refactor(config): streamline project root handling and update paths (#35)

This pull request refactors project root path discovery and configuration handling to centralize logic, simplify usage, and improve consistency across the codebase. The main changes include replacing the old get_project_root utility with a new get_root function, updating configuration defaults to use absolute paths relative to the project root, and reorganizing settings in the configuration classes.

Project root path discovery and usage:
Introduced a new get_root function in src/tracklistify/config/paths.py for project root discovery, replacing the previous logic in src/tracklistify/utils/project.py.
Updated all references to project root throughout the codebase (src/tracklistify/cli.py, src/tracklistify/core/run.py, config modules) to use get_root instead of get_project_root.

Configuration defaults and environment variable handling:
Changed default directory paths in BaseConfig to be absolute paths resolved from the project root using get_root, ensuring consistent placement of logs, cache, temp, and output files.
Improved environment variable loading for path fields: relative paths from environment variables are now resolved relative to the project root.

Configuration settings reorganization:
Reorganized and updated fields in TrackIdentificationConfig, including changes to default values, grouping settings by theme (provider, caching, rate limiting, output, downloader), and adding new fields for flexibility.
These changes make project configuration more robust and easier to maintain by centralizing root path logic and improving clarity of config settings.

Author: betmoar

.gitignore

@@ -164,10 +164,12 @@ cython_debug/
 .ruff_cache/
 .vscode/
 .DS_Store
+copilot*
 poetry.lock
 
 # Project-specific
 .tracklistify/
 examples/
 dev/
 docs/temp/
+coverage.json

src/tracklistify/cli.py

@@ -8,12 +8,11 @@
 
 from dotenv import load_dotenv
 
-from .config import ConfigError, get_config
+from .config import ConfigError, get_config, get_root
 from .core import ApplicationError, AsyncApp
 
 # Local/package imports
 from .utils.logger import get_logger, set_logger
-from .utils.project import get_project_root
 
 # Get the logger for this module
 logger = get_logger(__name__)
@@ -146,8 +145,8 @@ def cli() -> None:
     logger.info("Starting CLI")
 
     # Load environment variables first
-    env_file = get_project_root() / ".env"
-    load_environment_variables(env_file)
+    env_path = get_root() / ".env"
+    load_environment_variables(env_path)
 
     try:
         exit_code = asyncio.run(main(args))

src/tracklistify/config/__init__.py

@@ -4,11 +4,14 @@
 # Local imports
 from .base import BaseConfig, TrackIdentificationConfig
 from .factory import ConfigError, clear_config, get_config
+from .paths import clear_root, get_root
 
 __all__ = [
     "BaseConfig",
     "TrackIdentificationConfig",
     "get_config",
     "clear_config",
     "ConfigError",
+    "get_root",
+    "clear_root",
 ]

src/tracklistify/config/base.py

@@ -7,17 +7,23 @@
 from typing import List
 
 # Local imports
+from .paths import get_root
 from .validation import ConfigValidator, PathRequirement, PathRule
 
 
 @dataclass
 class BaseConfig:
     """Base configuration class."""
 
-    output_dir: Path = field(default=Path(".tracklistify/output"))
-    cache_dir: Path = field(default=Path(".tracklistify/cache"))
-    temp_dir: Path = field(default=Path(".tracklistify/temp"))
-    log_dir: Path = field(default=Path(".tracklistify/log"))
+    project_root = get_root()
+
+    # Directories
+    log_dir: Path = field(default=project_root / ".tracklistify/log")
+    temp_dir: Path = field(default=project_root / ".tracklistify/temp")
+    cache_dir: Path = field(default=project_root / ".tracklistify/cache")
+    output_dir: Path = field(default=project_root / ".tracklistify/output")
+
+    # Log settings
     verbose: bool = field(default=False)
     debug: bool = field(default=False)
 
@@ -61,8 +67,12 @@ def _load_from_env(self) -> None:
                         # Handle boolean values
                         value = env_value.lower() in ("true", "1", "yes", "on")
                     elif field_type == Path:
-                        # Handle paths
-                        value = Path(os.path.expanduser(env_value))
+                        # Handle paths - resolve relative paths relative to project root
+                        path = Path(os.path.expanduser(env_value))
+                        if not path.is_absolute():
+                            # Relative path - resolve relative to project root
+                            path = get_root() / path
+                        value = path
                     elif field_type == List[str]:
                         # Handle string lists (comma-separated)
                         value = [s.strip() for s in env_value.split(",") if s.strip()]
@@ -101,36 +111,52 @@ class TrackIdentificationConfig(BaseConfig):
     # Base config fields are inherited
 
     # Track identification specific fields
-    segment_length: int = field(default=30)
-    overlap_duration: int = field(default=10)
+    segment_length: int = field(default=60)
     min_confidence: float = field(default=0.5)
-    time_threshold: float = field(default=60.0)
+    time_threshold: float = field(default=30.0)
     max_duplicates: int = field(default=2)
+    overlap_duration: int = field(default=10)
+    overlap_strategy: str = field(default="weighted")
+    min_segment_length: int = field(default=10)
+
+    # Provider settings
     primary_provider: str = field(default="shazam")
-    fallback_enabled: bool = field(default=True)
+    fallback_enabled: bool = field(default=False)
     fallback_providers: List[str] = field(default_factory=list)
 
-    # Global rate limiting settings
-    max_requests_per_minute: int = field(default=25)
-    max_concurrent_requests: int = field(default=2)
-
+    # Caching settings
     cache_enabled: bool = field(default=True)
-    cache_ttl: int = field(default=86400)
-    cache_max_size: int = field(default=1000000)
+    cache_ttl: int = field(default=3600)
+    cache_max_size: int = field(default=1000)
     cache_storage_format: str = field(default="json")
     cache_compression_enabled: bool = field(default=True)
     cache_compression_level: int = field(default=6)
     cache_cleanup_enabled: bool = field(default=True)
     cache_cleanup_interval: int = field(default=3600)
-    cache_max_age: int = field(default=604800)
+    cache_max_age: int = field(default=86400)
     cache_min_free_space: int = field(default=104857600)
+
+    # Rate limiting settings
+    max_requests_per_minute: int = field(default=25)
+    max_concurrent_requests: int = field(default=2)
+
+    # ACRCloud settings
     acrcloud_max_rpm: int = field(default=300)
     acrcloud_max_concurrent: int = field(default=10)
+
+    # Shazam settings
     shazam_max_rpm: int = field(default=25)
     shazam_max_concurrent: int = field(default=1)
     shazam_cooldown_seconds: float = field(default=2.25)
+
+    # Output formats
     output_format: str = field(default="json")
 
+    # Downloader settings
+    download_quality: str = field(default="192")
+    download_format: str = field(default="mp3")
+    download_max_retries: int = field(default=3)
+
     def __post_init__(self):
         """Initialize configuration after dataclass creation."""
         # Load environment variables first

src/tracklistify/config/paths.py

@@ -0,0 +1,38 @@
+"""Project path discovery utilities."""
+
+import os
+from functools import lru_cache
+from pathlib import Path
+
+
+@lru_cache(maxsize=1)
+def get_root() -> Path:
+    """Get project root directory for loading .env files and resolving config paths.
+
+    Simple approach:
+    1. Check environment variable TRACKLISTIFY_PROJECT_ROOT
+    2. Walk up from current file until we find pyproject.toml
+    3. Fallback to current working directory
+
+    Returns:
+        Path: Project root directory
+    """
+    # Environment variable override
+    if root_env := os.getenv("TRACKLISTIFY_PROJECT_ROOT"):
+        root_path = Path(root_env).resolve()
+        if root_path.exists():
+            return root_path
+
+    # Walk up from this file to find pyproject.toml
+    current = Path(__file__).resolve()
+    for parent in current.parents:
+        if (parent / "pyproject.toml").exists():
+            return parent
+
+    # Fallback to current working directory
+    return Path.cwd()
+
+
+def clear_root() -> None:
+    """Clear the project root cache."""
+    get_root.cache_clear()

src/tracklistify/core/run.py

@@ -4,19 +4,19 @@
 import signal
 import sys
 
-from tracklistify.utils.project import get_project_root
+from tracklistify.config import get_root
 
 # Global variables for cleanup
 _cleanup_tasks = set()
 
 
 def setup_environment():
     """Setup the Python path and environment variables."""
-    env_file = get_project_root() / ".env"
-    if not env_file.exists() and (get_project_root() / ".env.example").exists():
+    env_path = get_root() / ".env"
+    if not env_path.exists() and (get_root() / ".env.example").exists():
         print("Creating .env from .env.example...")
-        with open(get_project_root() / ".env.example") as f:
-            with open(env_file, "w") as env:
+        with open(get_root() / ".env.example") as f:
+            with open(env_path, "w") as env:
                 env.write(f.read())
         print("Please edit .env with your credentials")
         sys.exit(1)