Replace 16bit hex Unicode characters with named Unicode in Python scripts

unicode_replace.py

# Example file content before: print("\u274c")
# After: print("\N{CROSS MARK}")
import re

REGEXP = re.compile(r"(\\u[0-9|a-f|A-F]{4})+")

with open("file.py", "r", encoding="utf-8") as file:
    lines = file.readlines()


def replace_unicode(uc: str) -> str:
    return uc.encode('utf-16', 'surrogatepass').decode('utf-16').encode('ascii', 'namereplace').decode('ascii')


res = []
for line in lines:
    for match in re.finditer(REGEXP, line):
        m = match[0]
        r = eval(f"u'{m}'")
        named_unicode = replace_unicode(r)
        print(f"{m} -> {named_unicode}")
        line = line.replace(m, named_unicode)
    res.append(line)


with open("output.py", "w", encoding="utf-8") as file:
    file.writelines(res)