Function decode

toon/decoder.py:70–152

Decode TOON format string to Python data structure. Args: toon_string: TOON formatted string options: Decoding options - strict: bool (default True) - validate structure - expand_paths: 'off' (default) or 'safe' - default_delimiter: '

(toon_string: str, options: Optional[Dict[str, Any]] = None)

def decode(toon_string: str, options: Optional[Dict[str, Any]] = None) -> Any:
    """
    Decode TOON format string to Python data structure.
    
    Args:
        toon_string: TOON formatted string
        options: Decoding options
            - strict: bool (default True) - validate structure
            - expand_paths: 'off' (default) or 'safe'
            - default_delimiter: ',' (default)
            
    Returns:
        Python object (dict or list)
        
    Example:
        >>> toon = '''users[1]{id,name}:
        ...   1,Alice'''
        >>> decode(toon)
        {'users': [{'id': 1, 'name': 'Alice'}]}
    """
    if options is None:
        options = {}

    # Auto-detect indent size unless explicitly provided
    indent_size = options.get('indent')
    if indent_size is None:
        indent_size = detect_indent(toon_string)

    opts = DecoderOptions(
        strict=options.get('strict', DEFAULT_STRICT),
        expand_paths=options.get('expand_paths', EXPAND_PATHS_OFF),
        default_delimiter=options.get('default_delimiter', DEFAULT_DELIMITER)
    )

    lines = toon_string.split(NEWLINE)

    # Handle special case of top-level inline values
    stripped = toon_string.strip()

    # Check if it's an empty object
    if stripped == '{}':
        return {}

    # Check if first line is a root-level array header (tabular or list)
    if lines and lines[0].strip():
        first_line = lines[0].strip()
        # Pattern: [N]{fields}: or [N\t]{fields}: or [N|]{fields}: or [N]:
        array_match = re.match(r'^\[(\d+)([\t|])?\](?:\{([^}]+)\})?' + COLON + r'\s*$', first_line)
        if array_match:
            count = int(array_match.group(1))
            delimiter_indicator = array_match.group(2)
            fields_str = array_match.group(3)

            # Determine delimiter from indicator if present
            if delimiter_indicator == '\t':
                detected_delimiter = TAB
            elif delimiter_indicator == '|':
                detected_delimiter = PIPE