Finds the longest sections in a text file that don't repeat letters.

norepeatingletters

import sys

input_file=[]
with open(sys.argv[1]) as f:
  while True:
    c = f.read(1)
    if not c:
      print "End of file"
      break
    input_file.append(c)

def process(start_here):
    subfile=input_file[start_here:]
    currentResult=""
    letters ={} #letters is a dictionary
    index=len(subfile)
    for i in range(index):
        c=subfile[i]
        if c in letters:
            #print "Found {} at index {}, last seen {} ago".format(c,i,i-letters[c])
            temp=currentResult.rsplit(' ',1)[0]
            ideas.append(temp.rstrip('?:!.,;').replace("\n",""))
            temp=letters[c]
            length_of_string=len(currentResult)
            #print length_of_string
            how_much_to_cut=length_of_string+letters[c]-i
            #print "Hey {}".format(how_much_to_cut)
            replacement=currentResult[how_much_to_cut+1:]
            removed=currentResult[:how_much_to_cut]
            #print "Current result was {}, and will now be {} ...".format(currentResult,replacement)
            letters={}
            for x in range(len(replacement)):
                letters[replacement[x]]=i-len(replacement)+x
                #print "setting {}".format(replacement[x])
            letters[c]=i
            currentResult=replacement
        currentResult+=c
        if not c.isspace():
            letters[c]=i
        index+=1

ideas=[]
index=0
process(index)


print "About to remove doubles"
ideas=sorted(set(ideas))
print "About to sort"
ideas.sort(lambda x,y: cmp(len(x), len(y)))
for x in ideas:
    print "X:"+x.strip()+":X"