cim_summary/backend/check-analysis-data.js

const { Pool } = require('pg');
const path = require('path');

// Load environment variables from the testing environment
require('dotenv').config({ path: path.join(__dirname, '.env') });

console.log('🔧 Environment check:');
console.log('   DATABASE_URL:', process.env.DATABASE_URL ? 'Set' : 'Not set');
console.log('   NODE_ENV:', process.env.NODE_ENV || 'Not set');
console.log('');

const pool = new Pool({
  connectionString: process.env.DATABASE_URL,
  ssl: process.env.NODE_ENV === 'production' ? { rejectUnauthorized: false } : false
});

// Test connection
pool.on('error', (err) => {
  console.error('❌ Database connection error:', err);
});

async function checkAnalysisData() {
  try {
    console.log('🔍 Checking analysis data in database...\n');
    
    // Check recent documents with analysis_data
    const result = await pool.query(`
      SELECT 
        id,
        original_file_name,
        status,
        analysis_data,
        processing_completed_at,
        created_at
      FROM documents 
      WHERE analysis_data IS NOT NULL 
      ORDER BY created_at DESC 
      LIMIT 5
    `);
    
    console.log(`📊 Found ${result.rows.length} documents with analysis_data:\n`);
    
    result.rows.forEach((row, index) => {
      console.log(`📄 Document ${index + 1}:`);
      console.log(`   ID: ${row.id}`);
      console.log(`   Name: ${row.original_file_name}`);
      console.log(`   Status: ${row.status}`);
      console.log(`   Created: ${row.created_at}`);
      console.log(`   Completed: ${row.processing_completed_at}`);
      
      if (row.analysis_data) {
        console.log(`   Analysis Data Keys: ${Object.keys(row.analysis_data).join(', ')}`);
        
        // Check if the data has the expected structure
        const expectedSections = [
          'dealOverview',
          'businessDescription', 
          'marketIndustryAnalysis',
          'financialSummary',
          'managementTeamOverview',
          'preliminaryInvestmentThesis',
          'keyQuestionsNextSteps'
        ];
        
        const missingSections = expectedSections.filter(section => !row.analysis_data[section]);
        const presentSections = expectedSections.filter(section => row.analysis_data[section]);
        
        console.log(`   ✅ Present Sections: ${presentSections.join(', ')}`);
        if (missingSections.length > 0) {
          console.log(`   ❌ Missing Sections: ${missingSections.join(', ')}`);
        }
        
        // Check if sections have actual data (not just empty objects)
        const emptySections = presentSections.filter(section => {
          const sectionData = row.analysis_data[section];
          return !sectionData || Object.keys(sectionData).length === 0 || 
                 (typeof sectionData === 'object' && Object.values(sectionData).every(val => 
                   !val || val === '' || val === 'N/A' || val === 'Not specified in CIM'
                 ));
        });
        
        if (emptySections.length > 0) {
          console.log(`   ⚠️  Empty Sections: ${emptySections.join(', ')}`);
        }
        
        // Show a sample of the data
        if (row.analysis_data.dealOverview) {
          console.log(`   📋 Sample - Deal Overview:`);
          console.log(`      Target Company: ${row.analysis_data.dealOverview.targetCompanyName || 'N/A'}`);
          console.log(`      Industry: ${row.analysis_data.dealOverview.industrySector || 'N/A'}`);
        }
        
      } else {
        console.log(`   ❌ No analysis_data found`);
      }
      
      console.log('');
    });
    
    // Check documents without analysis_data
    const noAnalysisResult = await pool.query(`
      SELECT 
        id,
        original_file_name,
        status,
        processing_completed_at,
        created_at
      FROM documents 
      WHERE analysis_data IS NULL 
      AND status = 'completed'
      ORDER BY created_at DESC 
      LIMIT 3
    `);
    
    if (noAnalysisResult.rows.length > 0) {
      console.log(`⚠️  Found ${noAnalysisResult.rows.length} completed documents WITHOUT analysis_data:\n`);
      noAnalysisResult.rows.forEach((row, index) => {
        console.log(`   ${index + 1}. ${row.original_file_name} (${row.status}) - ${row.created_at}`);
      });
      console.log('');
    }
    
    // Check total document counts
    const totalResult = await pool.query(`
      SELECT 
        COUNT(*) as total_documents,
        COUNT(CASE WHEN analysis_data IS NOT NULL THEN 1 END) as with_analysis,
        COUNT(CASE WHEN analysis_data IS NULL THEN 1 END) as without_analysis,
        COUNT(CASE WHEN status = 'completed' THEN 1 END) as completed,
        COUNT(CASE WHEN status = 'failed' THEN 1 END) as failed
      FROM documents
    `);
    
    const stats = totalResult.rows[0];
    console.log(`📈 Database Statistics:`);
    console.log(`   Total Documents: ${stats.total_documents}`);
    console.log(`   With Analysis Data: ${stats.with_analysis}`);
    console.log(`   Without Analysis Data: ${stats.without_analysis}`);
    console.log(`   Completed: ${stats.completed}`);
    console.log(`   Failed: ${stats.failed}`);
    
  } catch (error) {
    console.error('❌ Error checking analysis data:', error);
  } finally {
    await pool.end();
  }
}

checkAnalysisData();