问使用python消除两个文本块之间的重叠

EN

text1 = """Some of the major unsolved problems in physics are theoretical, meaning that existing theories seem incapable of explaining a certain observed phenomenon or experimental result. The others are experimental, meaning that there is a difficulty in creating an experiment to test a proposed theory or investigate a phenomenon in"""
text2 = """theory or investigate a phenomenon in greater detail.There are still some deficiencies in the Standard Model of physics, such as the origin of mass, the strong CP problem, neutrino mass, matter–antimatter asymmetry, and the nature of dark matter and dark energy."""

def remove_overlap(text1, text2):
    """Returns the part of text2 that doesn't overlap with text1"""

    words1 = text1.split()
    words2 = text2.split()

    # all apperances of the last word of text1 in text2
    last_word_appearances = [index for index, word in enumerate(words2) if word == words1[-1]]
    # we look for the largest possible overlap
    for n in reversed(last_word_appearances):
        # are the first n+1 words of text2 the same as the (n+1) last from text1? 
        if words2[:n+1] == words1[-(n+1):]:
            return ' '.join(words2[n+1:])
    else:
        # no overlap found
        return text2


remove_overlap(text1, text2)
# 'greater detail.There are still some deficiencies in [...]

text1 = """Some of the major unsolved problems in physics are theoretical, meaning that existing theories seem incapable of explaining a certain observed phenomenon or experimental result. The others are experimental, meaning that there is a difficulty in creating an experiment to test a proposed theory or investigate a phenomenon in"""
text2 = """theory or investigate a phenomenon in greater detail.There are still some deficiencies in the Standard Model of physics, such as the origin of mass, the strong CP problem, neutrino mass, matter–antimatter asymmetry, and the nature of dark matter and dark energy.""" 

text1_ls = list(filter(None,text1.split(".")))[-1]
text2_fs = text2.split(".")[0]

temp2 = text2_fs.split(" ")

for i in range(1, len(temp2)):  
    if " ".join(temp2[:i]) not in text1_ls:
        text2_fs = " ".join(temp2[(i - 1):])
        break

print(text1_ls, "\n")
print(text2_fs, "\n")

first_word_text2 = text2.split()[0]
pos = len(text1) - text1.rfind(first_word_text2)
text2[pos:].strip()