Add transcript passthrough processing

internal/cli/run.go

@@ -8,10 +8,9 @@ import (
 	"strings"
 
 	"gitea.maximumdirect.net/eric/audita/internal/core/config"
+	coreio "gitea.maximumdirect.net/eric/audita/internal/core/io"
 )
 
-const processNotImplementedMessage = "process command is not implemented yet"
-
 type processInvocation struct {
 	TranscriptPath string
 	GlossaryPath   string
@@ -20,9 +19,29 @@ type processInvocation struct {
 	Config         config.Config
 }
 
-var processRunner = func(inv processInvocation) error {
-	_ = inv
-	return errors.New(processNotImplementedMessage)
+var processRunner = func(inv processInvocation, stdout io.Writer) error {
+	transcriptBytes, err := coreio.ReadRequiredFile(inv.TranscriptPath, "transcript")
+	if err != nil {
+		return err
+	}
+	if err := coreio.ValidateWellFormedJSON(transcriptBytes); err != nil {
+		return err
+	}
+	if _, err := coreio.ReadRequiredFile(inv.GlossaryPath, "glossary"); err != nil {
+		return err
+	}
+
+	if strings.TrimSpace(inv.OutputPath) != "" {
+		if err := coreio.WriteFile(inv.OutputPath, transcriptBytes); err != nil {
+			return err
+		}
+		return nil
+	}
+
+	if _, err := stdout.Write(transcriptBytes); err != nil {
+		return fmt.Errorf("failed to write transcript to stdout: %w", err)
+	}
+	return nil
 }
 
 // Run executes the Audita CLI with the provided arguments and streams.
@@ -162,7 +181,7 @@ func runProcess(args []string, stdout, stderr io.Writer) int {
 		Config:         cfg,
 	}
 
-	if err := processRunner(inv); err != nil {
+	if err := processRunner(inv, stdout); err != nil {
 		fmt.Fprintf(stderr, "audita process: %v\n", err)
 		return 1
 	}

internal/cli/run_test.go

@@ -2,7 +2,11 @@ package cli
 
 import (
 	"bytes"
-	"errors"
+	"encoding/json"
+	"io"
+	"os"
+	"path/filepath"
+	"reflect"
 	"strings"
 	"testing"
 )
@@ -96,7 +100,7 @@ func TestRunProcessMissingTranscriptPath(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
 
-	exitCode := Run([]string{"process", "--glossary", "glossary.yaml"}, &stdout, &stderr)
+	exitCode := Run([]string{"process", "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
 	if exitCode == 0 {
 		t.Fatalf("expected nonzero exit code")
 	}
@@ -112,7 +116,7 @@ func TestRunProcessMissingGlossary(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
 
-	exitCode := Run([]string{"process", "transcript.json"}, &stdout, &stderr)
+	exitCode := Run([]string{"process", fixturePath("tiny_transcript.json")}, &stdout, &stderr)
 	if exitCode == 0 {
 		t.Fatalf("expected nonzero exit code")
 	}
@@ -124,38 +128,82 @@ func TestRunProcessMissingGlossary(t *testing.T) {
 	}
 }
 
-func TestRunProcessInvalidCLIConfig(t *testing.T) {
+func TestRunProcessUnreadableTranscript(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
 
-	exitCode := Run([]string{"process", "transcript.json", "--glossary", "glossary.yaml", "--work-dir-retention", "invalid"}, &stdout, &stderr)
-	if exitCode != 2 {
-		t.Fatalf("expected exit code 2, got %d", exitCode)
+	missingTranscript := filepath.Join(t.TempDir(), "missing.json")
+	exitCode := Run([]string{"process", missingTranscript, "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
+	if exitCode == 0 {
+		t.Fatalf("expected nonzero exit code")
 	}
 	if stdout.Len() != 0 {
 		t.Fatalf("expected empty stdout, got %q", stdout.String())
 	}
-	if !strings.Contains(stderr.String(), "invalid CLI configuration") {
-		t.Fatalf("expected invalid config error, got %q", stderr.String())
+	if !strings.Contains(stderr.String(), "failed to read transcript file") {
+		t.Fatalf("expected unreadable transcript error, got %q", stderr.String())
 	}
 }
 
-func TestRunProcessNotImplemented(t *testing.T) {
+func TestRunProcessMalformedTranscriptJSON(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
 
-	exitCode := Run([]string{"process", "transcript.json", "--glossary", "glossary.yaml"}, &stdout, &stderr)
-	if exitCode != 1 {
-		t.Fatalf("expected exit code 1 for not-implemented process, got %d", exitCode)
+	exitCode := Run([]string{"process", fixturePath("malformed_transcript.json"), "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
+	if exitCode == 0 {
+		t.Fatalf("expected nonzero exit code")
 	}
 	if stdout.Len() != 0 {
 		t.Fatalf("expected empty stdout, got %q", stdout.String())
 	}
-	if !strings.Contains(stderr.String(), processNotImplementedMessage) {
-		t.Fatalf("expected not-implemented message in stderr, got %q", stderr.String())
+	if !strings.Contains(stderr.String(), "transcript file is not valid JSON") {
+		t.Fatalf("expected malformed transcript error, got %q", stderr.String())
 	}
 }
 
+func TestRunProcessOutputToFile(t *testing.T) {
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	transcriptPath := fixturePath("tiny_transcript.json")
+	glossaryPath := fixturePath("tiny_glossary.yaml")
+	outputPath := filepath.Join(t.TempDir(), "corrected.json")
+
+	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())
+	}
+
+	inputBytes := readFile(t, transcriptPath)
+	outputBytes := readFile(t, outputPath)
+	assertJSONSemanticallyEqual(t, inputBytes, outputBytes)
+}
+
+func TestRunProcessOutputToStdout(t *testing.T) {
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	transcriptPath := fixturePath("tiny_transcript.json")
+	glossaryPath := fixturePath("tiny_glossary.yaml")
+
+	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())
+	}
+
+	inputBytes := readFile(t, transcriptPath)
+	assertJSONSemanticallyEqual(t, inputBytes, stdout.Bytes())
+}
+
 func TestRunProcessCLIOverridesEnvironment(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
@@ -163,11 +211,15 @@ func TestRunProcessCLIOverridesEnvironment(t *testing.T) {
 	t.Setenv("AUDITA_MODEL", "env-model")
 	t.Setenv("AUDITA_VALIDATION_LLM_CONCURRENCY", "2")
 
+	transcriptPath := fixturePath("tiny_transcript.json")
+	glossaryPath := fixturePath("tiny_glossary.yaml")
+
 	var captured processInvocation
 	originalRunner := processRunner
-	processRunner = func(inv processInvocation) error {
+	processRunner = func(inv processInvocation, output io.Writer) error {
+		_ = output
 		captured = inv
-		return errors.New(processNotImplementedMessage)
+		return nil
 	}
 	t.Cleanup(func() {
 		processRunner = originalRunner
@@ -175,17 +227,17 @@ func TestRunProcessCLIOverridesEnvironment(t *testing.T) {
 
 	exitCode := Run([]string{
 		"process",
-		"transcript.json",
+		transcriptPath,
 		"--glossary",
-		"glossary.yaml",
+		glossaryPath,
 		"--model",
 		"cli-model",
 		"--validation-llm-concurrency",
 		"5",
 	}, &stdout, &stderr)
 
-	if exitCode != 1 {
-		t.Fatalf("expected exit code 1 for not implemented, got %d", exitCode)
+	if exitCode != 0 {
+		t.Fatalf("expected exit code 0, got %d", exitCode)
 	}
 	if captured.Config.PrimaryLLM.Model != "cli-model" {
 		t.Fatalf("expected CLI model override, got %q", captured.Config.PrimaryLLM.Model)
@@ -193,7 +245,39 @@ func TestRunProcessCLIOverridesEnvironment(t *testing.T) {
 	if captured.Config.ValidationLLM.Concurrency == nil || *captured.Config.ValidationLLM.Concurrency != 5 {
 		t.Fatalf("expected CLI validation concurrency override, got %#v", captured.Config.ValidationLLM.Concurrency)
 	}
-	if captured.GlossaryPath != "glossary.yaml" {
+	if captured.GlossaryPath != glossaryPath {
 		t.Fatalf("unexpected glossary path: %q", captured.GlossaryPath)
 	}
 }
+
+func fixturePath(name string) string {
+	return filepath.Join("testdata", name)
+}
+
+func readFile(t *testing.T, path string) []byte {
+	t.Helper()
+	data, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("failed to read file %q: %v", path, err)
+	}
+	return data
+}
+
+func assertJSONSemanticallyEqual(t *testing.T, expected []byte, actual []byte) {
+	t.Helper()
+	if !json.Valid(actual) {
+		t.Fatalf("actual output is not valid JSON: %q", string(actual))
+	}
+
+	var expectedValue any
+	var actualValue any
+	if err := json.Unmarshal(expected, &expectedValue); err != nil {
+		t.Fatalf("failed to unmarshal expected JSON: %v", err)
+	}
+	if err := json.Unmarshal(actual, &actualValue); err != nil {
+		t.Fatalf("failed to unmarshal actual JSON: %v", err)
+	}
+	if !reflect.DeepEqual(expectedValue, actualValue) {
+		t.Fatalf("JSON content mismatch: expected %q got %q", string(expected), string(actual))
+	}
+}

internal/cli/testdata/malformed_transcript.json

@@ -0,0 +1 @@
+{"segments":[{"id":1,"text":"oops"}

internal/cli/testdata/tiny_glossary.yaml

@@ -0,0 +1,3 @@
+terms:
+  - source: audita
+    target: Audita

internal/cli/testdata/tiny_transcript.json

@@ -0,0 +1,9 @@
+[
+  {
+    "id": 1,
+    "speaker": "A",
+    "start": 0.0,
+    "end": 1.2,
+    "text": "hello world"
+  }
+]

internal/core/io/files.go

@@ -0,0 +1,29 @@
+package io
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+)
+
+func ReadRequiredFile(path string, label string) ([]byte, error) {
+	contents, err := os.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read %s file %q: %w", label, path, err)
+	}
+	return contents, nil
+}
+
+func ValidateWellFormedJSON(raw []byte) error {
+	if !json.Valid(raw) {
+		return fmt.Errorf("transcript file is not valid JSON")
+	}
+	return nil
+}
+
+func WriteFile(path string, contents []byte) error {
+	if err := os.WriteFile(path, contents, 0o644); err != nil {
+		return fmt.Errorf("failed to write output file %q: %w", path, err)
+	}
+	return nil
+}