Run normalization in process command

This commit is contained in:
2026-05-11 00:13:26 +00:00
parent 0b1b670baf
commit e2ae7f77d8
2 changed files with 206 additions and 28 deletions

View File

@@ -10,6 +10,7 @@ import (
"gitea.maximumdirect.net/eric/audita/internal/core/config"
"gitea.maximumdirect.net/eric/audita/internal/core/io"
"gitea.maximumdirect.net/eric/audita/internal/core/normalization"
"gitea.maximumdirect.net/eric/audita/internal/core/reporting"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
)
@@ -45,8 +46,8 @@ var processRunner = func(inv processInvocation, stdout io.Writer) error {
return fmt.Errorf("invalid glossary: %w", err)
}
// Convert to canonical transcript format for output
outputTranscript := &schema.Transcript{
// Convert to canonical transcript format for normalization
normalizedTranscript := &schema.Transcript{
Segments: make([]schema.Segment, len(transcript.Segments)),
}
for i, s := range transcript.Segments {
@@ -54,7 +55,7 @@ var processRunner = func(inv processInvocation, stdout io.Writer) error {
if s.ID != nil {
id = *s.ID
}
outputTranscript.Segments[i] = schema.Segment{
normalizedTranscript.Segments[i] = schema.Segment{
ID: id,
Speaker: s.Speaker,
Start: s.Start,
@@ -64,8 +65,18 @@ var processRunner = func(inv processInvocation, stdout io.Writer) error {
}
}
// Serialize output transcript to JSON
outputBytes, err := schema.TranscriptToJSON(outputTranscript)
// Apply deterministic normalization
normalizer := normalization.NewNormalizer(normalization.NormalizationConfig{
MaxSegmentGap: inv.Config.Normalization.MaxSegmentGap,
EllipsisGap: inv.Config.Normalization.EllipsisGap,
MaxSegmentDuration: inv.Config.Normalization.MaxSegmentDuration,
MaxSegmentTokens: inv.Config.Normalization.MaxSegmentTokens,
})
normalizedTranscript, _ = normalizer.Normalize(normalizedTranscript)
// Serialize normalized transcript to JSON
outputBytes, err := schema.TranscriptToJSON(normalizedTranscript)
if err != nil {
return fmt.Errorf("failed to serialize transcript: %w", err)
}

View File

@@ -507,35 +507,202 @@ func TestRunProcessEmptyStdoutWithOutput(t *testing.T) {
}
}
func TestRunProcessReportJSONOnParseFailure(t *testing.T) {
func TestRunProcessNormalizationMergeInOutput(t *testing.T) {
var stdout bytes.Buffer
var stderr bytes.Buffer
reportPath := filepath.Join(t.TempDir(), "report.json")
exitCode := Run([]string{
"process",
fixturePath("transcript_empty_speaker.json"),
"--glossary",
fixturePath("tiny_glossary.yaml"),
"--report-json",
reportPath,
}, &stdout, &stderr)
if exitCode == 0 {
t.Fatalf("expected nonzero exit code for parse failure")
}
if stdout.Len() != 0 {
t.Fatalf("expected empty stdout on failure, got %q", stdout.String())
// Create a test transcript with segments that should be merged
transcriptJSON := `[
{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"},
{"id": 2, "speaker": "Alice", "start": 1.5, "end": 2.5, "text": "world"}
]`
transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
glossaryPath := fixturePath("tiny_glossary.yaml")
outputPath := filepath.Join(t.TempDir(), "corrected.json")
if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
t.Fatalf("failed to create test transcript: %v", err)
}
// Report should still be written on parse failure
report := readProcessReport(t, reportPath)
if report.Status != "failed" {
t.Fatalf("expected failed report status, got %q", report.Status)
exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--output", outputPath}, &stdout, &stderr)
if exitCode != 0 {
t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
}
if report.ErrorMessage == "" {
t.Fatalf("expected error message in failed report")
if stdout.Len() != 0 {
t.Fatalf("expected empty stdout when --output is used, got %q", stdout.String())
}
if !strings.Contains(report.ErrorMessage, "invalid transcript:") {
t.Fatalf("expected invalid transcript error in report, got %q", report.ErrorMessage)
if stderr.Len() != 0 {
t.Fatalf("expected empty stderr on success, got %q", stderr.String())
}
// Read and parse the output
outputBytes := readFile(t, outputPath)
var outputTranscript schema.Transcript
if err := schema.ParseTranscriptJSON(outputBytes); err != nil {
t.Fatalf("failed to parse output transcript: %v (output: %s)", err, string(outputBytes))
}
// Should have merged the two segments into one
if len(outputTranscript.Segments) != 1 {
t.Fatalf("expected 1 merged segment, got %d segments", len(outputTranscript.Segments))
}
// Should have sequential ID starting at 1
if outputTranscript.Segments[0].ID != 1 {
t.Fatalf("expected segment ID 1, got %d", outputTranscript.Segments[0].ID)
}
// Should contain merged text
if !strings.Contains(outputTranscript.Segments[0].Text, "Hello") || !strings.Contains(outputTranscript.Segments[0].Text, "world") {
t.Fatalf("expected merged text to contain both parts, got %q", outputTranscript.Segments[0].Text)
}
}
func TestRunProcessNormalizedOutputToStdout(t *testing.T) {
var stdout bytes.Buffer
var stderr bytes.Buffer
transcriptJSON := `[
{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"},
{"id": 2, "speaker": "Alice", "start": 1.5, "end": 2.5, "text": "world"}
]`
transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
glossaryPath := fixturePath("tiny_glossary.yaml")
if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
t.Fatalf("failed to create test transcript: %v", err)
}
exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath}, &stdout, &stderr)
if exitCode != 0 {
t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
}
if stderr.Len() != 0 {
t.Fatalf("expected empty stderr on success, got %q", stderr.String())
}
// Should have normalized output in stdout
if stdout.Len() == 0 {
t.Fatalf("expected normalized transcript in stdout, got empty stdout")
}
// Should be valid JSON
if !json.Valid(stdout.Bytes()) {
t.Fatalf("expected valid JSON in stdout, got %q", stdout.String())
}
// Parse and verify it's normalized (merged)
var outputTranscript schema.Transcript
if err := schema.ParseTranscriptJSON(stdout.Bytes()); err != nil {
t.Fatalf("failed to parse stdout transcript: %v", err)
}
if len(outputTranscript.Segments) != 1 {
t.Fatalf("expected 1 merged segment in stdout, got %d", len(outputTranscript.Segments))
}
}
func TestRunProcessSequentialIDsInOutput(t *testing.T) {
var stdout bytes.Buffer
var stderr bytes.Buffer
transcriptJSON := `[
{"id": 5, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"},
{"id": 10, "speaker": "Bob", "start": 2.0, "end": 3.0, "text": "Hi"}
]`
transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
glossaryPath := fixturePath("tiny_glossary.yaml")
if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
t.Fatalf("failed to create test transcript: %v", err)
}
exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath}, &stdout, &stderr)
if exitCode != 0 {
t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
}
// Parse output and verify sequential IDs
var outputTranscript schema.Transcript
if err := schema.ParseTranscriptJSON(stdout.Bytes()); err != nil {
t.Fatalf("failed to parse output transcript: %v", err)
}
// Should have sequential IDs starting at 1
for i, segment := range outputTranscript.Segments {
expectedID := i + 1
if segment.ID != expectedID {
t.Fatalf("expected segment %d to have ID %d, got %d", i, expectedID, segment.ID)
}
}
}
func TestRunProcessNoStdoutWithOutput(t *testing.T) {
var stdout bytes.Buffer
var stderr bytes.Buffer
transcriptJSON := `[
{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"}
]`
transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
glossaryPath := fixturePath("tiny_glossary.yaml")
outputPath := filepath.Join(t.TempDir(), "corrected.json")
if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
t.Fatalf("failed to create test transcript: %v", err)
}
exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--output", outputPath}, &stdout, &stderr)
if exitCode != 0 {
t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
}
if stdout.Len() != 0 {
t.Fatalf("expected empty stdout when --output is used, got %q", stdout.String())
}
if stderr.Len() != 0 {
t.Fatalf("expected empty stderr on success, got %q", stderr.String())
}
// Verify output file exists and is valid
if _, err := os.Stat(outputPath); err != nil {
t.Fatalf("expected output file to be created: %v", err)
}
}
func TestRunProcessNormalizationConfigOverride(t *testing.T) {
var stdout bytes.Buffer
var stderr bytes.Buffer
// Create segments that would normally merge but set very small max gap
transcriptJSON := `[
{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"},
{"id": 2, "speaker": "Alice", "start": 1.5, "end": 2.5, "text": "world"}
]`
transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
glossaryPath := fixturePath("tiny_glossary.yaml")
if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
t.Fatalf("failed to create test transcript: %v", err)
}
// Set max segment gap to 0.1 (smaller than the 0.5 gap between segments)
exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--normalize-max-segment-gap", "0.1"}, &stdout, &stderr)
if exitCode != 0 {
t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
}
// Should NOT merge due to small max gap setting
var outputTranscript schema.Transcript
if err := schema.ParseTranscriptJSON(stdout.Bytes()); err != nil {
t.Fatalf("failed to parse output transcript: %v", err)
}
if len(outputTranscript.Segments) != 2 {
t.Fatalf("expected 2 unmerged segments due to small max gap, got %d", len(outputTranscript.Segments))
}
}