Mercurial > repos > greg > convert_chars
diff convert_characters.py @ 0:21b1788b85a4
Version 1
author | greg |
---|---|
date | Fri, 05 Aug 2011 16:31:46 -0400 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/convert_characters.py Fri Aug 05 16:31:46 2011 -0400 @@ -0,0 +1,42 @@ +#!/usr/bin/env python +#By, Guruprasad Ananda. + +from galaxy import eggs +import sys, re + +def stop_err(msg): + sys.stderr.write(msg) + sys.exit() + +def main(): + if len(sys.argv) != 4: + stop_err("usage: convert_characters infile from_char outfile") + + try: + fin = open(sys.argv[1],'r') + except: + stop_err("Input file cannot be opened for reading.") + + from_char = sys.argv[2] + + try: + fout = open(sys.argv[3],'w') + except: + stop_err("Output file cannot be opened for writing.") + + char_dict = {'T':'\t','s':'\s','Dt':'\.','C':',','D':'-','U':'_','P':'\|'} + from_ch = char_dict[from_char] + '+' #making an RE to match 1 or more occurences. + skipped = 0 + + for line in fin: + line = line.strip() + try: + fout.write("%s\n" %(re.sub(from_ch,'\t',line))) + except: + skipped += 1 + + if skipped: + print "Skipped %d lines as invalid." %skipped + +if __name__ == "__main__": + main() \ No newline at end of file