Feature/tests

api/serializers.py

@@ -19,7 +19,7 @@ class Meta:
             "audio_file",
             "start_time",
             "end_time",
-            "annotation",
+            "content",
             "timestamp",
         )
 
@@ -29,6 +29,6 @@ def create(self, validated_data):
     def update(self, instance, validated_data):
         instance.start_time = validated_data.get("start_time", instance.start_time)
         instance.end_time = validated_data.get("end_time", instance.end_time)
-        instance.annotation = validated_data.get("annotation", instance.annotation)
+        instance.content = validated_data.get("content", instance.content)
         instance.save()
         return instance

docker-compose.yml

@@ -44,7 +44,7 @@ services:
       interval: 10s
       timeout: 5s
       retries: 5
-    entrypoint: ["./db-entrypoint.sh"]
+    entrypoint: ["/db-entrypoint.sh"]
 
   migrate:
     build: 
@@ -53,7 +53,6 @@ services:
     command: conda run --no-capture-output -n comedy-project-docker python manage.py migrate
     volumes:
       - .:/audio-annonation
-      - D:/anaconda-envs:/envs
     depends_on:
       db:
         condition: service_healthy

pyproject.toml

@@ -1,124 +1,4 @@
-[tool.poetry]
-name = "audio-annonation"
-version = "0.1.0"
-description = ""
-authors = ["Unnati Patel", "Christopher Keim"]
-readme = "README.md"
-packages = [
-   { include = "api" },
-   { include = "waveform_audio" },
-]
-
-[tool.poetry.dependencies]
-python = ">=3.11, <3.12"
-
-# Web
-requests = "^2.31.0"
-urllib3 = "^2.0.2"
-django = "^4.2.1"
-djangorestframework = "^3.14.0"
-crispy-tailwind = "^0.5.0"
-whitenoise = "^6.6.0"
-asgiref = "^3.6.0"
-certifi = "^2023.5.7"
-tzdata = "^2023.3"
-python-dotenv = "^1.0.0"
-
-# Data Science
-pandas = "^1.5.0"
-numpy = "^1.24.3"
-scipy = "^1.10.1"
-scikit-learn = "^1.2.2"
-matplotlib = "^3.6.0"
-sqlparse = "^0.4.4"
-audioread = "^3.0.0"
-soundfile = "^0.12.1"
-pooch = "^1.6.0"
-soxr = "^0.3.5"
-librosa = "^0.10.0.post2"
-
-# MLOps
-threadpoolctl = "^3.1.0"
-numba = "^0.57.0"
-llvmlite = "^0.40.0"
-cffi = "^1.15.1"
-
-
-
-[tool.poetry.group.dev]
-optional = true
-[tool.poetry.group.dev.dependencies]
-
-# DevOps
-black = "^22.3.0"
-pytest = "^7.4.0"
-pytest-cov = "^4.1.0"
-ruff = "^0.0.285"
-
-# PostgresSQL psycopg2 pre-compiled binary
-psycopg2-binary = "^2.9.9"
-
-
-[tool.poetry.group.prod]
-optional = true
-[tool.poetry.group.prod.dependencies]
-
-# PostgresSQL psycopg2 source build 
-psycopg2 = "^2.9.9"
-
-
-[tool.ruff]
-# Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.
-select = ["E", "F"]
-ignore = []
-
-# Allow autofix for all enabled rules (when `--fix`) is provided.
-fixable = ["A", "B", "C", "D", "E", "F", "G", "I", "N", "Q", "S", "T", "W", "ANN", "ARG", "BLE", "COM", "DJ", "DTZ", "EM", "ERA", "EXE", "FBT", "ICN", "INP", "ISC", "NPY", "PD", "PGH", "PIE", "PL", "PT", "PTH", "PYI", "RET", "RSE", "RUF", "SIM", "SLF", "TCH", "TID", "TRY", "UP", "YTT"]
-unfixable = []
-
-# Exclude a variety of commonly ignored directories.
-exclude = [
-    ".bzr",
-    ".direnv",
-    ".eggs",
-    ".git",
-    ".git-rewrite",
-    ".hg",
-    ".mypy_cache",
-    ".nox",
-    ".pants.d",
-    ".pytype",
-    ".ruff_cache",
-    ".svn",
-    ".tox",
-    ".venv",
-    "__pypackages__",
-    "_build",
-    "buck-out",
-    "build",
-    "dist",
-    "node_modules",
-    "venv",
-    "tests",
-]
-
-# Same as Black.
-line-length = 88
-
-# Allow unused variables when underscore-prefixed.
-dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
-
-# Assume Python 3.9
-target-version = "py39"
-
-[tool.ruff.mccabe]
-# Unlike Flake8, default to a complexity level of 10.
-max-complexity = 10
-
 [tool.pytest.ini_options]
-# Configurations for pytest with coverage
-addopts = "-vv --cov"
-
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+DJANGO_SETTINGS_MODULE = "waveform_audio.settings"
+# -- recommended but optional:
+python_files = ["test_*.py", "*_test.py", "testing/python/*.py"]

waveform_audio/forms.py

@@ -1,8 +1,12 @@
 # import crispy_forms.helper as crispy_helper
 from django import forms
-from .models import AudioFile
+from django.utils.translation import gettext_lazy as _
+
+from waveform_audio.models import AudioFile, Subtitle
 from crispy_forms.helper import FormHelper
-from crispy_forms.layout import Submit  # Layout, Row, Column
+from crispy_forms.layout import Submit
+from waveform_audio import utils
+import mimetypes
 
 
 # url: https://stackoverflow.com/questions/24783275/django-form-with-choices-but-also-with-freetext-option?noredirect=1&lq=1
@@ -31,19 +35,30 @@ class Meta:
         model = AudioFile
         fields = ["file"]
         labels = {
-            "audio_file": "Select a file",
+            "file": "Select a file",
         }
         help_texts = {
-            "audio_file": "insert an audio file",
+            "file": "insert an audio file",
         }
         widgets = {
-            "audio_file": forms.FileInput(attrs={"accept": "audio/*"}),
+            "file": forms.FileInput(attrs={"accept": "audio/wav,audio/mp3,audio/mp4"}),
         }
 
+    def clean_file(self):
+        audio_file = self.cleaned_data.get("file")
+        if audio_file:
+            valid_mime_types = ["audio/mpeg", "audio/wav", "audio/mp3"]
+            mime_type, random_str = mimetypes.guess_type(audio_file.name)
+            if mime_type is None or mime_type not in valid_mime_types:
+                raise forms.ValidationError(
+                    _("Invalid audio file type"), code="invalid_file_type"
+                )
+        return audio_file
+
 
 class SubtitleFileForm(forms.Form):
     subtitle_file = forms.FileField(
-        label="Select a file",
+        label="Select a subtitle file",
         help_text="insert a subtitle file",
         widget=forms.FileInput(attrs={"accept": ".srt"}),
     )
@@ -54,3 +69,26 @@ def helper(self):
         helper.form_method = "POST"
         helper.inputs.append(Submit("submit", "Submit"))
         return helper
+
+    def clean_subtitle_file(self):
+        subtitle_file = self.cleaned_data.get("subtitle_file")
+        if subtitle_file:
+            try:
+                self.subtitle_texts = utils.process_subtitle_file(subtitle_file)
+            except Exception as e:
+                raise forms.ValidationError(f"Error processing subtitle file: {str(e)}")
+        return subtitle_file
+
+    def save(self, audio_file_instance):
+        if hasattr(self, "subtitle_texts"):
+            subtitles = [
+                Subtitle.objects.create(
+                    audio_file=audio_file_instance,
+                    start_time=subtitle["start_time"],
+                    end_time=subtitle["end_time"],
+                    content=subtitle["content"],
+                )
+                for subtitle in self.subtitle_texts
+            ]
+            return subtitles
+        return []

waveform_audio/migrations/0001_initial.py

@@ -1,7 +1,7 @@
-# Generated by Django 4.2.1 on 2023-06-30 06:06
+# Generated by Django 5.1 on 2024-08-24 16:53
 
-from django.db import migrations, models
 import django.db.models.deletion
+from django.db import migrations, models
 
 
 class Migration(migrations.Migration):
@@ -15,10 +15,13 @@ class Migration(migrations.Migration):
             name="AudioFile",
             fields=[
                 ("id", models.AutoField(primary_key=True, serialize=False)),
-                ("file", models.FileField(upload_to="audio/")),
+                ("file", models.FileField(unique=True, upload_to="audio/")),
+                ("file_hash", models.CharField(unique=True)),
                 ("timestamp", models.DateTimeField(auto_now_add=True)),
             ],
             options={
+                "verbose_name": "Audio File",
+                "verbose_name_plural": "Audio Files",
                 "db_table": "audio_file",
                 "ordering": ["timestamp"],
             },
@@ -29,34 +32,56 @@ class Migration(migrations.Migration):
                 ("id", models.AutoField(primary_key=True, serialize=False)),
                 ("start_time", models.TimeField()),
                 ("end_time", models.TimeField()),
+                ("timestamp", models.DateTimeField(auto_now_add=True)),
                 (
-                    "annotation",
+                    "content",
                     models.CharField(
-                        choices=[
-                            ("speech", "Speech"),
-                            ("music", "Music"),
-                            ("noise", "Noise"),
-                            ("laughter", "Laughter"),
-                            ("other", "Other"),
-                            ("unknown", "Unknown"),
-                        ],
-                        default="unknown",
-                        max_length=10,
+                        help_text="Annotation label of the audio segment",
+                        max_length=255,
                     ),
                 ),
-                ("timestamp", models.DateTimeField(auto_now_add=True)),
                 (
                     "audio_file",
                     models.ForeignKey(
                         on_delete=django.db.models.deletion.CASCADE,
-                        related_name="annotations",
                         to="waveform_audio.audiofile",
                     ),
                 ),
             ],
             options={
+                "verbose_name": "Audio Annotation",
+                "verbose_name_plural": "Audio Annotations",
                 "db_table": "audio_annotation",
                 "ordering": ["start_time", "end_time"],
+                "abstract": False,
+                "unique_together": {
+                    ("audio_file", "start_time", "end_time", "content")
+                },
+            },
+        ),
+        migrations.CreateModel(
+            name="Subtitle",
+            fields=[
+                ("id", models.AutoField(primary_key=True, serialize=False)),
+                ("start_time", models.TimeField()),
+                ("end_time", models.TimeField()),
+                ("timestamp", models.DateTimeField(auto_now_add=True)),
+                ("content", models.TextField(help_text="Subtitle content")),
+                (
+                    "audio_file",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to="waveform_audio.audiofile",
+                    ),
+                ),
+            ],
+            options={
+                "verbose_name": "Subtitle",
+                "verbose_name_plural": "Subtitles",
+                "db_table": "subtitle",
+                "ordering": ["start_time", "end_time"],
+                "abstract": False,
+                "unique_together": {("audio_file", "start_time", "end_time")},
             },
         ),
     ]