platform agnosticity

config.yaml

@@ -1,7 +1,6 @@
 input:
   paths:
     - "~/Pictures"
-    - "/mnt/storage3/aman/screenshots"
   patterns:
     - "SCR-*.png"
     - "*.jpg"
@@ -11,8 +10,8 @@ input:
   recursive: true
 
 ocr:
-  engine: "paddleocr"  # "paddleocr" | "tesseract" | "auto"
+  engine: "paddleocr"
-  languages: ["en"]  # For tesseract: eng, lat, deu, fra, spa, ita, por, chi_sim, jpn, kor
+  languages: ["en", "latin"]
   use_gpu: false
   use_angle_cls: true
   det_db_thresh: 0.3
@@ -20,13 +19,6 @@ ocr:
   det_db_unclip_ratio: 1.5
   rec_batch_num: 6
   cpu_threads: 4
-  preprocess:
-    deskew: true
-    denoise: true
-    clahe: true
-    adaptive_threshold: true
-    remove_lines: true
-    max_dimension: 4096
 
 processing:
   workers: 4
@@ -76,10 +68,11 @@ chunking:
   keep_separator: true
 
 output:
-  base_directory: "./data/ocr_output"
+  # Uses platformdirs default: ~/.local/share/ocr-pipeline (Linux), ~/Library/Application Support/ocr-pipeline (macOS), %LOCALAPPDATA%\ocr-pipeline (Windows)
   format: "markdown"
-  organize_by: "date_run"  # "date_run" | "source_dir" | "flat"
+  organize_by: "date_run"
   frontmatter:
+    fields:
       - "source_path"
       - "source_hash"
       - "timestamp"
@@ -92,14 +85,15 @@ output:
       - "citations_found"
       - "chunk_index"
       - "total_chunks"
+    include_raw_text: false
 
 watch:
   enabled: true
   debounce_seconds: 5
-  ignore_patterns:
+  # Uses platform-aware defaults from config.py
-    - ".DS_Store"
+  # ignore_patterns:
-    - "*.tmp"
+  #   - ".DS_Store"
-    - "*.partial"
+  #   - "*.tmp"
-    - "*.crdownload"
+  #   - "*.partial"
-  db_path: "./data/processed_files.db"
+  #   - "*.crdownload"
   poll_interval: 1.0

pyproject.toml

@@ -44,6 +44,7 @@ dependencies = [
     "python-slugify>=8.0.0",
     "xxhash>=3.4.0",
     "python-magic>=0.4.27",
+    "platformdirs>=4.2.0",
 ]
 
 [project.optional-dependencies]
@@ -75,6 +76,7 @@ dev-dependencies = [
     "mypy>=1.8.0",
     "pre-commit>=3.6.0",
 ]
+override-dependencies = ["lxml>=5.3.0"]
 
 [tool.ruff]
 line-length = 100

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(
+    ignore_patterns: list[str] = Field(default_factory=_get_platform_ignore_patterns)
-        default_factory=lambda: [
+    db_path: str = Field(
-            ".DS_Store",
+        default_factory=lambda: str(Path(platformdirs.user_data_dir(APP_NAME, APP_AUTHOR)) / "processed_files.db")
-            "*.tmp",
-            "*.partial",
-            "*.crdownload",
-        ]
     )
-    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)