Implements the approved plan to replace the broken regex/index-master extraction with an LLM-subagent pipeline. Four parallel lanes: Lane A — scripts/extract_common.py (PDF/docx/doc/pptx/html/zip, no max_pages truncation), normalize_sources.py, chunk_sources.py (~20pg chunks + overlap, manifest registry), activity_schema.json. Lane B — app/config_taxonomy.py (16 fixed category slugs), schema rebuilt from scratch in app/models/ with content_type, language, source_files, source_excerpt, normalized_name, extraction_confidence, needs_review; FTS5 + 3 triggers extended with materials_list and skills_developed. Lane C — build_database.py (--rebuild, atomic swap, schema + fuzzy source_excerpt validation, dedup with needs_review band), validate_extractions.py, review_queue.py, new run_extraction.py orchestrator, SUBAGENT_PROMPT.md. Lane D — search.py content_type/language filters (default search excludes non-game content), E7 schema-compat audit; fixed a NULL keywords AttributeError in _boost_search_relevance. Removes 8 orphaned/dead scripts and app/services/parser.py + indexer.py. Adds tests/ (70 passing, 1 skipped — libreoffice absent). Note: Lane D made one additive edit to app/models/database.py (_update_category_counts) to surface content_type/language in get_filter_options, outside its nominal lane boundary but after Lane B completed. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
238 lines
8.1 KiB
Python
238 lines
8.1 KiB
Python
"""
|
|
Flask routes for INDEX-SISTEM-JOCURI v2.0
|
|
Clean, minimalist web interface with dynamic filters
|
|
"""
|
|
|
|
from flask import Blueprint, request, render_template, jsonify, current_app
|
|
from app.models.database import DatabaseManager
|
|
from app.models.activity import Activity
|
|
from app.services.search import SearchService
|
|
from app.config_taxonomy import CATEGORIES, CONTENT_TYPES
|
|
import os
|
|
from pathlib import Path
|
|
|
|
bp = Blueprint('main', __name__)
|
|
|
|
# Slug -> Romanian display name. Category and content_type slugs never collide,
|
|
# so a single flat map is enough for the UI filter labels.
|
|
LANGUAGE_NAMES = {'ro': 'Română', 'en': 'Engleză'}
|
|
DISPLAY_NAMES = {**CATEGORIES, **CONTENT_TYPES, **LANGUAGE_NAMES}
|
|
|
|
# Initialize database manager (will be configured in application factory)
|
|
def get_db_manager():
|
|
"""Get database manager instance"""
|
|
db_path = current_app.config.get('DATABASE_URL', 'sqlite:///data/activities.db')
|
|
if db_path.startswith('sqlite:///'):
|
|
db_path = db_path[10:]
|
|
return DatabaseManager(db_path)
|
|
|
|
def get_search_service():
|
|
"""Get search service instance"""
|
|
return SearchService(get_db_manager())
|
|
|
|
@bp.route('/')
|
|
def index():
|
|
"""Main search page with dynamic filters"""
|
|
try:
|
|
db = get_db_manager()
|
|
|
|
# Get dynamic filter options from database
|
|
filter_options = db.get_filter_options()
|
|
|
|
# Get database statistics for the interface
|
|
stats = db.get_statistics()
|
|
|
|
return render_template('index.html',
|
|
filters=filter_options,
|
|
display_names=DISPLAY_NAMES,
|
|
stats=stats)
|
|
|
|
except Exception as e:
|
|
print(f"Error loading main page: {e}")
|
|
# Fallback with empty filters
|
|
return render_template('index.html',
|
|
filters={},
|
|
display_names=DISPLAY_NAMES,
|
|
stats={'total_activities': 0})
|
|
|
|
@bp.route('/search', methods=['GET', 'POST'])
|
|
def search():
|
|
"""Search activities with filters"""
|
|
try:
|
|
search_service = get_search_service()
|
|
|
|
# Get search parameters
|
|
if request.method == 'POST':
|
|
search_query = request.form.get('search_query', '').strip()
|
|
filters = {k: v for k, v in request.form.items()
|
|
if k != 'search_query' and v and v.strip()}
|
|
else:
|
|
search_query = request.args.get('q', '').strip()
|
|
filters = {k: v for k, v in request.args.items()
|
|
if k != 'q' and v and v.strip()}
|
|
|
|
# Perform search
|
|
results = search_service.search_activities(
|
|
search_text=search_query if search_query else None,
|
|
filters=filters,
|
|
limit=current_app.config.get('SEARCH_RESULTS_LIMIT', 100)
|
|
)
|
|
|
|
# Convert results to Activity objects for better template handling
|
|
activities = [Activity.from_dict(result) for result in results]
|
|
|
|
# Get filter options for the form
|
|
db = get_db_manager()
|
|
filter_options = db.get_filter_options()
|
|
|
|
return render_template('results.html',
|
|
activities=activities,
|
|
search_query=search_query,
|
|
applied_filters=filters,
|
|
filters=filter_options,
|
|
display_names=DISPLAY_NAMES,
|
|
results_count=len(activities))
|
|
|
|
except Exception as e:
|
|
print(f"Search error: {e}")
|
|
return render_template('results.html',
|
|
activities=[],
|
|
search_query='',
|
|
applied_filters={},
|
|
filters={},
|
|
display_names=DISPLAY_NAMES,
|
|
results_count=0,
|
|
error=str(e))
|
|
|
|
@bp.route('/activity/<int:activity_id>')
|
|
def activity_detail(activity_id):
|
|
"""Show detailed activity information"""
|
|
try:
|
|
db = get_db_manager()
|
|
|
|
# Get activity
|
|
activity_data = db.get_activity_by_id(activity_id)
|
|
if not activity_data:
|
|
return render_template('404.html'), 404
|
|
|
|
activity = Activity.from_dict(activity_data)
|
|
|
|
# Get similar activities (same category)
|
|
similar_results = db.search_activities(
|
|
category=activity.category,
|
|
limit=5
|
|
)
|
|
|
|
# Filter out current activity and convert to Activity objects
|
|
similar_activities = [
|
|
Activity.from_dict(result) for result in similar_results
|
|
if result['id'] != activity_id
|
|
][:3] # Limit to 3 recommendations
|
|
|
|
return render_template('activity.html',
|
|
activity=activity,
|
|
display_names=DISPLAY_NAMES,
|
|
similar_activities=similar_activities)
|
|
|
|
except Exception as e:
|
|
print(f"Error loading activity {activity_id}: {e}")
|
|
return render_template('404.html'), 404
|
|
|
|
@bp.route('/health')
|
|
def health_check():
|
|
"""Health check endpoint for Docker"""
|
|
try:
|
|
db = get_db_manager()
|
|
stats = db.get_statistics()
|
|
|
|
return jsonify({
|
|
'status': 'healthy',
|
|
'database': 'connected',
|
|
'activities_count': stats.get('total_activities', 0),
|
|
'timestamp': stats.get('timestamp', 'unknown')
|
|
})
|
|
|
|
except Exception as e:
|
|
return jsonify({
|
|
'status': 'unhealthy',
|
|
'error': str(e)
|
|
}), 500
|
|
|
|
@bp.route('/api/statistics')
|
|
def api_statistics():
|
|
"""API endpoint for database statistics"""
|
|
try:
|
|
db = get_db_manager()
|
|
stats = db.get_statistics()
|
|
return jsonify(stats)
|
|
|
|
except Exception as e:
|
|
return jsonify({'error': str(e)}), 500
|
|
|
|
@bp.route('/api/filters')
|
|
def api_filters():
|
|
"""API endpoint for dynamic filter options"""
|
|
try:
|
|
db = get_db_manager()
|
|
filters = db.get_filter_options()
|
|
return jsonify(filters)
|
|
|
|
except Exception as e:
|
|
return jsonify({'error': str(e)}), 500
|
|
|
|
@bp.route('/api/search')
|
|
def api_search():
|
|
"""JSON API for search (for AJAX requests)"""
|
|
try:
|
|
search_service = get_search_service()
|
|
|
|
# Get search parameters from query string
|
|
search_query = request.args.get('q', '').strip()
|
|
filters = {k: v for k, v in request.args.items()
|
|
if k not in ['q', 'limit', 'format'] and v and v.strip()}
|
|
|
|
limit = min(int(request.args.get('limit', 50)), 100) # Max 100 results
|
|
|
|
# Perform search
|
|
results = search_service.search_activities(
|
|
search_text=search_query if search_query else None,
|
|
filters=filters,
|
|
limit=limit
|
|
)
|
|
|
|
# Format results for JSON response
|
|
formatted_results = []
|
|
for result in results:
|
|
activity = Activity.from_dict(result)
|
|
formatted_results.append({
|
|
'id': activity.id,
|
|
'name': activity.name,
|
|
'description': activity.description[:200] + '...' if len(activity.description) > 200 else activity.description,
|
|
'category': activity.category,
|
|
'age_range': activity.get_age_range_display(),
|
|
'participants': activity.get_participants_display(),
|
|
'duration': activity.get_duration_display(),
|
|
'materials': activity.get_materials_display(),
|
|
'source_file': activity.source_file,
|
|
'url': f'/activity/{activity.id}'
|
|
})
|
|
|
|
return jsonify({
|
|
'results': formatted_results,
|
|
'count': len(formatted_results),
|
|
'query': search_query,
|
|
'filters': filters
|
|
})
|
|
|
|
except Exception as e:
|
|
return jsonify({'error': str(e)}), 500
|
|
|
|
@bp.errorhandler(404)
|
|
def not_found(error):
|
|
"""404 error handler"""
|
|
return render_template('404.html'), 404
|
|
|
|
@bp.errorhandler(500)
|
|
def internal_error(error):
|
|
"""500 error handler"""
|
|
return render_template('500.html'), 500 |