Include the small model in the Nix package

[onechat] / whatsapp_inbox.go

diff --git a/whatsapp_inbox.go b/whatsapp_inbox.go
index cff43c706607576d5ba9a0cfe447adb627a45de1..c9ca81b666148d4a43795a1b9a3d38fdb8cde0dd 100644 (file)
--- a/whatsapp_inbox.go
+++ b/whatsapp_inbox.go
@@ -4,6 +4,7 @@ import (
        "context"
        "fmt"
        "log/slog"
+       "path/filepath"
        "slices"
        "strings"
        "sync"
@@ -33,13 +34,16 @@ const (
 
 // newWhatsAppInbox returns the inbox of the batches in state, with clock for
 // the times of the batch texts and groups for the names of the groups. images
-// holds shared images, and logger gets image failures.
+// holds shared images, and logger gets image failures. Audio shares the data
+// directory of state.
 func newWhatsAppInbox(state *WhatsAppState, clock func() time.Time, groups *WhatsAppGroups, images *ImageStore, logger *slog.Logger) *WhatsAppInbox {
        return &WhatsAppInbox{
                state:    state,
                clock:    clock,
                groups:   groups,
                images:   images,
+               voices:   &VoiceStore{dir: filepath.Join(filepath.Dir(filepath.Dir(state.path)), voiceDirName)},
+               voice:    &VoiceTranscriber{},
                logger:   logger,
                wake:     make(chan struct{}, 1),
                failures: make(chan error, 1),
@@ -73,6 +77,8 @@ type WhatsAppInbox struct {
        clock    func() time.Time
        groups   *WhatsAppGroups
        images   *ImageStore
+       voices   *VoiceStore
+       voice    *VoiceTranscriber
        logger   *slog.Logger
        wake     chan struct{}
        failures chan error
@@ -224,10 +230,10 @@ func (i *WhatsAppInbox) startCatchup() {
        })
 }
 
-// receive stores an image before its batch and wakes Run. link gives the device
-// and the own IDs. It returns false when the state file cannot hold the
-// message, so that the library does not acknowledge it, and Run stops the
-// daemon. An image that cannot be downloaded or stored gets a text marker. A
+// receive stores images and transcribed voice notes before their batches and
+// wakes Run. link gives the device and the own IDs. It returns false when the
+// state file cannot hold the message, so that the library does not acknowledge
+// it, and Run stops the daemon. Failed media input gets a text marker. A
 // message that the batches do not take is handled with nothing to do.
 func (i *WhatsAppInbox) receive(ctx context.Context, link WhatsAppLink, event *events.Message) bool {
        lookupCtx, cancel := context.WithTimeout(ctx, whatsappContactLookupTimeout)
@@ -243,6 +249,8 @@ func (i *WhatsAppInbox) receive(ctx context.Context, link WhatsAppLink, event *e
                defer cancel()
 
                message.Text = i.imageText(ctx, link, event, message.Text)
+       } else if event.Message.GetAudioMessage().GetPTT() {
+               message.Text = whatsappRedact(link.own, whatsappVoice(ctx, link.client, i.voices, i.voice, event.Message.GetAudioMessage()))
        }
 
        _, err := i.state.Add(chat, message, time.Now())
@@ -356,7 +364,7 @@ func whatsappMessage(ctx context.Context, device *store.Device, own []string, ev
        chatJID := info.Chat.ToNonAD()
        switch {
        case device == nil:
-       case event.IsEdit, info.Edit != "", event.IsEphemeral, event.IsViewOnce, event.Message.GetImageMessage().GetViewOnce(), event.Message.GetVideoMessage().GetViewOnce(), event.SourceWebMsg != nil:
+       case event.IsEdit, info.Edit != "", event.IsEphemeral, event.IsViewOnce, event.Message.GetImageMessage().GetViewOnce(), event.Message.GetVideoMessage().GetViewOnce(), event.Message.GetAudioMessage().GetViewOnce(), event.SourceWebMsg != nil:
        case chatJID.Server != types.DefaultUserServer && chatJID.Server != types.HiddenUserServer && chatJID.Server != types.GroupServer:
        case slices.Contains(own, chatJID.User):
        default:
@@ -367,7 +375,8 @@ func whatsappMessage(ctx context.Context, device *store.Device, own []string, ev
 }
 
 // whatsappText returns the chat and the batch message of event, a message that
-// the batches take. An image returns its caption until receive stores it.
+// the batches take. An image returns its caption until receive stores it. A
+// voice note returns a marker until receive transcribes it.
 func whatsappText(ctx context.Context, device *store.Device, own []string, event *events.Message) (WhatsAppChat, WhatsAppMessage, bool) {
        info := event.Info
        text := event.Message.GetConversation()
@@ -378,6 +387,9 @@ func whatsappText(ctx context.Context, device *store.Device, own []string, event
 
        contextInfo := extended.GetContextInfo()
        switch {
+       case event.Message.GetAudioMessage().GetPTT():
+               text = "(voice not downloaded)"
+               contextInfo = event.Message.GetAudioMessage().GetContextInfo()
        case event.Message.GetImageMessage() != nil:
                image := event.Message.GetImageMessage()
                text = image.GetCaption()