Order model and chat declarations

[onechat] / whatsapp_inbox.go

diff --git a/whatsapp_inbox.go b/whatsapp_inbox.go
index 9d2183e7d5e282a96442f35ba13d0a7cf58ec1a1..a104a0d543a85f97df273841fba5b052c27a94cf 100644 (file)
--- a/whatsapp_inbox.go
+++ b/whatsapp_inbox.go
@@ -2,9 +2,9 @@ package main
 
 import (
        "context"
 
 import (
        "context"

-       "crypto/sha256"

        "fmt"
        "log/slog"
        "fmt"
        "log/slog"

+       "path/filepath"

        "slices"
        "strings"
        "sync"
        "slices"
        "strings"
        "sync"


@@ -32,21 +32,6 @@ const (
        whatsappCatchupTimeout = time.Minute
 )
 
        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.
 // 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.


@@ -74,6 +59,8 @@ type WhatsAppInbox struct {
        clock    func() time.Time
        groups   *WhatsAppGroups
        images   *ImageStore
        clock    func() time.Time
        groups   *WhatsAppGroups
        images   *ImageStore

+       voices   *VoiceStore
+       voice    *VoiceTranscriber

        logger   *slog.Logger
        wake     chan struct{}
        failures chan error
        logger   *slog.Logger
        wake     chan struct{}
        failures chan error


@@ -85,6 +72,24 @@ type WhatsAppInbox struct {
        catchupTimer *time.Timer
 }
 
        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 {
 // 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 {


@@ -225,10 +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)
 // 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)


@@ -244,6 +249,8 @@ func (i *WhatsAppInbox) receive(ctx context.Context, link WhatsAppLink, event *e
                defer cancel()
 
                message.Text = i.imageText(ctx, link, event, message.Text)
                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())
        }
 
        _, err := i.state.Add(chat, message, time.Now())


@@ -271,9 +278,8 @@ func (i *WhatsAppInbox) imageText(ctx context.Context, link WhatsAppLink, event
        name, err := whatsappImage(ctx, link.client, i.images, event.Message.GetImageMessage())
        if err != nil {
                chat := event.Info.Chat.ToNonAD()
        name, err := whatsappImage(ctx, link.client, i.images, event.Message.GetImageMessage())
        if err != nil {
                chat := event.Info.Chat.ToNonAD()

-               digest := sha256.Sum256([]byte(chat.String()))

                redact := append(slices.Clone(link.own), chat.User)
                redact := append(slices.Clone(link.own), chat.User)

-               i.logger.Error("image receive failed", "chat", fmt.Sprintf("%x", digest[:6]), "err", whatsappRedact(redact, err.Error()))
+               i.logger.Error("image receive failed", "chat", whatsappChatHash(chat), "err", whatsappRedact(redact, err.Error()))

 
                text := "(image not downloaded)"
                if caption != "" {
 
                text := "(image not downloaded)"
                if caption != "" {


@@ -358,7 +364,7 @@ func whatsappMessage(ctx context.Context, device *store.Device, own []string, ev
        chatJID := info.Chat.ToNonAD()
        switch {
        case device == nil:
        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:
        case chatJID.Server != types.DefaultUserServer && chatJID.Server != types.HiddenUserServer && chatJID.Server != types.GroupServer:
        case slices.Contains(own, chatJID.User):
        default:


@@ -369,7 +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
 }
 
 // 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()
 func whatsappText(ctx context.Context, device *store.Device, own []string, event *events.Message) (WhatsAppChat, WhatsAppMessage, bool) {
        info := event.Info
        text := event.Message.GetConversation()


@@ -380,6 +387,9 @@ func whatsappText(ctx context.Context, device *store.Device, own []string, event
 
        contextInfo := extended.GetContextInfo()
        switch {
 
        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()
        case event.Message.GetImageMessage() != nil:
                image := event.Message.GetImageMessage()
                text = image.GetCaption()