如何比较两个字符串中的字符序列

Question

Python version is 2.7.9 In python, I have the baseline strings and other strings to be compared:

baseline_string="c1,c2,c3,c4,c5,c6,c7,c8,c9,c10"
#all the characters appeared as the sequence defined in base line string ,this is ok
compared1="c1,c2,c3,c4,c5,c6,c7,c8,c9,c10" 
#all the characters appeared as the sequence defined in base line string,some charaters don't appear such as c2 and c7 don't appear ,this is ok
compared2="c1,c3,c4,c5,c6,c8,c9,c10"
#some character does not appear as the defind sequece,such as c4 is before c3 ,and c110 is before c9

The difflib.SequenceMatcher can not solve my problem. Need the python guru to give some advice. Thanks a lot.

Answer 1

Try this, using the itertools will help you overcome the strings being of different lengths. .zip compares character for character in each of the strings and returns them in tuples .

import itertools

compared1 = "c1,c2,c3,c4,c5,c6,c7,c8,c9,c10" 

compared2 = "c1,c3,c4,c5,c6,c8,c9,c10"

words = itertools.zip_longest(compared1,compared2,fillvalue=None)

incorrect = len([c for c,d in words if c!=d]) 

print(incorrect)

Answer 2

# the following code is run ok,but I think that should be better
#method to check
def check_order():
    from collections import OrderedDict
    compared1 = "c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,"
    compared2 = "c1,c3,c4,c5,c6,c8,c9,c10"
    compared2 = "c3,c4,c6,c5,c9,c10,c7"
    compared3 = "c4,c3,c6,c5,c8,c9,c10"
    base_dict = OrderedDict()
    base_order = 1
    compared_dict2 = OrderedDict()
    compared_order2 = OrderedDict()
    compare_order2 = 1

    compared_dict3 = OrderedDict()
    compare_order3 = 1
    check_result = True

    for base_substr in compared1.split(','):
        base_dict[base_substr] = base_order
        base_order = base_order + 1

    for base_keys, base_value in base_dict.items():
        print("key is " + str(base_keys) + \
              " order is " + str(base_value))

    for compared_substr2 in compared2.split(','):
        compared_dict2[compared_substr2] = compare_order2
        compared_order2[compare_order2] = compared_substr2
        compare_order2 = compare_order2 + 1

    for compare_key2, compared_value2 in compared_dict2.items():
        print("key is " + str(compare_key2) +\
              " order is " + str(compared_value2))

    compare_len_2 = len(compared_dict2)
    compare_key_tmp = None
    compare_key_order_in_base = 0
    for compare_key2, compared_value2 in compared_dict2.items():
        based_value = base_dict[compare_key2]
        for num in range(1, compared_value2):
            compare_key_tmp = compared_order2[num]
            compare_key_order_in_base = base_dict[compare_key_tmp]
            print("The key :" + str(compare_key_tmp) +\
                  "and order in base is:" + str(compare_key_order_in_base))
            if compare_key_order_in_base <= based_value:
                print("The key " + str(compare_key_tmp) + \
                      "is less than" + str(based_value))
            else:
                print("Error,The key " + str(compare_key_tmp) +\
                      "is larger than" + str(based_value))
                check_result = False

    return check_result


if __name__ == '__main__':
    check_result = check_order()
    if check_result:
        print("Pass")
    else:
        print("Failed")