import sys

# Parse the command line.
if (len(sys.argv) != 4):
  print "USAGE: find-unique-tags.py <genome> <tags> <output>"
  sys.exit(1)
genomeFilename = sys.argv[1]
tagsFilename = sys.argv[2]
outputFilename = sys.argv[3]

#############################################################################
def readSequenceList(genomeFilename):
  returnValue = []
  numBases = 0

  # Open the file for reading.
  genomeFile = open(genomeFilename, "r")

  # Each line is one chromosome.
  for chromosome in genomeFile:
    chromosome = chromosome.rstrip()
    numBases += len(chromosome)
    returnValue.append(chromosome)

  # Tell the user what happened.
  print "Read %d bases in %d chromosomes from %s." % (numBases,
                                                      len(returnValue),
                                                      genomeFilename)
  return(returnValue)


#############################################################################
# MAIN PROCEDURE
#############################################################################

# Read the genome into memory.
genome = readSequenceList(genomeFilename)

# Open the ouput file.
outputFile = open(outputFilename, "w")

# Initialize counters.
numTags = 0
numUniques = 0

# Read the tags line by line.
tagsFile = open(tagsFilename, "r")
for tag in tagsFile:
  tag = tag.rstrip()

  # Count the number of matches.
  numMatches = 0
  for chromosome in genome:
    numMatches += chromosome.count(tag)
  
  # Decide whether it's unique.
  if (numMatches == 1):
    outputFile.write("%s\n" % tag)
    numUniques += 1
  numTags += 1

tagsFile.close()

# Tell the user what happened.
print "Read %d tags from %s." % (numTags, tagsFilename)
print "Printed %d unique tags to %s." % (numUniques, outputFilename)