I have a python script that removes duplicate of a file which is given by -i
parameter to the script. So like -i input.txt
.
I want the -o
parameter, which is the output filename, be like this: input-file-name-without-extension_dupsremoved.txt
. Like -o input_dupsremoved.txt
.
removeDups.py
import optparse
def removeDups(inputfile, outputfile):
file1 = open(inputfile, "r")
lines = file1.readlines()
file1.close()
out = open(outputfile, "w")
out.writelines(uniquelines(lines))
out.close()
def uniquelines(lineslist):
unique = {}
result = []
for item in lineslist:
if item.strip() in unique: continue
unique[item.strip()] = 1
result.append(item)
return result
def main():
parser = optparse.OptionParser('usage %prog ' +\
'-i <inputfile> -o <outputfile>')
parser.add_option('-i', dest='inputfile', type='string',
help='specify your input file')
parser.add_option('-o', dest='outputfile', type='string',
help='specify your output file')
(options, args) = parser.parse_args()
inputfile = options.inputfile
outputfile = options.outputfile
if (inputfile == None) or (outputfile == None):
print (parser.usage)
exit(1)
else:
removeDups(inputfile, outputfile)
if __name__ == '__main__':
main()
Im currently using this batch file to do it but the batch file is not correct.
@echo off
set /p input= Input file:
set output= output.txt
set dupsremoved= %input%_dupsremoved.txt
script1.py -i %input% -o %output%
script2.py -i %output% -o %dupsremoved%
del %output%
which can be fixed by this answer from Gerhard Barnard:
@echo off
setlocal enabledelayedexpansion
set /p "input=Input file: "
set "output=output.txt"
set "ext=%input:*.=%
set "input=!input:.%ext%=!
set "dupsremoved=!input!_dupsremoved.txt"
script1.py -i %input% -o %output%
script2.py -i %output% -o %dupsremoved%
del %output%