tapir/internal/uploads/intake.go

package uploads

import (
	"context"
	"errors"
	"fmt"
	"io"
	"os"
	"time"

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

// ErrUnreadable is what a Prober returns when the FILE is the problem (not media,
// truncated, damaged), as opposed to the prober itself failing. Accept turns it
// into a user-facing rejection; any other prober error is our fault and surfaces
// as an internal error — a missing ffprobe must not read as "your file is bad".
var ErrUnreadable = errors.New("uploads: file is not readable media")

// Prober inspects a file on disk. The ffprobe adapter implements it.
type Prober interface {
	Probe(ctx context.Context, path string) (Probe, error)
}

// Store is the slice of the private transcript store the intake needs.
type Store interface {
	CreateUpload(ctx context.Context, userID, title string, hadVideo bool) (string, error)
	FailUpload(ctx context.Context, userID, id string, kind domain.UploadErrorKind) error
}

// Job is one accepted upload awaiting transcription. Path is a temp file the
// receiver owns: it must delete it when finished (the audio is never retained).
type Job struct {
	UserID   string
	UploadID string
	Path     string
	// Duration is what the file CLAIMED when probed. The worker compares it with what
	// was really converted; zero means unknown (ADR-035 review).
	Duration time.Duration
}

// Submitter hands accepted jobs to the in-process worker (ADR-033).
type Submitter interface {
	Submit(Job) error
}

// Intake validates an uploaded recording and, if it passes, queues it.
type Intake struct {
	store  Store
	prober Prober
	sub    Submitter
	limits Limits
	tmpDir string
}

// NewIntake wires an Intake. tmpDir is where uploads are spooled; it must exist.
func NewIntake(s Store, p Prober, sub Submitter, l Limits, tmpDir string) *Intake {
	return &Intake{store: s, prober: p, sub: sub, limits: l, tmpDir: tmpDir}
}

// ErrClientRead marks an error that came from READING the client's body: a connection that
// dropped, a body cut short. It is the sender's to retry, unlike a spool, probe or database
// fault, which is ours. It is a marker on the error, not a sentinel that others may wrap:
// io.ErrUnexpectedEOF alone is also what a database drop looks like.
var ErrClientRead = errors.New("uploads: client body read failed")

// clientReader remembers the last non-EOF error its source returned, so Accept can tell
// a failure reading the client from a failure writing the spool file.
type clientReader struct {
	r   io.Reader
	err error
}

func (c *clientReader) Read(p []byte) (int, error) {
	n, err := c.r.Read(p)
	if err != nil && !errors.Is(err, io.EOF) {
		c.err = err
	}
	return n, err
}

// busyMessage is what a user is told when the queue is full.
const busyMessage = "Too many recordings are waiting to be transcribed. Please try again in a few minutes."

// Accept spools src to disk (bounded by MaxBytes), probes it, validates it, records
// a queued upload and submits the job. It returns the upload id. A file that fails
// validation yields a *RejectError and creates NO row — rejection is synchronous
// and leaves nothing behind. On success the temp file is handed to the job and the
// worker deletes it; on every failure path Accept deletes it itself.
func (in *Intake) Accept(ctx context.Context, userID, title string, src io.Reader) (string, error) {
	// Refuse before spooling when the queue has no room, if the submitter can say so: a full
	// queue otherwise cost up to the upload cap on disk, an ffprobe run and a failed row for
	// every refused attempt.
	if rc, ok := in.sub.(interface{ HasRoom(userID string) bool }); ok && !rc.HasRoom(userID) {
		return "", &RejectError{Reason: ReasonBusy, Message: busyMessage}
	}
	f, err := os.CreateTemp(in.tmpDir, "upload-*")
	if err != nil {
		return "", fmt.Errorf("uploads: spool: %w", err)
	}
	path := f.Name()
	handedOver := false
	defer func() {
		if !handedOver {
			_ = os.Remove(path)
		}
	}()

	// Read one byte past the cap so "exactly at the limit" and "over" are told apart.
	cr := &clientReader{r: io.LimitReader(src, in.limits.MaxBytes+1)}
	n, err := io.Copy(f, cr)
	if cerr := f.Close(); err == nil {
		err = cerr
	}
	if err != nil {
		if cr.err != nil && errors.Is(err, cr.err) {
			return "", fmt.Errorf("%w: %w", ErrClientRead, err)
		}
		return "", fmt.Errorf("uploads: receive: %w", err)
	}
	if n > in.limits.MaxBytes {
		return "", &RejectError{Reason: ReasonTooLarge, Message: fmt.Sprintf(
			"This file is larger than the %d MB limit.", in.limits.MaxBytes>>20)}
	}

	probe, err := in.prober.Probe(ctx, path)
	if errors.Is(err, ErrUnreadable) {
		return "", &RejectError{
			Reason:  ReasonUnreadable,
			Message: "This file could not be read as audio; it may be damaged or not a recording.",
		}
	}
	if err != nil {
		return "", fmt.Errorf("uploads: probe: %w", err)
	}
	if err := Validate(probe, in.limits); err != nil {
		return "", err
	}

	id, err := in.store.CreateUpload(ctx, userID, title, probe.HasVideo)
	if err != nil {
		return "", fmt.Errorf("uploads: create: %w", err)
	}
	if err := in.sub.Submit(Job{UserID: userID, UploadID: id, Path: path, Duration: probe.Duration}); err != nil {
		if errors.Is(err, ErrQueueFull) {
			// The user's to retry, not a server fault: refuse it as such, and do not leave
			// the row queued -- that is the stuck spinner.
			if ferr := in.store.FailUpload(ctx, userID, id, domain.UploadErrBusy); ferr != nil {
				return "", fmt.Errorf("uploads: submit: %w (and failing the row: %v)", err, ferr)
			}
			return "", &RejectError{Reason: ReasonBusy, Message: busyMessage}
		}
		// A row that will never run must not sit queued: that is the stuck spinner.
		if ferr := in.store.FailUpload(ctx, userID, id, domain.UploadErrInterrupted); ferr != nil {
			return "", fmt.Errorf("uploads: submit: %w (and failing the row: %v)", err, ferr)
		}
		return "", fmt.Errorf("uploads: submit: %w", err)
	}
	handedOver = true
	return id, nil
}