From d38fbee2ec34bebd116feca72d26e8643a500b1d Mon Sep 17 00:00:00 2001
From: Karol Idaszak <karoel123@gamil.com>
Date: Wed, 1 Jun 2022 10:49:28 +0200
Subject: [PATCH] Add preprocessing for replacing polish characters

---
 system_mockup/analizator_jezyka_naturalnego.py | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/system_mockup/analizator_jezyka_naturalnego.py b/system_mockup/analizator_jezyka_naturalnego.py
index 7bc960f..e991c10 100644
--- a/system_mockup/analizator_jezyka_naturalnego.py
+++ b/system_mockup/analizator_jezyka_naturalnego.py
@@ -2,13 +2,13 @@ import re
 
 from acts import hello_act, name_request_act
 
-hello = ['dzie[ńn] dobry', 'dobry wiecz[oó]r', 'witam', 'witaj', 'siema', 'elo', 'cze[śs][ćc]']
-request_name = ['imi[eę]', 'nazywasz']
+hello = ['dzien dobry', 'dobry wieczor', 'witam', 'witaj', 'siema', 'elo', 'czesc']
+request_name = ['imie', 'nazywasz']
 question = ['\?$']
 
 acts = {hello_act: [hello],
         name_request_act: [request_name, question]}
-        
+
 def analizator_jezyka_naturalnego(text):
     text = text_preprocess(text)
     frame = act_check(text)
@@ -16,6 +16,18 @@ def analizator_jezyka_naturalnego(text):
 
 def text_preprocess(text):
     text = text.lower()
+    text = text.replace("ą", "a")
+    text = text.replace("ć", "c")
+    text = text.replace("ę", "e")
+    text = text.replace("ł", "l")
+    text = text.replace("ń", "n")
+    text = text.replace("ó", "o")
+    text = text.replace("ś", "s")
+    text = text.replace("ź", "z")
+    text = text.replace("ż", "z")
+    text = text.replace("\n", " ")
+    text = text.replace("\t", " ")
+    text = text.replace("  ", " ")
     return text
 
 def act_check(text):