PDF Document Layout Analysis

A Docker-powered microservice for intelligent PDF document layout analysis, OCR, and content extraction

📣 Feedback & Use Cases

Are you using this tool in your workflow? We’d love to learn more about your experience. Sharing your use case helps us improve the service for everyone.

👉 Submit your use case here

🚀 Overview

This project provides a powerful and flexible PDF analysis microservice built with Clean Architecture principles. The service enables OCR, segmentation, and classification of different parts of PDF pages, identifying elements such as texts, titles, pictures, tables, formulas, and more. Additionally, it determines the correct reading order of these identified elements and can convert PDFs to various formats including Markdown and HTML with automatic translation support powered by Ollama.

The service offers both a user-friendly Gradio web interface for interactive use and a comprehensive REST API for programmatic access and integration.

Gradio Web Interface - Easy-to-use UI for PDF analysis, conversion, and translation

🚀 Quick Start

1. Start the Service

make start # or just start (https://github.com/casey/just)

The service provides two interfaces:

• 🎨 Web UI (Gradio): http://localhost:7860 - User-friendly interface for all features
• 🔌 REST API: http://localhost:5060 - Programmatic access for integrations

make help

Check service status:

curl http://localhost:5060/info

2. Using the Web UI

Simply open your browser and navigate to http://localhost:7860 to access the intuitive web interface. The UI provides:

• 📄 PDF Analysis - Upload and analyze PDFs with visual results
• 🔄 Format Conversion - Convert to Markdown or HTML
• 🌍 Translation - Translate documents to multiple languages
• 👁️ Visualization - View segmentation overlays on your PDFs
• 🔍 OCR Processing - Apply OCR to scanned documents
• 📑 TOC Extraction - Extract table of contents

3. Using the REST API

Analyze a PDF document (VGT model - high accuracy):

curl -X POST -F 'file=@/path/to/your/document.pdf' http://localhost:5060

Fast analysis (LightGBM models - faster processing):

curl -X POST -F 'file=@/path/to/your/document.pdf' -F "fast=true" http://localhost:5060

4. Stop the Service

make stop

💡 Tip: The Web UI at http://localhost:7860 is the easiest way to get started. For automation and integration, use the REST API at http://localhost:5060.

✨ Key Features

• 🎨 User-Friendly Web UI - Intuitive Gradio interface for easy PDF processing
• 🔍 Advanced PDF Layout Analysis - Segment and classify PDF content with high accuracy
• 🖼️ Visual & Fast Models - Choose between VGT (Vision Grid Transformer) for accuracy or LightGBM for speed
• 📝 Multi-format Output - Export to JSON, Markdown, HTML, and visualize PDF segmentations
• 🌍 Automatic Translation - Translate documents to multiple languages using Ollama models
• 🌐 OCR Support - 150+ language support with Tesseract OCR
• 📊 Table & Formula Extraction - Extract tables as HTML and formulas as LaTeX
• 🏗️ Clean Architecture - Modular, testable, and maintainable codebase
• 🐳 Docker-Ready - Easy deployment with GPU support
• ⚡ RESTful API - Comprehensive API with 10+ endpoints

📸 Example Results

🔗 Project Links

• GitHub: pdf-document-layout-analysis
• HuggingFace: pdf-document-layout-analysis
• DockerHub: pdf-document-layout-analysis

📋 Table of Contents

• 🚀 Overview
• 🚀 Quick Start
• ✨ Key Features
• ⚙️ Dependencies
• 📋 Requirements
• 📚 API Reference
• 💡 Usage Examples

• 🏗️ Architecture
• 🤖 Models
• 📊 Data
• 🔧 Development
• 📈 Benchmarks

• 🌐 Installation of More Languages for OCR
• 🔗 Related Services
• 🤝 Contributing

⚙️ Dependencies

Required

• Docker Desktop 4.25.0+ - Installation Guide
• Python 3.10+ (for local development)

Optional

• NVIDIA Container Toolkit - Installation Guide (for GPU support)

📋 Requirements

System Requirements

• RAM: 2 GB minimum
• GPU Memory: 5 GB (optional, will fallback to CPU if unavailable)
• Disk Space: 10 GB for models and dependencies
• CPU: Multi-core recommended for better performance

Docker Requirements

• Docker Engine 20.10+
• Docker Compose 2.0+

🖥️ ARM64 / NVIDIA Grace-Blackwell (e.g. DGX Spark)

The GPU stack is picked by select_gpu_stack.sh based on compute capability, and its legacy/nextgen profiles already build and run on aarch64 hosts — their CUDA base images ship arm64 manifests, and nextgen's compute-capability check (>= 10.0) already matches Blackwell GPUs like the GB10, running via PTX JIT.

For native aarch64 hardware such as the DGX Spark (Grace CPU + GB10 GPU, sm_121), this adds an explicit grace profile that targets CUDA 13 and compiles native SASS for the GPU instead of relying on nextgen's PTX JIT fallback:

GPU_STACK_PROFILE=grace just start_detached_gpu

which resolves to:

| Build arg | Value | | ------------------------ | ----------------------------------------------- | | BUILDER_IMAGE | nvidia/cuda:13.0.3-cudnn-devel-ubuntu24.04 | | TORCH_INDEX_URL | https://download.pytorch.org/whl/cu130 | | TORCH_CUDA_ARCH_LIST | 12.0;12.1 |

Verified on: DGX Spark, aarch64, NVIDIA GB10 (compute capability 12.1), driver 580 / CUDA 13.0. No pin relaxation was needed — cu130 ships manylinux_2_28_aarch64 wheels for the exact torch/torchvision versions this project already pins, and 13.0.3-cudnn-devel-ubuntu24.04 is the newest cudnn-devel-ubuntu24.04 tag with an arm64 manifest at the time of writing.

| Note | Detail | | --- | --- | | Native vs. PTX JIT | nextgen (cu128, 12.0+PTX) also runs on the GB10 via PTX JIT; grace compiles native sm_120/sm_121 SASS to match the host's CUDA 13 driver, avoiding first-call JIT compilation. | | GPU device-name log line | Upstream's get_model_configuration device-name log line was not observed to fire on this hardware; GPU use is still confirmed via nvidia-smi and the "Is PyTorch using GPU: True" log line. | | detectron2 build | Compiles from source at the pinned commit against the grace arch list; no changes were needed beyond the existing TORCH_CUDA_ARCH_LIST build arg. | | Build time | Docker's layer cache makes rebuilds after the first near-instant; the first build compiles detectron2 and downloads several GB of wheels/models, same as any other profile. |

📚 API Reference

The service provides a comprehensive RESTful API with the following endpoints:

Core Analysis Endpoints

| Endpoint | Method | Description | Parameters | | ---------------------- | ------ | --------------------------------------- | --------------------------------------- | | / | POST | Analyze PDF layout and extract segments | file, fast, parse_tables_and_math | | /save_xml/{filename} | POST | Analyze PDF and save XML output | file, xml_file_name, fast | | /get_xml/{filename} | GET | Retrieve saved XML analysis | xml_file_name |

Content Extraction Endpoints

| Endpoint | Method | Description | Parameters | | ------------------------------ | ------ | ------------------------------ | ----------------------- | | /text | POST | Extract text by content types | file, fast, types | | /toc | POST | Extract table of contents | file, fast | | /toc_legacy_uwazi_compatible | POST | Extract TOC (Uwazi compatible) | file |

Format Conversion Endpoints

| Endpoint | Method | Description | Parameters | | ------------ | ------ | ----------------------------------------------------------- | -------------------------------------------------------------------------------------------- | | /markdown | POST | Convert PDF to Markdown (includes segmentation data in zip) | file, fast, extract_toc, dpi, output_file, target_languages, translation_model, segment_boxes | | /html | POST | Convert PDF to HTML (includes segmentation data in zip) | file, fast, extract_toc, dpi, output_file, target_languages, translation_model, segment_boxes | | /visualize | POST | Visualize segmentation results on the PDF | file, fast |

OCR & Utility Endpoints

| Endpoint | Method | Description | Parameters | | -------- | ------ | ---------------------------- | -------------------------------------------- | | /ocr | POST | Apply OCR to PDF | file, language, rotate_pages, deskew | | /info | GET | Get service information | - | | / | GET | Health check and system info | - | | /error | GET | Test error handling | - |

Common Parameters

• file: PDF file to process (multipart/form-data)
• fast: Use LightGBM models instead of VGT (boolean, default: false)
• parse_tables_and_math: Apply OCR to table regions (boolean, default: false) and convert formulas to LaTeX
• language: OCR language code (string, default: "en")
• types: Comma-separated content types to extract (string, default: "all")
• extract_toc: Include table of contents at the beginning of the output (boolean, default: false)
• dpi: Image resolution for conversion (integer, default: 120)
• target_languages: Comma-separated list of target languages for translation (e.g. "Turkish, Spanish, French")
• translation_model: Ollama model to use for translation (string, default: "gpt-oss")
• segment_boxes: JSON-encoded list of segment boxes from a prior analysis of the same document (e.g. the response of POST /). When provided, /markdown and /html skip re-running layout analysis and convert using these segments directly — the same pattern /toc_from_xml already uses for its own segment_boxes parameter

💡 Usage Examples

Basic PDF Analysis

Standard analysis with VGT model:

curl -X POST \
  -F '[email protected]' \
  http://localhost:5060

Fast analysis with LightGBM models:

curl -X POST \
  -F '[email protected]' \
  -F 'fast=true' \
  http://localhost:5060

Analysis with table and math parsing:

curl -X POST \
  -F '[email protected]' \
  -F 'parse_tables_and_math=true' \
  http://localhost:5060

Text Extraction

Extract all text:

curl -X POST \
  -F '[email protected]' \
  -F 'types=all' \
  http://localhost:5060/text

Extract specific content types:

curl -X POST \
  -F '[email protected]' \
  -F 'types=title,text,table' \
  http://localhost:5060/text

Format Conversion

Convert to Markdown:

curl -X POST http://localhost:5060/markdown \
  -F '[email protected]' \
  -F 'extract_toc=true' \
  -F 'output_file=document.md' \
  --output 'document.zip'

Convert to HTML:

curl -X POST http://localhost:5060/html \
  -F '[email protected]' \
  -F 'extract_toc=true' \
  -F 'output_file=document.md' \
  --output 'document.zip'

Convert to Markdown reusing segments from a prior analysis (skips re-analysis):

# 1. Analyze once and keep the segments
curl -X POST http://localhost:5060 -F '[email protected]' > segments.json
2. Reuse them for both /markdown and /html without re-running analysis
curl -X POST http://localhost:5060/markdown \
  -F '[email protected]' \
  -F "segment_boxes=$(cat segments.json)" \
  --output 'document.zip'

Convert to Markdown with Translation:

curl -X POST http://localhost:5060/markdown \
  -F '[email protected]' \
  -F 'output_file=document.md' \
  -F 'target_languages=Turkish, Spanish' \
  -F 'translation_model=gpt-oss' \
  --output 'document.zip'

Convert to HTML with Translation:

curl -X POST http://localhost:5060/html \
  -F '[email protected]' \
  -F 'output_file=document.md' \
  -F 'target_languages=French, Russian' \
  -F 'translation_model=huihui_ai/hunyuan-mt-abliterated' \
  --output 'document.zip'

📋 Segmentation Data & Translations: Format conversion endpoints automatically include detailed segmentation data in the zip output. The resulting zip file contains:

> - Original file: The converted document in the requested format

- Segmentation data: {filename}_segmentation.json file with information about each detected document segment:

- Coordinates: left, top, width, height

- Page information: page_number, page_width, page_height

- Content: text content and segment type (e.g., "Title", "Text", "Table", "Picture")

- Translated files (if target_languages specified): {filename}_{language}.{extension} for each target language

- Images (if present): {filename}_pictures/ directory containing extracted images

Translation Features

The /markdown and /html endpoints support automatic translation of the converted content into multiple languages using Ollama models.

Translation Requirements:

• The specified translation model must be available in Ollama
• An output_file must be specified (translations are only included in zip responses)

• Any Ollama-compatible model (e.g., gpt-oss, llama2, mistral, etc.)
• Models are automatically downloaded if not present locally

1. The service checks if the specified model is available in Ollama
2. If not available, it attempts to download the model using ollama pull
3. For each target language, the content is translated while preserving:

1. Translated files are named: {filename}_{language}.{extension}

Example Translation Output:

document.zip
├── document.md                   # Source text with markdown/html styling
├── document_Spanish.md           # Spanish translation
├── document_French.md            # French translation
├── document_Turkish.md           # Turkish translation
├── document_segmentation.json    # Segmentation information
└── document_pictures/       # (if images present)
    ├── document_1_1.png
    └── document_1_2.png

OCR Processing

OCR in English:

curl -X POST \
  -F 'file=@scanned_document.pdf' \
  -F 'language=en' \
  http://localhost:5060/ocr \
  --output ocr_processed.pdf

OCR in other languages:

# French
curl -X POST \
  -F 'file=@document_french.pdf' \
  -F 'language=fr' \
  http://localhost:5060/ocr \
  --output ocr_french.pdf
Spanish
curl -X POST \
  -F 'file=@document_spanish.pdf' \
  -F 'language=es' \
  http://localhost:5060/ocr \
  --output ocr_spanish.pdf

OCR with rotation fix for sideways scanned documents

curl -X POST \
  -F 'file=@scanned_document.pdf' \
  -F 'language=en' \
  -F 'rotate_pages=true' \
  http://localhost:5060/ocr \
  --output ocr_processed.pdf

OCR with deskew for crooked scans

curl -X POST \
  -F 'file=@scanned_document.pdf' \
  -F 'language=en' \
  -F 'deskew=true' \
  http://localhost:5060/ocr \
  --output ocr_processed.pdf

Visualization

Generate visualization PDF:

curl -X POST \
  -F '[email protected]' \
  http://localhost:5060/visualize \
  --output visualization.pdf

Table of Contents Extraction

Extract structured TOC:

curl -X POST \
  -F '[email protected]' \
  http://localhost:5060/toc

XML Storage and Retrieval

Analyze and save XML:

curl -X POST \
  -F '[email protected]' \
  http://localhost:5060/save_xml/my_analysis

Retrieve saved XML:

curl http://localhost:5060/get_xml/my_analysis.xml

Service Information

Get service info and supported languages:

curl http://localhost:5060/info

Health check:

curl http://localhost:5060/

Response Format

Most endpoints return JSON with segment information:

[
  {
    "left": 72.0,
    "top": 84.0,
    "width": 451.2,
    "height": 23.04,
    "page_number": 1,
    "page_width": 595.32,
    "page_height": 841.92,
    "text": "Document Title",
    "type": "Title"
  },
  {
    "left": 72.0,
    "top": 120.0,
    "width": 451.2,
    "height": 200.0,
    "page_number": 1,
    "page_width": 595.32,
    "page_height": 841.92,
    "text": "This is the main text content...",
    "type": "Text"
  }
]

Supported Content Types

• Caption - Image and table captions
• Footnote - Footnote text
• Formula - Mathematical formulas
• List item - List items and bullet points
• Page footer - Footer content
• Page header - Header content
• Picture - Images and figures
• Section header - Section headings
• Table - Table content
• Text - Regular text paragraphs
• Title - Document and section titles

🏗️ Architecture

This project follows Clean Architecture principles, ensuring separation of concerns, testability, and maintainability. The codebase is organized into distinct layers:

Directory Structure

src/
├── domain/                 # Enterprise Business Rules
│   ├── PdfImages.py       # PDF image handling domain logic
│   ├── PdfSegment.py      # PDF segment entity
│   ├── Prediction.py      # ML prediction entity
│   └── SegmentBox.py      # Core segment box entity
├── use_cases/             # Application Business Rules
│   ├── pdf_analysis/      # PDF analysis use case
│   ├── text_extraction/   # Text extraction use case
│   ├── toc_extraction/    # Table of contents extraction
│   ├── visualization/     # PDF visualization use case
│   ├── ocr/              # OCR processing use case
│   ├── markdown_conversion/ # Markdown conversion use case (with translation)
│   └── html_conversion/   # HTML conversion use case (with translation)
├── adapters/              # Interface Adapters
│   ├── infrastructure/    # External service adapters
│   ├── ml/               # Machine learning model adapters
│   ├── storage/          # File storage adapters
│   └── web/              # Web framework adapters
├── ports/                 # Interface definitions
│   ├── services/         # Service interfaces
│   └── repositories/     # Repository interfaces
└── drivers/              # Frameworks & Drivers
    └── web/              # FastAPI application setup

Layer Responsibilities

• Domain Layer: Contains core business entities and rules independent of external concerns
• Use Cases Layer: Orchestrates domain entities to fulfill specific application requirements
• Adapters Layer: Implements interfaces defined by inner layers and adapts external frameworks
• Drivers Layer: Contains frameworks, databases, and external agency configurations

Key Benefits

• 🔄 Dependency Inversion: High-level modules don't depend on low-level modules
• 🧪 Testability: Easy to unit test business logic in isolation
• 🔧 Maintainability: Changes to external frameworks don't affect business rules
• 📈 Scalability: Easy to add new features without modifying existing code

🤖 Models

The service offers two complementary model approaches, each optimized for different use cases:

1. Vision Grid Transformer (VGT) - High Accuracy Model

Overview: A state-of-the-art visual model developed by Alibaba Research Group that "sees" the entire page layout.

Key Features:

• 🎯 High Accuracy: Best-in-class performance on document layout analysis
• 👁️ Visual Understanding: Analyzes the entire page context including spatial relationships
• 📊 Trained on DocLayNet: Uses the comprehensive DocLayNet dataset
• 🔬 Research-Backed: Based on Advanced Literate Machinery

• GPU: 5GB+ VRAM (recommended)
• CPU: Falls back automatically if GPU unavailable
• Processing Speed: ~1.75 seconds/page (GPU [GTX 1070]) or ~13.5 seconds/page (CPU [i7-8700])

2. LightGBM Models - Fast & Efficient

Overview: Lightweight ensemble of two specialized models using XML-based features from Poppler.

Key Features:

• ⚡ High Speed: ~0.42 seconds per page on CPU (i7-8700)
• 💾 Low Resource Usage: CPU-only, minimal memory footprint
• 🔄 Dual Model Approach:

• 📄 XML-Based: Uses Poppler's PDF-to-XML conversion for feature extraction

• Slightly lower accuracy compared to VGT
• No visual context understanding
• Excellent for batch processing and resource-constrained environments

OCR Integration

Both models integrate seamlessly with OCR capabilities:

• Engine: Tesseract OCR
• Processing: ocrmypdf
• Languages: 150+ supported languages
• Output: Searchable PDFs with preserved layout

Model Selection Guide

| Use Case | Recommended Model | Reason | | -------------------------- | ----------------- | ----------------------------------- | | High accuracy requirements | VGT | Superior visual understanding | | Batch processing | LightGBM | Faster processing, lower resources | | GPU available | VGT | Leverages GPU acceleration | | CPU-only environment | LightGBM | Optimized for CPU processing | | Real-time applications | LightGBM | Consistent fast response times | | Research/analysis | VGT | Best accuracy for detailed analysis |

📊 Data

Training Dataset

Both model types are trained on the comprehensive DocLayNet dataset, a large-scale document layout analysis dataset containing over 80,000 document pages.

Document Categories

The models can identify and classify 11 distinct content types:

| ID | Category | Description | | --- | ------------------ | ----------------------------------- | | 1 | Caption | Image and table captions | | 2 | Footnote | Footnote references and text | | 3 | Formula | Mathematical equations and formulas | | 4 | List item | Bulleted and numbered list items | | 5 | Page footer | Footer content and page numbers | | 6 | Page header | Header content and titles | | 7 | Picture | Images, figures, and graphics | | 8 | Section header | Section and subsection headings | | 9 | Table | Tabular data and structures | | 10 | Text | Regular paragraph text | | 11 | Title | Document and chapter titles |

Dataset Characteristics

• Domain Coverage: Academic papers, technical documents, reports
• Language: Primarily English with multilingual support
• Quality: High-quality annotations with bounding boxes and labels
• Diversity: Various document layouts, fonts, and formatting styles

🔧 Development

Local Development Setup

1. Clone the repository:

git clone https://github.com/huridocs/pdf-document-layout-analysis.git
   cd pdf-document-layout-analysis

1. Create virtual environment:

make install_venv

1. Activate environment:

source .venv/bin/activate

1. Install dependencies:

make install

Code Quality

Format code:

make formatter

Check formatting:

make check_format

Testing

Run tests:

make test

Integration tests:

# End-to-end tests require a running service on http://localhost:5060
python -m pytest src/tests/test_end_to_end.py

Docker Development

Build and start:

# Standard start (includes translation features)
make start
Start without translation support
make start_no_translation
Start in detached mode (API only, no UI)
make start_detached
Start in detached mode with GPU (API only, no UI)
make start_detached_gpu
Force CPU mode with translation
make start_no_gpu

Clean up Docker resources:

# Stop all services
make stop
Remove containers
make remove_docker_containers
Remove images
make remove_docker_images

Project Structure

pdf-document-layout-analysis/
├── src/                    # Source code
│   ├── domain/            # Business entities
│   ├── use_cases/         # Application logic
│   ├── adapters/          # External integrations
│   ├── ports/             # Interface definitions
│   ├── drivers/           # Framework configurations
│   ├── app.py             # FastAPI application
│   └── gradio_app.py      # Gradio web interface
├── test_pdfs/             # Test PDF files
├── models/                # ML model storage
├── docker-compose.yml     # Docker configuration
├── Dockerfile             # FastAPI container definition
├── Dockerfile.gradio      # Gradio container definition
├── justfile              # Development commands (just)
├── pyproject.toml        # Python project configuration
└── requirements.txt      # Python dependencies

Environment Variables

Key configuration options:

# OCR configuration
OCR_SOURCE=/tmp/ocr_source
Model paths (auto-configured)
MODELS_PATH=./models
Service configuration
HOST=0.0.0.0
PORT=5060
Translation configuration (when using translation features)
OLLAMA_HOST=http://ollama:11434  # Ollama service endpoint

Adding New Features

1. Domain Logic: Add entities in src/domain/
2. Use Cases: Implement business logic in src/use_cases/
3. Adapters: Create integrations in src/adapters/
4. Ports: Define interfaces in src/ports/
5. Controllers: Add endpoints in src/adapters/web/

Debugging

View logs:

docker compose logs -f

Access container:

docker exec -it pdf-document-layout-analysis /bin/bash

Free up disk space:

make free_up_space

Order of Output Elements

The service returns SegmentBox elements in a carefully determined reading order:

Reading Order Algorithm

1. Poppler Integration: Uses Poppler PDF-to-XML conversion to establish initial token reading order
2. Segment Averaging: Calculates average reading order for multi-token segments
3. Type-Based Sorting: Prioritizes content types:

Non-Text Elements

For segments without text (e.g., images):

• Processed after text-based sorting
• Positioned based on nearest text segment proximity
• Uses spatial distance as the primary criterion

Advanced Table and Formula Extraction

Default Behavior

• Formulas: Automatically extracted as LaTeX format in the text property
• Tables: Basic text extraction included by default

Enhanced Table Extraction

Parse tables and extract them in HTML format by setting parse_tables_and_math=true:

curl -X POST -F '[email protected]' -F 'parse_tables_and_math=true' http://localhost:5060

Extraction Engines

• Formulas: LaTeX-OCR
• Tables: RapidTable

📈 Benchmarks

Performance

VGT model performance on PubLayNet dataset:

| Metric | Overall | Text | Title | List | Table | Figure | | ------------ | --------- | ----- | ----- | ----- | ----- | ------ | | F1 Score | 0.962 | 0.950 | 0.939 | 0.968 | 0.981 | 0.971 |

📊 Comparison: View comprehensive model comparisons at Papers With Code

Speed

Performance benchmarks on 15-page academic documents:

| Model | Hardware | Speed (sec/page) | Use Case | | ------------ | -------------------- | ---------------- | --------------- | | LightGBM | CPU (i7-8700 3.2GHz) | 0.42 | Fast processing | | VGT | GPU (GTX 1070) | 1.75 | High accuracy | | VGT | CPU (i7-8700 3.2GHz) | 13.5 | CPU fallback |

Performance Recommendations

• GPU Available: Use VGT for best accuracy-speed balance
• CPU Only: Use LightGBM for optimal performance
• Batch Processing: LightGBM for consistent throughput
• High Accuracy: VGT with GPU for best results

🌐 Installation of More Languages for OCR

The service uses Tesseract OCR with support for 150+ languages. The Docker image includes only common languages to minimize image size.

Installing Additional Languages

1. Access the Container

docker exec -it --user root pdf-document-layout-analysis /bin/bash

2. Install Language Packs

# Install specific language
apt-get update
apt-get install tesseract-ocr-[LANGCODE]

3. Common Language Examples

# Korean
apt-get install tesseract-ocr-kor
German
apt-get install tesseract-ocr-deu
French
apt-get install tesseract-ocr-fra
Spanish
apt-get install tesseract-ocr-spa
Chinese Simplified
apt-get install tesseract-ocr-chi-sim
Arabic
apt-get install tesseract-ocr-ara
Japanese
apt-get install tesseract-ocr-jpn

4. Verify Installation

curl http://localhost:5060/info

Language Code Reference

Find Tesseract language codes in the ISO to Tesseract mapping.

Supported Languages

Common language codes:

• eng - English
• fra - French
• deu - German
• spa - Spanish
• ita - Italian
• por - Portuguese
• rus - Russian
• chi-sim - Chinese Simplified
• chi-tra - Chinese Traditional
• jpn - Japanese
• kor - Korean
• ara - Arabic
• hin - Hindi

Usage with Multiple Languages

# OCR with specific language
curl -X POST \
  -F '[email protected]' \
  -F 'language=fr' \
  http://localhost:5060/ocr \
  --output french_ocr.pdf

🔗 Related Services

Explore our ecosystem of PDF processing services built on this foundation:

PDF Table of Contents Extractor

🔍 Purpose: Intelligent extraction of structured table of contents from PDF documents

Key Features:

• Leverages layout analysis for accurate TOC identification
• Hierarchical structure recognition
• Multiple output formats supported
• Integration-ready API

PDF Text Extraction

📝 Purpose: Advanced text extraction with layout awareness

Key Features:

• Content-type aware extraction
• Preserves document structure
• Reading order optimization
• Clean text output with metadata

Integration Benefits

These services work seamlessly together:

• Shared Analysis: Reuse layout analysis results across services
• Consistent Output: Standardized JSON format for easy integration
• Scalable Architecture: Deploy services independently or together
• Docker Ready: All services containerized for easy deployment

🤝 Contributing

We welcome contributions to improve the PDF Document Layout Analysis service!

How to Contribute

1. Fork the Repository

git clone https://github.com/your-username/pdf-document-layout-analysis.git

1. Create a Feature Branch

git checkout -b feature/your-feature-name

1. Set Up Development Environment

make install_venv
   make install

1. Make Your Changes

1. Run Tests and Quality Checks

make test
   make check_format

1. Submit a Pull Request

Contribution Guidelines

Code Standards

• Python: Follow PEP 8 with 125-character line length
• Architecture: Maintain Clean Architecture boundaries
• Testing: Include unit tests for new functionality
• Documentation: Update README and docstrings

Areas for Contribution

• 🐛 Bug Fixes: Report and fix issues
• ✨ New Features: Add new endpoints or functionality
• 📚 Documentation: Improve guides and examples
• 🧪 Testing: Expand test coverage
• 🚀 Performance: Optimize processing speed
• 🌐 Internationalization: Add language support

Development Workflow

1. Issue First: Create or comment on relevant issues
2. Small PRs: Keep pull requests focused and manageable
3. Clean Commits: Use descriptive commit messages
4. Documentation: Update relevant documentation
5. Testing: Ensure all tests pass

Getting Help

• 📚 Documentation: Check this README and inline docs
• 💬 Issues: Search existing issues or create new ones
• 🔍 Code: Explore the codebase structure
• 📧 Contact: Reach out to maintainers for guidance

License

This project is licensed under the terms specified in the LICENSE file.