1

我想让程序假设我的 word_str 是“例如，这是‘剑桥大学’”。如果单词的长度大于 3 个字符，它将保留单词的第一个和最后一个字母，并在单词的内部打乱。我的问题是它错误地在单词的开头或结尾用标点符号打乱了单词。我需要它来洗牌，以便标点符号保留在正确的索引中，然后保留单词的第一个和最后一个字母，并在单词的内部洗牌，如果有的话，在末尾添加标点符号。有任何想法吗？

def scramble_word(word_str):
char = ".,!?';:"
import random
if len(word_str) <= 3:
    return word_str + ' '
else:
    word_str = word_str.strip(char)
    word_str = list(word_str)
    scramble = word_str[1:-1]
    random.shuffle(scramble)
    scramble = ''.join(scramble)
    word_str = ''.join(word_str)
    new_word = word_str[0] + scramble + word_str[-1]
    return new_word + ' '
4

2 回答 2

6

使用正则表达式：

import random
import re

random.seed(1234) #remove this in production, just for replication of my results

def shuffle_word(m):
    word = m.group()
    inner = ''.join(random.sample(word[1:-1], len(word) - 2))
    return '%s%s%s' % (word[0], inner, word[-1])
    
s = """This is 'Cambridge University' for example."""

print re.sub(r'\b\w{3}\w+\b', shuffle_word, s)

哪个打印

Tihs is 'Cadibrgme Uinrtvsiey' for exlampe.

re.sub允许您向它传递一个函数（它接受一个正则表达式匹配对象）而不是替换字符串。

编辑 - 没有正则表达式

from StringIO import StringIO

def shuffle_word(m):
    inner = ''.join(random.sample(m[1:-1], len(m) - 2))
    return '%s%s%s' % (m[0], inner, m[-1])

def scramble(text)
    sio = StringIO(text)
    accum = []
    start = None
    while sio.tell() < sio.len:
        char = sio.read(1)
        if start is None:
            if char.isalnum():
                start = sio.tell() - 1
            else:
                accum.append(char)
        elif not char.isalnum():
            end = sio.tell() - 1
            sio.seek(start)
            accum.append(shuffle_word(sio.read(end - start)))
            print accum[-1]
            start = None
    else:
        if start is not None:
            sio.seek(start)
            word = sio.read()
            if len(word) > 3:
                accum.append(shuffle_word(sio.read()))
            else:
                accum.append(word)
    
    return ''.join(accum)

s = """This is 'Cambridge University' for example."""
print scramble(s)
于 2013-03-11T22:27:56.047 回答
1

使用正则表达式非常容易：

import re
import random

s = ('Pitcairn Islands, Saint Helena, '
     'Ascension and Tristan da Cunha, '
     'Saint Kitts and Nevis, '
     'Saint Vincent and the Grenadines, Singapore')

reg = re.compile('(?<=[a-zA-Z])[a-zA-Z]{2,}(?=[a-zA-Z])')

def ripl(m):
    g = list(m.group())
    random.shuffle(g)
    return ''.join(g)

print reg.sub(ripl,s)

结果

Piictran Islands, Sanit Heelna, Asnioecsn and Tiastrn da Cunha, Sniat Ktits and Neivs, Snait Vnnceit and the Giearndens, Snoiaprge
于 2013-03-11T22:41:02.307 回答