python文本编码程序

Question

当输入一个文本到定义run_length_encoder时，重复的字母应该被压缩，例如，当输入aaabbac时，输出应该是'a'，'a',3，'b'，'b',2，'a'，'c‘，但是我的代码不是压缩的。

def run_length_encoder(string):
#def compress(string):

    res = []

    count = 1

    #Add in first character
    res.append(string[0])

    #Iterate through loop, skipping last one
    for i in range(len(string)-1):
        if(string[i] == string[i+1]):
            count+=1
            res.append(string[i+1])
        else:
            if(count > 1):
                #Ignore if no repeats
                res.append(count)
            res.append(string[i+1])
            count = 1
    #print last one
    if(count > 1):
        res.append(str(count))
    return res

例如，当输入abbbbaa时，输出应该是这个'a'，'b'，'b'，4，'a'，'a'，2而我得到的是'a'，'b'，'b'，4，'a'，'a'，'2‘

Answer 1

你也可以这样做：

def run_length_encoder(str_):
    compressedString = ''
    countConsecutive = 0
    strLen = len(str_)
    for i in range(strLen):
        countConsecutive += 1
        if i + 1 >= strLen or str_[i] != str_[i + 1]:
            compressedString += '' + str_[i] + str(countConsecutive)
            countConsecutive = 0

    return compressedString

sample = 'aaabbac'
result = list(run_length_encoder(sample))
print(result)

Answer 2

Itertools爱你，希望你快乐：

from itertools import chain, groupby

def run_length_encoder(src):
    return list(
        # chain.from_iterable flattens the series of tuples we make inside the
        # loop into a single list.
        chain.from_iterable(
            # groupby returns an iterable (item, group) where group is an
            # iterable that yields a copy of `item` as many times as that item
            # appears consecutively in the input. Therefore, if you take the
            # length of `group`, you get the run length of `item`. This
            # whole expression then returns a series of (letter, count)
            # tuples.
            (letter, len(list(group))) for letter, group in groupby(src)
        )
    )


print(run_length_encoder("aajjjjiiiiohhkkkkkkkkhkkkk"))

Answer 3

你的逻辑需要修正。修复了处理偶数和奇数结束情况的编辑。

def run_length_encoder(string):
#def compress(string):

    res = []
    count = 1
    if(len(string) == 1):
        res.append(string[0])
        res.append(count)
        return res
    else:
        current = string[0]

        for i in range(1, len(string)):

            if(string[i] == current):
                count+=1
            else:
                res.append(current)
                res.append(count)
                current = string[i]
                count = 1
            i+=1
            if(i == len(string)):
                res.append(current)
                res.append(count)
        return res

字符串测试: string = "aaabbaadddaad“输出：'a'，3，'b'，2，'a'，2，'d'，3，'a'，2，'d'，1 string = "aaabbaaddd”输出：'a'，3，'b'，2，'a'，2，'d'，3 string = "aabccdd“输出：'a'，2，'b'，1，'c'，2，'d'，2