Nomad changes

e2e/swift_e2e/Tests/KreuzbergE2ETests/FormatSpecificTests.swift

@@ -0,0 +1,62 @@
+// 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
+// swift-format-ignore-file
+
+import XCTest
+import Foundation
+#if canImport(FoundationNetworking)
+import FoundationNetworking
+#endif
+import Kreuzberg
+import RustBridge
+
+/// E2e tests for category: format_specific.
+final class FormatSpecificTests: XCTestCase {
+    override class func setUp() {
+        super.setUp()
+        let _testDocs = URL(fileURLWithPath: #filePath)
+            .deletingLastPathComponent() // <Module>Tests/
+            .deletingLastPathComponent() // Tests/
+            .deletingLastPathComponent() // swift/
+            .deletingLastPathComponent() // packages/
+            .deletingLastPathComponent() // <repo root>
+            .appendingPathComponent("test_documents")
+        if FileManager.default.fileExists(atPath: _testDocs.path) {
+            FileManager.default.changeCurrentDirectoryPath(_testDocs.path)
+        }
+    }
+
+    func testFormatDocxStandalone() throws {
+        // Standalone DOCX extraction using extract_bytes_sync
+        let result = try Kreuzberg.extractBytesSync("docx/fake.docx", "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "{}")
+        XCTAssertGreaterThanOrEqual(result.content.count, 20)
+    }
+
+    func testFormatHwpxStandalone() throws {
+        // Standalone HWPX extraction using extract_bytes_sync
+        let result = try Kreuzberg.extractBytesSync("hwpx/simple.hwpx", "application/haansofthwpx", "{}")
+        XCTAssertGreaterThanOrEqual(result.content.count, 20)
+        XCTAssertTrue("Hello from HWPX".isEmpty || result.content.contains("Hello from HWPX"), "expected to contain: \("Hello from HWPX")")
+    }
+
+    func testFormatPdfText() throws {
+        // Standalone PDF text extraction using extract_bytes_sync
+        let result = try Kreuzberg.extractBytesSync("pdf/fake_memo.pdf", "application/pdf", "{}")
+        XCTAssertGreaterThanOrEqual(result.content.count, 50)
+        XCTAssertTrue(result.content.contains("Mallori") || result.content.contains("May"), "expected to contain at least one of the specified values")
+    }
+
+    func testFormatPptx() throws {
+        // PPTX presentation extraction using extract_file_sync
+        let result = try Kreuzberg.extractFileSync("pptx/simple.pptx", "application/vnd.openxmlformats-officedocument.presentationml.presentation", "{}")
+    }
+
+    func testFormatXlsx() throws {
+        // XLSX spreadsheet extraction using extract_file_sync
+        let result = try Kreuzberg.extractFileSync("xlsx/stanley_cups.xlsx", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", "{}")
+    }
+
+}