self-constructing_graph/graph/test/test_parse_txt.py

new_filename = 'D:\work\data\典型病例\典型病例合并后的数据1.txt'

with open(f"{new_filename}", 'r', encoding="utf-8") as f:
    buf_str = ""
    for line in f.readlines():
        line = line.strip()
        
        if len(buf_str) > 0:
            buf_str = buf_str + "\n" + line
        else:
            buf_str = buf_str + line

        while len(buf_str) > 256:
            chunk = buf_str[0:256]
            buf_str = buf_str[256:]      
            print("*" * 60)           
            if chunk[-1] != '\n' and chunk[-1] != "。":
                last_end1 = chunk.rfind("。")
                last_end2 = chunk.rfind("\n")
                if last_end1 == -1 and last_end2 == -1:
                    last_end1 = len(chunk)
                print("found end char: ", last_end1, last_end2)
                print("*" * 60)           
                if last_end2 > last_end1:
                    last_end1 = last_end2
                buf_str = chunk[last_end1 + 1:] + buf_str
                chunk = chunk[0:last_end1 + 1]
                print(len(chunk),chunk)