platform agnosticity

src/ocr_pipeline/config.py

@@ -1,14 +1,42 @@
 from __future__ import annotations
 
 import os
+import platform
 from pathlib import Path
 from typing import Any, ClassVar
 
+import platformdirs
 import yaml
 from pydantic import Field, field_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
+APP_NAME = "ocr-pipeline"
+APP_AUTHOR = "aman"
+
+
+def _get_platform_ignore_patterns() -> list[str]:
+    """Get platform-specific ignore patterns for file watching."""
+    patterns = [
+        "*.tmp",
+        "*.partial",
+        "*.crdownload",
+        "*.part",
+        "~$*",  # MS Office temp files
+        "*.swp",
+        "*.swo",  # Vim swap files
+    ]
+    system = platform.system().lower()
+    if system == "darwin":
+        patterns.extend([".DS_Store", "._*", ".Spotlight-V100", ".Trashes", ".fseventsd"])
+    elif system == "windows":
+        patterns.extend(["Thumbs.db", "desktop.ini", "*.lnk", "$RECYCLE.BIN"])
+    else:
+        # Linux/Unix
+        patterns.extend([".directory", "*.swp", "*.swo", ".git"])
+    return patterns
+
+
 class InputConfig(BaseSettings):
     paths: list[str] = Field(default_factory=lambda: ["~/Pictures"])
     patterns: list[str] = Field(
@@ -132,7 +160,9 @@ class FrontmatterConfig(BaseSettings):
 
 
 class OutputConfig(BaseSettings):
-    base_directory: str = "./data/ocr_output"
+    base_directory: str = Field(
+        default_factory=lambda: str(platformdirs.user_data_dir(APP_NAME, APP_AUTHOR))
+    )
     format: str = "markdown"
     organize_by: str = "date_run"  # date_run | source_dir | flat
     frontmatter: FrontmatterConfig = Field(default_factory=FrontmatterConfig)
@@ -141,15 +171,10 @@ class OutputConfig(BaseSettings):
 class WatchConfig(BaseSettings):
     enabled: bool = True
     debounce_seconds: int = 5
-    ignore_patterns: list[str] = Field(
-        default_factory=lambda: [
-            ".DS_Store",
-            "*.tmp",
-            "*.partial",
-            "*.crdownload",
-        ]
+    ignore_patterns: list[str] = Field(default_factory=_get_platform_ignore_patterns)
+    db_path: str = Field(
+        default_factory=lambda: str(Path(platformdirs.user_data_dir(APP_NAME, APP_AUTHOR)) / "processed_files.db")
     )
-    db_path: str = "./data/processed_files.db"
     poll_interval: float = 1.0
 
 

src/ocr_pipeline/utils/migrate.py

@@ -1,16 +1,40 @@
 from __future__ import annotations
 
 import hashlib
+import os
+import platform
 from pathlib import Path
 from typing import Any
 
 import nbformat
+import platformdirs
 
+from ocr_pipeline.config import settings
 from ocr_pipeline.utils.logging import get_logger
 
 logger = get_logger(__name__)
 
 
+def _get_pictures_dir() -> Path:
+    """Get platform-appropriate Pictures directory."""
+    system = platform.system().lower()
+    if system == "darwin":
+        return Path.home() / "Pictures"
+    elif system == "windows":
+        # Windows: Pictures folder in user profile
+        return Path.home() / "Pictures"
+    else:
+        # Linux/Unix: XDG Pictures dir or ~/Pictures
+        pictures = Path.home() / "Pictures"
+        if pictures.exists():
+            return pictures
+        # Fallback to XDG_PICTURES_DIR
+        xdg = os.environ.get("XDG_PICTURES_DIR")
+        if xdg:
+            return Path(xdg)
+        return pictures
+
+
 def parse_notebook_for_images(notebook_path: Path) -> list[Path]:
     image_paths = []
     try:
@@ -38,7 +62,7 @@ def parse_notebook_for_images(notebook_path: Path) -> list[Path]:
                                     if part.startswith("SCR-") and any(
                                         part.endswith(ext) for ext in (".png", ".jpg", ".jpeg")
                                     ):
-                                        path = Path("/Users/Aman/Pictures") / part
+                                        path = _get_pictures_dir() / part
                                         if path.exists():
                                             image_paths.append(path)