X-Git-Url: https://git.giacomolli.uk/onechat/blobdiff_plain/7b8d8e8f4b57bd51fd6d0f0d926b821f06b0e1f0..80e348724041a694002fc38f57e8868b9b9a2be9:/whatsapp_inbox.go

diff --git a/whatsapp_inbox.go b/whatsapp_inbox.go
index cff43c7..a104a0d 100644
--- a/whatsapp_inbox.go
+++ b/whatsapp_inbox.go
@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"log/slog"
+	"path/filepath"
 	"slices"
 	"strings"
 	"sync"
@@ -31,21 +32,6 @@ const (
 	whatsappCatchupTimeout = time.Minute
 )
 
-// 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.
-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,
-		logger:   logger,
-		wake:     make(chan struct{}, 1),
-		failures: make(chan error, 1),
-	}
-}
-
 // WhatsAppInbox puts messages into batches, one chat at a time, as
 // WhatsAppState says. deliver logs each closed batch as a work message that
 // starts with [WhatsApp], and a batch that needs the user wakes the turn loop.
@@ -73,6 +59,8 @@ type WhatsAppInbox struct {
 	clock    func() time.Time
 	groups   *WhatsAppGroups
 	images   *ImageStore
+	voices   *VoiceStore
+	voice    *VoiceTranscriber
 	logger   *slog.Logger
 	wake     chan struct{}
 	failures chan error
@@ -84,6 +72,24 @@ type WhatsAppInbox struct {
 	catchupTimer *time.Timer
 }
 
+// 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. 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),
+	}
+}
+
 // due returns a channel that gets a value when the next open batch is due, or
 // nil when no batch is open.
 func (i *WhatsAppInbox) due() <-chan time.Time {
@@ -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()