution: "unresolved"},
		},
	}

	return writeTrimArtifactFile(t, dir, name, value)
}

func writeTrimMinimalFixture(t *testing.T, dir string, name string) string {
	t.Helper()

	value := schema.MinimalTranscript{
		Metadata: schema.MinimalMetadata{
			Application:  "seriatim",
			Version:      "v-test",
			OutputSchema: config.OutputSchemaMinimal,
		},
		Segments: []schema.MinimalSegment{
			{ID: 1, Start: 1, End: 2, Speaker: "A", Text: "one"},
			{ID: 2, Start: 2, End: 3, Speaker: "B", Text: "two"},
		},
	}

	return writeTrimArtifactFile(t, dir, name, value)
}

func writeTrimArtifactFile(t *testing.T, dir string, name string, value any) string {
	t.Helper()

	data, err := json.MarshalIndent(value, "", "  ")
	if err != nil {
		t.Fatalf("marshal fixture: %v", err)
	}
	path := filepath.Join(dir, name)
	if err := os.WriteFile(path, append(data, '\n'), 0o600); err != nil {
		t.Fatalf("write fixture: %v", err)
	}
	return path
}

func assertSequentialIDs(t *testing.T, ids []int) {
	t.Helper()
	for index, id := range ids {
		want := index + 1
		if id != want {
			t.Fatalf("id at index %d = %d, want %d", index, id, want)
		}
	}
}

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)
		}
	}
}