Patches holes in tabular data. Good for cleaning up TSV and CSV files.

patcher.py

#!/usr/bin/env python
# encoding: utf-8
# David Wicks
"""
 patcher.py
 Fills holes in tabular data files (TSV)
 basic usage:	python patcher.py fileToPatch.tsv
 more control: python patcher.py fileToPatch.csv outputfile.csv replacementValue ,
"""

import sys
import os

# for command-line execution
def main(argv=None):
	if argv is None:
		argv = sys.argv
	try:
		args = len( argv ) - 1
		if( args == 1 ):
		   	patch( argv[1] )
		if( args == 2 ):
		   	patch( argv[1], argv[2] )
		if( args == 3 ):
		   	patch( argv[1], argv[2], argv[3] )
		if( args == 4 ):
			patch( argv[1], argv[2], argv[3], argv[4] )
	except:
		print "That didn't work. Try including a filename to load."

# does the patching 
def patch( filename, outputName="patched.tsv", filler="empty", sep="\t" ):
	file = open( filename, 'r' )
	lines = file.readlines()
	file.close()
	
	patchedLines = []
	
	for line in lines:
		while not line.find( sep + sep ) == -1:
			line = line.replace( sep + sep, sep + filler + sep )
		patchedLines.append( line )
	
	output = open( outputName, 'w' )
	output.write( "".join( patchedLines ) )
	output.close()
	print "Patched holes %s with '%s' and saved to %s." % ( filename, filler, outputName )

def patchLine( line, patch ):
	if( line == '' ):
		return patch
	return line

if __name__ == '__main__':
	main()