llm/SIA
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Better response parsing

Browse Source
This commit is contained in:
geens
2024-11-13 11:44:58 +01:00
parent aad9564e81
commit 50f05b6213
1 changed files with 16 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
sia/response_parser.py
View File

@@ -36,46 +36,6 @@ class ResponseParser:
io_buffer: Buffer to use for IO operations io_buffer: Buffer to use for IO operations
""" """
self.io_buffer = io_buffer 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]: def parse(self, xml: str) -> Union[Command, Entry]:
""" """
@@ -91,61 +51,49 @@ class ResponseParser:
entry_id = str(uuid.uuid4()) entry_id = str(uuid.uuid4())
timestamp = datetime.now() timestamp = datetime.now()
# First try to parse the XML
try: try:
root = ET.fromstring(xml.strip()) root = ET.fromstring(xml.strip())
except ET.ParseError as e: except ET.ParseError as e:
return ParseErrorEntry(xml, f"Invalid XML: {str(e)}", entry_id, timestamp) 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: try:
if root.tag == 'delete': if root.tag == 'delete':
# Extract target ID and create delete command
target_id = root.get('id') target_id = root.get('id')
if not target_id: if not target_id:
return ParseErrorEntry(xml, "Delete command missing required 'id' attribute", entry_id, timestamp) return ParseErrorEntry(xml, "Delete command missing required 'id' attribute", entry_id, timestamp)
return DeleteCommand(target_id) return DeleteCommand(target_id)
elif root.tag == 'stop': elif root.tag == 'stop':
# Create stop command
return StopCommand() return StopCommand()
elif root.tag == 'background': elif root.tag == 'background':
# Create background script entry if len(root) != 0 or root.attrib or root.text is None or root.text.strip() == '':
if not content: return ParseErrorEntry(xml, "Background entry requires (only) script content", entry_id, timestamp)
return ParseErrorEntry(xml, "Background entry missing script content", entry_id, timestamp) return ParseErrorEntry(xml, "Background entry requires script content", entry_id, timestamp)
return BackgroundEntry(content, entry_id, timestamp) return BackgroundEntry(root.text, entry_id, timestamp)
elif root.tag == 'repeat': elif root.tag == 'repeat':
# Create repeat script entry if len(root) != 0 or root.attrib or root.text is None or root.text.strip() == '':
if not content: return ParseErrorEntry(xml, "Repeat entry requires (only) script content", entry_id, timestamp)
return ParseErrorEntry(xml, "Repeat entry missing script content", entry_id, timestamp) return RepeatEntry(root.text, entry_id, timestamp)
return RepeatEntry(content, entry_id, timestamp)
elif root.tag == 'single': elif root.tag == 'single':
# Create single shot script entry if len(root) != 0 or root.attrib or root.text is None or root.text.strip() == '':
if not content: return ParseErrorEntry(xml, "Single entry requires (only) script content", entry_id, timestamp)
return ParseErrorEntry(xml, "Single shot entry missing script content", entry_id, timestamp) return SingleEntry(root.text, entry_id, timestamp)
return SingleEntry(content, entry_id, timestamp)
elif root.tag == 'reasoning': elif root.tag == 'reasoning':
# Create reasoning entry if len(root) != 0 or root.attrib or root.text is None or root.text.strip() == '':
if not content: return ParseErrorEntry(xml, "Reasoning entry requires (only) text content", entry_id, timestamp)
return ParseErrorEntry(xml, "Reasoning entry missing content", entry_id, timestamp) return ReasoningEntry(root.text, entry_id, timestamp)
return ReasoningEntry(content, entry_id, timestamp)
elif root.tag == 'read_stdin': elif root.tag == 'read_stdin':
# Create read entry - no content required
return ReadEntry(self.io_buffer, entry_id, timestamp) return ReadEntry(self.io_buffer, entry_id, timestamp)
elif root.tag == 'write_stdout': elif root.tag == 'write_stdout':
# Create write entry if len(root) != 0 or root.attrib or root.text is None or root.text.strip() == '':
if not content: return ParseErrorEntry(xml, "Write stdout entry requires (only) text content", entry_id, timestamp)
return ParseErrorEntry(xml, "Write entry missing content", entry_id, timestamp) return WriteEntry(root.text, self.io_buffer, entry_id, timestamp)
return WriteEntry(content, self.io_buffer, entry_id, timestamp)
else: else:
return ParseErrorEntry(xml, f"Unknown root element: {root.tag}", entry_id, timestamp) return ParseErrorEntry(xml, f"Unknown root element: {root.tag}", entry_id, timestamp)