def from_file()

in esm/data.py [0:0]

• 28 lines of code
• 5 McCabe index (conditional complexity)

    def from_file(cls, fasta_file):
        sequence_labels, sequence_strs = [], []
        cur_seq_label = None
        buf = []

        def _flush_current_seq():
            nonlocal cur_seq_label, buf
            if cur_seq_label is None:
                return
            sequence_labels.append(cur_seq_label)
            sequence_strs.append("".join(buf))
            cur_seq_label = None
            buf = []

        with open(fasta_file, "r") as infile:
            for line_idx, line in enumerate(infile):
                if line.startswith(">"):  # label line
                    _flush_current_seq()
                    line = line[1:].strip()
                    if len(line) > 0:
                        cur_seq_label = line
                    else:
                        cur_seq_label = f"seqnum{line_idx:09d}"
                else:  # sequence line
                    buf.append(line.strip())

        _flush_current_seq()

        assert len(set(sequence_labels)) == len(
            sequence_labels
        ), "Found duplicate sequence labels"

        return cls(sequence_labels, sequence_strs)