Changes for supporting newer python/numpy

.github/workflows/ci.yml

@@ -0,0 +1,68 @@
+name: CI
+
+on:
+  [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        python-version: ["3.11", "3.12", "3.13"]
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install system dependencies (Ubuntu)
+      if: runner.os == 'Linux'
+      run: |
+        bash install_dependencies.sh
+
+    - name: Install system dependencies (Windows)
+      if: runner.os == 'Windows'
+      run: |
+        # Install chocolatey packages if needed
+        # choco install espeak --yes
+        # For now, we'll use conda-forge for cross-platform audio packages
+        echo "Windows system dependencies would be installed here"
+
+    - name: Cache pip dependencies
+      uses: actions/cache@v4
+      with:
+        path: |
+          ~/.cache/pip
+          %APPDATA%\pip\Cache
+        key: ${{ runner.os }}-pip-${{ matrix.python-version }}-${{ hashFiles('**/requirements*.txt', '**/pyproject.toml', '**/setup.py') }}
+        restore-keys: |
+          ${{ runner.os }}-pip-${{ matrix.python-version }}-
+          ${{ runner.os }}-pip-
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build setuptools wheel
+
+    - name: Build package
+      run: |
+        python -m build
+
+    - name: Install package
+      shell: bash
+      run: |
+        # Install the built package
+        pip install dist/*.whl
+
+    - name: Run tests with pytest
+      run: |
+        pip install pytest 
+        pip install -r requirements_dev.txt
+        pytest aeneas/tests
+

aeneas/cdtw/cdtw_setup.py

@@ -30,7 +30,6 @@
 from __future__ import absolute_import
 from __future__ import print_function
 from numpy import get_include
-from numpy.distutils import misc_util
 from setuptools import Extension
 from setuptools import setup
 import sys
@@ -52,7 +51,7 @@
     version="1.7.4",
     description="Python C Extension for computing the DTW as fast as your bare metal allows.",
     ext_modules=[CMODULE],
-    include_dirs=misc_util.get_numpy_include_dirs()
+    include_dirs=[get_include()]
 )
 
 print("\n[INFO] Module cdtw successfully compiled\n")

aeneas/cmfcc/cmfcc_setup.py

@@ -30,7 +30,6 @@
 from __future__ import absolute_import
 from __future__ import print_function
 from numpy import get_include
-from numpy.distutils import misc_util
 from setuptools import Extension
 from setuptools import setup
 import sys
@@ -53,7 +52,7 @@
     version="1.7.4",
     description="Python C Extension for computing the MFCCs as fast as your bare metal allows.",
     ext_modules=[CMODULE],
-    include_dirs=misc_util.get_numpy_include_dirs()
+    include_dirs=[get_include()]
 )
 
 print("\n[INFO] Module cmfcc successfully compiled\n")

aeneas/cwave/cwave_setup.py

@@ -30,7 +30,6 @@
 from __future__ import absolute_import
 from __future__ import print_function
 from numpy import get_include
-from numpy.distutils import misc_util
 from setuptools import Extension
 from setuptools import setup
 import sys
@@ -52,7 +51,7 @@
     version="1.7.4",
     description="Python C Extension for for reading WAVE files.",
     ext_modules=[CMODULE],
-    include_dirs=misc_util.get_numpy_include_dirs()
+    include_dirs=[get_include()]
 )
 
 print("\n[INFO] Module cwave successfully compiled\n")

aeneas/tests/test_textfile.py

@@ -506,13 +506,13 @@ def test_filter_ignore_regex_strip(self):
         self.filter_ignore_regex("word", [u"word abc word"], [u"abc"])
 
     def test_filter_ignore_regex_parenthesis(self):
-        self.filter_ignore_regex("\(.*?\)", [u"(CHAR) bla bla bla"], [u"bla bla bla"])
+        self.filter_ignore_regex(r"\(.*?\)", [u"(CHAR) bla bla bla"], [u"bla bla bla"])
 
     def test_filter_ignore_regex_brackets(self):
-        self.filter_ignore_regex("\[.*?\]", [u"[CHAR] bla bla bla"], [u"bla bla bla"])
+        self.filter_ignore_regex(r"\[.*?\]", [u"[CHAR] bla bla bla"], [u"bla bla bla"])
 
     def test_filter_ignore_regex_braces(self):
-        self.filter_ignore_regex("\{.*?\}", [u"{CHAR} bla bla bla"], [u"bla bla bla"])
+        self.filter_ignore_regex(r"\{.*?\}", [u"{CHAR} bla bla bla"], [u"bla bla bla"])
 
     def test_filter_ignore_regex_entire_match(self):
         self.filter_ignore_regex("word", [u"word"], [u""])

aeneas/textfile.py

@@ -780,7 +780,7 @@ def nodes_at_level(root, level):
             indent = u" " * 2 * (level - 1)
             self.log([u"%sRegex for %s: '%s'", indent, attribute_name, regex_string])
             regex = re.compile(r".*\b" + regex_string + r"\b.*")
-            return root.findAll(attrs={attribute_name: regex})
+            return root.find_all(attrs={attribute_name: regex})
         #
         # TODO better and/or parametric parsing,
         #      for example, removing tags but keeping text, etc.
@@ -953,7 +953,7 @@ def filter_attributes():
         ids = []
         filter_attributes = filter_attributes()
         self.log([u"Finding elements matching attributes '%s'", filter_attributes])
-        nodes = soup.findAll(attrs=filter_attributes)
+        nodes = soup.find_all(attrs=filter_attributes)
         for node in nodes:
             try:
                 f_id = gf.safe_unicode(node["id"])

aeneas/wavfile.py

@@ -75,7 +75,7 @@ def _read_data_chunk(fid, comp, noc, bits, mmap=False):
         else:
             dtype += 'f%d' % bytes
     if not mmap:
-        data = numpy.fromstring(fid.read(size), dtype=dtype)
+        data = numpy.frombuffer(fid.read(size), dtype=dtype)
     else:
         start = fid.tell()
         data = numpy.memmap(fid, dtype=dtype, mode='c', offset=start,

pyproject.toml

@@ -0,0 +1,160 @@
+[build-system]
+requires = ["setuptools", "wheel", "numpy"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "aeneas"
+version = "1.7.4.0"
+description = "aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)"
+readme = "README.rst"
+authors = [
+    { name = "Alberto Pettarin", email = "alberto@albertopettarin.it" }
+]
+license = "AGPL-3.0-only"
+keywords = [
+    "AUD",
+    "AWS Polly TTS API",
+    "CSV",
+    "DTW",
+    "EAF",
+    "ELAN",
+    "EPUB 3 Media Overlay",
+    "EPUB 3",
+    "EPUB",
+    "Festival",
+    "JSON",
+    "MFCC",
+    "Mel-frequency cepstral coefficients",
+    "Nuance TTS API",
+    "ReadBeyond Sync",
+    "ReadBeyond",
+    "SBV",
+    "SMIL",
+    "SRT",
+    "SSV",
+    "SUB",
+    "TGT",
+    "TSV",
+    "TTML",
+    "TTS",
+    "TextGrid",
+    "VTT",
+    "XML",
+    "aeneas",
+    "audio/text alignment",
+    "dynamic time warping",
+    "eSpeak",
+    "eSpeak-ng",
+    "espeak",
+    "espeak-ng",
+    "festival",
+    "ffmpeg",
+    "ffprobe",
+    "forced alignment",
+    "media overlay",
+    "rb_smil_emulator",
+    "speech to text",
+    "subtitles",
+    "sync",
+    "synchronization",
+    "text to speech",
+    "text2wave",
+    "tts",
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "Intended Audience :: End Users/Desktop",
+    "Intended Audience :: Science/Research",
+    "Natural Language :: English",
+    "Operating System :: MacOS :: MacOS X",
+    "Operating System :: Microsoft :: Windows",
+    "Operating System :: POSIX :: Linux",
+    "Programming Language :: C",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 2",
+    "Programming Language :: Python :: 2.7",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.4",
+    "Programming Language :: Python :: 3.5",
+    "Topic :: Education",
+    "Topic :: Multimedia",
+    "Topic :: Multimedia :: Sound/Audio",
+    "Topic :: Multimedia :: Sound/Audio :: Analysis",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Topic :: Printing",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Scientific/Engineering :: Mathematics",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Text Processing",
+    "Topic :: Text Processing :: Linguistic",
+    "Topic :: Text Processing :: Markup",
+    "Topic :: Text Processing :: Markup :: HTML",
+    "Topic :: Text Processing :: Markup :: XML",
+    "Topic :: Utilities"
+]
+dependencies = [
+    "BeautifulSoup4>=4.5.1",
+    "lxml>=3.6.0",
+    "numpy>=1.9"
+]
+
+[project.optional-dependencies]
+full = [
+    "boto3>=1.4.2",
+    "Pillow>=3.1.1",
+    "requests>=2.9.1",
+    "tgt>=1.4.2",
+    "youtube-dl>=2016.9.27",
+]
+nopillow = [
+    "boto3>=1.4.2",
+    "requests>=2.9.1",
+    "tgt>=1.4.2",
+    "youtube-dl>=2016.9.27",
+]
+boto3 = ["boto3>=1.4.2"]
+pillow = ["Pillow>=3.1.1"]
+requests = ["requests>=2.9.1"]
+tgt = ["tgt>=1.4.2"]
+
+[project.urls]
+Homepage = "https://github.com/readbeyond/aeneas"
+
+[project.scripts]
+aeneas_check_setup = "aeneas.tools.bin.aeneas_check_setup:main"
+aeneas_convert_syncmap = "aeneas.tools.bin.aeneas_convert_syncmap:main"
+aeneas_download = "aeneas.tools.bin.aeneas_download:main"
+aeneas_execute_job = "aeneas.tools.bin.aeneas_execute_job:main"
+aeneas_execute_task = "aeneas.tools.bin.aeneas_execute_task:main"
+aeneas_plot_waveform = "aeneas.tools.bin.aeneas_plot_waveform:main"
+aeneas_synthesize_text = "aeneas.tools.bin.aeneas_synthesize_text:main"
+aeneas_validate = "aeneas.tools.bin.aeneas_validate:main"
+
+[tool.setuptools]
+packages = [
+    "aeneas",
+    "aeneas.cdtw",
+    "aeneas.cew",
+    "aeneas.cfw",
+    "aeneas.cmfcc",
+    "aeneas.cwave",
+    "aeneas.extra",
+    "aeneas.syncmap",
+    "aeneas.tools",
+    "aeneas.ttswrappers",
+    "aeneas.tools.bin",
+]
+
+[tool.setuptools.package-data]
+"aeneas" = ["res/*", "*.md"]
+"aeneas.cdtw" = ["*.c", "*.h", "*.md"]
+"aeneas.cew" = ["*.c", "*.h", "*.md", "*.dll", "*.cc"]
+"aeneas.cmfcc" = ["*.c", "*.h", "*.md"]
+"aeneas.cwave" = ["*.c", "*.h", "*.md"]
+"aeneas.extra" = ["*.md"]
+"aeneas.syncmap" = ["*.md"]
+"aeneas.tools" = ["res/*", "*.md"]
+"aeneas.ttswrappers" = ["*.md"]