difflib - 差异

‍

demo - 计算文本相似度

from difflib import SequenceMatcher

def similarity(a, b):
    return SequenceMatcher(None, a, b).ratio()

cases = (
    ("test","test"),
    ("aaaa", ""),
    ("aaaa", "bbbbbb"),
    ("aaaa", "bbbb"),
    ("aaaa", "aabb"),
    ("易查通日常升级的发布请示", "【易查通】易查通系统日常升级"),
)

for case in cases:
    print('case: ',case)
    print(similarity(*case))
"""
case:  ('test', 'test')
1.0
case:  ('aaaa', '')
0.0
case:  ('aaaa', 'bbbbbb')
0.0
case:  ('aaaa', 'bbbb')
0.0
case:  ('aaaa', 'aabb')
0.5
case:  ('易查通日常升级的发布请示', '【易查通】易查通系统日常升级')
0.5384615384615384
"""

‍