Method decompress

data_compression/lz77.py:111–142

Convert the list of tokens into an output string. Args: tokens: list containing triplets (offset, length, char) Returns: output: decompressed text Tests: >>> lz77_compressor = LZ77Compressor() >>> lz77_compressor.dec

(self, tokens: list[Token])

        return output

    def decompress(self, tokens: list[Token]) -> str:
        """
        Convert the list of tokens into an output string.

        Args:
            tokens: list containing triplets (offset, length, char)

        Returns:
            output: decompressed text

        Tests:
            >>> lz77_compressor = LZ77Compressor()
            >>> lz77_compressor.decompress([Token(0, 0, 'c'), Token(0, 0, 'a'),
            ... Token(0, 0, 'b'), Token(0, 0, 'r'), Token(3, 1, 'c'),
            ... Token(2, 1, 'd'), Token(7, 4, 'r'), Token(3, 5, 'd')])
            'cabracadabrarrarrad'
            >>> lz77_compressor.decompress([Token(0, 0, 'a'), Token(0, 0, 'b'),
            ... Token(2, 2, 'c'), Token(4, 3, 'a'), Token(2, 2, 'a')])
            'ababcbababaa'
            >>> lz77_compressor.decompress([Token(0, 0, 'a'), Token(1, 1, 'c'),
            ... Token(3, 4, 'b'), Token(3, 3, 'a'), Token(1, 2, 'c')])
            'aacaacabcabaaac'
        """

        output = ""

        for token in tokens:
            for _ in range(token.length):
                output += output[-token.offset]
            output += token.indicator

        return output

    def _find_encoding_token(self, text: str, search_buffer: str) -> Token:
        """Finds the encoding token for the first character in the text.