From 7b4eb9827e8689ea3dcb32d968a4fdad335af57d Mon Sep 17 00:00:00 2001 From: Jehan Date: Sat, 12 Dec 2015 18:00:30 +0100 Subject: [PATCH] BuildLangModel: add an exception handler on charset spec errors. --- script/BuildLangModel.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/script/BuildLangModel.py b/script/BuildLangModel.py index 89d6bb7..5d9eb43 100755 --- a/script/BuildLangModel.py +++ b/script/BuildLangModel.py @@ -359,7 +359,12 @@ for charset in charsets: elif cp_type == NUM: CTOM_str += 'NUM,' else: # LET - uchar = bytes([cp]).decode(charset) + try: + uchar = bytes([cp]).decode(charset) + except UnicodeDecodeError: + print('Unknown character 0X{:X} in {}.'.format(cp, charset)) + print('Please verify your charset specification.\n') + exit(1) #if lang.case_mapping and uchar.isupper() and \ #len(unicodedata.normalize('NFC', uchar.lower())) == 1: # Unless we encounter special cases of characters with no