From 8e4872d2e7094a31e9f5d25d24f01bbeb8d0781f Mon Sep 17 00:00:00 2001
From: Mathias <mthbqv@gmail.com>
Date: Sun, 4 Oct 2026 22:25:51 +0200
Subject: [PATCH] feat(domain): Language, a closed set carried to the engines
 on the context (#61)

sv and auto; an empty form value is sv, anything else is refused. LanguageFrom defaults to
sv so a caller that sets nothing behaves as before.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
---
 internal/domain/language.go      | 47 ++++++++++++++++++++++++++++++++
 internal/domain/language_test.go | 41 ++++++++++++++++++++++++++++
 2 files changed, 88 insertions(+)
 create mode 100644 internal/domain/language.go
 create mode 100644 internal/domain/language_test.go

diff --git a/internal/domain/language.go b/internal/domain/language.go
new file mode 100644
index 0000000..def4f07
--- /dev/null
+++ b/internal/domain/language.go
@@ -0,0 +1,47 @@
+package domain
+
+import "context"
+
+// Language is the spoken language an upload is transcribed as. It is chosen by the user on
+// the upload form and reaches the engines as one request field, so it is a closed set,
+// never free text (tapir#61).
+type Language string
+
+const (
+	// LangSwedish sends language=sv: the Swedish engines' own language, and what every
+	// upload was transcribed as before the choice existed.
+	LangSwedish Language = "sv"
+	// LangAuto sends no language, so the engine detects it. It is what "Other" on the form
+	// means: the Swedish-only engines are not used for it.
+	LangAuto Language = "auto"
+)
+
+// ParseLanguage reads a form value. An empty value is Swedish (a client that predates the
+// field); anything that is not exactly a known value is refused rather than normalised.
+func ParseLanguage(s string) (Language, bool) {
+	switch Language(s) {
+	case "", LangSwedish:
+		return LangSwedish, true
+	case LangAuto:
+		return LangAuto, true
+	}
+	return "", false
+}
+
+type languageKey struct{}
+
+// WithLanguage returns a context that carries the language of the job it serves. The
+// Transcriber interface does not change: engines read it with LanguageFrom, the same way
+// they read the progress Reporter (ADR-035).
+func WithLanguage(ctx context.Context, l Language) context.Context {
+	return context.WithValue(ctx, languageKey{}, l)
+}
+
+// LanguageFrom returns the language carried by ctx, or Swedish when it carries none, so a
+// caller that sets nothing behaves as it always did.
+func LanguageFrom(ctx context.Context) Language {
+	if l, ok := ctx.Value(languageKey{}).(Language); ok && l != "" {
+		return l
+	}
+	return LangSwedish
+}
diff --git a/internal/domain/language_test.go b/internal/domain/language_test.go
new file mode 100644
index 0000000..ba5db04
--- /dev/null
+++ b/internal/domain/language_test.go
@@ -0,0 +1,41 @@
+package domain_test
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"git.d-ma.be/mathias/tapir/internal/domain"
+)
+
+func TestParseLanguage_KnownValuesAndEmptyAreAcceptedEverythingElseIsNot(t *testing.T) {
+	tests := []struct {
+		in     string
+		want   domain.Language
+		wantOK bool
+	}{
+		{"sv", domain.LangSwedish, true},
+		{"auto", domain.LangAuto, true},
+		{"", domain.LangSwedish, true}, // a client that sends no field keeps today's behaviour
+		{"SV", "", false},              // exact match: the value reaches a request field
+		{" sv", "", false},
+		{"sv\n", "", false},
+		{"en", "", false}, // a specific other language is not offered yet
+		{"sv,en", "", false},
+		{"../sv", "", false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.in, func(t *testing.T) {
+			got, ok := domain.ParseLanguage(tt.in)
+			assert.Equal(t, tt.wantOK, ok)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func TestLanguageFrom_IsSwedishWhenTheContextCarriesNoneAndOtherwiseWhatWasSet(t *testing.T) {
+	assert.Equal(t, domain.LangSwedish, domain.LanguageFrom(context.Background()))
+	ctx := domain.WithLanguage(context.Background(), domain.LangAuto)
+	assert.Equal(t, domain.LangAuto, domain.LanguageFrom(ctx))
+}