Created
February 9, 2022 11:16
-
-
Save takana-v/3e639a59645c03e21b82de913d2c7a00 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import unicodedata | |
hankaku_alphabet = "".join(chr(0x21 + i) for i in range(94)) | |
zenkaku_alphabet = "".join(chr(0xff01 + i) for i in range(94)) | |
translate_table = str.maketrans(hankaku_alphabet, zenkaku_alphabet) | |
original_dict = "/path/to/naist-jdic.csv" | |
normalized_dict = "/path/to/normalized.csv" | |
def text_normalize(text: str): | |
text = text.translate(translate_table) | |
ret = "" | |
for s in text: | |
if s in zenkaku_alphabet: | |
ret += s.lower() | |
else: | |
ret += unicodedata.normalize("NFC", s) | |
return ret | |
write_log = set() | |
with open(original_dict, encoding="utf-8") as f: | |
with open(normalized_dict, mode="w", encoding="utf-8") as f2: | |
for l in f: | |
l_splitted = l.split(",") | |
l_splitted[0] = text_normalize(l_splitted[0]) | |
write_contents = ",".join(l_splitted) | |
log_contents = ",".join(l_splitted[0:10]+l_splitted[11:]) | |
if log_contents in write_log: | |
continue | |
else: | |
write_log.add(log_contents) | |
f2.write(write_contents) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment