Function defines the longest similar sequence between given iterables.

find_longest_similar.py

def find_longest_similar(a,b,is_similar=None,is_ignored = None):
  '''
  This function defines the longest similar sequence between given iterables.
  If no similarity function is given the function uses equality.
  '''
  
  # Default Functions
  if(not is_similar): is_similar = lambda x,y: x==y
  if(not is_ignored): is_ignored = lambda _:False
  
  # Default Values
  a_best, b_best, size_best = 0, 0, -1
  a_start,b_start = 0,0
  matching,match_index = False,-1
  
  for i,a_i in enumerate(a):
    if(is_ignored(a_i)): continue
    
    for j,b_j in enumerate(b):
      if(j <= match_index): continue
      if(is_ignored(b_j)):  continue
      
      # Compare
      if(is_similar(a_i,b_j)):
        # Starting Match
        if(not matching): a_start,b_start = i,j
        # Exit Actions
        matching,match_index = True,j
        break
      else:
        # Ending Match
        if(matching and size_best < i - a_start):
          size_best  = i - a_start
          a_best,b_best = a_start,b_start
        # Exit Actions
        matching,match_index = False,-1
  
  # Ending Match
  if(matching and size_best < len(a) - a_start):
    size_best  = len(a) - a_start
    a_best,b_best = a_start,b_start
  
  # Return
  return (a_best, b_best, size_best)