From 6c2af753df909b853a9ee1d53b2f3634809a5fe3 Mon Sep 17 00:00:00 2001
From: Wojciech Jarmosz <jarmoszw@gmail.com>
Date: Thu, 9 Jun 2022 01:32:43 +0200
Subject: [PATCH] Filter dummy errors

---
 backend/requirements.txt     | 15 +++++++++++++++
 backend/translation/views.py | 21 +++++++++++++++++++--
 2 files changed, 34 insertions(+), 2 deletions(-)
 create mode 100644 backend/requirements.txt

diff --git a/backend/requirements.txt b/backend/requirements.txt
new file mode 100644
index 0000000..9f670b8
--- /dev/null
+++ b/backend/requirements.txt
@@ -0,0 +1,15 @@
+asgiref==3.5.2
+backports.zoneinfo==0.2.1
+defusedxml==0.7.1
+Django==4.0.4
+django-cors-headers==3.12.0
+django-environ==0.8.1
+djangorestframework==3.13.1
+djangorestframework-xml==2.0.0
+langdetect==1.0.9
+lxml==4.8.0
+pytz==2022.1
+regex==2022.4.24
+six==1.16.0
+sqlparse==0.4.2
+websocket-client==1.3.2
diff --git a/backend/translation/views.py b/backend/translation/views.py
index 65d41af..2fe2bcc 100644
--- a/backend/translation/views.py
+++ b/backend/translation/views.py
@@ -11,12 +11,27 @@ from pathlib import Path
 import regex as re
 import uuid
 import os
+from langdetect import detect
 
 BASE_DIR = Path(__file__).resolve().parent
 
 from rest_framework.decorators import api_view, renderer_classes, parser_classes
 from .renderers import MyXMLRenderer
 
+def filter_dummy_errors(original, error):
+
+    if '//' in error:
+        return (False, "")
+    elif error.split(" ") > 2:
+        return (False, "")
+    # Check if is not english
+    elif detect(error) != 'pl':
+        return (False, "")
+    
+    return (True, error)
+    
+    
+
 def get_context(line, start_index, end_index):
 
     start_index = start_index - 20
@@ -46,8 +61,10 @@ def diff_text(original, corrected):
             start_position = re.search('\[-([^\[]*?)\+}', line).start()
             end_position = re.search('\[-([^\[]*?)\+}', line).end()
 
-
-            output.append({'id': 'grammar-error', 'type': 'grammar', 'correction': added[0], 'context': f'{get_context(lines[idx], start_position, end_position)}', 'msg': f"Zamiana '{removed[0]}' na '{added[0]}'"})
+            is_error, error = filter_dummy_errors(removed, added)
+            
+            if is_error:
+                output.append({'id': 'grammar-error', 'type': 'grammar', 'correction': added[0], 'context': f'{get_context(lines[idx], start_position, end_position)}', 'msg': f"Zamiana '{removed[0]}' na '{added[0]}'"})
         
         removed = re.findall('\[\-(.*?)\-]', new_line)
         added = re.findall('{\+(.*?)\+}', new_line)