Extract noisereduce and visrecognize to optional dependencies

.github/workflows/python-package.yml

@@ -16,14 +16,13 @@ on:
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: ["3.9", "3.10", "3.11"]
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
 
     - name: install ffmpeg
       run: |
@@ -44,29 +43,71 @@ jobs:
         cached: ${{ steps.cache-llvm.outputs.cache-hit }}
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
+        cache: 'pip'
+
+    - name: Install dependencies
+      run: |
+        sudo apt install libsndfile1-dev
+        python -m pip install wheel
+        python -m pip install --upgrade pip
+        python -m pip install flake8
+        pip install -e .[visrecognize,noisereduce,test]
 
-    - name: Cache pip
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
+    - name: Test with pytest
+      run: |
+        pytest
+
+
+  build-minimal:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11"]
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: install ffmpeg
+      run: |
+        sudo apt-get update && sudo apt-get install ffmpeg -y
+
+    - name: Cache LLVM and Clang
+      id: cache-llvm
       uses: actions/cache@v2
       with:
-        # This path is specific to Ubuntu
-        path: ~/.cache/pip
-        # Look to see if there is a cache hit for the corresponding requirements file
-        key: ${{ runner.os }}-pip-${{ hashFiles('requirements.txt') }}
-        restore-keys: |
-          ${{ runner.os }}-pip-
-          ${{ runner.os }}-
+        path: ${{ runner.temp }}/llvm
+        key: llvm-10.0
+
+    - name: Install LLVM and Clang
+      uses: KyleMayes/install-llvm-action@v1
+      with:
+        version: "10.0"
+        directory: ${{ runner.temp }}/llvm
+        cached: ${{ steps.cache-llvm.outputs.cache-hit }}
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+        cache: 'pip'
 
     - name: Install dependencies
       run: |
         sudo apt install libsndfile1-dev
         python -m pip install wheel
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-        if [ -f requirements_dev.txt ]; then pip install -r requirements_dev.txt; fi
+        python -m pip install flake8
+        pip install -e .[test]
 
     - name: Lint with flake8
       run: |
@@ -79,9 +120,42 @@ jobs:
       run: |
         pytest
 
-# replaced with this https://github.com/KyleMayes/install-llvm-action
-# sudo apt install llvm-9
-# sudo -i
-# cd /usr/bin
-# rm llvm-config #if it exists already, which probably it does
-# ln -s llvm-config-10 llvm-config
+  #
+  # build-windows:
+  #   runs-on: windows-latest
+  #   strategy:
+  #     matrix:
+  #       python-version: ["3.9", "3.10", "3.11"]
+  #
+  #   steps:
+  #   - uses: actions/checkout@v4
+  #   - uses: FedericoCarboni/setup-ffmpeg@v3
+  #     id: setup-ffmpeg
+  #     with:
+  #       ffmpeg-version: release
+  #       linking-type: static
+  #       github-token: ${{ github.server_url == 'https://github.com' && github.token || '' }}
+  #
+  #   - name: Set up Python ${{ matrix.python-version }}
+  #     uses: actions/setup-python@v5
+  #     with:
+  #       python-version: ${{ matrix.python-version }}
+  #       cache: 'pip'
+  #
+  #   - name: Install dependencies
+  #     run: |
+  #       python -m pip install wheel
+  #       python -m pip install --upgrade pip
+  #       python -m pip install flake8
+  #       pip install -e .[visrecognize,noisereduce,test]
+  #
+  #   - name: Lint with flake8
+  #     run: |
+  #       # stop the build if there are Python syntax errors or undefined names
+  #       flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+  #       # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+  #       flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+  #
+  #   - name: Test with pytest
+  #     run: |
+  #       pytest

.github/workflows/python-publish.yml

@@ -20,16 +20,16 @@ jobs:
     - uses: FedericoCarboni/setup-ffmpeg@v1-beta
       id: setup-ffmpeg
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: '3.x'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install setuptools wheel twine
+        pip install build wheel twine
     - name: Build and publish
       run: |
-        python setup.py sdist bdist_wheel
+        python -m build --wheel
     - name: Publish package
       uses: pypa/[email protected]
       with:

CHANGELOG.md

@@ -1,5 +1,12 @@
 # Change Log
 
+## [1.3.0] 2024 - 06 - 02
+
+### Changed
+
+- Migrated to pyproject.toml
+- Extracted noisereduce and visrecognize to optional dependencies
+
 ## [1.2.4] 2024 - 01 - 07
 
 ### Added

README.md

@@ -54,6 +54,11 @@ pip install audalign
 
 in the directory
 
+### Optional dependencies
+
+- visrecognize: additional recognizer based on spectrogram image comparison. `pip install audalign[visrecognize]`
+- noisereduce: wrapper utils around [timsainb/noisereduce](https://github.com/timsainb/noisereduce). `pip install audalign[noisereduce]`
+
 ## Recognizers
 
 There are currently four included recognizers, each with their own config objects.
@@ -64,7 +69,7 @@ import audalign as ad
 fingerprint_rec = ad.FingerprintRecognizer()
 correlation_rec = ad.CorrelationRecognizer()
 cor_spec_rec = ad.CorrelationSpectrogramRecognizer()
-visual_rec = ad.VisualRecognizer()
+visual_rec = ad.VisualRecognizer() # requires installting optional visrecognize dependencies
 
 fingerprint_rec.config.set_accuracy(3)
 # recognizer.config.some_item
@@ -108,7 +113,7 @@ Correlation is more precise than fingerprints and will always give a best alignm
 ## Other Functions
 
 ```python
-# wrapper for timsainb/noisereduce
+# wrapper for timsainb/noisereduce, optional dependency
 ad.remove_noise_file(
     "target/file",
     "5", # noise start in seconds

audalign/filehandler.py

@@ -4,15 +4,22 @@
 import os
 import typing
 from functools import partial
+from functools import wraps
 
-import noisereduce
 import numpy as np
 from numpy.core.defchararray import array
 from pydub import AudioSegment, effects
 from pydub.exceptions import CouldntDecodeError
 
 from audalign.config import BaseConfig
 
+try:
+    import noisereduce
+except ImportError:
+    # Optional dependency
+    ...
+
+
 cant_write_ext = [".mov", ".mp4", ".m4a"]
 cant_read_ext = [".txt", ".md", ".pkf", ".py", ".pyc"]
 can_read_ext = [
@@ -30,6 +37,18 @@
     ".flac",
 ]
 
+def _import_optional_dependencies(func):
+    @wraps(func)
+    def wrapper_decorator(*args, **kwargs):
+        try:
+            import noisereduce
+        except ImportError:
+            raise ImportError("skimage not found, please install 'visrecognize' module")
+        results = func(*args, **kwargs)
+        return results
+
+    return wrapper_decorator
+
 
 def find_files(path, extensions=["*"]):
     """
@@ -192,6 +211,7 @@ def _int16ify_data(data: array):
     return data.astype(np.int16)
 
 
+@_import_optional_dependencies
 def noise_remove(
     filepath,
     noise_start,
@@ -296,6 +316,7 @@ def noise_remove_directory(
             _reduce_noise(i)
 
 
+@_import_optional_dependencies
 def _remove_noise(
     file_path,
     noise_section=[],

audalign/recognizers/visrecognize/__init__.py

@@ -9,11 +9,24 @@
 import typing
 import copy
 from functools import partial
+from functools import wraps
 
+def _import_optional_dependencies(func):
+    @wraps(func)
+    def wrapper_decorator(*args, **kwargs):
+        try:
+            import skimage
+        except ImportError:
+            raise ImportError("skimage not found, please install 'visrecognize' module")
+        results = func(*args, **kwargs)
+        return results
+
+    return wrapper_decorator
 
 class VisualRecognizer(BaseRecognizer):
     config: VisualConfig
 
+    @_import_optional_dependencies
     def __init__(self, config: VisualConfig = None):
         self.config = VisualConfig() if config is None else config
         self.last_recognition = None

audalign/recognizers/visrecognize/visrecognize.py

@@ -12,8 +12,12 @@
 from audalign.filehandler import find_files, get_shifted_file, read
 from PIL import Image
 from pydub.exceptions import CouldntDecodeError
-from skimage.metrics import mean_squared_error
-from skimage.metrics import structural_similarity as ssim
+try:
+    from skimage.metrics import mean_squared_error
+    from skimage.metrics import structural_similarity as ssim
+except ImportError:
+    # Optional dependency
+    ...
 
 upper_clip = 255
 

pyproject.toml

@@ -0,0 +1,57 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "audalign"
+version = "1.3.0"
+description = "Audio Alignment and Recognition in Python"
+requires-python = ">= 3.8"
+readme = "README.md"
+license = "MIT"
+authors = [
+    { name = "Ben Miller", email = "[email protected]" },
+]
+maintainers = [
+    { name = "Ben Miller", email = "[email protected]" },
+]
+keywords = [
+    "align",
+    "alignment",
+    "audio",
+    "fingerprinting",
+    "music",
+    "python",
+]
+dependencies = [
+    "matplotlib==3.8.2",
+    "numpy==1.26.4",
+    "pydub==0.25.1",
+    "scipy==1.12.0",
+    "setuptools==59.6.0",
+    "tqdm==4.66.2",
+]
+
+[project.optional-dependencies]
+noisereduce = [
+    "noisereduce==2.0.1",
+    "torch==2.2.0",
+]
+visrecognize = [
+    "Pillow==10.2.0",
+    "scikit-image==0.19.3",
+]
+test = [
+    "pytest==8.0.0",
+    "pytest-xdist==3.1.0",
+]
+
+[project.urls]
+Homepage = "http://github.com/benfmiller/audalign"
+Documentation = "https://github.com/benfmiller/audalign/wiki"
+Changelog = "https://github.com/benfmiller/audalign/blob/main/CHANGELOG.md"
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "/audalign",
+]