#!/usr/bin/env python
#
# Copyright 2010 Open Source Beef Computing. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
# Redistributions of source code must retain the above copyright notice, this
# list of conditions and the following disclaimer.
# Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE OPEN SOURCE BEEF COMPUTING  PROJECT ``AS IS'' AND ANY EXPRESS
# OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
# OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
# EVENT SHALL THE FREEBSD PROJECT OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
# INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
# BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
# EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#

import sys
import os

__doc__="""
  The text file ROW MANipulation utility. Version 0.0.5

  -f name of file to process
  -o name of output file
  -u Parse a file an show only unique rows *line breaks are counted, so two identical
     lines but one having a line break and the other not will show a two unique lines

  -d Parse a file and show only duplicate rows
  -x Parse file removing duplicates. Duplicates will appear as one line in output

  -c if -d is specified -c will give the count of the number of time the row appears
"""

def main():
  FILE_NAME = ''
  WRITE = False
  COUNT = False

  argc = len(sys.argv)
  idx = 1

  while(idx < argc):
    if(sys.argv[idx] == "-f"):
      FILE_NAME = sys.argv[(idx+1)]
    elif(sys.argv[idx] == "-u"):
      UNIQUE = True
      DUPS = False
      REMOVE = False
    elif(sys.argv[idx] == "-d"):
      DUPS = True
      UNIQUE = False
      REMOVE = False
    elif(sys.argv[idx] == "-x"):
      REMOVE = True
      UNIQUE = False
      DUPS = False
    elif(sys.argv[idx] == "-c"):
      COUNT = True
    elif(sys.argv[idx] == "-o"):
      WRITE = True
      OUT_FILE = sys.argv[(idx+1)]
    elif(sys.argv[idx] in("-h","--help")):
      print __doc__
      sys.exit(0)
    idx = (idx + 1)

  fh = open(FILE_NAME)
  hold = set()
  unique_lines = set()
  dup_lines = set()
  dup_dict = {}

  if(UNIQUE):
    for line in fh:
      if line in hold:
        dup_lines.add(line)
      else:
        hold.add(line)

    unique_lines = hold.difference(dup_lines)

    if(WRITE):
      fo = open(OUT_FILE,'w+')
      for line in unique_lines:
        fo.write(line)
    else:
      for line in unique_lines:
        print line

  elif(DUPS):
    for line in fh:
      if line in hold:
        dup_lines.add(line)
        if(COUNT):
          if line in dup_dict.keys():
            dup_dict[line] += 1
          else:
            dup_dict[line] = 1
      else:
        hold.add(line)

    if(WRITE):
      fo = open(OUT_FILE,'w+')
      for line in dup_lines:
        if(COUNT):
          fo.write("%s : %s" % (dup_dict[line], line))
        else:
          fo.write(line)
    else:
      for line in dup_lines:
        if(COUNT):
          print "%s : %s" % (dup_dict[line], line)
        else:
          print line

  elif(REMOVE):
    for line in fh:
      unique_lines.add(line)

    if(WRITE):
      fo = open(OUT_FILE,'w+')
      for line in unique_lines:
        fo.write(line)
    else:
      for line in unique_lines:
        print line

  print 'Done'

if __name__ == "__main__":
  main()