cleanup

.flake8

@@ -16,12 +16,9 @@ extend-exclude =
 
 # Codes: https://flake8.pycqa.org/en/latest/user/error-codes.html
 extend-ignore =
-
+    # One-line docstring should fit on one line with quotes
     D200,
 
-    # No blank lines allowed after function docstring
-    #D202,
-
     # 1 blank line required between summary line and description
     D205,
 
@@ -44,7 +41,7 @@ extend-ignore =
     N802,
 
     # argument name should be lowercase
-    #N803,
+    N803,
 
     # variable in function should be lowercase
     N806,

requirements/requirements-direct.txt

@@ -1,4 +1,5 @@
 attrs==22.2.0
 click==8.1.3
 openai-whisper==20230918
+pydub==0.25.1
 Twisted==22.10.0

requirements/requirements-mypy.txt

@@ -1 +1,2 @@
 mypy==0.981
+pydub-stubs==0.25.1.1

src/transmissions/indexer/_indexer.py

@@ -3,13 +3,15 @@
 from datetime import timedelta as TimeDelta
 from datetime import timezone as TimeZone
 from enum import Enum
+from hashlib import sha256
 from os import walk
 from pathlib import Path
 from re import Pattern
 from re import compile as regex
 from typing import ClassVar
 
 from attrs import Factory, frozen
+from pydub import AudioSegment
 from twisted.logger import Logger
 from whisper import Whisper
 from whisper import load_model as loadWhisper
@@ -145,7 +147,9 @@ def whisper() -> Whisper:
 
     _whisper: Whisper = Factory(whisper)
 
-    def _transmissionFromFile(self, path: Path) -> Transmission:
+    def _transmissionFromFile(
+        self, path: Path, _expensiveParts: bool = False
+    ) -> Transmission:
         """
         Returns a Transmission based on the given Path to a file.
         """
@@ -194,38 +198,46 @@ def _transmissionFromFile(self, path: Path) -> Transmission:
         else:
             station = f"{stationType} {stationName}"
 
-        # # Channel
+        # Channel
 
         try:
             channel = match.group("channel1")
         except IndexError:
             channel = match.group("channel2")
 
-        # # Duration
+        if _expensiveParts:
+            # Duration
 
-        # duration = TimeDelta(0)  # FIXME
+            audio = AudioSegment.from_wav(str(path))
+            duration = TimeDelta(milliseconds=len(audio))
 
-        # # Checksum
+            # Checksum
 
-        # checksum = sha256()
-        # with path.open("rb") as f:
-        #     checksum.update(f.read())
+            hasher = sha256()
+            with path.open("rb") as f:
+                hasher.update(f.read())
+            sha256Digest = hasher.hexdigest()
 
-        # # Speech -> text
-        # text = self._whisper.transcribe(str(path))
+            # Speech -> text
+            text = self._whisper.transcribe(str(path))
 
-        # Packaged up
+        else:
+            duration = None
+            sha256Digest = None
+            text = None
+
+        # Return result
 
         return Transmission(
             eventID=self.eventID,
             station=station,
             system=system,
             channel=channel,
             startTime=startTime,
-            duration=None,
+            duration=duration,
             path=path,
-            sha256=None,  # checksum.hexdigest(),
-            text=None,  # text
+            sha256=sha256Digest,
+            text=text,
         )
 
     def transmissions(self) -> Iterable[Transmission | None]:

tox.ini

@@ -19,7 +19,7 @@ deps =
     coverage: {[testenv:coverage_report]deps}
 
 setenv =
-    PY_MODULE=deploy
+    PY_MODULE=transmissions
 
     PYTHONPYCACHEPREFIX={envtmpdir}/pycache