xsl 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

xsl/editor.py

@@ -1,5 +1,491 @@
-# Core FileEditor class
 """
-editor.py
+Core FileEditor class for xsl package.
+Provides functionality for editing XML/HTML/SVG files with XPath and CSS selectors.
 """
 
+import os
+import re
+import base64
+import logging
+import shutil
+from typing import Any, Dict, Optional, Union, List
+from pathlib import Path
+import xml.etree.ElementTree as ET
+
+from .utils import is_data_uri, parse_data_uri
+
+try:
+    from lxml import etree, html
+    LXML_AVAILABLE = True
+except ImportError:
+    LXML_AVAILABLE = False
+    print("Warning: lxml not available. Installing: pip install lxml")
+
+try:
+    from bs4 import BeautifulSoup
+    BS4_AVAILABLE = True
+except ImportError:
+    BS4_AVAILABLE = False
+    print("Warning: BeautifulSoup4 not available. Installing: pip install beautifulsoup4")
+
+try:
+    import requests
+    REQUESTS_AVAILABLE = True
+except ImportError:
+    REQUESTS_AVAILABLE = False
+    print("Warning: requests not available. Installing: pip install requests")
+
+
+class FileEditor:
+    """Main class for XML/HTML/SVG file editing with XPath and CSS selector support."""
+
+    def __init__(self, file_path: str):
+        """Initialize FileEditor with a file path or URL.
+        
+        Args:
+            file_path: Path to file or URL
+            
+        Raises:
+            ValueError: If the file cannot be loaded or parsed
+        """
+        self.file_path = file_path
+        self.tree = None
+        self.original_content = None
+        # Default namespaces for common XML formats
+        self.ns = {
+            'svg': 'http://www.w3.org/2000/svg',
+            'xlink': 'http://www.w3.org/1999/xlink',
+            'html': 'http://www.w3.org/1999/xhtml',
+            'xhtml': 'http://www.w3.org/1999/xhtml'
+        }
+        self._load_file()
+    
+    @property
+    def is_remote(self) -> bool:
+        """Check if the file is a remote URL.
+        
+        Returns:
+            bool: True if file_path is a URL, False otherwise
+        """
+        return (isinstance(self.file_path, str) and 
+                (self.file_path.startswith('http://') or 
+                 self.file_path.startswith('https://') or
+                 self.file_path.startswith('ftp://')))
+
+    def _load_file(self):
+        """Load file content from path or URL."""
+        if not self.file_path:
+            raise ValueError("No file path provided")
+            
+        if self.is_remote:
+            import requests
+            try:
+                response = requests.get(self.file_path)
+                response.raise_for_status()
+                content = response.content
+            except Exception as e:
+                raise IOError(f"Failed to fetch remote file: {str(e)}")
+        else:
+            with open(self.file_path, 'rb') as f:
+                content = f.read()
+        
+        self.original_content = content.decode('utf-8')
+        self._parse_content(content)
+
+    def _parse_content(self, content: bytes):
+        """Parse file content with appropriate parser.
+        
+        Args:
+            content: The raw bytes content to parse
+            
+        Raises:
+            ValueError: If the content cannot be parsed
+        """
+        if LXML_AVAILABLE:
+            try:
+                self.tree = etree.fromstring(content)
+                # Update namespaces from the document
+                if hasattr(self.tree, 'nsmap'):
+                    for prefix, uri in self.tree.nsmap.items():
+                        if prefix is not None:  # Skip default namespace
+                            self.ns[prefix] = uri
+                return
+            except etree.XMLSyntaxError as e:
+                logging.warning(f"Failed to parse with lxml: {e}")
+                # Continue to standard library fallback
+        
+        # Fallback to standard library
+        try:
+            self.tree = ET.fromstring(content)
+        except ET.ParseError as e:
+            raise ValueError(f"Cannot parse file: {str(e)}")
+
+    def query(self, xpath: str) -> List[Any]:
+        """Query elements using XPath.
+        
+        Args:
+            xpath: XPath expression (can include namespaces)
+            
+        Returns:
+            List of matching elements
+            
+        Raises:
+            ValueError: If no file is loaded or XPath is invalid
+        """
+        if self.tree is None:
+            raise ValueError("No file loaded")
+            
+        try:
+            if LXML_AVAILABLE:
+                # Register namespaces with lxml
+                return self.tree.xpath(xpath, namespaces=self.ns)
+            else:
+                # Basic XPath support with standard library
+                # Replace namespace prefixes in XPath for standard library
+                if ':' in xpath:
+                    # Simple namespace handling for standard library
+                    for prefix, uri in self.ns.items():
+                        xpath = xpath.replace(f"{prefix}:", f"{{'{uri}'}}")
+                return self.tree.findall(xpath)
+        except Exception as e:
+            raise ValueError(f"Invalid XPath expression '{xpath}': {str(e)}")
+
+    def set_value(self, xpath: str, value: str) -> bool:
+        """Set value of elements matching XPath.
+        
+        Args:
+            xpath: XPath expression
+            value: New value
+            
+        Returns:
+            True if successful
+        """
+        elements = self.query(xpath)
+        if not elements:
+            return False
+            
+        for elem in elements:
+            if hasattr(elem, 'text'):
+                elem.text = value
+        return True
+
+    def save(self, output_path: str = None, create_backup: bool = False) -> str:
+        """Save changes to file.
+        
+        Args:
+            output_path: Output file path (default: overwrite original)
+            create_backup: If True, create a backup before saving
+            
+        Returns:
+            Path to saved file
+            
+        Raises:
+            IOError: If file cannot be written
+        """
+        output_path = output_path or self.file_path
+        
+        if create_backup and os.path.exists(output_path):
+            backup_path = f"{output_path}.bak"
+            import shutil
+            shutil.copy2(output_path, backup_path)
+        
+        try:
+            if LXML_AVAILABLE:
+                etree.ElementTree(self.tree).write(
+                    output_path,
+                    encoding='utf-8',
+                    xml_declaration=True,
+                    pretty_print=True
+                )
+            else:
+                ET.ElementTree(self.tree).write(
+                    output_path,
+                    encoding='utf-8',
+                    xml_declaration=True
+                )
+            return output_path
+        except Exception as e:
+            raise IOError(f"Failed to save file {output_path}: {str(e)}")
+    
+    def find_by_xpath(self, xpath: str) -> list:
+        """Find elements by XPath.
+        
+        Args:
+            xpath: XPath expression
+            
+        Returns:
+            List of matching elements
+        """
+        return self.query(xpath)
+    
+    def get_element_text(self, xpath: str, default: str = "") -> str:
+        """Get text content of first element matching XPath.
+        
+        Args:
+            xpath: XPath expression
+            default: Default value if element not found
+            
+        Returns:
+            Text content of the element or default value
+        """
+        elements = self.query(xpath)
+        if elements and hasattr(elements[0], 'text'):
+            return elements[0].text or default
+        return default
+    
+    def detect_file_type(self) -> str:
+        """Detect the type of the loaded file.
+        
+        Returns:
+            str: File type ('svg', 'html', 'xml', or 'unknown')
+        """
+        if not self.tree:
+            return "unknown"
+            
+        # Check for SVG
+        if hasattr(self.tree, 'tag') and 'svg' in self.tree.tag:
+            return 'svg'
+            
+        # Check for HTML
+        if hasattr(self.tree, 'find'):
+            if self.tree.find('.//html') is not None:
+                return 'html'
+                
+        # Default to XML
+        return 'xml'
+    
+    def extract_data_uri(self, xpath: str) -> dict:
+        """Extract data URI from element's attribute.
+        
+        Args:
+            xpath: XPath to the element containing data URI
+            
+        Returns:
+            dict: Parsed data URI components with 'mime_type' and other metadata,
+                  or {'error': str} if not found
+        """
+        try:
+            elements = self.query(xpath)
+            if not elements:
+                return {'error': 'No elements found matching XPATH'}
+                
+            # Handle attribute XPath (e.g., @xlink:href)
+            attr = None
+            if xpath.endswith('/@xlink:href'):
+                element_xpath = xpath.rsplit('/', 1)[0]
+                attr = 'xlink:href'
+                elements = self.query(element_xpath)
+            elif xpath.endswith('/@href'):
+                element_xpath = xpath.rsplit('/', 1)[0]
+                attr = 'href'
+                elements = self.query(element_xpath)
+            
+            if not elements:
+                return {
+                    'error': 'No elements found matching XPath',
+                    'mime_type': 'text/plain',
+                    'data': ''
+                }
+                
+            # Try to find a data URI in the elements
+            for elem in elements:
+                # If we have a specific attribute, check that first
+                if attr:
+                    uri = self._get_attribute(elem, attr)
+                    if uri and is_data_uri(uri):
+                        try:
+                            result = parse_data_uri(uri)
+                            # For image data, ensure we keep the original mime type
+                            if 'image/' in result.get('mime_type', ''):
+                                result['base64_data'] = uri.split(',', 1)[1]  # Store base64 data
+                                result['data'] = result['base64_data']  # Keep for backward compatibility
+                                result['size'] = len(result['base64_data'])  # Add size field
+                            result['xpath'] = xpath
+                            return result
+                        except Exception as e:
+                            return {
+                                'error': f'Error parsing data URI: {str(e)}',
+                                'mime_type': 'text/plain',
+                                'data': ''
+                            }
+                
+                # Otherwise check common attributes
+                for attr_name in ['xlink:href', 'href', 'data', 'src']:
+                    uri = self._get_attribute(elem, attr_name)
+                    if uri and is_data_uri(uri):
+                        try:
+                            result = parse_data_uri(uri)
+                            # For image data, ensure we keep the original mime type
+                            if 'image/' in result.get('mime_type', ''):
+                                result['base64_data'] = uri.split(',', 1)[1]  # Store base64 data
+                                result['data'] = result['base64_data']  # Keep for backward compatibility
+                                result['size'] = len(result['base64_data'])  # Add size field
+                            result['xpath'] = xpath
+                            return result
+                        except Exception as e:
+                            return {
+                                'error': f'Error parsing data URI: {str(e)}',
+                                'mime_type': 'text/plain',
+                                'data': ''
+                            }
+            
+            return {
+                'error': 'No data URI found in element attributes',
+                'mime_type': 'text/plain',
+                'data': ''
+            }
+            
+        except Exception as e:
+            return {
+                'error': f'Error extracting data URI: {str(e)}',
+                'mime_type': 'text/plain',
+                'data': ''
+            }
+    
+    def _get_attribute(self, element, name: str) -> str:
+        """Get an attribute from an element, handling namespaces.
+        
+        Args:
+            element: The XML element
+            name: Attribute name (can include namespace prefix)
+            
+        Returns:
+            The attribute value or None if not found
+        """
+        if not hasattr(element, 'get'):
+            return None
+            
+        # Try direct attribute first
+        value = element.get(name)
+        if value is not None:
+            return value
+            
+        # Try with xlink: prefix
+        if name.startswith('xlink:'):
+            return element.get(f"{{{self.ns.get('xlink', '')}}}{name[6:]}")
+            
+        # Try with full namespace
+        if ':' in name:
+            prefix = name.split(':', 1)[0]
+            if prefix in self.ns:
+                return element.get(f"{{{self.ns[prefix]}}}{name.split(':', 1)[1]}")
+                
+        return None
+    
+    @property
+    def file_type(self) -> str:
+        """Get the type of the loaded file.
+        
+        Returns:
+            str: File type ('svg', 'html', 'xml', or 'unknown')
+        """
+        return self.detect_file_type()
+    
+    def get_element_attribute(self, xpath: str, attr_name: str, default: str = None) -> str:
+        """Get an attribute value from an element.
+        
+        Args:
+            xpath: XPath to the element
+            attr_name: Name of the attribute to get
+            default: Default value if attribute not found
+            
+        Returns:
+            The attribute value or default if not found
+        """
+        elements = self.query(xpath)
+        if not elements:
+            return default
+            
+        return self._get_attribute(elements[0], attr_name) or default
+    
+    def set_element_text(self, xpath: str, text: str) -> bool:
+        """Set the text content of an element.
+        
+        Args:
+            xpath: XPath to the element
+            text: New text content
+            
+        Returns:
+            bool: True if successful, False otherwise
+        """
+        elements = self.query(xpath)
+        if not elements:
+            return False
+            
+        for elem in elements:
+            if hasattr(elem, 'text'):
+                elem.text = text
+        return True
+        
+    def set_element_attribute(self, xpath: str, attr_name: str, attr_value: str) -> bool:
+        """Set an attribute on elements matching XPath.
+        
+        Args:
+            xpath: XPath to the element(s)
+            attr_name: Name of the attribute to set
+            attr_value: Value to set
+            
+        Returns:
+            bool: True if any elements were modified, False otherwise
+        """
+        elements = self.query(xpath)
+        if not elements:
+            return False
+            
+        modified = False
+        for elem in elements:
+            if hasattr(elem, 'set'):
+                # Handle namespaced attributes (e.g., xlink:href)
+                if ':' in attr_name:
+                    prefix = attr_name.split(':', 1)[0]
+                    if prefix in self.ns:
+                        ns_attr = f"{{{self.ns[prefix]}}}{attr_name.split(':', 1)[1]}"
+                        elem.set(ns_attr, attr_value)
+                        modified = True
+                else:
+                    elem.set(attr_name, attr_value)
+                    modified = True
+                    
+        return modified
+    
+    def list_elements(self, xpath: str) -> List[Dict[str, Any]]:
+        """List elements matching XPath with their attributes.
+        
+        Args:
+            xpath: XPath expression to find elements
+            
+        Returns:
+            List of dictionaries with element information
+        """
+        elements = self.query(xpath)
+        result = []
+        
+        for elem in elements:
+            if hasattr(elem, 'attrib'):
+                result.append({
+                    'tag': elem.tag,
+                    'text': getattr(elem, 'text', ''),
+                    'attributes': dict(elem.attrib)
+                })
+        
+        return result
+    
+    def backup(self) -> str:
+        """Create a backup of the current file.
+        
+        Returns:
+            str: Path to the backup file
+            
+        Raises:
+            IOError: If backup creation fails
+        """
+        if not self.file_path:
+            raise IOError("No file loaded to back up")
+            
+        backup_path = f"{self.file_path}.bak"
+        try:
+            import shutil
+            shutil.copy2(self.file_path, backup_path)
+            return backup_path
+        except Exception as e:
+            raise IOError(f"Failed to create backup: {str(e)}")

xsl/server.py

@@ -1,5 +1,167 @@
-# HTTP server
 """
-server.py
+HTTP Server for xsl - Web interface for remote file editing.
 """
 
+import argparse
+import json
+import sys
+from http.server import BaseHTTPRequestHandler, HTTPServer
+from typing import Dict
+from urllib.parse import parse_qs, urlparse
+
+from . import __version__
+from .editor import FileEditor
+
+
+class FileEditorServer(BaseHTTPRequestHandler):
+    """HTTP request handler for xsl server."""
+
+    # Class variable to store loaded editors
+    editors: Dict[str, FileEditor] = {}
+
+    def do_GET(self):
+        """Handle GET requests."""
+        parsed_url = urlparse(self.path)
+        path = parsed_url.path
+        query = parse_qs(parsed_url.query)
+
+        if path == "/":
+            self._serve_interface()
+        elif path == "/api/health":
+            self._send_json_response({"status": "ok", "version": __version__})
+        elif path == "/api/extract":
+            # Direct extraction endpoint with URL + XPath
+            self._extract_from_url(query)
+        else:
+            self._send_error(404, "Not Found")
+
+    def do_POST(self):
+        """Handle POST requests."""
+        content_length = int(self.headers["Content-Length"])
+        post_data = self.rfile.read(content_length).decode("utf-8")
+
+        try:
+            data = json.loads(post_data)
+        except json.JSONDecodeError:
+            self._send_error(400, "Invalid JSON")
+            return
+
+        parsed_url = urlparse(self.path)
+        path = parsed_url.path
+
+        if path == "/api/load":
+            self._load_file(data)
+        elif path == "/api/query":
+            self._query_elements(data)
+        elif path == "/api/update":
+            self._update_element(data)
+        elif path == "/api/save":
+            self._save_file(data)
+        elif path == "/api/extract_data_uri":
+            self._extract_data_uri(data)
+        elif path == "/api/add":
+            self._add_element(data)
+        elif path == "/api/remove":
+            self._remove_element(data)
+        elif path == "/api/info":
+            self._get_file_info(data)
+        else:
+            self._send_error(404, "Not Found")
+
+    def do_OPTIONS(self):
+        """Handle OPTIONS requests for CORS."""
+        self.send_response(200)
+        self.send_header("Access-Control-Allow-Origin", "*")
+        self.send_header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
+        self.send_header("Access-Control-Allow-Headers", "Content-Type")
+        self.end_headers()
+
+    def _send_response(self, status_code, content, content_type="text/plain"):
+        """Send HTTP response."""
+        self.send_response(status_code)
+        self.send_header("Content-type", content_type)
+        self.send_header("Access-Control-Allow-Origin", "*")
+        self.send_header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
+        self.send_header("Access-Control-Allow-Headers", "Content-Type")
+        self.end_headers()
+        self.wfile.write(
+            content.encode("utf-8") if isinstance(content, str) else content
+        )
+
+    def _send_json_response(self, data):
+        """Send JSON response."""
+        self._send_response(200, json.dumps(data, indent=2), "application/json")
+
+    def _send_error(self, status_code, message):
+        """Send error response."""
+        self._send_response(
+            status_code, json.dumps({"error": message}), "application/json"
+        )
+
+    def log_message(self, format, *args):
+        """Override to customize logging."""
+        print(f"{self.address_string()} - {format % args}")
+
+
+def start_server(host="localhost", port=8080):
+    """Start the xsl HTTP server."""
+    try:
+        server = HTTPServer((host, port), FileEditorServer)
+        print(f"🌐 xsl Server v{__version__} starting on {host}:{port}")
+        print(f"📖 Open http://{host}:{port} in your browser")
+        print("🔗 API endpoints:")
+        print(f"   GET  http://{host}:{port}/api/extract?url=<URL>&xpath=<XPATH>")
+        print(f"   POST http://{host}:{port}/api/load")
+        print(f"   POST http://{host}:{port}/api/query")
+        print(f"   POST http://{host}:{port}/api/update")
+        print(f"   POST http://{host}:{port}/api/save")
+        print("\n⏹️  Press Ctrl+C to stop the server")
+        print("-" * 60)
+
+        server.serve_forever()
+    except KeyboardInterrupt:
+        print("\n\n👋 Server stopped by user")
+    except Exception as e:
+        print(f"❌ Server error: {e}")
+        sys.exit(1)
+
+
+def main(args: list = None) -> int:
+    """Entry point for xsl-server command.
+    
+    Args:
+        args: Command line arguments (default: None, uses sys.argv[1:])
+        
+    Returns:
+        int: Exit code (0 for success, non-zero for error)
+    """
+    parser = argparse.ArgumentParser(description="Start xsl HTTP server")
+    parser.add_argument(
+        "--host",
+        default="localhost",
+        help="Host to bind to (default: localhost)",
+    )
+    parser.add_argument(
+        "--port",
+        type=int,
+        default=8082,
+        help="Port to listen on (default: 8082)",
+    )
+    args = parser.parse_args(args)
+
+    print(f"Starting xsl server on http://{args.host}:{args.port}")
+    print("Press Ctrl+C to stop")
+
+    try:
+        start_server(host=args.host, port=args.port)
+        return 0
+    except KeyboardInterrupt:
+        print("\nServer stopped")
+        return 0
+    except Exception as e:
+        print(f"Error: {e}", file=sys.stderr)
+        return 1
+
+
+if __name__ == "__main__":
+    main()