Python实现针对中文排序的方法

>> print ','< '1'<'A'<'a'<'阿'
True

>> print '曙'< '鲑','曾'<'怡'
True True

# encoding=utf8
char=['赵','钱','孙','李','佘']
char.sort()
for item in char:
  print item.decode('utf-8').encode('gb2312')

# encoding=gb2312
char=['赵','钱','孙','李','佘']
char.sort()
for item in char:
  print item

# 建立拼音辞典
dic_py = dict()
f_py = open('py.txt','r')
content_py = f_py.read()
lines_py = content_py.split('\n')
n=len(lines_py)
for i in range(0,n-1):
  word_py, mean_py = lines_py[i].split('\t', 1)
  dic_py[word_py]=mean_py
f_py.close()

# 辞典查找函数
def searchdict(dic,uchar):
  if isinstance(uchar, str):
    uchar = unicode(uchar,'utf-8')
  if uchar >= u'\u4e00' and uchar < = u'\u9fa5':
    value=dic.get(uchar.encode('utf-8'))
    if value == None:
      value = '*'
  else:
    value = uchar
  return value

#比较单个字符
def comp_char_PY(A,B):
  if A==B:
    return -1
  pyA=searchdict(dic_py,A)
  pyB=searchdict(dic_py,B)
  if pyA > pyB:
    return 1
  elif pyA < pyB:
    return 0
  else:
    bhA=eval(searchdict(dic_bh,A))
    bhB=eval(searchdict(dic_bh,B))
    if bhA > bhB:
      return 1
    elif bhA < bhB:
      return 0
    else:
      return 'Are you kidding?'
#比较字符串
def comp_char(A,B):
  charA = A.decode('utf-8')
  charB = B.decode('utf-8')
  n=min(len(charA),len(charB))
  i=0
  while i < n:
    dd=comp_char_PY(charA[i],charB[i])
    if dd == -1:
      i=i+1
      if i==n:
        dd=len(charA)>len(charB)
    else:
      break
  return dd
# 排序函数
def cnsort(nline):
  n = len(nline)
  lines='\n'.join(nline)
  for i in range(1, n): #插入法
    tmp = nline[i]
    j = i
    while j > 0 and comp_char(nline[j-1],tmp):
      nline[j] = nline[j-1]
      j -= 1
    nline[j] = tmp
  return nline

char=['赵','钱','孙','李','佘']
char=cnsort(char)
for item in char:
  print item.decode('utf-8').encode('gb2312')