Refactor shared constants and remove deprecated function

README.md

@@ -3,37 +3,17 @@
 </p>
 
 <p align="center">
-  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/releases/latest">
-    <img src="https://img.shields.io/github/v/release/BrainBehaviorAnalyticsLab/PyPLLR_GUI?label=Release&style=flat-square" alt="Release">
-  </a>
-  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/releases">
-    <img src="https://img.shields.io/github/downloads/BrainBehaviorAnalyticsLab/PyPLLR_GUI/total?style=flat-square" alt="Downloads">
-  </a>
-  <img src="./assets/coverage.svg" alt="Coverage">
+  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/releases/latest"><img src="https://img.shields.io/github/v/release/BrainBehaviorAnalyticsLab/PyPLLR_GUI?label=Release&style=flat-square" alt="Release"></a>
+  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/releases"><img src="https://img.shields.io/github/downloads/BrainBehaviorAnalyticsLab/PyPLLR_GUI/total?style=flat-square" alt="Downloads"></a>
+  <a href="https://github.com/WISCLab/shred-guard"><img src="https://img.shields.io/badge/ShredGuard-ON-06B6D4?logo=git&logoColor=white&style=flat-square" alt="ShredGuard"></a>
+  <a href="https://voxkit.atlassian.net/jira/software/projects/VOX/boards/2/"><img src="https://img.shields.io/badge/Project-Jira-0052CC?logo=jira&style=flat-square" alt="Jira"></a>
 </p>
 
 <p align="center">
-  <a href="https://github.com/WISCLab/shred-guard">
-    <img src="https://img.shields.io/badge/SHREDGUARD-Configured-06B6D4?style=for-the-badge&logo=git&logoColor=white" alt="ShredGuard">
-  </a>
-</p>
-
-<p align="center">
-  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/actions/workflows/tests-ubuntu.yml">
-    <img src="https://img.shields.io/github/actions/workflow/status/BrainBehaviorAnalyticsLab/PyPLLR_GUI/tests-ubuntu.yml?branch=main&label=Ubuntu&logo=ubuntu&style=flat-square" alt="Ubuntu Tests">
-  </a>
-  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/actions/workflows/tests-macos.yml">
-    <img src="https://img.shields.io/github/actions/workflow/status/BrainBehaviorAnalyticsLab/PyPLLR_GUI/tests-macos.yml?branch=main&label=macOS&logo=apple&style=flat-square" alt="macOS Tests">
-  </a>
-  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/actions/workflows/tests-windows.yml">
-    <img src="https://img.shields.io/github/actions/workflow/status/BrainBehaviorAnalyticsLab/PyPLLR_GUI/tests-windows.yml?branch=main&label=Windows&logo=windows&style=flat-square" alt="Windows Tests">
-  </a>
-  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/actions/workflows/code-quality.yml">
-    <img src="https://img.shields.io/github/actions/workflow/status/BrainBehaviorAnalyticsLab/PyPLLR_GUI/code-quality.yml?branch=main&label=Code%20Quality&style=flat-square" alt="Code Quality">
-  </a>
-  <a href="https://voxkit.atlassian.net/jira/software/projects/VOX/boards/2/">
-    <img src="https://img.shields.io/badge/Project-Jira-0052CC?logo=jira&style=flat-square" alt="Jira">
-  </a>
+  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/actions/workflows/tests-ubuntu.yml"><img src="https://img.shields.io/github/actions/workflow/status/BrainBehaviorAnalyticsLab/PyPLLR_GUI/tests-ubuntu.yml?branch=main&label=Ubuntu&logo=ubuntu&style=flat-square" alt="Ubuntu Tests"></a>
+  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/actions/workflows/tests-macos.yml"><img src="https://img.shields.io/github/actions/workflow/status/BrainBehaviorAnalyticsLab/PyPLLR_GUI/tests-macos.yml?branch=main&label=macOS&logo=apple&style=flat-square" alt="macOS Tests"></a>
+  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/actions/workflows/tests-windows.yml"><img src="https://img.shields.io/github/actions/workflow/status/BrainBehaviorAnalyticsLab/PyPLLR_GUI/tests-windows.yml?branch=main&label=Windows&logo=windows&style=flat-square" alt="Windows Tests"></a>
+  <a href="https://github.com/BrainBehaviorAnalyticsLab/PyPLLR_GUI/actions/workflows/code-quality.yml"><img src="https://img.shields.io/github/actions/workflow/status/BrainBehaviorAnalyticsLab/PyPLLR_GUI/code-quality.yml?branch=main&label=Code%20Quality&style=flat-square" alt="Code Quality"></a>
 </p>
 
 > [!IMPORTANT]

src/voxkit/analyzers/audio_format_profile.py

@@ -18,6 +18,8 @@
 from pathlib import Path
 from typing import Any, Dict, List
 
+from voxkit.storage.constants import SUPERSET_AUDIO_EXTENSIONS
+
 from .base import DatasetAnalyzer
 
 logger = logging.getLogger(__name__)
@@ -38,7 +40,7 @@ def analyze(self, dataset_path: str) -> List[Dict[str, Any]]:
         import torchaudio
 
         results = []
-        audio_extensions = {".wav", ".flac", ".mp3", ".ogg", ".m4a"}
+        audio_extensions = SUPERSET_AUDIO_EXTENSIONS
 
         try:
             for entry in os.scandir(dataset_path):

src/voxkit/analyzers/clip_duration_statistics.py

@@ -17,6 +17,8 @@
 from pathlib import Path
 from typing import Any, Dict, List
 
+from voxkit.storage.constants import SUPERSET_AUDIO_EXTENSIONS
+
 from .base import DatasetAnalyzer
 
 logger = logging.getLogger(__name__)
@@ -37,7 +39,7 @@ def analyze(self, dataset_path: str) -> List[Dict[str, Any]]:
         import torchaudio
 
         results = []
-        audio_extensions = {".wav", ".flac", ".mp3", ".ogg", ".m4a"}
+        audio_extensions = SUPERSET_AUDIO_EXTENSIONS
 
         try:
             for entry in os.scandir(dataset_path):

src/voxkit/analyzers/default_analyzer.py

@@ -17,6 +17,8 @@
 from pathlib import Path
 from typing import Any, Dict, List
 
+from voxkit.storage.constants import SUPERSET_AUDIO_EXTENSIONS
+
 from .base import DatasetAnalyzer
 
 
@@ -43,7 +45,7 @@ def analyze(self, dataset_path: str) -> List[Dict[str, Any]]:
             ``audio_file_count``.
         """
         results = []
-        audio_extensions = {".wav", ".flac", ".mp3", ".ogg", ".m4a"}
+        audio_extensions = SUPERSET_AUDIO_EXTENSIONS
 
         try:
             for entry in os.scandir(dataset_path):

src/voxkit/config/__init__.py

@@ -28,6 +28,7 @@
     get_profile_config_path,
     resolve_config_file,
 )
+from voxkit.config.constants import DEFAULT_HELP_URL
 from voxkit.config.logging_config import (
     LOG_FILE,
     reset_logging,
@@ -40,7 +41,6 @@
     get_pipeline_config,
 )
 from voxkit.config.startup_config import (
-    HELP_URL,
     STARTUP_SCRIPT,
     AppName,
     Defaults,
@@ -63,7 +63,7 @@
     "UIConfig",
     "get_pipeline_config",
     # Startup config
-    "HELP_URL",
+    "DEFAULT_HELP_URL",
     "AppName",
     "Dimensions",
     "Defaults",

src/voxkit/config/app_config.py

@@ -14,6 +14,8 @@
 
 import yaml
 
+from voxkit.config.constants import DEFAULT_HELP_URL
+
 
 def get_config_root() -> Path:
     """Get the path to the config root directory.
@@ -96,30 +98,12 @@ def resolve_config_file(filename: str) -> Path:
     if default_path.exists():
         return default_path
 
-    # Fall back to legacy location (config root)
-    legacy_path = config_root / filename
-    if legacy_path.exists():
-        return legacy_path
-
+    # Throw error if not found in either location
     raise FileNotFoundError(
-        f"Config file '{filename}' not found in profile '{profile}', "
-        f"default profile, or config root"
+        f"Config file '{filename}' not found in profile '{profile}' or default profile"
     )
 
 
-# Legacy alias for backwards compatibility
-def get_config_path() -> Path:
-    """Get the path to the config directory.
-
-    Deprecated: Use get_profile_config_path() for profile-aware loading,
-    or get_config_root() for the config root directory.
-
-    Returns:
-        Path to the active profile's config directory
-    """
-    return get_profile_config_path()
-
-
 @dataclass
 class AppConfig:
     """Application configuration data class."""
@@ -128,7 +112,7 @@ class AppConfig:
     version: str
     description: str
     introduction: str
-    help_url: str = "https://voxkit-web.vercel.app/help"
+    help_url: str | None = None
     release_date: Optional[str] = None
     release_notes: Optional[str] = None
     log_max_bytes: int = 5 * 1024 * 1024
@@ -164,7 +148,7 @@ def from_yaml(cls, config_path: Path) -> "AppConfig":
             version=version,
             description=data.get("description", ""),
             introduction=data.get("introduction", ""),
-            help_url=data.get("help_url", "https://voxkit-web.vercel.app/help"),
+            help_url=data.get("help_url", DEFAULT_HELP_URL),
             release_date=data.get("release_date"),
             release_notes=data.get("release_notes"),
             log_max_bytes=int(data.get("log_max_bytes", 5 * 1024 * 1024)),

src/voxkit/config/constants.py

@@ -0,0 +1,8 @@
+"""Constants relevant to configuration and setup.
+
+Constants
+---------
+- **DEFAULT_HELP_URL**: URL for user help documentation
+"""
+
+DEFAULT_HELP_URL = "https://voxkit-web.vercel.app/help"

src/voxkit/config/startup_config.py

@@ -3,7 +3,7 @@
 
 from voxkit.services.mfa import download_acoustic_model
 from voxkit.storage import models
-from voxkit.storage.config import MODELS_ROOT
+from voxkit.storage.constants import MODELS_ROOT
 from voxkit.storage.models import download_and_copy_huggingface_model
 from voxkit.storage.utils import get_storage_root
 
@@ -18,7 +18,6 @@
 }
 
 Mode = Literal["MFAENGINE", "W2TGENGINE"]
-HELP_URL = "https://voxkit-web.vercel.app/help"
 
 
 def startup_routine():

src/voxkit/engines/__init__.py

@@ -6,7 +6,7 @@
 - **EngineManager.list_engines**: List registered engine IDs
 - **EngineManager.get_engine**: Retrieve engine instance by ID
 - **EngineManager.get_tool_providers**: Get engines providing a specific tool type
-- **ToolType**: Literal type for compatible tool types
+- **AVAILABLE_TOOLS**: Literal type for compatible tool types
 
 Available Engines
 -----------------
@@ -48,7 +48,8 @@
 
 from typing import List
 
-from .base import AlignmentEngine, ToolType
+from .base import AlignmentEngine
+from .constants import AVAILABLE_TOOLS
 from .faster_whisper_engine import FasterWhisperEngine
 from .mfa_engine import MFAEngine
 from .w2tg_engine import W2TGEngine
@@ -82,7 +83,7 @@ def get_engine(self, engine_id: str) -> AlignmentEngine:
         except KeyError:
             raise ValueError(f"No engine with id: {engine_id}")
 
-    def get_tool_providers(self, tool: ToolType) -> dict[str, AlignmentEngine]:
+    def get_tool_providers(self, tool: AVAILABLE_TOOLS) -> dict[str, AlignmentEngine]:
         """Return a list of engines that provide the specified tool type."""
         engines = {}
         for _, engine in self._engines.items():
@@ -97,4 +98,4 @@ def get_tool_providers(self, tool: ToolType) -> dict[str, AlignmentEngine]:
 faster_whisper = FasterWhisperEngine(id="FASTERWHISPERENGINE")
 engines = EngineManager({mfa.id: mfa, faster_whisper.id: faster_whisper, w2tg.id: w2tg})
 
-__all__ = ["engines", "ToolType"]
+__all__ = ["engines", "AVAILABLE_TOOLS"]

src/voxkit/engines/base.py

@@ -32,8 +32,9 @@ def align(self, dataset_id: str, model_id: str) -> None:
 import json
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Any, Literal
+from typing import Any
 
+from voxkit.engines.constants import AVAILABLE_TOOLS
 from voxkit.storage.utils import get_storage_root
 
 """
@@ -42,18 +43,16 @@ def align(self, dataset_id: str, model_id: str) -> None:
 has its own settings that are stored in a JSON file.
 """
 
-ToolType = Literal["train", "align", "transcribe"]
-
 
 class AlignmentEngine(ABC):
     """
     Abstract base class for alignment engines.
 
-    Subclasses must implement at least one ToolType operation and provide
+    Subclasses must implement at least one AVAILABLE_TOOLS operation and provide
     specific validation criteria.
 
     Attributes:
-        settings_configurations (dict[ToolType, Any]): Mapping of
+        settings_configurations (dict[AVAILABLE_TOOLS, Any]): Mapping of
             tool type names ("train"/"align") to their store configuration.
         reference_url (str | None): Optional reference URL for the engine.
         description (str | None): Human-readable description of the engine.
@@ -63,7 +62,7 @@ class AlignmentEngine(ABC):
 
     def __init__(
         self,
-        settings_configurations: dict[ToolType, Any],
+        settings_configurations: dict[AVAILABLE_TOOLS, Any],
         reference_url: str | None = None,
         description: str | None = None,
         human_readable_name: str | None = None,
@@ -218,7 +217,7 @@ def _get_default_settings(self, cfg: Any) -> dict:
         """
         return {field.name: field.default_value for field in (cfg.fields or [])}
 
-    def get_settings(self, tool_type: ToolType) -> dict:
+    def get_settings(self, tool_type: AVAILABLE_TOOLS) -> dict:
         """
         Load and validate settings for a specific tool.
 
@@ -269,7 +268,7 @@ def get_settings(self, tool_type: ToolType) -> dict:
 
         return settings
 
-    def get_settings_config(self, tool_type: ToolType) -> Any:
+    def get_settings_config(self, tool_type: AVAILABLE_TOOLS) -> Any:
         """
         Return the :class:`Any` for a tool type.
 
@@ -287,7 +286,7 @@ def get_settings_config(self, tool_type: ToolType) -> Any:
             raise ValueError(f"No settings configuration found for tool type: {tool_type}")
         return config
 
-    def has_tool(self, tool_type: ToolType) -> bool:
+    def has_tool(self, tool_type: AVAILABLE_TOOLS) -> bool:
         """Check if the engine has a tool of the specified type."""
         return tool_type in self.settings_configurations
 

src/voxkit/engines/constants.py

@@ -0,0 +1,4 @@
+from typing import Literal
+
+# New engines can implement these tools or a subset of them
+AVAILABLE_TOOLS = Literal["train", "align", "transcribe"]

src/voxkit/gui/pages/pipeline/viewer_stacker.py

@@ -40,6 +40,7 @@
 from voxkit.gui.pages.pipeline.base_stacker import BaseStacker
 from voxkit.gui.styles import Buttons, Colors, Containers, Labels
 from voxkit.storage import alignments, datasets
+from voxkit.storage.constants import SUPERSET_AUDIO_EXTENSIONS
 
 if TYPE_CHECKING:
     from PyQt6.QtMultimedia import QAudioOutput, QMediaPlayer
@@ -52,7 +53,7 @@
     MULTIMEDIA_AVAILABLE = False
 
 
-_AUDIO_EXTENSIONS = {".wav", ".flac", ".mp3", ".ogg", ".m4a"}
+_AUDIO_EXTENSIONS = SUPERSET_AUDIO_EXTENSIONS
 _SILENCE_LABELS = {"", "sp", "sil", "<eps>", "spn"}
 
 # ---------------------------------------------------------------------------

src/voxkit/storage/alignments.py

@@ -38,7 +38,7 @@
 from pathlib import Path
 from typing import List, Literal, Tuple, TypedDict
 
-from .config import ALIGNMENTS_ROOT
+from .constants import ALIGNMENTS_ROOT, SUPERSET_AUDIO_EXTENSIONS
 from .datasets import _get_dataset_root, get_dataset_metadata
 from .models import ModelMetadata, get_model_metadata
 from .utils import generate_unique_id, readable_from_unique_id
@@ -192,7 +192,7 @@ def create_alignment(
         return False, f"Failed to create alignment metadata: {str(e)}"
 
 
-_AUDIO_EXTS = (".wav", ".flac", ".mp3", ".ogg", ".m4a")
+_AUDIO_EXTS = SUPERSET_AUDIO_EXTENSIONS
 
 
 def validate_hand_alignments(dataset_path: Path, hand_path: Path) -> Tuple[bool, str]:

src/voxkit/storage/constants.py

@@ -0,0 +1,21 @@
+"""This module contains constants for the VoxKit storage layer.
+
+Constants
+---------
+- **STORAGE_ROOT**: Root directory for all VoxKit storage (~/.voxkit)
+- **MODELS_ROOT**: Subdirectory for model storage relative to engine directory
+- **DATASETS_ROOT**: Subdirectory for dataset storage relative to STORAGE_ROOT
+- **ALIGNMENTS_ROOT**: Subdirectory for alignments relative to dataset directory
+- **SUPERSET_AUDIO_EXTENSIONS**: Comprehensive set of audio file extensions
+
+Notes
+-----
+- STORAGE_ROOT uses tilde (~) notation to reference the user's home directory
+- All paths are relative to appropriate parent directories in the hierarchy
+"""
+
+STORAGE_ROOT: str = "~/.voxkit"  # Root directory for all storage
+MODELS_ROOT: str = "train"  # Path from STORAGE_ROOT to models
+DATASETS_ROOT: str = "datasets"  # Path from STORAGE_ROOT to datasets
+ALIGNMENTS_ROOT: str = "alignments"  # Path from STORAGE_ROOT/DATASETS_ROOT to alignments
+SUPERSET_AUDIO_EXTENSIONS: frozenset[str] = frozenset({".wav", ".flac", ".mp3", ".ogg", ".m4a"})