From 9033ec60ca21d43c1a7ed13785c4e864d8e47b77 Mon Sep 17 00:00:00 2001
From: queukat <queukat@gmail.com>
Date: Sat, 23 Nov 2024 18:30:59 +0300
Subject: [PATCH] fix

---
 answer_editor.py   | 16 +++++++++++++---
 cleanse_answers.py | 29 +++++++++++------------------
 2 files changed, 24 insertions(+), 21 deletions(-)

diff --git a/answer_editor.py b/answer_editor.py
index aa8ff2633..cedf30cb1 100644
--- a/answer_editor.py
+++ b/answer_editor.py
@@ -3,6 +3,7 @@
 import os
 from pathlib import Path
 from flask_bootstrap import Bootstrap
+from src.ai_hawk.linkedIn_easy_applier import AIHawkEasyApplier
 
 app = Flask(__name__)
 Bootstrap(app)
@@ -26,6 +27,15 @@ def index():
 
         return render_template('index.html', data=data if isinstance(data, list) else [])
 
+easy_applier = AIHawkEasyApplier(
+    driver=None,
+    resume_dir=None,
+    set_old_answers=[],
+    gpt_answerer=None,
+    resume_generator_manager=None,
+    job_application_profile=None
+)
+
 def update():
     if not JSON_FILE.exists():
         data = []
@@ -37,9 +47,9 @@ def update():
     for i, item in enumerate(data):
         if f'delete_{i}' not in request.form:
             if item['type'] == 'radio':
-                item['answer'] = request.form.get(f'answer_{i}_radio', item['answer'])
+                item['answer'] = easy_applier._sanitize_text(request.form.get(f'answer_{i}_radio', item['answer']))
             else:
-                item['answer'] = request.form.get(f'answer_{i}', item['answer'])
+                item['answer'] = easy_applier._sanitize_text(request.form.get(f'answer_{i}', item['answer']))
             updated_data.append(item)
 
     # Sort updated data alphabetically by question
@@ -51,4 +61,4 @@ def update():
     return redirect(url_for('index'))
 
 if __name__ == '__main__':
-    app.run(debug=True)
\ No newline at end of file
+    app.run(debug=True)
diff --git a/cleanse_answers.py b/cleanse_answers.py
index 22f3ee131..b4dee071a 100644
--- a/cleanse_answers.py
+++ b/cleanse_answers.py
@@ -1,23 +1,16 @@
 import json
 import re
 
-def sanitize_text(text: str) -> str:
-    # Remove duplicates by splitting and rejoining
-    text = text.rstrip()
-    text = re.sub(r'\s+', ' ', text)
-    text = text.replace('?', '').replace('"', '').replace('\\', '')
-    words = text.lower().split()
-    unique_words = []
-    for word in words:
-        if word not in unique_words:
-            unique_words.append(word)
-    text = ' '.join(unique_words)
-    
-    # Remove common suffixes
-    text = re.sub(r'\s*\(?required\)?', '', text, flags=re.IGNORECASE)
-    text = re.sub(r'(\s*\(?yes\/no\)?|\s*\(?yes\)?|\s*\(?no\)?|\?)$', '', text, flags=re.IGNORECASE)
-    sanitized_text = re.sub(r'[^[:ascii:]]','', text)
-    return sanitized_text
+from src.ai_hawk.linkedIn_easy_applier import AIHawkEasyApplier
+
+easy_applier = AIHawkEasyApplier(
+    driver=None,
+    resume_dir=None,
+    set_old_answers=[],
+    gpt_answerer=None,
+    resume_generator_manager=None,
+    job_application_profile=None
+)
 
 def cleanse_answers_json(input_file: str, output_file: str):
     with open(input_file, 'r') as f:
@@ -27,7 +20,7 @@ def cleanse_answers_json(input_file: str, output_file: str):
     seen_questions = set()
 
     for item in data:
-        sanitized_question = sanitize_text(item['question'])
+        sanitized_question = easy_applier._sanitize_text(item['question'])
         if sanitized_question not in seen_questions:
             seen_questions.add(sanitized_question)
             cleansed_item = {