From d7926cde07e97335957d94c622b5ec98def8c270 Mon Sep 17 00:00:00 2001 From: jarbasai Date: Tue, 12 Dec 2017 03:10:00 +0000 Subject: [PATCH] pt unicode bug fix in normalization --- mycroft/util/parse.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mycroft/util/parse.py b/mycroft/util/parse.py index 63434c270b..8f19958460 100644 --- a/mycroft/util/parse.py +++ b/mycroft/util/parse.py @@ -2125,12 +2125,12 @@ def pt_pruning(text, symbols=True, accents=True, agressive=True): text = text.replace(symbol, "") text = text.replace("-", " ").replace("_", " ") if accents: - accents = {"a": [u"�", u"�", u"�", u"�"], - "e": [u"�", u"�", u"�"], - "i": [u"�", u"�"], - "o": [u"�", u"�"], - "u": [u"�", u"�"], - "c": [u"�", u"�"]} + accents = {"a": [u"á", u"à", u"ã", u"â"], + "e": [u"ê", u"è", u"é"], + "i": [u"í", u"ì"], + "o": [u"ò", u"ó"], + "u": [u"ú", u"ù"], + "c": [u"ç"]} for char in accents: for acc in accents[char]: text = text.replace(acc, char)