GST_LIVING_NOVEL / plot_extract /preprocessor.py
atad-tokyo's picture
Add files using upload-large-folder tool
08bfbca verified
Raw
History Blame Contribute Delete
431 Bytes
import re
def preprocess_remove_line_break(raw_text, replacements=""):
# 移除单独换行符
pattern = r"(?<!\n)\n(?!\n)"
text_content = re.sub(pattern, replacements, raw_text)
text_content = text_content.replace("“", "\"")
text_content = text_content.replace("”", "\"")
text_content = text_content.replace("‘", "'")
text_content = text_content.replace("’", "'")
return text_content