convert a wordperfect file to messy text

wpd2txt.py

#!/usr/bin/env python

import sys

"""
For each character c, if its value is:
    #13: treat as newline
    #128, #160: treat as space ' '
    #169..#171, #173, #174: treat as dash '-'
    #192..#236: skip ahead and ignore all characters until another occurrence
        of character c is found; resume at the following character
    #0..#31, #129..#159, #161..#168, #172, #175..#255: ignore (control characters)
    else treat as regular text character

from http://fileformats.archiveteam.org/wiki/WordPerfect
"""

def wpd2txt(filename):
    text = ''
    skip = None
    fh = open(filename, 'rb')
    for line in fh:
        for char in line:
            n = ord(char)
            if skip and skip == n:
                skip == None
            if n == 13:
                text += "\n"
            elif n in (128, 160):
                text += ' '
            elif n in (169, 170, 171, 173, 174):
                text += '-'
            elif n >= 192 and n <= 236:
                skip = n
            elif (n >= 0 and n <= 31) or (n >= 129 and n <= 159) or \
                 (n >= 161 and n <= 168) or n == 172 or (n >= 175 and n <= 255):
                pass
            else:
                text += char
    return text
    

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print "usage wpd2txt.py <filename>"
        sys.exit(1)
    filename = sys.argv[1]
    print wpd2txt(filename)