Script to Parse GEMPAK GDLIST Output

parser.py

import numpy as np


def parse(lines, mask=-9999.):
    '''
    A simple routine to parse the output of GEMPAK's GDLIST output.

    Parameters
    ----------
    lines : string, sequence
        The output from GDLIST. If a string, will parse on the '\n' character.
        If a list, will assume the file has already been split.
    mask : scalar
        The value of the mask. If no mask, use None or False.

    Returns
    -------
    An 2D numpy array

    '''
    begin = False
    lonsize = None; latsize = None
    vals = []
    if isinstance(lines, str):
        lines = lines.split('\n')
    for line in lines:
        if not lonsize:
            if 'GRID SIZE' not in line: continue
            parts = line.split()
            parts = [p.strip() for p in parts]
            lonsize = int(parts[-2])
            latsize = int(parts[-1])
        if 'ROW'+str(latsize) in line or (begin and 'ROW' in line):
            begin = True
            val_tmp = line.split('ROW')[1].split()[1:]
        elif begin:
            val_tmp = line.split()
        else:
            continue
        for val in val_tmp:
            vals.append(float(val))
    vals = np.array(vals)
    if mask:
        vals = np.ma.masked_where(vals == mask, vals)
    vals = vals.reshape(latsize, -1)
    return vals