字符串问题python实现（二）

# 问题：求字符串中重复出现且长度最长子字符串，要求输出：符合条件子字符串、其重复出现次数、其首字母位置。
# 分析：后缀数组方法求解。
# by chasdmeng

def build_suffix_array(suffix_array, text_string):
for i in range(len(text_string)):
suffix_array.append(text_string[i:])
suffix_array.sort()

def comlen(str_a, str_b):
max_len = 0
for i in range(1, len(str_a)+1):
max_len = i if str_a[:i]==str_b[:i] else max_len

return max_len

def longset_repeat_substring(suffix_array, text_string):
max_len, max_idx = 0, 0
t={}
for i in range(len(text_string) - 1):
com_len= comlen(suffix_array[i], suffix_array[i+1])
if com_len in t:
t[com_len]+=1
else:
t[com_len] = 2
[max_len, max_idx] = [com_len, i] if com_len > max_len else [max_len, max_idx]
loc = [len(text_string)-len(suffix_array[max_idx + i]) + 1 for i in range(t[max_len])]
loc.sort()
return suffix_array[max_idx][:max_len], t[max_len], loc

if __name__ == '__main__':
suffix_array = []
text_string = "yyabcdabjcabceg"

build_suffix_array(suffix_array, text_string)
substring, time, location = longset_repeat_substring(suffix_array, text_string)
print '\nIn \'', text_string, '\', the longest string', '\'', substring, '\'occuers',\
time, 'times',',the first character position', ','.join([str(i) for i in location]), '.'