154 lines
5.6 KiB
Python
154 lines
5.6 KiB
Python
from datetime import datetime
|
|
import uuid
|
|
import xml.etree.ElementTree as ET
|
|
from typing import Union
|
|
|
|
from .command import Command
|
|
from .delete_command import DeleteCommand
|
|
from .stop_command import StopCommand
|
|
|
|
from .entry import Entry
|
|
from .background_entry import BackgroundEntry
|
|
from .parse_error_entry import ParseErrorEntry
|
|
from .read_entry import ReadEntry
|
|
from .reasoning_entry import ReasoningEntry
|
|
from .repeat_entry import RepeatEntry
|
|
from .single_shot_entry import SingleShotEntry
|
|
from .write_entry import WriteEntry
|
|
|
|
class ResponseParser:
|
|
"""
|
|
Parses XML responses from the LLM into commands or entries.
|
|
|
|
The parser validates the XML structure and converts it into the appropriate
|
|
Command or Entry object based on the root element tag. Invalid input results
|
|
in ParseErrorEntry objects rather than raising exceptions.
|
|
|
|
Attributes:
|
|
io_buffer: Buffer to use for IO operations
|
|
"""
|
|
|
|
def __init__(self, io_buffer):
|
|
"""
|
|
Initialize parser with IO buffer.
|
|
|
|
Args:
|
|
io_buffer: Buffer to use for IO operations
|
|
"""
|
|
self.io_buffer = io_buffer
|
|
|
|
def _extract_content(self, xml: str, root: ET.Element) -> str:
|
|
"""
|
|
Extract content from XML, handling CDATA sections and preserving special characters.
|
|
|
|
Args:
|
|
xml: Original XML string
|
|
root: Parsed XML element
|
|
|
|
Returns:
|
|
str: Extracted content with proper handling of CDATA and special characters
|
|
"""
|
|
if root.text is None:
|
|
return ""
|
|
|
|
# Find opening tag end
|
|
tag_name = root.tag
|
|
tag_start = xml.find('<' + tag_name)
|
|
tag_end = xml.find('>', tag_start)
|
|
if tag_end == -1:
|
|
return ""
|
|
|
|
# Check for self-closing tag
|
|
if xml[tag_end-1] == '/':
|
|
return ""
|
|
|
|
# Find closing tag start
|
|
close_tag = '</' + tag_name + '>'
|
|
close_start = xml.rfind(close_tag)
|
|
if close_start == -1:
|
|
return ""
|
|
|
|
# Extract content
|
|
content = xml[tag_end+1:close_start]
|
|
|
|
# Handle CDATA sections
|
|
if content.startswith('<![CDATA[') and content.endswith(']]>'):
|
|
content = content[9:-3] # Remove CDATA markers
|
|
|
|
return content
|
|
|
|
def parse(self, xml: str) -> Union[Command, Entry]:
|
|
"""
|
|
Parse XML response into a Command or Entry.
|
|
|
|
Args:
|
|
xml: XML string to parse
|
|
|
|
Returns:
|
|
Command or Entry based on the XML content
|
|
ParseErrorEntry for any parsing or validation errors
|
|
"""
|
|
entry_id = str(uuid.uuid4())
|
|
timestamp = datetime.now()
|
|
|
|
# First try to parse the XML
|
|
try:
|
|
root = ET.fromstring(xml.strip())
|
|
except ET.ParseError as e:
|
|
return ParseErrorEntry(xml, f"Invalid XML: {str(e)}", entry_id, timestamp)
|
|
|
|
# Extract content preserving special characters and handling CDATA
|
|
content = self._extract_content(xml, root)
|
|
|
|
# Convert to appropriate type based on root tag
|
|
try:
|
|
if root.tag == 'delete':
|
|
# Extract target ID and create delete command
|
|
target_id = root.get('id')
|
|
if not target_id:
|
|
return ParseErrorEntry(xml, "Delete command missing required 'id' attribute", entry_id, timestamp)
|
|
return DeleteCommand(target_id)
|
|
|
|
elif root.tag == 'stop':
|
|
# Create stop command
|
|
return StopCommand()
|
|
|
|
elif root.tag == 'background':
|
|
# Create background script entry
|
|
if not content:
|
|
return ParseErrorEntry(xml, "Background entry missing script content", entry_id, timestamp)
|
|
return BackgroundEntry(content, entry_id, timestamp)
|
|
|
|
elif root.tag == 'repeat':
|
|
# Create repeat script entry
|
|
if not content:
|
|
return ParseErrorEntry(xml, "Repeat entry missing script content", entry_id, timestamp)
|
|
return RepeatEntry(content, entry_id, timestamp)
|
|
|
|
elif root.tag == 'single_shot':
|
|
# Create single shot script entry
|
|
if not content:
|
|
return ParseErrorEntry(xml, "Single shot entry missing script content", entry_id, timestamp)
|
|
return SingleShotEntry(content, entry_id, timestamp)
|
|
|
|
elif root.tag == 'reasoning':
|
|
# Create reasoning entry
|
|
if not content:
|
|
return ParseErrorEntry(xml, "Reasoning entry missing content", entry_id, timestamp)
|
|
return ReasoningEntry(content, entry_id, timestamp)
|
|
|
|
elif root.tag == 'read_stdin':
|
|
# Create read entry - no content required
|
|
return ReadEntry(self.io_buffer, entry_id, timestamp)
|
|
|
|
elif root.tag == 'write_stdout':
|
|
# Create write entry
|
|
if not content:
|
|
return ParseErrorEntry(xml, "Write entry missing content", entry_id, timestamp)
|
|
return WriteEntry(content, self.io_buffer, entry_id, timestamp)
|
|
|
|
else:
|
|
return ParseErrorEntry(xml, f"Unknown root element: {root.tag}", entry_id, timestamp)
|
|
|
|
except Exception as e:
|
|
return ParseErrorEntry(xml, f"Error parsing response: {str(e)}", entry_id, timestamp) |