Files
markitect-main/markitect/query_paradigms/paradigms/xpath_paradigm.py
tegwick 5143864a86 feat: implement comprehensive query paradigm zoo system (issue #62)
- Created extensible BaseQueryParadigm interface with standardized QueryResult format
- Implemented QueryParadigmRegistry for paradigm discovery and management
- Added 5 working paradigms: SQL, FTS, GraphQL, JSONPath, Natural Language
- Documented 9 additional paradigms: QBE, Batch Manipulation, Visual Query Builder, REST API, NoSQL, UNIX Pipeline, XPath/XQuery, RAG, Data Transformation
- Integrated full CLI interface: list, search, show, exec, categories commands
- Added comprehensive test suite with 23 test cases covering all components
- Auto-registration system enables easy addition of new paradigms
- Organized paradigms by category (structural, textual, semantic, visual, procedural, network) and complexity (beginner, intermediate, advanced)

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-03 23:06:57 +02:00

115 lines
3.6 KiB
Python

"""
XPath/XQuery Paradigm - Path-based data extraction.
"""
import time
from typing import Dict, Any, List, Optional
from ..base import BaseQueryParadigm, QueryResult
class XPathParadigm(BaseQueryParadigm):
"""XPath/XQuery paradigm for path-based data extraction."""
@property
def name(self) -> str:
return "XPath/XQuery"
@property
def description(self) -> str:
return "Path-based data extraction from structured documents using XPath and XQuery syntax"
@property
def category(self) -> str:
return "structural"
@property
def complexity(self) -> str:
return "advanced"
def execute(self, query: str, config: Dict[str, Any] = None) -> QueryResult:
"""Execute XPath query (not yet implemented)."""
start_time = time.time()
execution_time = (time.time() - start_time) * 1000
return QueryResult(
paradigm=self.name,
query=query,
execution_time_ms=execution_time,
result_count=0,
results=[],
metadata={
"status": "not_implemented",
"implementation_issue": "TBD - to be created",
"description": "XPath enables precise navigation through document structures"
},
success=False,
error_message="XPath/XQuery paradigm not yet implemented."
)
def get_examples(self) -> List[Dict[str, str]]:
"""Get example XPath queries."""
return [
{
"name": "Select files by attribute",
"description": "Find all files with specific author",
"query": "//file[@author='Alice']"
},
{
"name": "Deep path selection",
"description": "Select nested content elements",
"query": "//file/content/section[contains(@title, 'Introduction')]"
},
{
"name": "Conditional selection",
"description": "Select files with multiple conditions",
"query": "//file[@type='markdown' and @size > 1000]/tags/tag"
},
{
"name": "Position-based selection",
"description": "Select first 3 files by creation date",
"query": "//file[position() <= 3 and @created > '2024-01-01']"
}
]
def validate_query(self, query: str) -> tuple[bool, Optional[str]]:
"""Validate XPath query syntax."""
if not query.strip():
return False, "XPath query cannot be empty"
if not (query.startswith('//') or query.startswith('/')):
return False, "XPath query must start with / or //"
return True, None
def get_syntax_help(self) -> str:
"""Get syntax help for XPath queries."""
return """XPath/XQuery Syntax:
Basic Path Selection:
//element - Select all elements anywhere
/root/element - Select from root
element[@attribute='value'] - Select by attribute
Predicates:
//file[@author='Alice'] - Attribute equals
//file[position() <= 3] - Position-based
//file[contains(@tags, 'tutorial')] - Text contains
Functions:
position() - Element position
contains(string, substring) - Text contains
count(elements) - Count elements
text() - Get text content
Document Structure (conceptual):
//file - All files
//file/@author - All author attributes
//file/tags/tag - All tags in files
//file[content/section] - Files with sections
Examples:
//file[@type='markdown']
//file/tags/tag[text()='documentation']
//file[@created > '2024-01-01' and @author='Alice']
"""