Function _parse_lines

toon/decoder.py:155–244

Parse lines starting from start_idx with given base indentation. Args: lines: Lines to parse start_idx: Starting line index base_indent: Base indentation level opts: Decoder options indent_size: Size of one indentation level (default 2) Returns:

(lines: List[str], start_idx: int, base_indent: int, opts: DecoderOptions, indent_size: int = 2)

def _parse_lines(lines: List[str], start_idx: int, base_indent: int, opts: DecoderOptions, indent_size: int = 2) -> Tuple[Any, int]:
    """
    Parse lines starting from start_idx with given base indentation.

    Args:
        lines: Lines to parse
        start_idx: Starting line index
        base_indent: Base indentation level
        opts: Decoder options
        indent_size: Size of one indentation level (default 2)

    Returns:
        (parsed_value, next_line_index)
    """
    if start_idx >= len(lines):
        return {}, start_idx
    
    result = {}
    i = start_idx
    
    while i < len(lines):
        line = lines[i]
        
        # Skip empty lines
        if not line.strip():
            i += 1
            continue
        
        # Calculate indentation
        indent = len(line) - len(line.lstrip())
        
        # If indentation is less than base, we're done with this block
        if indent < base_indent:
            break
        
        # If indentation is greater than expected, skip (part of previous value)
        if indent > base_indent:
            i += 1
            continue
        
        # Parse the line
        stripped = line.strip()

        # Check for array header: name[N]{fields}: or name[N\t]{fields}: or name[N|]{fields}:
        # Capture optional delimiter indicator after length
        array_match = re.match(r'^([^:\[\]]+)\[(\d+)([\t|])?\](?:\{([^}]+)\})?' + COLON + r'\s*$', stripped)
        if array_match:
            key = array_match.group(1)
            count = int(array_match.group(2))
            delimiter_indicator = array_match.group(3)
            fields_str = array_match.group(4)

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