accsify-tesseract 1.0.5.1__tar.gz

accsify_tesseract-1.0.5.1/LICENSE

@@ -0,0 +1,79 @@
+ACCOSIFY TESSERACT - MULTI-LICENSE & THIRD-PARTY ATTRIBUTION NOTICE
+================================================================================
+
+This software is released under the MIT License by Accsify.
+It statically links and incorporates upstream components under their respective
+permissive open-source licenses (Apache-2.0, BSD-2-Clause, and Public Domain).
+
+--------------------------------------------------------------------------------
+1. ACCSIFY TESSERACT LICENSE (MIT)
+--------------------------------------------------------------------------------
+Copyright (c) 2026 accsify. All rights reserved.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+--------------------------------------------------------------------------------
+2. TESSERACT OCR LICENSE (Apache License 2.0)
+--------------------------------------------------------------------------------
+Copyright (C) 2006-2024 Google LLC, Ray Smith, and Tesseract contributors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+--------------------------------------------------------------------------------
+3. LEPTONICA LICENSE (BSD 2-Clause)
+--------------------------------------------------------------------------------
+Copyright (C) 2001-2024 Leptonica (Dan Bloomberg). All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+   this list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+--------------------------------------------------------------------------------
+4. STB_IMAGE (Public Domain / MIT)
+--------------------------------------------------------------------------------
+Developed by Sean Barrett (nothings.org).
+This software is in the public domain. Where public domain is not recognized,
+it is licensed under the MIT License.

accsify_tesseract-1.0.5.1/MANIFEST.in

@@ -0,0 +1,8 @@
+include README.md
+include LICENSE
+include pyproject.toml
+include setup.cfg
+recursive-include accsify_tesseract *.py py.typed
+recursive-include accsify_tesseract/lib *.dll *.exe *.lib
+recursive-include accsify_tesseract/examples *.py *.png *.md
+recursive-include tests *.py

accsify_tesseract-1.0.5.1/PKG-INFO

@@ -0,0 +1,361 @@
+Metadata-Version: 2.4
+Name: accsify-tesseract
+Version: 1.0.5.1
+Summary: Official Python SDK and CLI for the Accsify Monolithic Tesseract OCR Engine
+Home-page: https://github.com/accsify/tesseract
+Author: accsify
+Author-email: accsify <contact@accsify.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/accsify/tesseract
+Project-URL: Documentation, https://github.com/accsify/tesseract#readme
+Project-URL: Repository, https://github.com/accsify/tesseract.git
+Project-URL: Issues, https://github.com/accsify/tesseract/issues
+Keywords: ocr,tesseract,text-recognition,computer-vision,accsify,layout-analysis
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Classifier: Topic :: Scientific/Engineering :: Image Recognition
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pillow>=9.0.0
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+
+# accsify-tesseract
+
+Official high-performance Python package and CLI for the **Accsify Tesseract OCR Engine**.
+
+[![PyPI version](https://img.shields.io/badge/pypi-v5.5.0.1-blue.svg)](https://pypi.org/project/accsify-tesseract/)
+[![Python Versions](https://img.shields.io/badge/python-3.8%20%7C%203.9%20%7C%203.10%20%7C%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue.svg)](https://pypi.org/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Platform](https://img.shields.io/badge/platform-Windows%20x64%20%7C%20x86-green.svg)](https://microsoft.com)
+
+---
+
+## 1. Overview
+
+`accsify-tesseract` is a modern, object-oriented Python SDK built on top of the monolithic `tesseract_engine.dll` Windows dynamic link library. It provides thread-safe OCR recognition, structured document layout hierarchy, native Windows WinHTTP streaming model downloads, multi-image batch processing, and multi-language support.
+
+### Key Highlights
+* **Zero Runtime External Dependencies**: The underlying native engine is statically linked with `/MT` (MSVC C/C++ Static Runtime). No Visual C++ Redistributable or external DLLs are needed.
+* **Structured JSON & Dictionary Outputs**: Extract full page layout, words, confidences, bounding boxes, textline orders, and writing directions (LTR, RTL, TTB) directly into typed Python dictionaries or JSON.
+* **Concurrent Model Flavors**: Download and store both **fast** (`tessdata_fast`) and **best** (`tessdata_best`) models simultaneously in separated subdirectories without file collisions.
+* **Multi-Language OCR**: Seamlessly combine languages with `+` (e.g. `ara+eng`), with automatic downloading of missing language components.
+* **Multi-Image Batch Processing**: High-throughput processing of image lists with unified structured results via `recognize_batch()`.
+* **Native WinHTTP Downloader**: Download traineddata models with real-time progress callbacks and cancel tokens directly from official repositories over HTTPS.
+* **Universal Image Support**: Directly load file paths (`str`, `Path`), raw encoded bytes (`bytes`, `bytearray`), PIL Images (`PIL.Image`), and NumPy image arrays (OpenCV `ndarray`).
+
+---
+
+## 2. Installation
+
+### From PyPI
+```bash
+pip install accsify-tesseract
+```
+
+### From Local Source (Editable Mode)
+```bash
+cd d:\projects\c++\tesseract\python
+pip install -e .
+```
+
+The package automatically discovers and loads `tesseract_engine.dll` from `dist/x64/`, `dist/x86/`, `bin/`, or standard Windows search paths based on whether you are running a 64-bit or 32-bit Python interpreter.
+
+---
+
+## 3. Quickstart
+
+### One-Liner Recognition
+```python
+import accsify_tesseract as tess
+
+# Extract plain text
+text = tess.image_to_string("invoice.png", lang="eng")
+print(text)
+
+# Extract structured JSON string
+json_str = tess.image_to_json("document.png", lang="eng")
+
+# Extract structured dictionary with words and bounding boxes
+data = tess.image_to_dict("document.png", lang="eng")
+print(f"Mean confidence: {data['mean_confidence']}%")
+for word in data["words"]:
+    print(f"Word: {word['text']}, Box: {word['bbox']}, Conf: {word['confidence']}%")
+```
+
+---
+
+## 4. Object-Oriented Engine Interface
+
+The primary interface is `TesseractEngine`, implemented as a thread-safe context manager.
+
+```python
+from pathlib import Path
+from accsify_tesseract import TesseractEngine, PageSegMode, ModelType
+
+# Open engine with specific language and model flavor
+with TesseractEngine(language="eng", flavor=ModelType.FAST) as engine:
+    engine.set_page_seg_mode(PageSegMode.AUTO)
+    
+    # Load image from file path, bytes, PIL Image, or OpenCV ndarray
+    engine.set_image(Path("document.png"))
+    
+    # Run recognition pipeline
+    engine.recognize()
+    
+    # Retrieve outputs
+    text = engine.get_text()
+    mean_conf = engine.get_mean_confidence()
+    hocr = engine.get_hocr(page_num=0)
+    tsv = engine.get_tsv(page_num=0)
+    
+    print(f"Confidence: {mean_conf}%")
+    print(text)
+```
+
+---
+
+## 5. Structured JSON & Dictionary Extraction
+
+`TesseractEngine.get_json()` and `TesseractEngine.get_structured_dict()` return deep structured layout information natively generated by the C++ engine:
+
+```python
+with TesseractEngine(language="eng") as engine:
+    engine.set_image("sample.png")
+    
+    # Get Python dictionary
+    doc = engine.get_structured_dict()
+    
+    print(f"Total Text: {doc['text']}")
+    print(f"Mean Confidence: {doc['mean_confidence']}%")
+    print(f"PSM: {doc['psm']}")
+    
+    for w in doc["words"]:
+        print(f"Word: {w['text']:<20} Conf: {w['confidence']:<6.1f} Box: {w['bbox']} Direction: {w['direction']}")
+```
+
+### JSON Schema Specification
+```json
+{
+  "text": "Full extracted UTF-8 document text...",
+  "mean_confidence": 94,
+  "psm": 3,
+  "words": [
+    {
+      "text": "Accsify",
+      "confidence": 98.4,
+      "bbox": [120, 45, 230, 78],
+      "direction": "LeftToRight",
+      "order": "LTR",
+      "deskew_angle": 0.00012
+    }
+  ]
+}
+```
+
+---
+
+## 6. Multi-Image Batch Processing
+
+Process dozens or hundreds of images in a single session without recreating the engine:
+
+```python
+from accsify_tesseract import TesseractEngine
+
+images = ["page1.png", "page2.png", "page3.png"]
+
+with TesseractEngine(language="eng") as engine:
+    batch_results = engine.recognize_batch(images)
+    
+    for res in batch_results:
+        print(f"\n--- Result for: {res.image_path} ---")
+        print(f"Confidence: {res.mean_confidence}% | Words: {res.words_count}")
+        print(res.text[:150])  # preview first 150 chars
+        
+        # Export individual image result to JSON or dict
+        json_payload = res.to_json(indent=2)
+```
+
+---
+
+## 7. Multi-Language Combination & Auto-Download
+
+You can combine multiple languages using the `+` operator. With `auto_download=True`, the engine automatically verifies and downloads any missing language before initializing:
+
+```python
+from accsify_tesseract import TesseractEngine, ModelType
+
+# Combined Arabic and English recognition with auto-downloading
+with TesseractEngine(language="ara+eng", flavor=ModelType.BEST, auto_download=True) as engine:
+    engine.set_image("bilingual_contract.png")
+    engine.recognize()
+    print(engine.get_text())
+```
+
+---
+
+## 8. Model Management & Storage Organization
+
+Accsify Tesseract organizes models into structured subdirectories under the active `tessdata/` path to prevent collisions between different versions of the same language:
+
+```
+tessdata/
+├── fast/                 # Compact models (~1-5 MB)
+│   ├── eng.traineddata
+│   └── ara.traineddata
+├── best/                 # High-accuracy full LSTM models (~15-40 MB)
+│   ├── eng.traineddata
+│   └── ara.traineddata
+├── script/               # Script-specific models
+│   └── Arabic.traineddata
+└── standard/             # Standard release models
+```
+
+### Querying Catalog & Downloading
+```python
+from accsify_tesseract import ModelManager, ModelType
+
+# 1. Inspect installed models
+installed = ModelManager.list_installed()
+print("Installed models:", installed)
+
+# 2. Query available catalog models
+catalog = ModelManager.list_catalog(ModelType.FAST)
+for m in catalog:
+    print(f"{m.name:<15} {m.display_name:<30} {m.file_size_mb:.1f} MB (Installed: {m.is_installed})")
+
+# 3. Live progress callback
+def my_progress(name, model_type, downloaded, total, pct, status):
+    print(f"\rDownloading {name}: {pct:.1f}% ({downloaded / 1024 / 1024:.2f} MB)", end="")
+    return True  # return False to cancel download
+
+# 4. Download fast Arabic model
+ModelManager.download("ara", model_type=ModelType.FAST, progress_callback=my_progress)
+
+# 5. Download best Arabic model (stored in tessdata/best/ara.traineddata without overwriting fast!)
+ModelManager.download("ara", model_type=ModelType.BEST, progress_callback=my_progress)
+
+# 6. Download multiple models in one call
+ModelManager.download_many(["eng", "fra", "deu"], model_type=ModelType.FAST)
+
+# 7. Configure custom storage directory
+ModelManager.set_path("D:/my_models/tessdata")
+print("Active path:", ModelManager.get_path())
+```
+
+---
+
+## 9. Layout Analysis & Bounding Boxes
+
+Analyze the full page geometry across 5 hierarchy levels: `BLOCK`, `PARA`, `TEXTLINE`, `WORD`, `SYMBOL`.
+
+```python
+from accsify_tesseract import TesseractEngine, PageIteratorLevel, WritingDirection
+
+with TesseractEngine(language="ara+eng") as engine:
+    engine.set_image("mixed_layout.png")
+    layout = engine.analyse_layout(level=PageIteratorLevel.WORD)
+    
+    print(f"Discovered {len(layout.words)} words, {len(layout.lines)} lines")
+    
+    for word in layout.words:
+        b = word.bbox
+        is_rtl = word.writing_direction == WritingDirection.RIGHT_TO_LEFT
+        dir_label = "RTL (Arabic)" if is_rtl else "LTR (Latin)"
+        
+        print(f"[{b.left}, {b.top}, {b.right}, {b.bottom}] {word.text:<25} Conf: {word.confidence:.1f}% Dir: {dir_label}")
+    
+    # Export full layout to JSON
+    json_layout = layout.to_json(indent=2)
+```
+
+---
+
+## 10. Orientation and Script Detection (OSD)
+
+Detect page rotation degrees (0°, 90°, 180°, 270°) and identify the primary script:
+
+```python
+from accsify_tesseract import TesseractEngine, PageSegMode
+
+with TesseractEngine(language="osd") as engine:
+    engine.set_page_seg_mode(PageSegMode.OSD_ONLY)
+    engine.set_image("scanned_page.png")
+    
+    osd = engine.detect_orientation_and_script()
+    print(f"Orientation : {osd.orientation_deg}° (Confidence: {osd.orientation_confidence})")
+    print(f"Script      : {osd.script_name} (Confidence: {osd.script_confidence})")
+    print(f"Is Upright  : {osd.is_upright}")
+    
+    # Export to dict or JSON
+    print(osd.to_dict())
+```
+
+---
+
+## 11. Command-Line Interface (CLI)
+
+The package provides the `accsify-tesseract` console script:
+
+```bash
+# 1. OCR a single image
+accsify-tesseract ocr invoice.png -l eng
+
+# 2. Batch OCR multiple images to structured JSON
+accsify-tesseract ocr page1.png page2.png page3.png -l eng --format json -o batch_result.json
+
+# 3. Multi-language OCR with high-accuracy 'best' model
+accsify-tesseract ocr contract.png -l "ara+eng" --flavor best
+
+# 4. Detailed layout inspection
+accsify-tesseract layout document.png -l eng --format json
+
+# 5. Detect page orientation and script
+accsify-tesseract osd scanned.png
+
+# 6. List and download models
+accsify-tesseract models list --type fast
+accsify-tesseract models download ara --type best
+accsify-tesseract models installed
+accsify-tesseract models path --set-path "D:\tessdata"
+```
+
+---
+
+## 12. Exception Hierarchy
+
+```python
+from accsify_tesseract import (
+    TesseractError,         # Base exception for all errors
+    EngineInitError,        # Failed to initialize engine (missing traineddata, invalid path)
+    ImageLoadError,         # Image file missing or corrupted
+    RecognitionError,       # OCR recognition failure
+    ModelDownloadError,     # Network / WinHTTP download failure
+    ModelNotFoundError      # Requested model not found in catalog
+)
+
+try:
+    with TesseractEngine(language="nonexistent") as engine:
+        engine.set_image("sample.png")
+except EngineInitError as e:
+    print(f"Initialization error for {e.language} in {e.datapath}: {e}")
+```
+
+---
+
+## 13. License
+
+Distributed under the **MIT License**. Copyright (C) 2026 **accsify**. All rights reserved.