''''' 
Created on Dec 21, 2012 
处理文件中的每个词 
@author: liury_lab 
''' 
import codecs 
the_file = codecs.open('d:/text.txt', 'rU', 'UTF-8') 
for line in the_file: 
  for word in line.split(): 
    print(word, end = "|") 
the_file.close() 
# 若词的定义有变，可使用正则表达式 
# 如词被定义为数字字母，连字符或单引号构成的序列 
import re 
the_file = codecs.open('d:/text.txt', 'rU', 'UTF-8') 
print() 
print('************************************************************************') 
re_word = re.compile('[\w\'-]+') 
for line in the_file: 
  for word in re_word.finditer(line): 
    print(word.group(0), end = "|") 
the_file.close() 
# 封装成迭代器 
def words_of_file(file_path, line_to_words = str.split): 
  the_file = codecs.open('d:/text.txt', 'rU', 'UTF-8') 
  for line in the_file: 
    for word in line_to_words(line): 
      yield word 
  the_file.close() 
print() 
print('************************************************************************') 
for word in words_of_file('d:/text.txt'): 
  print(word, end = '|') 
def words_by_re(file_path, repattern = '[\w\'-]+'): 
  the_file = codecs.open('d:/text.txt', 'rU', 'UTF-8') 
  re_word = re.compile('[\w\'-]+') 
 
  def line_to_words(line): 
    for mo in re_word.finditer(line): 
      yield mo.group(0) # 原书为return，发现结果不对，改为yield 
  return words_of_file(file_path, line_to_words) 
print() 
print('************************************************************************') 
for word in words_by_re('d:/text.txt'): 
  print(word, end = '|')