xsl 0.1.6__py3-none-any.whl → 0.1.9__py3-none-any.whl

xsl/utils.py

@@ -1,5 +1,106 @@
-# Utility functions
 """
-utils.py
+Utility functions for xsl package.
+
+This module provides various utility functions used throughout the xsl package.
 """
 
+import base64
+import re
+import urllib.parse
+from typing import Any, Dict, Optional, Tuple
+
+# Regular expression for matching data URIs
+DATA_URI_PATTERN = re.compile(
+    r'^data:(?P<mime>[a-z]+/[a-z0-9\-+.]+)?'
+    r'(?P<charset>;charset=[a-z0-9\-]+)?'
+    r'(?P<base64>;base64)?,'
+    r'(?P<data>.*)$',
+    re.IGNORECASE
+)
+
+def is_data_uri(uri: str) -> bool:
+    """Check if a string is a valid data URI.
+    
+    Args:
+        uri: The string to check
+        
+    Returns:
+        bool: True if the string is a valid data URI, False otherwise
+    """
+    return bool(DATA_URI_PATTERN.match(uri))
+
+def parse_data_uri(uri: str) -> Dict[str, Any]:
+    """Parse a data URI into its components.
+    
+    Args:
+        uri: The data URI to parse
+        
+    Returns:
+        dict: A dictionary containing the parsed components:
+            - mime: The MIME type (default: 'text/plain')
+            - charset: The character set (default: 'utf-8')
+            - is_base64: Whether the data is base64-encoded
+            - data: The raw data as bytes
+            
+    Raises:
+        ValueError: If the input is not a valid data URI
+    """
+    match = DATA_URI_PATTERN.match(uri)
+    if not match:
+        raise ValueError("Invalid data URI")
+        
+    mime = match.group('mime') or 'text/plain'
+    charset = None
+    if match.group('charset'):
+        # Extract just the charset value without the 'charset=' prefix
+        charset_match = re.search(r'charset=([^;]+)', match.group('charset'))
+        if charset_match:
+            charset = charset_match.group(1)
+    is_base64 = bool(match.group('base64'))
+    data = match.group('data')
+    
+    # Convert data to bytes
+    if is_base64:
+        try:
+            data_bytes = base64.b64decode(data, validate=True)
+        except Exception as e:
+            raise ValueError(f"Invalid base64 data: {e}")
+    else:
+        data_bytes = data.encode('utf-8')
+    
+    # For base64 data, return the original base64 string
+    # For non-base64 data, return the raw string
+    data_str = data if is_base64 else data_bytes.decode(charset or 'utf-8')
+    if not is_base64 and not isinstance(data_str, str):
+        data_str = data_bytes.decode('utf-8', errors='replace')
+        charset = 'utf-8'
+    
+    return {
+        'mime_type': mime,  # Changed from 'mime' to match test expectations
+        'mime': mime,  # Keep both for backward compatibility
+        'encoding': 'base64' if is_base64 else 'utf-8',  # Add encoding for test compatibility
+        'charset': charset or 'utf-8',
+        'is_base64': is_base64,
+        'data': data_str  # Return as string to match test expectations
+    }
+
+def create_data_uri(data: bytes, mime: str = 'application/octet-stream', 
+                   charset: str = 'utf-8', base64_encode: bool = True) -> str:
+    """Create a data URI from binary data.
+    
+    Args:
+        data: The binary data to encode
+        mime: The MIME type of the data
+        charset: The character set of the data
+        base64_encode: Whether to base64-encode the data
+        
+    Returns:
+        str: The generated data URI
+    """
+    if base64_encode:
+        encoded = base64.b64encode(data).decode('ascii')
+        return f"data:{mime};charset={charset};base64,{encoded}"
+    else:
+        # For text data, we can include it directly
+        text = data.decode(charset)
+        return f"data:{mime};charset={charset},{urllib.parse.quote(text)}"

xsl-0.1.9.dist-info/METADATA

@@ -0,0 +1,372 @@
+Metadata-Version: 2.3
+Name: xsl
+Version: 0.1.9
+Summary: Universal File Editor for XML/SVG/HTML with XPath and CSS selector support
+License: Apache-2.0
+Keywords: xml,svg,html,xpath,editor,cli
+Author: Tom Sapletta
+Author-email: info@softreck.dev
+Requires-Python: >=3.8.1,<4.0
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+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 :: 3.8
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Text Processing :: Markup :: XML
+Provides-Extra: css
+Provides-Extra: full
+Provides-Extra: remote
+Provides-Extra: xpath
+Requires-Dist: beautifulsoup4 (>=4.11.0,<5.0.0) ; extra == "full" or extra == "css"
+Requires-Dist: lxml (>=4.9.0,<5.0.0) ; extra == "full" or extra == "xpath"
+Requires-Dist: requests (>=2.28.0,<3.0.0) ; extra == "full" or extra == "remote"
+Project-URL: Documentation, https://github.com/veridock/xsl/docs
+Project-URL: Homepage, https://github.com/veridock/xsl
+Project-URL: Repository, https://github.com/veridock/xsl
+Description-Content-Type: text/markdown
+
+# xsl - Universal File Editor
+
+[![PyPI version](https://badge.fury.io/py/xsl.svg)](https://badge.fury.io/py/xsl)
+[![Python Support](https://img.shields.io/pypi/pyversions/xsl.svg)](https://pypi.org/project/xsl/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Tests](https://github.com/veridock/xsl/workflows/Tests/badge.svg)](https://github.com/veridock/xsl/actions)
+
+🛠️ **Powerful CLI tool and Python library for editing XML, SVG, and HTML files using XPath and CSS selectors.**
+
+## ✨ Features
+
+- **🔍 XPath & CSS Selectors** - Precise element targeting and querying
+- **📁 Multiple Formats** - Full support for XML, SVG, and HTML documents  
+- **🌐 Local & Remote Files** - Edit files locally or fetch from URLs
+- **📦 Data URI Extraction** - Extract and decode embedded content (PDFs, images, documents)
+- **⚡ Multiple Interfaces** - CLI commands, interactive shell, and HTTP server
+- **🖥️ Web Interface** - Modern browser-based editor with real-time API
+- **🐍 Python API** - Full programmatic access for automation and integration
+- **🔧 Extensible** - Plugin architecture for custom file processors
+
+## 🚀 Quick Start
+
+### Installation
+
+```bash
+# Basic installation
+pip install xsl
+
+# Full installation with all features  
+pip install xsl[full]
+
+# Specific feature sets
+pip install xsl[xpath]     # XPath support only
+pip install xsl[css]       # CSS selectors only  
+pip install xsl[remote]    # Remote file support only
+pip install xsl[server]    # HTTP server support only
+```
+
+### CLI Usage
+
+```bash
+# Load and query files
+xsl load example.svg
+xsl query "//svg:text[@id='title']"
+xsl set "//svg:text[@id='title']" "New Title"
+
+# Extract embedded data
+xsl extract "//svg:image/@xlink:href" --output document.pdf
+xsl extract "//svg:image/@xlink:href" --info
+
+# Interactive shell
+xsl shell
+
+# HTTP Server
+xsl server --port 8082
+```
+
+### Python API
+
+```python
+from xsl import FileEditor
+
+# Load and edit file
+editor = FileEditor('example.svg')
+editor.set_element_text("//svg:text[@id='title']", "New Title")
+editor.save('modified.svg')
+
+# Extract Data URI
+result = editor.extract_data_uri("//svg:image/@xlink:href")
+if 'error' not in result:
+    print(f"Found {result['mime_type']} ({result['size']} bytes)")
+
+# Work with remote files
+remote_editor = FileEditor('https://example.com/diagram.svg')
+elements = remote_editor.list_elements("//svg:*[@id]")
+```
+
+## 📖 Documentation
+
+- **[CLI Reference](docs/cli.md)** - Complete command-line interface guide
+- **[Python API](docs/api.md)** - Full API documentation with examples  
+- **[Server Guide](docs/server.md)** - HTTP server setup and API reference
+- **[XPath Examples](docs/xpath.md)** - Common XPath patterns and use cases
+- **[Tutorials](docs/tutorials/)** - Step-by-step guides for common tasks
+
+## 🎯 Use Cases
+
+### 📊 **Extract Data from SVG Diagrams**
+```bash
+# Extract embedded PDF from technical diagram
+xsl extract "//svg:image/@xlink:href" --output manual.pdf
+
+# Get chart data from SVG
+xsl query "//svg:foreignObject//script[@type='application/json']"
+```
+
+### 🔧 **Batch Update XML Configurations**
+```bash
+# Update database connections across config files
+for config in configs/*.xml; do
+  xsl set "//database/host" "new-server.com" "$config"
+  xsl save "$config"
+done
+```
+
+### 🌐 **Parse Web Pages for Data**
+```bash
+# Extract structured data from HTML
+xsl query "//table[@id='data']//tr[@data-status='active']" page.html
+xsl extract "//script[@type='application/json']" --output data.json
+```
+
+### 🔄 **Document Format Conversion**
+```python
+# Convert XML structure using XPath
+from xsl import FileEditor
+
+source = FileEditor('legacy.xml')
+data = source.list_elements("//record")
+
+target = FileEditor('template.xml')
+for item in data:
+    target.add_element("//records", "entry", item['text'], item['attributes'])
+target.save('migrated.xml')
+```
+
+## 🔍 XPath Examples
+
+### SVG Files
+```bash
+# Get all text elements
+//svg:text
+
+# Find elements by ID
+//svg:*[@id='title']
+
+# Extract Data URIs
+//svg:image/@xlink:href[starts-with(., 'data:')]
+
+# Get metadata
+//svg:metadata
+```
+
+### XML Files  
+```bash
+# Find by attribute
+//user[@type='admin']
+
+# Text content search
+//*[contains(text(), 'error')]
+
+# Nested elements
+//config//database//host
+```
+
+### HTML Files
+```bash
+# CSS class targeting
+//div[@class='content']
+
+# Form elements
+//input[@type='checkbox'][@checked]
+
+# JSON script tags
+//script[@type='application/json']
+```
+
+## 🌐 HTTP Server API
+
+Start the server:
+```bash
+xsl server --port 8082
+```
+
+### Direct Data URI Extraction
+```bash
+# Extract from remote file
+curl "http://localhost:8082/api/extract?url=https://example.com/diagram.svg&xpath=//svg:image/@href"
+```
+
+### Full API Workflow
+```bash
+# Load file
+curl -X POST http://localhost:8082/api/load \
+  -H "Content-Type: application/json" \
+  -d '{"file_path": "example.svg"}'
+
+# Query elements  
+curl -X POST http://localhost:8082/api/query \
+  -H "Content-Type: application/json" \
+  -d '{"query": "//svg:text", "type": "xpath"}'
+
+# Update content
+curl -X POST http://localhost:8082/api/update \
+  -H "Content-Type: application/json" \
+  -d '{"xpath": "//svg:text[@id=\"title\"]", "type": "text", "value": "Updated"}'
+
+# Save changes
+curl -X POST http://localhost:8082/api/save \
+  -H "Content-Type: application/json" \
+  -d '{"output_path": "modified.svg"}'
+```
+
+### Web Interface
+
+Open `http://localhost:8082` in your browser for a full-featured web interface with:
+
+- 📁 **File Management** - Load local files or remote URLs
+- 🔍 **Interactive Queries** - Test XPath and CSS selectors with real-time results
+- ✏️ **Visual Editing** - Modify elements through web forms
+- 📦 **Data Extraction** - Extract and download embedded resources
+- 📊 **Element Browser** - Navigate document structure visually
+
+## 🧪 Examples and Testing
+
+Generate example files:
+```bash
+xsl examples --dir ./test_files
+```
+
+This creates:
+- `example.svg` - SVG with embedded Data URIs and metadata
+- `example.xml` - XML database with users and file data  
+- `example.html` - HTML with embedded SVG and JSON
+- `USAGE_EXAMPLES.md` - Comprehensive usage guide
+
+## ⚙️ Configuration
+
+### Optional Dependencies
+
+xsl works with basic XML support out of the box, but optional dependencies unlock additional features:
+
+- **`lxml`** - Required for XPath queries and advanced XML processing
+- **`beautifulsoup4`** - Enables CSS selectors for HTML files
+- **`requests`** - Allows loading files from remote URLs
+
+Install all features:
+```bash
+pip install xsl[full]
+```
+
+### Environment Variables
+
+```bash
+# Default server settings
+export xsl_DEFAULT_PORT=8082
+export xsl_DEFAULT_HOST=localhost
+
+# Debug mode
+export xsl_DEBUG=1
+```
+
+## 🔧 Development
+
+### Setup Development Environment
+
+```bash
+git clone https://github.com/veridock/xsl.git
+cd xsl
+
+# Install Poetry
+curl -sSL https://install.python-poetry.org | python3 -
+
+# Install dependencies
+poetry install --extras "full"
+
+# Run tests
+poetry run pytest
+
+# Format code
+poetry run black xsl/
+poetry run isort xsl/
+```
+
+### Running Tests
+
+```bash
+# All tests
+poetry run pytest
+
+# With coverage
+poetry run pytest --cov=xsl --cov-report=html
+
+# Specific test categories
+poetry run pytest -m "not slow"  # Skip slow tests
+poetry run pytest -m "integration"  # Only integration tests
+```
+
+### Code Quality
+
+```bash
+# Format and lint
+poetry run black xsl/ tests/
+poetry run isort xsl/ tests/
+poetry run flake8 xsl/ tests/
+poetry run mypy xsl/
+```
+
+## 🤝 Contributing
+
+We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
+
+### Quick Contribution Workflow
+
+1. Fork the repository
+2. Create a feature branch: `git checkout -b feature/amazing-feature`
+3. Make your changes and add tests
+4. Run tests: `poetry run pytest`
+5. Format code: `poetry run black xsl/`
+6. Commit: `git commit -m 'Add amazing feature'`
+7. Push: `git push origin feature/amazing-feature`
+8. Open a Pull Request
+
+## 📋 Requirements
+
+- **Python 3.8+**
+- **Optional:** lxml, beautifulsoup4, requests (install with `[full]` extra)
+
+## 📄 License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## 🙏 Acknowledgments
+
+- Built with [lxml](https://lxml.de/) for robust XML processing
+- Uses [Beautiful Soup](https://www.crummy.com/software/BeautifulSoup/) for HTML parsing
+- Powered by [Poetry](https://python-poetry.org/) for dependency management
+
+## 📞 Support
+
+- 📖 **Documentation:** [GitHub Wiki](https://github.com/veridock/xsl/wiki)
+- 🐛 **Bug Reports:** [GitHub Issues](https://github.com/veridock/xsl/issues)
+- 💬 **Discussions:** [GitHub Discussions](https://github.com/veridock/xsl/discussions)
+- 📧 **Email:** contact@veridock.com
+
+---
+
+**Made with ❤️ by the xsl team**

xsl-0.1.9.dist-info/RECORD

@@ -0,0 +1,11 @@
+xsl/__init__.py,sha256=XuRP23XWqzoLKiFYT7CMgw1uaw-_oytJtUkuTWFoNfU,364
+xsl/__main__.py,sha256=iH6k3Hxx17Vu36T_hMzgNKofE_HMkeDgSIGPOpLsuXg,279
+xsl/cli.py,sha256=XbBi3kJYPPggMGQ450pkdHZPn3biebBk6S37jWHAcbI,18046
+xsl/editor.py,sha256=yNY3yfOqDqAweOJ0MeW4ffV5q7l_Tij7qYeetgHCWs4,16954
+xsl/server.py,sha256=KFtHt86dD-v4gUAUpH1Ybd7bwrnVJ2GJkQs6G7ReboI,5462
+xsl/utils.py,sha256=5idokDuD-4tTkG7-Q2oc3my7jbLGTVzV7xizXGf4QZc,3546
+xsl-0.1.9.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+xsl-0.1.9.dist-info/METADATA,sha256=WFBO0xss5Tfwo3XDfrUAHpw1RyopQWXwAck71VhysXk,10331
+xsl-0.1.9.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+xsl-0.1.9.dist-info/entry_points.txt,sha256=Y83cfbwCADO-vxI6_fJ4pmonCXlrC39nPYCjJw0N1pc,63
+xsl-0.1.9.dist-info/RECORD,,