Comment puis-je analyser efficacement les lignes de fichiers de largeur fixe en Python ?

<code class="python">import struct

fieldwidths = (2, -10, 24)
fmtstring = ' '.join('{}{}'.format(abs(fw), 'x' if fw < 0 else 's') for fw in fieldwidths)

# Convert Unicode input to bytes and decode result.
unpack = struct.Struct(fmtstring).unpack_from  # Alias.
parse = lambda line: tuple(s.decode() for s in unpack(line.encode()))

# Parse a sample line.
line = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789\n'
fields = parse(line)
print('fields:', fields)</code>

<code class="python">from itertools import zip_longest
from itertools import accumulate

def make_parser(fieldwidths):
    # Calculate slice boundaries.
    cuts = tuple(cut for cut in accumulate(abs(fw) for fw in fieldwidths))
    # Create field slice tuples.
    flds = tuple(zip_longest(cuts, (0,)+cuts))[:-1]  # Ignore final value.
    # Construct the parsing function.
    parse = lambda line: tuple(line[i:j] for i, j in flds)
    parse.size = sum(abs(fw) for fw in fieldwidths)
    parse.fmtstring = ' '.join('{}{}'.format(abs(fw), 'x' if fw < 0 else 's')
                                            for fw in fieldwidths)
    return parse

# Parse a sample line.
line = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789\n'
fieldwidths = (2, -10, 24)  # Negative values indicate ignored padding fields.
parse = make_parser(fieldwidths)
fields = parse(line)
print('fmtstring:', parse.fmtstring, ', record size:', parse.size, 'chars')
print('fields:', fields)</code>