helpers.py 文件源码

def generate_frequency_table(text,charset):
   '''
   Generate a character frequency table for a given text
   and charset as dict with character or string as key and
   frequency of appearance as value expressed as a decimal
   percentage

   text - A sample of plaintext to analyze for frequency data
   charset - (list of strings) The set of items to count in the plaintext
      such as ['a','b','c', ... 'z','aa','ab','ac', ... 'zz']
   '''
   freq_table = {}
   text_len = 0 
   for char in charset:
      freq_table[char] = 0 
   for char in text:
      if char in charset:
         freq_table[char] += 1
         text_len += 1
   for multigraph in filter(lambda x: len(x)>1,charset):
      freq_table[multigraph] = string.count(text, multigraph)
   # Normalize frequencies with length of text
   for key in freq_table.keys():
      if text_len != 0:
         freq_table[key] /= float(text_len)
      else:
         freq_table[key] = 0 
   return freq_table