process_dna.py

#!/usr/bin/env python2

"""
Reads a Genbank file line by line.

"""

import re
from pprint import pprint


OPT_COMP = (1 << 0)
OPT_JOIN = (1 << 1)


def extract_cds_ranges(fd):
    buf = ''
    ranges = []

    for line in fd:
        if 'CDS' in line[:21]:
            buf += line[21:].strip()
        elif buf:
            line = line.strip()
            if not line.startswith('/'):
                buf += line
            else:
                # Get options
                options = 0
                if 'complement' in buf:
                    options |= OPT_COMP
                if 'join' in buf:
                    options |= OPT_JOIN

                # Remove everything but the ranges
                if '(' in buf:
                    o = buf.rfind('(')
                    c = buf.find(')')
                    buf = buf[o+1:c]

                # Parse ranges
                if options & OPT_JOIN:
                    tmp = []
                    for raw_range in buf.split(','):
                        s, e = raw_range.split('..')
                        tmp.append((int(s), int(e)))
                    buf = tuple(tmp)
                else:
                    s, e = buf.split('..')
                    buf = ((int(s), int(e)),)

                ranges.append((options, buf))
                buf = ''

        # The ORIGIN data is not going to be processed in this function
        if line.startswith('ORIGIN'):
            break

    return tuple(ranges)


if __name__ == '__main__':
    with open('Plasmodium falciparum 3D7 chromosome 5 (genbank).txt', 'r') as fd:
        ranges = extract_cds_ranges(fd)

        pprint(ranges)