distance.py 文件源码

def computeLevenhsteinDistance(b1,o1,b2,o2,isRead1,isRead2):

   counter = 0 
   distance = 0 

   for i in itertools.izip_longest(b1,o1,b2,o2,isRead1,isRead2):
      # check if read/write matches
      if i[4] == i[5]:
        #check if block IDs match
        if i[0] != i[2]:
           distance = distance + 1
        #check if offsets match
        if i[1] != i[3]:
           distance = distance + 1
      else:
        distance = distance + 2 
      counter = counter + 1
   # return normalized distance 
   return distance/float(counter*2)

# mix block IDs. Assign block IDs from Ngram1 to Ngram2