feat: add trigger_by_self option

channel/chat_channel.py

@@ -38,7 +38,7 @@ class ChatChannel(Channel):
         if first_in: # context首次传入时，receiver是None，根据类型设置receiver
             config = conf()
             cmsg = context['msg']
-            if cmsg.from_user_id == self.user_id:
+            if cmsg.from_user_id == self.user_id and not config.get('trigger_by_self', False):
                 logger.debug("[WX]self message skipped")
                 return None
             if context["isgroup"]:
@@ -70,17 +70,21 @@ class ChatChannel(Channel):
                 # 校验关键字
                 match_prefix = check_prefix(content, conf().get('group_chat_prefix'))
                 match_contain = check_contain(content, conf().get('group_chat_keyword'))
+                flag = False
                 if match_prefix is not None or match_contain is not None:
+                    flag = True
                     if match_prefix:
                         content = content.replace(match_prefix, '', 1).strip()
-                elif context['msg'].is_at and not conf().get("group_at_off", False):
-                    logger.info("[WX]receive group at, continue")
+                if context['msg'].is_at:
+                    logger.info("[WX]receive group at")
+                    if not conf().get("group_at_off", False):
+                        flag = True
                     pattern = f'@{self.name}(\u2005|\u0020)'
                     content = re.sub(pattern, r'', content)
-                elif context["origin_ctype"] == ContextType.VOICE:
-                    logger.info("[WX]receive group voice, checkprefix didn't match")
-                    return None
-                else:
+                
+                if not flag:
+                    if context["origin_ctype"] == ContextType.VOICE:
+                        logger.info("[WX]receive group voice, but checkprefix didn't match")
                     return None
             else: # 单聊
                 match_prefix = check_prefix(content, conf().get('single_chat_prefix'))  
@@ -106,7 +110,6 @@ class ChatChannel(Channel):
 
         return context
 
-    # 处理消息 TODO: 如果wechaty解耦，此处逻辑可以放置到父类
     def _handle(self, context: Context):
         if context is None or not context.content:
             return
@@ -144,9 +147,11 @@ class ChatChannel(Channel):
                 # 删除临时文件
                 try:
                     os.remove(file_path)
-                    os.remove(wav_path)
+                    if wav_path != file_path:
+                        os.remove(wav_path)
                 except Exception as e:
-                    logger.warning("[WX]delete temp file error: " + str(e))
+                    pass
+                    # logger.warning("[WX]delete temp file error: " + str(e))
 
                 if reply.type == ReplyType.TEXT:
                     new_context = self._compose_context(

channel/wechat/wechat_channel.py

@@ -70,11 +70,25 @@ def _check(func):
 def qrCallback(uuid,status,qrcode):
     # logger.debug("qrCallback: {} {}".format(uuid,status))
     if status == '0':
+        try:
+            from PIL import Image
+            img = Image.open(io.BytesIO(qrcode))
+            thread_pool.submit(img.show,"QRCode")
+        except Exception as e:
+            pass
+
         import qrcode
         url = f"https://login.weixin.qq.com/l/{uuid}"
-
-        qr_api="https://api.isoyu.com/qr/?m=1&e=L&p=20&url={}".format(url)
-        print("You can also scan QRCode in the website below:\n{}".format(qr_api))
+        
+        qr_api1="https://api.isoyu.com/qr/?m=1&e=L&p=20&url={}".format(url)
+        qr_api2="https://api.qrserver.com/v1/create-qr-code/?size=400×400&data={}".format(url)
+        qr_api3="https://api.pwmqr.com/qrcode/create/?url={}".format(url)
+        qr_api4="https://my.tv.sohu.com/user/a/wvideo/getQRCode.do?text={}".format(url)
+        print("You can also scan QRCode in any website below:")
+        print(qr_api3)
+        print(qr_api4)
+        print(qr_api2)
+        print(qr_api1)
         
         qr = qrcode.QRCode(border=1)
         qr.add_data(url)

channel/wechat/wechaty_channel.py

@@ -73,6 +73,9 @@ class WechatyChannel(ChatChannel):
             file_path = reply.content
             sil_file = os.path.splitext(file_path)[0] + '.sil'
             voiceLength = int(any_to_sil(file_path, sil_file))
+            if voiceLength >= 60000:
+                voiceLength = 60000
+                logger.info('[WX] voice too long, length={}, set to 60s'.format(voiceLength))
             # 发送语音
             t = int(time.time())
             msg = FileBox.from_file(sil_file, name=str(t) + '.sil')
@@ -81,7 +84,8 @@ class WechatyChannel(ChatChannel):
             asyncio.run_coroutine_threadsafe(receiver.say(msg),loop).result()
             try:
                 os.remove(file_path)
-                os.remove(sil_file)
+                if sil_file != file_path:
+                    os.remove(sil_file)
             except Exception as e:
                 pass
             logger.info('[WX] sendVoice={}, receiver={}'.format(reply.content, receiver))
@@ -113,7 +117,6 @@ class WechatyChannel(ChatChannel):
             return
         logger.debug('[WX] message:{}'.format(cmsg))
         room = msg.room()  # 获取消息来自的群聊. 如果消息不是来自群聊, 则返回None
-        
         isgroup = room is not None
         ctype = cmsg.ctype
         context = self._compose_context(ctype, cmsg.content, isgroup=isgroup, msg=cmsg)

config.py

@@ -25,6 +25,7 @@ available_setting = {
     "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"],  # 开启自动回复的群名称列表
     "group_name_keyword_white_list": [],  # 开启自动回复的群名称关键词列表
     "group_chat_in_one_session": ["ChatGPT测试群"],  # 支持会话上下文共享的群名称
+    "trigger_by_self": False,  # 是否允许机器人触发
     "image_create_prefix": ["画", "看", "找"],  # 开启图片回复的前缀
 
     # chatgpt会话参数

plugins/README.md

@@ -101,7 +101,7 @@ PS: 插件目前支持`itchat`和`wechaty`
 
 根据`Context`和回复`Reply`的类型，对回复的内容进行装饰。目前的装饰有以下两种:
 
-- `TEXT`文本回复，根据是否在群聊中来决定是艾特接收方还是添加回复的前缀。
+- `TEXT`文本回复:如果这次消息需要的回复是`VOICE`，进行文字转语音回复之后再次装饰。 否则根据是否在群聊中来决定是艾特接收方还是添加回复的前缀。
 
 - `INFO`或`ERROR`类型，会在消息前添加对应的系统提示字样。
 
@@ -110,8 +110,11 @@ PS: 插件目前支持`itchat`和`wechaty`
 ```python
     if reply.type == ReplyType.TEXT:
         reply_text = reply.content
+        if context.get('desire_rtype') == ReplyType.VOICE:
+            reply = super().build_text_to_voice(reply.content)
+            return self._decorate_reply(context, reply)
         if context['isgroup']:
-            reply_text = '@' +  context['msg']['ActualNickName'] + ' ' + reply_text.strip()
+            reply_text = '@' +  context['msg'].actual_user_nickname + ' ' + reply_text.strip()
             reply_text = conf().get("group_chat_reply_prefix", "")+reply_text
         else:
             reply_text = conf().get("single_chat_reply_prefix", "")+reply_text
@@ -213,11 +216,11 @@ class Hello(Plugin):
         if content == "Hello":
             reply = Reply()
             reply.type = ReplyType.TEXT
-            msg = e_context['context']['msg']
+            msg:ChatMessage = e_context['context']['msg']
             if e_context['context']['isgroup']:
-                reply.content = "Hello, " + msg['ActualNickName'] + " from " + msg['User'].get('NickName', "Group")
+                reply.content = f"Hello, {msg.actual_user_nickname} from {msg.from_user_nickname}"
             else:
-                reply.content = "Hello, " + msg['User'].get('NickName', "My friend")
+                reply.content = f"Hello, {msg.from_user_nickname}"
             e_context['reply'] = reply
             e_context.action = EventAction.BREAK_PASS # 事件结束，并跳过处理context的默认逻辑
         if content == "End":

plugins/hello/hello.py

@@ -2,6 +2,7 @@
 
 from bridge.context import ContextType
 from bridge.reply import Reply, ReplyType
+from channel.chat_message import ChatMessage
 import plugins
 from plugins import *
 from common.log import logger
@@ -24,11 +25,11 @@ class Hello(Plugin):
         if content == "Hello":
             reply = Reply()
             reply.type = ReplyType.TEXT
-            msg = e_context['context']['msg']
+            msg:ChatMessage = e_context['context']['msg']
             if e_context['context']['isgroup']:
-                reply.content = "Hello, " + msg['ActualNickName'] + " from " + msg['User'].get('NickName', "Group")
+                reply.content = f"Hello, {msg.actual_user_nickname} from {msg.from_user_nickname}"
             else:
-                reply.content = "Hello, " + msg['User'].get('NickName', "My friend")
+                reply.content = f"Hello, {msg.from_user_nickname}"
             e_context['reply'] = reply
             e_context.action = EventAction.BREAK_PASS # 事件结束，并跳过处理context的默认逻辑
 

voice/audio_convert.py

@@ -67,23 +67,28 @@ def pcm_to_sil(pcm_path, silk_path):
     return 声音长度，毫秒
     """
     audio = AudioSegment.from_wav(pcm_path)
-    wav_data = audio.raw_data
     rate = find_closest_sil_supports(audio.frame_rate)
+    # Convert to PCM_s16
+    pcm_s16 = audio.set_sample_width(2)
+    pcm_s16 = pcm_s16.set_frame_rate(rate)
+    wav_data = pcm_s16.raw_data
     silk_data = pysilk.encode(
         wav_data, data_rate=rate, sample_rate=rate)
     with open(silk_path, "wb") as f:
         f.write(silk_data)
     return audio.duration_seconds * 1000
 
-
 def mp3_to_sil(mp3_path, silk_path):
     """
     mp3 文件转成 silk
     return 声音长度，毫秒
     """
     audio = AudioSegment.from_mp3(mp3_path)
-    wav_data = audio.raw_data
     rate = find_closest_sil_supports(audio.frame_rate)
+    # Convert to PCM_s16
+    pcm_s16 = audio.set_sample_width(2)
+    pcm_s16 = pcm_s16.set_frame_rate(rate)
+    wav_data = pcm_s16.raw_data
     silk_data = pysilk.encode(wav_data, data_rate=rate, sample_rate=rate)
     # Save the silk file
     with open(silk_path, "wb") as f:

voice/azure/azure_voice.py

@@ -54,7 +54,7 @@ class AzureVoice(Voice):
         return reply
 
     def textToVoice(self, text):
-        fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.wav'
+        fileName = TmpDir().path() + 'reply-' + str(int(time.time())) + '.wav'
         audio_config = speechsdk.AudioConfig(filename=fileName)
         speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=self.speech_config, audio_config=audio_config)
         result = speech_synthesizer.speak_text(text)

voice/baidu/baidu_voice.py

@@ -80,7 +80,7 @@ class BaiduVoice(Voice):
         result = self.client.synthesis(text, self.lang, self.ctp, {
             'spd': self.spd, 'pit': self.pit, 'vol': self.vol, 'per': self.per})
         if not isinstance(result, dict):
-            fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
+            fileName = TmpDir().path() + 'reply-' + str(int(time.time())) + '.mp3'
             with open(fileName, 'wb') as f:
                 f.write(result)
             logger.info(

voice/google/google_voice.py

@@ -34,7 +34,7 @@ class GoogleVoice(Voice):
             return reply
     def textToVoice(self, text):
         try:
-            mp3File = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
+            mp3File = TmpDir().path() + 'reply-' + str(int(time.time())) + '.mp3'
             tts = gTTS(text=text, lang='zh')
             tts.save(mp3File)            
             logger.info(

voice/pytts/pytts_voice.py

@@ -25,7 +25,7 @@ class PyttsVoice(Voice):
 
     def textToVoice(self, text):
         try:
-            wavFile = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.wav'
+            wavFile = TmpDir().path() + 'reply-' + str(int(time.time())) + '.wav'
             self.engine.save_to_file(text, wavFile)
             self.engine.runAndWait()
             logger.info(