kreuzberg 4.1.2 → 4.2.1

data/vendor/kreuzberg/tests/contract_mcp.rs

@@ -0,0 +1,314 @@
+//! MCP contract tests - verify MCP config matches Rust core
+//!
+//! This test suite validates that MCP (Model Context Protocol) configuration
+//! produces identical JSON to the Rust core library when parsing configuration.
+//! This ensures that MCP users get the same configuration behavior as CLI and SDK users.
+
+use kreuzberg::core::config::ExtractionConfig;
+use kreuzberg::core::config::OutputFormat;
+use serde_json::json;
+
+#[test]
+fn test_mcp_basic_config_json_matches_rust_core() {
+    // Create config via Rust core
+    let rust_config = ExtractionConfig {
+        use_cache: true,
+        enable_quality_processing: true,
+        force_ocr: false,
+        output_format: OutputFormat::Plain,
+        result_format: kreuzberg::types::OutputFormat::Unified,
+        ..Default::default()
+    };
+    let rust_json = serde_json::to_value(&rust_config).expect("Failed to serialize rust config");
+
+    // Simulate MCP config parameter deserialization
+    let mcp_json = json!({
+        "use_cache": true,
+        "enable_quality_processing": true,
+        "force_ocr": false,
+        "output_format": "plain",
+        "result_format": "unified"
+    });
+    let mcp_config: ExtractionConfig =
+        serde_json::from_value(mcp_json.clone()).expect("Failed to deserialize MCP config");
+    let mcp_serialized = serde_json::to_value(&mcp_config).expect("Failed to serialize MCP config");
+
+    // Verify they produce identical JSON for the relevant fields
+    assert_eq!(
+        rust_json.get("use_cache"),
+        mcp_serialized.get("use_cache"),
+        "MCP use_cache must match Rust core"
+    );
+    assert_eq!(
+        rust_json.get("enable_quality_processing"),
+        mcp_serialized.get("enable_quality_processing"),
+        "MCP enable_quality_processing must match Rust core"
+    );
+    assert_eq!(
+        rust_json.get("force_ocr"),
+        mcp_serialized.get("force_ocr"),
+        "MCP force_ocr must match Rust core"
+    );
+    assert_eq!(
+        rust_json.get("output_format"),
+        mcp_serialized.get("output_format"),
+        "MCP output_format must match Rust core"
+    );
+}
+
+#[test]
+fn test_mcp_ocr_config_nested_matches_rust_core() {
+    let mcp_json = json!({
+        "ocr": {
+            "backend": "tesseract"
+        },
+        "force_ocr": true
+    });
+
+    let config: ExtractionConfig = serde_json::from_value(mcp_json).expect("Failed to deserialize OCR config");
+
+    // Verify OCR config deserialized correctly
+    assert!(config.ocr.is_some(), "OCR config should be present");
+    assert!(config.force_ocr, "force_ocr should be true");
+
+    if let Some(ocr) = &config.ocr {
+        assert_eq!(ocr.backend, "tesseract", "OCR backend should be tesseract");
+    }
+
+    // Verify roundtrip
+    let serialized = serde_json::to_value(&config).expect("Failed to serialize");
+    assert!(serialized.get("ocr").is_some(), "Serialized config should include ocr");
+}
+
+#[test]
+fn test_mcp_chunking_config_nested_matches_rust_core() {
+    let mcp_json = json!({
+        "chunking": {
+            "max_chars": 500,
+            "max_overlap": 50,
+            "strategy": "sliding_window"
+        }
+    });
+
+    let config: ExtractionConfig = serde_json::from_value(mcp_json).expect("Failed to deserialize chunking config");
+
+    // Verify chunking config deserialized correctly
+    assert!(config.chunking.is_some(), "Chunking config should be present");
+
+    if let Some(chunking) = &config.chunking {
+        assert_eq!(chunking.max_chars, 500, "max_chars should be 500");
+        assert_eq!(chunking.max_overlap, 50, "max_overlap should be 50");
+    }
+
+    // Verify roundtrip
+    let serialized = serde_json::to_value(&config).expect("Failed to serialize");
+    assert!(
+        serialized.get("chunking").is_some(),
+        "Serialized config should include chunking"
+    );
+}
+
+#[test]
+fn test_mcp_full_config_preserves_all_fields() {
+    let full_config_json = json!({
+        "use_cache": false,
+        "enable_quality_processing": true,
+        "force_ocr": true,
+        "output_format": "markdown",
+        "result_format": "unified",
+        "max_concurrent_extractions": 8,
+        "ocr": {
+            "backend": "tesseract"
+        },
+        "chunking": {
+            "max_chars": 1000,
+            "max_overlap": 200
+        }
+    });
+
+    let config: ExtractionConfig =
+        serde_json::from_value(full_config_json.clone()).expect("Failed to deserialize full config");
+    let roundtrip_json = serde_json::to_value(&config).expect("Failed to serialize");
+
+    // Verify all top-level fields preserved
+    assert!(!config.use_cache, "use_cache should be false");
+    assert!(
+        config.enable_quality_processing,
+        "enable_quality_processing should be true"
+    );
+    assert!(config.force_ocr, "force_ocr should be true");
+    assert_eq!(
+        config.max_concurrent_extractions,
+        Some(8),
+        "max_concurrent_extractions should be 8"
+    );
+
+    // Verify nested fields preserved
+    assert!(config.ocr.is_some(), "OCR config should be present");
+    assert!(config.chunking.is_some(), "Chunking config should be present");
+
+    // Verify roundtrip integrity
+    assert_eq!(
+        roundtrip_json.get("use_cache"),
+        full_config_json.get("use_cache"),
+        "use_cache should survive roundtrip"
+    );
+    assert_eq!(
+        roundtrip_json.get("force_ocr"),
+        full_config_json.get("force_ocr"),
+        "force_ocr should survive roundtrip"
+    );
+    assert_eq!(
+        roundtrip_json.get("max_concurrent_extractions"),
+        full_config_json.get("max_concurrent_extractions"),
+        "max_concurrent_extractions should survive roundtrip"
+    );
+}
+
+#[test]
+fn test_mcp_default_config_matches_rust_core_defaults() {
+    // Create Rust core default
+    let rust_default = ExtractionConfig::default();
+    let rust_json = serde_json::to_value(&rust_default).expect("Failed to serialize default");
+
+    // Create empty JSON (simulates MCP with no overrides)
+    let mcp_json = json!({});
+    let mcp_config: ExtractionConfig = serde_json::from_value(mcp_json).expect("Failed to deserialize empty config");
+    let mcp_json_serialized = serde_json::to_value(&mcp_config).expect("Failed to serialize MCP default");
+
+    // Verify defaults match
+    assert_eq!(
+        mcp_json_serialized.get("use_cache"),
+        rust_json.get("use_cache"),
+        "use_cache default should match"
+    );
+    assert_eq!(
+        mcp_json_serialized.get("enable_quality_processing"),
+        rust_json.get("enable_quality_processing"),
+        "enable_quality_processing default should match"
+    );
+    assert_eq!(
+        mcp_json_serialized.get("force_ocr"),
+        rust_json.get("force_ocr"),
+        "force_ocr default should match"
+    );
+    assert_eq!(
+        mcp_json_serialized.get("result_format"),
+        rust_json.get("result_format"),
+        "result_format default should match"
+    );
+    assert_eq!(
+        mcp_json_serialized.get("output_format"),
+        rust_json.get("output_format"),
+        "output_format default should match"
+    );
+}
+
+#[test]
+fn test_mcp_output_format_values_are_valid() {
+    // Test all valid output format values (lowercase, as per serde rename_all)
+    let valid_formats = vec!["plain", "markdown", "html"];
+
+    for format in valid_formats {
+        let mcp_json = json!({
+            "output_format": format
+        });
+
+        let result = serde_json::from_value::<ExtractionConfig>(mcp_json);
+        assert!(result.is_ok(), "Format '{}' should deserialize successfully", format);
+
+        let config = result.unwrap();
+        assert!(
+            !config.output_format.to_string().is_empty(),
+            "Deserialized format should have valid string representation"
+        );
+    }
+}
+
+#[test]
+fn test_mcp_result_format_values_are_valid() {
+    // Test valid result format values (lowercase, as per serde rename_all)
+    let valid_formats = vec!["unified", "element_based"];
+
+    for format in valid_formats {
+        let mcp_json = json!({
+            "result_format": format
+        });
+
+        let result = serde_json::from_value::<ExtractionConfig>(mcp_json);
+        assert!(
+            result.is_ok(),
+            "Result format '{}' should deserialize successfully",
+            format
+        );
+    }
+}
+
+#[test]
+fn test_mcp_partial_override_preserves_defaults() {
+    // Create a partial config that overrides only one field
+    let partial_json = json!({
+        "force_ocr": true
+    });
+
+    let config: ExtractionConfig = serde_json::from_value(partial_json).expect("Failed to deserialize partial config");
+
+    // Verify override applied
+    assert!(config.force_ocr, "force_ocr override should be applied");
+
+    // Verify defaults preserved for other fields
+    assert!(config.use_cache, "use_cache should retain default when not overridden");
+    assert!(
+        config.enable_quality_processing,
+        "enable_quality_processing should retain default when not overridden"
+    );
+}
+
+#[test]
+fn test_mcp_error_handling_for_invalid_json() {
+    // Test that invalid format values produce errors (or are handled gracefully)
+    let invalid_json = json!({
+        "output_format": "InvalidFormat"
+    });
+
+    let result = serde_json::from_value::<ExtractionConfig>(invalid_json);
+    // The deserialization should either fail or parse to a valid state
+    // depending on how OutputFormat handles unknown values
+    if let Ok(config) = result {
+        let _ = config.output_format.to_string();
+    }
+}
+
+#[test]
+fn test_mcp_concurrent_extractions_override() {
+    let mcp_json = json!({
+        "max_concurrent_extractions": 16
+    });
+
+    let config: ExtractionConfig =
+        serde_json::from_value(mcp_json).expect("Failed to deserialize config with concurrent extractions");
+
+    assert_eq!(
+        config.max_concurrent_extractions,
+        Some(16),
+        "max_concurrent_extractions should be overridden to 16"
+    );
+}
+
+#[test]
+fn test_mcp_config_json_keys_case_sensitive() {
+    // Verify that config JSON keys are case-sensitive
+    let lowercase_json = json!({
+        "use_cache": true,
+        "force_ocr": false
+    });
+
+    let config: ExtractionConfig =
+        serde_json::from_value(lowercase_json).expect("Failed to deserialize lowercase config");
+
+    assert!(config.use_cache, "use_cache should be true");
+    assert!(!config.force_ocr, "force_ocr should be false");
+
+    // Note: serde by default fails on unknown fields, so camelCase would fail
+    // This test documents the expected behavior
+}

data/vendor/kreuzberg/tests/core_integration.rs

@@ -26,16 +26,16 @@ fn assert_text_content(actual: &str, expected: &str) {
 /// Test basic file extraction with MIME detection.
 #[tokio::test]
 async fn test_extract_file_basic() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let file_path = dir.path().join("test.txt");
-    let mut file = File::create(&file_path).unwrap();
-    file.write_all(b"Hello, Kreuzberg!").unwrap();
+    let mut file = File::create(&file_path).expect("Operation failed");
+    file.write_all(b"Hello, Kreuzberg!").expect("Operation failed");
 
     let config = ExtractionConfig::default();
     let result = extract_file(&file_path, None, &config).await;
 
     assert!(result.is_ok(), "Basic file extraction should succeed");
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
 
     assert_text_content(&result.content, "Hello, Kreuzberg!");
     assert_eq!(result.mime_type, "text/plain");
@@ -47,16 +47,16 @@ async fn test_extract_file_basic() {
 /// Test extraction with explicit MIME type override.
 #[tokio::test]
 async fn test_extract_file_with_mime_override() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let file_path = dir.path().join("data.bin");
-    let mut file = File::create(&file_path).unwrap();
-    file.write_all(b"Binary content").unwrap();
+    let mut file = File::create(&file_path).expect("Operation failed");
+    file.write_all(b"Binary content").expect("Operation failed");
 
     let config = ExtractionConfig::default();
     let result = extract_file(&file_path, Some("text/plain"), &config).await;
 
     assert!(result.is_ok(), "MIME override should work");
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
 
     assert_eq!(result.mime_type, "text/plain");
     assert!(!result.content.is_empty(), "Should extract content");
@@ -66,7 +66,7 @@ async fn test_extract_file_with_mime_override() {
 /// Test extraction of multiple file types.
 #[tokio::test]
 async fn test_extract_multiple_file_types() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let config = ExtractionConfig::default();
 
     let test_files: Vec<(&str, &[u8], &str)> = vec![
@@ -80,9 +80,11 @@ async fn test_extract_multiple_file_types() {
 
     for (filename, content, expected_mime) in test_files {
         let file_path = dir.path().join(filename);
-        fs::write(&file_path, content).unwrap();
+        fs::write(&file_path, content).expect("Operation failed");
 
-        let result = extract_file(&file_path, None, &config).await.unwrap();
+        let result = extract_file(&file_path, None, &config)
+            .await
+            .expect("Async operation failed");
 
         assert_eq!(result.mime_type, expected_mime, "MIME type mismatch for {}", filename);
         assert!(
@@ -115,7 +117,7 @@ async fn test_extract_bytes_various_mime_types() {
         let result = extract_bytes(content, mime_type, &config).await;
         assert!(result.is_ok(), "Extract bytes failed for MIME type: {}", mime_type);
 
-        let result = result.unwrap();
+        let result = result.expect("Operation failed");
 
         assert_eq!(result.mime_type, mime_type, "MIME type mismatch");
         assert!(
@@ -131,7 +133,7 @@ async fn test_extract_bytes_various_mime_types() {
 /// Test batch extraction with concurrent processing.
 #[tokio::test]
 async fn test_batch_extract_file_concurrency() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let config = ExtractionConfig::default();
 
     let num_files = 10;
@@ -139,14 +141,14 @@ async fn test_batch_extract_file_concurrency() {
 
     for i in 0..num_files {
         let file_path = dir.path().join(format!("test_{}.txt", i));
-        fs::write(&file_path, format!("Content {}", i)).unwrap();
+        fs::write(&file_path, format!("Content {}", i)).expect("Operation failed");
         paths.push(file_path);
     }
 
     let results = batch_extract_file(paths.clone(), &config).await;
     assert!(results.is_ok());
 
-    let results = results.unwrap();
+    let results = results.expect("Operation failed");
     assert_eq!(results.len(), num_files);
 
     for (i, result) in results.iter().enumerate() {
@@ -169,7 +171,7 @@ async fn test_batch_extract_empty() {
 
     let results = batch_extract_file(paths, &config).await;
     assert!(results.is_ok());
-    assert_eq!(results.unwrap().len(), 0);
+    assert_eq!(results.expect("Operation failed").len(), 0);
 }
 
 /// Test batch_extract_bytes with concurrent processing.
@@ -193,7 +195,7 @@ async fn test_batch_extract_bytes_concurrency() {
     let results = batch_extract_bytes(owned_contents, &config).await;
     assert!(results.is_ok());
 
-    let results = results.unwrap();
+    let results = results.expect("Operation failed");
     assert_eq!(results.len(), 5);
 
     for (i, result) in results.iter().enumerate() {
@@ -214,28 +216,28 @@ async fn test_batch_extract_bytes_concurrency() {
 /// Test sync wrappers for extraction functions.
 #[test]
 fn test_sync_wrappers() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let file_path = dir.path().join("sync_test.txt");
-    fs::write(&file_path, "sync content").unwrap();
+    fs::write(&file_path, "sync content").expect("Operation failed");
 
     let config = ExtractionConfig::default();
 
     let result = extract_file_sync(&file_path, None, &config);
     assert!(result.is_ok(), "Sync file extraction should succeed");
-    let extraction = result.unwrap();
+    let extraction = result.expect("Operation failed");
     assert_text_content(&extraction.content, "sync content");
     assert!(extraction.chunks.is_none(), "Chunks should be None");
 
     let result = extract_bytes_sync(b"test bytes", "text/plain", &config);
     assert!(result.is_ok(), "Sync bytes extraction should succeed");
-    let extraction = result.unwrap();
+    let extraction = result.expect("Operation failed");
     assert_text_content(&extraction.content, "test bytes");
     assert!(extraction.chunks.is_none(), "Chunks should be None");
 
     let paths = vec![file_path];
     let results = batch_extract_file_sync(paths, &config);
     assert!(results.is_ok(), "Batch sync file should succeed");
-    let results = results.unwrap();
+    let results = results.expect("Operation failed");
     assert_eq!(results.len(), 1);
     assert_text_content(&results[0].content, "sync content");
     assert!(results[0].chunks.is_none(), "Chunks should be None");
@@ -247,7 +249,7 @@ fn test_sync_wrappers() {
         .collect();
     let results = batch_extract_bytes_sync(owned_contents, &config);
     assert!(results.is_ok(), "Batch bytes sync should succeed");
-    let results = results.unwrap();
+    let results = results.expect("Operation failed");
     assert_eq!(results.len(), 1);
     assert_text_content(&results[0].content, "test");
     assert!(results[0].chunks.is_none(), "Chunks should be None");
@@ -256,7 +258,7 @@ fn test_sync_wrappers() {
 /// Test MIME type detection for various extensions.
 #[test]
 fn test_mime_detection_comprehensive() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
 
     let test_cases = vec![
         ("test.txt", "text/plain"),
@@ -287,9 +289,9 @@ fn test_mime_detection_comprehensive() {
 
     for (filename, expected_mime) in test_cases {
         let file_path = dir.path().join(filename);
-        File::create(&file_path).unwrap();
+        File::create(&file_path).expect("Operation failed");
 
-        let detected = detect_mime_type(&file_path, true).unwrap();
+        let detected = detect_mime_type(&file_path, true).expect("Operation failed");
         assert_eq!(detected, expected_mime, "Failed for {}", filename);
 
         let validated = validate_mime_type(&detected);
@@ -312,7 +314,7 @@ fn test_mime_validation() {
 /// Test case-insensitive extension handling.
 #[test]
 fn test_case_insensitive_extensions() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
 
     let test_cases = vec![
         ("test.PDF", "application/pdf"),
@@ -326,9 +328,9 @@ fn test_case_insensitive_extensions() {
 
     for (filename, expected_mime) in test_cases {
         let file_path = dir.path().join(filename);
-        File::create(&file_path).unwrap();
+        File::create(&file_path).expect("Operation failed");
 
-        let detected = detect_mime_type(&file_path, true).unwrap();
+        let detected = detect_mime_type(&file_path, true).expect("Operation failed");
         assert_eq!(detected, expected_mime, "Failed for {}", filename);
     }
 }
@@ -336,7 +338,7 @@ fn test_case_insensitive_extensions() {
 /// Test config loading from TOML file.
 #[test]
 fn test_config_loading() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let config_path = dir.path().join("kreuzberg.toml");
 
     fs::write(
@@ -355,19 +357,19 @@ max_chars = 2000
 max_overlap = 300
     "#,
     )
-    .unwrap();
+    .expect("Operation failed");
 
-    let config = ExtractionConfig::from_toml_file(&config_path).unwrap();
+    let config = ExtractionConfig::from_toml_file(&config_path).expect("Operation failed");
 
     assert!(!config.use_cache);
     assert!(config.enable_quality_processing);
     assert!(!config.force_ocr);
 
-    let ocr_config = config.ocr.unwrap();
+    let ocr_config = config.ocr.expect("Operation failed");
     assert_eq!(ocr_config.backend, "tesseract");
     assert_eq!(ocr_config.language, "deu");
 
-    let chunking_config = config.chunking.unwrap();
+    let chunking_config = config.chunking.expect("Operation failed");
     assert_eq!(chunking_config.max_chars, 2000);
     assert_eq!(chunking_config.max_overlap, 300);
 }
@@ -375,9 +377,9 @@ max_overlap = 300
 /// Test config discovery in parent directories.
 #[test]
 fn test_config_discovery() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let subdir = dir.path().join("subdir");
-    fs::create_dir(&subdir).unwrap();
+    fs::create_dir(&subdir).expect("Operation failed");
 
     let config_path = dir.path().join("kreuzberg.toml");
     fs::write(
@@ -387,16 +389,16 @@ use_cache = false
 enable_quality_processing = true
     "#,
     )
-    .unwrap();
+    .expect("Operation failed");
 
-    let original_dir = std::env::current_dir().unwrap();
-    std::env::set_current_dir(&subdir).unwrap();
+    let original_dir = std::env::current_dir().expect("Operation failed");
+    std::env::set_current_dir(&subdir).expect("Operation failed");
 
-    let config = ExtractionConfig::discover().unwrap();
+    let config = ExtractionConfig::discover().expect("Operation failed");
     assert!(config.is_some());
-    assert!(!config.unwrap().use_cache);
+    assert!(!config.expect("Operation failed").use_cache);
 
-    std::env::set_current_dir(original_dir).unwrap();
+    std::env::set_current_dir(original_dir).expect("Operation failed");
 }
 
 /// Test error handling for nonexistent files.
@@ -406,10 +408,8 @@ async fn test_nonexistent_file_error() {
     let result = extract_file("/nonexistent/file.txt", None, &config).await;
 
     assert!(result.is_err());
-    assert!(matches!(
-        result.unwrap_err(),
-        kreuzberg::KreuzbergError::Validation { .. }
-    ));
+    // File validation returns Io error for missing files (NotFound)
+    assert!(matches!(result.unwrap_err(), kreuzberg::KreuzbergError::Io(_)));
 }
 
 /// Test error handling for unsupported MIME types.
@@ -428,9 +428,9 @@ async fn test_unsupported_mime_type_error() {
 /// Test pipeline execution (currently stub, will be expanded in Phase 2).
 #[tokio::test]
 async fn test_pipeline_execution() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let file_path = dir.path().join("pipeline_test.txt");
-    fs::write(&file_path, "pipeline content").unwrap();
+    fs::write(&file_path, "pipeline content").expect("Operation failed");
 
     let config = ExtractionConfig {
         enable_quality_processing: true,
@@ -440,7 +440,7 @@ async fn test_pipeline_execution() {
     let result = extract_file(&file_path, None, &config).await;
     assert!(result.is_ok(), "Pipeline execution should succeed");
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert_text_content(&result.content, "pipeline content");
     assert_eq!(result.mime_type, "text/plain");
     assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
@@ -450,9 +450,9 @@ async fn test_pipeline_execution() {
 /// Test extraction with OCR config (placeholder test for Phase 2).
 #[tokio::test]
 async fn test_extraction_with_ocr_config() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let file_path = dir.path().join("ocr_test.txt");
-    fs::write(&file_path, "ocr content").unwrap();
+    fs::write(&file_path, "ocr content").expect("Operation failed");
 
     let config = ExtractionConfig {
         ocr: Some(kreuzberg::OcrConfig {
@@ -473,11 +473,11 @@ async fn test_extraction_with_ocr_config() {
 #[cfg(feature = "chunking")]
 #[tokio::test]
 async fn test_extraction_with_chunking_config() {
-    let dir = tempdir().unwrap();
+    let dir = tempdir().expect("Operation failed");
     let file_path = dir.path().join("chunking_test.txt");
 
     let long_content = "content for chunking. ".repeat(100);
-    fs::write(&file_path, &long_content).unwrap();
+    fs::write(&file_path, &long_content).expect("Operation failed");
 
     let config = ExtractionConfig {
         chunking: Some(kreuzberg::ChunkingConfig {
@@ -492,21 +492,21 @@ async fn test_extraction_with_chunking_config() {
     let result = extract_file(&file_path, None, &config).await;
     assert!(result.is_ok(), "Extraction with chunking should succeed");
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
 
     assert!(
         result.chunks.is_some(),
         "Chunks should be populated when chunking enabled"
     );
 
-    let chunks = result.chunks.unwrap();
+    let chunks = result.chunks.expect("Operation failed");
     assert!(chunks.len() > 1, "Should have multiple chunks for long content");
 
     assert!(result.metadata.additional.contains_key("chunk_count"));
-    let chunk_count = result.metadata.additional.get("chunk_count").unwrap();
+    let chunk_count = result.metadata.additional.get("chunk_count").expect("Value not found");
     assert_eq!(
         chunks.len(),
-        chunk_count.as_u64().unwrap() as usize,
+        chunk_count.as_u64().expect("Operation failed") as usize,
         "chunk_count should match chunks length"
     );