feat(audio): Add helper method to downsize audio records

README.md

@@ -311,14 +311,25 @@ from courts across the country and standardizes the format for our end users.
 
 This endpoint also adds the SEAL of the court to the MP3 file and updates the metadata to reflect our updates.
 
-This isn't the cleanest of CURLs because we have to convert the large JSON file to a query string, but for proof of concept here is the result
-
     curl 'http://localhost:5050/convert/audio/mp3/?audio_data=%7B%22court_full_name%22%3A+%22Testing+Supreme+Court%22%2C+%22court_short_name%22%3A+%22Testing+Supreme+Court%22%2C+%22court_pk%22%3A+%22test%22%2C+%22court_url%22%3A+%22http%3A%2F%2Fwww.example.com%2F%22%2C+%22docket_number%22%3A+%22docket+number+1+005%22%2C+%22date_argued%22%3A+%222020-01-01%22%2C+%22date_argued_year%22%3A+%222020%22%2C+%22case_name%22%3A+%22SEC+v.+Frank+J.+Custable%2C+Jr.%22%2C+%22case_name_full%22%3A+%22case+name+full%22%2C+%22case_name_short%22%3A+%22short%22%2C+%22download_url%22%3A+%22http%3A%2F%2Fmedia.ca7.uscourts.gov%2Fsound%2Fexternal%2Fgw.15-1442.15-1442_07_08_2015.mp3%22%7D' \
      -X 'POST' \
      -F "file=@doctor/test_assets/1.wma"
 
 This returns the audio file as a file response.
 
+### Endpoint: /convert/audio/ogg/
+
+This endpoint takes an audio file and converts it to an OGG file. The conversion process downsizes files by using
+a single audio channel and fixing the sampling rate to 8 kHz.
+
+This endpoint also optimizes the output for voice over IP applications.
+
+    curl 'http://localhost:5050/convert/audio/ogg/' \
+     -X 'POST' \
+     -F "file=@doctor/test_assets/1.wma"
+
+This returns the audio file as a file response.
+
 
 ## Testing
 

doctor/forms.py

@@ -44,7 +44,7 @@ class AudioForm(BaseAudioFile):
     audio_data = forms.JSONField(label="audio-data", required=False)
 
     def clean(self):
-        self.cleaned_data["fp"] = f"/tmp/audio_{uuid.uuid4().hex}.mp3"
+        self.cleaned_data["fp"] = f"/tmp/audio_{uuid.uuid4().hex}"
         if self.cleaned_data.get("file", None):
             filename = self.cleaned_data["file"].name
             self.cleaned_data["extension"] = filename.split(".")[-1]

doctor/tasks.py

@@ -479,6 +479,47 @@ def convert_to_mp3(output_path: AnyStr, media: Any) -> None:
     return output_path
 
 
+def convert_to_ogg(output_path: AnyStr, media: Any) -> None:
+    """Converts audio data to the ogg format (.ogg)
+
+    This function uses ffmpeg to convert the audio data provided in `media` to
+    the ogg format with the following specifications:
+
+    * Single audio channel (`-ac 1`)
+    * 8 kHz sampling rate (`-b:a 8k`)
+    * Optimized for voice over IP applications (`-application voip`)
+
+    :param output_path: Audio file bytes sent to Doctor
+    :param media: Temporary filepath for output of audioprocess
+    :return:
+    """
+    av_command = [
+        "ffmpeg",
+        "-i",
+        "/dev/stdin",
+        "-vn",
+        "-map_metadata",
+        "-1",
+        "-ac",
+        "1",
+        "-c:a",
+        "libopus",
+        "-b:a",
+        "8k",
+        "-application",
+        "voip",
+        "-f",
+        "ogg",
+        output_path,
+    ]
+
+    ffmpeg_cmd = subprocess.Popen(
+        av_command, stdin=subprocess.PIPE, stdout=subprocess.PIPE, shell=False
+    )
+    ffmpeg_cmd.communicate(media.read())
+    return output_path
+
+
 def set_mp3_meta_data(
     audio_data: Dict, mp3_path: AnyStr
 ) -> eyed3.core.AudioFile:

doctor/urls.py

@@ -1,4 +1,4 @@
-from django.urls import path
+from django.urls import path, re_path
 
 from . import views
 
@@ -23,7 +23,9 @@
         views.make_png_thumbnails_from_range,
         name="thumbnails",
     ),
-    path("convert/audio/mp3/", views.convert_audio, name="convert-audio"),
+    re_path(
+        "convert/audio/(mp3|ogg)/", views.convert_audio, name="convert-audio"
+    ),
     path("utils/page-count/pdf/", views.page_count, name="page_count"),
     path("utils/mime-type/", views.extract_mime_type, name="mime_type"),
     path(

doctor/views.py

@@ -34,6 +34,7 @@
 from doctor.tasks import (
     convert_tiff_to_pdf_bytes,
     convert_to_mp3,
+    convert_to_ogg,
     download_images,
     extract_from_doc,
     extract_from_docx,
@@ -367,8 +368,11 @@ def fetch_audio_duration(request) -> HttpResponse:
         return HttpResponse(str(e))
 
 
-def convert_audio(request) -> Union[FileResponse, HttpResponse]:
-    """Convert audio file to MP3 and update metadata on mp3.
+def convert_audio(
+    request, output_format: str
+) -> Union[FileResponse, HttpResponse]:
+    """Converts an uploaded audio file to the specified output format and
+    updates its metadata.
 
     :return: Converted audio
     """
@@ -378,8 +382,14 @@ def convert_audio(request) -> Union[FileResponse, HttpResponse]:
     filepath = form.cleaned_data["fp"]
     media_file = form.cleaned_data["file"]
     audio_data = {k: v[0] for k, v in dict(request.GET).items()}
-    convert_to_mp3(filepath, media_file)
-    set_mp3_meta_data(audio_data, filepath)
+    match output_format:
+        case "mp3":
+            convert_to_mp3(filepath, media_file)
+            set_mp3_meta_data(audio_data, filepath)
+        case "ogg":
+            convert_to_ogg(filepath, media_file)
+        case _:
+            raise NotImplemented
     response = FileResponse(open(filepath, "rb"))
     cleanup_form(form)
     return response