mathias
4a2067063d
Upload a recording (audio, or video with the camera off), get a private Swedish transcript, and chat about it. - ADR-033: RLS-scoped private transcript store; ffprobe/ffmpeg intake; gateway transcription (iguana kb-whisper, berget fallback); in-process single-replica worker; chat over the transcript (local models only). - ADR-034: optional two-engine mode (pianissimo + kb-whisper) reconciled by a LOCAL model; off unless TAPIR_RECONCILE_BASE_MODEL is set. - ADR-035: real progress (phases, running/quiet/lost), phase logging, every judged spot stored, merged segments. - Hardening from four adversarial reviews: errors logged and stored as kinds never text; per-engine deadlines; converted-length check; bounded queue; client hang-ups are not errors; strict local-alias check. - Dockerfile: static ffmpeg/ffprobe 7.0.2 pinned by sha256 (#34). Built and inspected by hand; CI does not build the image on a PR, so its first CI build is this merge. Uploads stay OFF until TAPIR_UPLOADS_ENABLED is set in the deployment. Closes #33, #34, #42, #43, #44. Co-authored-by: Mathias <mthbqv@gmail.com>
73 lines
3.3 KiB
Go
73 lines
3.3 KiB
Go
package web_test
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
// The stored judged spots include the ones the model kept as the base (ADR-035), for a
|
|
// later evaluation. The page lists only the ones a reader should check: changed and
|
|
// uncertain.
|
|
|
|
func TestUploadStatus_OnlyChangedAndUncertainSpotsAreListedNotTheKeptOnes(t *testing.T) {
|
|
app, _ := newUploadApp(t, audioOK, 200<<20)
|
|
id := seedUpload(t, userID, "m", "done", "Synthetic transcript.")
|
|
setReconciliation(t, id, `{"status":"reconciled","base":"a","alt":"b","reconciler":"c","disputes":3,"adjudicated":3,"changed":1,"unsure":1,
|
|
"contested":[
|
|
{"seconds":60,"base":"CHANGEDBASE","alt":"CHANGEDALT","used":"alt","unsure":false},
|
|
{"seconds":120,"base":"KEPTBASE","alt":"KEPTALT","used":"base","unsure":false},
|
|
{"seconds":180,"base":"UNSUREBASE","alt":"UNSUREALT","used":"base","unsure":true}]}`)
|
|
|
|
b := body(t, do(t, app, get("/uploads/"+id+"/status")))
|
|
|
|
assert.Contains(t, b, "CHANGEDBASE")
|
|
assert.Contains(t, b, "UNSUREALT")
|
|
assert.NotContains(t, b, "KEPTBASE", "a spot the model confidently kept is not one for the reader to check")
|
|
assert.NotContains(t, b, "KEPTALT")
|
|
}
|
|
|
|
func TestUploadStatus_TheMoreCountIgnoresKeptSpotsAndMatchesTheListedKind(t *testing.T) {
|
|
app, _ := newUploadApp(t, audioOK, 200<<20)
|
|
id := seedUpload(t, userID, "m", "done", "Synthetic transcript.")
|
|
var spots []string
|
|
for i := 0; i < 60; i++ {
|
|
spots = append(spots, fmt.Sprintf(`{"seconds":%d,"base":"b%d","alt":"a%d","used":"alt","unsure":false}`, i*10, i, i))
|
|
spots = append(spots, fmt.Sprintf(`{"seconds":%d,"base":"k%d","alt":"j%d","used":"base","unsure":false}`, i*10+5, i, i))
|
|
}
|
|
setReconciliation(t, id, `{"status":"reconciled","base":"a","alt":"b","reconciler":"c","disputes":400,"changed":60,"contested":[`+strings.Join(spots, ",")+`]}`)
|
|
|
|
b := body(t, do(t, app, get("/uploads/"+id+"/status")))
|
|
|
|
assert.Contains(t, b, "10 more", "60 changed, 50 shown: the 60 kept ones do not count")
|
|
assert.NotContains(t, b, "k0 / j0", "a kept spot is not rendered even when it is among the first stored")
|
|
}
|
|
|
|
func TestUploadStatus_WhenNothingNeedsCheckingThereIsNoSpotsSection(t *testing.T) {
|
|
app, _ := newUploadApp(t, audioOK, 200<<20)
|
|
id := seedUpload(t, userID, "m", "done", "Synthetic transcript.")
|
|
setReconciliation(t, id, `{"status":"reconciled","base":"a","alt":"b","reconciler":"c","disputes":1,"adjudicated":1,
|
|
"contested":[{"seconds":60,"base":"KEPTBASE","alt":"KEPTALT","used":"base","unsure":false}]}`)
|
|
|
|
b := body(t, do(t, app, get("/uploads/"+id+"/status")))
|
|
|
|
require.Contains(t, b, "Reconciled from two transcripts")
|
|
assert.NotContains(t, b, "Spots to check", "an empty list would invite checking nothing")
|
|
}
|
|
|
|
func TestUploadStatus_ASpotShowsTheWordsJustBeforeIt(t *testing.T) {
|
|
app, _ := newUploadApp(t, audioOK, 200<<20)
|
|
id := seedUpload(t, userID, "m", "done", "Synthetic transcript.")
|
|
setReconciliation(t, id, `{"status":"reconciled","base":"a","alt":"b","reconciler":"c","disputes":1,"changed":1,
|
|
"contested":[{"seconds":2640,"base":"vanligt","alt":"KORT","used":"alt","unsure":false,"before":"grannen målar ett"}]}`)
|
|
|
|
b := body(t, do(t, app, get("/uploads/"+id+"/status")))
|
|
|
|
assert.Contains(t, b, "grannen målar ett", "the words before the spot are how a reader finds it in the audio")
|
|
assert.Contains(t, b, "vanligt")
|
|
assert.Contains(t, b, "KORT")
|
|
}
|