quiz-gen 0.1.5__py3-none-any.whl

quiz_gen-0.1.5.dist-info/METADATA

@@ -0,0 +1,395 @@
+Metadata-Version: 2.4
+Name: quiz-gen
+Version: 0.1.5
+Summary: AI-powered quiz generator for regulatory, certification, and educational documentation
+Author-email: Yauheniya Varabyova <yauheniya.ai@gmail.com>
+License-Expression: MIT
+Project-URL: Documentation, https://quiz-gen.readthedocs.io
+Project-URL: Repository, https://github.com/yauheniya-ai/quiz-gen
+Project-URL: Bug Tracker, https://github.com/yauheniya-ai/quiz-gen/issues
+Keywords: quiz,regulation,certification,education,eur-lex,cfr
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: beautifulsoup4>=4.12.0
+Requires-Dist: lxml>=5.0.0
+Requires-Dist: requests>=2.31.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.5.0; extra == "dev"
+Requires-Dist: pre-commit>=3.4.0; extra == "dev"
+Requires-Dist: twine>=4.0.0; extra == "dev"
+Requires-Dist: mkdocs; extra == "dev"
+Requires-Dist: mkdocs-material; extra == "dev"
+Dynamic: license-file
+
+# quiz-gen
+
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![PyPI version](https://img.shields.io/pypi/v/quiz-gen?color=blue&label=PyPI)](https://pypi.org/project/quiz-gen/)
+[![GitHub last commit](https://img.shields.io/github/last-commit/yauheniya-ai/quiz-gen)](https://github.com/yauheniya-ai/quiz-gen/commits/main)
+[![Downloads](https://pepy.tech/badge/quiz-gen)](https://pepy.tech/project/quiz-gen)
+
+
+AI-powered quiz generator for regulatory, certification, and educational documentation. Extract structured content from complex legal and technical documents to create comprehensive learning materials.
+
+## Features
+
+- **EUR-Lex Document Parser**: Parse and structure European Union legal documents with full table of contents extraction
+- **Hierarchical Document Analysis**: Automatically identify document structure including chapters, sections, articles, and recitals
+- **Intelligent Chunking**: Extract meaningful content chunks at appropriate granularity levels (articles and recitals)
+- **Table of Contents Generation**: Build complete document navigation structure with 3-level hierarchy
+- **Regulatory Document Support**: Specialized parsing for aviation regulations, directives, and other technical documentation
+
+## Installation
+
+```bash
+pip install quiz-gen
+```
+
+## Quick Start
+
+### Parsing EUR-Lex Documents
+
+```python
+from quiz_gen import EURLexParser
+
+# Parse a regulation document
+url = "https://eur-lex.europa.eu/legal-content/EN/TXT/HTML/?uri=OJ:L_202401689"
+parser = EURLexParser(url=url)
+chunks, toc = parser.parse()
+
+# Access structured content
+print(f"Extracted {len(chunks)} content chunks")
+print(f"Document has {len(toc['sections'])} major sections")
+
+# Save results
+parser.save_chunks('output_chunks.json')
+parser.save_toc('output_toc.json')
+```
+
+### Document Structure
+
+The parser extracts documents into a multi-level hierarchy:
+
+**Level 1**: Major Sections
+- Preamble
+- Enacting Terms
+
+**Level 2/3**: Structural Divisions
+- Chapters
+- Sections
+
+**Level 1/2/3/4**: Content Elements
+- Title
+- Citation
+- Recitals
+- Articles
+- Concluding formulas
+- Annex
+- Appendix
+
+### Working with Chunks
+
+```python
+# Iterate through extracted chunks
+for chunk in chunks:
+    print(f"{chunk.title}")
+    print(f"Type: {chunk.section_type.value}")
+    print(f"Number: {chunk.number}")
+    print(f"Content: {chunk.content[:200]}...")
+    print(f"Hierarchy: {' > '.join(chunk.hierarchy_path)}")
+    print()
+```
+
+### Displaying Table of Contents
+
+```python
+# Print formatted TOC
+parser.print_toc()
+
+# Output:
+# PREAMBLE
+#   Citation 
+#   Recital 1
+#   Recital 2
+#   ...
+# 
+# ENACTING TERMS
+#   CHAPTER I - PRINCIPLES
+#     Article 1 - Subject matter and objectives
+#     Article 2 - Scope
+```
+
+## Use Cases
+
+### Compliance and Legal
+
+- Analyze regulatory requirements systematically
+- Track changes across document versions
+- Build searchable knowledge bases from legal texts
+
+### Documentation Processing
+
+- Convert unstructured documents into structured data
+- Build citation networks and cross-references
+- Support automated document analysis workflows
+
+### Education and Training
+
+- Generate study materials from regulatory documents
+- Create structured learning paths for certification programs
+- Extract key concepts for examination preparation
+
+## Supported Document Types
+
+Currently supports:
+
+- **EUR-Lex HTML Documents**: European Union regulations, directives, decisions
+- **Legislative Acts**: Structured legal documents with formal hierarchies
+
+### Document Format Requirements
+
+- Documents must use EUR-Lex HTML format
+- Must contain `eli-subdivision` elements for proper structure identification
+- Supports multi-level hierarchies with chapters, sections, and articles
+
+## Advanced Usage
+
+### Custom Parsing Workflows
+
+```python
+from quiz_gen import EURLexParser
+
+parser = EURLexParser(url=document_url)
+
+# Parse specific sections
+parser._parse_preamble()  # Extract citations and recitals
+parser._parse_enacting_terms()  # Extract chapters and articles
+parser._parse_annexes()  # Extract annexes
+
+# Access intermediate results
+toc = parser.toc  # Full table of contents
+chunks = parser.chunks  # Content chunks only
+```
+
+### Filtering Chunks by Type
+
+```python
+from quiz_gen import SectionType
+
+# Get only recitals
+recitals = [c for c in chunks if c.section_type == SectionType.RECITAL]
+
+# Get only articles
+articles = [c for c in chunks if c.section_type == SectionType.ARTICLE]
+
+# Filter by chapter
+chapter_1_articles = [
+    c for c in articles 
+    if 'CHAPTER I' in ' > '.join(c.hierarchy_path)
+]
+```
+
+### Accessing Metadata
+
+```python
+for chunk in chunks:
+    # Access structured metadata
+    print(chunk.metadata)  # {'id': 'art_1', 'subtitle': '...'}
+    
+    # Navigate hierarchy
+    print(chunk.hierarchy_path)  # ['CHAPTER I - PRINCIPLES', 'Article 1']
+    
+    # Identify parent sections
+    print(chunk.parent_section)
+```
+
+## Project Structure
+
+```
+quiz-gen/
+├── src/
+│   └── quiz_gen/
+│       ├── parsers/
+│       │   └── html/
+│       │       └── eu_lex_parser.py
+│       ├── models/
+│       │   ├── chunk.py
+│       │   ├── document.py
+│       │   └── quiz.py
+│       └── utils/
+├── examples/
+│   └── eu_lex_toc_chunks.py
+├── tests/
+├── data/
+│   ├── processed/
+│   └── raw/
+└── docs/
+```
+
+## Development
+
+### Setting up Development Environment
+
+```bash
+# Clone the repository
+git clone https://github.com/yauheniya-ai/quiz-gen.git
+cd quiz-gen
+
+# Install with development dependencies
+pip install -e ".[dev]"
+
+# Run tests
+pytest
+
+# Run linting
+ruff check .
+black .
+```
+
+
+### Contributing
+
+Contributions are welcome! Please ensure:
+
+1. Code follows PEP 8 style guidelines
+2. All tests pass
+3. New features include appropriate tests
+4. Documentation is updated
+
+## API Reference
+
+### EURLexParser
+
+Main parser class for EUR-Lex documents.
+
+**Methods**:
+- `parse()` -> `tuple[List[RegulationChunk], Dict]`: Parse document and return chunks and TOC
+- `fetch()` -> `str`: Fetch HTML content from URL
+- `save_chunks(filepath: str)`: Save chunks to JSON file
+- `save_toc(filepath: str)`: Save table of contents to JSON file
+- `print_toc()`: Display formatted table of contents
+
+### RegulationChunk
+
+Represents a parsed content chunk (article or recital).
+
+**Attributes**:
+- `section_type`: Type of section (ARTICLE, RECITAL, etc.)
+- `number`: Section number (e.g., "1", "42")
+- `title`: Full title including subtitle
+- `content`: Text content
+- `hierarchy_path`: List of parent sections
+- `metadata`: Additional structured data
+
+### SectionType
+
+Enumeration of document section types.
+
+**Values**:
+- `PREAMBLE`: Preamble section
+- `ENACTING_TERMS`: Main regulatory content
+- `CITATION`: Citation in preamble
+- `RECITAL`: Recital in preamble
+- `CHAPTER`: Chapter division
+- `SECTION`: Section within chapter
+- `ARTICLE`: Article (main content unit)
+- `ANNEX`: Annex section
+
+## Roadmap
+
+Future enhancements planned:
+
+- AI-powered quiz generation from extracted content
+- Support for additional document formats (PDF, DOCX, PPTX)
+- Multi-language support
+- Question validation and quality metrics
+- Integration with learning management systems
+- Version comparison and diff analysis
+
+## License
+
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
+
+## Citation
+
+If you use this software in academic work, please cite:
+
+```
+Varabyova, Y. (2026). Quiz Gen AI: AI-powered quiz generator for regulatory documentation.
+GitHub repository: https://github.com/yauheniya-ai/quiz-gen
+```
+
+## Support
+
+- Documentation: https://quiz-gen.readthedocs.io
+- Issue Tracker: https://github.com/yauheniya-ai/quiz-gen/issues
+
+## Acknowledgments
+
+Built with:
+- BeautifulSoup4 for HTML parsing
+- lxml for XML processing
+- EUR-Lex for providing structured legal documents
+
+## Changelog
+
+### Version 0.1.0 (2026-01-17)
+
+Initial release:
+- EUR-Lex document parser
+- Hierarchical document structure extraction
+- Table of contents generation
+- JSON export for chunks and TOC
+
+### Version 0.1.1 (2026-01-18)
+
+Parser enhancements:
+- Added regulation title extraction and chunking
+- Support for flexible 3-4 level hierarchy with sections within chapters
+- Complete annexes extraction including table-based content
+- Combined citations into single chunk matching EU-Lex structure
+- Added concluding formulas parsing
+
+### Version 0.1.2 (2026-01-18)
+
+Text formatting and tooling:
+- Implemented smart text cleaning for proper list formatting (removes extra newlines after list markers)
+- Fixed numbered paragraph spacing
+- Added professional command-line interface (CLI)
+- Created comprehensive documentation with MkDocs and Material theme
+
+### Version 0.1.3 (2026-01-19)
+
+Parser robustness improvements:
+- Fixed parsing of articles directly under enacting terms (without chapter hierarchy)
+- Enhanced article content extraction to handle table-based list items (e.g., (a), (b), (c) in table cells)
+- Added proper appendix detection and parsing (distinguishes appendices from annexes)
+- Improved title extraction for multi-paragraph appendix titles
+
+### Version 0.1.4 (2026-01-19)
+
+Annex parsing improvements:
+- Added intelligent detection and parsing of parts within annexes (PART 1, PART 2, etc.)
+- Improved part titles to include annex identifier (e.g., "ANNEX 1 - PART 1" instead of "ANNEX - PART 1")
+- Removed arbitrary content truncation in annexes and appendices - all content now preserved in full
+- Enhanced content collection for parts with proper boundary detection between sections
+
+### Version 0.1.5 (2026-01-19)
+
+Bug fixes:
+- Fixed annex TOC title to display with identifier (e.g., "ANNEX 1" instead of "ANNEX")
+- Fixed empty content in annex parts by switching from sibling navigation to descendants iteration

quiz_gen-0.1.5.dist-info/RECORD

@@ -0,0 +1,37 @@
+quiz_gen/__init__.py,sha256=BLiiFuMIAzlX_G0mTpoGpx1Y6V19kurOM7dhqZopAJg,540
+quiz_gen/__version__.py,sha256=03oJbrV_EJ7RkHGfnaj4OK9XO1l5fKnBwqKcHiKtgKk,410
+quiz_gen/cli.py,sha256=rpqIDQMqnqppeOQkDNtXq63egC-eUgIEsdcGDpWyz1E,6264
+quiz_gen/config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/agents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/agents/answer_generator.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/agents/base_agent.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/agents/orchestrator.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/agents/question_generator.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/agents/reviewer.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/agents/validator.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/models/chunk.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/models/document.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/models/question.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/models/quiz.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/parsers/__init__.py,sha256=g2KpJf5yen7mZJy-GWQXybGK2k7mZuYEpyfqKg1rZEw,230
+quiz_gen/parsers/base.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/parsers/pdf_parser.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/parsers/utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/parsers/html/eu_lex_parser.py,sha256=-3bJ8RVjqeD9qKysMKG6ICPcLYI81_TtYuWdkn-Yobo,36109
+quiz_gen/storage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/storage/base.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/storage/database.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/storage/json_storage.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/utils/helpers.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/utils/logging.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/validation/human_feedback.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen/validation/quality_checker.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+quiz_gen-0.1.5.dist-info/licenses/LICENSE,sha256=bJXbgXAmDWf3_2rn3BVh6-4wZtB5xbycNfqTHyGu_tE,1076
+quiz_gen-0.1.5.dist-info/METADATA,sha256=NSWmeH_HCGkIA6gqqevP7BCObHA8jxprD0ZK2Y7saoA,11475
+quiz_gen-0.1.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+quiz_gen-0.1.5.dist-info/entry_points.txt,sha256=uRVta04GJsOC3b3AZUONSq924-Vqwp2UjsEGYsJKQe4,47
+quiz_gen-0.1.5.dist-info/top_level.txt,sha256=Nrt267uGX_L3FsFX2NSW0Uh9XQ9LthH7Mss9n9VrL2g,9
+quiz_gen-0.1.5.dist-info/RECORD,,

quiz_gen-0.1.5.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

quiz_gen-0.1.5.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+quiz-gen = quiz_gen.cli:main

quiz_gen-0.1.5.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Yauheniya Varabyova
+
+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.

quiz_gen-0.1.5.dist-info/top_level.txt

@@ -0,0 +1 @@
+quiz_gen