fastq_parser.py

def read_fastq(file_fq):
    """
    takes a fastq file as input
    yields idSeq, sequence and score
    for each fastq entry
    learned from:
    http://codereview.stackexchange.com/questions/32897/efficient-parsing-of-fastq
    """

    line_count = 0

    while True:

        line = file_fq.readline()
        line_count += 1
        #break if we hit the end of the file
        if not line:
            break

        if line_count == 1:
            idSeq = line.strip().lstrip('@')

        elif line_count == 2:
            sequence = line.strip()

        elif line_count == 4:
            score = line.strip()
            line_count = 0
            yield idSeq,sequence, score

    yield idSeq, sequence, score