From 58e5d1b83d8162be287c8756b70612a34436cd32 Mon Sep 17 00:00:00 2001
From: ske087 <ske087@site-host.homeserver>
Date: Thu, 24 Jul 2025 19:06:21 +0300
Subject: [PATCH] feat: Improve adventure story text parsing and keyword
 extraction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Text Processing Improvements:
- Better separation of keywords from actual story text
- Extract standalone keywords before <br><br> patterns
- Remove keywords from main text display to show only story content
- Handle both **keyword** patterns and standalone keyword lines
- Clean up multiple <br> tags for better formatting

User Experience:
- Keywords now display as tags above story sections
- Story text shows only the narrative content without keyword clutter
- Example: 'Transalpina Ciungetu Stana lui stefan <br><br> Așa am pornit...'
  now shows keywords as tags and only 'Așa am pornit...' as story text
- Better visual separation between metadata and story content

Technical:
- Improved Jinja2 template logic for text parsing
- Added text length and word count heuristics for keyword detection
- Enhanced text cleaning and formatting
- Fixed template syntax errors from previous edits
---
 app/templates/community/post_detail.html | 46 +++++++++++++++++++-----
 1 file changed, 37 insertions(+), 9 deletions(-)

diff --git a/app/templates/community/post_detail.html b/app/templates/community/post_detail.html
index a29ecab..c65a3e7 100644
--- a/app/templates/community/post_detail.html
+++ b/app/templates/community/post_detail.html
@@ -108,33 +108,61 @@
                                     <div class="mb-8 pb-6 {% if not loop.last %}border-b border-gray-200{% endif %}">
                                         {% set section_text = section.strip() %}
                                         
-                                        <!-- Extract keywords from **bold** text -->
+                                        <!-- Extract keywords and clean text -->
                                         {% set keywords = [] %}
                                         {% set clean_text = section_text %}
                                         
-                                        <!-- Simple keyword extraction for **word** patterns -->
+                                        <!-- Process **keyword** patterns and standalone keywords -->
                                         {% if '**' in section_text %}
                                             {% set parts = section_text.split('**') %}
                                             {% set clean_parts = [] %}
                                             {% for i in range(parts|length) %}
                                                 {% if i % 2 == 1 %}
-                                                    {% set _ = keywords.append(parts[i]) %}
-                                                    {% set _ = clean_parts.append(parts[i]) %}
+                                                    <!-- This is a keyword between ** ** -->
+                                                    {% set _ = keywords.append(parts[i].strip()) %}
                                                 {% else %}
+                                                    <!-- This is regular text -->
                                                     {% set _ = clean_parts.append(parts[i]) %}
                                                 {% endif %}
                                             {% endfor %}
-                                            {% set clean_text = clean_parts|join('') %}
+                                            {% set clean_text = clean_parts|join(' ')|trim %}
                                         {% endif %}
                                         
+                                        <!-- Also extract standalone keywords (before <br><br>) -->
+                                        {% if '<br>' in clean_text %}
+                                            {% set text_parts = clean_text.split('<br>') %}
+                                            {% set first_part = text_parts[0].strip() %}
+                                            
+                                            <!-- If first part looks like keywords (short words), extract them -->
+                                            {% if first_part and first_part|length < 100 and ' ' in first_part %}
+                                                {% set potential_keywords = first_part.split() %}
+                                                {% if potential_keywords|length <= 5 %}
+                                                    <!-- Likely keywords, add them and remove from text -->
+                                                    {% for kw in potential_keywords %}
+                                                        {% if kw.strip() %}
+                                                            {% set _ = keywords.append(kw.strip()) %}
+                                                        {% endif %}
+                                                    {% endfor %}
+                                                    <!-- Keep only text after the first <br><br> -->
+                                                    {% set remaining_parts = text_parts[1:] %}
+                                                    {% set clean_text = remaining_parts|join('<br>')|trim %}
+                                                {% endif %}
+                                            {% endif %}
+                                        {% endif %}
+                                        
+                                        <!-- Clean up multiple <br> tags -->
+                                        {% set clean_text = clean_text.replace('<br><br><br>', '<br><br>').replace('<br> <br>', '<br><br>').strip() %}
+                                        
                                         <!-- Section Keywords -->
                                         {% if keywords %}
                                             <div class="mb-4">
                                                 {% for keyword in keywords %}
-                                                    <span class="inline-flex items-center px-3 py-1 rounded-full text-sm font-medium bg-gradient-to-r from-amber-500 to-orange-500 text-white mr-2 mb-2">
-                                                        <i class="fas fa-tag mr-1 text-xs"></i>
-                                                        {{ keyword }}
-                                                    </span>
+                                                    {% if keyword.strip() %}
+                                                        <span class="inline-flex items-center px-3 py-1 rounded-full text-sm font-medium bg-gradient-to-r from-amber-500 to-orange-500 text-white mr-2 mb-2">
+                                                            <i class="fas fa-tag mr-1 text-xs"></i>
+                                                            {{ keyword.strip() }}
+                                                        </span>
+                                                    {% endif %}
                                                 {% endfor %}
                                             </div>
                                         {% endif %}