einvoice/test/suite/einvoice_pdf-operations/test.pdf-02.zugferd-v1-extraction.ts

import { tap, expect } from '@git.zone/tstest/tapbundle';
import * as plugins from '../../../ts/plugins.ts';
import { EInvoice } from '../../../ts/classes.xinvoice.ts';
import { CorpusLoader } from '../../helpers/corpus.loader.ts';
import { PerformanceTracker } from '../../helpers/performance.tracker.ts';

const testTimeout = 300000; // 5 minutes timeout for PDF processing

// PDF-02: ZUGFeRD v1 Extraction
// Tests XML extraction from ZUGFeRD v1 PDFs with specific format validation
// and compatibility checks for legacy ZUGFeRD implementations

tap.test('PDF-02: ZUGFeRD v1 Extraction - Basic Extraction', async (tools) => {
  const startTime = Date.now();
  
  // Test basic ZUGFeRD v1 extraction functionality
  try {
    const zugferdV1Files = await CorpusLoader.getFiles('ZUGFERD_V1');
    
    if (zugferdV1Files.length === 0) {
      tools.log('⚠ No ZUGFeRD v1 files found in corpus, skipping basic extraction test');
      return;
    }
    
    const testFile = zugferdV1Files[0];
    tools.log(`Testing ZUGFeRD v1 extraction with: ${plugins.path.basename(testFile)}`);
    
    const invoice = new EInvoice();
    
    // Check if file exists and is readable
    const fileExists = await plugins.fs.pathExists(testFile);
    expect(fileExists).toBeTrue();
    
    const fileStats = await plugins.fs.stat(testFile);
    tools.log(`File size: ${(fileStats.size / 1024).toFixed(1)}KB`);
    
    // Attempt PDF extraction
    let extractionResult;
    try {
      extractionResult = await invoice.fromFile(testFile);
      
      if (extractionResult) {
        tools.log('✓ ZUGFeRD v1 XML extraction successful');
        
        // Verify extracted content contains ZUGFeRD v1 characteristics
        const extractedXml = await invoice.toXmlString();
        expect(extractedXml).toBeTruthy();
        expect(extractedXml.length).toBeGreaterThan(100);
        
        // Check for ZUGFeRD v1 namespace or characteristics
        const hasZugferdV1Markers = extractedXml.includes('urn:ferd:CrossIndustryDocument:invoice:1p0') ||
                                   extractedXml.includes('ZUGFeRD') ||
                                   extractedXml.includes('FERD');
        
        if (hasZugferdV1Markers) {
          tools.log('✓ ZUGFeRD v1 format markers detected in extracted XML');
        } else {
          tools.log('⚠ ZUGFeRD v1 format markers not clearly detected');
        }
        
        // Test basic validation of extracted content
        try {
          const validationResult = await invoice.validate();
          if (validationResult.valid) {
            tools.log('✓ Extracted ZUGFeRD v1 content passes validation');
          } else {
            tools.log(`⚠ Validation issues found: ${validationResult.errors?.length || 0} errors`);
          }
        } catch (validationError) {
          tools.log(`⚠ Validation failed: ${validationError.message}`);
        }
        
      } else {
        tools.log('⚠ ZUGFeRD v1 extraction returned no result');
      }
      
    } catch (extractionError) {
      tools.log(`⚠ ZUGFeRD v1 extraction failed: ${extractionError.message}`);
      // This might be expected if PDF extraction is not fully implemented
    }
    
  } catch (error) {
    tools.log(`ZUGFeRD v1 basic extraction test failed: ${error.message}`);
  }
  
  const duration = Date.now() - startTime;
  PerformanceTracker.recordMetric('pdf-zugferd-v1-basic-extraction', duration);
});

tap.test('PDF-02: ZUGFeRD v1 Extraction - Corpus Processing', { timeout: testTimeout }, async (tools) => {
  const startTime = Date.now();
  
  let processedFiles = 0;
  let successfulExtractions = 0;
  let extractionErrors = 0;
  let totalExtractionTime = 0;
  
  try {
    const zugferdV1Files = await CorpusLoader.getFiles('ZUGFERD_V1');
    tools.log(`Processing ${zugferdV1Files.length} ZUGFeRD v1 files`);
    
    if (zugferdV1Files.length === 0) {
      tools.log('⚠ No ZUGFeRD v1 files found in corpus');
      return;
    }
    
    for (const filePath of zugferdV1Files) {
      const fileName = plugins.path.basename(filePath);
      const fileExtractionStart = Date.now();
      
      try {
        processedFiles++;
        
        // Check file accessibility
        const fileExists = await plugins.fs.pathExists(filePath);
        if (!fileExists) {
          tools.log(`⚠ File not found: ${fileName}`);
          continue;
        }
        
        const fileStats = await plugins.fs.stat(filePath);
        const fileSizeKB = fileStats.size / 1024;
        
        // Attempt extraction
        const invoice = new EInvoice();
        const extractionResult = await invoice.fromFile(filePath);
        
        const fileExtractionTime = Date.now() - fileExtractionStart;
        totalExtractionTime += fileExtractionTime;
        
        if (extractionResult) {
          successfulExtractions++;
          
          tools.log(`✓ ${fileName}: Extracted (${fileSizeKB.toFixed(1)}KB, ${fileExtractionTime}ms)`);
          
          // Quick validation of extracted content
          try {
            const xmlContent = await invoice.toXmlString();
            if (xmlContent && xmlContent.length > 50) {
              tools.log(`  Content length: ${xmlContent.length} chars`);
            }
          } catch (contentError) {
            tools.log(`  ⚠ Content extraction error: ${contentError.message}`);
          }
          
        } else {
          extractionErrors++;
          tools.log(`⚠ ${fileName}: No XML content extracted`);
        }
        
      } catch (error) {
        extractionErrors++;
        const fileExtractionTime = Date.now() - fileExtractionStart;
        totalExtractionTime += fileExtractionTime;
        
        tools.log(`✗ ${fileName}: Extraction failed - ${error.message}`);
      }
    }
    
    // Calculate statistics
    const successRate = processedFiles > 0 ? (successfulExtractions / processedFiles) * 100 : 0;
    const averageExtractionTime = processedFiles > 0 ? totalExtractionTime / processedFiles : 0;
    
    tools.log(`\nZUGFeRD v1 Extraction Summary:`);
    tools.log(`- Files processed: ${processedFiles}`);
    tools.log(`- Successful extractions: ${successfulExtractions} (${successRate.toFixed(1)}%)`);
    tools.log(`- Extraction errors: ${extractionErrors}`);
    tools.log(`- Average extraction time: ${averageExtractionTime.toFixed(1)}ms`);
    
    // Performance expectations
    if (processedFiles > 0) {
      expect(averageExtractionTime).toBeLessThan(5000); // 5 seconds max per file
    }
    
    // We expect at least some extractions to work, but don't require 100% success
    // as some files might be corrupted or use unsupported PDF features
    if (processedFiles > 0) {
      expect(successRate).toBeGreaterThan(0); // At least one file should work
    }
    
  } catch (error) {
    tools.log(`ZUGFeRD v1 corpus processing failed: ${error.message}`);
    throw error;
  }
  
  const totalDuration = Date.now() - startTime;
  PerformanceTracker.recordMetric('pdf-zugferd-v1-corpus-extraction', totalDuration);
  
  tools.log(`ZUGFeRD v1 corpus processing completed in ${totalDuration}ms`);
});

tap.test('PDF-02: ZUGFeRD v1 Extraction - Format Validation', async (tools) => {
  const startTime = Date.now();
  
  try {
    const zugferdV1Files = await CorpusLoader.getFiles('ZUGFERD_V1');
    
    if (zugferdV1Files.length === 0) {
      tools.log('⚠ No ZUGFeRD v1 files found for format validation');
      return;
    }
    
    // Test with first available file for detailed format validation
    const testFile = zugferdV1Files[0];
    const fileName = plugins.path.basename(testFile);
    
    tools.log(`Testing ZUGFeRD v1 format validation with: ${fileName}`);
    
    const invoice = new EInvoice();
    
    try {
      const extractionResult = await invoice.fromFile(testFile);
      
      if (extractionResult) {
        const xmlContent = await invoice.toXmlString();
        
        // ZUGFeRD v1 specific format checks
        const formatChecks = {
          hasXmlDeclaration: xmlContent.startsWith('<?xml'),
          hasZugferdNamespace: xmlContent.includes('urn:ferd:CrossIndustryDocument:invoice:1p0') ||
                              xmlContent.includes('ZUGFeRD') ||
                              xmlContent.includes('FERD'),
          hasInvoiceElements: xmlContent.includes('<Invoice') || 
                             xmlContent.includes('<CrossIndustryDocument') ||
                             xmlContent.includes('<invoice'),
          isWellFormed: true // Assume true if we got this far
        };
        
        tools.log(`ZUGFeRD v1 Format Validation Results:`);
        tools.log(`- Has XML Declaration: ${formatChecks.hasXmlDeclaration}`);
        tools.log(`- Has ZUGFeRD Namespace: ${formatChecks.hasZugferdNamespace}`);
        tools.log(`- Has Invoice Elements: ${formatChecks.hasInvoiceElements}`);
        tools.log(`- Is Well-Formed: ${formatChecks.isWellFormed}`);
        
        // Basic format expectations
        expect(formatChecks.hasXmlDeclaration).toBeTrue();
        expect(formatChecks.isWellFormed).toBeTrue();
        
        if (formatChecks.hasZugferdNamespace && formatChecks.hasInvoiceElements) {
          tools.log('✓ ZUGFeRD v1 format validation passed');
        } else {
          tools.log('⚠ ZUGFeRD v1 format markers not fully detected');
        }
        
        // Test format detection if available
        if (typeof invoice.detectFormat === 'function') {
          try {
            const detectedFormat = await invoice.detectFormat(xmlContent);
            tools.log(`Detected format: ${detectedFormat}`);
            
            if (detectedFormat.toLowerCase().includes('zugferd') || 
                detectedFormat.toLowerCase().includes('cii')) {
              tools.log('✓ Format detection correctly identified ZUGFeRD/CII');
            }
          } catch (detectionError) {
            tools.log(`Format detection error: ${detectionError.message}`);
          }
        }
        
      } else {
        tools.log('⚠ No content extracted for format validation');
      }
      
    } catch (extractionError) {
      tools.log(`Format validation extraction failed: ${extractionError.message}`);
    }
    
  } catch (error) {
    tools.log(`ZUGFeRD v1 format validation failed: ${error.message}`);
  }
  
  const duration = Date.now() - startTime;
  PerformanceTracker.recordMetric('pdf-zugferd-v1-format-validation', duration);
});

tap.test('PDF-02: ZUGFeRD v1 Extraction - Error Handling', async (tools) => {
  const startTime = Date.now();
  
  // Test error handling with various problematic scenarios
  const errorTestCases = [
    {
      name: 'Non-existent file',
      filePath: '/non/existent/zugferd.pdf',
      expectedError: true
    },
    {
      name: 'Empty file path',
      filePath: '',
      expectedError: true
    }
  ];
  
  for (const testCase of errorTestCases) {
    tools.log(`Testing error handling: ${testCase.name}`);
    
    try {
      const invoice = new EInvoice();
      
      if (testCase.filePath) {
        const result = await invoice.fromFile(testCase.filePath);
        
        if (testCase.expectedError) {
          tools.log(`⚠ Expected error for ${testCase.name} but operation succeeded`);
        } else {
          tools.log(`✓ ${testCase.name}: Operation succeeded as expected`);
        }
      } else {
        // Test with empty/invalid path
        try {
          await invoice.fromFile(testCase.filePath);
          if (testCase.expectedError) {
            tools.log(`⚠ Expected error for ${testCase.name} but no error occurred`);
          }
        } catch (error) {
          if (testCase.expectedError) {
            tools.log(`✓ ${testCase.name}: Expected error caught - ${error.message}`);
          } else {
            throw error;
          }
        }
      }
      
    } catch (error) {
      if (testCase.expectedError) {
        tools.log(`✓ ${testCase.name}: Expected error caught - ${error.message}`);
        expect(error.message).toBeTruthy();
      } else {
        tools.log(`✗ ${testCase.name}: Unexpected error - ${error.message}`);
        throw error;
      }
    }
  }
  
  const duration = Date.now() - startTime;
  PerformanceTracker.recordMetric('pdf-zugferd-v1-error-handling', duration);
});

tap.test('PDF-02: Performance Summary', async (tools) => {
  const operations = [
    'pdf-zugferd-v1-basic-extraction',
    'pdf-zugferd-v1-corpus-extraction', 
    'pdf-zugferd-v1-format-validation',
    'pdf-zugferd-v1-error-handling'
  ];
  
  tools.log(`\n=== ZUGFeRD v1 Extraction Performance Summary ===`);
  
  for (const operation of operations) {
    const summary = await PerformanceTracker.getSummary(operation);
    if (summary) {
      tools.log(`${operation}:`);
      tools.log(`  avg=${summary.average}ms, min=${summary.min}ms, max=${summary.max}ms, p95=${summary.p95}ms`);
    }
  }
  
  tools.log(`\nZUGFeRD v1 extraction testing completed.`);
});