minor refactor

.gitignore

@@ -167,7 +167,7 @@ transcript_timestamps.txt
 *.pkl
 transcript_*.txt
 test_*.txt
-*.png
+wordcloud*.png
 *.ini
 test_samples/
 *.wav

scripts/clear_artefacts.sh

@@ -7,7 +7,7 @@ directory="."
 text_file_pattern="transcript_*.txt"
 pickle_file_pattern="*.pkl"
 html_file_pattern="*.html"
-png_file_pattern="*.png"
+png_file_pattern="wordcloud*.png"
 
 find "$directory" -type f -name "$text_file_pattern" -delete
 find "$directory" -type f -name "$pickle_file_pattern" -delete

stream_client.py

@@ -11,9 +11,10 @@ import ast
 import stamina
 from aiortc import (RTCPeerConnection, RTCSessionDescription)
 from aiortc.contrib.media import (MediaPlayer, MediaRelay)
+from utils.server_utils import Mutex
 
 logger = logging.getLogger("pc")
-file_lock = threading.Lock()
+file_lock = Mutex(open("test_sm_6.txt", "a"))
 
 config = configparser.ConfigParser()
 config.read('config.ini')
@@ -24,8 +25,7 @@ class StreamClient:
         signaling,
         url="http://127.0.0.1:1250",
         play_from=None,
-        ping_pong=False,
+        ping_pong=False
-        audio_stream=None
     ):
         self.signaling = signaling
         self.server_url = url
@@ -36,7 +36,6 @@ class StreamClient:
         self.pc = RTCPeerConnection()
 
         self.loop = asyncio.get_event_loop()
-        # self.loop = asyncio.new_event_loop()
         self.relay = None
         self.pcs = set()
         self.time_start = None
@@ -68,7 +67,6 @@ class StreamClient:
         channel.send(message)
 
     def current_stamp(self):
-
         if self.time_start is None:
             self.time_start = time.time()
             return 0
@@ -94,9 +92,7 @@ class StreamClient:
         @pc.on("track")
         def on_track(track):
             print("Sending %s" % track.kind)
-            # Trials
             self.pc.addTrack(track)
-            # self.pc.addTrack(self.microphone)
 
             @track.on("ended")
             async def on_ended():
@@ -104,7 +100,6 @@ class StreamClient:
 
         self.pc.addTrack(audio)
 
-        # DataChannel
         channel = pc.createDataChannel("data-channel")
         self.channel_log(channel, "-", "created by local party")
 
@@ -155,14 +150,12 @@ class StreamClient:
         while True:
             msg = await self.queue.get()
             msg = ast.literal_eval(msg)
-            with file_lock:
+            with file_lock.lock() as file:
-                with open("test_sm_6.txt", "a") as f:
+                file.write(msg["text"])
-                    f.write(msg["text"])
             yield msg["text"]
             self.queue.task_done()
 
     async def start(self):
-        print("Starting stream client")
         coro = self.run_offer(self.pc, self.signaling)
         task = asyncio.create_task(coro)
         await task

utils/server_utils.py

@@ -1,7 +1,25 @@
 import asyncio
 from functools import partial
+import contextlib
+from threading import Lock
+from typing import ContextManager, Generic, TypeVar
 
 def run_in_executor(func, *args, executor=None, **kwargs):
     callback = partial(func, *args, **kwargs)
     loop = asyncio.get_event_loop()
     return asyncio.get_event_loop().run_in_executor(executor, callback)
+
+
+T = TypeVar("T")
+class Mutex(Generic[T]):
+    def __init__(self, value: T):
+        self.__value = value
+        self.__lock = Lock()
+
+    @contextlib.contextmanager
+    def lock(self) -> ContextManager[T]:
+        self.__lock.acquire()
+        try:
+            yield self.__value
+        finally:
+            self.__lock.release()

utils/text_utilities.py

@@ -19,6 +19,9 @@ def preprocess_sentence(sentence):
     return ' '.join(tokens)
 
 def compute_similarity(sent1, sent2):
+    """
+    Compute the similarity
+    """
     tfidf_vectorizer = TfidfVectorizer()
     if sent1 is not None and sent2 is not None:
         tfidf_matrix = tfidf_vectorizer.fit_transform([sent1, sent2])

utils/viz_utilities.py

@@ -19,6 +19,7 @@ spacy_stopwords = en.Defaults.stop_words
 
 STOPWORDS = set(STOPWORDS).union(set(stopwords.words("english"))).union(set(spacy_stopwords))
 
+
 def create_wordcloud(timestamp, real_time=False):
     """
     Create a basic word cloud visualization of transcribed text