Fix integration tests

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "speech-prep"
-version = "0.1.0"
+dynamic = ["version"]  # Tell build tools that version is determined dynamically
 description = "Audio preprocessing toolkit for speech-to-text applications using ffmpeg"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -33,9 +33,13 @@ Repository = "https://github.com/dimdasci/speech-prep"
 Issues = "https://github.com/dimdasci/speech-prep/issues"
 
 [build-system]
-requires = ["hatchling"]
+requires = ["hatchling", "hatch-vcs"]
 build-backend = "hatchling.build"
 
+[tool.hatch.version]
+source = "vcs"
+path = "src/speech_prep/_version.py"
+
 [tool.ruff]
 target-version = "py39"
 line-length = 88
@@ -107,4 +111,5 @@ dev = [
     "pytest-mock>=3.11.1",
     "pydub>=0.25.1",
     "pre-commit>=4.2.0",
+    "hatch-vcs>=0.5.0",
 ]

scripts/dev.sh

@@ -12,6 +12,7 @@ function usage() {
   echo "  fix       - Fix linting issues automatically"
   echo "  check-all - Run all checks"
   echo "  tests     - Run tests"
+  echo "  hooks     - Run all pre-commit hooks on all files"
   echo ""
   exit 1
 }
@@ -51,6 +52,10 @@ case "$1" in
     echo "🧪 Running tests..."
     uv run pytest tests/
     ;;
+  hooks)
+    echo "🪝 Running all pre-commit hooks on all files..."
+    uv run pre-commit run --all-files
+    ;;
   *)
     usage
     ;;

src/speech_prep/__init__.py

@@ -5,6 +5,7 @@
 including silence detection and removal, speed adjustment, and format conversion.
 """
 
+from ._version import __version__
 from .core import SoundFile
 from .exceptions import (
     AudioPropertiesError,
@@ -14,13 +15,12 @@
     SpeechPrepError,
 )
 
-__version__ = "0.1.0"
-
 __all__ = [
     "SoundFile",
     "SpeechPrepError",
     "FFmpegError",
     "FileValidationError",
     "AudioPropertiesError",
     "SilenceDetectionError",
+    "__version__",
 ]

src/speech_prep/_version.py

@@ -0,0 +1,4 @@
+"""Version information."""
+
+# This file is automatically generated by hatch-vcs
+__version__ = "0.0.0"  # This will be replaced during build

src/speech_prep/core.py

@@ -41,9 +41,7 @@ def __init__(
             raise FileNotFoundError(f"Audio file not found: {self.path}")
 
         try:
-            duration, self.format, file_size = get_audio_properties(self.path)
-            self.duration = float(duration)
-            self.file_size = int(file_size)
+            self.duration, self.file_size, self.format = get_audio_properties(self.path)
         except Exception as e:
             raise SpeechPrepError(f"Failed to extract metadata: {e}") from e
 

tests/integration/__init__.py

@@ -0,0 +1 @@
+"""Integration tests for speech-prep package."""

tests/integration/test_sound_file_integration.py

@@ -0,0 +1,127 @@
+"""Integration tests for SoundFile class using real files and no mocks."""
+
+import shutil
+
+import pytest
+
+from speech_prep.core import SoundFile
+from speech_prep.exceptions import SpeechPrepError
+
+# Skip the entire module if ffmpeg is not installed
+pytestmark = pytest.mark.skipif(
+    shutil.which("ffmpeg") is None, reason="ffmpeg is required for integration tests"
+)
+
+
+@pytest.fixture
+def check_audio_file_exists(audio_file_with_silence):
+    """Ensure the test audio file exists before running tests."""
+    file_path, _ = audio_file_with_silence
+    if not file_path.exists():
+        pytest.skip(f"Test audio file {file_path} not found")
+    return file_path
+
+
+class TestSoundFileIntegrationWithRealFiles:
+    """
+    Integration tests for SoundFile class using real files and no mocks.
+
+    These tests verify that the SoundFile class works correctly with real audio files
+    and the actual implementations of its dependencies.
+    """
+
+    def test_soundfile_initialization(self, check_audio_file_exists):
+        """Test SoundFile initialization with a real audio file."""
+        # Get the real audio file
+        file_path = check_audio_file_exists
+
+        # Create a SoundFile instance without any mocks
+        sound_file = SoundFile(file_path)
+
+        # Verify basic properties
+        assert sound_file.path == file_path
+        assert sound_file.duration > 0
+        assert isinstance(sound_file.format, str)
+        assert sound_file.file_size > 0
+
+        # Verify silence detection
+        assert isinstance(sound_file.silence_periods, list)
+
+        # Print debug info
+        print(f"File: {file_path}")
+        print(f"Duration: {sound_file.duration}")
+        print(f"Format: {sound_file.format}")
+        print(f"File size: {sound_file.file_size}")
+        print(f"Silence periods: {len(sound_file.silence_periods)}")
+
+    def test_full_processing_pipeline(self, check_audio_file_exists, temp_dir):
+        """
+        Test a complete processing pipeline with real operations.
+
+        This test performs:
+        1. SoundFile initialization
+        2. Silence stripping
+        3. Speed adjustment
+        4. Format conversion
+
+        No functions are mocked, so this is a true integration test.
+        """
+        # Get the real audio file
+        input_path = check_audio_file_exists
+
+        # Define paths for outputs
+        stripped_path = temp_dir / "real_stripped.wav"
+        sped_path = temp_dir / "real_sped.wav"
+        converted_path = temp_dir / "real_final.mp3"
+
+        # Create initial SoundFile
+        original = SoundFile(input_path)
+        print(f"Original file: {original}")
+
+        # 1. Strip silence
+        stripped = original.strip(stripped_path)
+        assert stripped is not None, "Strip operation failed"
+        assert stripped.path.exists(), "Stripped file doesn't exist"
+        assert (
+            stripped.duration <= original.duration
+        ), "Stripped file should be shorter or equal"
+        print(f"Stripped file: {stripped}")
+
+        # 2. Adjust speed
+        speed_factor = 1.5
+        sped = stripped.speed(sped_path, speed_factor)
+        assert sped is not None, "Speed operation failed"
+        assert sped.path.exists(), "Sped file doesn't exist"
+        # Duration should be approximately 1/speed_factor of the original
+        # Allow for some tolerance due to encoding differences
+        expected_duration = stripped.duration / speed_factor
+        tolerance = 0.2  # 20% tolerance
+        assert (
+            abs(sped.duration - expected_duration) <= expected_duration * tolerance
+        ), f"Speed adjustment incorrect: {sped.duration} vs {expected_duration}"
+        print(f"Sped file: {sped}")
+
+        # 3. Convert format
+        converted = sped.convert(converted_path, audio_bitrate="192k")
+        assert converted is not None, "Convert operation failed"
+        assert converted.path.exists(), "Converted file doesn't exist"
+        assert converted.format.lower() == "mp3", "Format conversion failed"
+        print(f"Converted file: {converted}")
+
+        # Verify final file properties
+        assert converted.duration > 0, "Final file has no duration"
+        assert converted.file_size > 0, "Final file has no size"
+
+    def test_error_handling_with_real_files(self, temp_dir):
+        """Test error handling with real but problematic files."""
+        # Create an empty file (which will cause processing errors)
+        empty_file = temp_dir / "empty.wav"
+        empty_file.touch()
+
+        # Attempt to create a SoundFile from the empty file
+        with pytest.raises(SpeechPrepError) as exc_info:
+            SoundFile(empty_file)
+
+        assert "Failed to extract metadata" in str(
+            exc_info.value
+        ), "Empty file should raise metadata extraction error"

tests/test_core.py

@@ -52,7 +52,7 @@ def test_init_silence_detection_error(
         # Mock get_audio_properties to return test values
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(5.0, "wav", 10000),
+            return_value=(5.0, 10000, "wav"),
         )
 
         # Should not raise an exception, but should set silence_periods to empty list
@@ -74,7 +74,7 @@ def test_equality_same_path(
         # Mock dependencies to ensure consistent behavior
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(5.0, "wav", 10000),
+            return_value=(5.0, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -97,7 +97,7 @@ def test_equality_different_path(self, mocker: MockFixture, temp_dir: Path) -> N
         # Mock dependencies to ensure consistent behavior
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(5.0, "wav", 10000),
+            return_value=(5.0, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -118,7 +118,7 @@ def test_equality_non_soundfile(
         # Mock dependencies to ensure consistent behavior
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(5.0, "wav", 10000),
+            return_value=(5.0, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -145,7 +145,7 @@ def test_str_basic_info(
         # Mock dependencies to return consistent values
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(duration, "wav", 10000),
+            return_value=(duration, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -172,7 +172,7 @@ def test_str_no_silence_periods(
         # Mock dependencies
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(duration, "wav", 10000),
+            return_value=(duration, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -200,7 +200,7 @@ def test_str_few_silence_periods(
         # Mock dependencies
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(duration, "wav", 10000),
+            return_value=(duration, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -231,7 +231,7 @@ def test_str_many_silence_periods(
         # Mock dependencies
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(duration, "wav", 10000),
+            return_value=(duration, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -278,7 +278,7 @@ def test_strip_success(
         # Mock dependencies for the input file
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            side_effect=[(duration, "wav", 10000), (3.0, "wav", 8000)],
+            side_effect=[(duration, 10000, "wav"), (3.0, 8000, "wav")],
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -327,7 +327,7 @@ def test_strip_no_silence(
         # Mock dependencies
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(duration, "wav", 10000),
+            return_value=(duration, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -362,7 +362,7 @@ def test_strip_error(
         # Mock dependencies
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(duration, "wav", 10000),
+            return_value=(duration, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -411,7 +411,7 @@ def test_convert_success(
         # Mock dependencies for the input file
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            side_effect=[(duration, "wav", 10000), (duration, "mp3", 8000)],
+            side_effect=[(duration, 10000, "wav"), (duration, 8000, "mp3")],
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -454,7 +454,7 @@ def test_convert_error(
         # Mock dependencies
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(duration, "wav", 10000),
+            return_value=(duration, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -501,8 +501,8 @@ def test_speed_success(
         mocker.patch(
             "speech_prep.core.get_audio_properties",
             side_effect=[
-                (duration, "wav", 10000),
-                (duration / speed_factor, "wav", 8000),
+                (duration, 10000, "wav"),
+                (duration / speed_factor, 8000, "wav"),
             ],
         )
         mocker.patch(
@@ -550,7 +550,7 @@ def test_speed_error(
         # Mock dependencies
         mocker.patch(
             "speech_prep.core.get_audio_properties",
-            return_value=(duration, "wav", 10000),
+            return_value=(duration, 10000, "wav"),
         )
         mocker.patch(
             "speech_prep.core.detect_silence",
@@ -610,13 +610,13 @@ def mock_process_file(*args, **kwargs):
         # Mock get_audio_properties to return different values for different files
         def mock_get_properties(file_path):
             if str(file_path).endswith("stripped.wav"):
-                return 3.0, "wav", 8000
+                return 3.0, 8000, "wav"
             elif str(file_path).endswith("sped.wav"):
-                return 2.0, "wav", 7000
+                return 2.0, 7000, "wav"
             elif str(file_path).endswith("final.mp3"):
-                return 2.0, "mp3", 6000
+                return 2.0, 6000, "mp3"
             else:
-                return 5.0, "wav", 10000
+                return 5.0, 10000, "wav"
 
         mocker.patch(
             "speech_prep.core.get_audio_properties", side_effect=mock_get_properties