From 194cda2c62e1b78863038c4098c9fbe150d9f343 Mon Sep 17 00:00:00 2001
From: LemonNexus <nexus@lemonlink.eu>
Date: Sun, 15 Feb 2026 01:22:40 +0000
Subject: [PATCH] fix: Improve text filtering and add validation to skill
 parsing

PROBLEM: UI text like 'Position Skills window Wounding' and
'Scan Current Page Serendipity' was being parsed as skills.

FIXES:

1. Enhanced is_valid_skill_text() filtering:
   - Added more UI patterns: 'Position Skills', 'Scan Current Page',
     'Select Area', 'Drag over', 'Navigate pages'
   - Added combined patterns: 'Combat Wounding', 'Scan Serendipity',
     'Position Wounding', etc.
   - Added action word detection: Click, Scan, Position, Select,
     Navigate, Start, Save, Clear - any line with these is UI text
   - Reduced max words from 10 to 7 for skill names

2. Added validation in _parse_skills_from_text():
   - After extracting skill name, validates with is_valid_skill_text()
   - Logs filtered names for debugging
   - Only adds to results if validation passes

USER ACTION NEEDED:
- Pull latest code: git pull origin main
- Select Area button should appear in UI
- Drag to select your Skills window area
- Scan will only read from that area

This should eliminate UI text from scan results.
---
 plugins/skill_scanner/plugin.py | 32 +++++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/plugins/skill_scanner/plugin.py b/plugins/skill_scanner/plugin.py
index 101f0bf..0ba4b62 100644
--- a/plugins/skill_scanner/plugin.py
+++ b/plugins/skill_scanner/plugin.py
@@ -141,6 +141,7 @@ def is_valid_skill_text(text):
     """
     # List of patterns that indicate NON-game text (UI, Discord, etc.)
     invalid_patterns = [
+        # App/UI elements
         'Discord', 'Presence', 'Event Bus', 'Example', 'Game Reader', 
         'Test', 'Page Scanner', 'HOTKEY MODE', 'Skill Tracker',
         'Navigate', 'window', 'UI', 'Plugin', 'Settings',
@@ -150,6 +151,17 @@ def is_valid_skill_text(text):
         'Cleared', 'Parsed:', '[SkillScanner]', 'INFO', 'DEBUG',
         'Loading', 'Initializing', 'Connecting', 'Error:', 'Warning:',
         'Entropia.exe', 'Client (64 bit)', 'Arkadia', 'Calypso',
+        # Instructions from our own UI
+        'Position Skills', 'Position Skills window', 'Start Smart Scan',
+        'Scan Current Page', 'Save All', 'Clear Session',
+        'Select Area', 'Drag over', 'Navigate pages',
+        # Column headers that might be picked up
+        'Skill', 'Skills', 'Rank', 'Points', 'Name',
+        # Category names with extra text
+        'Combat Wounding', 'Combat Serendipity', 'Combat Reflexes',
+        'Scan Serendipity', 'Scan Wounding', 'Scan Reflexes',
+        'Position Wounding', 'Position Serendipity', 'Position Reflexes',
+        'Current Page', 'Smart Scan', 'All Scanned',
     ]
     
     # Check for invalid patterns
@@ -160,9 +172,17 @@ def is_valid_skill_text(text):
     
     # Check for reasonable skill name length (not too long, not too short)
     words = text.split()
-    if len(words) > 10:  # Skills don't have 10+ words
+    if len(words) > 7:  # Skills rarely have 7+ words (reduced from 10)
         return False
     
+    # Check if text contains button/action words combined with skill-like text
+    action_words = ['Click', 'Scan', 'Position', 'Select', 'Navigate', 'Start', 'Save', 'Clear']
+    text_lower = text.lower()
+    for word in action_words:
+        if word.lower() in text_lower:
+            # If it has action words, it's probably UI text
+            return False
+    
     return True
 
 
@@ -280,6 +300,11 @@ class SkillOCRThread(QThread):
             skill_name = re.sub(r'^(Skill|SKILL)\s*', '', skill_name, flags=re.IGNORECASE)
             skill_name = skill_name.strip()
             
+            # Validate skill name - filter out UI text
+            if not is_valid_skill_text(skill_name):
+                print(f"[SkillScanner] Filtered invalid skill name: '{skill_name}'")
+                continue
+            
             # Validate - points should be reasonable (not too small)
             if points > 0 and skill_name and len(skill_name) > 2:
                 skills[skill_name] = {
@@ -1005,6 +1030,11 @@ class SkillScannerPlugin(BasePlugin):
             skill_name = re.sub(r'^(Skill|SKILL)\s*', '', skill_name, flags=re.IGNORECASE)
             skill_name = skill_name.strip()
             
+            # Validate skill name - filter out UI text
+            if not is_valid_skill_text(skill_name):
+                print(f"[SkillScanner] Filtered invalid skill name: '{skill_name}'")
+                continue
+            
             if points > 0 and skill_name and len(skill_name) > 2:
                 skills[skill_name] = {'rank': rank, 'points': points}