python 文本编码程序

Question

将文本输入到定义 run_length_encoder 时，应压缩重复字母例如，当输入 aaabbac 时，输出应为 ['a','a',3,'b','b',2,'a','c']但我的代码没有压缩。

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] 而我得到的是这个 ['a ', 'b', 'b', '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)