From b405a53fe151a0ae2c3f3fa0c56f1a4f3797e485 Mon Sep 17 00:00:00 2001 From: Al Date: Tue, 22 Sep 2015 08:14:27 -0400 Subject: [PATCH] [fix] chars out of range in get_string_script Python version --- scripts/geodata/language_id/disambiguation.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/geodata/language_id/disambiguation.py b/scripts/geodata/language_id/disambiguation.py index b6c47341..6ba20ae0 100644 --- a/scripts/geodata/language_id/disambiguation.py +++ b/scripts/geodata/language_id/disambiguation.py @@ -163,6 +163,8 @@ def get_string_script(s): is_ascii = True script_len = 0 for c in s: + if (ord(c)) >= len(char_scripts): + continue script = char_scripts[ord(c)] if script == COMMON_SCRIPT and last_script != UNKNOWN_SCRIPT: script = last_script