einvoice/test/suite/einvoice_format-detection/test.fd-08.performance.ts

import { expect, tap } from '@git.zone/tstest/tapbundle';
import { promises as fs } from 'fs';
import * as path from 'path';
import { CorpusLoader } from '../../helpers/corpus.loader.js';
import { PerformanceTracker } from '../../helpers/performance.tracker.js';

tap.test('FD-08: Format Detection Performance - should meet performance thresholds', async () => {
  const { FormatDetector } = await import('../../../ts/formats/utils/format.detector.js');

  // Test with different sizes of XML content
  const performanceTests = [
    {
      name: 'Minimal UBL',
      xml: `<?xml version="1.0"?><Invoice xmlns="urn:oasis:names:specification:ubl:schema:xsd:Invoice-2"><ID>123</ID></Invoice>`,
      threshold: 1 // ms
    },
    {
      name: 'Small CII',
      xml: `<?xml version="1.0"?>
<rsm:CrossIndustryInvoice xmlns:rsm="urn:un:unece:uncefact:data:standard:CrossIndustryInvoice:100">
  <rsm:ExchangedDocument>
    <ram:ID xmlns:ram="urn:un:unece:uncefact:data:standard:ReusableAggregateBusinessInformationEntity:100">TEST-001</ram:ID>
  </rsm:ExchangedDocument>
</rsm:CrossIndustryInvoice>`,
      threshold: 2 // ms
    }
  ];

  for (const test of performanceTests) {
    console.log(`\nTesting ${test.name} (${test.xml.length} bytes)`);
    
    const times: number[] = [];
    let detectedFormat = '';

    // Run multiple iterations for accurate measurement
    for (let i = 0; i < 100; i++) {
      const { result: format, metric } = await PerformanceTracker.track(
        'performance-detection',
        async () => FormatDetector.detectFormat(test.xml)
      );
      
      times.push(metric.duration);
      detectedFormat = format.toString();
    }

    const avgTime = times.reduce((a, b) => a + b, 0) / times.length;
    const minTime = Math.min(...times);
    const maxTime = Math.max(...times);
    const p95Time = times.sort((a, b) => a - b)[Math.floor(times.length * 0.95)];

    console.log(`  Format: ${detectedFormat}`);
    console.log(`  Average: ${avgTime.toFixed(3)}ms`);
    console.log(`  Min: ${minTime.toFixed(3)}ms`);
    console.log(`  Max: ${maxTime.toFixed(3)}ms`);
    console.log(`  P95: ${p95Time.toFixed(3)}ms`);

    // Performance assertions
    expect(avgTime).toBeLessThan(test.threshold);
    expect(p95Time).toBeLessThan(test.threshold * 2);
  }
});

tap.test('FD-08: Real File Performance - should perform well on real corpus files', async () => {
  const { FormatDetector } = await import('../../../ts/formats/utils/format.detector.js');

  // Get sample files from different categories
  const testCategories = [
    { name: 'CII XML-Rechnung', category: 'CII_XMLRECHNUNG' as const },
    { name: 'UBL XML-Rechnung', category: 'UBL_XMLRECHNUNG' as const },
    { name: 'EN16931 CII', category: 'EN16931_CII' as const }
  ];

  for (const testCategory of testCategories) {
    try {
      const files = await CorpusLoader.getFiles(testCategory.category);
      if (files.length === 0) {
        console.log(`No files found in ${testCategory.name}, skipping`);
        continue;
      }

      // Test first 3 files from category
      const testFiles = files.slice(0, 3);
      console.log(`\nTesting ${testCategory.name} (${testFiles.length} files)`);

      let totalTime = 0;
      let totalSize = 0;
      let fileCount = 0;

      for (const filePath of testFiles) {
        try {
          const xmlContent = await fs.readFile(filePath, 'utf-8');
          const fileSize = xmlContent.length;

          const { result: format, metric } = await PerformanceTracker.track(
            'real-file-performance',
            async () => FormatDetector.detectFormat(xmlContent)
          );

          totalTime += metric.duration;
          totalSize += fileSize;
          fileCount++;

          console.log(`  ${path.basename(filePath)}: ${format} (${metric.duration.toFixed(2)}ms, ${Math.round(fileSize/1024)}KB)`);

        } catch (error) {
          console.log(`  ${path.basename(filePath)}: Error - ${error.message}`);
        }
      }

      if (fileCount > 0) {
        const avgTime = totalTime / fileCount;
        const avgSize = totalSize / fileCount;
        const throughput = avgSize / avgTime; // bytes per ms

        console.log(`  Category average: ${avgTime.toFixed(2)}ms per file (${Math.round(avgSize/1024)}KB avg)`);
        console.log(`  Throughput: ${Math.round(throughput * 1000 / 1024)} KB/s`);

        // Performance expectations
        expect(avgTime).toBeLessThan(20); // Average under 20ms
      }

    } catch (error) {
      console.log(`Error testing ${testCategory.name}: ${error.message}`);
    }
  }
});

tap.test('FD-08: Concurrent Detection Performance - should handle concurrent operations', async () => {
  const { FormatDetector } = await import('../../../ts/formats/utils/format.detector.js');

  // Create test XMLs of different formats
  const testXmls = [
    {
      name: 'UBL',
      xml: `<?xml version="1.0"?><Invoice xmlns="urn:oasis:names:specification:ubl:schema:xsd:Invoice-2"><ID>UBL-001</ID></Invoice>`
    },
    {
      name: 'CII',
      xml: `<?xml version="1.0"?><rsm:CrossIndustryInvoice xmlns:rsm="urn:un:unece:uncefact:data:standard:CrossIndustryInvoice:100"><rsm:ExchangedDocument/></rsm:CrossIndustryInvoice>`
    },
    {
      name: 'XRechnung',
      xml: `<?xml version="1.0"?><Invoice xmlns="urn:oasis:names:specification:ubl:schema:xsd:Invoice-2"><cbc:CustomizationID xmlns:cbc="urn:oasis:names:specification:ubl:schema:xsd:CommonBasicComponents-2">urn:cen.eu:en16931:2017#compliant#urn:xoev-de:kosit:standard:xrechnung_3.0</cbc:CustomizationID></Invoice>`
    }
  ];

  const concurrencyLevels = [1, 5, 10, 20];

  for (const concurrency of concurrencyLevels) {
    console.log(`\nTesting with ${concurrency} concurrent operations`);

    // Create tasks for concurrent execution
    const tasks = [];
    for (let i = 0; i < concurrency; i++) {
      const testXml = testXmls[i % testXmls.length];
      tasks.push(async () => {
        return await PerformanceTracker.track(
          `concurrent-detection-${concurrency}`,
          async () => FormatDetector.detectFormat(testXml.xml)
        );
      });
    }

    // Execute all tasks concurrently
    const startTime = performance.now();
    const results = await Promise.all(tasks.map(task => task()));
    const totalTime = performance.now() - startTime;

    // Analyze results
    const durations = results.map(r => r.metric.duration);
    const avgTime = durations.reduce((a, b) => a + b, 0) / durations.length;
    const maxTime = Math.max(...durations);
    const throughput = (concurrency / totalTime) * 1000; // operations per second

    console.log(`  Total time: ${totalTime.toFixed(2)}ms`);
    console.log(`  Average per operation: ${avgTime.toFixed(2)}ms`);
    console.log(`  Max time: ${maxTime.toFixed(2)}ms`);
    console.log(`  Throughput: ${throughput.toFixed(1)} ops/sec`);

    // Performance expectations
    expect(avgTime).toBeLessThan(5); // Individual operations should stay fast
    expect(maxTime).toBeLessThan(20); // No operation should be extremely slow
    expect(throughput).toBeGreaterThan(10); // Should handle at least 10 ops/sec
  }
});

tap.test('FD-08: Memory Usage - should not consume excessive memory', async () => {
  const { FormatDetector } = await import('../../../ts/formats/utils/format.detector.js');

  // Generate increasingly large XML documents
  function generateLargeXML(sizeKB: number): string {
    const targetSize = sizeKB * 1024;
    let xml = `<?xml version="1.0"?><Invoice xmlns="urn:oasis:names:specification:ubl:schema:xsd:Invoice-2">`;
    
    const itemTemplate = `<Item><ID>ITEM-{ID}</ID><Name>Product {ID}</Name><Description>Long description for product {ID} with lots of text to increase file size</Description></Item>`;
    let currentSize = xml.length;
    let itemId = 1;

    while (currentSize < targetSize) {
      const item = itemTemplate.replace(/{ID}/g, itemId.toString());
      xml += item;
      currentSize += item.length;
      itemId++;
    }

    xml += '</Invoice>';
    return xml;
  }

  const testSizes = [1, 10, 50, 100]; // KB

  for (const sizeKB of testSizes) {
    const xml = generateLargeXML(sizeKB);
    const actualSizeKB = Math.round(xml.length / 1024);
    
    console.log(`\nTesting ${actualSizeKB}KB XML document`);

    // Measure memory before
    const memBefore = process.memoryUsage();
    
    // Force garbage collection if available
    if (global.gc) {
      global.gc();
    }

    const { result: format, metric } = await PerformanceTracker.track(
      'memory-usage-test',
      async () => FormatDetector.detectFormat(xml)
    );

    // Measure memory after
    const memAfter = process.memoryUsage();
    
    const heapIncrease = (memAfter.heapUsed - memBefore.heapUsed) / 1024 / 1024; // MB
    const heapTotal = memAfter.heapTotal / 1024 / 1024; // MB

    console.log(`  Format: ${format}`);
    console.log(`  Detection time: ${metric.duration.toFixed(2)}ms`);
    console.log(`  Heap increase: ${heapIncrease.toFixed(2)}MB`);
    console.log(`  Total heap: ${heapTotal.toFixed(2)}MB`);

    // Memory expectations
    expect(heapIncrease).toBeLessThan(actualSizeKB * 0.1); // Should not use more than 10% of file size in heap
    expect(metric.duration).toBeLessThan(actualSizeKB * 2); // Should not be slower than 2ms per KB
  }
});

tap.test('FD-08: Performance Summary Report', async () => {
  // Generate comprehensive performance report
  const perfSummary = await PerformanceTracker.getSummary('performance-detection');
  if (perfSummary) {
    console.log(`\nFormat Detection Performance Summary:`);
    console.log(`  Average: ${perfSummary.average.toFixed(3)}ms`);
    console.log(`  Min: ${perfSummary.min.toFixed(3)}ms`);
    console.log(`  Max: ${perfSummary.max.toFixed(3)}ms`);
    console.log(`  P95: ${perfSummary.p95.toFixed(3)}ms`);
    
    // Overall performance expectations
    expect(perfSummary.average).toBeLessThan(5);
    expect(perfSummary.p95).toBeLessThan(10);
  }

  const realFileSummary = await PerformanceTracker.getSummary('real-file-performance');
  if (realFileSummary) {
    console.log(`\nReal File Performance Summary:`);
    console.log(`  Average: ${realFileSummary.average.toFixed(2)}ms`);
    console.log(`  Min: ${realFileSummary.min.toFixed(2)}ms`);
    console.log(`  Max: ${realFileSummary.max.toFixed(2)}ms`);
    console.log(`  P95: ${realFileSummary.p95.toFixed(2)}ms`);
  }
});

tap.start();