tapir/internal/web/uploads_language_handler_test.go

package web_test

// The language of a recording is chosen on the upload form (tapir#61). These drive the real
// Router, Intake and Postgres store; the submitter is the process boundary and records the
// job the worker would receive.

import (
	"bytes"
	"context"
	"mime/multipart"
	"net/http"
	"net/http/httptest"
	"strings"
	"testing"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"

	"git.d-ma.be/mathias/tapir/internal/domain"
)

// langReq builds an upload whose parts come in the order given: "title", "language" and
// "file" (the file part always carries the same synthetic bytes).
func langReq(t *testing.T, order []string, language string) *http.Request {
	t.Helper()
	var buf bytes.Buffer
	mw := multipart.NewWriter(&buf)
	for _, part := range order {
		switch part {
		case "title":
			require.NoError(t, mw.WriteField("title", "m"))
		case "language":
			require.NoError(t, mw.WriteField("language", language))
		case "file":
			fw, err := mw.CreateFormFile("file", "m.wav")
			require.NoError(t, err)
			_, err = fw.Write([]byte("RIFF....WAVE"))
			require.NoError(t, err)
		}
	}
	require.NoError(t, mw.Close())
	req := httptest.NewRequest(http.MethodPost, "/uploads", &buf)
	req.Header.Set("Content-Type", mw.FormDataContentType())
	return req
}

func rowLanguage(t *testing.T, location string) domain.Language {
	t.Helper()
	id := strings.TrimPrefix(location, "/uploads/")
	got, err := newStore(t).GetUpload(context.Background(), userID, id)
	require.NoError(t, err)
	return got.Language
}

func TestUploadPost_TheLanguageFieldReachesTheJobAndTheRow(t *testing.T) {
	for _, tt := range []struct {
		name     string
		language string
		want     domain.Language
	}{
		{"other", "auto", domain.LangAuto},
		{"swedish", "sv", domain.LangSwedish},
	} {
		t.Run(tt.name, func(t *testing.T) {
			app, sub := newUploadApp(t, audioOK, 200<<20)

			rec := do(t, app, langReq(t, []string{"title", "language", "file"}, tt.language))

			require.Equal(t, http.StatusSeeOther, rec.Code)
			require.Len(t, sub.jobs, 1)
			assert.Equal(t, tt.want, sub.jobs[0].Language)
			assert.Equal(t, tt.want, rowLanguage(t, rec.Header().Get("Location")))
		})
	}
}

func TestUploadPost_NoLanguageFieldIsSwedishAsBefore(t *testing.T) {
	app, sub := newUploadApp(t, audioOK, 200<<20)

	rec := do(t, app, langReq(t, []string{"title", "file"}, ""))

	require.Equal(t, http.StatusSeeOther, rec.Code)
	require.Len(t, sub.jobs, 1)
	assert.Equal(t, domain.LangSwedish, sub.jobs[0].Language)
	assert.Equal(t, domain.LangSwedish, rowLanguage(t, rec.Header().Get("Location")))
}

// A part after the file is never read (the file part ends the stream), so a client that
// orders its fields wrongly gets Swedish, the old behaviour, not a guess.
func TestUploadPost_ALanguageFieldAfterTheFileIsNotReadAndTheUploadIsSwedish(t *testing.T) {
	app, sub := newUploadApp(t, audioOK, 200<<20)

	rec := do(t, app, langReq(t, []string{"title", "file", "language"}, "auto"))

	require.Equal(t, http.StatusSeeOther, rec.Code)
	require.Len(t, sub.jobs, 1)
	assert.Equal(t, domain.LangSwedish, sub.jobs[0].Language)
}

func TestUploadPost_ALanguageOutsideTheClosedSetIsRefusedBeforeAnythingIsSpooledOrStored(t *testing.T) {
	for _, bad := range []string{"en", "SV", " sv", "sv,auto", "../auto", strings.Repeat("a", 5000)} {
		t.Run(bad[:min(len(bad), 12)], func(t *testing.T) {
			app, sub := newUploadApp(t, audioOK, 200<<20)

			rec := do(t, app, langReq(t, []string{"title", "language", "file"}, bad))

			assert.Equal(t, http.StatusBadRequest, rec.Code)
			assert.Empty(t, sub.jobs, "a refused post must not enqueue transcription")
			rows, err := newStore(t).ListUploads(context.Background(), userID)
			require.NoError(t, err)
			assert.Empty(t, rows, "and must leave no row")
			assert.Contains(t, body(t, rec), "Choose a language from the list.")
		})
	}
}

func TestUploadPage_TheFormOffersSwedishPreselectedAndOtherBeforeTheFilePart(t *testing.T) {
	app, _ := newUploadApp(t, audioOK, 200<<20)

	b := body(t, do(t, app, get("/uploads")))

	sel := strings.Index(b, `name="language"`)
	file := strings.Index(b, `name="file"`)
	require.True(t, sel >= 0, "the form has a language field")
	assert.True(t, sel < file, "the field must come before the file part: the stream ends at the file")
	assert.Regexp(t, `<option value="sv" selected`, b, "Swedish is preselected: today's behaviour")
	assert.Contains(t, b, `<option value="auto"`)
}

func TestUploadPage_NamesTheLanguageInEveryState(t *testing.T) {
	for _, status := range []string{"queued", "transcribing", "done", "failed"} {
		for _, tt := range []struct {
			language domain.Language
			want     string
		}{
			{domain.LangSwedish, "Swedish"},
			{domain.LangAuto, "Other (detected by the engine)"},
		} {
			t.Run(status+"/"+string(tt.language), func(t *testing.T) {
				app, _ := newUploadApp(t, audioOK, 200<<20)
				id := seedUpload(t, userID, "m", status, "Synthetic transcript text.")
				_, err := rawPool(t).Exec(context.Background(), `UPDATE uploaded_transcripts SET language = $2 WHERE id = $1`, id, string(tt.language))
				require.NoError(t, err)

				b := body(t, do(t, app, get("/uploads/"+id)))

				assert.Contains(t, b, "Language: "+tt.want)
			})
		}
	}
}