// This file is auto-generated by alef — DO NOT EDIT. // alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75 // To regenerate: alef generate // To verify freshness: alef verify --exit-code // Issues & docs: https://github.com/kreuzberg-dev/alef // ignore_for_file: unused_local_variable import 'package:test/test.dart'; import 'dart:io'; import 'package:kreuzberg/kreuzberg.dart'; import 'package:kreuzberg/src/kreuzberg_bridge_generated/frb_generated.dart' show RustLib; // E2e tests for category: smoke String _alefE2eText(Object? value) { if (value == null) return ''; // Check if it's an enum by examining its toString representation. final str = value.toString(); if (str.contains('.')) { // Enum.toString() returns 'EnumName.variantName'. Extract the variant name. final parts = str.split('.'); if (parts.length == 2) { final variantName = parts[1]; // Convert camelCase variant names to snake_case for serde compatibility. // E.g. 'toolCalls' -> 'tool_calls', 'stop' -> 'stop'. return _camelToSnake(variantName); } } return str; } String _camelToSnake(String camel) { final buffer = StringBuffer(); for (int i = 0; i < camel.length; i++) { final char = camel[i]; if (char.contains(RegExp(r'[A-Z]'))) { if (i > 0) buffer.write('_'); buffer.write(char.toLowerCase()); } else { buffer.write(char); } } return buffer.toString(); } void main() { setUpAll(() async { await RustLib.init(); final _testDocs = Platform.environment['FIXTURES_DIR'] ?? '../../test_documents'; final _dir = Directory(_testDocs); if (_dir.existsSync()) Directory.current = _dir; }); test('OCR: PNG image extraction with OCR enabled. In WASM this exercises the Uint8Array bridge parameter and Promise await in the generated OcrBackend bridge.', () async { final result = await KreuzbergBridge.extractBytes(File('images/test_hello_world.png').readAsBytesSync(), 'image/png'); expect(result.mimeType.toString().trim(), equals('image/png'.toString().trim())); expect(result.content.length, greaterThanOrEqualTo(1)); expect(result.content.contains('Hello') || result.content.contains('World') || result.content.contains('hello') || result.content.contains('world'), isTrue); }); test('Smoke test: DOCX with formatted text', () async { final result = await KreuzbergBridge.extractBytes(File('docx/fake.docx').readAsBytesSync(), 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'); expect(result.mimeType.toString().trim(), equals('application/vnd.openxmlformats-officedocument.wordprocessingml.document'.toString().trim())); expect(result.content.length, greaterThanOrEqualTo(20)); expect(result.content.contains('Lorem') || result.content.contains('ipsum') || result.content.contains('document') || result.content.contains('text'), isTrue); }); test('Smoke test: HTML table extraction', () async { final result = await KreuzbergBridge.extractBytes(File('html/simple_table.html').readAsBytesSync(), 'text/html'); expect(result.mimeType.toString().trim(), equals('text/html'.toString().trim())); expect(result.content.length, greaterThanOrEqualTo(10)); expect(result.content.contains('Sample Data Table') || result.content.contains('Laptop') || result.content.contains('Electronics') || result.content.contains('Product'), isTrue); }); test('Smoke test: PNG image (without OCR, metadata only)', () async { final result = await KreuzbergBridge.extractBytes(File('images/sample.png').readAsBytesSync(), 'image/png', ExtractionConfig(useCache: true, enableQualityProcessing: true, forceOcr: false, disableOcr: true, resultFormat: ResultFormat.unified, outputFormat: OutputFormat.plain(), includeDocumentStructure: false, useLayoutForMarkdown: false, maxArchiveDepth: 3)); expect(result.mimeType.toString().trim(), equals('image/png'.toString().trim())); }); test('Smoke test: JSON file extraction', () async { final result = await KreuzbergBridge.extractBytes(File('json/simple.json').readAsBytesSync(), 'application/json'); expect(result.mimeType.toString().trim(), equals('application/json'.toString().trim())); expect(result.content.length, greaterThanOrEqualTo(5)); }); test('Smoke test: PDF with simple text extraction', () async { final result = await KreuzbergBridge.extractBytes(File('pdf/fake_memo.pdf').readAsBytesSync(), 'application/pdf'); expect(result.mimeType.toString().trim(), equals('application/pdf'.toString().trim())); expect(result.content.length, greaterThanOrEqualTo(50)); expect(result.content.contains('May 5, 2023') || result.content.contains('To Whom it May Concern'), isTrue); }); test('Smoke test: Plain text file', () async { final result = await KreuzbergBridge.extractBytes(File('text/report.txt').readAsBytesSync(), 'text/plain'); expect(result.mimeType.toString().trim(), equals('text/plain'.toString().trim())); expect(result.content.length, greaterThanOrEqualTo(5)); }); test('Smoke test: XLSX with basic spreadsheet data including tables', () async { final result = await KreuzbergBridge.extractBytes(File('xlsx/stanley_cups.xlsx').readAsBytesSync(), 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'); expect(result.mimeType.toString().trim(), equals('application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'.toString().trim())); expect(result.content.length, greaterThanOrEqualTo(100)); expect(result.content, contains('Team')); expect(result.content, contains('Location')); expect(result.content, contains('Stanley Cups')); expect(result.content, contains('Blues')); expect(result.content, contains('Flyers')); expect(result.content, contains('Maple Leafs')); expect(result.content, contains('STL')); expect(result.content, contains('PHI')); expect(result.content, contains('TOR')); // skipped: field 'tables' not available on dart result type // skipped: field 'metadata.format.excel.sheet_count' not available on dart result type // skipped: field 'metadata.format.excel.sheet_names' not available on dart result type }); }