INNER CODE UNIT · Python

read_fasta

linsalrob/ComputationalGenomicsManual · Python/countfasta.py:16

def read_fasta(fname: str, whole_id: bool = False, qual: bool = False) -> dict:
    """
    Read a fasta file and return a hash.

    If wholeId is set to false only the first part of the ID
    (upto the first white space) is returned

    :param fname: The file name to read
    :param whole_id: Whether to keep the whole id, or trim to first whitespace (default = all)
    :param qual: these are quality scores (so add a space between lines!)
    :return: dict
    """

    try:
        if fname.endswith('.gz'):
            f = gzip.open(fname, 'rt')
        elif fname.endswith('.lrz'):
            f = subprocess.Popen(['/usr/bin/lrunzip', '-q', '-d', '-f', '-o-', fname], stdout=subprocess.PIPE).stdout

View source record →