docorient 0.3.1__tar.gz → 0.3.2__tar.gz

docorient-0.3.2/CHANGELOG.md

@@ -0,0 +1,44 @@
+# Changelog
+
+## 0.3.2 (2026-02-27)
+
+- Fix: update project URLs to correct GitHub repository
+- Add changelog link to PyPI metadata
+
+## 0.3.1 (2026-02-27)
+
+- Fix: author metadata corrected to Lucas Gabriel Vaz
+- Remove `tesseract` from PyPI keywords
+
+## 0.3.0 (2026-02-27)
+
+- **Breaking:** detection engines refactored to class-based architecture with `DetectionEngine` Protocol
+- Introduce `DetectionPipeline` for extensible engine orchestration
+- Introduce `PrimaryEngine` and `SecondaryEngine` classes
+- Extract `rotation.py` and `voting.py` as standalone modules
+- Encapsulate worker state in `WorkerContext` dataclass
+- Transform `_imaging.py` functions into `ImageIO` class
+- Decompose `process_directory` into focused sub-functions
+- Apply custom exceptions (`DetectionError`, `CorrectionError`, `BatchProcessingError`) throughout codebase
+- Export `DetectionEngine`, `DetectionPipeline`, `PrimaryEngine`, `SecondaryEngine` in public API
+
+## 0.2.0 (2026-02-26)
+
+- **Breaking:** renamed config params `osd_confidence_threshold` → `secondary_confidence_threshold`, `max_osd_dimension` → `secondary_max_dimension`, `projection_target_dimension` → `primary_max_dimension`
+- **Breaking:** renamed CLI flag `--no-ocr` → `--no-secondary`
+- Internal engines renamed to `primary` and `secondary`
+- Updated `OrientationResult.method` trace strings
+
+## 0.1.1 (2026-02-26)
+
+- Docs: added `if __name__ == "__main__":` note for `process_directory` on macOS/Windows
+
+## 0.1.0 (2026-02-25)
+
+- Initial release
+- Primary engine for 90°/270° detection
+- Optional secondary engine for 180° detection
+- Single image and batch directory processing
+- Multi-page majority voting
+- Resumable batch processing
+- CLI interface

{docorient-0.3.1 → docorient-0.3.2}/PKG-INFO

@@ -1,10 +1,11 @@
 Metadata-Version: 2.4
 Name: docorient
-Version: 0.3.1
+Version: 0.3.2
 Summary: Document image orientation detection and correction.
-Project-URL: Homepage, https://github.com/cebraspe-lab/docorient
-Project-URL: Repository, https://github.com/cebraspe-lab/docorient
-Project-URL: Issues, https://github.com/cebraspe-lab/docorient/issues
+Project-URL: Homepage, https://github.com/lucasleirbag/DocOrient
+Project-URL: Repository, https://github.com/lucasleirbag/DocOrient
+Project-URL: Issues, https://github.com/lucasleirbag/DocOrient/issues
+Project-URL: Changelog, https://github.com/lucasleirbag/DocOrient/blob/main/CHANGELOG.md
 Author: Lucas Gabriel Vaz
 License-Expression: MIT
 License-File: LICENSE

{docorient-0.3.1 → docorient-0.3.2}/docs/architecture.md

@@ -6,21 +6,24 @@
 src/docorient/
 ├── __init__.py              Public API re-exports
 ├── _version.py              Version string
-├── _imaging.py              Internal image utilities
+├── _imaging.py              ImageIO class for image operations
 ├── config.py                OrientationConfig dataclass
 ├── types.py                 Result dataclasses
 ├── exceptions.py            Exception hierarchy
+├── rotation.py              Image rotation utility
+├── voting.py                Majority voting logic
 ├── correction.py            correct_image, correct_document_pages
 ├── cli.py                   CLI entry point
 ├── detection/
-│   ├── __init__.py          Re-exports detect_orientation
-│   ├── engine.py            Detection orchestrator
-│   ├── primary.py           Primary detection engine (90°/270°)
-│   └── secondary.py         Secondary detection engine (180°)
+│   ├── __init__.py          Re-exports detection API
+│   ├── base.py              DetectionEngine Protocol
+│   ├── engine.py            DetectionPipeline orchestrator
+│   ├── primary.py           PrimaryEngine (90°/270°)
+│   └── secondary.py         SecondaryEngine (180°)
 └── batch/
     ├── __init__.py          Re-exports process_directory
     ├── scanner.py           Directory scanning and grouping
-    ├── worker.py            Multiprocessing worker logic
+    ├── worker.py            WorkerContext and multiprocessing logic
     └── processor.py         Batch orchestrator with resume and progress
 ```
 
@@ -30,17 +33,22 @@ src/docorient/
 detect_orientation()
         │
         ▼
-Primary Engine (detection/primary.py)
+DetectionPipeline.run()
+Iterates through list[DetectionEngine]
+        │
+        ▼
+PrimaryEngine.detect()
 Analyzes pixel density distribution to determine text alignment.
         │
         ├── angle ∈ {90, 270} ──► Return result immediately
         │
-        └── angle = 0 (aligned) ──► Secondary Engine available?
+        └── angle = 0 (aligned) ──► SecondaryEngine.detect()
+                                            │
+                                  is_available()?
                                             │
                                Yes ─────────┴───────── No
                                 ▼                       ▼
-                     Secondary Engine          Return 0° (no change)
-                     (detection/secondary.py)
+                     Runs secondary analysis    Return 0° (no change)
                      Checks for 180° inversion
                      with confidence scoring
                                 │
@@ -51,27 +59,52 @@ Analyzes pixel density distribution to determine text alignment.
               Return 180°           Return 0°
 ```
 
+## Engine Architecture
+
+The detection system is built on a `DetectionEngine` Protocol:
+
+```
+DetectionEngine (Protocol)
+├── name: str
+└── detect(image, config) → OrientationResult | None
+
+PrimaryEngine implements DetectionEngine
+├── Always returns OrientationResult (never None)
+└── Detects 0°, 90°, 270° via energy analysis
+
+SecondaryEngine implements DetectionEngine
+├── Returns None when unavailable or low confidence
+└── Detects 180° via optional OCR dependency
+
+DetectionPipeline
+├── Holds list[DetectionEngine] (default: [PrimaryEngine(), SecondaryEngine()])
+└── Executes engines in sequence with short-circuit logic
+```
+
 ## Batch Processing Pipeline
 
 ```
 process_directory()
         │
         ▼
+   _resolve_output_directory()
+   Resolves explicit path or generates UUID
+        │
+        ▼
    scan_directory()          ← scanner.py
    Groups images by
    source document name
         │
         ▼
-   Load resume log           ← _orientation_done.log
-   Skip already done files
-        │
-        ▼
-   Distribute pending
-   sources into N batches    ← N = effective_workers
+   _filter_pending_sources()
+   Loads resume log, skips completed
         │
         ▼
-   multiprocessing.Pool      ← worker.py
+   _run_parallel_processing()
    ┌─────────────────────────────────────┐
+   │  multiprocessing.Pool              │
+   │  WorkerContext encapsulates state   │
+   │                                     │
    │  For each source in batch:          │
    │  1. Run detection per page          │
    │  2. Apply majority voting           │
@@ -93,12 +126,12 @@ Majority voting resolves this:
 2. Find the most common angle (`Counter.most_common`)
 3. Override any unreliable detection that differs from the majority
 
-Implemented in `correction._apply_majority_voting()`, reused by both
+Implemented in `voting.apply_majority_voting()`, reused by both
 `correct_document_pages()` and `batch/worker._process_single_source()`.
 
 ## Multiprocessing Design
 
-- **No shared mutable state** — each worker reconstructs `OrientationConfig` from a dict
+- **WorkerContext dataclass** encapsulates all shared state in a single object
 - **Progress tracking** via `multiprocessing.Value` + `multiprocessing.Lock`
 - **Resume log** written atomically per source file, protected by the shared lock
 - **`maxtasksperchild=1`** prevents memory accumulation in long jobs

{docorient-0.3.1 → docorient-0.3.2}/docs/contributing.md

@@ -28,9 +28,8 @@ ruff check src/ tests/ --fix
 - No comments — code must be self-explanatory through naming
 - Descriptive variable names — never single-letter variables in non-trivial scopes
 - Full type hints on all function signatures
-- Docstrings only on public API functions
 - Functions must do exactly one thing, max ~30 lines of logic
-- No global state — configuration is always passed as a parameter
+- Configuration is always passed as a parameter
 
 ## Publishing a New Version
 

{docorient-0.3.1 → docorient-0.3.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "docorient"
-version = "0.3.1"
+version = "0.3.2"
 description = "Document image orientation detection and correction."
 readme = "README.md"
 license = "MIT"
@@ -37,9 +37,10 @@ dev = ["pytest >= 8.0", "pytest-cov", "ruff >= 0.4", "build", "twine"]
 docorient = "docorient.cli:main"
 
 [project.urls]
-Homepage = "https://github.com/cebraspe-lab/docorient"
-Repository = "https://github.com/cebraspe-lab/docorient"
-Issues = "https://github.com/cebraspe-lab/docorient/issues"
+Homepage = "https://github.com/lucasleirbag/DocOrient"
+Repository = "https://github.com/lucasleirbag/DocOrient"
+Issues = "https://github.com/lucasleirbag/DocOrient/issues"
+Changelog = "https://github.com/lucasleirbag/DocOrient/blob/main/CHANGELOG.md"
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/docorient"]

docorient-0.3.2/src/docorient/_version.py

@@ -0,0 +1 @@
+__version__ = "0.3.2"

docorient-0.3.1/CHANGELOG.md

@@ -1,22 +0,0 @@
-# Changelog
-
-## 0.2.0 (2026-02-26)
-
-- **Breaking:** renamed config params `osd_confidence_threshold` → `secondary_confidence_threshold`, `max_osd_dimension` → `secondary_max_dimension`, `projection_target_dimension` → `primary_max_dimension`
-- **Breaking:** renamed CLI flag `--no-ocr` → `--no-secondary`
-- Internal engines renamed to `primary` and `secondary` — no external algorithm references
-- Updated `OrientationResult.method` trace strings to `primary(...)` and `secondary(...)`
-
-## 0.1.1 (2026-02-26)
-
-- Docs: added `if __name__ == "__main__":` note for `process_directory` on macOS/Windows
-
-## 0.1.0 (2026-02-25)
-
-- Initial release
-- Projection profile engine for 90°/270° detection
-- Optional Tesseract OSD engine for 180° detection
-- Single image and batch directory processing
-- Multi-page majority voting
-- Resumable batch processing
-- CLI interface

docorient-0.3.1/src/docorient/_version.py

@@ -1 +0,0 @@
-__version__ = "0.3.1"