def __init__()

in chunking/chunkers/spreadsheet_chunker.py [0:0]

• 16 lines of code
• 4 McCabe index (conditional complexity)

    def __init__(self, data, max_chunk_size=None, chunking_by_row=None, include_header_in_chunks=None):
        """
        Initializes the SpreadsheetChunker with the provided data and environment configurations.
        
        Args:
            data (str): The spreadsheet content to be chunked.
            max_chunk_size (int, optional): Maximum allowed size of each chunk in tokens. Defaults to an environment variable 'SPREADSHEET_NUM_TOKENS' or 0 if not set.
            chunking_by_row (bool, optional): Whether to chunk by row instead of by sheet. Defaults to an environment variable 'CHUNKING_BY_ROW' or False.
            include_header_in_chunks (bool, optional): Whether to include the header row in each chunk if chunking by row. Defaults to 'INCLUDE_HEADER_IN_CHUNKS' environment variable or False.
        """
        super().__init__(data)
        
        if max_chunk_size is None:
            self.max_chunk_size = int(os.getenv("SPREADSHEET_NUM_TOKENS", 0))
        else:
            self.max_chunk_size = int(max_chunk_size)
        
        if chunking_by_row is None:
            chunking_env = os.getenv("SPREADSHEET_CHUNKING_BY_ROW", "false").lower()
            self.chunking_by_row = chunking_env in ["true", "1", "yes"]
        else:
            self.chunking_by_row = bool(chunking_by_row)
        
        if include_header_in_chunks is None:
            include_header_env = os.getenv("SPREADSHEET_CHUNKING_BY_ROW_INCLUDE_HEADER", "false").lower()
            self.include_header_in_chunks = include_header_env in ["true", "1", "yes"]
        else:
            self.include_header_in_chunks = bool(include_header_in_chunks)