This topic was archived here:

https://web.archive.org/web/20230000000000fw_/https://www.zenhax.com/viewtopic.php?t=9513

month, posted Fri Feb 15, 2019 8:07 pm (43532)

---

This script cannot display Chinese, Japanese, Korean and some symbols correctly after extracting the text. Can anyone modify the code so that they can display correctly?


import os
import json
import codecs


def read_block(f):
block_size = 0
index = int.from_bytes(bytes(f.read(4)), byteorder='little')
block_size = 4

len1 = int.from_bytes(bytes(f.read(2)), byteorder='little')
block_size = 2
str1 = codecs.decode(bytes(f.read(len1 * 2)), encoding='utf-8', errors='replace').replace('\00','')
block_size = len1 * 2

return {"index": index, "str1": str1, "size": block_size}

fname = 'tb_npc_script.res'
fsize = os.path.getsize(fname)
entries = []
with open("tb_npc_script.res", "rb") as f:
try:
entry_count = int.from_bytes(f.read(4), byteorder='little')
fsize -= 4
while entry_count > 0:
block = read_block(f)
fsize -= block["size"]
entry_count -= 1
entries.append(block)

except Exception as e:
print(e)

with open('tb_npc_script.txt', 'w', encoding='utf-8') as c:
json.dump(entries, c, ensure_ascii=False, indent=4)

print('??')

tb_npc_script.rar

akintos, posted Fri Feb 15, 2019 11:59 pm (43538)

---

replace line 14

Code:

   str1 = codecs.decode(bytes(f.read(len1 * 2)), encoding='utf-8', errors='replace').replace('\00','')

to this

Code:

   str1 = codecs.decode(bytes(f.read(len1 * 2)), encoding='utf-16', errors='replace').replace('\00','')

month, posted Sat Feb 16, 2019 4:24 am (43541)

---

Thank you. Thank you very much.