Snippets from XWN

import codecs

'''
Snippets from xWN, a wordnet toy-tool developed with Open Multilingual WordNet http://www.casta-net.jp/~kuribayashi/multi/
'''

# This function reads a .tab WN file and returns the WN in dic format.
def readWNfile(wnfile, option="ss"):
  reader = codecs.open(wnfile, "r", "utf8").readlines()
  wn = {}
  for l in reader:
    if l[0] == "#": continue
    if l.split("\t")[0][-1] == "n":
      if option=="ss":
        k = l.split("\t")[0] #ss as key
        v = l.split("\t")[2][:-1] #word
      else:
        v = l.split("\t")[0] #ss as value
        k = l.split("\t")[2][:-1] #word as key
      try:
        temp = wn[k]
        wn[k] = temp + ";" + v
      except KeyError:
        wn[k] = v
    else:
      continue
  return wn

def createDicfrom2WNs(wnfile1, wnfile2, outfile=None, delimiter=None):
  wn1 = readWNfile(wnfile1,"ss")
  wn2 = readWNfile(wnfile2,"ss")
  newdic = {}
  # Load WNs' entries into dictionary.
  for i in wn1:
    if i in wn2:
      if len(wn1[i]) or len(wn2[i]) is 1:
        for j in wn1[i].split(";"):
          print j, wn2[i]
          newdic[j] = wn2[i]
    # Configure output file.
  outfile = wnfile1[-7:-4]+"-"+wnfile2[-7:-4]+".dic" if outfile==None else outfile
  out = codecs.open(outfile,"w","utf8")
  delimiter = "\t" if delimiter ==None else delimiter
  # Loop through dictionary and output entries.
  for k in sorted(newdic):
    for v in sorted(newdic[k].split(";")):
        print>>out, k + delimiter + v
  return newdic

eng_wnfile = '/media/E418A6B618A686E0/xling/wordnet/wn-data-eng.tab'
spa_wnfile = '/media/E418A6B618A686E0/xling/wordnet/wn-data-ind.tab'

createDicfrom2WNs(eng_wnfile,spa_wnfile, delimiter=" @ ")