Files
tapir/internal/uploads/validate.go
T

84 lines
2.9 KiB
Go

// Package uploads is the use case behind "upload an audio recording" (ADR-033):
// validate the file by PROBING it, keep the transcript private, never retain the
// audio. It depends only on ports (a Prober, a store, a job Submitter) — the
// concrete ffprobe adapter, the web handler and the transcription worker are wired
// from outside.
package uploads
import (
"fmt"
"time"
)
// Limits bound what an upload may be. Both are rejected synchronously, with a
// specific message, rather than by a timeout (ADR-033).
type Limits struct {
MaxBytes int64
MaxDuration time.Duration
}
// Probe is what inspecting an uploaded file revealed. It is the input to Validate
// because a name or MIME type cannot say what a container holds: a Teams recording
// is an .mp4 whether or not the camera was on.
type Probe struct {
Duration time.Duration
HasAudio bool
HasVideo bool
}
// Reason is the machine-checkable class of a rejection.
type Reason string
const (
ReasonNoAudio Reason = "no_audio"
ReasonTooLong Reason = "too_long"
ReasonTooLarge Reason = "too_large"
ReasonUnreadable Reason = "unreadable"
// ReasonBusy: the queue is full. Not about the file: the user retries later.
ReasonBusy Reason = "busy"
)
// RejectError is a synchronous, user-presentable refusal. Message is written for
// the person who uploaded the file; Reason is for code and tests.
type RejectError struct {
Reason Reason
Message string
}
func (e *RejectError) Error() string { return string(e.Reason) + ": " + e.Message }
// Validate decides whether a probed file may be transcribed. A video track is NOT
// a reason to refuse: a Teams meeting with the camera off is still an .mp4 with a
// video track, so rejecting video would reject the primary use case. Only the audio
// is used (Probe.HasVideo is recorded so the user can be told the video was
// ignored). What IS refused: no audio at all, an unreadable length, too long.
func Validate(p Probe, l Limits) error {
switch {
case !p.HasAudio:
return &RejectError{Reason: ReasonNoAudio, Message: "This file has no audio track to transcribe."}
case p.Duration <= 0:
return &RejectError{Reason: ReasonUnreadable, Message: "Could not read a length from this file; it may be damaged."}
case p.Duration > l.MaxDuration:
return &RejectError{Reason: ReasonTooLong, Message: fmt.Sprintf(
"This recording is %s long; the limit is %s.", FormatDuration(p.Duration), FormatDuration(l.MaxDuration))}
}
return nil
}
// FormatDuration renders a length for people: "1 h 42 min", "45 min", "30 s".
func FormatDuration(d time.Duration) string {
d = d.Round(time.Second)
h := int(d / time.Hour)
m := int(d % time.Hour / time.Minute)
switch {
case h > 0 && m > 0:
return fmt.Sprintf("%d h %d min", h, m)
case h > 0:
return fmt.Sprintf("%d h", h)
case m > 0:
return fmt.Sprintf("%d min", m)
default:
return fmt.Sprintf("%d s", int(d/time.Second))
}
}